1945 files changed, 46670 insertions, 23153 deletions

diff --git a/CREDITS b/CREDITS
index 090ed4b004a5..9add7e6a4fa0 100644
--- a/CREDITS
+++ b/CREDITS
@@ -710,6 +710,10 @@ S: Las Cuevas 2385 - Bo Guemes
 S: Las Heras, Mendoza CP 5539
 S: Argentina
 
+N: Jay Cliburn
+E: jcliburn@gmail.com
+D: ATLX Ethernet drivers
+
 N: Steven P. Cole
 E: scole@lanl.gov
 E: elenstev@mesatop.com
@@ -1284,6 +1288,10 @@ D: Major kbuild rework during the 2.5 cycle
 D: ISDN Maintainer
 S: USA
 
+N: Gerrit Renker
+E: gerrit@erg.abdn.ac.uk
+D: DCCP protocol support.
+
 N: Philip Gladstone
 E: philip@gladstonefamily.net
 D: Kernel / timekeeping stuff
@@ -2138,6 +2146,10 @@ E: seasons@falcon.sch.bme.hu
 E: seasons@makosteszta.sote.hu
 D: Original author of software suspend
 
+N: Alexey Kuznetsov
+E: kuznet@ms2.inr.ac.ru
+D: Author and maintainer of large parts of the networking stack
+
 N: Jaroslav Kysela
 E: perex@perex.cz
 W: https://www.perex.cz
@@ -2696,6 +2708,10 @@ N: Wolfgang Muees
 E: wolfgang@iksw-muees.de
 D: Auerswald USB driver
 
+N: Shrijeet Mukherjee
+E: shrijeet@gmail.com
+D: Network routing domains (VRF).
+
 N: Paul Mundt
 E: paul.mundt@gmail.com
 D: SuperH maintainer
@@ -4110,6 +4126,10 @@ S: B-1206 Jingmao Guojigongyu
 S: 16 Baliqiao Nanjie, Beijing 101100
 S: People's Repulic of China
 
+N: Aviad Yehezkel
+E: aviadye@nvidia.com
+D: Kernel TLS implementation and offload support.
+
 N: Victor Yodaiken
 E: yodaiken@fsmlabs.com
 D: RTLinux (RealTime Linux)
@@ -4167,6 +4187,10 @@ S: 1507 145th Place SE #B5
 S: Bellevue, Washington 98007
 S: USA
 
+N: Wensong Zhang
+E: wensong@linux-vs.org
+D: IP virtual server (IPVS).
+
 N: Haojian Zhuang
 E: haojian.zhuang@gmail.com
 D: MMP support
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 1a04ca8162ad..0eee30b27ab6 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -264,7 +264,8 @@ Description:	Discover CPUs in the same CPU frequency coordination domain
 		attribute is useful for user space DVFS controllers to get better
 		power/performance results for platforms using acpi-cpufreq.
 
-		This file is only present if the acpi-cpufreq driver is in use.
+		This file is only present if the acpi-cpufreq or the cppc-cpufreq
+		drivers are in use.
 
 
 What:		/sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1}
diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst
index 83ae3b79a643..a648b423ba0e 100644
--- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst
+++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst
@@ -473,7 +473,7 @@ read-side critical sections that follow the idle period (the oval near
 the bottom of the diagram above).
 
 Plumbing this into the full grace-period execution is described
-`below <#Forcing%20Quiescent%20States>`__.
+`below <Forcing Quiescent States_>`__.
 
 CPU-Hotplug Interface
 ^^^^^^^^^^^^^^^^^^^^^
@@ -494,7 +494,7 @@ mask to detect CPUs having gone offline since the beginning of this
 grace period.
 
 Plumbing this into the full grace-period execution is described
-`below <#Forcing%20Quiescent%20States>`__.
+`below <Forcing Quiescent States_>`__.
 
 Forcing Quiescent States
 ^^^^^^^^^^^^^^^^^^^^^^^^
@@ -532,7 +532,7 @@ from other CPUs.
 | RCU. But this diagram is complex enough as it is, so simplicity       |
 | overrode accuracy. You can think of it as poetic license, or you can  |
 | think of it as misdirection that is resolved in the                   |
-| `stitched-together diagram <#Putting%20It%20All%20Together>`__.       |
+| `stitched-together diagram <Putting It All Together_>`__.             |
 +-----------------------------------------------------------------------+
 
 Grace-Period Cleanup
@@ -596,7 +596,7 @@ maintain ordering. For example, if the callback function wakes up a task
 that runs on some other CPU, proper ordering must in place in both the
 callback function and the task being awakened. To see why this is
 important, consider the top half of the `grace-period
-cleanup <#Grace-Period%20Cleanup>`__ diagram. The callback might be
+cleanup`_ diagram. The callback might be
 running on a CPU corresponding to the leftmost leaf ``rcu_node``
 structure, and awaken a task that is to run on a CPU corresponding to
 the rightmost leaf ``rcu_node`` structure, and the grace-period kernel
diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst
index e8c84fcc0507..d4c9a016074b 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.rst
+++ b/Documentation/RCU/Design/Requirements/Requirements.rst
@@ -45,7 +45,7 @@ requirements:
 #. `Other RCU Flavors`_
 #. `Possible Future Changes`_
 
-This is followed by a `summary <#Summary>`__, however, the answers to
+This is followed by a summary_, however, the answers to
 each quick quiz immediately follows the quiz. Select the big white space
 with your mouse to see the answer.
 
@@ -1096,7 +1096,7 @@ memory barriers.
 | case, voluntary context switch) within an RCU read-side critical      |
 | section. However, sleeping locks may be used within userspace RCU     |
 | read-side critical sections, and also within Linux-kernel sleepable   |
-| RCU `(SRCU) <#Sleepable%20RCU>`__ read-side critical sections. In     |
+| RCU `(SRCU) <Sleepable RCU_>`__ read-side critical sections. In       |
 | addition, the -rt patchset turns spinlocks into a sleeping locks so   |
 | that the corresponding critical sections can be preempted, which also |
 | means that these sleeplockified spinlocks (but not other sleeping     |
@@ -1186,7 +1186,7 @@ non-preemptible (``CONFIG_PREEMPT=n``) kernels, and thus `tiny
 RCU <https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com>`__
 was born. Josh Triplett has since taken over the small-memory banner
 with his `Linux kernel tinification <https://tiny.wiki.kernel.org/>`__
-project, which resulted in `SRCU <#Sleepable%20RCU>`__ becoming optional
+project, which resulted in `SRCU <Sleepable RCU_>`__ becoming optional
 for those kernels not needing it.
 
 The remaining performance requirements are, for the most part,
@@ -1457,8 +1457,8 @@ will vary as the value of ``HZ`` varies, and can also be changed using
 the relevant Kconfig options and kernel boot parameters. RCU currently
 does not do much sanity checking of these parameters, so please use
 caution when changing them. Note that these forward-progress measures
-are provided only for RCU, not for `SRCU <#Sleepable%20RCU>`__ or `Tasks
-RCU <#Tasks%20RCU>`__.
+are provided only for RCU, not for `SRCU <Sleepable RCU_>`__ or `Tasks
+RCU`_.
 
 RCU takes the following steps in ``call_rcu()`` to encourage timely
 invocation of callbacks when any given non-\ ``rcu_nocbs`` CPU has
@@ -1477,8 +1477,8 @@ encouragement was provided:
 
 Again, these are default values when running at ``HZ=1000``, and can be
 overridden. Again, these forward-progress measures are provided only for
-RCU, not for `SRCU <#Sleepable%20RCU>`__ or `Tasks
-RCU <#Tasks%20RCU>`__. Even for RCU, callback-invocation forward
+RCU, not for `SRCU <Sleepable RCU_>`__ or `Tasks
+RCU`_. Even for RCU, callback-invocation forward
 progress for ``rcu_nocbs`` CPUs is much less well-developed, in part
 because workloads benefiting from ``rcu_nocbs`` CPUs tend to invoke
 ``call_rcu()`` relatively infrequently. If workloads emerge that need
@@ -1920,7 +1920,7 @@ Hotplug CPU
 
 The Linux kernel supports CPU hotplug, which means that CPUs can come
 and go. It is of course illegal to use any RCU API member from an
-offline CPU, with the exception of `SRCU <#Sleepable%20RCU>`__ read-side
+offline CPU, with the exception of `SRCU <Sleepable RCU_>`__ read-side
 critical sections. This requirement was present from day one in
 DYNIX/ptx, but on the other hand, the Linux kernel's CPU-hotplug
 implementation is “interesting.”
@@ -2177,7 +2177,7 @@ handles these states differently:
 However, RCU must be reliably informed as to whether any given CPU is
 currently in the idle loop, and, for ``NO_HZ_FULL``, also whether that
 CPU is executing in usermode, as discussed
-`earlier <#Energy%20Efficiency>`__. It also requires that the
+`earlier <Energy Efficiency_>`__. It also requires that the
 scheduling-clock interrupt be enabled when RCU needs it to be:
 
 #. If a CPU is either idle or executing in usermode, and RCU believes it
@@ -2294,7 +2294,7 @@ Performance, Scalability, Response Time, and Reliability
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Expanding on the `earlier
-discussion <#Performance%20and%20Scalability>`__, RCU is used heavily by
+discussion <Performance and Scalability_>`__, RCU is used heavily by
 hot code paths in performance-critical portions of the Linux kernel's
 networking, security, virtualization, and scheduling code paths. RCU
 must therefore use efficient implementations, especially in its
diff --git a/Documentation/admin-guide/binfmt-misc.rst b/Documentation/admin-guide/binfmt-misc.rst
index 7a864131e5ea..59cd902e3549 100644
--- a/Documentation/admin-guide/binfmt-misc.rst
+++ b/Documentation/admin-guide/binfmt-misc.rst
@@ -23,7 +23,7 @@ Here is what the fields mean:
 
 - ``name``
    is an identifier string. A new /proc file will be created with this
-   ``name below /proc/sys/fs/binfmt_misc``; cannot contain slashes ``/`` for
+   name below ``/proc/sys/fs/binfmt_misc``; cannot contain slashes ``/`` for
    obvious reasons.
 - ``type``
    is the type of recognition. Give ``M`` for magic and ``E`` for extension.
@@ -83,7 +83,7 @@ Here is what the fields mean:
       ``F`` - fix binary
             The usual behaviour of binfmt_misc is to spawn the
 	    binary lazily when the misc format file is invoked.  However,
-	    this doesn``t work very well in the face of mount namespaces and
+	    this doesn't work very well in the face of mount namespaces and
 	    changeroots, so the ``F`` mode opens the binary as soon as the
 	    emulation is installed and uses the opened image to spawn the
 	    emulator, meaning it is always available once installed,
diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst
index 9b90efcc3a35..452b7dcd7f6b 100644
--- a/Documentation/admin-guide/bootconfig.rst
+++ b/Documentation/admin-guide/bootconfig.rst
@@ -154,7 +154,7 @@ get the boot configuration data.
 Because of this "piggyback" method, there is no need to change or
 update the boot loader and the kernel image itself as long as the boot
 loader passes the correct initrd file size. If by any chance, the boot
-loader passes a longer size, the kernel feils to find the bootconfig data.
+loader passes a longer size, the kernel fails to find the bootconfig data.
 
 To do this operation, Linux kernel provides "bootconfig" command under
 tools/bootconfig, which allows admin to apply or delete the config file
diff --git a/Documentation/admin-guide/device-mapper/verity.rst b/Documentation/admin-guide/device-mapper/verity.rst
index 8c50e5c96ee1..1a6b91368e59 100644
--- a/Documentation/admin-guide/device-mapper/verity.rst
+++ b/Documentation/admin-guide/device-mapper/verity.rst
@@ -134,7 +134,12 @@ root_hash_sig_key_desc <key_description>
     the pkcs7 signature of the roothash. The pkcs7 signature is used to validate
     the root hash during the creation of the device mapper block device.
     Verification of roothash depends on the config DM_VERITY_VERIFY_ROOTHASH_SIG
-    being set in the kernel.
+    being set in the kernel.  The signatures are checked against the builtin
+    trusted keyring by default, or the secondary trusted keyring if
+    DM_VERITY_VERIFY_ROOTHASH_SIG_SECONDARY_KEYRING is set.  The secondary
+    trusted keyring includes by default the builtin trusted keyring, and it can
+    also gain new certificates at run time if they are signed by a certificate
+    already in the secondary trusted keyring.
 
 Theory of operation
 ===================
diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index 06fb1b4aa849..682ab28b5c94 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/Documentation/admin-guide/kernel-parameters.rst
@@ -3,8 +3,8 @@
 The kernel's command-line parameters
 ====================================
 
-The following is a consolidated list of the kernel parameters as
-implemented by the __setup(), core_param() and module_param() macros
+The following is a consolidated list of the kernel parameters as implemented
+by the __setup(), early_param(), core_param() and module_param() macros
 and sorted into English Dictionary order (defined as ignoring all
 punctuation and sorting digits before letters in a case insensitive
 manner), and with descriptions where known.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index d24336109c2e..a10b545c2070 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1385,7 +1385,7 @@
 
 	ftrace_filter=[function-list]
 			[FTRACE] Limit the functions traced by the function
-			tracer at boot up. function-list is a comma separated
+			tracer at boot up. function-list is a comma-separated
 			list of functions. This list can be changed at run
 			time by the set_ftrace_filter file in the debugfs
 			tracing directory.
@@ -1399,13 +1399,13 @@
 	ftrace_graph_filter=[function-list]
 			[FTRACE] Limit the top level callers functions traced
 			by the function graph tracer at boot up.
-			function-list is a comma separated list of functions
+			function-list is a comma-separated list of functions
 			that can be changed at run time by the
 			set_graph_function file in the debugfs tracing directory.
 
 	ftrace_graph_notrace=[function-list]
 			[FTRACE] Do not trace from the functions specified in
-			function-list.  This list is a comma separated list of
+			function-list.  This list is a comma-separated list of
 			functions that can be changed at run time by the
 			set_graph_notrace file in the debugfs tracing directory.
 
@@ -2254,6 +2254,16 @@
 			for all guests.
 			Default is 1 (enabled) if in 64-bit or 32-bit PAE mode.
 
+	kvm-arm.mode=
+			[KVM,ARM] Select one of KVM/arm64's modes of operation.
+
+			protected: nVHE-based mode with support for guests whose
+				   state is kept private from the host.
+				   Not valid if the kernel is running in EL2.
+
+			Defaults to VHE/nVHE based on hardware support and
+			the value of CONFIG_ARM64_VHE.
+
 	kvm-arm.vgic_v3_group0_trap=
 			[KVM,ARM] Trap guest accesses to GICv3 group-0
 			system registers
@@ -2411,7 +2421,7 @@
 			when set.
 			Format: <int>
 
-	libata.force=	[LIBATA] Force configurations.  The format is comma
+	libata.force=	[LIBATA] Force configurations.  The format is comma-
 			separated list of "[ID:]VAL" where ID is
 			PORT[.DEVICE].  PORT and DEVICE are decimal numbers
 			matching port, link or device.  Basically, it matches
@@ -5135,7 +5145,7 @@
 
 	stacktrace_filter=[function-list]
 			[FTRACE] Limit the functions that the stack tracer
-			will trace at boot up. function-list is a comma separated
+			will trace at boot up. function-list is a comma-separated
 			list of functions. This list can be changed at run
 			time by the stack_trace_filter file in the debugfs
 			tracing directory. Note, this enables stack tracing
@@ -5338,7 +5348,7 @@
 	trace_event=[event-list]
 			[FTRACE] Set and start specified trace events in order
 			to facilitate early boot debugging. The event-list is a
-			comma separated list of trace events to enable. See
+			comma-separated list of trace events to enable. See
 			also Documentation/trace/events.rst
 
 	trace_options=[option-list]
@@ -5962,6 +5972,10 @@
 			This option is obsoleted by the "nopv" option, which
 			has equivalent effect for XEN platform.
 
+	xen_no_vector_callback
+			[KNL,X86,XEN] Disable the vector callback for Xen
+			event channel interrupts.
+
 	xen_scrub_pages=	[XEN]
 			Boolean option to control scrubbing pages before giving them back
 			to Xen, for use by other domains. Can be also changed at runtime
diff --git a/Documentation/admin-guide/mm/concepts.rst b/Documentation/admin-guide/mm/concepts.rst
index fa0974fbeae7..b966fcff993b 100644
--- a/Documentation/admin-guide/mm/concepts.rst
+++ b/Documentation/admin-guide/mm/concepts.rst
@@ -184,7 +184,7 @@ pages either asynchronously or synchronously, depending on the state
 of the system. When the system is not loaded, most of the memory is free
 and allocation requests will be satisfied immediately from the free
 pages supply. As the load increases, the amount of the free pages goes
-down and when it reaches a certain threshold (high watermark), an
+down and when it reaches a certain threshold (low watermark), an
 allocation request will awaken the ``kswapd`` daemon. It will
 asynchronously scan memory pages and either just free them if the data
 they contain is available elsewhere, or evict to the backing storage
diff --git a/Documentation/admin-guide/perf-security.rst b/Documentation/admin-guide/perf-security.rst
index 1307b5274a0f..904e4eb37f99 100644
--- a/Documentation/admin-guide/perf-security.rst
+++ b/Documentation/admin-guide/perf-security.rst
@@ -84,11 +84,14 @@ capabilities then providing the process with CAP_PERFMON capability singly
 is recommended as the preferred secure approach to resolve double access
 denial logging related to usage of performance monitoring and observability.
 
-Unprivileged processes using perf_events system call are also subject
-for PTRACE_MODE_READ_REALCREDS ptrace access mode check [7]_ , whose
-outcome determines whether monitoring is permitted. So unprivileged
-processes provided with CAP_SYS_PTRACE capability are effectively
-permitted to pass the check.
+Prior Linux v5.9 unprivileged processes using perf_events system call
+are also subject for PTRACE_MODE_READ_REALCREDS ptrace access mode check
+[7]_ , whose outcome determines whether monitoring is permitted.
+So unprivileged processes provided with CAP_SYS_PTRACE capability are
+effectively permitted to pass the check. Starting from Linux v5.9
+CAP_SYS_PTRACE capability is not required and CAP_PERFMON is enough to
+be provided for processes to make performance monitoring and observability
+operations.
 
 Other capabilities being granted to unprivileged processes can
 effectively enable capturing of additional data required for later
@@ -99,11 +102,11 @@ CAP_SYSLOG capability permits reading kernel space memory addresses from
 Privileged Perf users groups
 ---------------------------------
 
-Mechanisms of capabilities, privileged capability-dumb files [6]_ and
-file system ACLs [10]_ can be used to create dedicated groups of
-privileged Perf users who are permitted to execute performance monitoring
-and observability without scope limits. The following steps can be
-taken to create such groups of privileged Perf users.
+Mechanisms of capabilities, privileged capability-dumb files [6]_,
+file system ACLs [10]_ and sudo [15]_ utility can be used to create
+dedicated groups of privileged Perf users who are permitted to execute
+performance monitoring and observability without limits. The following
+steps can be taken to create such groups of privileged Perf users.
 
 1. Create perf_users group of privileged Perf users, assign perf_users
    group to Perf tool executable and limit access to the executable for
@@ -133,7 +136,7 @@ taken to create such groups of privileged Perf users.
    # getcap perf
    perf = cap_sys_ptrace,cap_syslog,cap_perfmon+ep
 
-If the libcap installed doesn't yet support "cap_perfmon", use "38" instead,
+If the libcap [16]_ installed doesn't yet support "cap_perfmon", use "38" instead,
 i.e.:
 
 ::
@@ -159,6 +162,60 @@ performance monitoring and observability by using functionality of the
 configured Perf tool executable that, when executes, passes perf_events
 subsystem scope checks.
 
+In case Perf tool executable can't be assigned required capabilities (e.g.
+file system is mounted with nosuid option or extended attributes are
+not supported by the file system) then creation of the capabilities
+privileged environment, naturally shell, is possible. The shell provides
+inherent processes with CAP_PERFMON and other required capabilities so that
+performance monitoring and observability operations are available in the
+environment without limits. Access to the environment can be open via sudo
+utility for members of perf_users group only. In order to create such
+environment:
+
+1. Create shell script that uses capsh utility [16]_ to assign CAP_PERFMON
+   and other required capabilities into ambient capability set of the shell
+   process, lock the process security bits after enabling SECBIT_NO_SETUID_FIXUP,
+   SECBIT_NOROOT and SECBIT_NO_CAP_AMBIENT_RAISE bits and then change
+   the process identity to sudo caller of the script who should essentially
+   be a member of perf_users group:
+
+::
+
+   # ls -alh /usr/local/bin/perf.shell
+   -rwxr-xr-x. 1 root root 83 Oct 13 23:57 /usr/local/bin/perf.shell
+   # cat /usr/local/bin/perf.shell
+   exec /usr/sbin/capsh --iab=^cap_perfmon --secbits=239 --user=$SUDO_USER -- -l
+
+2. Extend sudo policy at /etc/sudoers file with a rule for perf_users group:
+
+::
+
+   # grep perf_users /etc/sudoers
+   %perf_users    ALL=/usr/local/bin/perf.shell
+
+3. Check that members of perf_users group have access to the privileged
+   shell and have CAP_PERFMON and other required capabilities enabled
+   in permitted, effective and ambient capability sets of an inherent process:
+
+::
+
+  $ id
+  uid=1003(capsh_test) gid=1004(capsh_test) groups=1004(capsh_test),1000(perf_users) context=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023
+  $ sudo perf.shell
+  [sudo] password for capsh_test:
+  $ grep Cap /proc/self/status
+  CapInh:        0000004000000000
+  CapPrm:        0000004000000000
+  CapEff:        0000004000000000
+  CapBnd:        000000ffffffffff
+  CapAmb:        0000004000000000
+  $ capsh --decode=0000004000000000
+  0x0000004000000000=cap_perfmon
+
+As a result, members of perf_users group have access to the privileged
+environment where they can use tools employing performance monitoring APIs
+governed by CAP_PERFMON Linux capability.
+
 This specific access control management is only available to superuser
 or root running processes with CAP_SETPCAP, CAP_SETFCAP [6]_
 capabilities.
@@ -264,3 +321,5 @@ Bibliography
 .. [12] `<http://man7.org/linux/man-pages/man5/limits.conf.5.html>`_
 .. [13] `<https://sites.google.com/site/fullycapable>`_
 .. [14] `<http://man7.org/linux/man-pages/man8/auditd.8.html>`_
+.. [15] `<https://man7.org/linux/man-pages/man8/sudo.8.html>`_
+.. [16] `<https://git.kernel.org/pub/scm/libs/libcap/libcap.git/>`_
diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index e972caa43bd4..e35a3f2fb006 100644
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -428,7 +428,7 @@ While most applications need less than a thousand maps, certain
 programs, particularly malloc debuggers, may consume lots of them,
 e.g., up to one or two maps per allocation.
 
-The default value is 65536.
+The default value is 65530.
 
 
 memory_failure_early_kill:
diff --git a/Documentation/arm/memory.rst b/Documentation/arm/memory.rst
index 0521b4ce5c96..0cb1e2938823 100644
--- a/Documentation/arm/memory.rst
+++ b/Documentation/arm/memory.rst
@@ -45,9 +45,14 @@ fffe8000	fffeffff	DTCM mapping area for platforms with
 fffe0000	fffe7fff	ITCM mapping area for platforms with
 				ITCM mounted inside the CPU.
 
-ffc00000	ffefffff	Fixmap mapping region.  Addresses provided
+ffc80000	ffefffff	Fixmap mapping region.  Addresses provided
 				by fix_to_virt() will be located here.
 
+ffc00000	ffc7ffff	Guard region
+
+ff800000	ffbfffff	Permanent, fixed read-only mapping of the
+				firmware provided DT blob
+
 fee00000	feffffff	Mapping of PCI I/O space. This is a static
 				mapping within the vmalloc space.
 
@@ -72,6 +77,11 @@ MODULES_VADDR	MODULES_END-1	Kernel module space
 				Kernel modules inserted via insmod are
 				placed here using dynamic mappings.
 
+TASK_SIZE	MODULES_VADDR-1	KASAn shadow memory when KASan is in use.
+				The range from MODULES_VADDR to the top
+				of the memory is shadowed here with 1 bit
+				per byte of memory.
+
 00001000	TASK_SIZE-1	User space mappings
 				Per-thread mappings are placed here via
 				the mmap() system call.
diff --git a/Documentation/arm64/memory.rst b/Documentation/arm64/memory.rst
index e7522e5c8322..901cd094f4ec 100644
--- a/Documentation/arm64/memory.rst
+++ b/Documentation/arm64/memory.rst
@@ -97,7 +97,7 @@ hypervisor maps kernel pages in EL2 at a fixed (and potentially
 random) offset from the linear mapping. See the kern_hyp_va macro and
 kvm_update_va_mask function for more details. MMIO devices such as
 GICv2 gets mapped next to the HYP idmap page, as do vectors when
-ARM64_HARDEN_EL2_VECTORS is selected for particular CPUs.
+ARM64_SPECTRE_V3A is enabled for particular CPUs.
 
 When using KVM with the Virtualization Host Extensions, no additional
 mappings are created, since the host kernel runs directly in EL2.
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index 69171b1799f2..f1c9d20bd42d 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -53,7 +53,6 @@ How Linux keeps everything from happening at the same time.  See
 .. toctree::
    :maxdepth: 1
 
-   atomic_ops
    refcount-vs-atomic
    irq/index
    local_ops
diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index 6b752a45a936..0fc3fb1860c4 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -4,13 +4,16 @@ The Kernel Address Sanitizer (KASAN)
 Overview
 --------
 
-KernelAddressSANitizer (KASAN) is a dynamic memory error detector designed to
-find out-of-bound and use-after-free bugs. KASAN has two modes: generic KASAN
-(similar to userspace ASan) and software tag-based KASAN (similar to userspace
-HWASan).
+KernelAddressSANitizer (KASAN) is a dynamic memory safety error detector
+designed to find out-of-bound and use-after-free bugs. KASAN has three modes:
 
-KASAN uses compile-time instrumentation to insert validity checks before every
-memory access, and therefore requires a compiler version that supports that.
+1. generic KASAN (similar to userspace ASan),
+2. software tag-based KASAN (similar to userspace HWASan),
+3. hardware tag-based KASAN (based on hardware memory tagging).
+
+Software KASAN modes (1 and 2) use compile-time instrumentation to insert
+validity checks before every memory access, and therefore require a compiler
+version that supports that.
 
 Generic KASAN is supported in both GCC and Clang. With GCC it requires version
 8.3.0 or later. Any supported Clang version is compatible, but detection of
@@ -18,8 +21,8 @@ out-of-bounds accesses for global variables is only supported since Clang 11.
 
 Tag-based KASAN is only supported in Clang.
 
-Currently generic KASAN is supported for the x86_64, arm64, xtensa, s390 and
-riscv architectures, and tag-based KASAN is supported only for arm64.
+Currently generic KASAN is supported for the x86_64, arm, arm64, xtensa, s390
+and riscv architectures, and tag-based KASAN modes are supported only for arm64.
 
 Usage
 -----
@@ -28,30 +31,22 @@ To enable KASAN configure kernel with::
 
 	  CONFIG_KASAN = y
 
-and choose between CONFIG_KASAN_GENERIC (to enable generic KASAN) and
-CONFIG_KASAN_SW_TAGS (to enable software tag-based KASAN).
+and choose between CONFIG_KASAN_GENERIC (to enable generic KASAN),
+CONFIG_KASAN_SW_TAGS (to enable software tag-based KASAN), and
+CONFIG_KASAN_HW_TAGS (to enable hardware tag-based KASAN).
+
+For software modes, you also need to choose between CONFIG_KASAN_OUTLINE and
+CONFIG_KASAN_INLINE. Outline and inline are compiler instrumentation types.
+The former produces smaller binary while the latter is 1.1 - 2 times faster.
 
-You also need to choose between CONFIG_KASAN_OUTLINE and CONFIG_KASAN_INLINE.
-Outline and inline are compiler instrumentation types. The former produces
-smaller binary while the latter is 1.1 - 2 times faster.
+Both software KASAN modes work with both SLUB and SLAB memory allocators,
+while the hardware tag-based KASAN currently only support SLUB.
 
-Both KASAN modes work with both SLUB and SLAB memory allocators.
-For better bug detection and nicer reporting, enable CONFIG_STACKTRACE.
+For better error reports that include stack traces, enable CONFIG_STACKTRACE.
 
 To augment reports with last allocation and freeing stack of the physical page,
 it is recommended to enable also CONFIG_PAGE_OWNER and boot with page_owner=on.
 
-To disable instrumentation for specific files or directories, add a line
-similar to the following to the respective kernel Makefile:
-
-- For a single file (e.g. main.o)::
-
-    KASAN_SANITIZE_main.o := n
-
-- For all files in one directory::
-
-    KASAN_SANITIZE := n
-
 Error reports
 ~~~~~~~~~~~~~
 
@@ -136,22 +131,75 @@ freed (in case of a use-after-free bug report). Next comes a description of
 the accessed slab object and information about the accessed memory page.
 
 In the last section the report shows memory state around the accessed address.
-Reading this part requires some understanding of how KASAN works.
-
-The state of each 8 aligned bytes of memory is encoded in one shadow byte.
-Those 8 bytes can be accessible, partially accessible, freed or be a redzone.
-We use the following encoding for each shadow byte: 0 means that all 8 bytes
-of the corresponding memory region are accessible; number N (1 <= N <= 7) means
-that the first N bytes are accessible, and other (8 - N) bytes are not;
-any negative value indicates that the entire 8-byte word is inaccessible.
-We use different negative values to distinguish between different kinds of
-inaccessible memory like redzones or freed memory (see mm/kasan/kasan.h).
+Internally KASAN tracks memory state separately for each memory granule, which
+is either 8 or 16 aligned bytes depending on KASAN mode. Each number in the
+memory state section of the report shows the state of one of the memory
+granules that surround the accessed address.
+
+For generic KASAN the size of each memory granule is 8. The state of each
+granule is encoded in one shadow byte. Those 8 bytes can be accessible,
+partially accessible, freed or be a part of a redzone. KASAN uses the following
+encoding for each shadow byte: 0 means that all 8 bytes of the corresponding
+memory region are accessible; number N (1 <= N <= 7) means that the first N
+bytes are accessible, and other (8 - N) bytes are not; any negative value
+indicates that the entire 8-byte word is inaccessible. KASAN uses different
+negative values to distinguish between different kinds of inaccessible memory
+like redzones or freed memory (see mm/kasan/kasan.h).
 
 In the report above the arrows point to the shadow byte 03, which means that
 the accessed address is partially accessible.
 
 For tag-based KASAN this last report section shows the memory tags around the
-accessed address (see Implementation details section).
+accessed address (see `Implementation details`_ section).
+
+Boot parameters
+~~~~~~~~~~~~~~~
+
+Hardware tag-based KASAN mode (see the section about different mode below) is
+intended for use in production as a security mitigation. Therefore it supports
+boot parameters that allow to disable KASAN competely or otherwise control
+particular KASAN features.
+
+The things that can be controlled are:
+
+1. Whether KASAN is enabled at all.
+2. Whether KASAN collects and saves alloc/free stacks.
+3. Whether KASAN panics on a detected bug or not.
+
+The ``kasan.mode`` boot parameter allows to choose one of three main modes:
+
+- ``kasan.mode=off`` - KASAN is disabled, no tag checks are performed
+- ``kasan.mode=prod`` - only essential production features are enabled
+- ``kasan.mode=full`` - all KASAN features are enabled
+
+The chosen mode provides default control values for the features mentioned
+above. However it's also possible to override the default values by providing:
+
+- ``kasan.stacktrace=off`` or ``=on`` - enable alloc/free stack collection
+					(default: ``on`` for ``mode=full``,
+					 otherwise ``off``)
+- ``kasan.fault=report`` or ``=panic`` - only print KASAN report or also panic
+					 (default: ``report``)
+
+If ``kasan.mode`` parameter is not provided, it defaults to ``full`` when
+``CONFIG_DEBUG_KERNEL`` is enabled, and to ``prod`` otherwise.
+
+For developers
+~~~~~~~~~~~~~~
+
+Software KASAN modes use compiler instrumentation to insert validity checks.
+Such instrumentation might be incompatible with some part of the kernel, and
+therefore needs to be disabled. To disable instrumentation for specific files
+or directories, add a line similar to the following to the respective kernel
+Makefile:
+
+- For a single file (e.g. main.o)::
+
+    KASAN_SANITIZE_main.o := n
+
+- For all files in one directory::
+
+    KASAN_SANITIZE := n
 
 
 Implementation details
@@ -160,10 +208,10 @@ Implementation details
 Generic KASAN
 ~~~~~~~~~~~~~
 
-From a high level, our approach to memory error detection is similar to that
-of kmemcheck: use shadow memory to record whether each byte of memory is safe
-to access, and use compile-time instrumentation to insert checks of shadow
-memory on each memory access.
+From a high level perspective, KASAN's approach to memory error detection is
+similar to that of kmemcheck: use shadow memory to record whether each byte of
+memory is safe to access, and use compile-time instrumentation to insert checks
+of shadow memory on each memory access.
 
 Generic KASAN dedicates 1/8th of kernel memory to its shadow memory (e.g. 16TB
 to cover 128TB on x86_64) and uses direct mapping with a scale and offset to
@@ -194,20 +242,30 @@ Generic KASAN also reports the last 2 call stacks to creation of work that
 potentially has access to an object. Call stacks for the following are shown:
 call_rcu() and workqueue queuing.
 
+Generic KASAN is the only mode that delays the reuse of freed object via
+quarantine (see mm/kasan/quarantine.c for implementation).
+
 Software tag-based KASAN
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
-Tag-based KASAN uses the Top Byte Ignore (TBI) feature of modern arm64 CPUs to
-store a pointer tag in the top byte of kernel pointers. Like generic KASAN it
-uses shadow memory to store memory tags associated with each 16-byte memory
+Software tag-based KASAN requires software memory tagging support in the form
+of HWASan-like compiler instrumentation (see HWASan documentation for details).
+
+Software tag-based KASAN is currently only implemented for arm64 architecture.
+
+Software tag-based KASAN uses the Top Byte Ignore (TBI) feature of arm64 CPUs
+to store a pointer tag in the top byte of kernel pointers. Like generic KASAN
+it uses shadow memory to store memory tags associated with each 16-byte memory
 cell (therefore it dedicates 1/16th of the kernel memory for shadow memory).
 
-On each memory allocation tag-based KASAN generates a random tag, tags the
-allocated memory with this tag, and embeds this tag into the returned pointer.
+On each memory allocation software tag-based KASAN generates a random tag, tags
+the allocated memory with this tag, and embeds this tag into the returned
+pointer.
+
 Software tag-based KASAN uses compile-time instrumentation to insert checks
 before each memory access. These checks make sure that tag of the memory that
 is being accessed is equal to tag of the pointer that is used to access this
-memory. In case of a tag mismatch tag-based KASAN prints a bug report.
+memory. In case of a tag mismatch software tag-based KASAN prints a bug report.
 
 Software tag-based KASAN also has two instrumentation modes (outline, that
 emits callbacks to check memory accesses; and inline, that performs the shadow
@@ -216,9 +274,36 @@ simply printed from the function that performs the access check. With inline
 instrumentation a brk instruction is emitted by the compiler, and a dedicated
 brk handler is used to print bug reports.
 
-A potential expansion of this mode is a hardware tag-based mode, which would
-use hardware memory tagging support instead of compiler instrumentation and
-manual shadow memory manipulation.
+Software tag-based KASAN uses 0xFF as a match-all pointer tag (accesses through
+pointers with 0xFF pointer tag aren't checked). The value 0xFE is currently
+reserved to tag freed memory regions.
+
+Software tag-based KASAN currently only supports tagging of
+kmem_cache_alloc/kmalloc and page_alloc memory.
+
+Hardware tag-based KASAN
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Hardware tag-based KASAN is similar to the software mode in concept, but uses
+hardware memory tagging support instead of compiler instrumentation and
+shadow memory.
+
+Hardware tag-based KASAN is currently only implemented for arm64 architecture
+and based on both arm64 Memory Tagging Extension (MTE) introduced in ARMv8.5
+Instruction Set Architecture, and Top Byte Ignore (TBI).
+
+Special arm64 instructions are used to assign memory tags for each allocation.
+Same tags are assigned to pointers to those allocations. On every memory
+access, hardware makes sure that tag of the memory that is being accessed is
+equal to tag of the pointer that is used to access this memory. In case of a
+tag mismatch a fault is generated and a report is printed.
+
+Hardware tag-based KASAN uses 0xFF as a match-all pointer tag (accesses through
+pointers with 0xFF pointer tag aren't checked). The value 0xFE is currently
+reserved to tag freed memory regions.
+
+Hardware tag-based KASAN currently only supports tagging of
+kmem_cache_alloc/kmalloc and page_alloc memory.
 
 What memory accesses are sanitised by KASAN?
 --------------------------------------------
@@ -265,17 +350,17 @@ Most mappings in vmalloc space are small, requiring less than a full
 page of shadow space. Allocating a full shadow page per mapping would
 therefore be wasteful. Furthermore, to ensure that different mappings
 use different shadow pages, mappings would have to be aligned to
-``KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE``.
+``KASAN_GRANULE_SIZE * PAGE_SIZE``.
 
-Instead, we share backing space across multiple mappings. We allocate
+Instead, KASAN shares backing space across multiple mappings. It allocates
 a backing page when a mapping in vmalloc space uses a particular page
 of the shadow region. This page can be shared by other vmalloc
 mappings later on.
 
-We hook in to the vmap infrastructure to lazily clean up unused shadow
+KASAN hooks into the vmap infrastructure to lazily clean up unused shadow
 memory.
 
-To avoid the difficulties around swapping mappings around, we expect
+To avoid the difficulties around swapping mappings around, KASAN expects
 that the part of the shadow region that covers the vmalloc space will
 not be covered by the early shadow page, but will be left
 unmapped. This will require changes in arch-specific code.
@@ -286,24 +371,31 @@ architectures that do not have a fixed module region.
 CONFIG_KASAN_KUNIT_TEST & CONFIG_TEST_KASAN_MODULE
 --------------------------------------------------
 
-``CONFIG_KASAN_KUNIT_TEST`` utilizes the KUnit Test Framework for testing.
-This means each test focuses on a small unit of functionality and
-there are a few ways these tests can be run.
+KASAN tests consist on two parts:
+
+1. Tests that are integrated with the KUnit Test Framework. Enabled with
+``CONFIG_KASAN_KUNIT_TEST``. These tests can be run and partially verified
+automatically in a few different ways, see the instructions below.
 
-Each test will print the KASAN report if an error is detected and then
-print the number of the test and the status of the test:
+2. Tests that are currently incompatible with KUnit. Enabled with
+``CONFIG_TEST_KASAN_MODULE`` and can only be run as a module. These tests can
+only be verified manually, by loading the kernel module and inspecting the
+kernel log for KASAN reports.
 
-pass::
+Each KUnit-compatible KASAN test prints a KASAN report if an error is detected.
+Then the test prints its number and status.
+
+When a test passes::
 
         ok 28 - kmalloc_double_kzfree
 
-or, if kmalloc failed::
+When a test fails due to a failed ``kmalloc``::
 
         # kmalloc_large_oob_right: ASSERTION FAILED at lib/test_kasan.c:163
         Expected ptr is not null, but is
         not ok 4 - kmalloc_large_oob_right
 
-or, if a KASAN report was expected, but not found::
+When a test fails due to a missing KASAN report::
 
         # kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:629
         Expected kasan_data->report_expected == kasan_data->report_found, but
@@ -311,46 +403,38 @@ or, if a KASAN report was expected, but not found::
         kasan_data->report_found == 0
         not ok 28 - kmalloc_double_kzfree
 
-All test statuses are tracked as they run and an overall status will
-be printed at the end::
+At the end the cumulative status of all KASAN tests is printed. On success::
 
         ok 1 - kasan
 
-or::
+Or, if one of the tests failed::
 
         not ok 1 - kasan
 
-(1) Loadable Module
-~~~~~~~~~~~~~~~~~~~~
+
+There are a few ways to run KUnit-compatible KASAN tests.
+
+1. Loadable module
+~~~~~~~~~~~~~~~~~~
 
 With ``CONFIG_KUNIT`` enabled, ``CONFIG_KASAN_KUNIT_TEST`` can be built as
-a loadable module and run on any architecture that supports KASAN
-using something like insmod or modprobe. The module is called ``test_kasan``.
+a loadable module and run on any architecture that supports KASAN by loading
+the module with insmod or modprobe. The module is called ``test_kasan``.
 
-(2) Built-In
-~~~~~~~~~~~~~
+2. Built-In
+~~~~~~~~~~~
 
 With ``CONFIG_KUNIT`` built-in, ``CONFIG_KASAN_KUNIT_TEST`` can be built-in
-on any architecture that supports KASAN. These and any other KUnit
-tests enabled will run and print the results at boot as a late-init
-call.
+on any architecure that supports KASAN. These and any other KUnit tests enabled
+will run and print the results at boot as a late-init call.
 
-(3) Using kunit_tool
-~~~~~~~~~~~~~~~~~~~~~
+3. Using kunit_tool
+~~~~~~~~~~~~~~~~~~~
 
-With ``CONFIG_KUNIT`` and ``CONFIG_KASAN_KUNIT_TEST`` built-in, we can also
-use kunit_tool to see the results of these along with other KUnit
-tests in a more readable way. This will not print the KASAN reports
-of tests that passed. Use `KUnit documentation <https://www.kernel.org/doc/html/latest/dev-tools/kunit/index.html>`_ for more up-to-date
-information on kunit_tool.
+With ``CONFIG_KUNIT`` and ``CONFIG_KASAN_KUNIT_TEST`` built-in, it's also
+possible use ``kunit_tool`` to see the results of these and other KUnit tests
+in a more readable way. This will not print the KASAN reports of the tests that
+passed. Use `KUnit documentation <https://www.kernel.org/doc/html/latest/dev-tools/kunit/index.html>`_
+for more up-to-date information on ``kunit_tool``.
 
 .. _KUnit: https://www.kernel.org/doc/html/latest/dev-tools/kunit/index.html
-
-``CONFIG_TEST_KASAN_MODULE`` is a set of KASAN tests that could not be
-converted to KUnit. These tests can be run only as a module with
-``CONFIG_TEST_KASAN_MODULE`` built as a loadable module and
-``CONFIG_KASAN`` built-in. The type of error expected and the
-function being run is printed before the expression expected to give
-an error. Then the error is printed, if found, and that test
-should be interpreted to pass only if the error was the one expected
-by the test.
diff --git a/Documentation/devicetree/bindings/arm/idle-states.yaml b/Documentation/devicetree/bindings/arm/idle-states.yaml
index ea805c1e6b20..52bce5dbb11f 100644
--- a/Documentation/devicetree/bindings/arm/idle-states.yaml
+++ b/Documentation/devicetree/bindings/arm/idle-states.yaml
@@ -313,7 +313,7 @@ patternProperties:
           wakeup-latency-us by this duration.
 
       idle-state-name:
-        $ref: /schemas/types.yaml#definitions/string
+        $ref: /schemas/types.yaml#/definitions/string
         description:
           A string used as a descriptive name for the idle state.
 
diff --git a/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml b/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml
index 0503651cd214..863a287ebc7e 100644
--- a/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml
+++ b/Documentation/devicetree/bindings/bus/allwinner,sun50i-a64-de2.yaml
@@ -34,7 +34,7 @@ properties:
     description:
       The SRAM that needs to be claimed to access the display engine
       bus.
-    $ref: /schemas/types.yaml#definitions/phandle-array
+    $ref: /schemas/types.yaml#/definitions/phandle-array
     maxItems: 1
 
   ranges: true
diff --git a/Documentation/devicetree/bindings/bus/baikal,bt1-axi.yaml b/Documentation/devicetree/bindings/bus/baikal,bt1-axi.yaml
index 0bee4694578a..4ac78b44e45e 100644
--- a/Documentation/devicetree/bindings/bus/baikal,bt1-axi.yaml
+++ b/Documentation/devicetree/bindings/bus/baikal,bt1-axi.yaml
@@ -46,7 +46,7 @@ properties:
     const: 1
 
   syscon:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description: Phandle to the Baikal-T1 System Controller DT node
 
   interrupts:
diff --git a/Documentation/devicetree/bindings/clock/adi,axi-clkgen.yaml b/Documentation/devicetree/bindings/clock/adi,axi-clkgen.yaml
new file mode 100644
index 000000000000..0d06387184d6
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/adi,axi-clkgen.yaml
@@ -0,0 +1,53 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/adi,axi-clkgen.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Binding for Analog Devices AXI clkgen pcore clock generator
+
+maintainers:
+  - Lars-Peter Clausen <lars@metafoo.de>
+  - Michael Hennerich <michael.hennerich@analog.com>
+
+description: |
+  The axi_clkgen IP core is a software programmable clock generator,
+  that can be synthesized on various FPGA platforms.
+
+  Link: https://wiki.analog.com/resources/fpga/docs/axi_clkgen
+
+properties:
+  compatible:
+    enum:
+      - adi,axi-clkgen-2.00.a
+
+  clocks:
+    description:
+      Specifies the reference clock(s) from which the output frequency is
+      derived. This must either reference one clock if only the first clock
+      input is connected or two if both clock inputs are connected.
+    minItems: 1
+    maxItems: 2
+
+  '#clock-cells':
+    const: 0
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - '#clock-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    clock-controller@ff000000 {
+      compatible = "adi,axi-clkgen-2.00.a";
+      #clock-cells = <0>;
+      reg = <0xff000000 0x1000>;
+      clocks = <&osc 1>;
+    };
diff --git a/Documentation/devicetree/bindings/clock/axi-clkgen.txt b/Documentation/devicetree/bindings/clock/axi-clkgen.txt
deleted file mode 100644
index aca94fe9416f..000000000000
--- a/Documentation/devicetree/bindings/clock/axi-clkgen.txt
+++ /dev/null
@@ -1,25 +0,0 @@
-Binding for the axi-clkgen clock generator
-
-This binding uses the common clock binding[1].
-
-[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
-
-Required properties:
-- compatible : shall be "adi,axi-clkgen-1.00.a" or "adi,axi-clkgen-2.00.a".
-- #clock-cells : from common clock binding; Should always be set to 0.
-- reg : Address and length of the axi-clkgen register set.
-- clocks : Phandle and clock specifier for the parent clock(s). This must
-	either reference one clock if only the first clock input is connected or two
-	if both clock inputs are connected. For the later case the clock connected
-	to the first input must be specified first.
-
-Optional properties:
-- clock-output-names : From common clock binding.
-
-Example:
-	clock@ff000000 {
-		compatible = "adi,axi-clkgen";
-		#clock-cells = <0>;
-		reg = <0xff000000 0x1000>;
-		clocks = <&osc 1>;
-	};
diff --git a/Documentation/devicetree/bindings/clock/canaan,k210-clk.yaml b/Documentation/devicetree/bindings/clock/canaan,k210-clk.yaml
new file mode 100644
index 000000000000..565ca468cb44
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/canaan,k210-clk.yaml
@@ -0,0 +1,54 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/canaan,k210-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Canaan Kendryte K210 Clock Device Tree Bindings
+
+maintainers:
+  - Damien Le Moal <damien.lemoal@wdc.com>
+
+description: |
+  Canaan Kendryte K210 SoC clocks driver bindings. The clock
+  controller node must be defined as a child node of the K210
+  system controller node.
+
+  See also:
+  - dt-bindings/clock/k210-clk.h
+
+properties:
+  compatible:
+    const: canaan,k210-clk
+
+  clocks:
+    description:
+      Phandle of the SoC 26MHz fixed-rate oscillator clock.
+
+  '#clock-cells':
+    const: 1
+
+required:
+  - compatible
+  - '#clock-cells'
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/k210-clk.h>
+    clocks {
+      in0: oscillator {
+        compatible = "fixed-clock";
+        #clock-cells = <0>;
+        clock-frequency = <26000000>;
+      };
+    };
+
+    /* ... */
+    sysclk: clock-controller {
+      #clock-cells = <1>;
+      compatible = "canaan,k210-clk";
+      clocks = <&in0>;
+    };
diff --git a/Documentation/devicetree/bindings/clock/fsl,flexspi-clock.yaml b/Documentation/devicetree/bindings/clock/fsl,flexspi-clock.yaml
new file mode 100644
index 000000000000..1fa390ee7b9b
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/fsl,flexspi-clock.yaml
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/fsl,flexspi-clock.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Freescale FlexSPI clock driver for Layerscape SoCs
+
+maintainers:
+  - Michael Walle <michael@walle.cc>
+
+description:
+  The Freescale Layerscape SoCs have a special FlexSPI clock which is
+  derived from the platform PLL.
+
+properties:
+  compatible:
+    enum:
+      - fsl,ls1028a-flexspi-clk
+      - fsl,lx2160a-flexspi-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  '#clock-cells':
+    const: 0
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - '#clock-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    dcfg {
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        fspi_clk: clock-controller@900 {
+            compatible = "fsl,ls1028a-flexspi-clk";
+            reg = <0x900 0x4>;
+            #clock-cells = <0>;
+            clocks = <&parentclk>;
+            clock-output-names = "fspi_clk";
+        };
+    };
diff --git a/Documentation/devicetree/bindings/clock/imx8qxp-lpcg.yaml b/Documentation/devicetree/bindings/clock/imx8qxp-lpcg.yaml
index e709e530e17a..940486ef1051 100644
--- a/Documentation/devicetree/bindings/clock/imx8qxp-lpcg.yaml
+++ b/Documentation/devicetree/bindings/clock/imx8qxp-lpcg.yaml
@@ -29,18 +29,18 @@ properties:
       - const: fsl,imx8qxp-lpcg
       - items:
           - enum:
-            - fsl,imx8qm-lpcg
+              - fsl,imx8qm-lpcg
           - const: fsl,imx8qxp-lpcg
       - enum:
-        - fsl,imx8qxp-lpcg-adma
-        - fsl,imx8qxp-lpcg-conn
-        - fsl,imx8qxp-lpcg-dc
-        - fsl,imx8qxp-lpcg-dsp
-        - fsl,imx8qxp-lpcg-gpu
-        - fsl,imx8qxp-lpcg-hsio
-        - fsl,imx8qxp-lpcg-img
-        - fsl,imx8qxp-lpcg-lsio
-        - fsl,imx8qxp-lpcg-vpu
+          - fsl,imx8qxp-lpcg-adma
+          - fsl,imx8qxp-lpcg-conn
+          - fsl,imx8qxp-lpcg-dc
+          - fsl,imx8qxp-lpcg-dsp
+          - fsl,imx8qxp-lpcg-gpu
+          - fsl,imx8qxp-lpcg-hsio
+          - fsl,imx8qxp-lpcg-img
+          - fsl,imx8qxp-lpcg-lsio
+          - fsl,imx8qxp-lpcg-vpu
         deprecated: true
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/clock/qcom,aoncc-sm8250.yaml b/Documentation/devicetree/bindings/clock/qcom,aoncc-sm8250.yaml
new file mode 100644
index 000000000000..c40a74b5d672
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,aoncc-sm8250.yaml
@@ -0,0 +1,58 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,aoncc-sm8250.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Clock bindings for LPASS Always ON Clock Controller on SM8250 SoCs
+
+maintainers:
+  - Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+
+description: |
+  The clock consumer should specify the desired clock by having the clock
+  ID in its "clocks" phandle cell.
+  See include/dt-bindings/clock/qcom,sm8250-lpass-aoncc.h for the full list
+  of Audio Clock controller clock IDs.
+
+properties:
+  compatible:
+    const: qcom,sm8250-lpass-aon
+
+  reg:
+    maxItems: 1
+
+  '#clock-cells':
+    const: 1
+
+  clocks:
+    items:
+      - description: LPASS Core voting clock
+      - description: Glitch Free Mux register clock
+
+  clock-names:
+    items:
+      - const: core
+      - const: bus
+
+required:
+  - compatible
+  - reg
+  - '#clock-cells'
+  - clocks
+  - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,sm8250-lpass-aoncc.h>
+    #include <dt-bindings/sound/qcom,q6afe.h>
+    clock-controller@3800000 {
+      #clock-cells = <1>;
+      compatible = "qcom,sm8250-lpass-aon";
+      reg = <0x03380000 0x40000>;
+      clocks = <&q6afecc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+               <&q6afecc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
+      clock-names = "core", "bus";
+    };
diff --git a/Documentation/devicetree/bindings/clock/qcom,audiocc-sm8250.yaml b/Documentation/devicetree/bindings/clock/qcom,audiocc-sm8250.yaml
new file mode 100644
index 000000000000..915d76206ad0
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,audiocc-sm8250.yaml
@@ -0,0 +1,58 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,audiocc-sm8250.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Clock bindings for LPASS Audio Clock Controller on SM8250 SoCs
+
+maintainers:
+  - Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+
+description: |
+  The clock consumer should specify the desired clock by having the clock
+  ID in its "clocks" phandle cell.
+  See include/dt-bindings/clock/qcom,sm8250-lpass-audiocc.h for the full list
+  of Audio Clock controller clock IDs.
+
+properties:
+  compatible:
+    const: qcom,sm8250-lpass-audiocc
+
+  reg:
+    maxItems: 1
+
+  '#clock-cells':
+    const: 1
+
+  clocks:
+    items:
+      - description: LPASS Core voting clock
+      - description: Glitch Free Mux register clock
+
+  clock-names:
+    items:
+      - const: core
+      - const: bus
+
+required:
+  - compatible
+  - reg
+  - '#clock-cells'
+  - clocks
+  - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,sm8250-lpass-audiocc.h>
+    #include <dt-bindings/sound/qcom,q6afe.h>
+    clock-controller@3300000 {
+      #clock-cells = <1>;
+      compatible = "qcom,sm8250-lpass-audiocc";
+      reg = <0x03300000 0x30000>;
+      clocks = <&q6afecc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+               <&q6afecc LPASS_CLK_ID_TX_CORE_MCLK LPASS_CLK_ATTRIBUTE_COUPLE_NO>;
+      clock-names = "core", "bus";
+    };
diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-sdx55.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-sdx55.yaml
new file mode 100644
index 000000000000..1121b3934cb9
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,gcc-sdx55.yaml
@@ -0,0 +1,77 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,gcc-sdx55.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Global Clock & Reset Controller Binding for SDX55
+
+maintainers:
+  - Vinod Koul <vkoul@kernel.org>
+  - Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+
+description: |
+  Qualcomm global clock control module which supports the clocks, resets and
+  power domains on SDX55
+
+  See also:
+  - dt-bindings/clock/qcom,gcc-sdx55.h
+
+properties:
+  compatible:
+    const: qcom,gcc-sdx55
+
+  clocks:
+    items:
+      - description: Board XO source
+      - description: Sleep clock source
+      - description: PLL test clock source (Optional clock)
+    minItems: 2
+    maxItems: 3
+
+  clock-names:
+    items:
+      - const: bi_tcxo
+      - const: sleep_clk
+      - const: core_bi_pll_test_se # Optional clock
+    minItems: 2
+    maxItems: 3
+
+  '#clock-cells':
+    const: 1
+
+  '#reset-cells':
+    const: 1
+
+  '#power-domain-cells':
+    const: 1
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - '#clock-cells'
+  - '#reset-cells'
+  - '#power-domain-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,rpmh.h>
+    clock-controller@100000 {
+      compatible = "qcom,gcc-sdx55";
+      reg = <0x00100000 0x1f0000>;
+      clocks = <&rpmhcc RPMH_CXO_CLK>,
+               <&sleep_clk>, <&pll_test_clk>;
+      clock-names = "bi_tcxo", "sleep_clk", "core_bi_pll_test_se";
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml b/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
index a46a3a799a70..12c9cbc0ebf9 100644
--- a/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
@@ -19,8 +19,10 @@ properties:
     enum:
       - qcom,sc7180-rpmh-clk
       - qcom,sdm845-rpmh-clk
+      - qcom,sdx55-rpmh-clk
       - qcom,sm8150-rpmh-clk
       - qcom,sm8250-rpmh-clk
+      - qcom,sm8350-rpmh-clk
 
   clocks:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/clock/qcom,sc7180-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sc7180-camcc.yaml
new file mode 100644
index 000000000000..f49027edfc44
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,sc7180-camcc.yaml
@@ -0,0 +1,73 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,sc7180-camcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Camera Clock & Reset Controller Binding for SC7180
+
+maintainers:
+  - Taniya Das <tdas@codeaurora.org>
+
+description: |
+  Qualcomm camera clock control module which supports the clocks, resets and
+  power domains on SC7180.
+
+  See also:
+  - dt-bindings/clock/qcom,camcc-sc7180.h
+
+properties:
+  compatible:
+    const: qcom,sc7180-camcc
+
+  clocks:
+    items:
+      - description: Board XO source
+      - description: Camera_ahb clock from GCC
+      - description: Camera XO clock from GCC
+
+  clock-names:
+    items:
+      - const: bi_tcxo
+      - const: iface
+      - const: xo
+
+  '#clock-cells':
+    const: 1
+
+  '#reset-cells':
+    const: 1
+
+  '#power-domain-cells':
+    const: 1
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - '#clock-cells'
+  - '#reset-cells'
+  - '#power-domain-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/qcom,gcc-sc7180.h>
+    #include <dt-bindings/clock/qcom,rpmh.h>
+    clock-controller@ad00000 {
+      compatible = "qcom,sc7180-camcc";
+      reg = <0x0ad00000 0x10000>;
+      clocks = <&rpmhcc RPMH_CXO_CLK>,
+               <&gcc GCC_CAMERA_AHB_CLK>,
+               <&gcc GCC_CAMERA_XO_CLK>;
+      clock-names = "bi_tcxo", "iface", "xo";
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.txt b/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.txt
deleted file mode 100644
index da92f5748dee..000000000000
--- a/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.txt
+++ /dev/null
@@ -1,68 +0,0 @@
-* Renesas R-Car USB 2.0 clock selector
-
-This file provides information on what the device node for the R-Car USB 2.0
-clock selector.
-
-If you connect an external clock to the USB_EXTAL pin only, you should set
-the clock rate to "usb_extal" node only.
-If you connect an oscillator to both the USB_XTAL and USB_EXTAL, this module
-is not needed because this is default setting. (Of course, you can set the
-clock rates to both "usb_extal" and "usb_xtal" nodes.
-
-Case 1: An external clock connects to R-Car SoC
-	+----------+   +--- R-Car ---------------------+
-	|External  |---|USB_EXTAL ---> all usb channels|
-	|clock     |   |USB_XTAL                       |
-	+----------+   +-------------------------------+
-In this case, we need this driver with "usb_extal" clock.
-
-Case 2: An oscillator connects to R-Car SoC
-	+----------+   +--- R-Car ---------------------+
-	|Oscillator|---|USB_EXTAL -+-> all usb channels|
-	|          |---|USB_XTAL --+                   |
-	+----------+   +-------------------------------+
-In this case, we don't need this selector.
-
-Required properties:
-- compatible: "renesas,r8a7795-rcar-usb2-clock-sel" if the device is a part of
-	      an R8A7795 SoC.
-	      "renesas,r8a7796-rcar-usb2-clock-sel" if the device if a part of
-	      an R8A77960 SoC.
-	      "renesas,r8a77961-rcar-usb2-clock-sel" if the device if a part of
-	      an R8A77961 SoC.
-	      "renesas,rcar-gen3-usb2-clock-sel" for a generic R-Car Gen3
-	      compatible device.
-
-	      When compatible with the generic version, nodes must list the
-	      SoC-specific version corresponding to the platform first
-	      followed by the generic version.
-
-- reg: offset and length of the USB 2.0 clock selector register block.
-- clocks: A list of phandles and specifier pairs.
-- clock-names: Name of the clocks.
- - The functional clock of USB 2.0 host side must be "ehci_ohci"
- - The functional clock of HS-USB side must be "hs-usb-if"
- - The USB_EXTAL clock pin must be "usb_extal"
- - The USB_XTAL clock pin must be "usb_xtal"
-- #clock-cells: Must be 0
-- power-domains: A phandle and symbolic PM domain specifier.
-                 See power/renesas,rcar-sysc.yaml.
-- resets: A list of phandles and specifier pairs.
-- reset-names: Name of the resets.
- - The reset of USB 2.0 host side must be "ehci_ohci"
- - The reset of HS-USB side must be "hs-usb-if"
-
-Example (R-Car H3):
-
-	usb2_clksel: clock-controller@e6590630 {
-		compatible = "renesas,r8a7795-rcar-usb2-clock-sel",
-			     "renesas,rcar-gen3-usb2-clock-sel";
-		reg = <0 0xe6590630 0 0x02>;
-		clocks = <&cpg CPG_MOD 703>, <&cpg CPG_MOD 704>,
-			 <&usb_extal>, <&usb_xtal>;
-		clock-names = "ehci_ohci", "hs-usb-if", "usb_extal", "usb_xtal";
-		#clock-cells = <0>;
-		power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
-		resets = <&cpg 703>, <&cpg 704>;
-		reset-names = "ehci_ohci", "hs-usb-if";
-	};
diff --git a/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.yaml b/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.yaml
new file mode 100644
index 000000000000..5be1229b3d6e
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/renesas,rcar-usb2-clock-sel.yaml
@@ -0,0 +1,100 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/clock/renesas,rcar-usb2-clock-sel.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: Renesas R-Car USB 2.0 clock selector
+
+maintainers:
+  - Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
+
+description: |
+  If you connect an external clock to the USB_EXTAL pin only, you should set
+  the clock rate to "usb_extal" node only.
+  If you connect an oscillator to both the USB_XTAL and USB_EXTAL, this module
+  is not needed because this is default setting. (Of course, you can set the
+  clock rates to both "usb_extal" and "usb_xtal" nodes.
+
+  Case 1: An external clock connects to R-Car SoC
+    +----------+   +--- R-Car ---------------------+
+    |External  |---|USB_EXTAL ---> all usb channels|
+    |clock     |   |USB_XTAL                       |
+    +----------+   +-------------------------------+
+
+  In this case, we need this driver with "usb_extal" clock.
+
+  Case 2: An oscillator connects to R-Car SoC
+    +----------+   +--- R-Car ---------------------+
+    |Oscillator|---|USB_EXTAL -+-> all usb channels|
+    |          |---|USB_XTAL --+                   |
+    +----------+   +-------------------------------+
+  In this case, we don't need this selector.
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - renesas,r8a7795-rcar-usb2-clock-sel  # R-Car H3
+          - renesas,r8a7796-rcar-usb2-clock-sel  # R-Car M3-W
+          - renesas,r8a77961-rcar-usb2-clock-sel # R-Car M3-W+
+      - const: renesas,rcar-gen3-usb2-clock-sel
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 4
+    maxItems: 4
+
+  clock-names:
+    items:
+      - const: ehci_ohci
+      - const: hs-usb-if
+      - const: usb_extal
+      - const: usb_xtal
+
+  '#clock-cells':
+    const: 0
+
+  power-domains:
+    maxItems: 1
+
+  resets:
+    minItems: 2
+    maxItems: 2
+
+  reset-names:
+    items:
+      - const: ehci_ohci
+      - const: hs-usb-if
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - '#clock-cells'
+  - power-domains
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/r8a7795-cpg-mssr.h>
+    #include <dt-bindings/power/r8a7795-sysc.h>
+
+    usb2_clksel: clock-controller@e6590630 {
+        compatible = "renesas,r8a7795-rcar-usb2-clock-sel",
+                     "renesas,rcar-gen3-usb2-clock-sel";
+        reg = <0xe6590630 0x02>;
+        clocks = <&cpg CPG_MOD 703>, <&cpg CPG_MOD 704>,
+                 <&usb_extal>, <&usb_xtal>;
+        clock-names = "ehci_ohci", "hs-usb-if", "usb_extal", "usb_xtal";
+        #clock-cells = <0>;
+        power-domains = <&sysc R8A7795_PD_ALWAYS_ON>;
+        resets = <&cpg 703>, <&cpg 704>;
+        reset-names = "ehci_ohci", "hs-usb-if";
+    };
diff --git a/Documentation/devicetree/bindings/clock/sifive/fu740-prci.yaml b/Documentation/devicetree/bindings/clock/sifive/fu740-prci.yaml
new file mode 100644
index 000000000000..e17143cac316
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/sifive/fu740-prci.yaml
@@ -0,0 +1,60 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 SiFive, Inc.
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/sifive/fu740-prci.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: SiFive FU740 Power Reset Clock Interrupt Controller (PRCI)
+
+maintainers:
+  - Zong Li <zong.li@sifive.com>
+  - Paul Walmsley  <paul.walmsley@sifive.com>
+
+description:
+  On the FU740 family of SoCs, most system-wide clock and reset integration
+  is via the PRCI IP block.
+  The clock consumer should specify the desired clock via the clock ID
+  macros defined in include/dt-bindings/clock/sifive-fu740-prci.h.
+  These macros begin with PRCI_CLK_.
+
+  The hfclk and rtcclk nodes are required, and represent physical
+  crystals or resonators located on the PCB.  These nodes should be present
+  underneath /, rather than /soc.
+
+properties:
+  compatible:
+    const: sifive,fu740-c000-prci
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: high frequency clock.
+      - description: RTL clock.
+
+  clock-names:
+    items:
+      - const: hfclk
+      - const: rtcclk
+
+  "#clock-cells":
+    const: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - "#clock-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    prci: clock-controller@10000000 {
+      compatible = "sifive,fu740-c000-prci";
+      reg = <0x10000000 0x1000>;
+      clocks = <&hfclk>, <&rtcclk>;
+      #clock-cells = <1>;
+    };
diff --git a/Documentation/devicetree/bindings/connector/usb-connector.yaml b/Documentation/devicetree/bindings/connector/usb-connector.yaml
index a84464b3e1f2..4286ed767a0a 100644
--- a/Documentation/devicetree/bindings/connector/usb-connector.yaml
+++ b/Documentation/devicetree/bindings/connector/usb-connector.yaml
@@ -37,7 +37,7 @@ properties:
     description: Size of the connector, should be specified in case of
       non-fullsize 'usb-a-connector' or 'usb-b-connector' compatible
       connectors.
-    $ref: /schemas/types.yaml#definitions/string
+    $ref: /schemas/types.yaml#/definitions/string
 
     enum:
       - mini
@@ -67,7 +67,7 @@ properties:
   power-role:
     description: Determines the power role that the Type C connector will
       support. "dual" refers to Dual Role Port (DRP).
-    $ref: /schemas/types.yaml#definitions/string
+    $ref: /schemas/types.yaml#/definitions/string
 
     enum:
       - source
@@ -76,7 +76,7 @@ properties:
 
   try-power-role:
     description: Preferred power role.
-    $ref: /schemas/types.yaml#definitions/string
+    $ref: /schemas/types.yaml#/definitions/string
 
     enum:
       - source
@@ -86,7 +86,7 @@ properties:
   data-role:
     description: Data role if Type C connector supports USB data. "dual" refers
       Dual Role Device (DRD).
-    $ref: /schemas/types.yaml#definitions/string
+    $ref: /schemas/types.yaml#/definitions/string
 
     enum:
       - host
@@ -105,7 +105,7 @@ properties:
         Type-C Cable and Connector specification, when Power Delivery is not
         supported.
     allOf:
-      - $ref: /schemas/types.yaml#definitions/string
+      - $ref: /schemas/types.yaml#/definitions/string
     enum:
       - default
       - 1.5A
diff --git a/Documentation/devicetree/bindings/display/bridge/analogix,anx7625.yaml b/Documentation/devicetree/bindings/display/bridge/analogix,anx7625.yaml
index 60585a4fc22b..9392b5502a32 100644
--- a/Documentation/devicetree/bindings/display/bridge/analogix,anx7625.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/analogix,anx7625.yaml
@@ -49,8 +49,8 @@ properties:
           Video port for panel or connector.
 
     required:
-        - port@0
-        - port@1
+      - port@0
+      - port@1
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/display/bridge/anx6345.yaml b/Documentation/devicetree/bindings/display/bridge/anx6345.yaml
index 8c0e4f285fbc..fccd63521a8c 100644
--- a/Documentation/devicetree/bindings/display/bridge/anx6345.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/anx6345.yaml
@@ -26,11 +26,9 @@ properties:
     description: GPIO connected to active low reset
 
   dvdd12-supply:
-    maxItems: 1
     description: Regulator for 1.2V digital core power.
 
   dvdd25-supply:
-    maxItems: 1
     description: Regulator for 2.5V digital core power.
 
   ports:
diff --git a/Documentation/devicetree/bindings/display/bridge/intel,keembay-dsi.yaml b/Documentation/devicetree/bindings/display/bridge/intel,keembay-dsi.yaml
index ab5be2625224..35c9dfd86650 100644
--- a/Documentation/devicetree/bindings/display/bridge/intel,keembay-dsi.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/intel,keembay-dsi.yaml
@@ -39,10 +39,10 @@ properties:
 
     properties:
       '#address-cells':
-       const: 1
+        const: 1
 
       '#size-cells':
-       const: 0
+        const: 0
 
       port@0:
         type: object
diff --git a/Documentation/devicetree/bindings/display/bridge/ite,it6505.yaml b/Documentation/devicetree/bindings/display/bridge/ite,it6505.yaml
index efbb3d0117dc..02cfc0a3b550 100644
--- a/Documentation/devicetree/bindings/display/bridge/ite,it6505.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/ite,it6505.yaml
@@ -35,11 +35,9 @@ properties:
     maxItems: 1
 
   ovdd-supply:
-    maxItems: 1
     description: I/O voltage
 
   pwr18-supply:
-    maxItems: 1
     description: core voltage
 
   interrupts:
diff --git a/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml b/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml
index e5e3c72630cf..66a14d60ce1d 100644
--- a/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml
@@ -79,8 +79,7 @@ properties:
       The GPIO used to control the power down line of this device.
     maxItems: 1
 
-  power-supply:
-    maxItems: 1
+  power-supply: true
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/display/bridge/ps8640.yaml b/Documentation/devicetree/bindings/display/bridge/ps8640.yaml
index 7e27cfcf770d..763c7909473e 100644
--- a/Documentation/devicetree/bindings/display/bridge/ps8640.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/ps8640.yaml
@@ -35,11 +35,9 @@ properties:
     description: GPIO connected to active low reset.
 
   vdd12-supply:
-    maxItems: 1
     description: Regulator for 1.2V digital core power.
 
   vdd33-supply:
-    maxItems: 1
     description: Regulator for 3.3V digital core power.
 
   ports:
diff --git a/Documentation/devicetree/bindings/display/bridge/simple-bridge.yaml b/Documentation/devicetree/bindings/display/bridge/simple-bridge.yaml
index 3ddb35fcf0a2..64e8a1c24b40 100644
--- a/Documentation/devicetree/bindings/display/bridge/simple-bridge.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/simple-bridge.yaml
@@ -60,7 +60,6 @@ properties:
     description: GPIO controlling bridge enable
 
   vdd-supply:
-    maxItems: 1
     description: Power supply for the bridge
 
 required:
diff --git a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.yaml b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.yaml
index 469ac4a34273..3d5ce08a5792 100644
--- a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvd1024.yaml
@@ -74,7 +74,6 @@ properties:
     description: Power down GPIO signal, pin name "/PDWN", active low.
 
   vcc-supply:
-    maxItems: 1
     description:
       Power supply for the TTL output, TTL CLOCKOUT signal, LVDS input, PLL and
       digital circuitry.
diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358775.yaml b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358775.yaml
index fd3113aa9ccd..b5959cc78b8d 100644
--- a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358775.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358775.yaml
@@ -28,11 +28,9 @@ properties:
     description: i2c address of the bridge, 0x0f
 
   vdd-supply:
-    maxItems: 1
     description: 1.2V LVDS Power Supply
 
   vddio-supply:
-    maxItems: 1
     description: 1.8V IO Power Supply
 
   stby-gpios:
diff --git a/Documentation/devicetree/bindings/display/intel,keembay-msscam.yaml b/Documentation/devicetree/bindings/display/intel,keembay-msscam.yaml
index 40caa6118809..a222b52d8b8f 100644
--- a/Documentation/devicetree/bindings/display/intel,keembay-msscam.yaml
+++ b/Documentation/devicetree/bindings/display/intel,keembay-msscam.yaml
@@ -18,8 +18,8 @@ description: |
 properties:
   compatible:
     items:
-     - const: intel,keembay-msscam
-     - const: syscon
+      - const: intel,keembay-msscam
+      - const: syscon
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/display/panel/abt,y030xx067a.yaml b/Documentation/devicetree/bindings/display/panel/abt,y030xx067a.yaml
index 91cb4c3e0198..a108029ecfab 100644
--- a/Documentation/devicetree/bindings/display/panel/abt,y030xx067a.yaml
+++ b/Documentation/devicetree/bindings/display/panel/abt,y030xx067a.yaml
@@ -32,7 +32,7 @@ required:
   - power-supply
   - reset-gpios
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/display/panel/novatek,nt36672a.yaml b/Documentation/devicetree/bindings/display/panel/novatek,nt36672a.yaml
index d2170de6b723..2f5df1d235ae 100644
--- a/Documentation/devicetree/bindings/display/panel/novatek,nt36672a.yaml
+++ b/Documentation/devicetree/bindings/display/panel/novatek,nt36672a.yaml
@@ -22,7 +22,7 @@ properties:
   compatible:
     items:
       - enum:
-         - tianma,fhd-video
+          - tianma,fhd-video
       - const: novatek,nt36672a
     description: This indicates the panel manufacturer of the panel that is
       in turn using the NT36672A panel driver. This compatible string
diff --git a/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml b/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml
index 7b9d468c3e52..403d57977ee7 100644
--- a/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml
+++ b/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml
@@ -98,7 +98,6 @@ properties:
     maxItems: 1
 
   dmas:
-    maxItems: 4
     items:
       - description: Video layer, plane 0 (RGB or luma)
       - description: Video layer, plane 1 (U/V or U)
diff --git a/Documentation/devicetree/bindings/dma/dma-common.yaml b/Documentation/devicetree/bindings/dma/dma-common.yaml
index 307b499e8968..ad06d36af208 100644
--- a/Documentation/devicetree/bindings/dma/dma-common.yaml
+++ b/Documentation/devicetree/bindings/dma/dma-common.yaml
@@ -38,12 +38,12 @@ properties:
       maxItems: 255
 
   dma-channels:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description:
       Number of DMA channels supported by the controller.
 
   dma-requests:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description:
       Number of DMA request signals supported by the controller.
 
diff --git a/Documentation/devicetree/bindings/dma/dma-router.yaml b/Documentation/devicetree/bindings/dma/dma-router.yaml
index 4cee5667b8a8..e72748496fd9 100644
--- a/Documentation/devicetree/bindings/dma/dma-router.yaml
+++ b/Documentation/devicetree/bindings/dma/dma-router.yaml
@@ -23,7 +23,7 @@ properties:
     pattern: "^dma-router(@.*)?$"
 
   dma-masters:
-    $ref: /schemas/types.yaml#definitions/phandle-array
+    $ref: /schemas/types.yaml#/definitions/phandle-array
     description:
       Array of phandles to the DMA controllers the router can direct
       the signal to.
diff --git a/Documentation/devicetree/bindings/dma/ingenic,dma.yaml b/Documentation/devicetree/bindings/dma/ingenic,dma.yaml
index 00f19b3cac31..6a2043721b95 100644
--- a/Documentation/devicetree/bindings/dma/ingenic,dma.yaml
+++ b/Documentation/devicetree/bindings/dma/ingenic,dma.yaml
@@ -48,7 +48,7 @@ properties:
         ingenic,reserved-channels property.
 
   ingenic,reserved-channels:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: >
       Bitmask of channels to reserve for devices that need a specific
       channel. These channels will only be assigned when explicitely
diff --git a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml
index b548e4723936..c07eb6f2fc8d 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml
+++ b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.yaml
@@ -73,7 +73,6 @@ properties:
     maxItems: 1
 
   clock-names:
-    maxItems: 1
     items:
       - const: fck
 
diff --git a/Documentation/devicetree/bindings/dma/snps,dma-spear1340.yaml b/Documentation/devicetree/bindings/dma/snps,dma-spear1340.yaml
index ef1d6879c158..6b35089ac017 100644
--- a/Documentation/devicetree/bindings/dma/snps,dma-spear1340.yaml
+++ b/Documentation/devicetree/bindings/dma/snps,dma-spear1340.yaml
@@ -54,7 +54,7 @@ properties:
     maximum: 16
 
   dma-masters:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
       Number of DMA masters supported by the controller. In case if
       not specified the driver will try to auto-detect this and
@@ -63,7 +63,7 @@ properties:
     maximum: 4
 
   chan_allocation_order:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
       DMA channels allocation order specifier. Zero means ascending order
       (first free allocated), while one - descending (last free allocated).
@@ -71,7 +71,7 @@ properties:
     enum: [0, 1]
 
   chan_priority:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
       DMA channels priority order. Zero means ascending channels priority
       so the very first channel has the highest priority. While 1 means
@@ -80,7 +80,7 @@ properties:
     enum: [0, 1]
 
   block_size:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: Maximum block size supported by the DMA controller.
     enum: [3, 7, 15, 31, 63, 127, 255, 511, 1023, 2047, 4095]
 
@@ -139,7 +139,7 @@ properties:
         default: 256
 
   snps,dma-protection-control:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
       Bits one-to-one passed to the AHB HPROT[3:1] bus. Each bit setting
       indicates the following features: bit 0 - privileged mode,
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
index b15f68c499cb..df29d59d13a8 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
 %YAML 1.2
 ---
 $id: http://devicetree.org/schemas/dma/ti/k3-bcdma.yaml#
@@ -7,7 +9,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Texas Instruments K3 DMSS BCDMA Device Tree Bindings
 
 maintainers:
-  - Peter Ujfalusi <peter.ujfalusi@ti.com>
+  - Peter Ujfalusi <peter.ujfalusi@gmail.com>
 
 description: |
   The Block Copy DMA (BCDMA) is intended to perform similar functions as the TR
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
index b13ab60cd740..ea19d12a9337 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
 %YAML 1.2
 ---
 $id: http://devicetree.org/schemas/dma/ti/k3-pktdma.yaml#
@@ -7,7 +9,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Texas Instruments K3 DMSS PKTDMA Device Tree Bindings
 
 maintainers:
-  - Peter Ujfalusi <peter.ujfalusi@ti.com>
+  - Peter Ujfalusi <peter.ujfalusi@gmail.com>
 
 description: |
   The Packet DMA (PKTDMA) is intended to perform similar functions as the packet
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
index 9a87fd9041eb..6a09bbf83d46 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2019 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
 %YAML 1.2
 ---
 $id: http://devicetree.org/schemas/dma/ti/k3-udma.yaml#
@@ -7,7 +9,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Texas Instruments K3 NAVSS Unified DMA Device Tree Bindings
 
 maintainers:
-  - Peter Ujfalusi <peter.ujfalusi@ti.com>
+  - Peter Ujfalusi <peter.ujfalusi@gmail.com>
 
 description: |
   The UDMA-P is intended to perform similar (but significantly upgraded)
diff --git a/Documentation/devicetree/bindings/eeprom/at24.yaml b/Documentation/devicetree/bindings/eeprom/at24.yaml
index 6edfa705b486..d5117c638b75 100644
--- a/Documentation/devicetree/bindings/eeprom/at24.yaml
+++ b/Documentation/devicetree/bindings/eeprom/at24.yaml
@@ -131,7 +131,7 @@ properties:
     default: 1
 
   read-only:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Disables writes to the eeprom.
 
@@ -141,7 +141,7 @@ properties:
       Total eeprom size in bytes.
 
   no-read-rollover:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Indicates that the multi-address eeprom does not automatically roll
       over reads to the next slave address. Please consult the manual of
diff --git a/Documentation/devicetree/bindings/eeprom/at25.yaml b/Documentation/devicetree/bindings/eeprom/at25.yaml
index 744973637678..121a601db22e 100644
--- a/Documentation/devicetree/bindings/eeprom/at25.yaml
+++ b/Documentation/devicetree/bindings/eeprom/at25.yaml
@@ -45,13 +45,13 @@ properties:
   spi-max-frequency: true
 
   pagesize:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     enum: [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192, 16384, 32768, 65536, 131072]
     description:
       Size of the eeprom page.
 
   size:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description:
       Total eeprom size in bytes.
 
diff --git a/Documentation/devicetree/bindings/hwmon/moortec,mr75203.yaml b/Documentation/devicetree/bindings/hwmon/moortec,mr75203.yaml
index 6f3e3c01f717..b79f069a04c2 100644
--- a/Documentation/devicetree/bindings/hwmon/moortec,mr75203.yaml
+++ b/Documentation/devicetree/bindings/hwmon/moortec,mr75203.yaml
@@ -32,7 +32,7 @@ properties:
       PVT controller has 5 VM (voltage monitor) sensors.
       vm-map defines CPU core to VM instance mapping. A
       value of 0xff means that VM sensor is unused.
-    $ref: /schemas/types.yaml#definitions/uint8-array
+    $ref: /schemas/types.yaml#/definitions/uint8-array
     maxItems: 5
 
   clocks:
diff --git a/Documentation/devicetree/bindings/hwmon/sensirion,shtc1.yaml b/Documentation/devicetree/bindings/hwmon/sensirion,shtc1.yaml
index c523a1beb2b7..7d49478d9668 100644
--- a/Documentation/devicetree/bindings/hwmon/sensirion,shtc1.yaml
+++ b/Documentation/devicetree/bindings/hwmon/sensirion,shtc1.yaml
@@ -29,12 +29,12 @@ properties:
     const: 0x70
 
   sensirion,blocking-io:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       If set, the driver hold the i2c bus until measurement is finished.
 
   sensirion,low-precision:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       If set, the sensor aquire data with low precision (not recommended).
       The driver aquire data with high precision by default.
diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp513.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp513.yaml
index c17e5d3ee3f1..8020d739a078 100644
--- a/Documentation/devicetree/bindings/hwmon/ti,tmp513.yaml
+++ b/Documentation/devicetree/bindings/hwmon/ti,tmp513.yaml
@@ -61,7 +61,7 @@ properties:
       Array of three(TMP513) or two(TMP512) n-Factor value for each remote
       temperature channel.
       See datasheet Table 11 for n-Factor range list and value interpretation.
-    $ref: /schemas/types.yaml#definitions/uint32-array
+    $ref: /schemas/types.yaml#/definitions/uint32-array
     minItems: 2
     maxItems: 3
     items:
diff --git a/Documentation/devicetree/bindings/iio/adc/lltc,ltc2496.yaml b/Documentation/devicetree/bindings/iio/adc/lltc,ltc2496.yaml
index 6a991e9f78e2..2716d4e95329 100644
--- a/Documentation/devicetree/bindings/iio/adc/lltc,ltc2496.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/lltc,ltc2496.yaml
@@ -17,8 +17,7 @@ properties:
       - lltc,ltc2496
 
   vref-supply:
-    description: phandle to an external regulator providing the reference voltage
-    $ref: /schemas/types.yaml#/definitions/phandle
+    description: Power supply for the reference voltage
 
   reg:
     description: spi chipselect number according to the usual spi bindings
diff --git a/Documentation/devicetree/bindings/iio/humidity/ti,hdc2010.yaml b/Documentation/devicetree/bindings/iio/humidity/ti,hdc2010.yaml
index 7037f82ec753..88384b69f917 100644
--- a/Documentation/devicetree/bindings/iio/humidity/ti,hdc2010.yaml
+++ b/Documentation/devicetree/bindings/iio/humidity/ti,hdc2010.yaml
@@ -22,8 +22,7 @@ properties:
       - ti,hdc2010
       - ti,hdc2080
 
-  vdd-supply:
-    maxItems: 1
+  vdd-supply: true
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/iio/light/upisemi,us5182.yaml b/Documentation/devicetree/bindings/iio/light/upisemi,us5182.yaml
index 4a9b2827cf7b..de5882cb3360 100644
--- a/Documentation/devicetree/bindings/iio/light/upisemi,us5182.yaml
+++ b/Documentation/devicetree/bindings/iio/light/upisemi,us5182.yaml
@@ -45,7 +45,7 @@ properties:
     default: 0x16
 
   upisemi,continuous:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description: |
       This chip has two power modes: one-shot (chip takes one measurement and
       then shuts itself down) and continuous (chip takes continuous
diff --git a/Documentation/devicetree/bindings/iio/proximity/semtech,sx9310.yaml b/Documentation/devicetree/bindings/iio/proximity/semtech,sx9310.yaml
index ccfb163f3d34..5de0bb2180e6 100644
--- a/Documentation/devicetree/bindings/iio/proximity/semtech,sx9310.yaml
+++ b/Documentation/devicetree/bindings/iio/proximity/semtech,sx9310.yaml
@@ -72,7 +72,7 @@ properties:
       - finest
 
   semtech,startup-sensor:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     enum: [0, 1, 2, 3]
     default: 0
     description:
@@ -81,7 +81,7 @@ properties:
       compensation.
 
   semtech,proxraw-strength:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     enum: [0, 2, 4, 8]
     default: 2
     description:
@@ -89,7 +89,7 @@ properties:
       represent 1-1/N.
 
   semtech,avg-pos-strength:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     enum: [0, 16, 64, 128, 256, 512, 1024, 4294967295]
     default: 16
     description:
diff --git a/Documentation/devicetree/bindings/input/fsl,mpr121-touchkey.yaml b/Documentation/devicetree/bindings/input/fsl,mpr121-touchkey.yaml
index 378a85c09d34..878464f128dc 100644
--- a/Documentation/devicetree/bindings/input/fsl,mpr121-touchkey.yaml
+++ b/Documentation/devicetree/bindings/input/fsl,mpr121-touchkey.yaml
@@ -31,8 +31,7 @@ properties:
   interrupts:
     maxItems: 1
 
-  vdd-supply:
-    maxItems: 1
+  vdd-supply: true
 
   linux,keycodes:
     minItems: 1
diff --git a/Documentation/devicetree/bindings/input/gpio-keys.yaml b/Documentation/devicetree/bindings/input/gpio-keys.yaml
index 6966ab009fa3..060a309ff8e7 100644
--- a/Documentation/devicetree/bindings/input/gpio-keys.yaml
+++ b/Documentation/devicetree/bindings/input/gpio-keys.yaml
@@ -34,13 +34,13 @@ patternProperties:
 
         linux,code:
           description: Key / Axis code to emit.
-          $ref: /schemas/types.yaml#definitions/uint32
+          $ref: /schemas/types.yaml#/definitions/uint32
 
         linux,input-type:
           description:
             Specify event type this button/key generates. If not specified defaults to
             <1> == EV_KEY.
-          $ref: /schemas/types.yaml#definitions/uint32
+          $ref: /schemas/types.yaml#/definitions/uint32
 
           default: 1
 
@@ -56,12 +56,12 @@ patternProperties:
 
             linux,input-value = <0xffffffff>; /* -1 */
 
-          $ref: /schemas/types.yaml#definitions/uint32
+          $ref: /schemas/types.yaml#/definitions/uint32
 
         debounce-interval:
           description:
             Debouncing interval time in milliseconds. If not specified defaults to 5.
-          $ref: /schemas/types.yaml#definitions/uint32
+          $ref: /schemas/types.yaml#/definitions/uint32
 
           default: 5
 
@@ -79,7 +79,7 @@ patternProperties:
               EV_ACT_ANY        - both asserted and deasserted
               EV_ACT_ASSERTED   - asserted
               EV_ACT_DEASSERTED - deasserted
-          $ref: /schemas/types.yaml#definitions/uint32
+          $ref: /schemas/types.yaml#/definitions/uint32
           enum: [0, 1, 2]
 
         linux,can-disable:
@@ -118,7 +118,7 @@ then:
     poll-interval:
       description:
         Poll interval time in milliseconds
-      $ref: /schemas/types.yaml#definitions/uint32
+      $ref: /schemas/types.yaml#/definitions/uint32
 
   required:
     - poll-interval
diff --git a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
index 4ce109476a0e..bfc3a8b5e118 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
@@ -55,8 +55,7 @@ properties:
 
   wakeup-source: true
 
-  vcc-supply:
-    maxItems: 1
+  vcc-supply: true
 
   gain:
     description: Allows setting the sensitivity in the range from 0 to 31.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mti,gic.yaml b/Documentation/devicetree/bindings/interrupt-controller/mti,gic.yaml
index 039e08af98bb..91bb3c2307a7 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/mti,gic.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/mti,gic.yaml
@@ -42,7 +42,7 @@ properties:
       Specifies the list of CPU interrupt vectors to which the GIC may not
       route interrupts. This property is ignored if the CPU is started in EIC
       mode.
-    $ref: /schemas/types.yaml#definitions/uint32-array
+    $ref: /schemas/types.yaml#/definitions/uint32-array
     minItems: 1
     maxItems: 6
     uniqueItems: true
@@ -56,7 +56,7 @@ properties:
       It accepts two values: the 1st is the starting interrupt and the 2nd is
       the size of the reserved range. If not specified, the driver will
       allocate the last (2 * number of VPEs in the system).
-    $ref: /schemas/types.yaml#definitions/uint32-array
+    $ref: /schemas/types.yaml#/definitions/uint32-array
     items:
       - minimum: 0
         maximum: 254
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,pruss-intc.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,pruss-intc.yaml
index 1c4c009dedd0..c2ce215501a5 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,pruss-intc.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,pruss-intc.yaml
@@ -80,7 +80,7 @@ properties:
       mapping is provided.
 
   ti,irqs-reserved:
-    $ref: /schemas/types.yaml#definitions/uint8
+    $ref: /schemas/types.yaml#/definitions/uint8
     description: |
       Bitmask of host interrupts between 0 and 7 (corresponding to PRUSS INTC
       output interrupts 2 through 9) that are not connected to the Arm interrupt
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
index b5af12011499..3d89668573e8 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
@@ -76,7 +76,7 @@ properties:
             "limit" specifies the limit for translation
 
   ti,unmapped-event-sources:
-    $ref: /schemas/types.yaml#definitions/phandle-array
+    $ref: /schemas/types.yaml#/definitions/phandle-array
     description:
       Array of phandles to DMA controllers where the unmapped events originate.
 
diff --git a/Documentation/devicetree/bindings/leds/backlight/common.yaml b/Documentation/devicetree/bindings/leds/backlight/common.yaml
index bc817f77d2b1..702ba350d869 100644
--- a/Documentation/devicetree/bindings/leds/backlight/common.yaml
+++ b/Documentation/devicetree/bindings/leds/backlight/common.yaml
@@ -22,7 +22,7 @@ properties:
       The default brightness that should be applied to the LED by the operating
       system on start-up. The brightness should not exceed the brightness the
       LED can provide.
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
 
   max-brightness:
     description:
@@ -31,6 +31,6 @@ properties:
       on the brightness apart from what the driver says, as it could happen
       that a LED can be made so bright that it gets damaged or causes damage
       due to restrictions in a specific system, such as mounting conditions.
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
 
 additionalProperties: true
diff --git a/Documentation/devicetree/bindings/leds/common.yaml b/Documentation/devicetree/bindings/leds/common.yaml
index f1211e7045f1..b1f363747a62 100644
--- a/Documentation/devicetree/bindings/leds/common.yaml
+++ b/Documentation/devicetree/bindings/leds/common.yaml
@@ -27,21 +27,21 @@ properties:
       List of device current outputs the LED is connected to. The outputs are
       identified by the numbers that must be defined in the LED device binding
       documentation.
-    $ref: /schemas/types.yaml#definitions/uint32-array
+    $ref: /schemas/types.yaml#/definitions/uint32-array
 
   function:
     description:
       LED function. Use one of the LED_FUNCTION_* prefixed definitions
       from the header include/dt-bindings/leds/common.h. If there is no
       matching LED_FUNCTION available, add a new one.
-    $ref: /schemas/types.yaml#definitions/string
+    $ref: /schemas/types.yaml#/definitions/string
 
   color:
     description:
       Color of the LED. Use one of the LED_COLOR_ID_* prefixed definitions from
       the header include/dt-bindings/leds/common.h. If there is no matching
       LED_COLOR_ID available, add a new one.
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     minimum: 0
     maximum: 9
 
@@ -49,7 +49,7 @@ properties:
     description:
       Integer to be used when more than one instance of the same function is
       needed, differing only with an ordinal number.
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
 
   label:
     description:
@@ -66,7 +66,7 @@ properties:
       produced where the LED momentarily turns off (or on). The "keep" setting
       will keep the LED at whatever its current state is, without producing a
       glitch.
-    $ref: /schemas/types.yaml#definitions/string
+    $ref: /schemas/types.yaml#/definitions/string
     enum:
       - on
       - off
@@ -77,7 +77,7 @@ properties:
     description:
       This parameter, if present, is a string defining the trigger assigned to
       the LED.
-    $ref: /schemas/types.yaml#definitions/string
+    $ref: /schemas/types.yaml#/definitions/string
 
     enum:
         # LED will act as a back-light, controlled by the framebuffer system
@@ -109,7 +109,7 @@ properties:
           brightness and duration (in ms).  The exact format is
           described in:
           Documentation/devicetree/bindings/leds/leds-trigger-pattern.txt
-    $ref: /schemas/types.yaml#definitions/uint32-matrix
+    $ref: /schemas/types.yaml#/definitions/uint32-matrix
     items:
       minItems: 2
       maxItems: 2
@@ -143,7 +143,7 @@ properties:
       the device tree and be referenced by a phandle and a set of phandle
       arguments. A length of arguments should be specified by the
       #trigger-source-cells property in the source node.
-    $ref: /schemas/types.yaml#definitions/phandle-array
+    $ref: /schemas/types.yaml#/definitions/phandle-array
 
   # Required properties for flash LED child nodes:
   flash-max-microamp:
diff --git a/Documentation/devicetree/bindings/leds/leds-lp55xx.yaml b/Documentation/devicetree/bindings/leds/leds-lp55xx.yaml
index 58e974793a79..f552cd143d5b 100644
--- a/Documentation/devicetree/bindings/leds/leds-lp55xx.yaml
+++ b/Documentation/devicetree/bindings/leds/leds-lp55xx.yaml
@@ -35,7 +35,7 @@ properties:
     description: I2C slave address
 
   clock-mode:
-    $ref: /schemas/types.yaml#definitions/uint8
+    $ref: /schemas/types.yaml#/definitions/uint8
     description: |
       Input clock mode
     enum:
@@ -49,7 +49,7 @@ properties:
       GPIO attached to the chip's enable pin
 
   pwr-sel:
-    $ref: /schemas/types.yaml#definitions/uint8
+    $ref: /schemas/types.yaml#/definitions/uint8
     description: |
       LP8501 specific property. Power selection for output channels.
     enum:
@@ -70,14 +70,14 @@ patternProperties:
     $ref: common.yaml#
     properties:
       led-cur:
-        $ref: /schemas/types.yaml#definitions/uint8
+        $ref: /schemas/types.yaml#/definitions/uint8
         description: |
           Current setting at each LED channel (mA x10, 0 if LED is not connected)
         minimum: 0
         maximum: 255
 
       max-cur:
-        $ref: /schemas/types.yaml#definitions/uint8
+        $ref: /schemas/types.yaml#/definitions/uint8
         description: Maximun current at each LED channel.
 
       reg:
@@ -97,7 +97,7 @@ patternProperties:
           - 8 # LED output D9
 
       chan-name:
-        $ref: /schemas/types.yaml#definitions/string
+        $ref: /schemas/types.yaml#/definitions/string
         description: name of channel
 
 required:
diff --git a/Documentation/devicetree/bindings/mailbox/arm,mhu.yaml b/Documentation/devicetree/bindings/mailbox/arm,mhu.yaml
index d43791a2dde7..d07eb00b97c8 100644
--- a/Documentation/devicetree/bindings/mailbox/arm,mhu.yaml
+++ b/Documentation/devicetree/bindings/mailbox/arm,mhu.yaml
@@ -61,7 +61,6 @@ properties:
       - description: low-priority non-secure
       - description: high-priority non-secure
       - description: Secure
-    maxItems: 3
 
   clocks:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/media/coda.yaml b/Documentation/devicetree/bindings/media/coda.yaml
index 7bac0057faf7..36781ee4617f 100644
--- a/Documentation/devicetree/bindings/media/coda.yaml
+++ b/Documentation/devicetree/bindings/media/coda.yaml
@@ -44,6 +44,21 @@ properties:
       - const: per
       - const: ahb
 
+  interrupts:
+    minItems: 1
+    items:
+      - description: BIT processor interrupt
+      - description: JPEG unit interrupt
+
+  interrupt-names:
+    minItems: 1
+    items:
+      - const: bit
+      - const: jpeg
+
+  power-domains:
+    maxItems: 1
+
   resets:
     maxItems: 1
 
@@ -59,6 +74,8 @@ required:
   - clocks
   - clock-names
 
+additionalProperties: false
+
 allOf:
   - if:
       properties:
@@ -68,34 +85,17 @@ allOf:
     then:
       properties:
         interrupts:
-          items:
-            - description: BIT processor interrupt
-            - description: JPEG unit interrupt
+          minItems: 2
 
         interrupt-names:
-          items:
-            - const: bit
-            - const: jpeg
+          minItems: 2
     else:
       properties:
         interrupts:
-          items:
-            - description: BIT processor interrupt
-
-  - if:
-      properties:
-        compatible:
-          contains:
-            enum:
-              - fsl,imx6dl-vpu
-              - fsl,imx6q-vpu
-    then:
-      properties:
-        power-domains:
-          $ref: /schemas/types.yaml#/definitions/phandle
-          description: phandle pointing to the PU power domain
           maxItems: 1
 
+        power-domains: false
+
 examples:
   - |
     vpu: video-codec@63ff4000 {
diff --git a/Documentation/devicetree/bindings/media/i2c/maxim,max9286.yaml b/Documentation/devicetree/bindings/media/i2c/maxim,max9286.yaml
index 9ea827092fdd..68ee8c7d9e79 100644
--- a/Documentation/devicetree/bindings/media/i2c/maxim,max9286.yaml
+++ b/Documentation/devicetree/bindings/media/i2c/maxim,max9286.yaml
@@ -40,7 +40,6 @@ properties:
 
   poc-supply:
     description: Regulator providing Power over Coax to the cameras
-    maxItems: 1
 
   enable-gpios:
     description: GPIO connected to the \#PWDN pin with inverted polarity
diff --git a/Documentation/devicetree/bindings/media/i2c/mipi-ccs.yaml b/Documentation/devicetree/bindings/media/i2c/mipi-ccs.yaml
index d94bd67ccea1..bb3528315f20 100644
--- a/Documentation/devicetree/bindings/media/i2c/mipi-ccs.yaml
+++ b/Documentation/devicetree/bindings/media/i2c/mipi-ccs.yaml
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 # Copyright (C) 2014--2020 Intel Corporation
-
+%YAML 1.2
+---
 $id: http://devicetree.org/schemas/media/i2c/mipi-ccs.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
@@ -26,11 +27,11 @@ properties:
   compatible:
     oneOf:
       - items:
-        - const: mipi-ccs-1.1
-        - const: mipi-ccs
+          - const: mipi-ccs-1.1
+          - const: mipi-ccs
       - items:
-        - const: mipi-ccs-1.0
-        - const: mipi-ccs
+          - const: mipi-ccs-1.0
+          - const: mipi-ccs
       - const: nokia,smia
 
   reg:
@@ -38,15 +39,12 @@ properties:
 
   vana-supply:
     description: Analogue voltage supply (VANA), sensor dependent.
-    maxItems: 1
 
   vcore-supply:
     description: Core voltage supply (VCore), sensor dependent.
-    maxItems: 1
 
   vio-supply:
     description: I/O voltage supply (VIO), sensor dependent.
-    maxItems: 1
 
   clocks:
     description: External clock to the sensor.
diff --git a/Documentation/devicetree/bindings/media/i2c/sony,imx214.yaml b/Documentation/devicetree/bindings/media/i2c/sony,imx214.yaml
index 1a3590dd0e98..eb12526a462f 100644
--- a/Documentation/devicetree/bindings/media/i2c/sony,imx214.yaml
+++ b/Documentation/devicetree/bindings/media/i2c/sony,imx214.yaml
@@ -37,15 +37,12 @@ properties:
 
   vdddo-supply:
     description: Chip digital IO regulator (1.8V).
-    maxItems: 1
 
   vdda-supply:
     description: Chip analog regulator (2.7V).
-    maxItems: 1
 
   vddd-supply:
     description: Chip digital core regulator (1.12V).
-    maxItems: 1
 
   flash-leds:
     description: See ../video-interfaces.txt
diff --git a/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml b/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
index f697e1a20beb..a66acb20d59b 100644
--- a/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
+++ b/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
@@ -33,15 +33,12 @@ properties:
 
   vana-supply:
     description: Sensor 2.8 V analog supply.
-    maxItems: 1
 
   vdig-supply:
     description: Sensor 1.8 V digital core supply.
-    maxItems: 1
 
   vddl-supply:
     description: Sensor digital IO 1.2 V supply.
-    maxItems: 1
 
   port:
     type: object
diff --git a/Documentation/devicetree/bindings/mfd/st,stmfx.yaml b/Documentation/devicetree/bindings/mfd/st,stmfx.yaml
index 888ab4b5df45..19e9afb385ac 100644
--- a/Documentation/devicetree/bindings/mfd/st,stmfx.yaml
+++ b/Documentation/devicetree/bindings/mfd/st,stmfx.yaml
@@ -26,8 +26,7 @@ properties:
 
   drive-open-drain: true
 
-  vdd-supply:
-    maxItems: 1
+  vdd-supply: true
 
   pinctrl:
     type: object
diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
index c7c9ad4e3f9f..7f2578d48e3f 100644
--- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
+++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
@@ -38,7 +38,7 @@ properties:
     const: stmmaceth
 
   syscon:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       Phandle to the device containing the EMAC or GMAC clock
       register
@@ -114,7 +114,7 @@ allOf:
     then:
       properties:
         allwinner,leds-active-low:
-          $ref: /schemas/types.yaml#definitions/flag
+          $ref: /schemas/types.yaml#/definitions/flag
           description:
             EPHY LEDs are active low.
 
@@ -126,7 +126,7 @@ allOf:
               const: allwinner,sun8i-h3-mdio-mux
 
             mdio-parent-bus:
-              $ref: /schemas/types.yaml#definitions/phandle
+              $ref: /schemas/types.yaml#/definitions/phandle
               description:
                 Phandle to EMAC MDIO.
 
diff --git a/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml b/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
index 6b057b117aa0..1f133f4a2924 100644
--- a/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
@@ -60,7 +60,7 @@ allOf:
             - const: timing-adjustment
 
         amlogic,tx-delay-ns:
-          $ref: /schemas/types.yaml#definitions/uint32
+          $ref: /schemas/types.yaml#/definitions/uint32
           description:
             The internal RGMII TX clock delay (provided by this driver) in
             nanoseconds. Allowed values are 0ns, 2ns, 4ns, 6ns.
diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.yaml b/Documentation/devicetree/bindings/net/dsa/dsa.yaml
index 8e044631bcf7..8a3494db4d8d 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.yaml
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.yaml
@@ -54,7 +54,7 @@ patternProperties:
             description:
               Describes the label associated with this port, which will become
               the netdev name
-            $ref: /schemas/types.yaml#definitions/string
+            $ref: /schemas/types.yaml#/definitions/string
 
           link:
             description:
@@ -62,13 +62,13 @@ patternProperties:
               port is used as the outgoing port towards the phandle ports. The
               full routing information must be given, not just the one hop
               routes to neighbouring switches
-            $ref: /schemas/types.yaml#definitions/phandle-array
+            $ref: /schemas/types.yaml#/definitions/phandle-array
 
           ethernet:
             description:
               Should be a phandle to a valid Ethernet device node.  This host
               device is what the switch port is connected to
-            $ref: /schemas/types.yaml#definitions/phandle
+            $ref: /schemas/types.yaml#/definitions/phandle
 
           phy-handle: true
 
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index cc93063a8f39..0965f6515f9e 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -16,7 +16,7 @@ properties:
   local-mac-address:
     description:
       Specifies the MAC address that was assigned to the network device.
-    $ref: /schemas/types.yaml#definitions/uint8-array
+    $ref: /schemas/types.yaml#/definitions/uint8-array
     items:
       - minItems: 6
         maxItems: 6
@@ -27,20 +27,20 @@ properties:
       program; should be used in cases where the MAC address assigned
       to the device by the boot program is different from the
       local-mac-address property.
-    $ref: /schemas/types.yaml#definitions/uint8-array
+    $ref: /schemas/types.yaml#/definitions/uint8-array
     items:
       - minItems: 6
         maxItems: 6
 
   max-frame-size:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description:
       Maximum transfer unit (IEEE defined MTU), rather than the
       maximum frame size (there\'s contradiction in the Devicetree
       Specification).
 
   max-speed:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description:
       Specifies maximum speed in Mbit/s supported by the device.
 
@@ -101,7 +101,7 @@ properties:
     $ref: "#/properties/phy-connection-type"
 
   phy-handle:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       Specifies a reference to a node representing a PHY device.
 
@@ -114,7 +114,7 @@ properties:
     deprecated: true
 
   rx-fifo-depth:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description:
       The size of the controller\'s receive fifo in bytes. This is used
       for components that can have configurable receive fifo sizes,
@@ -129,12 +129,12 @@ properties:
       If this property is present then the MAC applies the RX delay.
 
   sfp:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       Specifies a reference to a node representing a SFP cage.
 
   tx-fifo-depth:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description:
       The size of the controller\'s transmit fifo in bytes. This
       is used for components that can have configurable fifo sizes.
@@ -150,7 +150,7 @@ properties:
     description:
       Specifies the PHY management type. If auto is set and fixed-link
       is not specified, it uses MDIO for management.
-    $ref: /schemas/types.yaml#definitions/string
+    $ref: /schemas/types.yaml#/definitions/string
     default: auto
     enum:
       - auto
@@ -198,17 +198,17 @@ properties:
             speed:
               description:
                 Link speed.
-              $ref: /schemas/types.yaml#definitions/uint32
+              $ref: /schemas/types.yaml#/definitions/uint32
               enum: [10, 100, 1000]
 
             full-duplex:
-              $ref: /schemas/types.yaml#definitions/flag
+              $ref: /schemas/types.yaml#/definitions/flag
               description:
                 Indicates that full-duplex is used. When absent, half
                 duplex is assumed.
 
             asym-pause:
-              $ref: /schemas/types.yaml#definitions/flag
+              $ref: /schemas/types.yaml#/definitions/flag
               description:
                 Indicates that asym_pause should be enabled.
 
diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
index 6dd72faebd89..2766fe45bb98 100644
--- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
@@ -78,57 +78,57 @@ properties:
       Maximum PHY supported speed in Mbits / seconds.
 
   broken-turn-around:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       If set, indicates the PHY device does not correctly release
       the turn around line low at end of the control phase of the
       MDIO transaction.
 
   enet-phy-lane-swap:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       If set, indicates the PHY will swap the TX/RX lanes to
       compensate for the board being designed with the lanes
       swapped.
 
   eee-broken-100tx:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Mark the corresponding energy efficient ethernet mode as
       broken and request the ethernet to stop advertising it.
 
   eee-broken-1000t:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Mark the corresponding energy efficient ethernet mode as
       broken and request the ethernet to stop advertising it.
 
   eee-broken-10gt:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Mark the corresponding energy efficient ethernet mode as
       broken and request the ethernet to stop advertising it.
 
   eee-broken-1000kx:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Mark the corresponding energy efficient ethernet mode as
       broken and request the ethernet to stop advertising it.
 
   eee-broken-10gkx4:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Mark the corresponding energy efficient ethernet mode as
       broken and request the ethernet to stop advertising it.
 
   eee-broken-10gkr:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Mark the corresponding energy efficient ethernet mode as
       broken and request the ethernet to stop advertising it.
 
   phy-is-integrated:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       If set, indicates that the PHY is integrated into the same
       physical package as the Ethernet MAC. If needed, muxers
@@ -158,7 +158,7 @@ properties:
       this property is missing the delay will be skipped.
 
   sfp:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       Specifies a reference to a node representing a SFP cage.
 
diff --git a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml
index 2159b7d1f537..7f620a71a972 100644
--- a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml
+++ b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml
@@ -31,7 +31,7 @@ properties:
   phy-mode: true
 
   pcs-handle:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       A reference to a node representing a PCS PHY device found on
       the internal MDIO bus.
diff --git a/Documentation/devicetree/bindings/net/mdio.yaml b/Documentation/devicetree/bindings/net/mdio.yaml
index e811e0fd851c..08e15fb1584f 100644
--- a/Documentation/devicetree/bindings/net/mdio.yaml
+++ b/Documentation/devicetree/bindings/net/mdio.yaml
@@ -70,7 +70,7 @@ patternProperties:
           The ID number for the device.
 
       broken-turn-around:
-        $ref: /schemas/types.yaml#definitions/flag
+        $ref: /schemas/types.yaml#/definitions/flag
         description:
           If set, indicates the MDIO device does not correctly release
           the turn around line low at end of the control phase of the
diff --git a/Documentation/devicetree/bindings/net/mediatek,star-emac.yaml b/Documentation/devicetree/bindings/net/mediatek,star-emac.yaml
index 0bbd598704e9..e6a5ff208253 100644
--- a/Documentation/devicetree/bindings/net/mediatek,star-emac.yaml
+++ b/Documentation/devicetree/bindings/net/mediatek,star-emac.yaml
@@ -42,7 +42,7 @@ properties:
       - const: trans
 
   mediatek,pericfg:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       Phandle to the device containing the PERICFG register range. This is used
       to control the MII mode.
diff --git a/Documentation/devicetree/bindings/net/qcom,ipa.yaml b/Documentation/devicetree/bindings/net/qcom,ipa.yaml
index 4d8464b2676d..8a2d12644675 100644
--- a/Documentation/devicetree/bindings/net/qcom,ipa.yaml
+++ b/Documentation/devicetree/bindings/net/qcom,ipa.yaml
@@ -114,14 +114,13 @@ properties:
       validating firwmare used by the GSI.
 
   modem-remoteproc:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       This defines the phandle to the remoteproc node representing
       the modem subsystem.  This is requied so the IPA driver can
       receive and act on notifications of modem up/down events.
 
   memory-region:
-    $ref: /schemas/types.yaml#/definitions/phandle-array
     maxItems: 1
     description:
       If present, a phandle for a reserved memory area that holds
diff --git a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml
index 244befb6402a..de9dd574a2f9 100644
--- a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml
+++ b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml
@@ -163,6 +163,7 @@ allOf:
             enum:
               - renesas,etheravb-r8a774a1
               - renesas,etheravb-r8a774b1
+              - renesas,etheravb-r8a774e1
               - renesas,etheravb-r8a7795
               - renesas,etheravb-r8a7796
               - renesas,etheravb-r8a77961
diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
index 11a6fdb657c9..dfbf5fe4547a 100644
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@@ -126,7 +126,7 @@ properties:
       in a different mode than the PHY in order to function.
 
   snps,axi-config:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       AXI BUS Mode parameters. Phandle to a node that can contain the
       following properties
@@ -141,7 +141,7 @@ properties:
         * snps,rb, rebuild INCRx Burst
 
   snps,mtl-rx-config:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       Multiple RX Queues parameters. Phandle to a node that can
       contain the following properties
@@ -161,10 +161,11 @@ properties:
             * snps,route-dcbcp, DCB Control Packets
             * snps,route-up, Untagged Packets
             * snps,route-multi-broad, Multicast & Broadcast Packets
-          * snps,priority, RX queue priority (Range 0x0 to 0xF)
+          * snps,priority, bitmask of the tagged frames priorities assigned to
+            the queue
 
   snps,mtl-tx-config:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       Multiple TX Queues parameters. Phandle to a node that can
       contain the following properties
@@ -188,7 +189,10 @@ properties:
             * snps,idle_slope, unlock on WoL
             * snps,high_credit, max write outstanding req. limit
             * snps,low_credit, max read outstanding req. limit
-          * snps,priority, TX queue priority (Range 0x0 to 0xF)
+          * snps,priority, bitmask of the priorities assigned to the queue.
+            When a PFC frame is received with priorities matching the bitmask,
+            the queue is blocked from transmitting for the pause time specified
+            in the PFC frame.
 
   snps,reset-gpio:
     deprecated: true
@@ -198,7 +202,7 @@ properties:
 
   snps,reset-active-low:
     deprecated: true
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Indicates that the PHY Reset is active low
 
@@ -208,55 +212,55 @@ properties:
       Triplet of delays. The 1st cell is reset pre-delay in micro
       seconds. The 2nd cell is reset pulse in micro seconds. The 3rd
       cell is reset post-delay in micro seconds.
-    $ref: /schemas/types.yaml#definitions/uint32-array
+    $ref: /schemas/types.yaml#/definitions/uint32-array
     minItems: 3
     maxItems: 3
 
   snps,aal:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Use Address-Aligned Beats
 
   snps,fixed-burst:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Program the DMA to use the fixed burst mode
 
   snps,mixed-burst:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Program the DMA to use the mixed burst mode
 
   snps,force_thresh_dma_mode:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Force DMA to use the threshold mode for both tx and rx
 
   snps,force_sf_dma_mode:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Force DMA to use the Store and Forward mode for both tx and
       rx. This flag is ignored if force_thresh_dma_mode is set.
 
   snps,en-tx-lpi-clockgating:
-    $ref: /schemas/types.yaml#definitions/flag
+    $ref: /schemas/types.yaml#/definitions/flag
     description:
       Enable gating of the MAC TX clock during TX low-power mode
 
   snps,multicast-filter-bins:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description:
       Number of multicast filter hash bins supported by this device
       instance
 
   snps,perfect-filter-entries:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description:
       Number of perfect filter entries supported by this device
       instance
 
   snps,ps-speed:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description:
       Port selection speed that can be passed to the core when PCS
       is supported. For example, this is used in case of SGMII and
@@ -307,25 +311,25 @@ allOf:
         snps,pbl:
           description:
             Programmable Burst Length (tx and rx)
-          $ref: /schemas/types.yaml#definitions/uint32
+          $ref: /schemas/types.yaml#/definitions/uint32
           enum: [2, 4, 8]
 
         snps,txpbl:
           description:
             Tx Programmable Burst Length. If set, DMA tx will use this
             value rather than snps,pbl.
-          $ref: /schemas/types.yaml#definitions/uint32
+          $ref: /schemas/types.yaml#/definitions/uint32
           enum: [2, 4, 8]
 
         snps,rxpbl:
           description:
             Rx Programmable Burst Length. If set, DMA rx will use this
             value rather than snps,pbl.
-          $ref: /schemas/types.yaml#definitions/uint32
+          $ref: /schemas/types.yaml#/definitions/uint32
           enum: [2, 4, 8]
 
         snps,no-pbl-x8:
-          $ref: /schemas/types.yaml#definitions/flag
+          $ref: /schemas/types.yaml#/definitions/flag
           description:
             Don\'t multiply the pbl/txpbl/rxpbl values by 8. For core
             rev < 3.50, don\'t multiply the values by 4.
@@ -351,7 +355,7 @@ allOf:
     then:
       properties:
         snps,tso:
-          $ref: /schemas/types.yaml#definitions/flag
+          $ref: /schemas/types.yaml#/definitions/flag
           description:
             Enables the TSO feature otherwise it will be managed by
             MAC HW capability register.
diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml
index cbacc04fc9e6..8a03a24a2019 100644
--- a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml
+++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml
@@ -64,7 +64,7 @@ properties:
       - const: ether    # for others
 
   socionext,syscon-phy-mode:
-    $ref: /schemas/types.yaml#definitions/phandle-array
+    $ref: /schemas/types.yaml#/definitions/phandle-array
     description:
       A phandle to syscon with one argument that configures phy mode.
       The argument is the ID of MAC instance.
diff --git a/Documentation/devicetree/bindings/net/ti,cpsw-switch.yaml b/Documentation/devicetree/bindings/net/ti,cpsw-switch.yaml
index dadeb8f811c0..07a00f53adbf 100644
--- a/Documentation/devicetree/bindings/net/ti,cpsw-switch.yaml
+++ b/Documentation/devicetree/bindings/net/ti,cpsw-switch.yaml
@@ -70,7 +70,7 @@ properties:
   pinctrl-names: true
 
   syscon:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       Phandle to the system control device node which provides access to
       efuse IO range with MAC addresses
diff --git a/Documentation/devicetree/bindings/net/ti,dp83867.yaml b/Documentation/devicetree/bindings/net/ti,dp83867.yaml
index 4050a3608658..047d757e8d82 100644
--- a/Documentation/devicetree/bindings/net/ti,dp83867.yaml
+++ b/Documentation/devicetree/bindings/net/ti,dp83867.yaml
@@ -47,31 +47,31 @@ properties:
         takes precedence.
 
   tx-fifo-depth:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
        Transmitt FIFO depth see dt-bindings/net/ti-dp83867.h for values
 
   rx-fifo-depth:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
        Receive FIFO depth see dt-bindings/net/ti-dp83867.h for values
 
   ti,clk-output-sel:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
       Muxing option for CLK_OUT pin.  See dt-bindings/net/ti-dp83867.h
       for applicable values. The CLK_OUT pin can also be disabled by this
       property.  When omitted, the PHY's default will be left as is.
 
   ti,rx-internal-delay:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
       RGMII Receive Clock Delay - see dt-bindings/net/ti-dp83867.h
       for applicable values. Required only if interface type is
       PHY_INTERFACE_MODE_RGMII_ID or PHY_INTERFACE_MODE_RGMII_RXID.
 
   ti,tx-internal-delay:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
       RGMII Transmit Clock Delay - see dt-bindings/net/ti-dp83867.h
       for applicable values. Required only if interface type is
@@ -101,7 +101,7 @@ properties:
 
   ti,fifo-depth:
     deprecated: true
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
       Transmitt FIFO depth- see dt-bindings/net/ti-dp83867.h for applicable
       values.
diff --git a/Documentation/devicetree/bindings/net/ti,dp83869.yaml b/Documentation/devicetree/bindings/net/ti,dp83869.yaml
index c3235f08e326..70a1209cb13b 100644
--- a/Documentation/devicetree/bindings/net/ti,dp83869.yaml
+++ b/Documentation/devicetree/bindings/net/ti,dp83869.yaml
@@ -44,22 +44,22 @@ properties:
        to a maximum value (70 ohms).
 
   tx-fifo-depth:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
        Transmitt FIFO depth see dt-bindings/net/ti-dp83869.h for values
 
   rx-fifo-depth:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
        Receive FIFO depth see dt-bindings/net/ti-dp83869.h for values
 
   ti,clk-output-sel:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
        Muxing option for CLK_OUT pin see dt-bindings/net/ti-dp83869.h for values.
 
   ti,op-mode:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
        Operational mode for the PHY.  If this is not set then the operational
        mode is set by the straps. see dt-bindings/net/ti-dp83869.h for values
diff --git a/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml b/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml
index 227270cbf892..c47b58f3e3f6 100644
--- a/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml
+++ b/Documentation/devicetree/bindings/net/ti,k3-am654-cpsw-nuss.yaml
@@ -119,12 +119,12 @@ properties:
             description: label associated with this port
 
           ti,mac-only:
-            $ref: /schemas/types.yaml#definitions/flag
+            $ref: /schemas/types.yaml#/definitions/flag
             description:
               Specifies the port works in mac-only mode.
 
           ti,syscon-efuse:
-            $ref: /schemas/types.yaml#definitions/phandle-array
+            $ref: /schemas/types.yaml#/definitions/phandle-array
             description:
               Phandle to the system control device node which provides access
               to efuse IO range with MAC addresses
diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
index 6af999191559..85c2f699d602 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
@@ -136,7 +136,7 @@ properties:
       - const: tcl2host-status-ring
 
   qcom,rproc:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       DT entry of q6v5-wcss remoteproc driver.
       Phandle to a node that can contain the following properties
diff --git a/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml b/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml
index 83d5d0aceb04..cbbf5e8b1197 100644
--- a/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml
+++ b/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml
@@ -44,13 +44,13 @@ properties:
       - const: refclk
 
   syscon-phy-power:
-    $ref: /schemas/types.yaml#definitions/phandle-array
+    $ref: /schemas/types.yaml#/definitions/phandle-array
     description:
       phandle/offset pair. Phandle to the system control module and
       register offset to power on/off the PHY.
 
   ctrl-module:
-    $ref: /schemas/types.yaml#definitions/phandle
+    $ref: /schemas/types.yaml#/definitions/phandle
     description:
       (deprecated) phandle of the control module used by PHY driver
       to power on the PHY. Use syscon-phy-power instead.
diff --git a/Documentation/devicetree/bindings/power/mediatek,power-controller.yaml b/Documentation/devicetree/bindings/power/mediatek,power-controller.yaml
index fd12bafe3548..d14cb9bac849 100644
--- a/Documentation/devicetree/bindings/power/mediatek,power-controller.yaml
+++ b/Documentation/devicetree/bindings/power/mediatek,power-controller.yaml
@@ -83,11 +83,11 @@ patternProperties:
           SUSBSYS clocks.
 
       mediatek,infracfg:
-        $ref: /schemas/types.yaml#definitions/phandle
+        $ref: /schemas/types.yaml#/definitions/phandle
         description: phandle to the device containing the INFRACFG register range.
 
       mediatek,smi:
-        $ref: /schemas/types.yaml#definitions/phandle
+        $ref: /schemas/types.yaml#/definitions/phandle
         description: phandle to the device containing the SMI register range.
 
     patternProperties:
@@ -131,11 +131,11 @@ patternProperties:
               SUSBSYS clocks.
 
           mediatek,infracfg:
-            $ref: /schemas/types.yaml#definitions/phandle
+            $ref: /schemas/types.yaml#/definitions/phandle
             description: phandle to the device containing the INFRACFG register range.
 
           mediatek,smi:
-            $ref: /schemas/types.yaml#definitions/phandle
+            $ref: /schemas/types.yaml#/definitions/phandle
             description: phandle to the device containing the SMI register range.
 
         patternProperties:
@@ -179,11 +179,11 @@ patternProperties:
                   SUSBSYS clocks.
 
               mediatek,infracfg:
-                $ref: /schemas/types.yaml#definitions/phandle
+                $ref: /schemas/types.yaml#/definitions/phandle
                 description: phandle to the device containing the INFRACFG register range.
 
               mediatek,smi:
-                $ref: /schemas/types.yaml#definitions/phandle
+                $ref: /schemas/types.yaml#/definitions/phandle
                 description: phandle to the device containing the SMI register range.
 
             required:
diff --git a/Documentation/devicetree/bindings/power/supply/cw2015_battery.yaml b/Documentation/devicetree/bindings/power/supply/cw2015_battery.yaml
index ee92e6a076ac..5fcdf5801536 100644
--- a/Documentation/devicetree/bindings/power/supply/cw2015_battery.yaml
+++ b/Documentation/devicetree/bindings/power/supply/cw2015_battery.yaml
@@ -27,7 +27,7 @@ properties:
       of this binary blob is kept secret by CellWise. The only way to obtain
       it is to mail two batteries to a test facility of CellWise and receive
       back a test report with the binary blob.
-    $ref: /schemas/types.yaml#definitions/uint8-array
+    $ref: /schemas/types.yaml#/definitions/uint8-array
     minItems: 64
     maxItems: 64
 
diff --git a/Documentation/devicetree/bindings/powerpc/sleep.yaml b/Documentation/devicetree/bindings/powerpc/sleep.yaml
index 6494c7d08b93..1b0936a5beec 100644
--- a/Documentation/devicetree/bindings/powerpc/sleep.yaml
+++ b/Documentation/devicetree/bindings/powerpc/sleep.yaml
@@ -42,6 +42,6 @@ select: true
 
 properties:
   sleep:
-    $ref: /schemas/types.yaml#definitions/phandle-array
+    $ref: /schemas/types.yaml#/definitions/phandle-array
 
 additionalProperties: true
diff --git a/Documentation/devicetree/bindings/regulator/anatop-regulator.yaml b/Documentation/devicetree/bindings/regulator/anatop-regulator.yaml
index e7b3abe30363..0a66338c7e5a 100644
--- a/Documentation/devicetree/bindings/regulator/anatop-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/anatop-regulator.yaml
@@ -59,7 +59,6 @@ properties:
     description: u32 value representing regulator enable bit offset.
 
   vin-supply:
-    $ref: '/schemas/types.yaml#/definitions/phandle'
     description: input supply phandle.
 
 required:
diff --git a/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml b/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml
index a6c259ce9785..956156fe52a3 100644
--- a/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml
@@ -19,7 +19,9 @@ description: |
 properties:
   compatible:
     enum:
-      - nxp,pf8x00
+      - nxp,pf8100
+      - nxp,pf8121a
+      - nxp,pf8200
 
   reg:
     maxItems: 1
@@ -118,7 +120,7 @@ examples:
         #size-cells = <0>;
 
         pmic@8 {
-            compatible = "nxp,pf8x00";
+            compatible = "nxp,pf8100";
             reg = <0x08>;
 
             regulators {
diff --git a/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt
index b8f0b7809c02..7d462b899473 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt
@@ -44,6 +44,7 @@ First Level Nodes - PMIC
 	Definition: Must be one of below:
 		    "qcom,pm8005-rpmh-regulators"
 		    "qcom,pm8009-rpmh-regulators"
+		    "qcom,pm8009-1-rpmh-regulators"
 		    "qcom,pm8150-rpmh-regulators"
 		    "qcom,pm8150l-rpmh-regulators"
 		    "qcom,pm8350-rpmh-regulators"
diff --git a/Documentation/devicetree/bindings/rtc/rtc.yaml b/Documentation/devicetree/bindings/rtc/rtc.yaml
index 8acd2de3de3a..d30dc045aac6 100644
--- a/Documentation/devicetree/bindings/rtc/rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/rtc.yaml
@@ -63,6 +63,11 @@ properties:
     description:
       Enables wake up of host system on alarm.
 
+  reset-source:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      The RTC is able to reset the machine.
+
 additionalProperties: true
 
 ...
diff --git a/Documentation/devicetree/bindings/serial/8250.yaml b/Documentation/devicetree/bindings/serial/8250.yaml
index c1d4c196f005..f54cae9ff7b2 100644
--- a/Documentation/devicetree/bindings/serial/8250.yaml
+++ b/Documentation/devicetree/bindings/serial/8250.yaml
@@ -126,7 +126,7 @@ properties:
     maxItems: 1
 
   current-speed:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: The current active speed of the UART.
 
   reg-offset:
@@ -154,7 +154,7 @@ properties:
       Set to indicate that the port does not implement loopback test mode.
 
   fifo-size:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: The fifo size of the UART.
 
   auto-flow-control:
@@ -165,7 +165,7 @@ properties:
       property.
 
   tx-threshold:
-    $ref: /schemas/types.yaml#definitions/uint32
+    $ref: /schemas/types.yaml#/definitions/uint32
     description: |
       Specify the TX FIFO low water indication for parts with programmable
       TX FIFO thresholds.
diff --git a/Documentation/devicetree/bindings/serial/litex,liteuart.yaml b/Documentation/devicetree/bindings/serial/litex,liteuart.yaml
index bc79b3cca542..c4f1f489dc2d 100644
--- a/Documentation/devicetree/bindings/serial/litex,liteuart.yaml
+++ b/Documentation/devicetree/bindings/serial/litex,liteuart.yaml
@@ -29,6 +29,8 @@ required:
   - compatible
   - reg
 
+additionalProperties: false
+
 examples:
   - |
     uart0: serial@e0001800 {
diff --git a/Documentation/devicetree/bindings/soc/litex/litex,soc-controller.yaml b/Documentation/devicetree/bindings/soc/litex/litex,soc-controller.yaml
index e2b788796e79..c8b57c7fd08c 100644
--- a/Documentation/devicetree/bindings/soc/litex/litex,soc-controller.yaml
+++ b/Documentation/devicetree/bindings/soc/litex/litex,soc-controller.yaml
@@ -28,6 +28,8 @@ required:
   - compatible
   - reg
 
+additionalProperties: false
+
 examples:
   - |
     soc_ctrl0: soc-controller@f0000000 {
diff --git a/Documentation/devicetree/bindings/soc/mediatek/devapc.yaml b/Documentation/devicetree/bindings/soc/mediatek/devapc.yaml
index 6c763f873a63..31e4d3c339bf 100644
--- a/Documentation/devicetree/bindings/soc/mediatek/devapc.yaml
+++ b/Documentation/devicetree/bindings/soc/mediatek/devapc.yaml
@@ -44,6 +44,8 @@ required:
   - clocks
   - clock-names
 
+additionalProperties: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
diff --git a/Documentation/devicetree/bindings/soc/ti/k3-ringacc.yaml b/Documentation/devicetree/bindings/soc/ti/k3-ringacc.yaml
index c3c595e235a8..ddea3d41971d 100644
--- a/Documentation/devicetree/bindings/soc/ti/k3-ringacc.yaml
+++ b/Documentation/devicetree/bindings/soc/ti/k3-ringacc.yaml
@@ -55,7 +55,7 @@ properties:
     description: TI-SCI RM subtype for GP ring range
 
   ti,sci:
-    $ref: /schemas/types.yaml#definitions/phandle-array
+    $ref: /schemas/types.yaml#/definitions/phandle-array
     description: phandle on TI-SCI compatible System controller node
 
   ti,sci-dev-id:
diff --git a/Documentation/devicetree/bindings/soc/xilinx/xlnx,vcu-settings.yaml b/Documentation/devicetree/bindings/soc/xilinx/xlnx,vcu-settings.yaml
index 378d0ced43c8..cb245f400287 100644
--- a/Documentation/devicetree/bindings/soc/xilinx/xlnx,vcu-settings.yaml
+++ b/Documentation/devicetree/bindings/soc/xilinx/xlnx,vcu-settings.yaml
@@ -26,9 +26,18 @@ required:
   - compatible
   - reg
 
+additionalProperties: false
+
 examples:
   - |
-    xlnx_vcu: vcu@a0041000 {
-          compatible = "xlnx,vcu-settings", "syscon";
-          reg = <0x0 0xa0041000 0x0 0x1000>;
+    fpga {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        xlnx_vcu: vcu@a0041000 {
+            compatible = "xlnx,vcu-settings", "syscon";
+            reg = <0x0 0xa0041000 0x0 0x1000>;
+        };
     };
+
+...
diff --git a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-codec.yaml b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-codec.yaml
index be390accdd07..dd47fef9854d 100644
--- a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-codec.yaml
+++ b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-codec.yaml
@@ -57,7 +57,7 @@ properties:
       A list of the connections between audio components.  Each entry
       is a pair of strings, the first being the connection's sink, the
       second being the connection's source.
-    $ref: /schemas/types.yaml#definitions/non-unique-string-array
+    $ref: /schemas/types.yaml#/definitions/non-unique-string-array
     minItems: 2
     maxItems: 18
     items:
diff --git a/Documentation/devicetree/bindings/sound/nvidia,tegra30-hda.yaml b/Documentation/devicetree/bindings/sound/nvidia,tegra30-hda.yaml
index e543a6123792..b55775e21de6 100644
--- a/Documentation/devicetree/bindings/sound/nvidia,tegra30-hda.yaml
+++ b/Documentation/devicetree/bindings/sound/nvidia,tegra30-hda.yaml
@@ -44,7 +44,6 @@ properties:
     maxItems: 3
 
   clock-names:
-    maxItems: 3
     items:
       - const: hda
       - const: hda2hdmi
@@ -54,7 +53,6 @@ properties:
     maxItems: 3
 
   reset-names:
-    maxItems: 3
     items:
       - const: hda
       - const: hda2hdmi
diff --git a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml
index 6ad48c7681c1..f2443b651282 100644
--- a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml
+++ b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml
@@ -106,7 +106,7 @@ patternProperties:
           Must contain the phandle and index of the SAI sub-block providing
           the synchronization.
         allOf:
-          - $ref: /schemas/types.yaml#definitions/phandle-array
+          - $ref: /schemas/types.yaml#/definitions/phandle-array
           - maxItems: 1
 
       st,iec60958:
@@ -117,7 +117,7 @@ patternProperties:
           configured according to protocol defined in related DAI link node,
           such as i2s, left justified, right justified, dsp and pdm protocols.
         allOf:
-          - $ref: /schemas/types.yaml#definitions/flag
+          - $ref: /schemas/types.yaml#/definitions/flag
 
       "#clock-cells":
         description: Configure the SAI device as master clock provider.
diff --git a/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml b/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml
index 805da4d6a88e..ec06789b21df 100644
--- a/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml
+++ b/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
 %YAML 1.2
 ---
 $id: http://devicetree.org/schemas/sound/ti,j721e-cpb-audio.yaml#
@@ -7,7 +9,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Texas Instruments J721e Common Processor Board Audio Support
 
 maintainers:
-  - Peter Ujfalusi <peter.ujfalusi@ti.com>
+  - Peter Ujfalusi <peter.ujfalusi@gmail.com>
 
 description: |
   The audio support on the board is using pcm3168a codec connected to McASP10
diff --git a/Documentation/devicetree/bindings/sound/ti,j721e-cpb-ivi-audio.yaml b/Documentation/devicetree/bindings/sound/ti,j721e-cpb-ivi-audio.yaml
index bb780f621628..ee9f960de36b 100644
--- a/Documentation/devicetree/bindings/sound/ti,j721e-cpb-ivi-audio.yaml
+++ b/Documentation/devicetree/bindings/sound/ti,j721e-cpb-ivi-audio.yaml
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
 %YAML 1.2
 ---
 $id: http://devicetree.org/schemas/sound/ti,j721e-cpb-ivi-audio.yaml#
@@ -7,7 +9,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Texas Instruments J721e Common Processor Board Audio Support
 
 maintainers:
-  - Peter Ujfalusi <peter.ujfalusi@ti.com>
+  - Peter Ujfalusi <peter.ujfalusi@gmail.com>
 
 description: |
   The Infotainment board plugs into the Common Processor Board, the support of the
diff --git a/Documentation/devicetree/bindings/usb/renesas,usb-xhci.yaml b/Documentation/devicetree/bindings/usb/renesas,usb-xhci.yaml
index 0f078bd0a3e5..22603256ddf8 100644
--- a/Documentation/devicetree/bindings/usb/renesas,usb-xhci.yaml
+++ b/Documentation/devicetree/bindings/usb/renesas,usb-xhci.yaml
@@ -51,7 +51,6 @@ properties:
     maxItems: 1
 
   phy-names:
-    maxItems: 1
     items:
       - const: usb
 
diff --git a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
index 737c1f47b7de..54c361d4a7af 100644
--- a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
+++ b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
@@ -74,11 +74,8 @@ properties:
 
   phys:
     maxItems: 1
-    items:
-      - description: phandle + phy specifier pair.
 
   phy-names:
-    maxItems: 1
     items:
       - const: usb
 
diff --git a/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml
index 388245b91a55..148b3fb4ceaf 100644
--- a/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml
+++ b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml
@@ -11,8 +11,12 @@ maintainers:
 
 properties:
   compatible:
-    items:
+    oneOf:
       - const: ti,j721e-usb
+      - const: ti,am64-usb
+      - items:
+          - const: ti,j721e-usb
+          - const: ti,am64-usb
 
   reg:
     description: module registers
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index ffaf833b97ee..041ae90b0d8f 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -187,6 +187,8 @@ patternProperties:
     description: CALAO Systems SAS
   "^calxeda,.*":
     description: Calxeda
+  "^canaan,.*":
+    description: Canaan, Inc.
   "^caninos,.*":
     description: Caninos Loucos Program
   "^capella,.*":
diff --git a/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml b/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml
index e8f226376108..5ac607de8be4 100644
--- a/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml
@@ -22,6 +22,9 @@ properties:
           - const: allwinner,sun50i-a64-wdt
           - const: allwinner,sun6i-a31-wdt
       - items:
+          - const: allwinner,sun50i-a100-wdt
+          - const: allwinner,sun6i-a31-wdt
+      - items:
           - const: allwinner,sun50i-h6-wdt
           - const: allwinner,sun6i-a31-wdt
       - items:
diff --git a/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml
index d9fc7bb851b1..f7ee9229c29f 100644
--- a/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml
@@ -14,7 +14,15 @@ maintainers:
 
 properties:
   compatible:
-    const: snps,dw-wdt
+    oneOf:
+      - const: snps,dw-wdt
+      - items:
+          - enum:
+              - rockchip,rk3066-wdt
+              - rockchip,rk3188-wdt
+              - rockchip,rk3288-wdt
+              - rockchip,rk3368-wdt
+          - const: snps,dw-wdt
 
   reg:
     maxItems: 1
diff --git a/Documentation/doc-guide/sphinx.rst b/Documentation/doc-guide/sphinx.rst
index 2fb2ff297d69..36ac2166ad67 100644
--- a/Documentation/doc-guide/sphinx.rst
+++ b/Documentation/doc-guide/sphinx.rst
@@ -48,12 +48,12 @@ or ``virtualenv``, depending on how your distribution packaged Python 3.
       those versions, you should run ``pip install 'docutils==0.12'``.
 
    #) It is recommended to use the RTD theme for html output. Depending
-      on the Sphinx version, it should be installed  in separate,
+      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 work,
+   #) Some ReST pages contain math expressions. Due to the way Sphinx works,
       those expressions are written using LaTeX notation. It needs texlive
-      installed with amdfonts and amsmath in order to evaluate them.
+      installed with amsfonts and amsmath in order to evaluate them.
 
 In summary, if you want to install Sphinx version 1.7.9, you should do::
 
@@ -128,7 +128,7 @@ Sphinx Build
 ============
 
 The usual way to generate the documentation is to run ``make htmldocs`` or
-``make pdfdocs``. There are also other formats available, see the documentation
+``make pdfdocs``. There are also other formats available: see the documentation
 section of ``make help``. The generated documentation is placed in
 format-specific subdirectories under ``Documentation/output``.
 
@@ -303,17 +303,17 @@ and *targets* (e.g. a ref to ``:ref:`last row <last row>``` / :ref:`last row
         - head col 3
         - head col 4
 
-      * - column 1
+      * - row 1
         - field 1.1
         - field 1.2 with autospan
 
-      * - column 2
+      * - row 2
         - field 2.1
         - :rspan:`1` :cspan:`1` field 2.2 - 3.3
 
       * .. _`last row`:
 
-        - column 3
+        - row 3
 
 Rendered as:
 
@@ -325,17 +325,17 @@ Rendered as:
         - head col 3
         - head col 4
 
-      * - column 1
+      * - row 1
         - field 1.1
         - field 1.2 with autospan
 
-      * - column 2
+      * - row 2
         - field 2.1
         - :rspan:`1` :cspan:`1` field 2.2 - 3.3
 
       * .. _`last row`:
 
-        - column 3
+        - row 3
 
 Cross-referencing
 -----------------
@@ -361,7 +361,7 @@ Figures & Images
 
 If you want to add an image, you should use the ``kernel-figure`` and
 ``kernel-image`` directives. E.g. to insert a figure with a scalable
-image format use SVG (:ref:`svg_image_example`)::
+image format, use SVG (:ref:`svg_image_example`)::
 
     .. kernel-figure::  svg_image.svg
        :alt:    simple SVG image
@@ -375,7 +375,7 @@ image format use SVG (:ref:`svg_image_example`)::
 
    SVG image example
 
-The kernel figure (and image) directive support **DOT** formatted files, see
+The kernel figure (and image) directive supports **DOT** formatted files, see
 
 * DOT: http://graphviz.org/pdf/dotguide.pdf
 * Graphviz: http://www.graphviz.org/content/dot-language
@@ -394,7 +394,7 @@ A simple example (:ref:`hello_dot_file`)::
 
    DOT's hello world example
 
-Embed *render* markups (or languages) like Graphviz's **DOT** is provided by the
+Embedded *render* markups (or languages) like Graphviz's **DOT** are provided by the
 ``kernel-render`` directives.::
 
   .. kernel-render:: DOT
@@ -406,7 +406,7 @@ Embed *render* markups (or languages) like Graphviz's **DOT** is provided by the
      }
 
 How this will be rendered depends on the installed tools. If Graphviz is
-installed, you will see an vector image. If not the raw markup is inserted as
+installed, you will see a vector image. If not, the raw markup is inserted as
 *literal-block* (:ref:`hello_dot_render`).
 
 .. _hello_dot_render:
@@ -421,8 +421,8 @@ installed, you will see an vector image. If not the raw markup is inserted as
 
 The *render* directive has all the options known from the *figure* directive,
 plus option ``caption``.  If ``caption`` has a value, a *figure* node is
-inserted. If not, a *image* node is inserted. A ``caption`` is also needed, if
-you want to refer it (:ref:`hello_svg_render`).
+inserted. If not, an *image* node is inserted. A ``caption`` is also needed, if
+you want to refer to it (:ref:`hello_svg_render`).
 
 Embedded **SVG**::
 
diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index bb676570acc3..cd8b6e657b94 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -411,6 +411,12 @@ RESET
   devm_reset_control_get()
   devm_reset_controller_register()
 
+RTC
+  devm_rtc_device_register()
+  devm_rtc_allocate_device()
+  devm_rtc_register_device()
+  devm_rtc_nvmem_register()
+
 SERDEV
   devm_serdev_device_open()
 
diff --git a/Documentation/features/debug/KASAN/arch-support.txt b/Documentation/features/debug/KASAN/arch-support.txt
index c3fe9b266e7b..b2288dc14b72 100644
--- a/Documentation/features/debug/KASAN/arch-support.txt
+++ b/Documentation/features/debug/KASAN/arch-support.txt
@@ -8,7 +8,7 @@
     -----------------------
     |       alpha: | TODO |
     |         arc: | TODO |
-    |         arm: | TODO |
+    |         arm: |  ok  |
     |       arm64: |  ok  |
     |         c6x: | TODO |
     |        csky: | TODO |
diff --git a/Documentation/filesystems/ext4/journal.rst b/Documentation/filesystems/ext4/journal.rst
index 849d5b119eb8..cdbfec473167 100644
--- a/Documentation/filesystems/ext4/journal.rst
+++ b/Documentation/filesystems/ext4/journal.rst
@@ -681,3 +681,53 @@ Here is the list of supported tags and their meanings:
      - Stores the TID of the commit, CRC of the fast commit of which this tag
        represents the end of
 
+Fast Commit Replay Idempotence
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Fast commits tags are idempotent in nature provided the recovery code follows
+certain rules. The guiding principle that the commit path follows while
+committing is that it stores the result of a particular operation instead of
+storing the procedure.
+
+Let's consider this rename operation: 'mv /a /b'. Let's assume dirent '/a'
+was associated with inode 10. During fast commit, instead of storing this
+operation as a procedure "rename a to b", we store the resulting file system
+state as a "series" of outcomes:
+
+- Link dirent b to inode 10
+- Unlink dirent a
+- Inode 10 with valid refcount
+
+Now when recovery code runs, it needs "enforce" this state on the file
+system. This is what guarantees idempotence of fast commit replay.
+
+Let's take an example of a procedure that is not idempotent and see how fast
+commits make it idempotent. Consider following sequence of operations:
+
+1) rm A
+2) mv B A
+3) read A
+
+If we store this sequence of operations as is then the replay is not idempotent.
+Let's say while in replay, we crash after (2). During the second replay,
+file A (which was actually created as a result of "mv B A" operation) would get
+deleted. Thus, file named A would be absent when we try to read A. So, this
+sequence of operations is not idempotent. However, as mentioned above, instead
+of storing the procedure fast commits store the outcome of each procedure. Thus
+the fast commit log for above procedure would be as follows:
+
+(Let's assume dirent A was linked to inode 10 and dirent B was linked to
+inode 11 before the replay)
+
+1) Unlink A
+2) Link A to inode 11
+3) Unlink B
+4) Inode 11
+
+If we crash after (3) we will have file A linked to inode 11. During the second
+replay, we will remove file A (inode 11). But we will create it back and make
+it point to inode 11. We won't find B, so we'll just skip that step. At this
+point, the refcount for inode 11 is not reliable, but that gets fixed by the
+replay of last inode 11 tag. Thus, by converting a non-idempotent procedure
+into a series of idempotent outcomes, fast commits ensured idempotence during
+the replay.
diff --git a/Documentation/firmware-guide/acpi/apei/einj.rst b/Documentation/firmware-guide/acpi/apei/einj.rst
index e588bccf5158..c042176e1707 100644
--- a/Documentation/firmware-guide/acpi/apei/einj.rst
+++ b/Documentation/firmware-guide/acpi/apei/einj.rst
@@ -50,8 +50,8 @@ The following files belong to it:
   0x00000010        Memory Uncorrectable non-fatal
   0x00000020        Memory Uncorrectable fatal
   0x00000040        PCI Express Correctable
-  0x00000080        PCI Express Uncorrectable fatal
-  0x00000100        PCI Express Uncorrectable non-fatal
+  0x00000080        PCI Express Uncorrectable non-fatal
+  0x00000100        PCI Express Uncorrectable fatal
   0x00000200        Platform Correctable
   0x00000400        Platform Uncorrectable non-fatal
   0x00000800        Platform Uncorrectable fatal
diff --git a/Documentation/hwmon/sbtsi_temp.rst b/Documentation/hwmon/sbtsi_temp.rst
index 922b3c8db666..749f518389c3 100644
--- a/Documentation/hwmon/sbtsi_temp.rst
+++ b/Documentation/hwmon/sbtsi_temp.rst
@@ -1,7 +1,7 @@
 .. SPDX-License-Identifier: GPL-2.0-or-later
 
 Kernel driver sbtsi_temp
-==================
+========================
 
 Supported hardware:
 
diff --git a/Documentation/kbuild/kconfig-language.rst b/Documentation/kbuild/kconfig-language.rst
index 1cf1aebdd6cd..226ae072da7d 100644
--- a/Documentation/kbuild/kconfig-language.rst
+++ b/Documentation/kbuild/kconfig-language.rst
@@ -553,6 +553,41 @@ with "depends on m".  E.g.::
 
 limits FOO to module (=m) or disabled (=n).
 
+Compile-testing
+~~~~~~~~~~~~~~~
+If a config symbol has a dependency, but the code controlled by the config
+symbol can still be compiled if the dependency is not met, it is encouraged to
+increase build coverage by adding an "|| COMPILE_TEST" clause to the
+dependency. This is especially useful for drivers for more exotic hardware, as
+it allows continuous-integration systems to compile-test the code on a more
+common system, and detect bugs that way.
+Note that compile-tested code should avoid crashing when run on a system where
+the dependency is not met.
+
+Architecture and platform dependencies
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Due to the presence of stubs, most drivers can now be compiled on most
+architectures. However, this does not mean it makes sense to have all drivers
+available everywhere, as the actual hardware may only exist on specific
+architectures and platforms. This is especially true for on-SoC IP cores,
+which may be limited to a specific vendor or SoC family.
+
+To prevent asking the user about drivers that cannot be used on the system(s)
+the user is compiling a kernel for, and if it makes sense, config symbols
+controlling the compilation of a driver should contain proper dependencies,
+limiting the visibility of the symbol to (a superset of) the platform(s) the
+driver can be used on. The dependency can be an architecture (e.g. ARM) or
+platform (e.g. ARCH_OMAP4) dependency. This makes life simpler not only for
+distro config owners, but also for every single developer or user who
+configures a kernel.
+
+Such a dependency can be relaxed by combining it with the compile-testing rule
+above, leading to:
+
+  config FOO
+	bool "Support for foo hardware"
+	depends on ARCH_FOO_VENDOR || COMPILE_TEST
+
 Kconfig recursive dependency limitations
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/Documentation/kbuild/kconfig-macro-language.rst b/Documentation/kbuild/kconfig-macro-language.rst
index 8b413ef9603d..6163467f6ae4 100644
--- a/Documentation/kbuild/kconfig-macro-language.rst
+++ b/Documentation/kbuild/kconfig-macro-language.rst
@@ -97,7 +97,7 @@ Like Make, Kconfig provides several built-in functions. Every function takes a
 particular number of arguments.
 
 In Make, every built-in function takes at least one argument. Kconfig allows
-zero argument for built-in functions, such as $(fileno), $(lineno). You could
+zero argument for built-in functions, such as $(filename), $(lineno). You could
 consider those as "built-in variable", but it is just a matter of how we call
 it after all. Let's say "built-in function" here to refer to natively supported
 functionality.
diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst
index 0d5dd5413af0..9f6a11881951 100644
--- a/Documentation/kbuild/makefiles.rst
+++ b/Documentation/kbuild/makefiles.rst
@@ -15,13 +15,15 @@ This document describes the Linux kernel Makefiles.
 	   --- 3.4 Objects which export symbols
 	   --- 3.5 Library file goals - lib-y
 	   --- 3.6 Descending down in directories
-	   --- 3.7 Compilation flags
-	   --- 3.8 <deleted>
-	   --- 3.9 Dependency tracking
-	   --- 3.10 Special Rules
-	   --- 3.11 $(CC) support functions
-	   --- 3.12 $(LD) support functions
-	   --- 3.13 Script Invocation
+	   --- 3.7 Non-builtin vmlinux targets - extra-y
+	   --- 3.8 Always built goals - always-y
+	   --- 3.9 Compilation flags
+	   --- 3.10 Dependency tracking
+	   --- 3.11 Custom Rules
+	   --- 3.12 Command change detection
+	   --- 3.13 $(CC) support functions
+	   --- 3.14 $(LD) support functions
+	   --- 3.15 Script Invocation
 
 	=== 4 Host Program support
 	   --- 4.1 Simple Host Program
@@ -46,7 +48,7 @@ This document describes the Linux kernel Makefiles.
 	   --- 7.5 Architecture-specific boot images
 	   --- 7.6 Building non-kbuild targets
 	   --- 7.7 Commands useful for building a boot image
-	   --- 7.8 Custom kbuild commands
+	   --- 7.8 <deleted>
 	   --- 7.9 Preprocessing linker scripts
 	   --- 7.10 Generic header files
 	   --- 7.11 Post-link pass
@@ -67,11 +69,11 @@ This document describes the Linux kernel Makefiles.
 
 The Makefiles have five parts::
 
-	Makefile		the top Makefile.
-	.config			the kernel configuration file.
-	arch/$(ARCH)/Makefile	the arch Makefile.
-	scripts/Makefile.*	common rules etc. for all kbuild Makefiles.
-	kbuild Makefiles	there are about 500 of these.
+	Makefile                    the top Makefile.
+	.config                     the kernel configuration file.
+	arch/$(SRCARCH)/Makefile    the arch Makefile.
+	scripts/Makefile.*          common rules etc. for all kbuild Makefiles.
+	kbuild Makefiles            exist in every subdirectory
 
 The top Makefile reads the .config file, which comes from the kernel
 configuration process.
@@ -82,7 +84,7 @@ It builds these goals by recursively descending into the subdirectories of
 the kernel source tree.
 The list of subdirectories which are visited depends upon the kernel
 configuration. The top Makefile textually includes an arch Makefile
-with the name arch/$(ARCH)/Makefile. The arch Makefile supplies
+with the name arch/$(SRCARCH)/Makefile. The arch Makefile supplies
 architecture-specific information to the top Makefile.
 
 Each subdirectory has a kbuild Makefile which carries out the commands
@@ -278,7 +280,7 @@ more details, with real examples.
 	actually recognize that there is a lib.a being built, the directory
 	shall be listed in libs-y.
 
-	See also "6.4 List directories to visit when descending".
+	See also "7.4 List directories to visit when descending".
 
 	Use of lib-y is normally restricted to `lib/` and `arch/*/lib`.
 
@@ -317,11 +319,79 @@ more details, with real examples.
 	that directory specifies obj-y, those objects will be left orphan.
 	It is very likely a bug of the Makefile or of dependencies in Kconfig.
 
+	Kbuild also supports dedicated syntax, subdir-y and subdir-m, for
+	descending into subdirectories. It is a good fit when you know they
+	do not contain kernel-space objects at all. A typical usage is to let
+	Kbuild descend into subdirectories to build tools.
+
+	Examples::
+
+		# scripts/Makefile
+		subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins
+		subdir-$(CONFIG_MODVERSIONS) += genksyms
+		subdir-$(CONFIG_SECURITY_SELINUX) += selinux
+
+	Unlike obj-y/m, subdir-y/m does not need the trailing slash since this
+	syntax is always used for directories.
+
 	It is good practice to use a `CONFIG_` variable when assigning directory
 	names. This allows kbuild to totally skip the directory if the
 	corresponding `CONFIG_` option is neither 'y' nor 'm'.
 
-3.7 Compilation flags
+3.7 Non-builtin vmlinux targets - extra-y
+-----------------------------------------
+
+	extra-y specifies targets which are needed for building vmlinux,
+	but not combined into built-in.a.
+
+	Examples are:
+
+	1) head objects
+
+	    Some objects must be placed at the head of vmlinux. They are
+	    directly linked to vmlinux without going through built-in.a
+	    A typical use-case is an object that contains the entry point.
+
+	    arch/$(SRCARCH)/Makefile should specify such objects as head-y.
+
+	    Discussion:
+	      Given that we can control the section order in the linker script,
+	      why do we need head-y?
+
+	2) vmlinux linker script
+
+	    The linker script for vmlinux is located at
+	    arch/$(SRCARCH)/kernel/vmlinux.lds
+
+	Example::
+
+		# arch/x86/kernel/Makefile
+		extra-y	:= head_$(BITS).o
+		extra-y	+= head$(BITS).o
+		extra-y	+= ebda.o
+		extra-y	+= platform-quirks.o
+		extra-y	+= vmlinux.lds
+
+	$(extra-y) should only contain targets needed for vmlinux.
+
+	Kbuild skips extra-y when vmlinux is apparently not a final goal.
+	(e.g. 'make modules', or building external modules)
+
+	If you intend to build targets unconditionally, always-y (explained
+	in the next section) is the correct syntax to use.
+
+3.8 Always built goals - always-y
+---------------------------------
+
+	always-y specifies targets which are literally always built when
+	Kbuild visits the Makefile.
+
+	Example::
+	  # ./Kbuild
+	  offsets-file := include/generated/asm-offsets.h
+	  always-y += $(offsets-file)
+
+3.9 Compilation flags
 ---------------------
 
     ccflags-y, asflags-y and ldflags-y
@@ -410,8 +480,8 @@ more details, with real examples.
 		AFLAGS_iwmmxt.o      := -Wa,-mcpu=iwmmxt
 
 
-3.9 Dependency tracking
------------------------
+3.10 Dependency tracking
+------------------------
 
 	Kbuild tracks dependencies on the following:
 
@@ -422,21 +492,21 @@ more details, with real examples.
 	Thus, if you change an option to $(CC) all affected files will
 	be re-compiled.
 
-3.10 Special Rules
-------------------
+3.11 Custom Rules
+-----------------
 
-	Special rules are used when the kbuild infrastructure does
+	Custom rules are used when the kbuild infrastructure does
 	not provide the required support. A typical example is
 	header files generated during the build process.
 	Another example are the architecture-specific Makefiles which
-	need special rules to prepare boot images etc.
+	need custom rules to prepare boot images etc.
 
-	Special rules are written as normal Make rules.
+	Custom rules are written as normal Make rules.
 	Kbuild is not executing in the directory where the Makefile is
-	located, so all special rules shall provide a relative
+	located, so all custom rules shall use a relative
 	path to prerequisite files and target files.
 
-	Two variables are used when defining special rules:
+	Two variables are used when defining custom rules:
 
 	$(src)
 	    $(src) is a relative path which points to the directory
@@ -454,7 +524,7 @@ more details, with real examples.
 		$(obj)/53c8xx_d.h: $(src)/53c7,8xx.scr $(src)/script_asm.pl
 			$(CPP) -DCHIP=810 - < $< | ... $(src)/script_asm.pl
 
-	    This is a special rule, following the normal syntax
+	    This is a custom rule, following the normal syntax
 	    required by make.
 
 	    The target file depends on two prerequisite files. References
@@ -471,13 +541,81 @@ more details, with real examples.
 
 	Example::
 
-		#arch/blackfin/boot/Makefile
-		$(obj)/vmImage: $(obj)/vmlinux.gz
-			$(call if_changed,uimage)
-			@$(kecho) 'Kernel: $@ is ready'
+		# arch/arm/Makefile
+		$(BOOT_TARGETS): vmlinux
+			$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
+			@$(kecho) '  Kernel: $(boot)/$@ is ready'
+
+	When kbuild is executing with KBUILD_VERBOSE=0, then only a shorthand
+	of a command is normally displayed.
+	To enable this behaviour for custom commands kbuild requires
+	two variables to be set::
+
+		quiet_cmd_<command>	- what shall be echoed
+		      cmd_<command>	- the command to execute
+
+	Example::
+
+		# lib/Makefile
+		quiet_cmd_crc32 = GEN     $@
+		      cmd_crc32 = $< > $@
+
+		$(obj)/crc32table.h: $(obj)/gen_crc32table
+			$(call cmd,crc32)
+
+	When updating the $(obj)/crc32table.h target, the line:
+
+		  GEN     lib/crc32table.h
+
+	will be displayed with "make KBUILD_VERBOSE=0".
+
+3.12 Command change detection
+-----------------------------
+
+	When the rule is evaluated, timestamps are compared between the target
+	and its prerequisite files. GNU Make updates the target when any of the
+	prerequisites is newer than that.
+
+	The target should be rebuilt also when the command line has changed
+	since the last invocation. This is not supported by Make itself, so
+	Kbuild achieves this by a kind of meta-programming.
+
+	if_changed is the macro used for this purpose, in the following form::
+
+		quiet_cmd_<command> = ...
+		      cmd_<command> = ...
+
+		<target>: <source(s)> FORCE
+			$(call if_changed,<command>)
+
+	Any target that utilizes if_changed must be listed in $(targets),
+	otherwise the command line check will fail, and the target will
+	always be built.
+
+	If the target is already listed in the recognized syntax such as
+	obj-y/m, lib-y/m, extra-y/m, always-y/m, hostprogs, userprogs, Kbuild
+	automatically adds it to $(targets). Otherwise, the target must be
+	explicitly added to $(targets).
+
+	Assignments to $(targets) are without $(obj)/ prefix. if_changed may be
+	used in conjunction with custom rules as defined in "3.11 Custom Rules".
+
+	Note: It is a typical mistake to forget the FORCE prerequisite.
+	Another common pitfall is that whitespace is sometimes significant; for
+	instance, the below will fail (note the extra space after the comma)::
+
+		target: source(s) FORCE
+
+	**WRONG!**	$(call if_changed, objcopy)
 
+	Note:
+		if_changed should not be used more than once per target.
+		It stores the executed command in a corresponding .cmd
+		file and multiple calls would result in overwrites and
+		unwanted results when the target is up to date and only the
+		tests on changed commands trigger execution of commands.
 
-3.11 $(CC) support functions
+3.13 $(CC) support functions
 ----------------------------
 
 	The kernel may be built with several different versions of
@@ -592,7 +730,7 @@ more details, with real examples.
 			endif
 		endif
 
-3.12 $(LD) support functions
+3.14 $(LD) support functions
 ----------------------------
 
     ld-option
@@ -606,7 +744,7 @@ more details, with real examples.
 		#Makefile
 		LDFLAGS_vmlinux += $(call ld-option, -X)
 
-3.13 Script invocation
+3.15 Script invocation
 ----------------------
 
 	Make rules may invoke scripts to build the kernel. The rules shall
@@ -744,7 +882,7 @@ Both possibilities are described in the following.
 	as a prerequisite.
 	This is possible in two ways:
 
-	(1) List the prerequisite explicitly in a special rule.
+	(1) List the prerequisite explicitly in a custom rule.
 
 	Example::
 
@@ -755,11 +893,11 @@ Both possibilities are described in the following.
 
 	The target $(obj)/devlist.h will not be built before
 	$(obj)/gen-devlist is updated. Note that references to
-	the host programs in special rules must be prefixed with $(obj).
+	the host programs in custom rules must be prefixed with $(obj).
 
 	(2) Use always-y
 
-	When there is no suitable special rule, and the host program
+	When there is no suitable custom rule, and the host program
 	shall be built when a makefile is entered, the always-y
 	variable shall be used.
 
@@ -933,7 +1071,7 @@ When "make clean" is executed, make will descend down in arch/x86/boot,
 and clean as usual. The Makefile located in arch/x86/boot/ may use
 the subdir- trick to descend further down.
 
-Note 1: arch/$(ARCH)/Makefile cannot use "subdir-", because that file is
+Note 1: arch/$(SRCARCH)/Makefile cannot use "subdir-", because that file is
 included in the top level makefile, and the kbuild infrastructure
 is not operational at that point.
 
@@ -946,9 +1084,9 @@ be visited during "make clean".
 The top level Makefile sets up the environment and does the preparation,
 before starting to descend down in the individual directories.
 The top level makefile contains the generic part, whereas
-arch/$(ARCH)/Makefile contains what is required to set up kbuild
+arch/$(SRCARCH)/Makefile contains what is required to set up kbuild
 for said architecture.
-To do so, arch/$(ARCH)/Makefile sets up a number of variables and defines
+To do so, arch/$(SRCARCH)/Makefile sets up a number of variables and defines
 a few targets.
 
 When kbuild executes, the following steps are followed (roughly):
@@ -956,14 +1094,14 @@ When kbuild executes, the following steps are followed (roughly):
 1) Configuration of the kernel => produce .config
 2) Store kernel version in include/linux/version.h
 3) Updating all other prerequisites to the target prepare:
-   - Additional prerequisites are specified in arch/$(ARCH)/Makefile
+   - Additional prerequisites are specified in arch/$(SRCARCH)/Makefile
 4) Recursively descend down in all directories listed in
    init-* core* drivers-* net-* libs-* and build all targets.
-   - The values of the above variables are expanded in arch/$(ARCH)/Makefile.
+   - The values of the above variables are expanded in arch/$(SRCARCH)/Makefile.
 5) All object files are then linked and the resulting file vmlinux is
    located at the root of the obj tree.
    The very first objects linked are listed in head-y, assigned by
-   arch/$(ARCH)/Makefile.
+   arch/$(SRCARCH)/Makefile.
 6) Finally, the architecture-specific part does any required post processing
    and builds the final bootimage.
    - This includes building boot records
@@ -1154,7 +1292,7 @@ When kbuild executes, the following steps are followed (roughly):
 	machinery is all architecture-independent.
 
 
-	head-y, init-y, core-y, libs-y, drivers-y, net-y
+	head-y, core-y, libs-y, drivers-y
 	    $(head-y) lists objects to be linked first in vmlinux.
 
 	    $(libs-y) lists directories where a lib.a archive can be located.
@@ -1162,23 +1300,24 @@ When kbuild executes, the following steps are followed (roughly):
 	    The rest list directories where a built-in.a object file can be
 	    located.
 
-	    $(init-y) objects will be located after $(head-y).
-
 	    Then the rest follows in this order:
 
-		$(core-y), $(libs-y), $(drivers-y) and $(net-y).
+		$(core-y), $(libs-y), $(drivers-y)
 
 	    The top level Makefile defines values for all generic directories,
-	    and arch/$(ARCH)/Makefile only adds architecture-specific
+	    and arch/$(SRCARCH)/Makefile only adds architecture-specific
 	    directories.
 
 	    Example::
 
-		#arch/sparc64/Makefile
-		core-y += arch/sparc64/kernel/
-		libs-y += arch/sparc64/prom/ arch/sparc64/lib/
-		drivers-$(CONFIG_OPROFILE)  += arch/sparc64/oprofile/
+		# arch/sparc/Makefile
+		core-y                 += arch/sparc/
+
+		libs-y                 += arch/sparc/prom/
+		libs-y                 += arch/sparc/lib/
 
+		drivers-$(CONFIG_PM) += arch/sparc/power/
+		drivers-$(CONFIG_OPROFILE)	+= arch/sparc/oprofile/
 
 7.5 Architecture-specific boot images
 -------------------------------------
@@ -1189,15 +1328,15 @@ When kbuild executes, the following steps are followed (roughly):
 	The actual goals are not standardized across architectures.
 
 	It is common to locate any additional processing in a boot/
-	directory below arch/$(ARCH)/.
+	directory below arch/$(SRCARCH)/.
 
 	Kbuild does not provide any smart way to support building a
-	target specified in boot/. Therefore arch/$(ARCH)/Makefile shall
+	target specified in boot/. Therefore arch/$(SRCARCH)/Makefile shall
 	call make manually to build a target in boot/.
 
 	The recommended approach is to include shortcuts in
-	arch/$(ARCH)/Makefile, and use the full path when calling down
-	into the arch/$(ARCH)/boot/Makefile.
+	arch/$(SRCARCH)/Makefile, and use the full path when calling down
+	into the arch/$(SRCARCH)/boot/Makefile.
 
 	Example::
 
@@ -1217,7 +1356,7 @@ When kbuild executes, the following steps are followed (roughly):
 
 		#arch/x86/Makefile
 		define archhelp
-		  echo  '* bzImage      - Image (arch/$(ARCH)/boot/bzImage)'
+		  echo  '* bzImage      - Compressed kernel image (arch/x86/boot/bzImage)'
 		endif
 
 	When make is executed without arguments, the first goal encountered
@@ -1235,71 +1374,12 @@ When kbuild executes, the following steps are followed (roughly):
 
 	When "make" is executed without arguments, bzImage will be built.
 
-7.6 Building non-kbuild targets
--------------------------------
-
-    extra-y
-	extra-y specifies additional targets created in the current
-	directory, in addition to any targets specified by `obj-*`.
-
-	Listing all targets in extra-y is required for two purposes:
-
-	1) Enable kbuild to check changes in command lines
-
-	   - When $(call if_changed,xxx) is used
-
-	2) kbuild knows what files to delete during "make clean"
-
-	Example::
-
-		#arch/x86/kernel/Makefile
-		extra-y := head.o init_task.o
-
-	In this example, extra-y is used to list object files that
-	shall be built, but shall not be linked as part of built-in.a.
-
 7.7 Commands useful for building a boot image
 ---------------------------------------------
 
     Kbuild provides a few macros that are useful when building a
     boot image.
 
-    if_changed
-	if_changed is the infrastructure used for the following commands.
-
-	Usage::
-
-		target: source(s) FORCE
-			$(call if_changed,ld/objcopy/gzip/...)
-
-	When the rule is evaluated, it is checked to see if any files
-	need an update, or the command line has changed since the last
-	invocation. The latter will force a rebuild if any options
-	to the executable have changed.
-	Any target that utilises if_changed must be listed in $(targets),
-	otherwise the command line check will fail, and the target will
-	always be built.
-	Assignments to $(targets) are without $(obj)/ prefix.
-	if_changed may be used in conjunction with custom commands as
-	defined in 7.8 "Custom kbuild commands".
-
-	Note: It is a typical mistake to forget the FORCE prerequisite.
-	Another common pitfall is that whitespace is sometimes
-	significant; for instance, the below will fail (note the extra space
-	after the comma)::
-
-		target: source(s) FORCE
-
-	**WRONG!**	$(call if_changed, ld/objcopy/gzip/...)
-
-        Note:
-	      if_changed should not be used more than once per target.
-              It stores the executed command in a corresponding .cmd
-
-        file and multiple calls would result in overwrites and
-        unwanted results when the target is up to date and only the
-        tests on changed commands trigger execution of commands.
-
     ld
 	Link target. Often, LDFLAGS_$@ is used to set specific options to ld.
 
@@ -1332,7 +1412,7 @@ When kbuild executes, the following steps are followed (roughly):
 
     objcopy
 	Copy binary. Uses OBJCOPYFLAGS usually specified in
-	arch/$(ARCH)/Makefile.
+	arch/$(SRCARCH)/Makefile.
 	OBJCOPYFLAGS_$@ may be used to set additional options.
 
     gzip
@@ -1361,41 +1441,11 @@ When kbuild executes, the following steps are followed (roughly):
 		targets += $(dtb-y)
 		DTC_FLAGS ?= -p 1024
 
-7.8 Custom kbuild commands
---------------------------
-
-	When kbuild is executing with KBUILD_VERBOSE=0, then only a shorthand
-	of a command is normally displayed.
-	To enable this behaviour for custom commands kbuild requires
-	two variables to be set::
-
-		quiet_cmd_<command>	- what shall be echoed
-		      cmd_<command>	- the command to execute
-
-	Example::
-
-		#
-		quiet_cmd_image = BUILD   $@
-		      cmd_image = $(obj)/tools/build $(BUILDFLAGS) \
-		                                     $(obj)/vmlinux.bin > $@
-
-		targets += bzImage
-		$(obj)/bzImage: $(obj)/vmlinux.bin $(obj)/tools/build FORCE
-			$(call if_changed,image)
-			@echo 'Kernel: $@ is ready'
-
-	When updating the $(obj)/bzImage target, the line:
-
-		BUILD    arch/x86/boot/bzImage
-
-	will be displayed with "make KBUILD_VERBOSE=0".
-
-
 7.9 Preprocessing linker scripts
 --------------------------------
 
 	When the vmlinux image is built, the linker script
-	arch/$(ARCH)/kernel/vmlinux.lds is used.
+	arch/$(SRCARCH)/kernel/vmlinux.lds is used.
 	The script is a preprocessed variant of the file vmlinux.lds.S
 	located in the same directory.
 	kbuild knows .lds files and includes a rule `*lds.S` -> `*lds`.
@@ -1405,9 +1455,6 @@ When kbuild executes, the following steps are followed (roughly):
 		#arch/x86/kernel/Makefile
 		extra-y := vmlinux.lds
 
-		#Makefile
-		export CPPFLAGS_vmlinux.lds += -P -C -U$(ARCH)
-
 	The assignment to extra-y is used to tell kbuild to build the
 	target vmlinux.lds.
 	The assignment to $(CPPFLAGS_vmlinux.lds) tells kbuild to use the
@@ -1481,7 +1528,7 @@ See subsequent chapter for the syntax of the Kbuild file.
 
 	If an architecture uses a verbatim copy of a header from
 	include/asm-generic then this is listed in the file
-	arch/$(ARCH)/include/asm/Kbuild like this:
+	arch/$(SRCARCH)/include/asm/Kbuild like this:
 
 		Example::
 
@@ -1492,7 +1539,7 @@ See subsequent chapter for the syntax of the Kbuild file.
 	During the prepare phase of the build a wrapper include
 	file is generated in the directory::
 
-		arch/$(ARCH)/include/generated/asm
+		arch/$(SRCARCH)/include/generated/asm
 
 	When a header is exported where the architecture uses
 	the generic header a similar wrapper is generated as part
@@ -1527,8 +1574,8 @@ See subsequent chapter for the syntax of the Kbuild file.
 	to define the minimum set of ASM headers that all architectures must have.
 
 	This works like optional generic-y. If a mandatory header is missing
-	in arch/$(ARCH)/include/(uapi/)/asm, Kbuild will automatically generate
-	a wrapper of the asm-generic one.
+	in arch/$(SRCARCH)/include/(uapi/)/asm, Kbuild will automatically
+	generate a wrapper of the asm-generic one.
 
 9 Kbuild Variables
 ==================
@@ -1564,6 +1611,16 @@ The top Makefile exports the following variables:
 
 	    make ARCH=m68k ...
 
+    SRCARCH
+	This variable specifies the directory in arch/ to build.
+
+	ARCH and SRCARCH may not necessarily match. A couple of arch
+	directories are biarch, that is, a single `arch/*/` directory supports
+	both 32-bit and 64-bit.
+
+	For example, you can pass in ARCH=i386, ARCH=x86_64, or ARCH=x86.
+	For all of them, SRCARCH=x86 because arch/x86/ supports	both i386 and
+	x86_64.
 
     INSTALL_PATH
 	This variable defines a place for the arch Makefiles to install
diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst
index 85ccc878895e..a1f3eb7a43e2 100644
--- a/Documentation/kbuild/modules.rst
+++ b/Documentation/kbuild/modules.rst
@@ -332,7 +332,7 @@ according to the following rule:
 	      There are two notable exceptions to this rule: larger
 	      subsystems have their own directory under include/, such as
 	      include/scsi; and architecture specific headers are located
-	      under arch/$(ARCH)/include/.
+	      under arch/$(SRCARCH)/include/.
 
 4.1 Kernel Includes
 -------------------
diff --git a/Documentation/kernel-hacking/locking.rst b/Documentation/kernel-hacking/locking.rst
index 6ed806e6061b..c3448929a824 100644
--- a/Documentation/kernel-hacking/locking.rst
+++ b/Documentation/kernel-hacking/locking.rst
@@ -118,11 +118,11 @@ spinlock, but you may block holding a mutex. If you can't lock a mutex,
 your task will suspend itself, and be woken up when the mutex is
 released. This means the CPU can do something else while you are
 waiting. There are many cases when you simply can't sleep (see
-`What Functions Are Safe To Call From Interrupts? <#sleeping-things>`__),
+`What Functions Are Safe To Call From Interrupts?`_),
 and so have to use a spinlock instead.
 
 Neither type of lock is recursive: see
-`Deadlock: Simple and Advanced <#deadlock>`__.
+`Deadlock: Simple and Advanced`_.
 
 Locks and Uniprocessor Kernels
 ------------------------------
@@ -179,7 +179,7 @@ perfect world).
 
 Note that you can also use spin_lock_irq() or
 spin_lock_irqsave() here, which stop hardware interrupts
-as well: see `Hard IRQ Context <#hard-irq-context>`__.
+as well: see `Hard IRQ Context`_.
 
 This works perfectly for UP as well: the spin lock vanishes, and this
 macro simply becomes local_bh_disable()
@@ -230,7 +230,7 @@ The Same Softirq
 ~~~~~~~~~~~~~~~~
 
 The same softirq can run on the other CPUs: you can use a per-CPU array
-(see `Per-CPU Data <#per-cpu-data>`__) for better performance. If you're
+(see `Per-CPU Data`_) for better performance. If you're
 going so far as to use a softirq, you probably care about scalable
 performance enough to justify the extra complexity.
 
diff --git a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
index d3fcf536d14e..61e850460e18 100644
--- a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
+++ b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
@@ -164,46 +164,56 @@ Devlink health reporters
 
 NPA Reporters
 -------------
-The NPA reporters are responsible for reporting and recovering the following group of errors
+The NPA reporters are responsible for reporting and recovering the following group of errors:
+
 1. GENERAL events
+
    - Error due to operation of unmapped PF.
    - Error due to disabled alloc/free for other HW blocks (NIX, SSO, TIM, DPI and AURA).
+
 2. ERROR events
+
    - Fault due to NPA_AQ_INST_S read or NPA_AQ_RES_S write.
    - AQ Doorbell Error.
+
 3. RAS events
+
    - RAS Error Reporting for NPA_AQ_INST_S/NPA_AQ_RES_S.
+
 4. RVU events
+
    - Error due to unmapped slot.
 
-Sample Output
--------------
-~# devlink health
-pci/0002:01:00.0:
-  reporter hw_npa_intr
-      state healthy error 2872 recover 2872 last_dump_date 2020-12-10 last_dump_time 09:39:09 grace_period 0 auto_recover true auto_dump true
-  reporter hw_npa_gen
-      state healthy error 2872 recover 2872 last_dump_date 2020-12-11 last_dump_time 04:43:04 grace_period 0 auto_recover true auto_dump true
-  reporter hw_npa_err
-      state healthy error 2871 recover 2871 last_dump_date 2020-12-10 last_dump_time 09:39:17 grace_period 0 auto_recover true auto_dump true
-   reporter hw_npa_ras
-      state healthy error 0 recover 0 last_dump_date 2020-12-10 last_dump_time 09:32:40 grace_period 0 auto_recover true auto_dump true
+Sample Output::
+
+	~# devlink health
+	pci/0002:01:00.0:
+	  reporter hw_npa_intr
+	      state healthy error 2872 recover 2872 last_dump_date 2020-12-10 last_dump_time 09:39:09 grace_period 0 auto_recover true auto_dump true
+	  reporter hw_npa_gen
+	      state healthy error 2872 recover 2872 last_dump_date 2020-12-11 last_dump_time 04:43:04 grace_period 0 auto_recover true auto_dump true
+	  reporter hw_npa_err
+	      state healthy error 2871 recover 2871 last_dump_date 2020-12-10 last_dump_time 09:39:17 grace_period 0 auto_recover true auto_dump true
+	   reporter hw_npa_ras
+	      state healthy error 0 recover 0 last_dump_date 2020-12-10 last_dump_time 09:32:40 grace_period 0 auto_recover true auto_dump true
 
 Each reporter dumps the
+
  - Error Type
  - Error Register value
  - Reason in words
 
-For eg:
-~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_gen
- NPA_AF_GENERAL:
-         NPA General Interrupt Reg : 1
-         NIX0: free disabled RX
-~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_intr
- NPA_AF_RVU:
-         NPA RVU Interrupt Reg : 1
-         Unmap Slot Error
-~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_err
- NPA_AF_ERR:
-        NPA Error Interrupt Reg : 4096
-        AQ Doorbell Error
+For example::
+
+	~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_gen
+	 NPA_AF_GENERAL:
+	         NPA General Interrupt Reg : 1
+	         NIX0: free disabled RX
+	~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_intr
+	 NPA_AF_RVU:
+	         NPA RVU Interrupt Reg : 1
+	         Unmap Slot Error
+	~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_err
+	 NPA_AF_ERR:
+	        NPA Error Interrupt Reg : 4096
+	        AQ Doorbell Error
diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst
index 4b9ed5874d5a..ae2ae37cd921 100644
--- a/Documentation/networking/netdev-FAQ.rst
+++ b/Documentation/networking/netdev-FAQ.rst
@@ -6,9 +6,9 @@
 netdev FAQ
 ==========
 
-Q: What is netdev?
-------------------
-A: It is a mailing list for all network-related Linux stuff.  This
+What is netdev?
+---------------
+It is a mailing list for all network-related Linux stuff.  This
 includes anything found under net/ (i.e. core code like IPv6) and
 drivers/net (i.e. hardware specific drivers) in the Linux source tree.
 
@@ -25,9 +25,9 @@ Aside from subsystems like that mentioned above, all network-related
 Linux development (i.e. RFC, review, comments, etc.) takes place on
 netdev.
 
-Q: How do the changes posted to netdev make their way into Linux?
------------------------------------------------------------------
-A: There are always two trees (git repositories) in play.  Both are
+How do the changes posted to netdev make their way into Linux?
+--------------------------------------------------------------
+There are always two trees (git repositories) in play.  Both are
 driven by David Miller, the main network maintainer.  There is the
 ``net`` tree, and the ``net-next`` tree.  As you can probably guess from
 the names, the ``net`` tree is for fixes to existing code already in the
@@ -37,9 +37,9 @@ for the future release.  You can find the trees here:
 - https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
 - https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
 
-Q: How often do changes from these trees make it to the mainline Linus tree?
-----------------------------------------------------------------------------
-A: To understand this, you need to know a bit of background information on
+How often do changes from these trees make it to the mainline Linus tree?
+-------------------------------------------------------------------------
+To understand this, you need to know a bit of background information on
 the cadence of Linux development.  Each new release starts off with a
 two week "merge window" where the main maintainers feed their new stuff
 to Linus for merging into the mainline tree.  After the two weeks, the
@@ -81,7 +81,8 @@ focus for ``net`` is on stabilization and bug fixes.
 
 Finally, the vX.Y gets released, and the whole cycle starts over.
 
-Q: So where are we now in this cycle?
+So where are we now in this cycle?
+----------------------------------
 
 Load the mainline (Linus) page here:
 
@@ -91,9 +92,9 @@ and note the top of the "tags" section.  If it is rc1, it is early in
 the dev cycle.  If it was tagged rc7 a week ago, then a release is
 probably imminent.
 
-Q: How do I indicate which tree (net vs. net-next) my patch should be in?
--------------------------------------------------------------------------
-A: Firstly, think whether you have a bug fix or new "next-like" content.
+How do I indicate which tree (net vs. net-next) my patch should be in?
+----------------------------------------------------------------------
+Firstly, think whether you have a bug fix or new "next-like" content.
 Then once decided, assuming that you use git, use the prefix flag, i.e.
 ::
 
@@ -105,48 +106,45 @@ in the above is just the subject text of the outgoing e-mail, and you
 can manually change it yourself with whatever MUA you are comfortable
 with.
 
-Q: I sent a patch and I'm wondering what happened to it?
---------------------------------------------------------
-Q: How can I tell whether it got merged?
-A: Start by looking at the main patchworks queue for netdev:
+I sent a patch and I'm wondering what happened to it - how can I tell whether it got merged?
+--------------------------------------------------------------------------------------------
+Start by looking at the main patchworks queue for netdev:
 
   https://patchwork.kernel.org/project/netdevbpf/list/
 
 The "State" field will tell you exactly where things are at with your
 patch.
 
-Q: The above only says "Under Review".  How can I find out more?
-----------------------------------------------------------------
-A: Generally speaking, the patches get triaged quickly (in less than
+The above only says "Under Review".  How can I find out more?
+-------------------------------------------------------------
+Generally speaking, the patches get triaged quickly (in less than
 48h).  So be patient.  Asking the maintainer for status updates on your
 patch is a good way to ensure your patch is ignored or pushed to the
 bottom of the priority list.
 
-Q: I submitted multiple versions of the patch series
-----------------------------------------------------
-Q: should I directly update patchwork for the previous versions of these
-patch series?
-A: No, please don't interfere with the patch status on patchwork, leave
+I submitted multiple versions of the patch series. Should I directly update patchwork for the previous versions of these patch series?
+--------------------------------------------------------------------------------------------------------------------------------------
+No, please don't interfere with the patch status on patchwork, leave
 it to the maintainer to figure out what is the most recent and current
 version that should be applied. If there is any doubt, the maintainer
 will reply and ask what should be done.
 
-Q: I made changes to only a few patches in a patch series should I resend only those changed?
----------------------------------------------------------------------------------------------
-A: No, please resend the entire patch series and make sure you do number your
+I made changes to only a few patches in a patch series should I resend only those changed?
+------------------------------------------------------------------------------------------
+No, please resend the entire patch series and make sure you do number your
 patches such that it is clear this is the latest and greatest set of patches
 that can be applied.
 
-Q: I submitted multiple versions of a patch series and it looks like a version other than the last one has been accepted, what should I do?
--------------------------------------------------------------------------------------------------------------------------------------------
-A: There is no revert possible, once it is pushed out, it stays like that.
+I submitted multiple versions of a patch series and it looks like a version other than the last one has been accepted, what should I do?
+----------------------------------------------------------------------------------------------------------------------------------------
+There is no revert possible, once it is pushed out, it stays like that.
 Please send incremental versions on top of what has been merged in order to fix
 the patches the way they would look like if your latest patch series was to be
 merged.
 
-Q: How can I tell what patches are queued up for backporting to the various stable releases?
---------------------------------------------------------------------------------------------
-A: Normally Greg Kroah-Hartman collects stable commits himself, but for
+How can I tell what patches are queued up for backporting to the various stable releases?
+-----------------------------------------------------------------------------------------
+Normally Greg Kroah-Hartman collects stable commits himself, but for
 networking, Dave collects up patches he deems critical for the
 networking subsystem, and then hands them off to Greg.
 
@@ -169,11 +167,9 @@ simply clone the repo, and then git grep the mainline commit ID, e.g.
   releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
   stable/stable-queue$
 
-Q: I see a network patch and I think it should be backported to stable.
------------------------------------------------------------------------
-Q: Should I request it via stable@vger.kernel.org like the references in
-the kernel's Documentation/process/stable-kernel-rules.rst file say?
-A: No, not for networking.  Check the stable queues as per above first
+I see a network patch and I think it should be backported to stable. Should I request it via stable@vger.kernel.org like the references in the kernel's Documentation/process/stable-kernel-rules.rst file say?
+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+No, not for networking.  Check the stable queues as per above first
 to see if it is already queued.  If not, then send a mail to netdev,
 listing the upstream commit ID and why you think it should be a stable
 candidate.
@@ -190,11 +186,9 @@ mainline, the better the odds that it is an OK candidate for stable.  So
 scrambling to request a commit be added the day after it appears should
 be avoided.
 
-Q: I have created a network patch and I think it should be backported to stable.
---------------------------------------------------------------------------------
-Q: Should I add a Cc: stable@vger.kernel.org like the references in the
-kernel's Documentation/ directory say?
-A: No.  See above answer.  In short, if you think it really belongs in
+I have created a network patch and I think it should be backported to stable. Should I add a Cc: stable@vger.kernel.org like the references in the kernel's Documentation/ directory say?
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+No.  See above answer.  In short, if you think it really belongs in
 stable, then ensure you write a decent commit log that describes who
 gets impacted by the bug fix and how it manifests itself, and when the
 bug was introduced.  If you do that properly, then the commit will get
@@ -207,18 +201,18 @@ marker line as described in
 :ref:`Documentation/process/submitting-patches.rst <the_canonical_patch_format>`
 to temporarily embed that information into the patch that you send.
 
-Q: Are all networking bug fixes backported to all stable releases?
-------------------------------------------------------------------
-A: Due to capacity, Dave could only take care of the backports for the
+Are all networking bug fixes backported to all stable releases?
+---------------------------------------------------------------
+Due to capacity, Dave could only take care of the backports for the
 last two stable releases. For earlier stable releases, each stable
 branch maintainer is supposed to take care of them. If you find any
 patch is missing from an earlier stable branch, please notify
 stable@vger.kernel.org with either a commit ID or a formal patch
 backported, and CC Dave and other relevant networking developers.
 
-Q: Is the comment style convention different for the networking content?
-------------------------------------------------------------------------
-A: Yes, in a largely trivial way.  Instead of this::
+Is the comment style convention different for the networking content?
+---------------------------------------------------------------------
+Yes, in a largely trivial way.  Instead of this::
 
   /*
    * foobar blah blah blah
@@ -231,32 +225,30 @@ it is requested that you make it look like this::
    * another line of text
    */
 
-Q: I am working in existing code that has the former comment style and not the latter.
---------------------------------------------------------------------------------------
-Q: Should I submit new code in the former style or the latter?
-A: Make it the latter style, so that eventually all code in the domain
+I am working in existing code that has the former comment style and not the latter. Should I submit new code in the former style or the latter?
+-----------------------------------------------------------------------------------------------------------------------------------------------
+Make it the latter style, so that eventually all code in the domain
 of netdev is of this format.
 
-Q: I found a bug that might have possible security implications or similar.
----------------------------------------------------------------------------
-Q: Should I mail the main netdev maintainer off-list?**
-A: No. The current netdev maintainer has consistently requested that
+I found a bug that might have possible security implications or similar. Should I mail the main netdev maintainer off-list?
+---------------------------------------------------------------------------------------------------------------------------
+No. The current netdev maintainer has consistently requested that
 people use the mailing lists and not reach out directly.  If you aren't
 OK with that, then perhaps consider mailing security@kernel.org or
 reading about http://oss-security.openwall.org/wiki/mailing-lists/distros
 as possible alternative mechanisms.
 
-Q: What level of testing is expected before I submit my change?
----------------------------------------------------------------
-A: If your changes are against ``net-next``, the expectation is that you
+What level of testing is expected before I submit my change?
+------------------------------------------------------------
+If your changes are against ``net-next``, the expectation is that you
 have tested by layering your changes on top of ``net-next``.  Ideally
 you will have done run-time testing specific to your change, but at a
 minimum, your changes should survive an ``allyesconfig`` and an
 ``allmodconfig`` build without new warnings or failures.
 
-Q: How do I post corresponding changes to user space components?
-----------------------------------------------------------------
-A: User space code exercising kernel features should be posted
+How do I post corresponding changes to user space components?
+-------------------------------------------------------------
+User space code exercising kernel features should be posted
 alongside kernel patches. This gives reviewers a chance to see
 how any new interface is used and how well it works.
 
@@ -280,9 +272,9 @@ to the mailing list, e.g.::
 Posting as one thread is discouraged because it confuses patchwork
 (as of patchwork 2.2.2).
 
-Q: Any other tips to help ensure my net/net-next patch gets OK'd?
------------------------------------------------------------------
-A: Attention to detail.  Re-read your own work as if you were the
+Any other tips to help ensure my net/net-next patch gets OK'd?
+--------------------------------------------------------------
+Attention to detail.  Re-read your own work as if you were the
 reviewer.  You can start with using ``checkpatch.pl``, perhaps even with
 the ``--strict`` flag.  But do not be mindlessly robotic in doing so.
 If your change is a bug fix, make sure your commit log indicates the
diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst
index 5a85fcc80c76..17bdcb746dcf 100644
--- a/Documentation/networking/netdevices.rst
+++ b/Documentation/networking/netdevices.rst
@@ -10,18 +10,177 @@ Introduction
 The following is a random collection of documentation regarding
 network devices.
 
-struct net_device allocation rules
-==================================
+struct net_device lifetime rules
+================================
 Network device structures need to persist even after module is unloaded and
 must be allocated with alloc_netdev_mqs() and friends.
 If device has registered successfully, it will be freed on last use
-by free_netdev(). This is required to handle the pathologic case cleanly
-(example: rmmod mydriver </sys/class/net/myeth/mtu )
+by free_netdev(). This is required to handle the pathological case cleanly
+(example: ``rmmod mydriver </sys/class/net/myeth/mtu``)
 
-alloc_netdev_mqs()/alloc_netdev() reserve extra space for driver
+alloc_netdev_mqs() / alloc_netdev() reserve extra space for driver
 private data which gets freed when the network device is freed. If
 separately allocated data is attached to the network device
-(netdev_priv(dev)) then it is up to the module exit handler to free that.
+(netdev_priv()) then it is up to the module exit handler to free that.
+
+There are two groups of APIs for registering struct net_device.
+First group can be used in normal contexts where ``rtnl_lock`` is not already
+held: register_netdev(), unregister_netdev().
+Second group can be used when ``rtnl_lock`` is already held:
+register_netdevice(), unregister_netdevice(), free_netdevice().
+
+Simple drivers
+--------------
+
+Most drivers (especially device drivers) handle lifetime of struct net_device
+in context where ``rtnl_lock`` is not held (e.g. driver probe and remove paths).
+
+In that case the struct net_device registration is done using
+the register_netdev(), and unregister_netdev() functions:
+
+.. code-block:: c
+
+  int probe()
+  {
+    struct my_device_priv *priv;
+    int err;
+
+    dev = alloc_netdev_mqs(...);
+    if (!dev)
+      return -ENOMEM;
+    priv = netdev_priv(dev);
+
+    /* ... do all device setup before calling register_netdev() ...
+     */
+
+    err = register_netdev(dev);
+    if (err)
+      goto err_undo;
+
+    /* net_device is visible to the user! */
+
+  err_undo:
+    /* ... undo the device setup ... */
+    free_netdev(dev);
+    return err;
+  }
+
+  void remove()
+  {
+    unregister_netdev(dev);
+    free_netdev(dev);
+  }
+
+Note that after calling register_netdev() the device is visible in the system.
+Users can open it and start sending / receiving traffic immediately,
+or run any other callback, so all initialization must be done prior to
+registration.
+
+unregister_netdev() closes the device and waits for all users to be done
+with it. The memory of struct net_device itself may still be referenced
+by sysfs but all operations on that device will fail.
+
+free_netdev() can be called after unregister_netdev() returns on when
+register_netdev() failed.
+
+Device management under RTNL
+----------------------------
+
+Registering struct net_device while in context which already holds
+the ``rtnl_lock`` requires extra care. In those scenarios most drivers
+will want to make use of struct net_device's ``needs_free_netdev``
+and ``priv_destructor`` members for freeing of state.
+
+Example flow of netdev handling under ``rtnl_lock``:
+
+.. code-block:: c
+
+  static void my_setup(struct net_device *dev)
+  {
+    dev->needs_free_netdev = true;
+  }
+
+  static void my_destructor(struct net_device *dev)
+  {
+    some_obj_destroy(priv->obj);
+    some_uninit(priv);
+  }
+
+  int create_link()
+  {
+    struct my_device_priv *priv;
+    int err;
+
+    ASSERT_RTNL();
+
+    dev = alloc_netdev(sizeof(*priv), "net%d", NET_NAME_UNKNOWN, my_setup);
+    if (!dev)
+      return -ENOMEM;
+    priv = netdev_priv(dev);
+
+    /* Implicit constructor */
+    err = some_init(priv);
+    if (err)
+      goto err_free_dev;
+
+    priv->obj = some_obj_create();
+    if (!priv->obj) {
+      err = -ENOMEM;
+      goto err_some_uninit;
+    }
+    /* End of constructor, set the destructor: */
+    dev->priv_destructor = my_destructor;
+
+    err = register_netdevice(dev);
+    if (err)
+      /* register_netdevice() calls destructor on failure */
+      goto err_free_dev;
+
+    /* If anything fails now unregister_netdevice() (or unregister_netdev())
+     * will take care of calling my_destructor and free_netdev().
+     */
+
+    return 0;
+
+  err_some_uninit:
+    some_uninit(priv);
+  err_free_dev:
+    free_netdev(dev);
+    return err;
+  }
+
+If struct net_device.priv_destructor is set it will be called by the core
+some time after unregister_netdevice(), it will also be called if
+register_netdevice() fails. The callback may be invoked with or without
+``rtnl_lock`` held.
+
+There is no explicit constructor callback, driver "constructs" the private
+netdev state after allocating it and before registration.
+
+Setting struct net_device.needs_free_netdev makes core call free_netdevice()
+automatically after unregister_netdevice() when all references to the device
+are gone. It only takes effect after a successful call to register_netdevice()
+so if register_netdevice() fails driver is responsible for calling
+free_netdev().
+
+free_netdev() is safe to call on error paths right after unregister_netdevice()
+or when register_netdevice() fails. Parts of netdev (de)registration process
+happen after ``rtnl_lock`` is released, therefore in those cases free_netdev()
+will defer some of the processing until ``rtnl_lock`` is released.
+
+Devices spawned from struct rtnl_link_ops should never free the
+struct net_device directly.
+
+.ndo_init and .ndo_uninit
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+``.ndo_init`` and ``.ndo_uninit`` callbacks are called during net_device
+registration and de-registration, under ``rtnl_lock``. Drivers can use
+those e.g. when parts of their init process need to run under ``rtnl_lock``.
+
+``.ndo_init`` runs before device is visible in the system, ``.ndo_uninit``
+runs during de-registering after device is closed but other subsystems
+may still have outstanding references to the netdevice.
 
 MTU
 ===
@@ -64,8 +223,8 @@ ndo_do_ioctl:
 	Context: process
 
 ndo_get_stats:
-	Synchronization: dev_base_lock rwlock.
-	Context: nominally process, but don't sleep inside an rwlock
+	Synchronization: rtnl_lock() semaphore, dev_base_lock rwlock, or RCU.
+	Context: atomic (can't sleep under rwlock or RCU)
 
 ndo_start_xmit:
 	Synchronization: __netif_tx_lock spinlock.
diff --git a/Documentation/networking/packet_mmap.rst b/Documentation/networking/packet_mmap.rst
index 6c009ceb1183..500ef60b1b82 100644
--- a/Documentation/networking/packet_mmap.rst
+++ b/Documentation/networking/packet_mmap.rst
@@ -8,7 +8,7 @@ Abstract
 ========
 
 This file documents the mmap() facility available with the PACKET
-socket interface on 2.4/2.6/3.x kernels. This type of sockets is used for
+socket interface. This type of sockets is used for
 
 i) capture network traffic with utilities like tcpdump,
 ii) transmit network traffic, or any other that needs raw
@@ -25,12 +25,12 @@ Please send your comments to
 Why use PACKET_MMAP
 ===================
 
-In Linux 2.4/2.6/3.x if PACKET_MMAP is not enabled, the capture process is very
+Non PACKET_MMAP capture process (plain AF_PACKET) is very
 inefficient. It uses very limited buffers and requires one system call to
 capture each packet, it requires two if you want to get packet's timestamp
 (like libpcap always does).
 
-In the other hand PACKET_MMAP is very efficient. PACKET_MMAP provides a size
+On the other hand PACKET_MMAP is very efficient. PACKET_MMAP provides a size
 configurable circular buffer mapped in user space that can be used to either
 send or receive packets. This way reading packets just needs to wait for them,
 most of the time there is no need to issue a single system call. Concerning
@@ -252,8 +252,7 @@ PACKET_MMAP setting constraints
 
 In kernel versions prior to 2.4.26 (for the 2.4 branch) and 2.6.5 (2.6 branch),
 the PACKET_MMAP buffer could hold only 32768 frames in a 32 bit architecture or
-16384 in a 64 bit architecture. For information on these kernel versions
-see http://pusa.uv.es/~ulisses/packet_mmap/packet_mmap.pre-2.4.26_2.6.5.txt
+16384 in a 64 bit architecture.
 
 Block size limit
 ----------------
@@ -437,7 +436,7 @@ and the following flags apply:
 Capture process
 ^^^^^^^^^^^^^^^
 
-     from include/linux/if_packet.h
+From include/linux/if_packet.h::
 
      #define TP_STATUS_COPY          (1 << 1)
      #define TP_STATUS_LOSING        (1 << 2)
diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst
index 0f55c6d540f9..9af3334d9ad0 100644
--- a/Documentation/networking/tls-offload.rst
+++ b/Documentation/networking/tls-offload.rst
@@ -530,7 +530,7 @@ TLS device feature flags only control adding of new TLS connection
 offloads, old connections will remain active after flags are cleared.
 
 TLS encryption cannot be offloaded to devices without checksum calculation
-offload. Hence, TLS TX device feature flag requires NETIF_F_HW_CSUM being set.
+offload. Hence, TLS TX device feature flag requires TX csum offload being set.
 Disabling the latter implies clearing the former. Disabling TX checksum offload
 should not affect old connections, and drivers should make sure checksum
 calculation does not break for them.
diff --git a/Documentation/process/4.Coding.rst b/Documentation/process/4.Coding.rst
index c27e59d2f702..0825dc496f22 100644
--- a/Documentation/process/4.Coding.rst
+++ b/Documentation/process/4.Coding.rst
@@ -249,10 +249,8 @@ features; most of these are found in the "kernel hacking" submenu.  Several
 of these options should be turned on for any kernel used for development or
 testing purposes.  In particular, you should turn on:
 
- - ENABLE_MUST_CHECK and FRAME_WARN to get an
-   extra set of warnings for problems like the use of deprecated interfaces
-   or ignoring an important return value from a function.  The output
-   generated by these warnings can be verbose, but one need not worry about
+ - FRAME_WARN to get warnings for stack frames larger than a given amount.
+   The output generated can be verbose, but one need not worry about
    warnings from other parts of the kernel.
 
  - DEBUG_OBJECTS will add code to track the lifetime of various objects
diff --git a/Documentation/process/submit-checklist.rst b/Documentation/process/submit-checklist.rst
index 1879f881c300..230ee42f872f 100644
--- a/Documentation/process/submit-checklist.rst
+++ b/Documentation/process/submit-checklist.rst
@@ -75,44 +75,44 @@ and elsewhere regarding submitting Linux kernel patches.
 13) Has been build- and runtime tested with and without ``CONFIG_SMP`` and
     ``CONFIG_PREEMPT.``
 
-16) All codepaths have been exercised with all lockdep features enabled.
+14) All codepaths have been exercised with all lockdep features enabled.
 
-17) All new ``/proc`` entries are documented under ``Documentation/``
+15) All new ``/proc`` entries are documented under ``Documentation/``
 
-18) All new kernel boot parameters are documented in
+16) All new kernel boot parameters are documented in
     ``Documentation/admin-guide/kernel-parameters.rst``.
 
-19) All new module parameters are documented with ``MODULE_PARM_DESC()``
+17) All new module parameters are documented with ``MODULE_PARM_DESC()``
 
-20) All new userspace interfaces are documented in ``Documentation/ABI/``.
+18) All new userspace interfaces are documented in ``Documentation/ABI/``.
     See ``Documentation/ABI/README`` for more information.
     Patches that change userspace interfaces should be CCed to
     linux-api@vger.kernel.org.
 
-21) Check that it all passes ``make headers_check``.
+19) Check that it all passes ``make headers_check``.
 
-22) Has been checked with injection of at least slab and page-allocation
+20) Has been checked with injection of at least slab and page-allocation
     failures.  See ``Documentation/fault-injection/``.
 
     If the new code is substantial, addition of subsystem-specific fault
     injection might be appropriate.
 
-23) Newly-added code has been compiled with ``gcc -W`` (use
+21) Newly-added code has been compiled with ``gcc -W`` (use
     ``make EXTRA_CFLAGS=-W``).  This will generate lots of noise, but is good
     for finding bugs like "warning: comparison between signed and unsigned".
 
-24) Tested after it has been merged into the -mm patchset to make sure
+22) Tested after it has been merged into the -mm patchset to make sure
     that it still works with all of the other queued patches and various
     changes in the VM, VFS, and other subsystems.
 
-25) All memory barriers {e.g., ``barrier()``, ``rmb()``, ``wmb()``} need a
+23) All memory barriers {e.g., ``barrier()``, ``rmb()``, ``wmb()``} need a
     comment in the source code that explains the logic of what they are doing
     and why.
 
-26) If any ioctl's are added by the patch, then also update
+24) If any ioctl's are added by the patch, then also update
     ``Documentation/userspace-api/ioctl/ioctl-number.rst``.
 
-27) If your modified source code depends on or uses any of the kernel
+25) If your modified source code depends on or uses any of the kernel
     APIs or features that are related to the following ``Kconfig`` symbols,
     then test multiple builds with the related ``Kconfig`` symbols disabled
     and/or ``=m`` (if that option is available) [not all of these at the
diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst
index fb8261a4be30..5ba54120bef7 100644
--- a/Documentation/process/submitting-patches.rst
+++ b/Documentation/process/submitting-patches.rst
@@ -411,6 +411,12 @@ Some people also put extra tags at the end.  They'll just be ignored for
 now, but you can do this to mark internal company procedures or just
 point out some special detail about the sign-off.
 
+Any further SoBs (Signed-off-by:'s) following the author's SoB are from
+people handling and transporting the patch, but were not involved in its
+development. SoB chains should reflect the **real** route a patch took
+as it was propagated to the maintainers and ultimately to Linus, with
+the first SoB entry signalling primary authorship of a single author.
+
 
 When to use Acked-by:, Cc:, and Co-developed-by:
 ------------------------------------------------
@@ -446,7 +452,7 @@ patch.  This tag documents that potentially interested parties
 have been included in the discussion.
 
 Co-developed-by: states that the patch was co-created by multiple developers;
-it is a used to give attribution to co-authors (in addition to the author
+it is used to give attribution to co-authors (in addition to the author
 attributed by the From: tag) when several people work on a single patch.  Since
 Co-developed-by: denotes authorship, every Co-developed-by: must be immediately
 followed by a Signed-off-by: of the associated co-author.  Standard sign-off
diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst
index fe52c314b763..b36af65a08ed 100644
--- a/Documentation/sound/alsa-configuration.rst
+++ b/Documentation/sound/alsa-configuration.rst
@@ -1501,7 +1501,7 @@ Module for Digigram miXart8 sound cards.
 
 This module supports multiple cards.
 Note: One miXart8 board will be represented as 4 alsa cards.
-See MIXART.txt for details.
+See Documentation/sound/cards/mixart.rst for details.
 
 When the driver is compiled as a module and the hotplug firmware
 is supported, the firmware data is loaded via hotplug automatically.
diff --git a/Documentation/sound/kernel-api/writing-an-alsa-driver.rst b/Documentation/sound/kernel-api/writing-an-alsa-driver.rst
index 73bbd59afc33..e6365836fa8b 100644
--- a/Documentation/sound/kernel-api/writing-an-alsa-driver.rst
+++ b/Documentation/sound/kernel-api/writing-an-alsa-driver.rst
@@ -71,7 +71,7 @@ core/oss
 The codes for PCM and mixer OSS emulation modules are stored in this
 directory. The rawmidi OSS emulation is included in the ALSA rawmidi
 code since it's quite small. The sequencer code is stored in
-``core/seq/oss`` directory (see `below <#core-seq-oss>`__).
+``core/seq/oss`` directory (see `below <core/seq/oss_>`__).
 
 core/seq
 ~~~~~~~~
@@ -382,7 +382,7 @@ where ``enable[dev]`` is the module option.
 Each time the ``probe`` callback is called, check the availability of
 the device. If not available, simply increment the device index and
 returns. dev will be incremented also later (`step 7
-<#set-the-pci-driver-data-and-return-zero>`__).
+<7) Set the PCI driver data and return zero._>`__).
 
 2) Create a card instance
 ~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -450,10 +450,10 @@ field contains the information shown in ``/proc/asound/cards``.
 5) Create other components, such as mixer, MIDI, etc.
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Here you define the basic components such as `PCM <#PCM-Interface>`__,
-mixer (e.g. `AC97 <#API-for-AC97-Codec>`__), MIDI (e.g.
-`MPU-401 <#MIDI-MPU401-UART-Interface>`__), and other interfaces.
-Also, if you want a `proc file <#Proc-Interface>`__, define it here,
+Here you define the basic components such as `PCM <PCM Interface_>`__,
+mixer (e.g. `AC97 <API for AC97 Codec_>`__), MIDI (e.g.
+`MPU-401 <MIDI (MPU401-UART) Interface_>`__), and other interfaces.
+Also, if you want a `proc file <Proc Interface_>`__, define it here,
 too.
 
 6) Register the card instance.
@@ -941,7 +941,7 @@ The allocation of an interrupt source is done like this:
   chip->irq = pci->irq;
 
 where :c:func:`snd_mychip_interrupt()` is the interrupt handler
-defined `later <#pcm-interface-interrupt-handler>`__. Note that
+defined `later <PCM Interrupt Handler_>`__. Note that
 ``chip->irq`` should be defined only when :c:func:`request_irq()`
 succeeded.
 
@@ -3104,7 +3104,7 @@ processing the output stream in the irq handler.
 
 If the MPU-401 interface shares its interrupt with the other logical
 devices on the card, set ``MPU401_INFO_IRQ_HOOK`` (see
-`below <#MIDI-Interrupt-Handler>`__).
+`below <MIDI Interrupt Handler_>`__).
 
 Usually, the port address corresponds to the command port and port + 1
 corresponds to the data port. If not, you may change the ``cport``
diff --git a/Documentation/sphinx/parse-headers.pl b/Documentation/sphinx/parse-headers.pl
index 1910079f984f..b063f2f1cfb2 100755
--- a/Documentation/sphinx/parse-headers.pl
+++ b/Documentation/sphinx/parse-headers.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
 use strict;
 use Text::Tabs;
 use Getopt::Long;
diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py
index 1548d8420499..54492aa813b9 100755
--- a/Documentation/target/tcm_mod_builder.py
+++ b/Documentation/target/tcm_mod_builder.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 # The TCM v4 multi-protocol fabric module generation script for drivers/target/$NEW_MOD
 #
 # Copyright (c) 2010 Rising Tide Systems
diff --git a/Documentation/trace/postprocess/decode_msr.py b/Documentation/trace/postprocess/decode_msr.py
index 0ab40e0db580..aa9cc7abd5c2 100644
--- a/Documentation/trace/postprocess/decode_msr.py
+++ b/Documentation/trace/postprocess/decode_msr.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 # add symbolic names to read_msr / write_msr in trace
 # decode_msr msr-index.h < trace
 import sys
diff --git a/Documentation/trace/postprocess/trace-pagealloc-postprocess.pl b/Documentation/trace/postprocess/trace-pagealloc-postprocess.pl
index 0a120aae33ce..b9b7d80c2f9d 100644
--- a/Documentation/trace/postprocess/trace-pagealloc-postprocess.pl
+++ b/Documentation/trace/postprocess/trace-pagealloc-postprocess.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
 # This is a POC (proof of concept or piece of crap, take your pick) for reading the
 # text representation of trace output related to page allocation. It makes an attempt
 # to extract some high-level information on what is going on. The accuracy of the parser
diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
index 995da15b16ca..2f4e39875fb3 100644
--- a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
+++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
 # This is a POC for reading the text representation of trace output related to
 # page reclaim. It makes an attempt to extract some high-level information on
 # what is going on. The accuracy of the parser may vary
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index e00a66d72372..c136e254b496 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -262,6 +262,18 @@ The KVM_RUN ioctl (cf.) communicates with userspace via a shared
 memory region.  This ioctl returns the size of that region.  See the
 KVM_RUN documentation for details.
 
+Besides the size of the KVM_RUN communication region, other areas of
+the VCPU file descriptor can be mmap-ed, including:
+
+- if KVM_CAP_COALESCED_MMIO is available, a page at
+  KVM_COALESCED_MMIO_PAGE_OFFSET * PAGE_SIZE; for historical reasons,
+  this page is included in the result of KVM_GET_VCPU_MMAP_SIZE.
+  KVM_CAP_COALESCED_MMIO is not documented yet.
+
+- if KVM_CAP_DIRTY_LOG_RING is available, a number of pages at
+  KVM_DIRTY_LOG_PAGE_OFFSET * PAGE_SIZE.  For more information on
+  KVM_CAP_DIRTY_LOG_RING, see section 8.3.
+
 
 4.6 KVM_SET_MEMORY_REGION
 -------------------------
@@ -380,9 +392,14 @@ This ioctl is obsolete and has been removed.
 
 Errors:
 
-  =====      =============================
+  =======    ==============================================================
   EINTR      an unmasked signal is pending
-  =====      =============================
+  ENOEXEC    the vcpu hasn't been initialized or the guest tried to execute
+             instructions from device memory (arm64)
+  ENOSYS     data abort outside memslots with no syndrome info and
+             KVM_CAP_ARM_NISV_TO_USER not enabled (arm64)
+  EPERM      SVE feature set but not finalized (arm64)
+  =======    ==============================================================
 
 This ioctl is used to run a guest virtual cpu.  While there are no
 explicit parameters, there is an implicit parameter block that can be
@@ -4455,9 +4472,9 @@ that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present.
 4.118 KVM_GET_SUPPORTED_HV_CPUID
 --------------------------------
 
-:Capability: KVM_CAP_HYPERV_CPUID
+:Capability: KVM_CAP_HYPERV_CPUID (vcpu), KVM_CAP_SYS_HYPERV_CPUID (system)
 :Architectures: x86
-:Type: vcpu ioctl
+:Type: system ioctl, vcpu ioctl
 :Parameters: struct kvm_cpuid2 (in/out)
 :Returns: 0 on success, -1 on error
 
@@ -4502,9 +4519,6 @@ Currently, the following list of CPUID leaves are returned:
  - HYPERV_CPUID_SYNDBG_INTERFACE
  - HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES
 
-HYPERV_CPUID_NESTED_FEATURES leaf is only exposed when Enlightened VMCS was
-enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).
-
 Userspace invokes KVM_GET_SUPPORTED_HV_CPUID by passing a kvm_cpuid2 structure
 with the 'nent' field indicating the number of entries in the variable-size
 array 'entries'.  If the number of entries is too low to describe all Hyper-V
@@ -4515,6 +4529,15 @@ number of valid entries in the 'entries' array, which is then filled.
 'index' and 'flags' fields in 'struct kvm_cpuid_entry2' are currently reserved,
 userspace should not expect to get any particular value there.
 
+Note, vcpu version of KVM_GET_SUPPORTED_HV_CPUID is currently deprecated. Unlike
+system ioctl which exposes all supported feature bits unconditionally, vcpu
+version has the following quirks:
+- HYPERV_CPUID_NESTED_FEATURES leaf and HV_X64_ENLIGHTENED_VMCS_RECOMMENDED
+  feature bit are only exposed when Enlightened VMCS was previously enabled
+  on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).
+- HV_STIMER_DIRECT_MODE_AVAILABLE bit is only exposed with in-kernel LAPIC.
+  (presumes KVM_CREATE_IRQCHIP has already been called).
+
 4.119 KVM_ARM_VCPU_FINALIZE
 ---------------------------
 
@@ -6390,3 +6413,91 @@ When enabled, KVM will disable paravirtual features provided to the
 guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf
 (0x40000001). Otherwise, a guest may use the paravirtual features
 regardless of what has actually been exposed through the CPUID leaf.
+
+
+8.29 KVM_CAP_DIRTY_LOG_RING
+---------------------------
+
+:Architectures: x86
+:Parameters: args[0] - size of the dirty log ring
+
+KVM is capable of tracking dirty memory using ring buffers that are
+mmaped into userspace; there is one dirty ring per vcpu.
+
+The dirty ring is available to userspace as an array of
+``struct kvm_dirty_gfn``.  Each dirty entry it's defined as::
+
+  struct kvm_dirty_gfn {
+          __u32 flags;
+          __u32 slot; /* as_id | slot_id */
+          __u64 offset;
+  };
+
+The following values are defined for the flags field to define the
+current state of the entry::
+
+  #define KVM_DIRTY_GFN_F_DIRTY           BIT(0)
+  #define KVM_DIRTY_GFN_F_RESET           BIT(1)
+  #define KVM_DIRTY_GFN_F_MASK            0x3
+
+Userspace should call KVM_ENABLE_CAP ioctl right after KVM_CREATE_VM
+ioctl to enable this capability for the new guest and set the size of
+the rings.  Enabling the capability is only allowed before creating any
+vCPU, and the size of the ring must be a power of two.  The larger the
+ring buffer, the less likely the ring is full and the VM is forced to
+exit to userspace. The optimal size depends on the workload, but it is
+recommended that it be at least 64 KiB (4096 entries).
+
+Just like for dirty page bitmaps, the buffer tracks writes to
+all user memory regions for which the KVM_MEM_LOG_DIRTY_PAGES flag was
+set in KVM_SET_USER_MEMORY_REGION.  Once a memory region is registered
+with the flag set, userspace can start harvesting dirty pages from the
+ring buffer.
+
+An entry in the ring buffer can be unused (flag bits ``00``),
+dirty (flag bits ``01``) or harvested (flag bits ``1X``).  The
+state machine for the entry is as follows::
+
+          dirtied         harvested        reset
+     00 -----------> 01 -------------> 1X -------+
+      ^                                          |
+      |                                          |
+      +------------------------------------------+
+
+To harvest the dirty pages, userspace accesses the mmaped ring buffer
+to read the dirty GFNs.  If the flags has the DIRTY bit set (at this stage
+the RESET bit must be cleared), then it means this GFN is a dirty GFN.
+The userspace should harvest this GFN and mark the flags from state
+``01b`` to ``1Xb`` (bit 0 will be ignored by KVM, but bit 1 must be set
+to show that this GFN is harvested and waiting for a reset), and move
+on to the next GFN.  The userspace should continue to do this until the
+flags of a GFN have the DIRTY bit cleared, meaning that it has harvested
+all the dirty GFNs that were available.
+
+It's not necessary for userspace to harvest the all dirty GFNs at once.
+However it must collect the dirty GFNs in sequence, i.e., the userspace
+program cannot skip one dirty GFN to collect the one next to it.
+
+After processing one or more entries in the ring buffer, userspace
+calls the VM ioctl KVM_RESET_DIRTY_RINGS to notify the kernel about
+it, so that the kernel will reprotect those collected GFNs.
+Therefore, the ioctl must be called *before* reading the content of
+the dirty pages.
+
+The dirty ring can get full.  When it happens, the KVM_RUN of the
+vcpu will return with exit reason KVM_EXIT_DIRTY_LOG_FULL.
+
+The dirty ring interface has a major difference comparing to the
+KVM_GET_DIRTY_LOG interface in that, when reading the dirty ring from
+userspace, it's still possible that the kernel has not yet flushed the
+processor's dirty page buffers into the kernel buffer (with dirty bitmaps, the
+flushing is done by the KVM_GET_DIRTY_LOG ioctl).  To achieve that, one
+needs to kick the vcpu out of KVM_RUN using a signal.  The resulting
+vmexit ensures that all dirty GFNs are flushed to the dirty rings.
+
+NOTE: the capability KVM_CAP_DIRTY_LOG_RING and the corresponding
+ioctl KVM_RESET_DIRTY_RINGS are mutual exclusive to the existing ioctls
+KVM_GET_DIRTY_LOG and KVM_CLEAR_DIRTY_LOG.  After enabling
+KVM_CAP_DIRTY_LOG_RING with an acceptable dirty ring size, the virtual
+machine will switch to ring-buffer dirty page tracking and further
+KVM_GET_DIRTY_LOG or KVM_CLEAR_DIRTY_LOG ioctls will fail.
diff --git a/Documentation/virt/kvm/arm/pvtime.rst b/Documentation/virt/kvm/arm/pvtime.rst
index 687b60d76ca9..392521af7c90 100644
--- a/Documentation/virt/kvm/arm/pvtime.rst
+++ b/Documentation/virt/kvm/arm/pvtime.rst
@@ -19,8 +19,8 @@ Two new SMCCC compatible hypercalls are defined:
 
 These are only available in the SMC64/HVC64 calling convention as
 paravirtualized time is not available to 32 bit Arm guests. The existence of
-the PV_FEATURES hypercall should be probed using the SMCCC 1.1 ARCH_FEATURES
-mechanism before calling it.
+the PV_TIME_FEATURES hypercall should be probed using the SMCCC 1.1
+ARCH_FEATURES mechanism before calling it.
 
 PV_TIME_FEATURES
     ============= ========    ==========
diff --git a/MAINTAINERS b/MAINTAINERS
index 8798a6497678..00836f6452f0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -203,8 +203,8 @@ F:	include/uapi/linux/nl80211.h
 F:	net/wireless/
 
 8169 10/100/1000 GIGABIT ETHERNET DRIVER
-M:	Realtek linux nic maintainers <nic_swsd@realtek.com>
 M:	Heiner Kallweit <hkallweit1@gmail.com>
+M:	nic_swsd@realtek.com
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/realtek/r8169*
@@ -820,7 +820,6 @@ M:	Netanel Belgazal <netanel@amazon.com>
 M:	Arthur Kiyanovski <akiyano@amazon.com>
 R:	Guy Tzalik <gtzalik@amazon.com>
 R:	Saeed Bishara <saeedb@amazon.com>
-R:	Zorik Machulsky <zorik@amazon.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/device_drivers/ethernet/amazon/ena.rst
@@ -907,7 +906,7 @@ AMD KFD
 M:	Felix Kuehling <Felix.Kuehling@amd.com>
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
-T:	git git://people.freedesktop.org/~agd5f/linux
+T:	git https://gitlab.freedesktop.org/agd5f/linux.git
 F:	drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd*.[ch]
 F:	drivers/gpu/drm/amd/amdkfd/
 F:	drivers/gpu/drm/amd/include/cik_structs.h
@@ -1183,7 +1182,7 @@ F:	Documentation/devicetree/bindings/interrupt-controller/google,goldfish-pic.tx
 F:	drivers/irqchip/irq-goldfish-pic.c
 
 ANDROID GOLDFISH RTC DRIVER
-M:	Miodrag Dinic <miodrag.dinic@mips.com>
+M:	Jiaxun Yang <jiaxun.yang@flygoat.com>
 S:	Supported
 F:	Documentation/devicetree/bindings/rtc/google,goldfish-rtc.txt
 F:	drivers/rtc/rtc-goldfish.c
@@ -2119,7 +2118,7 @@ N:	atmel
 ARM/Microchip Sparx5 SoC support
 M:	Lars Povlsen <lars.povlsen@microchip.com>
 M:	Steen Hegelund <Steen.Hegelund@microchip.com>
-M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M:	UNGLinuxDriver@microchip.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 T:	git git://github.com/microchip-ung/linux-upstream.git
@@ -2942,7 +2941,6 @@ S:	Maintained
 F:	drivers/hwmon/asus_atk0110.c
 
 ATLX ETHERNET DRIVERS
-M:	Jay Cliburn <jcliburn@gmail.com>
 M:	Chris Snook <chris.snook@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -3199,6 +3197,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 F:	block/
 F:	drivers/block/
+F:	fs/block_dev.c
 F:	include/linux/blk*
 F:	kernel/trace/blktrace.c
 F:	lib/sbitmap.c
@@ -3555,7 +3554,7 @@ S:	Supported
 F:	drivers/net/ethernet/broadcom/bnxt/
 
 BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER
-M:	Arend van Spriel <arend.vanspriel@broadcom.com>
+M:	Arend van Spriel <aspriel@gmail.com>
 M:	Franky Lin <franky.lin@broadcom.com>
 M:	Hante Meuleman <hante.meuleman@broadcom.com>
 M:	Chi-hsien Lin <chi-hsien.lin@infineon.com>
@@ -3882,7 +3881,7 @@ F:	drivers/mtd/nand/raw/cadence-nand-controller.c
 CADENCE USB3 DRD IP DRIVER
 M:	Peter Chen <peter.chen@nxp.com>
 M:	Pawel Laszczak <pawell@cadence.com>
-M:	Roger Quadros <rogerq@ti.com>
+R:	Roger Quadros <rogerq@kernel.org>
 R:	Aswath Govindraju <a-govindraju@ti.com>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
@@ -3960,7 +3959,7 @@ F:	net/can/
 CAN-J1939 NETWORK LAYER
 M:	Robin van der Gracht <robin@protonic.nl>
 M:	Oleksij Rempel <o.rempel@pengutronix.de>
-R:	Pengutronix Kernel Team <kernel@pengutronix.de>
+R:	kernel@pengutronix.de
 L:	linux-can@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/j1939.rst
@@ -4354,8 +4353,8 @@ T:	git git://linuxtv.org/media_tree.git
 F:	drivers/media/pci/cobalt/
 
 COCCINELLE/Semantic Patches (SmPL)
-M:	Julia Lawall <Julia.Lawall@lip6.fr>
-M:	Gilles Muller <Gilles.Muller@lip6.fr>
+M:	Julia Lawall <Julia.Lawall@inria.fr>
+M:	Gilles Muller <Gilles.Muller@inria.fr>
 M:	Nicolas Palix <nicolas.palix@imag.fr>
 M:	Michal Marek <michal.lkml@markovi.net>
 L:	cocci@systeme.lip6.fr (moderated for non-subscribers)
@@ -4587,7 +4586,7 @@ B:	https://bugzilla.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
 F:	Documentation/admin-guide/pm/cpuidle.rst
 F:	Documentation/driver-api/pm/cpuidle.rst
-F:	drivers/cpuidle/*
+F:	drivers/cpuidle/
 F:	include/linux/cpuidle.h
 
 CPU POWER MONITORING SUBSYSTEM
@@ -4921,9 +4920,8 @@ F:	Documentation/scsi/dc395x.rst
 F:	drivers/scsi/dc395x.*
 
 DCCP PROTOCOL
-M:	Gerrit Renker <gerrit@erg.abdn.ac.uk>
 L:	dccp@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	http://www.linuxfoundation.org/collaborate/workgroups/networking/dccp
 F:	include/linux/dccp.h
 F:	include/linux/tfrc.h
@@ -5297,6 +5295,12 @@ F:	include/linux/dma-mapping.h
 F:	include/linux/dma-map-ops.h
 F:	kernel/dma/
 
+DMA MAPPING BENCHMARK
+M:	Barry Song <song.bao.hua@hisilicon.com>
+L:	iommu@lists.linux-foundation.org
+F:	kernel/dma/map_benchmark.c
+F:	tools/testing/selftests/dma/
+
 DMA-BUF HEAPS FRAMEWORK
 M:	Sumit Semwal <sumit.semwal@linaro.org>
 R:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
@@ -7356,7 +7360,6 @@ L:	linux-hardening@vger.kernel.org
 S:	Maintained
 F:	Documentation/kbuild/gcc-plugins.rst
 F:	scripts/Makefile.gcc-plugins
-F:	scripts/gcc-plugin.sh
 F:	scripts/gcc-plugins/
 
 GCOV BASED KERNEL PROFILING
@@ -9233,7 +9236,7 @@ F:	tools/testing/selftests/sgx/*
 K:	\bSGX_
 
 INTERCONNECT API
-M:	Georgi Djakov <georgi.djakov@linaro.org>
+M:	Georgi Djakov <djakov@kernel.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/interconnect/
@@ -9266,7 +9269,7 @@ F:	drivers/net/ethernet/sgi/ioc3-eth.c
 
 IOMAP FILESYSTEM LIBRARY
 M:	Christoph Hellwig <hch@infradead.org>
-M:	Darrick J. Wong <darrick.wong@oracle.com>
+M:	Darrick J. Wong <djwong@kernel.org>
 M:	linux-xfs@vger.kernel.org
 M:	linux-fsdevel@vger.kernel.org
 L:	linux-xfs@vger.kernel.org
@@ -9320,7 +9323,6 @@ W:	http://www.adaptec.com/
 F:	drivers/scsi/ips*
 
 IPVS
-M:	Wensong Zhang <wensong@linux-vs.org>
 M:	Simon Horman <horms@verge.net.au>
 M:	Julian Anastasov <ja@ssi.bg>
 L:	netdev@vger.kernel.org
@@ -9769,7 +9771,7 @@ F:	tools/testing/selftests/kvm/s390x/
 
 KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86)
 M:	Paolo Bonzini <pbonzini@redhat.com>
-R:	Sean Christopherson <sean.j.christopherson@intel.com>
+R:	Sean Christopherson <seanjc@google.com>
 R:	Vitaly Kuznetsov <vkuznets@redhat.com>
 R:	Wanpeng Li <wanpengli@tencent.com>
 R:	Jim Mattson <jmattson@google.com>
@@ -10253,7 +10255,6 @@ S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	Documentation/atomic_bitops.txt
 F:	Documentation/atomic_t.txt
-F:	Documentation/core-api/atomic_ops.rst
 F:	Documentation/core-api/refcount-vs-atomic.rst
 F:	Documentation/litmus-tests/
 F:	Documentation/memory-barriers.txt
@@ -10840,7 +10841,7 @@ F:	drivers/media/radio/radio-maxiradio*
 
 MCAN MMIO DEVICE DRIVER
 M:	Dan Murphy <dmurphy@ti.com>
-M:	Sriram Dash <sriram.dash@samsung.com>
+M:	Pankaj Sharma <pankj.sharma@samsung.com>
 L:	linux-can@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/can/bosch,m_can.yaml
@@ -11660,7 +11661,7 @@ F:	drivers/media/platform/atmel/atmel-isi.h
 
 MICROCHIP KSZ SERIES ETHERNET SWITCH DRIVER
 M:	Woojung Huh <woojung.huh@microchip.com>
-M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M:	UNGLinuxDriver@microchip.com
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
@@ -11670,7 +11671,7 @@ F:	net/dsa/tag_ksz.c
 
 MICROCHIP LAN743X ETHERNET DRIVER
 M:	Bryan Whitehead <bryan.whitehead@microchip.com>
-M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M:	UNGLinuxDriver@microchip.com
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/microchip/lan743x_*
@@ -11764,7 +11765,7 @@ F:	drivers/net/wireless/microchip/wilc1000/
 
 MICROSEMI MIPS SOCS
 M:	Alexandre Belloni <alexandre.belloni@bootlin.com>
-M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M:	UNGLinuxDriver@microchip.com
 L:	linux-mips@vger.kernel.org
 S:	Supported
 F:	Documentation/devicetree/bindings/mips/mscc.txt
@@ -12411,7 +12412,6 @@ F:	tools/testing/selftests/net/ipsec.c
 
 NETWORKING [IPv4/IPv6]
 M:	"David S. Miller" <davem@davemloft.net>
-M:	Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
 M:	Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -12468,7 +12468,6 @@ F:	net/ipv6/tcp*.c
 
 NETWORKING [TLS]
 M:	Boris Pismenny <borisp@nvidia.com>
-M:	Aviad Yehezkel <aviadye@nvidia.com>
 M:	John Fastabend <john.fastabend@gmail.com>
 M:	Daniel Borkmann <daniel@iogearbox.net>
 M:	Jakub Kicinski <kuba@kernel.org>
@@ -12818,10 +12817,10 @@ F:	tools/objtool/
 F:	include/linux/objtool.h
 
 OCELOT ETHERNET SWITCH DRIVER
-M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
 M:	Vladimir Oltean <vladimir.oltean@nxp.com>
 M:	Claudiu Manoil <claudiu.manoil@nxp.com>
 M:	Alexandre Belloni <alexandre.belloni@bootlin.com>
+M:	UNGLinuxDriver@microchip.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/dsa/ocelot/*
@@ -12843,7 +12842,7 @@ F:	include/misc/ocxl*
 F:	include/uapi/misc/ocxl.h
 
 OMAP AUDIO SUPPORT
-M:	Peter Ujfalusi <peter.ujfalusi@ti.com>
+M:	Peter Ujfalusi <peter.ujfalusi@gmail.com>
 M:	Jarkko Nikula <jarkko.nikula@bitmer.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 L:	linux-omap@vger.kernel.org
@@ -13883,7 +13882,7 @@ F:	drivers/platform/x86/peaq-wmi.c
 
 PENSANDO ETHERNET DRIVERS
 M:	Shannon Nelson <snelson@pensando.io>
-M:	Pensando Drivers <drivers@pensando.io>
+M:	drivers@pensando.io
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/device_drivers/ethernet/pensando/ionic.rst
@@ -14662,7 +14661,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
 F:	drivers/net/wireless/ath/ath11k/
 
 QUALCOMM ATHEROS ATH9K WIRELESS DRIVER
-M:	QCA ath9k Development <ath9k-devel@qca.qualcomm.com>
+M:	ath9k-devel@qca.qualcomm.com
 L:	linux-wireless@vger.kernel.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath9k
@@ -14813,7 +14812,7 @@ M:	Alex Deucher <alexander.deucher@amd.com>
 M:	Christian König <christian.koenig@amd.com>
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
-T:	git git://people.freedesktop.org/~agd5f/linux
+T:	git https://gitlab.freedesktop.org/agd5f/linux.git
 F:	drivers/gpu/drm/amd/
 F:	drivers/gpu/drm/radeon/
 F:	include/uapi/drm/amdgpu_drm.h
@@ -15108,7 +15107,7 @@ RENESAS CLOCK DRIVERS
 M:	Geert Uytterhoeven <geert+renesas@glider.be>
 L:	linux-renesas-soc@vger.kernel.org
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-drivers.git clk-renesas
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-drivers.git renesas-clk
 F:	Documentation/devicetree/bindings/clock/renesas,*
 F:	drivers/clk/renesas/
 
@@ -16314,6 +16313,7 @@ M:	Pekka Enberg <penberg@kernel.org>
 M:	David Rientjes <rientjes@google.com>
 M:	Joonsoo Kim <iamjoonsoo.kim@lge.com>
 M:	Andrew Morton <akpm@linux-foundation.org>
+M:	Vlastimil Babka <vbabka@suse.cz>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	include/linux/sl?b*.h
@@ -16703,6 +16703,8 @@ M:	Samuel Thibault <samuel.thibault@ens-lyon.org>
 L:	speakup@linux-speakup.org
 S:	Odd Fixes
 W:	http://www.linux-speakup.org/
+W:	https://github.com/linux-speakup/speakup
+B:	https://github.com/linux-speakup/speakup/issues
 F:	drivers/accessibility/speakup/
 
 SPEAR CLOCK FRAMEWORK SUPPORT
@@ -16910,6 +16912,22 @@ M:	Ion Badulescu <ionut@badula.org>
 S:	Odd Fixes
 F:	drivers/net/ethernet/adaptec/starfire*
 
+STATIC BRANCH/CALL
+M:	Peter Zijlstra <peterz@infradead.org>
+M:	Josh Poimboeuf <jpoimboe@redhat.com>
+M:	Jason Baron <jbaron@akamai.com>
+R:	Steven Rostedt <rostedt@goodmis.org>
+R:	Ard Biesheuvel <ardb@kernel.org>
+S:	Supported
+F:	arch/*/include/asm/jump_label*.h
+F:	arch/*/include/asm/static_call*.h
+F:	arch/*/kernel/jump_label.c
+F:	arch/*/kernel/static_call.c
+F:	include/linux/jump_label*.h
+F:	include/linux/static_call*.h
+F:	kernel/jump_label.c
+F:	kernel/static_call.c
+
 STEC S1220 SKD DRIVER
 M:	Damien Le Moal <Damien.LeMoal@wdc.com>
 L:	linux-block@vger.kernel.org
@@ -17518,7 +17536,7 @@ F:	arch/xtensa/
 F:	drivers/irqchip/irq-xtensa-*
 
 TEXAS INSTRUMENTS ASoC DRIVERS
-M:	Peter Ujfalusi <peter.ujfalusi@ti.com>
+M:	Peter Ujfalusi <peter.ujfalusi@gmail.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Maintained
 F:	sound/soc/ti/
@@ -17530,6 +17548,19 @@ S:	Supported
 F:	Documentation/devicetree/bindings/iio/dac/ti,dac7612.txt
 F:	drivers/iio/dac/ti-dac7612.c
 
+TEXAS INSTRUMENTS DMA DRIVERS
+M:	Peter Ujfalusi <peter.ujfalusi@gmail.com>
+L:	dmaengine@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt
+F:	Documentation/devicetree/bindings/dma/ti-edma.txt
+F:	Documentation/devicetree/bindings/dma/ti/
+F:	drivers/dma/ti/
+X:	drivers/dma/ti/cppi41.c
+F:	include/linux/dma/k3-udma-glue.h
+F:	include/linux/dma/ti-cppi5.h
+F:	include/linux/dma/k3-psil.h
+
 TEXAS INSTRUMENTS' SYSTEM CONTROL INTERFACE (TISCI) PROTOCOL DRIVER
 M:	Nishanth Menon <nm@ti.com>
 M:	Tero Kristo <t-kristo@ti.com>
@@ -17815,7 +17846,7 @@ F:	Documentation/devicetree/bindings/net/nfc/trf7970a.txt
 F:	drivers/nfc/trf7970a.c
 
 TI TWL4030 SERIES SOC CODEC DRIVER
-M:	Peter Ujfalusi <peter.ujfalusi@ti.com>
+M:	Peter Ujfalusi <peter.ujfalusi@gmail.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Maintained
 F:	sound/soc/codecs/twl4030*
@@ -18347,7 +18378,7 @@ F:	include/linux/usb/isp116x.h
 
 USB LAN78XX ETHERNET DRIVER
 M:	Woojung Huh <woojung.huh@microchip.com>
-M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M:	UNGLinuxDriver@microchip.com
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/microchip,lan78xx.txt
@@ -18461,7 +18492,7 @@ F:	drivers/net/usb/smsc75xx.*
 
 USB SMSC95XX ETHERNET DRIVER
 M:	Steve Glendinning <steve.glendinning@shawell.net>
-M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M:	UNGLinuxDriver@microchip.com
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/usb/smsc95xx.*
@@ -19008,7 +19039,7 @@ F:	drivers/input/mouse/vmmouse.h
 
 VMWARE VMXNET3 ETHERNET DRIVER
 M:	Ronak Doshi <doshir@vmware.com>
-M:	"VMware, Inc." <pv-drivers@vmware.com>
+M:	pv-drivers@vmware.com
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/vmxnet3/
@@ -19035,7 +19066,6 @@ K:	regulator_get_optional
 
 VRF
 M:	David Ahern <dsahern@kernel.org>
-M:	Shrijeet Mukherjee <shrijeet@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/vrf.rst
@@ -19482,7 +19512,7 @@ F:	arch/x86/xen/*swiotlb*
 F:	drivers/xen/*swiotlb*
 
 XFS FILESYSTEM
-M:	Darrick J. Wong <darrick.wong@oracle.com>
+M:	Darrick J. Wong <djwong@kernel.org>
 M:	linux-xfs@vger.kernel.org
 L:	linux-xfs@vger.kernel.org
 S:	Supported
diff --git a/Makefile b/Makefile
index e30cf02da8b8..b0e4767735dc 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
-PATCHLEVEL = 10
+PATCHLEVEL = 11
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc4
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
@@ -450,7 +450,7 @@ LEX		= flex
 YACC		= bison
 AWK		= awk
 INSTALLKERNEL  := installkernel
-DEPMOD		= /sbin/depmod
+DEPMOD		= depmod
 PERL		= perl
 PYTHON		= python
 PYTHON3		= python3
diff --git a/arch/Kconfig b/arch/Kconfig
index a08999dfcf16..24862d15f3a3 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -976,16 +976,16 @@ config VMAP_STACK
 	default y
 	bool "Use a virtually-mapped stack"
 	depends on HAVE_ARCH_VMAP_STACK
-	depends on !KASAN || KASAN_VMALLOC
+	depends on !KASAN || KASAN_HW_TAGS || KASAN_VMALLOC
 	help
 	  Enable this if you want the use virtually-mapped kernel stacks
 	  with guard pages.  This causes kernel stack overflows to be
 	  caught immediately rather than causing difficult-to-diagnose
 	  corruption.
 
-	  To use this with KASAN, the architecture must support backing
-	  virtual mappings with real shadow memory, and KASAN_VMALLOC must
-	  be enabled.
+	  To use this with software KASAN modes, the architecture must support
+	  backing virtual mappings with real shadow memory, and KASAN_VMALLOC
+	  must be enabled.
 
 config ARCH_OPTIONAL_KERNEL_RWX
 	def_bool n
@@ -1105,6 +1105,12 @@ config HAVE_ARCH_PFN_VALID
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	bool
 
+config ARCH_SPLIT_ARG64
+	bool
+	help
+	   If a 32-bit architecture requires 64-bit arguments to be split into
+	   pairs of 32-bit arguments, select this option.
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/alpha/include/asm/local64.h b/arch/alpha/include/asm/local64.h
deleted file mode 100644
index 36c93b5cc239..000000000000
--- a/arch/alpha/include/asm/local64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/local64.h>
diff --git a/arch/alpha/kernel/rtc.c b/arch/alpha/kernel/rtc.c
index 1b1d5963ac55..ce3077946e1d 100644
--- a/arch/alpha/kernel/rtc.c
+++ b/arch/alpha/kernel/rtc.c
@@ -216,6 +216,6 @@ alpha_rtc_init(void)
 		rtc->ops = &remote_rtc_ops;
 #endif
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 device_initcall(alpha_rtc_init);
diff --git a/arch/alpha/kernel/sys_jensen.c b/arch/alpha/kernel/sys_jensen.c
index 0a2ab6cb18db..e5d870ff225f 100644
--- a/arch/alpha/kernel/sys_jensen.c
+++ b/arch/alpha/kernel/sys_jensen.c
@@ -7,7 +7,7 @@
  *
  * Code supporting the Jensen.
  */
-
+#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/mm.h>
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 0c6bf0d1df7a..578bdbbb0fa7 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -102,16 +102,22 @@ libs-y		+= arch/arc/lib/ $(LIBGCC)
 
 boot		:= arch/arc/boot
 
-#default target for make without any arguments.
-KBUILD_IMAGE	:= $(boot)/bootpImage
-
-all:	bootpImage
-bootpImage: vmlinux
-
-boot_targets += uImage uImage.bin uImage.gz
+boot_targets := uImage.bin uImage.gz uImage.lzma
 
+PHONY += $(boot_targets)
 $(boot_targets): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
+uimage-default-y			:= uImage.bin
+uimage-default-$(CONFIG_KERNEL_GZIP)	:= uImage.gz
+uimage-default-$(CONFIG_KERNEL_LZMA)	:= uImage.lzma
+
+PHONY += uImage
+uImage: $(uimage-default-y)
+	@ln -sf $< $(boot)/uImage
+	@$(kecho) '  Image $(boot)/uImage is ready'
+
+CLEAN_FILES += $(boot)/uImage
+
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
diff --git a/arch/arc/boot/Makefile b/arch/arc/boot/Makefile
index 538b92f4dd25..5648748c285f 100644
--- a/arch/arc/boot/Makefile
+++ b/arch/arc/boot/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-targets := vmlinux.bin vmlinux.bin.gz uImage
 
 # uImage build relies on mkimage being availble on your host for ARC target
 # You will need to build u-boot for ARC, rename mkimage to arc-elf32-mkimage
@@ -7,23 +6,18 @@ targets := vmlinux.bin vmlinux.bin.gz uImage
 
 OBJCOPYFLAGS= -O binary -R .note -R .note.gnu.build-id -R .comment -S
 
-LINUX_START_TEXT = $$(readelf -h vmlinux | \
+LINUX_START_TEXT = $$($(READELF) -h vmlinux | \
 			grep "Entry point address" | grep -o 0x.*)
 
 UIMAGE_LOADADDR    = $(CONFIG_LINUX_LINK_BASE)
 UIMAGE_ENTRYADDR   = $(LINUX_START_TEXT)
 
-suffix-y := bin
-suffix-$(CONFIG_KERNEL_GZIP)	:= gz
-suffix-$(CONFIG_KERNEL_LZMA)	:= lzma
-
-targets += uImage
+targets += vmlinux.bin
+targets += vmlinux.bin.gz
+targets += vmlinux.bin.lzma
 targets += uImage.bin
 targets += uImage.gz
 targets += uImage.lzma
-extra-y += vmlinux.bin
-extra-y += vmlinux.bin.gz
-extra-y += vmlinux.bin.lzma
 
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
@@ -42,7 +36,3 @@ $(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
 
 $(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE
 	$(call if_changed,uimage,lzma)
-
-$(obj)/uImage: $(obj)/uImage.$(suffix-y)
-	@ln -sf $(notdir $<) $@
-	@echo '  Image $@ is ready'
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 81f4edec0c2a..3c1afa524b9c 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 generic-y += extable.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h
 generic-y += user.h
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index 23e41e890eda..ad9b7fe4dba3 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -10,6 +10,7 @@
 #ifndef __ASSEMBLY__
 
 #define clear_page(paddr)		memset((paddr), 0, PAGE_SIZE)
+#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 #define copy_page(to, from)		memcpy((to), (from), PAGE_SIZE)
 
 struct vm_area_struct;
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 1f5308abf36d..1743506081da 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -307,7 +307,7 @@ resume_user_mode_begin:
 	mov r0, sp	; pt_regs for arg to do_signal()/do_notify_resume()
 
 	GET_CURR_THR_INFO_FLAGS   r9
-	and.f  0,  r9, TIF_SIGPENDING|TIF_NOTIFY_SIGNAL
+	and.f  0,  r9, _TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL
 	bz .Lchk_notify_resume
 
 	; Normal Trap/IRQ entry only saves Scratch (caller-saved) regs
diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig
index 6b5c54576f54..a2d10c29fbcc 100644
--- a/arch/arc/plat-hsdk/Kconfig
+++ b/arch/arc/plat-hsdk/Kconfig
@@ -7,6 +7,7 @@ menuconfig ARC_SOC_HSDK
 	depends on ISA_ARCV2
 	select ARC_HAS_ACCL_REGS
 	select ARC_IRQ_NO_AUTOSAVE
+	select ARC_FPU_SAVE_RESTORE
 	select CLK_HSDK
 	select RESET_CONTROLLER
 	select RESET_HSDK
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index b8ade91281bc..138248999df7 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -68,6 +68,7 @@ config ARM
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
+	select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_PFN_VALID
 	select HAVE_ARCH_SECCOMP
@@ -245,7 +246,7 @@ config ARM_PATCH_PHYS_VIRT
 	  kernel in system memory.
 
 	  This can only be used with non-XIP MMU kernels where the base
-	  of physical memory is at a 16MB boundary.
+	  of physical memory is at a 2 MiB boundary.
 
 	  Only disable this option if you know that you do not require
 	  this feature (eg, building a kernel for a single machine) and
@@ -1298,6 +1299,15 @@ config PAGE_OFFSET
 	default 0xB0000000 if VMSPLIT_3G_OPT
 	default 0xC0000000
 
+config KASAN_SHADOW_OFFSET
+	hex
+	depends on KASAN
+	default 0x1f000000 if PAGE_OFFSET=0x40000000
+	default 0x5f000000 if PAGE_OFFSET=0x80000000
+	default 0x9f000000 if PAGE_OFFSET=0xC0000000
+	default 0x8f000000 if PAGE_OFFSET=0xB0000000
+	default 0xffffffff
+
 config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 4a066c687cec..4aaec9599e8a 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -10,7 +10,7 @@
 #
 # Copyright (C) 1995-2001 by Russell King
 
-LDFLAGS_vmlinux	:= --no-undefined -X --pic-veneer
+LDFLAGS_vmlinux	:= --no-undefined -X --pic-veneer -z norelro
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux	+= --be8
 KBUILD_LDFLAGS_MODULE	+= --be8
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index e1567418a2b1..fb521efcc6c2 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -24,6 +24,7 @@ OBJS		+= hyp-stub.o
 endif
 
 GCOV_PROFILE		:= n
+KASAN_SANITIZE		:= n
 
 # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
 KCOV_INSTRUMENT		:= n
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index caa27322a0ab..d9cce7238a36 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -11,6 +11,12 @@
 
 #include "efi-header.S"
 
+#ifdef __ARMEB__
+#define OF_DT_MAGIC 0xd00dfeed
+#else
+#define OF_DT_MAGIC 0xedfe0dd0
+#endif
+
  AR_CLASS(	.arch	armv7-a	)
  M_CLASS(	.arch	armv7-m	)
 
@@ -116,7 +122,7 @@
 		/*
 		 * Debug print of the final appended DTB location
 		 */
-		.macro dbgadtb, begin, end
+		.macro dbgadtb, begin, size
 #ifdef DEBUG
 		kputc   #'D'
 		kputc   #'T'
@@ -129,7 +135,7 @@
 		kputc	#'('
 		kputc	#'0'
 		kputc	#'x'
-		kphex	\end, 8		/* End of appended DTB */
+		kphex	\size, 8	/* Size of appended DTB */
 		kputc	#')'
 		kputc	#'\n'
 #endif
@@ -165,6 +171,16 @@
 		orr	\res, \res, \tmp1, lsl #24
 		.endm
 
+		.macro	be32tocpu, val, tmp
+#ifndef __ARMEB__
+		/* convert to little endian */
+		eor	\tmp, \val, \val, ror #16
+		bic	\tmp, \tmp, #0x00ff0000
+		mov	\val, \val, ror #8
+		eor	\val, \val, \tmp, lsr #8
+#endif
+		.endm
+
 		.section ".start", "ax"
 /*
  * sort out different calling conventions
@@ -325,11 +341,7 @@ restart:	adr	r0, LC1
  */
 
 		ldr	lr, [r6, #0]
-#ifndef __ARMEB__
-		ldr	r1, =0xedfe0dd0		@ sig is 0xd00dfeed big endian
-#else
-		ldr	r1, =0xd00dfeed
-#endif
+		ldr	r1, =OF_DT_MAGIC
 		cmp	lr, r1
 		bne	dtb_check_done		@ not found
 
@@ -345,13 +357,7 @@ restart:	adr	r0, LC1
 
 		/* Get the initial DTB size */
 		ldr	r5, [r6, #4]
-#ifndef __ARMEB__
-		/* convert to little endian */
-		eor	r1, r5, r5, ror #16
-		bic	r1, r1, #0x00ff0000
-		mov	r5, r5, ror #8
-		eor	r5, r5, r1, lsr #8
-#endif
+		be32tocpu r5, r1
 		dbgadtb	r6, r5
 		/* 50% DTB growth should be good enough */
 		add	r5, r5, r5, lsr #1
@@ -403,13 +409,7 @@ restart:	adr	r0, LC1
 
 		/* Get the current DTB size */
 		ldr	r5, [r6, #4]
-#ifndef __ARMEB__
-		/* convert r5 (dtb size) to little endian */
-		eor	r1, r5, r5, ror #16
-		bic	r1, r1, #0x00ff0000
-		mov	r5, r5, ror #8
-		eor	r5, r5, r1, lsr #8
-#endif
+		be32tocpu r5, r1
 
 		/* preserve 64-bit alignment */
 		add	r5, r5, #7
@@ -468,15 +468,10 @@ dtb_check_done:
 
 		/*
 		 * Compute the address of the hyp vectors after relocation.
-		 * This requires some arithmetic since we cannot directly
-		 * reference __hyp_stub_vectors in a PC-relative way.
 		 * Call __hyp_set_vectors with the new address so that we
 		 * can HVC again after the copy.
 		 */
-0:		adr	r0, 0b
-		movw	r1, #:lower16:__hyp_stub_vectors - 0b
-		movt	r1, #:upper16:__hyp_stub_vectors - 0b
-		add	r0, r0, r1
+		adr_l	r0, __hyp_stub_vectors
 		sub	r0, r0, r5
 		add	r0, r0, r10
 		bl	__hyp_set_vectors
@@ -627,17 +622,11 @@ not_relocated:	mov	r0, #0
 		cmp	r0, #HYP_MODE		@ if not booted in HYP mode...
 		bne	__enter_kernel		@ boot kernel directly
 
-		adr	r12, .L__hyp_reentry_vectors_offset
-		ldr	r0, [r12]
-		add	r0, r0, r12
-
+		adr_l	r0, __hyp_reentry_vectors
 		bl	__hyp_set_vectors
 		__HVC(0)			@ otherwise bounce to hyp mode
 
 		b	.			@ should never be reached
-
-		.align	2
-.L__hyp_reentry_vectors_offset:	.long	__hyp_reentry_vectors - .
 #else
 		b	__enter_kernel
 #endif
@@ -1440,8 +1429,7 @@ ENTRY(efi_enter_kernel)
 		mov	r4, r0			@ preserve image base
 		mov	r8, r1			@ preserve DT pointer
 
- ARM(		adrl	r0, call_cache_fn	)
- THUMB(		adr	r0, call_cache_fn	)
+		adr_l	r0, call_cache_fn
 		adr	r1, 0f			@ clean the region of code we
 		bl	cache_clean_flush	@ may run with the MMU off
 
diff --git a/arch/arm/boot/compressed/string.c b/arch/arm/boot/compressed/string.c
index ade5079bebbf..8c0fa276d994 100644
--- a/arch/arm/boot/compressed/string.c
+++ b/arch/arm/boot/compressed/string.c
@@ -7,6 +7,25 @@
 
 #include <linux/string.h>
 
+/*
+ * The decompressor is built without KASan but uses the same redirects as the
+ * rest of the kernel when CONFIG_KASAN is enabled, defining e.g. memcpy()
+ * to __memcpy() but since we are not linking with the main kernel string
+ * library in the decompressor, that will lead to link failures.
+ *
+ * Undefine KASan's versions, define the wrapped functions and alias them to
+ * the right names so that when e.g. __memcpy() appear in the code, it will
+ * still be linked to this local version of memcpy().
+ */
+#ifdef CONFIG_KASAN
+#undef memcpy
+#undef memmove
+#undef memset
+void *__memcpy(void *__dest, __const void *__src, size_t __n) __alias(memcpy);
+void *__memmove(void *__dest, __const void *__src, size_t count) __alias(memmove);
+void *__memset(void *s, int c, size_t count) __alias(memset);
+#endif
+
 void *memcpy(void *__dest, __const void *__src, size_t __n)
 {
 	int i = 0;
diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index 11d41e86f814..7dde9fbb06d3 100644
--- a/arch/arm/boot/dts/omap3-n950-n9.dtsi
+++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi
@@ -494,3 +494,11 @@
 		clock-names = "sysclk";
 	};
 };
+
+&aes1_target {
+	status = "disabled";
+};
+
+&aes2_target {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/picoxcell-pc3x2.dtsi b/arch/arm/boot/dts/picoxcell-pc3x2.dtsi
index c4c6c7e9e37b..5898879a3038 100644
--- a/arch/arm/boot/dts/picoxcell-pc3x2.dtsi
+++ b/arch/arm/boot/dts/picoxcell-pc3x2.dtsi
@@ -45,18 +45,21 @@
 		emac: gem@30000 {
 			compatible = "cadence,gem";
 			reg = <0x30000 0x10000>;
+			interrupt-parent = <&vic0>;
 			interrupts = <31>;
 		};
 
 		dmac1: dmac@40000 {
 			compatible = "snps,dw-dmac";
 			reg = <0x40000 0x10000>;
+			interrupt-parent = <&vic0>;
 			interrupts = <25>;
 		};
 
 		dmac2: dmac@50000 {
 			compatible = "snps,dw-dmac";
 			reg = <0x50000 0x10000>;
+			interrupt-parent = <&vic0>;
 			interrupts = <26>;
 		};
 
@@ -233,6 +236,7 @@
 		axi2pico@c0000000 {
 			compatible = "picochip,axi2pico-pc3x2";
 			reg = <0xc0000000 0x10000>;
+			interrupt-parent = <&vic0>;
 			interrupts = <13 14 15 16 17 18 19 20 21>;
 		};
 	};
diff --git a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts
index 496f9d3ba7b7..60fe6189e728 100644
--- a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts
+++ b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts
@@ -329,6 +329,7 @@
 				panel@0 {
 					compatible = "samsung,s6e63m0";
 					reg = <0>;
+					max-brightness = <15>;
 					vdd3-supply = <&panel_reg_3v0>;
 					vci-supply = <&panel_reg_1v8>;
 					reset-gpios = <&gpio4 11 GPIO_ACTIVE_LOW>;
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 1c11d1557779..b515c31f0ab7 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -279,6 +279,7 @@ CONFIG_SERIAL_OMAP_CONSOLE=y
 CONFIG_SERIAL_DEV_BUS=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_SPI=y
+CONFIG_SPI_GPIO=m
 CONFIG_SPI_OMAP24XX=y
 CONFIG_SPI_TI_QSPI=m
 CONFIG_HSI=m
@@ -296,7 +297,6 @@ CONFIG_GPIO_TWL4030=y
 CONFIG_W1=m
 CONFIG_HDQ_MASTER_OMAP=m
 CONFIG_W1_SLAVE_DS250X=m
-CONFIG_POWER_AVS=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_GPIO=y
 CONFIG_BATTERY_BQ27XXX=m
diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c
index 7b5cf8430c6d..cdde8fd01f8f 100644
--- a/arch/arm/crypto/chacha-glue.c
+++ b/arch/arm/crypto/chacha-glue.c
@@ -60,6 +60,7 @@ static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
 		chacha_block_xor_neon(state, d, s, nrounds);
 		if (d != dst)
 			memcpy(dst, buf, bytes);
+		state[12]++;
 	}
 }
 
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 4a0848aef207..03657ff8fbe3 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -2,7 +2,6 @@
 generic-y += early_ioremap.h
 generic-y += extable.h
 generic-y += flat.h
-generic-y += local64.h
 generic-y += parport.h
 
 generated-y += mach-types.h
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index feac2c8b86f2..6ed30421f697 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -259,7 +259,7 @@
  */
 #define ALT_UP(instr...)					\
 	.pushsection ".alt.smp.init", "a"			;\
-	.long	9998b						;\
+	.long	9998b - .					;\
 9997:	instr							;\
 	.if . - 9997b == 2					;\
 		nop						;\
@@ -270,7 +270,7 @@
 	.popsection
 #define ALT_UP_B(label)					\
 	.pushsection ".alt.smp.init", "a"			;\
-	.long	9998b						;\
+	.long	9998b - .					;\
 	W(b)	. + (label - 9998b)					;\
 	.popsection
 #else
@@ -494,4 +494,88 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #define _ASM_NOKPROBE(entry)
 #endif
 
+	.macro		__adldst_l, op, reg, sym, tmp, c
+	.if		__LINUX_ARM_ARCH__ < 7
+	ldr\c		\tmp, .La\@
+	.subsection	1
+	.align		2
+.La\@:	.long		\sym - .Lpc\@
+	.previous
+	.else
+	.ifnb		\c
+ THUMB(	ittt		\c			)
+	.endif
+	movw\c		\tmp, #:lower16:\sym - .Lpc\@
+	movt\c		\tmp, #:upper16:\sym - .Lpc\@
+	.endif
+
+#ifndef CONFIG_THUMB2_KERNEL
+	.set		.Lpc\@, . + 8			// PC bias
+	.ifc		\op, add
+	add\c		\reg, \tmp, pc
+	.else
+	\op\c		\reg, [pc, \tmp]
+	.endif
+#else
+.Lb\@:	add\c		\tmp, \tmp, pc
+	/*
+	 * In Thumb-2 builds, the PC bias depends on whether we are currently
+	 * emitting into a .arm or a .thumb section. The size of the add opcode
+	 * above will be 2 bytes when emitting in Thumb mode and 4 bytes when
+	 * emitting in ARM mode, so let's use this to account for the bias.
+	 */
+	.set		.Lpc\@, . + (. - .Lb\@)
+
+	.ifnc		\op, add
+	\op\c		\reg, [\tmp]
+	.endif
+#endif
+	.endm
+
+	/*
+	 * mov_l - move a constant value or [relocated] address into a register
+	 */
+	.macro		mov_l, dst:req, imm:req
+	.if		__LINUX_ARM_ARCH__ < 7
+	ldr		\dst, =\imm
+	.else
+	movw		\dst, #:lower16:\imm
+	movt		\dst, #:upper16:\imm
+	.endif
+	.endm
+
+	/*
+	 * adr_l - adr pseudo-op with unlimited range
+	 *
+	 * @dst: destination register
+	 * @sym: name of the symbol
+	 * @cond: conditional opcode suffix
+	 */
+	.macro		adr_l, dst:req, sym:req, cond
+	__adldst_l	add, \dst, \sym, \dst, \cond
+	.endm
+
+	/*
+	 * ldr_l - ldr <literal> pseudo-op with unlimited range
+	 *
+	 * @dst: destination register
+	 * @sym: name of the symbol
+	 * @cond: conditional opcode suffix
+	 */
+	.macro		ldr_l, dst:req, sym:req, cond
+	__adldst_l	ldr, \dst, \sym, \dst, \cond
+	.endm
+
+	/*
+	 * str_l - str <literal> pseudo-op with unlimited range
+	 *
+	 * @src: source register
+	 * @sym: name of the symbol
+	 * @tmp: mandatory scratch register
+	 * @cond: conditional opcode suffix
+	 */
+	.macro		str_l, src:req, sym:req, tmp:req, cond
+	__adldst_l	str, \src, \sym, \tmp, \cond
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */
diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h
index 898e9c78a7e7..595e538f5bfb 100644
--- a/arch/arm/include/asm/div64.h
+++ b/arch/arm/include/asm/div64.h
@@ -21,29 +21,20 @@
  * assembly implementation with completely non standard calling convention
  * for arguments and results (beware).
  */
-
-#ifdef __ARMEB__
-#define __xh "r0"
-#define __xl "r1"
-#else
-#define __xl "r0"
-#define __xh "r1"
-#endif
-
 static inline uint32_t __div64_32(uint64_t *n, uint32_t base)
 {
 	register unsigned int __base      asm("r4") = base;
 	register unsigned long long __n   asm("r0") = *n;
 	register unsigned long long __res asm("r2");
-	register unsigned int __rem       asm(__xh);
-	asm(	__asmeq("%0", __xh)
+	unsigned int __rem;
+	asm(	__asmeq("%0", "r0")
 		__asmeq("%1", "r2")
-		__asmeq("%2", "r0")
-		__asmeq("%3", "r4")
+		__asmeq("%2", "r4")
 		"bl	__do_div64"
-		: "=r" (__rem), "=r" (__res)
-		: "r" (__n), "r" (__base)
+		: "+r" (__n), "=r" (__res)
+		: "r" (__base)
 		: "ip", "lr", "cc");
+	__rem = __n >> 32;
 	*n = __res;
 	return __rem;
 }
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index 3ee4f4381985..9de7ab2ce05d 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -66,24 +66,17 @@ static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
 #define MAX_UNCOMP_KERNEL_SIZE	SZ_32M
 
 /*
- * phys-to-virt patching requires that the physical to virtual offset fits
- * into the immediate field of an add/sub instruction, which comes down to the
- * 24 least significant bits being zero, and so the offset should be a multiple
- * of 16 MB. Since PAGE_OFFSET itself is a multiple of 16 MB, the physical
- * base should be aligned to 16 MB as well.
+ * phys-to-virt patching requires that the physical to virtual offset is a
+ * multiple of 2 MiB. However, using an alignment smaller than TEXT_OFFSET
+ * here throws off the memory allocation logic, so let's use the lowest power
+ * of two greater than 2 MiB and greater than TEXT_OFFSET.
  */
-#define EFI_PHYS_ALIGN		SZ_16M
-
-/* on ARM, the FDT should be located in a lowmem region */
-static inline unsigned long efi_get_max_fdt_addr(unsigned long image_addr)
-{
-	return round_down(image_addr, EFI_PHYS_ALIGN) + SZ_512M;
-}
+#define EFI_PHYS_ALIGN		max(UL(SZ_2M), roundup_pow_of_two(TEXT_OFFSET))
 
 /* on ARM, the initrd should be loaded in a lowmem region */
 static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr)
 {
-	return round_down(image_addr, EFI_PHYS_ALIGN) + SZ_512M;
+	return round_down(image_addr, SZ_4M) + SZ_512M;
 }
 
 struct efi_arm_entry_state {
@@ -93,4 +86,9 @@ struct efi_arm_entry_state {
 	u32	sctlr_after_ebs;
 };
 
+static inline void efi_capsule_flush_cache_range(void *addr, int size)
+{
+	__cpuc_flush_dcache_area(addr, size);
+}
+
 #endif /* _ASM_ARM_EFI_H */
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 61941f369861..b8102a6ddf16 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -51,6 +51,7 @@ typedef struct user_fp elf_fpregset_t;
 #define R_ARM_NONE		0
 #define R_ARM_PC24		1
 #define R_ARM_ABS32		2
+#define R_ARM_REL32		3
 #define R_ARM_CALL		28
 #define R_ARM_JUMP24		29
 #define R_ARM_TARGET1		38
@@ -58,11 +59,15 @@ typedef struct user_fp elf_fpregset_t;
 #define R_ARM_PREL31		42
 #define R_ARM_MOVW_ABS_NC	43
 #define R_ARM_MOVT_ABS		44
+#define R_ARM_MOVW_PREL_NC	45
+#define R_ARM_MOVT_PREL		46
 
 #define R_ARM_THM_CALL		10
 #define R_ARM_THM_JUMP24	30
 #define R_ARM_THM_MOVW_ABS_NC	47
 #define R_ARM_THM_MOVT_ABS	48
+#define R_ARM_THM_MOVW_PREL_NC	49
+#define R_ARM_THM_MOVT_PREL	50
 
 /*
  * These are used to set parameters in the core dumps.
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index c279a8a463a2..707068f852c2 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_FIXMAP_H
 #define _ASM_FIXMAP_H
 
-#define FIXADDR_START		0xffc00000UL
+#define FIXADDR_START		0xffc80000UL
 #define FIXADDR_END		0xfff00000UL
 #define FIXADDR_TOP		(FIXADDR_END - PAGE_SIZE)
 
diff --git a/arch/arm/include/asm/kasan.h b/arch/arm/include/asm/kasan.h
new file mode 100644
index 000000000000..303c35df3135
--- /dev/null
+++ b/arch/arm/include/asm/kasan.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * arch/arm/include/asm/kasan.h
+ *
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ *
+ */
+
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifdef CONFIG_KASAN
+
+#include <asm/kasan_def.h>
+
+#define KASAN_SHADOW_SCALE_SHIFT 3
+
+/*
+ * The compiler uses a shadow offset assuming that addresses start
+ * from 0. Kernel addresses don't start from 0, so shadow
+ * for kernel really starts from 'compiler's shadow offset' +
+ * ('kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT)
+ */
+
+asmlinkage void kasan_early_init(void);
+extern void kasan_init(void);
+
+#else
+static inline void kasan_init(void) { }
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/kasan_def.h b/arch/arm/include/asm/kasan_def.h
new file mode 100644
index 000000000000..5739605aa7cf
--- /dev/null
+++ b/arch/arm/include/asm/kasan_def.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  arch/arm/include/asm/kasan_def.h
+ *
+ *  Copyright (c) 2018 Huawei Technologies Co., Ltd.
+ *
+ *  Author: Abbott Liu <liuwenliang@huawei.com>
+ */
+
+#ifndef __ASM_KASAN_DEF_H
+#define __ASM_KASAN_DEF_H
+
+#ifdef CONFIG_KASAN
+
+/*
+ * Define KASAN_SHADOW_OFFSET,KASAN_SHADOW_START and KASAN_SHADOW_END for
+ * the Arm kernel address sanitizer. We are "stealing" lowmem (the 4GB
+ * addressable by a 32bit architecture) out of the virtual address
+ * space to use as shadow memory for KASan as follows:
+ *
+ * +----+ 0xffffffff
+ * |    |							\
+ * |    | |-> Static kernel image (vmlinux) BSS and page table
+ * |    |/
+ * +----+ PAGE_OFFSET
+ * |    |							\
+ * |    | |->  Loadable kernel modules virtual address space area
+ * |    |/
+ * +----+ MODULES_VADDR = KASAN_SHADOW_END
+ * |    |						\
+ * |    | |-> The shadow area of kernel virtual address.
+ * |    |/
+ * +----+->  TASK_SIZE (start of kernel space) = KASAN_SHADOW_START the
+ * |    |\   shadow address of MODULES_VADDR
+ * |    | |
+ * |    | |
+ * |    | |-> The user space area in lowmem. The kernel address
+ * |    | |   sanitizer do not use this space, nor does it map it.
+ * |    | |
+ * |    | |
+ * |    | |
+ * |    | |
+ * |    |/
+ * ------ 0
+ *
+ * 1) KASAN_SHADOW_START
+ *   This value begins with the MODULE_VADDR's shadow address. It is the
+ *   start of kernel virtual space. Since we have modules to load, we need
+ *   to cover also that area with shadow memory so we can find memory
+ *   bugs in modules.
+ *
+ * 2) KASAN_SHADOW_END
+ *   This value is the 0x100000000's shadow address: the mapping that would
+ *   be after the end of the kernel memory at 0xffffffff. It is the end of
+ *   kernel address sanitizer shadow area. It is also the start of the
+ *   module area.
+ *
+ * 3) KASAN_SHADOW_OFFSET:
+ *   This value is used to map an address to the corresponding shadow
+ *   address by the following formula:
+ *
+ *	shadow_addr = (address >> 3) + KASAN_SHADOW_OFFSET;
+ *
+ *  As you would expect, >> 3 is equal to dividing by 8, meaning each
+ *  byte in the shadow memory covers 8 bytes of kernel memory, so one
+ *  bit shadow memory per byte of kernel memory is used.
+ *
+ *  The KASAN_SHADOW_OFFSET is provided in a Kconfig option depending
+ *  on the VMSPLIT layout of the system: the kernel and userspace can
+ *  split up lowmem in different ways according to needs, so we calculate
+ *  the shadow offset depending on this.
+ */
+
+#define KASAN_SHADOW_SCALE_SHIFT	3
+#define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
+#define KASAN_SHADOW_END	((UL(1) << (32 - KASAN_SHADOW_SCALE_SHIFT)) \
+				 + KASAN_SHADOW_OFFSET)
+#define KASAN_SHADOW_START      ((KASAN_SHADOW_END >> 3) + KASAN_SHADOW_OFFSET)
+
+#endif
+#endif
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 99035b5891ef..2f841cb65c30 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -18,6 +18,7 @@
 #ifdef CONFIG_NEED_MACH_MEMORY_H
 #include <mach/memory.h>
 #endif
+#include <asm/kasan_def.h>
 
 /* PAGE_OFFSET - the virtual address of the start of the kernel image */
 #define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
@@ -28,7 +29,11 @@
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
  */
+#ifndef CONFIG_KASAN
 #define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M))
+#else
+#define TASK_SIZE		(KASAN_SHADOW_START)
+#endif
 #define TASK_UNMAPPED_BASE	ALIGN(TASK_SIZE / 3, SZ_16M)
 
 /*
@@ -67,6 +72,10 @@
  */
 #define XIP_VIRT_ADDR(physaddr)  (MODULES_VADDR + ((physaddr) & 0x000fffff))
 
+#define FDT_FIXED_BASE		UL(0xff800000)
+#define FDT_FIXED_SIZE		(2 * SECTION_SIZE)
+#define FDT_VIRT_BASE(physbase)	((void *)(FDT_FIXED_BASE | (physbase) % SECTION_SIZE))
+
 #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 /*
  * Allow 16MB-aligned ioremap pages
@@ -107,6 +116,7 @@ extern unsigned long vectors_base;
 #define MODULES_VADDR		PAGE_OFFSET
 
 #define XIP_VIRT_ADDR(physaddr)  (physaddr)
+#define FDT_VIRT_BASE(physbase)  ((void *)(physbase))
 
 #endif /* !CONFIG_MMU */
 
@@ -173,6 +183,7 @@ extern unsigned long vectors_base;
  * so that all we need to do is modify the 8-bit constant field.
  */
 #define __PV_BITS_31_24	0x81000000
+#define __PV_BITS_23_16	0x810000
 #define __PV_BITS_7_0	0x81
 
 extern unsigned long __pv_phys_pfn_offset;
@@ -183,43 +194,65 @@ extern const void *__pv_table_begin, *__pv_table_end;
 #define PHYS_OFFSET	((phys_addr_t)__pv_phys_pfn_offset << PAGE_SHIFT)
 #define PHYS_PFN_OFFSET	(__pv_phys_pfn_offset)
 
-#define __pv_stub(from,to,instr,type)			\
+#ifndef CONFIG_THUMB2_KERNEL
+#define __pv_stub(from,to,instr)			\
 	__asm__("@ __pv_stub\n"				\
 	"1:	" instr "	%0, %1, %2\n"		\
+	"2:	" instr "	%0, %0, %3\n"		\
 	"	.pushsection .pv_table,\"a\"\n"		\
-	"	.long	1b\n"				\
+	"	.long	1b - ., 2b - .\n"		\
 	"	.popsection\n"				\
 	: "=r" (to)					\
-	: "r" (from), "I" (type))
+	: "r" (from), "I" (__PV_BITS_31_24),		\
+	  "I"(__PV_BITS_23_16))
 
-#define __pv_stub_mov_hi(t)				\
-	__asm__ volatile("@ __pv_stub_mov\n"		\
-	"1:	mov	%R0, %1\n"			\
+#define __pv_add_carry_stub(x, y)			\
+	__asm__("@ __pv_add_carry_stub\n"		\
+	"0:	movw	%R0, #0\n"			\
+	"	adds	%Q0, %1, %R0, lsl #20\n"	\
+	"1:	mov	%R0, %2\n"			\
+	"	adc	%R0, %R0, #0\n"			\
 	"	.pushsection .pv_table,\"a\"\n"		\
-	"	.long	1b\n"				\
+	"	.long	0b - ., 1b - .\n"		\
 	"	.popsection\n"				\
-	: "=r" (t)					\
-	: "I" (__PV_BITS_7_0))
+	: "=&r" (y)					\
+	: "r" (x), "I" (__PV_BITS_7_0)			\
+	: "cc")
+
+#else
+#define __pv_stub(from,to,instr)			\
+	__asm__("@ __pv_stub\n"				\
+	"0:	movw	%0, #0\n"			\
+	"	lsl	%0, #21\n"			\
+	"	" instr " %0, %1, %0\n"			\
+	"	.pushsection .pv_table,\"a\"\n"		\
+	"	.long	0b - .\n"			\
+	"	.popsection\n"				\
+	: "=&r" (to)					\
+	: "r" (from))
 
 #define __pv_add_carry_stub(x, y)			\
-	__asm__ volatile("@ __pv_add_carry_stub\n"	\
-	"1:	adds	%Q0, %1, %2\n"			\
+	__asm__("@ __pv_add_carry_stub\n"		\
+	"0:	movw	%R0, #0\n"			\
+	"	lsls	%R0, #21\n"			\
+	"	adds	%Q0, %1, %R0\n"			\
+	"1:	mvn	%R0, #0\n"			\
 	"	adc	%R0, %R0, #0\n"			\
 	"	.pushsection .pv_table,\"a\"\n"		\
-	"	.long	1b\n"				\
+	"	.long	0b - ., 1b - .\n"		\
 	"	.popsection\n"				\
-	: "+r" (y)					\
-	: "r" (x), "I" (__PV_BITS_31_24)		\
+	: "=&r" (y)					\
+	: "r" (x)					\
 	: "cc")
+#endif
 
 static inline phys_addr_t __virt_to_phys_nodebug(unsigned long x)
 {
 	phys_addr_t t;
 
 	if (sizeof(phys_addr_t) == 4) {
-		__pv_stub(x, t, "add", __PV_BITS_31_24);
+		__pv_stub(x, t, "add");
 	} else {
-		__pv_stub_mov_hi(t);
 		__pv_add_carry_stub(x, t);
 	}
 	return t;
@@ -235,7 +268,7 @@ static inline unsigned long __phys_to_virt(phys_addr_t x)
 	 * assembler expression receives 32 bit argument
 	 * in place where 'r' 32 bit operand is expected.
 	 */
-	__pv_stub((unsigned long) x, t, "sub", __PV_BITS_31_24);
+	__pv_stub((unsigned long) x, t, "sub");
 	return t;
 }
 
diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h
index 15f4674715f8..fdee1f04f4f3 100644
--- a/arch/arm/include/asm/pgalloc.h
+++ b/arch/arm/include/asm/pgalloc.h
@@ -21,6 +21,7 @@
 #define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL))
 
 #ifdef CONFIG_ARM_LPAE
+#define PGD_SIZE		(PTRS_PER_PGD * sizeof(pgd_t))
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
@@ -28,14 +29,19 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 }
 
 #else	/* !CONFIG_ARM_LPAE */
+#define PGD_SIZE		(PAGE_SIZE << 2)
 
 /*
  * Since we have only two-level page tables, these are trivial
  */
 #define pmd_alloc_one(mm,addr)		({ BUG(); ((pmd_t *)2); })
 #define pmd_free(mm, pmd)		do { } while (0)
+#ifdef CONFIG_KASAN
+/* The KASan core unconditionally calls pud_populate() on all architectures */
+#define pud_populate(mm,pmd,pte)	do { } while (0)
+#else
 #define pud_populate(mm,pmd,pte)	BUG()
-
+#endif
 #endif	/* CONFIG_ARM_LPAE */
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index baf7d0204eb5..70fe69bdcce2 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -179,11 +179,28 @@
  * the pud: the pud entry is never bad, always exists, and can't be set or
  * cleared.
  */
-#define pud_none(pud)		(0)
-#define pud_bad(pud)		(0)
-#define pud_present(pud)	(1)
-#define pud_clear(pudp)		do { } while (0)
-#define set_pud(pud,pudp)	do { } while (0)
+static inline int pud_none(pud_t pud)
+{
+	return 0;
+}
+
+static inline int pud_bad(pud_t pud)
+{
+	return 0;
+}
+
+static inline int pud_present(pud_t pud)
+{
+	return 1;
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+}
+
+static inline void set_pud(pud_t *pudp, pud_t pud)
+{
+}
 
 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 {
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index b9241051e5cb..9e6b97286307 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -96,7 +96,7 @@ unsigned long get_wchan(struct task_struct *p);
 #define __ALT_SMP_ASM(smp, up)						\
 	"9998:	" smp "\n"						\
 	"	.pushsection \".alt.smp.init\", \"a\"\n"		\
-	"	.long	9998b\n"					\
+	"	.long	9998b - .\n"					\
 	"	" up "\n"						\
 	"	.popsection\n"
 #else
diff --git a/arch/arm/include/asm/prom.h b/arch/arm/include/asm/prom.h
index 1e36c40533c1..402e3f34c7ed 100644
--- a/arch/arm/include/asm/prom.h
+++ b/arch/arm/include/asm/prom.h
@@ -9,12 +9,12 @@
 
 #ifdef CONFIG_OF
 
-extern const struct machine_desc *setup_machine_fdt(unsigned int dt_phys);
+extern const struct machine_desc *setup_machine_fdt(void *dt_virt);
 extern void __init arm_dt_init_cpu_maps(void);
 
 #else /* CONFIG_OF */
 
-static inline const struct machine_desc *setup_machine_fdt(unsigned int dt_phys)
+static inline const struct machine_desc *setup_machine_fdt(void *dt_virt)
 {
 	return NULL;
 }
diff --git a/arch/arm/include/asm/string.h b/arch/arm/include/asm/string.h
index 111a1d8a41dd..6c607c68f3ad 100644
--- a/arch/arm/include/asm/string.h
+++ b/arch/arm/include/asm/string.h
@@ -5,6 +5,9 @@
 /*
  * We don't do inline string functions, since the
  * optimised inline asm versions are not small.
+ *
+ * The __underscore versions of some functions are for KASan to be able
+ * to replace them with instrumented versions.
  */
 
 #define __HAVE_ARCH_STRRCHR
@@ -15,15 +18,18 @@ extern char * strchr(const char * s, int c);
 
 #define __HAVE_ARCH_MEMCPY
 extern void * memcpy(void *, const void *, __kernel_size_t);
+extern void *__memcpy(void *dest, const void *src, __kernel_size_t n);
 
 #define __HAVE_ARCH_MEMMOVE
 extern void * memmove(void *, const void *, __kernel_size_t);
+extern void *__memmove(void *dest, const void *src, __kernel_size_t n);
 
 #define __HAVE_ARCH_MEMCHR
 extern void * memchr(const void *, int, __kernel_size_t);
 
 #define __HAVE_ARCH_MEMSET
 extern void * memset(void *, int, __kernel_size_t);
+extern void *__memset(void *s, int c, __kernel_size_t n);
 
 #define __HAVE_ARCH_MEMSET32
 extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
@@ -39,4 +45,24 @@ static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n)
 	return __memset64(p, v, n * 8, v >> 32);
 }
 
+/*
+ * For files that are not instrumented (e.g. mm/slub.c) we
+ * must use non-instrumented versions of the mem*
+ * functions named __memcpy() etc. All such kernel code has
+ * been tagged with KASAN_SANITIZE_file.o = n, which means
+ * that the address sanitization argument isn't passed to the
+ * compiler, and __SANITIZE_ADDRESS__ is not set. As a result
+ * these defines kick in.
+ */
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memmove(dst, src, len) __memmove(dst, src, len)
+#define memset(s, c, n) __memset(s, c, n)
+
+#ifndef __NO_FORTIFY
+#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */
+#endif
+
+#endif
+
 #endif
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index eb7ce2747eb0..70d4cbc49ae1 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -13,7 +13,15 @@
 #include <asm/fpstate.h>
 #include <asm/page.h>
 
+#ifdef CONFIG_KASAN
+/*
+ * KASan uses a lot of extra stack space so the thread size order needs to
+ * be increased.
+ */
+#define THREAD_SIZE_ORDER	2
+#else
 #define THREAD_SIZE_ORDER	1
+#endif
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 #define THREAD_START_SP		(THREAD_SIZE - 8)
 
diff --git a/arch/arm/include/asm/uaccess-asm.h b/arch/arm/include/asm/uaccess-asm.h
index 907571fd05c6..e6eb7a2aaf1e 100644
--- a/arch/arm/include/asm/uaccess-asm.h
+++ b/arch/arm/include/asm/uaccess-asm.h
@@ -85,7 +85,7 @@
 	 */
 	.macro	uaccess_entry, tsk, tmp0, tmp1, tmp2, disable
 	ldr	\tmp1, [\tsk, #TI_ADDR_LIMIT]
-	mov	\tmp2, #TASK_SIZE
+	ldr	\tmp2, =TASK_SIZE
 	str	\tmp2, [\tsk, #TI_ADDR_LIMIT]
  DACR(	mrc	p15, 0, \tmp0, c3, c0, 0)
  DACR(	str	\tmp0, [sp, #SVC_DACR])
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 09e67cb02b20..ae295a3bcfef 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -21,6 +21,9 @@ obj-y		:= elf.o entry-common.o irq.o opcodes.o \
 		   setup.o signal.o sigreturn_codes.o \
 		   stacktrace.o sys_arm.o time.o traps.o
 
+KASAN_SANITIZE_stacktrace.o := n
+KASAN_SANITIZE_traps.o := n
+
 ifneq ($(CONFIG_ARM_UNWIND),y)
 obj-$(CONFIG_FRAME_POINTER)	+= return_address.o
 endif
@@ -88,6 +91,7 @@ obj-$(CONFIG_PARAVIRT)	+= paravirt.o
 head-y			:= head$(MMUEXT).o
 obj-$(CONFIG_DEBUG_LL)	+= debug.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
+obj-$(CONFIG_ARM_PATCH_PHYS_VIRT)	+= phys2virt.o
 
 # This is executed very early using a temporary stack when no memory allocator
 # nor global data is available. Everything has to be allocated on the stack.
diff --git a/arch/arm/kernel/atags.h b/arch/arm/kernel/atags.h
index 067e12edc341..f2819c25b602 100644
--- a/arch/arm/kernel/atags.h
+++ b/arch/arm/kernel/atags.h
@@ -2,11 +2,11 @@
 void convert_to_tag_list(struct tag *tags);
 
 #ifdef CONFIG_ATAGS
-const struct machine_desc *setup_machine_tags(phys_addr_t __atags_pointer,
+const struct machine_desc *setup_machine_tags(void *__atags_vaddr,
 	unsigned int machine_nr);
 #else
 static inline const struct machine_desc * __init __noreturn
-setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
+setup_machine_tags(void *__atags_vaddr, unsigned int machine_nr)
 {
 	early_print("no ATAGS support: can't continue\n");
 	while (true);
diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c
index 6c12d9fe694e..373b61f9a4f0 100644
--- a/arch/arm/kernel/atags_parse.c
+++ b/arch/arm/kernel/atags_parse.c
@@ -174,7 +174,7 @@ static void __init squash_mem_tags(struct tag *tag)
 }
 
 const struct machine_desc * __init
-setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
+setup_machine_tags(void *atags_vaddr, unsigned int machine_nr)
 {
 	struct tag *tags = (struct tag *)&default_tags;
 	const struct machine_desc *mdesc = NULL, *p;
@@ -195,8 +195,8 @@ setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
 	if (!mdesc)
 		return NULL;
 
-	if (__atags_pointer)
-		tags = phys_to_virt(__atags_pointer);
+	if (atags_vaddr)
+		tags = atags_vaddr;
 	else if (mdesc->atag_offset)
 		tags = (void *)(PAGE_OFFSET + mdesc->atag_offset);
 
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 7f0745a97e20..28311dd0fee6 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -203,12 +203,12 @@ static const void * __init arch_get_next_mach(const char *const **match)
 
 /**
  * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
- * @dt_phys: physical address of dt blob
+ * @dt_virt: virtual address of dt blob
  *
  * If a dtb was passed to the kernel in r2, then use it to choose the
  * correct machine_desc and to setup the system.
  */
-const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
+const struct machine_desc * __init setup_machine_fdt(void *dt_virt)
 {
 	const struct machine_desc *mdesc, *mdesc_best = NULL;
 
@@ -221,7 +221,7 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 	mdesc_best = &__mach_desc_GENERIC_DT;
 #endif
 
-	if (!dt_phys || !early_init_dt_verify(phys_to_virt(dt_phys)))
+	if (!dt_virt || !early_init_dt_verify(dt_virt))
 		return NULL;
 
 	mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 55a47df04773..0ea8529a4872 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -252,31 +252,10 @@ __und_svc:
 #else
 	svc_entry
 #endif
-	@
-	@ call emulation code, which returns using r9 if it has emulated
-	@ the instruction, or the more conventional lr if we are to treat
-	@ this as a real undefined instruction
-	@
-	@  r0 - instruction
-	@
-#ifndef CONFIG_THUMB2_KERNEL
-	ldr	r0, [r4, #-4]
-#else
-	mov	r1, #2
-	ldrh	r0, [r4, #-2]			@ Thumb instruction at LR - 2
-	cmp	r0, #0xe800			@ 32-bit instruction if xx >= 0
-	blo	__und_svc_fault
-	ldrh	r9, [r4]			@ bottom 16 bits
-	add	r4, r4, #2
-	str	r4, [sp, #S_PC]
-	orr	r0, r9, r0, lsl #16
-#endif
-	badr	r9, __und_svc_finish
-	mov	r2, r4
-	bl	call_fpe
 
 	mov	r1, #4				@ PC correction to apply
-__und_svc_fault:
+ THUMB(	tst	r5, #PSR_T_BIT		)	@ exception taken in Thumb mode?
+ THUMB(	movne	r1, #2			)	@ if so, fix up PC correction
 	mov	r0, sp				@ struct pt_regs *regs
 	bl	__und_fault
 
@@ -427,7 +406,8 @@ ENDPROC(__fiq_abt)
 	@ if it was interrupted in a critical region.  Here we
 	@ perform a quick test inline since it should be false
 	@ 99.9999% of the time.  The rest is done out of line.
-	cmp	r4, #TASK_SIZE
+	ldr	r0, =TASK_SIZE
+	cmp	r4, r0
 	blhs	kuser_cmpxchg64_fixup
 #endif
 #endif
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 77d16390a524..e0d7833a1827 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -50,7 +50,8 @@ __ret_fast_syscall:
  UNWIND(.cantunwind	)
 	disable_irq_notrace			@ disable interrupts
 	ldr	r2, [tsk, #TI_ADDR_LIMIT]
-	cmp	r2, #TASK_SIZE
+	ldr	r1, =TASK_SIZE
+	cmp	r2, r1
 	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
 	movs	r1, r1, lsl #16
@@ -87,7 +88,8 @@ __ret_fast_syscall:
 #endif
 	disable_irq_notrace			@ disable interrupts
 	ldr	r2, [tsk, #TI_ADDR_LIMIT]
-	cmp	r2, #TASK_SIZE
+	ldr     r1, =TASK_SIZE
+	cmp     r2, r1
 	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
 	movs	r1, r1, lsl #16
@@ -128,7 +130,8 @@ ret_slow_syscall:
 	disable_irq_notrace			@ disable interrupts
 ENTRY(ret_to_user_from_irq)
 	ldr	r2, [tsk, #TI_ADDR_LIMIT]
-	cmp	r2, #TASK_SIZE
+	ldr     r1, =TASK_SIZE
+	cmp	r2, r1
 	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]
 	movs	r1, r1, lsl #16
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 4a3982812a40..29b2eda136bb 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -95,7 +95,7 @@ __mmap_switched:
  THUMB(	ldmia	r4!, {r0, r1, r2, r3} )
  THUMB(	mov	sp, r3 )
 	sub	r2, r2, r1
-	bl	memcpy				@ copy .data to RAM
+	bl	__memcpy			@ copy .data to RAM
 #endif
 
    ARM(	ldmia	r4!, {r0, r1, sp} )
@@ -103,7 +103,7 @@ __mmap_switched:
  THUMB(	mov	sp, r3 )
 	sub	r2, r1, r0
 	mov	r1, #0
-	bl	memset				@ clear .bss
+	bl	__memset			@ clear .bss
 
 	ldmia	r4, {r0, r1, r2, r3}
 	str	r9, [r0]			@ Save processor ID
@@ -111,6 +111,9 @@ __mmap_switched:
 	str	r8, [r2]			@ Save atags pointer
 	cmp	r3, #0
 	strne	r10, [r3]			@ Save control register values
+#ifdef CONFIG_KASAN
+	bl	kasan_early_init
+#endif
 	mov	lr, #0
 	b	start_kernel
 ENDPROC(__mmap_switched)
@@ -170,11 +173,12 @@ ENDPROC(lookup_processor_type)
  *	r9 = cpuid (preserved)
  */
 __lookup_processor_type:
-	adr	r3, __lookup_processor_type_data
-	ldmia	r3, {r4 - r6}
-	sub	r3, r3, r4			@ get offset between virt&phys
-	add	r5, r5, r3			@ convert virt addresses to
-	add	r6, r6, r3			@ physical address space
+	/*
+	 * Look in <asm/procinfo.h> for information about the __proc_info
+	 * structure.
+	 */
+	adr_l	r5, __proc_info_begin
+	adr_l	r6, __proc_info_end
 1:	ldmia	r5, {r3, r4}			@ value, mask
 	and	r4, r4, r9			@ mask wanted bits
 	teq	r3, r4
@@ -186,17 +190,6 @@ __lookup_processor_type:
 2:	ret	lr
 ENDPROC(__lookup_processor_type)
 
-/*
- * Look in <asm/procinfo.h> for information about the __proc_info structure.
- */
-	.align	2
-	.type	__lookup_processor_type_data, %object
-__lookup_processor_type_data:
-	.long	.
-	.long	__proc_info_begin
-	.long	__proc_info_end
-	.size	__lookup_processor_type_data, . - __lookup_processor_type_data
-
 __error_lpae:
 #ifdef CONFIG_DEBUG_LL
 	adr	r0, str_lpae
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index f8904227e7fd..7f62c5eccdf3 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -103,10 +103,8 @@ ENTRY(stext)
 #endif
 
 #ifndef CONFIG_XIP_KERNEL
-	adr	r3, 2f
-	ldmia	r3, {r4, r8}
-	sub	r4, r3, r4			@ (PHYS_OFFSET - PAGE_OFFSET)
-	add	r8, r8, r4			@ PHYS_OFFSET
+	adr_l	r8, _text			@ __pa(_text)
+	sub	r8, r8, #TEXT_OFFSET		@ PHYS_OFFSET
 #else
 	ldr	r8, =PLAT_PHYS_OFFSET		@ always constant in this case
 #endif
@@ -158,10 +156,6 @@ ENTRY(stext)
 1:	b	__enable_mmu
 ENDPROC(stext)
 	.ltorg
-#ifndef CONFIG_XIP_KERNEL
-2:	.long	.
-	.long	PAGE_OFFSET
-#endif
 
 /*
  * Setup the initial page tables.  We only setup the barest
@@ -224,11 +218,8 @@ __create_page_tables:
 	 * Create identity mapping to cater for __enable_mmu.
 	 * This identity mapping will be removed by paging_init().
 	 */
-	adr	r0, __turn_mmu_on_loc
-	ldmia	r0, {r3, r5, r6}
-	sub	r0, r0, r3			@ virt->phys offset
-	add	r5, r5, r0			@ phys __turn_mmu_on
-	add	r6, r6, r0			@ phys __turn_mmu_on_end
+	adr_l	r5, __turn_mmu_on		@ _pa(__turn_mmu_on)
+	adr_l	r6, __turn_mmu_on_end		@ _pa(__turn_mmu_on_end)
 	mov	r5, r5, lsr #SECTION_SHIFT
 	mov	r6, r6, lsr #SECTION_SHIFT
 
@@ -274,11 +265,10 @@ __create_page_tables:
 	 * We map 2 sections in case the ATAGs/DTB crosses a section boundary.
 	 */
 	mov	r0, r2, lsr #SECTION_SHIFT
-	movs	r0, r0, lsl #SECTION_SHIFT
-	subne	r3, r0, r8
-	addne	r3, r3, #PAGE_OFFSET
-	addne	r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER)
-	orrne	r6, r7, r0
+	cmp	r2, #0
+	ldrne	r3, =FDT_FIXED_BASE >> (SECTION_SHIFT - PMD_ORDER)
+	addne	r3, r3, r4
+	orrne	r6, r7, r0, lsl #SECTION_SHIFT
 	strne	r6, [r3], #1 << PMD_ORDER
 	addne	r6, r6, #1 << SECTION_SHIFT
 	strne	r6, [r3]
@@ -351,11 +341,6 @@ __create_page_tables:
 	ret	lr
 ENDPROC(__create_page_tables)
 	.ltorg
-	.align
-__turn_mmu_on_loc:
-	.long	.
-	.long	__turn_mmu_on
-	.long	__turn_mmu_on_end
 
 #if defined(CONFIG_SMP)
 	.text
@@ -391,10 +376,8 @@ ENTRY(secondary_startup)
 	/*
 	 * Use the page tables supplied from  __cpu_up.
 	 */
-	adr	r4, __secondary_data
-	ldmia	r4, {r5, r7, r12}		@ address to jump to after
-	sub	lr, r4, r5			@ mmu has been enabled
-	add	r3, r7, lr
+	adr_l	r3, secondary_data
+	mov_l	r12, __secondary_switched
 	ldrd	r4, r5, [r3, #0]		@ get secondary_data.pgdir
 ARM_BE8(eor	r4, r4, r5)			@ Swap r5 and r4 in BE:
 ARM_BE8(eor	r5, r4, r5)			@ it can be done in 3 steps
@@ -409,22 +392,13 @@ ARM_BE8(eor	r4, r4, r5)			@ without using a temp reg.
 ENDPROC(secondary_startup)
 ENDPROC(secondary_startup_arm)
 
-	/*
-	 * r6  = &secondary_data
-	 */
 ENTRY(__secondary_switched)
-	ldr	sp, [r7, #12]			@ get secondary_data.stack
+	ldr_l	r7, secondary_data + 12		@ get secondary_data.stack
+	mov	sp, r7
 	mov	fp, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
 
-	.align
-
-	.type	__secondary_data, %object
-__secondary_data:
-	.long	.
-	.long	secondary_data
-	.long	__secondary_switched
 #endif /* defined(CONFIG_SMP) */
 
 
@@ -539,19 +513,11 @@ ARM_BE8(rev	r0, r0)			@ byteswap if big endian
 	retne	lr
 
 __fixup_smp_on_up:
-	adr	r0, 1f
-	ldmia	r0, {r3 - r5}
-	sub	r3, r0, r3
-	add	r4, r4, r3
-	add	r5, r5, r3
+	adr_l	r4, __smpalt_begin
+	adr_l	r5, __smpalt_end
 	b	__do_fixup_smp_on_up
 ENDPROC(__fixup_smp)
 
-	.align
-1:	.word	.
-	.word	__smpalt_begin
-	.word	__smpalt_end
-
 	.pushsection .data
 	.align	2
 	.globl	smp_on_up
@@ -565,14 +531,15 @@ smp_on_up:
 __do_fixup_smp_on_up:
 	cmp	r4, r5
 	reths	lr
-	ldmia	r4!, {r0, r6}
- ARM(	str	r6, [r0, r3]	)
- THUMB(	add	r0, r0, r3	)
+	ldmia	r4, {r0, r6}
+ ARM(	str	r6, [r0, r4]	)
+ THUMB(	add	r0, r0, r4	)
+	add	r4, r4, #8
 #ifdef __ARMEB__
  THUMB(	mov	r6, r6, ror #16	)	@ Convert word order for big-endian.
 #endif
  THUMB(	strh	r6, [r0], #2	)	@ For Thumb-2, store as two halfwords
- THUMB(	mov	r6, r6, lsr #16	)	@ to be robust against misaligned r3.
+ THUMB(	mov	r6, r6, lsr #16	)	@ to be robust against misaligned r0.
  THUMB(	strh	r6, [r0]	)
 	b	__do_fixup_smp_on_up
 ENDPROC(__do_fixup_smp_on_up)
@@ -581,151 +548,8 @@ ENTRY(fixup_smp)
 	stmfd	sp!, {r4 - r6, lr}
 	mov	r4, r0
 	add	r5, r0, r1
-	mov	r3, #0
 	bl	__do_fixup_smp_on_up
 	ldmfd	sp!, {r4 - r6, pc}
 ENDPROC(fixup_smp)
 
-#ifdef __ARMEB__
-#define LOW_OFFSET	0x4
-#define HIGH_OFFSET	0x0
-#else
-#define LOW_OFFSET	0x0
-#define HIGH_OFFSET	0x4
-#endif
-
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
-
-/* __fixup_pv_table - patch the stub instructions with the delta between
- * PHYS_OFFSET and PAGE_OFFSET, which is assumed to be 16MiB aligned and
- * can be expressed by an immediate shifter operand. The stub instruction
- * has a form of '(add|sub) rd, rn, #imm'.
- */
-	__HEAD
-__fixup_pv_table:
-	adr	r0, 1f
-	ldmia	r0, {r3-r7}
-	mvn	ip, #0
-	subs	r3, r0, r3	@ PHYS_OFFSET - PAGE_OFFSET
-	add	r4, r4, r3	@ adjust table start address
-	add	r5, r5, r3	@ adjust table end address
-	add	r6, r6, r3	@ adjust __pv_phys_pfn_offset address
-	add	r7, r7, r3	@ adjust __pv_offset address
-	mov	r0, r8, lsr #PAGE_SHIFT	@ convert to PFN
-	str	r0, [r6]	@ save computed PHYS_OFFSET to __pv_phys_pfn_offset
-	strcc	ip, [r7, #HIGH_OFFSET]	@ save to __pv_offset high bits
-	mov	r6, r3, lsr #24	@ constant for add/sub instructions
-	teq	r3, r6, lsl #24 @ must be 16MiB aligned
-THUMB(	it	ne		@ cross section branch )
-	bne	__error
-	str	r3, [r7, #LOW_OFFSET]	@ save to __pv_offset low bits
-	b	__fixup_a_pv_table
-ENDPROC(__fixup_pv_table)
-
-	.align
-1:	.long	.
-	.long	__pv_table_begin
-	.long	__pv_table_end
-2:	.long	__pv_phys_pfn_offset
-	.long	__pv_offset
-
-	.text
-__fixup_a_pv_table:
-	adr	r0, 3f
-	ldr	r6, [r0]
-	add	r6, r6, r3
-	ldr	r0, [r6, #HIGH_OFFSET]	@ pv_offset high word
-	ldr	r6, [r6, #LOW_OFFSET]	@ pv_offset low word
-	mov	r6, r6, lsr #24
-	cmn	r0, #1
-#ifdef CONFIG_THUMB2_KERNEL
-	moveq	r0, #0x200000	@ set bit 21, mov to mvn instruction
-	lsls	r6, #24
-	beq	2f
-	clz	r7, r6
-	lsr	r6, #24
-	lsl	r6, r7
-	bic	r6, #0x0080
-	lsrs	r7, #1
-	orrcs	r6, #0x0080
-	orr	r6, r6, r7, lsl #12
-	orr	r6, #0x4000
-	b	2f
-1:	add     r7, r3
-	ldrh	ip, [r7, #2]
-ARM_BE8(rev16	ip, ip)
-	tst	ip, #0x4000
-	and	ip, #0x8f00
-	orrne	ip, r6	@ mask in offset bits 31-24
-	orreq	ip, r0	@ mask in offset bits 7-0
-ARM_BE8(rev16	ip, ip)
-	strh	ip, [r7, #2]
-	bne	2f
-	ldrh	ip, [r7]
-ARM_BE8(rev16	ip, ip)
-	bic	ip, #0x20
-	orr	ip, ip, r0, lsr #16
-ARM_BE8(rev16	ip, ip)
-	strh	ip, [r7]
-2:	cmp	r4, r5
-	ldrcc	r7, [r4], #4	@ use branch for delay slot
-	bcc	1b
-	bx	lr
-#else
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	moveq	r0, #0x00004000	@ set bit 22, mov to mvn instruction
-#else
-	moveq	r0, #0x400000	@ set bit 22, mov to mvn instruction
-#endif
-	b	2f
-1:	ldr	ip, [r7, r3]
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	@ in BE8, we load data in BE, but instructions still in LE
-	bic	ip, ip, #0xff000000
-	tst	ip, #0x000f0000	@ check the rotation field
-	orrne	ip, ip, r6, lsl #24 @ mask in offset bits 31-24
-	biceq	ip, ip, #0x00004000 @ clear bit 22
-	orreq	ip, ip, r0      @ mask in offset bits 7-0
-#else
-	bic	ip, ip, #0x000000ff
-	tst	ip, #0xf00	@ check the rotation field
-	orrne	ip, ip, r6	@ mask in offset bits 31-24
-	biceq	ip, ip, #0x400000	@ clear bit 22
-	orreq	ip, ip, r0	@ mask in offset bits 7-0
-#endif
-	str	ip, [r7, r3]
-2:	cmp	r4, r5
-	ldrcc	r7, [r4], #4	@ use branch for delay slot
-	bcc	1b
-	ret	lr
-#endif
-ENDPROC(__fixup_a_pv_table)
-
-	.align
-3:	.long __pv_offset
-
-ENTRY(fixup_pv_table)
-	stmfd	sp!, {r4 - r7, lr}
-	mov	r3, #0			@ no offset
-	mov	r4, r0			@ r0 = table start
-	add	r5, r0, r1		@ r1 = table size
-	bl	__fixup_a_pv_table
-	ldmfd	sp!, {r4 - r7, pc}
-ENDPROC(fixup_pv_table)
-
-	.data
-	.align	2
-	.globl	__pv_phys_pfn_offset
-	.type	__pv_phys_pfn_offset, %object
-__pv_phys_pfn_offset:
-	.word	0
-	.size	__pv_phys_pfn_offset, . -__pv_phys_pfn_offset
-
-	.globl	__pv_offset
-	.type	__pv_offset, %object
-__pv_offset:
-	.quad	0
-	.size	__pv_offset, . -__pv_offset
-#endif
-
 #include "head-common.S"
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 26d8e03b1dd3..b699b22a4db1 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -24,41 +24,38 @@ ENTRY(__boot_cpu_mode)
 .text
 
 	/*
-	 * Save the primary CPU boot mode. Requires 3 scratch registers.
+	 * Save the primary CPU boot mode. Requires 2 scratch registers.
 	 */
-	.macro	store_primary_cpu_mode	reg1, reg2, reg3
+	.macro	store_primary_cpu_mode	reg1, reg2
 	mrs	\reg1, cpsr
 	and	\reg1, \reg1, #MODE_MASK
-	adr	\reg2, .L__boot_cpu_mode_offset
-	ldr	\reg3, [\reg2]
-	str	\reg1, [\reg2, \reg3]
+	str_l	\reg1, __boot_cpu_mode, \reg2
 	.endm
 
 	/*
 	 * Compare the current mode with the one saved on the primary CPU.
 	 * If they don't match, record that fact. The Z bit indicates
 	 * if there's a match or not.
-	 * Requires 3 additionnal scratch registers.
+	 * Requires 2 additional scratch registers.
 	 */
-	.macro	compare_cpu_mode_with_primary mode, reg1, reg2, reg3
-	adr	\reg2, .L__boot_cpu_mode_offset
-	ldr	\reg3, [\reg2]
-	ldr	\reg1, [\reg2, \reg3]
+	.macro	compare_cpu_mode_with_primary mode, reg1, reg2
+	adr_l	\reg2, __boot_cpu_mode
+	ldr	\reg1, [\reg2]
 	cmp	\mode, \reg1		@ matches primary CPU boot mode?
 	orrne	\reg1, \reg1, #BOOT_CPU_MODE_MISMATCH
-	strne	\reg1, [\reg2, \reg3]	@ record what happened and give up
+	strne	\reg1, [\reg2]		@ record what happened and give up
 	.endm
 
 #else	/* ZIMAGE */
 
-	.macro	store_primary_cpu_mode	reg1:req, reg2:req, reg3:req
+	.macro	store_primary_cpu_mode	reg1:req, reg2:req
 	.endm
 
 /*
  * The zImage loader only runs on one CPU, so we don't bother with mult-CPU
  * consistency checking:
  */
-	.macro	compare_cpu_mode_with_primary mode, reg1, reg2, reg3
+	.macro	compare_cpu_mode_with_primary mode, reg1, reg2
 	cmp	\mode, \mode
 	.endm
 
@@ -73,7 +70,7 @@ ENTRY(__boot_cpu_mode)
  */
 @ Call this from the primary CPU
 ENTRY(__hyp_stub_install)
-	store_primary_cpu_mode	r4, r5, r6
+	store_primary_cpu_mode	r4, r5
 ENDPROC(__hyp_stub_install)
 
 	@ fall through...
@@ -87,7 +84,7 @@ ENTRY(__hyp_stub_install_secondary)
 	 * If the secondary has booted with a different mode, give up
 	 * immediately.
 	 */
-	compare_cpu_mode_with_primary	r4, r5, r6, r7
+	compare_cpu_mode_with_primary	r4, r5, r6
 	retne	lr
 
 	/*
@@ -228,12 +225,6 @@ ENTRY(__hyp_soft_restart)
 	ret	lr
 ENDPROC(__hyp_soft_restart)
 
-#ifndef ZIMAGE
-.align 2
-.L__boot_cpu_mode_offset:
-	.long	__boot_cpu_mode - .
-#endif
-
 .align 5
 ENTRY(__hyp_stub_vectors)
 __hyp_stub_reset:	W(b)	.
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index 0dcae787b004..d2b4ac06e4ed 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -16,6 +16,7 @@
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
+#include "iwmmxt.h"
 
 #if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B)
 #define PJ4(code...)		code
@@ -113,33 +114,33 @@ concan_save:
 
 concan_dump:
 
-	wstrw	wCSSF, [r1, #MMX_WCSSF]
-	wstrw	wCASF, [r1, #MMX_WCASF]
-	wstrw	wCGR0, [r1, #MMX_WCGR0]
-	wstrw	wCGR1, [r1, #MMX_WCGR1]
-	wstrw	wCGR2, [r1, #MMX_WCGR2]
-	wstrw	wCGR3, [r1, #MMX_WCGR3]
+	wstrw	wCSSF, r1, MMX_WCSSF
+	wstrw	wCASF, r1, MMX_WCASF
+	wstrw	wCGR0, r1, MMX_WCGR0
+	wstrw	wCGR1, r1, MMX_WCGR1
+	wstrw	wCGR2, r1, MMX_WCGR2
+	wstrw	wCGR3, r1, MMX_WCGR3
 
 1:	@ MUP? wRn
 	tst	r2, #0x2
 	beq	2f
 
-	wstrd	wR0,  [r1, #MMX_WR0]
-	wstrd	wR1,  [r1, #MMX_WR1]
-	wstrd	wR2,  [r1, #MMX_WR2]
-	wstrd	wR3,  [r1, #MMX_WR3]
-	wstrd	wR4,  [r1, #MMX_WR4]
-	wstrd	wR5,  [r1, #MMX_WR5]
-	wstrd	wR6,  [r1, #MMX_WR6]
-	wstrd	wR7,  [r1, #MMX_WR7]
-	wstrd	wR8,  [r1, #MMX_WR8]
-	wstrd	wR9,  [r1, #MMX_WR9]
-	wstrd	wR10, [r1, #MMX_WR10]
-	wstrd	wR11, [r1, #MMX_WR11]
-	wstrd	wR12, [r1, #MMX_WR12]
-	wstrd	wR13, [r1, #MMX_WR13]
-	wstrd	wR14, [r1, #MMX_WR14]
-	wstrd	wR15, [r1, #MMX_WR15]
+	wstrd	wR0,  r1, MMX_WR0
+	wstrd	wR1,  r1, MMX_WR1
+	wstrd	wR2,  r1, MMX_WR2
+	wstrd	wR3,  r1, MMX_WR3
+	wstrd	wR4,  r1, MMX_WR4
+	wstrd	wR5,  r1, MMX_WR5
+	wstrd	wR6,  r1, MMX_WR6
+	wstrd	wR7,  r1, MMX_WR7
+	wstrd	wR8,  r1, MMX_WR8
+	wstrd	wR9,  r1, MMX_WR9
+	wstrd	wR10, r1, MMX_WR10
+	wstrd	wR11, r1, MMX_WR11
+	wstrd	wR12, r1, MMX_WR12
+	wstrd	wR13, r1, MMX_WR13
+	wstrd	wR14, r1, MMX_WR14
+	wstrd	wR15, r1, MMX_WR15
 
 2:	teq	r0, #0				@ anything to load?
 	reteq	lr				@ if not, return
@@ -147,30 +148,30 @@ concan_dump:
 concan_load:
 
 	@ Load wRn
-	wldrd	wR0,  [r0, #MMX_WR0]
-	wldrd	wR1,  [r0, #MMX_WR1]
-	wldrd	wR2,  [r0, #MMX_WR2]
-	wldrd	wR3,  [r0, #MMX_WR3]
-	wldrd	wR4,  [r0, #MMX_WR4]
-	wldrd	wR5,  [r0, #MMX_WR5]
-	wldrd	wR6,  [r0, #MMX_WR6]
-	wldrd	wR7,  [r0, #MMX_WR7]
-	wldrd	wR8,  [r0, #MMX_WR8]
-	wldrd	wR9,  [r0, #MMX_WR9]
-	wldrd	wR10, [r0, #MMX_WR10]
-	wldrd	wR11, [r0, #MMX_WR11]
-	wldrd	wR12, [r0, #MMX_WR12]
-	wldrd	wR13, [r0, #MMX_WR13]
-	wldrd	wR14, [r0, #MMX_WR14]
-	wldrd	wR15, [r0, #MMX_WR15]
+	wldrd	wR0,  r0, MMX_WR0
+	wldrd	wR1,  r0, MMX_WR1
+	wldrd	wR2,  r0, MMX_WR2
+	wldrd	wR3,  r0, MMX_WR3
+	wldrd	wR4,  r0, MMX_WR4
+	wldrd	wR5,  r0, MMX_WR5
+	wldrd	wR6,  r0, MMX_WR6
+	wldrd	wR7,  r0, MMX_WR7
+	wldrd	wR8,  r0, MMX_WR8
+	wldrd	wR9,  r0, MMX_WR9
+	wldrd	wR10, r0, MMX_WR10
+	wldrd	wR11, r0, MMX_WR11
+	wldrd	wR12, r0, MMX_WR12
+	wldrd	wR13, r0, MMX_WR13
+	wldrd	wR14, r0, MMX_WR14
+	wldrd	wR15, r0, MMX_WR15
 
 	@ Load wCx
-	wldrw	wCSSF, [r0, #MMX_WCSSF]
-	wldrw	wCASF, [r0, #MMX_WCASF]
-	wldrw	wCGR0, [r0, #MMX_WCGR0]
-	wldrw	wCGR1, [r0, #MMX_WCGR1]
-	wldrw	wCGR2, [r0, #MMX_WCGR2]
-	wldrw	wCGR3, [r0, #MMX_WCGR3]
+	wldrw	wCSSF, r0, MMX_WCSSF
+	wldrw	wCASF, r0, MMX_WCASF
+	wldrw	wCGR0, r0, MMX_WCGR0
+	wldrw	wCGR1, r0, MMX_WCGR1
+	wldrw	wCGR2, r0, MMX_WCGR2
+	wldrw	wCGR3, r0, MMX_WCGR3
 
 	@ clear CUP/MUP (only if r1 != 0)
 	teq	r1, #0
diff --git a/arch/arm/kernel/iwmmxt.h b/arch/arm/kernel/iwmmxt.h
new file mode 100644
index 000000000000..fb627286f5bb
--- /dev/null
+++ b/arch/arm/kernel/iwmmxt.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __IWMMXT_H__
+#define __IWMMXT_H__
+
+.irp b, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
+.set .LwR\b, \b
+.set .Lr\b, \b
+.endr
+
+.set .LwCSSF, 0x2
+.set .LwCASF, 0x3
+.set .LwCGR0, 0x8
+.set .LwCGR1, 0x9
+.set .LwCGR2, 0xa
+.set .LwCGR3, 0xb
+
+.macro wldrd, reg:req, base:req, offset:req
+.inst 0xedd00100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2)
+.endm
+
+.macro wldrw, reg:req, base:req, offset:req
+.inst 0xfd900100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2)
+.endm
+
+.macro wstrd, reg:req, base:req, offset:req
+.inst 0xedc00100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2)
+.endm
+
+.macro wstrw, reg:req, base:req, offset:req
+.inst 0xfd800100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2)
+.endm
+
+#ifdef __clang__
+
+#define wCon c1
+
+.macro tmrc, dest:req, control:req
+mrc p1, 0, \dest, \control, c0, 0
+.endm
+
+.macro tmcr, control:req, src:req
+mcr p1, 0, \src, \control, c0, 0
+.endm
+#endif
+
+#endif
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index e15444b25ca0..beac45e89ba6 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -185,14 +185,24 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			*(u32 *)loc |= offset & 0x7fffffff;
 			break;
 
+		case R_ARM_REL32:
+			*(u32 *)loc += sym->st_value - loc;
+			break;
+
 		case R_ARM_MOVW_ABS_NC:
 		case R_ARM_MOVT_ABS:
+		case R_ARM_MOVW_PREL_NC:
+		case R_ARM_MOVT_PREL:
 			offset = tmp = __mem_to_opcode_arm(*(u32 *)loc);
 			offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff);
 			offset = (offset ^ 0x8000) - 0x8000;
 
 			offset += sym->st_value;
-			if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS)
+			if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_PREL ||
+			    ELF32_R_TYPE(rel->r_info) == R_ARM_MOVW_PREL_NC)
+				offset -= loc;
+			if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS ||
+			    ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_PREL)
 				offset >>= 16;
 
 			tmp &= 0xfff0f000;
@@ -283,6 +293,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 
 		case R_ARM_THM_MOVW_ABS_NC:
 		case R_ARM_THM_MOVT_ABS:
+		case R_ARM_THM_MOVW_PREL_NC:
+		case R_ARM_THM_MOVT_PREL:
 			upper = __mem_to_opcode_thumb16(*(u16 *)loc);
 			lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
 
@@ -302,7 +314,11 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			offset = (offset ^ 0x8000) - 0x8000;
 			offset += sym->st_value;
 
-			if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS)
+			if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_PREL ||
+			    ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVW_PREL_NC)
+				offset -= loc;
+			if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS ||
+			    ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_PREL)
 				offset >>= 16;
 
 			upper = (u16)((upper & 0xfbf0) |
diff --git a/arch/arm/kernel/phys2virt.S b/arch/arm/kernel/phys2virt.S
new file mode 100644
index 000000000000..fb53db78fe78
--- /dev/null
+++ b/arch/arm/kernel/phys2virt.S
@@ -0,0 +1,238 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  Copyright (C) 1994-2002 Russell King
+ *  Copyright (c) 2003, 2020 ARM Limited
+ *  All Rights Reserved
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/page.h>
+
+#ifdef __ARMEB__
+#define LOW_OFFSET	0x4
+#define HIGH_OFFSET	0x0
+#else
+#define LOW_OFFSET	0x0
+#define HIGH_OFFSET	0x4
+#endif
+
+/*
+ * __fixup_pv_table - patch the stub instructions with the delta between
+ *                    PHYS_OFFSET and PAGE_OFFSET, which is assumed to be
+ *                    2 MiB aligned.
+ *
+ * Called from head.S, which expects the following registers to be preserved:
+ *   r1 = machine no, r2 = atags or dtb,
+ *   r8 = phys_offset, r9 = cpuid, r10 = procinfo
+ */
+	__HEAD
+ENTRY(__fixup_pv_table)
+	mov	r0, r8, lsr #PAGE_SHIFT	@ convert to PFN
+	str_l	r0, __pv_phys_pfn_offset, r3
+
+	adr_l	r0, __pv_offset
+	subs	r3, r8, #PAGE_OFFSET	@ PHYS_OFFSET - PAGE_OFFSET
+	mvn	ip, #0
+	strcc	ip, [r0, #HIGH_OFFSET]	@ save to __pv_offset high bits
+	str	r3, [r0, #LOW_OFFSET]	@ save to __pv_offset low bits
+
+	mov	r0, r3, lsr #21		@ constant for add/sub instructions
+	teq	r3, r0, lsl #21 	@ must be 2 MiB aligned
+	bne	0f
+
+	adr_l	r4, __pv_table_begin
+	adr_l	r5, __pv_table_end
+	b	__fixup_a_pv_table
+
+0:	mov	r0, r0			@ deadloop on error
+	b	0b
+ENDPROC(__fixup_pv_table)
+
+	.text
+__fixup_a_pv_table:
+	adr_l	r6, __pv_offset
+	ldr	r0, [r6, #HIGH_OFFSET]	@ pv_offset high word
+	ldr	r6, [r6, #LOW_OFFSET]	@ pv_offset low word
+	cmn	r0, #1
+#ifdef CONFIG_THUMB2_KERNEL
+	@
+	@ The Thumb-2 versions of the patchable sequences are
+	@
+	@ phys-to-virt:			movw	<reg>, #offset<31:21>
+	@				lsl	<reg>, #21
+	@				sub	<VA>, <PA>, <reg>
+	@
+	@ virt-to-phys (non-LPAE):	movw	<reg>, #offset<31:21>
+	@				lsl	<reg>, #21
+	@				add	<PA>, <VA>, <reg>
+	@
+	@ virt-to-phys (LPAE):		movw	<reg>, #offset<31:21>
+	@				lsl	<reg>, #21
+	@				adds	<PAlo>, <VA>, <reg>
+	@				mov	<PAhi>, #offset<39:32>
+	@				adc	<PAhi>, <PAhi>, #0
+	@
+	@ In the non-LPAE case, all patchable instructions are MOVW
+	@ instructions, where we need to patch in the offset into the
+	@ second halfword of the opcode (the 16-bit immediate is encoded
+	@ as imm4:i:imm3:imm8)
+	@
+	@       15       11 10  9           4 3    0  15  14  12 11 8 7    0
+	@      +-----------+---+-------------+------++---+------+----+------+
+	@ MOVW | 1 1 1 1 0 | i | 1 0 0 1 0 0 | imm4 || 0 | imm3 | Rd | imm8 |
+	@      +-----------+---+-------------+------++---+------+----+------+
+	@
+	@ In the LPAE case, we also need to patch in the high word of the
+	@ offset into the immediate field of the MOV instruction, or patch it
+	@ to a MVN instruction if the offset is negative. In this case, we
+	@ need to inspect the first halfword of the opcode, to check whether
+	@ it is MOVW or MOV/MVN, and to perform the MOV to MVN patching if
+	@ needed. The encoding of the immediate is rather complex for values
+	@ of i:imm3 != 0b0000, but fortunately, we never need more than 8 lower
+	@ order bits, which can be patched into imm8 directly (and i:imm3
+	@ cleared)
+	@
+	@      15       11 10  9        5         0  15  14  12 11 8 7    0
+	@     +-----------+---+---------------------++---+------+----+------+
+	@ MOV | 1 1 1 1 0 | i | 0 0 0 1 0 0 1 1 1 1 || 0 | imm3 | Rd | imm8 |
+	@ MVN | 1 1 1 1 0 | i | 0 0 0 1 1 0 1 1 1 1 || 0 | imm3 | Rd | imm8 |
+	@     +-----------+---+---------------------++---+------+----+------+
+	@
+	moveq	r0, #0x200000		@ set bit 21, mov to mvn instruction
+	lsrs	r3, r6, #29		@ isolate top 3 bits of displacement
+	ubfx	r6, r6, #21, #8		@ put bits 28:21 into the MOVW imm8 field
+	bfi	r6, r3, #12, #3		@ put bits 31:29 into the MOVW imm3 field
+	b	.Lnext
+.Lloop:	add	r7, r4
+	adds	r4, #4			@ clears Z flag
+#ifdef CONFIG_ARM_LPAE
+	ldrh	ip, [r7]
+ARM_BE8(rev16	ip, ip)
+	tst	ip, #0x200		@ MOVW has bit 9 set, MVN has it clear
+	bne	0f			@ skip to MOVW handling (Z flag is clear)
+	bic	ip, #0x20		@ clear bit 5 (MVN -> MOV)
+	orr	ip, ip, r0, lsr #16	@ MOV -> MVN if offset < 0
+ARM_BE8(rev16	ip, ip)
+	strh	ip, [r7]
+	@ Z flag is set
+0:
+#endif
+	ldrh	ip, [r7, #2]
+ARM_BE8(rev16	ip, ip)
+	and	ip, #0xf00		@ clear everything except Rd field
+	orreq	ip, r0			@ Z flag set -> MOV/MVN -> patch in high bits
+	orrne	ip, r6			@ Z flag clear -> MOVW -> patch in low bits
+ARM_BE8(rev16	ip, ip)
+	strh	ip, [r7, #2]
+#else
+#ifdef CONFIG_CPU_ENDIAN_BE8
+@ in BE8, we load data in BE, but instructions still in LE
+#define PV_BIT24	0x00000001
+#define PV_IMM8_MASK	0xff000000
+#define PV_IMMR_MSB	0x00080000
+#else
+#define PV_BIT24	0x01000000
+#define PV_IMM8_MASK	0x000000ff
+#define PV_IMMR_MSB	0x00000800
+#endif
+
+	@
+	@ The ARM versions of the patchable sequences are
+	@
+	@ phys-to-virt:			sub	<VA>, <PA>, #offset<31:24>, lsl #24
+	@				sub	<VA>, <PA>, #offset<23:16>, lsl #16
+	@
+	@ virt-to-phys (non-LPAE):	add	<PA>, <VA>, #offset<31:24>, lsl #24
+	@				add	<PA>, <VA>, #offset<23:16>, lsl #16
+	@
+	@ virt-to-phys (LPAE):		movw	<reg>, #offset<31:20>
+	@				adds	<PAlo>, <VA>, <reg>, lsl #20
+	@				mov	<PAhi>, #offset<39:32>
+	@				adc	<PAhi>, <PAhi>, #0
+	@
+	@ In the non-LPAE case, all patchable instructions are ADD or SUB
+	@ instructions, where we need to patch in the offset into the
+	@ immediate field of the opcode, which is emitted with the correct
+	@ rotation value. (The effective value of the immediate is imm12<7:0>
+	@ rotated right by [2 * imm12<11:8>] bits)
+	@
+	@      31   28 27      23 22  20 19  16 15  12 11    0
+	@      +------+-----------------+------+------+-------+
+	@  ADD | cond | 0 0 1 0 1 0 0 0 |  Rn  |  Rd  | imm12 |
+	@  SUB | cond | 0 0 1 0 0 1 0 0 |  Rn  |  Rd  | imm12 |
+	@  MOV | cond | 0 0 1 1 1 0 1 0 |  Rn  |  Rd  | imm12 |
+	@  MVN | cond | 0 0 1 1 1 1 1 0 |  Rn  |  Rd  | imm12 |
+	@      +------+-----------------+------+------+-------+
+	@
+	@ In the LPAE case, we use a MOVW instruction to carry the low offset
+	@ word, and patch in the high word of the offset into the immediate
+	@ field of the subsequent MOV instruction, or patch it to a MVN
+	@ instruction if the offset is negative. We can distinguish MOVW
+	@ instructions based on bits 23:22 of the opcode, and ADD/SUB can be
+	@ distinguished from MOV/MVN (all using the encodings above) using
+	@ bit 24.
+	@
+	@      31   28 27      23 22  20 19  16 15  12 11    0
+	@      +------+-----------------+------+------+-------+
+	@ MOVW | cond | 0 0 1 1 0 0 0 0 | imm4 |  Rd  | imm12 |
+	@      +------+-----------------+------+------+-------+
+	@
+	moveq	r0, #0x400000		@ set bit 22, mov to mvn instruction
+	mov	r3, r6, lsr #16		@ put offset bits 31-16 into r3
+	mov	r6, r6, lsr #24		@ put offset bits 31-24 into r6
+	and	r3, r3, #0xf0		@ only keep offset bits 23-20 in r3
+	b	.Lnext
+.Lloop:	ldr	ip, [r7, r4]
+#ifdef CONFIG_ARM_LPAE
+	tst	ip, #PV_BIT24		@ ADD/SUB have bit 24 clear
+	beq	1f
+ARM_BE8(rev	ip, ip)
+	tst	ip, #0xc00000		@ MOVW has bits 23:22 clear
+	bic	ip, ip, #0x400000	@ clear bit 22
+	bfc	ip, #0, #12		@ clear imm12 field of MOV[W] instruction
+	orreq	ip, ip, r6, lsl #4	@ MOVW -> mask in offset bits 31-24
+	orreq	ip, ip, r3, lsr #4	@ MOVW -> mask in offset bits 23-20
+	orrne	ip, ip, r0		@ MOV  -> mask in offset bits 7-0 (or bit 22)
+ARM_BE8(rev	ip, ip)
+	b	2f
+1:
+#endif
+	tst	ip, #PV_IMMR_MSB		@ rotation value >= 16 ?
+	bic	ip, ip, #PV_IMM8_MASK
+	orreq	ip, ip, r6 ARM_BE8(, lsl #24)	@ mask in offset bits 31-24
+	orrne	ip, ip, r3 ARM_BE8(, lsl #24)	@ mask in offset bits 23-20
+2:
+	str	ip, [r7, r4]
+	add	r4, r4, #4
+#endif
+
+.Lnext:
+	cmp	r4, r5
+	ldrcc	r7, [r4]		@ use branch for delay slot
+	bcc	.Lloop
+	ret	lr
+ENDPROC(__fixup_a_pv_table)
+
+ENTRY(fixup_pv_table)
+	stmfd	sp!, {r4 - r7, lr}
+	mov	r4, r0			@ r0 = table start
+	add	r5, r0, r1		@ r1 = table size
+	bl	__fixup_a_pv_table
+	ldmfd	sp!, {r4 - r7, pc}
+ENDPROC(fixup_pv_table)
+
+	.data
+	.align	2
+	.globl	__pv_phys_pfn_offset
+	.type	__pv_phys_pfn_offset, %object
+__pv_phys_pfn_offset:
+	.word	0
+	.size	__pv_phys_pfn_offset, . -__pv_phys_pfn_offset
+
+	.globl	__pv_offset
+	.type	__pv_offset, %object
+__pv_offset:
+	.quad	0
+	.size	__pv_offset, . -__pv_offset
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 3f65d0ac9f63..1a5edf562e85 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -18,6 +18,7 @@
 #include <linux/of_platform.h>
 #include <linux/init.h>
 #include <linux/kexec.h>
+#include <linux/libfdt.h>
 #include <linux/of_fdt.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
@@ -58,6 +59,7 @@
 #include <asm/unwind.h>
 #include <asm/memblock.h>
 #include <asm/virt.h>
+#include <asm/kasan.h>
 
 #include "atags.h"
 
@@ -763,7 +765,7 @@ int __init arm_add_memory(u64 start, u64 size)
 #ifndef CONFIG_PHYS_ADDR_T_64BIT
 	if (aligned_start > ULONG_MAX) {
 		pr_crit("Ignoring memory at 0x%08llx outside 32-bit physical address space\n",
-			(long long)start);
+			start);
 		return -EINVAL;
 	}
 
@@ -1081,19 +1083,27 @@ void __init hyp_mode_check(void)
 
 void __init setup_arch(char **cmdline_p)
 {
-	const struct machine_desc *mdesc;
+	const struct machine_desc *mdesc = NULL;
+	void *atags_vaddr = NULL;
+
+	if (__atags_pointer)
+		atags_vaddr = FDT_VIRT_BASE(__atags_pointer);
 
 	setup_processor();
-	mdesc = setup_machine_fdt(__atags_pointer);
+	if (atags_vaddr) {
+		mdesc = setup_machine_fdt(atags_vaddr);
+		if (mdesc)
+			memblock_reserve(__atags_pointer,
+					 fdt_totalsize(atags_vaddr));
+	}
 	if (!mdesc)
-		mdesc = setup_machine_tags(__atags_pointer, __machine_arch_type);
+		mdesc = setup_machine_tags(atags_vaddr, __machine_arch_type);
 	if (!mdesc) {
 		early_print("\nError: invalid dtb and unrecognized/unsupported machine ID\n");
 		early_print("  r1=0x%08x, r2=0x%08x\n", __machine_arch_type,
 			    __atags_pointer);
 		if (__atags_pointer)
-			early_print("  r2[]=%*ph\n", 16,
-				    phys_to_virt(__atags_pointer));
+			early_print("  r2[]=%*ph\n", 16, atags_vaddr);
 		dump_machine_table();
 	}
 
@@ -1126,7 +1136,7 @@ void __init setup_arch(char **cmdline_p)
 	efi_init();
 	/*
 	 * Make sure the calculation for lowmem/highmem is set appropriately
-	 * before reserving/allocating any mmeory
+	 * before reserving/allocating any memory
 	 */
 	adjust_lowmem_bounds();
 	arm_memblock_init(mdesc);
@@ -1136,6 +1146,7 @@ void __init setup_arch(char **cmdline_p)
 	early_ioremap_reset();
 
 	paging_init(mdesc);
+	kasan_init();
 	request_standard_resources(mdesc);
 
 	if (mdesc->restart)
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 5dc8b80bb693..43077e11dafd 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -72,8 +72,9 @@ ENTRY(__cpu_suspend)
 	ldr	r3, =sleep_save_sp
 	stmfd	sp!, {r0, r1}		@ save suspend func arg and pointer
 	ldr	r3, [r3, #SLEEP_SAVE_SP_VIRT]
-	ALT_SMP(ldr r0, =mpidr_hash)
+	ALT_SMP(W(nop))			@ don't use adr_l inside ALT_SMP()
 	ALT_UP_B(1f)
+	adr_l	r0, mpidr_hash
 	/* This ldmia relies on the memory layout of the mpidr_hash struct */
 	ldmia	r0, {r1, r6-r8}	@ r1 = mpidr mask (r6,r7,r8) = l[0,1,2] shifts
 	compute_mpidr_hash	r0, r6, r7, r8, r2, r1
@@ -147,9 +148,8 @@ no_hyp:
 	mov	r1, #0
 	ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
 	ALT_UP_B(1f)
-	adr	r2, mpidr_hash_ptr
-	ldr	r3, [r2]
-	add	r2, r2, r3		@ r2 = struct mpidr_hash phys address
+	adr_l	r2, mpidr_hash		@ r2 = struct mpidr_hash phys address
+
 	/*
 	 * This ldmia relies on the memory layout of the mpidr_hash
 	 * struct mpidr_hash.
@@ -157,10 +157,7 @@ no_hyp:
 	ldmia	r2, { r3-r6 }	@ r3 = mpidr mask (r4,r5,r6) = l[0,1,2] shifts
 	compute_mpidr_hash	r1, r4, r5, r6, r0, r3
 1:
-	adr	r0, _sleep_save_sp
-	ldr	r2, [r0]
-	add	r0, r0, r2
-	ldr	r0, [r0, #SLEEP_SAVE_SP_PHYS]
+	ldr_l	r0, sleep_save_sp + SLEEP_SAVE_SP_PHYS
 	ldr	r0, [r0, r1, lsl #2]
 
 	@ load phys pgd, stack, resume fn
@@ -177,12 +174,6 @@ ENDPROC(cpu_resume_arm)
 ENDPROC(cpu_resume_no_hyp)
 #endif
 
-	.align 2
-_sleep_save_sp:
-	.long	sleep_save_sp - .
-mpidr_hash_ptr:
-	.long	mpidr_hash - .			@ mpidr_hash struct offset
-
 	.data
 	.align	2
 	.type	sleep_save_sp, #object
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 48099c6e1e4a..5c48eb4fd0e5 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -524,14 +524,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 }
 
 static const char *ipi_types[NR_IPI] __tracepoint_string = {
-#define S(x,s)	[x] = s
-	S(IPI_WAKEUP, "CPU wakeup interrupts"),
-	S(IPI_TIMER, "Timer broadcast interrupts"),
-	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
-	S(IPI_CALL_FUNC, "Function call interrupts"),
-	S(IPI_CPU_STOP, "CPU stop interrupts"),
-	S(IPI_IRQ_WORK, "IRQ work interrupts"),
-	S(IPI_COMPLETION, "completion interrupts"),
+	[IPI_WAKEUP]		= "CPU wakeup interrupts",
+	[IPI_TIMER]		= "Timer broadcast interrupts",
+	[IPI_RESCHEDULE]	= "Rescheduling interrupts",
+	[IPI_CALL_FUNC]		= "Function call interrupts",
+	[IPI_CPU_STOP]		= "CPU stop interrupts",
+	[IPI_IRQ_WORK]		= "IRQ work interrupts",
+	[IPI_COMPLETION]	= "completion interrupts",
 };
 
 static void smp_cross_call(const struct cpumask *target, unsigned int ipinr);
@@ -550,7 +549,7 @@ void show_ipi_list(struct seq_file *p, int prec)
 		seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
 
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+			seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu));
 
 		seq_printf(p, " %s\n", ipi_types[i]);
 	}
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index d2bd0df2318d..59fdf257bf8b 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -18,9 +18,6 @@
 #warning Your compiler does not have EABI support.
 #warning    ARM unwind is known to compile only with EABI compilers.
 #warning    Change compiler or disable ARM_UNWIND option.
-#elif (__GNUC__ == 4 && __GNUC_MINOR__ <= 2) && !defined(__clang__)
-#warning Your compiler is too buggy; it is known to not compile ARM unwind support.
-#warning    Change compiler or disable ARM_UNWIND option.
 #endif
 #endif /* __CHECKER__ */
 
@@ -236,7 +233,11 @@ static int unwind_pop_register(struct unwind_ctrl_block *ctrl,
 		if (*vsp >= (unsigned long *)ctrl->sp_high)
 			return -URC_FAILURE;
 
-	ctrl->vrs[reg] = *(*vsp)++;
+	/* Use READ_ONCE_NOCHECK here to avoid this memory access
+	 * from being tracked by KASAN.
+	 */
+	ctrl->vrs[reg] = READ_ONCE_NOCHECK(*(*vsp));
+	(*vsp)++;
 	return URC_OK;
 }
 
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index 09a333153dc6..e4caf48c089f 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -58,10 +58,12 @@
 
 /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
 
+ENTRY(__memcpy)
 ENTRY(mmiocpy)
-ENTRY(memcpy)
+WEAK(memcpy)
 
 #include "copy_template.S"
 
 ENDPROC(memcpy)
 ENDPROC(mmiocpy)
+ENDPROC(__memcpy)
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index b50e5770fb44..6fecc12a1f51 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -24,12 +24,13 @@
  * occurring in the opposite direction.
  */
 
-ENTRY(memmove)
+ENTRY(__memmove)
+WEAK(memmove)
 	UNWIND(	.fnstart			)
 
 		subs	ip, r0, r1
 		cmphi	r2, ip
-		bls	memcpy
+		bls	__memcpy
 
 		stmfd	sp!, {r0, r4, lr}
 	UNWIND(	.fnend				)
@@ -222,3 +223,4 @@ ENTRY(memmove)
 18:		backward_copy_shift	push=24	pull=8
 
 ENDPROC(memmove)
+ENDPROC(__memmove)
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index 6ca4535c47fb..9817cb258c1a 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -13,8 +13,9 @@
 	.text
 	.align	5
 
+ENTRY(__memset)
 ENTRY(mmioset)
-ENTRY(memset)
+WEAK(memset)
 UNWIND( .fnstart         )
 	ands	r3, r0, #3		@ 1 unaligned?
 	mov	ip, r0			@ preserve r0 as return value
@@ -132,6 +133,7 @@ UNWIND( .fnstart            )
 UNWIND( .fnend   )
 ENDPROC(memset)
 ENDPROC(mmioset)
+ENDPROC(__memset)
 
 ENTRY(__memset32)
 UNWIND( .fnstart         )
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index f3191704cab9..56d6814bec26 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -230,10 +230,12 @@ static int _omap_device_notifier_call(struct notifier_block *nb,
 		break;
 	case BUS_NOTIFY_BIND_DRIVER:
 		od = to_omap_device(pdev);
-		if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) &&
-		    pm_runtime_status_suspended(dev)) {
+		if (od) {
 			od->_driver_status = BUS_NOTIFY_BIND_DRIVER;
-			pm_runtime_set_active(dev);
+			if (od->_state == OMAP_DEVICE_STATE_ENABLED &&
+			    pm_runtime_status_suspended(dev)) {
+				pm_runtime_set_active(dev);
+			}
 		}
 		break;
 	case BUS_NOTIFY_ADD_DEVICE:
diff --git a/arch/arm/mach-omap2/pmic-cpcap.c b/arch/arm/mach-omap2/pmic-cpcap.c
index eab281a5fc9f..09076ad0576d 100644
--- a/arch/arm/mach-omap2/pmic-cpcap.c
+++ b/arch/arm/mach-omap2/pmic-cpcap.c
@@ -71,7 +71,7 @@ static struct omap_voltdm_pmic omap_cpcap_iva = {
 	.vp_vstepmin = OMAP4_VP_VSTEPMIN_VSTEPMIN,
 	.vp_vstepmax = OMAP4_VP_VSTEPMAX_VSTEPMAX,
 	.vddmin = 900000,
-	.vddmax = 1350000,
+	.vddmax = 1375000,
 	.vp_timeout_us = OMAP4_VP_VLIMITTO_TIMEOUT_US,
 	.i2c_slave_addr = 0x44,
 	.volt_reg_addr = 0x0,
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 65e4482e3849..02692fbe2db5 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -743,6 +743,7 @@ config SWP_EMULATE
 config CPU_BIG_ENDIAN
 	bool "Build big-endian kernel"
 	depends on ARCH_SUPPORTS_BIG_ENDIAN
+	depends on !LD_IS_LLD
 	help
 	  Say Y if you plan on running a kernel in big-endian mode.
 	  Note that your board must be properly built and your board
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index c4ce477c5261..3510503bc5e6 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -7,6 +7,7 @@ obj-y				:= extable.o fault.o init.o iomap.o
 obj-y				+= dma-mapping$(MMUEXT).o
 obj-$(CONFIG_MMU)		+= fault-armv.o flush.o idmap.o ioremap.o \
 				   mmap.o pgd.o mmu.o pageattr.o
+KASAN_SANITIZE_mmu.o		:= n
 
 ifneq ($(CONFIG_MMU),y)
 obj-y				+= nommu.o
@@ -16,6 +17,7 @@ endif
 obj-$(CONFIG_ARM_PTDUMP_CORE)	+= dump.o
 obj-$(CONFIG_ARM_PTDUMP_DEBUGFS)	+= ptdump_debugfs.o
 obj-$(CONFIG_MODULES)		+= proc-syms.o
+KASAN_SANITIZE_physaddr.o	:= n
 obj-$(CONFIG_DEBUG_VIRTUAL)	+= physaddr.o
 
 obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
@@ -110,3 +112,6 @@ obj-$(CONFIG_CACHE_L2X0_PMU)	+= cache-l2x0-pmu.o
 obj-$(CONFIG_CACHE_XSC3L2)	+= cache-xsc3l2.o
 obj-$(CONFIG_CACHE_TAUROS2)	+= cache-tauros2.o
 obj-$(CONFIG_CACHE_UNIPHIER)	+= cache-uniphier.o
+
+KASAN_SANITIZE_kasan_init.o	:= n
+obj-$(CONFIG_KASAN)		+= kasan_init.o
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index db623d7c30de..828a2561b229 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -223,7 +223,6 @@ void __init arm_memblock_init(const struct machine_desc *mdesc)
 	if (mdesc->reserve)
 		mdesc->reserve();
 
-	early_init_fdt_reserve_self();
 	early_init_fdt_scan_reserved_mem();
 
 	/* reserve memory for DMA contiguous allocations */
diff --git a/arch/arm/mm/kasan_init.c b/arch/arm/mm/kasan_init.c
new file mode 100644
index 000000000000..9c348042a724
--- /dev/null
+++ b/arch/arm/mm/kasan_init.c
@@ -0,0 +1,291 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file contains kasan initialization code for ARM.
+ *
+ * Copyright (c) 2018 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ * Author: Linus Walleij <linus.walleij@linaro.org>
+ */
+
+#define pr_fmt(fmt) "kasan: " fmt
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memblock.h>
+#include <linux/sched/task.h>
+#include <linux/start_kernel.h>
+#include <linux/pgtable.h>
+#include <asm/cputype.h>
+#include <asm/highmem.h>
+#include <asm/mach/map.h>
+#include <asm/memory.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/procinfo.h>
+#include <asm/proc-fns.h>
+
+#include "mm.h"
+
+static pgd_t tmp_pgd_table[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
+
+pmd_t tmp_pmd_table[PTRS_PER_PMD] __page_aligned_bss;
+
+static __init void *kasan_alloc_block(size_t size)
+{
+	return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS),
+				      MEMBLOCK_ALLOC_KASAN, NUMA_NO_NODE);
+}
+
+static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
+				      unsigned long end, bool early)
+{
+	unsigned long next;
+	pte_t *ptep = pte_offset_kernel(pmdp, addr);
+
+	do {
+		pte_t entry;
+		void *p;
+
+		next = addr + PAGE_SIZE;
+
+		if (!early) {
+			if (!pte_none(READ_ONCE(*ptep)))
+				continue;
+
+			p = kasan_alloc_block(PAGE_SIZE);
+			if (!p) {
+				panic("%s failed to allocate shadow page for address 0x%lx\n",
+				      __func__, addr);
+				return;
+			}
+			memset(p, KASAN_SHADOW_INIT, PAGE_SIZE);
+			entry = pfn_pte(virt_to_pfn(p),
+					__pgprot(pgprot_val(PAGE_KERNEL)));
+		} else if (pte_none(READ_ONCE(*ptep))) {
+			/*
+			 * The early shadow memory is mapping all KASan
+			 * operations to one and the same page in memory,
+			 * "kasan_early_shadow_page" so that the instrumentation
+			 * will work on a scratch area until we can set up the
+			 * proper KASan shadow memory.
+			 */
+			entry = pfn_pte(virt_to_pfn(kasan_early_shadow_page),
+					__pgprot(_L_PTE_DEFAULT | L_PTE_DIRTY | L_PTE_XN));
+		} else {
+			/*
+			 * Early shadow mappings are PMD_SIZE aligned, so if the
+			 * first entry is already set, they must all be set.
+			 */
+			return;
+		}
+
+		set_pte_at(&init_mm, addr, ptep, entry);
+	} while (ptep++, addr = next, addr != end);
+}
+
+/*
+ * The pmd (page middle directory) is only used on LPAE
+ */
+static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
+				      unsigned long end, bool early)
+{
+	unsigned long next;
+	pmd_t *pmdp = pmd_offset(pudp, addr);
+
+	do {
+		if (pmd_none(*pmdp)) {
+			/*
+			 * We attempt to allocate a shadow block for the PMDs
+			 * used by the PTEs for this address if it isn't already
+			 * allocated.
+			 */
+			void *p = early ? kasan_early_shadow_pte :
+				kasan_alloc_block(PAGE_SIZE);
+
+			if (!p) {
+				panic("%s failed to allocate shadow block for address 0x%lx\n",
+				      __func__, addr);
+				return;
+			}
+			pmd_populate_kernel(&init_mm, pmdp, p);
+			flush_pmd_entry(pmdp);
+		}
+
+		next = pmd_addr_end(addr, end);
+		kasan_pte_populate(pmdp, addr, next, early);
+	} while (pmdp++, addr = next, addr != end);
+}
+
+static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
+				      bool early)
+{
+	unsigned long next;
+	pgd_t *pgdp;
+	p4d_t *p4dp;
+	pud_t *pudp;
+
+	pgdp = pgd_offset_k(addr);
+
+	do {
+		/*
+		 * Allocate and populate the shadow block of p4d folded into
+		 * pud folded into pmd if it doesn't already exist
+		 */
+		if (!early && pgd_none(*pgdp)) {
+			void *p = kasan_alloc_block(PAGE_SIZE);
+
+			if (!p) {
+				panic("%s failed to allocate shadow block for address 0x%lx\n",
+				      __func__, addr);
+				return;
+			}
+			pgd_populate(&init_mm, pgdp, p);
+		}
+
+		next = pgd_addr_end(addr, end);
+		/*
+		 * We just immediately jump over the p4d and pud page
+		 * directories since we believe ARM32 will never gain four
+		 * nor five level page tables.
+		 */
+		p4dp = p4d_offset(pgdp, addr);
+		pudp = pud_offset(p4dp, addr);
+
+		kasan_pmd_populate(pudp, addr, next, early);
+	} while (pgdp++, addr = next, addr != end);
+}
+
+extern struct proc_info_list *lookup_processor_type(unsigned int);
+
+void __init kasan_early_init(void)
+{
+	struct proc_info_list *list;
+
+	/*
+	 * locate processor in the list of supported processor
+	 * types.  The linker builds this table for us from the
+	 * entries in arch/arm/mm/proc-*.S
+	 */
+	list = lookup_processor_type(read_cpuid_id());
+	if (list) {
+#ifdef MULTI_CPU
+		processor = *list->proc;
+#endif
+	}
+
+	BUILD_BUG_ON((KASAN_SHADOW_END - (1UL << 29)) != KASAN_SHADOW_OFFSET);
+	/*
+	 * We walk the page table and set all of the shadow memory to point
+	 * to the scratch page.
+	 */
+	kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, true);
+}
+
+static void __init clear_pgds(unsigned long start,
+			unsigned long end)
+{
+	for (; start && start < end; start += PMD_SIZE)
+		pmd_clear(pmd_off_k(start));
+}
+
+static int __init create_mapping(void *start, void *end)
+{
+	void *shadow_start, *shadow_end;
+
+	shadow_start = kasan_mem_to_shadow(start);
+	shadow_end = kasan_mem_to_shadow(end);
+
+	pr_info("Mapping kernel virtual memory block: %px-%px at shadow: %px-%px\n",
+		start, end, shadow_start, shadow_end);
+
+	kasan_pgd_populate((unsigned long)shadow_start & PAGE_MASK,
+			   PAGE_ALIGN((unsigned long)shadow_end), false);
+	return 0;
+}
+
+void __init kasan_init(void)
+{
+	phys_addr_t pa_start, pa_end;
+	u64 i;
+
+	/*
+	 * We are going to perform proper setup of shadow memory.
+	 *
+	 * At first we should unmap early shadow (clear_pgds() call bellow).
+	 * However, instrumented code can't execute without shadow memory.
+	 *
+	 * To keep the early shadow memory MMU tables around while setting up
+	 * the proper shadow memory, we copy swapper_pg_dir (the initial page
+	 * table) to tmp_pgd_table and use that to keep the early shadow memory
+	 * mapped until the full shadow setup is finished. Then we swap back
+	 * to the proper swapper_pg_dir.
+	 */
+
+	memcpy(tmp_pgd_table, swapper_pg_dir, sizeof(tmp_pgd_table));
+#ifdef CONFIG_ARM_LPAE
+	/* We need to be in the same PGD or this won't work */
+	BUILD_BUG_ON(pgd_index(KASAN_SHADOW_START) !=
+		     pgd_index(KASAN_SHADOW_END));
+	memcpy(tmp_pmd_table,
+	       pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_START)),
+	       sizeof(tmp_pmd_table));
+	set_pgd(&tmp_pgd_table[pgd_index(KASAN_SHADOW_START)],
+		__pgd(__pa(tmp_pmd_table) | PMD_TYPE_TABLE | L_PGD_SWAPPER));
+#endif
+	cpu_switch_mm(tmp_pgd_table, &init_mm);
+	local_flush_tlb_all();
+
+	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+	kasan_populate_early_shadow(kasan_mem_to_shadow((void *)VMALLOC_START),
+				    kasan_mem_to_shadow((void *)-1UL) + 1);
+
+	for_each_mem_range(i, &pa_start, &pa_end) {
+		void *start = __va(pa_start);
+		void *end = __va(pa_end);
+
+		/* Do not attempt to shadow highmem */
+		if (pa_start >= arm_lowmem_limit) {
+			pr_info("Skip highmem block at %pa-%pa\n", &pa_start, &pa_end);
+			continue;
+		}
+		if (pa_end > arm_lowmem_limit) {
+			pr_info("Truncating shadow for memory block at %pa-%pa to lowmem region at %pa\n",
+				&pa_start, &pa_end, &arm_lowmem_limit);
+			end = __va(arm_lowmem_limit);
+		}
+		if (start >= end) {
+			pr_info("Skipping invalid memory block %pa-%pa (virtual %p-%p)\n",
+				&pa_start, &pa_end, start, end);
+			continue;
+		}
+
+		create_mapping(start, end);
+	}
+
+	/*
+	 * 1. The module global variables are in MODULES_VADDR ~ MODULES_END,
+	 *    so we need to map this area.
+	 * 2. PKMAP_BASE ~ PKMAP_BASE+PMD_SIZE's shadow and MODULES_VADDR
+	 *    ~ MODULES_END's shadow is in the same PMD_SIZE, so we can't
+	 *    use kasan_populate_zero_shadow.
+	 */
+	create_mapping((void *)MODULES_VADDR, (void *)(PKMAP_BASE + PMD_SIZE));
+
+	/*
+	 * KAsan may reuse the contents of kasan_early_shadow_pte directly, so
+	 * we should make sure that it maps the zero page read-only.
+	 */
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte_at(&init_mm, KASAN_SHADOW_START + i*PAGE_SIZE,
+			   &kasan_early_shadow_pte[i],
+			   pfn_pte(virt_to_pfn(kasan_early_shadow_page),
+				__pgprot(pgprot_val(PAGE_KERNEL)
+					 | L_PTE_RDONLY)));
+
+	cpu_switch_mm(swapper_pg_dir, &init_mm);
+	local_flush_tlb_all();
+
+	memset(kasan_early_shadow_page, 0, PAGE_SIZE);
+	pr_info("Kernel address sanitizer initialized\n");
+	init_task.kasan_depth = 0;
+}
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index ab69250a86bc..c06ebfbc48c4 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -29,6 +29,7 @@
 #include <asm/procinfo.h>
 #include <asm/memory.h>
 #include <asm/pgalloc.h>
+#include <asm/kasan_def.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -39,6 +40,8 @@
 #include "mm.h"
 #include "tcm.h"
 
+extern unsigned long __atags_pointer;
+
 /*
  * empty_zero_page is a special page that is used for
  * zero-initialized data and COW.
@@ -946,7 +949,7 @@ static void __init create_mapping(struct map_desc *md)
 		return;
 	}
 
-	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
+	if (md->type == MT_DEVICE &&
 	    md->virtual >= PAGE_OFFSET && md->virtual < FIXADDR_START &&
 	    (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) {
 		pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n",
@@ -1253,8 +1256,25 @@ static inline void prepare_page_table(void)
 	/*
 	 * Clear out all the mappings below the kernel image.
 	 */
+#ifdef CONFIG_KASAN
+	/*
+	 * KASan's shadow memory inserts itself between the TASK_SIZE
+	 * and MODULES_VADDR. Do not clear the KASan shadow memory mappings.
+	 */
+	for (addr = 0; addr < KASAN_SHADOW_START; addr += PMD_SIZE)
+		pmd_clear(pmd_off_k(addr));
+	/*
+	 * Skip over the KASan shadow area. KASAN_SHADOW_END is sometimes
+	 * equal to MODULES_VADDR and then we exit the pmd clearing. If we
+	 * are using a thumb-compiled kernel, there there will be 8MB more
+	 * to clear as KASan always offset to 16 MB below MODULES_VADDR.
+	 */
+	for (addr = KASAN_SHADOW_END; addr < MODULES_VADDR; addr += PMD_SIZE)
+		pmd_clear(pmd_off_k(addr));
+#else
 	for (addr = 0; addr < MODULES_VADDR; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
+#endif
 
 #ifdef CONFIG_XIP_KERNEL
 	/* The XIP kernel is mapped in the module area -- skip over it */
@@ -1333,6 +1353,15 @@ static void __init devicemaps_init(const struct machine_desc *mdesc)
 	for (addr = VMALLOC_START; addr < (FIXADDR_TOP & PMD_MASK); addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
+	if (__atags_pointer) {
+		/* create a read-only mapping of the device tree */
+		map.pfn = __phys_to_pfn(__atags_pointer & SECTION_MASK);
+		map.virtual = FDT_FIXED_BASE;
+		map.length = FDT_FIXED_SIZE;
+		map.type = MT_ROM;
+		create_mapping(&map);
+	}
+
 	/*
 	 * Map the kernel if it is XIP.
 	 * It is always first in the modulearea.
@@ -1489,8 +1518,7 @@ static void __init map_lowmem(void)
 }
 
 #ifdef CONFIG_ARM_PV_FIXUP
-extern unsigned long __atags_pointer;
-typedef void pgtables_remap(long long offset, unsigned long pgd, void *bdata);
+typedef void pgtables_remap(long long offset, unsigned long pgd);
 pgtables_remap lpae_pgtables_remap_asm;
 
 /*
@@ -1503,7 +1531,6 @@ static void __init early_paging_init(const struct machine_desc *mdesc)
 	unsigned long pa_pgd;
 	unsigned int cr, ttbcr;
 	long long offset;
-	void *boot_data;
 
 	if (!mdesc->pv_fixup)
 		return;
@@ -1520,7 +1547,6 @@ static void __init early_paging_init(const struct machine_desc *mdesc)
 	 */
 	lpae_pgtables_remap = (pgtables_remap *)(unsigned long)__pa(lpae_pgtables_remap_asm);
 	pa_pgd = __pa(swapper_pg_dir);
-	boot_data = __va(__atags_pointer);
 	barrier();
 
 	pr_info("Switching physical address space to 0x%08llx\n",
@@ -1556,7 +1582,7 @@ static void __init early_paging_init(const struct machine_desc *mdesc)
 	 * needs to be assembly.  It's fairly simple, as we're using the
 	 * temporary tables setup by the initial assembly code.
 	 */
-	lpae_pgtables_remap(offset, pa_pgd, boot_data);
+	lpae_pgtables_remap(offset, pa_pgd);
 
 	/* Re-enable the caches and cacheable TLB walks */
 	asm volatile("mcr p15, 0, %0, c2, c0, 2" : : "r" (ttbcr));
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index c5e1b27046a8..f8e9bc58a84f 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -66,7 +66,21 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	new_pmd = pmd_alloc(mm, new_pud, 0);
 	if (!new_pmd)
 		goto no_pmd;
-#endif
+#ifdef CONFIG_KASAN
+	/*
+	 * Copy PMD table for KASAN shadow mappings.
+	 */
+	init_pgd = pgd_offset_k(TASK_SIZE);
+	init_p4d = p4d_offset(init_pgd, TASK_SIZE);
+	init_pud = pud_offset(init_p4d, TASK_SIZE);
+	init_pmd = pmd_offset(init_pud, TASK_SIZE);
+	new_pmd = pmd_offset(new_pud, TASK_SIZE);
+	memcpy(new_pmd, init_pmd,
+	       (pmd_index(MODULES_VADDR) - pmd_index(TASK_SIZE))
+	       * sizeof(pmd_t));
+	clean_dcache_area(new_pmd, PTRS_PER_PMD * sizeof(pmd_t));
+#endif /* CONFIG_KASAN */
+#endif /* CONFIG_LPAE */
 
 	if (!vectors_high()) {
 		/*
diff --git a/arch/arm/mm/pv-fixup-asm.S b/arch/arm/mm/pv-fixup-asm.S
index 8eade0416739..5c5e1952000a 100644
--- a/arch/arm/mm/pv-fixup-asm.S
+++ b/arch/arm/mm/pv-fixup-asm.S
@@ -39,8 +39,8 @@ ENTRY(lpae_pgtables_remap_asm)
 
 	/* Update level 2 entries for the boot data */
 	add	r7, r2, #0x1000
-	add	r7, r7, r3, lsr #SECTION_SHIFT - L2_ORDER
-	bic	r7, r7, #(1 << L2_ORDER) - 1
+	movw	r3, #FDT_FIXED_BASE >> (SECTION_SHIFT - L2_ORDER)
+	add	r7, r7, r3
 	ldrd	r4, r5, [r7]
 	adds	r4, r4, r0
 	adc	r5, r5, r1
diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
index 150ce6e6a5d3..b558bee0e1f6 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
@@ -42,6 +42,8 @@ GCOV_PROFILE := n
 # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
 KCOV_INSTRUMENT := n
 
+KASAN_SANITIZE := n
+
 # Force dependency
 $(obj)/vdso.o : $(obj)/vdso.so
 
diff --git a/arch/arm/vfp/entry.S b/arch/arm/vfp/entry.S
index 0186cf9da890..27b0a1f27fbd 100644
--- a/arch/arm/vfp/entry.S
+++ b/arch/arm/vfp/entry.S
@@ -37,20 +37,3 @@ ENDPROC(vfp_null_entry)
 	.align	2
 .LCvfp:
 	.word	vfp_vector
-
-@ This code is called if the VFP does not exist. It needs to flag the
-@ failure to the VFP initialisation code.
-
-	__INIT
-ENTRY(vfp_testing_entry)
-	dec_preempt_count_ti r10, r4
-	ldr	r0, VFP_arch_address
-	str	r0, [r0]		@ set to non-zero value
-	ret	r9			@ we have handled the fault
-ENDPROC(vfp_testing_entry)
-
-	.align	2
-VFP_arch_address:
-	.word	VFP_arch
-
-	__FINIT
diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S
index 4fcff9f59947..d5837bf05a9a 100644
--- a/arch/arm/vfp/vfphw.S
+++ b/arch/arm/vfp/vfphw.S
@@ -79,11 +79,6 @@ ENTRY(vfp_support_entry)
 	DBGSTR3	"instr %08x pc %08x state %p", r0, r2, r10
 
 	.fpu	vfpv2
-	ldr	r3, [sp, #S_PSR]	@ Neither lazy restore nor FP exceptions
-	and	r3, r3, #MODE_MASK	@ are supported in kernel mode
-	teq	r3, #USR_MODE
-	bne	vfp_kmode_exception	@ Returns through lr
-
 	VFPFMRX	r1, FPEXC		@ Is the VFP enabled?
 	DBGSTR1	"fpexc %08x", r1
 	tst	r1, #FPEXC_EN
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 8c9e7f9f0277..2cb355c1b5b7 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -23,6 +23,7 @@
 #include <asm/cputype.h>
 #include <asm/system_info.h>
 #include <asm/thread_notify.h>
+#include <asm/traps.h>
 #include <asm/vfp.h>
 
 #include "vfpinstr.h"
@@ -31,7 +32,6 @@
 /*
  * Our undef handlers (in entry.S)
  */
-asmlinkage void vfp_testing_entry(void);
 asmlinkage void vfp_support_entry(void);
 asmlinkage void vfp_null_entry(void);
 
@@ -42,7 +42,7 @@ asmlinkage void (*vfp_vector)(void) = vfp_null_entry;
  * Used in startup: set to non-zero if VFP checks fail
  * After startup, holds VFP architecture
  */
-unsigned int VFP_arch;
+static unsigned int __initdata VFP_arch;
 
 /*
  * The pointer to the vfpstate structure of the thread which currently
@@ -436,7 +436,7 @@ static void vfp_enable(void *unused)
  * present on all CPUs within a SMP complex. Needs to be called prior to
  * vfp_init().
  */
-void vfp_disable(void)
+void __init vfp_disable(void)
 {
 	if (VFP_arch) {
 		pr_debug("%s: should be called prior to vfp_init\n", __func__);
@@ -642,7 +642,9 @@ static int vfp_starting_cpu(unsigned int unused)
 	return 0;
 }
 
-void vfp_kmode_exception(void)
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+static int vfp_kmode_exception(struct pt_regs *regs, unsigned int instr)
 {
 	/*
 	 * If we reach this point, a floating point exception has been raised
@@ -660,9 +662,51 @@ void vfp_kmode_exception(void)
 		pr_crit("BUG: unsupported FP instruction in kernel mode\n");
 	else
 		pr_crit("BUG: FP instruction issued in kernel mode with FP unit disabled\n");
+	pr_crit("FPEXC == 0x%08x\n", fmrx(FPEXC));
+	return 1;
 }
 
-#ifdef CONFIG_KERNEL_MODE_NEON
+static struct undef_hook vfp_kmode_exception_hook[] = {{
+	.instr_mask	= 0xfe000000,
+	.instr_val	= 0xf2000000,
+	.cpsr_mask	= MODE_MASK | PSR_T_BIT,
+	.cpsr_val	= SVC_MODE,
+	.fn		= vfp_kmode_exception,
+}, {
+	.instr_mask	= 0xff100000,
+	.instr_val	= 0xf4000000,
+	.cpsr_mask	= MODE_MASK | PSR_T_BIT,
+	.cpsr_val	= SVC_MODE,
+	.fn		= vfp_kmode_exception,
+}, {
+	.instr_mask	= 0xef000000,
+	.instr_val	= 0xef000000,
+	.cpsr_mask	= MODE_MASK | PSR_T_BIT,
+	.cpsr_val	= SVC_MODE | PSR_T_BIT,
+	.fn		= vfp_kmode_exception,
+}, {
+	.instr_mask	= 0xff100000,
+	.instr_val	= 0xf9000000,
+	.cpsr_mask	= MODE_MASK | PSR_T_BIT,
+	.cpsr_val	= SVC_MODE | PSR_T_BIT,
+	.fn		= vfp_kmode_exception,
+}, {
+	.instr_mask	= 0x0c000e00,
+	.instr_val	= 0x0c000a00,
+	.cpsr_mask	= MODE_MASK,
+	.cpsr_val	= SVC_MODE,
+	.fn		= vfp_kmode_exception,
+}};
+
+static int __init vfp_kmode_exception_hook_init(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(vfp_kmode_exception_hook); i++)
+		register_undef_hook(&vfp_kmode_exception_hook[i]);
+	return 0;
+}
+subsys_initcall(vfp_kmode_exception_hook_init);
 
 /*
  * Kernel-side NEON support functions
@@ -708,6 +752,21 @@ EXPORT_SYMBOL(kernel_neon_end);
 
 #endif /* CONFIG_KERNEL_MODE_NEON */
 
+static int __init vfp_detect(struct pt_regs *regs, unsigned int instr)
+{
+	VFP_arch = UINT_MAX;	/* mark as not present */
+	regs->ARM_pc += 4;
+	return 0;
+}
+
+static struct undef_hook vfp_detect_hook __initdata = {
+	.instr_mask	= 0x0c000e00,
+	.instr_val	= 0x0c000a00,
+	.cpsr_mask	= MODE_MASK,
+	.cpsr_val	= SVC_MODE,
+	.fn		= vfp_detect,
+};
+
 /*
  * VFP support code initialisation.
  */
@@ -728,10 +787,11 @@ static int __init vfp_init(void)
 	 * The handler is already setup to just log calls, so
 	 * we just need to read the VFPSID register.
 	 */
-	vfp_vector = vfp_testing_entry;
+	register_undef_hook(&vfp_detect_hook);
 	barrier();
 	vfpsid = fmrx(FPSID);
 	barrier();
+	unregister_undef_hook(&vfp_detect_hook);
 	vfp_vector = vfp_null_entry;
 
 	pr_info("VFP support v0.3: ");
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 60e901cd0de6..5a957a9a0984 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -371,7 +371,7 @@ static int __init xen_guest_init(void)
 	}
 	gnttab_init();
 	if (!xen_initial_domain())
-		xenbus_probe(NULL);
+		xenbus_probe();
 
 	/*
 	 * Making sure board specific code will not set up ops for
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 81463eb537bb..f39568b28ec1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -137,6 +137,7 @@ config ARM64
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
 	select HAVE_ARCH_KASAN_SW_TAGS if HAVE_ARCH_KASAN
+	select HAVE_ARCH_KASAN_HW_TAGS if (HAVE_ARCH_KASAN && ARM64_MTE)
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
@@ -173,8 +174,6 @@ config ARM64
 	select HAVE_NMI
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
-	select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS
-	select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
@@ -334,7 +333,7 @@ config BROKEN_GAS_INST
 
 config KASAN_SHADOW_OFFSET
 	hex
-	depends on KASAN
+	depends on KASAN_GENERIC || KASAN_SW_TAGS
 	default 0xdfff800000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && !KASAN_SW_TAGS
 	default 0xdfffc00000000000 if ARM64_VA_BITS_47 && !KASAN_SW_TAGS
 	default 0xdffffe0000000000 if ARM64_VA_BITS_42 && !KASAN_SW_TAGS
@@ -1571,6 +1570,9 @@ endmenu
 
 menu "ARMv8.5 architectural features"
 
+config AS_HAS_ARMV8_5
+	def_bool $(cc-option,-Wa$(comma)-march=armv8.5-a)
+
 config ARM64_BTI
 	bool "Branch Target Identification support"
 	default y
@@ -1645,6 +1647,9 @@ config ARM64_MTE
 	bool "Memory Tagging Extension support"
 	default y
 	depends on ARM64_AS_HAS_MTE && ARM64_TAGGED_ADDR_ABI
+	depends on AS_HAS_ARMV8_5
+	# Required for tag checking in the uaccess routines
+	depends on ARM64_PAN
 	select ARCH_USES_HIGH_VMA_FLAGS
 	help
 	  Memory Tagging (part of the ARMv8.5 Extensions) provides
@@ -1870,6 +1875,7 @@ config EFI
 	select EFI_RUNTIME_WRAPPERS
 	select EFI_STUB
 	select EFI_GENERIC_STUB
+	imply IMA_SECURE_AND_OR_TRUSTED_BOOT
 	default y
 	help
 	  This option provides support for runtime services provided
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 6a87d592bd00..90309208bb28 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -10,7 +10,7 @@
 #
 # Copyright (C) 1995-2001 by Russell King
 
-LDFLAGS_vmlinux	:=--no-undefined -X -z norelro
+LDFLAGS_vmlinux	:=--no-undefined -X
 
 ifeq ($(CONFIG_RELOCATABLE), y)
 # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour
@@ -96,6 +96,11 @@ ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
 asm-arch := armv8.4-a
 endif
 
+ifeq ($(CONFIG_AS_HAS_ARMV8_5), y)
+# make sure to pass the newest target architecture to -march.
+asm-arch := armv8.5-a
+endif
+
 ifdef asm-arch
 KBUILD_CFLAGS	+= -Wa,-march=$(asm-arch) \
 		   -DARM64_ASM_ARCH='"$(asm-arch)"'
@@ -110,16 +115,20 @@ KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__AARCH64EB__
 # Prefer the baremetal ELF build target, but not all toolchains include
 # it so fall back to the standard linux version if needed.
-KBUILD_LDFLAGS	+= -EB $(call ld-option, -maarch64elfb, -maarch64linuxb)
+KBUILD_LDFLAGS	+= -EB $(call ld-option, -maarch64elfb, -maarch64linuxb -z norelro)
 UTS_MACHINE	:= aarch64_be
 else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 CHECKFLAGS	+= -D__AARCH64EL__
 # Same as above, prefer ELF but fall back to linux target if needed.
-KBUILD_LDFLAGS	+= -EL $(call ld-option, -maarch64elf, -maarch64linux)
+KBUILD_LDFLAGS	+= -EL $(call ld-option, -maarch64elf, -maarch64linux -z norelro)
 UTS_MACHINE	:= aarch64
 endif
 
+ifeq ($(CONFIG_LD_IS_LLD), y)
+KBUILD_LDFLAGS	+= -z norelro
+endif
+
 CHECKFLAGS	+= -D__aarch64__
 
 ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y)
@@ -132,7 +141,7 @@ head-y		:= arch/arm64/kernel/head.o
 
 ifeq ($(CONFIG_KASAN_SW_TAGS), y)
 KASAN_SHADOW_SCALE_SHIFT := 4
-else
+else ifeq ($(CONFIG_KASAN_GENERIC), y)
 KASAN_SHADOW_SCALE_SHIFT := 3
 endif
 
diff --git a/arch/arm64/boot/dts/bitmain/bm1880.dtsi b/arch/arm64/boot/dts/bitmain/bm1880.dtsi
index fa6e6905f588..53a9b76057aa 100644
--- a/arch/arm64/boot/dts/bitmain/bm1880.dtsi
+++ b/arch/arm64/boot/dts/bitmain/bm1880.dtsi
@@ -127,7 +127,7 @@
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <32>;
+				ngpios = <32>;
 				reg = <0>;
 				interrupt-controller;
 				#interrupt-cells = <2>;
@@ -145,7 +145,7 @@
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <32>;
+				ngpios = <32>;
 				reg = <0>;
 				interrupt-controller;
 				#interrupt-cells = <2>;
@@ -163,7 +163,7 @@
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <8>;
+				ngpios = <8>;
 				reg = <0>;
 				interrupt-controller;
 				#interrupt-cells = <2>;
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index ff9cbb631212..07ac208edc89 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 generic-y += early_ioremap.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += qrwlock.h
 generic-y += qspinlock.h
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index ddbe6bf00e33..bf125c591116 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -473,7 +473,7 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 #define NOKPROBE(x)
 #endif
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 #define EXPORT_SYMBOL_NOKASAN(name)
 #else
 #define EXPORT_SYMBOL_NOKASAN(name)	EXPORT_SYMBOL(name)
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 015ddffaf6ca..b56a4b2bc248 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -17,7 +17,7 @@
 #include <asm/lse.h>
 
 #define ATOMIC_OP(op)							\
-static inline void arch_##op(int i, atomic_t *v)			\
+static __always_inline void arch_##op(int i, atomic_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -32,7 +32,7 @@ ATOMIC_OP(atomic_sub)
 #undef ATOMIC_OP
 
 #define ATOMIC_FETCH_OP(name, op)					\
-static inline int arch_##op##name(int i, atomic_t *v)			\
+static __always_inline int arch_##op##name(int i, atomic_t *v)		\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -56,7 +56,7 @@ ATOMIC_FETCH_OPS(atomic_sub_return)
 #undef ATOMIC_FETCH_OPS
 
 #define ATOMIC64_OP(op)							\
-static inline void arch_##op(long i, atomic64_t *v)			\
+static __always_inline void arch_##op(long i, atomic64_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -71,7 +71,7 @@ ATOMIC64_OP(atomic64_sub)
 #undef ATOMIC64_OP
 
 #define ATOMIC64_FETCH_OP(name, op)					\
-static inline long arch_##op##name(long i, atomic64_t *v)		\
+static __always_inline long arch_##op##name(long i, atomic64_t *v)	\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -94,7 +94,7 @@ ATOMIC64_FETCH_OPS(atomic64_sub_return)
 #undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_FETCH_OPS
 
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	return __lse_ll_sc_body(atomic64_dec_if_positive, v);
 }
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 63d43b5f82f6..77cbbe3625f2 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -6,6 +6,7 @@
 #define __ASM_CACHE_H
 
 #include <asm/cputype.h>
+#include <asm/mte-kasan.h>
 
 #define CTR_L1IP_SHIFT		14
 #define CTR_L1IP_MASK		3
@@ -51,6 +52,8 @@
 
 #ifdef CONFIG_KASAN_SW_TAGS
 #define ARCH_SLAB_MINALIGN	(1ULL << KASAN_SHADOW_SCALE_SHIFT)
+#elif defined(CONFIG_KASAN_HW_TAGS)
+#define ARCH_SLAB_MINALIGN	MTE_GRANULE_SIZE
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index a7242ef2a2cd..b77d997b173b 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -19,7 +19,7 @@
 #define ARM64_HAS_VIRT_HOST_EXTN		11
 #define ARM64_WORKAROUND_CAVIUM_27456		12
 #define ARM64_HAS_32BIT_EL0			13
-#define ARM64_HARDEN_EL2_VECTORS		14
+#define ARM64_SPECTRE_V3A			14
 #define ARM64_HAS_CNP				15
 #define ARM64_HAS_NO_FPSIMD			16
 #define ARM64_WORKAROUND_REPEAT_TLBI		17
@@ -65,7 +65,8 @@
 #define ARM64_MTE				57
 #define ARM64_WORKAROUND_1508412		58
 #define ARM64_HAS_LDAPR				59
+#define ARM64_KVM_PROTECTED_MODE		60
 
-#define ARM64_NCAPS				60
+#define ARM64_NCAPS				61
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 1c406e8ae27e..9a555809b89c 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -705,6 +705,11 @@ static inline bool system_supports_generic_auth(void)
 		cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH);
 }
 
+static inline bool system_has_full_ptr_auth(void)
+{
+	return system_supports_address_auth() && system_supports_generic_auth();
+}
+
 static __always_inline bool system_uses_irq_prio_masking(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 973b14415271..3578aba9c608 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -64,12 +64,6 @@ efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...);
 #define EFI_KIMG_ALIGN	\
 	(SEGMENT_ALIGN > THREAD_ALIGN ? SEGMENT_ALIGN : THREAD_ALIGN)
 
-/* on arm64, the FDT may be located anywhere in system RAM */
-static inline unsigned long efi_get_max_fdt_addr(unsigned long image_addr)
-{
-	return ULONG_MAX;
-}
-
 /*
  * On arm64, we have to ensure that the initrd ends up in the linear region,
  * which is a 1 GB aligned region of size '1UL << (VA_BITS_MIN - 1)' that is
@@ -141,4 +135,9 @@ static inline void efi_set_pgd(struct mm_struct *mm)
 void efi_virtmap_load(void);
 void efi_virtmap_unload(void);
 
+static inline void efi_capsule_flush_cache_range(void *addr, int size)
+{
+	__flush_dcache_area(addr, size);
+}
+
 #endif /* _ASM_EFI_H */
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
new file mode 100644
index 000000000000..a7f5a1bbc8ac
--- /dev/null
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -0,0 +1,181 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM_KVM_INIT_H__
+#define __ARM_KVM_INIT_H__
+
+#ifndef __ASSEMBLY__
+#error Assembly-only header
+#endif
+
+#include <asm/kvm_arm.h>
+#include <asm/ptrace.h>
+#include <asm/sysreg.h>
+#include <linux/irqchip/arm-gic-v3.h>
+
+.macro __init_el2_sctlr
+	mov_q	x0, INIT_SCTLR_EL2_MMU_OFF
+	msr	sctlr_el2, x0
+	isb
+.endm
+
+/*
+ * Allow Non-secure EL1 and EL0 to access physical timer and counter.
+ * This is not necessary for VHE, since the host kernel runs in EL2,
+ * and EL0 accesses are configured in the later stage of boot process.
+ * Note that when HCR_EL2.E2H == 1, CNTHCTL_EL2 has the same bit layout
+ * as CNTKCTL_EL1, and CNTKCTL_EL1 accessing instructions are redefined
+ * to access CNTHCTL_EL2. This allows the kernel designed to run at EL1
+ * to transparently mess with the EL0 bits via CNTKCTL_EL1 access in
+ * EL2.
+ */
+.macro __init_el2_timers mode
+.ifeqs "\mode", "nvhe"
+	mrs	x0, cnthctl_el2
+	orr	x0, x0, #3			// Enable EL1 physical timers
+	msr	cnthctl_el2, x0
+.endif
+	msr	cntvoff_el2, xzr		// Clear virtual offset
+.endm
+
+.macro __init_el2_debug mode
+	mrs	x1, id_aa64dfr0_el1
+	sbfx	x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4
+	cmp	x0, #1
+	b.lt	1f				// Skip if no PMU present
+	mrs	x0, pmcr_el0			// Disable debug access traps
+	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
+1:
+	csel	x2, xzr, x0, lt			// all PMU counters from EL1
+
+	/* Statistical profiling */
+	ubfx	x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
+	cbz	x0, 3f				// Skip if SPE not present
+
+.ifeqs "\mode", "nvhe"
+	mrs_s	x0, SYS_PMBIDR_EL1              // If SPE available at EL2,
+	and	x0, x0, #(1 << SYS_PMBIDR_EL1_P_SHIFT)
+	cbnz	x0, 2f				// then permit sampling of physical
+	mov	x0, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \
+		      1 << SYS_PMSCR_EL2_PA_SHIFT)
+	msr_s	SYS_PMSCR_EL2, x0		// addresses and physical counter
+2:
+	mov	x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
+	orr	x2, x2, x0			// If we don't have VHE, then
+						// use EL1&0 translation.
+.else
+	orr	x2, x2, #MDCR_EL2_TPMS		// For VHE, use EL2 translation
+						// and disable access from EL1
+.endif
+
+3:
+	msr	mdcr_el2, x2			// Configure debug traps
+.endm
+
+/* LORegions */
+.macro __init_el2_lor
+	mrs	x1, id_aa64mmfr1_el1
+	ubfx	x0, x1, #ID_AA64MMFR1_LOR_SHIFT, 4
+	cbz	x0, 1f
+	msr_s	SYS_LORC_EL1, xzr
+1:
+.endm
+
+/* Stage-2 translation */
+.macro __init_el2_stage2
+	msr	vttbr_el2, xzr
+.endm
+
+/* GICv3 system register access */
+.macro __init_el2_gicv3
+	mrs	x0, id_aa64pfr0_el1
+	ubfx	x0, x0, #ID_AA64PFR0_GIC_SHIFT, #4
+	cbz	x0, 1f
+
+	mrs_s	x0, SYS_ICC_SRE_EL2
+	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
+	orr	x0, x0, #ICC_SRE_EL2_ENABLE	// Set ICC_SRE_EL2.Enable==1
+	msr_s	SYS_ICC_SRE_EL2, x0
+	isb					// Make sure SRE is now set
+	mrs_s	x0, SYS_ICC_SRE_EL2		// Read SRE back,
+	tbz	x0, #0, 1f			// and check that it sticks
+	msr_s	SYS_ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
+1:
+.endm
+
+.macro __init_el2_hstr
+	msr	hstr_el2, xzr			// Disable CP15 traps to EL2
+.endm
+
+/* Virtual CPU ID registers */
+.macro __init_el2_nvhe_idregs
+	mrs	x0, midr_el1
+	mrs	x1, mpidr_el1
+	msr	vpidr_el2, x0
+	msr	vmpidr_el2, x1
+.endm
+
+/* Coprocessor traps */
+.macro __init_el2_nvhe_cptr
+	mov	x0, #0x33ff
+	msr	cptr_el2, x0			// Disable copro. traps to EL2
+.endm
+
+/* SVE register access */
+.macro __init_el2_nvhe_sve
+	mrs	x1, id_aa64pfr0_el1
+	ubfx	x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4
+	cbz	x1, 1f
+
+	bic	x0, x0, #CPTR_EL2_TZ		// Also disable SVE traps
+	msr	cptr_el2, x0			// Disable copro. traps to EL2
+	isb
+	mov	x1, #ZCR_ELx_LEN_MASK		// SVE: Enable full vector
+	msr_s	SYS_ZCR_EL2, x1			// length for EL1.
+1:
+.endm
+
+.macro __init_el2_nvhe_prepare_eret
+	mov	x0, #INIT_PSTATE_EL1
+	msr	spsr_el2, x0
+.endm
+
+/**
+ * Initialize EL2 registers to sane values. This should be called early on all
+ * cores that were booted in EL2.
+ *
+ * Regs: x0, x1 and x2 are clobbered.
+ */
+.macro init_el2_state mode
+.ifnes "\mode", "vhe"
+.ifnes "\mode", "nvhe"
+.error "Invalid 'mode' argument"
+.endif
+.endif
+
+	__init_el2_sctlr
+	__init_el2_timers \mode
+	__init_el2_debug \mode
+	__init_el2_lor
+	__init_el2_stage2
+	__init_el2_gicv3
+	__init_el2_hstr
+
+	/*
+	 * When VHE is not in use, early init of EL2 needs to be done here.
+	 * When VHE _is_ in use, EL1 will not be used in the host and
+	 * requires no configuration, and all non-hyp-specific EL2 setup
+	 * will be done via the _EL1 system register aliases in __cpu_setup.
+	 */
+.ifeqs "\mode", "nvhe"
+	__init_el2_nvhe_idregs
+	__init_el2_nvhe_cptr
+	__init_el2_nvhe_sve
+	__init_el2_nvhe_prepare_eret
+.endif
+.endm
+
+#endif /* __ARM_KVM_INIT_H__ */
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 85a3e49f92f4..29f97eb3dad4 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -106,6 +106,7 @@
 #define ESR_ELx_FSC_TYPE	(0x3C)
 #define ESR_ELx_FSC_LEVEL	(0x03)
 #define ESR_ELx_FSC_EXTABT	(0x10)
+#define ESR_ELx_FSC_MTE		(0x11)
 #define ESR_ELx_FSC_SERROR	(0x11)
 #define ESR_ELx_FSC_ACCESS	(0x08)
 #define ESR_ELx_FSC_FAULT	(0x04)
diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h
index b0dc4abc3589..0aaf9044cd6a 100644
--- a/arch/arm64/include/asm/kasan.h
+++ b/arch/arm64/include/asm/kasan.h
@@ -12,7 +12,9 @@
 #define arch_kasan_reset_tag(addr)	__tag_reset(addr)
 #define arch_kasan_get_tag(addr)	__tag_get(addr)
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+
+void kasan_init(void);
 
 /*
  * KASAN_SHADOW_START: beginning of the kernel virtual addresses.
@@ -33,7 +35,6 @@
 #define _KASAN_SHADOW_START(va)	(KASAN_SHADOW_END - (1UL << ((va) - KASAN_SHADOW_SCALE_SHIFT)))
 #define KASAN_SHADOW_START      _KASAN_SHADOW_START(vabits_actual)
 
-void kasan_init(void);
 void kasan_copy_shadow(pgd_t *pgdir);
 asmlinkage void kasan_early_init(void);
 
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 64ce29378467..4e90c2debf70 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -80,6 +80,7 @@
 			 HCR_FMO | HCR_IMO | HCR_PTW )
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
 #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
+#define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 8e5fa28b78c2..8a33d83ea843 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -34,8 +34,6 @@
  */
 #define KVM_VECTOR_PREAMBLE	(2 * AARCH64_INSN_SIZE)
 
-#define __SMCCC_WORKAROUND_1_SMC_SZ 36
-
 #define KVM_HOST_SMCCC_ID(id)						\
 	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
 			   ARM_SMCCC_SMC_64,				\
@@ -150,6 +148,14 @@ extern void *__vhe_undefined_symbol;
 
 #endif
 
+struct kvm_nvhe_init_params {
+	unsigned long mair_el2;
+	unsigned long tcr_el2;
+	unsigned long tpidr_el2;
+	unsigned long stack_hyp_va;
+	phys_addr_t pgd_pa;
+};
+
 /* Translate a kernel address @ptr into its equivalent linear mapping */
 #define kvm_ksym_ref(ptr)						\
 	({								\
@@ -165,17 +171,14 @@ struct kvm_vcpu;
 struct kvm_s2_mmu;
 
 DECLARE_KVM_NVHE_SYM(__kvm_hyp_init);
-DECLARE_KVM_NVHE_SYM(__kvm_hyp_host_vector);
 DECLARE_KVM_HYP_SYM(__kvm_hyp_vector);
 #define __kvm_hyp_init		CHOOSE_NVHE_SYM(__kvm_hyp_init)
-#define __kvm_hyp_host_vector	CHOOSE_NVHE_SYM(__kvm_hyp_host_vector)
 #define __kvm_hyp_vector	CHOOSE_HYP_SYM(__kvm_hyp_vector)
 
 extern unsigned long kvm_arm_hyp_percpu_base[NR_CPUS];
 DECLARE_KVM_NVHE_SYM(__per_cpu_start);
 DECLARE_KVM_NVHE_SYM(__per_cpu_end);
 
-extern atomic_t arm64_el2_vector_last_slot;
 DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs);
 #define __bp_harden_hyp_vecs	CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
 
@@ -189,8 +192,6 @@ extern void __kvm_timer_set_cntvoff(u64 cntvoff);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
-extern void __kvm_enable_ssbs(void);
-
 extern u64 __vgic_v3_get_ich_vtr_el2(void);
 extern u64 __vgic_v3_read_vmcr(void);
 extern void __vgic_v3_write_vmcr(u32 vmcr);
@@ -198,8 +199,6 @@ extern void __vgic_v3_init_lrs(void);
 
 extern u32 __kvm_get_mdcr_el2(void);
 
-extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
-
 #if defined(GCC_VERSION) && GCC_VERSION < 50000
 #define SYM_CONSTRAINT	"i"
 #else
diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h
deleted file mode 100644
index d6bb40122fdb..000000000000
--- a/arch/arm64/include/asm/kvm_coproc.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * Derived from arch/arm/include/asm/kvm_coproc.h
- * Copyright (C) 2012 Rusty Russell IBM Corporation
- */
-
-#ifndef __ARM64_KVM_COPROC_H__
-#define __ARM64_KVM_COPROC_H__
-
-#include <linux/kvm_host.h>
-
-void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
-
-struct kvm_sys_reg_table {
-	const struct sys_reg_desc *table;
-	size_t num;
-};
-
-int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu);
-int kvm_handle_cp14_32(struct kvm_vcpu *vcpu);
-int kvm_handle_cp14_64(struct kvm_vcpu *vcpu);
-int kvm_handle_cp15_32(struct kvm_vcpu *vcpu);
-int kvm_handle_cp15_64(struct kvm_vcpu *vcpu);
-int kvm_handle_sys_reg(struct kvm_vcpu *vcpu);
-
-#define kvm_coproc_table_init kvm_sys_reg_table_init
-void kvm_sys_reg_table_init(void);
-
-struct kvm_one_reg;
-int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
-int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
-int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
-unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu);
-
-#endif /* __ARM64_KVM_COPROC_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 00bc6f1234ba..f612c090f2e4 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -21,20 +21,25 @@
 #include <asm/cputype.h>
 #include <asm/virt.h>
 
-unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num);
-unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu);
-void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v);
+#define CURRENT_EL_SP_EL0_VECTOR	0x0
+#define CURRENT_EL_SP_ELx_VECTOR	0x200
+#define LOWER_EL_AArch64_VECTOR		0x400
+#define LOWER_EL_AArch32_VECTOR		0x600
+
+enum exception_type {
+	except_type_sync	= 0,
+	except_type_irq		= 0x80,
+	except_type_fiq		= 0x100,
+	except_type_serror	= 0x180,
+};
 
 bool kvm_condition_valid32(const struct kvm_vcpu *vcpu);
-void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr);
+void kvm_skip_instr32(struct kvm_vcpu *vcpu);
 
 void kvm_inject_undefined(struct kvm_vcpu *vcpu);
 void kvm_inject_vabt(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
-void kvm_inject_undef32(struct kvm_vcpu *vcpu);
-void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr);
-void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr);
 
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
@@ -168,30 +173,6 @@ static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
 		vcpu_gp_regs(vcpu)->regs[reg_num] = val;
 }
 
-static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu)
-{
-	if (vcpu_mode_is_32bit(vcpu))
-		return vcpu_read_spsr32(vcpu);
-
-	if (vcpu->arch.sysregs_loaded_on_cpu)
-		return read_sysreg_el1(SYS_SPSR);
-	else
-		return __vcpu_sys_reg(vcpu, SPSR_EL1);
-}
-
-static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
-{
-	if (vcpu_mode_is_32bit(vcpu)) {
-		vcpu_write_spsr32(vcpu, v);
-		return;
-	}
-
-	if (vcpu->arch.sysregs_loaded_on_cpu)
-		write_sysreg_el1(v, SYS_SPSR);
-	else
-		__vcpu_sys_reg(vcpu, SPSR_EL1) = v;
-}
-
 /*
  * The layout of SPSR for an AArch32 state is different when observed from an
  * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32
@@ -477,32 +458,9 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
 	return data;		/* Leave LE untouched */
 }
 
-static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
-{
-	if (vcpu_mode_is_32bit(vcpu)) {
-		kvm_skip_instr32(vcpu, is_wide_instr);
-	} else {
-		*vcpu_pc(vcpu) += 4;
-		*vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK;
-	}
-
-	/* advance the singlestep state machine */
-	*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
-}
-
-/*
- * Skip an instruction which has been emulated at hyp while most guest sysregs
- * are live.
- */
-static __always_inline void __kvm_skip_instr(struct kvm_vcpu *vcpu)
+static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
 {
-	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
-	vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR);
-
-	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
-
-	write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR);
-	write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
+	vcpu->arch.flags |= KVM_ARM64_INCREMENT_PC;
 }
 
 #endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 0cd9f0f75c13..8fcfab0c2567 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -17,6 +17,7 @@
 #include <linux/jump_label.h>
 #include <linux/kvm_types.h>
 #include <linux/percpu.h>
+#include <linux/psci.h>
 #include <asm/arch_gicv3.h>
 #include <asm/barrier.h>
 #include <asm/cpufeature.h>
@@ -50,6 +51,16 @@
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
 
+/*
+ * Mode of operation configurable with kvm-arm.mode early param.
+ * See Documentation/admin-guide/kernel-parameters.txt for more information.
+ */
+enum kvm_mode {
+	KVM_MODE_DEFAULT,
+	KVM_MODE_PROTECTED,
+};
+enum kvm_mode kvm_get_mode(void);
+
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
 extern unsigned int kvm_sve_max_vl;
@@ -58,8 +69,6 @@ int kvm_arm_init_sve(void);
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);
-int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext);
-void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
 
 struct kvm_vmid {
 	/* The VMID generation used for the virt. memory system */
@@ -89,6 +98,9 @@ struct kvm_s2_mmu {
 	struct kvm *kvm;
 };
 
+struct kvm_arch_memory_slot {
+};
+
 struct kvm_arch {
 	struct kvm_s2_mmu mmu;
 
@@ -120,6 +132,7 @@ struct kvm_arch {
 	unsigned int pmuver;
 
 	u8 pfr0_csv2;
+	u8 pfr0_csv3;
 };
 
 struct kvm_vcpu_fault_info {
@@ -203,48 +216,6 @@ enum vcpu_sysreg {
 	NR_SYS_REGS	/* Nothing after this line! */
 };
 
-/* 32bit mapping */
-#define c0_MPIDR	(MPIDR_EL1 * 2)	/* MultiProcessor ID Register */
-#define c0_CSSELR	(CSSELR_EL1 * 2)/* Cache Size Selection Register */
-#define c1_SCTLR	(SCTLR_EL1 * 2)	/* System Control Register */
-#define c1_ACTLR	(ACTLR_EL1 * 2)	/* Auxiliary Control Register */
-#define c1_CPACR	(CPACR_EL1 * 2)	/* Coprocessor Access Control */
-#define c2_TTBR0	(TTBR0_EL1 * 2)	/* Translation Table Base Register 0 */
-#define c2_TTBR0_high	(c2_TTBR0 + 1)	/* TTBR0 top 32 bits */
-#define c2_TTBR1	(TTBR1_EL1 * 2)	/* Translation Table Base Register 1 */
-#define c2_TTBR1_high	(c2_TTBR1 + 1)	/* TTBR1 top 32 bits */
-#define c2_TTBCR	(TCR_EL1 * 2)	/* Translation Table Base Control R. */
-#define c3_DACR		(DACR32_EL2 * 2)/* Domain Access Control Register */
-#define c5_DFSR		(ESR_EL1 * 2)	/* Data Fault Status Register */
-#define c5_IFSR		(IFSR32_EL2 * 2)/* Instruction Fault Status Register */
-#define c5_ADFSR	(AFSR0_EL1 * 2)	/* Auxiliary Data Fault Status R */
-#define c5_AIFSR	(AFSR1_EL1 * 2)	/* Auxiliary Instr Fault Status R */
-#define c6_DFAR		(FAR_EL1 * 2)	/* Data Fault Address Register */
-#define c6_IFAR		(c6_DFAR + 1)	/* Instruction Fault Address Register */
-#define c7_PAR		(PAR_EL1 * 2)	/* Physical Address Register */
-#define c7_PAR_high	(c7_PAR + 1)	/* PAR top 32 bits */
-#define c10_PRRR	(MAIR_EL1 * 2)	/* Primary Region Remap Register */
-#define c10_NMRR	(c10_PRRR + 1)	/* Normal Memory Remap Register */
-#define c12_VBAR	(VBAR_EL1 * 2)	/* Vector Base Address Register */
-#define c13_CID		(CONTEXTIDR_EL1 * 2)	/* Context ID Register */
-#define c13_TID_URW	(TPIDR_EL0 * 2)	/* Thread ID, User R/W */
-#define c13_TID_URO	(TPIDRRO_EL0 * 2)/* Thread ID, User R/O */
-#define c13_TID_PRIV	(TPIDR_EL1 * 2)	/* Thread ID, Privileged */
-#define c10_AMAIR0	(AMAIR_EL1 * 2)	/* Aux Memory Attr Indirection Reg */
-#define c10_AMAIR1	(c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
-#define c14_CNTKCTL	(CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */
-
-#define cp14_DBGDSCRext	(MDSCR_EL1 * 2)
-#define cp14_DBGBCR0	(DBGBCR0_EL1 * 2)
-#define cp14_DBGBVR0	(DBGBVR0_EL1 * 2)
-#define cp14_DBGBXVR0	(cp14_DBGBVR0 + 1)
-#define cp14_DBGWCR0	(DBGWCR0_EL1 * 2)
-#define cp14_DBGWVR0	(DBGWVR0_EL1 * 2)
-#define cp14_DBGDCCINT	(MDCCINT_EL1 * 2)
-#define cp14_DBGVCR	(DBGVCR32_EL2 * 2)
-
-#define NR_COPRO_REGS	(NR_SYS_REGS * 2)
-
 struct kvm_cpu_context {
 	struct user_pt_regs regs;	/* sp = sp_el0 */
 
@@ -255,10 +226,7 @@ struct kvm_cpu_context {
 
 	struct user_fpsimd_state fp_regs;
 
-	union {
-		u64 sys_regs[NR_SYS_REGS];
-		u32 copro[NR_COPRO_REGS];
-	};
+	u64 sys_regs[NR_SYS_REGS];
 
 	struct kvm_vcpu *__hyp_running_vcpu;
 };
@@ -273,6 +241,28 @@ struct kvm_host_data {
 	struct kvm_pmu_events pmu_events;
 };
 
+struct kvm_host_psci_config {
+	/* PSCI version used by host. */
+	u32 version;
+
+	/* Function IDs used by host if version is v0.1. */
+	struct psci_0_1_function_ids function_ids_0_1;
+
+	bool psci_0_1_cpu_suspend_implemented;
+	bool psci_0_1_cpu_on_implemented;
+	bool psci_0_1_cpu_off_implemented;
+	bool psci_0_1_migrate_implemented;
+};
+
+extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config);
+#define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config)
+
+extern s64 kvm_nvhe_sym(hyp_physvirt_offset);
+#define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset)
+
+extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS];
+#define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map)
+
 struct vcpu_reset_state {
 	unsigned long	pc;
 	unsigned long	r0;
@@ -409,8 +399,33 @@ struct kvm_vcpu_arch {
 #define KVM_ARM64_GUEST_HAS_SVE		(1 << 5) /* SVE exposed to guest */
 #define KVM_ARM64_VCPU_SVE_FINALIZED	(1 << 6) /* SVE config completed */
 #define KVM_ARM64_GUEST_HAS_PTRAUTH	(1 << 7) /* PTRAUTH exposed to guest */
+#define KVM_ARM64_PENDING_EXCEPTION	(1 << 8) /* Exception pending */
+#define KVM_ARM64_EXCEPT_MASK		(7 << 9) /* Target EL/MODE */
+
+/*
+ * When KVM_ARM64_PENDING_EXCEPTION is set, KVM_ARM64_EXCEPT_MASK can
+ * take the following values:
+ *
+ * For AArch32 EL1:
+ */
+#define KVM_ARM64_EXCEPT_AA32_UND	(0 << 9)
+#define KVM_ARM64_EXCEPT_AA32_IABT	(1 << 9)
+#define KVM_ARM64_EXCEPT_AA32_DABT	(2 << 9)
+/* For AArch64: */
+#define KVM_ARM64_EXCEPT_AA64_ELx_SYNC	(0 << 9)
+#define KVM_ARM64_EXCEPT_AA64_ELx_IRQ	(1 << 9)
+#define KVM_ARM64_EXCEPT_AA64_ELx_FIQ	(2 << 9)
+#define KVM_ARM64_EXCEPT_AA64_ELx_SERR	(3 << 9)
+#define KVM_ARM64_EXCEPT_AA64_EL1	(0 << 11)
+#define KVM_ARM64_EXCEPT_AA64_EL2	(1 << 11)
+
+/*
+ * Overlaps with KVM_ARM64_EXCEPT_MASK on purpose so that it can't be
+ * set together with an exception...
+ */
+#define KVM_ARM64_INCREMENT_PC		(1 << 9) /* Increment PC */
 
-#define vcpu_has_sve(vcpu) (system_supports_sve() && \
+#define vcpu_has_sve(vcpu) (system_supports_sve() &&			\
 			    ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE))
 
 #ifdef CONFIG_ARM64_PTR_AUTH
@@ -440,14 +455,96 @@ struct kvm_vcpu_arch {
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
 void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
 
-/*
- * CP14 and CP15 live in the same array, as they are backed by the
- * same system registers.
- */
-#define CPx_BIAS		IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)
+static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
+{
+	/*
+	 * *** VHE ONLY ***
+	 *
+	 * System registers listed in the switch are not saved on every
+	 * exit from the guest but are only saved on vcpu_put.
+	 *
+	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
+	 * should never be listed below, because the guest cannot modify its
+	 * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's
+	 * thread when emulating cross-VCPU communication.
+	 */
+	if (!has_vhe())
+		return false;
+
+	switch (reg) {
+	case CSSELR_EL1:	*val = read_sysreg_s(SYS_CSSELR_EL1);	break;
+	case SCTLR_EL1:		*val = read_sysreg_s(SYS_SCTLR_EL12);	break;
+	case CPACR_EL1:		*val = read_sysreg_s(SYS_CPACR_EL12);	break;
+	case TTBR0_EL1:		*val = read_sysreg_s(SYS_TTBR0_EL12);	break;
+	case TTBR1_EL1:		*val = read_sysreg_s(SYS_TTBR1_EL12);	break;
+	case TCR_EL1:		*val = read_sysreg_s(SYS_TCR_EL12);	break;
+	case ESR_EL1:		*val = read_sysreg_s(SYS_ESR_EL12);	break;
+	case AFSR0_EL1:		*val = read_sysreg_s(SYS_AFSR0_EL12);	break;
+	case AFSR1_EL1:		*val = read_sysreg_s(SYS_AFSR1_EL12);	break;
+	case FAR_EL1:		*val = read_sysreg_s(SYS_FAR_EL12);	break;
+	case MAIR_EL1:		*val = read_sysreg_s(SYS_MAIR_EL12);	break;
+	case VBAR_EL1:		*val = read_sysreg_s(SYS_VBAR_EL12);	break;
+	case CONTEXTIDR_EL1:	*val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break;
+	case TPIDR_EL0:		*val = read_sysreg_s(SYS_TPIDR_EL0);	break;
+	case TPIDRRO_EL0:	*val = read_sysreg_s(SYS_TPIDRRO_EL0);	break;
+	case TPIDR_EL1:		*val = read_sysreg_s(SYS_TPIDR_EL1);	break;
+	case AMAIR_EL1:		*val = read_sysreg_s(SYS_AMAIR_EL12);	break;
+	case CNTKCTL_EL1:	*val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		*val = read_sysreg_s(SYS_ELR_EL12);	break;
+	case PAR_EL1:		*val = read_sysreg_par();		break;
+	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
+	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
+	case DBGVCR32_EL2:	*val = read_sysreg_s(SYS_DBGVCR32_EL2);	break;
+	default:		return false;
+	}
+
+	return true;
+}
 
-#define vcpu_cp14(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
-#define vcpu_cp15(v,r)		((v)->arch.ctxt.copro[(r) ^ CPx_BIAS])
+static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
+{
+	/*
+	 * *** VHE ONLY ***
+	 *
+	 * System registers listed in the switch are not restored on every
+	 * entry to the guest but are only restored on vcpu_load.
+	 *
+	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
+	 * should never be listed below, because the MPIDR should only be set
+	 * once, before running the VCPU, and never changed later.
+	 */
+	if (!has_vhe())
+		return false;
+
+	switch (reg) {
+	case CSSELR_EL1:	write_sysreg_s(val, SYS_CSSELR_EL1);	break;
+	case SCTLR_EL1:		write_sysreg_s(val, SYS_SCTLR_EL12);	break;
+	case CPACR_EL1:		write_sysreg_s(val, SYS_CPACR_EL12);	break;
+	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
+	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
+	case TCR_EL1:		write_sysreg_s(val, SYS_TCR_EL12);	break;
+	case ESR_EL1:		write_sysreg_s(val, SYS_ESR_EL12);	break;
+	case AFSR0_EL1:		write_sysreg_s(val, SYS_AFSR0_EL12);	break;
+	case AFSR1_EL1:		write_sysreg_s(val, SYS_AFSR1_EL12);	break;
+	case FAR_EL1:		write_sysreg_s(val, SYS_FAR_EL12);	break;
+	case MAIR_EL1:		write_sysreg_s(val, SYS_MAIR_EL12);	break;
+	case VBAR_EL1:		write_sysreg_s(val, SYS_VBAR_EL12);	break;
+	case CONTEXTIDR_EL1:	write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break;
+	case TPIDR_EL0:		write_sysreg_s(val, SYS_TPIDR_EL0);	break;
+	case TPIDRRO_EL0:	write_sysreg_s(val, SYS_TPIDRRO_EL0);	break;
+	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	break;
+	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
+	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
+	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
+	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
+	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
+	case DBGVCR32_EL2:	write_sysreg_s(val, SYS_DBGVCR32_EL2);	break;
+	default:		return false;
+	}
+
+	return true;
+}
 
 struct kvm_vm_stat {
 	ulong remote_tlb_flush;
@@ -473,6 +570,12 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+
+unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
+int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
+int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
+
 int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 			      struct kvm_vcpu_events *events);
 
@@ -535,6 +638,17 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 int handle_exit(struct kvm_vcpu *vcpu, int exception_index);
 void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index);
 
+int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu);
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu);
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu);
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu);
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu);
+int kvm_handle_sys_reg(struct kvm_vcpu *vcpu);
+
+void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
+
+void kvm_sys_reg_table_init(void);
+
 /* MMIO helpers */
 void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
 unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
@@ -654,4 +768,7 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 #define kvm_arm_vcpu_sve_finalized(vcpu) \
 	((vcpu)->arch.flags & KVM_ARM64_VCPU_SVE_FINALIZED)
 
+#define kvm_vcpu_has_pmu(vcpu)					\
+	(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))
+
 #endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 6b664de5ec1f..c0450828378b 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -14,6 +14,7 @@
 
 DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
 DECLARE_PER_CPU(unsigned long, kvm_hyp_vector);
+DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
 #define read_sysreg_elx(r,nvh,vh)					\
 	({								\
@@ -92,10 +93,11 @@ void deactivate_traps_vhe_put(void);
 
 u64 __guest_enter(struct kvm_vcpu *vcpu);
 
+bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt);
+
 void __noreturn hyp_panic(void);
 #ifdef __KVM_NVHE_HYPERVISOR__
 void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
 #endif
 
 #endif /* __ARM64_KVM_HYP_H__ */
-
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 331394306cce..e52d82aeadca 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -72,6 +72,52 @@ alternative_cb kvm_update_va_mask
 alternative_cb_end
 .endm
 
+/*
+ * Convert a kernel image address to a PA
+ * reg: kernel address to be converted in place
+ * tmp: temporary register
+ *
+ * The actual code generation takes place in kvm_get_kimage_voffset, and
+ * the instructions below are only there to reserve the space and
+ * perform the register allocation (kvm_get_kimage_voffset uses the
+ * specific registers encoded in the instructions).
+ */
+.macro kimg_pa reg, tmp
+alternative_cb kvm_get_kimage_voffset
+	movz	\tmp, #0
+	movk	\tmp, #0, lsl #16
+	movk	\tmp, #0, lsl #32
+	movk	\tmp, #0, lsl #48
+alternative_cb_end
+
+	/* reg = __pa(reg) */
+	sub	\reg, \reg, \tmp
+.endm
+
+/*
+ * Convert a kernel image address to a hyp VA
+ * reg: kernel address to be converted in place
+ * tmp: temporary register
+ *
+ * The actual code generation takes place in kvm_get_kimage_voffset, and
+ * the instructions below are only there to reserve the space and
+ * perform the register allocation (kvm_update_kimg_phys_offset uses the
+ * specific registers encoded in the instructions).
+ */
+.macro kimg_hyp_va reg, tmp
+alternative_cb kvm_update_kimg_phys_offset
+	movz	\tmp, #0
+	movk	\tmp, #0, lsl #16
+	movk	\tmp, #0, lsl #32
+	movk	\tmp, #0, lsl #48
+alternative_cb_end
+
+	sub	\reg, \reg, \tmp
+	mov_q	\tmp, PAGE_OFFSET
+	orr	\reg, \reg, \tmp
+	kern_hyp_va \reg
+.endm
+
 #else
 
 #include <linux/pgtable.h>
@@ -98,6 +144,24 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 
 #define kern_hyp_va(v) 	((typeof(v))(__kern_hyp_va((unsigned long)(v))))
 
+static __always_inline unsigned long __kimg_hyp_va(unsigned long v)
+{
+	unsigned long offset;
+
+	asm volatile(ALTERNATIVE_CB("movz %0, #0\n"
+				    "movk %0, #0, lsl #16\n"
+				    "movk %0, #0, lsl #32\n"
+				    "movk %0, #0, lsl #48\n",
+				    kvm_update_kimg_phys_offset)
+		     : "=r" (offset));
+
+	return __kern_hyp_va((v - offset) | PAGE_OFFSET);
+}
+
+#define kimg_fn_hyp_va(v) 	((typeof(*v))(__kimg_hyp_va((unsigned long)(v))))
+
+#define kimg_fn_ptr(x)	(typeof(x) **)(x)
+
 /*
  * We currently support using a VM-specified IPA size. For backward
  * compatibility, the default IPA size is fixed to 40bits.
@@ -208,52 +272,6 @@ static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
 	return ret;
 }
 
-/*
- * EL2 vectors can be mapped and rerouted in a number of ways,
- * depending on the kernel configuration and CPU present:
- *
- * - If the CPU is affected by Spectre-v2, the hardening sequence is
- *   placed in one of the vector slots, which is executed before jumping
- *   to the real vectors.
- *
- * - If the CPU also has the ARM64_HARDEN_EL2_VECTORS cap, the slot
- *   containing the hardening sequence is mapped next to the idmap page,
- *   and executed before jumping to the real vectors.
- *
- * - If the CPU only has the ARM64_HARDEN_EL2_VECTORS cap, then an
- *   empty slot is selected, mapped next to the idmap page, and
- *   executed before jumping to the real vectors.
- *
- * Note that ARM64_HARDEN_EL2_VECTORS is somewhat incompatible with
- * VHE, as we don't have hypervisor-specific mappings. If the system
- * is VHE and yet selects this capability, it will be ignored.
- */
-extern void *__kvm_bp_vect_base;
-extern int __kvm_harden_el2_vector_slot;
-
-static inline void *kvm_get_hyp_vector(void)
-{
-	struct bp_hardening_data *data = arm64_get_bp_hardening_data();
-	void *vect = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
-	int slot = -1;
-
-	if (cpus_have_const_cap(ARM64_SPECTRE_V2) && data->fn) {
-		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs));
-		slot = data->hyp_vectors_slot;
-	}
-
-	if (this_cpu_has_cap(ARM64_HARDEN_EL2_VECTORS) && !has_vhe()) {
-		vect = __kvm_bp_vect_base;
-		if (slot == -1)
-			slot = __kvm_harden_el2_vector_slot;
-	}
-
-	if (slot != -1)
-		vect += slot * SZ_2K;
-
-	return vect;
-}
-
 #define kvm_phys_to_vttbr(addr)		phys_to_ttbr(addr)
 
 static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 556cb2d62b5b..18fce223b67b 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -72,7 +72,7 @@
  * address space for the shadow region respectively. They can bloat the stack
  * significantly, so double the (minimum) stack size when they are in use.
  */
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 #define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
 #define KASAN_SHADOW_END	((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) \
 					+ KASAN_SHADOW_OFFSET)
@@ -214,7 +214,7 @@ static inline unsigned long kaslr_offset(void)
 	(__force __typeof__(addr))__addr;				\
 })
 
-#ifdef CONFIG_KASAN_SW_TAGS
+#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
 #define __tag_shifted(tag)	((u64)(tag) << 56)
 #define __tag_reset(addr)	__untagged_addr(addr)
 #define __tag_get(addr)		(__u8)((u64)(addr) >> 56)
@@ -222,7 +222,7 @@ static inline unsigned long kaslr_offset(void)
 #define __tag_shifted(tag)	0UL
 #define __tag_reset(addr)	(addr)
 #define __tag_get(addr)		0
-#endif /* CONFIG_KASAN_SW_TAGS */
+#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
 
 static inline const void *__tag_set(const void *addr, u8 tag)
 {
@@ -230,6 +230,15 @@ static inline const void *__tag_set(const void *addr, u8 tag)
 	return (const void *)(__addr | __tag_shifted(tag));
 }
 
+#ifdef CONFIG_KASAN_HW_TAGS
+#define arch_enable_tagging()			mte_enable_kernel()
+#define arch_init_tags(max_tag)			mte_init_tags(max_tag)
+#define arch_get_random_tag()			mte_get_random_tag()
+#define arch_get_mem_tag(addr)			mte_get_mem_tag(addr)
+#define arch_set_mem_tag_range(addr, size, tag)	\
+			mte_set_mem_tag_range((addr), (size), (tag))
+#endif /* CONFIG_KASAN_HW_TAGS */
+
 /*
  * Physical vs virtual RAM address space conversion.  These are
  * private definitions which should NOT be used outside memory.h
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index b2e91c187e2a..75beffe2ee8a 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -12,9 +12,6 @@
 #define USER_ASID_FLAG	(UL(1) << USER_ASID_BIT)
 #define TTBR_ASID_MASK	(UL(0xffff) << 48)
 
-#define BP_HARDEN_EL2_SLOTS 4
-#define __BP_HARDEN_HYP_VECS_SZ (BP_HARDEN_EL2_SLOTS * SZ_2K)
-
 #ifndef __ASSEMBLY__
 
 #include <linux/refcount.h>
@@ -41,32 +38,6 @@ static inline bool arm64_kernel_unmapped_at_el0(void)
 	return cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0);
 }
 
-typedef void (*bp_hardening_cb_t)(void);
-
-struct bp_hardening_data {
-	int			hyp_vectors_slot;
-	bp_hardening_cb_t	fn;
-};
-
-DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
-
-static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
-{
-	return this_cpu_ptr(&bp_hardening_data);
-}
-
-static inline void arm64_apply_bp_hardening(void)
-{
-	struct bp_hardening_data *d;
-
-	if (!cpus_have_const_cap(ARM64_SPECTRE_V2))
-		return;
-
-	d = arm64_get_bp_hardening_data();
-	if (d->fn)
-		d->fn();
-}
-
 extern void arm64_memblock_init(void);
 extern void paging_init(void);
 extern void bootmem_init(void);
diff --git a/arch/arm64/include/asm/mte-def.h b/arch/arm64/include/asm/mte-def.h
new file mode 100644
index 000000000000..2d73a1612f09
--- /dev/null
+++ b/arch/arm64/include/asm/mte-def.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef __ASM_MTE_DEF_H
+#define __ASM_MTE_DEF_H
+
+#define MTE_GRANULE_SIZE	UL(16)
+#define MTE_GRANULE_MASK	(~(MTE_GRANULE_SIZE - 1))
+#define MTE_TAG_SHIFT		56
+#define MTE_TAG_SIZE		4
+#define MTE_TAG_MASK		GENMASK((MTE_TAG_SHIFT + (MTE_TAG_SIZE - 1)), MTE_TAG_SHIFT)
+
+#endif /* __ASM_MTE_DEF_H  */
diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h
new file mode 100644
index 000000000000..26349a4b5e2e
--- /dev/null
+++ b/arch/arm64/include/asm/mte-kasan.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef __ASM_MTE_KASAN_H
+#define __ASM_MTE_KASAN_H
+
+#include <asm/mte-def.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * The functions below are meant to be used only for the
+ * KASAN_HW_TAGS interface defined in asm/memory.h.
+ */
+#ifdef CONFIG_ARM64_MTE
+
+static inline u8 mte_get_ptr_tag(void *ptr)
+{
+	/* Note: The format of KASAN tags is 0xF<x> */
+	u8 tag = 0xF0 | (u8)(((u64)(ptr)) >> MTE_TAG_SHIFT);
+
+	return tag;
+}
+
+u8 mte_get_mem_tag(void *addr);
+u8 mte_get_random_tag(void);
+void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag);
+
+void mte_enable_kernel(void);
+void mte_init_tags(u64 max_tag);
+
+#else /* CONFIG_ARM64_MTE */
+
+static inline u8 mte_get_ptr_tag(void *ptr)
+{
+	return 0xFF;
+}
+
+static inline u8 mte_get_mem_tag(void *addr)
+{
+	return 0xFF;
+}
+static inline u8 mte_get_random_tag(void)
+{
+	return 0xFF;
+}
+static inline void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag)
+{
+	return addr;
+}
+
+static inline void mte_enable_kernel(void)
+{
+}
+
+static inline void mte_init_tags(u64 max_tag)
+{
+}
+
+#endif /* CONFIG_ARM64_MTE */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_MTE_KASAN_H  */
diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index 1c99fcadb58c..d02aff9f493d 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -5,17 +5,21 @@
 #ifndef __ASM_MTE_H
 #define __ASM_MTE_H
 
-#define MTE_GRANULE_SIZE	UL(16)
-#define MTE_GRANULE_MASK	(~(MTE_GRANULE_SIZE - 1))
-#define MTE_TAG_SHIFT		56
-#define MTE_TAG_SIZE		4
+#include <asm/compiler.h>
+#include <asm/mte-def.h>
+
+#define __MTE_PREAMBLE		ARM64_ASM_PREAMBLE ".arch_extension memtag\n"
 
 #ifndef __ASSEMBLY__
 
+#include <linux/bitfield.h>
 #include <linux/page-flags.h>
+#include <linux/types.h>
 
 #include <asm/pgtable-types.h>
 
+extern u64 gcr_kernel_excl;
+
 void mte_clear_page_tags(void *addr);
 unsigned long mte_copy_tags_from_user(void *to, const void __user *from,
 				      unsigned long n);
@@ -45,7 +49,9 @@ long get_mte_ctrl(struct task_struct *task);
 int mte_ptrace_copy_tags(struct task_struct *child, long request,
 			 unsigned long addr, unsigned long data);
 
-#else
+void mte_assign_mem_tag_range(void *addr, size_t size);
+
+#else /* CONFIG_ARM64_MTE */
 
 /* unused if !CONFIG_ARM64_MTE, silence the compiler */
 #define PG_mte_tagged	0
@@ -80,7 +86,11 @@ static inline int mte_ptrace_copy_tags(struct task_struct *child,
 	return -EIO;
 }
 
-#endif
+static inline void mte_assign_mem_tag_range(void *addr, size_t size)
+{
+}
+
+#endif /* CONFIG_ARM64_MTE */
 
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_MTE_H  */
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 1599e17379d8..8f1661603b78 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -239,6 +239,12 @@ PERCPU_RET_OP(add, add, ldadd)
 #define this_cpu_cmpxchg_8(pcp, o, n)	\
 	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
 
+#ifdef __KVM_NVHE_HYPERVISOR__
+extern unsigned long __hyp_per_cpu_offset(unsigned int cpu);
+#define __per_cpu_offset
+#define per_cpu_offset(cpu)	__hyp_per_cpu_offset((cpu))
+#endif
+
 #include <asm-generic/percpu.h>
 
 /* Redefine macros for nVHE hyp under DEBUG_PREEMPT to avoid its dependencies. */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 724249f37af5..ca2cd75d3286 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -152,7 +152,7 @@ struct thread_struct {
 #endif
 #ifdef CONFIG_ARM64_MTE
 	u64			sctlr_tcf0;
-	u64			gcr_user_incl;
+	u64			gcr_user_excl;
 #endif
 };
 
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 3994169985ef..8ff579361731 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -11,6 +11,7 @@ extern char __alt_instructions[], __alt_instructions_end[];
 extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
 extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
 extern char __hyp_text_start[], __hyp_text_end[];
+extern char __hyp_data_ro_after_init_start[], __hyp_data_ro_after_init_end[];
 extern char __idmap_text_start[], __idmap_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __inittext_begin[], __inittext_end[];
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 2e7f529ec5a6..bcb01ca15325 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -46,9 +46,9 @@ DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
  * Logical CPU mapping.
  */
 extern u64 __cpu_logical_map[NR_CPUS];
-extern u64 cpu_logical_map(int cpu);
+extern u64 cpu_logical_map(unsigned int cpu);
 
-static inline void set_cpu_logical_map(int cpu, u64 hwid)
+static inline void set_cpu_logical_map(unsigned int cpu, u64 hwid)
 {
 	__cpu_logical_map[cpu] = hwid;
 }
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index fcdfbce302bd..f62ca39da6c5 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -9,7 +9,15 @@
 #ifndef __ASM_SPECTRE_H
 #define __ASM_SPECTRE_H
 
+#define BP_HARDEN_EL2_SLOTS 4
+#define __BP_HARDEN_HYP_VECS_SZ	((BP_HARDEN_EL2_SLOTS - 1) * SZ_2K)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/percpu.h>
+
 #include <asm/cpufeature.h>
+#include <asm/virt.h>
 
 /* Watch out, ordering is important here. */
 enum mitigation_state {
@@ -20,13 +28,70 @@ enum mitigation_state {
 
 struct task_struct;
 
+/*
+ * Note: the order of this enum corresponds to __bp_harden_hyp_vecs and
+ * we rely on having the direct vectors first.
+ */
+enum arm64_hyp_spectre_vector {
+	/*
+	 * Take exceptions directly to __kvm_hyp_vector. This must be
+	 * 0 so that it used by default when mitigations are not needed.
+	 */
+	HYP_VECTOR_DIRECT,
+
+	/*
+	 * Bounce via a slot in the hypervisor text mapping of
+	 * __bp_harden_hyp_vecs, which contains an SMC call.
+	 */
+	HYP_VECTOR_SPECTRE_DIRECT,
+
+	/*
+	 * Bounce via a slot in a special mapping of __bp_harden_hyp_vecs
+	 * next to the idmap page.
+	 */
+	HYP_VECTOR_INDIRECT,
+
+	/*
+	 * Bounce via a slot in a special mapping of __bp_harden_hyp_vecs
+	 * next to the idmap page, which contains an SMC call.
+	 */
+	HYP_VECTOR_SPECTRE_INDIRECT,
+};
+
+typedef void (*bp_hardening_cb_t)(void);
+
+struct bp_hardening_data {
+	enum arm64_hyp_spectre_vector	slot;
+	bp_hardening_cb_t		fn;
+};
+
+DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
+
+static inline void arm64_apply_bp_hardening(void)
+{
+	struct bp_hardening_data *d;
+
+	if (!cpus_have_const_cap(ARM64_SPECTRE_V2))
+		return;
+
+	d = this_cpu_ptr(&bp_hardening_data);
+	if (d->fn)
+		d->fn();
+}
+
 enum mitigation_state arm64_get_spectre_v2_state(void);
 bool has_spectre_v2(const struct arm64_cpu_capabilities *cap, int scope);
 void spectre_v2_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
 
+bool has_spectre_v3a(const struct arm64_cpu_capabilities *cap, int scope);
+void spectre_v3a_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
+
 enum mitigation_state arm64_get_spectre_v4_state(void);
 bool has_spectre_v4(const struct arm64_cpu_capabilities *cap, int scope);
 void spectre_v4_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
 void spectre_v4_enable_task_mitigation(struct task_struct *tsk);
 
+enum mitigation_state arm64_get_meltdown_state(void);
+
+#endif	/* __ASSEMBLY__ */
 #endif	/* __ASM_SPECTRE_H */
diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
index b31e8e87a0db..3a3264ff47b9 100644
--- a/arch/arm64/include/asm/string.h
+++ b/arch/arm64/include/asm/string.h
@@ -5,7 +5,7 @@
 #ifndef __ASM_STRING_H
 #define __ASM_STRING_H
 
-#ifndef CONFIG_KASAN
+#if !(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS))
 #define __HAVE_ARCH_STRRCHR
 extern char *strrchr(const char *, int c);
 
@@ -48,7 +48,8 @@ extern void *__memset(void *, int, __kernel_size_t);
 void memcpy_flushcache(void *dst, const void *src, size_t cnt);
 #endif
 
-#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
+	!defined(__SANITIZE_ADDRESS__)
 
 /*
  * For files that are not instrumented (e.g. mm/slub.c) we
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index cf7922f23808..8b5e7e5c3cc8 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -469,6 +469,7 @@
 
 #define SYS_PMCCFILTR_EL0		sys_reg(3, 3, 14, 15, 7)
 
+#define SYS_SCTLR_EL2			sys_reg(3, 4, 1, 0, 0)
 #define SYS_ZCR_EL2			sys_reg(3, 4, 1, 2, 0)
 #define SYS_DACR32_EL2			sys_reg(3, 4, 3, 0, 0)
 #define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index abb31aa1f8ca..f0fe0cc6abe0 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -159,8 +159,39 @@ static inline void __uaccess_enable_hw_pan(void)
 			CONFIG_ARM64_PAN));
 }
 
+/*
+ * The Tag Check Flag (TCF) mode for MTE is per EL, hence TCF0
+ * affects EL0 and TCF affects EL1 irrespective of which TTBR is
+ * used.
+ * The kernel accesses TTBR0 usually with LDTR/STTR instructions
+ * when UAO is available, so these would act as EL0 accesses using
+ * TCF0.
+ * However futex.h code uses exclusives which would be executed as
+ * EL1, this can potentially cause a tag check fault even if the
+ * user disables TCF0.
+ *
+ * To address the problem we set the PSTATE.TCO bit in uaccess_enable()
+ * and reset it in uaccess_disable().
+ *
+ * The Tag check override (TCO) bit disables temporarily the tag checking
+ * preventing the issue.
+ */
+static inline void __uaccess_disable_tco(void)
+{
+	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(0),
+				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+}
+
+static inline void __uaccess_enable_tco(void)
+{
+	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1),
+				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+}
+
 static inline void uaccess_disable_privileged(void)
 {
+	__uaccess_disable_tco();
+
 	if (uaccess_ttbr0_disable())
 		return;
 
@@ -169,6 +200,8 @@ static inline void uaccess_disable_privileged(void)
 
 static inline void uaccess_enable_privileged(void)
 {
+	__uaccess_enable_tco();
+
 	if (uaccess_ttbr0_enable())
 		return;
 
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 6069be50baf9..ee6a48df89d9 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -65,9 +65,19 @@ extern u32 __boot_cpu_mode[2];
 void __hyp_set_vectors(phys_addr_t phys_vector_base);
 void __hyp_reset_vectors(void);
 
+DECLARE_STATIC_KEY_FALSE(kvm_protected_mode_initialized);
+
 /* Reports the availability of HYP mode */
 static inline bool is_hyp_mode_available(void)
 {
+	/*
+	 * If KVM protected mode is initialized, all CPUs must have been booted
+	 * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1.
+	 */
+	if (IS_ENABLED(CONFIG_KVM) &&
+	    static_branch_likely(&kvm_protected_mode_initialized))
+		return true;
+
 	return (__boot_cpu_mode[0] == BOOT_CPU_MODE_EL2 &&
 		__boot_cpu_mode[1] == BOOT_CPU_MODE_EL2);
 }
@@ -75,6 +85,14 @@ static inline bool is_hyp_mode_available(void)
 /* Check if the bootloader has booted CPUs in different modes */
 static inline bool is_hyp_mode_mismatched(void)
 {
+	/*
+	 * If KVM protected mode is initialized, all CPUs must have been booted
+	 * in EL2. Avoid checking __boot_cpu_mode as CPUs now come up in EL1.
+	 */
+	if (IS_ENABLED(CONFIG_KVM) &&
+	    static_branch_likely(&kvm_protected_mode_initialized))
+		return false;
+
 	return __boot_cpu_mode[0] != __boot_cpu_mode[1];
 }
 
@@ -97,6 +115,14 @@ static __always_inline bool has_vhe(void)
 		return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN);
 }
 
+static __always_inline bool is_protected_kvm_enabled(void)
+{
+	if (is_vhe_hyp_code())
+		return false;
+	else
+		return cpus_have_final_cap(ARM64_KVM_PROTECTED_MODE);
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* ! __ASM__VIRT_H */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 1c17c3a24411..24223adae150 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -156,9 +156,6 @@ struct kvm_sync_regs {
 	__u64 device_irq_level;
 };
 
-struct kvm_arch_memory_slot {
-};
-
 /*
  * PMU filter structure. Describe a range of events with a particular
  * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 679b19b8a7ff..301784463587 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -47,6 +47,9 @@ int main(void)
   DEFINE(THREAD_KEYS_USER,	offsetof(struct task_struct, thread.keys_user));
   DEFINE(THREAD_KEYS_KERNEL,	offsetof(struct task_struct, thread.keys_kernel));
 #endif
+#ifdef CONFIG_ARM64_MTE
+  DEFINE(THREAD_GCR_EL1_USER,	offsetof(struct task_struct, thread.gcr_user_excl));
+#endif
   BLANK();
   DEFINE(S_X0,			offsetof(struct pt_regs, regs[0]));
   DEFINE(S_X2,			offsetof(struct pt_regs, regs[2]));
@@ -72,7 +75,7 @@ int main(void)
   DEFINE(S_SDEI_TTBR1,		offsetof(struct pt_regs, sdei_ttbr1));
   DEFINE(S_PMR_SAVE,		offsetof(struct pt_regs, pmr_save));
   DEFINE(S_STACKFRAME,		offsetof(struct pt_regs, stackframe));
-  DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
+  DEFINE(PT_REGS_SIZE,		sizeof(struct pt_regs));
   BLANK();
 #ifdef CONFIG_COMPAT
   DEFINE(COMPAT_SIGFRAME_REGS_OFFSET,		offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));
@@ -109,6 +112,11 @@ int main(void)
   DEFINE(CPU_APGAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APGAKEYLO_EL1]));
   DEFINE(HOST_CONTEXT_VCPU,	offsetof(struct kvm_cpu_context, __hyp_running_vcpu));
   DEFINE(HOST_DATA_CONTEXT,	offsetof(struct kvm_host_data, host_ctxt));
+  DEFINE(NVHE_INIT_MAIR_EL2,	offsetof(struct kvm_nvhe_init_params, mair_el2));
+  DEFINE(NVHE_INIT_TCR_EL2,	offsetof(struct kvm_nvhe_init_params, tcr_el2));
+  DEFINE(NVHE_INIT_TPIDR_EL2,	offsetof(struct kvm_nvhe_init_params, tpidr_el2));
+  DEFINE(NVHE_INIT_STACK_HYP_VA,	offsetof(struct kvm_nvhe_init_params, stack_hyp_va));
+  DEFINE(NVHE_INIT_PGD_PA,	offsetof(struct kvm_nvhe_init_params, pgd_pa));
 #endif
 #ifdef CONFIG_CPU_PM
   DEFINE(CPU_CTX_SP,		offsetof(struct cpu_suspend_ctx, sp));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index cafaf0da05b7..a63428301f42 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -196,16 +196,6 @@ has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
 	return is_midr_in_range(midr, &range) && has_dic;
 }
 
-#ifdef CONFIG_RANDOMIZE_BASE
-
-static const struct midr_range ca57_a72[] = {
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
-	{},
-};
-
-#endif
-
 #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
 static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = {
 #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009
@@ -461,9 +451,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	},
 #ifdef CONFIG_RANDOMIZE_BASE
 	{
-		.desc = "EL2 vector hardening",
-		.capability = ARM64_HARDEN_EL2_VECTORS,
-		ERRATA_MIDR_RANGE_LIST(ca57_a72),
+	/* Must come after the Spectre-v2 entry */
+		.desc = "Spectre-v3a",
+		.capability = ARM64_SPECTRE_V3A,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_spectre_v3a,
+		.cpu_enable = spectre_v3a_enable_mitigation,
 	},
 #endif
 	{
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 39138f6d3ba2..e99eddec0a46 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -70,10 +70,12 @@
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/cpu.h>
+#include <linux/kasan.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
 #include <asm/fpsimd.h>
+#include <asm/kvm_host.h>
 #include <asm/mmu_context.h>
 #include <asm/mte.h>
 #include <asm/processor.h>
@@ -1709,9 +1711,26 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap)
 		cleared_zero_page = true;
 		mte_clear_page_tags(lm_alias(empty_zero_page));
 	}
+
+	kasan_init_hw_tags_cpu();
 }
 #endif /* CONFIG_ARM64_MTE */
 
+#ifdef CONFIG_KVM
+static bool is_kvm_protected_mode(const struct arm64_cpu_capabilities *entry, int __unused)
+{
+	if (kvm_get_mode() != KVM_MODE_PROTECTED)
+		return false;
+
+	if (is_kernel_in_hyp_mode()) {
+		pr_warn("Protected KVM not available with VHE\n");
+		return false;
+	}
+
+	return true;
+}
+#endif /* CONFIG_KVM */
+
 /* Internal helper functions to match cpu capability type */
 static bool
 cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
@@ -1803,6 +1822,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64PFR0_EL1_SHIFT,
 		.min_field_value = ID_AA64PFR0_EL1_32BIT_64BIT,
 	},
+	{
+		.desc = "Protected KVM",
+		.capability = ARM64_KVM_PROTECTED_MODE,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = is_kvm_protected_mode,
+	},
 #endif
 	{
 		.desc = "Kernel page table isolation (KPTI)",
@@ -2543,7 +2568,7 @@ static void verify_hyp_capabilities(void)
 	int parange, ipa_max;
 	unsigned int safe_vmid_bits, vmid_bits;
 
-	if (!IS_ENABLED(CONFIG_KVM) || !IS_ENABLED(CONFIG_KVM_ARM_HOST))
+	if (!IS_ENABLED(CONFIG_KVM))
 		return;
 
 	safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
@@ -2831,14 +2856,28 @@ static int __init enable_mrs_emulation(void)
 
 core_initcall(enable_mrs_emulation);
 
+enum mitigation_state arm64_get_meltdown_state(void)
+{
+	if (__meltdown_safe)
+		return SPECTRE_UNAFFECTED;
+
+	if (arm64_kernel_unmapped_at_el0())
+		return SPECTRE_MITIGATED;
+
+	return SPECTRE_VULNERABLE;
+}
+
 ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr,
 			  char *buf)
 {
-	if (__meltdown_safe)
+	switch (arm64_get_meltdown_state()) {
+	case SPECTRE_UNAFFECTED:
 		return sprintf(buf, "Not affected\n");
 
-	if (arm64_kernel_unmapped_at_el0())
+	case SPECTRE_MITIGATED:
 		return sprintf(buf, "Mitigation: PTI\n");
 
-	return sprintf(buf, "Vulnerable\n");
+	default:
+		return sprintf(buf, "Vulnerable\n");
+	}
 }
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index a338f40e64d3..b3e4f9a088b1 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -35,7 +35,7 @@
  */
 	.macro  ftrace_regs_entry, allregs=0
 	/* Make room for pt_regs, plus a callee frame */
-	sub	sp, sp, #(S_FRAME_SIZE + 16)
+	sub	sp, sp, #(PT_REGS_SIZE + 16)
 
 	/* Save function arguments (and x9 for simplicity) */
 	stp	x0, x1, [sp, #S_X0]
@@ -61,15 +61,15 @@
 	.endif
 
 	/* Save the callsite's SP and LR */
-	add	x10, sp, #(S_FRAME_SIZE + 16)
+	add	x10, sp, #(PT_REGS_SIZE + 16)
 	stp	x9, x10, [sp, #S_LR]
 
 	/* Save the PC after the ftrace callsite */
 	str	x30, [sp, #S_PC]
 
 	/* Create a frame record for the callsite above pt_regs */
-	stp	x29, x9, [sp, #S_FRAME_SIZE]
-	add	x29, sp, #S_FRAME_SIZE
+	stp	x29, x9, [sp, #PT_REGS_SIZE]
+	add	x29, sp, #PT_REGS_SIZE
 
 	/* Create our frame record within pt_regs. */
 	stp	x29, x30, [sp, #S_STACKFRAME]
@@ -120,7 +120,7 @@ ftrace_common_return:
 	ldr	x9, [sp, #S_PC]
 
 	/* Restore the callsite's SP */
-	add	sp, sp, #S_FRAME_SIZE + 16
+	add	sp, sp, #PT_REGS_SIZE + 16
 
 	ret	x9
 SYM_CODE_END(ftrace_common)
@@ -130,7 +130,7 @@ SYM_CODE_START(ftrace_graph_caller)
 	ldr	x0, [sp, #S_PC]
 	sub	x0, x0, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
 	add	x1, sp, #S_LR			// parent_ip (callsite's LR)
-	ldr	x2, [sp, #S_FRAME_SIZE]	   	// parent fp (callsite's FP)
+	ldr	x2, [sp, #PT_REGS_SIZE]	   	// parent fp (callsite's FP)
 	bl	prepare_ftrace_return
 	b	ftrace_common_return
 SYM_CODE_END(ftrace_graph_caller)
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 51c762156099..c9bae73f2621 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -75,7 +75,7 @@ alternative_else_nop_endif
 	.endif
 #endif
 
-	sub	sp, sp, #S_FRAME_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
 #ifdef CONFIG_VMAP_STACK
 	/*
 	 * Test whether the SP has overflowed, without corrupting a GPR.
@@ -96,7 +96,7 @@ alternative_else_nop_endif
 	 * userspace, and can clobber EL0 registers to free up GPRs.
 	 */
 
-	/* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */
+	/* Stash the original SP (minus PT_REGS_SIZE) in tpidr_el0. */
 	msr	tpidr_el0, x0
 
 	/* Recover the original x0 value and stash it in tpidrro_el0 */
@@ -173,6 +173,43 @@ alternative_else_nop_endif
 #endif
 	.endm
 
+	.macro mte_set_gcr, tmp, tmp2
+#ifdef CONFIG_ARM64_MTE
+	/*
+	 * Calculate and set the exclude mask preserving
+	 * the RRND (bit[16]) setting.
+	 */
+	mrs_s	\tmp2, SYS_GCR_EL1
+	bfi	\tmp2, \tmp, #0, #16
+	msr_s	SYS_GCR_EL1, \tmp2
+#endif
+	.endm
+
+	.macro mte_set_kernel_gcr, tmp, tmp2
+#ifdef CONFIG_KASAN_HW_TAGS
+alternative_if_not ARM64_MTE
+	b	1f
+alternative_else_nop_endif
+	ldr_l	\tmp, gcr_kernel_excl
+
+	mte_set_gcr \tmp, \tmp2
+	isb
+1:
+#endif
+	.endm
+
+	.macro mte_set_user_gcr, tsk, tmp, tmp2
+#ifdef CONFIG_ARM64_MTE
+alternative_if_not ARM64_MTE
+	b	1f
+alternative_else_nop_endif
+	ldr	\tmp, [\tsk, #THREAD_GCR_EL1_USER]
+
+	mte_set_gcr \tmp, \tmp2
+1:
+#endif
+	.endm
+
 	.macro	kernel_entry, el, regsize = 64
 	.if	\regsize == 32
 	mov	w0, w0				// zero upper 32 bits of x0
@@ -212,9 +249,11 @@ alternative_else_nop_endif
 
 	ptrauth_keys_install_kernel tsk, x20, x22, x23
 
+	mte_set_kernel_gcr x22, x23
+
 	scs_load tsk, x20
 	.else
-	add	x21, sp, #S_FRAME_SIZE
+	add	x21, sp, #PT_REGS_SIZE
 	get_current_task tsk
 	.endif /* \el == 0 */
 	mrs	x22, elr_el1
@@ -315,6 +354,8 @@ alternative_else_nop_endif
 	/* No kernel C function calls after this as user keys are set. */
 	ptrauth_keys_install_user tsk, x0, x1, x2
 
+	mte_set_user_gcr tsk, x0, x1
+
 	apply_ssbd 0, x0, x1
 	.endif
 
@@ -336,7 +377,7 @@ alternative_else_nop_endif
 	ldp	x26, x27, [sp, #16 * 13]
 	ldp	x28, x29, [sp, #16 * 14]
 	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #S_FRAME_SIZE		// restore sp
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
 
 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
@@ -539,12 +580,12 @@ __bad_stack:
 
 	/*
 	 * Store the original GPRs to the new stack. The orginal SP (minus
-	 * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry.
+	 * PT_REGS_SIZE) was stashed in tpidr_el0 by kernel_ventry.
 	 */
-	sub	sp, sp, #S_FRAME_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
 	kernel_entry 1
 	mrs	x0, tpidr_el0
-	add	x0, x0, #S_FRAME_SIZE
+	add	x0, x0, #PT_REGS_SIZE
 	str	x0, [sp, #S_SP]
 
 	/* Stash the regs for handle_bad_stack */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index f2eb206920a2..a0dc987724ed 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -11,7 +11,6 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
-#include <linux/irqchip/arm-gic-v3.h>
 #include <linux/pgtable.h>
 
 #include <asm/asm_pointer_auth.h>
@@ -21,6 +20,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/cache.h>
 #include <asm/cputype.h>
+#include <asm/el2_setup.h>
 #include <asm/elf.h>
 #include <asm/image.h>
 #include <asm/kernel-pgtable.h>
@@ -433,7 +433,7 @@ SYM_FUNC_START_LOCAL(__primary_switched)
 	bl	__pi_memset
 	dsb	ishst				// Make zero page visible to PTW
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	bl	kasan_early_init
 #endif
 #ifdef CONFIG_RANDOMIZE_BASE
@@ -493,155 +493,56 @@ SYM_INNER_LABEL(init_el1, SYM_L_LOCAL)
 	eret
 
 SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
-	mov_q	x0, INIT_SCTLR_EL2_MMU_OFF
-	msr	sctlr_el2, x0
-
 #ifdef CONFIG_ARM64_VHE
 	/*
-	 * Check for VHE being present. For the rest of the EL2 setup,
-	 * x2 being non-zero indicates that we do have VHE, and that the
-	 * kernel is intended to run at EL2.
+	 * Check for VHE being present. x2 being non-zero indicates that we
+	 * do have VHE, and that the kernel is intended to run at EL2.
 	 */
 	mrs	x2, id_aa64mmfr1_el1
 	ubfx	x2, x2, #ID_AA64MMFR1_VHE_SHIFT, #4
 #else
 	mov	x2, xzr
 #endif
+	cbz	x2, init_el2_nvhe
 
-	/* Hyp configuration. */
-	mov_q	x0, HCR_HOST_NVHE_FLAGS
-	cbz	x2, set_hcr
+	/*
+	 * When VHE _is_ in use, EL1 will not be used in the host and
+	 * requires no configuration, and all non-hyp-specific EL2 setup
+	 * will be done via the _EL1 system register aliases in __cpu_setup.
+	 */
 	mov_q	x0, HCR_HOST_VHE_FLAGS
-set_hcr:
 	msr	hcr_el2, x0
 	isb
 
-	/*
-	 * Allow Non-secure EL1 and EL0 to access physical timer and counter.
-	 * This is not necessary for VHE, since the host kernel runs in EL2,
-	 * and EL0 accesses are configured in the later stage of boot process.
-	 * Note that when HCR_EL2.E2H == 1, CNTHCTL_EL2 has the same bit layout
-	 * as CNTKCTL_EL1, and CNTKCTL_EL1 accessing instructions are redefined
-	 * to access CNTHCTL_EL2. This allows the kernel designed to run at EL1
-	 * to transparently mess with the EL0 bits via CNTKCTL_EL1 access in
-	 * EL2.
-	 */
-	cbnz	x2, 1f
-	mrs	x0, cnthctl_el2
-	orr	x0, x0, #3			// Enable EL1 physical timers
-	msr	cnthctl_el2, x0
-1:
-	msr	cntvoff_el2, xzr		// Clear virtual offset
-
-#ifdef CONFIG_ARM_GIC_V3
-	/* GICv3 system register access */
-	mrs	x0, id_aa64pfr0_el1
-	ubfx	x0, x0, #ID_AA64PFR0_GIC_SHIFT, #4
-	cbz	x0, 3f
-
-	mrs_s	x0, SYS_ICC_SRE_EL2
-	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
-	orr	x0, x0, #ICC_SRE_EL2_ENABLE	// Set ICC_SRE_EL2.Enable==1
-	msr_s	SYS_ICC_SRE_EL2, x0
-	isb					// Make sure SRE is now set
-	mrs_s	x0, SYS_ICC_SRE_EL2		// Read SRE back,
-	tbz	x0, #0, 3f			// and check that it sticks
-	msr_s	SYS_ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
-
-3:
-#endif
-
-	/* Populate ID registers. */
-	mrs	x0, midr_el1
-	mrs	x1, mpidr_el1
-	msr	vpidr_el2, x0
-	msr	vmpidr_el2, x1
-
-#ifdef CONFIG_COMPAT
-	msr	hstr_el2, xzr			// Disable CP15 traps to EL2
-#endif
-
-	/* EL2 debug */
-	mrs	x1, id_aa64dfr0_el1
-	sbfx	x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4
-	cmp	x0, #1
-	b.lt	4f				// Skip if no PMU present
-	mrs	x0, pmcr_el0			// Disable debug access traps
-	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
-4:
-	csel	x3, xzr, x0, lt			// all PMU counters from EL1
-
-	/* Statistical profiling */
-	ubfx	x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
-	cbz	x0, 7f				// Skip if SPE not present
-	cbnz	x2, 6f				// VHE?
-	mrs_s	x4, SYS_PMBIDR_EL1		// If SPE available at EL2,
-	and	x4, x4, #(1 << SYS_PMBIDR_EL1_P_SHIFT)
-	cbnz	x4, 5f				// then permit sampling of physical
-	mov	x4, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \
-		      1 << SYS_PMSCR_EL2_PA_SHIFT)
-	msr_s	SYS_PMSCR_EL2, x4		// addresses and physical counter
-5:
-	mov	x1, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
-	orr	x3, x3, x1			// If we don't have VHE, then
-	b	7f				// use EL1&0 translation.
-6:						// For VHE, use EL2 translation
-	orr	x3, x3, #MDCR_EL2_TPMS		// and disable access from EL1
-7:
-	msr	mdcr_el2, x3			// Configure debug traps
-
-	/* LORegions */
-	mrs	x1, id_aa64mmfr1_el1
-	ubfx	x0, x1, #ID_AA64MMFR1_LOR_SHIFT, 4
-	cbz	x0, 1f
-	msr_s	SYS_LORC_EL1, xzr
-1:
-
-	/* Stage-2 translation */
-	msr	vttbr_el2, xzr
-
-	cbz	x2, install_el2_stub
+	init_el2_state vhe
 
 	isb
+
 	mov_q	x0, INIT_PSTATE_EL2
 	msr	spsr_el2, x0
 	msr	elr_el2, lr
 	mov	w0, #BOOT_CPU_MODE_EL2
 	eret
 
-SYM_INNER_LABEL(install_el2_stub, SYM_L_LOCAL)
+SYM_INNER_LABEL(init_el2_nvhe, SYM_L_LOCAL)
 	/*
 	 * When VHE is not in use, early init of EL2 and EL1 needs to be
 	 * done here.
-	 * When VHE _is_ in use, EL1 will not be used in the host and
-	 * requires no configuration, and all non-hyp-specific EL2 setup
-	 * will be done via the _EL1 system register aliases in __cpu_setup.
 	 */
 	mov_q	x0, INIT_SCTLR_EL1_MMU_OFF
 	msr	sctlr_el1, x0
 
-	/* Coprocessor traps. */
-	mov	x0, #0x33ff
-	msr	cptr_el2, x0			// Disable copro. traps to EL2
-
-	/* SVE register access */
-	mrs	x1, id_aa64pfr0_el1
-	ubfx	x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4
-	cbz	x1, 7f
-
-	bic	x0, x0, #CPTR_EL2_TZ		// Also disable SVE traps
-	msr	cptr_el2, x0			// Disable copro. traps to EL2
+	mov_q	x0, HCR_HOST_NVHE_FLAGS
+	msr	hcr_el2, x0
 	isb
-	mov	x1, #ZCR_ELx_LEN_MASK		// SVE: Enable full vector
-	msr_s	SYS_ZCR_EL2, x1			// length for EL1.
+
+	init_el2_state nvhe
 
 	/* Hypervisor stub */
-7:	adr_l	x0, __hyp_stub_vectors
+	adr_l	x0, __hyp_stub_vectors
 	msr	vbar_el2, x0
-
 	isb
-	mov	x0, #INIT_PSTATE_EL1
-	msr	spsr_el2, x0
+
 	msr	elr_el2, lr
 	mov	w0, #BOOT_CPU_MODE_EL2
 	eret
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 42003774d261..9c9f47e9f7f4 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -371,6 +371,11 @@ static void swsusp_mte_restore_tags(void)
 		unsigned long pfn = xa_state.xa_index;
 		struct page *page = pfn_to_online_page(pfn);
 
+		/*
+		 * It is not required to invoke page_kasan_tag_reset(page)
+		 * at this point since the tags stored in page->flags are
+		 * already restored.
+		 */
 		mte_restore_page_tags(page_address(page), tags);
 
 		mte_free_tag_storage(tags);
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index c615b285ff5b..f676243abac6 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -37,7 +37,7 @@ __efistub_strncmp		= __pi_strncmp;
 __efistub_strrchr		= __pi_strrchr;
 __efistub___clean_dcache_area_poc = __pi___clean_dcache_area_poc;
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 __efistub___memcpy		= __pi_memcpy;
 __efistub___memmove		= __pi_memmove;
 __efistub___memset		= __pi_memset;
@@ -64,13 +64,12 @@ __efistub__ctype		= _ctype;
 /* Alternative callbacks for init-time patching of nVHE hyp code. */
 KVM_NVHE_ALIAS(kvm_patch_vector_branch);
 KVM_NVHE_ALIAS(kvm_update_va_mask);
+KVM_NVHE_ALIAS(kvm_update_kimg_phys_offset);
+KVM_NVHE_ALIAS(kvm_get_kimage_voffset);
 
 /* Global kernel state accessed by nVHE hyp code. */
 KVM_NVHE_ALIAS(kvm_vgic_global_state);
 
-/* Kernel constant needed to compute idmap addresses. */
-KVM_NVHE_ALIAS(kimage_voffset);
-
 /* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */
 KVM_NVHE_ALIAS(__hyp_panic_string);
 KVM_NVHE_ALIAS(panic);
@@ -78,9 +77,6 @@ KVM_NVHE_ALIAS(panic);
 /* Vectors installed by hyp-init on reset HVC. */
 KVM_NVHE_ALIAS(__hyp_stub_vectors);
 
-/* IDMAP TCR_EL1.T0SZ as computed by the EL1 init code */
-KVM_NVHE_ALIAS(idmap_t0sz);
-
 /* Kernel symbol used by icache_is_vpipt(). */
 KVM_NVHE_ALIAS(__icache_flags);
 
@@ -103,6 +99,9 @@ KVM_NVHE_ALIAS(gic_nonsecure_priorities);
 KVM_NVHE_ALIAS(__start___kvm_ex_table);
 KVM_NVHE_ALIAS(__stop___kvm_ex_table);
 
+/* Array containing bases of nVHE per-CPU memory regions. */
+KVM_NVHE_ALIAS(kvm_arm_hyp_percpu_base);
+
 #endif /* CONFIG_KVM */
 
 #endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 0921aa1520b0..1c74c45b9494 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -161,7 +161,8 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	/* use the top 16 bits to randomize the linear region */
 	memstart_offset_seed = seed >> 48;
 
-	if (IS_ENABLED(CONFIG_KASAN))
+	if (IS_ENABLED(CONFIG_KASAN_GENERIC) ||
+	    IS_ENABLED(CONFIG_KASAN_SW_TAGS))
 		/*
 		 * KASAN does not expect the module region to intersect the
 		 * vmalloc region, since shadow memory is allocated for each
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 2a1ad95d9b2c..fe21e0f06492 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -30,7 +30,8 @@ void *module_alloc(unsigned long size)
 	if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
 		gfp_mask |= __GFP_NOWARN;
 
-	if (IS_ENABLED(CONFIG_KASAN))
+	if (IS_ENABLED(CONFIG_KASAN_GENERIC) ||
+	    IS_ENABLED(CONFIG_KASAN_SW_TAGS))
 		/* don't exceed the static module region - see below */
 		module_alloc_end = MODULES_END;
 
@@ -39,7 +40,8 @@ void *module_alloc(unsigned long size)
 				NUMA_NO_NODE, __builtin_return_address(0));
 
 	if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
-	    !IS_ENABLED(CONFIG_KASAN))
+	    !IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+	    !IS_ENABLED(CONFIG_KASAN_SW_TAGS))
 		/*
 		 * KASAN can only deal with module allocations being served
 		 * from the reserved module region, since the remainder of
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index ef15c8a2a49d..dc9ada64feed 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -13,13 +13,18 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/thread_info.h>
+#include <linux/types.h>
 #include <linux/uio.h>
 
+#include <asm/barrier.h>
 #include <asm/cpufeature.h>
 #include <asm/mte.h>
+#include <asm/mte-kasan.h>
 #include <asm/ptrace.h>
 #include <asm/sysreg.h>
 
+u64 gcr_kernel_excl __ro_after_init;
+
 static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
 {
 	pte_t old_pte = READ_ONCE(*ptep);
@@ -31,6 +36,15 @@ static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
 			return;
 	}
 
+	page_kasan_tag_reset(page);
+	/*
+	 * We need smp_wmb() in between setting the flags and clearing the
+	 * tags because if another thread reads page->flags and builds a
+	 * tagged address out of it, there is an actual dependency to the
+	 * memory access, but on the current thread we do not guarantee that
+	 * the new page->flags are visible before the tags were updated.
+	 */
+	smp_wmb();
 	mte_clear_page_tags(page_address(page));
 }
 
@@ -72,6 +86,78 @@ int memcmp_pages(struct page *page1, struct page *page2)
 	return ret;
 }
 
+u8 mte_get_mem_tag(void *addr)
+{
+	if (!system_supports_mte())
+		return 0xFF;
+
+	asm(__MTE_PREAMBLE "ldg %0, [%0]"
+	    : "+r" (addr));
+
+	return mte_get_ptr_tag(addr);
+}
+
+u8 mte_get_random_tag(void)
+{
+	void *addr;
+
+	if (!system_supports_mte())
+		return 0xFF;
+
+	asm(__MTE_PREAMBLE "irg %0, %0"
+	    : "+r" (addr));
+
+	return mte_get_ptr_tag(addr);
+}
+
+void *mte_set_mem_tag_range(void *addr, size_t size, u8 tag)
+{
+	void *ptr = addr;
+
+	if ((!system_supports_mte()) || (size == 0))
+		return addr;
+
+	/* Make sure that size is MTE granule aligned. */
+	WARN_ON(size & (MTE_GRANULE_SIZE - 1));
+
+	/* Make sure that the address is MTE granule aligned. */
+	WARN_ON((u64)addr & (MTE_GRANULE_SIZE - 1));
+
+	tag = 0xF0 | tag;
+	ptr = (void *)__tag_set(ptr, tag);
+
+	mte_assign_mem_tag_range(ptr, size);
+
+	return ptr;
+}
+
+void mte_init_tags(u64 max_tag)
+{
+	static bool gcr_kernel_excl_initialized;
+
+	if (!gcr_kernel_excl_initialized) {
+		/*
+		 * The format of the tags in KASAN is 0xFF and in MTE is 0xF.
+		 * This conversion extracts an MTE tag from a KASAN tag.
+		 */
+		u64 incl = GENMASK(FIELD_GET(MTE_TAG_MASK >> MTE_TAG_SHIFT,
+					     max_tag), 0);
+
+		gcr_kernel_excl = ~incl & SYS_GCR_EL1_EXCL_MASK;
+		gcr_kernel_excl_initialized = true;
+	}
+
+	/* Enable the kernel exclude mask for random tags generation. */
+	write_sysreg_s(SYS_GCR_EL1_RRND | gcr_kernel_excl, SYS_GCR_EL1);
+}
+
+void mte_enable_kernel(void)
+{
+	/* Enable MTE Sync Mode for EL1. */
+	sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, SCTLR_ELx_TCF_SYNC);
+	isb();
+}
+
 static void update_sctlr_el1_tcf0(u64 tcf0)
 {
 	/* ISB required for the kernel uaccess routines */
@@ -92,23 +178,26 @@ static void set_sctlr_el1_tcf0(u64 tcf0)
 	preempt_enable();
 }
 
-static void update_gcr_el1_excl(u64 incl)
+static void update_gcr_el1_excl(u64 excl)
 {
-	u64 excl = ~incl & SYS_GCR_EL1_EXCL_MASK;
 
 	/*
-	 * Note that 'incl' is an include mask (controlled by the user via
-	 * prctl()) while GCR_EL1 accepts an exclude mask.
+	 * Note that the mask controlled by the user via prctl() is an
+	 * include while GCR_EL1 accepts an exclude mask.
 	 * No need for ISB since this only affects EL0 currently, implicit
 	 * with ERET.
 	 */
 	sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, excl);
 }
 
-static void set_gcr_el1_excl(u64 incl)
+static void set_gcr_el1_excl(u64 excl)
 {
-	current->thread.gcr_user_incl = incl;
-	update_gcr_el1_excl(incl);
+	current->thread.gcr_user_excl = excl;
+
+	/*
+	 * SYS_GCR_EL1 will be set to current->thread.gcr_user_excl value
+	 * by mte_set_user_gcr() in kernel_exit,
+	 */
 }
 
 void flush_mte_state(void)
@@ -123,7 +212,7 @@ void flush_mte_state(void)
 	/* disable tag checking */
 	set_sctlr_el1_tcf0(SCTLR_EL1_TCF0_NONE);
 	/* reset tag generation mask */
-	set_gcr_el1_excl(0);
+	set_gcr_el1_excl(SYS_GCR_EL1_EXCL_MASK);
 }
 
 void mte_thread_switch(struct task_struct *next)
@@ -134,7 +223,6 @@ void mte_thread_switch(struct task_struct *next)
 	/* avoid expensive SCTLR_EL1 accesses if no change */
 	if (current->thread.sctlr_tcf0 != next->thread.sctlr_tcf0)
 		update_sctlr_el1_tcf0(next->thread.sctlr_tcf0);
-	update_gcr_el1_excl(next->thread.gcr_user_incl);
 }
 
 void mte_suspend_exit(void)
@@ -142,13 +230,14 @@ void mte_suspend_exit(void)
 	if (!system_supports_mte())
 		return;
 
-	update_gcr_el1_excl(current->thread.gcr_user_incl);
+	update_gcr_el1_excl(gcr_kernel_excl);
 }
 
 long set_mte_ctrl(struct task_struct *task, unsigned long arg)
 {
 	u64 tcf0;
-	u64 gcr_incl = (arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT;
+	u64 gcr_excl = ~((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT) &
+		       SYS_GCR_EL1_EXCL_MASK;
 
 	if (!system_supports_mte())
 		return 0;
@@ -169,10 +258,10 @@ long set_mte_ctrl(struct task_struct *task, unsigned long arg)
 
 	if (task != current) {
 		task->thread.sctlr_tcf0 = tcf0;
-		task->thread.gcr_user_incl = gcr_incl;
+		task->thread.gcr_user_excl = gcr_excl;
 	} else {
 		set_sctlr_el1_tcf0(tcf0);
-		set_gcr_el1_excl(gcr_incl);
+		set_gcr_el1_excl(gcr_excl);
 	}
 
 	return 0;
@@ -181,11 +270,12 @@ long set_mte_ctrl(struct task_struct *task, unsigned long arg)
 long get_mte_ctrl(struct task_struct *task)
 {
 	unsigned long ret;
+	u64 incl = ~task->thread.gcr_user_excl & SYS_GCR_EL1_EXCL_MASK;
 
 	if (!system_supports_mte())
 		return 0;
 
-	ret = task->thread.gcr_user_incl << PR_MTE_TAG_SHIFT;
+	ret = incl << PR_MTE_TAG_SHIFT;
 
 	switch (task->thread.sctlr_tcf0) {
 	case SCTLR_EL1_TCF0_NONE:
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 38bb07eff872..3605f77ad4df 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -23,8 +23,6 @@
 #include <linux/platform_device.h>
 #include <linux/sched_clock.h>
 #include <linux/smp.h>
-#include <linux/nmi.h>
-#include <linux/cpufreq.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
@@ -1250,21 +1248,10 @@ static struct platform_driver armv8_pmu_driver = {
 
 static int __init armv8_pmu_driver_init(void)
 {
-	int ret;
-
 	if (acpi_disabled)
-		ret = platform_driver_register(&armv8_pmu_driver);
+		return platform_driver_register(&armv8_pmu_driver);
 	else
-		ret = arm_pmu_acpi_probe(armv8_pmuv3_init);
-
-	/*
-	 * Try to re-initialize lockup detector after PMU init in
-	 * case PMU events are triggered via NMIs.
-	 */
-	if (ret == 0 && arm_pmu_irq_is_nmi())
-		lockup_detector_init();
-
-	return ret;
+		return arm_pmu_acpi_probe(armv8_pmuv3_init);
 }
 device_initcall(armv8_pmu_driver_init)
 
@@ -1322,27 +1309,3 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time_zero = 1;
 	userpg->cap_user_time_short = 1;
 }
-
-#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
-/*
- * Safe maximum CPU frequency in case a particular platform doesn't implement
- * cpufreq driver. Although, architecture doesn't put any restrictions on
- * maximum frequency but 5 GHz seems to be safe maximum given the available
- * Arm CPUs in the market which are clocked much less than 5 GHz. On the other
- * hand, we can't make it much higher as it would lead to a large hard-lockup
- * detection timeout on parts which are running slower (eg. 1GHz on
- * Developerbox) and doesn't possess a cpufreq driver.
- */
-#define SAFE_MAX_CPU_FREQ	5000000000UL // 5 GHz
-u64 hw_nmi_get_sample_period(int watchdog_thresh)
-{
-	unsigned int cpu = smp_processor_id();
-	unsigned long max_cpu_freq;
-
-	max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL;
-	if (!max_cpu_freq)
-		max_cpu_freq = SAFE_MAX_CPU_FREQ;
-
-	return (u64)max_cpu_freq * watchdog_thresh;
-}
-#endif
diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S
index 890ca72c5a51..288a84e253cc 100644
--- a/arch/arm64/kernel/probes/kprobes_trampoline.S
+++ b/arch/arm64/kernel/probes/kprobes_trampoline.S
@@ -25,7 +25,7 @@
 	stp x24, x25, [sp, #S_X24]
 	stp x26, x27, [sp, #S_X26]
 	stp x28, x29, [sp, #S_X28]
-	add x0, sp, #S_FRAME_SIZE
+	add x0, sp, #PT_REGS_SIZE
 	stp lr, x0, [sp, #S_LR]
 	/*
 	 * Construct a useful saved PSTATE
@@ -62,7 +62,7 @@
 	.endm
 
 SYM_CODE_START(kretprobe_trampoline)
-	sub sp, sp, #S_FRAME_SIZE
+	sub sp, sp, #PT_REGS_SIZE
 
 	save_all_base_regs
 
@@ -76,7 +76,7 @@ SYM_CODE_START(kretprobe_trampoline)
 
 	restore_all_base_regs
 
-	add sp, sp, #S_FRAME_SIZE
+	add sp, sp, #PT_REGS_SIZE
 	ret
 
 SYM_CODE_END(kretprobe_trampoline)
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index 4c25c008504f..902e4084c477 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Handle detection, reporting and mitigation of Spectre v1, v2 and v4, as
+ * Handle detection, reporting and mitigation of Spectre v1, v2, v3a and v4, as
  * detailed at:
  *
  *   https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability
@@ -27,6 +27,7 @@
 #include <asm/insn.h>
 #include <asm/spectre.h>
 #include <asm/traps.h>
+#include <asm/virt.h>
 
 /*
  * We try to ensure that the mitigation state can never change as the result of
@@ -171,72 +172,26 @@ bool has_spectre_v2(const struct arm64_cpu_capabilities *entry, int scope)
 	return true;
 }
 
-DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
-
 enum mitigation_state arm64_get_spectre_v2_state(void)
 {
 	return spectre_v2_state;
 }
 
-#ifdef CONFIG_KVM
-#include <asm/cacheflush.h>
-#include <asm/kvm_asm.h>
-
-atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
-
-static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
-				const char *hyp_vecs_end)
-{
-	void *dst = lm_alias(__bp_harden_hyp_vecs + slot * SZ_2K);
-	int i;
-
-	for (i = 0; i < SZ_2K; i += 0x80)
-		memcpy(dst + i, hyp_vecs_start, hyp_vecs_end - hyp_vecs_start);
-
-	__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
-}
+DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
 
 static void install_bp_hardening_cb(bp_hardening_cb_t fn)
 {
-	static DEFINE_RAW_SPINLOCK(bp_lock);
-	int cpu, slot = -1;
-	const char *hyp_vecs_start = __smccc_workaround_1_smc;
-	const char *hyp_vecs_end = __smccc_workaround_1_smc +
-				   __SMCCC_WORKAROUND_1_SMC_SZ;
+	__this_cpu_write(bp_hardening_data.fn, fn);
 
 	/*
 	 * Vinz Clortho takes the hyp_vecs start/end "keys" at
 	 * the door when we're a guest. Skip the hyp-vectors work.
 	 */
-	if (!is_hyp_mode_available()) {
-		__this_cpu_write(bp_hardening_data.fn, fn);
+	if (!is_hyp_mode_available())
 		return;
-	}
-
-	raw_spin_lock(&bp_lock);
-	for_each_possible_cpu(cpu) {
-		if (per_cpu(bp_hardening_data.fn, cpu) == fn) {
-			slot = per_cpu(bp_hardening_data.hyp_vectors_slot, cpu);
-			break;
-		}
-	}
-
-	if (slot == -1) {
-		slot = atomic_inc_return(&arm64_el2_vector_last_slot);
-		BUG_ON(slot >= BP_HARDEN_EL2_SLOTS);
-		__copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end);
-	}
 
-	__this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot);
-	__this_cpu_write(bp_hardening_data.fn, fn);
-	raw_spin_unlock(&bp_lock);
-}
-#else
-static void install_bp_hardening_cb(bp_hardening_cb_t fn)
-{
-	__this_cpu_write(bp_hardening_data.fn, fn);
+	__this_cpu_write(bp_hardening_data.slot, HYP_VECTOR_SPECTRE_DIRECT);
 }
-#endif	/* CONFIG_KVM */
 
 static void call_smc_arch_workaround_1(void)
 {
@@ -318,6 +273,33 @@ void spectre_v2_enable_mitigation(const struct arm64_cpu_capabilities *__unused)
 }
 
 /*
+ * Spectre-v3a.
+ *
+ * Phew, there's not an awful lot to do here! We just instruct EL2 to use
+ * an indirect trampoline for the hyp vectors so that guests can't read
+ * VBAR_EL2 to defeat randomisation of the hypervisor VA layout.
+ */
+bool has_spectre_v3a(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	static const struct midr_range spectre_v3a_unsafe_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
+		{},
+	};
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+	return is_midr_in_range_list(read_cpuid_id(), spectre_v3a_unsafe_list);
+}
+
+void spectre_v3a_enable_mitigation(const struct arm64_cpu_capabilities *__unused)
+{
+	struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data);
+
+	if (this_cpu_has_cap(ARM64_SPECTRE_V3A))
+		data->slot += HYP_VECTOR_INDIRECT;
+}
+
+/*
  * Spectre v4.
  *
  * If you thought Spectre v2 was nasty, wait until you see this mess. A CPU is
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 1a57a76e1cc2..c18aacde8bb0 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -276,7 +276,7 @@ arch_initcall(reserve_memblock_reserved_regions);
 
 u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
-u64 cpu_logical_map(int cpu)
+u64 cpu_logical_map(unsigned int cpu)
 {
 	return __cpu_logical_map[cpu];
 }
@@ -358,7 +358,7 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
 	smp_build_mpidr_hash();
 
 	/* Init percpu seeds for random tags after cpus are set up. */
-	kasan_init_tags();
+	kasan_init_sw_tags();
 
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	/*
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index f71d6ce4673f..6237486ff6bb 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -914,13 +914,6 @@ static void do_signal(struct pt_regs *regs)
 asmlinkage void do_notify_resume(struct pt_regs *regs,
 				 unsigned long thread_flags)
 {
-	/*
-	 * The assembly code enters us with IRQs off, but it hasn't
-	 * informed the tracing code of that for efficiency reasons.
-	 * Update the trace code with the current status.
-	 */
-	trace_hardirqs_off();
-
 	do {
 		if (thread_flags & _TIF_NEED_RESCHED) {
 			/* Unmask Debug and SError for the next task */
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index 4be7f7eed875..6bdef7362c0e 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -133,7 +133,7 @@ SYM_FUNC_START(_cpu_resume)
 	 */
 	bl	cpu_do_resume
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
 	mov	x0, sp
 	bl	kasan_unpoison_task_stack_below
 #endif
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 2499b895efea..ad00f99ee9b0 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -434,7 +434,7 @@ static void __init hyp_mode_check(void)
 			   "CPU: CPUs started in inconsistent modes");
 	else
 		pr_info("CPU: All CPU(s) started at EL1\n");
-	if (IS_ENABLED(CONFIG_KVM))
+	if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode())
 		kvm_compute_layout();
 }
 
@@ -462,6 +462,8 @@ void __init smp_prepare_boot_cpu(void)
 	/* Conditionally switch to GIC PMR for interrupt masking */
 	if (system_uses_irq_prio_masking())
 		init_gic_priority_masking();
+
+	kasan_init_hw_tags();
 }
 
 static u64 __init of_get_cpu_mpidr(struct device_node *dn)
@@ -805,11 +807,10 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	unsigned int cpu, i;
 
 	for (i = 0; i < NR_IPI; i++) {
-		unsigned int irq = irq_desc_get_irq(ipi_desc[i]);
 		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
 			   prec >= 4 ? " " : "");
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+			seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu));
 		seq_printf(p, "      %s\n", ipi_types[i]);
 	}
 
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index f61e9d8cc55a..c2877c332f2d 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -9,6 +9,7 @@
 
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
+#include <asm/exception.h>
 #include <asm/fpsimd.h>
 #include <asm/syscall.h>
 #include <asm/thread_info.h>
@@ -165,15 +166,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
-			/*
-			 * We're off to userspace, where interrupts are
-			 * always enabled after we restore the flags from
-			 * the SPSR.
-			 */
-			trace_hardirqs_on();
+		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP))
 			return;
-		}
 		local_daif_restore(DAIF_PROCCTX);
 	}
 
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 08156be75569..6895ce777e7f 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -42,7 +42,6 @@
 #include <asm/smp.h>
 #include <asm/stack_pointer.h>
 #include <asm/stacktrace.h>
-#include <asm/exception.h>
 #include <asm/system_misc.h>
 #include <asm/sysreg.h>
 
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index a8f8e409e2bf..cd9c3fa25902 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -24,8 +24,7 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti
 # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so
 # preparation in build-time C")).
 ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv	\
-	     -Bsymbolic $(call ld-option, --no-eh-frame-hdr) --build-id=sha1 -n	\
-	     $(btildflags-y) -T
+	     -Bsymbolic --build-id=sha1 -n $(btildflags-y) -T
 
 ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
 ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S
index d808ad31e01f..61dbb4c838ef 100644
--- a/arch/arm64/kernel/vdso/vdso.lds.S
+++ b/arch/arm64/kernel/vdso/vdso.lds.S
@@ -40,9 +40,6 @@ SECTIONS
 	PROVIDE (_etext = .);
 	PROVIDE (etext = .);
 
-	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
-	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
-
 	.dynamic	: { *(.dynamic) }		:text	:dynamic
 
 	.rodata		: { *(.rodata*) }		:text
@@ -54,6 +51,7 @@ SECTIONS
 		*(.note.GNU-stack)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
+		*(.eh_frame .eh_frame_hdr)
 	}
 }
 
@@ -66,7 +64,6 @@ PHDRS
 	text		PT_LOAD		FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
 	dynamic		PT_DYNAMIC	FLAGS(4);		/* PF_R */
 	note		PT_NOTE		FLAGS(4);		/* PF_R */
-	eh_frame_hdr	PT_GNU_EH_FRAME;
 }
 
 /*
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 5d5857c5b025..4c0b0c89ad59 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -30,6 +30,13 @@ jiffies = jiffies_64;
 	*(__kvm_ex_table)					\
 	__stop___kvm_ex_table = .;
 
+#define HYPERVISOR_DATA_SECTIONS				\
+	HYP_SECTION_NAME(.data..ro_after_init) : {		\
+		__hyp_data_ro_after_init_start = .;		\
+		*(HYP_SECTION_NAME(.data..ro_after_init))	\
+		__hyp_data_ro_after_init_end = .;		\
+	}
+
 #define HYPERVISOR_PERCPU_SECTION				\
 	. = ALIGN(PAGE_SIZE);					\
 	HYP_SECTION_NAME(.data..percpu) : {			\
@@ -37,6 +44,7 @@ jiffies = jiffies_64;
 	}
 #else /* CONFIG_KVM */
 #define HYPERVISOR_EXTABLE
+#define HYPERVISOR_DATA_SECTIONS
 #define HYPERVISOR_PERCPU_SECTION
 #endif
 
@@ -232,6 +240,8 @@ SECTIONS
 	_sdata = .;
 	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN)
 
+	HYPERVISOR_DATA_SECTIONS
+
 	/*
 	 * Data written with the MMU off but read with the MMU on requires
 	 * cache lines to be invalidated, discarding up to a Cache Writeback
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 043756db8f6e..3964acf5451e 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -49,14 +49,6 @@ if KVM
 
 source "virt/kvm/Kconfig"
 
-config KVM_ARM_PMU
-	bool "Virtual Performance Monitoring Unit (PMU) support"
-	depends on HW_PERF_EVENTS
-	default y
-	help
-	  Adds support for a virtual Performance Monitoring Unit (PMU) in
-	  virtual machines.
-
 endif # KVM
 
 endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 1504c81fbf5d..13b017284bf9 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -13,10 +13,10 @@ obj-$(CONFIG_KVM) += hyp/
 kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 $(KVM)/vfio.o $(KVM)/irqchip.o \
 	 arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \
-	 inject_fault.o regmap.o va_layout.o handle_exit.o \
+	 inject_fault.o va_layout.o handle_exit.o \
 	 guest.o debug.o reset.o sys_regs.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o \
-	 aarch32.o arch_timer.o \
+	 arch_timer.o \
 	 vgic/vgic.o vgic/vgic-init.o \
 	 vgic/vgic-irqfd.o vgic/vgic-v2.o \
 	 vgic/vgic-v3.o vgic/vgic-v4.o \
@@ -24,4 +24,4 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \
 	 vgic/vgic-its.o vgic/vgic-debug.o
 
-kvm-$(CONFIG_KVM_ARM_PMU)  += pmu-emul.o
+kvm-$(CONFIG_HW_PERF_EVENTS)  += pmu-emul.o
diff --git a/arch/arm64/kvm/aarch32.c b/arch/arm64/kvm/aarch32.c
deleted file mode 100644
index 40a62a99fbf8..000000000000
--- a/arch/arm64/kvm/aarch32.c
+++ /dev/null
@@ -1,232 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * (not much of an) Emulation layer for 32bit guests.
- *
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * based on arch/arm/kvm/emulate.c
- * Copyright (C) 2012 - Virtual Open Systems and Columbia University
- * Author: Christoffer Dall <c.dall@virtualopensystems.com>
- */
-
-#include <linux/bits.h>
-#include <linux/kvm_host.h>
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_hyp.h>
-
-#define DFSR_FSC_EXTABT_LPAE	0x10
-#define DFSR_FSC_EXTABT_nLPAE	0x08
-#define DFSR_LPAE		BIT(9)
-
-/*
- * Table taken from ARMv8 ARM DDI0487B-B, table G1-10.
- */
-static const u8 return_offsets[8][2] = {
-	[0] = { 0, 0 },		/* Reset, unused */
-	[1] = { 4, 2 },		/* Undefined */
-	[2] = { 0, 0 },		/* SVC, unused */
-	[3] = { 4, 4 },		/* Prefetch abort */
-	[4] = { 8, 8 },		/* Data abort */
-	[5] = { 0, 0 },		/* HVC, unused */
-	[6] = { 4, 4 },		/* IRQ, unused */
-	[7] = { 4, 4 },		/* FIQ, unused */
-};
-
-static bool pre_fault_synchronize(struct kvm_vcpu *vcpu)
-{
-	preempt_disable();
-	if (vcpu->arch.sysregs_loaded_on_cpu) {
-		kvm_arch_vcpu_put(vcpu);
-		return true;
-	}
-
-	preempt_enable();
-	return false;
-}
-
-static void post_fault_synchronize(struct kvm_vcpu *vcpu, bool loaded)
-{
-	if (loaded) {
-		kvm_arch_vcpu_load(vcpu, smp_processor_id());
-		preempt_enable();
-	}
-}
-
-/*
- * When an exception is taken, most CPSR fields are left unchanged in the
- * handler. However, some are explicitly overridden (e.g. M[4:0]).
- *
- * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with
- * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was
- * obsoleted by the ARMv7 virtualization extensions and is RES0.
- *
- * For the SPSR layout seen from AArch32, see:
- * - ARM DDI 0406C.d, page B1-1148
- * - ARM DDI 0487E.a, page G8-6264
- *
- * For the SPSR_ELx layout for AArch32 seen from AArch64, see:
- * - ARM DDI 0487E.a, page C5-426
- *
- * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from
- * MSB to LSB.
- */
-static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode)
-{
-	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
-	unsigned long old, new;
-
-	old = *vcpu_cpsr(vcpu);
-	new = 0;
-
-	new |= (old & PSR_AA32_N_BIT);
-	new |= (old & PSR_AA32_Z_BIT);
-	new |= (old & PSR_AA32_C_BIT);
-	new |= (old & PSR_AA32_V_BIT);
-	new |= (old & PSR_AA32_Q_BIT);
-
-	// CPSR.IT[7:0] are set to zero upon any exception
-	// See ARM DDI 0487E.a, section G1.12.3
-	// See ARM DDI 0406C.d, section B1.8.3
-
-	new |= (old & PSR_AA32_DIT_BIT);
-
-	// CPSR.SSBS is set to SCTLR.DSSBS upon any exception
-	// See ARM DDI 0487E.a, page G8-6244
-	if (sctlr & BIT(31))
-		new |= PSR_AA32_SSBS_BIT;
-
-	// CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0
-	// SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented
-	// See ARM DDI 0487E.a, page G8-6246
-	new |= (old & PSR_AA32_PAN_BIT);
-	if (!(sctlr & BIT(23)))
-		new |= PSR_AA32_PAN_BIT;
-
-	// SS does not exist in AArch32, so ignore
-
-	// CPSR.IL is set to zero upon any exception
-	// See ARM DDI 0487E.a, page G1-5527
-
-	new |= (old & PSR_AA32_GE_MASK);
-
-	// CPSR.IT[7:0] are set to zero upon any exception
-	// See prior comment above
-
-	// CPSR.E is set to SCTLR.EE upon any exception
-	// See ARM DDI 0487E.a, page G8-6245
-	// See ARM DDI 0406C.d, page B4-1701
-	if (sctlr & BIT(25))
-		new |= PSR_AA32_E_BIT;
-
-	// CPSR.A is unchanged upon an exception to Undefined, Supervisor
-	// CPSR.A is set upon an exception to other modes
-	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
-	// See ARM DDI 0406C.d, page B1-1182
-	new |= (old & PSR_AA32_A_BIT);
-	if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC)
-		new |= PSR_AA32_A_BIT;
-
-	// CPSR.I is set upon any exception
-	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
-	// See ARM DDI 0406C.d, page B1-1182
-	new |= PSR_AA32_I_BIT;
-
-	// CPSR.F is set upon an exception to FIQ
-	// CPSR.F is unchanged upon an exception to other modes
-	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
-	// See ARM DDI 0406C.d, page B1-1182
-	new |= (old & PSR_AA32_F_BIT);
-	if (mode == PSR_AA32_MODE_FIQ)
-		new |= PSR_AA32_F_BIT;
-
-	// CPSR.T is set to SCTLR.TE upon any exception
-	// See ARM DDI 0487E.a, page G8-5514
-	// See ARM DDI 0406C.d, page B1-1181
-	if (sctlr & BIT(30))
-		new |= PSR_AA32_T_BIT;
-
-	new |= mode;
-
-	return new;
-}
-
-static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
-{
-	unsigned long spsr = *vcpu_cpsr(vcpu);
-	bool is_thumb = (spsr & PSR_AA32_T_BIT);
-	u32 return_offset = return_offsets[vect_offset >> 2][is_thumb];
-	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
-
-	*vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode);
-
-	/* Note: These now point to the banked copies */
-	vcpu_write_spsr(vcpu, host_spsr_to_spsr32(spsr));
-	*vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
-
-	/* Branch to exception vector */
-	if (sctlr & (1 << 13))
-		vect_offset += 0xffff0000;
-	else /* always have security exceptions */
-		vect_offset += vcpu_cp15(vcpu, c12_VBAR);
-
-	*vcpu_pc(vcpu) = vect_offset;
-}
-
-void kvm_inject_undef32(struct kvm_vcpu *vcpu)
-{
-	bool loaded = pre_fault_synchronize(vcpu);
-
-	prepare_fault32(vcpu, PSR_AA32_MODE_UND, 4);
-	post_fault_synchronize(vcpu, loaded);
-}
-
-/*
- * Modelled after TakeDataAbortException() and TakePrefetchAbortException
- * pseudocode.
- */
-static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
-			 unsigned long addr)
-{
-	u32 vect_offset;
-	u32 *far, *fsr;
-	bool is_lpae;
-	bool loaded;
-
-	loaded = pre_fault_synchronize(vcpu);
-
-	if (is_pabt) {
-		vect_offset = 12;
-		far = &vcpu_cp15(vcpu, c6_IFAR);
-		fsr = &vcpu_cp15(vcpu, c5_IFSR);
-	} else { /* !iabt */
-		vect_offset = 16;
-		far = &vcpu_cp15(vcpu, c6_DFAR);
-		fsr = &vcpu_cp15(vcpu, c5_DFSR);
-	}
-
-	prepare_fault32(vcpu, PSR_AA32_MODE_ABT, vect_offset);
-
-	*far = addr;
-
-	/* Give the guest an IMPLEMENTATION DEFINED exception */
-	is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31);
-	if (is_lpae) {
-		*fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE;
-	} else {
-		/* no need to shuffle FS[4] into DFSR[10] as its 0 */
-		*fsr = DFSR_FSC_EXTABT_nLPAE;
-	}
-
-	post_fault_synchronize(vcpu, loaded);
-}
-
-void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr)
-{
-	inject_abt32(vcpu, false, addr);
-}
-
-void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr)
-{
-	inject_abt32(vcpu, true, addr);
-}
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 32ba6fbc3814..74e0699661e9 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -1129,9 +1129,10 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 	if (!irqchip_in_kernel(vcpu->kvm))
 		goto no_vgic;
 
-	if (!vgic_initialized(vcpu->kvm))
-		return -ENODEV;
-
+	/*
+	 * At this stage, we have the guarantee that the vgic is both
+	 * available and initialized.
+	 */
 	if (!timer_irqs_are_valid(vcpu)) {
 		kvm_debug("incorrectly configured timer irqs\n");
 		return -EINVAL;
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index c0ffb019ca8b..04c44853b103 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -19,6 +19,7 @@
 #include <linux/kvm_irqfd.h>
 #include <linux/irqbypass.h>
 #include <linux/sched/stat.h>
+#include <linux/psci.h>
 #include <trace/events/kvm.h>
 
 #define CREATE_TRACE_POINTS
@@ -35,7 +36,6 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_emulate.h>
-#include <asm/kvm_coproc.h>
 #include <asm/sections.h>
 
 #include <kvm/arm_hypercalls.h>
@@ -46,10 +46,14 @@
 __asm__(".arch_extension	virt");
 #endif
 
+static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT;
+DEFINE_STATIC_KEY_FALSE(kvm_protected_mode_initialized);
+
 DECLARE_KVM_HYP_PER_CPU(unsigned long, kvm_hyp_vector);
 
 static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
 unsigned long kvm_arm_hyp_percpu_base[NR_CPUS];
+DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
 /* The VMID used in the VTTBR */
 static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
@@ -102,7 +106,7 @@ static int kvm_arm_default_max_vcpus(void)
 	return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;
 }
 
-static void set_default_csv2(struct kvm *kvm)
+static void set_default_spectre(struct kvm *kvm)
 {
 	/*
 	 * The default is to expose CSV2 == 1 if the HW isn't affected.
@@ -114,6 +118,8 @@ static void set_default_csv2(struct kvm *kvm)
 	 */
 	if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED)
 		kvm->arch.pfr0_csv2 = 1;
+	if (arm64_get_meltdown_state() == SPECTRE_UNAFFECTED)
+		kvm->arch.pfr0_csv3 = 1;
 }
 
 /**
@@ -141,7 +147,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	/* The maximum number of VCPUs is limited by the host's GIC model */
 	kvm->arch.max_vcpus = kvm_arm_default_max_vcpus();
 
-	set_default_csv2(kvm);
+	set_default_spectre(kvm);
 
 	return ret;
 out_free_stage2_pgd:
@@ -198,6 +204,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_IRQ_LINE_LAYOUT_2:
 	case KVM_CAP_ARM_NISV_TO_USER:
 	case KVM_CAP_ARM_INJECT_EXT_DABT:
+	case KVM_CAP_SET_GUEST_DEBUG:
+	case KVM_CAP_VCPU_ATTRIBUTES:
 		r = 1;
 		break;
 	case KVM_CAP_ARM_SET_DEVICE_ADDR:
@@ -229,10 +237,35 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_STEAL_TIME:
 		r = kvm_arm_pvtime_supported();
 		break;
-	default:
-		r = kvm_arch_vm_ioctl_check_extension(kvm, ext);
+	case KVM_CAP_ARM_EL1_32BIT:
+		r = cpus_have_const_cap(ARM64_HAS_32BIT_EL1);
+		break;
+	case KVM_CAP_GUEST_DEBUG_HW_BPS:
+		r = get_num_brps();
+		break;
+	case KVM_CAP_GUEST_DEBUG_HW_WPS:
+		r = get_num_wrps();
+		break;
+	case KVM_CAP_ARM_PMU_V3:
+		r = kvm_arm_support_pmu_v3();
+		break;
+	case KVM_CAP_ARM_INJECT_SERROR_ESR:
+		r = cpus_have_const_cap(ARM64_HAS_RAS_EXTN);
+		break;
+	case KVM_CAP_ARM_VM_IPA_SIZE:
+		r = get_kvm_ipa_limit();
 		break;
+	case KVM_CAP_ARM_SVE:
+		r = system_supports_sve();
+		break;
+	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
+	case KVM_CAP_ARM_PTRAUTH_GENERIC:
+		r = system_has_full_ptr_auth();
+		break;
+	default:
+		r = 0;
 	}
+
 	return r;
 }
 
@@ -547,11 +580,9 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 		 * Map the VGIC hardware resources before running a vcpu the
 		 * first time on this VM.
 		 */
-		if (unlikely(!vgic_ready(kvm))) {
-			ret = kvm_vgic_map_resources(kvm);
-			if (ret)
-				return ret;
-		}
+		ret = kvm_vgic_map_resources(kvm);
+		if (ret)
+			return ret;
 	} else {
 		/*
 		 * Tell the rest of the code that there are userspace irqchip
@@ -1311,47 +1342,52 @@ static unsigned long nvhe_percpu_order(void)
 	return size ? get_order(size) : 0;
 }
 
-static int kvm_map_vectors(void)
+/* A lookup table holding the hypervisor VA for each vector slot */
+static void *hyp_spectre_vector_selector[BP_HARDEN_EL2_SLOTS];
+
+static int __kvm_vector_slot2idx(enum arm64_hyp_spectre_vector slot)
 {
-	/*
-	 * SV2  = ARM64_SPECTRE_V2
-	 * HEL2 = ARM64_HARDEN_EL2_VECTORS
-	 *
-	 * !SV2 + !HEL2 -> use direct vectors
-	 *  SV2 + !HEL2 -> use hardened vectors in place
-	 * !SV2 +  HEL2 -> allocate one vector slot and use exec mapping
-	 *  SV2 +  HEL2 -> use hardened vectors and use exec mapping
-	 */
-	if (cpus_have_const_cap(ARM64_SPECTRE_V2)) {
-		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs);
-		__kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base);
-	}
+	return slot - (slot != HYP_VECTOR_DIRECT);
+}
 
-	if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) {
-		phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs);
-		unsigned long size = __BP_HARDEN_HYP_VECS_SZ;
+static void kvm_init_vector_slot(void *base, enum arm64_hyp_spectre_vector slot)
+{
+	int idx = __kvm_vector_slot2idx(slot);
 
-		/*
-		 * Always allocate a spare vector slot, as we don't
-		 * know yet which CPUs have a BP hardening slot that
-		 * we can reuse.
-		 */
-		__kvm_harden_el2_vector_slot = atomic_inc_return(&arm64_el2_vector_last_slot);
-		BUG_ON(__kvm_harden_el2_vector_slot >= BP_HARDEN_EL2_SLOTS);
-		return create_hyp_exec_mappings(vect_pa, size,
-						&__kvm_bp_vect_base);
+	hyp_spectre_vector_selector[slot] = base + (idx * SZ_2K);
+}
+
+static int kvm_init_vector_slots(void)
+{
+	int err;
+	void *base;
+
+	base = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
+	kvm_init_vector_slot(base, HYP_VECTOR_DIRECT);
+
+	base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs));
+	kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT);
+
+	if (!cpus_have_const_cap(ARM64_SPECTRE_V3A))
+		return 0;
+
+	if (!has_vhe()) {
+		err = create_hyp_exec_mappings(__pa_symbol(__bp_harden_hyp_vecs),
+					       __BP_HARDEN_HYP_VECS_SZ, &base);
+		if (err)
+			return err;
 	}
 
+	kvm_init_vector_slot(base, HYP_VECTOR_INDIRECT);
+	kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_INDIRECT);
 	return 0;
 }
 
 static void cpu_init_hyp_mode(void)
 {
-	phys_addr_t pgd_ptr;
-	unsigned long hyp_stack_ptr;
-	unsigned long vector_ptr;
-	unsigned long tpidr_el2;
+	struct kvm_nvhe_init_params *params = this_cpu_ptr_nvhe_sym(kvm_init_params);
 	struct arm_smccc_res res;
+	unsigned long tcr;
 
 	/* Switch from the HYP stub to our own HYP init vector */
 	__hyp_set_vectors(kvm_get_idmap_vector());
@@ -1361,13 +1397,38 @@ static void cpu_init_hyp_mode(void)
 	 * kernel's mapping to the linear mapping, and store it in tpidr_el2
 	 * so that we can use adr_l to access per-cpu variables in EL2.
 	 */
-	tpidr_el2 = (unsigned long)this_cpu_ptr_nvhe_sym(__per_cpu_start) -
-		    (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start));
+	params->tpidr_el2 = (unsigned long)this_cpu_ptr_nvhe_sym(__per_cpu_start) -
+			    (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start));
+
+	params->mair_el2 = read_sysreg(mair_el1);
+
+	/*
+	 * The ID map may be configured to use an extended virtual address
+	 * range. This is only the case if system RAM is out of range for the
+	 * currently configured page size and VA_BITS, in which case we will
+	 * also need the extended virtual range for the HYP ID map, or we won't
+	 * be able to enable the EL2 MMU.
+	 *
+	 * However, at EL2, there is only one TTBR register, and we can't switch
+	 * between translation tables *and* update TCR_EL2.T0SZ at the same
+	 * time. Bottom line: we need to use the extended range with *both* our
+	 * translation tables.
+	 *
+	 * So use the same T0SZ value we use for the ID map.
+	 */
+	tcr = (read_sysreg(tcr_el1) & TCR_EL2_MASK) | TCR_EL2_RES1;
+	tcr &= ~TCR_T0SZ_MASK;
+	tcr |= (idmap_t0sz & GENMASK(TCR_TxSZ_WIDTH - 1, 0)) << TCR_T0SZ_OFFSET;
+	params->tcr_el2 = tcr;
 
-	pgd_ptr = kvm_mmu_get_httbr();
-	hyp_stack_ptr = __this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE;
-	hyp_stack_ptr = kern_hyp_va(hyp_stack_ptr);
-	vector_ptr = (unsigned long)kern_hyp_va(kvm_ksym_ref(__kvm_hyp_host_vector));
+	params->stack_hyp_va = kern_hyp_va(__this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE);
+	params->pgd_pa = kvm_mmu_get_httbr();
+
+	/*
+	 * Flush the init params from the data cache because the struct will
+	 * be read while the MMU is off.
+	 */
+	kvm_flush_dcache_to_poc(params, sizeof(*params));
 
 	/*
 	 * Call initialization code, and switch to the full blown HYP code.
@@ -1376,8 +1437,7 @@ static void cpu_init_hyp_mode(void)
 	 * cpus_have_const_cap() wrapper.
 	 */
 	BUG_ON(!system_capabilities_finalized());
-	arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(__kvm_hyp_init),
-			  pgd_ptr, tpidr_el2, hyp_stack_ptr, vector_ptr, &res);
+	arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(__kvm_hyp_init), virt_to_phys(params), &res);
 	WARN_ON(res.a0 != SMCCC_RET_SUCCESS);
 
 	/*
@@ -1396,13 +1456,40 @@ static void cpu_hyp_reset(void)
 		__hyp_reset_vectors();
 }
 
+/*
+ * EL2 vectors can be mapped and rerouted in a number of ways,
+ * depending on the kernel configuration and CPU present:
+ *
+ * - If the CPU is affected by Spectre-v2, the hardening sequence is
+ *   placed in one of the vector slots, which is executed before jumping
+ *   to the real vectors.
+ *
+ * - If the CPU also has the ARM64_SPECTRE_V3A cap, the slot
+ *   containing the hardening sequence is mapped next to the idmap page,
+ *   and executed before jumping to the real vectors.
+ *
+ * - If the CPU only has the ARM64_SPECTRE_V3A cap, then an
+ *   empty slot is selected, mapped next to the idmap page, and
+ *   executed before jumping to the real vectors.
+ *
+ * Note that ARM64_SPECTRE_V3A is somewhat incompatible with
+ * VHE, as we don't have hypervisor-specific mappings. If the system
+ * is VHE and yet selects this capability, it will be ignored.
+ */
+static void cpu_set_hyp_vector(void)
+{
+	struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data);
+	void *vector = hyp_spectre_vector_selector[data->slot];
+
+	*this_cpu_ptr_hyp_sym(kvm_hyp_vector) = (unsigned long)vector;
+}
+
 static void cpu_hyp_reinit(void)
 {
 	kvm_init_host_cpu_context(&this_cpu_ptr_hyp_sym(kvm_host_data)->host_ctxt);
 
 	cpu_hyp_reset();
-
-	*this_cpu_ptr_hyp_sym(kvm_hyp_vector) = (unsigned long)kvm_get_hyp_vector();
+	cpu_set_hyp_vector();
 
 	if (is_kernel_in_hyp_mode())
 		kvm_timer_init_vhe();
@@ -1439,7 +1526,8 @@ static void _kvm_arch_hardware_disable(void *discard)
 
 void kvm_arch_hardware_disable(void)
 {
-	_kvm_arch_hardware_disable(NULL);
+	if (!is_protected_kvm_enabled())
+		_kvm_arch_hardware_disable(NULL);
 }
 
 #ifdef CONFIG_CPU_PM
@@ -1480,13 +1568,15 @@ static struct notifier_block hyp_init_cpu_pm_nb = {
 	.notifier_call = hyp_init_cpu_pm_notifier,
 };
 
-static void __init hyp_cpu_pm_init(void)
+static void hyp_cpu_pm_init(void)
 {
-	cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
+	if (!is_protected_kvm_enabled())
+		cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
 }
-static void __init hyp_cpu_pm_exit(void)
+static void hyp_cpu_pm_exit(void)
 {
-	cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb);
+	if (!is_protected_kvm_enabled())
+		cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb);
 }
 #else
 static inline void hyp_cpu_pm_init(void)
@@ -1497,6 +1587,46 @@ static inline void hyp_cpu_pm_exit(void)
 }
 #endif
 
+static void init_cpu_logical_map(void)
+{
+	unsigned int cpu;
+
+	/*
+	 * Copy the MPIDR <-> logical CPU ID mapping to hyp.
+	 * Only copy the set of online CPUs whose features have been chacked
+	 * against the finalized system capabilities. The hypervisor will not
+	 * allow any other CPUs from the `possible` set to boot.
+	 */
+	for_each_online_cpu(cpu)
+		hyp_cpu_logical_map[cpu] = cpu_logical_map(cpu);
+}
+
+#define init_psci_0_1_impl_state(config, what)	\
+	config.psci_0_1_ ## what ## _implemented = psci_ops.what
+
+static bool init_psci_relay(void)
+{
+	/*
+	 * If PSCI has not been initialized, protected KVM cannot install
+	 * itself on newly booted CPUs.
+	 */
+	if (!psci_ops.get_version) {
+		kvm_err("Cannot initialize protected mode without PSCI\n");
+		return false;
+	}
+
+	kvm_host_psci_config.version = psci_ops.get_version();
+
+	if (kvm_host_psci_config.version == PSCI_VERSION(0, 1)) {
+		kvm_host_psci_config.function_ids_0_1 = get_psci_0_1_function_ids();
+		init_psci_0_1_impl_state(kvm_host_psci_config, cpu_suspend);
+		init_psci_0_1_impl_state(kvm_host_psci_config, cpu_on);
+		init_psci_0_1_impl_state(kvm_host_psci_config, cpu_off);
+		init_psci_0_1_impl_state(kvm_host_psci_config, migrate);
+	}
+	return true;
+}
+
 static int init_common_resources(void)
 {
 	return kvm_set_ipa_limit();
@@ -1541,10 +1671,11 @@ static int init_subsystems(void)
 		goto out;
 
 	kvm_perf_init();
-	kvm_coproc_table_init();
+	kvm_sys_reg_table_init();
 
 out:
-	on_each_cpu(_kvm_arch_hardware_disable, NULL, 1);
+	if (err || !is_protected_kvm_enabled())
+		on_each_cpu(_kvm_arch_hardware_disable, NULL, 1);
 
 	return err;
 }
@@ -1618,6 +1749,14 @@ static int init_hyp_mode(void)
 		goto out_err;
 	}
 
+	err = create_hyp_mappings(kvm_ksym_ref(__hyp_data_ro_after_init_start),
+				  kvm_ksym_ref(__hyp_data_ro_after_init_end),
+				  PAGE_HYP_RO);
+	if (err) {
+		kvm_err("Cannot map .hyp.data..ro_after_init section\n");
+		goto out_err;
+	}
+
 	err = create_hyp_mappings(kvm_ksym_ref(__start_rodata),
 				  kvm_ksym_ref(__end_rodata), PAGE_HYP_RO);
 	if (err) {
@@ -1632,12 +1771,6 @@ static int init_hyp_mode(void)
 		goto out_err;
 	}
 
-	err = kvm_map_vectors();
-	if (err) {
-		kvm_err("Cannot map vectors\n");
-		goto out_err;
-	}
-
 	/*
 	 * Map the Hyp stack pages
 	 */
@@ -1667,6 +1800,13 @@ static int init_hyp_mode(void)
 		}
 	}
 
+	if (is_protected_kvm_enabled()) {
+		init_cpu_logical_map();
+
+		if (!init_psci_relay())
+			goto out_err;
+	}
+
 	return 0;
 
 out_err:
@@ -1781,14 +1921,24 @@ int kvm_arch_init(void *opaque)
 			goto out_err;
 	}
 
+	err = kvm_init_vector_slots();
+	if (err) {
+		kvm_err("Cannot initialise vector slots\n");
+		goto out_err;
+	}
+
 	err = init_subsystems();
 	if (err)
 		goto out_hyp;
 
-	if (in_hyp_mode)
+	if (is_protected_kvm_enabled()) {
+		static_branch_enable(&kvm_protected_mode_initialized);
+		kvm_info("Protected nVHE mode initialized successfully\n");
+	} else if (in_hyp_mode) {
 		kvm_info("VHE mode initialized successfully\n");
-	else
+	} else {
 		kvm_info("Hyp mode initialized successfully\n");
+	}
 
 	return 0;
 
@@ -1806,6 +1956,25 @@ void kvm_arch_exit(void)
 	kvm_perf_teardown();
 }
 
+static int __init early_kvm_mode_cfg(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	if (strcmp(arg, "protected") == 0) {
+		kvm_mode = KVM_MODE_PROTECTED;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+early_param("kvm-arm.mode", early_kvm_mode_cfg);
+
+enum kvm_mode kvm_get_mode(void)
+{
+	return kvm_mode;
+}
+
 static int arm_init(void)
 {
 	int rc = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index dfb5218137ca..9bbd30e62799 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -24,7 +24,6 @@
 #include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_emulate.h>
-#include <asm/kvm_coproc.h>
 #include <asm/sigcontext.h>
 
 #include "trace.h"
@@ -252,10 +251,32 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	memcpy(addr, valp, KVM_REG_SIZE(reg->id));
 
 	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
-		int i;
+		int i, nr_reg;
+
+		switch (*vcpu_cpsr(vcpu)) {
+		/*
+		 * Either we are dealing with user mode, and only the
+		 * first 15 registers (+ PC) must be narrowed to 32bit.
+		 * AArch32 r0-r14 conveniently map to AArch64 x0-x14.
+		 */
+		case PSR_AA32_MODE_USR:
+		case PSR_AA32_MODE_SYS:
+			nr_reg = 15;
+			break;
+
+		/*
+		 * Otherwide, this is a priviledged mode, and *all* the
+		 * registers must be narrowed to 32bit.
+		 */
+		default:
+			nr_reg = 31;
+			break;
+		}
+
+		for (i = 0; i < nr_reg; i++)
+			vcpu_set_reg(vcpu, i, (u32)vcpu_get_reg(vcpu, i));
 
-		for (i = 0; i < 16; i++)
-			*vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i);
+		*vcpu_pc(vcpu) = (u32)*vcpu_pc(vcpu);
 	}
 out:
 	return err;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 5d690d60ccad..cebe39f3b1b6 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -14,7 +14,6 @@
 #include <asm/esr.h>
 #include <asm/exception.h>
 #include <asm/kvm_asm.h>
-#include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
 #include <asm/debug-monitors.h>
@@ -61,7 +60,7 @@ static int handle_smc(struct kvm_vcpu *vcpu)
 	 * otherwise return to the same address...
 	 */
 	vcpu_set_reg(vcpu, 0, ~0UL);
-	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	kvm_incr_pc(vcpu);
 	return 1;
 }
 
@@ -100,7 +99,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
 		kvm_clear_request(KVM_REQ_UNHALT, vcpu);
 	}
 
-	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	kvm_incr_pc(vcpu);
 
 	return 1;
 }
@@ -221,7 +220,7 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu)
 	 * that fail their condition code check"
 	 */
 	if (!kvm_condition_valid(vcpu)) {
-		kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+		kvm_incr_pc(vcpu);
 		handled = 1;
 	} else {
 		exit_handle_fn exit_handler;
@@ -241,23 +240,6 @@ int handle_exit(struct kvm_vcpu *vcpu, int exception_index)
 {
 	struct kvm_run *run = vcpu->run;
 
-	if (ARM_SERROR_PENDING(exception_index)) {
-		u8 esr_ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu));
-
-		/*
-		 * HVC/SMC already have an adjusted PC, which we need
-		 * to correct in order to return to after having
-		 * injected the SError.
-		 */
-		if (esr_ec == ESR_ELx_EC_HVC32 || esr_ec == ESR_ELx_EC_HVC64 ||
-		    esr_ec == ESR_ELx_EC_SMC32 || esr_ec == ESR_ELx_EC_SMC64) {
-			u32 adj =  kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2;
-			*vcpu_pc(vcpu) -= adj;
-		}
-
-		return 1;
-	}
-
 	exception_index = ARM_EXCEPTION_CODE(exception_index);
 
 	switch (exception_index) {
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 4a81eddabcd8..687598e41b21 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -10,4 +10,4 @@ subdir-ccflags-y := -I$(incdir)				\
 		    -DDISABLE_BRANCH_PROFILING		\
 		    $(DISABLE_STACKLEAK_PLUGIN)
 
-obj-$(CONFIG_KVM) += vhe/ nvhe/ pgtable.o smccc_wa.o
+obj-$(CONFIG_KVM) += vhe/ nvhe/ pgtable.o
diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c
index ae56d8a4b382..f98cbe2626a1 100644
--- a/arch/arm64/kvm/hyp/aarch32.c
+++ b/arch/arm64/kvm/hyp/aarch32.c
@@ -123,13 +123,13 @@ static void kvm_adjust_itstate(struct kvm_vcpu *vcpu)
  * kvm_skip_instr - skip a trapped instruction and proceed to the next
  * @vcpu: The vcpu pointer
  */
-void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
+void kvm_skip_instr32(struct kvm_vcpu *vcpu)
 {
 	u32 pc = *vcpu_pc(vcpu);
 	bool is_thumb;
 
 	is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT);
-	if (is_thumb && !is_wide_instr)
+	if (is_thumb && !kvm_vcpu_trap_il_is32bit(vcpu))
 		pc += 2;
 	else
 		pc += 4;
diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
new file mode 100644
index 000000000000..73629094f903
--- /dev/null
+++ b/arch/arm64/kvm/hyp/exception.c
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Fault injection for both 32 and 64bit guests.
+ *
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Based on arch/arm/kvm/emulate.c
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ */
+
+#include <hyp/adjust_pc.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+
+#if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__)
+#error Hypervisor code only!
+#endif
+
+static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
+{
+	u64 val;
+
+	if (__vcpu_read_sys_reg_from_cpu(reg, &val))
+		return val;
+
+	return __vcpu_sys_reg(vcpu, reg);
+}
+
+static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
+{
+	if (__vcpu_write_sys_reg_to_cpu(val, reg))
+		return;
+
+	 __vcpu_sys_reg(vcpu, reg) = val;
+}
+
+static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, u64 val)
+{
+	write_sysreg_el1(val, SYS_SPSR);
+}
+
+static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val)
+{
+	if (has_vhe())
+		write_sysreg(val, spsr_abt);
+	else
+		vcpu->arch.ctxt.spsr_abt = val;
+}
+
+static void __vcpu_write_spsr_und(struct kvm_vcpu *vcpu, u64 val)
+{
+	if (has_vhe())
+		write_sysreg(val, spsr_und);
+	else
+		vcpu->arch.ctxt.spsr_und = val;
+}
+
+/*
+ * This performs the exception entry at a given EL (@target_mode), stashing PC
+ * and PSTATE into ELR and SPSR respectively, and compute the new PC/PSTATE.
+ * The EL passed to this function *must* be a non-secure, privileged mode with
+ * bit 0 being set (PSTATE.SP == 1).
+ *
+ * When an exception is taken, most PSTATE fields are left unchanged in the
+ * handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all
+ * of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx
+ * layouts, so we don't need to shuffle these for exceptions from AArch32 EL0.
+ *
+ * For the SPSR_ELx layout for AArch64, see ARM DDI 0487E.a page C5-429.
+ * For the SPSR_ELx layout for AArch32, see ARM DDI 0487E.a page C5-426.
+ *
+ * Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from
+ * MSB to LSB.
+ */
+static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
+			      enum exception_type type)
+{
+	unsigned long sctlr, vbar, old, new, mode;
+	u64 exc_offset;
+
+	mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+	if      (mode == target_mode)
+		exc_offset = CURRENT_EL_SP_ELx_VECTOR;
+	else if ((mode | PSR_MODE_THREAD_BIT) == target_mode)
+		exc_offset = CURRENT_EL_SP_EL0_VECTOR;
+	else if (!(mode & PSR_MODE32_BIT))
+		exc_offset = LOWER_EL_AArch64_VECTOR;
+	else
+		exc_offset = LOWER_EL_AArch32_VECTOR;
+
+	switch (target_mode) {
+	case PSR_MODE_EL1h:
+		vbar = __vcpu_read_sys_reg(vcpu, VBAR_EL1);
+		sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1);
+		__vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1);
+		break;
+	default:
+		/* Don't do that */
+		BUG();
+	}
+
+	*vcpu_pc(vcpu) = vbar + exc_offset + type;
+
+	old = *vcpu_cpsr(vcpu);
+	new = 0;
+
+	new |= (old & PSR_N_BIT);
+	new |= (old & PSR_Z_BIT);
+	new |= (old & PSR_C_BIT);
+	new |= (old & PSR_V_BIT);
+
+	// TODO: TCO (if/when ARMv8.5-MemTag is exposed to guests)
+
+	new |= (old & PSR_DIT_BIT);
+
+	// PSTATE.UAO is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D5-2579.
+
+	// PSTATE.PAN is unchanged unless SCTLR_ELx.SPAN == 0b0
+	// SCTLR_ELx.SPAN is RES1 when ARMv8.1-PAN is not implemented
+	// See ARM DDI 0487E.a, page D5-2578.
+	new |= (old & PSR_PAN_BIT);
+	if (!(sctlr & SCTLR_EL1_SPAN))
+		new |= PSR_PAN_BIT;
+
+	// PSTATE.SS is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D2-2452.
+
+	// PSTATE.IL is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D1-2306.
+
+	// PSTATE.SSBS is set to SCTLR_ELx.DSSBS upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D13-3258
+	if (sctlr & SCTLR_ELx_DSSBS)
+		new |= PSR_SSBS_BIT;
+
+	// PSTATE.BTYPE is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, pages D1-2293 to D1-2294.
+
+	new |= PSR_D_BIT;
+	new |= PSR_A_BIT;
+	new |= PSR_I_BIT;
+	new |= PSR_F_BIT;
+
+	new |= target_mode;
+
+	*vcpu_cpsr(vcpu) = new;
+	__vcpu_write_spsr(vcpu, old);
+}
+
+/*
+ * When an exception is taken, most CPSR fields are left unchanged in the
+ * handler. However, some are explicitly overridden (e.g. M[4:0]).
+ *
+ * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with
+ * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was
+ * obsoleted by the ARMv7 virtualization extensions and is RES0.
+ *
+ * For the SPSR layout seen from AArch32, see:
+ * - ARM DDI 0406C.d, page B1-1148
+ * - ARM DDI 0487E.a, page G8-6264
+ *
+ * For the SPSR_ELx layout for AArch32 seen from AArch64, see:
+ * - ARM DDI 0487E.a, page C5-426
+ *
+ * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from
+ * MSB to LSB.
+ */
+static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode)
+{
+	u32 sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1);
+	unsigned long old, new;
+
+	old = *vcpu_cpsr(vcpu);
+	new = 0;
+
+	new |= (old & PSR_AA32_N_BIT);
+	new |= (old & PSR_AA32_Z_BIT);
+	new |= (old & PSR_AA32_C_BIT);
+	new |= (old & PSR_AA32_V_BIT);
+	new |= (old & PSR_AA32_Q_BIT);
+
+	// CPSR.IT[7:0] are set to zero upon any exception
+	// See ARM DDI 0487E.a, section G1.12.3
+	// See ARM DDI 0406C.d, section B1.8.3
+
+	new |= (old & PSR_AA32_DIT_BIT);
+
+	// CPSR.SSBS is set to SCTLR.DSSBS upon any exception
+	// See ARM DDI 0487E.a, page G8-6244
+	if (sctlr & BIT(31))
+		new |= PSR_AA32_SSBS_BIT;
+
+	// CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0
+	// SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented
+	// See ARM DDI 0487E.a, page G8-6246
+	new |= (old & PSR_AA32_PAN_BIT);
+	if (!(sctlr & BIT(23)))
+		new |= PSR_AA32_PAN_BIT;
+
+	// SS does not exist in AArch32, so ignore
+
+	// CPSR.IL is set to zero upon any exception
+	// See ARM DDI 0487E.a, page G1-5527
+
+	new |= (old & PSR_AA32_GE_MASK);
+
+	// CPSR.IT[7:0] are set to zero upon any exception
+	// See prior comment above
+
+	// CPSR.E is set to SCTLR.EE upon any exception
+	// See ARM DDI 0487E.a, page G8-6245
+	// See ARM DDI 0406C.d, page B4-1701
+	if (sctlr & BIT(25))
+		new |= PSR_AA32_E_BIT;
+
+	// CPSR.A is unchanged upon an exception to Undefined, Supervisor
+	// CPSR.A is set upon an exception to other modes
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= (old & PSR_AA32_A_BIT);
+	if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC)
+		new |= PSR_AA32_A_BIT;
+
+	// CPSR.I is set upon any exception
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= PSR_AA32_I_BIT;
+
+	// CPSR.F is set upon an exception to FIQ
+	// CPSR.F is unchanged upon an exception to other modes
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= (old & PSR_AA32_F_BIT);
+	if (mode == PSR_AA32_MODE_FIQ)
+		new |= PSR_AA32_F_BIT;
+
+	// CPSR.T is set to SCTLR.TE upon any exception
+	// See ARM DDI 0487E.a, page G8-5514
+	// See ARM DDI 0406C.d, page B1-1181
+	if (sctlr & BIT(30))
+		new |= PSR_AA32_T_BIT;
+
+	new |= mode;
+
+	return new;
+}
+
+/*
+ * Table taken from ARMv8 ARM DDI0487B-B, table G1-10.
+ */
+static const u8 return_offsets[8][2] = {
+	[0] = { 0, 0 },		/* Reset, unused */
+	[1] = { 4, 2 },		/* Undefined */
+	[2] = { 0, 0 },		/* SVC, unused */
+	[3] = { 4, 4 },		/* Prefetch abort */
+	[4] = { 8, 8 },		/* Data abort */
+	[5] = { 0, 0 },		/* HVC, unused */
+	[6] = { 4, 4 },		/* IRQ, unused */
+	[7] = { 4, 4 },		/* FIQ, unused */
+};
+
+static void enter_exception32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
+{
+	unsigned long spsr = *vcpu_cpsr(vcpu);
+	bool is_thumb = (spsr & PSR_AA32_T_BIT);
+	u32 sctlr = __vcpu_read_sys_reg(vcpu, SCTLR_EL1);
+	u32 return_address;
+
+	*vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode);
+	return_address   = *vcpu_pc(vcpu);
+	return_address  += return_offsets[vect_offset >> 2][is_thumb];
+
+	/* KVM only enters the ABT and UND modes, so only deal with those */
+	switch(mode) {
+	case PSR_AA32_MODE_ABT:
+		__vcpu_write_spsr_abt(vcpu, host_spsr_to_spsr32(spsr));
+		vcpu_gp_regs(vcpu)->compat_lr_abt = return_address;
+		break;
+
+	case PSR_AA32_MODE_UND:
+		__vcpu_write_spsr_und(vcpu, host_spsr_to_spsr32(spsr));
+		vcpu_gp_regs(vcpu)->compat_lr_und = return_address;
+		break;
+	}
+
+	/* Branch to exception vector */
+	if (sctlr & (1 << 13))
+		vect_offset += 0xffff0000;
+	else /* always have security exceptions */
+		vect_offset += __vcpu_read_sys_reg(vcpu, VBAR_EL1);
+
+	*vcpu_pc(vcpu) = vect_offset;
+}
+
+void kvm_inject_exception(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_el1_is_32bit(vcpu)) {
+		switch (vcpu->arch.flags & KVM_ARM64_EXCEPT_MASK) {
+		case KVM_ARM64_EXCEPT_AA32_UND:
+			enter_exception32(vcpu, PSR_AA32_MODE_UND, 4);
+			break;
+		case KVM_ARM64_EXCEPT_AA32_IABT:
+			enter_exception32(vcpu, PSR_AA32_MODE_ABT, 12);
+			break;
+		case KVM_ARM64_EXCEPT_AA32_DABT:
+			enter_exception32(vcpu, PSR_AA32_MODE_ABT, 16);
+			break;
+		default:
+			/* Err... */
+			break;
+		}
+	} else {
+		switch (vcpu->arch.flags & KVM_ARM64_EXCEPT_MASK) {
+		case (KVM_ARM64_EXCEPT_AA64_ELx_SYNC |
+		      KVM_ARM64_EXCEPT_AA64_EL1):
+			enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync);
+			break;
+		default:
+			/*
+			 * Only EL1_SYNC makes sense so far, EL2_{SYNC,IRQ}
+			 * will be implemented at some point. Everything
+			 * else gets silently ignored.
+			 */
+			break;
+		}
+	}
+}
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 0a5b36eb54b3..d179056e1af8 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -13,6 +13,7 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
 #include <asm/mmu.h>
+#include <asm/spectre.h>
 
 .macro save_caller_saved_regs_vect
 	/* x0 and x1 were saved in the vector entry */
@@ -187,52 +188,60 @@ SYM_CODE_START(__kvm_hyp_vector)
 	valid_vect	el1_error		// Error 32-bit EL1
 SYM_CODE_END(__kvm_hyp_vector)
 
-.macro hyp_ventry
-	.align 7
+.macro spectrev2_smccc_wa1_smc
+	sub	sp, sp, #(8 * 4)
+	stp	x2, x3, [sp, #(8 * 0)]
+	stp	x0, x1, [sp, #(8 * 2)]
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
+	smc	#0
+	ldp	x2, x3, [sp, #(8 * 0)]
+	add	sp, sp, #(8 * 2)
+.endm
+
+.macro hyp_ventry	indirect, spectrev2
+	.align	7
 1:	esb
-	.rept 26
-	nop
-	.endr
-/*
- * The default sequence is to directly branch to the KVM vectors,
- * using the computed offset. This applies for VHE as well as
- * !ARM64_HARDEN_EL2_VECTORS. The first vector must always run the preamble.
- *
- * For ARM64_HARDEN_EL2_VECTORS configurations, this gets replaced
- * with:
- *
- * stp	x0, x1, [sp, #-16]!
- * movz	x0, #(addr & 0xffff)
- * movk	x0, #((addr >> 16) & 0xffff), lsl #16
- * movk	x0, #((addr >> 32) & 0xffff), lsl #32
- * br	x0
- *
- * Where:
- * addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + KVM_VECTOR_PREAMBLE.
- * See kvm_patch_vector_branch for details.
- */
-alternative_cb	kvm_patch_vector_branch
+	.if \spectrev2 != 0
+	spectrev2_smccc_wa1_smc
+	.else
 	stp	x0, x1, [sp, #-16]!
-	b	__kvm_hyp_vector + (1b - 0b + KVM_VECTOR_PREAMBLE)
+	.endif
+	.if \indirect != 0
+	alternative_cb  kvm_patch_vector_branch
+	/*
+	 * For ARM64_SPECTRE_V3A configurations, these NOPs get replaced with:
+	 *
+	 * movz	x0, #(addr & 0xffff)
+	 * movk	x0, #((addr >> 16) & 0xffff), lsl #16
+	 * movk	x0, #((addr >> 32) & 0xffff), lsl #32
+	 * br	x0
+	 *
+	 * Where:
+	 * addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + KVM_VECTOR_PREAMBLE.
+	 * See kvm_patch_vector_branch for details.
+	 */
 	nop
 	nop
 	nop
-alternative_cb_end
+	nop
+	alternative_cb_end
+	.endif
+	b	__kvm_hyp_vector + (1b - 0b + KVM_VECTOR_PREAMBLE)
 .endm
 
-.macro generate_vectors
+.macro generate_vectors	indirect, spectrev2
 0:
 	.rept 16
-	hyp_ventry
+	hyp_ventry	\indirect, \spectrev2
 	.endr
 	.org 0b + SZ_2K		// Safety measure
 .endm
 
 	.align	11
 SYM_CODE_START(__bp_harden_hyp_vecs)
-	.rept BP_HARDEN_EL2_SLOTS
-	generate_vectors
-	.endr
+	generate_vectors indirect = 0, spectrev2 = 1 // HYP_VECTOR_SPECTRE_DIRECT
+	generate_vectors indirect = 1, spectrev2 = 0 // HYP_VECTOR_INDIRECT
+	generate_vectors indirect = 1, spectrev2 = 1 // HYP_VECTOR_SPECTRE_INDIRECT
 1:	.org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ
 	.org 1b
 SYM_CODE_END(__bp_harden_hyp_vecs)
diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
new file mode 100644
index 000000000000..61716359035d
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Guest PC manipulation helpers
+ *
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Copyright (C) 2020 - Google LLC
+ * Author: Marc Zyngier <maz@kernel.org>
+ */
+
+#ifndef __ARM64_KVM_HYP_ADJUST_PC_H__
+#define __ARM64_KVM_HYP_ADJUST_PC_H__
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_host.h>
+
+void kvm_inject_exception(struct kvm_vcpu *vcpu);
+
+static inline void kvm_skip_instr(struct kvm_vcpu *vcpu)
+{
+	if (vcpu_mode_is_32bit(vcpu)) {
+		kvm_skip_instr32(vcpu);
+	} else {
+		*vcpu_pc(vcpu) += 4;
+		*vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK;
+	}
+
+	/* advance the singlestep state machine */
+	*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
+}
+
+/*
+ * Skip an instruction which has been emulated at hyp while most guest sysregs
+ * are live.
+ */
+static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu)
+{
+	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
+	vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR);
+
+	kvm_skip_instr(vcpu);
+
+	write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR);
+	write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
+}
+
+/*
+ * Adjust the guest PC on entry, depending on flags provided by EL1
+ * for the purpose of emulation (MMIO, sysreg) or exception injection.
+ */
+static inline void __adjust_pc(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) {
+		kvm_inject_exception(vcpu);
+		vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION |
+				      KVM_ARM64_EXCEPT_MASK);
+	} else 	if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) {
+		kvm_skip_instr(vcpu);
+		vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC;
+	}
+}
+
+/*
+ * Skip an instruction while host sysregs are live.
+ * Assumes host is always 64-bit.
+ */
+static inline void kvm_skip_host_instr(void)
+{
+	write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR);
+}
+
+#endif
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 1f875a8f20c4..84473574c2e7 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -7,6 +7,8 @@
 #ifndef __ARM64_KVM_HYP_SWITCH_H__
 #define __ARM64_KVM_HYP_SWITCH_H__
 
+#include <hyp/adjust_pc.h>
+
 #include <linux/arm-smccc.h>
 #include <linux/kvm_host.h>
 #include <linux/types.h>
@@ -409,6 +411,21 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
 
+	if (ARM_SERROR_PENDING(*exit_code)) {
+		u8 esr_ec = kvm_vcpu_trap_get_class(vcpu);
+
+		/*
+		 * HVC already have an adjusted PC, which we need to
+		 * correct in order to return to after having injected
+		 * the SError.
+		 *
+		 * SMC, on the other hand, is *trapped*, meaning its
+		 * preferred return address is the SMC itself.
+		 */
+		if (esr_ec == ESR_ELx_EC_HVC32 || esr_ec == ESR_ELx_EC_HVC64)
+			write_sysreg_el2(read_sysreg_el2(SYS_ELR) - 4, SYS_ELR);
+	}
+
 	/*
 	 * We're using the raw exception code in order to only process
 	 * the trap if no SError is pending. We will come back to the
diff --git a/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h b/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h
new file mode 100644
index 000000000000..1e6d995968a1
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Trap handler helpers.
+ *
+ * Copyright (C) 2020 - Google LLC
+ * Author: Marc Zyngier <maz@kernel.org>
+ */
+
+#ifndef __ARM64_KVM_NVHE_TRAP_HANDLER_H__
+#define __ARM64_KVM_NVHE_TRAP_HANDLER_H__
+
+#include <asm/kvm_host.h>
+
+#define cpu_reg(ctxt, r)	(ctxt)->regs.regs[r]
+#define DECLARE_REG(type, name, ctxt, reg)	\
+				type name = (type)cpu_reg(ctxt, (reg))
+
+#endif /* __ARM64_KVM_NVHE_TRAP_HANDLER_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index ddde15fe85f2..1f1e351c5fe2 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -6,9 +6,10 @@
 asflags-y := -D__KVM_NVHE_HYPERVISOR__
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__
 
-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o hyp-main.o
+obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \
+	 hyp-main.o hyp-smp.o psci-relay.o
 obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
-	 ../fpsimd.o ../hyp-entry.o
+	 ../fpsimd.o ../hyp-entry.o ../exception.o
 
 ##
 ## Build rules for compiling nVHE hyp code
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index ed27f06a31ba..a820dfdc9c25 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -13,8 +13,6 @@
 	.text
 
 SYM_FUNC_START(__host_exit)
-	stp	x0, x1, [sp, #-16]!
-
 	get_host_ctxt	x0, x1
 
 	/* Store the host regs x2 and x3 */
@@ -41,6 +39,7 @@ SYM_FUNC_START(__host_exit)
 	bl	handle_trap
 
 	/* Restore host regs x0-x17 */
+__host_enter_restore_full:
 	ldp	x0, x1,   [x29, #CPU_XREG_OFFSET(0)]
 	ldp	x2, x3,   [x29, #CPU_XREG_OFFSET(2)]
 	ldp	x4, x5,   [x29, #CPU_XREG_OFFSET(4)]
@@ -64,6 +63,14 @@ __host_enter_without_restoring:
 SYM_FUNC_END(__host_exit)
 
 /*
+ * void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt);
+ */
+SYM_FUNC_START(__host_enter)
+	mov	x29, x0
+	b	__host_enter_restore_full
+SYM_FUNC_END(__host_enter)
+
+/*
  * void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
  */
 SYM_FUNC_START(__hyp_do_panic)
@@ -99,13 +106,15 @@ SYM_FUNC_END(__hyp_do_panic)
 	mrs	x0, esr_el2
 	lsr	x0, x0, #ESR_ELx_EC_SHIFT
 	cmp	x0, #ESR_ELx_EC_HVC64
-	ldp	x0, x1, [sp], #16
 	b.ne	__host_exit
 
+	ldp	x0, x1, [sp]		// Don't fixup the stack yet
+
 	/* Check for a stub HVC call */
 	cmp	x0, #HVC_STUB_HCALL_NR
 	b.hs	__host_exit
 
+	add	sp, sp, #16
 	/*
 	 * Compute the idmap address of __kvm_handle_stub_hvc and
 	 * jump there. Since we use kimage_voffset, do not use the
@@ -115,10 +124,7 @@ SYM_FUNC_END(__hyp_do_panic)
 	 * Preserve x0-x4, which may contain stub parameters.
 	 */
 	ldr	x5, =__kvm_handle_stub_hvc
-	ldr_l	x6, kimage_voffset
-
-	/* x5 = __pa(x5) */
-	sub	x5, x5, x6
+	kimg_pa x5, x6
 	br	x5
 .L__vect_end\@:
 .if ((.L__vect_end\@ - .L__vect_start\@) > 0x80)
@@ -183,3 +189,41 @@ SYM_CODE_START(__kvm_hyp_host_vector)
 	invalid_host_el1_vect			// FIQ 32-bit EL1
 	invalid_host_el1_vect			// Error 32-bit EL1
 SYM_CODE_END(__kvm_hyp_host_vector)
+
+/*
+ * Forward SMC with arguments in struct kvm_cpu_context, and
+ * store the result into the same struct. Assumes SMCCC 1.2 or older.
+ *
+ * x0: struct kvm_cpu_context*
+ */
+SYM_CODE_START(__kvm_hyp_host_forward_smc)
+	/*
+	 * Use x18 to keep the pointer to the host context because
+	 * x18 is callee-saved in SMCCC but not in AAPCS64.
+	 */
+	mov	x18, x0
+
+	ldp	x0, x1,   [x18, #CPU_XREG_OFFSET(0)]
+	ldp	x2, x3,   [x18, #CPU_XREG_OFFSET(2)]
+	ldp	x4, x5,   [x18, #CPU_XREG_OFFSET(4)]
+	ldp	x6, x7,   [x18, #CPU_XREG_OFFSET(6)]
+	ldp	x8, x9,   [x18, #CPU_XREG_OFFSET(8)]
+	ldp	x10, x11, [x18, #CPU_XREG_OFFSET(10)]
+	ldp	x12, x13, [x18, #CPU_XREG_OFFSET(12)]
+	ldp	x14, x15, [x18, #CPU_XREG_OFFSET(14)]
+	ldp	x16, x17, [x18, #CPU_XREG_OFFSET(16)]
+
+	smc	#0
+
+	stp	x0, x1,   [x18, #CPU_XREG_OFFSET(0)]
+	stp	x2, x3,   [x18, #CPU_XREG_OFFSET(2)]
+	stp	x4, x5,   [x18, #CPU_XREG_OFFSET(4)]
+	stp	x6, x7,   [x18, #CPU_XREG_OFFSET(6)]
+	stp	x8, x9,   [x18, #CPU_XREG_OFFSET(8)]
+	stp	x10, x11, [x18, #CPU_XREG_OFFSET(10)]
+	stp	x12, x13, [x18, #CPU_XREG_OFFSET(12)]
+	stp	x14, x15, [x18, #CPU_XREG_OFFSET(14)]
+	stp	x16, x17, [x18, #CPU_XREG_OFFSET(16)]
+
+	ret
+SYM_CODE_END(__kvm_hyp_host_forward_smc)
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index b11a9d7db677..31b060a44045 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -9,6 +9,7 @@
 
 #include <asm/alternative.h>
 #include <asm/assembler.h>
+#include <asm/el2_setup.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmu.h>
@@ -47,10 +48,7 @@ __invalid:
 
 	/*
 	 * x0: SMCCC function ID
-	 * x1: HYP pgd
-	 * x2: per-CPU offset
-	 * x3: HYP stack
-	 * x4: HYP vectors
+	 * x1: struct kvm_nvhe_init_params PA
 	 */
 __do_hyp_init:
 	/* Check for a stub HVC call */
@@ -71,48 +69,53 @@ __do_hyp_init:
 	mov	x0, #SMCCC_RET_NOT_SUPPORTED
 	eret
 
-1:
-	/* Set tpidr_el2 for use by HYP to free a register */
-	msr	tpidr_el2, x2
+1:	mov	x0, x1
+	mov	x4, lr
+	bl	___kvm_hyp_init
+	mov	lr, x4
 
-	phys_to_ttbr x0, x1
-alternative_if ARM64_HAS_CNP
-	orr	x0, x0, #TTBR_CNP_BIT
+	/* Hello, World! */
+	mov	x0, #SMCCC_RET_SUCCESS
+	eret
+SYM_CODE_END(__kvm_hyp_init)
+
+/*
+ * Initialize the hypervisor in EL2.
+ *
+ * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers
+ * and leave x4 for the caller.
+ *
+ * x0: struct kvm_nvhe_init_params PA
+ */
+SYM_CODE_START_LOCAL(___kvm_hyp_init)
+alternative_if ARM64_KVM_PROTECTED_MODE
+	mov_q	x1, HCR_HOST_NVHE_PROTECTED_FLAGS
+	msr	hcr_el2, x1
 alternative_else_nop_endif
-	msr	ttbr0_el2, x0
 
-	mrs	x0, tcr_el1
-	mov_q	x1, TCR_EL2_MASK
-	and	x0, x0, x1
-	mov	x1, #TCR_EL2_RES1
-	orr	x0, x0, x1
+	ldr	x1, [x0, #NVHE_INIT_TPIDR_EL2]
+	msr	tpidr_el2, x1
 
-	/*
-	 * The ID map may be configured to use an extended virtual address
-	 * range. This is only the case if system RAM is out of range for the
-	 * currently configured page size and VA_BITS, in which case we will
-	 * also need the extended virtual range for the HYP ID map, or we won't
-	 * be able to enable the EL2 MMU.
-	 *
-	 * However, at EL2, there is only one TTBR register, and we can't switch
-	 * between translation tables *and* update TCR_EL2.T0SZ at the same
-	 * time. Bottom line: we need to use the extended range with *both* our
-	 * translation tables.
-	 *
-	 * So use the same T0SZ value we use for the ID map.
-	 */
-	ldr_l	x1, idmap_t0sz
-	bfi	x0, x1, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+	ldr	x1, [x0, #NVHE_INIT_STACK_HYP_VA]
+	mov	sp, x1
+
+	ldr	x1, [x0, #NVHE_INIT_MAIR_EL2]
+	msr	mair_el2, x1
+
+	ldr	x1, [x0, #NVHE_INIT_PGD_PA]
+	phys_to_ttbr x2, x1
+alternative_if ARM64_HAS_CNP
+	orr	x2, x2, #TTBR_CNP_BIT
+alternative_else_nop_endif
+	msr	ttbr0_el2, x2
 
 	/*
 	 * Set the PS bits in TCR_EL2.
 	 */
-	tcr_compute_pa_size x0, #TCR_EL2_PS_SHIFT, x1, x2
+	ldr	x1, [x0, #NVHE_INIT_TCR_EL2]
+	tcr_compute_pa_size x1, #TCR_EL2_PS_SHIFT, x2, x3
+	msr	tcr_el2, x1
 
-	msr	tcr_el2, x0
-
-	mrs	x0, mair_el1
-	msr	mair_el2, x0
 	isb
 
 	/* Invalidate the stale TLBs from Bootloader */
@@ -134,14 +137,70 @@ alternative_else_nop_endif
 	msr	sctlr_el2, x0
 	isb
 
-	/* Set the stack and new vectors */
-	mov	sp, x3
-	msr	vbar_el2, x4
+	/* Set the host vector */
+	ldr	x0, =__kvm_hyp_host_vector
+	kimg_hyp_va x0, x1
+	msr	vbar_el2, x0
 
-	/* Hello, World! */
-	mov	x0, #SMCCC_RET_SUCCESS
-	eret
-SYM_CODE_END(__kvm_hyp_init)
+	ret
+SYM_CODE_END(___kvm_hyp_init)
+
+/*
+ * PSCI CPU_ON entry point
+ *
+ * x0: struct kvm_nvhe_init_params PA
+ */
+SYM_CODE_START(kvm_hyp_cpu_entry)
+	mov	x1, #1				// is_cpu_on = true
+	b	__kvm_hyp_init_cpu
+SYM_CODE_END(kvm_hyp_cpu_entry)
+
+/*
+ * PSCI CPU_SUSPEND / SYSTEM_SUSPEND entry point
+ *
+ * x0: struct kvm_nvhe_init_params PA
+ */
+SYM_CODE_START(kvm_hyp_cpu_resume)
+	mov	x1, #0				// is_cpu_on = false
+	b	__kvm_hyp_init_cpu
+SYM_CODE_END(kvm_hyp_cpu_resume)
+
+/*
+ * Common code for CPU entry points. Initializes EL2 state and
+ * installs the hypervisor before handing over to a C handler.
+ *
+ * x0: struct kvm_nvhe_init_params PA
+ * x1: bool is_cpu_on
+ */
+SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
+	mov	x28, x0				// Stash arguments
+	mov	x29, x1
+
+	/* Check that the core was booted in EL2. */
+	mrs	x0, CurrentEL
+	cmp	x0, #CurrentEL_EL2
+	b.eq	2f
+
+	/* The core booted in EL1. KVM cannot be initialized on it. */
+1:	wfe
+	wfi
+	b	1b
+
+2:	msr	SPsel, #1			// We want to use SP_EL{1,2}
+
+	/* Initialize EL2 CPU state to sane values. */
+	init_el2_state nvhe			// Clobbers x0..x2
+
+	/* Enable MMU, set vectors and stack. */
+	mov	x0, x28
+	bl	___kvm_hyp_init			// Clobbers x0..x3
+
+	/* Leave idmap. */
+	mov	x0, x29
+	ldr	x1, =kvm_host_psci_cpu_entry
+	kimg_hyp_va x1, x2
+	br	x1
+SYM_CODE_END(__kvm_hyp_init_cpu)
 
 SYM_CODE_START(__kvm_handle_stub_hvc)
 	cmp	x0, #HVC_SOFT_RESTART
@@ -176,6 +235,11 @@ reset:
 	msr	sctlr_el2, x5
 	isb
 
+alternative_if ARM64_KVM_PROTECTED_MODE
+	mov_q	x5, HCR_HOST_NVHE_FLAGS
+	msr	hcr_el2, x5
+alternative_else_nop_endif
+
 	/* Install stub vectors */
 	adr_l	x5, __hyp_stub_vectors
 	msr	vbar_el2, x5
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index e2eafe2c93af..a906f9e2ff34 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -12,106 +12,175 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
 
-#include <kvm/arm_hypercalls.h>
+#include <nvhe/trap_handler.h>
 
-static void handle_host_hcall(unsigned long func_id,
-			      struct kvm_cpu_context *host_ctxt)
+DEFINE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
+
+void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt);
+
+static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 {
-	unsigned long ret = 0;
+	DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
 
-	switch (func_id) {
-	case KVM_HOST_SMCCC_FUNC(__kvm_vcpu_run): {
-		unsigned long r1 = host_ctxt->regs.regs[1];
-		struct kvm_vcpu *vcpu = (struct kvm_vcpu *)r1;
+	cpu_reg(host_ctxt, 1) =  __kvm_vcpu_run(kern_hyp_va(vcpu));
+}
 
-		ret = __kvm_vcpu_run(kern_hyp_va(vcpu));
-		break;
-	}
-	case KVM_HOST_SMCCC_FUNC(__kvm_flush_vm_context):
-		__kvm_flush_vm_context();
-		break;
-	case KVM_HOST_SMCCC_FUNC(__kvm_tlb_flush_vmid_ipa): {
-		unsigned long r1 = host_ctxt->regs.regs[1];
-		struct kvm_s2_mmu *mmu = (struct kvm_s2_mmu *)r1;
-		phys_addr_t ipa = host_ctxt->regs.regs[2];
-		int level = host_ctxt->regs.regs[3];
+static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt)
+{
+	__kvm_flush_vm_context();
+}
 
-		__kvm_tlb_flush_vmid_ipa(kern_hyp_va(mmu), ipa, level);
-		break;
-	}
-	case KVM_HOST_SMCCC_FUNC(__kvm_tlb_flush_vmid): {
-		unsigned long r1 = host_ctxt->regs.regs[1];
-		struct kvm_s2_mmu *mmu = (struct kvm_s2_mmu *)r1;
+static void handle___kvm_tlb_flush_vmid_ipa(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
+	DECLARE_REG(phys_addr_t, ipa, host_ctxt, 2);
+	DECLARE_REG(int, level, host_ctxt, 3);
 
-		__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
-		break;
-	}
-	case KVM_HOST_SMCCC_FUNC(__kvm_tlb_flush_local_vmid): {
-		unsigned long r1 = host_ctxt->regs.regs[1];
-		struct kvm_s2_mmu *mmu = (struct kvm_s2_mmu *)r1;
+	__kvm_tlb_flush_vmid_ipa(kern_hyp_va(mmu), ipa, level);
+}
 
-		__kvm_tlb_flush_local_vmid(kern_hyp_va(mmu));
-		break;
-	}
-	case KVM_HOST_SMCCC_FUNC(__kvm_timer_set_cntvoff): {
-		u64 cntvoff = host_ctxt->regs.regs[1];
+static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
 
-		__kvm_timer_set_cntvoff(cntvoff);
-		break;
-	}
-	case KVM_HOST_SMCCC_FUNC(__kvm_enable_ssbs):
-		__kvm_enable_ssbs();
-		break;
-	case KVM_HOST_SMCCC_FUNC(__vgic_v3_get_ich_vtr_el2):
-		ret = __vgic_v3_get_ich_vtr_el2();
-		break;
-	case KVM_HOST_SMCCC_FUNC(__vgic_v3_read_vmcr):
-		ret = __vgic_v3_read_vmcr();
-		break;
-	case KVM_HOST_SMCCC_FUNC(__vgic_v3_write_vmcr): {
-		u32 vmcr = host_ctxt->regs.regs[1];
+	__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
+}
 
-		__vgic_v3_write_vmcr(vmcr);
-		break;
-	}
-	case KVM_HOST_SMCCC_FUNC(__vgic_v3_init_lrs):
-		__vgic_v3_init_lrs();
-		break;
-	case KVM_HOST_SMCCC_FUNC(__kvm_get_mdcr_el2):
-		ret = __kvm_get_mdcr_el2();
-		break;
-	case KVM_HOST_SMCCC_FUNC(__vgic_v3_save_aprs): {
-		unsigned long r1 = host_ctxt->regs.regs[1];
-		struct vgic_v3_cpu_if *cpu_if = (struct vgic_v3_cpu_if *)r1;
+static void handle___kvm_tlb_flush_local_vmid(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
 
-		__vgic_v3_save_aprs(kern_hyp_va(cpu_if));
-		break;
-	}
-	case KVM_HOST_SMCCC_FUNC(__vgic_v3_restore_aprs): {
-		unsigned long r1 = host_ctxt->regs.regs[1];
-		struct vgic_v3_cpu_if *cpu_if = (struct vgic_v3_cpu_if *)r1;
+	__kvm_tlb_flush_local_vmid(kern_hyp_va(mmu));
+}
 
-		__vgic_v3_restore_aprs(kern_hyp_va(cpu_if));
-		break;
-	}
-	default:
-		/* Invalid host HVC. */
-		host_ctxt->regs.regs[0] = SMCCC_RET_NOT_SUPPORTED;
-		return;
-	}
+static void handle___kvm_timer_set_cntvoff(struct kvm_cpu_context *host_ctxt)
+{
+	__kvm_timer_set_cntvoff(cpu_reg(host_ctxt, 1));
+}
+
+static void handle___kvm_enable_ssbs(struct kvm_cpu_context *host_ctxt)
+{
+	u64 tmp;
+
+	tmp = read_sysreg_el2(SYS_SCTLR);
+	tmp |= SCTLR_ELx_DSSBS;
+	write_sysreg_el2(tmp, SYS_SCTLR);
+}
+
+static void handle___vgic_v3_get_ich_vtr_el2(struct kvm_cpu_context *host_ctxt)
+{
+	cpu_reg(host_ctxt, 1) = __vgic_v3_get_ich_vtr_el2();
+}
+
+static void handle___vgic_v3_read_vmcr(struct kvm_cpu_context *host_ctxt)
+{
+	cpu_reg(host_ctxt, 1) = __vgic_v3_read_vmcr();
+}
+
+static void handle___vgic_v3_write_vmcr(struct kvm_cpu_context *host_ctxt)
+{
+	__vgic_v3_write_vmcr(cpu_reg(host_ctxt, 1));
+}
+
+static void handle___vgic_v3_init_lrs(struct kvm_cpu_context *host_ctxt)
+{
+	__vgic_v3_init_lrs();
+}
+
+static void handle___kvm_get_mdcr_el2(struct kvm_cpu_context *host_ctxt)
+{
+	cpu_reg(host_ctxt, 1) = __kvm_get_mdcr_el2();
+}
+
+static void handle___vgic_v3_save_aprs(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);
+
+	__vgic_v3_save_aprs(kern_hyp_va(cpu_if));
+}
+
+static void handle___vgic_v3_restore_aprs(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);
+
+	__vgic_v3_restore_aprs(kern_hyp_va(cpu_if));
+}
+
+typedef void (*hcall_t)(struct kvm_cpu_context *);
+
+#define HANDLE_FUNC(x)	[__KVM_HOST_SMCCC_FUNC_##x] = kimg_fn_ptr(handle_##x)
+
+static const hcall_t *host_hcall[] = {
+	HANDLE_FUNC(__kvm_vcpu_run),
+	HANDLE_FUNC(__kvm_flush_vm_context),
+	HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
+	HANDLE_FUNC(__kvm_tlb_flush_vmid),
+	HANDLE_FUNC(__kvm_tlb_flush_local_vmid),
+	HANDLE_FUNC(__kvm_timer_set_cntvoff),
+	HANDLE_FUNC(__kvm_enable_ssbs),
+	HANDLE_FUNC(__vgic_v3_get_ich_vtr_el2),
+	HANDLE_FUNC(__vgic_v3_read_vmcr),
+	HANDLE_FUNC(__vgic_v3_write_vmcr),
+	HANDLE_FUNC(__vgic_v3_init_lrs),
+	HANDLE_FUNC(__kvm_get_mdcr_el2),
+	HANDLE_FUNC(__vgic_v3_save_aprs),
+	HANDLE_FUNC(__vgic_v3_restore_aprs),
+};
+
+static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(unsigned long, id, host_ctxt, 0);
+	const hcall_t *kfn;
+	hcall_t hfn;
+
+	id -= KVM_HOST_SMCCC_ID(0);
+
+	if (unlikely(id >= ARRAY_SIZE(host_hcall)))
+		goto inval;
+
+	kfn = host_hcall[id];
+	if (unlikely(!kfn))
+		goto inval;
 
-	host_ctxt->regs.regs[0] = SMCCC_RET_SUCCESS;
-	host_ctxt->regs.regs[1] = ret;
+	cpu_reg(host_ctxt, 0) = SMCCC_RET_SUCCESS;
+
+	hfn = kimg_fn_hyp_va(kfn);
+	hfn(host_ctxt);
+
+	return;
+inval:
+	cpu_reg(host_ctxt, 0) = SMCCC_RET_NOT_SUPPORTED;
+}
+
+static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt)
+{
+	__kvm_hyp_host_forward_smc(host_ctxt);
+}
+
+static void handle_host_smc(struct kvm_cpu_context *host_ctxt)
+{
+	bool handled;
+
+	handled = kvm_host_psci_handler(host_ctxt);
+	if (!handled)
+		default_host_smc_handler(host_ctxt);
+
+	/* SMC was trapped, move ELR past the current PC. */
+	kvm_skip_host_instr();
 }
 
 void handle_trap(struct kvm_cpu_context *host_ctxt)
 {
 	u64 esr = read_sysreg_el2(SYS_ESR);
-	unsigned long func_id;
 
-	if (ESR_ELx_EC(esr) != ESR_ELx_EC_HVC64)
+	switch (ESR_ELx_EC(esr)) {
+	case ESR_ELx_EC_HVC64:
+		handle_host_hcall(host_ctxt);
+		break;
+	case ESR_ELx_EC_SMC64:
+		handle_host_smc(host_ctxt);
+		break;
+	default:
 		hyp_panic();
-
-	func_id = host_ctxt->regs.regs[0];
-	handle_host_hcall(func_id, host_ctxt);
+	}
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c
new file mode 100644
index 000000000000..2997aa156d8e
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 - Google LLC
+ * Author: David Brazdil <dbrazdil@google.com>
+ */
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+
+/*
+ * nVHE copy of data structures tracking available CPU cores.
+ * Only entries for CPUs that were online at KVM init are populated.
+ * Other CPUs should not be allowed to boot because their features were
+ * not checked against the finalized system capabilities.
+ */
+u64 __ro_after_init hyp_cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
+
+u64 cpu_logical_map(unsigned int cpu)
+{
+	if (cpu >= ARRAY_SIZE(hyp_cpu_logical_map))
+		hyp_panic();
+
+	return hyp_cpu_logical_map[cpu];
+}
+
+unsigned long __hyp_per_cpu_offset(unsigned int cpu)
+{
+	unsigned long *cpu_base_array;
+	unsigned long this_cpu_base;
+	unsigned long elf_base;
+
+	if (cpu >= ARRAY_SIZE(kvm_arm_hyp_percpu_base))
+		hyp_panic();
+
+	cpu_base_array = (unsigned long *)hyp_symbol_addr(kvm_arm_hyp_percpu_base);
+	this_cpu_base = kern_hyp_va(cpu_base_array[cpu]);
+	elf_base = (unsigned long)hyp_symbol_addr(__per_cpu_start);
+	return this_cpu_base - elf_base;
+}
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
index a797abace13f..1206d0d754d5 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
@@ -21,4 +21,5 @@ SECTIONS {
 	HYP_SECTION_NAME(.data..percpu) : {
 		PERCPU_INPUT(L1_CACHE_BYTES)
 	}
+	HYP_SECTION(.data..ro_after_init)
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
new file mode 100644
index 000000000000..e3947846ffcb
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -0,0 +1,309 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 - Google LLC
+ * Author: David Brazdil <dbrazdil@google.com>
+ */
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <uapi/linux/psci.h>
+
+#include <nvhe/trap_handler.h>
+
+void kvm_hyp_cpu_entry(unsigned long r0);
+void kvm_hyp_cpu_resume(unsigned long r0);
+
+void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt);
+
+/* Config options set by the host. */
+struct kvm_host_psci_config __ro_after_init kvm_host_psci_config;
+s64 __ro_after_init hyp_physvirt_offset;
+
+#define __hyp_pa(x) ((phys_addr_t)((x)) + hyp_physvirt_offset)
+
+#define INVALID_CPU_ID	UINT_MAX
+
+struct psci_boot_args {
+	atomic_t lock;
+	unsigned long pc;
+	unsigned long r0;
+};
+
+#define PSCI_BOOT_ARGS_UNLOCKED		0
+#define PSCI_BOOT_ARGS_LOCKED		1
+
+#define PSCI_BOOT_ARGS_INIT					\
+	((struct psci_boot_args){				\
+		.lock = ATOMIC_INIT(PSCI_BOOT_ARGS_UNLOCKED),	\
+	})
+
+static DEFINE_PER_CPU(struct psci_boot_args, cpu_on_args) = PSCI_BOOT_ARGS_INIT;
+static DEFINE_PER_CPU(struct psci_boot_args, suspend_args) = PSCI_BOOT_ARGS_INIT;
+
+#define	is_psci_0_1(what, func_id)					\
+	(kvm_host_psci_config.psci_0_1_ ## what ## _implemented &&	\
+	 (func_id) == kvm_host_psci_config.function_ids_0_1.what)
+
+static bool is_psci_0_1_call(u64 func_id)
+{
+	return (is_psci_0_1(cpu_suspend, func_id) ||
+		is_psci_0_1(cpu_on, func_id) ||
+		is_psci_0_1(cpu_off, func_id) ||
+		is_psci_0_1(migrate, func_id));
+}
+
+static bool is_psci_0_2_call(u64 func_id)
+{
+	/* SMCCC reserves IDs 0x00-1F with the given 32/64-bit base for PSCI. */
+	return (PSCI_0_2_FN(0) <= func_id && func_id <= PSCI_0_2_FN(31)) ||
+	       (PSCI_0_2_FN64(0) <= func_id && func_id <= PSCI_0_2_FN64(31));
+}
+
+static unsigned long psci_call(unsigned long fn, unsigned long arg0,
+			       unsigned long arg1, unsigned long arg2)
+{
+	struct arm_smccc_res res;
+
+	arm_smccc_1_1_smc(fn, arg0, arg1, arg2, &res);
+	return res.a0;
+}
+
+static unsigned long psci_forward(struct kvm_cpu_context *host_ctxt)
+{
+	return psci_call(cpu_reg(host_ctxt, 0), cpu_reg(host_ctxt, 1),
+			 cpu_reg(host_ctxt, 2), cpu_reg(host_ctxt, 3));
+}
+
+static __noreturn unsigned long psci_forward_noreturn(struct kvm_cpu_context *host_ctxt)
+{
+	psci_forward(host_ctxt);
+	hyp_panic(); /* unreachable */
+}
+
+static unsigned int find_cpu_id(u64 mpidr)
+{
+	unsigned int i;
+
+	/* Reject invalid MPIDRs */
+	if (mpidr & ~MPIDR_HWID_BITMASK)
+		return INVALID_CPU_ID;
+
+	for (i = 0; i < NR_CPUS; i++) {
+		if (cpu_logical_map(i) == mpidr)
+			return i;
+	}
+
+	return INVALID_CPU_ID;
+}
+
+static __always_inline bool try_acquire_boot_args(struct psci_boot_args *args)
+{
+	return atomic_cmpxchg_acquire(&args->lock,
+				      PSCI_BOOT_ARGS_UNLOCKED,
+				      PSCI_BOOT_ARGS_LOCKED) ==
+		PSCI_BOOT_ARGS_UNLOCKED;
+}
+
+static __always_inline void release_boot_args(struct psci_boot_args *args)
+{
+	atomic_set_release(&args->lock, PSCI_BOOT_ARGS_UNLOCKED);
+}
+
+static int psci_cpu_on(u64 func_id, struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(u64, mpidr, host_ctxt, 1);
+	DECLARE_REG(unsigned long, pc, host_ctxt, 2);
+	DECLARE_REG(unsigned long, r0, host_ctxt, 3);
+
+	unsigned int cpu_id;
+	struct psci_boot_args *boot_args;
+	struct kvm_nvhe_init_params *init_params;
+	int ret;
+
+	/*
+	 * Find the logical CPU ID for the given MPIDR. The search set is
+	 * the set of CPUs that were online at the point of KVM initialization.
+	 * Booting other CPUs is rejected because their cpufeatures were not
+	 * checked against the finalized capabilities. This could be relaxed
+	 * by doing the feature checks in hyp.
+	 */
+	cpu_id = find_cpu_id(mpidr);
+	if (cpu_id == INVALID_CPU_ID)
+		return PSCI_RET_INVALID_PARAMS;
+
+	boot_args = per_cpu_ptr(hyp_symbol_addr(cpu_on_args), cpu_id);
+	init_params = per_cpu_ptr(hyp_symbol_addr(kvm_init_params), cpu_id);
+
+	/* Check if the target CPU is already being booted. */
+	if (!try_acquire_boot_args(boot_args))
+		return PSCI_RET_ALREADY_ON;
+
+	boot_args->pc = pc;
+	boot_args->r0 = r0;
+	wmb();
+
+	ret = psci_call(func_id, mpidr,
+			__hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_entry)),
+			__hyp_pa(init_params));
+
+	/* If successful, the lock will be released by the target CPU. */
+	if (ret != PSCI_RET_SUCCESS)
+		release_boot_args(boot_args);
+
+	return ret;
+}
+
+static int psci_cpu_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(u64, power_state, host_ctxt, 1);
+	DECLARE_REG(unsigned long, pc, host_ctxt, 2);
+	DECLARE_REG(unsigned long, r0, host_ctxt, 3);
+
+	struct psci_boot_args *boot_args;
+	struct kvm_nvhe_init_params *init_params;
+
+	boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args));
+	init_params = this_cpu_ptr(hyp_symbol_addr(kvm_init_params));
+
+	/*
+	 * No need to acquire a lock before writing to boot_args because a core
+	 * can only suspend itself. Racy CPU_ON calls use a separate struct.
+	 */
+	boot_args->pc = pc;
+	boot_args->r0 = r0;
+
+	/*
+	 * Will either return if shallow sleep state, or wake up into the entry
+	 * point if it is a deep sleep state.
+	 */
+	return psci_call(func_id, power_state,
+			 __hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_resume)),
+			 __hyp_pa(init_params));
+}
+
+static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(unsigned long, pc, host_ctxt, 1);
+	DECLARE_REG(unsigned long, r0, host_ctxt, 2);
+
+	struct psci_boot_args *boot_args;
+	struct kvm_nvhe_init_params *init_params;
+
+	boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args));
+	init_params = this_cpu_ptr(hyp_symbol_addr(kvm_init_params));
+
+	/*
+	 * No need to acquire a lock before writing to boot_args because a core
+	 * can only suspend itself. Racy CPU_ON calls use a separate struct.
+	 */
+	boot_args->pc = pc;
+	boot_args->r0 = r0;
+
+	/* Will only return on error. */
+	return psci_call(func_id,
+			 __hyp_pa(hyp_symbol_addr(kvm_hyp_cpu_resume)),
+			 __hyp_pa(init_params), 0);
+}
+
+asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on)
+{
+	struct psci_boot_args *boot_args;
+	struct kvm_cpu_context *host_ctxt;
+
+	host_ctxt = &this_cpu_ptr(hyp_symbol_addr(kvm_host_data))->host_ctxt;
+
+	if (is_cpu_on)
+		boot_args = this_cpu_ptr(hyp_symbol_addr(cpu_on_args));
+	else
+		boot_args = this_cpu_ptr(hyp_symbol_addr(suspend_args));
+
+	cpu_reg(host_ctxt, 0) = boot_args->r0;
+	write_sysreg_el2(boot_args->pc, SYS_ELR);
+
+	if (is_cpu_on)
+		release_boot_args(boot_args);
+
+	__host_enter(host_ctxt);
+}
+
+static unsigned long psci_0_1_handler(u64 func_id, struct kvm_cpu_context *host_ctxt)
+{
+	if (is_psci_0_1(cpu_off, func_id) || is_psci_0_1(migrate, func_id))
+		return psci_forward(host_ctxt);
+	if (is_psci_0_1(cpu_on, func_id))
+		return psci_cpu_on(func_id, host_ctxt);
+	if (is_psci_0_1(cpu_suspend, func_id))
+		return psci_cpu_suspend(func_id, host_ctxt);
+
+	return PSCI_RET_NOT_SUPPORTED;
+}
+
+static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_ctxt)
+{
+	switch (func_id) {
+	case PSCI_0_2_FN_PSCI_VERSION:
+	case PSCI_0_2_FN_CPU_OFF:
+	case PSCI_0_2_FN64_AFFINITY_INFO:
+	case PSCI_0_2_FN64_MIGRATE:
+	case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
+	case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
+		return psci_forward(host_ctxt);
+	case PSCI_0_2_FN_SYSTEM_OFF:
+	case PSCI_0_2_FN_SYSTEM_RESET:
+		psci_forward_noreturn(host_ctxt);
+		unreachable();
+	case PSCI_0_2_FN64_CPU_SUSPEND:
+		return psci_cpu_suspend(func_id, host_ctxt);
+	case PSCI_0_2_FN64_CPU_ON:
+		return psci_cpu_on(func_id, host_ctxt);
+	default:
+		return PSCI_RET_NOT_SUPPORTED;
+	}
+}
+
+static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_ctxt)
+{
+	switch (func_id) {
+	case PSCI_1_0_FN_PSCI_FEATURES:
+	case PSCI_1_0_FN_SET_SUSPEND_MODE:
+	case PSCI_1_1_FN64_SYSTEM_RESET2:
+		return psci_forward(host_ctxt);
+	case PSCI_1_0_FN64_SYSTEM_SUSPEND:
+		return psci_system_suspend(func_id, host_ctxt);
+	default:
+		return psci_0_2_handler(func_id, host_ctxt);
+	}
+}
+
+bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(u64, func_id, host_ctxt, 0);
+	unsigned long ret;
+
+	switch (kvm_host_psci_config.version) {
+	case PSCI_VERSION(0, 1):
+		if (!is_psci_0_1_call(func_id))
+			return false;
+		ret = psci_0_1_handler(func_id, host_ctxt);
+		break;
+	case PSCI_VERSION(0, 2):
+		if (!is_psci_0_2_call(func_id))
+			return false;
+		ret = psci_0_2_handler(func_id, host_ctxt);
+		break;
+	default:
+		if (!is_psci_0_2_call(func_id))
+			return false;
+		ret = psci_1_0_handler(func_id, host_ctxt);
+		break;
+	}
+
+	cpu_reg(host_ctxt, 0) = ret;
+	cpu_reg(host_ctxt, 1) = 0;
+	cpu_reg(host_ctxt, 2) = 0;
+	cpu_reg(host_ctxt, 3) = 0;
+	return true;
+}
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 8ae8160bc93a..f3d0e9eca56c 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -4,6 +4,7 @@
  * Author: Marc Zyngier <marc.zyngier@arm.com>
  */
 
+#include <hyp/adjust_pc.h>
 #include <hyp/switch.h>
 #include <hyp/sysreg-sr.h>
 
@@ -96,7 +97,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 	mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
 
 	write_sysreg(mdcr_el2, mdcr_el2);
-	write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
+	if (is_protected_kvm_enabled())
+		write_sysreg(HCR_HOST_NVHE_PROTECTED_FLAGS, hcr_el2);
+	else
+		write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2);
 	write_sysreg(CPTR_EL2_DEFAULT, cptr_el2);
 	write_sysreg(__kvm_hyp_host_vector, vbar_el2);
 }
@@ -189,6 +193,8 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	__sysreg_save_state_nvhe(host_ctxt);
 
+	__adjust_pc(vcpu);
+
 	/*
 	 * We must restore the 32-bit state before the sysregs, thanks
 	 * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
index 88a25fc8fcd3..29305022bc04 100644
--- a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
@@ -33,14 +33,3 @@ void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
 	__sysreg_restore_user_state(ctxt);
 	__sysreg_restore_el2_return_state(ctxt);
 }
-
-void __kvm_enable_ssbs(void)
-{
-	u64 tmp;
-
-	asm volatile(
-	"mrs	%0, sctlr_el2\n"
-	"orr	%0, %0, %1\n"
-	"msr	sctlr_el2, %0"
-	: "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS));
-}
diff --git a/arch/arm64/kvm/hyp/smccc_wa.S b/arch/arm64/kvm/hyp/smccc_wa.S
deleted file mode 100644
index b0441dbdf68b..000000000000
--- a/arch/arm64/kvm/hyp/smccc_wa.S
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2015-2018 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- */
-
-#include <linux/arm-smccc.h>
-#include <linux/linkage.h>
-
-#include <asm/kvm_asm.h>
-#include <asm/kvm_mmu.h>
-
-	/*
-	 * This is not executed directly and is instead copied into the vectors
-	 * by install_bp_hardening_cb().
-	 */
-	.data
-	.pushsection	.rodata
-	.global		__smccc_workaround_1_smc
-SYM_DATA_START(__smccc_workaround_1_smc)
-	esb
-	sub	sp, sp, #(8 * 4)
-	stp	x2, x3, [sp, #(8 * 0)]
-	stp	x0, x1, [sp, #(8 * 2)]
-	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
-	smc	#0
-	ldp	x2, x3, [sp, #(8 * 0)]
-	ldp	x0, x1, [sp, #(8 * 2)]
-	add	sp, sp, #(8 * 4)
-1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
-	.org 1b
-SYM_DATA_END(__smccc_workaround_1_smc)
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index bd1bab551d48..8f0585640241 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -4,6 +4,8 @@
  * Author: Marc Zyngier <marc.zyngier@arm.com>
  */
 
+#include <hyp/adjust_pc.h>
+
 #include <linux/compiler.h>
 #include <linux/irqchip/arm-gic.h>
 #include <linux/kvm_host.h>
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 452f4cacd674..80406f463c28 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -4,6 +4,8 @@
  * Author: Marc Zyngier <marc.zyngier@arm.com>
  */
 
+#include <hyp/adjust_pc.h>
+
 #include <linux/compiler.h>
 #include <linux/irqchip/arm-gic-v3.h>
 #include <linux/kvm_host.h>
diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 461e97c375cc..96bec0ecf9dd 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -8,4 +8,4 @@ ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
 obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o
 obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
-	 ../fpsimd.o ../hyp-entry.o
+	 ../fpsimd.o ../hyp-entry.o ../exception.o
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 62546e20b251..af8e940d0f03 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -4,6 +4,7 @@
  * Author: Marc Zyngier <marc.zyngier@arm.com>
  */
 
+#include <hyp/adjust_pc.h>
 #include <hyp/switch.h>
 
 #include <linux/arm-smccc.h>
@@ -133,6 +134,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	__load_guest_stage2(vcpu->arch.hw_mmu);
 	__activate_traps(vcpu);
 
+	__adjust_pc(vcpu);
+
 	sysreg_restore_guest_state_vhe(guest_ctxt);
 	__debug_switch_to_guest(vcpu);
 
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 34a96ab244fa..b47df73e98d7 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -14,119 +14,15 @@
 #include <asm/kvm_emulate.h>
 #include <asm/esr.h>
 
-#define CURRENT_EL_SP_EL0_VECTOR	0x0
-#define CURRENT_EL_SP_ELx_VECTOR	0x200
-#define LOWER_EL_AArch64_VECTOR		0x400
-#define LOWER_EL_AArch32_VECTOR		0x600
-
-enum exception_type {
-	except_type_sync	= 0,
-	except_type_irq		= 0x80,
-	except_type_fiq		= 0x100,
-	except_type_serror	= 0x180,
-};
-
-/*
- * This performs the exception entry at a given EL (@target_mode), stashing PC
- * and PSTATE into ELR and SPSR respectively, and compute the new PC/PSTATE.
- * The EL passed to this function *must* be a non-secure, privileged mode with
- * bit 0 being set (PSTATE.SP == 1).
- *
- * When an exception is taken, most PSTATE fields are left unchanged in the
- * handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all
- * of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx
- * layouts, so we don't need to shuffle these for exceptions from AArch32 EL0.
- *
- * For the SPSR_ELx layout for AArch64, see ARM DDI 0487E.a page C5-429.
- * For the SPSR_ELx layout for AArch32, see ARM DDI 0487E.a page C5-426.
- *
- * Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from
- * MSB to LSB.
- */
-static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
-			      enum exception_type type)
-{
-	unsigned long sctlr, vbar, old, new, mode;
-	u64 exc_offset;
-
-	mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
-
-	if      (mode == target_mode)
-		exc_offset = CURRENT_EL_SP_ELx_VECTOR;
-	else if ((mode | PSR_MODE_THREAD_BIT) == target_mode)
-		exc_offset = CURRENT_EL_SP_EL0_VECTOR;
-	else if (!(mode & PSR_MODE32_BIT))
-		exc_offset = LOWER_EL_AArch64_VECTOR;
-	else
-		exc_offset = LOWER_EL_AArch32_VECTOR;
-
-	switch (target_mode) {
-	case PSR_MODE_EL1h:
-		vbar = vcpu_read_sys_reg(vcpu, VBAR_EL1);
-		sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
-		vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1);
-		break;
-	default:
-		/* Don't do that */
-		BUG();
-	}
-
-	*vcpu_pc(vcpu) = vbar + exc_offset + type;
-
-	old = *vcpu_cpsr(vcpu);
-	new = 0;
-
-	new |= (old & PSR_N_BIT);
-	new |= (old & PSR_Z_BIT);
-	new |= (old & PSR_C_BIT);
-	new |= (old & PSR_V_BIT);
-
-	// TODO: TCO (if/when ARMv8.5-MemTag is exposed to guests)
-
-	new |= (old & PSR_DIT_BIT);
-
-	// PSTATE.UAO is set to zero upon any exception to AArch64
-	// See ARM DDI 0487E.a, page D5-2579.
-
-	// PSTATE.PAN is unchanged unless SCTLR_ELx.SPAN == 0b0
-	// SCTLR_ELx.SPAN is RES1 when ARMv8.1-PAN is not implemented
-	// See ARM DDI 0487E.a, page D5-2578.
-	new |= (old & PSR_PAN_BIT);
-	if (!(sctlr & SCTLR_EL1_SPAN))
-		new |= PSR_PAN_BIT;
-
-	// PSTATE.SS is set to zero upon any exception to AArch64
-	// See ARM DDI 0487E.a, page D2-2452.
-
-	// PSTATE.IL is set to zero upon any exception to AArch64
-	// See ARM DDI 0487E.a, page D1-2306.
-
-	// PSTATE.SSBS is set to SCTLR_ELx.DSSBS upon any exception to AArch64
-	// See ARM DDI 0487E.a, page D13-3258
-	if (sctlr & SCTLR_ELx_DSSBS)
-		new |= PSR_SSBS_BIT;
-
-	// PSTATE.BTYPE is set to zero upon any exception to AArch64
-	// See ARM DDI 0487E.a, pages D1-2293 to D1-2294.
-
-	new |= PSR_D_BIT;
-	new |= PSR_A_BIT;
-	new |= PSR_I_BIT;
-	new |= PSR_F_BIT;
-
-	new |= target_mode;
-
-	*vcpu_cpsr(vcpu) = new;
-	vcpu_write_spsr(vcpu, old);
-}
-
 static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
 	bool is_aarch32 = vcpu_mode_is_32bit(vcpu);
 	u32 esr = 0;
 
-	enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync);
+	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1		|
+			     KVM_ARM64_EXCEPT_AA64_ELx_SYNC	|
+			     KVM_ARM64_PENDING_EXCEPTION);
 
 	vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
 
@@ -156,7 +52,9 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 {
 	u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
 
-	enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync);
+	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1		|
+			     KVM_ARM64_EXCEPT_AA64_ELx_SYNC	|
+			     KVM_ARM64_PENDING_EXCEPTION);
 
 	/*
 	 * Build an unknown exception, depending on the instruction
@@ -168,6 +66,53 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	vcpu_write_sys_reg(vcpu, esr, ESR_EL1);
 }
 
+#define DFSR_FSC_EXTABT_LPAE	0x10
+#define DFSR_FSC_EXTABT_nLPAE	0x08
+#define DFSR_LPAE		BIT(9)
+#define TTBCR_EAE		BIT(31)
+
+static void inject_undef32(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA32_UND |
+			     KVM_ARM64_PENDING_EXCEPTION);
+}
+
+/*
+ * Modelled after TakeDataAbortException() and TakePrefetchAbortException
+ * pseudocode.
+ */
+static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt, u32 addr)
+{
+	u64 far;
+	u32 fsr;
+
+	/* Give the guest an IMPLEMENTATION DEFINED exception */
+	if (vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE) {
+		fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE;
+	} else {
+		/* no need to shuffle FS[4] into DFSR[10] as its 0 */
+		fsr = DFSR_FSC_EXTABT_nLPAE;
+	}
+
+	far = vcpu_read_sys_reg(vcpu, FAR_EL1);
+
+	if (is_pabt) {
+		vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA32_IABT |
+				     KVM_ARM64_PENDING_EXCEPTION);
+		far &= GENMASK(31, 0);
+		far |= (u64)addr << 32;
+		vcpu_write_sys_reg(vcpu, fsr, IFSR32_EL2);
+	} else { /* !iabt */
+		vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA32_DABT |
+				     KVM_ARM64_PENDING_EXCEPTION);
+		far &= GENMASK(63, 32);
+		far |= addr;
+		vcpu_write_sys_reg(vcpu, fsr, ESR_EL1);
+	}
+
+	vcpu_write_sys_reg(vcpu, far, FAR_EL1);
+}
+
 /**
  * kvm_inject_dabt - inject a data abort into the guest
  * @vcpu: The VCPU to receive the data abort
@@ -179,7 +124,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
 	if (vcpu_el1_is_32bit(vcpu))
-		kvm_inject_dabt32(vcpu, addr);
+		inject_abt32(vcpu, false, addr);
 	else
 		inject_abt64(vcpu, false, addr);
 }
@@ -195,7 +140,7 @@ void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
 {
 	if (vcpu_el1_is_32bit(vcpu))
-		kvm_inject_pabt32(vcpu, addr);
+		inject_abt32(vcpu, true, addr);
 	else
 		inject_abt64(vcpu, true, addr);
 }
@@ -210,7 +155,7 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
 void kvm_inject_undefined(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_el1_is_32bit(vcpu))
-		kvm_inject_undef32(vcpu);
+		inject_undef32(vcpu);
 	else
 		inject_undef64(vcpu);
 }
diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c
index 6a2826f1bf5e..3e2d8ba11a02 100644
--- a/arch/arm64/kvm/mmio.c
+++ b/arch/arm64/kvm/mmio.c
@@ -115,7 +115,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu)
 	 * The MMIO instruction is emulated and should not be re-executed
 	 * in the guest.
 	 */
-	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+	kvm_incr_pc(vcpu);
 
 	return 0;
 }
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 75814a02d189..7d2257cc5438 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1023,7 +1023,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		 * cautious, and skip the instruction.
 		 */
 		if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) {
-			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+			kvm_incr_pc(vcpu);
 			ret = 1;
 			goto out_unlock;
 		}
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 2ed5ef8f274b..4ad66a532e38 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -384,7 +384,7 @@ static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	bool overflow;
 
-	if (!kvm_arm_pmu_v3_ready(vcpu))
+	if (!kvm_vcpu_has_pmu(vcpu))
 		return;
 
 	overflow = !!kvm_pmu_overflow_status(vcpu);
@@ -825,9 +825,12 @@ bool kvm_arm_support_pmu_v3(void)
 
 int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->arch.pmu.created)
+	if (!kvm_vcpu_has_pmu(vcpu))
 		return 0;
 
+	if (!vcpu->arch.pmu.created)
+		return -EINVAL;
+
 	/*
 	 * A valid interrupt configuration for the PMU is either to have a
 	 * properly configured interrupt number and using an in-kernel
@@ -835,9 +838,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 	 */
 	if (irqchip_in_kernel(vcpu->kvm)) {
 		int irq = vcpu->arch.pmu.irq_num;
-		if (!kvm_arm_pmu_irq_initialized(vcpu))
-			return -EINVAL;
-
 		/*
 		 * If we are using an in-kernel vgic, at this point we know
 		 * the vgic will be initialized, so we can check the PMU irq
@@ -850,9 +850,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 		   return -EINVAL;
 	}
 
-	kvm_pmu_vcpu_reset(vcpu);
-	vcpu->arch.pmu.ready = true;
-
 	return 0;
 }
 
@@ -913,8 +910,7 @@ static bool pmu_irq_is_valid(struct kvm *kvm, int irq)
 
 int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 {
-	if (!kvm_arm_support_pmu_v3() ||
-	    !test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+	if (!kvm_vcpu_has_pmu(vcpu))
 		return -ENODEV;
 
 	if (vcpu->arch.pmu.created)
@@ -1015,7 +1011,7 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		if (!irqchip_in_kernel(vcpu->kvm))
 			return -EINVAL;
 
-		if (!test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+		if (!kvm_vcpu_has_pmu(vcpu))
 			return -ENODEV;
 
 		if (!kvm_arm_pmu_irq_initialized(vcpu))
@@ -1035,8 +1031,7 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 	case KVM_ARM_VCPU_PMU_V3_IRQ:
 	case KVM_ARM_VCPU_PMU_V3_INIT:
 	case KVM_ARM_VCPU_PMU_V3_FILTER:
-		if (kvm_arm_support_pmu_v3() &&
-		    test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
+		if (kvm_vcpu_has_pmu(vcpu))
 			return 0;
 	}
 
diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c
index 920ac43077ad..78a09f7a6637 100644
--- a/arch/arm64/kvm/pvtime.c
+++ b/arch/arm64/kvm/pvtime.c
@@ -53,7 +53,6 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	struct pvclock_vcpu_stolen_time init_values = {};
 	struct kvm *kvm = vcpu->kvm;
 	u64 base = vcpu->arch.steal.base;
-	int idx;
 
 	if (base == GPA_INVALID)
 		return base;
@@ -63,10 +62,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	 * the feature enabled.
 	 */
 	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
-
-	idx = srcu_read_lock(&kvm->srcu);
-	kvm_write_guest(kvm, base, &init_values, sizeof(init_values));
-	srcu_read_unlock(&kvm->srcu, idx);
+	kvm_write_guest_lock(kvm, base, &init_values, sizeof(init_values));
 
 	return base;
 }
diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c
deleted file mode 100644
index accc1d5fba61..000000000000
--- a/arch/arm64/kvm/regmap.c
+++ /dev/null
@@ -1,224 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * Derived from arch/arm/kvm/emulate.c:
- * Copyright (C) 2012 - Virtual Open Systems and Columbia University
- * Author: Christoffer Dall <c.dall@virtualopensystems.com>
- */
-
-#include <linux/mm.h>
-#include <linux/kvm_host.h>
-#include <asm/kvm_emulate.h>
-#include <asm/ptrace.h>
-
-#define VCPU_NR_MODES 6
-#define REG_OFFSET(_reg) \
-	(offsetof(struct user_pt_regs, _reg) / sizeof(unsigned long))
-
-#define USR_REG_OFFSET(R) REG_OFFSET(compat_usr(R))
-
-static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][16] = {
-	/* USR Registers */
-	{
-		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
-		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
-		USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
-		USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
-		USR_REG_OFFSET(12), USR_REG_OFFSET(13),	USR_REG_OFFSET(14),
-		REG_OFFSET(pc)
-	},
-
-	/* FIQ Registers */
-	{
-		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
-		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
-		USR_REG_OFFSET(6), USR_REG_OFFSET(7),
-		REG_OFFSET(compat_r8_fiq),  /* r8 */
-		REG_OFFSET(compat_r9_fiq),  /* r9 */
-		REG_OFFSET(compat_r10_fiq), /* r10 */
-		REG_OFFSET(compat_r11_fiq), /* r11 */
-		REG_OFFSET(compat_r12_fiq), /* r12 */
-		REG_OFFSET(compat_sp_fiq),  /* r13 */
-		REG_OFFSET(compat_lr_fiq),  /* r14 */
-		REG_OFFSET(pc)
-	},
-
-	/* IRQ Registers */
-	{
-		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
-		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
-		USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
-		USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
-		USR_REG_OFFSET(12),
-		REG_OFFSET(compat_sp_irq), /* r13 */
-		REG_OFFSET(compat_lr_irq), /* r14 */
-		REG_OFFSET(pc)
-	},
-
-	/* SVC Registers */
-	{
-		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
-		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
-		USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
-		USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
-		USR_REG_OFFSET(12),
-		REG_OFFSET(compat_sp_svc), /* r13 */
-		REG_OFFSET(compat_lr_svc), /* r14 */
-		REG_OFFSET(pc)
-	},
-
-	/* ABT Registers */
-	{
-		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
-		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
-		USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
-		USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
-		USR_REG_OFFSET(12),
-		REG_OFFSET(compat_sp_abt), /* r13 */
-		REG_OFFSET(compat_lr_abt), /* r14 */
-		REG_OFFSET(pc)
-	},
-
-	/* UND Registers */
-	{
-		USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
-		USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
-		USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
-		USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
-		USR_REG_OFFSET(12),
-		REG_OFFSET(compat_sp_und), /* r13 */
-		REG_OFFSET(compat_lr_und), /* r14 */
-		REG_OFFSET(pc)
-	},
-};
-
-/*
- * Return a pointer to the register number valid in the current mode of
- * the virtual CPU.
- */
-unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num)
-{
-	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.regs;
-	unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
-
-	switch (mode) {
-	case PSR_AA32_MODE_USR ... PSR_AA32_MODE_SVC:
-		mode &= ~PSR_MODE32_BIT; /* 0 ... 3 */
-		break;
-
-	case PSR_AA32_MODE_ABT:
-		mode = 4;
-		break;
-
-	case PSR_AA32_MODE_UND:
-		mode = 5;
-		break;
-
-	case PSR_AA32_MODE_SYS:
-		mode = 0;	/* SYS maps to USR */
-		break;
-
-	default:
-		BUG();
-	}
-
-	return reg_array + vcpu_reg_offsets[mode][reg_num];
-}
-
-/*
- * Return the SPSR for the current mode of the virtual CPU.
- */
-static int vcpu_spsr32_mode(const struct kvm_vcpu *vcpu)
-{
-	unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
-	switch (mode) {
-	case PSR_AA32_MODE_SVC: return KVM_SPSR_SVC;
-	case PSR_AA32_MODE_ABT: return KVM_SPSR_ABT;
-	case PSR_AA32_MODE_UND: return KVM_SPSR_UND;
-	case PSR_AA32_MODE_IRQ: return KVM_SPSR_IRQ;
-	case PSR_AA32_MODE_FIQ: return KVM_SPSR_FIQ;
-	default: BUG();
-	}
-}
-
-unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu)
-{
-	int spsr_idx = vcpu_spsr32_mode(vcpu);
-
-	if (!vcpu->arch.sysregs_loaded_on_cpu) {
-		switch (spsr_idx) {
-		case KVM_SPSR_SVC:
-			return __vcpu_sys_reg(vcpu, SPSR_EL1);
-		case KVM_SPSR_ABT:
-			return vcpu->arch.ctxt.spsr_abt;
-		case KVM_SPSR_UND:
-			return vcpu->arch.ctxt.spsr_und;
-		case KVM_SPSR_IRQ:
-			return vcpu->arch.ctxt.spsr_irq;
-		case KVM_SPSR_FIQ:
-			return vcpu->arch.ctxt.spsr_fiq;
-		}
-	}
-
-	switch (spsr_idx) {
-	case KVM_SPSR_SVC:
-		return read_sysreg_el1(SYS_SPSR);
-	case KVM_SPSR_ABT:
-		return read_sysreg(spsr_abt);
-	case KVM_SPSR_UND:
-		return read_sysreg(spsr_und);
-	case KVM_SPSR_IRQ:
-		return read_sysreg(spsr_irq);
-	case KVM_SPSR_FIQ:
-		return read_sysreg(spsr_fiq);
-	default:
-		BUG();
-	}
-}
-
-void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v)
-{
-	int spsr_idx = vcpu_spsr32_mode(vcpu);
-
-	if (!vcpu->arch.sysregs_loaded_on_cpu) {
-		switch (spsr_idx) {
-		case KVM_SPSR_SVC:
-			__vcpu_sys_reg(vcpu, SPSR_EL1) = v;
-			break;
-		case KVM_SPSR_ABT:
-			vcpu->arch.ctxt.spsr_abt = v;
-			break;
-		case KVM_SPSR_UND:
-			vcpu->arch.ctxt.spsr_und = v;
-			break;
-		case KVM_SPSR_IRQ:
-			vcpu->arch.ctxt.spsr_irq = v;
-			break;
-		case KVM_SPSR_FIQ:
-			vcpu->arch.ctxt.spsr_fiq = v;
-			break;
-		}
-
-		return;
-	}
-
-	switch (spsr_idx) {
-	case KVM_SPSR_SVC:
-		write_sysreg_el1(v, SYS_SPSR);
-		break;
-	case KVM_SPSR_ABT:
-		write_sysreg(v, spsr_abt);
-		break;
-	case KVM_SPSR_UND:
-		write_sysreg(v, spsr_und);
-		break;
-	case KVM_SPSR_IRQ:
-		write_sysreg(v, spsr_irq);
-		break;
-	case KVM_SPSR_FIQ:
-		write_sysreg(v, spsr_fiq);
-		break;
-	}
-}
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index f32490229a4c..47f3f035f3ea 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -25,7 +25,6 @@
 #include <asm/ptrace.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_asm.h>
-#include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
 #include <asm/virt.h>
@@ -42,58 +41,6 @@ static u32 kvm_ipa_limit;
 #define VCPU_RESET_PSTATE_SVC	(PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \
 				 PSR_AA32_I_BIT | PSR_AA32_F_BIT)
 
-static bool system_has_full_ptr_auth(void)
-{
-	return system_supports_address_auth() && system_supports_generic_auth();
-}
-
-/**
- * kvm_arch_vm_ioctl_check_extension
- *
- * We currently assume that the number of HW registers is uniform
- * across all CPUs (see cpuinfo_sanity_check).
- */
-int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
-{
-	int r;
-
-	switch (ext) {
-	case KVM_CAP_ARM_EL1_32BIT:
-		r = cpus_have_const_cap(ARM64_HAS_32BIT_EL1);
-		break;
-	case KVM_CAP_GUEST_DEBUG_HW_BPS:
-		r = get_num_brps();
-		break;
-	case KVM_CAP_GUEST_DEBUG_HW_WPS:
-		r = get_num_wrps();
-		break;
-	case KVM_CAP_ARM_PMU_V3:
-		r = kvm_arm_support_pmu_v3();
-		break;
-	case KVM_CAP_ARM_INJECT_SERROR_ESR:
-		r = cpus_have_const_cap(ARM64_HAS_RAS_EXTN);
-		break;
-	case KVM_CAP_SET_GUEST_DEBUG:
-	case KVM_CAP_VCPU_ATTRIBUTES:
-		r = 1;
-		break;
-	case KVM_CAP_ARM_VM_IPA_SIZE:
-		r = kvm_ipa_limit;
-		break;
-	case KVM_CAP_ARM_SVE:
-		r = system_supports_sve();
-		break;
-	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
-	case KVM_CAP_ARM_PTRAUTH_GENERIC:
-		r = system_has_full_ptr_auth();
-		break;
-	default:
-		r = 0;
-	}
-
-	return r;
-}
-
 unsigned int kvm_sve_max_vl;
 
 int kvm_arm_init_sve(void)
@@ -286,6 +233,10 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 			pstate = VCPU_RESET_PSTATE_EL1;
 		}
 
+		if (kvm_vcpu_has_pmu(vcpu) && !kvm_arm_support_pmu_v3()) {
+			ret = -EINVAL;
+			goto out;
+		}
 		break;
 	}
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index c1fac9836af1..42ccc27fb684 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -20,7 +20,6 @@
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/kvm_arm.h>
-#include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
@@ -64,87 +63,6 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu,
 	return false;
 }
 
-static bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
-{
-	/*
-	 * System registers listed in the switch are not saved on every
-	 * exit from the guest but are only saved on vcpu_put.
-	 *
-	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
-	 * should never be listed below, because the guest cannot modify its
-	 * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's
-	 * thread when emulating cross-VCPU communication.
-	 */
-	switch (reg) {
-	case CSSELR_EL1:	*val = read_sysreg_s(SYS_CSSELR_EL1);	break;
-	case SCTLR_EL1:		*val = read_sysreg_s(SYS_SCTLR_EL12);	break;
-	case CPACR_EL1:		*val = read_sysreg_s(SYS_CPACR_EL12);	break;
-	case TTBR0_EL1:		*val = read_sysreg_s(SYS_TTBR0_EL12);	break;
-	case TTBR1_EL1:		*val = read_sysreg_s(SYS_TTBR1_EL12);	break;
-	case TCR_EL1:		*val = read_sysreg_s(SYS_TCR_EL12);	break;
-	case ESR_EL1:		*val = read_sysreg_s(SYS_ESR_EL12);	break;
-	case AFSR0_EL1:		*val = read_sysreg_s(SYS_AFSR0_EL12);	break;
-	case AFSR1_EL1:		*val = read_sysreg_s(SYS_AFSR1_EL12);	break;
-	case FAR_EL1:		*val = read_sysreg_s(SYS_FAR_EL12);	break;
-	case MAIR_EL1:		*val = read_sysreg_s(SYS_MAIR_EL12);	break;
-	case VBAR_EL1:		*val = read_sysreg_s(SYS_VBAR_EL12);	break;
-	case CONTEXTIDR_EL1:	*val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break;
-	case TPIDR_EL0:		*val = read_sysreg_s(SYS_TPIDR_EL0);	break;
-	case TPIDRRO_EL0:	*val = read_sysreg_s(SYS_TPIDRRO_EL0);	break;
-	case TPIDR_EL1:		*val = read_sysreg_s(SYS_TPIDR_EL1);	break;
-	case AMAIR_EL1:		*val = read_sysreg_s(SYS_AMAIR_EL12);	break;
-	case CNTKCTL_EL1:	*val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
-	case ELR_EL1:		*val = read_sysreg_s(SYS_ELR_EL12);	break;
-	case PAR_EL1:		*val = read_sysreg_par();		break;
-	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
-	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
-	case DBGVCR32_EL2:	*val = read_sysreg_s(SYS_DBGVCR32_EL2);	break;
-	default:		return false;
-	}
-
-	return true;
-}
-
-static bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
-{
-	/*
-	 * System registers listed in the switch are not restored on every
-	 * entry to the guest but are only restored on vcpu_load.
-	 *
-	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
-	 * should never be listed below, because the MPIDR should only be set
-	 * once, before running the VCPU, and never changed later.
-	 */
-	switch (reg) {
-	case CSSELR_EL1:	write_sysreg_s(val, SYS_CSSELR_EL1);	break;
-	case SCTLR_EL1:		write_sysreg_s(val, SYS_SCTLR_EL12);	break;
-	case CPACR_EL1:		write_sysreg_s(val, SYS_CPACR_EL12);	break;
-	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
-	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
-	case TCR_EL1:		write_sysreg_s(val, SYS_TCR_EL12);	break;
-	case ESR_EL1:		write_sysreg_s(val, SYS_ESR_EL12);	break;
-	case AFSR0_EL1:		write_sysreg_s(val, SYS_AFSR0_EL12);	break;
-	case AFSR1_EL1:		write_sysreg_s(val, SYS_AFSR1_EL12);	break;
-	case FAR_EL1:		write_sysreg_s(val, SYS_FAR_EL12);	break;
-	case MAIR_EL1:		write_sysreg_s(val, SYS_MAIR_EL12);	break;
-	case VBAR_EL1:		write_sysreg_s(val, SYS_VBAR_EL12);	break;
-	case CONTEXTIDR_EL1:	write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break;
-	case TPIDR_EL0:		write_sysreg_s(val, SYS_TPIDR_EL0);	break;
-	case TPIDRRO_EL0:	write_sysreg_s(val, SYS_TPIDRRO_EL0);	break;
-	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	break;
-	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
-	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
-	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
-	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
-	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
-	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
-	case DBGVCR32_EL2:	write_sysreg_s(val, SYS_DBGVCR32_EL2);	break;
-	default:		return false;
-	}
-
-	return true;
-}
-
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 {
 	u64 val = 0x8badf00d8badf00d;
@@ -169,7 +87,7 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 static u32 cache_levels;
 
 /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
-#define CSSELR_MAX 12
+#define CSSELR_MAX 14
 
 /* Which cache CCSIDR represents depends on CSSELR value. */
 static u32 get_ccsidr(u32 csselr)
@@ -209,6 +127,24 @@ static bool access_dcsw(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static void get_access_mask(const struct sys_reg_desc *r, u64 *mask, u64 *shift)
+{
+	switch (r->aarch32_map) {
+	case AA32_LO:
+		*mask = GENMASK_ULL(31, 0);
+		*shift = 0;
+		break;
+	case AA32_HI:
+		*mask = GENMASK_ULL(63, 32);
+		*shift = 32;
+		break;
+	default:
+		*mask = GENMASK_ULL(63, 0);
+		*shift = 0;
+		break;
+	}
+}
+
 /*
  * Generic accessor for VM registers. Only called as long as HCR_TVM
  * is set. If the guest enables the MMU, we stop trapping the VM
@@ -219,26 +155,21 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 			  const struct sys_reg_desc *r)
 {
 	bool was_enabled = vcpu_has_cache_enabled(vcpu);
-	u64 val;
-	int reg = r->reg;
+	u64 val, mask, shift;
 
 	BUG_ON(!p->is_write);
 
-	/* See the 32bit mapping in kvm_host.h */
-	if (p->is_aarch32)
-		reg = r->reg / 2;
+	get_access_mask(r, &mask, &shift);
 
-	if (!p->is_aarch32 || !p->is_32bit) {
-		val = p->regval;
+	if (~mask) {
+		val = vcpu_read_sys_reg(vcpu, r->reg);
+		val &= ~mask;
 	} else {
-		val = vcpu_read_sys_reg(vcpu, reg);
-		if (r->reg % 2)
-			val = (p->regval << 32) | (u64)lower_32_bits(val);
-		else
-			val = ((u64)upper_32_bits(val) << 32) |
-				lower_32_bits(p->regval);
+		val = 0;
 	}
-	vcpu_write_sys_reg(vcpu, val, reg);
+
+	val |= (p->regval & (mask >> shift)) << shift;
+	vcpu_write_sys_reg(vcpu, val, r->reg);
 
 	kvm_toggle_cache(vcpu, was_enabled);
 	return true;
@@ -248,17 +179,13 @@ static bool access_actlr(struct kvm_vcpu *vcpu,
 			 struct sys_reg_params *p,
 			 const struct sys_reg_desc *r)
 {
+	u64 mask, shift;
+
 	if (p->is_write)
 		return ignore_write(vcpu, p);
 
-	p->regval = vcpu_read_sys_reg(vcpu, ACTLR_EL1);
-
-	if (p->is_aarch32) {
-		if (r->Op2 & 2)
-			p->regval = upper_32_bits(p->regval);
-		else
-			p->regval = lower_32_bits(p->regval);
-	}
+	get_access_mask(r, &mask, &shift);
+	p->regval = (vcpu_read_sys_reg(vcpu, r->reg) & mask) >> shift;
 
 	return true;
 }
@@ -285,7 +212,7 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
 	 * equivalent to ICC_SGI0R_EL1, as there is no "alternative" secure
 	 * group.
 	 */
-	if (p->is_aarch32) {
+	if (p->Op0 == 0) {		/* AArch32 */
 		switch (p->Op1) {
 		default:		/* Keep GCC quiet */
 		case 0:			/* ICC_SGI1R */
@@ -296,7 +223,7 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
 			g1 = false;
 			break;
 		}
-	} else {
+	} else {			/* AArch64 */
 		switch (p->Op2) {
 		default:		/* Keep GCC quiet */
 		case 5:			/* ICC_SGI1R_EL1 */
@@ -438,26 +365,30 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu,
  */
 static void reg_to_dbg(struct kvm_vcpu *vcpu,
 		       struct sys_reg_params *p,
+		       const struct sys_reg_desc *rd,
 		       u64 *dbg_reg)
 {
-	u64 val = p->regval;
+	u64 mask, shift, val;
 
-	if (p->is_32bit) {
-		val &= 0xffffffffUL;
-		val |= ((*dbg_reg >> 32) << 32);
-	}
+	get_access_mask(rd, &mask, &shift);
 
+	val = *dbg_reg;
+	val &= ~mask;
+	val |= (p->regval & (mask >> shift)) << shift;
 	*dbg_reg = val;
+
 	vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
 }
 
 static void dbg_to_reg(struct kvm_vcpu *vcpu,
 		       struct sys_reg_params *p,
+		       const struct sys_reg_desc *rd,
 		       u64 *dbg_reg)
 {
-	p->regval = *dbg_reg;
-	if (p->is_32bit)
-		p->regval &= 0xffffffffUL;
+	u64 mask, shift;
+
+	get_access_mask(rd, &mask, &shift);
+	p->regval = (*dbg_reg & mask) >> shift;
 }
 
 static bool trap_bvr(struct kvm_vcpu *vcpu,
@@ -467,9 +398,9 @@ static bool trap_bvr(struct kvm_vcpu *vcpu,
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
 
 	if (p->is_write)
-		reg_to_dbg(vcpu, p, dbg_reg);
+		reg_to_dbg(vcpu, p, rd, dbg_reg);
 	else
-		dbg_to_reg(vcpu, p, dbg_reg);
+		dbg_to_reg(vcpu, p, rd, dbg_reg);
 
 	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);
 
@@ -509,9 +440,9 @@ static bool trap_bcr(struct kvm_vcpu *vcpu,
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];
 
 	if (p->is_write)
-		reg_to_dbg(vcpu, p, dbg_reg);
+		reg_to_dbg(vcpu, p, rd, dbg_reg);
 	else
-		dbg_to_reg(vcpu, p, dbg_reg);
+		dbg_to_reg(vcpu, p, rd, dbg_reg);
 
 	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);
 
@@ -552,9 +483,9 @@ static bool trap_wvr(struct kvm_vcpu *vcpu,
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];
 
 	if (p->is_write)
-		reg_to_dbg(vcpu, p, dbg_reg);
+		reg_to_dbg(vcpu, p, rd, dbg_reg);
 	else
-		dbg_to_reg(vcpu, p, dbg_reg);
+		dbg_to_reg(vcpu, p, rd, dbg_reg);
 
 	trace_trap_reg(__func__, rd->reg, p->is_write,
 		vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]);
@@ -595,9 +526,9 @@ static bool trap_wcr(struct kvm_vcpu *vcpu,
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];
 
 	if (p->is_write)
-		reg_to_dbg(vcpu, p, dbg_reg);
+		reg_to_dbg(vcpu, p, rd, dbg_reg);
 	else
-		dbg_to_reg(vcpu, p, dbg_reg);
+		dbg_to_reg(vcpu, p, rd, dbg_reg);
 
 	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);
 
@@ -663,6 +594,10 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 pmcr, val;
 
+	/* No PMU available, PMCR_EL0 may UNDEF... */
+	if (!kvm_arm_support_pmu_v3())
+		return;
+
 	pmcr = read_sysreg(pmcr_el0);
 	/*
 	 * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN
@@ -678,8 +613,9 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags)
 {
 	u64 reg = __vcpu_sys_reg(vcpu, PMUSERENR_EL0);
-	bool enabled = (reg & flags) || vcpu_mode_priv(vcpu);
+	bool enabled = kvm_vcpu_has_pmu(vcpu);
 
+	enabled &= (reg & flags) || vcpu_mode_priv(vcpu);
 	if (!enabled)
 		kvm_inject_undefined(vcpu);
 
@@ -711,9 +647,6 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 {
 	u64 val;
 
-	if (!kvm_arm_pmu_v3_ready(vcpu))
-		return trap_raz_wi(vcpu, p, r);
-
 	if (pmu_access_el0_disabled(vcpu))
 		return false;
 
@@ -740,9 +673,6 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
-	if (!kvm_arm_pmu_v3_ready(vcpu))
-		return trap_raz_wi(vcpu, p, r);
-
 	if (pmu_access_event_counter_el0_disabled(vcpu))
 		return false;
 
@@ -761,9 +691,6 @@ static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 {
 	u64 pmceid;
 
-	if (!kvm_arm_pmu_v3_ready(vcpu))
-		return trap_raz_wi(vcpu, p, r);
-
 	BUG_ON(p->is_write);
 
 	if (pmu_access_el0_disabled(vcpu))
@@ -794,10 +721,7 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 			      struct sys_reg_params *p,
 			      const struct sys_reg_desc *r)
 {
-	u64 idx;
-
-	if (!kvm_arm_pmu_v3_ready(vcpu))
-		return trap_raz_wi(vcpu, p, r);
+	u64 idx = ~0UL;
 
 	if (r->CRn == 9 && r->CRm == 13) {
 		if (r->Op2 == 2) {
@@ -813,8 +737,6 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 				return false;
 
 			idx = ARMV8_PMU_CYCLE_IDX;
-		} else {
-			return false;
 		}
 	} else if (r->CRn == 0 && r->CRm == 9) {
 		/* PMCCNTR */
@@ -828,10 +750,11 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 			return false;
 
 		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
-	} else {
-		return false;
 	}
 
+	/* Catch any decoding mistake */
+	WARN_ON(idx == ~0UL);
+
 	if (!pmu_counter_idx_valid(vcpu, idx))
 		return false;
 
@@ -852,9 +775,6 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 {
 	u64 idx, reg;
 
-	if (!kvm_arm_pmu_v3_ready(vcpu))
-		return trap_raz_wi(vcpu, p, r);
-
 	if (pmu_access_el0_disabled(vcpu))
 		return false;
 
@@ -892,9 +812,6 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 {
 	u64 val, mask;
 
-	if (!kvm_arm_pmu_v3_ready(vcpu))
-		return trap_raz_wi(vcpu, p, r);
-
 	if (pmu_access_el0_disabled(vcpu))
 		return false;
 
@@ -923,13 +840,8 @@ static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 {
 	u64 mask = kvm_pmu_valid_counter_mask(vcpu);
 
-	if (!kvm_arm_pmu_v3_ready(vcpu))
-		return trap_raz_wi(vcpu, p, r);
-
-	if (!vcpu_mode_priv(vcpu)) {
-		kvm_inject_undefined(vcpu);
+	if (check_pmu_access_disabled(vcpu, 0))
 		return false;
-	}
 
 	if (p->is_write) {
 		u64 val = p->regval & mask;
@@ -952,9 +864,6 @@ static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 {
 	u64 mask = kvm_pmu_valid_counter_mask(vcpu);
 
-	if (!kvm_arm_pmu_v3_ready(vcpu))
-		return trap_raz_wi(vcpu, p, r);
-
 	if (pmu_access_el0_disabled(vcpu))
 		return false;
 
@@ -977,9 +886,6 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 {
 	u64 mask;
 
-	if (!kvm_arm_pmu_v3_ready(vcpu))
-		return trap_raz_wi(vcpu, p, r);
-
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p, r);
 
@@ -994,8 +900,10 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			     const struct sys_reg_desc *r)
 {
-	if (!kvm_arm_pmu_v3_ready(vcpu))
-		return trap_raz_wi(vcpu, p, r);
+	if (!kvm_vcpu_has_pmu(vcpu)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
 
 	if (p->is_write) {
 		if (!vcpu_mode_priv(vcpu)) {
@@ -1015,7 +923,7 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 #define reg_to_encoding(x)						\
 	sys_reg((u32)(x)->Op0, (u32)(x)->Op1,				\
-		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2);
+		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2)
 
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
@@ -1122,6 +1030,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 		val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT);
 		val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT);
 		val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT);
+		val &= ~(0xfUL << ID_AA64PFR0_CSV3_SHIFT);
+		val |= ((u64)vcpu->kvm->arch.pfr0_csv3 << ID_AA64PFR0_CSV3_SHIFT);
 	} else if (id == SYS_ID_AA64PFR1_EL1) {
 		val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT);
 	} else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
@@ -1130,10 +1040,15 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 			 (0xfUL << ID_AA64ISAR1_GPA_SHIFT) |
 			 (0xfUL << ID_AA64ISAR1_GPI_SHIFT));
 	} else if (id == SYS_ID_AA64DFR0_EL1) {
+		u64 cap = 0;
+
 		/* Limit guests to PMUv3 for ARMv8.1 */
+		if (kvm_vcpu_has_pmu(vcpu))
+			cap = ID_AA64DFR0_PMUVER_8_1;
+
 		val = cpuid_feature_cap_perfmon_field(val,
 						ID_AA64DFR0_PMUVER_SHIFT,
-						ID_AA64DFR0_PMUVER_8_1);
+						cap);
 	} else if (id == SYS_ID_DFR0_EL1) {
 		/* Limit guests to PMUv3 for ARMv8.1 */
 		val = cpuid_feature_cap_perfmon_field(val,
@@ -1209,9 +1124,9 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
 			       const struct kvm_one_reg *reg, void __user *uaddr)
 {
 	const u64 id = sys_reg_to_index(rd);
+	u8 csv2, csv3;
 	int err;
 	u64 val;
-	u8 csv2;
 
 	err = reg_from_user(&val, uaddr, id);
 	if (err)
@@ -1227,13 +1142,21 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
 	    (csv2 && arm64_get_spectre_v2_state() != SPECTRE_UNAFFECTED))
 		return -EINVAL;
 
-	/* We can only differ with CSV2, and anything else is an error */
+	/* Same thing for CSV3 */
+	csv3 = cpuid_feature_extract_unsigned_field(val, ID_AA64PFR0_CSV3_SHIFT);
+	if (csv3 > 1 ||
+	    (csv3 && arm64_get_meltdown_state() != SPECTRE_UNAFFECTED))
+		return -EINVAL;
+
+	/* We can only differ with CSV[23], and anything else is an error */
 	val ^= read_id_reg(vcpu, rd, false);
-	val &= ~(0xFUL << ID_AA64PFR0_CSV2_SHIFT);
+	val &= ~((0xFUL << ID_AA64PFR0_CSV2_SHIFT) |
+		 (0xFUL << ID_AA64PFR0_CSV3_SHIFT));
 	if (val)
 		return -EINVAL;
 
 	vcpu->kvm->arch.pfr0_csv2 = csv2;
+	vcpu->kvm->arch.pfr0_csv3 = csv3 ;
 
 	return 0;
 }
@@ -1327,10 +1250,6 @@ static bool access_csselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 {
 	int reg = r->reg;
 
-	/* See the 32bit mapping in kvm_host.h */
-	if (p->is_aarch32)
-		reg = r->reg / 2;
-
 	if (p->is_write)
 		vcpu_write_sys_reg(vcpu, p->regval, reg);
 	else
@@ -1801,66 +1720,27 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu,
 	}
 }
 
-static bool trap_debug32(struct kvm_vcpu *vcpu,
-			 struct sys_reg_params *p,
-			 const struct sys_reg_desc *r)
-{
-	if (p->is_write) {
-		vcpu_cp14(vcpu, r->reg) = p->regval;
-		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
-	} else {
-		p->regval = vcpu_cp14(vcpu, r->reg);
-	}
-
-	return true;
-}
-
-/* AArch32 debug register mappings
+/*
+ * AArch32 debug register mappings
  *
  * AArch32 DBGBVRn is mapped to DBGBVRn_EL1[31:0]
  * AArch32 DBGBXVRn is mapped to DBGBVRn_EL1[63:32]
  *
- * All control registers and watchpoint value registers are mapped to
- * the lower 32 bits of their AArch64 equivalents. We share the trap
- * handlers with the above AArch64 code which checks what mode the
- * system is in.
+ * None of the other registers share their location, so treat them as
+ * if they were 64bit.
  */
-
-static bool trap_xvr(struct kvm_vcpu *vcpu,
-		     struct sys_reg_params *p,
-		     const struct sys_reg_desc *rd)
-{
-	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
-
-	if (p->is_write) {
-		u64 val = *dbg_reg;
-
-		val &= 0xffffffffUL;
-		val |= p->regval << 32;
-		*dbg_reg = val;
-
-		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
-	} else {
-		p->regval = *dbg_reg >> 32;
-	}
-
-	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);
-
-	return true;
-}
-
-#define DBG_BCR_BVR_WCR_WVR(n)						\
-	/* DBGBVRn */							\
-	{ Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_bvr, NULL, n }, 	\
-	/* DBGBCRn */							\
-	{ Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_bcr, NULL, n },	\
-	/* DBGWVRn */							\
-	{ Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_wvr, NULL, n },	\
-	/* DBGWCRn */							\
+#define DBG_BCR_BVR_WCR_WVR(n)						      \
+	/* DBGBVRn */							      \
+	{ AA32(LO), Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_bvr, NULL, n }, \
+	/* DBGBCRn */							      \
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_bcr, NULL, n },	      \
+	/* DBGWVRn */							      \
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_wvr, NULL, n },	      \
+	/* DBGWCRn */							      \
 	{ Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_wcr, NULL, n }
 
-#define DBGBXVR(n)							\
-	{ Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_xvr, NULL, n }
+#define DBGBXVR(n)							      \
+	{ AA32(HI), Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_bvr, NULL, n }
 
 /*
  * Trapped cp14 registers. We generally ignore most of the external
@@ -1878,9 +1758,9 @@ static const struct sys_reg_desc cp14_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi },
 	DBG_BCR_BVR_WCR_WVR(1),
 	/* DBGDCCINT */
-	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32, NULL, cp14_DBGDCCINT },
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug_regs, NULL, MDCCINT_EL1 },
 	/* DBGDSCRext */
-	{ Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32, NULL, cp14_DBGDSCRext },
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug_regs, NULL, MDSCR_EL1 },
 	DBG_BCR_BVR_WCR_WVR(2),
 	/* DBGDTR[RT]Xint */
 	{ Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi },
@@ -1895,7 +1775,7 @@ static const struct sys_reg_desc cp14_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi },
 	DBG_BCR_BVR_WCR_WVR(6),
 	/* DBGVCR */
-	{ Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32, NULL, cp14_DBGVCR },
+	{ Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug_regs, NULL, DBGVCR32_EL2 },
 	DBG_BCR_BVR_WCR_WVR(7),
 	DBG_BCR_BVR_WCR_WVR(8),
 	DBG_BCR_BVR_WCR_WVR(9),
@@ -1981,19 +1861,29 @@ static const struct sys_reg_desc cp14_64_regs[] = {
  */
 static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 0), Op2( 1), access_ctr },
-	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR },
-	{ Op1( 0), CRn( 1), CRm( 0), Op2( 1), access_actlr },
-	{ Op1( 0), CRn( 1), CRm( 0), Op2( 3), access_actlr },
-	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
-	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
-	{ Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },
-	{ Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR },
-	{ Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR },
-	{ Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR },
-	{ Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, c5_ADFSR },
-	{ Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, c5_AIFSR },
-	{ Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, c6_DFAR },
-	{ Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, c6_IFAR },
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, SCTLR_EL1 },
+	/* ACTLR */
+	{ AA32(LO), Op1( 0), CRn( 1), CRm( 0), Op2( 1), access_actlr, NULL, ACTLR_EL1 },
+	/* ACTLR2 */
+	{ AA32(HI), Op1( 0), CRn( 1), CRm( 0), Op2( 3), access_actlr, NULL, ACTLR_EL1 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, TTBR0_EL1 },
+	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, TTBR1_EL1 },
+	/* TTBCR */
+	{ AA32(LO), Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, TCR_EL1 },
+	/* TTBCR2 */
+	{ AA32(HI), Op1( 0), CRn( 2), CRm( 0), Op2( 3), access_vm_reg, NULL, TCR_EL1 },
+	{ Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, DACR32_EL2 },
+	/* DFSR */
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, ESR_EL1 },
+	{ Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, IFSR32_EL2 },
+	/* ADFSR */
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, AFSR0_EL1 },
+	/* AIFSR */
+	{ Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, AFSR1_EL1 },
+	/* DFAR */
+	{ AA32(LO), Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, FAR_EL1 },
+	/* IFAR */
+	{ AA32(HI), Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, FAR_EL1 },
 
 	/*
 	 * DC{C,I,CI}SW operations:
@@ -2019,15 +1909,19 @@ static const struct sys_reg_desc cp15_regs[] = {
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 2), access_pminten },
 	{ Op1( 0), CRn( 9), CRm(14), Op2( 3), access_pmovs },
 
-	{ Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR },
-	{ Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR },
-	{ Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 },
-	{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
+	/* PRRR/MAIR0 */
+	{ AA32(LO), Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, MAIR_EL1 },
+	/* NMRR/MAIR1 */
+	{ AA32(HI), Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, MAIR_EL1 },
+	/* AMAIR0 */
+	{ AA32(LO), Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, AMAIR_EL1 },
+	/* AMAIR1 */
+	{ AA32(HI), Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, AMAIR_EL1 },
 
 	/* ICC_SRE */
 	{ Op1( 0), CRn(12), CRm(12), Op2( 5), access_gic_sre },
 
-	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
+	{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, CONTEXTIDR_EL1 },
 
 	/* Arch Tmers */
 	{ SYS_DESC(SYS_AARCH32_CNTP_TVAL), access_arch_timer },
@@ -2102,14 +1996,14 @@ static const struct sys_reg_desc cp15_regs[] = {
 
 	{ Op1(1), CRn( 0), CRm( 0), Op2(0), access_ccsidr },
 	{ Op1(1), CRn( 0), CRm( 0), Op2(1), access_clidr },
-	{ Op1(2), CRn( 0), CRm( 0), Op2(0), access_csselr, NULL, c0_CSSELR },
+	{ Op1(2), CRn( 0), CRm( 0), Op2(0), access_csselr, NULL, CSSELR_EL1 },
 };
 
 static const struct sys_reg_desc cp15_64_regs[] = {
-	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR0_EL1 },
 	{ Op1( 0), CRn( 0), CRm( 9), Op2( 0), access_pmu_evcntr },
 	{ Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI1R */
-	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
+	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR1_EL1 },
 	{ Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */
 	{ Op1( 2), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI0R */
 	{ SYS_DESC(SYS_AARCH32_CNTP_CVAL),    access_arch_timer },
@@ -2180,7 +2074,7 @@ static void perform_access(struct kvm_vcpu *vcpu,
 
 	/* Skip instruction if instructed so */
 	if (likely(r->access(vcpu, params, r)))
-		kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+		kvm_incr_pc(vcpu);
 }
 
 /*
@@ -2253,8 +2147,6 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 	int Rt = kvm_vcpu_sys_get_rt(vcpu);
 	int Rt2 = (esr >> 10) & 0x1f;
 
-	params.is_aarch32 = true;
-	params.is_32bit = false;
 	params.CRm = (esr >> 1) & 0xf;
 	params.is_write = ((esr & 1) == 0);
 
@@ -2304,8 +2196,6 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 	u32 esr = kvm_vcpu_get_esr(vcpu);
 	int Rt  = kvm_vcpu_sys_get_rt(vcpu);
 
-	params.is_aarch32 = true;
-	params.is_32bit = true;
 	params.CRm = (esr >> 1) & 0xf;
 	params.regval = vcpu_get_reg(vcpu, Rt);
 	params.is_write = ((esr & 1) == 0);
@@ -2399,8 +2289,6 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu)
 
 	trace_kvm_handle_sys_reg(esr);
 
-	params.is_aarch32 = false;
-	params.is_32bit = false;
 	params.Op0 = (esr >> 20) & 3;
 	params.Op1 = (esr >> 14) & 0x7;
 	params.CRn = (esr >> 10) & 0xf;
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 0f95964339b1..9d0621417c2a 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -19,14 +19,18 @@ struct sys_reg_params {
 	u8	Op2;
 	u64	regval;
 	bool	is_write;
-	bool	is_aarch32;
-	bool	is_32bit;	/* Only valid if is_aarch32 is true */
 };
 
 struct sys_reg_desc {
 	/* Sysreg string for debug */
 	const char *name;
 
+	enum {
+		AA32_ZEROHIGH,
+		AA32_LO,
+		AA32_HI,
+	} aarch32_map;
+
 	/* MRS/MSR instruction which accesses it. */
 	u8	Op0;
 	u8	Op1;
@@ -153,6 +157,7 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
 					  const struct sys_reg_desc table[],
 					  unsigned int num);
 
+#define AA32(_x)	.aarch32_map = AA32_##_x
 #define Op0(_x) 	.Op0 = _x
 #define Op1(_x) 	.Op1 = _x
 #define CRn(_x)		.CRn = _x
diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index e0404bcab019..70fcd6a12fe1 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -11,6 +11,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/insn.h>
 #include <asm/kvm_mmu.h>
+#include <asm/memory.h>
 
 /*
  * The LSB of the HYP VA tag
@@ -23,6 +24,29 @@ static u64 tag_val;
 static u64 va_mask;
 
 /*
+ * Compute HYP VA by using the same computation as kern_hyp_va().
+ */
+static u64 __early_kern_hyp_va(u64 addr)
+{
+	addr &= va_mask;
+	addr |= tag_val << tag_lsb;
+	return addr;
+}
+
+/*
+ * Store a hyp VA <-> PA offset into a EL2-owned variable.
+ */
+static void init_hyp_physvirt_offset(void)
+{
+	u64 kern_va, hyp_va;
+
+	/* Compute the offset from the hyp VA and PA of a random symbol. */
+	kern_va = (u64)lm_alias(__hyp_text_start);
+	hyp_va = __early_kern_hyp_va(kern_va);
+	hyp_physvirt_offset = (s64)__pa(kern_va) - (s64)hyp_va;
+}
+
+/*
  * We want to generate a hyp VA with the following format (with V ==
  * vabits_actual):
  *
@@ -53,6 +77,8 @@ __init void kvm_compute_layout(void)
 		tag_val |= get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb);
 	}
 	tag_val >>= tag_lsb;
+
+	init_hyp_physvirt_offset();
 }
 
 static u32 compute_instruction(int n, u32 rd, u32 rn)
@@ -131,28 +157,21 @@ void __init kvm_update_va_mask(struct alt_instr *alt,
 	}
 }
 
-void *__kvm_bp_vect_base;
-int __kvm_harden_el2_vector_slot;
-
 void kvm_patch_vector_branch(struct alt_instr *alt,
 			     __le32 *origptr, __le32 *updptr, int nr_inst)
 {
 	u64 addr;
 	u32 insn;
 
-	BUG_ON(nr_inst != 5);
+	BUG_ON(nr_inst != 4);
 
-	if (has_vhe() || !cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) {
-		WARN_ON_ONCE(cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS));
+	if (!cpus_have_const_cap(ARM64_SPECTRE_V3A) || WARN_ON_ONCE(has_vhe()))
 		return;
-	}
 
 	/*
 	 * Compute HYP VA by using the same computation as kern_hyp_va()
 	 */
-	addr = (uintptr_t)kvm_ksym_ref(__kvm_hyp_vector);
-	addr &= va_mask;
-	addr |= tag_val << tag_lsb;
+	addr = __early_kern_hyp_va((u64)kvm_ksym_ref(__kvm_hyp_vector));
 
 	/* Use PC[10:7] to branch to the same vector in KVM */
 	addr |= ((u64)origptr & GENMASK_ULL(10, 7));
@@ -163,15 +182,6 @@ void kvm_patch_vector_branch(struct alt_instr *alt,
 	 */
 	addr += KVM_VECTOR_PREAMBLE;
 
-	/* stp x0, x1, [sp, #-16]! */
-	insn = aarch64_insn_gen_load_store_pair(AARCH64_INSN_REG_0,
-						AARCH64_INSN_REG_1,
-						AARCH64_INSN_REG_SP,
-						-16,
-						AARCH64_INSN_VARIANT_64BIT,
-						AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX);
-	*updptr++ = cpu_to_le32(insn);
-
 	/* movz x0, #(addr & 0xffff) */
 	insn = aarch64_insn_gen_movewide(AARCH64_INSN_REG_0,
 					 (u16)addr,
@@ -201,3 +211,58 @@ void kvm_patch_vector_branch(struct alt_instr *alt,
 					   AARCH64_INSN_BRANCH_NOLINK);
 	*updptr++ = cpu_to_le32(insn);
 }
+
+static void generate_mov_q(u64 val, __le32 *origptr, __le32 *updptr, int nr_inst)
+{
+	u32 insn, oinsn, rd;
+
+	BUG_ON(nr_inst != 4);
+
+	/* Compute target register */
+	oinsn = le32_to_cpu(*origptr);
+	rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, oinsn);
+
+	/* movz rd, #(val & 0xffff) */
+	insn = aarch64_insn_gen_movewide(rd,
+					 (u16)val,
+					 0,
+					 AARCH64_INSN_VARIANT_64BIT,
+					 AARCH64_INSN_MOVEWIDE_ZERO);
+	*updptr++ = cpu_to_le32(insn);
+
+	/* movk rd, #((val >> 16) & 0xffff), lsl #16 */
+	insn = aarch64_insn_gen_movewide(rd,
+					 (u16)(val >> 16),
+					 16,
+					 AARCH64_INSN_VARIANT_64BIT,
+					 AARCH64_INSN_MOVEWIDE_KEEP);
+	*updptr++ = cpu_to_le32(insn);
+
+	/* movk rd, #((val >> 32) & 0xffff), lsl #32 */
+	insn = aarch64_insn_gen_movewide(rd,
+					 (u16)(val >> 32),
+					 32,
+					 AARCH64_INSN_VARIANT_64BIT,
+					 AARCH64_INSN_MOVEWIDE_KEEP);
+	*updptr++ = cpu_to_le32(insn);
+
+	/* movk rd, #((val >> 48) & 0xffff), lsl #48 */
+	insn = aarch64_insn_gen_movewide(rd,
+					 (u16)(val >> 48),
+					 48,
+					 AARCH64_INSN_VARIANT_64BIT,
+					 AARCH64_INSN_MOVEWIDE_KEEP);
+	*updptr++ = cpu_to_le32(insn);
+}
+
+void kvm_update_kimg_phys_offset(struct alt_instr *alt,
+				 __le32 *origptr, __le32 *updptr, int nr_inst)
+{
+	generate_mov_q(kimage_voffset + PHYS_OFFSET, origptr, updptr, nr_inst);
+}
+
+void kvm_get_kimage_voffset(struct alt_instr *alt,
+			    __le32 *origptr, __le32 *updptr, int nr_inst)
+{
+	generate_mov_q(kimage_voffset, origptr, updptr, nr_inst);
+}
diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c
index 2f92bdcb1188..07d5271e9f05 100644
--- a/arch/arm64/kvm/vgic-sys-reg-v3.c
+++ b/arch/arm64/kvm/vgic-sys-reg-v3.c
@@ -268,8 +268,6 @@ int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, bool is_write, u64 id,
 
 	params.regval = *reg;
 	params.is_write = is_write;
-	params.is_aarch32 = false;
-	params.is_32bit = false;
 
 	if (find_reg_by_id(sysreg, &params, gic_v3_icc_reg_descs,
 			      ARRAY_SIZE(gic_v3_icc_reg_descs)))
@@ -288,8 +286,6 @@ int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, bool is_write, u64 id,
 	if (is_write)
 		params.regval = *reg;
 	params.is_write = is_write;
-	params.is_aarch32 = false;
-	params.is_32bit = false;
 
 	r = find_reg_by_id(sysreg, &params, gic_v3_icc_reg_descs,
 			   ARRAY_SIZE(gic_v3_icc_reg_descs));
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 32e32d67a127..052917deb149 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -419,7 +419,8 @@ int vgic_lazy_init(struct kvm *kvm)
  * Map the MMIO regions depending on the VGIC model exposed to the guest
  * called on the first VCPU run.
  * Also map the virtual CPU interface into the VM.
- * v2/v3 derivatives call vgic_init if not already done.
+ * v2 calls vgic_init() if not already done.
+ * v3 and derivatives return an error if the VGIC is not initialized.
  * vgic_ready() returns true if this function has succeeded.
  * @kvm: kvm struct pointer
  */
@@ -428,7 +429,13 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	int ret = 0;
 
+	if (likely(vgic_ready(kvm)))
+		return 0;
+
 	mutex_lock(&kvm->lock);
+	if (vgic_ready(kvm))
+		goto out;
+
 	if (!irqchip_in_kernel(kvm))
 		goto out;
 
@@ -439,6 +446,8 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 
 	if (ret)
 		__kvm_vgic_destroy(kvm);
+	else
+		dist->ready = true;
 
 out:
 	mutex_unlock(&kvm->lock);
diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c
index ebf53a4e1296..11934c2af2f4 100644
--- a/arch/arm64/kvm/vgic/vgic-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-v2.c
@@ -306,20 +306,15 @@ int vgic_v2_map_resources(struct kvm *kvm)
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	int ret = 0;
 
-	if (vgic_ready(kvm))
-		goto out;
-
 	if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
 	    IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) {
 		kvm_err("Need to set vgic cpu and dist addresses first\n");
-		ret = -ENXIO;
-		goto out;
+		return -ENXIO;
 	}
 
 	if (!vgic_v2_check_base(dist->vgic_dist_base, dist->vgic_cpu_base)) {
 		kvm_err("VGIC CPU and dist frames overlap\n");
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	/*
@@ -329,13 +324,13 @@ int vgic_v2_map_resources(struct kvm *kvm)
 	ret = vgic_init(kvm);
 	if (ret) {
 		kvm_err("Unable to initialize VGIC dynamic data structures\n");
-		goto out;
+		return ret;
 	}
 
 	ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V2);
 	if (ret) {
 		kvm_err("Unable to register VGIC MMIO regions\n");
-		goto out;
+		return ret;
 	}
 
 	if (!static_branch_unlikely(&vgic_v2_cpuif_trap)) {
@@ -344,14 +339,11 @@ int vgic_v2_map_resources(struct kvm *kvm)
 					    KVM_VGIC_V2_CPU_SIZE, true);
 		if (ret) {
 			kvm_err("Unable to remap VGIC CPU to VCPU\n");
-			goto out;
+			return ret;
 		}
 	}
 
-	dist->ready = true;
-
-out:
-	return ret;
+	return 0;
 }
 
 DEFINE_STATIC_KEY_FALSE(vgic_v2_cpuif_trap);
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 9cdf39a94a63..52915b342351 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -500,29 +500,23 @@ int vgic_v3_map_resources(struct kvm *kvm)
 	int ret = 0;
 	int c;
 
-	if (vgic_ready(kvm))
-		goto out;
-
 	kvm_for_each_vcpu(c, vcpu, kvm) {
 		struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
 		if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) {
 			kvm_debug("vcpu %d redistributor base not set\n", c);
-			ret = -ENXIO;
-			goto out;
+			return -ENXIO;
 		}
 	}
 
 	if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) {
 		kvm_err("Need to set vgic distributor addresses first\n");
-		ret = -ENXIO;
-		goto out;
+		return -ENXIO;
 	}
 
 	if (!vgic_v3_check_base(kvm)) {
 		kvm_err("VGIC redist and dist frames overlap\n");
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	/*
@@ -530,22 +524,19 @@ int vgic_v3_map_resources(struct kvm *kvm)
 	 * the VGIC before we need to use it.
 	 */
 	if (!vgic_initialized(kvm)) {
-		ret = -EBUSY;
-		goto out;
+		return -EBUSY;
 	}
 
 	ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V3);
 	if (ret) {
 		kvm_err("Unable to register VGICv3 dist MMIO regions\n");
-		goto out;
+		return ret;
 	}
 
 	if (kvm_vgic_global_state.has_gicv4_1)
 		vgic_v4_configure_vsgis(kvm);
-	dist->ready = true;
 
-out:
-	return ret;
+	return 0;
 }
 
 DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap);
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index b5fa73c9fd35..66508b03094f 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -353,6 +353,18 @@ int vgic_v4_load(struct kvm_vcpu *vcpu)
 	return err;
 }
 
+void vgic_v4_commit(struct kvm_vcpu *vcpu)
+{
+	struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
+
+	/*
+	 * No need to wait for the vPE to be ready across a shallow guest
+	 * exit, as only a vcpu_put will invalidate it.
+	 */
+	if (!vpe->ready)
+		its_commit_vpe(vpe);
+}
+
 static struct vgic_its *vgic_get_its(struct kvm *kvm,
 				     struct kvm_kernel_irq_routing_entry *irq_entry)
 {
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index c3643b7f101b..1c597c9885fa 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -915,6 +915,9 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 
 	if (can_access_vgic_from_kernel())
 		vgic_restore_state(vcpu);
+
+	if (vgic_supports_direct_msis(vcpu->kvm))
+		vgic_v4_commit(vcpu);
 }
 
 void kvm_vgic_load(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/lib/mte.S b/arch/arm64/lib/mte.S
index 351537c12f36..9e1a12e10053 100644
--- a/arch/arm64/lib/mte.S
+++ b/arch/arm64/lib/mte.S
@@ -149,3 +149,19 @@ SYM_FUNC_START(mte_restore_page_tags)
 
 	ret
 SYM_FUNC_END(mte_restore_page_tags)
+
+/*
+ * Assign allocation tags for a region of memory based on the pointer tag
+ *   x0 - source pointer
+ *   x1 - size
+ *
+ * Note: The address must be non-NULL and MTE_GRANULE_SIZE aligned and
+ * size must be non-zero and MTE_GRANULE_SIZE aligned.
+ */
+SYM_FUNC_START(mte_assign_mem_tag_range)
+1:	stg	x0, [x0]
+	add	x0, x0, #MTE_GRANULE_SIZE
+	subs	x1, x1, #MTE_GRANULE_SIZE
+	b.gt	1b
+	ret
+SYM_FUNC_END(mte_assign_mem_tag_range)
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index 70a71f38b6a9..b5447e53cd73 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -23,6 +23,15 @@ void copy_highpage(struct page *to, struct page *from)
 
 	if (system_supports_mte() && test_bit(PG_mte_tagged, &from->flags)) {
 		set_bit(PG_mte_tagged, &to->flags);
+		page_kasan_tag_reset(to);
+		/*
+		 * We need smp_wmb() in between setting the flags and clearing the
+		 * tags because if another thread reads page->flags and builds a
+		 * tagged address out of it, there is an actual dependency to the
+		 * memory access, but on the current thread we do not guarantee that
+		 * the new page->flags are visible before the tags were updated.
+		 */
+		smp_wmb();
 		mte_copy_page_tags(kto, kfrom);
 	}
 }
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 2848952b178d..3c40da479899 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -14,6 +14,7 @@
 #include <linux/mm.h>
 #include <linux/hardirq.h>
 #include <linux/init.h>
+#include <linux/kasan.h>
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
 #include <linux/page-flags.h>
@@ -33,6 +34,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/kprobes.h>
+#include <asm/mte.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
 #include <asm/system_misc.h>
@@ -296,6 +298,57 @@ static void die_kernel_fault(const char *msg, unsigned long addr,
 	do_exit(SIGKILL);
 }
 
+#ifdef CONFIG_KASAN_HW_TAGS
+static void report_tag_fault(unsigned long addr, unsigned int esr,
+			     struct pt_regs *regs)
+{
+	bool is_write  = ((esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT) != 0;
+
+	/*
+	 * SAS bits aren't set for all faults reported in EL1, so we can't
+	 * find out access size.
+	 */
+	kasan_report(addr, 0, is_write, regs->pc);
+}
+#else
+/* Tag faults aren't enabled without CONFIG_KASAN_HW_TAGS. */
+static inline void report_tag_fault(unsigned long addr, unsigned int esr,
+				    struct pt_regs *regs) { }
+#endif
+
+static void do_tag_recovery(unsigned long addr, unsigned int esr,
+			   struct pt_regs *regs)
+{
+	static bool reported;
+
+	if (!READ_ONCE(reported)) {
+		report_tag_fault(addr, esr, regs);
+		WRITE_ONCE(reported, true);
+	}
+
+	/*
+	 * Disable MTE Tag Checking on the local CPU for the current EL.
+	 * It will be done lazily on the other CPUs when they will hit a
+	 * tag fault.
+	 */
+	sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, SCTLR_ELx_TCF_NONE);
+	isb();
+}
+
+static bool is_el1_mte_sync_tag_check_fault(unsigned int esr)
+{
+	unsigned int ec = ESR_ELx_EC(esr);
+	unsigned int fsc = esr & ESR_ELx_FSC;
+
+	if (ec != ESR_ELx_EC_DABT_CUR)
+		return false;
+
+	if (fsc == ESR_ELx_FSC_MTE)
+		return true;
+
+	return false;
+}
+
 static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
@@ -312,6 +365,12 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 	    "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr))
 		return;
 
+	if (is_el1_mte_sync_tag_check_fault(esr)) {
+		do_tag_recovery(addr, esr, regs);
+
+		return;
+	}
+
 	if (is_el1_permission_fault(addr, esr, regs)) {
 		if (esr & ESR_ELx_WNR)
 			msg = "write to read-only memory";
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 75addb36354a..709d98fea90c 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -53,13 +53,13 @@ s64 memstart_addr __ro_after_init = -1;
 EXPORT_SYMBOL(memstart_addr);
 
 /*
- * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of
- * memory as some devices, namely the Raspberry Pi 4, have peripherals with
- * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32
- * bit addressable memory area.
+ * If the corresponding config options are enabled, we create both ZONE_DMA
+ * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory
+ * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
+ * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
+ * otherwise it is empty.
  */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
-static phys_addr_t arm64_dma32_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -84,7 +84,7 @@ static void __init reserve_crashkernel(void)
 
 	if (crash_base == 0) {
 		/* Current arm64 boot protocol requires 2MB alignment */
-		crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
+		crash_base = memblock_find_in_range(0, arm64_dma_phys_limit,
 				crash_size, SZ_2M);
 		if (crash_base == 0) {
 			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -196,6 +196,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
 	unsigned int __maybe_unused acpi_zone_dma_bits;
 	unsigned int __maybe_unused dt_zone_dma_bits;
+	phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32);
 
 #ifdef CONFIG_ZONE_DMA
 	acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
@@ -205,8 +206,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
 #endif
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
+	if (!arm64_dma_phys_limit)
+		arm64_dma_phys_limit = dma32_phys_limit;
 #endif
+	if (!arm64_dma_phys_limit)
+		arm64_dma_phys_limit = PHYS_MASK + 1;
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init(max_zone_pfns);
@@ -394,16 +399,9 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA32))
-		arm64_dma32_phys_limit = max_zone_phys(32);
-	else
-		arm64_dma32_phys_limit = PHYS_MASK + 1;
-
 	reserve_elfcorehdr();
 
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
-
-	dma_contiguous_reserve(arm64_dma32_phys_limit);
 }
 
 void __init bootmem_init(void)
@@ -439,6 +437,11 @@ void __init bootmem_init(void)
 	zone_sizes_init(min, max);
 
 	/*
+	 * Reserve the CMA area after arm64_dma_phys_limit was initialised.
+	 */
+	dma_contiguous_reserve(arm64_dma_phys_limit);
+
+	/*
 	 * request_standard_resources() depends on crashkernel's memory being
 	 * reserved, so do it here.
 	 */
@@ -455,7 +458,7 @@ void __init bootmem_init(void)
 void __init mem_init(void)
 {
 	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
+	    max_pfn > PFN_DOWN(arm64_dma_phys_limit))
 		swiotlb_init(1);
 	else
 		swiotlb_force = SWIOTLB_NO_FORCE;
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index b24e43d20667..d8e66c78440e 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -21,6 +21,8 @@
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
 
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+
 static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE);
 
 /*
@@ -208,7 +210,7 @@ static void __init clear_pgds(unsigned long start,
 		set_pgd(pgd_offset_k(start), __pgd(0));
 }
 
-void __init kasan_init(void)
+static void __init kasan_init_shadow(void)
 {
 	u64 kimg_shadow_start, kimg_shadow_end;
 	u64 mod_shadow_start, mod_shadow_end;
@@ -269,8 +271,21 @@ void __init kasan_init(void)
 
 	memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE);
 	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+}
 
-	/* At this point kasan is fully initialized. Enable error messages */
+static void __init kasan_init_depth(void)
+{
 	init_task.kasan_depth = 0;
+}
+
+void __init kasan_init(void)
+{
+	kasan_init_shadow();
+	kasan_init_depth();
+#if defined(CONFIG_KASAN_GENERIC)
+	/* CONFIG_KASAN_SW_TAGS also requires kasan_init_sw_tags(). */
 	pr_info("KernelAddressSanitizer initialized\n");
+#endif
 }
+
+#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c
index c52c1847079c..7c4ef56265ee 100644
--- a/arch/arm64/mm/mteswap.c
+++ b/arch/arm64/mm/mteswap.c
@@ -53,6 +53,15 @@ bool mte_restore_tags(swp_entry_t entry, struct page *page)
 	if (!tags)
 		return false;
 
+	page_kasan_tag_reset(page);
+	/*
+	 * We need smp_wmb() in between setting the flags and clearing the
+	 * tags because if another thread reads page->flags and builds a
+	 * tagged address out of it, there is an actual dependency to the
+	 * memory access, but on the current thread we do not guarantee that
+	 * the new page->flags are visible before the tags were updated.
+	 */
+	smp_wmb();
 	mte_restore_page_tags(page_address(page), tags);
 
 	return true;
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index a0831bf8a018..1f7ee8c8b7b8 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -40,9 +40,15 @@
 #define TCR_CACHE_FLAGS	TCR_IRGN_WBWA | TCR_ORGN_WBWA
 
 #ifdef CONFIG_KASAN_SW_TAGS
-#define TCR_KASAN_FLAGS TCR_TBI1 | TCR_TBID1
+#define TCR_KASAN_SW_FLAGS TCR_TBI1 | TCR_TBID1
 #else
-#define TCR_KASAN_FLAGS 0
+#define TCR_KASAN_SW_FLAGS 0
+#endif
+
+#ifdef CONFIG_KASAN_HW_TAGS
+#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1
+#else
+#define TCR_KASAN_HW_FLAGS 0
 #endif
 
 /*
@@ -427,6 +433,10 @@ SYM_FUNC_START(__cpu_setup)
 	 */
 	mov_q	x5, MAIR_EL1_SET
 #ifdef CONFIG_ARM64_MTE
+	mte_tcr	.req	x20
+
+	mov	mte_tcr, #0
+
 	/*
 	 * Update MAIR_EL1, GCR_EL1 and TFSR*_EL1 if MTE is supported
 	 * (ID_AA64PFR1_EL1[11:8] > 1).
@@ -447,6 +457,9 @@ SYM_FUNC_START(__cpu_setup)
 	/* clear any pending tag check faults in TFSR*_EL1 */
 	msr_s	SYS_TFSR_EL1, xzr
 	msr_s	SYS_TFSRE0_EL1, xzr
+
+	/* set the TCR_EL1 bits */
+	mov_q	mte_tcr, TCR_KASAN_HW_FLAGS
 1:
 #endif
 	msr	mair_el1, x5
@@ -456,7 +469,11 @@ SYM_FUNC_START(__cpu_setup)
 	 */
 	mov_q	x10, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
 			TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \
-			TCR_TBI0 | TCR_A1 | TCR_KASAN_FLAGS
+			TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS
+#ifdef CONFIG_ARM64_MTE
+	orr	x10, x10, mte_tcr
+	.unreq	mte_tcr
+#endif
 	tcr_clear_errata_bits x10, x9, x5
 
 #ifdef CONFIG_ARM64_VA_BITS_52
diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c
index 807dc634bbd2..04137a8f3d2d 100644
--- a/arch/arm64/mm/ptdump.c
+++ b/arch/arm64/mm/ptdump.c
@@ -29,7 +29,7 @@
 enum address_markers_idx {
 	PAGE_OFFSET_NR = 0,
 	PAGE_END_NR,
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	KASAN_START_NR,
 #endif
 };
@@ -37,7 +37,7 @@ enum address_markers_idx {
 static struct addr_marker address_markers[] = {
 	{ PAGE_OFFSET,			"Linear Mapping start" },
 	{ 0 /* PAGE_END */,		"Linear Mapping end" },
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	{ 0 /* KASAN_SHADOW_START */,	"Kasan shadow start" },
 	{ KASAN_SHADOW_END,		"Kasan shadow end" },
 #endif
@@ -383,7 +383,7 @@ void ptdump_check_wx(void)
 static int ptdump_init(void)
 {
 	address_markers[PAGE_END_NR].start_address = PAGE_END;
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	address_markers[KASAN_START_NR].start_address = KASAN_SHADOW_START;
 #endif
 	ptdump_initialize();
diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild
index 93372255984d..cc24bb8e539f 100644
--- a/arch/csky/include/asm/Kbuild
+++ b/arch/csky/include/asm/Kbuild
@@ -2,7 +2,6 @@
 generic-y += asm-offsets.h
 generic-y += gpio.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += qrwlock.h
 generic-y += user.h
 generic-y += vmlinux.lds.h
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index ddf04f32b546..60ee7f0d60a8 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -2,7 +2,6 @@
 generic-y += asm-offsets.h
 generic-y += extable.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h
 generic-y += spinlock.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 373964bb177e..3ece3c93fe08 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -2,5 +2,4 @@
 generic-y += extable.h
 generic-y += iomap.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
diff --git a/arch/ia64/include/asm/local64.h b/arch/ia64/include/asm/local64.h
deleted file mode 100644
index 36c93b5cc239..000000000000
--- a/arch/ia64/include/asm/local64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/local64.h>
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 9b5acf8fb092..e76386a3479e 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -536,7 +536,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
 
 	if (map_start < map_end)
 		memmap_init_zone((unsigned long)(map_end - map_start),
-				 args->nid, args->zone, page_to_pfn(map_start),
+				 args->nid, args->zone, page_to_pfn(map_start), page_to_pfn(map_end),
 				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	return 0;
 }
@@ -546,7 +546,7 @@ memmap_init (unsigned long size, int nid, unsigned long zone,
 	     unsigned long start_pfn)
 {
 	if (!vmem_map) {
-		memmap_init_zone(size, nid, zone, start_pfn,
+		memmap_init_zone(size, nid, zone, start_pfn, start_pfn + size,
 				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	} else {
 		struct page *start;
diff --git a/arch/ia64/scripts/unwcheck.py b/arch/ia64/scripts/unwcheck.py
index c55276e31b6b..bfd1b671e35f 100644
--- a/arch/ia64/scripts/unwcheck.py
+++ b/arch/ia64/scripts/unwcheck.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 # SPDX-License-Identifier: GPL-2.0
 #
 # Usage: unwcheck.py FILE
diff --git a/arch/m68k/68000/Makefile b/arch/m68k/68000/Makefile
index 4f7d4b45a46f..674541fdf5b8 100644
--- a/arch/m68k/68000/Makefile
+++ b/arch/m68k/68000/Makefile
@@ -10,10 +10,11 @@
 
 # 68328, 68EZ328, 68VZ328
 
-obj-y			+= entry.o ints.o timers.o
-obj-$(CONFIG_M68328)	+= m68328.o
-obj-$(CONFIG_M68EZ328)	+= m68EZ328.o
-obj-$(CONFIG_M68VZ328)	+= m68VZ328.o
+obj-y			+= entry.o ints.o timers.o m68328.o
 obj-$(CONFIG_ROM)	+= romvec.o
 
+obj-$(CONFIG_DRAGEN2)	+= dragen2.o
+obj-$(CONFIG_UCSIMM)	+= ucsimm.o
+obj-$(CONFIG_UCDIMM)	+= ucsimm.o
+
 extra-y 		:= head.o
diff --git a/arch/m68k/68000/dragen2.c b/arch/m68k/68000/dragen2.c
new file mode 100644
index 000000000000..584893c57c37
--- /dev/null
+++ b/arch/m68k/68000/dragen2.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 1993 Hamish Macdonald
+ *  Copyright (C) 1999 D. Jeff Dionne
+ *  Copyright (C) 2001 Georges Menie, Ken Desmet
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
+#include <linux/init.h>
+#include <asm/machdep.h>
+#include <asm/MC68VZ328.h>
+
+/***************************************************************************/
+/*                        Init Drangon Engine hardware                     */
+/***************************************************************************/
+
+static void dragen2_reset(void)
+{
+	local_irq_disable();
+
+#ifdef CONFIG_INIT_LCD
+	PBDATA |= 0x20;				/* disable CCFL light */
+	PKDATA |= 0x4;				/* disable LCD controller */
+	LCKCON = 0;
+#endif
+
+	__asm__ __volatile__(
+		"reset\n\t"
+		"moveal #0x04000000, %a0\n\t"
+		"moveal 0(%a0), %sp\n\t"
+		"moveal 4(%a0), %a0\n\t"
+		"jmp (%a0)"
+	);
+}
+
+void __init init_dragen2(char *command, int size)
+{
+	mach_reset = dragen2_reset;
+
+#ifdef CONFIG_DIRECT_IO_ACCESS
+	SCR = 0x10;					/* allow user access to internal registers */
+#endif
+
+	/* CSGB Init */
+	CSGBB = 0x4000;
+	CSB = 0x1a1;
+
+	/* CS8900 init */
+	/* PK3: hardware sleep function pin, active low */
+	PKSEL |= PK(3);				/* select pin as I/O */
+	PKDIR |= PK(3);				/* select pin as output */
+	PKDATA |= PK(3);			/* set pin high */
+
+	/* PF5: hardware reset function pin, active high */
+	PFSEL |= PF(5);				/* select pin as I/O */
+	PFDIR |= PF(5);				/* select pin as output */
+	PFDATA &= ~PF(5);			/* set pin low */
+
+	/* cs8900 hardware reset */
+	PFDATA |= PF(5);
+	{ int i; for (i = 0; i < 32000; ++i); }
+	PFDATA &= ~PF(5);
+
+	/* INT1 enable (cs8900 IRQ) */
+	PDPOL &= ~PD(1);			/* active high signal */
+	PDIQEG &= ~PD(1);
+	PDIRQEN |= PD(1);			/* IRQ enabled */
+
+#ifdef CONFIG_INIT_LCD
+	/* initialize LCD controller */
+	LSSA = (long) screen_bits;
+	LVPW = 0x14;
+	LXMAX = 0x140;
+	LYMAX = 0xef;
+	LRRA = 0;
+	LPXCD = 3;
+	LPICF = 0x08;
+	LPOLCF = 0;
+	LCKCON = 0x80;
+	PCPDEN = 0xff;
+	PCSEL = 0;
+
+	/* Enable LCD controller */
+	PKDIR |= 0x4;
+	PKSEL |= 0x4;
+	PKDATA &= ~0x4;
+
+	/* Enable CCFL backlighting circuit */
+	PBDIR |= 0x20;
+	PBSEL |= 0x20;
+	PBDATA &= ~0x20;
+
+	/* contrast control register */
+	PFDIR |= 0x1;
+	PFSEL &= ~0x1;
+	PWMR = 0x037F;
+#endif
+}
diff --git a/arch/m68k/68000/m68328.c b/arch/m68k/68000/m68328.c
index 419751b15ec8..eab08da058c6 100644
--- a/arch/m68k/68000/m68328.c
+++ b/arch/m68k/68000/m68328.c
@@ -1,10 +1,11 @@
 /***************************************************************************/
 
 /*
- *  m68328.c - 68328 specific config
+ *  m68328.c - 68328/68EZ328/68VZ328 specific config
  *
  *  Copyright (C) 1993 Hamish Macdonald
  *  Copyright (C) 1999 D. Jeff Dionne
+ *  Copyright (C) 2001 Georges Menie, Ken Desmet
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file COPYING in the main directory of this archive
@@ -20,18 +21,18 @@
 #include <linux/kernel.h>
 #include <linux/rtc.h>
 #include <asm/machdep.h>
-#include <asm/MC68328.h>
-#if defined(CONFIG_PILOT) || defined(CONFIG_INIT_LCD)
+
+#if defined(CONFIG_INIT_LCD) && defined(CONFIG_M68VZ328)
+#include "bootlogo-vz.h"
+#elif defined(CONFIG_PILOT) || defined(CONFIG_INIT_LCD)
 #include "bootlogo.h"
 #endif
 
-/***************************************************************************/
-
-int m68328_hwclk(int set, struct rtc_time *t);
+#include "m68328.h"
 
 /***************************************************************************/
 
-void m68328_reset (void)
+static void m68328_reset(void)
 {
   local_irq_disable();
   asm volatile ("moveal #0x10c00000, %a0;\n\t"
@@ -45,12 +46,19 @@ void m68328_reset (void)
 
 void __init config_BSP(char *command, int len)
 {
-  pr_info("68328 support D. Jeff Dionne <jeff@uclinux.org>\n");
-  pr_info("68328 support Kenneth Albanowski <kjahds@kjshds.com>\n");
-  pr_info("68328/Pilot support Bernhard Kuhn <kuhn@lpr.e-technik.tu-muenchen.de>\n");
+	mach_sched_init = hw_timer_init;
+	mach_hwclk = m68328_hwclk;
+	mach_reset = m68328_reset;
 
-  mach_hwclk = m68328_hwclk;
-  mach_reset = m68328_reset;
+#if   defined(CONFIG_PILOT) && defined(CONFIG_M68328)
+	mach_sched_init = NULL;
+#elif defined(CONFIG_UCSIMM)
+	init_ucsimm(command, len);
+#elif defined(CONFIG_UCDIMM)
+	init_ucsimm(command, len);
+#elif defined(CONFIG_DRAGEN2)
+	init_dragen2(command, len);
+#endif
 }
 
 /***************************************************************************/
diff --git a/arch/m68k/68000/m68328.h b/arch/m68k/68000/m68328.h
new file mode 100644
index 000000000000..f6047c3168d4
--- /dev/null
+++ b/arch/m68k/68000/m68328.h
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+void init_dragen2(char *command, int size);
+void init_ucsimm(char *command, int size);
+struct rtc_time;
+int m68328_hwclk(int set, struct rtc_time *t);
diff --git a/arch/m68k/68000/m68EZ328.c b/arch/m68k/68000/m68EZ328.c
deleted file mode 100644
index 05f137dc257e..000000000000
--- a/arch/m68k/68000/m68EZ328.c
+++ /dev/null
@@ -1,77 +0,0 @@
-/***************************************************************************/
-
-/*
- *  m68EZ328.c - 68EZ328 specific config
- *
- *  Copyright (C) 1993 Hamish Macdonald
- *  Copyright (C) 1999 D. Jeff Dionne
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-
-/***************************************************************************/
-
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/rtc.h>
-#include <linux/pgtable.h>
-#include <asm/machdep.h>
-#include <asm/MC68EZ328.h>
-#ifdef CONFIG_UCSIMM
-#include <asm/bootstd.h>
-#endif
-
-/***************************************************************************/
-
-int m68328_hwclk(int set, struct rtc_time *t);
-
-/***************************************************************************/
-
-void m68ez328_reset(void)
-{
-  local_irq_disable();
-  asm volatile (
-    "moveal #0x10c00000, %a0;\n"
-    "moveb #0, 0xFFFFF300;\n"
-    "moveal 0(%a0), %sp;\n"
-    "moveal 4(%a0), %a0;\n"
-    "jmp (%a0);\n"
-    );
-}
-
-/***************************************************************************/
-
-unsigned char *cs8900a_hwaddr;
-static int errno;
-
-#ifdef CONFIG_UCSIMM
-_bsc0(char *, getserialnum)
-_bsc1(unsigned char *, gethwaddr, int, a)
-_bsc1(char *, getbenv, char *, a)
-#endif
-
-void __init config_BSP(char *command, int len)
-{
-  unsigned char *p;
-
-  pr_info("68EZ328 DragonBallEZ support (C) 1999 Rt-Control, Inc\n");
-
-#ifdef CONFIG_UCSIMM
-  pr_info("uCsimm serial string [%s]\n", getserialnum());
-  p = cs8900a_hwaddr = gethwaddr(0);
-  pr_info("uCsimm hwaddr %pM\n", p);
-
-  p = getbenv("APPEND");
-  if (p) strcpy(p,command);
-  else command[0] = 0;
-#endif
-
-  mach_sched_init = hw_timer_init;
-  mach_hwclk = m68328_hwclk;
-  mach_reset = m68ez328_reset;
-}
-
-/***************************************************************************/
diff --git a/arch/m68k/68000/m68VZ328.c b/arch/m68k/68000/m68VZ328.c
deleted file mode 100644
index ada87b23afdc..000000000000
--- a/arch/m68k/68000/m68VZ328.c
+++ /dev/null
@@ -1,189 +0,0 @@
-/***************************************************************************/
-
-/*
- *  m68VZ328.c - 68VZ328 specific config
- *
- *  Copyright (C) 1993 Hamish Macdonald
- *  Copyright (C) 1999 D. Jeff Dionne
- *  Copyright (C) 2001 Georges Menie, Ken Desmet
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-
-/***************************************************************************/
-
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/kd.h>
-#include <linux/netdevice.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/rtc.h>
-#include <linux/pgtable.h>
-
-#include <asm/machdep.h>
-#include <asm/MC68VZ328.h>
-#include <asm/bootstd.h>
-
-#ifdef CONFIG_INIT_LCD
-#include "bootlogo-vz.h"
-#endif
-
-/***************************************************************************/
-
-int m68328_hwclk(int set, struct rtc_time *t);
-
-/***************************************************************************/
-/*                        Init Drangon Engine hardware                     */
-/***************************************************************************/
-#if defined(CONFIG_DRAGEN2)
-
-static void m68vz328_reset(void)
-{
-	local_irq_disable();
-
-#ifdef CONFIG_INIT_LCD
-	PBDATA |= 0x20;				/* disable CCFL light */
-	PKDATA |= 0x4;				/* disable LCD controller */
-	LCKCON = 0;
-#endif
-
-	__asm__ __volatile__(
-		"reset\n\t"
-		"moveal #0x04000000, %a0\n\t"
-		"moveal 0(%a0), %sp\n\t"
-		"moveal 4(%a0), %a0\n\t"
-		"jmp (%a0)"
-	);
-}
-
-static void __init init_hardware(char *command, int size)
-{
-#ifdef CONFIG_DIRECT_IO_ACCESS
-	SCR = 0x10;					/* allow user access to internal registers */
-#endif
-
-	/* CSGB Init */
-	CSGBB = 0x4000;
-	CSB = 0x1a1;
-
-	/* CS8900 init */
-	/* PK3: hardware sleep function pin, active low */
-	PKSEL |= PK(3);				/* select pin as I/O */
-	PKDIR |= PK(3);				/* select pin as output */
-	PKDATA |= PK(3);			/* set pin high */
-
-	/* PF5: hardware reset function pin, active high */
-	PFSEL |= PF(5);				/* select pin as I/O */
-	PFDIR |= PF(5);				/* select pin as output */
-	PFDATA &= ~PF(5);			/* set pin low */
-
-	/* cs8900 hardware reset */
-	PFDATA |= PF(5);
-	{ int i; for (i = 0; i < 32000; ++i); }
-	PFDATA &= ~PF(5);
-
-	/* INT1 enable (cs8900 IRQ) */
-	PDPOL &= ~PD(1);			/* active high signal */
-	PDIQEG &= ~PD(1);
-	PDIRQEN |= PD(1);			/* IRQ enabled */
-
-#ifdef CONFIG_INIT_LCD
-	/* initialize LCD controller */
-	LSSA = (long) screen_bits;
-	LVPW = 0x14;
-	LXMAX = 0x140;
-	LYMAX = 0xef;
-	LRRA = 0;
-	LPXCD = 3;
-	LPICF = 0x08;
-	LPOLCF = 0;
-	LCKCON = 0x80;
-	PCPDEN = 0xff;
-	PCSEL = 0;
-
-	/* Enable LCD controller */
-	PKDIR |= 0x4;
-	PKSEL |= 0x4;
-	PKDATA &= ~0x4;
-
-	/* Enable CCFL backlighting circuit */
-	PBDIR |= 0x20;
-	PBSEL |= 0x20;
-	PBDATA &= ~0x20;
-
-	/* contrast control register */
-	PFDIR |= 0x1;
-	PFSEL &= ~0x1;
-	PWMR = 0x037F;
-#endif
-}
-
-/***************************************************************************/
-/*                      Init RT-Control uCdimm hardware                    */
-/***************************************************************************/
-#elif defined(CONFIG_UCDIMM)
-
-static void m68vz328_reset(void)
-{
-	local_irq_disable();
-	asm volatile (
-		"moveal #0x10c00000, %a0;\n\t"
-		"moveb #0, 0xFFFFF300;\n\t"
-		"moveal 0(%a0), %sp;\n\t"
-		"moveal 4(%a0), %a0;\n\t"
-		"jmp (%a0);\n"
-	);
-}
-
-unsigned char *cs8900a_hwaddr;
-static int errno;
-
-_bsc0(char *, getserialnum)
-_bsc1(unsigned char *, gethwaddr, int, a)
-_bsc1(char *, getbenv, char *, a)
-
-static void __init init_hardware(char *command, int size)
-{
-	char *p;
-
-	pr_info("uCdimm serial string [%s]\n", getserialnum());
-	p = cs8900a_hwaddr = gethwaddr(0);
-	pr_info("uCdimm hwaddr %pM\n", p);
-	p = getbenv("APPEND");
-	if (p)
-		strcpy(p, command);
-	else
-		command[0] = 0;
-}
-
-/***************************************************************************/
-#else
-
-static void m68vz328_reset(void)
-{
-}
-
-static void __init init_hardware(char *command, int size)
-{
-}
-
-/***************************************************************************/
-#endif
-/***************************************************************************/
-
-void __init config_BSP(char *command, int size)
-{
-	pr_info("68VZ328 DragonBallVZ support (c) 2001 Lineo, Inc.\n");
-
-	init_hardware(command, size);
-
-	mach_sched_init = hw_timer_init;
-	mach_hwclk = m68328_hwclk;
-	mach_reset = m68vz328_reset;
-}
-
-/***************************************************************************/
diff --git a/arch/m68k/68000/ucsimm.c b/arch/m68k/68000/ucsimm.c
new file mode 100644
index 000000000000..7c6cbf643712
--- /dev/null
+++ b/arch/m68k/68000/ucsimm.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 1993 Hamish Macdonald
+ *  Copyright (C) 1999 D. Jeff Dionne
+ *  Copyright (C) 2001 Georges Menie, Ken Desmet
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
+#include <linux/init.h>
+#include <asm/bootstd.h>
+#include <asm/machdep.h>
+#include <asm/MC68VZ328.h>
+
+
+#include "m68328.h"
+
+unsigned char *cs8900a_hwaddr;
+static int errno;
+
+_bsc0(char *, getserialnum)
+_bsc1(unsigned char *, gethwaddr, int, a)
+_bsc1(char *, getbenv, char *, a)
+
+void __init init_ucsimm(char *command, int size)
+{
+	char *p;
+
+	pr_info("uCsimm/uCdimm serial string [%s]\n", getserialnum());
+	p = cs8900a_hwaddr = gethwaddr(0);
+	pr_info("uCsimm/uCdimm hwaddr %pM\n", p);
+	p = getbenv("APPEND");
+	if (p)
+		strcpy(p, command);
+	else
+		command[0] = 0;
+}
diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
index 7246aa50298e..f4d23977d2a5 100644
--- a/arch/m68k/Kconfig.cpu
+++ b/arch/m68k/Kconfig.cpu
@@ -36,7 +36,7 @@ endchoice
 if M68KCLASSIC
 
 config M68000
-	bool "MC68000"
+	bool
 	depends on !MMU
 	select CPU_HAS_NO_BITFIELDS
 	select CPU_HAS_NO_MULDIV64
@@ -103,7 +103,7 @@ config M68060
 	  processor, say Y. Otherwise, say N.
 
 config M68328
-	bool "MC68328"
+	bool
 	depends on !MMU
 	select LEGACY_TIMER_TICK
 	select M68000
@@ -111,7 +111,7 @@ config M68328
 	  Motorola 68328 processor support.
 
 config M68EZ328
-	bool "MC68EZ328"
+	bool
 	depends on !MMU
 	select LEGACY_TIMER_TICK
 	select M68000
@@ -119,7 +119,7 @@ config M68EZ328
 	  Motorola 68EX328 processor support.
 
 config M68VZ328
-	bool "MC68VZ328"
+	bool
 	depends on !MMU
 	select LEGACY_TIMER_TICK
 	select M68000
diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine
index cf6961d4e657..4d59ec2f5b8d 100644
--- a/arch/m68k/Kconfig.machine
+++ b/arch/m68k/Kconfig.machine
@@ -145,14 +145,13 @@ config SUN3
 
 	  If you don't want to compile a kernel exclusively for a Sun 3, say N.
 
-endif # M68KCLASSIC
-
 config PILOT
 	bool
 
 config PILOT3
 	bool "Pilot 1000/5000, PalmPilot Personal/Pro, or PalmIII support"
-	depends on M68328
+	depends on !MMU
+	select M68328
 	select PILOT
 	help
 	  Support for the Palm Pilot 1000/5000, Personal/Pro and PalmIII.
@@ -165,19 +164,22 @@ config XCOPILOT_BUGS
 
 config UCSIMM
 	bool "uCsimm module support"
-	depends on M68EZ328
+	depends on !MMU
+	select M68EZ328
 	help
 	  Support for the Arcturus Networks uCsimm module.
 
 config UCDIMM
 	bool "uDsimm module support"
-	depends on M68VZ328
+	depends on !MMU
+	select M68VZ328
 	help
 	  Support for the Arcturus Networks uDsimm module.
 
 config DRAGEN2
 	bool "DragenEngine II board support"
-	depends on M68VZ328
+	depends on !MMU
+	select M68VZ328
 	help
 	  Support for the DragenEngine II board.
 
@@ -200,6 +202,8 @@ config MEMORY_RESERVE
 	help
 	  Reserve certain memory regions on 68x328 based boards.
 
+endif # M68KCLASSIC
+
 config ARN5206
 	bool "Arnewsh 5206 board support"
 	depends on M5206
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 1bff55aa2d54..0dbf9c5c6fae 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -2,6 +2,5 @@
 generated-y += syscall_table.h
 generic-y += extable.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += spinlock.h
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index e377b4219528..d1b7988efc91 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -106,8 +106,16 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_UCDIMM
 	pr_info("uCdimm by Lineo, Inc. <www.lineo.com>\n");
 #endif
+#ifdef CONFIG_M68328
+	pr_info("68328 support D. Jeff Dionne <jeff@uclinux.org>\n");
+	pr_info("68328 support Kenneth Albanowski <kjahds@kjshds.com>\n");
+#endif
+#ifdef CONFIG_M68EZ328
+	pr_info("68EZ328 DragonBallEZ support (C) 1999 Rt-Control, Inc\n");
+#endif
 #ifdef CONFIG_M68VZ328
 	pr_info("M68VZ328 support by Evan Stawnyczy <e@lineo.ca>\n");
+	pr_info("68VZ328 DragonBallVZ support (c) 2001 Lineo, Inc.\n");
 #endif
 #ifdef CONFIG_COLDFIRE
 	pr_info("COLDFIRE port done by Greg Ungerer, gerg@snapgear.com\n");
@@ -121,6 +129,7 @@ void __init setup_arch(char **cmdline_p)
 	pr_info("Flat model support (C) 1998,1999 Kenneth Albanowski, D. Jeff Dionne\n");
 
 #if defined( CONFIG_PILOT ) && defined( CONFIG_M68328 )
+	pr_info("68328/Pilot support Bernhard Kuhn <kuhn@lpr.e-technik.tu-muenchen.de>\n");
 	pr_info("TRG SuperPilot FLASH card support <info@trgnet.com>\n");
 #endif
 #if defined( CONFIG_PILOT ) && defined( CONFIG_M68EZ328 )
diff --git a/arch/m68k/kernel/vmlinux-nommu.lds b/arch/m68k/kernel/vmlinux-nommu.lds
index 396e126a4258..387f334e87d3 100644
--- a/arch/m68k/kernel/vmlinux-nommu.lds
+++ b/arch/m68k/kernel/vmlinux-nommu.lds
@@ -81,7 +81,7 @@ SECTIONS {
 		__init_end = .;
 	}
 
-	BSS_SECTION(0, 0, 0)
+	BSS_SECTION(4, 0, 4)
 
 	_end = .;
 
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 63bce836b9f1..29b0e557aa7c 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -2,7 +2,6 @@
 generated-y += syscall_table.h
 generic-y += extable.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h
 generic-y += syscalls.h
diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index c61c641674e6..e3946b06e840 100644
--- a/arch/mips/boot/compressed/decompress.c
+++ b/arch/mips/boot/compressed/decompress.c
@@ -13,6 +13,7 @@
 #include <linux/libfdt.h>
 
 #include <asm/addrspace.h>
+#include <asm/unaligned.h>
 
 /*
  * These two variables specify the free mem region
@@ -117,7 +118,7 @@ void decompress_kernel(unsigned long boot_heap_start)
 		dtb_size = fdt_totalsize((void *)&__appended_dtb);
 
 		/* last four bytes is always image size in little endian */
-		image_size = le32_to_cpup((void *)&__image_end - 4);
+		image_size = get_unaligned_le32((void *)&__image_end - 4);
 
 		/* copy dtb to where the booted kernel will expect it */
 		memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size,
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index bd47e15d02c7..be5d4afcd30f 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -1444,7 +1444,7 @@ static void octeon_irq_setup_secondary_ciu2(void)
 static int __init octeon_irq_init_ciu(
 	struct device_node *ciu_node, struct device_node *parent)
 {
-	unsigned int i, r;
+	int i, r;
 	struct irq_chip *chip;
 	struct irq_chip *chip_edge;
 	struct irq_chip *chip_mbox;
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 198b3bafdac9..95b4fa7bd0d1 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -6,7 +6,6 @@ generated-y += syscall_table_64_n64.h
 generated-y += syscall_table_64_o32.h
 generic-y += export.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h
 generic-y += qrwlock.h
diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c
index 6ee3f7218c67..c4441416e96b 100644
--- a/arch/mips/kernel/binfmt_elfn32.c
+++ b/arch/mips/kernel/binfmt_elfn32.c
@@ -103,4 +103,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value)
 #undef ns_to_kernel_old_timeval
 #define ns_to_kernel_old_timeval ns_to_old_timeval32
 
+/*
+ * Some data types as stored in coredump.
+ */
+#define user_long_t             compat_long_t
+#define user_siginfo_t          compat_siginfo_t
+#define copy_siginfo_to_external        copy_siginfo_to_external32
+
 #include "../../../fs/binfmt_elf.c"
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 6dd103d3cebb..7b2a23f48c1a 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -106,4 +106,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value)
 #undef ns_to_kernel_old_timeval
 #define ns_to_kernel_old_timeval ns_to_old_timeval32
 
+/*
+ * Some data types as stored in coredump.
+ */
+#define user_long_t             compat_long_t
+#define user_siginfo_t          compat_siginfo_t
+#define copy_siginfo_to_external        copy_siginfo_to_external32
+
 #include "../../../fs/binfmt_elf.c"
diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c
index 47aeb3350a76..0e365b7c742d 100644
--- a/arch/mips/kernel/relocate.c
+++ b/arch/mips/kernel/relocate.c
@@ -187,8 +187,14 @@ static int __init relocate_exception_table(long offset)
 static inline __init unsigned long rotate_xor(unsigned long hash,
 					      const void *area, size_t size)
 {
-	size_t i;
-	unsigned long *ptr = (unsigned long *)area;
+	const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash));
+	size_t diff, i;
+
+	diff = (void *)ptr - area;
+	if (unlikely(size < diff + sizeof(hash)))
+		return hash;
+
+	size = ALIGN_DOWN(size - diff, sizeof(hash));
 
 	for (i = 0; i < size / sizeof(hash); i++) {
 		/* Rotate by odd number of bits and XOR. */
diff --git a/arch/nds32/include/asm/Kbuild b/arch/nds32/include/asm/Kbuild
index ff1e94299317..82a4453c9c2d 100644
--- a/arch/nds32/include/asm/Kbuild
+++ b/arch/nds32/include/asm/Kbuild
@@ -4,6 +4,5 @@ generic-y += cmpxchg.h
 generic-y += export.h
 generic-y += gpio.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += parport.h
 generic-y += user.h
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 442f3d3bcd90..ca5987e11053 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 generic-y += extable.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += qspinlock_types.h
 generic-y += qspinlock.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index f16c4db80116..4406475a2304 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -3,6 +3,5 @@ generated-y += syscall_table_32.h
 generated-y += syscall_table_64.h
 generated-y += syscall_table_c32.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += user.h
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index e76c86619949..49cd6d2caefb 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -216,12 +216,9 @@ int show_interrupts(struct seq_file *p, void *v)
 		if (!action)
 			goto skip;
 		seq_printf(p, "%3d: ", i);
-#ifdef CONFIG_SMP
+
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-#else
-		seq_printf(p, "%10u ", kstat_irqs(i));
-#endif
+			seq_printf(p, "%10u ", irq_desc_kstat_cpu(desc, j));
 
 		seq_printf(p, " %14s", irq_desc_get_chip(desc)->name);
 #ifndef PARISC_IRQ_CR16_COUNTS
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index ae7391627054..107bb4319e0e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -161,6 +161,7 @@ config PPC
 	select DCACHE_WORD_ACCESS		if PPC64 && CPU_LITTLE_ENDIAN
 	select DMA_OPS				if PPC64
 	select DMA_OPS_BYPASS			if PPC64
+	select ARCH_HAS_DMA_MAP_DIRECT 		if PPC64 && PPC_PSERIES
 	select DYNAMIC_FTRACE			if FUNCTION_TRACER
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index ec0b2186e41c..2b8da923ceca 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -373,6 +373,8 @@ initrd-y := $(filter-out $(image-y), $(initrd-y))
 targets	+= $(image-y) $(initrd-y)
 targets += $(foreach x, dtbImage uImage cuImage simpleImage treeImage, \
 		$(patsubst $(x).%, dts/%.dtb, $(filter $(x).%, $(image-y))))
+targets += $(foreach x, dtbImage uImage cuImage simpleImage treeImage, \
+		$(patsubst $(x).%, dts/fsl/%.dtb, $(filter $(x).%, $(image-y))))
 
 $(addprefix $(obj)/, $(initrd-y)): $(obj)/ramdisk.image.gz
 
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 90cd5c53af66..e1f9b4ea1c53 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -5,7 +5,6 @@ generated-y += syscall_table_c32.h
 generated-y += syscall_table_spu.h
 generic-y += export.h
 generic-y += kvm_types.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += qrwlock.h
 generic-y += vtime.h
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index cfa814824285..cc1bca571332 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -180,7 +180,12 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define VCPU_GPR(n)	__VCPU_GPR(__REG_##n)
 
 #ifdef __KERNEL__
-#ifdef CONFIG_PPC64
+
+/*
+ * We use __powerpc64__ here because we want the compat VDSO to use the 32-bit
+ * version below in the else case of the ifdef.
+ */
+#ifdef __powerpc64__
 
 #define STACKFRAMESIZE 256
 #define __STK_REG(i)   (112 + ((i)-14)*8)
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index 81671aa365b3..77c635c2c90d 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -103,6 +103,8 @@ int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz
 	return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz);
 }
 
+#ifdef __powerpc64__
+
 static __always_inline
 int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 {
@@ -115,11 +117,23 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
 	return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts);
 }
 
-#ifdef CONFIG_VDSO32
+#else
 
 #define BUILD_VDSO32		1
 
 static __always_inline
+int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts);
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts);
+}
+
+static __always_inline
 int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
 {
 	return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts);
diff --git a/arch/powerpc/include/asm/vdso/timebase.h b/arch/powerpc/include/asm/vdso/timebase.h
index b558b07959ce..881f655caa0a 100644
--- a/arch/powerpc/include/asm/vdso/timebase.h
+++ b/arch/powerpc/include/asm/vdso/timebase.h
@@ -49,7 +49,7 @@ static inline unsigned long get_tbl(void)
 	return mftb();
 }
 
-static inline u64 get_tb(void)
+static __always_inline u64 get_tb(void)
 {
 	unsigned int tbhi, tblo, tbhi2;
 
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index a1c744194018..111249fd619d 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -10,6 +10,63 @@
 #include <linux/pci.h>
 #include <asm/iommu.h>
 
+#ifdef CONFIG_ARCH_HAS_DMA_MAP_DIRECT
+#define can_map_direct(dev, addr) \
+	((dev)->bus_dma_limit >= phys_to_dma((dev), (addr)))
+
+bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr)
+{
+	if (likely(!dev->bus_dma_limit))
+		return false;
+
+	return can_map_direct(dev, addr);
+}
+
+#define is_direct_handle(dev, h) ((h) >= (dev)->archdata.dma_offset)
+
+bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle)
+{
+	if (likely(!dev->bus_dma_limit))
+		return false;
+
+	return is_direct_handle(dev, dma_handle);
+}
+
+bool arch_dma_map_sg_direct(struct device *dev, struct scatterlist *sg,
+			    int nents)
+{
+	struct scatterlist *s;
+	int i;
+
+	if (likely(!dev->bus_dma_limit))
+		return false;
+
+	for_each_sg(sg, s, nents, i) {
+		if (!can_map_direct(dev, sg_phys(s) + s->offset + s->length))
+			return false;
+	}
+
+	return true;
+}
+
+bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
+			      int nents)
+{
+	struct scatterlist *s;
+	int i;
+
+	if (likely(!dev->bus_dma_limit))
+		return false;
+
+	for_each_sg(sg, s, nents, i) {
+		if (!is_direct_handle(dev, s->dma_address + s->length))
+			return false;
+	}
+
+	return true;
+}
+#endif /* CONFIG_ARCH_HAS_DMA_MAP_DIRECT */
+
 /*
  * Generic iommu implementation
  */
@@ -90,8 +147,18 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask)
 	struct iommu_table *tbl = get_iommu_table_base(dev);
 
 	if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) {
-		dev->dma_ops_bypass = true;
-		dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
+		/*
+		 * dma_iommu_bypass_supported() sets dma_max when there is
+		 * 1:1 mapping but it is somehow limited.
+		 * ibm,pmemory is one example.
+		 */
+		dev->dma_ops_bypass = dev->bus_dma_limit == 0;
+		if (!dev->dma_ops_bypass)
+			dev_warn(dev,
+				 "iommu: 64-bit OK but direct DMA is limited by %llx\n",
+				 dev->bus_dma_limit);
+		else
+			dev_dbg(dev, "iommu: 64-bit OK, using fixed ops\n");
 		return 1;
 	}
 
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 541664d95702..a2f72c966baf 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -121,18 +121,28 @@
 #ifdef CONFIG_VMAP_STACK
 	mfspr	r11, SPRN_SRR0
 	mtctr	r11
-#endif
 	andi.	r11, r9, MSR_PR
-	lwz	r11,TASK_STACK-THREAD(r12)
+	mr	r11, r1
+	lwz	r1,TASK_STACK-THREAD(r12)
 	beq-	99f
-	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
-#ifdef CONFIG_VMAP_STACK
+	addi	r1, r1, THREAD_SIZE - INT_FRAME_SIZE
 	li	r10, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
 	mtmsr	r10
 	isync
+	tovirt(r12, r12)
+	stw	r11,GPR1(r1)
+	stw	r11,0(r1)
+	mr	r11, r1
+#else
+	andi.	r11, r9, MSR_PR
+	lwz	r11,TASK_STACK-THREAD(r12)
+	beq-	99f
+	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
+	tophys(r11, r11)
+	stw	r1,GPR1(r11)
+	stw	r1,0(r11)
+	tovirt(r1, r11)		/* set new kernel sp */
 #endif
-	tovirt_vmstack r12, r12
-	tophys_novmstack r11, r11
 	mflr	r10
 	stw	r10, _LINK(r11)
 #ifdef CONFIG_VMAP_STACK
@@ -140,9 +150,6 @@
 #else
 	mfspr	r10,SPRN_SRR0
 #endif
-	stw	r1,GPR1(r11)
-	stw	r1,0(r11)
-	tovirt_novmstack r1, r11	/* set new kernel sp */
 	stw	r10,_NIP(r11)
 	mfcr	r10
 	rlwinm	r10,r10,0,4,2	/* Clear SO bit in CR */
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 349bf3f0c3af..858fbc8b19f3 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -260,10 +260,19 @@ __secondary_hold_acknowledge:
 MachineCheck:
 	EXCEPTION_PROLOG_0
 #ifdef CONFIG_PPC_CHRP
+#ifdef CONFIG_VMAP_STACK
+	mtspr	SPRN_SPRG_SCRATCH2,r1
+	mfspr	r1, SPRN_SPRG_THREAD
+	lwz	r1, RTAS_SP(r1)
+	cmpwi	cr1, r1, 0
+	bne	cr1, 7f
+	mfspr	r1, SPRN_SPRG_SCRATCH2
+#else
 	mfspr	r11, SPRN_SPRG_THREAD
 	lwz	r11, RTAS_SP(r11)
 	cmpwi	cr1, r11, 0
 	bne	cr1, 7f
+#endif
 #endif /* CONFIG_PPC_CHRP */
 	EXCEPTION_PROLOG_1 for_rtas=1
 7:	EXCEPTION_PROLOG_2
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 2b9b1bb4c5f2..9e2246e80efd 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -990,7 +990,7 @@ static struct sched_domain_topology_level powerpc_topology[] = {
 	{ NULL, },
 };
 
-static int init_big_cores(void)
+static int __init init_big_cores(void)
 {
 	int cpu;
 
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index 59aa2944ecae..9cb6f524854b 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -2,7 +2,7 @@
 
 # List of files in the vdso, has to be asm only for now
 
-ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN
+ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN|R_PPC_REL24
 include $(srctree)/lib/vdso/Makefile
 
 obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
@@ -27,7 +27,7 @@ endif
 CC32FLAGS :=
 ifdef CONFIG_PPC64
 CC32FLAGS += -m32
-KBUILD_CFLAGS := $(filter-out -mcmodel=medium,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc,$(KBUILD_CFLAGS))
 endif
 
 targets := $(obj-vdso32) vdso32.so.dbg
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index d365810a689a..bf363ff37152 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # List of files in the vdso, has to be asm only for now
 
-ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN
+ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN|R_PPC_REL24
 include $(srctree)/lib/vdso/Makefile
 
 obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 0318ba436f34..4ab426b8b0e0 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -85,7 +85,7 @@ SECTIONS
 		ALIGN_FUNCTION();
 #endif
 		/* careful! __ftr_alt_* sections need to be close to .text */
-		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text);
+		*(.text.hot .text.hot.* TEXT_MAIN .text.fixup .text.unlikely .text.unlikely.* .fixup __ftr_alt_* .ref.text);
 #ifdef CONFIG_PPC64
 		*(.tramp.ftrace.text);
 #endif
@@ -187,6 +187,12 @@ SECTIONS
 	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
 		_sinittext = .;
 		INIT_TEXT
+
+		/*
+		 *.init.text might be RO so we must ensure this section ends on
+		 * a page boundary.
+		 */
+		. = ALIGN(PAGE_SIZE);
 		_einittext = .;
 #ifdef CONFIG_PPC64
 		*(.tramp.ftrace.init);
@@ -200,6 +206,8 @@ SECTIONS
 		EXIT_TEXT
 	}
 
+	. = ALIGN(PAGE_SIZE);
+
 	INIT_DATA_SECTION(16)
 
 	. = ALIGN(8);
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index e4198700ed1a..9fc5217f0c8e 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -839,7 +839,7 @@ static void remove_ddw(struct device_node *np, bool remove_prop)
 			np, ret);
 }
 
-static u64 find_existing_ddw(struct device_node *pdn)
+static u64 find_existing_ddw(struct device_node *pdn, int *window_shift)
 {
 	struct direct_window *window;
 	const struct dynamic_dma_window_prop *direct64;
@@ -851,6 +851,7 @@ static u64 find_existing_ddw(struct device_node *pdn)
 		if (window->device == pdn) {
 			direct64 = window->prop;
 			dma_addr = be64_to_cpu(direct64->dma_base);
+			*window_shift = be32_to_cpu(direct64->window_shift);
 			break;
 		}
 	}
@@ -1111,11 +1112,12 @@ static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn)
  */
 static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 {
-	int len, ret;
+	int len = 0, ret;
+	int max_ram_len = order_base_2(ddw_memory_hotplug_max());
 	struct ddw_query_response query;
 	struct ddw_create_response create;
 	int page_shift;
-	u64 dma_addr, max_addr;
+	u64 dma_addr;
 	struct device_node *dn;
 	u32 ddw_avail[DDW_APPLICABLE_SIZE];
 	struct direct_window *window;
@@ -1123,10 +1125,15 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	struct dynamic_dma_window_prop *ddwprop;
 	struct failed_ddw_pdn *fpdn;
 	bool default_win_removed = false;
+	bool pmem_present;
+
+	dn = of_find_node_by_type(NULL, "ibm,pmemory");
+	pmem_present = dn != NULL;
+	of_node_put(dn);
 
 	mutex_lock(&direct_window_init_mutex);
 
-	dma_addr = find_existing_ddw(pdn);
+	dma_addr = find_existing_ddw(pdn, &len);
 	if (dma_addr != 0)
 		goto out_unlock;
 
@@ -1212,14 +1219,29 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	}
 	/* verify the window * number of ptes will map the partition */
 	/* check largest block * page size > max memory hotplug addr */
-	max_addr = ddw_memory_hotplug_max();
-	if (query.largest_available_block < (max_addr >> page_shift)) {
-		dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu "
-			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
-			  1ULL << page_shift);
+	/*
+	 * The "ibm,pmemory" can appear anywhere in the address space.
+	 * Assuming it is still backed by page structs, try MAX_PHYSMEM_BITS
+	 * for the upper limit and fallback to max RAM otherwise but this
+	 * disables device::dma_ops_bypass.
+	 */
+	len = max_ram_len;
+	if (pmem_present) {
+		if (query.largest_available_block >=
+		    (1ULL << (MAX_PHYSMEM_BITS - page_shift)))
+			len = MAX_PHYSMEM_BITS - page_shift;
+		else
+			dev_info(&dev->dev, "Skipping ibm,pmemory");
+	}
+
+	if (query.largest_available_block < (1ULL << (len - page_shift))) {
+		dev_dbg(&dev->dev,
+			"can't map partition max 0x%llx with %llu %llu-sized pages\n",
+			1ULL << len,
+			query.largest_available_block,
+			1ULL << page_shift);
 		goto out_failed;
 	}
-	len = order_base_2(max_addr);
 	win64 = kzalloc(sizeof(struct property), GFP_KERNEL);
 	if (!win64) {
 		dev_info(&dev->dev,
@@ -1299,6 +1321,15 @@ out_failed:
 
 out_unlock:
 	mutex_unlock(&direct_window_init_mutex);
+
+	/*
+	 * If we have persistent memory and the window size is only as big
+	 * as RAM, then we failed to create a window to cover persistent
+	 * memory and need to set the DMA limit.
+	 */
+	if (pmem_present && dma_addr && (len == max_ram_len))
+		dev->dev.bus_dma_limit = dma_addr + (1ULL << len);
+
 	return dma_addr;
 }
 
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 81b76d44725d..e9e2c1f0a690 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -137,7 +137,7 @@ config PA_BITS
 
 config PAGE_OFFSET
 	hex
-	default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB
+	default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB
 	default 0x80000000 if 64BIT && !MMU
 	default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
 	default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
@@ -247,10 +247,12 @@ config MODULE_SECTIONS
 
 choice
 	prompt "Maximum Physical Memory"
-	default MAXPHYSMEM_2GB if 32BIT
+	default MAXPHYSMEM_1GB if 32BIT
 	default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW
 	default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY
 
+	config MAXPHYSMEM_1GB
+		bool "1GiB"
 	config MAXPHYSMEM_2GB
 		bool "2GiB"
 	config MAXPHYSMEM_128GB
diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
index 8a55f6156661..3284d5c291be 100644
--- a/arch/riscv/Kconfig.socs
+++ b/arch/riscv/Kconfig.socs
@@ -5,7 +5,7 @@ config SOC_SIFIVE
 	select SERIAL_SIFIVE if TTY
 	select SERIAL_SIFIVE_CONSOLE if TTY
 	select CLK_SIFIVE
-	select CLK_SIFIVE_FU540_PRCI
+	select CLK_SIFIVE_PRCI
 	select SIFIVE_PLIC
 	help
 	  This enables support for SiFive SoC platform hardware.
diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
index 4a2729f5ca3f..24d75a146e02 100644
--- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
+++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
@@ -88,7 +88,9 @@
 	phy-mode = "gmii";
 	phy-handle = <&phy0>;
 	phy0: ethernet-phy@0 {
+		compatible = "ethernet-phy-id0007.0771";
 		reg = <0>;
+		reset-gpios = <&gpio 12 GPIO_ACTIVE_LOW>;
 	};
 };
 
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index d222d353d86d..8c3d1e451703 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -64,6 +64,8 @@ CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_VIRTIO=y
 CONFIG_SPI=y
 CONFIG_SPI_SIFIVE=y
+CONFIG_GPIOLIB=y
+CONFIG_GPIO_SIFIVE=y
 # CONFIG_PTP_1588_CLOCK is not set
 CONFIG_POWER_RESET=y
 CONFIG_DRM=y
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 59dd7be55005..445ccc97305a 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -3,6 +3,5 @@ generic-y += early_ioremap.h
 generic-y += extable.h
 generic-y += flat.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += user.h
 generic-y += vmlinux.lds.h
diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h
index 7542282f1141..6d98cd999680 100644
--- a/arch/riscv/include/asm/efi.h
+++ b/arch/riscv/include/asm/efi.h
@@ -27,12 +27,6 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
 
 #define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE)
 
-/* on RISC-V, the FDT may be located anywhere in system RAM */
-static inline unsigned long efi_get_max_fdt_addr(unsigned long image_addr)
-{
-	return ULONG_MAX;
-}
-
 /* Load initrd at enough distance from DRAM start */
 static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr)
 {
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 41a72861987c..251e1db088fa 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -99,7 +99,6 @@
 				| _PAGE_DIRTY)
 
 #define PAGE_KERNEL		__pgprot(_PAGE_KERNEL)
-#define PAGE_KERNEL_EXEC	__pgprot(_PAGE_KERNEL | _PAGE_EXEC)
 #define PAGE_KERNEL_READ	__pgprot(_PAGE_KERNEL & ~_PAGE_WRITE)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_KERNEL | _PAGE_EXEC)
 #define PAGE_KERNEL_READ_EXEC	__pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
index 8454f746bbfd..1453a2f563bc 100644
--- a/arch/riscv/include/asm/vdso.h
+++ b/arch/riscv/include/asm/vdso.h
@@ -10,7 +10,7 @@
 
 #include <linux/types.h>
 
-#ifndef GENERIC_TIME_VSYSCALL
+#ifndef CONFIG_GENERIC_TIME_VSYSCALL
 struct vdso_data {
 };
 #endif
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index de59dd457b41..d86781357044 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -26,7 +26,16 @@ cache_get_priv_group(struct cacheinfo *this_leaf)
 
 static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type)
 {
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id());
+	/*
+	 * Using raw_smp_processor_id() elides a preemptability check, but this
+	 * is really indicative of a larger problem: the cacheinfo UABI assumes
+	 * that cores have a homonogenous view of the cache hierarchy.  That
+	 * happens to be the case for the current set of RISC-V systems, but
+	 * likely won't be true in general.  Since there's no way to provide
+	 * correct information for these systems via the current UABI we're
+	 * just eliding the check for now.
+	 */
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id());
 	struct cacheinfo *this_leaf;
 	int index;
 
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 524d918f3601..744f3209c48d 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -124,15 +124,15 @@ skip_context_tracking:
 	REG_L a1, (a1)
 	jr a1
 1:
-#ifdef CONFIG_TRACE_IRQFLAGS
-	call trace_hardirqs_on
-#endif
 	/*
 	 * Exceptions run with interrupts enabled or disabled depending on the
 	 * state of SR_PIE in m/sstatus.
 	 */
 	andi t0, s1, SR_PIE
 	beqz t0, 1f
+#ifdef CONFIG_TRACE_IRQFLAGS
+	call trace_hardirqs_on
+#endif
 	csrs CSR_STATUS, SR_IE
 
 1:
@@ -155,6 +155,15 @@ skip_context_tracking:
 	tail do_trap_unknown
 
 handle_syscall:
+#ifdef CONFIG_RISCV_M_MODE
+	/*
+	 * When running is M-Mode (no MMU config), MPIE does not get set.
+	 * As a result, we need to force enable interrupts here because
+	 * handle_exception did not do set SR_IE as it always sees SR_PIE
+	 * being cleared.
+	 */
+	csrs CSR_STATUS, SR_IE
+#endif
 #if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
 	/* Recover a0 - a7 for system calls */
 	REG_L a0, PT_A0(sp)
@@ -186,14 +195,7 @@ check_syscall_nr:
 	 * Syscall number held in a7.
 	 * If syscall number is above allowed value, redirect to ni_syscall.
 	 */
-	bge a7, t0, 1f
-	/*
-	 * Check if syscall is rejected by tracer, i.e., a7 == -1.
-	 * If yes, we pretend it was executed.
-	 */
-	li t1, -1
-	beq a7, t1, ret_from_syscall_rejected
-	blt a7, t1, 1f
+	bgeu a7, t0, 1f
 	/* Call syscall */
 	la s0, sys_call_table
 	slli t0, a7, RISCV_LGPTR
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 1d85e9bf783c..3fa3f26dde85 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -127,7 +127,9 @@ static void __init init_resources(void)
 {
 	struct memblock_region *region = NULL;
 	struct resource *res = NULL;
-	int ret = 0;
+	struct resource *mem_res = NULL;
+	size_t mem_res_sz = 0;
+	int ret = 0, i = 0;
 
 	code_res.start = __pa_symbol(_text);
 	code_res.end = __pa_symbol(_etext) - 1;
@@ -145,16 +147,17 @@ static void __init init_resources(void)
 	bss_res.end = __pa_symbol(__bss_stop) - 1;
 	bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
+	mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res);
+	mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES);
+	if (!mem_res)
+		panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz);
 	/*
 	 * Start by adding the reserved regions, if they overlap
 	 * with /memory regions, insert_resource later on will take
 	 * care of it.
 	 */
 	for_each_reserved_mem_region(region) {
-		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
-		if (!res)
-			panic("%s: Failed to allocate %zu bytes\n", __func__,
-			      sizeof(struct resource));
+		res = &mem_res[i++];
 
 		res->name = "Reserved";
 		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
@@ -171,8 +174,10 @@ static void __init init_resources(void)
 		 * Ignore any other reserved regions within
 		 * system memory.
 		 */
-		if (memblock_is_memory(res->start))
+		if (memblock_is_memory(res->start)) {
+			memblock_free((phys_addr_t) res, sizeof(struct resource));
 			continue;
+		}
 
 		ret = add_resource(&iomem_resource, res);
 		if (ret < 0)
@@ -181,10 +186,7 @@ static void __init init_resources(void)
 
 	/* Add /memory regions to the resource tree */
 	for_each_mem_region(region) {
-		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
-		if (!res)
-			panic("%s: Failed to allocate %zu bytes\n", __func__,
-			      sizeof(struct resource));
+		res = &mem_res[i++];
 
 		if (unlikely(memblock_is_nomap(region))) {
 			res->name = "Reserved";
@@ -205,9 +207,9 @@ static void __init init_resources(void)
 	return;
 
  error:
-	memblock_free((phys_addr_t) res, sizeof(struct resource));
 	/* Better an empty resource tree than an inconsistent one */
 	release_child_resources(&iomem_resource);
+	memblock_free((phys_addr_t) mem_res, mem_res_sz);
 }
 
 
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 48b870a685b3..df5d2da7c40b 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -14,7 +14,7 @@
 
 #include <asm/stacktrace.h>
 
-register unsigned long sp_in_global __asm__("sp");
+register const unsigned long sp_in_global __asm__("sp");
 
 #ifdef CONFIG_FRAME_POINTER
 
@@ -28,9 +28,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
 		sp = user_stack_pointer(regs);
 		pc = instruction_pointer(regs);
 	} else if (task == NULL || task == current) {
-		const register unsigned long current_sp = sp_in_global;
 		fp = (unsigned long)__builtin_frame_address(0);
-		sp = current_sp;
+		sp = sp_in_global;
 		pc = (unsigned long)walk_stackframe;
 	} else {
 		/* task blocked in __switch_to */
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
index 4d3a1048ad8b..8a5cf99c0776 100644
--- a/arch/riscv/kernel/time.c
+++ b/arch/riscv/kernel/time.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/of_clk.h>
 #include <linux/clocksource.h>
 #include <linux/delay.h>
 #include <asm/sbi.h>
@@ -24,6 +25,8 @@ void __init time_init(void)
 	riscv_timebase = prop;
 
 	lpj_fine = riscv_timebase / HZ;
+
+	of_clk_init(NULL);
 	timer_probe();
 }
 
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 678204231700..3f1d35e7c98a 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -12,7 +12,7 @@
 #include <linux/binfmts.h>
 #include <linux/err.h>
 #include <asm/page.h>
-#ifdef GENERIC_TIME_VSYSCALL
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL
 #include <vdso/datapage.h>
 #else
 #include <asm/vdso.h>
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 13ba533f462b..7cd4993f4ff2 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -157,9 +157,10 @@ disable:
 void __init setup_bootmem(void)
 {
 	phys_addr_t mem_start = 0;
-	phys_addr_t start, end = 0;
+	phys_addr_t start, dram_end, end = 0;
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
 	phys_addr_t vmlinux_start = __pa_symbol(&_start);
+	phys_addr_t max_mapped_addr = __pa(~(ulong)0);
 	u64 i;
 
 	/* Find the memory region containing the kernel */
@@ -176,12 +177,23 @@ void __init setup_bootmem(void)
 	 * Make sure that any memory beyond mem_start + (-PAGE_OFFSET) is removed
 	 * as it is unusable by kernel.
 	 */
-	memblock_enforce_memory_limit(mem_start - PAGE_OFFSET);
+	memblock_enforce_memory_limit(-PAGE_OFFSET);
 
 	/* Reserve from the start of the kernel to the end of the kernel */
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
-	max_pfn = PFN_DOWN(memblock_end_of_DRAM());
+	dram_end = memblock_end_of_DRAM();
+
+	/*
+	 * memblock allocator is not aware of the fact that last 4K bytes of
+	 * the addressable memory can not be mapped because of IS_ERR_VALUE
+	 * macro. Make sure that last 4k bytes are not usable by memblock
+	 * if end of dram is equal to maximum addressable memory.
+	 */
+	if (max_mapped_addr == (dram_end - 1))
+		memblock_set_current_limit(max_mapped_addr - 4096);
+
+	max_pfn = PFN_DOWN(dram_end);
 	max_low_pfn = max_pfn;
 	dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn));
 	set_max_mapnr(max_low_pfn);
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 12ddd1f6bf70..a8a2ffd9114a 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -93,8 +93,8 @@ void __init kasan_init(void)
 								VMALLOC_END));
 
 	for_each_mem_range(i, &_start, &_end) {
-		void *start = (void *)_start;
-		void *end = (void *)_end;
+		void *start = (void *)__va(_start);
+		void *end = (void *)__va(_end);
 
 		if (start >= end)
 			break;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index e84bdd15150b..c72874f09741 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -54,17 +54,23 @@ config KASAN_SHADOW_OFFSET
 
 config S390
 	def_bool y
+	#
+	# Note: keep this list sorted alphabetically
+	#
+	imply IMA_SECURE_AND_OR_TRUSTED_BOOT
 	select ARCH_BINFMT_ELF_STATE
 	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DEBUG_WX
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_SCALED_CPUTIME
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
@@ -111,8 +117,10 @@ config S390
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS2
+	select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
 	select DMA_OPS if PCI
 	select DYNAMIC_FTRACE if FUNCTION_TRACER
+	select GENERIC_ALLOCATOR
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_FIND_FIRST_BIT
@@ -126,22 +134,21 @@ config S390
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN
 	select HAVE_ARCH_KASAN_VMALLOC
-	select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_SOFT_DIRTY
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_VMAP_STACK
 	select HAVE_ASM_MODVERSIONS
-	select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
-	select HAVE_FAST_GUP
+	select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select HAVE_FAST_GUP
 	select HAVE_FENTRY
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_ERROR_INJECTION
@@ -163,16 +170,15 @@ config S390
 	select HAVE_KRETPROBES
 	select HAVE_KVM
 	select HAVE_LIVEPATCH
-	select HAVE_PERF_REGS
-	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_MEMBLOCK_PHYS_MAP
-	select MMU_GATHER_NO_GATHER
 	select HAVE_MOD_ARCH_SPECIFIC
+	select HAVE_NMI
 	select HAVE_NOP_MCOUNT
 	select HAVE_OPROFILE
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
-	select MMU_GATHER_RCU_TABLE_FREE
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE
 	select HAVE_RSEQ
@@ -181,6 +187,8 @@ config S390
 	select HAVE_VIRT_CPU_ACCOUNTING_IDLE
 	select IOMMU_HELPER		if PCI
 	select IOMMU_SUPPORT		if PCI
+	select MMU_GATHER_NO_GATHER
+	select MMU_GATHER_RCU_TABLE_FREE
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE	if PCI
 	select NEED_SG_DMA_LENGTH	if PCI
@@ -190,17 +198,12 @@ config S390
 	select PCI_MSI			if PCI
 	select PCI_MSI_ARCH_FALLBACKS	if PCI_MSI
 	select SPARSE_IRQ
+	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
 	select TTY
 	select VIRT_CPU_ACCOUNTING
-	select ARCH_HAS_SCALED_CPUTIME
-	select HAVE_NMI
-	select ARCH_HAS_FORCE_DMA_UNENCRYPTED
-	select SWIOTLB
-	select GENERIC_ALLOCATOR
-	imply IMA_SECURE_AND_OR_TRUSTED_BOOT
-
+	# Note: keep the above list sorted alphabetically
 
 config SCHED_OMIT_FRAME_POINTER
 	def_bool y
diff --git a/arch/s390/boot/string.c b/arch/s390/boot/string.c
index b11e8108773a..faccb33b462c 100644
--- a/arch/s390/boot/string.c
+++ b/arch/s390/boot/string.c
@@ -3,6 +3,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #undef CONFIG_KASAN
+#undef CONFIG_KASAN_GENERIC
 #include "../lib/string.c"
 
 int strncmp(const char *cs, const char *ct, size_t count)
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 1be32fcf6f2e..c4f6ff98a612 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -61,7 +61,9 @@ CONFIG_OPROFILE=m
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
 CONFIG_STATIC_KEYS_SELFTEST=y
+CONFIG_SECCOMP_CACHE_DEBUG=y
 CONFIG_LOCK_EVENT_COUNTS=y
+# CONFIG_GCC_PLUGINS is not set
 CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y
 CONFIG_MODULE_UNLOAD=y
@@ -410,12 +412,12 @@ CONFIG_SCSI_ENCLOSURE=m
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SPI_ATTRS=m
-CONFIG_SCSI_FC_ATTRS=y
+CONFIG_SCSI_FC_ATTRS=m
 CONFIG_SCSI_SAS_LIBSAS=m
 CONFIG_SCSI_SRP_ATTRS=m
 CONFIG_ISCSI_TCP=m
 CONFIG_SCSI_DEBUG=m
-CONFIG_ZFCP=y
+CONFIG_ZFCP=m
 CONFIG_SCSI_VIRTIO=m
 CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
@@ -444,6 +446,7 @@ CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
 CONFIG_DM_MULTIPATH_ST=m
 CONFIG_DM_MULTIPATH_HST=m
+CONFIG_DM_MULTIPATH_IOA=m
 CONFIG_DM_DELAY=m
 CONFIG_DM_UEVENT=y
 CONFIG_DM_FLAKEY=m
@@ -542,7 +545,6 @@ CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 CONFIG_LEGACY_PTY_COUNT=0
-CONFIG_NULL_TTY=m
 CONFIG_VIRTIO_CONSOLE=y
 CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_RAW_DRIVER=m
@@ -574,6 +576,7 @@ CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
+# CONFIG_SURFACE_PLATFORMS is not set
 CONFIG_S390_CCW_IOMMU=y
 CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
@@ -655,6 +658,7 @@ CONFIG_CIFS_XATTR=y
 CONFIG_CIFS_POSIX=y
 # CONFIG_CIFS_DEBUG is not set
 CONFIG_CIFS_DFS_UPCALL=y
+CONFIG_CIFS_SWN_UPCALL=y
 CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=m
 CONFIG_NLS_CODEPAGE_850=m
@@ -826,6 +830,8 @@ CONFIG_FTRACE_SYSCALLS=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
+CONFIG_FTRACE_STARTUP_TEST=y
+# CONFIG_EVENT_TRACE_STARTUP_TEST is not set
 CONFIG_DEBUG_USER_ASCE=y
 CONFIG_NOTIFIER_ERROR_INJECTION=m
 CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index e2171a008809..51135893cffe 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -58,6 +58,7 @@ CONFIG_S390_UNWIND_SELFTEST=m
 CONFIG_OPROFILE=m
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
+# CONFIG_GCC_PLUGINS is not set
 CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y
 CONFIG_MODULE_UNLOAD=y
@@ -95,7 +96,6 @@ CONFIG_ZSMALLOC_STAT=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
 CONFIG_PERCPU_STATS=y
-CONFIG_GUP_TEST=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=m
@@ -403,12 +403,12 @@ CONFIG_SCSI_ENCLOSURE=m
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SPI_ATTRS=m
-CONFIG_SCSI_FC_ATTRS=y
+CONFIG_SCSI_FC_ATTRS=m
 CONFIG_SCSI_SAS_LIBSAS=m
 CONFIG_SCSI_SRP_ATTRS=m
 CONFIG_ISCSI_TCP=m
 CONFIG_SCSI_DEBUG=m
-CONFIG_ZFCP=y
+CONFIG_ZFCP=m
 CONFIG_SCSI_VIRTIO=m
 CONFIG_SCSI_DH=y
 CONFIG_SCSI_DH_RDAC=m
@@ -437,6 +437,7 @@ CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
 CONFIG_DM_MULTIPATH_ST=m
 CONFIG_DM_MULTIPATH_HST=m
+CONFIG_DM_MULTIPATH_IOA=m
 CONFIG_DM_DELAY=m
 CONFIG_DM_UEVENT=y
 CONFIG_DM_FLAKEY=m
@@ -536,7 +537,6 @@ CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 CONFIG_LEGACY_PTY_COUNT=0
-CONFIG_NULL_TTY=m
 CONFIG_VIRTIO_CONSOLE=y
 CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_RAW_DRIVER=m
@@ -568,6 +568,7 @@ CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
+# CONFIG_SURFACE_PLATFORMS is not set
 CONFIG_S390_CCW_IOMMU=y
 CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
@@ -645,6 +646,7 @@ CONFIG_CIFS_XATTR=y
 CONFIG_CIFS_POSIX=y
 # CONFIG_CIFS_DEBUG is not set
 CONFIG_CIFS_DFS_UPCALL=y
+CONFIG_CIFS_SWN_UPCALL=y
 CONFIG_NLS_DEFAULT="utf8"
 CONFIG_NLS_CODEPAGE_437=m
 CONFIG_NLS_CODEPAGE_850=m
@@ -778,6 +780,7 @@ CONFIG_FTRACE_SYSCALLS=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
+CONFIG_DEBUG_USER_ASCE=y
 CONFIG_LKDTM=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index a302630341ef..1ef211dae77a 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -22,6 +22,7 @@ CONFIG_CRASH_DUMP=y
 # CONFIG_VIRTUALIZATION is not set
 # CONFIG_S390_GUEST is not set
 # CONFIG_SECCOMP is not set
+# CONFIG_GCC_PLUGINS is not set
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
@@ -58,6 +59,7 @@ CONFIG_RAW_DRIVER=y
 # CONFIG_HID is not set
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_VHOST_MENU is not set
+# CONFIG_SURFACE_PLATFORMS is not set
 # CONFIG_IOMMU_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 319efa0e6d02..1a18d7b82f86 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -7,5 +7,4 @@ generated-y += unistd_nr.h
 generic-y += asm-offsets.h
 generic-y += export.h
 generic-y += kvm_types.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 463c24e26000..74f9a036bab2 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -459,6 +459,7 @@ struct kvm_vcpu_stat {
 	u64 diagnose_308;
 	u64 diagnose_500;
 	u64 diagnose_other;
+	u64 pfault_sync;
 };
 
 #define PGM_OPERATION			0x01
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 3514420f0259..f8a8b9428ae2 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -124,7 +124,7 @@ static void show_msi_interrupt(struct seq_file *p, int irq)
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	seq_printf(p, "%3d: ", irq);
 	for_each_online_cpu(cpu)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+		seq_printf(p, "%10u ", irq_desc_kstat_cpu(desc, cpu));
 
 	if (desc->irq_data.chip)
 		seq_printf(p, " %8s", desc->irq_data.chip->name);
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index 394a5f53805b..3765c4223bf9 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -184,7 +184,7 @@ static int __import_wp_info(struct kvm_vcpu *vcpu,
 	if (wp_info->len < 0 || wp_info->len > MAX_WP_SIZE)
 		return -EINVAL;
 
-	wp_info->old_data = kmalloc(bp_data->len, GFP_KERNEL);
+	wp_info->old_data = kmalloc(bp_data->len, GFP_KERNEL_ACCOUNT);
 	if (!wp_info->old_data)
 		return -ENOMEM;
 	/* try to backup the original value */
@@ -234,7 +234,7 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu,
 	if (nr_wp > 0) {
 		wp_info = kmalloc_array(nr_wp,
 					sizeof(*wp_info),
-					GFP_KERNEL);
+					GFP_KERNEL_ACCOUNT);
 		if (!wp_info) {
 			ret = -ENOMEM;
 			goto error;
@@ -243,7 +243,7 @@ int kvm_s390_import_bp_data(struct kvm_vcpu *vcpu,
 	if (nr_bp > 0) {
 		bp_info = kmalloc_array(nr_bp,
 					sizeof(*bp_info),
-					GFP_KERNEL);
+					GFP_KERNEL_ACCOUNT);
 		if (!bp_info) {
 			ret = -ENOMEM;
 			goto error;
@@ -349,7 +349,7 @@ static struct kvm_hw_wp_info_arch *any_wp_changed(struct kvm_vcpu *vcpu)
 		if (!wp_info || !wp_info->old_data || wp_info->len <= 0)
 			continue;
 
-		temp = kmalloc(wp_info->len, GFP_KERNEL);
+		temp = kmalloc(wp_info->len, GFP_KERNEL_ACCOUNT);
 		if (!temp)
 			continue;
 
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index e7a7c499a73f..72b25b7cc6ae 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -398,7 +398,7 @@ int handle_sthyi(struct kvm_vcpu *vcpu)
 	if (!kvm_s390_pv_cpu_is_protected(vcpu) && (addr & ~PAGE_MASK))
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	sctns = (void *)get_zeroed_page(GFP_KERNEL);
+	sctns = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
 	if (!sctns)
 		return -ENOMEM;
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 2f177298c663..e3183bd05910 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1792,7 +1792,7 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 		goto out;
 	}
 gisa_out:
-	tmp_inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	tmp_inti = kzalloc(sizeof(*inti), GFP_KERNEL_ACCOUNT);
 	if (tmp_inti) {
 		tmp_inti->type = KVM_S390_INT_IO(1, 0, 0, 0);
 		tmp_inti->io.io_int_word = isc_to_int_word(isc);
@@ -2015,7 +2015,7 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	struct kvm_s390_interrupt_info *inti;
 	int rc;
 
-	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL_ACCOUNT);
 	if (!inti)
 		return -ENOMEM;
 
@@ -2414,7 +2414,7 @@ static int enqueue_floating_irq(struct kvm_device *dev,
 		return -EINVAL;
 
 	while (len >= sizeof(struct kvm_s390_irq)) {
-		inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+		inti = kzalloc(sizeof(*inti), GFP_KERNEL_ACCOUNT);
 		if (!inti)
 			return -ENOMEM;
 
@@ -2462,7 +2462,7 @@ static int register_io_adapter(struct kvm_device *dev,
 	if (dev->kvm->arch.adapters[adapter_info.id] != NULL)
 		return -EINVAL;
 
-	adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
+	adapter = kzalloc(sizeof(*adapter), GFP_KERNEL_ACCOUNT);
 	if (!adapter)
 		return -ENOMEM;
 
@@ -3290,7 +3290,7 @@ int kvm_s390_gib_init(u8 nisc)
 		goto out;
 	}
 
-	gib = (struct kvm_s390_gib *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	gib = (struct kvm_s390_gib *)get_zeroed_page(GFP_KERNEL_ACCOUNT | GFP_DMA);
 	if (!gib) {
 		rc = -ENOMEM;
 		goto out;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 425d3d75320b..dbafd057ca6a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -60,6 +60,7 @@
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	VCPU_STAT("userspace_handled", exit_userspace),
 	VCPU_STAT("exit_null", exit_null),
+	VCPU_STAT("pfault_sync", pfault_sync),
 	VCPU_STAT("exit_validity", exit_validity),
 	VCPU_STAT("exit_stop_request", exit_stop_request),
 	VCPU_STAT("exit_external_request", exit_external_request),
@@ -1254,7 +1255,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 		ret = -EBUSY;
 		goto out;
 	}
-	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
+	proc = kzalloc(sizeof(*proc), GFP_KERNEL_ACCOUNT);
 	if (!proc) {
 		ret = -ENOMEM;
 		goto out;
@@ -1416,7 +1417,7 @@ static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr)
 	struct kvm_s390_vm_cpu_processor *proc;
 	int ret = 0;
 
-	proc = kzalloc(sizeof(*proc), GFP_KERNEL);
+	proc = kzalloc(sizeof(*proc), GFP_KERNEL_ACCOUNT);
 	if (!proc) {
 		ret = -ENOMEM;
 		goto out;
@@ -1444,7 +1445,7 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
 	struct kvm_s390_vm_cpu_machine *mach;
 	int ret = 0;
 
-	mach = kzalloc(sizeof(*mach), GFP_KERNEL);
+	mach = kzalloc(sizeof(*mach), GFP_KERNEL_ACCOUNT);
 	if (!mach) {
 		ret = -ENOMEM;
 		goto out;
@@ -1812,7 +1813,7 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX)
 		return -EINVAL;
 
-	keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL);
+	keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL_ACCOUNT);
 	if (!keys)
 		return -ENOMEM;
 
@@ -1857,7 +1858,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX)
 		return -EINVAL;
 
-	keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL);
+	keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL_ACCOUNT);
 	if (!keys)
 		return -ENOMEM;
 
@@ -2625,7 +2626,7 @@ static void sca_dispose(struct kvm *kvm)
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
-	gfp_t alloc_flags = GFP_KERNEL;
+	gfp_t alloc_flags = GFP_KERNEL_ACCOUNT;
 	int i, rc;
 	char debug_name[16];
 	static unsigned long sca_offset;
@@ -2670,7 +2671,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	BUILD_BUG_ON(sizeof(struct sie_page2) != 4096);
 	kvm->arch.sie_page2 =
-	     (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	     (struct sie_page2 *) get_zeroed_page(GFP_KERNEL_ACCOUNT | GFP_DMA);
 	if (!kvm->arch.sie_page2)
 		goto out_err;
 
@@ -2900,7 +2901,7 @@ static int sca_switch_to_extended(struct kvm *kvm)
 	if (kvm->arch.use_esca)
 		return 0;
 
-	new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO);
+	new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 	if (!new_sca)
 		return -ENOMEM;
 
@@ -3133,7 +3134,7 @@ void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu)
 
 int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.sie_block->cbrlo = get_zeroed_page(GFP_KERNEL);
+	vcpu->arch.sie_block->cbrlo = get_zeroed_page(GFP_KERNEL_ACCOUNT);
 	if (!vcpu->arch.sie_block->cbrlo)
 		return -ENOMEM;
 	return 0;
@@ -3243,7 +3244,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	int rc;
 
 	BUILD_BUG_ON(sizeof(struct sie_page) != 4096);
-	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
+	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL_ACCOUNT);
 	if (!sie_page)
 		return -ENOMEM;
 
@@ -4109,6 +4110,7 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 		current->thread.gmap_pfault = 0;
 		if (kvm_arch_setup_async_pf(vcpu))
 			return 0;
+		vcpu->stat.pfault_sync++;
 		return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1);
 	}
 	return vcpu_post_run_fault_in_sie(vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index cd74989ce0b0..9928f785c677 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -879,7 +879,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	switch (fc) {
 	case 1: /* same handling for 1 and 2 */
 	case 2:
-		mem = get_zeroed_page(GFP_KERNEL);
+		mem = get_zeroed_page(GFP_KERNEL_ACCOUNT);
 		if (!mem)
 			goto out_no_data;
 		if (stsi((void *) mem, fc, sel1, sel2))
@@ -888,7 +888,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	case 3:
 		if (sel1 != 2 || sel2 != 2)
 			goto out_no_data;
-		mem = get_zeroed_page(GFP_KERNEL);
+		mem = get_zeroed_page(GFP_KERNEL_ACCOUNT);
 		if (!mem)
 			goto out_no_data;
 		handle_stsi_3_2_2(vcpu, (void *) mem);
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index f5847f9dec7c..813b6e93dc83 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -60,7 +60,7 @@ int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
 	if (kvm_s390_pv_cpu_get_handle(vcpu))
 		return -EINVAL;
 
-	vcpu->arch.pv.stor_base = __get_free_pages(GFP_KERNEL,
+	vcpu->arch.pv.stor_base = __get_free_pages(GFP_KERNEL_ACCOUNT,
 						   get_order(uv_info.guest_cpu_stor_len));
 	if (!vcpu->arch.pv.stor_base)
 		return -ENOMEM;
@@ -72,7 +72,7 @@ int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
 	uvcb.stor_origin = (u64)vcpu->arch.pv.stor_base;
 
 	/* Alloc Secure Instruction Data Area Designation */
-	vcpu->arch.sie_block->sidad = __get_free_page(GFP_KERNEL | __GFP_ZERO);
+	vcpu->arch.sie_block->sidad = __get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 	if (!vcpu->arch.sie_block->sidad) {
 		free_pages(vcpu->arch.pv.stor_base,
 			   get_order(uv_info.guest_cpu_stor_len));
@@ -120,7 +120,7 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm)
 	struct kvm_memory_slot *memslot;
 
 	kvm->arch.pv.stor_var = NULL;
-	kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL, get_order(base));
+	kvm->arch.pv.stor_base = __get_free_pages(GFP_KERNEL_ACCOUNT, get_order(base));
 	if (!kvm->arch.pv.stor_base)
 		return -ENOMEM;
 
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 4f3cbf6003a9..c5d0a58b2c29 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1234,7 +1234,7 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
 
 	mutex_lock(&kvm->arch.vsie.mutex);
 	if (kvm->arch.vsie.page_count < nr_vcpus) {
-		page = alloc_page(GFP_KERNEL | __GFP_ZERO | GFP_DMA);
+		page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA);
 		if (!page) {
 			mutex_unlock(&kvm->arch.vsie.mutex);
 			return ERR_PTR(-ENOMEM);
@@ -1336,7 +1336,7 @@ out_put:
 void kvm_s390_vsie_init(struct kvm *kvm)
 {
 	mutex_init(&kvm->arch.vsie.mutex);
-	INIT_RADIX_TREE(&kvm->arch.vsie.addr_to_page, GFP_KERNEL);
+	INIT_RADIX_TREE(&kvm->arch.vsie.addr_to_page, GFP_KERNEL_ACCOUNT);
 }
 
 /* Destroy the vsie data structures. To be called when a vm is destroyed. */
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 64795d034926..9bb2c7512cd5 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2,7 +2,7 @@
 /*
  *  KVM guest address space mapping code
  *
- *    Copyright IBM Corp. 2007, 2016, 2018
+ *    Copyright IBM Corp. 2007, 2020
  *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  *		 David Hildenbrand <david@redhat.com>
  *		 Janosch Frank <frankja@linux.vnet.ibm.com>
@@ -56,19 +56,19 @@ static struct gmap *gmap_alloc(unsigned long limit)
 		atype = _ASCE_TYPE_REGION1;
 		etype = _REGION1_ENTRY_EMPTY;
 	}
-	gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL);
+	gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL_ACCOUNT);
 	if (!gmap)
 		goto out;
 	INIT_LIST_HEAD(&gmap->crst_list);
 	INIT_LIST_HEAD(&gmap->children);
 	INIT_LIST_HEAD(&gmap->pt_list);
-	INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL);
-	INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC);
-	INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC);
+	INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL_ACCOUNT);
+	INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC | __GFP_ACCOUNT);
+	INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC | __GFP_ACCOUNT);
 	spin_lock_init(&gmap->guest_table_lock);
 	spin_lock_init(&gmap->shadow_lock);
 	refcount_set(&gmap->ref_count, 1);
-	page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER);
+	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
 	if (!page)
 		goto out_free;
 	page->index = 0;
@@ -309,7 +309,7 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
 	unsigned long *new;
 
 	/* since we dont free the gmap table until gmap_free we can unlock */
-	page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER);
+	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
 	if (!page)
 		return -ENOMEM;
 	new = (unsigned long *) page_to_phys(page);
@@ -594,7 +594,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	if (pmd_large(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m)
 		return -EFAULT;
 	/* Link gmap segment table entry location to page table. */
-	rc = radix_tree_preload(GFP_KERNEL);
+	rc = radix_tree_preload(GFP_KERNEL_ACCOUNT);
 	if (rc)
 		return rc;
 	ptl = pmd_lock(mm, pmd);
@@ -1218,11 +1218,11 @@ static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr,
 		vmaddr = __gmap_translate(parent, paddr);
 		if (IS_ERR_VALUE(vmaddr))
 			return vmaddr;
-		rmap = kzalloc(sizeof(*rmap), GFP_KERNEL);
+		rmap = kzalloc(sizeof(*rmap), GFP_KERNEL_ACCOUNT);
 		if (!rmap)
 			return -ENOMEM;
 		rmap->raddr = raddr;
-		rc = radix_tree_preload(GFP_KERNEL);
+		rc = radix_tree_preload(GFP_KERNEL_ACCOUNT);
 		if (rc) {
 			kfree(rmap);
 			return rc;
@@ -1741,7 +1741,7 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
 
 	BUG_ON(!gmap_is_shadow(sg));
 	/* Allocate a shadow region second table */
-	page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER);
+	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
 	if (!page)
 		return -ENOMEM;
 	page->index = r2t & _REGION_ENTRY_ORIGIN;
@@ -1825,7 +1825,7 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
 
 	BUG_ON(!gmap_is_shadow(sg));
 	/* Allocate a shadow region second table */
-	page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER);
+	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
 	if (!page)
 		return -ENOMEM;
 	page->index = r3t & _REGION_ENTRY_ORIGIN;
@@ -1909,7 +1909,7 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
 
 	BUG_ON(!gmap_is_shadow(sg) || (sgt & _REGION3_ENTRY_LARGE));
 	/* Allocate a shadow segment table */
-	page = alloc_pages(GFP_KERNEL, CRST_ALLOC_ORDER);
+	page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER);
 	if (!page)
 		return -ENOMEM;
 	page->index = sgt & _REGION_ENTRY_ORIGIN;
@@ -2116,7 +2116,7 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte)
 	parent = sg->parent;
 	prot = (pte_val(pte) & _PAGE_PROTECT) ? PROT_READ : PROT_WRITE;
 
-	rmap = kzalloc(sizeof(*rmap), GFP_KERNEL);
+	rmap = kzalloc(sizeof(*rmap), GFP_KERNEL_ACCOUNT);
 	if (!rmap)
 		return -ENOMEM;
 	rmap->raddr = (saddr & PAGE_MASK) | _SHADOW_RMAP_PGTABLE;
@@ -2128,7 +2128,7 @@ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte)
 			rc = vmaddr;
 			break;
 		}
-		rc = radix_tree_preload(GFP_KERNEL);
+		rc = radix_tree_preload(GFP_KERNEL_ACCOUNT);
 		if (rc)
 			break;
 		rc = -EAGAIN;
diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c
index bffbe69b2236..921d76fc3358 100644
--- a/arch/sh/boards/of-generic.c
+++ b/arch/sh/boards/of-generic.c
@@ -6,10 +6,10 @@
  */
 
 #include <linux/of.h>
+#include <linux/of_clk.h>
 #include <linux/of_fdt.h>
 #include <linux/clocksource.h>
 #include <linux/irqchip.h>
-#include <linux/clk-provider.h>
 #include <asm/machvec.h>
 #include <asm/rtc.h>
 
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 7435182ef846..fc44d9c88b41 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 generated-y += syscall_table.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 5269a704801f..3688fdae50e4 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -6,5 +6,4 @@ generated-y += syscall_table_64.h
 generated-y += syscall_table_c32.h
 generic-y += export.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7b6dd10b162a..21f851179ff0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -19,6 +19,7 @@ config X86_32
 	select KMAP_LOCAL
 	select MODULES_USE_ELF_REL
 	select OLD_SIGACTION
+	select ARCH_SPLIT_ARG64
 
 config X86_64
 	def_bool y
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 40b8fd375d52..e0bc3988c3fa 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -35,7 +35,7 @@ cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small -mno-red-zone
 KBUILD_CFLAGS += $(cflags-y)
 KBUILD_CFLAGS += -mno-mmx -mno-sse
-KBUILD_CFLAGS += -ffreestanding
+KBUILD_CFLAGS += -ffreestanding -fshort-wchar
 KBUILD_CFLAGS += -fno-stack-protector
 KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index d9a631c5973c..901ea5ebec22 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -12,6 +12,7 @@
 #undef CONFIG_PARAVIRT_XXL
 #undef CONFIG_PARAVIRT_SPINLOCKS
 #undef CONFIG_KASAN
+#undef CONFIG_KASAN_GENERIC
 
 /* cpu_feature_enabled() cannot be used this early */
 #define USE_EARLY_PGTABLE_L5
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index e04d90af4c27..4638a52d8eae 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -16,6 +16,7 @@
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 #include <asm/idtentry.h>
+#include <linux/kexec.h>
 #include <linux/version.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
@@ -26,6 +27,8 @@
 #include <linux/syscore_ops.h>
 #include <clocksource/hyperv_timer.h>
 
+int hyperv_init_cpuhp;
+
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 
@@ -401,6 +404,7 @@ void __init hyperv_init(void)
 
 	register_syscore_ops(&hv_syscore_ops);
 
+	hyperv_init_cpuhp = cpuhp;
 	return;
 
 remove_cpuhp_state:
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 5208ba49c89a..2c87350c1fb0 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -66,11 +66,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	if (!hv_hypercall_pg)
 		goto do_native;
 
-	if (cpumask_empty(cpus))
-		return;
-
 	local_irq_save(flags);
 
+	/*
+	 * Only check the mask _after_ interrupt has been disabled to avoid the
+	 * mask changing under our feet.
+	 */
+	if (cpumask_empty(cpus)) {
+		local_irq_restore(flags);
+		return;
+	}
+
 	flush_pcpu = (struct hv_tlb_flush **)
 		     this_cpu_ptr(hyperv_pcpu_input_arg);
 
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f5ef2d5b9231..84b887825f12 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -237,6 +237,7 @@
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
 #define X86_FEATURE_SEV_ES		( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_VM_PAGE_FLUSH	( 8*32+21) /* "" VM Page Flush MSR is supported */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -376,6 +377,7 @@
 #define X86_FEATURE_TSXLDTRK		(18*32+16) /* TSX Suspend Load Address Tracking */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_ARCH_LBR		(18*32+19) /* Intel ARCH LBR */
+#define X86_FEATURE_AVX512_FP16		(18*32+23) /* AVX512 FP16 */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index bc9758ef292e..c98f78330b09 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -213,8 +213,6 @@ static inline bool efi_is_64bit(void)
 
 static inline bool efi_is_native(void)
 {
-	if (!IS_ENABLED(CONFIG_X86_64))
-		return true;
 	return efi_is_64bit();
 }
 
@@ -382,4 +380,7 @@ static inline void efi_fake_memmap_early(void)
 }
 #endif
 
+#define arch_ima_efi_boot_mode	\
+	({ extern struct boot_params boot_params; boot_params.secure_boot; })
+
 #endif /* _ASM_X86_EFI_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7e5f33a0d0e2..3d6616f6f6ef 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -614,6 +614,7 @@ struct kvm_vcpu_arch {
 
 	struct kvm_pio_request pio;
 	void *pio_data;
+	void *guest_ins_data;
 
 	u8 event_exit_inst_len;
 
@@ -805,6 +806,9 @@ struct kvm_vcpu_arch {
 		 */
 		bool enforce;
 	} pv_cpuid;
+
+	/* Protected Guests */
+	bool guest_state_protected;
 };
 
 struct kvm_lpage_info {
@@ -1006,9 +1010,21 @@ struct kvm_arch {
 	 */
 	bool tdp_mmu_enabled;
 
-	/* List of struct tdp_mmu_pages being used as roots */
+	/*
+	 * List of struct kvmp_mmu_pages being used as roots.
+	 * All struct kvm_mmu_pages in the list should have
+	 * tdp_mmu_page set.
+	 * All struct kvm_mmu_pages in the list should have a positive
+	 * root_count except when a thread holds the MMU lock and is removing
+	 * an entry from the list.
+	 */
 	struct list_head tdp_mmu_roots;
-	/* List of struct tdp_mmu_pages not being used as roots */
+
+	/*
+	 * List of struct kvmp_mmu_pages not being used as roots.
+	 * All struct kvm_mmu_pages in the list should have
+	 * tdp_mmu_page set and a root_count of 0.
+	 */
 	struct list_head tdp_mmu_pages;
 };
 
@@ -1088,7 +1104,7 @@ struct kvm_x86_ops {
 	void (*hardware_disable)(void);
 	void (*hardware_unsetup)(void);
 	bool (*cpu_has_accelerated_tpr)(void);
-	bool (*has_emulated_msr)(u32 index);
+	bool (*has_emulated_msr)(struct kvm *kvm, u32 index);
 	void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu);
 
 	unsigned int vm_size;
@@ -1115,7 +1131,8 @@ struct kvm_x86_ops {
 			    struct kvm_segment *var, int seg);
 	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
 	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
-	int (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
+	bool (*is_valid_cr4)(struct kvm_vcpu *vcpu, unsigned long cr0);
+	void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
 	int (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
 	void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 	void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
@@ -1231,6 +1248,7 @@ struct kvm_x86_ops {
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
+	int (*cpu_dirty_log_size)(void);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
@@ -1280,6 +1298,9 @@ struct kvm_x86_ops {
 
 	void (*migrate_timers)(struct kvm_vcpu *vcpu);
 	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
+	int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
+
+	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
 };
 
 struct kvm_x86_nested_ops {
@@ -1461,6 +1482,7 @@ int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in);
 int kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
 int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int kvm_vcpu_halt(struct kvm_vcpu *vcpu);
+int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu);
 int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
 
 void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
@@ -1470,6 +1492,10 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
 int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
 		    int reason, bool has_error_code, u32 error_code);
 
+void kvm_free_guest_fpu(struct kvm_vcpu *vcpu);
+
+void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0);
+void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4);
 int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
 int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
@@ -1696,7 +1722,8 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
 
 int kvm_is_in_guest(void);
 
-int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
+void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
+				     u32 size);
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
 bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 
@@ -1743,4 +1770,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define GET_SMSTATE(type, buf, offset)		\
 	(*(type *)((buf) + (offset) - 0x7e00))
 
+int kvm_cpu_dirty_log_size(void);
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h
deleted file mode 100644
index 36c93b5cc239..000000000000
--- a/arch/x86/include/asm/local64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/local64.h>
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index ffc289992d1b..30f76b966857 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -74,6 +74,8 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {}
 
 
 #if IS_ENABLED(CONFIG_HYPERV)
+extern int hyperv_init_cpuhp;
+
 extern void *hv_hypercall_pg;
 extern void  __percpu  **hyperv_pcpu_input_arg;
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 2b5fc9accec4..546d6ecf0a35 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -472,6 +472,7 @@
 #define MSR_AMD64_ICIBSEXTDCTL		0xc001103c
 #define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_VM_PAGE_FLUSH		0xc001011e
 #define MSR_AMD64_SEV_ES_GHCB		0xc0010130
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 71d630bb5e08..1c561945b426 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -98,6 +98,16 @@ enum {
 	INTERCEPT_MWAIT_COND,
 	INTERCEPT_XSETBV,
 	INTERCEPT_RDPRU,
+	TRAP_EFER_WRITE,
+	TRAP_CR0_WRITE,
+	TRAP_CR1_WRITE,
+	TRAP_CR2_WRITE,
+	TRAP_CR3_WRITE,
+	TRAP_CR4_WRITE,
+	TRAP_CR5_WRITE,
+	TRAP_CR6_WRITE,
+	TRAP_CR7_WRITE,
+	TRAP_CR8_WRITE,
 	/* Byte offset 014h (word 5) */
 	INTERCEPT_INVLPGB = 160,
 	INTERCEPT_INVLPGB_ILLEGAL,
@@ -130,7 +140,7 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u32 exit_int_info_err;
 	u64 nested_ctl;
 	u64 avic_vapic_bar;
-	u8 reserved_4[8];
+	u64 ghcb_gpa;
 	u32 event_inj;
 	u32 event_inj_err;
 	u64 nested_cr3;
@@ -144,6 +154,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u8 reserved_6[8];	/* Offset 0xe8 */
 	u64 avic_logical_id;	/* Offset 0xf0 */
 	u64 avic_physical_id;	/* Offset 0xf8 */
+	u8 reserved_7[8];
+	u64 vmsa_pa;		/* Used for an SEV-ES guest */
 };
 
 
@@ -178,7 +190,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 #define LBR_CTL_ENABLE_MASK BIT_ULL(0)
 #define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1)
 
-#define SVM_INTERRUPT_SHADOW_MASK 1
+#define SVM_INTERRUPT_SHADOW_MASK	BIT_ULL(0)
+#define SVM_GUEST_INTERRUPT_MASK	BIT_ULL(1)
 
 #define SVM_IOIO_STR_SHIFT 2
 #define SVM_IOIO_REP_SHIFT 3
@@ -197,6 +210,7 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 
 #define SVM_NESTED_CTL_NP_ENABLE	BIT(0)
 #define SVM_NESTED_CTL_SEV_ENABLE	BIT(1)
+#define SVM_NESTED_CTL_SEV_ES_ENABLE	BIT(2)
 
 struct vmcb_seg {
 	u16 selector;
@@ -220,7 +234,8 @@ struct vmcb_save_area {
 	u8 cpl;
 	u8 reserved_2[4];
 	u64 efer;
-	u8 reserved_3[112];
+	u8 reserved_3[104];
+	u64 xss;		/* Valid for SEV-ES only */
 	u64 cr4;
 	u64 cr3;
 	u64 cr0;
@@ -251,9 +266,12 @@ struct vmcb_save_area {
 
 	/*
 	 * The following part of the save area is valid only for
-	 * SEV-ES guests when referenced through the GHCB.
+	 * SEV-ES guests when referenced through the GHCB or for
+	 * saving to the host save area.
 	 */
-	u8 reserved_7[104];
+	u8 reserved_7[80];
+	u32 pkru;
+	u8 reserved_7a[20];
 	u64 reserved_8;		/* rax already available at 0x01f8 */
 	u64 rcx;
 	u64 rdx;
@@ -294,7 +312,7 @@ struct ghcb {
 
 
 #define EXPECTED_VMCB_SAVE_AREA_SIZE		1032
-#define EXPECTED_VMCB_CONTROL_AREA_SIZE		256
+#define EXPECTED_VMCB_CONTROL_AREA_SIZE		272
 #define EXPECTED_GHCB_SIZE			PAGE_SIZE
 
 static inline void __unused_size_checks(void)
@@ -379,6 +397,16 @@ struct vmcb {
 				(unsigned long *)&ghcb->save.valid_bitmap);	\
 	}									\
 										\
+	static inline u64 ghcb_get_##field(struct ghcb *ghcb)			\
+	{									\
+		return ghcb->save.field;					\
+	}									\
+										\
+	static inline u64 ghcb_get_##field##_if_valid(struct ghcb *ghcb)	\
+	{									\
+		return ghcb_##field##_is_valid(ghcb) ? ghcb->save.field : 0;	\
+	}									\
+										\
 	static inline void ghcb_set_##field(struct ghcb *ghcb, u64 value)	\
 	{									\
 		__set_bit(GHCB_BITMAP_IDX(field),				\
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index f8ba5289ecb0..38ca445a8429 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -113,6 +113,7 @@
 #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
 #define VMX_MISC_SAVE_EFER_LMA			0x00000020
 #define VMX_MISC_ACTIVITY_HLT			0x00000040
+#define VMX_MISC_ACTIVITY_WAIT_SIPI		0x00000100
 #define VMX_MISC_ZERO_LEN_INS			0x40000000
 #define VMX_MISC_MSR_LIST_MULTIPLIER		512
 
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 89e5f3d1bba8..8e76d3701db3 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -12,6 +12,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define KVM_DIRTY_LOG_PAGE_OFFSET 64
 
 #define DE_VECTOR 0
 #define DB_VECTOR 1
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index f1d8307454e0..554f75fe013c 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -77,10 +77,28 @@
 #define SVM_EXIT_MWAIT_COND    0x08c
 #define SVM_EXIT_XSETBV        0x08d
 #define SVM_EXIT_RDPRU         0x08e
+#define SVM_EXIT_EFER_WRITE_TRAP		0x08f
+#define SVM_EXIT_CR0_WRITE_TRAP			0x090
+#define SVM_EXIT_CR1_WRITE_TRAP			0x091
+#define SVM_EXIT_CR2_WRITE_TRAP			0x092
+#define SVM_EXIT_CR3_WRITE_TRAP			0x093
+#define SVM_EXIT_CR4_WRITE_TRAP			0x094
+#define SVM_EXIT_CR5_WRITE_TRAP			0x095
+#define SVM_EXIT_CR6_WRITE_TRAP			0x096
+#define SVM_EXIT_CR7_WRITE_TRAP			0x097
+#define SVM_EXIT_CR8_WRITE_TRAP			0x098
+#define SVM_EXIT_CR9_WRITE_TRAP			0x099
+#define SVM_EXIT_CR10_WRITE_TRAP		0x09a
+#define SVM_EXIT_CR11_WRITE_TRAP		0x09b
+#define SVM_EXIT_CR12_WRITE_TRAP		0x09c
+#define SVM_EXIT_CR13_WRITE_TRAP		0x09d
+#define SVM_EXIT_CR14_WRITE_TRAP		0x09e
+#define SVM_EXIT_CR15_WRITE_TRAP		0x09f
 #define SVM_EXIT_INVPCID       0x0a2
 #define SVM_EXIT_NPF           0x400
 #define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS	0x402
+#define SVM_EXIT_VMGEXIT       0x403
 
 /* SEV-ES software-defined VMGEXIT events */
 #define SVM_VMGEXIT_MMIO_READ			0x80000001
@@ -183,10 +201,20 @@
 	{ SVM_EXIT_MONITOR,     "monitor" }, \
 	{ SVM_EXIT_MWAIT,       "mwait" }, \
 	{ SVM_EXIT_XSETBV,      "xsetbv" }, \
+	{ SVM_EXIT_EFER_WRITE_TRAP,	"write_efer_trap" }, \
+	{ SVM_EXIT_CR0_WRITE_TRAP,	"write_cr0_trap" }, \
+	{ SVM_EXIT_CR4_WRITE_TRAP,	"write_cr4_trap" }, \
+	{ SVM_EXIT_CR8_WRITE_TRAP,	"write_cr8_trap" }, \
 	{ SVM_EXIT_INVPCID,     "invpcid" }, \
 	{ SVM_EXIT_NPF,         "npf" }, \
 	{ SVM_EXIT_AVIC_INCOMPLETE_IPI,		"avic_incomplete_ipi" }, \
 	{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS,   "avic_unaccelerated_access" }, \
+	{ SVM_EXIT_VMGEXIT,		"vmgexit" }, \
+	{ SVM_VMGEXIT_MMIO_READ,	"vmgexit_mmio_read" }, \
+	{ SVM_VMGEXIT_MMIO_WRITE,	"vmgexit_mmio_write" }, \
+	{ SVM_VMGEXIT_NMI_COMPLETE,	"vmgexit_nmi_complete" }, \
+	{ SVM_VMGEXIT_AP_HLT_LOOP,	"vmgexit_ap_hlt_loop" }, \
+	{ SVM_VMGEXIT_AP_JUMP_TABLE,	"vmgexit_ap_jump_table" }, \
 	{ SVM_EXIT_ERR,         "invalid_guest_state" }
 
 
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index b8ff9e8ac0d5..ada955c5ebb6 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -32,6 +32,7 @@
 #define EXIT_REASON_EXTERNAL_INTERRUPT  1
 #define EXIT_REASON_TRIPLE_FAULT        2
 #define EXIT_REASON_INIT_SIGNAL			3
+#define EXIT_REASON_SIPI_SIGNAL         4
 
 #define EXIT_REASON_INTERRUPT_WINDOW    7
 #define EXIT_REASON_NMI_WINDOW          8
@@ -94,6 +95,7 @@
 	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
 	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
 	{ EXIT_REASON_INIT_SIGNAL,           "INIT_SIGNAL" }, \
+	{ EXIT_REASON_SIPI_SIGNAL,           "SIPI_SIGNAL" }, \
 	{ EXIT_REASON_INTERRUPT_WINDOW,      "INTERRUPT_WINDOW" }, \
 	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
 	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 68608bd892c0..5eeb808eb024 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -161,5 +161,3 @@ ifeq ($(CONFIG_X86_64),y)
 	obj-$(CONFIG_MMCONF_FAM10H)	+= mmconf-fam10h_64.o
 	obj-y				+= vsmp_64.o
 endif
-
-obj-$(CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT)	+= ima_arch.o
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index c8daa92f38dc..5d3a0b8fd379 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -112,7 +112,7 @@ SYM_FUNC_START(do_suspend_lowlevel)
 	movq	pt_regs_r14(%rax), %r14
 	movq	pt_regs_r15(%rax), %r15
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
 	/*
 	 * The suspend path may have poisoned some areas deeper in the stack,
 	 * which we now need to unpoison.
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index d502241995a3..42af31b64c2c 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -69,6 +69,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_CQM_MBM_TOTAL,		X86_FEATURE_CQM_LLC   },
 	{ X86_FEATURE_CQM_MBM_LOCAL,		X86_FEATURE_CQM_LLC   },
 	{ X86_FEATURE_AVX512_BF16,		X86_FEATURE_AVX512VL  },
+	{ X86_FEATURE_AVX512_FP16,		X86_FEATURE_AVX512BW  },
 	{ X86_FEATURE_ENQCMD,			X86_FEATURE_XSAVES    },
 	{ X86_FEATURE_PER_THREAD_MBA,		X86_FEATURE_MBA       },
 	{}
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index f628e3dc150f..43b54bef5448 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -135,14 +135,32 @@ static void hv_machine_shutdown(void)
 {
 	if (kexec_in_progress && hv_kexec_handler)
 		hv_kexec_handler();
+
+	/*
+	 * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor
+	 * corrupts the old VP Assist Pages and can crash the kexec kernel.
+	 */
+	if (kexec_in_progress && hyperv_init_cpuhp > 0)
+		cpuhp_remove_state(hyperv_init_cpuhp);
+
+	/* The function calls stop_other_cpus(). */
 	native_machine_shutdown();
+
+	/* Disable the hypercall page when there is only 1 active CPU. */
+	if (kexec_in_progress)
+		hyperv_cleanup();
 }
 
 static void hv_machine_crash_shutdown(struct pt_regs *regs)
 {
 	if (hv_crash_handler)
 		hv_crash_handler(regs);
+
+	/* The function calls crash_smp_send_stop(). */
 	native_machine_crash_shutdown(regs);
+
+	/* Disable the hypercall page when there is only 1 active CPU. */
+	hyperv_cleanup();
 }
 #endif /* CONFIG_KEXEC_CORE */
 #endif /* CONFIG_HYPERV */
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 23ad8e953dfb..a29997e6cf9e 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -167,9 +167,6 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
 	*repeat = 0;
 	*uniform = 1;
 
-	/* Make end inclusive instead of exclusive */
-	end--;
-
 	prev_match = MTRR_TYPE_INVALID;
 	for (i = 0; i < num_var_ranges; ++i) {
 		unsigned short start_state, end_state, inclusive;
@@ -261,6 +258,9 @@ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform)
 	int repeat;
 	u64 partial_end;
 
+	/* Make end inclusive instead of exclusive */
+	end--;
+
 	if (!mtrr_state_set)
 		return MTRR_TYPE_INVALID;
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 29ffb95b25ff..460f3e0df106 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -525,89 +525,70 @@ static void rdtgroup_remove(struct rdtgroup *rdtgrp)
 	kfree(rdtgrp);
 }
 
-struct task_move_callback {
-	struct callback_head	work;
-	struct rdtgroup		*rdtgrp;
-};
-
-static void move_myself(struct callback_head *head)
+static void _update_task_closid_rmid(void *task)
 {
-	struct task_move_callback *callback;
-	struct rdtgroup *rdtgrp;
-
-	callback = container_of(head, struct task_move_callback, work);
-	rdtgrp = callback->rdtgrp;
-
 	/*
-	 * If resource group was deleted before this task work callback
-	 * was invoked, then assign the task to root group and free the
-	 * resource group.
+	 * If the task is still current on this CPU, update PQR_ASSOC MSR.
+	 * Otherwise, the MSR is updated when the task is scheduled in.
 	 */
-	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
-	    (rdtgrp->flags & RDT_DELETED)) {
-		current->closid = 0;
-		current->rmid = 0;
-		rdtgroup_remove(rdtgrp);
-	}
-
-	if (unlikely(current->flags & PF_EXITING))
-		goto out;
-
-	preempt_disable();
-	/* update PQR_ASSOC MSR to make resource group go into effect */
-	resctrl_sched_in();
-	preempt_enable();
+	if (task == current)
+		resctrl_sched_in();
+}
 
-out:
-	kfree(callback);
+static void update_task_closid_rmid(struct task_struct *t)
+{
+	if (IS_ENABLED(CONFIG_SMP) && task_curr(t))
+		smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1);
+	else
+		_update_task_closid_rmid(t);
 }
 
 static int __rdtgroup_move_task(struct task_struct *tsk,
 				struct rdtgroup *rdtgrp)
 {
-	struct task_move_callback *callback;
-	int ret;
-
-	callback = kzalloc(sizeof(*callback), GFP_KERNEL);
-	if (!callback)
-		return -ENOMEM;
-	callback->work.func = move_myself;
-	callback->rdtgrp = rdtgrp;
+	/* If the task is already in rdtgrp, no need to move the task. */
+	if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid &&
+	     tsk->rmid == rdtgrp->mon.rmid) ||
+	    (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid &&
+	     tsk->closid == rdtgrp->mon.parent->closid))
+		return 0;
 
 	/*
-	 * Take a refcount, so rdtgrp cannot be freed before the
-	 * callback has been invoked.
+	 * Set the task's closid/rmid before the PQR_ASSOC MSR can be
+	 * updated by them.
+	 *
+	 * For ctrl_mon groups, move both closid and rmid.
+	 * For monitor groups, can move the tasks only from
+	 * their parent CTRL group.
 	 */
-	atomic_inc(&rdtgrp->waitcount);
-	ret = task_work_add(tsk, &callback->work, TWA_RESUME);
-	if (ret) {
-		/*
-		 * Task is exiting. Drop the refcount and free the callback.
-		 * No need to check the refcount as the group cannot be
-		 * deleted before the write function unlocks rdtgroup_mutex.
-		 */
-		atomic_dec(&rdtgrp->waitcount);
-		kfree(callback);
-		rdt_last_cmd_puts("Task exited\n");
-	} else {
-		/*
-		 * For ctrl_mon groups move both closid and rmid.
-		 * For monitor groups, can move the tasks only from
-		 * their parent CTRL group.
-		 */
-		if (rdtgrp->type == RDTCTRL_GROUP) {
-			tsk->closid = rdtgrp->closid;
+
+	if (rdtgrp->type == RDTCTRL_GROUP) {
+		tsk->closid = rdtgrp->closid;
+		tsk->rmid = rdtgrp->mon.rmid;
+	} else if (rdtgrp->type == RDTMON_GROUP) {
+		if (rdtgrp->mon.parent->closid == tsk->closid) {
 			tsk->rmid = rdtgrp->mon.rmid;
-		} else if (rdtgrp->type == RDTMON_GROUP) {
-			if (rdtgrp->mon.parent->closid == tsk->closid) {
-				tsk->rmid = rdtgrp->mon.rmid;
-			} else {
-				rdt_last_cmd_puts("Can't move task to different control group\n");
-				ret = -EINVAL;
-			}
+		} else {
+			rdt_last_cmd_puts("Can't move task to different control group\n");
+			return -EINVAL;
 		}
 	}
-	return ret;
+
+	/*
+	 * Ensure the task's closid and rmid are written before determining if
+	 * the task is current that will decide if it will be interrupted.
+	 */
+	barrier();
+
+	/*
+	 * By now, the task's closid and rmid are set. If the task is current
+	 * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource
+	 * group go into effect. If the task is not current, the MSR will be
+	 * updated when the task is scheduled in.
+	 */
+	update_task_closid_rmid(tsk);
+
+	return 0;
 }
 
 static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 866c9a9bcdee..236924930bf0 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -44,6 +44,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_SEV,		CPUID_EAX,  1, 0x8000001f, 0 },
 	{ X86_FEATURE_SEV_ES,		CPUID_EAX,  3, 0x8000001f, 0 },
 	{ X86_FEATURE_SME_COHERENT,	CPUID_EAX, 10, 0x8000001f, 0 },
+	{ X86_FEATURE_VM_PAGE_FLUSH,	CPUID_EAX,  2, 0x8000001f, 0 },
 	{ 0, 0, 0, 0, 0 }
 };
 
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 924571fe5864..c6ede3b3d302 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -501,12 +501,12 @@ static bool vmware_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs)
 	      ghcb_rbp_is_valid(ghcb)))
 		return false;
 
-	regs->bx = ghcb->save.rbx;
-	regs->cx = ghcb->save.rcx;
-	regs->dx = ghcb->save.rdx;
-	regs->si = ghcb->save.rsi;
-	regs->di = ghcb->save.rdi;
-	regs->bp = ghcb->save.rbp;
+	regs->bx = ghcb_get_rbx(ghcb);
+	regs->cx = ghcb_get_rcx(ghcb);
+	regs->dx = ghcb_get_rdx(ghcb);
+	regs->si = ghcb_get_rsi(ghcb);
+	regs->di = ghcb_get_rdi(ghcb);
+	regs->bp = ghcb_get_rbp(ghcb);
 
 	return true;
 }
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 34b18f6eeb2c..aa593743acf6 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -44,7 +44,6 @@ static int __init parse_no_kvmclock_vsyscall(char *arg)
 early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
 
 /* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
-#define HV_CLOCK_SIZE	(sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS)
 #define HVC_BOOT_ARRAY_SIZE \
 	(PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
 
diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c
index 7d04b356d44d..cdc04d091242 100644
--- a/arch/x86/kernel/sev-es-shared.c
+++ b/arch/x86/kernel/sev-es-shared.c
@@ -305,14 +305,14 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 	case 0xe4:
 	case 0xe5:
 		*exitinfo |= IOIO_TYPE_IN;
-		*exitinfo |= (u64)insn->immediate.value << 16;
+		*exitinfo |= (u8)insn->immediate.value << 16;
 		break;
 
 	/* OUT immediate opcodes */
 	case 0xe6:
 	case 0xe7:
 		*exitinfo |= IOIO_TYPE_OUT;
-		*exitinfo |= (u64)insn->immediate.value << 16;
+		*exitinfo |= (u8)insn->immediate.value << 16;
 		break;
 
 	/* IN register opcodes */
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 0a2ec801b63f..f5477eab5692 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -25,6 +25,7 @@
  *
  * Send feedback to <colpatch@us.ibm.com>
  */
+#include <linux/interrupt.h>
 #include <linux/nodemask.h>
 #include <linux/export.h>
 #include <linux/mmzone.h>
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index fb55981f2a0d..7f5aec758f0e 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -303,11 +303,12 @@ DEFINE_IDTENTRY_ERRORCODE(exc_alignment_check)
 	local_irq_enable();
 
 	if (handle_user_split_lock(regs, error_code))
-		return;
+		goto out;
 
 	do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs,
 		error_code, BUS_ADRALN, NULL);
 
+out:
 	local_irq_disable();
 }
 
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index f92dfd8ef10d..7ac592664c52 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -100,7 +100,8 @@ config KVM_AMD_SEV
 	depends on KVM_AMD && X86_64
 	depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
 	help
-	Provides support for launching Encrypted VMs on AMD processors.
+	  Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
+	  with Encrypted State (SEV-ES) on AMD processors.
 
 config KVM_MMU_AUDIT
 	bool "Audit KVM MMU"
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index b804444e16d4..4bd14ab01323 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -10,7 +10,8 @@ endif
 KVM := ../../../virt/kvm
 
 kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
-				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
+				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \
+				$(KVM)/dirty_ring.o
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
 kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 83637a2ff605..13036cf0b912 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -146,6 +146,7 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
 					   MSR_IA32_MISC_ENABLE_MWAIT);
 	}
 }
+EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime);
 
 static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
@@ -418,7 +419,7 @@ void kvm_set_cpu_caps(void)
 		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
 		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
 		F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) |
-		F(SERIALIZE) | F(TSXLDTRK)
+		F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16)
 	);
 
 	/* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index f7a6e8f83783..dc921d76e42e 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -264,6 +264,20 @@ static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu)
 	return x86_stepping(best->eax);
 }
 
+static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu)
+{
+	return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) ||
+		guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) ||
+		guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) ||
+		guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD));
+}
+
+static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu)
+{
+	return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) ||
+		guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB));
+}
+
 static inline bool supports_cpuid_fault(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.msr_platform_info & MSR_PLATFORM_INFO_CPUID_FAULT;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 5c7c4060b45c..922c69dcca4d 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1951,8 +1951,8 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args)
 	return kvm_hv_eventfd_assign(kvm, args->conn_id, args->fd);
 }
 
-int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
-				struct kvm_cpuid_entry2 __user *entries)
+int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
+		     struct kvm_cpuid_entry2 __user *entries)
 {
 	uint16_t evmcs_ver = 0;
 	struct kvm_cpuid_entry2 cpuid_entries[] = {
@@ -2037,7 +2037,7 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 			 * Direct Synthetic timers only make sense with in-kernel
 			 * LAPIC
 			 */
-			if (lapic_in_kernel(vcpu))
+			if (!vcpu || lapic_in_kernel(vcpu))
 				ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE;
 
 			break;
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index e68c6c2e9649..6d7def2b0aad 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -126,7 +126,7 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 void kvm_hv_init_vm(struct kvm *kvm);
 void kvm_hv_destroy_vm(struct kvm *kvm);
 int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args);
-int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
-				struct kvm_cpuid_entry2 __user *entries);
+int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
+		     struct kvm_cpuid_entry2 __user *entries);
 
 #endif
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index a889563ad02d..f15bc16de07c 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -9,6 +9,31 @@
 	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR  \
 	 | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE)
 
+static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu,
+					     enum kvm_reg reg)
+{
+	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu,
+					 enum kvm_reg reg)
+{
+	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
+static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu,
+					       enum kvm_reg reg)
+{
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu,
+					   enum kvm_reg reg)
+{
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
 #define BUILD_KVM_GPR_ACCESSORS(lname, uname)				      \
 static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
 {									      \
@@ -18,6 +43,7 @@ static __always_inline void kvm_##lname##_write(struct kvm_vcpu *vcpu,	      \
 						unsigned long val)	      \
 {									      \
 	vcpu->arch.regs[VCPU_REGS_##uname] = val;			      \
+	kvm_register_mark_dirty(vcpu, VCPU_REGS_##uname);		      \
 }
 BUILD_KVM_GPR_ACCESSORS(rax, RAX)
 BUILD_KVM_GPR_ACCESSORS(rbx, RBX)
@@ -37,31 +63,6 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14)
 BUILD_KVM_GPR_ACCESSORS(r15, R15)
 #endif
 
-static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu,
-					     enum kvm_reg reg)
-{
-	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
-}
-
-static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu,
-					 enum kvm_reg reg)
-{
-	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
-}
-
-static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu,
-					       enum kvm_reg reg)
-{
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
-}
-
-static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu,
-					   enum kvm_reg reg)
-{
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
-}
-
 static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg)
 {
 	if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS))
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 86c33d53c90a..43cceadd073e 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -674,7 +674,7 @@ static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu)
 			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
 		return false;
 	}
-	return val & 0x1;
+	return val & KVM_PV_EOI_ENABLED;
 }
 
 static void pv_eoi_set_pending(struct kvm_vcpu *vcpu)
@@ -2843,14 +2843,35 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u8 sipi_vector;
+	int r;
 	unsigned long pe;
 
-	if (!lapic_in_kernel(vcpu) || !apic->pending_events)
+	if (!lapic_in_kernel(vcpu))
 		return;
 
 	/*
+	 * Read pending events before calling the check_events
+	 * callback.
+	 */
+	pe = smp_load_acquire(&apic->pending_events);
+	if (!pe)
+		return;
+
+	if (is_guest_mode(vcpu)) {
+		r = kvm_x86_ops.nested_ops->check_events(vcpu);
+		if (r < 0)
+			return;
+		/*
+		 * If an event has happened and caused a vmexit,
+		 * we know INITs are latched and therefore
+		 * we will not incorrectly deliver an APIC
+		 * event instead of a vmexit.
+		 */
+	}
+
+	/*
 	 * INITs are latched while CPU is in specific states
-	 * (SMM, VMX non-root mode, SVM with GIF=0).
+	 * (SMM, VMX root mode, SVM with GIF=0).
 	 * Because a CPU cannot be in these states immediately
 	 * after it has processed an INIT signal (and thus in
 	 * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs
@@ -2858,26 +2879,28 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 	 */
 	if (kvm_vcpu_latch_init(vcpu)) {
 		WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED);
-		if (test_bit(KVM_APIC_SIPI, &apic->pending_events))
+		if (test_bit(KVM_APIC_SIPI, &pe))
 			clear_bit(KVM_APIC_SIPI, &apic->pending_events);
 		return;
 	}
 
-	pe = xchg(&apic->pending_events, 0);
 	if (test_bit(KVM_APIC_INIT, &pe)) {
+		clear_bit(KVM_APIC_INIT, &apic->pending_events);
 		kvm_vcpu_reset(vcpu, true);
 		if (kvm_vcpu_is_bsp(apic->vcpu))
 			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 		else
 			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
 	}
-	if (test_bit(KVM_APIC_SIPI, &pe) &&
-	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
-		/* evaluate pending_events before reading the vector */
-		smp_rmb();
-		sipi_vector = apic->sipi_vector;
-		kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector);
-		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+	if (test_bit(KVM_APIC_SIPI, &pe)) {
+		clear_bit(KVM_APIC_SIPI, &apic->pending_events);
+		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
+			/* evaluate pending_events before reading the vector */
+			smp_rmb();
+			sipi_vector = apic->sipi_vector;
+			kvm_x86_ops.vcpu_deliver_sipi_vector(vcpu, sipi_vector);
+			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		}
 	}
 }
 
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 9c4a9c8e43d9..581925e476d6 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -49,7 +49,7 @@ static inline u64 rsvd_bits(int s, int e)
 	if (e < s)
 		return 0;
 
-	return ((1ULL << (e - s + 1)) - 1) << s;
+	return ((2ULL << (e - s)) - 1) << s;
 }
 
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 7a6ae9e90bd7..6d16481aa29d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -820,7 +820,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
 		return NULL;
-	if (no_dirty_log && slot->dirty_bitmap)
+	if (no_dirty_log && kvm_slot_dirty_track_enabled(slot))
 		return NULL;
 
 	return slot;
@@ -1289,6 +1289,14 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
 }
 
+int kvm_cpu_dirty_log_size(void)
+{
+	if (kvm_x86_ops.cpu_dirty_log_size)
+		return kvm_x86_ops.cpu_dirty_log_size();
+
+	return 0;
+}
+
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn)
 {
@@ -3485,26 +3493,25 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
  * Return the level of the lowest level SPTE added to sptes.
  * That SPTE may be non-present.
  */
-static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
+static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level)
 {
 	struct kvm_shadow_walk_iterator iterator;
-	int leaf = vcpu->arch.mmu->root_level;
+	int leaf = -1;
 	u64 spte;
 
-
 	walk_shadow_page_lockless_begin(vcpu);
 
-	for (shadow_walk_init(&iterator, vcpu, addr);
+	for (shadow_walk_init(&iterator, vcpu, addr),
+	     *root_level = iterator.level;
 	     shadow_walk_okay(&iterator);
 	     __shadow_walk_next(&iterator, spte)) {
 		leaf = iterator.level;
 		spte = mmu_spte_get_lockless(iterator.sptep);
 
-		sptes[leaf - 1] = spte;
+		sptes[leaf] = spte;
 
 		if (!is_shadow_present_pte(spte))
 			break;
-
 	}
 
 	walk_shadow_page_lockless_end(vcpu);
@@ -3512,14 +3519,12 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
 	return leaf;
 }
 
-/* return true if reserved bit is detected on spte. */
+/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
 static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
-	u64 sptes[PT64_ROOT_MAX_LEVEL];
+	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
 	struct rsvd_bits_validate *rsvd_check;
-	int root = vcpu->arch.mmu->shadow_root_level;
-	int leaf;
-	int level;
+	int root, leaf, level;
 	bool reserved = false;
 
 	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) {
@@ -3528,35 +3533,45 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 	}
 
 	if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa))
-		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes);
+		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
 	else
-		leaf = get_walk(vcpu, addr, sptes);
+		leaf = get_walk(vcpu, addr, sptes, &root);
+
+	if (unlikely(leaf < 0)) {
+		*sptep = 0ull;
+		return reserved;
+	}
+
+	*sptep = sptes[leaf];
+
+	/*
+	 * Skip reserved bits checks on the terminal leaf if it's not a valid
+	 * SPTE.  Note, this also (intentionally) skips MMIO SPTEs, which, by
+	 * design, always have reserved bits set.  The purpose of the checks is
+	 * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs.
+	 */
+	if (!is_shadow_present_pte(sptes[leaf]))
+		leaf++;
 
 	rsvd_check = &vcpu->arch.mmu->shadow_zero_check;
 
-	for (level = root; level >= leaf; level--) {
-		if (!is_shadow_present_pte(sptes[level - 1]))
-			break;
+	for (level = root; level >= leaf; level--)
 		/*
 		 * Use a bitwise-OR instead of a logical-OR to aggregate the
 		 * reserved bit and EPT's invalid memtype/XWR checks to avoid
 		 * adding a Jcc in the loop.
 		 */
-		reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level - 1]) |
-			    __is_rsvd_bits_set(rsvd_check, sptes[level - 1],
-					       level);
-	}
+		reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) |
+			    __is_rsvd_bits_set(rsvd_check, sptes[level], level);
 
 	if (reserved) {
 		pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n",
 		       __func__, addr);
 		for (level = root; level >= leaf; level--)
 			pr_err("------ spte 0x%llx level %d.\n",
-			       sptes[level - 1], level);
+			       sptes[level], level);
 	}
 
-	*sptep = sptes[leaf - 1];
-
 	return reserved;
 }
 
diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
index 213699b27b44..e798489b56b5 100644
--- a/arch/x86/kvm/mmu/mmutrace.h
+++ b/arch/x86/kvm/mmu/mmutrace.h
@@ -381,6 +381,35 @@ TRACE_EVENT(
 	)
 );
 
+TRACE_EVENT(
+	kvm_tdp_mmu_spte_changed,
+	TP_PROTO(int as_id, gfn_t gfn, int level, u64 old_spte, u64 new_spte),
+	TP_ARGS(as_id, gfn, level, old_spte, new_spte),
+
+	TP_STRUCT__entry(
+		__field(u64, gfn)
+		__field(u64, old_spte)
+		__field(u64, new_spte)
+		/* Level cannot be larger than 5 on x86, so it fits in a u8. */
+		__field(u8, level)
+		/* as_id can only be 0 or 1 x86, so it fits in a u8. */
+		__field(u8, as_id)
+	),
+
+	TP_fast_assign(
+		__entry->gfn = gfn;
+		__entry->old_spte = old_spte;
+		__entry->new_spte = new_spte;
+		__entry->level = level;
+		__entry->as_id = as_id;
+	),
+
+	TP_printk("as id %d gfn %llx level %d old_spte %llx new_spte %llx",
+		  __entry->as_id, __entry->gfn, __entry->level,
+		  __entry->old_spte, __entry->new_spte
+	)
+);
+
 #endif /* _TRACE_KVMMMU_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 84c8f06bec26..2ef8615f9dba 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -7,6 +7,8 @@
 #include "tdp_mmu.h"
 #include "spte.h"
 
+#include <trace/events/kvm.h>
+
 #ifdef CONFIG_X86_64
 static bool __read_mostly tdp_mmu_enabled = false;
 module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644);
@@ -42,7 +44,48 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
 }
 
-#define for_each_tdp_mmu_root(_kvm, _root)			    \
+static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
+{
+	if (kvm_mmu_put_root(kvm, root))
+		kvm_tdp_mmu_free_root(kvm, root);
+}
+
+static inline bool tdp_mmu_next_root_valid(struct kvm *kvm,
+					   struct kvm_mmu_page *root)
+{
+	lockdep_assert_held(&kvm->mmu_lock);
+
+	if (list_entry_is_head(root, &kvm->arch.tdp_mmu_roots, link))
+		return false;
+
+	kvm_mmu_get_root(kvm, root);
+	return true;
+
+}
+
+static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
+						     struct kvm_mmu_page *root)
+{
+	struct kvm_mmu_page *next_root;
+
+	next_root = list_next_entry(root, link);
+	tdp_mmu_put_root(kvm, root);
+	return next_root;
+}
+
+/*
+ * Note: this iterator gets and puts references to the roots it iterates over.
+ * This makes it safe to release the MMU lock and yield within the loop, but
+ * if exiting the loop early, the caller must drop the reference to the most
+ * recent root. (Unless keeping a live reference is desirable.)
+ */
+#define for_each_tdp_mmu_root_yield_safe(_kvm, _root)				\
+	for (_root = list_first_entry(&_kvm->arch.tdp_mmu_roots,	\
+				      typeof(*_root), link);		\
+	     tdp_mmu_next_root_valid(_kvm, _root);			\
+	     _root = tdp_mmu_next_root(_kvm, _root))
+
+#define for_each_tdp_mmu_root(_kvm, _root)				\
 	list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link)
 
 bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa)
@@ -108,6 +151,8 @@ static struct kvm_mmu_page *alloc_tdp_mmu_page(struct kvm_vcpu *vcpu, gfn_t gfn,
 	sp->gfn = gfn;
 	sp->tdp_mmu_page = true;
 
+	trace_kvm_mmu_get_page(sp, true);
+
 	return sp;
 }
 
@@ -185,7 +230,7 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
 	if ((!is_writable_pte(old_spte) || pfn_changed) &&
 	    is_writable_pte(new_spte)) {
 		slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn);
-		mark_page_dirty_in_slot(slot, gfn);
+		mark_page_dirty_in_slot(kvm, slot, gfn);
 	}
 }
 
@@ -244,6 +289,8 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 	if (old_spte == new_spte)
 		return;
 
+	trace_kvm_tdp_mmu_spte_changed(as_id, gfn, level, old_spte, new_spte);
+
 	/*
 	 * The only times a SPTE should be changed from a non-present to
 	 * non-present state is when an MMIO entry is installed/modified/
@@ -278,6 +325,8 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 		pt = spte_to_child_pt(old_spte, level);
 		sp = sptep_to_sp(pt);
 
+		trace_kvm_mmu_prepare_zap_page(sp);
+
 		list_del(&sp->link);
 
 		if (sp->lpage_disallowed)
@@ -439,18 +488,9 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
 	struct kvm_mmu_page *root;
 	bool flush = false;
 
-	for_each_tdp_mmu_root(kvm, root) {
-		/*
-		 * Take a reference on the root so that it cannot be freed if
-		 * this thread releases the MMU lock and yields in this loop.
-		 */
-		kvm_mmu_get_root(kvm, root);
-
+	for_each_tdp_mmu_root_yield_safe(kvm, root)
 		flush |= zap_gfn_range(kvm, root, start, end, true);
 
-		kvm_mmu_put_root(kvm, root);
-	}
-
 	return flush;
 }
 
@@ -480,11 +520,13 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write,
 	if (unlikely(is_noslot_pfn(pfn))) {
 		new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
 		trace_mark_mmio_spte(iter->sptep, iter->gfn, new_spte);
-	} else
+	} else {
 		make_spte_ret = make_spte(vcpu, ACC_ALL, iter->level, iter->gfn,
 					 pfn, iter->old_spte, prefault, true,
 					 map_writable, !shadow_accessed_mask,
 					 &new_spte);
+		trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep);
+	}
 
 	if (new_spte == iter->old_spte)
 		ret = RET_PF_SPURIOUS;
@@ -609,13 +651,7 @@ static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start,
 	int ret = 0;
 	int as_id;
 
-	for_each_tdp_mmu_root(kvm, root) {
-		/*
-		 * Take a reference on the root so that it cannot be freed if
-		 * this thread releases the MMU lock and yields in this loop.
-		 */
-		kvm_mmu_get_root(kvm, root);
-
+	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		as_id = kvm_mmu_page_as_id(root);
 		slots = __kvm_memslots(kvm, as_id);
 		kvm_for_each_memslot(memslot, slots) {
@@ -637,8 +673,6 @@ static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start,
 			ret |= handler(kvm, memslot, root, gfn_start,
 				       gfn_end, data);
 		}
-
-		kvm_mmu_put_root(kvm, root);
 	}
 
 	return ret;
@@ -698,6 +732,8 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot,
 
 		tdp_mmu_set_spte_no_acc_track(kvm, &iter, new_spte);
 		young = 1;
+
+		trace_kvm_age_page(iter.gfn, iter.level, slot, young);
 	}
 
 	return young;
@@ -826,21 +862,13 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot,
 	int root_as_id;
 	bool spte_set = false;
 
-	for_each_tdp_mmu_root(kvm, root) {
+	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
 			continue;
 
-		/*
-		 * Take a reference on the root so that it cannot be freed if
-		 * this thread releases the MMU lock and yields in this loop.
-		 */
-		kvm_mmu_get_root(kvm, root);
-
 		spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn,
 			     slot->base_gfn + slot->npages, min_level);
-
-		kvm_mmu_put_root(kvm, root);
 	}
 
 	return spte_set;
@@ -894,21 +922,13 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
 	int root_as_id;
 	bool spte_set = false;
 
-	for_each_tdp_mmu_root(kvm, root) {
+	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
 			continue;
 
-		/*
-		 * Take a reference on the root so that it cannot be freed if
-		 * this thread releases the MMU lock and yields in this loop.
-		 */
-		kvm_mmu_get_root(kvm, root);
-
 		spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn,
 				slot->base_gfn + slot->npages);
-
-		kvm_mmu_put_root(kvm, root);
 	}
 
 	return spte_set;
@@ -1017,21 +1037,13 @@ bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot)
 	int root_as_id;
 	bool spte_set = false;
 
-	for_each_tdp_mmu_root(kvm, root) {
+	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
 			continue;
 
-		/*
-		 * Take a reference on the root so that it cannot be freed if
-		 * this thread releases the MMU lock and yields in this loop.
-		 */
-		kvm_mmu_get_root(kvm, root);
-
 		spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn,
 				slot->base_gfn + slot->npages);
-
-		kvm_mmu_put_root(kvm, root);
 	}
 	return spte_set;
 }
@@ -1077,21 +1089,13 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
 	struct kvm_mmu_page *root;
 	int root_as_id;
 
-	for_each_tdp_mmu_root(kvm, root) {
+	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
 			continue;
 
-		/*
-		 * Take a reference on the root so that it cannot be freed if
-		 * this thread releases the MMU lock and yields in this loop.
-		 */
-		kvm_mmu_get_root(kvm, root);
-
 		zap_collapsible_spte_range(kvm, root, slot->base_gfn,
 					   slot->base_gfn + slot->npages);
-
-		kvm_mmu_put_root(kvm, root);
 	}
 }
 
@@ -1148,16 +1152,19 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
  * Return the level of the lowest level SPTE added to sptes.
  * That SPTE may be non-present.
  */
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			 int *root_level)
 {
 	struct tdp_iter iter;
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
-	int leaf = vcpu->arch.mmu->shadow_root_level;
 	gfn_t gfn = addr >> PAGE_SHIFT;
+	int leaf = -1;
+
+	*root_level = vcpu->arch.mmu->shadow_root_level;
 
 	tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
 		leaf = iter.level;
-		sptes[leaf - 1] = iter.old_spte;
+		sptes[leaf] = iter.old_spte;
 	}
 
 	return leaf;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 556e065503f6..cbbdbadd1526 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -44,5 +44,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
 bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn);
 
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes);
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			 int *root_level);
+
 #endif /* __KVM_X86_MMU_TDP_MMU_H */
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 7f0059aa30e1..f472fdb6ae7e 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -84,12 +84,8 @@ bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	} else
 		/* MTRR mask */
 		mask |= 0x7ff;
-	if (data & mask) {
-		kvm_inject_gp(vcpu, 0);
-		return false;
-	}
 
-	return true;
+	return (data & mask) == 0;
 }
 EXPORT_SYMBOL_GPL(kvm_mtrr_valid);
 
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 8c550999ace0..0ef84d57b72e 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -233,7 +233,8 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
  */
 static int avic_update_access_page(struct kvm *kvm, bool activate)
 {
-	int ret = 0;
+	void __user *ret;
+	int r = 0;
 
 	mutex_lock(&kvm->slots_lock);
 	/*
@@ -249,13 +250,15 @@ static int avic_update_access_page(struct kvm *kvm, bool activate)
 				      APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
 				      APIC_DEFAULT_PHYS_BASE,
 				      activate ? PAGE_SIZE : 0);
-	if (ret)
+	if (IS_ERR(ret)) {
+		r = PTR_ERR(ret);
 		goto out;
+	}
 
 	kvm->arch.apic_access_page_done = activate;
 out:
 	mutex_unlock(&kvm->slots_lock);
-	return ret;
+	return r;
 }
 
 static int avic_init_backing_page(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 9e4c226dbf7d..cb4c6ee10029 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -199,6 +199,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+
 	if (!nested_svm_vmrun_msrpm(svm)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror =
@@ -254,7 +255,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
 		    (vmcb12->save.cr3 & MSR_CR3_LONG_MBZ_MASK))
 			return false;
 	}
-	if (kvm_valid_cr4(&svm->vcpu, vmcb12->save.cr4))
+	if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4))
 		return false;
 
 	return nested_vmcb_check_controls(&vmcb12->control);
@@ -381,7 +382,7 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	svm->vmcb->save.ds = vmcb12->save.ds;
 	svm->vmcb->save.gdtr = vmcb12->save.gdtr;
 	svm->vmcb->save.idtr = vmcb12->save.idtr;
-	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags);
+	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED);
 	svm_set_efer(&svm->vcpu, vmcb12->save.efer);
 	svm_set_cr0(&svm->vcpu, vmcb12->save.cr0);
 	svm_set_cr4(&svm->vcpu, vmcb12->save.cr4);
@@ -394,8 +395,8 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	svm->vmcb->save.rax = vmcb12->save.rax;
 	svm->vmcb->save.rsp = vmcb12->save.rsp;
 	svm->vmcb->save.rip = vmcb12->save.rip;
-	svm->vmcb->save.dr7 = vmcb12->save.dr7;
-	svm->vcpu.arch.dr6  = vmcb12->save.dr6;
+	svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1;
+	svm->vcpu.arch.dr6  = vmcb12->save.dr6 | DR6_FIXED_1 | DR6_RTM;
 	svm->vmcb->save.cpl = vmcb12->save.cpl;
 }
 
@@ -595,6 +596,8 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	svm->nested.vmcb12_gpa = 0;
 	WARN_ON_ONCE(svm->nested.nested_run_pending);
 
+	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu);
+
 	/* in case we halted in L2 */
 	svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
@@ -660,13 +663,14 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	svm->vmcb->save.gdtr = hsave->save.gdtr;
 	svm->vmcb->save.idtr = hsave->save.idtr;
 	kvm_set_rflags(&svm->vcpu, hsave->save.rflags);
+	kvm_set_rflags(&svm->vcpu, hsave->save.rflags | X86_EFLAGS_FIXED);
 	svm_set_efer(&svm->vcpu, hsave->save.efer);
 	svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE);
 	svm_set_cr4(&svm->vcpu, hsave->save.cr4);
 	kvm_rax_write(&svm->vcpu, hsave->save.rax);
 	kvm_rsp_write(&svm->vcpu, hsave->save.rsp);
 	kvm_rip_write(&svm->vcpu, hsave->save.rip);
-	svm->vmcb->save.dr7 = 0;
+	svm->vmcb->save.dr7 = DR7_FIXED_1;
 	svm->vmcb->save.cpl = 0;
 	svm->vmcb->control.exit_int_info = 0;
 
@@ -753,6 +757,7 @@ void svm_leave_nested(struct vcpu_svm *svm)
 		leave_guest_mode(&svm->vcpu);
 		copy_vmcb_control_area(&vmcb->control, &hsave->control);
 		nested_svm_uninit_mmu_context(&svm->vcpu);
+		vmcb_mark_all_dirty(svm->vmcb);
 	}
 
 	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu);
@@ -1193,6 +1198,10 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	 * in the registers, the save area of the nested state instead
 	 * contains saved L1 state.
 	 */
+
+	svm->nested.nested_run_pending =
+		!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
+
 	copy_vmcb_control_area(&hsave->control, &svm->vmcb->control);
 	hsave->save = *save;
 
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 566f4d18185b..c8ffdbc81709 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -14,10 +14,20 @@
 #include <linux/psp-sev.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
+#include <linux/processor.h>
+#include <linux/trace_events.h>
+#include <asm/fpu/internal.h>
+
+#include <asm/trapnr.h>
 
 #include "x86.h"
 #include "svm.h"
+#include "cpuid.h"
+#include "trace.h"
+
+#define __ex(x) __kvm_handle_fault_on_reboot(x)
 
+static u8 sev_enc_bit;
 static int sev_flush_asids(void);
 static DECLARE_RWSEM(sev_deactivate_lock);
 static DEFINE_MUTEX(sev_bitmap_lock);
@@ -25,7 +35,6 @@ unsigned int max_sev_asid;
 static unsigned int min_sev_asid;
 static unsigned long *sev_asid_bitmap;
 static unsigned long *sev_reclaim_asid_bitmap;
-#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
 
 struct enc_region {
 	struct list_head list;
@@ -57,19 +66,19 @@ static int sev_flush_asids(void)
 }
 
 /* Must be called with the sev_bitmap_lock held */
-static bool __sev_recycle_asids(void)
+static bool __sev_recycle_asids(int min_asid, int max_asid)
 {
 	int pos;
 
 	/* Check if there are any ASIDs to reclaim before performing a flush */
-	pos = find_next_bit(sev_reclaim_asid_bitmap,
-			    max_sev_asid, min_sev_asid - 1);
-	if (pos >= max_sev_asid)
+	pos = find_next_bit(sev_reclaim_asid_bitmap, max_sev_asid, min_asid);
+	if (pos >= max_asid)
 		return false;
 
 	if (sev_flush_asids())
 		return false;
 
+	/* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */
 	bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
 		   max_sev_asid);
 	bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid);
@@ -77,20 +86,23 @@ static bool __sev_recycle_asids(void)
 	return true;
 }
 
-static int sev_asid_new(void)
+static int sev_asid_new(struct kvm_sev_info *sev)
 {
+	int pos, min_asid, max_asid;
 	bool retry = true;
-	int pos;
 
 	mutex_lock(&sev_bitmap_lock);
 
 	/*
-	 * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid.
+	 * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
+	 * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
 	 */
+	min_asid = sev->es_active ? 0 : min_sev_asid - 1;
+	max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
 again:
-	pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1);
-	if (pos >= max_sev_asid) {
-		if (retry && __sev_recycle_asids()) {
+	pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_asid);
+	if (pos >= max_asid) {
+		if (retry && __sev_recycle_asids(min_asid, max_asid)) {
 			retry = false;
 			goto again;
 		}
@@ -172,7 +184,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (unlikely(sev->active))
 		return ret;
 
-	asid = sev_asid_new();
+	asid = sev_asid_new(sev);
 	if (asid < 0)
 		return ret;
 
@@ -191,6 +203,16 @@ e_free:
 	return ret;
 }
 
+static int sev_es_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	if (!sev_es)
+		return -ENOTTY;
+
+	to_kvm_svm(kvm)->sev_info.es_active = true;
+
+	return sev_guest_init(kvm, argp);
+}
+
 static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
 {
 	struct sev_data_activate *data;
@@ -490,6 +512,96 @@ e_free:
 	return ret;
 }
 
+static int sev_es_sync_vmsa(struct vcpu_svm *svm)
+{
+	struct vmcb_save_area *save = &svm->vmcb->save;
+
+	/* Check some debug related fields before encrypting the VMSA */
+	if (svm->vcpu.guest_debug || (save->dr7 & ~DR7_FIXED_1))
+		return -EINVAL;
+
+	/* Sync registgers */
+	save->rax = svm->vcpu.arch.regs[VCPU_REGS_RAX];
+	save->rbx = svm->vcpu.arch.regs[VCPU_REGS_RBX];
+	save->rcx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
+	save->rdx = svm->vcpu.arch.regs[VCPU_REGS_RDX];
+	save->rsp = svm->vcpu.arch.regs[VCPU_REGS_RSP];
+	save->rbp = svm->vcpu.arch.regs[VCPU_REGS_RBP];
+	save->rsi = svm->vcpu.arch.regs[VCPU_REGS_RSI];
+	save->rdi = svm->vcpu.arch.regs[VCPU_REGS_RDI];
+#ifdef CONFIG_X86_64
+	save->r8  = svm->vcpu.arch.regs[VCPU_REGS_R8];
+	save->r9  = svm->vcpu.arch.regs[VCPU_REGS_R9];
+	save->r10 = svm->vcpu.arch.regs[VCPU_REGS_R10];
+	save->r11 = svm->vcpu.arch.regs[VCPU_REGS_R11];
+	save->r12 = svm->vcpu.arch.regs[VCPU_REGS_R12];
+	save->r13 = svm->vcpu.arch.regs[VCPU_REGS_R13];
+	save->r14 = svm->vcpu.arch.regs[VCPU_REGS_R14];
+	save->r15 = svm->vcpu.arch.regs[VCPU_REGS_R15];
+#endif
+	save->rip = svm->vcpu.arch.regs[VCPU_REGS_RIP];
+
+	/* Sync some non-GPR registers before encrypting */
+	save->xcr0 = svm->vcpu.arch.xcr0;
+	save->pkru = svm->vcpu.arch.pkru;
+	save->xss  = svm->vcpu.arch.ia32_xss;
+
+	/*
+	 * SEV-ES will use a VMSA that is pointed to by the VMCB, not
+	 * the traditional VMSA that is part of the VMCB. Copy the
+	 * traditional VMSA as it has been built so far (in prep
+	 * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state.
+	 */
+	memcpy(svm->vmsa, save, sizeof(*save));
+
+	return 0;
+}
+
+static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_data_launch_update_vmsa *vmsa;
+	int i, ret;
+
+	if (!sev_es_guest(kvm))
+		return -ENOTTY;
+
+	vmsa = kzalloc(sizeof(*vmsa), GFP_KERNEL);
+	if (!vmsa)
+		return -ENOMEM;
+
+	for (i = 0; i < kvm->created_vcpus; i++) {
+		struct vcpu_svm *svm = to_svm(kvm->vcpus[i]);
+
+		/* Perform some pre-encryption checks against the VMSA */
+		ret = sev_es_sync_vmsa(svm);
+		if (ret)
+			goto e_free;
+
+		/*
+		 * The LAUNCH_UPDATE_VMSA command will perform in-place
+		 * encryption of the VMSA memory content (i.e it will write
+		 * the same memory region with the guest's key), so invalidate
+		 * it first.
+		 */
+		clflush_cache_range(svm->vmsa, PAGE_SIZE);
+
+		vmsa->handle = sev->handle;
+		vmsa->address = __sme_pa(svm->vmsa);
+		vmsa->len = PAGE_SIZE;
+		ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, vmsa,
+				    &argp->error);
+		if (ret)
+			goto e_free;
+
+		svm->vcpu.arch.guest_state_protected = true;
+	}
+
+e_free:
+	kfree(vmsa);
+	return ret;
+}
+
 static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	void __user *measure = (void __user *)(uintptr_t)argp->data;
@@ -932,7 +1044,7 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 	struct kvm_sev_cmd sev_cmd;
 	int r;
 
-	if (!svm_sev_enabled())
+	if (!svm_sev_enabled() || !sev)
 		return -ENOTTY;
 
 	if (!argp)
@@ -947,12 +1059,18 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 	case KVM_SEV_INIT:
 		r = sev_guest_init(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_ES_INIT:
+		r = sev_es_guest_init(kvm, &sev_cmd);
+		break;
 	case KVM_SEV_LAUNCH_START:
 		r = sev_launch_start(kvm, &sev_cmd);
 		break;
 	case KVM_SEV_LAUNCH_UPDATE_DATA:
 		r = sev_launch_update_data(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_LAUNCH_UPDATE_VMSA:
+		r = sev_launch_update_vmsa(kvm, &sev_cmd);
+		break;
 	case KVM_SEV_LAUNCH_MEASURE:
 		r = sev_launch_measure(kvm, &sev_cmd);
 		break;
@@ -1125,49 +1243,61 @@ void sev_vm_destroy(struct kvm *kvm)
 	sev_asid_free(sev->asid);
 }
 
-int __init sev_hardware_setup(void)
+void __init sev_hardware_setup(void)
 {
-	struct sev_user_data_status *status;
-	int rc;
+	unsigned int eax, ebx, ecx, edx;
+	bool sev_es_supported = false;
+	bool sev_supported = false;
+
+	/* Does the CPU support SEV? */
+	if (!boot_cpu_has(X86_FEATURE_SEV))
+		goto out;
+
+	/* Retrieve SEV CPUID information */
+	cpuid(0x8000001f, &eax, &ebx, &ecx, &edx);
+
+	/* Set encryption bit location for SEV-ES guests */
+	sev_enc_bit = ebx & 0x3f;
 
 	/* Maximum number of encrypted guests supported simultaneously */
-	max_sev_asid = cpuid_ecx(0x8000001F);
+	max_sev_asid = ecx;
 
 	if (!svm_sev_enabled())
-		return 1;
+		goto out;
 
 	/* Minimum ASID value that should be used for SEV guest */
-	min_sev_asid = cpuid_edx(0x8000001F);
+	min_sev_asid = edx;
 
 	/* Initialize SEV ASID bitmaps */
 	sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
 	if (!sev_asid_bitmap)
-		return 1;
+		goto out;
 
 	sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
 	if (!sev_reclaim_asid_bitmap)
-		return 1;
+		goto out;
 
-	status = kmalloc(sizeof(*status), GFP_KERNEL);
-	if (!status)
-		return 1;
+	pr_info("SEV supported: %u ASIDs\n", max_sev_asid - min_sev_asid + 1);
+	sev_supported = true;
 
-	/*
-	 * Check SEV platform status.
-	 *
-	 * PLATFORM_STATUS can be called in any state, if we failed to query
-	 * the PLATFORM status then either PSP firmware does not support SEV
-	 * feature or SEV firmware is dead.
-	 */
-	rc = sev_platform_status(status, NULL);
-	if (rc)
-		goto err;
+	/* SEV-ES support requested? */
+	if (!sev_es)
+		goto out;
 
-	pr_info("SEV supported\n");
+	/* Does the CPU support SEV-ES? */
+	if (!boot_cpu_has(X86_FEATURE_SEV_ES))
+		goto out;
 
-err:
-	kfree(status);
-	return rc;
+	/* Has the system been allocated ASIDs for SEV-ES? */
+	if (min_sev_asid == 1)
+		goto out;
+
+	pr_info("SEV-ES supported: %u ASIDs\n", min_sev_asid - 1);
+	sev_es_supported = true;
+
+out:
+	sev = sev_supported;
+	sev_es = sev_es_supported;
 }
 
 void sev_hardware_teardown(void)
@@ -1181,13 +1311,330 @@ void sev_hardware_teardown(void)
 	sev_flush_asids();
 }
 
+/*
+ * Pages used by hardware to hold guest encrypted state must be flushed before
+ * returning them to the system.
+ */
+static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va,
+				   unsigned long len)
+{
+	/*
+	 * If hardware enforced cache coherency for encrypted mappings of the
+	 * same physical page is supported, nothing to do.
+	 */
+	if (boot_cpu_has(X86_FEATURE_SME_COHERENT))
+		return;
+
+	/*
+	 * If the VM Page Flush MSR is supported, use it to flush the page
+	 * (using the page virtual address and the guest ASID).
+	 */
+	if (boot_cpu_has(X86_FEATURE_VM_PAGE_FLUSH)) {
+		struct kvm_sev_info *sev;
+		unsigned long va_start;
+		u64 start, stop;
+
+		/* Align start and stop to page boundaries. */
+		va_start = (unsigned long)va;
+		start = (u64)va_start & PAGE_MASK;
+		stop = PAGE_ALIGN((u64)va_start + len);
+
+		if (start < stop) {
+			sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
+
+			while (start < stop) {
+				wrmsrl(MSR_AMD64_VM_PAGE_FLUSH,
+				       start | sev->asid);
+
+				start += PAGE_SIZE;
+			}
+
+			return;
+		}
+
+		WARN(1, "Address overflow, using WBINVD\n");
+	}
+
+	/*
+	 * Hardware should always have one of the above features,
+	 * but if not, use WBINVD and issue a warning.
+	 */
+	WARN_ONCE(1, "Using WBINVD to flush guest memory\n");
+	wbinvd_on_all_cpus();
+}
+
+void sev_free_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm;
+
+	if (!sev_es_guest(vcpu->kvm))
+		return;
+
+	svm = to_svm(vcpu);
+
+	if (vcpu->arch.guest_state_protected)
+		sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE);
+	__free_page(virt_to_page(svm->vmsa));
+
+	if (svm->ghcb_sa_free)
+		kfree(svm->ghcb_sa);
+}
+
+static void dump_ghcb(struct vcpu_svm *svm)
+{
+	struct ghcb *ghcb = svm->ghcb;
+	unsigned int nbits;
+
+	/* Re-use the dump_invalid_vmcb module parameter */
+	if (!dump_invalid_vmcb) {
+		pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
+		return;
+	}
+
+	nbits = sizeof(ghcb->save.valid_bitmap) * 8;
+
+	pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa);
+	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code",
+	       ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb));
+	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1",
+	       ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb));
+	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2",
+	       ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb));
+	pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch",
+	       ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb));
+	pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap);
+}
+
+static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct ghcb *ghcb = svm->ghcb;
+
+	/*
+	 * The GHCB protocol so far allows for the following data
+	 * to be returned:
+	 *   GPRs RAX, RBX, RCX, RDX
+	 *
+	 * Copy their values to the GHCB if they are dirty.
+	 */
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RAX))
+		ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]);
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RBX))
+		ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]);
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RCX))
+		ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]);
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RDX))
+		ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]);
+}
+
+static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
+{
+	struct vmcb_control_area *control = &svm->vmcb->control;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct ghcb *ghcb = svm->ghcb;
+	u64 exit_code;
+
+	/*
+	 * The GHCB protocol so far allows for the following data
+	 * to be supplied:
+	 *   GPRs RAX, RBX, RCX, RDX
+	 *   XCR0
+	 *   CPL
+	 *
+	 * VMMCALL allows the guest to provide extra registers. KVM also
+	 * expects RSI for hypercalls, so include that, too.
+	 *
+	 * Copy their values to the appropriate location if supplied.
+	 */
+	memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));
+
+	vcpu->arch.regs[VCPU_REGS_RAX] = ghcb_get_rax_if_valid(ghcb);
+	vcpu->arch.regs[VCPU_REGS_RBX] = ghcb_get_rbx_if_valid(ghcb);
+	vcpu->arch.regs[VCPU_REGS_RCX] = ghcb_get_rcx_if_valid(ghcb);
+	vcpu->arch.regs[VCPU_REGS_RDX] = ghcb_get_rdx_if_valid(ghcb);
+	vcpu->arch.regs[VCPU_REGS_RSI] = ghcb_get_rsi_if_valid(ghcb);
+
+	svm->vmcb->save.cpl = ghcb_get_cpl_if_valid(ghcb);
+
+	if (ghcb_xcr0_is_valid(ghcb)) {
+		vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb);
+		kvm_update_cpuid_runtime(vcpu);
+	}
+
+	/* Copy the GHCB exit information into the VMCB fields */
+	exit_code = ghcb_get_sw_exit_code(ghcb);
+	control->exit_code = lower_32_bits(exit_code);
+	control->exit_code_hi = upper_32_bits(exit_code);
+	control->exit_info_1 = ghcb_get_sw_exit_info_1(ghcb);
+	control->exit_info_2 = ghcb_get_sw_exit_info_2(ghcb);
+
+	/* Clear the valid entries fields */
+	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
+}
+
+static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu;
+	struct ghcb *ghcb;
+	u64 exit_code = 0;
+
+	ghcb = svm->ghcb;
+
+	/* Only GHCB Usage code 0 is supported */
+	if (ghcb->ghcb_usage)
+		goto vmgexit_err;
+
+	/*
+	 * Retrieve the exit code now even though is may not be marked valid
+	 * as it could help with debugging.
+	 */
+	exit_code = ghcb_get_sw_exit_code(ghcb);
+
+	if (!ghcb_sw_exit_code_is_valid(ghcb) ||
+	    !ghcb_sw_exit_info_1_is_valid(ghcb) ||
+	    !ghcb_sw_exit_info_2_is_valid(ghcb))
+		goto vmgexit_err;
+
+	switch (ghcb_get_sw_exit_code(ghcb)) {
+	case SVM_EXIT_READ_DR7:
+		break;
+	case SVM_EXIT_WRITE_DR7:
+		if (!ghcb_rax_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
+	case SVM_EXIT_RDTSC:
+		break;
+	case SVM_EXIT_RDPMC:
+		if (!ghcb_rcx_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
+	case SVM_EXIT_CPUID:
+		if (!ghcb_rax_is_valid(ghcb) ||
+		    !ghcb_rcx_is_valid(ghcb))
+			goto vmgexit_err;
+		if (ghcb_get_rax(ghcb) == 0xd)
+			if (!ghcb_xcr0_is_valid(ghcb))
+				goto vmgexit_err;
+		break;
+	case SVM_EXIT_INVD:
+		break;
+	case SVM_EXIT_IOIO:
+		if (ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_STR_MASK) {
+			if (!ghcb_sw_scratch_is_valid(ghcb))
+				goto vmgexit_err;
+		} else {
+			if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK))
+				if (!ghcb_rax_is_valid(ghcb))
+					goto vmgexit_err;
+		}
+		break;
+	case SVM_EXIT_MSR:
+		if (!ghcb_rcx_is_valid(ghcb))
+			goto vmgexit_err;
+		if (ghcb_get_sw_exit_info_1(ghcb)) {
+			if (!ghcb_rax_is_valid(ghcb) ||
+			    !ghcb_rdx_is_valid(ghcb))
+				goto vmgexit_err;
+		}
+		break;
+	case SVM_EXIT_VMMCALL:
+		if (!ghcb_rax_is_valid(ghcb) ||
+		    !ghcb_cpl_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
+	case SVM_EXIT_RDTSCP:
+		break;
+	case SVM_EXIT_WBINVD:
+		break;
+	case SVM_EXIT_MONITOR:
+		if (!ghcb_rax_is_valid(ghcb) ||
+		    !ghcb_rcx_is_valid(ghcb) ||
+		    !ghcb_rdx_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
+	case SVM_EXIT_MWAIT:
+		if (!ghcb_rax_is_valid(ghcb) ||
+		    !ghcb_rcx_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
+	case SVM_VMGEXIT_MMIO_READ:
+	case SVM_VMGEXIT_MMIO_WRITE:
+		if (!ghcb_sw_scratch_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
+	case SVM_VMGEXIT_NMI_COMPLETE:
+	case SVM_VMGEXIT_AP_HLT_LOOP:
+	case SVM_VMGEXIT_AP_JUMP_TABLE:
+	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
+		break;
+	default:
+		goto vmgexit_err;
+	}
+
+	return 0;
+
+vmgexit_err:
+	vcpu = &svm->vcpu;
+
+	if (ghcb->ghcb_usage) {
+		vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n",
+			    ghcb->ghcb_usage);
+	} else {
+		vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n",
+			    exit_code);
+		dump_ghcb(svm);
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
+	vcpu->run->internal.ndata = 2;
+	vcpu->run->internal.data[0] = exit_code;
+	vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
+
+	return -EINVAL;
+}
+
+static void pre_sev_es_run(struct vcpu_svm *svm)
+{
+	if (!svm->ghcb)
+		return;
+
+	if (svm->ghcb_sa_free) {
+		/*
+		 * The scratch area lives outside the GHCB, so there is a
+		 * buffer that, depending on the operation performed, may
+		 * need to be synced, then freed.
+		 */
+		if (svm->ghcb_sa_sync) {
+			kvm_write_guest(svm->vcpu.kvm,
+					ghcb_get_sw_scratch(svm->ghcb),
+					svm->ghcb_sa, svm->ghcb_sa_len);
+			svm->ghcb_sa_sync = false;
+		}
+
+		kfree(svm->ghcb_sa);
+		svm->ghcb_sa = NULL;
+		svm->ghcb_sa_free = false;
+	}
+
+	trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->ghcb);
+
+	sev_es_sync_to_ghcb(svm);
+
+	kvm_vcpu_unmap(&svm->vcpu, &svm->ghcb_map, true);
+	svm->ghcb = NULL;
+}
+
 void pre_sev_run(struct vcpu_svm *svm, int cpu)
 {
 	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 	int asid = sev_get_asid(svm->vcpu.kvm);
 
+	/* Perform any SEV-ES pre-run actions */
+	pre_sev_es_run(svm);
+
 	/* Assign the asid allocated with this SEV guest */
-	svm->vmcb->control.asid = asid;
+	svm->asid = asid;
 
 	/*
 	 * Flush guest TLB:
@@ -1203,3 +1650,415 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu)
 	svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID;
 	vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
 }
+
+#define GHCB_SCRATCH_AREA_LIMIT		(16ULL * PAGE_SIZE)
+static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
+{
+	struct vmcb_control_area *control = &svm->vmcb->control;
+	struct ghcb *ghcb = svm->ghcb;
+	u64 ghcb_scratch_beg, ghcb_scratch_end;
+	u64 scratch_gpa_beg, scratch_gpa_end;
+	void *scratch_va;
+
+	scratch_gpa_beg = ghcb_get_sw_scratch(ghcb);
+	if (!scratch_gpa_beg) {
+		pr_err("vmgexit: scratch gpa not provided\n");
+		return false;
+	}
+
+	scratch_gpa_end = scratch_gpa_beg + len;
+	if (scratch_gpa_end < scratch_gpa_beg) {
+		pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n",
+		       len, scratch_gpa_beg);
+		return false;
+	}
+
+	if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) {
+		/* Scratch area begins within GHCB */
+		ghcb_scratch_beg = control->ghcb_gpa +
+				   offsetof(struct ghcb, shared_buffer);
+		ghcb_scratch_end = control->ghcb_gpa +
+				   offsetof(struct ghcb, reserved_1);
+
+		/*
+		 * If the scratch area begins within the GHCB, it must be
+		 * completely contained in the GHCB shared buffer area.
+		 */
+		if (scratch_gpa_beg < ghcb_scratch_beg ||
+		    scratch_gpa_end > ghcb_scratch_end) {
+			pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n",
+			       scratch_gpa_beg, scratch_gpa_end);
+			return false;
+		}
+
+		scratch_va = (void *)svm->ghcb;
+		scratch_va += (scratch_gpa_beg - control->ghcb_gpa);
+	} else {
+		/*
+		 * The guest memory must be read into a kernel buffer, so
+		 * limit the size
+		 */
+		if (len > GHCB_SCRATCH_AREA_LIMIT) {
+			pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n",
+			       len, GHCB_SCRATCH_AREA_LIMIT);
+			return false;
+		}
+		scratch_va = kzalloc(len, GFP_KERNEL);
+		if (!scratch_va)
+			return false;
+
+		if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) {
+			/* Unable to copy scratch area from guest */
+			pr_err("vmgexit: kvm_read_guest for scratch area failed\n");
+
+			kfree(scratch_va);
+			return false;
+		}
+
+		/*
+		 * The scratch area is outside the GHCB. The operation will
+		 * dictate whether the buffer needs to be synced before running
+		 * the vCPU next time (i.e. a read was requested so the data
+		 * must be written back to the guest memory).
+		 */
+		svm->ghcb_sa_sync = sync;
+		svm->ghcb_sa_free = true;
+	}
+
+	svm->ghcb_sa = scratch_va;
+	svm->ghcb_sa_len = len;
+
+	return true;
+}
+
+static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask,
+			      unsigned int pos)
+{
+	svm->vmcb->control.ghcb_gpa &= ~(mask << pos);
+	svm->vmcb->control.ghcb_gpa |= (value & mask) << pos;
+}
+
+static u64 get_ghcb_msr_bits(struct vcpu_svm *svm, u64 mask, unsigned int pos)
+{
+	return (svm->vmcb->control.ghcb_gpa >> pos) & mask;
+}
+
+static void set_ghcb_msr(struct vcpu_svm *svm, u64 value)
+{
+	svm->vmcb->control.ghcb_gpa = value;
+}
+
+static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
+{
+	struct vmcb_control_area *control = &svm->vmcb->control;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	u64 ghcb_info;
+	int ret = 1;
+
+	ghcb_info = control->ghcb_gpa & GHCB_MSR_INFO_MASK;
+
+	trace_kvm_vmgexit_msr_protocol_enter(svm->vcpu.vcpu_id,
+					     control->ghcb_gpa);
+
+	switch (ghcb_info) {
+	case GHCB_MSR_SEV_INFO_REQ:
+		set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX,
+						    GHCB_VERSION_MIN,
+						    sev_enc_bit));
+		break;
+	case GHCB_MSR_CPUID_REQ: {
+		u64 cpuid_fn, cpuid_reg, cpuid_value;
+
+		cpuid_fn = get_ghcb_msr_bits(svm,
+					     GHCB_MSR_CPUID_FUNC_MASK,
+					     GHCB_MSR_CPUID_FUNC_POS);
+
+		/* Initialize the registers needed by the CPUID intercept */
+		vcpu->arch.regs[VCPU_REGS_RAX] = cpuid_fn;
+		vcpu->arch.regs[VCPU_REGS_RCX] = 0;
+
+		ret = svm_invoke_exit_handler(svm, SVM_EXIT_CPUID);
+		if (!ret) {
+			ret = -EINVAL;
+			break;
+		}
+
+		cpuid_reg = get_ghcb_msr_bits(svm,
+					      GHCB_MSR_CPUID_REG_MASK,
+					      GHCB_MSR_CPUID_REG_POS);
+		if (cpuid_reg == 0)
+			cpuid_value = vcpu->arch.regs[VCPU_REGS_RAX];
+		else if (cpuid_reg == 1)
+			cpuid_value = vcpu->arch.regs[VCPU_REGS_RBX];
+		else if (cpuid_reg == 2)
+			cpuid_value = vcpu->arch.regs[VCPU_REGS_RCX];
+		else
+			cpuid_value = vcpu->arch.regs[VCPU_REGS_RDX];
+
+		set_ghcb_msr_bits(svm, cpuid_value,
+				  GHCB_MSR_CPUID_VALUE_MASK,
+				  GHCB_MSR_CPUID_VALUE_POS);
+
+		set_ghcb_msr_bits(svm, GHCB_MSR_CPUID_RESP,
+				  GHCB_MSR_INFO_MASK,
+				  GHCB_MSR_INFO_POS);
+		break;
+	}
+	case GHCB_MSR_TERM_REQ: {
+		u64 reason_set, reason_code;
+
+		reason_set = get_ghcb_msr_bits(svm,
+					       GHCB_MSR_TERM_REASON_SET_MASK,
+					       GHCB_MSR_TERM_REASON_SET_POS);
+		reason_code = get_ghcb_msr_bits(svm,
+						GHCB_MSR_TERM_REASON_MASK,
+						GHCB_MSR_TERM_REASON_POS);
+		pr_info("SEV-ES guest requested termination: %#llx:%#llx\n",
+			reason_set, reason_code);
+		fallthrough;
+	}
+	default:
+		ret = -EINVAL;
+	}
+
+	trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id,
+					    control->ghcb_gpa, ret);
+
+	return ret;
+}
+
+int sev_handle_vmgexit(struct vcpu_svm *svm)
+{
+	struct vmcb_control_area *control = &svm->vmcb->control;
+	u64 ghcb_gpa, exit_code;
+	struct ghcb *ghcb;
+	int ret;
+
+	/* Validate the GHCB */
+	ghcb_gpa = control->ghcb_gpa;
+	if (ghcb_gpa & GHCB_MSR_INFO_MASK)
+		return sev_handle_vmgexit_msr_protocol(svm);
+
+	if (!ghcb_gpa) {
+		vcpu_unimpl(&svm->vcpu, "vmgexit: GHCB gpa is not set\n");
+		return -EINVAL;
+	}
+
+	if (kvm_vcpu_map(&svm->vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->ghcb_map)) {
+		/* Unable to map GHCB from guest */
+		vcpu_unimpl(&svm->vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n",
+			    ghcb_gpa);
+		return -EINVAL;
+	}
+
+	svm->ghcb = svm->ghcb_map.hva;
+	ghcb = svm->ghcb_map.hva;
+
+	trace_kvm_vmgexit_enter(svm->vcpu.vcpu_id, ghcb);
+
+	exit_code = ghcb_get_sw_exit_code(ghcb);
+
+	ret = sev_es_validate_vmgexit(svm);
+	if (ret)
+		return ret;
+
+	sev_es_sync_from_ghcb(svm);
+	ghcb_set_sw_exit_info_1(ghcb, 0);
+	ghcb_set_sw_exit_info_2(ghcb, 0);
+
+	ret = -EINVAL;
+	switch (exit_code) {
+	case SVM_VMGEXIT_MMIO_READ:
+		if (!setup_vmgexit_scratch(svm, true, control->exit_info_2))
+			break;
+
+		ret = kvm_sev_es_mmio_read(&svm->vcpu,
+					   control->exit_info_1,
+					   control->exit_info_2,
+					   svm->ghcb_sa);
+		break;
+	case SVM_VMGEXIT_MMIO_WRITE:
+		if (!setup_vmgexit_scratch(svm, false, control->exit_info_2))
+			break;
+
+		ret = kvm_sev_es_mmio_write(&svm->vcpu,
+					    control->exit_info_1,
+					    control->exit_info_2,
+					    svm->ghcb_sa);
+		break;
+	case SVM_VMGEXIT_NMI_COMPLETE:
+		ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET);
+		break;
+	case SVM_VMGEXIT_AP_HLT_LOOP:
+		ret = kvm_emulate_ap_reset_hold(&svm->vcpu);
+		break;
+	case SVM_VMGEXIT_AP_JUMP_TABLE: {
+		struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
+
+		switch (control->exit_info_1) {
+		case 0:
+			/* Set AP jump table address */
+			sev->ap_jump_table = control->exit_info_2;
+			break;
+		case 1:
+			/* Get AP jump table address */
+			ghcb_set_sw_exit_info_2(ghcb, sev->ap_jump_table);
+			break;
+		default:
+			pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n",
+			       control->exit_info_1);
+			ghcb_set_sw_exit_info_1(ghcb, 1);
+			ghcb_set_sw_exit_info_2(ghcb,
+						X86_TRAP_UD |
+						SVM_EVTINJ_TYPE_EXEPT |
+						SVM_EVTINJ_VALID);
+		}
+
+		ret = 1;
+		break;
+	}
+	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
+		vcpu_unimpl(&svm->vcpu,
+			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
+			    control->exit_info_1, control->exit_info_2);
+		break;
+	default:
+		ret = svm_invoke_exit_handler(svm, exit_code);
+	}
+
+	return ret;
+}
+
+int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
+{
+	if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2))
+		return -EINVAL;
+
+	return kvm_sev_es_string_io(&svm->vcpu, size, port,
+				    svm->ghcb_sa, svm->ghcb_sa_len, in);
+}
+
+void sev_es_init_vmcb(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+
+	svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE;
+	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
+
+	/*
+	 * An SEV-ES guest requires a VMSA area that is a separate from the
+	 * VMCB page. Do not include the encryption mask on the VMSA physical
+	 * address since hardware will access it using the guest key.
+	 */
+	svm->vmcb->control.vmsa_pa = __pa(svm->vmsa);
+
+	/* Can't intercept CR register access, HV can't modify CR registers */
+	svm_clr_intercept(svm, INTERCEPT_CR0_READ);
+	svm_clr_intercept(svm, INTERCEPT_CR4_READ);
+	svm_clr_intercept(svm, INTERCEPT_CR8_READ);
+	svm_clr_intercept(svm, INTERCEPT_CR0_WRITE);
+	svm_clr_intercept(svm, INTERCEPT_CR4_WRITE);
+	svm_clr_intercept(svm, INTERCEPT_CR8_WRITE);
+
+	svm_clr_intercept(svm, INTERCEPT_SELECTIVE_CR0);
+
+	/* Track EFER/CR register changes */
+	svm_set_intercept(svm, TRAP_EFER_WRITE);
+	svm_set_intercept(svm, TRAP_CR0_WRITE);
+	svm_set_intercept(svm, TRAP_CR4_WRITE);
+	svm_set_intercept(svm, TRAP_CR8_WRITE);
+
+	/* No support for enable_vmware_backdoor */
+	clr_exception_intercept(svm, GP_VECTOR);
+
+	/* Can't intercept XSETBV, HV can't modify XCR0 directly */
+	svm_clr_intercept(svm, INTERCEPT_XSETBV);
+
+	/* Clear intercepts on selected MSRs */
+	set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
+}
+
+void sev_es_create_vcpu(struct vcpu_svm *svm)
+{
+	/*
+	 * Set the GHCB MSR value as per the GHCB specification when creating
+	 * a vCPU for an SEV-ES guest.
+	 */
+	set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX,
+					    GHCB_VERSION_MIN,
+					    sev_enc_bit));
+}
+
+void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu)
+{
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+	struct vmcb_save_area *hostsa;
+	unsigned int i;
+
+	/*
+	 * As an SEV-ES guest, hardware will restore the host state on VMEXIT,
+	 * of which one step is to perform a VMLOAD. Since hardware does not
+	 * perform a VMSAVE on VMRUN, the host savearea must be updated.
+	 */
+	asm volatile(__ex("vmsave %0") : : "a" (__sme_page_pa(sd->save_area)) : "memory");
+
+	/*
+	 * Certain MSRs are restored on VMEXIT, only save ones that aren't
+	 * restored.
+	 */
+	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) {
+		if (host_save_user_msrs[i].sev_es_restored)
+			continue;
+
+		rdmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]);
+	}
+
+	/* XCR0 is restored on VMEXIT, save the current host value */
+	hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400);
+	hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+
+	/* PKRU is restored on VMEXIT, save the curent host value */
+	hostsa->pkru = read_pkru();
+
+	/* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */
+	hostsa->xss = host_xss;
+}
+
+void sev_es_vcpu_put(struct vcpu_svm *svm)
+{
+	unsigned int i;
+
+	/*
+	 * Certain MSRs are restored on VMEXIT and were saved with vmsave in
+	 * sev_es_vcpu_load() above. Only restore ones that weren't.
+	 */
+	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) {
+		if (host_save_user_msrs[i].sev_es_restored)
+			continue;
+
+		wrmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]);
+	}
+}
+
+void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	/* First SIPI: Use the values as initially set by the VMM */
+	if (!svm->received_first_sipi) {
+		svm->received_first_sipi = true;
+		return;
+	}
+
+	/*
+	 * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where
+	 * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a
+	 * non-zero value.
+	 */
+	ghcb_set_sw_exit_info_2(svm->ghcb, 1);
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index da7eb4aaf44f..7ef171790d02 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -33,9 +33,9 @@
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
 #include <asm/irq_remapping.h>
-#include <asm/mce.h>
 #include <asm/spec-ctrl.h>
 #include <asm/cpu_device_id.h>
+#include <asm/traps.h>
 
 #include <asm/virtext.h>
 #include "trace.h"
@@ -90,7 +90,7 @@ static DEFINE_PER_CPU(u64, current_tsc_ratio);
 
 static const struct svm_direct_access_msrs {
 	u32 index;   /* Index of the MSR */
-	bool always; /* True if intercept is always on */
+	bool always; /* True if intercept is initially cleared */
 } direct_access_msrs[MAX_DIRECT_ACCESS_MSRS] = {
 	{ .index = MSR_STAR,				.always = true  },
 	{ .index = MSR_IA32_SYSENTER_CS,		.always = true  },
@@ -108,6 +108,9 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTTOIP,		.always = false },
+	{ .index = MSR_EFER,				.always = false },
+	{ .index = MSR_IA32_CR_PAT,			.always = false },
+	{ .index = MSR_AMD64_SEV_ES_GHCB,		.always = true  },
 	{ .index = MSR_INVALID,				.always = false },
 };
 
@@ -187,10 +190,14 @@ static int vgif = true;
 module_param(vgif, int, 0444);
 
 /* enable/disable SEV support */
-static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT);
+int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT);
 module_param(sev, int, 0444);
 
-static bool __read_mostly dump_invalid_vmcb = 0;
+/* enable/disable SEV-ES support */
+int sev_es = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT);
+module_param(sev_es, int, 0444);
+
+bool __read_mostly dump_invalid_vmcb;
 module_param(dump_invalid_vmcb, bool, 0644);
 
 static u8 rsm_ins_bytes[] = "\x0f\xaa";
@@ -336,6 +343,13 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	/*
+	 * SEV-ES does not expose the next RIP. The RIP update is controlled by
+	 * the type of exit and the #VC handler in the guest.
+	 */
+	if (sev_es_guest(vcpu->kvm))
+		goto done;
+
 	if (nrips && svm->vmcb->control.next_rip != 0) {
 		WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS));
 		svm->next_rip = svm->vmcb->control.next_rip;
@@ -347,6 +361,8 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	} else {
 		kvm_rip_write(vcpu, svm->next_rip);
 	}
+
+done:
 	svm_set_interrupt_shadow(vcpu, 0);
 
 	return 1;
@@ -484,7 +500,7 @@ static int svm_hardware_enable(void)
 
 	wrmsrl(MSR_EFER, efer | EFER_SVME);
 
-	wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT);
+	wrmsrl(MSR_VM_HSAVE_PA, __sme_page_pa(sd->save_area));
 
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
 		wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
@@ -552,6 +568,7 @@ static int svm_cpu_init(int cpu)
 	sd->save_area = alloc_page(GFP_KERNEL);
 	if (!sd->save_area)
 		goto free_cpu_data;
+	clear_page(page_address(sd->save_area));
 
 	if (svm_sev_enabled()) {
 		sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1,
@@ -662,8 +679,8 @@ static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm,
 	msrpm[offset] = tmp;
 }
 
-static void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr,
-				 int read, int write)
+void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr,
+			  int read, int write)
 {
 	set_shadow_msr_intercept(vcpu, msr, read, write);
 	set_msr_interception_bitmap(vcpu, msrpm, msr, read, write);
@@ -959,15 +976,11 @@ static __init int svm_hardware_setup(void)
 		kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE);
 	}
 
-	if (sev) {
-		if (boot_cpu_has(X86_FEATURE_SEV) &&
-		    IS_ENABLED(CONFIG_KVM_AMD_SEV)) {
-			r = sev_hardware_setup();
-			if (r)
-				sev = false;
-		} else {
-			sev = false;
-		}
+	if (IS_ENABLED(CONFIG_KVM_AMD_SEV) && sev) {
+		sev_hardware_setup();
+	} else {
+		sev = false;
+		sev_es = false;
 	}
 
 	svm_adjust_mmio_mask();
@@ -1215,6 +1228,7 @@ static void init_vmcb(struct vcpu_svm *svm)
 		save->cr4 = 0;
 	}
 	svm->asid_generation = 0;
+	svm->asid = 0;
 
 	svm->nested.vmcb12_gpa = 0;
 	svm->vcpu.arch.hflags = 0;
@@ -1252,6 +1266,11 @@ static void init_vmcb(struct vcpu_svm *svm)
 	if (sev_guest(svm->vcpu.kvm)) {
 		svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE;
 		clr_exception_intercept(svm, UD_VECTOR);
+
+		if (sev_es_guest(svm->vcpu.kvm)) {
+			/* Perform SEV-ES specific VMCB updates */
+			sev_es_init_vmcb(svm);
+		}
 	}
 
 	vmcb_mark_all_dirty(svm->vmcb);
@@ -1288,6 +1307,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm;
 	struct page *vmcb_page;
+	struct page *vmsa_page = NULL;
 	int err;
 
 	BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0);
@@ -1298,9 +1318,27 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 	if (!vmcb_page)
 		goto out;
 
+	if (sev_es_guest(svm->vcpu.kvm)) {
+		/*
+		 * SEV-ES guests require a separate VMSA page used to contain
+		 * the encrypted register state of the guest.
+		 */
+		vmsa_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+		if (!vmsa_page)
+			goto error_free_vmcb_page;
+
+		/*
+		 * SEV-ES guests maintain an encrypted version of their FPU
+		 * state which is restored and saved on VMRUN and VMEXIT.
+		 * Free the fpu structure to prevent KVM from attempting to
+		 * access the FPU state.
+		 */
+		kvm_free_guest_fpu(vcpu);
+	}
+
 	err = avic_init_vcpu(svm);
 	if (err)
-		goto error_free_vmcb_page;
+		goto error_free_vmsa_page;
 
 	/* We initialize this flag to true to make sure that the is_running
 	 * bit would be set the first time the vcpu is loaded.
@@ -1311,21 +1349,32 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 	svm->msrpm = svm_vcpu_alloc_msrpm();
 	if (!svm->msrpm) {
 		err = -ENOMEM;
-		goto error_free_vmcb_page;
+		goto error_free_vmsa_page;
 	}
 
 	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
 
 	svm->vmcb = page_address(vmcb_page);
 	svm->vmcb_pa = __sme_set(page_to_pfn(vmcb_page) << PAGE_SHIFT);
+
+	if (vmsa_page)
+		svm->vmsa = page_address(vmsa_page);
+
 	svm->asid_generation = 0;
 	init_vmcb(svm);
 
 	svm_init_osvw(vcpu);
 	vcpu->arch.microcode_version = 0x01000065;
 
+	if (sev_es_guest(svm->vcpu.kvm))
+		/* Perform SEV-ES specific VMCB creation updates */
+		sev_es_create_vcpu(svm);
+
 	return 0;
 
+error_free_vmsa_page:
+	if (vmsa_page)
+		__free_page(vmsa_page);
 error_free_vmcb_page:
 	__free_page(vmcb_page);
 out:
@@ -1353,6 +1402,8 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 
 	svm_free_nested(svm);
 
+	sev_free_vcpu(vcpu);
+
 	__free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT));
 	__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
 }
@@ -1368,15 +1419,20 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		vmcb_mark_all_dirty(svm->vmcb);
 	}
 
+	if (sev_es_guest(svm->vcpu.kvm)) {
+		sev_es_vcpu_load(svm, cpu);
+	} else {
 #ifdef CONFIG_X86_64
-	rdmsrl(MSR_GS_BASE, to_svm(vcpu)->host.gs_base);
+		rdmsrl(MSR_GS_BASE, to_svm(vcpu)->host.gs_base);
 #endif
-	savesegment(fs, svm->host.fs);
-	savesegment(gs, svm->host.gs);
-	svm->host.ldt = kvm_read_ldt();
+		savesegment(fs, svm->host.fs);
+		savesegment(gs, svm->host.gs);
+		svm->host.ldt = kvm_read_ldt();
 
-	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
-		rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
+		for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
+			rdmsrl(host_save_user_msrs[i].index,
+			       svm->host_user_msrs[i]);
+	}
 
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
 		u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio;
@@ -1404,18 +1460,24 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 	avic_vcpu_put(vcpu);
 
 	++vcpu->stat.host_state_reload;
-	kvm_load_ldt(svm->host.ldt);
+	if (sev_es_guest(svm->vcpu.kvm)) {
+		sev_es_vcpu_put(svm);
+	} else {
+		kvm_load_ldt(svm->host.ldt);
 #ifdef CONFIG_X86_64
-	loadsegment(fs, svm->host.fs);
-	wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gsbase);
-	load_gs_index(svm->host.gs);
+		loadsegment(fs, svm->host.fs);
+		wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gsbase);
+		load_gs_index(svm->host.gs);
 #else
 #ifdef CONFIG_X86_32_LAZY_GS
-	loadsegment(gs, svm->host.gs);
+		loadsegment(gs, svm->host.gs);
 #endif
 #endif
-	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
-		wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
+
+		for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
+			wrmsrl(host_save_user_msrs[i].index,
+			       svm->host_user_msrs[i]);
+	}
 }
 
 static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
@@ -1633,9 +1695,18 @@ static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 
 static void update_cr0_intercept(struct vcpu_svm *svm)
 {
-	ulong gcr0 = svm->vcpu.arch.cr0;
-	u64 *hcr0 = &svm->vmcb->save.cr0;
+	ulong gcr0;
+	u64 *hcr0;
 
+	/*
+	 * SEV-ES guests must always keep the CR intercepts cleared. CR
+	 * tracking is done using the CR write traps.
+	 */
+	if (sev_es_guest(svm->vcpu.kvm))
+		return;
+
+	gcr0 = svm->vcpu.arch.cr0;
+	hcr0 = &svm->vmcb->save.cr0;
 	*hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK)
 		| (gcr0 & SVM_CR0_SELECTIVE_MASK);
 
@@ -1655,7 +1726,7 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 #ifdef CONFIG_X86_64
-	if (vcpu->arch.efer & EFER_LME) {
+	if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) {
 		if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
 			vcpu->arch.efer |= EFER_LMA;
 			svm->vmcb->save.efer |= EFER_LMA | EFER_LME;
@@ -1684,13 +1755,15 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	update_cr0_intercept(svm);
 }
 
-int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+static bool svm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE;
-	unsigned long old_cr4 = to_svm(vcpu)->vmcb->save.cr4;
+	return true;
+}
 
-	if (cr4 & X86_CR4_VMXE)
-		return 1;
+void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+	unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE;
+	unsigned long old_cr4 = vcpu->arch.cr4;
 
 	if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE))
 		svm_flush_tlb(vcpu);
@@ -1701,7 +1774,9 @@ int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	cr4 |= host_cr4_mce;
 	to_svm(vcpu)->vmcb->save.cr4 = cr4;
 	vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR);
-	return 0;
+
+	if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
+		kvm_update_cpuid_runtime(vcpu);
 }
 
 static void svm_set_segment(struct kvm_vcpu *vcpu,
@@ -1753,18 +1828,20 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
 		++sd->asid_generation;
 		sd->next_asid = sd->min_asid;
 		svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID;
+		vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
 	}
 
 	svm->asid_generation = sd->asid_generation;
-	svm->vmcb->control.asid = sd->next_asid++;
-
-	vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
+	svm->asid = sd->next_asid++;
 }
 
 static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value)
 {
 	struct vmcb *vmcb = svm->vmcb;
 
+	if (svm->vcpu.arch.guest_state_protected)
+		return;
+
 	if (unlikely(value != vmcb->save.dr6)) {
 		vmcb->save.dr6 = value;
 		vmcb_mark_dirty(vmcb, VMCB_DR);
@@ -1775,6 +1852,9 @@ static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (vcpu->arch.guest_state_protected)
+		return;
+
 	get_debugreg(vcpu->arch.db[0], 0);
 	get_debugreg(vcpu->arch.db[1], 1);
 	get_debugreg(vcpu->arch.db[2], 2);
@@ -1793,6 +1873,9 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (vcpu->arch.guest_state_protected)
+		return;
+
 	svm->vmcb->save.dr7 = value;
 	vmcb_mark_dirty(svm->vmcb, VMCB_DR);
 }
@@ -1931,25 +2014,6 @@ static bool is_erratum_383(void)
 	return true;
 }
 
-/*
- * Trigger machine check on the host. We assume all the MSRs are already set up
- * by the CPU and that we still run on the same CPU as the MCE occurred on.
- * We pass a fake environment to the machine check handler because we want
- * the guest to be always treated like user space, no matter what context
- * it used internally.
- */
-static void kvm_machine_check(void)
-{
-#if defined(CONFIG_X86_MCE)
-	struct pt_regs regs = {
-		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
-		.flags = X86_EFLAGS_IF,
-	};
-
-	do_machine_check(&regs);
-#endif
-}
-
 static void svm_handle_mce(struct vcpu_svm *svm)
 {
 	if (is_erratum_383()) {
@@ -1981,6 +2045,13 @@ static int shutdown_interception(struct vcpu_svm *svm)
 	struct kvm_run *kvm_run = svm->vcpu.run;
 
 	/*
+	 * The VM save area has already been encrypted so it
+	 * cannot be reinitialized - just terminate.
+	 */
+	if (sev_es_guest(svm->vcpu.kvm))
+		return -EINVAL;
+
+	/*
 	 * VMCB is undefined after a SHUTDOWN intercept
 	 * so reinitialize it.
 	 */
@@ -2001,11 +2072,16 @@ static int io_interception(struct vcpu_svm *svm)
 	++svm->vcpu.stat.io_exits;
 	string = (io_info & SVM_IOIO_STR_MASK) != 0;
 	in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
-	if (string)
-		return kvm_emulate_instruction(vcpu, 0);
-
 	port = io_info >> 16;
 	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
+
+	if (string) {
+		if (sev_es_guest(vcpu->kvm))
+			return sev_es_string_io(svm, size, port, in);
+		else
+			return kvm_emulate_instruction(vcpu, 0);
+	}
+
 	svm->next_rip = svm->vmcb->control.exit_info_2;
 
 	return kvm_fast_pio(&svm->vcpu, size, port, in);
@@ -2269,9 +2345,11 @@ static int cpuid_interception(struct vcpu_svm *svm)
 static int iret_interception(struct vcpu_svm *svm)
 {
 	++svm->vcpu.stat.nmi_window_exits;
-	svm_clr_intercept(svm, INTERCEPT_IRET);
 	svm->vcpu.arch.hflags |= HF_IRET_MASK;
-	svm->nmi_iret_rip = kvm_rip_read(&svm->vcpu);
+	if (!sev_es_guest(svm->vcpu.kvm)) {
+		svm_clr_intercept(svm, INTERCEPT_IRET);
+		svm->nmi_iret_rip = kvm_rip_read(&svm->vcpu);
+	}
 	kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 	return 1;
 }
@@ -2408,6 +2486,41 @@ static int cr_interception(struct vcpu_svm *svm)
 	return kvm_complete_insn_gp(&svm->vcpu, err);
 }
 
+static int cr_trap(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	unsigned long old_value, new_value;
+	unsigned int cr;
+	int ret = 0;
+
+	new_value = (unsigned long)svm->vmcb->control.exit_info_1;
+
+	cr = svm->vmcb->control.exit_code - SVM_EXIT_CR0_WRITE_TRAP;
+	switch (cr) {
+	case 0:
+		old_value = kvm_read_cr0(vcpu);
+		svm_set_cr0(vcpu, new_value);
+
+		kvm_post_set_cr0(vcpu, old_value, new_value);
+		break;
+	case 4:
+		old_value = kvm_read_cr4(vcpu);
+		svm_set_cr4(vcpu, new_value);
+
+		kvm_post_set_cr4(vcpu, old_value, new_value);
+		break;
+	case 8:
+		ret = kvm_set_cr8(&svm->vcpu, new_value);
+		break;
+	default:
+		WARN(1, "unhandled CR%d write trap", cr);
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	return kvm_complete_insn_gp(vcpu, ret);
+}
+
 static int dr_interception(struct vcpu_svm *svm)
 {
 	int reg, dr;
@@ -2461,6 +2574,25 @@ static int cr8_write_interception(struct vcpu_svm *svm)
 	return 0;
 }
 
+static int efer_trap(struct vcpu_svm *svm)
+{
+	struct msr_data msr_info;
+	int ret;
+
+	/*
+	 * Clear the EFER_SVME bit from EFER. The SVM code always sets this
+	 * bit in svm_set_efer(), but __kvm_valid_efer() checks it against
+	 * whether the guest has X86_FEATURE_SVM - this avoids a failure if
+	 * the guest doesn't have X86_FEATURE_SVM.
+	 */
+	msr_info.host_initiated = false;
+	msr_info.index = MSR_EFER;
+	msr_info.data = svm->vmcb->control.exit_info_1 & ~EFER_SVME;
+	ret = kvm_set_msr_common(&svm->vcpu, &msr_info);
+
+	return kvm_complete_insn_gp(&svm->vcpu, ret);
+}
+
 static int svm_get_msr_feature(struct kvm_msr_entry *msr)
 {
 	msr->data = 0;
@@ -2543,10 +2675,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD))
+		    !guest_has_spec_ctrl_msr(vcpu))
 			return 1;
 
 		msr_info->data = svm->spec_ctrl;
@@ -2584,6 +2713,20 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	return 0;
 }
 
+static int svm_complete_emulated_msr(struct kvm_vcpu *vcpu, int err)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	if (!sev_es_guest(svm->vcpu.kvm) || !err)
+		return kvm_complete_insn_gp(&svm->vcpu, err);
+
+	ghcb_set_sw_exit_info_1(svm->ghcb, 1);
+	ghcb_set_sw_exit_info_2(svm->ghcb,
+				X86_TRAP_GP |
+				SVM_EVTINJ_TYPE_EXEPT |
+				SVM_EVTINJ_VALID);
+	return 1;
+}
+
 static int rdmsr_interception(struct vcpu_svm *svm)
 {
 	return kvm_emulate_rdmsr(&svm->vcpu);
@@ -2630,10 +2773,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD))
+		    !guest_has_spec_ctrl_msr(vcpu))
 			return 1;
 
 		if (kvm_spec_ctrl_test_value(data))
@@ -2658,12 +2798,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		break;
 	case MSR_IA32_PRED_CMD:
 		if (!msr->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB))
+		    !guest_has_pred_cmd_msr(vcpu))
 			return 1;
 
 		if (data & ~PRED_CMD_IBPB)
 			return 1;
-		if (!boot_cpu_has(X86_FEATURE_AMD_IBPB))
+		if (!boot_cpu_has(X86_FEATURE_IBPB))
 			return 1;
 		if (!data)
 			break;
@@ -2805,7 +2945,14 @@ static int interrupt_window_interception(struct vcpu_svm *svm)
 static int pause_interception(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
-	bool in_kernel = (svm_get_cpl(vcpu) == 0);
+	bool in_kernel;
+
+	/*
+	 * CPL is not made available for an SEV-ES guest, therefore
+	 * vcpu->arch.preempted_in_kernel can never be true.  Just
+	 * set in_kernel to false as well.
+	 */
+	in_kernel = !sev_es_guest(svm->vcpu.kvm) && svm_get_cpl(vcpu) == 0;
 
 	if (!kvm_pause_in_guest(vcpu->kvm))
 		grow_ple_window(vcpu);
@@ -2920,11 +3067,16 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_MWAIT]			= mwait_interception,
 	[SVM_EXIT_XSETBV]			= xsetbv_interception,
 	[SVM_EXIT_RDPRU]			= rdpru_interception,
+	[SVM_EXIT_EFER_WRITE_TRAP]		= efer_trap,
+	[SVM_EXIT_CR0_WRITE_TRAP]		= cr_trap,
+	[SVM_EXIT_CR4_WRITE_TRAP]		= cr_trap,
+	[SVM_EXIT_CR8_WRITE_TRAP]		= cr_trap,
 	[SVM_EXIT_INVPCID]                      = invpcid_interception,
 	[SVM_EXIT_NPF]				= npf_interception,
 	[SVM_EXIT_RSM]                          = rsm_interception,
 	[SVM_EXIT_AVIC_INCOMPLETE_IPI]		= avic_incomplete_ipi_interception,
 	[SVM_EXIT_AVIC_UNACCELERATED_ACCESS]	= avic_unaccelerated_access_interception,
+	[SVM_EXIT_VMGEXIT]			= sev_handle_vmgexit,
 };
 
 static void dump_vmcb(struct kvm_vcpu *vcpu)
@@ -2966,6 +3118,7 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	pr_err("%-20s%lld\n", "nested_ctl:", control->nested_ctl);
 	pr_err("%-20s%016llx\n", "nested_cr3:", control->nested_cr3);
 	pr_err("%-20s%016llx\n", "avic_vapic_bar:", control->avic_vapic_bar);
+	pr_err("%-20s%016llx\n", "ghcb:", control->ghcb_gpa);
 	pr_err("%-20s%08x\n", "event_inj:", control->event_inj);
 	pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err);
 	pr_err("%-20s%lld\n", "virt_ext:", control->virt_ext);
@@ -2973,6 +3126,7 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	pr_err("%-20s%016llx\n", "avic_backing_page:", control->avic_backing_page);
 	pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id);
 	pr_err("%-20s%016llx\n", "avic_physical_id:", control->avic_physical_id);
+	pr_err("%-20s%016llx\n", "vmsa_pa:", control->vmsa_pa);
 	pr_err("VMCB State Save Area:\n");
 	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
 	       "es:",
@@ -3045,6 +3199,43 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	       "excp_to:", save->last_excp_to);
 }
 
+static int svm_handle_invalid_exit(struct kvm_vcpu *vcpu, u64 exit_code)
+{
+	if (exit_code < ARRAY_SIZE(svm_exit_handlers) &&
+	    svm_exit_handlers[exit_code])
+		return 0;
+
+	vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%llx\n", exit_code);
+	dump_vmcb(vcpu);
+	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
+	vcpu->run->internal.ndata = 2;
+	vcpu->run->internal.data[0] = exit_code;
+	vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
+
+	return -EINVAL;
+}
+
+int svm_invoke_exit_handler(struct vcpu_svm *svm, u64 exit_code)
+{
+	if (svm_handle_invalid_exit(&svm->vcpu, exit_code))
+		return 0;
+
+#ifdef CONFIG_RETPOLINE
+	if (exit_code == SVM_EXIT_MSR)
+		return msr_interception(svm);
+	else if (exit_code == SVM_EXIT_VINTR)
+		return interrupt_window_interception(svm);
+	else if (exit_code == SVM_EXIT_INTR)
+		return intr_interception(svm);
+	else if (exit_code == SVM_EXIT_HLT)
+		return halt_interception(svm);
+	else if (exit_code == SVM_EXIT_NPF)
+		return npf_interception(svm);
+#endif
+	return svm_exit_handlers[exit_code](svm);
+}
+
 static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2,
 			      u32 *intr_info, u32 *error_code)
 {
@@ -3068,10 +3259,13 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 
 	trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM);
 
-	if (!svm_is_intercept(svm, INTERCEPT_CR0_WRITE))
-		vcpu->arch.cr0 = svm->vmcb->save.cr0;
-	if (npt_enabled)
-		vcpu->arch.cr3 = svm->vmcb->save.cr3;
+	/* SEV-ES guests must use the CR write traps to track CR registers. */
+	if (!sev_es_guest(vcpu->kvm)) {
+		if (!svm_is_intercept(svm, INTERCEPT_CR0_WRITE))
+			vcpu->arch.cr0 = svm->vmcb->save.cr0;
+		if (npt_enabled)
+			vcpu->arch.cr3 = svm->vmcb->save.cr3;
+	}
 
 	if (is_guest_mode(vcpu)) {
 		int vmexit;
@@ -3108,32 +3302,7 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	if (exit_fastpath != EXIT_FASTPATH_NONE)
 		return 1;
 
-	if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
-	    || !svm_exit_handlers[exit_code]) {
-		vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code);
-		dump_vmcb(vcpu);
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror =
-			KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
-		vcpu->run->internal.ndata = 2;
-		vcpu->run->internal.data[0] = exit_code;
-		vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
-		return 0;
-	}
-
-#ifdef CONFIG_RETPOLINE
-	if (exit_code == SVM_EXIT_MSR)
-		return msr_interception(svm);
-	else if (exit_code == SVM_EXIT_VINTR)
-		return interrupt_window_interception(svm);
-	else if (exit_code == SVM_EXIT_INTR)
-		return intr_interception(svm);
-	else if (exit_code == SVM_EXIT_HLT)
-		return halt_interception(svm);
-	else if (exit_code == SVM_EXIT_NPF)
-		return npf_interception(svm);
-#endif
-	return svm_exit_handlers[exit_code](svm);
+	return svm_invoke_exit_handler(svm, exit_code);
 }
 
 static void reload_tss(struct kvm_vcpu *vcpu)
@@ -3162,7 +3331,8 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu)
 
 	svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI;
 	vcpu->arch.hflags |= HF_NMI_MASK;
-	svm_set_intercept(svm, INTERCEPT_IRET);
+	if (!sev_es_guest(svm->vcpu.kvm))
+		svm_set_intercept(svm, INTERCEPT_IRET);
 	++vcpu->stat.nmi_injections;
 }
 
@@ -3183,6 +3353,13 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	/*
+	 * SEV-ES guests must always keep the CR intercepts cleared. CR
+	 * tracking is done using the CR write traps.
+	 */
+	if (sev_es_guest(vcpu->kvm))
+		return;
+
 	if (nested_svm_virtualize_tpr(vcpu))
 		return;
 
@@ -3239,10 +3416,12 @@ static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
 
 	if (masked) {
 		svm->vcpu.arch.hflags |= HF_NMI_MASK;
-		svm_set_intercept(svm, INTERCEPT_IRET);
+		if (!sev_es_guest(svm->vcpu.kvm))
+			svm_set_intercept(svm, INTERCEPT_IRET);
 	} else {
 		svm->vcpu.arch.hflags &= ~HF_NMI_MASK;
-		svm_clr_intercept(svm, INTERCEPT_IRET);
+		if (!sev_es_guest(svm->vcpu.kvm))
+			svm_clr_intercept(svm, INTERCEPT_IRET);
 	}
 }
 
@@ -3254,7 +3433,14 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu)
 	if (!gif_set(svm))
 		return true;
 
-	if (is_guest_mode(vcpu)) {
+	if (sev_es_guest(svm->vcpu.kvm)) {
+		/*
+		 * SEV-ES guests to not expose RFLAGS. Use the VMCB interrupt mask
+		 * bit to determine the state of the IF flag.
+		 */
+		if (!(vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK))
+			return true;
+	} else if (is_guest_mode(vcpu)) {
 		/* As long as interrupts are being delivered...  */
 		if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK)
 		    ? !(svm->nested.hsave->save.rflags & X86_EFLAGS_IF)
@@ -3413,8 +3599,9 @@ static void svm_complete_interrupts(struct vcpu_svm *svm)
 	 * If we've made progress since setting HF_IRET_MASK, we've
 	 * executed an IRET and can allow NMI injection.
 	 */
-	if ((svm->vcpu.arch.hflags & HF_IRET_MASK)
-	    && kvm_rip_read(&svm->vcpu) != svm->nmi_iret_rip) {
+	if ((svm->vcpu.arch.hflags & HF_IRET_MASK) &&
+	    (sev_es_guest(svm->vcpu.kvm) ||
+	     kvm_rip_read(&svm->vcpu) != svm->nmi_iret_rip)) {
 		svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK);
 		kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 	}
@@ -3437,6 +3624,12 @@ static void svm_complete_interrupts(struct vcpu_svm *svm)
 		break;
 	case SVM_EXITINTINFO_TYPE_EXEPT:
 		/*
+		 * Never re-inject a #VC exception.
+		 */
+		if (vector == X86_TRAP_VC)
+			break;
+
+		/*
 		 * In case of software exceptions, do not reinject the vector,
 		 * but re-execute the instruction instead. Rewind RIP first
 		 * if we emulated INT3 before.
@@ -3484,8 +3677,6 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 	return EXIT_FASTPATH_NONE;
 }
 
-void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
-
 static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 					struct vcpu_svm *svm)
 {
@@ -3509,16 +3700,20 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 	guest_enter_irqoff();
 	lockdep_hardirqs_on(CALLER_ADDR0);
 
-	__svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs);
+	if (sev_es_guest(svm->vcpu.kvm)) {
+		__svm_sev_es_vcpu_run(svm->vmcb_pa);
+	} else {
+		__svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs);
 
 #ifdef CONFIG_X86_64
-	native_wrmsrl(MSR_GS_BASE, svm->host.gs_base);
+		native_wrmsrl(MSR_GS_BASE, svm->host.gs_base);
 #else
-	loadsegment(fs, svm->host.fs);
+		loadsegment(fs, svm->host.fs);
 #ifndef CONFIG_X86_32_LAZY_GS
-	loadsegment(gs, svm->host.gs);
+		loadsegment(gs, svm->host.gs);
 #endif
 #endif
+	}
 
 	/*
 	 * VMEXIT disables interrupts (host state), but tracing and lockdep
@@ -3568,6 +3763,10 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	sync_lapic_to_cr8(vcpu);
 
+	if (unlikely(svm->asid != svm->vmcb->control.asid)) {
+		svm->vmcb->control.asid = svm->asid;
+		vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
+	}
 	svm->vmcb->save.cr2 = vcpu->arch.cr2;
 
 	/*
@@ -3612,14 +3811,17 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
 		svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
-	reload_tss(vcpu);
+	if (!sev_es_guest(svm->vcpu.kvm))
+		reload_tss(vcpu);
 
 	x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
 
-	vcpu->arch.cr2 = svm->vmcb->save.cr2;
-	vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax;
-	vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
-	vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
+	if (!sev_es_guest(svm->vcpu.kvm)) {
+		vcpu->arch.cr2 = svm->vmcb->save.cr2;
+		vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax;
+		vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
+		vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
+	}
 
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(&svm->vcpu);
@@ -3722,12 +3924,21 @@ static bool svm_cpu_has_accelerated_tpr(void)
 	return false;
 }
 
-static bool svm_has_emulated_msr(u32 index)
+/*
+ * The kvm parameter can be NULL (module initialization, or invocation before
+ * VM creation). Be sure to check the kvm parameter before using it.
+ */
+static bool svm_has_emulated_msr(struct kvm *kvm, u32 index)
 {
 	switch (index) {
 	case MSR_IA32_MCG_EXT_CTL:
 	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
 		return false;
+	case MSR_IA32_SMBASE:
+		/* SEV-ES guests do not support SMM, so report false */
+		if (kvm && sev_es_guest(kvm))
+			return false;
+		break;
 	default:
 		break;
 	}
@@ -4086,6 +4297,12 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int i
 	unsigned long cr4;
 
 	/*
+	 * When the guest is an SEV-ES guest, emulation is not possible.
+	 */
+	if (sev_es_guest(vcpu->kvm))
+		return false;
+
+	/*
 	 * Detect and workaround Errata 1096 Fam_17h_00_0Fh.
 	 *
 	 * Errata:
@@ -4165,6 +4382,14 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
 		   (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT));
 }
 
+static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
+{
+	if (!sev_es_guest(vcpu->kvm))
+		return kvm_vcpu_deliver_sipi_vector(vcpu, vector);
+
+	sev_vcpu_deliver_sipi_vector(vcpu, vector);
+}
+
 static void svm_vm_destroy(struct kvm *kvm)
 {
 	avic_vm_destroy(kvm);
@@ -4217,6 +4442,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.get_cpl = svm_get_cpl,
 	.get_cs_db_l_bits = kvm_get_cs_db_l_bits,
 	.set_cr0 = svm_set_cr0,
+	.is_valid_cr4 = svm_is_valid_cr4,
 	.set_cr4 = svm_set_cr4,
 	.set_efer = svm_set_efer,
 	.get_idt = svm_get_idt,
@@ -4305,6 +4531,9 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.apic_init_signal_blocked = svm_apic_init_signal_blocked,
 
 	.msr_filter_changed = svm_msr_filter_changed,
+	.complete_emulated_msr = svm_complete_emulated_msr,
+
+	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
 };
 
 static struct kvm_x86_init_ops svm_init_ops __initdata = {
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 1d853fe4c778..0fe874ae5498 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -17,21 +17,32 @@
 
 #include <linux/kvm_types.h>
 #include <linux/kvm_host.h>
+#include <linux/bits.h>
 
 #include <asm/svm.h>
 
-static const u32 host_save_user_msrs[] = {
+#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
+
+static const struct svm_host_save_msrs {
+	u32 index;		/* Index of the MSR */
+	bool sev_es_restored;	/* True if MSR is restored on SEV-ES VMEXIT */
+} host_save_user_msrs[] = {
 #ifdef CONFIG_X86_64
-	MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
-	MSR_FS_BASE,
+	{ .index = MSR_STAR,			.sev_es_restored = true },
+	{ .index = MSR_LSTAR,			.sev_es_restored = true },
+	{ .index = MSR_CSTAR,			.sev_es_restored = true },
+	{ .index = MSR_SYSCALL_MASK,		.sev_es_restored = true },
+	{ .index = MSR_KERNEL_GS_BASE,		.sev_es_restored = true },
+	{ .index = MSR_FS_BASE,			.sev_es_restored = true },
 #endif
-	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
-	MSR_TSC_AUX,
+	{ .index = MSR_IA32_SYSENTER_CS,	.sev_es_restored = true },
+	{ .index = MSR_IA32_SYSENTER_ESP,	.sev_es_restored = true },
+	{ .index = MSR_IA32_SYSENTER_EIP,	.sev_es_restored = true },
+	{ .index = MSR_TSC_AUX,			.sev_es_restored = false },
 };
-
 #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)
 
-#define MAX_DIRECT_ACCESS_MSRS	15
+#define MAX_DIRECT_ACCESS_MSRS	18
 #define MSRPM_OFFSETS	16
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
@@ -61,11 +72,13 @@ enum {
 
 struct kvm_sev_info {
 	bool active;		/* SEV enabled guest */
+	bool es_active;		/* SEV-ES enabled guest */
 	unsigned int asid;	/* ASID used for this guest */
 	unsigned int handle;	/* SEV firmware handle */
 	int fd;			/* SEV device fd */
 	unsigned long pages_locked; /* Number of pages locked */
 	struct list_head regions_list;  /* List of registered regions */
+	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */
 };
 
 struct kvm_svm {
@@ -106,6 +119,7 @@ struct vcpu_svm {
 	struct vmcb *vmcb;
 	unsigned long vmcb_pa;
 	struct svm_cpu_data *svm_data;
+	u32 asid;
 	uint64_t asid_generation;
 	uint64_t sysenter_esp;
 	uint64_t sysenter_eip;
@@ -166,6 +180,18 @@ struct vcpu_svm {
 		DECLARE_BITMAP(read, MAX_DIRECT_ACCESS_MSRS);
 		DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS);
 	} shadow_msr_intercept;
+
+	/* SEV-ES support */
+	struct vmcb_save_area *vmsa;
+	struct ghcb *ghcb;
+	struct kvm_host_map ghcb_map;
+	bool received_first_sipi;
+
+	/* SEV-ES scratch area support */
+	void *ghcb_sa;
+	u64 ghcb_sa_len;
+	bool ghcb_sa_sync;
+	bool ghcb_sa_free;
 };
 
 struct svm_cpu_data {
@@ -193,6 +219,28 @@ static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
 	return container_of(kvm, struct kvm_svm, kvm);
 }
 
+static inline bool sev_guest(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_AMD_SEV
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+
+	return sev->active;
+#else
+	return false;
+#endif
+}
+
+static inline bool sev_es_guest(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_AMD_SEV
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+
+	return sev_guest(kvm) && sev->es_active;
+#else
+	return false;
+#endif
+}
+
 static inline void vmcb_mark_all_dirty(struct vmcb *vmcb)
 {
 	vmcb->control.clean = 0;
@@ -244,21 +292,24 @@ static inline void set_dr_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ);
+	if (!sev_es_guest(svm->vcpu.kvm)) {
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE);
+	}
+
 	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE);
 	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
 
 	recalc_intercepts(svm);
@@ -270,6 +321,12 @@ static inline void clr_dr_intercepts(struct vcpu_svm *svm)
 
 	vmcb->control.intercepts[INTERCEPT_DR] = 0;
 
+	/* DR7 access must remain intercepted for an SEV-ES guest */
+	if (sev_es_guest(svm->vcpu.kvm)) {
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
+	}
+
 	recalc_intercepts(svm);
 }
 
@@ -351,6 +408,10 @@ static inline bool gif_set(struct vcpu_svm *svm)
 #define MSR_CR3_LONG_MBZ_MASK			0xfff0000000000000U
 #define MSR_INVALID				0xffffffffU
 
+extern int sev;
+extern int sev_es;
+extern bool dump_invalid_vmcb;
+
 u32 svm_msrpm_offset(u32 msr);
 u32 *svm_vcpu_alloc_msrpm(void);
 void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm);
@@ -358,13 +419,16 @@ void svm_vcpu_free_msrpm(u32 *msrpm);
 
 int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer);
 void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
-int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
+void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
 void svm_flush_tlb(struct kvm_vcpu *vcpu);
 void disable_nmi_singlestep(struct vcpu_svm *svm);
 bool svm_smi_blocked(struct kvm_vcpu *vcpu);
 bool svm_nmi_blocked(struct kvm_vcpu *vcpu);
 bool svm_interrupt_blocked(struct kvm_vcpu *vcpu);
 void svm_set_gif(struct vcpu_svm *svm, bool value);
+int svm_invoke_exit_handler(struct vcpu_svm *svm, u64 exit_code);
+void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr,
+			  int read, int write);
 
 /* nested.c */
 
@@ -470,18 +534,42 @@ void svm_vcpu_unblocking(struct kvm_vcpu *vcpu);
 
 /* sev.c */
 
-extern unsigned int max_sev_asid;
+#define GHCB_VERSION_MAX		1ULL
+#define GHCB_VERSION_MIN		1ULL
+
+#define GHCB_MSR_INFO_POS		0
+#define GHCB_MSR_INFO_MASK		(BIT_ULL(12) - 1)
+
+#define GHCB_MSR_SEV_INFO_RESP		0x001
+#define GHCB_MSR_SEV_INFO_REQ		0x002
+#define GHCB_MSR_VER_MAX_POS		48
+#define GHCB_MSR_VER_MAX_MASK		0xffff
+#define GHCB_MSR_VER_MIN_POS		32
+#define GHCB_MSR_VER_MIN_MASK		0xffff
+#define GHCB_MSR_CBIT_POS		24
+#define GHCB_MSR_CBIT_MASK		0xff
+#define GHCB_MSR_SEV_INFO(_max, _min, _cbit)				\
+	((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) |	\
+	 (((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) |	\
+	 (((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) |	\
+	 GHCB_MSR_SEV_INFO_RESP)
+
+#define GHCB_MSR_CPUID_REQ		0x004
+#define GHCB_MSR_CPUID_RESP		0x005
+#define GHCB_MSR_CPUID_FUNC_POS		32
+#define GHCB_MSR_CPUID_FUNC_MASK	0xffffffff
+#define GHCB_MSR_CPUID_VALUE_POS	32
+#define GHCB_MSR_CPUID_VALUE_MASK	0xffffffff
+#define GHCB_MSR_CPUID_REG_POS		30
+#define GHCB_MSR_CPUID_REG_MASK		0x3
+
+#define GHCB_MSR_TERM_REQ		0x100
+#define GHCB_MSR_TERM_REASON_SET_POS	12
+#define GHCB_MSR_TERM_REASON_SET_MASK	0xf
+#define GHCB_MSR_TERM_REASON_POS	16
+#define GHCB_MSR_TERM_REASON_MASK	0xff
 
-static inline bool sev_guest(struct kvm *kvm)
-{
-#ifdef CONFIG_KVM_AMD_SEV
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-
-	return sev->active;
-#else
-	return false;
-#endif
-}
+extern unsigned int max_sev_asid;
 
 static inline bool svm_sev_enabled(void)
 {
@@ -495,7 +583,20 @@ int svm_register_enc_region(struct kvm *kvm,
 int svm_unregister_enc_region(struct kvm *kvm,
 			      struct kvm_enc_region *range);
 void pre_sev_run(struct vcpu_svm *svm, int cpu);
-int __init sev_hardware_setup(void);
+void __init sev_hardware_setup(void);
 void sev_hardware_teardown(void);
+void sev_free_vcpu(struct kvm_vcpu *vcpu);
+int sev_handle_vmgexit(struct vcpu_svm *svm);
+int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
+void sev_es_init_vmcb(struct vcpu_svm *svm);
+void sev_es_create_vcpu(struct vcpu_svm *svm);
+void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu);
+void sev_es_vcpu_put(struct vcpu_svm *svm);
+void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
+
+/* vmenter.S */
+
+void __svm_sev_es_vcpu_run(unsigned long vmcb_pa);
+void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
 
 #endif
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 1ec1ac40e328..6feb8c08f45a 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -168,3 +168,53 @@ SYM_FUNC_START(__svm_vcpu_run)
 	pop %_ASM_BP
 	ret
 SYM_FUNC_END(__svm_vcpu_run)
+
+/**
+ * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode
+ * @vmcb_pa:	unsigned long
+ */
+SYM_FUNC_START(__svm_sev_es_vcpu_run)
+	push %_ASM_BP
+#ifdef CONFIG_X86_64
+	push %r15
+	push %r14
+	push %r13
+	push %r12
+#else
+	push %edi
+	push %esi
+#endif
+	push %_ASM_BX
+
+	/* Enter guest mode */
+	mov %_ASM_ARG1, %_ASM_AX
+	sti
+
+1:	vmrun %_ASM_AX
+	jmp 3f
+2:	cmpb $0, kvm_rebooting
+	jne 3f
+	ud2
+	_ASM_EXTABLE(1b, 2b)
+
+3:	cli
+
+#ifdef CONFIG_RETPOLINE
+	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+#endif
+
+	pop %_ASM_BX
+
+#ifdef CONFIG_X86_64
+	pop %r12
+	pop %r13
+	pop %r14
+	pop %r15
+#else
+	pop %esi
+	pop %edi
+#endif
+	pop %_ASM_BP
+	ret
+SYM_FUNC_END(__svm_sev_es_vcpu_run)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index aef960f90f26..2de30c20bc26 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1578,6 +1578,103 @@ TRACE_EVENT(kvm_hv_syndbg_get_msr,
 		  __entry->vcpu_id, __entry->vp_index, __entry->msr,
 		  __entry->data)
 );
+
+/*
+ * Tracepoint for the start of VMGEXIT processing
+ */
+TRACE_EVENT(kvm_vmgexit_enter,
+	TP_PROTO(unsigned int vcpu_id, struct ghcb *ghcb),
+	TP_ARGS(vcpu_id, ghcb),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, vcpu_id)
+		__field(u64, exit_reason)
+		__field(u64, info1)
+		__field(u64, info2)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id     = vcpu_id;
+		__entry->exit_reason = ghcb->save.sw_exit_code;
+		__entry->info1       = ghcb->save.sw_exit_info_1;
+		__entry->info2       = ghcb->save.sw_exit_info_2;
+	),
+
+	TP_printk("vcpu %u, exit_reason %llx, exit_info1 %llx, exit_info2 %llx",
+		  __entry->vcpu_id, __entry->exit_reason,
+		  __entry->info1, __entry->info2)
+);
+
+/*
+ * Tracepoint for the end of VMGEXIT processing
+ */
+TRACE_EVENT(kvm_vmgexit_exit,
+	TP_PROTO(unsigned int vcpu_id, struct ghcb *ghcb),
+	TP_ARGS(vcpu_id, ghcb),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, vcpu_id)
+		__field(u64, exit_reason)
+		__field(u64, info1)
+		__field(u64, info2)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id     = vcpu_id;
+		__entry->exit_reason = ghcb->save.sw_exit_code;
+		__entry->info1       = ghcb->save.sw_exit_info_1;
+		__entry->info2       = ghcb->save.sw_exit_info_2;
+	),
+
+	TP_printk("vcpu %u, exit_reason %llx, exit_info1 %llx, exit_info2 %llx",
+		  __entry->vcpu_id, __entry->exit_reason,
+		  __entry->info1, __entry->info2)
+);
+
+/*
+ * Tracepoint for the start of VMGEXIT MSR procotol processing
+ */
+TRACE_EVENT(kvm_vmgexit_msr_protocol_enter,
+	TP_PROTO(unsigned int vcpu_id, u64 ghcb_gpa),
+	TP_ARGS(vcpu_id, ghcb_gpa),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, vcpu_id)
+		__field(u64, ghcb_gpa)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id  = vcpu_id;
+		__entry->ghcb_gpa = ghcb_gpa;
+	),
+
+	TP_printk("vcpu %u, ghcb_gpa %016llx",
+		  __entry->vcpu_id, __entry->ghcb_gpa)
+);
+
+/*
+ * Tracepoint for the end of VMGEXIT MSR procotol processing
+ */
+TRACE_EVENT(kvm_vmgexit_msr_protocol_exit,
+	TP_PROTO(unsigned int vcpu_id, u64 ghcb_gpa, int result),
+	TP_ARGS(vcpu_id, ghcb_gpa, result),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, vcpu_id)
+		__field(u64, ghcb_gpa)
+		__field(int, result)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id  = vcpu_id;
+		__entry->ghcb_gpa = ghcb_gpa;
+		__entry->result   = result;
+	),
+
+	TP_printk("vcpu %u, ghcb_gpa %016llx, result %d",
+		  __entry->vcpu_id, __entry->ghcb_gpa, __entry->result)
+);
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c
index f3199bb02f22..41f24661af04 100644
--- a/arch/x86/kvm/vmx/evmcs.c
+++ b/arch/x86/kvm/vmx/evmcs.c
@@ -326,7 +326,6 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa)
 
 uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	/*
 	 * vmcs_version represents the range of supported Enlightened VMCS
 	 * versions: lower 8 bits is the minimal version, higher 8 bits is the
@@ -334,7 +333,7 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
 	 * KVM_EVMCS_VERSION.
 	 */
 	if (kvm_cpu_cap_get(X86_FEATURE_VMX) &&
-	    vmx->nested.enlightened_vmcs_enabled)
+	    (!vcpu || to_vmx(vcpu)->nested.enlightened_vmcs_enabled))
 		return (KVM_EVMCS_VERSION << 8) | 1;
 
 	return 0;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 89af692deb7e..0fbb46990dfc 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2952,7 +2952,8 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
 static int nested_check_guest_non_reg_state(struct vmcs12 *vmcs12)
 {
 	if (CC(vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE &&
-	       vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT))
+	       vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT &&
+	       vmcs12->guest_activity_state != GUEST_ACTIVITY_WAIT_SIPI))
 		return -EINVAL;
 
 	return 0;
@@ -3559,19 +3560,29 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 */
 	nested_cache_shadow_vmcs12(vcpu, vmcs12);
 
-	/*
-	 * If we're entering a halted L2 vcpu and the L2 vcpu won't be
-	 * awakened by event injection or by an NMI-window VM-exit or
-	 * by an interrupt-window VM-exit, halt the vcpu.
-	 */
-	if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
-	    !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) &&
-	    !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_NMI_WINDOW_EXITING) &&
-	    !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_INTR_WINDOW_EXITING) &&
-	      (vmcs12->guest_rflags & X86_EFLAGS_IF))) {
+	switch (vmcs12->guest_activity_state) {
+	case GUEST_ACTIVITY_HLT:
+		/*
+		 * If we're entering a halted L2 vcpu and the L2 vcpu won't be
+		 * awakened by event injection or by an NMI-window VM-exit or
+		 * by an interrupt-window VM-exit, halt the vcpu.
+		 */
+		if (!(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) &&
+		    !nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING) &&
+		    !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) &&
+		      (vmcs12->guest_rflags & X86_EFLAGS_IF))) {
+			vmx->nested.nested_run_pending = 0;
+			return kvm_vcpu_halt(vcpu);
+		}
+		break;
+	case GUEST_ACTIVITY_WAIT_SIPI:
 		vmx->nested.nested_run_pending = 0;
-		return kvm_vcpu_halt(vcpu);
+		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+		break;
+	default:
+		break;
 	}
+
 	return 1;
 
 vmentry_failed:
@@ -3797,7 +3808,20 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
 			return -EBUSY;
 		nested_vmx_update_pending_dbg(vcpu);
 		clear_bit(KVM_APIC_INIT, &apic->pending_events);
-		nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
+		if (vcpu->arch.mp_state != KVM_MP_STATE_INIT_RECEIVED)
+			nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
+		return 0;
+	}
+
+	if (lapic_in_kernel(vcpu) &&
+	    test_bit(KVM_APIC_SIPI, &apic->pending_events)) {
+		if (block_nested_events)
+			return -EBUSY;
+
+		clear_bit(KVM_APIC_SIPI, &apic->pending_events);
+		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
+			nested_vmx_vmexit(vcpu, EXIT_REASON_SIPI_SIGNAL, 0,
+						apic->sipi_vector & 0xFFUL);
 		return 0;
 	}
 
@@ -4036,6 +4060,8 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
 		vmcs12->guest_activity_state = GUEST_ACTIVITY_HLT;
+	else if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
+		vmcs12->guest_activity_state = GUEST_ACTIVITY_WAIT_SIPI;
 	else
 		vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE;
 
@@ -4416,6 +4442,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	/* trying to cancel vmlaunch/vmresume is a bug */
 	WARN_ON_ONCE(vmx->nested.nested_run_pending);
 
+	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+
 	/* Service the TLB flush request for L2 before switching to L1. */
 	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
 		kvm_vcpu_flush_tlb_current(vcpu);
@@ -4814,7 +4842,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 	/*
 	 * The Intel VMX Instruction Reference lists a bunch of bits that are
 	 * prerequisite to running VMXON, most notably cr4.VMXE must be set to
-	 * 1 (see vmx_set_cr4() for when we allow the guest to set this).
+	 * 1 (see vmx_is_valid_cr4() for when we allow the guest to set this).
 	 * Otherwise, we should fail with #UD.  But most faulting conditions
 	 * have already been checked by hardware, prior to the VM-exit for
 	 * VMXON.  We do test guest cr4.VMXE because processor CR4 always has
@@ -6483,7 +6511,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 	msrs->misc_low |=
 		MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
 		VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
-		VMX_MISC_ACTIVITY_HLT;
+		VMX_MISC_ACTIVITY_HLT |
+		VMX_MISC_ACTIVITY_WAIT_SIPI;
 	msrs->misc_high = 0;
 
 	/*
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 90ad7a6246e3..e85aa5faa22d 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -132,7 +132,7 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	mov (%_ASM_SP), %_ASM_AX
 
 	/* Check if vmlaunch or vmresume is needed */
-	cmpb $0, %bl
+	testb %bl, %bl
 
 	/* Load guest registers.  Don't clobber flags. */
 	mov VCPU_RCX(%_ASM_AX), %_ASM_CX
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 47b8357b9751..2af05d3b0590 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -40,7 +40,6 @@
 #include <asm/irq_remapping.h>
 #include <asm/kexec.h>
 #include <asm/perf_event.h>
-#include <asm/mce.h>
 #include <asm/mmu_context.h>
 #include <asm/mshyperv.h>
 #include <asm/mwait.h>
@@ -1826,7 +1825,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+		    !guest_has_spec_ctrl_msr(vcpu))
 			return 1;
 
 		msr_info->data = to_vmx(vcpu)->spec_ctrl;
@@ -2028,7 +2027,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+		    !guest_has_spec_ctrl_msr(vcpu))
 			return 1;
 
 		if (kvm_spec_ctrl_test_value(data))
@@ -2063,12 +2062,12 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		goto find_uret_msr;
 	case MSR_IA32_PRED_CMD:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+		    !guest_has_pred_cmd_msr(vcpu))
 			return 1;
 
 		if (data & ~PRED_CMD_IBPB)
 			return 1;
-		if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL))
+		if (!boot_cpu_has(X86_FEATURE_IBPB))
 			return 1;
 		if (!data)
 			break;
@@ -3095,8 +3094,25 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd,
 		vmcs_writel(GUEST_CR3, guest_cr3);
 }
 
-int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
+	/*
+	 * We operate under the default treatment of SMM, so VMX cannot be
+	 * enabled under SMM.  Note, whether or not VMXE is allowed at all is
+	 * handled by kvm_is_valid_cr4().
+	 */
+	if ((cr4 & X86_CR4_VMXE) && is_smm(vcpu))
+		return false;
+
+	if (to_vmx(vcpu)->nested.vmxon && !nested_cr4_valid(vcpu, cr4))
+		return false;
+
+	return true;
+}
+
+void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+	unsigned long old_cr4 = vcpu->arch.cr4;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	/*
 	 * Pass through host's Machine Check Enable value to hw_cr4, which
@@ -3123,21 +3139,6 @@ int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 		}
 	}
 
-	if (cr4 & X86_CR4_VMXE) {
-		/*
-		 * To use VMXON (and later other VMX instructions), a guest
-		 * must first be able to turn on cr4.VMXE (see handle_vmon()).
-		 * So basically the check on whether to allow nested VMX
-		 * is here.  We operate under the default treatment of SMM,
-		 * so VMX cannot be enabled under SMM.
-		 */
-		if (!nested_vmx_allowed(vcpu) || is_smm(vcpu))
-			return 1;
-	}
-
-	if (vmx->nested.vmxon && !nested_cr4_valid(vcpu, cr4))
-		return 1;
-
 	vcpu->arch.cr4 = cr4;
 	kvm_register_mark_available(vcpu, VCPU_EXREG_CR4);
 
@@ -3168,7 +3169,9 @@ int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 
 	vmcs_writel(CR4_READ_SHADOW, cr4);
 	vmcs_writel(GUEST_CR4, hw_cr4);
-	return 0;
+
+	if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
+		kvm_update_cpuid_runtime(vcpu);
 }
 
 void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg)
@@ -3515,42 +3518,33 @@ bool __vmx_guest_state_valid(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static int init_rmode_tss(struct kvm *kvm)
+static int init_rmode_tss(struct kvm *kvm, void __user *ua)
 {
-	gfn_t fn;
-	u16 data = 0;
-	int idx, r;
+	const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
+	u16 data;
+	int i;
+
+	for (i = 0; i < 3; i++) {
+		if (__copy_to_user(ua + PAGE_SIZE * i, zero_page, PAGE_SIZE))
+			return -EFAULT;
+	}
 
-	idx = srcu_read_lock(&kvm->srcu);
-	fn = to_kvm_vmx(kvm)->tss_addr >> PAGE_SHIFT;
-	r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
-	if (r < 0)
-		goto out;
 	data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE;
-	r = kvm_write_guest_page(kvm, fn++, &data,
-			TSS_IOPB_BASE_OFFSET, sizeof(u16));
-	if (r < 0)
-		goto out;
-	r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE);
-	if (r < 0)
-		goto out;
-	r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
-	if (r < 0)
-		goto out;
+	if (__copy_to_user(ua + TSS_IOPB_BASE_OFFSET, &data, sizeof(u16)))
+		return -EFAULT;
+
 	data = ~0;
-	r = kvm_write_guest_page(kvm, fn, &data,
-				 RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1,
-				 sizeof(u8));
-out:
-	srcu_read_unlock(&kvm->srcu, idx);
-	return r;
+	if (__copy_to_user(ua + RMODE_TSS_SIZE - 1, &data, sizeof(u8)))
+		return -EFAULT;
+
+	return 0;
 }
 
 static int init_rmode_identity_map(struct kvm *kvm)
 {
 	struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm);
 	int i, r = 0;
-	kvm_pfn_t identity_map_pfn;
+	void __user *uaddr;
 	u32 tmp;
 
 	/* Protect kvm_vmx->ept_identity_pagetable_done. */
@@ -3561,24 +3555,24 @@ static int init_rmode_identity_map(struct kvm *kvm)
 
 	if (!kvm_vmx->ept_identity_map_addr)
 		kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR;
-	identity_map_pfn = kvm_vmx->ept_identity_map_addr >> PAGE_SHIFT;
 
-	r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
-				    kvm_vmx->ept_identity_map_addr, PAGE_SIZE);
-	if (r < 0)
+	uaddr = __x86_set_memory_region(kvm,
+					IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
+					kvm_vmx->ept_identity_map_addr,
+					PAGE_SIZE);
+	if (IS_ERR(uaddr)) {
+		r = PTR_ERR(uaddr);
 		goto out;
+	}
 
-	r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
-	if (r < 0)
-		goto out;
 	/* Set up identity-mapping pagetable for EPT in real mode */
 	for (i = 0; i < PT32_ENT_PER_PAGE; i++) {
 		tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
 			_PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE);
-		r = kvm_write_guest_page(kvm, identity_map_pfn,
-				&tmp, i * sizeof(tmp), sizeof(tmp));
-		if (r < 0)
+		if (__copy_to_user(uaddr + i * sizeof(tmp), &tmp, sizeof(tmp))) {
+			r = -EFAULT;
 			goto out;
+		}
 	}
 	kvm_vmx->ept_identity_pagetable_done = true;
 
@@ -3605,19 +3599,22 @@ static void seg_setup(int seg)
 static int alloc_apic_access_page(struct kvm *kvm)
 {
 	struct page *page;
-	int r = 0;
+	void __user *hva;
+	int ret = 0;
 
 	mutex_lock(&kvm->slots_lock);
 	if (kvm->arch.apic_access_page_done)
 		goto out;
-	r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
-				    APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
-	if (r)
+	hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
+				      APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
+	if (IS_ERR(hva)) {
+		ret = PTR_ERR(hva);
 		goto out;
+	}
 
 	page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
 	if (is_error_page(page)) {
-		r = -EFAULT;
+		ret = -EFAULT;
 		goto out;
 	}
 
@@ -3629,7 +3626,7 @@ static int alloc_apic_access_page(struct kvm *kvm)
 	kvm->arch.apic_access_page_done = true;
 out:
 	mutex_unlock(&kvm->slots_lock);
-	return r;
+	return ret;
 }
 
 int allocate_vpid(void)
@@ -4638,7 +4635,7 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 {
-	int ret;
+	void __user *ret;
 
 	if (enable_unrestricted_guest)
 		return 0;
@@ -4648,10 +4645,12 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 				      PAGE_SIZE * 3);
 	mutex_unlock(&kvm->slots_lock);
 
-	if (ret)
-		return ret;
+	if (IS_ERR(ret))
+		return PTR_ERR(ret);
+
 	to_kvm_vmx(kvm)->tss_addr = addr;
-	return init_rmode_tss(kvm);
+
+	return init_rmode_tss(kvm, ret);
 }
 
 static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr)
@@ -4716,25 +4715,6 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
-/*
- * Trigger machine check on the host. We assume all the MSRs are already set up
- * by the CPU and that we still run on the same CPU as the MCE occurred on.
- * We pass a fake environment to the machine check handler because we want
- * the guest to be always treated like user space, no matter what context
- * it used internally.
- */
-static void kvm_machine_check(void)
-{
-#if defined(CONFIG_X86_MCE)
-	struct pt_regs regs = {
-		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
-		.flags = X86_EFLAGS_IF,
-	};
-
-	do_machine_check(&regs);
-#endif
-}
-
 static int handle_machine_check(struct kvm_vcpu *vcpu)
 {
 	/* handled by vmx_vcpu_run() */
@@ -6399,7 +6379,11 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 		handle_exception_nmi_irqoff(vmx);
 }
 
-static bool vmx_has_emulated_msr(u32 index)
+/*
+ * The kvm parameter can be NULL (module initialization, or invocation before
+ * VM creation). Be sure to check the kvm parameter before using it.
+ */
+static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index)
 {
 	switch (index) {
 	case MSR_IA32_SMBASE:
@@ -7558,7 +7542,7 @@ static void enable_smi_window(struct kvm_vcpu *vcpu)
 
 static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
 {
-	return to_vmx(vcpu)->nested.vmxon;
+	return to_vmx(vcpu)->nested.vmxon && !is_guest_mode(vcpu);
 }
 
 static void vmx_migrate_timers(struct kvm_vcpu *vcpu)
@@ -7587,6 +7571,11 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit)
 	return supported & BIT(bit);
 }
 
+static int vmx_cpu_dirty_log_size(void)
+{
+	return enable_pml ? PML_ENTITY_NUM : 0;
+}
+
 static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.hardware_unsetup = hardware_unsetup,
 
@@ -7616,6 +7605,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.get_cpl = vmx_get_cpl,
 	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
 	.set_cr0 = vmx_set_cr0,
+	.is_valid_cr4 = vmx_is_valid_cr4,
 	.set_cr4 = vmx_set_cr4,
 	.set_efer = vmx_set_efer,
 	.get_idt = vmx_get_idt,
@@ -7715,6 +7705,10 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.migrate_timers = vmx_migrate_timers,
 
 	.msr_filter_changed = vmx_msr_filter_changed,
+	.complete_emulated_msr = kvm_complete_insn_gp,
+	.cpu_dirty_log_size = vmx_cpu_dirty_log_size,
+
+	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
 };
 
 static __init int hardware_setup(void)
@@ -7832,6 +7826,7 @@ static __init int hardware_setup(void)
 		vmx_x86_ops.slot_disable_log_dirty = NULL;
 		vmx_x86_ops.flush_log_dirty = NULL;
 		vmx_x86_ops.enable_log_dirty_pt_masked = NULL;
+		vmx_x86_ops.cpu_dirty_log_size = NULL;
 	}
 
 	if (!cpu_has_vmx_preemption_timer())
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index f6f66e5c6510..9d3a557949ac 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -321,7 +321,7 @@ u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu);
 void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask);
 int vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer);
 void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
-int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
+void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
 void set_cr4_guest_host_mask(struct vcpu_vmx *vmx);
 void ept_save_pdptrs(struct kvm_vcpu *vcpu);
 void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b05aec109242..9a8969a6dd06 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -197,7 +197,8 @@ EXPORT_SYMBOL_GPL(host_efer);
 bool __read_mostly allow_smaller_maxphyaddr = 0;
 EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
 
-static u64 __read_mostly host_xss;
+u64 __read_mostly host_xss;
+EXPORT_SYMBOL_GPL(host_xss);
 u64 __read_mostly supported_xss;
 EXPORT_SYMBOL_GPL(supported_xss);
 
@@ -804,11 +805,29 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(pdptrs_changed);
 
+void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0)
+{
+	unsigned long update_bits = X86_CR0_PG | X86_CR0_WP;
+
+	if ((cr0 ^ old_cr0) & X86_CR0_PG) {
+		kvm_clear_async_pf_completion_queue(vcpu);
+		kvm_async_pf_hash_reset(vcpu);
+	}
+
+	if ((cr0 ^ old_cr0) & update_bits)
+		kvm_mmu_reset_context(vcpu);
+
+	if (((cr0 ^ old_cr0) & X86_CR0_CD) &&
+	    kvm_arch_has_noncoherent_dma(vcpu->kvm) &&
+	    !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+		kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL);
+}
+EXPORT_SYMBOL_GPL(kvm_post_set_cr0);
+
 int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
 	unsigned long old_cr0 = kvm_read_cr0(vcpu);
 	unsigned long pdptr_bits = X86_CR0_CD | X86_CR0_NW | X86_CR0_PG;
-	unsigned long update_bits = X86_CR0_PG | X86_CR0_WP;
 
 	cr0 |= X86_CR0_ET;
 
@@ -847,18 +866,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	kvm_x86_ops.set_cr0(vcpu, cr0);
 
-	if ((cr0 ^ old_cr0) & X86_CR0_PG) {
-		kvm_clear_async_pf_completion_queue(vcpu);
-		kvm_async_pf_hash_reset(vcpu);
-	}
-
-	if ((cr0 ^ old_cr0) & update_bits)
-		kvm_mmu_reset_context(vcpu);
-
-	if (((cr0 ^ old_cr0) & X86_CR0_CD) &&
-	    kvm_arch_has_noncoherent_dma(vcpu->kvm) &&
-	    !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
-		kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL);
+	kvm_post_set_cr0(vcpu, old_cr0, cr0);
 
 	return 0;
 }
@@ -872,6 +880,9 @@ EXPORT_SYMBOL_GPL(kvm_lmsw);
 
 void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 {
+	if (vcpu->arch.guest_state_protected)
+		return;
+
 	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
 
 		if (vcpu->arch.xcr0 != host_xcr0)
@@ -892,6 +903,9 @@ EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);
 
 void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 {
+	if (vcpu->arch.guest_state_protected)
+		return;
+
 	if (static_cpu_has(X86_FEATURE_PKU) &&
 	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
 	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) {
@@ -964,26 +978,36 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 }
 EXPORT_SYMBOL_GPL(kvm_set_xcr);
 
-int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	if (cr4 & cr4_reserved_bits)
-		return -EINVAL;
+		return false;
 
 	if (cr4 & vcpu->arch.cr4_guest_rsvd_bits)
-		return -EINVAL;
+		return false;
 
-	return 0;
+	return kvm_x86_ops.is_valid_cr4(vcpu, cr4);
+}
+EXPORT_SYMBOL_GPL(kvm_is_valid_cr4);
+
+void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4)
+{
+	unsigned long mmu_role_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+				      X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
+
+	if (((cr4 ^ old_cr4) & mmu_role_bits) ||
+	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
+		kvm_mmu_reset_context(vcpu);
 }
-EXPORT_SYMBOL_GPL(kvm_valid_cr4);
+EXPORT_SYMBOL_GPL(kvm_post_set_cr4);
 
 int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
 				   X86_CR4_SMEP;
-	unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;
 
-	if (kvm_valid_cr4(vcpu, cr4))
+	if (!kvm_is_valid_cr4(vcpu, cr4))
 		return 1;
 
 	if (is_long_mode(vcpu)) {
@@ -1006,15 +1030,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 			return 1;
 	}
 
-	if (kvm_x86_ops.set_cr4(vcpu, cr4))
-		return 1;
+	kvm_x86_ops.set_cr4(vcpu, cr4);
 
-	if (((cr4 ^ old_cr4) & mmu_role_bits) ||
-	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
-		kvm_mmu_reset_context(vcpu);
-
-	if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE))
-		kvm_update_cpuid_runtime(vcpu);
+	kvm_post_set_cr4(vcpu, old_cr4, cr4);
 
 	return 0;
 }
@@ -1638,27 +1656,20 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
 }
 EXPORT_SYMBOL_GPL(kvm_set_msr);
 
-static int complete_emulated_msr(struct kvm_vcpu *vcpu, bool is_read)
+static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->run->msr.error) {
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	} else if (is_read) {
+	int err = vcpu->run->msr.error;
+	if (!err) {
 		kvm_rax_write(vcpu, (u32)vcpu->run->msr.data);
 		kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32);
 	}
 
-	return kvm_skip_emulated_instruction(vcpu);
-}
-
-static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu)
-{
-	return complete_emulated_msr(vcpu, true);
+	return kvm_x86_ops.complete_emulated_msr(vcpu, err);
 }
 
 static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu)
 {
-	return complete_emulated_msr(vcpu, false);
+	return kvm_x86_ops.complete_emulated_msr(vcpu, vcpu->run->msr.error);
 }
 
 static u64 kvm_msr_reason(int r)
@@ -1721,18 +1732,16 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
-	/* MSR read failed? Inject a #GP */
-	if (r) {
+	if (!r) {
+		trace_kvm_msr_read(ecx, data);
+
+		kvm_rax_write(vcpu, data & -1u);
+		kvm_rdx_write(vcpu, (data >> 32) & -1u);
+	} else {
 		trace_kvm_msr_read_ex(ecx);
-		kvm_inject_gp(vcpu, 0);
-		return 1;
 	}
 
-	trace_kvm_msr_read(ecx, data);
-
-	kvm_rax_write(vcpu, data & -1u);
-	kvm_rdx_write(vcpu, (data >> 32) & -1u);
-	return kvm_skip_emulated_instruction(vcpu);
+	return kvm_x86_ops.complete_emulated_msr(vcpu, r);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr);
 
@@ -1753,15 +1762,12 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
 	if (r < 0)
 		return r;
 
-	/* MSR write failed? Inject a #GP */
-	if (r > 0) {
+	if (!r)
+		trace_kvm_msr_write(ecx, data);
+	else
 		trace_kvm_msr_write_ex(ecx, data);
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
 
-	trace_kvm_msr_write(ecx, data);
-	return kvm_skip_emulated_instruction(vcpu);
+	return kvm_x86_ops.complete_emulated_msr(vcpu, r);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr);
 
@@ -3678,6 +3684,27 @@ static inline bool kvm_can_mwait_in_guest(void)
 		boot_cpu_has(X86_FEATURE_ARAT);
 }
 
+static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
+					    struct kvm_cpuid2 __user *cpuid_arg)
+{
+	struct kvm_cpuid2 cpuid;
+	int r;
+
+	r = -EFAULT;
+	if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
+		return r;
+
+	r = kvm_get_hv_cpuid(vcpu, &cpuid, cpuid_arg->entries);
+	if (r)
+		return r;
+
+	r = -EFAULT;
+	if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
+		return r;
+
+	return 0;
+}
+
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r = 0;
@@ -3714,6 +3741,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_HYPERV_TLBFLUSH:
 	case KVM_CAP_HYPERV_SEND_IPI:
 	case KVM_CAP_HYPERV_CPUID:
+	case KVM_CAP_SYS_HYPERV_CPUID:
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -3762,7 +3790,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 * fringe case that is not enabled except via specific settings
 		 * of the module parameters.
 		 */
-		r = kvm_x86_ops.has_emulated_msr(MSR_IA32_SMBASE);
+		r = kvm_x86_ops.has_emulated_msr(kvm, MSR_IA32_SMBASE);
 		break;
 	case KVM_CAP_VAPIC:
 		r = !kvm_x86_ops.cpu_has_accelerated_tpr();
@@ -3899,6 +3927,9 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	case KVM_GET_MSRS:
 		r = msr_io(NULL, argp, do_get_msr_feature, 1);
 		break;
+	case KVM_GET_SUPPORTED_HV_CPUID:
+		r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -3997,7 +4028,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	int idx;
 
-	if (vcpu->preempted)
+	if (vcpu->preempted && !vcpu->arch.guest_state_protected)
 		vcpu->arch.preempted_in_kernel = !kvm_x86_ops.get_cpl(vcpu);
 
 	/*
@@ -4481,6 +4512,9 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
+	if (!vcpu->arch.guest_fpu)
+		return;
+
 	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		memset(guest_xsave, 0, sizeof(struct kvm_xsave));
 		fill_xsave((u8 *) guest_xsave->region, vcpu);
@@ -4498,9 +4532,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
-	u64 xstate_bv =
-		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
-	u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
+	u64 xstate_bv;
+	u32 mxcsr;
+
+	if (!vcpu->arch.guest_fpu)
+		return 0;
+
+	xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+	mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
 
 	if (boot_cpu_has(X86_FEATURE_XSAVE)) {
 		/*
@@ -4977,25 +5016,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
-	case KVM_GET_SUPPORTED_HV_CPUID: {
-		struct kvm_cpuid2 __user *cpuid_arg = argp;
-		struct kvm_cpuid2 cpuid;
-
-		r = -EFAULT;
-		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
-			goto out;
-
-		r = kvm_vcpu_ioctl_get_hv_cpuid(vcpu, &cpuid,
-						cpuid_arg->entries);
-		if (r)
-			goto out;
-
-		r = -EFAULT;
-		if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
-			goto out;
-		r = 0;
+	case KVM_GET_SUPPORTED_HV_CPUID:
+		r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp);
 		break;
-	}
 	default:
 		r = -EINVAL;
 	}
@@ -5776,7 +5799,7 @@ static void kvm_init_msr_list(void)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) {
-		if (!kvm_x86_ops.has_emulated_msr(emulated_msrs_all[i]))
+		if (!kvm_x86_ops.has_emulated_msr(NULL, emulated_msrs_all[i]))
 			continue;
 
 		emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
@@ -7953,17 +7976,22 @@ void kvm_arch_exit(void)
 	kmem_cache_destroy(x86_fpu_cache);
 }
 
-int kvm_vcpu_halt(struct kvm_vcpu *vcpu)
+static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason)
 {
 	++vcpu->stat.halt_exits;
 	if (lapic_in_kernel(vcpu)) {
-		vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+		vcpu->arch.mp_state = state;
 		return 1;
 	} else {
-		vcpu->run->exit_reason = KVM_EXIT_HLT;
+		vcpu->run->exit_reason = reason;
 		return 0;
 	}
 }
+
+int kvm_vcpu_halt(struct kvm_vcpu *vcpu)
+{
+	return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT);
+}
 EXPORT_SYMBOL_GPL(kvm_vcpu_halt);
 
 int kvm_emulate_halt(struct kvm_vcpu *vcpu)
@@ -7977,6 +8005,14 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
+int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu)
+{
+	int ret = kvm_skip_emulated_instruction(vcpu);
+
+	return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret;
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold);
+
 #ifdef CONFIG_X86_64
 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,
 			        unsigned long clock_type)
@@ -8158,7 +8194,14 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *kvm_run = vcpu->run;
 
-	kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
+	/*
+	 * if_flag is obsolete and useless, so do not bother
+	 * setting it for SEV-ES guests.  Userspace can just
+	 * use kvm_run->ready_for_interrupt_injection.
+	 */
+	kvm_run->if_flag = !vcpu->arch.guest_state_protected
+		&& (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
+
 	kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0;
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
@@ -8748,9 +8791,20 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	bool req_immediate_exit = false;
 
+	/* Forbid vmenter if vcpu dirty ring is soft-full */
+	if (unlikely(vcpu->kvm->dirty_ring_size &&
+		     kvm_dirty_ring_soft_full(&vcpu->dirty_ring))) {
+		vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL;
+		trace_kvm_dirty_ring_exit(vcpu);
+		r = 0;
+		goto out;
+	}
+
 	if (kvm_request_pending(vcpu)) {
 		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
-			if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
+			if (WARN_ON_ONCE(!is_guest_mode(vcpu)))
+				;
+			else if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
 				r = 0;
 				goto out;
 			}
@@ -9055,6 +9109,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 	kvm_apic_accept_events(vcpu);
 	switch(vcpu->arch.mp_state) {
 	case KVM_MP_STATE_HALTED:
+	case KVM_MP_STATE_AP_RESET_HOLD:
 		vcpu->arch.pv.pv_unhalted = false;
 		vcpu->arch.mp_state =
 			KVM_MP_STATE_RUNNABLE;
@@ -9223,9 +9278,14 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 
 	kvm_save_current_fpu(vcpu->arch.user_fpu);
 
-	/* PKRU is separately restored in kvm_x86_ops.run.  */
-	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
-				~XFEATURE_MASK_PKRU);
+	/*
+	 * Guests with protected state can't have it set by the hypervisor,
+	 * so skip trying to set it.
+	 */
+	if (vcpu->arch.guest_fpu)
+		/* PKRU is separately restored in kvm_x86_ops.run. */
+		__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
+					~XFEATURE_MASK_PKRU);
 
 	fpregs_mark_activate();
 	fpregs_unlock();
@@ -9238,7 +9298,12 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	kvm_save_current_fpu(vcpu->arch.guest_fpu);
+	/*
+	 * Guests with protected state can't have it read by the hypervisor,
+	 * so skip trying to save it.
+	 */
+	if (vcpu->arch.guest_fpu)
+		kvm_save_current_fpu(vcpu->arch.guest_fpu);
 
 	copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
 
@@ -9417,6 +9482,9 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct desc_ptr dt;
 
+	if (vcpu->arch.guest_state_protected)
+		goto skip_protected_regs;
+
 	kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
 	kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
 	kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES);
@@ -9434,9 +9502,11 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->gdt.limit = dt.size;
 	sregs->gdt.base = dt.address;
 
-	sregs->cr0 = kvm_read_cr0(vcpu);
 	sregs->cr2 = vcpu->arch.cr2;
 	sregs->cr3 = kvm_read_cr3(vcpu);
+
+skip_protected_regs:
+	sregs->cr0 = kvm_read_cr0(vcpu);
 	sregs->cr4 = kvm_read_cr4(vcpu);
 	sregs->cr8 = kvm_get_cr8(vcpu);
 	sregs->efer = vcpu->arch.efer;
@@ -9466,8 +9536,9 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 		kvm_load_guest_fpu(vcpu);
 
 	kvm_apic_accept_events(vcpu);
-	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
-					vcpu->arch.pv.pv_unhalted)
+	if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED ||
+	     vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) &&
+	    vcpu->arch.pv.pv_unhalted)
 		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
 	else
 		mp_state->mp_state = vcpu->arch.mp_state;
@@ -9535,7 +9606,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
 }
 EXPORT_SYMBOL_GPL(kvm_task_switch);
 
-static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
 		/*
@@ -9543,31 +9614,29 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		 * 64-bit mode (though maybe in a 32-bit code segment).
 		 * CR4.PAE and EFER.LMA must be set.
 		 */
-		if (!(sregs->cr4 & X86_CR4_PAE)
-		    || !(sregs->efer & EFER_LMA))
-			return -EINVAL;
+		if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA))
+			return false;
 	} else {
 		/*
 		 * Not in 64-bit mode: EFER.LMA is clear and the code
 		 * segment cannot be 64-bit.
 		 */
 		if (sregs->efer & EFER_LMA || sregs->cs.l)
-			return -EINVAL;
+			return false;
 	}
 
-	return kvm_valid_cr4(vcpu, sregs->cr4);
+	return kvm_is_valid_cr4(vcpu, sregs->cr4);
 }
 
 static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
 	struct msr_data apic_base_msr;
 	int mmu_reset_needed = 0;
-	int cpuid_update_needed = 0;
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
 	int ret = -EINVAL;
 
-	if (kvm_valid_sregs(vcpu, sregs))
+	if (!kvm_is_valid_sregs(vcpu, sregs))
 		goto out;
 
 	apic_base_msr.data = sregs->apic_base;
@@ -9575,6 +9644,9 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	if (kvm_set_apic_base(vcpu, &apic_base_msr))
 		goto out;
 
+	if (vcpu->arch.guest_state_protected)
+		goto skip_protected_regs;
+
 	dt.size = sregs->idt.limit;
 	dt.address = sregs->idt.base;
 	kvm_x86_ops.set_idt(vcpu, &dt);
@@ -9597,11 +9669,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	vcpu->arch.cr0 = sregs->cr0;
 
 	mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
-	cpuid_update_needed |= ((kvm_read_cr4(vcpu) ^ sregs->cr4) &
-				(X86_CR4_OSXSAVE | X86_CR4_PKE));
 	kvm_x86_ops.set_cr4(vcpu, sregs->cr4);
-	if (cpuid_update_needed)
-		kvm_update_cpuid_runtime(vcpu);
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	if (is_pae_paging(vcpu)) {
@@ -9613,14 +9681,6 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	if (mmu_reset_needed)
 		kvm_mmu_reset_context(vcpu);
 
-	max_bits = KVM_NR_INTERRUPTS;
-	pending_vec = find_first_bit(
-		(const unsigned long *)sregs->interrupt_bitmap, max_bits);
-	if (pending_vec < max_bits) {
-		kvm_queue_interrupt(vcpu, pending_vec, false);
-		pr_debug("Set back pending irq %d\n", pending_vec);
-	}
-
 	kvm_set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
 	kvm_set_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
 	kvm_set_segment(vcpu, &sregs->es, VCPU_SREG_ES);
@@ -9639,6 +9699,15 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	    !is_protmode(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
+skip_protected_regs:
+	max_bits = KVM_NR_INTERRUPTS;
+	pending_vec = find_first_bit(
+		(const unsigned long *)sregs->interrupt_bitmap, max_bits);
+	if (pending_vec < max_bits) {
+		kvm_queue_interrupt(vcpu, pending_vec, false);
+		pr_debug("Set back pending irq %d\n", pending_vec);
+	}
+
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	ret = 0;
@@ -9663,6 +9732,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	unsigned long rflags;
 	int i, r;
 
+	if (vcpu->arch.guest_state_protected)
+		return -EINVAL;
+
 	vcpu_load(vcpu);
 
 	if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) {
@@ -9742,6 +9814,9 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	struct fxregs_state *fxsave;
 
+	if (!vcpu->arch.guest_fpu)
+		return 0;
+
 	vcpu_load(vcpu);
 
 	fxsave = &vcpu->arch.guest_fpu->state.fxsave;
@@ -9762,6 +9837,9 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	struct fxregs_state *fxsave;
 
+	if (!vcpu->arch.guest_fpu)
+		return 0;
+
 	vcpu_load(vcpu);
 
 	fxsave = &vcpu->arch.guest_fpu->state.fxsave;
@@ -9820,6 +9898,9 @@ static int sync_regs(struct kvm_vcpu *vcpu)
 
 static void fx_init(struct kvm_vcpu *vcpu)
 {
+	if (!vcpu->arch.guest_fpu)
+		return;
+
 	fpstate_init(&vcpu->arch.guest_fpu->state);
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		vcpu->arch.guest_fpu->state.xsave.header.xcomp_bv =
@@ -9833,6 +9914,15 @@ static void fx_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr0 |= X86_CR0_ET;
 }
 
+void kvm_free_guest_fpu(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.guest_fpu) {
+		kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu);
+		vcpu->arch.guest_fpu = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(kvm_free_guest_fpu);
+
 int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 {
 	if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
@@ -9928,7 +10018,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	return 0;
 
 free_guest_fpu:
-	kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu);
+	kvm_free_guest_fpu(vcpu);
 free_user_fpu:
 	kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu);
 free_emulate_ctxt:
@@ -9982,7 +10072,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
 	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
 	kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu);
-	kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu);
+	kvm_free_guest_fpu(vcpu);
 
 	kvm_hv_vcpu_uninit(vcpu);
 	kvm_pmu_destroy(vcpu);
@@ -10030,7 +10120,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	kvm_async_pf_hash_reset(vcpu);
 	vcpu->arch.apf.halted = false;
 
-	if (kvm_mpx_supported()) {
+	if (vcpu->arch.guest_fpu && kvm_mpx_supported()) {
 		void *mpx_state_buffer;
 
 		/*
@@ -10079,6 +10169,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 	kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
 	kvm_rip_write(vcpu, 0);
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector);
 
 int kvm_arch_hardware_enable(void)
 {
@@ -10349,7 +10440,32 @@ void kvm_arch_sync_events(struct kvm *kvm)
 	kvm_free_pit(kvm);
 }
 
-int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
+#define  ERR_PTR_USR(e)  ((void __user *)ERR_PTR(e))
+
+/**
+ * __x86_set_memory_region: Setup KVM internal memory slot
+ *
+ * @kvm: the kvm pointer to the VM.
+ * @id: the slot ID to setup.
+ * @gpa: the GPA to install the slot (unused when @size == 0).
+ * @size: the size of the slot. Set to zero to uninstall a slot.
+ *
+ * This function helps to setup a KVM internal memory slot.  Specify
+ * @size > 0 to install a new slot, while @size == 0 to uninstall a
+ * slot.  The return code can be one of the following:
+ *
+ *   HVA:           on success (uninstall will return a bogus HVA)
+ *   -errno:        on error
+ *
+ * The caller should always use IS_ERR() to check the return value
+ * before use.  Note, the KVM internal memory slots are guaranteed to
+ * remain valid and unchanged until the VM is destroyed, i.e., the
+ * GPA->HVA translation will not change.  However, the HVA is a user
+ * address, i.e. its accessibility is not guaranteed, and must be
+ * accessed via __copy_{to,from}_user().
+ */
+void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
+				      u32 size)
 {
 	int i, r;
 	unsigned long hva, old_npages;
@@ -10358,12 +10474,12 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 
 	/* Called with kvm->slots_lock held.  */
 	if (WARN_ON(id >= KVM_MEM_SLOTS_NUM))
-		return -EINVAL;
+		return ERR_PTR_USR(-EINVAL);
 
 	slot = id_to_memslot(slots, id);
 	if (size) {
 		if (slot && slot->npages)
-			return -EEXIST;
+			return ERR_PTR_USR(-EEXIST);
 
 		/*
 		 * MAP_SHARED to prevent internal slot pages from being moved
@@ -10372,7 +10488,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 		hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE,
 			      MAP_SHARED | MAP_ANONYMOUS, 0);
 		if (IS_ERR((void *)hva))
-			return PTR_ERR((void *)hva);
+			return (void __user *)hva;
 	} else {
 		if (!slot || !slot->npages)
 			return 0;
@@ -10391,13 +10507,13 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 		m.memory_size = size;
 		r = __kvm_set_memory_region(kvm, &m);
 		if (r < 0)
-			return r;
+			return ERR_PTR_USR(r);
 	}
 
 	if (!size)
 		vm_munmap(hva, old_npages * PAGE_SIZE);
 
-	return 0;
+	return (void __user *)hva;
 }
 EXPORT_SYMBOL_GPL(__x86_set_memory_region);
 
@@ -10754,6 +10870,10 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
 
 unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu)
 {
+	/* Can't read the RIP when guest state is protected, just return 0 */
+	if (vcpu->arch.guest_state_protected)
+		return 0;
+
 	if (is_64_bit_mode(vcpu))
 		return kvm_rip_read(vcpu);
 	return (u32)(get_segment_base(vcpu, VCPU_SREG_CS) +
@@ -11263,6 +11383,179 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva)
 }
 EXPORT_SYMBOL_GPL(kvm_handle_invpcid);
 
+static int complete_sev_es_emulated_mmio(struct kvm_vcpu *vcpu)
+{
+	struct kvm_run *run = vcpu->run;
+	struct kvm_mmio_fragment *frag;
+	unsigned int len;
+
+	BUG_ON(!vcpu->mmio_needed);
+
+	/* Complete previous fragment */
+	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment];
+	len = min(8u, frag->len);
+	if (!vcpu->mmio_is_write)
+		memcpy(frag->data, run->mmio.data, len);
+
+	if (frag->len <= 8) {
+		/* Switch to the next fragment. */
+		frag++;
+		vcpu->mmio_cur_fragment++;
+	} else {
+		/* Go forward to the next mmio piece. */
+		frag->data += len;
+		frag->gpa += len;
+		frag->len -= len;
+	}
+
+	if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
+		vcpu->mmio_needed = 0;
+
+		// VMG change, at this point, we're always done
+		// RIP has already been advanced
+		return 1;
+	}
+
+	// More MMIO is needed
+	run->mmio.phys_addr = frag->gpa;
+	run->mmio.len = min(8u, frag->len);
+	run->mmio.is_write = vcpu->mmio_is_write;
+	if (run->mmio.is_write)
+		memcpy(run->mmio.data, frag->data, min(8u, frag->len));
+	run->exit_reason = KVM_EXIT_MMIO;
+
+	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;
+
+	return 0;
+}
+
+int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes,
+			  void *data)
+{
+	int handled;
+	struct kvm_mmio_fragment *frag;
+
+	if (!data)
+		return -EINVAL;
+
+	handled = write_emultor.read_write_mmio(vcpu, gpa, bytes, data);
+	if (handled == bytes)
+		return 1;
+
+	bytes -= handled;
+	gpa += handled;
+	data += handled;
+
+	/*TODO: Check if need to increment number of frags */
+	frag = vcpu->mmio_fragments;
+	vcpu->mmio_nr_fragments = 1;
+	frag->len = bytes;
+	frag->gpa = gpa;
+	frag->data = data;
+
+	vcpu->mmio_needed = 1;
+	vcpu->mmio_cur_fragment = 0;
+
+	vcpu->run->mmio.phys_addr = gpa;
+	vcpu->run->mmio.len = min(8u, frag->len);
+	vcpu->run->mmio.is_write = 1;
+	memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len));
+	vcpu->run->exit_reason = KVM_EXIT_MMIO;
+
+	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_write);
+
+int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes,
+			 void *data)
+{
+	int handled;
+	struct kvm_mmio_fragment *frag;
+
+	if (!data)
+		return -EINVAL;
+
+	handled = read_emultor.read_write_mmio(vcpu, gpa, bytes, data);
+	if (handled == bytes)
+		return 1;
+
+	bytes -= handled;
+	gpa += handled;
+	data += handled;
+
+	/*TODO: Check if need to increment number of frags */
+	frag = vcpu->mmio_fragments;
+	vcpu->mmio_nr_fragments = 1;
+	frag->len = bytes;
+	frag->gpa = gpa;
+	frag->data = data;
+
+	vcpu->mmio_needed = 1;
+	vcpu->mmio_cur_fragment = 0;
+
+	vcpu->run->mmio.phys_addr = gpa;
+	vcpu->run->mmio.len = min(8u, frag->len);
+	vcpu->run->mmio.is_write = 0;
+	vcpu->run->exit_reason = KVM_EXIT_MMIO;
+
+	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_mmio;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read);
+
+static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
+{
+	memcpy(vcpu->arch.guest_ins_data, vcpu->arch.pio_data,
+	       vcpu->arch.pio.count * vcpu->arch.pio.size);
+	vcpu->arch.pio.count = 0;
+
+	return 1;
+}
+
+static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
+			   unsigned int port, void *data,  unsigned int count)
+{
+	int ret;
+
+	ret = emulator_pio_out_emulated(vcpu->arch.emulate_ctxt, size, port,
+					data, count);
+	if (ret)
+		return ret;
+
+	vcpu->arch.pio.count = 0;
+
+	return 0;
+}
+
+static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
+			  unsigned int port, void *data, unsigned int count)
+{
+	int ret;
+
+	ret = emulator_pio_in_emulated(vcpu->arch.emulate_ctxt, size, port,
+				       data, count);
+	if (ret) {
+		vcpu->arch.pio.count = 0;
+	} else {
+		vcpu->arch.guest_ins_data = data;
+		vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins;
+	}
+
+	return 0;
+}
+
+int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size,
+			 unsigned int port, void *data,  unsigned int count,
+			 int in)
+{
+	return in ? kvm_sev_es_ins(vcpu, size, port, data, count)
+		  : kvm_sev_es_outs(vcpu, size, port, data, count);
+}
+EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
@@ -11285,3 +11578,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_apicv_update_request);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index e7ca622a468f..c5ee0f5ce0f1 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -3,6 +3,7 @@
 #define ARCH_X86_KVM_X86_H
 
 #include <linux/kvm_host.h>
+#include <asm/mce.h>
 #include <asm/pvclock.h>
 #include "kvm_cache_regs.h"
 #include "kvm_emulate.h"
@@ -278,6 +279,7 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);
 
 extern u64 host_xcr0;
 extern u64 supported_xcr0;
+extern u64 host_xss;
 extern u64 supported_xss;
 
 static inline bool kvm_mpx_supported(void)
@@ -366,10 +368,29 @@ static inline bool kvm_dr6_valid(u64 data)
 	return !(data >> 32);
 }
 
+/*
+ * Trigger machine check on the host. We assume all the MSRs are already set up
+ * by the CPU and that we still run on the same CPU as the MCE occurred on.
+ * We pass a fake environment to the machine check handler because we want
+ * the guest to be always treated like user space, no matter what context
+ * it used internally.
+ */
+static inline void kvm_machine_check(void)
+{
+#if defined(CONFIG_X86_MCE)
+	struct pt_regs regs = {
+		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
+		.flags = X86_EFLAGS_IF,
+	};
+
+	do_machine_check(&regs);
+#endif
+}
+
 void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu);
 void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu);
 int kvm_spec_ctrl_test_value(u64 value);
-int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
+bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
 bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu);
 int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
 			      struct x86_exception *e);
@@ -407,4 +428,12 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type);
 	__reserved_bits;                                \
 })
 
+int kvm_sev_es_mmio_write(struct kvm_vcpu *vcpu, gpa_t src, unsigned int bytes,
+			  void *dst);
+int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t src, unsigned int bytes,
+			 void *dst);
+int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size,
+			 unsigned int port, void *data,  unsigned int count,
+			 int in);
+
 #endif
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index dfd82f51ba66..f6a9e2e36642 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -829,6 +829,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 	}
 
 	free_page((unsigned long)pmd_sv);
+
+	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	free_page((unsigned long)pmd);
 
 	return 1;
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index 205a9bc981b0..7d7ffb9c826a 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -93,37 +93,22 @@ static efi_system_table_t __init *xen_efi_probe(void)
 
 /*
  * Determine whether we're in secure boot mode.
- *
- * Please keep the logic in sync with
- * drivers/firmware/efi/libstub/secureboot.c:efi_get_secureboot().
  */
 static enum efi_secureboot_mode xen_efi_get_secureboot(void)
 {
-	static efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
 	static efi_guid_t shim_guid = EFI_SHIM_LOCK_GUID;
+	enum efi_secureboot_mode mode;
 	efi_status_t status;
-	u8 moksbstate, secboot, setupmode;
+	u8 moksbstate;
 	unsigned long size;
 
-	size = sizeof(secboot);
-	status = efi.get_variable(L"SecureBoot", &efi_variable_guid,
-				  NULL, &size, &secboot);
-
-	if (status == EFI_NOT_FOUND)
-		return efi_secureboot_mode_disabled;
-
-	if (status != EFI_SUCCESS)
-		goto out_efi_err;
-
-	size = sizeof(setupmode);
-	status = efi.get_variable(L"SetupMode", &efi_variable_guid,
-				  NULL, &size, &setupmode);
-
-	if (status != EFI_SUCCESS)
-		goto out_efi_err;
-
-	if (secboot == 0 || setupmode == 1)
-		return efi_secureboot_mode_disabled;
+	mode = efi_get_secureboot_mode(efi.get_variable);
+	if (mode == efi_secureboot_mode_unknown) {
+		pr_err("Could not determine UEFI Secure Boot status.\n");
+		return efi_secureboot_mode_unknown;
+	}
+	if (mode != efi_secureboot_mode_enabled)
+		return mode;
 
 	/* See if a user has put the shim into insecure mode. */
 	size = sizeof(moksbstate);
@@ -140,10 +125,6 @@ static enum efi_secureboot_mode xen_efi_get_secureboot(void)
  secure_boot_enabled:
 	pr_info("UEFI Secure Boot is enabled.\n");
 	return efi_secureboot_mode_enabled;
-
- out_efi_err:
-	pr_err("Could not determine UEFI Secure Boot status.\n");
-	return efi_secureboot_mode_unknown;
 }
 
 void __init xen_efi_init(struct boot_params *boot_params)
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 9e87ab010c82..e68ea5f4ad1c 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -164,10 +164,10 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu)
 	else
 		per_cpu(xen_vcpu_id, cpu) = cpu;
 	rc = xen_vcpu_setup(cpu);
-	if (rc)
+	if (rc || !xen_have_vector_callback)
 		return rc;
 
-	if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock))
+	if (xen_feature(XENFEAT_hvm_safe_pvclock))
 		xen_setup_timer(cpu);
 
 	rc = xen_smp_intr_init(cpu);
@@ -188,6 +188,8 @@ static int xen_cpu_dead_hvm(unsigned int cpu)
        return 0;
 }
 
+static bool no_vector_callback __initdata;
+
 static void __init xen_hvm_guest_init(void)
 {
 	if (xen_pv_domain())
@@ -207,7 +209,7 @@ static void __init xen_hvm_guest_init(void)
 
 	xen_panic_handler_init();
 
-	if (xen_feature(XENFEAT_hvm_callback_vector))
+	if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector))
 		xen_have_vector_callback = 1;
 
 	xen_hvm_smp_init();
@@ -233,6 +235,13 @@ static __init int xen_parse_nopv(char *arg)
 }
 early_param("xen_nopv", xen_parse_nopv);
 
+static __init int xen_parse_no_vector_callback(char *arg)
+{
+	no_vector_callback = true;
+	return 0;
+}
+early_param("xen_no_vector_callback", xen_parse_no_vector_callback);
+
 bool __init xen_hvm_need_lapic(void)
 {
 	if (xen_pv_domain())
diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c
index f5e7db4f82ab..056430a1080b 100644
--- a/arch/x86/xen/smp_hvm.c
+++ b/arch/x86/xen/smp_hvm.c
@@ -33,9 +33,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 	int cpu;
 
 	native_smp_prepare_cpus(max_cpus);
-	WARN_ON(xen_smp_intr_init(0));
 
-	xen_init_lock_cpu(0);
+	if (xen_have_vector_callback) {
+		WARN_ON(xen_smp_intr_init(0));
+		xen_init_lock_cpu(0);
+	}
 
 	for_each_possible_cpu(cpu) {
 		if (cpu == 0)
@@ -50,9 +52,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 static void xen_hvm_cpu_die(unsigned int cpu)
 {
 	if (common_cpu_die(cpu) == 0) {
-		xen_smp_intr_free(cpu);
-		xen_uninit_lock_cpu(cpu);
-		xen_teardown_timer(cpu);
+		if (xen_have_vector_callback) {
+			xen_smp_intr_free(cpu);
+			xen_uninit_lock_cpu(cpu);
+			xen_teardown_timer(cpu);
+		}
 	}
 }
 #else
@@ -64,14 +68,17 @@ static void xen_hvm_cpu_die(unsigned int cpu)
 
 void __init xen_hvm_smp_init(void)
 {
-	if (!xen_have_vector_callback)
+	smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
+	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
+	smp_ops.smp_cpus_done = xen_smp_cpus_done;
+	smp_ops.cpu_die = xen_hvm_cpu_die;
+
+	if (!xen_have_vector_callback) {
+		nopvspin = true;
 		return;
+	}
 
-	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
 	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
-	smp_ops.cpu_die = xen_hvm_cpu_die;
 	smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
 	smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
-	smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
-	smp_ops.smp_cpus_done = xen_smp_cpus_done;
 }
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 9718e9593564..854c5e07e867 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -2,7 +2,6 @@
 generated-y += syscall_table.h
 generic-y += extable.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += param.h
 generic-y += qrwlock.h
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 77971fe4cc95..e8ceb1528608 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -13,7 +13,7 @@
  */
 
 #include <linux/clk.h>
-#include <linux/clk-provider.h>
+#include <linux/of_clk.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/time.h>
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 9e81d1052091..9e4eb0fc1c16 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -6332,13 +6332,13 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd,
 	 * limit 'something'.
 	 */
 	/* no more than 50% of tags for async I/O */
-	bfqd->word_depths[0][0] = max((1U << bt->sb.shift) >> 1, 1U);
+	bfqd->word_depths[0][0] = max(bt->sb.depth >> 1, 1U);
 	/*
 	 * no more than 75% of tags for sync writes (25% extra tags
 	 * w.r.t. async I/O, to prevent async I/O from starving sync
 	 * writes)
 	 */
-	bfqd->word_depths[0][1] = max(((1U << bt->sb.shift) * 3) >> 2, 1U);
+	bfqd->word_depths[0][1] = max((bt->sb.depth * 3) >> 2, 1U);
 
 	/*
 	 * In-word depths in case some bfq_queue is being weight-
@@ -6348,9 +6348,9 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd,
 	 * shortage.
 	 */
 	/* no more than ~18% of tags for async I/O */
-	bfqd->word_depths[1][0] = max(((1U << bt->sb.shift) * 3) >> 4, 1U);
+	bfqd->word_depths[1][0] = max((bt->sb.depth * 3) >> 4, 1U);
 	/* no more than ~37% of tags for sync writes (~20% extra tags) */
-	bfqd->word_depths[1][1] = max(((1U << bt->sb.shift) * 6) >> 4, 1U);
+	bfqd->word_depths[1][1] = max((bt->sb.depth * 6) >> 4, 1U);
 
 	for (i = 0; i < 2; i++)
 		for (j = 0; j < 2; j++)
diff --git a/block/blk-core.c b/block/blk-core.c
index 96e5fcd7f071..7663a9b94b80 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -18,6 +18,7 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/blk-mq.h>
+#include <linux/blk-pm.h>
 #include <linux/highmem.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
@@ -424,11 +425,11 @@ EXPORT_SYMBOL(blk_cleanup_queue);
 /**
  * blk_queue_enter() - try to increase q->q_usage_counter
  * @q: request queue pointer
- * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PREEMPT
+ * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM
  */
 int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 {
-	const bool pm = flags & BLK_MQ_REQ_PREEMPT;
+	const bool pm = flags & BLK_MQ_REQ_PM;
 
 	while (true) {
 		bool success = false;
@@ -440,7 +441,8 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 			 * responsible for ensuring that that counter is
 			 * globally visible before the queue is unfrozen.
 			 */
-			if (pm || !blk_queue_pm_only(q)) {
+			if ((pm && queue_rpm_status(q) != RPM_SUSPENDED) ||
+			    !blk_queue_pm_only(q)) {
 				success = true;
 			} else {
 				percpu_ref_put(&q->q_usage_counter);
@@ -465,8 +467,7 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 
 		wait_event(q->mq_freeze_wq,
 			   (!q->mq_freeze_depth &&
-			    (pm || (blk_pm_request_resume(q),
-				    !blk_queue_pm_only(q)))) ||
+			    blk_pm_resume_queue(pm, q)) ||
 			   blk_queue_dying(q));
 		if (blk_queue_dying(q))
 			return -ENODEV;
@@ -630,7 +631,7 @@ struct request *blk_get_request(struct request_queue *q, unsigned int op,
 	struct request *req;
 
 	WARN_ON_ONCE(op & REQ_NOWAIT);
-	WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PREEMPT));
+	WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM));
 
 	req = blk_mq_alloc_request(q, op, flags);
 	if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index ffa418c0dcb1..98d656bdb42b 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2185,6 +2185,9 @@ static int ioc_check_iocgs(struct ioc *ioc, struct ioc_now *now)
 							    WEIGHT_ONE);
 			}
 
+			TRACE_IOCG_PATH(iocg_idle, iocg, now,
+					atomic64_read(&iocg->active_period),
+					atomic64_read(&ioc->cur_period), vtime);
 			__propagate_weights(iocg, 0, 0, false, now);
 			list_del_init(&iocg->active_list);
 		}
@@ -2548,8 +2551,8 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio)
 	bool use_debt, ioc_locked;
 	unsigned long flags;
 
-	/* bypass IOs if disabled or for root cgroup */
-	if (!ioc->enabled || !iocg->level)
+	/* bypass IOs if disabled, still initializing, or for root cgroup */
+	if (!ioc->enabled || !iocg || !iocg->level)
 		return;
 
 	/* calculate the absolute vtime cost */
@@ -2676,14 +2679,14 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq,
 			   struct bio *bio)
 {
 	struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg);
-	struct ioc *ioc = iocg->ioc;
+	struct ioc *ioc = rqos_to_ioc(rqos);
 	sector_t bio_end = bio_end_sector(bio);
 	struct ioc_now now;
 	u64 vtime, abs_cost, cost;
 	unsigned long flags;
 
-	/* bypass if disabled or for root cgroup */
-	if (!ioc->enabled || !iocg->level)
+	/* bypass if disabled, still initializing, or for root cgroup */
+	if (!ioc->enabled || !iocg || !iocg->level)
 		return;
 
 	abs_cost = calc_vtime_cost(bio, iocg, true);
@@ -2860,6 +2863,12 @@ static int blk_iocost_init(struct request_queue *q)
 	ioc_refresh_params(ioc, true);
 	spin_unlock_irq(&ioc->lock);
 
+	/*
+	 * rqos must be added before activation to allow iocg_pd_init() to
+	 * lookup the ioc from q. This means that the rqos methods may get
+	 * called before policy activation completion, can't assume that the
+	 * target bio has an iocg associated and need to test for NULL iocg.
+	 */
 	rq_qos_add(q, rqos);
 	ret = blkcg_activate_policy(q, &blkcg_policy_iocost);
 	if (ret) {
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 3094542e12ae..4de03da9a624 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -129,6 +129,7 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(PCI_P2PDMA),
 	QUEUE_FLAG_NAME(ZONE_RESETALL),
 	QUEUE_FLAG_NAME(RQ_ALLOC_TIME),
+	QUEUE_FLAG_NAME(NOWAIT),
 };
 #undef QUEUE_FLAG_NAME
 
@@ -245,6 +246,7 @@ static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(BLOCKING),
 	HCTX_FLAG_NAME(NO_SCHED),
 	HCTX_FLAG_NAME(STACKING),
+	HCTX_FLAG_NAME(TAG_HCTX_SHARED),
 };
 #undef HCTX_FLAG_NAME
 
@@ -297,7 +299,6 @@ static const char *const rqf_name[] = {
 	RQF_NAME(MIXED_MERGE),
 	RQF_NAME(MQ_INFLIGHT),
 	RQF_NAME(DONTPREP),
-	RQF_NAME(PREEMPT),
 	RQF_NAME(FAILED),
 	RQF_NAME(QUIET),
 	RQF_NAME(ELVPRIV),
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b09ce00cc6af..f285a9123a8b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -294,8 +294,8 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	rq->mq_hctx = data->hctx;
 	rq->rq_flags = 0;
 	rq->cmd_flags = data->cmd_flags;
-	if (data->flags & BLK_MQ_REQ_PREEMPT)
-		rq->rq_flags |= RQF_PREEMPT;
+	if (data->flags & BLK_MQ_REQ_PM)
+		rq->rq_flags |= RQF_PM;
 	if (blk_queue_io_stat(data->q))
 		rq->rq_flags |= RQF_IO_STAT;
 	INIT_LIST_HEAD(&rq->queuelist);
@@ -650,6 +650,14 @@ static inline bool blk_mq_complete_need_ipi(struct request *rq)
 	if (!IS_ENABLED(CONFIG_SMP) ||
 	    !test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags))
 		return false;
+	/*
+	 * With force threaded interrupts enabled, raising softirq from an SMP
+	 * function call will always result in waking the ksoftirqd thread.
+	 * This is probably worse than completing the request on a different
+	 * cache domain.
+	 */
+	if (force_irqthreads)
+		return false;
 
 	/* same CPU or cache domain?  Complete locally */
 	if (cpu == rq->mq_ctx->cpu ||
@@ -1496,31 +1504,6 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	int srcu_idx;
 
 	/*
-	 * We should be running this queue from one of the CPUs that
-	 * are mapped to it.
-	 *
-	 * There are at least two related races now between setting
-	 * hctx->next_cpu from blk_mq_hctx_next_cpu() and running
-	 * __blk_mq_run_hw_queue():
-	 *
-	 * - hctx->next_cpu is found offline in blk_mq_hctx_next_cpu(),
-	 *   but later it becomes online, then this warning is harmless
-	 *   at all
-	 *
-	 * - hctx->next_cpu is found online in blk_mq_hctx_next_cpu(),
-	 *   but later it becomes offline, then the warning can't be
-	 *   triggered, and we depend on blk-mq timeout handler to
-	 *   handle dispatched requests to this hctx
-	 */
-	if (!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
-		cpu_online(hctx->next_cpu)) {
-		printk(KERN_WARNING "run queue from wrong CPU %d, hctx %s\n",
-			raw_smp_processor_id(),
-			cpumask_empty(hctx->cpumask) ? "inactive": "active");
-		dump_stack();
-	}
-
-	/*
 	 * We can't run the queue inline with ints disabled. Ensure that
 	 * we catch bad users of this early.
 	 */
diff --git a/block/blk-pm.c b/block/blk-pm.c
index b85234d758f7..17bd020268d4 100644
--- a/block/blk-pm.c
+++ b/block/blk-pm.c
@@ -67,6 +67,10 @@ int blk_pre_runtime_suspend(struct request_queue *q)
 
 	WARN_ON_ONCE(q->rpm_status != RPM_ACTIVE);
 
+	spin_lock_irq(&q->queue_lock);
+	q->rpm_status = RPM_SUSPENDING;
+	spin_unlock_irq(&q->queue_lock);
+
 	/*
 	 * Increase the pm_only counter before checking whether any
 	 * non-PM blk_queue_enter() calls are in progress to avoid that any
@@ -89,15 +93,14 @@ int blk_pre_runtime_suspend(struct request_queue *q)
 	/* Switch q_usage_counter back to per-cpu mode. */
 	blk_mq_unfreeze_queue(q);
 
-	spin_lock_irq(&q->queue_lock);
-	if (ret < 0)
+	if (ret < 0) {
+		spin_lock_irq(&q->queue_lock);
+		q->rpm_status = RPM_ACTIVE;
 		pm_runtime_mark_last_busy(q->dev);
-	else
-		q->rpm_status = RPM_SUSPENDING;
-	spin_unlock_irq(&q->queue_lock);
+		spin_unlock_irq(&q->queue_lock);
 
-	if (ret)
 		blk_clear_pm_only(q);
+	}
 
 	return ret;
 }
diff --git a/block/blk-pm.h b/block/blk-pm.h
index ea5507d23e75..a2283cc9f716 100644
--- a/block/blk-pm.h
+++ b/block/blk-pm.h
@@ -6,11 +6,14 @@
 #include <linux/pm_runtime.h>
 
 #ifdef CONFIG_PM
-static inline void blk_pm_request_resume(struct request_queue *q)
+static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q)
 {
-	if (q->dev && (q->rpm_status == RPM_SUSPENDED ||
-		       q->rpm_status == RPM_SUSPENDING))
-		pm_request_resume(q->dev);
+	if (!q->dev || !blk_queue_pm_only(q))
+		return 1;	/* Nothing to do */
+	if (pm && q->rpm_status != RPM_SUSPENDED)
+		return 1;	/* Request allowed */
+	pm_request_resume(q->dev);
+	return 0;
 }
 
 static inline void blk_pm_mark_last_busy(struct request *rq)
@@ -44,8 +47,9 @@ static inline void blk_pm_put_request(struct request *rq)
 		--rq->q->nr_pending;
 }
 #else
-static inline void blk_pm_request_resume(struct request_queue *q)
+static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q)
 {
+	return 1;
 }
 
 static inline void blk_pm_mark_last_busy(struct request *rq)
diff --git a/block/genhd.c b/block/genhd.c
index b84b8671e627..419548e92d82 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  *  gendisk handling
+ *
+ * Portions Copyright (C) 2020 Christoph Hellwig
  */
 
 #include <linux/module.h>
@@ -244,15 +246,18 @@ struct block_device *disk_part_iter_next(struct disk_part_iter *piter)
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
+		piter->part = bdgrab(part);
+		if (!piter->part)
+			continue;
 		if (!bdev_nr_sectors(part) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
-		      piter->idx == 0))
+		      piter->idx == 0)) {
+			bdput(piter->part);
+			piter->part = NULL;
 			continue;
+		}
 
-		piter->part = bdgrab(part);
-		if (!piter->part)
-			continue;
 		piter->idx += inc;
 		break;
 	}
diff --git a/block/partitions/core.c b/block/partitions/core.c
index deca253583bd..e7d776db803b 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (C) 1991-1998  Linus Torvalds
  * Re-organised Feb 1998 Russell King
+ * Copyright (C) 2020 Christoph Hellwig
  */
 #include <linux/fs.h>
 #include <linux/slab.h>
diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c
index 511932aa94a6..0959613560b9 100644
--- a/crypto/asymmetric_keys/asym_tpm.c
+++ b/crypto/asymmetric_keys/asym_tpm.c
@@ -354,7 +354,7 @@ static uint32_t derive_pub_key(const void *pub_key, uint32_t len, uint8_t *buf)
 	memcpy(cur, e, sizeof(e));
 	cur += sizeof(e);
 	/* Zero parameters to satisfy set_pub_key ABI. */
-	memset(cur, 0, SETKEY_PARAMS_SIZE);
+	memzero_explicit(cur, SETKEY_PARAMS_SIZE);
 
 	return cur - buf;
 }
diff --git a/crypto/ecdh.c b/crypto/ecdh.c
index d56b8603dec9..96f80c8f8e30 100644
--- a/crypto/ecdh.c
+++ b/crypto/ecdh.c
@@ -39,7 +39,8 @@ static int ecdh_set_secret(struct crypto_kpp *tfm, const void *buf,
 	struct ecdh params;
 	unsigned int ndigits;
 
-	if (crypto_ecdh_decode_key(buf, len, &params) < 0)
+	if (crypto_ecdh_decode_key(buf, len, &params) < 0 ||
+	    params.key_size > sizeof(ctx->private_key))
 		return -EINVAL;
 
 	ndigits = ecdh_supported_curve(params.curve_id);
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index edf1558c1105..ebcf534514be 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -395,9 +395,6 @@ config ACPI_CONTAINER
 
 	  This helps support hotplug of nodes, CPUs, and memory.
 
-	  To compile this driver as a module, choose M here:
-	  the module will be called container.
-
 config ACPI_HOTPLUG_MEMORY
 	bool "Memory Hotplug"
 	depends on MEMORY_HOTPLUG
@@ -411,9 +408,6 @@ config ACPI_HOTPLUG_MEMORY
 	  removing memory devices at runtime, you need not enable
 	  this driver.
 
-	  To compile this driver as a module, choose M here:
-	  the module will be called acpi_memhotplug.
-
 config ACPI_HOTPLUG_IOAPIC
 	bool
 	depends on PCI
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 44e412506317..076894a3330f 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -54,6 +54,7 @@ acpi-y				+= property.o
 acpi-$(CONFIG_X86)		+= acpi_cmos_rtc.o
 acpi-$(CONFIG_X86)		+= x86/apple.o
 acpi-$(CONFIG_X86)		+= x86/utils.o
+acpi-$(CONFIG_X86)		+= x86/s2idle.o
 acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
 acpi-y				+= acpi_lpat.o
 acpi-$(CONFIG_ACPI_LPIT)	+= acpi_lpit.o
diff --git a/drivers/acpi/acpi_pnp.c b/drivers/acpi/acpi_pnp.c
index 4ed755a963aa..8f2dc176bb41 100644
--- a/drivers/acpi/acpi_pnp.c
+++ b/drivers/acpi/acpi_pnp.c
@@ -319,6 +319,9 @@ static bool matching_id(const char *idstr, const char *list_id)
 {
 	int i;
 
+	if (strlen(idstr) != strlen(list_id))
+		return false;
+
 	if (memcmp(idstr, list_id, 3))
 		return false;
 
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index a852dc4927f7..75aaf94ae0a9 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -414,109 +414,88 @@ end:
 	return result;
 }
 
+bool acpi_cpc_valid(void)
+{
+	struct cpc_desc *cpc_ptr;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
+		if (!cpc_ptr)
+			return false;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(acpi_cpc_valid);
+
 /**
- * acpi_get_psd_map - Map the CPUs in a common freq domain.
- * @all_cpu_data: Ptrs to CPU specific CPPC data including PSD info.
+ * acpi_get_psd_map - Map the CPUs in the freq domain of a given cpu
+ * @cpu: Find all CPUs that share a domain with cpu.
+ * @cpu_data: Pointer to CPU specific CPPC data including PSD info.
  *
  *	Return: 0 for success or negative value for err.
  */
-int acpi_get_psd_map(struct cppc_cpudata **all_cpu_data)
+int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data)
 {
-	int count_target;
-	int retval = 0;
-	unsigned int i, j;
-	cpumask_var_t covered_cpus;
-	struct cppc_cpudata *pr, *match_pr;
-	struct acpi_psd_package *pdomain;
-	struct acpi_psd_package *match_pdomain;
 	struct cpc_desc *cpc_ptr, *match_cpc_ptr;
-
-	if (!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))
-		return -ENOMEM;
+	struct acpi_psd_package *match_pdomain;
+	struct acpi_psd_package *pdomain;
+	int count_target, i;
 
 	/*
 	 * Now that we have _PSD data from all CPUs, let's setup P-state
 	 * domain info.
 	 */
-	for_each_possible_cpu(i) {
-		if (cpumask_test_cpu(i, covered_cpus))
-			continue;
-
-		pr = all_cpu_data[i];
-		cpc_ptr = per_cpu(cpc_desc_ptr, i);
-		if (!cpc_ptr) {
-			retval = -EFAULT;
-			goto err_ret;
-		}
+	cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
+	if (!cpc_ptr)
+		return -EFAULT;
 
-		pdomain = &(cpc_ptr->domain_info);
-		cpumask_set_cpu(i, pr->shared_cpu_map);
-		cpumask_set_cpu(i, covered_cpus);
-		if (pdomain->num_processors <= 1)
-			continue;
+	pdomain = &(cpc_ptr->domain_info);
+	cpumask_set_cpu(cpu, cpu_data->shared_cpu_map);
+	if (pdomain->num_processors <= 1)
+		return 0;
 
-		/* Validate the Domain info */
-		count_target = pdomain->num_processors;
-		if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
-			pr->shared_type = CPUFREQ_SHARED_TYPE_ALL;
-		else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
-			pr->shared_type = CPUFREQ_SHARED_TYPE_HW;
-		else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
-			pr->shared_type = CPUFREQ_SHARED_TYPE_ANY;
-
-		for_each_possible_cpu(j) {
-			if (i == j)
-				continue;
-
-			match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
-			if (!match_cpc_ptr) {
-				retval = -EFAULT;
-				goto err_ret;
-			}
+	/* Validate the Domain info */
+	count_target = pdomain->num_processors;
+	if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
+		cpu_data->shared_type = CPUFREQ_SHARED_TYPE_ALL;
+	else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
+		cpu_data->shared_type = CPUFREQ_SHARED_TYPE_HW;
+	else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
+		cpu_data->shared_type = CPUFREQ_SHARED_TYPE_ANY;
 
-			match_pdomain = &(match_cpc_ptr->domain_info);
-			if (match_pdomain->domain != pdomain->domain)
-				continue;
+	for_each_possible_cpu(i) {
+		if (i == cpu)
+			continue;
 
-			/* Here i and j are in the same domain */
-			if (match_pdomain->num_processors != count_target) {
-				retval = -EFAULT;
-				goto err_ret;
-			}
+		match_cpc_ptr = per_cpu(cpc_desc_ptr, i);
+		if (!match_cpc_ptr)
+			goto err_fault;
 
-			if (pdomain->coord_type != match_pdomain->coord_type) {
-				retval = -EFAULT;
-				goto err_ret;
-			}
+		match_pdomain = &(match_cpc_ptr->domain_info);
+		if (match_pdomain->domain != pdomain->domain)
+			continue;
 
-			cpumask_set_cpu(j, covered_cpus);
-			cpumask_set_cpu(j, pr->shared_cpu_map);
-		}
+		/* Here i and cpu are in the same domain */
+		if (match_pdomain->num_processors != count_target)
+			goto err_fault;
 
-		for_each_cpu(j, pr->shared_cpu_map) {
-			if (i == j)
-				continue;
+		if (pdomain->coord_type != match_pdomain->coord_type)
+			goto err_fault;
 
-			match_pr = all_cpu_data[j];
-			match_pr->shared_type = pr->shared_type;
-			cpumask_copy(match_pr->shared_cpu_map,
-				     pr->shared_cpu_map);
-		}
+		cpumask_set_cpu(i, cpu_data->shared_cpu_map);
 	}
-	goto out;
 
-err_ret:
-	for_each_possible_cpu(i) {
-		pr = all_cpu_data[i];
+	return 0;
 
-		/* Assume no coordination on any error parsing domain info */
-		cpumask_clear(pr->shared_cpu_map);
-		cpumask_set_cpu(i, pr->shared_cpu_map);
-		pr->shared_type = CPUFREQ_SHARED_TYPE_ALL;
-	}
-out:
-	free_cpumask_var(covered_cpus);
-	return retval;
+err_fault:
+	/* Assume no coordination on any error parsing domain info */
+	cpumask_clear(cpu_data->shared_cpu_map);
+	cpumask_set_cpu(cpu, cpu_data->shared_cpu_map);
+	cpu_data->shared_type = CPUFREQ_SHARED_TYPE_NONE;
+
+	return -EFAULT;
 }
 EXPORT_SYMBOL_GPL(acpi_get_psd_map);
 
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index cb229e24c563..e6a5d997241c 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -97,7 +97,7 @@ void acpi_scan_table_handler(u32 event, void *table, void *context);
 extern struct list_head acpi_bus_id_list;
 
 struct acpi_device_bus_id {
-	char bus_id[15];
+	const char *bus_id;
 	unsigned int instance_no;
 	struct list_head node;
 };
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 442608220b5c..b11b08a60684 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -5,6 +5,7 @@
 #include <linux/list_sort.h>
 #include <linux/libnvdimm.h>
 #include <linux/module.h>
+#include <linux/nospec.h>
 #include <linux/mutex.h>
 #include <linux/ndctl.h>
 #include <linux/sysfs.h>
@@ -282,18 +283,19 @@ err:
 
 static union acpi_object *int_to_buf(union acpi_object *integer)
 {
-	union acpi_object *buf = ACPI_ALLOCATE(sizeof(*buf) + 4);
+	union acpi_object *buf = NULL;
 	void *dst = NULL;
 
-	if (!buf)
-		goto err;
-
 	if (integer->type != ACPI_TYPE_INTEGER) {
 		WARN_ONCE(1, "BIOS bug, unexpected element type: %d\n",
 				integer->type);
 		goto err;
 	}
 
+	buf = ACPI_ALLOCATE(sizeof(*buf) + 4);
+	if (!buf)
+		goto err;
+
 	dst = buf + 1;
 	buf->type = ACPI_TYPE_BUFFER;
 	buf->buffer.length = 4;
@@ -478,8 +480,11 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		cmd_mask = nd_desc->cmd_mask;
 		if (cmd == ND_CMD_CALL && call_pkg->nd_family) {
 			family = call_pkg->nd_family;
-			if (!test_bit(family, &nd_desc->bus_family_mask))
+			if (family > NVDIMM_BUS_FAMILY_MAX ||
+			    !test_bit(family, &nd_desc->bus_family_mask))
 				return -EINVAL;
+			family = array_index_nospec(family,
+						    NVDIMM_BUS_FAMILY_MAX + 1);
 			dsm_mask = acpi_desc->family_dsm_mask[family];
 			guid = to_nfit_bus_uuid(family);
 		} else {
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 0dcedd652807..32f0f554ccae 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -708,7 +708,7 @@ err_ret:
 		if (retval) {
 			cpumask_clear(pr->performance->shared_cpu_map);
 			cpumask_set_cpu(i, pr->performance->shared_cpu_map);
-			pr->performance->shared_type = CPUFREQ_SHARED_TYPE_ALL;
+			pr->performance->shared_type = CPUFREQ_SHARED_TYPE_NONE;
 		}
 		pr->performance = NULL; /* Will be set for real in register */
 	}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index a1b226eb2ce2..58ff36340cd7 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -486,6 +486,7 @@ static void acpi_device_del(struct acpi_device *device)
 				acpi_device_bus_id->instance_no--;
 			else {
 				list_del(&acpi_device_bus_id->node);
+				kfree_const(acpi_device_bus_id->bus_id);
 				kfree(acpi_device_bus_id);
 			}
 			break;
@@ -674,7 +675,14 @@ int acpi_device_add(struct acpi_device *device,
 	}
 	if (!found) {
 		acpi_device_bus_id = new_bus_id;
-		strcpy(acpi_device_bus_id->bus_id, acpi_device_hid(device));
+		acpi_device_bus_id->bus_id =
+			kstrdup_const(acpi_device_hid(device), GFP_KERNEL);
+		if (!acpi_device_bus_id->bus_id) {
+			pr_err(PREFIX "Memory allocation error for bus id\n");
+			result = -ENOMEM;
+			goto err_free_new_bus_id;
+		}
+
 		acpi_device_bus_id->instance_no = 0;
 		list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list);
 	}
@@ -709,6 +717,11 @@ int acpi_device_add(struct acpi_device *device,
 	if (device->parent)
 		list_del(&device->node);
 	list_del(&device->wakeup_list);
+
+ err_free_new_bus_id:
+	if (!found)
+		kfree(new_bus_id);
+
 	mutex_unlock(&acpi_device_lock);
 
  err_detach:
@@ -752,6 +765,7 @@ static bool acpi_info_matches_ids(struct acpi_device_info *info,
 /* List of HIDs for which we ignore matching ACPI devices, when checking _DEP lists. */
 static const char * const acpi_ignore_dep_ids[] = {
 	"PNP0D80", /* Windows-compatible System Power Management Controller */
+	"INT33BD", /* Intel Baytrail Mailbox Device */
 	NULL
 };
 
@@ -1635,8 +1649,6 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 	device_initialize(&device->dev);
 	dev_set_uevent_suppress(&device->dev, true);
 	acpi_init_coherency(device);
-	/* Assume there are unmet deps until acpi_device_dep_initialize() runs */
-	device->dep_unmet = 1;
 }
 
 void acpi_device_add_finalize(struct acpi_device *device)
@@ -1842,32 +1854,36 @@ static void acpi_scan_init_hotplug(struct acpi_device *adev)
 	}
 }
 
-static void acpi_device_dep_initialize(struct acpi_device *adev)
+static u32 acpi_scan_check_dep(acpi_handle handle)
 {
-	struct acpi_dep_data *dep;
 	struct acpi_handle_list dep_devices;
 	acpi_status status;
+	u32 count;
 	int i;
 
-	adev->dep_unmet = 0;
-
-	if (!acpi_has_method(adev->handle, "_DEP"))
-		return;
+	/*
+	 * Check for _HID here to avoid deferring the enumeration of:
+	 * 1. PCI devices.
+	 * 2. ACPI nodes describing USB ports.
+	 * Still, checking for _HID catches more then just these cases ...
+	 */
+	if (!acpi_has_method(handle, "_DEP") || !acpi_has_method(handle, "_HID"))
+		return 0;
 
-	status = acpi_evaluate_reference(adev->handle, "_DEP", NULL,
-					&dep_devices);
+	status = acpi_evaluate_reference(handle, "_DEP", NULL, &dep_devices);
 	if (ACPI_FAILURE(status)) {
-		dev_dbg(&adev->dev, "Failed to evaluate _DEP.\n");
-		return;
+		acpi_handle_debug(handle, "Failed to evaluate _DEP.\n");
+		return 0;
 	}
 
-	for (i = 0; i < dep_devices.count; i++) {
+	for (count = 0, i = 0; i < dep_devices.count; i++) {
 		struct acpi_device_info *info;
-		int skip;
+		struct acpi_dep_data *dep;
+		bool skip;
 
 		status = acpi_get_object_info(dep_devices.handles[i], &info);
 		if (ACPI_FAILURE(status)) {
-			dev_dbg(&adev->dev, "Error reading _DEP device info\n");
+			acpi_handle_debug(handle, "Error reading _DEP device info\n");
 			continue;
 		}
 
@@ -1877,26 +1893,45 @@ static void acpi_device_dep_initialize(struct acpi_device *adev)
 		if (skip)
 			continue;
 
-		dep = kzalloc(sizeof(struct acpi_dep_data), GFP_KERNEL);
+		dep = kzalloc(sizeof(*dep), GFP_KERNEL);
 		if (!dep)
-			return;
+			continue;
+
+		count++;
 
 		dep->supplier = dep_devices.handles[i];
-		dep->consumer  = adev->handle;
-		adev->dep_unmet++;
+		dep->consumer = handle;
 
 		mutex_lock(&acpi_dep_list_lock);
 		list_add_tail(&dep->node , &acpi_dep_list);
 		mutex_unlock(&acpi_dep_list_lock);
 	}
+
+	return count;
+}
+
+static void acpi_scan_dep_init(struct acpi_device *adev)
+{
+	struct acpi_dep_data *dep;
+
+	mutex_lock(&acpi_dep_list_lock);
+
+	list_for_each_entry(dep, &acpi_dep_list, node) {
+		if (dep->consumer == adev->handle)
+			adev->dep_unmet++;
+	}
+
+	mutex_unlock(&acpi_dep_list_lock);
 }
 
-static acpi_status acpi_bus_check_add(acpi_handle handle, u32 lvl_not_used,
-				      void *not_used, void **return_value)
+static bool acpi_bus_scan_second_pass;
+
+static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep,
+				      struct acpi_device **adev_p)
 {
 	struct acpi_device *device = NULL;
-	int type;
 	unsigned long long sta;
+	int type;
 	int result;
 
 	acpi_bus_get_device(handle, &device);
@@ -1912,20 +1947,42 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, u32 lvl_not_used,
 		return AE_OK;
 	}
 
+	if (type == ACPI_BUS_TYPE_DEVICE && check_dep) {
+		u32 count = acpi_scan_check_dep(handle);
+		/* Bail out if the number of recorded dependencies is not 0. */
+		if (count > 0) {
+			acpi_bus_scan_second_pass = true;
+			return AE_CTRL_DEPTH;
+		}
+	}
+
 	acpi_add_single_object(&device, handle, type, sta);
 	if (!device)
 		return AE_CTRL_DEPTH;
 
 	acpi_scan_init_hotplug(device);
-	acpi_device_dep_initialize(device);
+	if (!check_dep)
+		acpi_scan_dep_init(device);
 
- out:
-	if (!*return_value)
-		*return_value = device;
+out:
+	if (!*adev_p)
+		*adev_p = device;
 
 	return AE_OK;
 }
 
+static acpi_status acpi_bus_check_add_1(acpi_handle handle, u32 lvl_not_used,
+					void *not_used, void **ret_p)
+{
+	return acpi_bus_check_add(handle, true, (struct acpi_device **)ret_p);
+}
+
+static acpi_status acpi_bus_check_add_2(acpi_handle handle, u32 lvl_not_used,
+					void *not_used, void **ret_p)
+{
+	return acpi_bus_check_add(handle, false, (struct acpi_device **)ret_p);
+}
+
 static void acpi_default_enumeration(struct acpi_device *device)
 {
 	/*
@@ -1993,12 +2050,16 @@ static int acpi_scan_attach_handler(struct acpi_device *device)
 	return ret;
 }
 
-static void acpi_bus_attach(struct acpi_device *device)
+static void acpi_bus_attach(struct acpi_device *device, bool first_pass)
 {
 	struct acpi_device *child;
+	bool skip = !first_pass && device->flags.visited;
 	acpi_handle ejd;
 	int ret;
 
+	if (skip)
+		goto ok;
+
 	if (ACPI_SUCCESS(acpi_bus_get_ejd(device->handle, &ejd)))
 		register_dock_dependent_device(device, ejd);
 
@@ -2045,9 +2106,9 @@ static void acpi_bus_attach(struct acpi_device *device)
 
  ok:
 	list_for_each_entry(child, &device->children, node)
-		acpi_bus_attach(child);
+		acpi_bus_attach(child, first_pass);
 
-	if (device->handler && device->handler->hotplug.notify_online)
+	if (!skip && device->handler && device->handler->hotplug.notify_online)
 		device->handler->hotplug.notify_online(device);
 }
 
@@ -2065,7 +2126,8 @@ void acpi_walk_dep_device_list(acpi_handle handle)
 
 			adev->dep_unmet--;
 			if (!adev->dep_unmet)
-				acpi_bus_attach(adev);
+				acpi_bus_attach(adev, true);
+
 			list_del(&dep->node);
 			kfree(dep);
 		}
@@ -2090,17 +2152,37 @@ EXPORT_SYMBOL_GPL(acpi_walk_dep_device_list);
  */
 int acpi_bus_scan(acpi_handle handle)
 {
-	void *device = NULL;
+	struct acpi_device *device = NULL;
 
-	if (ACPI_SUCCESS(acpi_bus_check_add(handle, 0, NULL, &device)))
+	acpi_bus_scan_second_pass = false;
+
+	/* Pass 1: Avoid enumerating devices with missing dependencies. */
+
+	if (ACPI_SUCCESS(acpi_bus_check_add(handle, true, &device)))
 		acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX,
-				    acpi_bus_check_add, NULL, NULL, &device);
+				    acpi_bus_check_add_1, NULL, NULL,
+				    (void **)&device);
 
-	if (device) {
-		acpi_bus_attach(device);
+	if (!device)
+		return -ENODEV;
+
+	acpi_bus_attach(device, true);
+
+	if (!acpi_bus_scan_second_pass)
 		return 0;
-	}
-	return -ENODEV;
+
+	/* Pass 2: Enumerate all of the remaining devices. */
+
+	device = NULL;
+
+	if (ACPI_SUCCESS(acpi_bus_check_add(handle, false, &device)))
+		acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX,
+				    acpi_bus_check_add_2, NULL, NULL,
+				    (void **)&device);
+
+	acpi_bus_attach(device, false);
+
+	return 0;
 }
 EXPORT_SYMBOL(acpi_bus_scan);
 
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index aff13bf4d947..09fd13757b65 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -92,10 +92,6 @@ bool acpi_sleep_state_supported(u8 sleep_state)
 }
 
 #ifdef CONFIG_ACPI_SLEEP
-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 u32 acpi_target_sleep_state = ACPI_STATE_S0;
 
 u32 acpi_target_system_state(void)
@@ -165,7 +161,7 @@ static int __init init_nvs_nosave(const struct dmi_system_id *d)
 	return 0;
 }
 
-static bool acpi_sleep_default_s3;
+bool acpi_sleep_default_s3;
 
 static int __init init_default_s3(const struct dmi_system_id *d)
 {
@@ -688,268 +684,13 @@ static const struct platform_suspend_ops acpi_suspend_ops_old = {
 
 static bool s2idle_wakeup;
 
-/*
- * On platforms supporting the Low Power S0 Idle interface there is an ACPI
- * device object with the PNP0D80 compatible device ID (System Power Management
- * Controller) and a specific _DSM method under it.  That method, if present,
- * can be used to indicate to the platform that the OS is transitioning into a
- * low-power state in which certain types of activity are not desirable or that
- * it is leaving such a state, which allows the platform to adjust its operation
- * mode accordingly.
- */
-static const struct acpi_device_id lps0_device_ids[] = {
-	{"PNP0D80", },
-	{"", },
-};
-
-#define ACPI_LPS0_DSM_UUID	"c4eb40a0-6cd2-11e2-bcfd-0800200c9a66"
-
-#define ACPI_LPS0_GET_DEVICE_CONSTRAINTS	1
-#define ACPI_LPS0_SCREEN_OFF	3
-#define ACPI_LPS0_SCREEN_ON	4
-#define ACPI_LPS0_ENTRY		5
-#define ACPI_LPS0_EXIT		6
-
-static acpi_handle lps0_device_handle;
-static guid_t lps0_dsm_guid;
-static char lps0_dsm_func_mask;
-
-/* Device constraint entry structure */
-struct lpi_device_info {
-	char *name;
-	int enabled;
-	union acpi_object *package;
-};
-
-/* Constraint package structure */
-struct lpi_device_constraint {
-	int uid;
-	int min_dstate;
-	int function_states;
-};
-
-struct lpi_constraints {
-	acpi_handle handle;
-	int min_dstate;
-};
-
-static struct lpi_constraints *lpi_constraints_table;
-static int lpi_constraints_table_size;
-
-static void lpi_device_get_constraints(void)
-{
-	union acpi_object *out_obj;
-	int i;
-
-	out_obj = acpi_evaluate_dsm_typed(lps0_device_handle, &lps0_dsm_guid,
-					  1, ACPI_LPS0_GET_DEVICE_CONSTRAINTS,
-					  NULL, ACPI_TYPE_PACKAGE);
-
-	acpi_handle_debug(lps0_device_handle, "_DSM function 1 eval %s\n",
-			  out_obj ? "successful" : "failed");
-
-	if (!out_obj)
-		return;
-
-	lpi_constraints_table = kcalloc(out_obj->package.count,
-					sizeof(*lpi_constraints_table),
-					GFP_KERNEL);
-	if (!lpi_constraints_table)
-		goto free_acpi_buffer;
-
-	acpi_handle_debug(lps0_device_handle, "LPI: constraints list begin:\n");
-
-	for (i = 0; i < out_obj->package.count; i++) {
-		struct lpi_constraints *constraint;
-		acpi_status status;
-		union acpi_object *package = &out_obj->package.elements[i];
-		struct lpi_device_info info = { };
-		int package_count = 0, j;
-
-		if (!package)
-			continue;
-
-		for (j = 0; j < package->package.count; ++j) {
-			union acpi_object *element =
-					&(package->package.elements[j]);
-
-			switch (element->type) {
-			case ACPI_TYPE_INTEGER:
-				info.enabled = element->integer.value;
-				break;
-			case ACPI_TYPE_STRING:
-				info.name = element->string.pointer;
-				break;
-			case ACPI_TYPE_PACKAGE:
-				package_count = element->package.count;
-				info.package = element->package.elements;
-				break;
-			}
-		}
-
-		if (!info.enabled || !info.package || !info.name)
-			continue;
-
-		constraint = &lpi_constraints_table[lpi_constraints_table_size];
-
-		status = acpi_get_handle(NULL, info.name, &constraint->handle);
-		if (ACPI_FAILURE(status))
-			continue;
-
-		acpi_handle_debug(lps0_device_handle,
-				  "index:%d Name:%s\n", i, info.name);
-
-		constraint->min_dstate = -1;
-
-		for (j = 0; j < package_count; ++j) {
-			union acpi_object *info_obj = &info.package[j];
-			union acpi_object *cnstr_pkg;
-			union acpi_object *obj;
-			struct lpi_device_constraint dev_info;
-
-			switch (info_obj->type) {
-			case ACPI_TYPE_INTEGER:
-				/* version */
-				break;
-			case ACPI_TYPE_PACKAGE:
-				if (info_obj->package.count < 2)
-					break;
-
-				cnstr_pkg = info_obj->package.elements;
-				obj = &cnstr_pkg[0];
-				dev_info.uid = obj->integer.value;
-				obj = &cnstr_pkg[1];
-				dev_info.min_dstate = obj->integer.value;
-
-				acpi_handle_debug(lps0_device_handle,
-					"uid:%d min_dstate:%s\n",
-					dev_info.uid,
-					acpi_power_state_string(dev_info.min_dstate));
-
-				constraint->min_dstate = dev_info.min_dstate;
-				break;
-			}
-		}
-
-		if (constraint->min_dstate < 0) {
-			acpi_handle_debug(lps0_device_handle,
-					  "Incomplete constraint defined\n");
-			continue;
-		}
-
-		lpi_constraints_table_size++;
-	}
-
-	acpi_handle_debug(lps0_device_handle, "LPI: constraints list end\n");
-
-free_acpi_buffer:
-	ACPI_FREE(out_obj);
-}
-
-static void lpi_check_constraints(void)
-{
-	int i;
-
-	for (i = 0; i < lpi_constraints_table_size; ++i) {
-		acpi_handle handle = lpi_constraints_table[i].handle;
-		struct acpi_device *adev;
-
-		if (!handle || acpi_bus_get_device(handle, &adev))
-			continue;
-
-		acpi_handle_debug(handle,
-			"LPI: required min power state:%s current power state:%s\n",
-			acpi_power_state_string(lpi_constraints_table[i].min_dstate),
-			acpi_power_state_string(adev->power.state));
-
-		if (!adev->flags.power_manageable) {
-			acpi_handle_info(handle, "LPI: Device not power manageable\n");
-			lpi_constraints_table[i].handle = NULL;
-			continue;
-		}
-
-		if (adev->power.state < lpi_constraints_table[i].min_dstate)
-			acpi_handle_info(handle,
-				"LPI: Constraint not met; min power state:%s current power state:%s\n",
-				acpi_power_state_string(lpi_constraints_table[i].min_dstate),
-				acpi_power_state_string(adev->power.state));
-	}
-}
-
-static void acpi_sleep_run_lps0_dsm(unsigned int func)
-{
-	union acpi_object *out_obj;
-
-	if (!(lps0_dsm_func_mask & (1 << func)))
-		return;
-
-	out_obj = acpi_evaluate_dsm(lps0_device_handle, &lps0_dsm_guid, 1, func, NULL);
-	ACPI_FREE(out_obj);
-
-	acpi_handle_debug(lps0_device_handle, "_DSM function %u evaluation %s\n",
-			  func, out_obj ? "successful" : "failed");
-}
-
-static int lps0_device_attach(struct acpi_device *adev,
-			      const struct acpi_device_id *not_used)
-{
-	union acpi_object *out_obj;
-
-	if (lps0_device_handle)
-		return 0;
-
-	if (!(acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0))
-		return 0;
-
-	guid_parse(ACPI_LPS0_DSM_UUID, &lps0_dsm_guid);
-	/* Check if the _DSM is present and as expected. */
-	out_obj = acpi_evaluate_dsm(adev->handle, &lps0_dsm_guid, 1, 0, NULL);
-	if (!out_obj || out_obj->type != ACPI_TYPE_BUFFER) {
-		acpi_handle_debug(adev->handle,
-				  "_DSM function 0 evaluation failed\n");
-		return 0;
-	}
-
-	lps0_dsm_func_mask = *(char *)out_obj->buffer.pointer;
-
-	ACPI_FREE(out_obj);
-
-	acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n",
-			  lps0_dsm_func_mask);
-
-	lps0_device_handle = adev->handle;
-
-	lpi_device_get_constraints();
-
-	/*
-	 * Use suspend-to-idle by default if the default suspend mode was not
-	 * set from the command line.
-	 */
-	if (mem_sleep_default > PM_SUSPEND_MEM && !acpi_sleep_default_s3)
-		mem_sleep_current = PM_SUSPEND_TO_IDLE;
-
-	/*
-	 * Some LPS0 systems, like ASUS Zenbook UX430UNR/i7-8550U, require the
-	 * EC GPE to be enabled while suspended for certain wakeup devices to
-	 * work, so mark it as wakeup-capable.
-	 */
-	acpi_ec_mark_gpe_for_wake();
-
-	return 0;
-}
-
-static struct acpi_scan_handler lps0_handler = {
-	.ids = lps0_device_ids,
-	.attach = lps0_device_attach,
-};
-
-static int acpi_s2idle_begin(void)
+int acpi_s2idle_begin(void)
 {
 	acpi_scan_lock_acquire();
 	return 0;
 }
 
-static int acpi_s2idle_prepare(void)
+int acpi_s2idle_prepare(void)
 {
 	if (acpi_sci_irq_valid()) {
 		enable_irq_wake(acpi_sci_irq);
@@ -966,21 +707,7 @@ static int acpi_s2idle_prepare(void)
 	return 0;
 }
 
-static int acpi_s2idle_prepare_late(void)
-{
-	if (!lps0_device_handle || sleep_no_lps0)
-		return 0;
-
-	if (pm_debug_messages_on)
-		lpi_check_constraints();
-
-	acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF);
-	acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY);
-
-	return 0;
-}
-
-static bool acpi_s2idle_wake(void)
+bool acpi_s2idle_wake(void)
 {
 	if (!acpi_sci_irq_valid())
 		return pm_wakeup_pending();
@@ -1046,16 +773,7 @@ static bool acpi_s2idle_wake(void)
 	return false;
 }
 
-static void acpi_s2idle_restore_early(void)
-{
-	if (!lps0_device_handle || sleep_no_lps0)
-		return;
-
-	acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT);
-	acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON);
-}
-
-static void acpi_s2idle_restore(void)
+void acpi_s2idle_restore(void)
 {
 	/*
 	 * Drain pending events before restoring the working-state configuration
@@ -1077,7 +795,7 @@ static void acpi_s2idle_restore(void)
 	}
 }
 
-static void acpi_s2idle_end(void)
+void acpi_s2idle_end(void)
 {
 	acpi_scan_lock_release();
 }
@@ -1085,13 +803,16 @@ static void acpi_s2idle_end(void)
 static const struct platform_s2idle_ops acpi_s2idle_ops = {
 	.begin = acpi_s2idle_begin,
 	.prepare = acpi_s2idle_prepare,
-	.prepare_late = acpi_s2idle_prepare_late,
 	.wake = acpi_s2idle_wake,
-	.restore_early = acpi_s2idle_restore_early,
 	.restore = acpi_s2idle_restore,
 	.end = acpi_s2idle_end,
 };
 
+void __weak acpi_s2idle_setup(void)
+{
+	s2idle_set_ops(&acpi_s2idle_ops);
+}
+
 static void acpi_sleep_suspend_setup(void)
 {
 	int i;
@@ -1103,13 +824,11 @@ static void acpi_sleep_suspend_setup(void)
 	suspend_set_ops(old_suspend_ordering ?
 		&acpi_suspend_ops_old : &acpi_suspend_ops);
 
-	acpi_scan_add_handler(&lps0_handler);
-	s2idle_set_ops(&acpi_s2idle_ops);
+	acpi_s2idle_setup();
 }
 
 #else /* !CONFIG_SUSPEND */
 #define s2idle_wakeup		(false)
-#define lps0_device_handle	(NULL)
 static inline void acpi_sleep_suspend_setup(void) {}
 #endif /* !CONFIG_SUSPEND */
 
diff --git a/drivers/acpi/sleep.h b/drivers/acpi/sleep.h
index 3d90480ce1b1..1856f76ac83f 100644
--- a/drivers/acpi/sleep.h
+++ b/drivers/acpi/sleep.h
@@ -15,3 +15,19 @@ static inline acpi_status acpi_set_waking_vector(u32 wakeup_address)
 	return acpi_set_firmware_waking_vector(
 				(acpi_physical_address)wakeup_address, 0);
 }
+
+extern int acpi_s2idle_begin(void);
+extern int acpi_s2idle_prepare(void);
+extern int acpi_s2idle_prepare_late(void);
+extern bool acpi_s2idle_wake(void);
+extern void acpi_s2idle_restore_early(void);
+extern void acpi_s2idle_restore(void);
+extern void acpi_s2idle_end(void);
+
+extern void acpi_s2idle_setup(void);
+
+#ifdef CONFIG_ACPI_SLEEP
+extern bool acpi_sleep_default_s3;
+#else
+#define acpi_sleep_default_s3	(1)
+#endif
diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c
new file mode 100644
index 000000000000..2b69536cdccb
--- /dev/null
+++ b/drivers/acpi/x86/s2idle.c
@@ -0,0 +1,448 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Architecture-specific ACPI-based support for suspend-to-idle.
+ *
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ * Author: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
+ * Author: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
+ *
+ * On platforms supporting the Low Power S0 Idle interface there is an ACPI
+ * device object with the PNP0D80 compatible device ID (System Power Management
+ * Controller) and a specific _DSM method under it.  That method, if present,
+ * can be used to indicate to the platform that the OS is transitioning into a
+ * low-power state in which certain types of activity are not desirable or that
+ * it is leaving such a state, which allows the platform to adjust its operation
+ * mode accordingly.
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/suspend.h>
+
+#include "../sleep.h"
+
+#ifdef CONFIG_SUSPEND
+
+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 const struct acpi_device_id lps0_device_ids[] = {
+	{"PNP0D80", },
+	{"", },
+};
+
+#define ACPI_LPS0_DSM_UUID	"c4eb40a0-6cd2-11e2-bcfd-0800200c9a66"
+
+#define ACPI_LPS0_GET_DEVICE_CONSTRAINTS	1
+#define ACPI_LPS0_SCREEN_OFF	3
+#define ACPI_LPS0_SCREEN_ON	4
+#define ACPI_LPS0_ENTRY		5
+#define ACPI_LPS0_EXIT		6
+
+/* AMD */
+#define ACPI_LPS0_DSM_UUID_AMD      "e3f32452-febc-43ce-9039-932122d37721"
+#define ACPI_LPS0_SCREEN_OFF_AMD    4
+#define ACPI_LPS0_SCREEN_ON_AMD     5
+
+static acpi_handle lps0_device_handle;
+static guid_t lps0_dsm_guid;
+static char lps0_dsm_func_mask;
+
+/* Device constraint entry structure */
+struct lpi_device_info {
+	char *name;
+	int enabled;
+	union acpi_object *package;
+};
+
+/* Constraint package structure */
+struct lpi_device_constraint {
+	int uid;
+	int min_dstate;
+	int function_states;
+};
+
+struct lpi_constraints {
+	acpi_handle handle;
+	int min_dstate;
+};
+
+/* AMD */
+/* Device constraint entry structure */
+struct lpi_device_info_amd {
+	int revision;
+	int count;
+	union acpi_object *package;
+};
+
+/* Constraint package structure */
+struct lpi_device_constraint_amd {
+	char *name;
+	int enabled;
+	int function_states;
+	int min_dstate;
+};
+
+static struct lpi_constraints *lpi_constraints_table;
+static int lpi_constraints_table_size;
+static int rev_id;
+
+static void lpi_device_get_constraints_amd(void)
+{
+	union acpi_object *out_obj;
+	int i, j, k;
+
+	out_obj = acpi_evaluate_dsm_typed(lps0_device_handle, &lps0_dsm_guid,
+					  1, ACPI_LPS0_GET_DEVICE_CONSTRAINTS,
+					  NULL, ACPI_TYPE_PACKAGE);
+
+	if (!out_obj)
+		return;
+
+	acpi_handle_debug(lps0_device_handle, "_DSM function 1 eval %s\n",
+			  out_obj ? "successful" : "failed");
+
+	for (i = 0; i < out_obj->package.count; i++) {
+		union acpi_object *package = &out_obj->package.elements[i];
+
+		if (package->type == ACPI_TYPE_PACKAGE) {
+			lpi_constraints_table = kcalloc(package->package.count,
+							sizeof(*lpi_constraints_table),
+							GFP_KERNEL);
+
+			if (!lpi_constraints_table)
+				goto free_acpi_buffer;
+
+			acpi_handle_debug(lps0_device_handle,
+					  "LPI: constraints list begin:\n");
+
+			for (j = 0; j < package->package.count; ++j) {
+				union acpi_object *info_obj = &package->package.elements[j];
+				struct lpi_device_constraint_amd dev_info = {};
+				struct lpi_constraints *list;
+				acpi_status status;
+
+				for (k = 0; k < info_obj->package.count; ++k) {
+					union acpi_object *obj = &info_obj->package.elements[k];
+
+					list = &lpi_constraints_table[lpi_constraints_table_size];
+					list->min_dstate = -1;
+
+					switch (k) {
+					case 0:
+						dev_info.enabled = obj->integer.value;
+						break;
+					case 1:
+						dev_info.name = obj->string.pointer;
+						break;
+					case 2:
+						dev_info.function_states = obj->integer.value;
+						break;
+					case 3:
+						dev_info.min_dstate = obj->integer.value;
+						break;
+					}
+
+					if (!dev_info.enabled || !dev_info.name ||
+					    !dev_info.min_dstate)
+						continue;
+
+					status = acpi_get_handle(NULL, dev_info.name,
+								 &list->handle);
+					if (ACPI_FAILURE(status))
+						continue;
+
+					acpi_handle_debug(lps0_device_handle,
+							  "Name:%s\n", dev_info.name);
+
+					list->min_dstate = dev_info.min_dstate;
+
+					if (list->min_dstate < 0) {
+						acpi_handle_debug(lps0_device_handle,
+								  "Incomplete constraint defined\n");
+						continue;
+					}
+				}
+				lpi_constraints_table_size++;
+			}
+		}
+	}
+
+	acpi_handle_debug(lps0_device_handle, "LPI: constraints list end\n");
+
+free_acpi_buffer:
+	ACPI_FREE(out_obj);
+}
+
+static void lpi_device_get_constraints(void)
+{
+	union acpi_object *out_obj;
+	int i;
+
+	out_obj = acpi_evaluate_dsm_typed(lps0_device_handle, &lps0_dsm_guid,
+					  1, ACPI_LPS0_GET_DEVICE_CONSTRAINTS,
+					  NULL, ACPI_TYPE_PACKAGE);
+
+	acpi_handle_debug(lps0_device_handle, "_DSM function 1 eval %s\n",
+			  out_obj ? "successful" : "failed");
+
+	if (!out_obj)
+		return;
+
+	lpi_constraints_table = kcalloc(out_obj->package.count,
+					sizeof(*lpi_constraints_table),
+					GFP_KERNEL);
+	if (!lpi_constraints_table)
+		goto free_acpi_buffer;
+
+	acpi_handle_debug(lps0_device_handle, "LPI: constraints list begin:\n");
+
+	for (i = 0; i < out_obj->package.count; i++) {
+		struct lpi_constraints *constraint;
+		acpi_status status;
+		union acpi_object *package = &out_obj->package.elements[i];
+		struct lpi_device_info info = { };
+		int package_count = 0, j;
+
+		if (!package)
+			continue;
+
+		for (j = 0; j < package->package.count; ++j) {
+			union acpi_object *element =
+					&(package->package.elements[j]);
+
+			switch (element->type) {
+			case ACPI_TYPE_INTEGER:
+				info.enabled = element->integer.value;
+				break;
+			case ACPI_TYPE_STRING:
+				info.name = element->string.pointer;
+				break;
+			case ACPI_TYPE_PACKAGE:
+				package_count = element->package.count;
+				info.package = element->package.elements;
+				break;
+			}
+		}
+
+		if (!info.enabled || !info.package || !info.name)
+			continue;
+
+		constraint = &lpi_constraints_table[lpi_constraints_table_size];
+
+		status = acpi_get_handle(NULL, info.name, &constraint->handle);
+		if (ACPI_FAILURE(status))
+			continue;
+
+		acpi_handle_debug(lps0_device_handle,
+				  "index:%d Name:%s\n", i, info.name);
+
+		constraint->min_dstate = -1;
+
+		for (j = 0; j < package_count; ++j) {
+			union acpi_object *info_obj = &info.package[j];
+			union acpi_object *cnstr_pkg;
+			union acpi_object *obj;
+			struct lpi_device_constraint dev_info;
+
+			switch (info_obj->type) {
+			case ACPI_TYPE_INTEGER:
+				/* version */
+				break;
+			case ACPI_TYPE_PACKAGE:
+				if (info_obj->package.count < 2)
+					break;
+
+				cnstr_pkg = info_obj->package.elements;
+				obj = &cnstr_pkg[0];
+				dev_info.uid = obj->integer.value;
+				obj = &cnstr_pkg[1];
+				dev_info.min_dstate = obj->integer.value;
+
+				acpi_handle_debug(lps0_device_handle,
+					"uid:%d min_dstate:%s\n",
+					dev_info.uid,
+					acpi_power_state_string(dev_info.min_dstate));
+
+				constraint->min_dstate = dev_info.min_dstate;
+				break;
+			}
+		}
+
+		if (constraint->min_dstate < 0) {
+			acpi_handle_debug(lps0_device_handle,
+					  "Incomplete constraint defined\n");
+			continue;
+		}
+
+		lpi_constraints_table_size++;
+	}
+
+	acpi_handle_debug(lps0_device_handle, "LPI: constraints list end\n");
+
+free_acpi_buffer:
+	ACPI_FREE(out_obj);
+}
+
+static void lpi_check_constraints(void)
+{
+	int i;
+
+	for (i = 0; i < lpi_constraints_table_size; ++i) {
+		acpi_handle handle = lpi_constraints_table[i].handle;
+		struct acpi_device *adev;
+
+		if (!handle || acpi_bus_get_device(handle, &adev))
+			continue;
+
+		acpi_handle_debug(handle,
+			"LPI: required min power state:%s current power state:%s\n",
+			acpi_power_state_string(lpi_constraints_table[i].min_dstate),
+			acpi_power_state_string(adev->power.state));
+
+		if (!adev->flags.power_manageable) {
+			acpi_handle_info(handle, "LPI: Device not power manageable\n");
+			lpi_constraints_table[i].handle = NULL;
+			continue;
+		}
+
+		if (adev->power.state < lpi_constraints_table[i].min_dstate)
+			acpi_handle_info(handle,
+				"LPI: Constraint not met; min power state:%s current power state:%s\n",
+				acpi_power_state_string(lpi_constraints_table[i].min_dstate),
+				acpi_power_state_string(adev->power.state));
+	}
+}
+
+static void acpi_sleep_run_lps0_dsm(unsigned int func)
+{
+	union acpi_object *out_obj;
+
+	if (!(lps0_dsm_func_mask & (1 << func)))
+		return;
+
+	out_obj = acpi_evaluate_dsm(lps0_device_handle, &lps0_dsm_guid, rev_id, func, NULL);
+	ACPI_FREE(out_obj);
+
+	acpi_handle_debug(lps0_device_handle, "_DSM function %u evaluation %s\n",
+			  func, out_obj ? "successful" : "failed");
+}
+
+static bool acpi_s2idle_vendor_amd(void)
+{
+	return boot_cpu_data.x86_vendor == X86_VENDOR_AMD;
+}
+
+static int lps0_device_attach(struct acpi_device *adev,
+			      const struct acpi_device_id *not_used)
+{
+	union acpi_object *out_obj;
+
+	if (lps0_device_handle)
+		return 0;
+
+	if (!(acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0))
+		return 0;
+
+	if (acpi_s2idle_vendor_amd()) {
+		guid_parse(ACPI_LPS0_DSM_UUID_AMD, &lps0_dsm_guid);
+		out_obj = acpi_evaluate_dsm(adev->handle, &lps0_dsm_guid, 0, 0, NULL);
+		rev_id = 0;
+	} else {
+		guid_parse(ACPI_LPS0_DSM_UUID, &lps0_dsm_guid);
+		out_obj = acpi_evaluate_dsm(adev->handle, &lps0_dsm_guid, 1, 0, NULL);
+		rev_id = 1;
+	}
+
+	/* Check if the _DSM is present and as expected. */
+	if (!out_obj || out_obj->type != ACPI_TYPE_BUFFER) {
+		acpi_handle_debug(adev->handle,
+				  "_DSM function 0 evaluation failed\n");
+		return 0;
+	}
+
+	lps0_dsm_func_mask = *(char *)out_obj->buffer.pointer;
+
+	ACPI_FREE(out_obj);
+
+	acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n",
+			  lps0_dsm_func_mask);
+
+	lps0_device_handle = adev->handle;
+
+	if (acpi_s2idle_vendor_amd())
+		lpi_device_get_constraints_amd();
+	else
+		lpi_device_get_constraints();
+
+	/*
+	 * Use suspend-to-idle by default if the default suspend mode was not
+	 * set from the command line.
+	 */
+	if (mem_sleep_default > PM_SUSPEND_MEM && !acpi_sleep_default_s3)
+		mem_sleep_current = PM_SUSPEND_TO_IDLE;
+
+	/*
+	 * Some LPS0 systems, like ASUS Zenbook UX430UNR/i7-8550U, require the
+	 * EC GPE to be enabled while suspended for certain wakeup devices to
+	 * work, so mark it as wakeup-capable.
+	 */
+	acpi_ec_mark_gpe_for_wake();
+
+	return 0;
+}
+
+static struct acpi_scan_handler lps0_handler = {
+	.ids = lps0_device_ids,
+	.attach = lps0_device_attach,
+};
+
+int acpi_s2idle_prepare_late(void)
+{
+	if (!lps0_device_handle || sleep_no_lps0)
+		return 0;
+
+	if (pm_debug_messages_on)
+		lpi_check_constraints();
+
+	if (acpi_s2idle_vendor_amd()) {
+		acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF_AMD);
+	} else {
+		acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF);
+		acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY);
+	}
+
+	return 0;
+}
+
+void acpi_s2idle_restore_early(void)
+{
+	if (!lps0_device_handle || sleep_no_lps0)
+		return;
+
+	if (acpi_s2idle_vendor_amd()) {
+		acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON_AMD);
+	} else {
+		acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT);
+		acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON);
+	}
+}
+
+static const struct platform_s2idle_ops acpi_s2idle_ops_lps0 = {
+	.begin = acpi_s2idle_begin,
+	.prepare = acpi_s2idle_prepare,
+	.prepare_late = acpi_s2idle_prepare_late,
+	.wake = acpi_s2idle_wake,
+	.restore_early = acpi_s2idle_restore_early,
+	.restore = acpi_s2idle_restore,
+	.end = acpi_s2idle_end,
+};
+
+void acpi_s2idle_setup(void)
+{
+	acpi_scan_add_handler(&lps0_handler);
+	s2idle_set_ops(&acpi_s2idle_ops_lps0);
+}
+
+#endif /* CONFIG_SUSPEND */
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index 65a3886f68c9..5f0472c18bcb 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -3607,7 +3607,7 @@ static int idt77252_init_one(struct pci_dev *pcidev,
 
 	if ((err = dma_set_mask_and_coherent(&pcidev->dev, DMA_BIT_MASK(32)))) {
 		printk("idt77252: can't enable DMA for PCI device at %s\n", pci_name(pcidev));
-		return err;
+		goto err_out_disable_pdev;
 	}
 
 	card = kzalloc(sizeof(struct idt77252_dev), GFP_KERNEL);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 25e08e5f40bd..14f165816742 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -4414,6 +4414,12 @@ static inline bool fwnode_is_primary(struct fwnode_handle *fwnode)
  *
  * Set the device's firmware node pointer to @fwnode, but if a secondary
  * firmware node of the device is present, preserve it.
+ *
+ * Valid fwnode cases are:
+ *  - primary --> secondary --> -ENODEV
+ *  - primary --> NULL
+ *  - secondary --> -ENODEV
+ *  - NULL
  */
 void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
 {
@@ -4432,8 +4438,9 @@ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
 	} else {
 		if (fwnode_is_primary(fn)) {
 			dev->fwnode = fn->secondary;
+			/* Set fn->secondary = NULL, so fn remains the primary fwnode */
 			if (!(parent && fn == parent->fwnode))
-				fn->secondary = ERR_PTR(-ENODEV);
+				fn->secondary = NULL;
 		} else {
 			dev->fwnode = NULL;
 		}
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 8dfac7f3ed7a..ff2ee87987c7 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -582,8 +582,12 @@ void regmap_debugfs_init(struct regmap *map)
 		devname = dev_name(map->dev);
 
 	if (name) {
-		map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s",
+		if (!map->debugfs_name) {
+			map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s",
 					      devname, name);
+			if (!map->debugfs_name)
+				return;
+		}
 		name = map->debugfs_name;
 	} else {
 		name = devname;
@@ -591,9 +595,10 @@ void regmap_debugfs_init(struct regmap *map)
 
 	if (!strcmp(name, "dummy")) {
 		kfree(map->debugfs_name);
-
 		map->debugfs_name = kasprintf(GFP_KERNEL, "dummy%d",
 						dummy_index);
+		if (!map->debugfs_name)
+				return;
 		name = map->debugfs_name;
 		dummy_index++;
 	}
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 262326973ee0..583b671b1d2d 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -445,6 +445,7 @@ config BLK_DEV_RBD
 config BLK_DEV_RSXX
 	tristate "IBM Flash Adapter 900GB Full Height PCIe Device Driver"
 	depends on PCI
+	select CRC32
 	help
 	  Device driver for IBM's high speed PCIe SSD
 	  storage device: Flash Adapter 900GB Full Height.
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 92f84ed0ba9e..6727358e147d 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -318,7 +318,8 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
 	blk_queue_logical_block_size(nbd->disk->queue, blksize);
 	blk_queue_physical_block_size(nbd->disk->queue, blksize);
 
-	set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
+	if (max_part)
+		set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
 	if (!set_capacity_and_notify(nbd->disk, bytesize >> 9))
 		kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
 	return 0;
@@ -1476,9 +1477,11 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
 		refcount_set(&nbd->config_refs, 1);
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
-		set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
+		if (max_part)
+			set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 	} else if (nbd_disconnected(nbd->config)) {
-		set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
+		if (max_part)
+			set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
 	}
 out:
 	mutex_unlock(&nbd_index_mutex);
diff --git a/drivers/block/rnbd/Kconfig b/drivers/block/rnbd/Kconfig
index 4b6d3d816d1f..2ff05a0d2646 100644
--- a/drivers/block/rnbd/Kconfig
+++ b/drivers/block/rnbd/Kconfig
@@ -7,6 +7,7 @@ config BLK_DEV_RNBD_CLIENT
 	tristate "RDMA Network Block Device driver client"
 	depends on INFINIBAND_RTRS_CLIENT
 	select BLK_DEV_RNBD
+	select SG_POOL
 	help
 	  RNBD client is a network block device driver using rdma transport.
 
diff --git a/drivers/block/rnbd/README b/drivers/block/rnbd/README
index 1773c0aa0bd4..080f58a5400a 100644
--- a/drivers/block/rnbd/README
+++ b/drivers/block/rnbd/README
@@ -90,3 +90,4 @@ Kleber Souza <kleber.souza@profitbricks.com>
 Lutz Pogrell <lutz.pogrell@cloud.ionos.com>
 Milind Dumbare <Milind.dumbare@gmail.com>
 Roman Penyaev <roman.penyaev@profitbricks.com>
+Swapnil Ingle <ingleswapnil@gmail.com>
diff --git a/drivers/block/rnbd/rnbd-clt-sysfs.c b/drivers/block/rnbd/rnbd-clt-sysfs.c
index a7caeedeb198..d4aa6bfc9555 100644
--- a/drivers/block/rnbd/rnbd-clt-sysfs.c
+++ b/drivers/block/rnbd/rnbd-clt-sysfs.c
@@ -432,7 +432,7 @@ void rnbd_clt_remove_dev_symlink(struct rnbd_clt_dev *dev)
 	 * i.e. rnbd_clt_unmap_dev_store() leading to a sysfs warning because
 	 * of sysfs link already was removed already.
 	 */
-	if (strlen(dev->blk_symlink_name) && try_module_get(THIS_MODULE)) {
+	if (dev->blk_symlink_name && try_module_get(THIS_MODULE)) {
 		sysfs_remove_link(rnbd_devs_kobj, dev->blk_symlink_name);
 		kfree(dev->blk_symlink_name);
 		module_put(THIS_MODULE);
@@ -521,7 +521,8 @@ static int rnbd_clt_add_dev_symlink(struct rnbd_clt_dev *dev)
 	return 0;
 
 out_err:
-	dev->blk_symlink_name[0] = '\0';
+	kfree(dev->blk_symlink_name);
+	dev->blk_symlink_name = NULL ;
 	return ret;
 }
 
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index a199b190c73d..45a470076652 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -88,6 +88,8 @@ static int rnbd_clt_set_dev_attr(struct rnbd_clt_dev *dev,
 	dev->discard_alignment	    = le32_to_cpu(rsp->discard_alignment);
 	dev->secure_discard	    = le16_to_cpu(rsp->secure_discard);
 	dev->rotational		    = rsp->rotational;
+	dev->wc 		    = !!(rsp->cache_policy & RNBD_WRITEBACK);
+	dev->fua		    = !!(rsp->cache_policy & RNBD_FUA);
 
 	dev->max_hw_sectors = sess->max_io_size / SECTOR_SIZE;
 	dev->max_segments = BMAX_SEGMENTS;
@@ -347,32 +349,48 @@ static struct rnbd_iu *rnbd_get_iu(struct rnbd_clt_session *sess,
 	struct rnbd_iu *iu;
 	struct rtrs_permit *permit;
 
+	iu = kzalloc(sizeof(*iu), GFP_KERNEL);
+	if (!iu) {
+		return NULL;
+	}
+
 	permit = rnbd_get_permit(sess, con_type,
 				  wait ? RTRS_PERMIT_WAIT :
 				  RTRS_PERMIT_NOWAIT);
-	if (unlikely(!permit))
+	if (unlikely(!permit)) {
+		kfree(iu);
 		return NULL;
-	iu = rtrs_permit_to_pdu(permit);
+	}
+
 	iu->permit = permit;
 	/*
 	 * 1st reference is dropped after finishing sending a "user" message,
 	 * 2nd reference is dropped after confirmation with the response is
 	 * returned.
 	 * 1st and 2nd can happen in any order, so the rnbd_iu should be
-	 * released (rtrs_permit returned to ibbtrs) only leased after both
+	 * released (rtrs_permit returned to rtrs) only after both
 	 * are finished.
 	 */
 	atomic_set(&iu->refcount, 2);
 	init_waitqueue_head(&iu->comp.wait);
 	iu->comp.errno = INT_MAX;
 
+	if (sg_alloc_table(&iu->sgt, 1, GFP_KERNEL)) {
+		rnbd_put_permit(sess, permit);
+		kfree(iu);
+		return NULL;
+	}
+
 	return iu;
 }
 
 static void rnbd_put_iu(struct rnbd_clt_session *sess, struct rnbd_iu *iu)
 {
-	if (atomic_dec_and_test(&iu->refcount))
+	if (atomic_dec_and_test(&iu->refcount)) {
+		sg_free_table(&iu->sgt);
 		rnbd_put_permit(sess, iu->permit);
+		kfree(iu);
+	}
 }
 
 static void rnbd_softirq_done_fn(struct request *rq)
@@ -382,6 +400,7 @@ static void rnbd_softirq_done_fn(struct request *rq)
 	struct rnbd_iu *iu;
 
 	iu = blk_mq_rq_to_pdu(rq);
+	sg_free_table_chained(&iu->sgt, RNBD_INLINE_SG_CNT);
 	rnbd_put_permit(sess, iu->permit);
 	blk_mq_end_request(rq, errno_to_blk_status(iu->errno));
 }
@@ -475,8 +494,6 @@ static int send_msg_close(struct rnbd_clt_dev *dev, u32 device_id, bool wait)
 	iu->buf = NULL;
 	iu->dev = dev;
 
-	sg_mark_end(&iu->sglist[0]);
-
 	msg.hdr.type	= cpu_to_le16(RNBD_MSG_CLOSE);
 	msg.device_id	= cpu_to_le32(device_id);
 
@@ -562,7 +579,7 @@ static int send_msg_open(struct rnbd_clt_dev *dev, bool wait)
 	iu->buf = rsp;
 	iu->dev = dev;
 
-	sg_init_one(iu->sglist, rsp, sizeof(*rsp));
+	sg_init_one(iu->sgt.sgl, rsp, sizeof(*rsp));
 
 	msg.hdr.type	= cpu_to_le16(RNBD_MSG_OPEN);
 	msg.access_mode	= dev->access_mode;
@@ -570,7 +587,7 @@ static int send_msg_open(struct rnbd_clt_dev *dev, bool wait)
 
 	WARN_ON(!rnbd_clt_get_dev(dev));
 	err = send_usr_msg(sess->rtrs, READ, iu,
-			   &vec, sizeof(*rsp), iu->sglist, 1,
+			   &vec, sizeof(*rsp), iu->sgt.sgl, 1,
 			   msg_open_conf, &errno, wait);
 	if (err) {
 		rnbd_clt_put_dev(dev);
@@ -607,8 +624,7 @@ static int send_msg_sess_info(struct rnbd_clt_session *sess, bool wait)
 
 	iu->buf = rsp;
 	iu->sess = sess;
-
-	sg_init_one(iu->sglist, rsp, sizeof(*rsp));
+	sg_init_one(iu->sgt.sgl, rsp, sizeof(*rsp));
 
 	msg.hdr.type = cpu_to_le16(RNBD_MSG_SESS_INFO);
 	msg.ver      = RNBD_PROTO_VER_MAJOR;
@@ -624,7 +640,7 @@ static int send_msg_sess_info(struct rnbd_clt_session *sess, bool wait)
 		goto put_iu;
 	}
 	err = send_usr_msg(sess->rtrs, READ, iu,
-			   &vec, sizeof(*rsp), iu->sglist, 1,
+			   &vec, sizeof(*rsp), iu->sgt.sgl, 1,
 			   msg_sess_info_conf, &errno, wait);
 	if (err) {
 		rnbd_clt_put_sess(sess);
@@ -634,7 +650,6 @@ put_iu:
 	} else {
 		err = errno;
 	}
-
 	rnbd_put_iu(sess, iu);
 	return err;
 }
@@ -803,7 +818,7 @@ static struct rnbd_clt_session *alloc_sess(const char *sessname)
 	rnbd_init_cpu_qlists(sess->cpu_queues);
 
 	/*
-	 * That is simple percpu variable which stores cpu indeces, which are
+	 * That is simple percpu variable which stores cpu indices, which are
 	 * incremented on each access.  We need that for the sake of fairness
 	 * to wake up queues in a round-robin manner.
 	 */
@@ -1014,11 +1029,10 @@ static int rnbd_client_xfer_request(struct rnbd_clt_dev *dev,
 	 * See queue limits.
 	 */
 	if (req_op(rq) != REQ_OP_DISCARD)
-		sg_cnt = blk_rq_map_sg(dev->queue, rq, iu->sglist);
+		sg_cnt = blk_rq_map_sg(dev->queue, rq, iu->sgt.sgl);
 
 	if (sg_cnt == 0)
-		/* Do not forget to mark the end */
-		sg_mark_end(&iu->sglist[0]);
+		sg_mark_end(&iu->sgt.sgl[0]);
 
 	msg.hdr.type	= cpu_to_le16(RNBD_MSG_IO);
 	msg.device_id	= cpu_to_le32(dev->device_id);
@@ -1027,13 +1041,13 @@ static int rnbd_client_xfer_request(struct rnbd_clt_dev *dev,
 		.iov_base = &msg,
 		.iov_len  = sizeof(msg)
 	};
-	size = rnbd_clt_get_sg_size(iu->sglist, sg_cnt);
+	size = rnbd_clt_get_sg_size(iu->sgt.sgl, sg_cnt);
 	req_ops = (struct rtrs_clt_req_ops) {
 		.priv = iu,
 		.conf_fn = msg_io_conf,
 	};
 	err = rtrs_clt_request(rq_data_dir(rq), &req_ops, rtrs, permit,
-			       &vec, 1, size, iu->sglist, sg_cnt);
+			       &vec, 1, size, iu->sgt.sgl, sg_cnt);
 	if (unlikely(err)) {
 		rnbd_clt_err_rl(dev, "RTRS failed to transfer IO, err: %d\n",
 				 err);
@@ -1120,6 +1134,7 @@ static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct rnbd_clt_dev *dev = rq->rq_disk->private_data;
 	struct rnbd_iu *iu = blk_mq_rq_to_pdu(rq);
 	int err;
+	blk_status_t ret = BLK_STS_IOERR;
 
 	if (unlikely(dev->dev_state != DEV_STATE_MAPPED))
 		return BLK_STS_IOERR;
@@ -1131,32 +1146,35 @@ static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 		return BLK_STS_RESOURCE;
 	}
 
+	iu->sgt.sgl = iu->first_sgl;
+	err = sg_alloc_table_chained(&iu->sgt,
+				     /* Even-if the request has no segment,
+				      * sglist must have one entry at least */
+				     blk_rq_nr_phys_segments(rq) ? : 1,
+				     iu->sgt.sgl,
+				     RNBD_INLINE_SG_CNT);
+	if (err) {
+		rnbd_clt_err_rl(dev, "sg_alloc_table_chained ret=%d\n", err);
+		rnbd_clt_dev_kick_mq_queue(dev, hctx, 10/*ms*/);
+		rnbd_put_permit(dev->sess, iu->permit);
+		return BLK_STS_RESOURCE;
+	}
+
 	blk_mq_start_request(rq);
 	err = rnbd_client_xfer_request(dev, rq, iu);
 	if (likely(err == 0))
 		return BLK_STS_OK;
 	if (unlikely(err == -EAGAIN || err == -ENOMEM)) {
 		rnbd_clt_dev_kick_mq_queue(dev, hctx, 10/*ms*/);
-		rnbd_put_permit(dev->sess, iu->permit);
-		return BLK_STS_RESOURCE;
+		ret = BLK_STS_RESOURCE;
 	}
-
+	sg_free_table_chained(&iu->sgt, RNBD_INLINE_SG_CNT);
 	rnbd_put_permit(dev->sess, iu->permit);
-	return BLK_STS_IOERR;
-}
-
-static int rnbd_init_request(struct blk_mq_tag_set *set, struct request *rq,
-			      unsigned int hctx_idx, unsigned int numa_node)
-{
-	struct rnbd_iu *iu = blk_mq_rq_to_pdu(rq);
-
-	sg_init_table(iu->sglist, BMAX_SEGMENTS);
-	return 0;
+	return ret;
 }
 
 static struct blk_mq_ops rnbd_mq_ops = {
 	.queue_rq	= rnbd_queue_rq,
-	.init_request	= rnbd_init_request,
 	.complete	= rnbd_softirq_done_fn,
 };
 
@@ -1170,7 +1188,7 @@ static int setup_mq_tags(struct rnbd_clt_session *sess)
 	tag_set->numa_node		= NUMA_NO_NODE;
 	tag_set->flags		= BLK_MQ_F_SHOULD_MERGE |
 				  BLK_MQ_F_TAG_QUEUE_SHARED;
-	tag_set->cmd_size		= sizeof(struct rnbd_iu);
+	tag_set->cmd_size	= sizeof(struct rnbd_iu) + RNBD_RDMA_SGL_SIZE;
 	tag_set->nr_hw_queues	= num_online_cpus();
 
 	return blk_mq_alloc_tag_set(tag_set);
@@ -1208,7 +1226,7 @@ find_and_get_or_create_sess(const char *sessname,
 	 */
 	sess->rtrs = rtrs_clt_open(&rtrs_ops, sessname,
 				   paths, path_cnt, port_nr,
-				   sizeof(struct rnbd_iu),
+				   0, /* Do not use pdu of rtrs */
 				   RECONNECT_DELAY, BMAX_SEGMENTS,
 				   BLK_MAX_SEGMENT_SIZE,
 				   MAX_RECONNECTS);
@@ -1305,7 +1323,7 @@ static void setup_request_queue(struct rnbd_clt_dev *dev)
 	blk_queue_max_segments(dev->queue, dev->max_segments);
 	blk_queue_io_opt(dev->queue, dev->sess->max_io_size);
 	blk_queue_virt_boundary(dev->queue, SZ_4K - 1);
-	blk_queue_write_cache(dev->queue, true, true);
+	blk_queue_write_cache(dev->queue, dev->wc, dev->fua);
 	dev->queue->queuedata = dev;
 }
 
@@ -1388,12 +1406,11 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess,
 		goto out_queues;
 	}
 
-	dev->pathname = kzalloc(strlen(pathname) + 1, GFP_KERNEL);
+	dev->pathname = kstrdup(pathname, GFP_KERNEL);
 	if (!dev->pathname) {
 		ret = -ENOMEM;
 		goto out_queues;
 	}
-	strlcpy(dev->pathname, pathname, strlen(pathname) + 1);
 
 	dev->clt_device_id	= ret;
 	dev->sess		= sess;
@@ -1529,13 +1546,13 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname,
 	}
 
 	rnbd_clt_info(dev,
-		       "map_device: Device mapped as %s (nsectors: %zu, logical_block_size: %d, physical_block_size: %d, max_write_same_sectors: %d, max_discard_sectors: %d, discard_granularity: %d, discard_alignment: %d, secure_discard: %d, max_segments: %d, max_hw_sectors: %d, rotational: %d)\n",
+		       "map_device: Device mapped as %s (nsectors: %zu, logical_block_size: %d, physical_block_size: %d, max_write_same_sectors: %d, max_discard_sectors: %d, discard_granularity: %d, discard_alignment: %d, secure_discard: %d, max_segments: %d, max_hw_sectors: %d, rotational: %d, wc: %d, fua: %d)\n",
 		       dev->gd->disk_name, dev->nsectors,
 		       dev->logical_block_size, dev->physical_block_size,
 		       dev->max_write_same_sectors, dev->max_discard_sectors,
 		       dev->discard_granularity, dev->discard_alignment,
 		       dev->secure_discard, dev->max_segments,
-		       dev->max_hw_sectors, dev->rotational);
+		       dev->max_hw_sectors, dev->rotational, dev->wc, dev->fua);
 
 	mutex_unlock(&dev->lock);
 
@@ -1667,7 +1684,7 @@ static void rnbd_destroy_sessions(void)
 	/*
 	 * Here at this point there is no any concurrent access to sessions
 	 * list and devices list:
-	 *   1. New session or device can'be be created - session sysfs files
+	 *   1. New session or device can't be created - session sysfs files
 	 *      are removed.
 	 *   2. Device or session can't be removed - module reference is taken
 	 *      into account in unmap device sysfs callback.
@@ -1680,7 +1697,8 @@ static void rnbd_destroy_sessions(void)
 	 */
 
 	list_for_each_entry_safe(sess, sn, &sess_list, list) {
-		WARN_ON(!rnbd_clt_get_sess(sess));
+		if (!rnbd_clt_get_sess(sess))
+			continue;
 		close_rtrs(sess);
 		list_for_each_entry_safe(dev, tn, &sess->devs_list, list) {
 			/*
diff --git a/drivers/block/rnbd/rnbd-clt.h b/drivers/block/rnbd/rnbd-clt.h
index b193d5904050..537d499dad3b 100644
--- a/drivers/block/rnbd/rnbd-clt.h
+++ b/drivers/block/rnbd/rnbd-clt.h
@@ -44,6 +44,13 @@ struct rnbd_iu_comp {
 	int errno;
 };
 
+#ifdef CONFIG_ARCH_NO_SG_CHAIN
+#define RNBD_INLINE_SG_CNT 0
+#else
+#define RNBD_INLINE_SG_CNT 2
+#endif
+#define RNBD_RDMA_SGL_SIZE (sizeof(struct scatterlist) * RNBD_INLINE_SG_CNT)
+
 struct rnbd_iu {
 	union {
 		struct request *rq; /* for block io */
@@ -56,11 +63,12 @@ struct rnbd_iu {
 		/* use to send msg associated with a sess */
 		struct rnbd_clt_session *sess;
 	};
-	struct scatterlist	sglist[BMAX_SEGMENTS];
+	struct sg_table		sgt;
 	struct work_struct	work;
 	int			errno;
 	struct rnbd_iu_comp	comp;
 	atomic_t		refcount;
+	struct scatterlist	first_sgl[]; /* must be the last one */
 };
 
 struct rnbd_cpu_qlist {
@@ -112,6 +120,8 @@ struct rnbd_clt_dev {
 	enum rnbd_access_mode	access_mode;
 	bool			read_only;
 	bool			rotational;
+	bool			wc;
+	bool			fua;
 	u32			max_hw_sectors;
 	u32			max_write_same_sectors;
 	u32			max_discard_sectors;
diff --git a/drivers/block/rnbd/rnbd-proto.h b/drivers/block/rnbd/rnbd-proto.h
index ca166241452c..c1bc5c0fef71 100644
--- a/drivers/block/rnbd/rnbd-proto.h
+++ b/drivers/block/rnbd/rnbd-proto.h
@@ -108,6 +108,11 @@ struct rnbd_msg_close {
 	__le32		device_id;
 };
 
+enum rnbd_cache_policy {
+	RNBD_FUA = 1 << 0,
+	RNBD_WRITEBACK = 1 << 1,
+};
+
 /**
  * struct rnbd_msg_open_rsp - response message to RNBD_MSG_OPEN
  * @hdr:		message header
@@ -124,6 +129,7 @@ struct rnbd_msg_close {
  * @max_segments:	max segments hardware support in one transfer
  * @secure_discard:	supports secure discard
  * @rotation:		is a rotational disc?
+ * @cache_policy: 	support write-back caching or FUA?
  */
 struct rnbd_msg_open_rsp {
 	struct rnbd_msg_hdr	hdr;
@@ -139,7 +145,8 @@ struct rnbd_msg_open_rsp {
 	__le16			max_segments;
 	__le16			secure_discard;
 	u8			rotational;
-	u8			reserved[11];
+	u8			cache_policy;
+	u8			reserved[10];
 };
 
 /**
diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c
index d1ee72ed8384..a6a68d44f517 100644
--- a/drivers/block/rnbd/rnbd-srv.c
+++ b/drivers/block/rnbd/rnbd-srv.c
@@ -338,9 +338,12 @@ static int rnbd_srv_link_ev(struct rtrs_srv *rtrs,
 
 void rnbd_srv_sess_dev_force_close(struct rnbd_srv_sess_dev *sess_dev)
 {
-	rnbd_srv_destroy_dev_session_sysfs(sess_dev);
-	sess_dev->keep_id = true;
+	struct rnbd_srv_session	*sess = sess_dev->sess;
 
+	sess_dev->keep_id = true;
+	mutex_lock(&sess->lock);
+	rnbd_srv_destroy_dev_session_sysfs(sess_dev);
+	mutex_unlock(&sess->lock);
 }
 
 static int process_msg_close(struct rtrs_srv *rtrs,
@@ -549,6 +552,7 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 					struct rnbd_srv_sess_dev *sess_dev)
 {
 	struct rnbd_dev *rnbd_dev = sess_dev->rnbd_dev;
+	struct request_queue *q = bdev_get_queue(rnbd_dev->bdev);
 
 	rsp->hdr.type = cpu_to_le16(RNBD_MSG_OPEN_RSP);
 	rsp->device_id =
@@ -573,8 +577,12 @@ static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp,
 		cpu_to_le32(rnbd_dev_get_discard_alignment(rnbd_dev));
 	rsp->secure_discard =
 		cpu_to_le16(rnbd_dev_get_secure_discard(rnbd_dev));
-	rsp->rotational =
-		!blk_queue_nonrot(bdev_get_queue(rnbd_dev->bdev));
+	rsp->rotational = !blk_queue_nonrot(q);
+	rsp->cache_policy = 0;
+	if (test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+		rsp->cache_policy |= RNBD_WRITEBACK;
+	if (blk_queue_fua(q))
+		rsp->cache_policy |= RNBD_FUA;
 }
 
 static struct rnbd_srv_sess_dev *
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index c715d4681a0b..85856cff506c 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -188,6 +188,14 @@ config COMMON_CLK_CS2000_CP
 	help
 	  If you say yes here you get support for the CS2000 clock multiplier.
 
+config COMMON_CLK_FSL_FLEXSPI
+	tristate "Clock driver for FlexSPI on Layerscape SoCs"
+	depends on ARCH_LAYERSCAPE || COMPILE_TEST
+	default ARCH_LAYERSCAPE && SPI_NXP_FLEXSPI
+	help
+	  On Layerscape SoCs there is a special clock for the FlexSPI
+	  interface.
+
 config COMMON_CLK_FSL_SAI
 	bool "Clock driver for BCLK of Freescale SAI cores"
 	depends on ARCH_LAYERSCAPE || COMPILE_TEST
@@ -246,7 +254,8 @@ config COMMON_CLK_AXI_CLKGEN
 
 config CLK_QORIQ
 	bool "Clock driver for Freescale QorIQ platforms"
-	depends on (PPC_E500MC || ARM || ARM64 || COMPILE_TEST) && OF
+	depends on OF
+	depends on PPC_E500MC || SOC_LS1021A || ARCH_LAYERSCAPE || COMPILE_TEST
 	help
 	  This adds the clock driver support for Freescale QorIQ platforms
 	  using common clock framework.
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index da8fcf147eb1..dbdc590e7de3 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -30,6 +30,7 @@ obj-$(CONFIG_COMMON_CLK_CS2000_CP)	+= clk-cs2000-cp.o
 obj-$(CONFIG_ARCH_EFM32)		+= clk-efm32gg.o
 obj-$(CONFIG_ARCH_SPARX5)		+= clk-sparx5.o
 obj-$(CONFIG_COMMON_CLK_FIXED_MMIO)	+= clk-fixed-mmio.o
+obj-$(CONFIG_COMMON_CLK_FSL_FLEXSPI)	+= clk-fsl-flexspi.o
 obj-$(CONFIG_COMMON_CLK_FSL_SAI)	+= clk-fsl-sai.o
 obj-$(CONFIG_COMMON_CLK_GEMINI)		+= clk-gemini.o
 obj-$(CONFIG_COMMON_CLK_ASPEED)		+= clk-aspeed.o
diff --git a/drivers/clk/at91/at91rm9200.c b/drivers/clk/at91/at91rm9200.c
index 2c3d8e6ca63c..0fad1009f315 100644
--- a/drivers/clk/at91/at91rm9200.c
+++ b/drivers/clk/at91/at91rm9200.c
@@ -7,6 +7,8 @@
 
 #include "pmc.h"
 
+static DEFINE_SPINLOCK(rm9200_mck_lock);
+
 struct sck {
 	char *n;
 	char *p;
@@ -137,9 +139,20 @@ static void __init at91rm9200_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "pllack";
 	parent_names[3] = "pllbck";
-	hw = at91_clk_register_master(regmap, "masterck", 4, parent_names,
-				      &at91rm9200_master_layout,
-				      &rm9200_mck_characteristics);
+	hw = at91_clk_register_master_pres(regmap, "masterck_pres", 4,
+					   parent_names,
+					   &at91rm9200_master_layout,
+					   &rm9200_mck_characteristics,
+					   &rm9200_mck_lock, CLK_SET_RATE_GATE,
+					   INT_MIN);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = at91_clk_register_master_div(regmap, "masterck_div",
+					  "masterck_pres",
+					  &at91rm9200_master_layout,
+					  &rm9200_mck_characteristics,
+					  &rm9200_mck_lock, CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -181,7 +194,7 @@ static void __init at91rm9200_pmc_setup(struct device_node *np)
 	for (i = 0; i < ARRAY_SIZE(at91rm9200_periphck); i++) {
 		hw = at91_clk_register_peripheral(regmap,
 						  at91rm9200_periphck[i].n,
-						  "masterck",
+						  "masterck_div",
 						  at91rm9200_periphck[i].id);
 		if (IS_ERR(hw))
 			goto err_free;
diff --git a/drivers/clk/at91/at91sam9260.c b/drivers/clk/at91/at91sam9260.c
index bb81ff731ad8..ceb5495f723a 100644
--- a/drivers/clk/at91/at91sam9260.c
+++ b/drivers/clk/at91/at91sam9260.c
@@ -32,6 +32,8 @@ struct at91sam926x_data {
 	bool has_slck;
 };
 
+static DEFINE_SPINLOCK(at91sam9260_mck_lock);
+
 static const struct clk_master_characteristics sam9260_mck_characteristics = {
 	.output = { .min = 0, .max = 105000000 },
 	.divisors = { 1, 2, 4, 0 },
@@ -218,8 +220,8 @@ static const struct sck at91sam9261_systemck[] = {
 	{ .n = "pck1",  .p = "prog1",    .id = 9 },
 	{ .n = "pck2",  .p = "prog2",    .id = 10 },
 	{ .n = "pck3",  .p = "prog3",    .id = 11 },
-	{ .n = "hclk0", .p = "masterck", .id = 16 },
-	{ .n = "hclk1", .p = "masterck", .id = 17 },
+	{ .n = "hclk0", .p = "masterck_div", .id = 16 },
+	{ .n = "hclk1", .p = "masterck_div", .id = 17 },
 };
 
 static const struct pck at91sam9261_periphck[] = {
@@ -413,9 +415,21 @@ static void __init at91sam926x_pmc_setup(struct device_node *np,
 	parent_names[1] = "mainck";
 	parent_names[2] = "pllack";
 	parent_names[3] = "pllbck";
-	hw = at91_clk_register_master(regmap, "masterck", 4, parent_names,
-				      &at91rm9200_master_layout,
-				      data->mck_characteristics);
+	hw = at91_clk_register_master_pres(regmap, "masterck_pres", 4,
+					   parent_names,
+					   &at91rm9200_master_layout,
+					   data->mck_characteristics,
+					   &at91sam9260_mck_lock,
+					   CLK_SET_RATE_GATE, INT_MIN);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = at91_clk_register_master_div(regmap, "masterck_div",
+					  "masterck_pres",
+					  &at91rm9200_master_layout,
+					  data->mck_characteristics,
+					  &at91sam9260_mck_lock,
+					  CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -457,7 +471,7 @@ static void __init at91sam926x_pmc_setup(struct device_node *np,
 	for (i = 0; i < data->num_pck; i++) {
 		hw = at91_clk_register_peripheral(regmap,
 						  data->pck[i].n,
-						  "masterck",
+						  "masterck_div",
 						  data->pck[i].id);
 		if (IS_ERR(hw))
 			goto err_free;
diff --git a/drivers/clk/at91/at91sam9g45.c b/drivers/clk/at91/at91sam9g45.c
index cb4a406ed15d..0214333dedd3 100644
--- a/drivers/clk/at91/at91sam9g45.c
+++ b/drivers/clk/at91/at91sam9g45.c
@@ -7,6 +7,8 @@
 
 #include "pmc.h"
 
+static DEFINE_SPINLOCK(at91sam9g45_mck_lock);
+
 static const struct clk_master_characteristics mck_characteristics = {
 	.output = { .min = 0, .max = 133333333 },
 	.divisors = { 1, 2, 4, 3 },
@@ -40,10 +42,10 @@ static const struct {
 	char *p;
 	u8 id;
 } at91sam9g45_systemck[] = {
-	{ .n = "ddrck", .p = "masterck", .id = 2 },
-	{ .n = "uhpck", .p = "usbck",    .id = 6 },
-	{ .n = "pck0",  .p = "prog0",    .id = 8 },
-	{ .n = "pck1",  .p = "prog1",    .id = 9 },
+	{ .n = "ddrck", .p = "masterck_div", .id = 2 },
+	{ .n = "uhpck", .p = "usbck",        .id = 6 },
+	{ .n = "pck0",  .p = "prog0",        .id = 8 },
+	{ .n = "pck1",  .p = "prog1",        .id = 9 },
 };
 
 struct pck {
@@ -148,9 +150,21 @@ static void __init at91sam9g45_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "utmick";
-	hw = at91_clk_register_master(regmap, "masterck", 4, parent_names,
-				      &at91rm9200_master_layout,
-				      &mck_characteristics);
+	hw = at91_clk_register_master_pres(regmap, "masterck_pres", 4,
+					   parent_names,
+					   &at91rm9200_master_layout,
+					   &mck_characteristics,
+					   &at91sam9g45_mck_lock,
+					   CLK_SET_RATE_GATE, INT_MIN);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = at91_clk_register_master_div(regmap, "masterck_div",
+					  "masterck_pres",
+					  &at91rm9200_master_layout,
+					  &mck_characteristics,
+					  &at91sam9g45_mck_lock,
+					  CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -166,7 +180,7 @@ static void __init at91sam9g45_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "utmick";
-	parent_names[4] = "masterck";
+	parent_names[4] = "masterck_div";
 	for (i = 0; i < 2; i++) {
 		char name[6];
 
@@ -195,7 +209,7 @@ static void __init at91sam9g45_pmc_setup(struct device_node *np)
 	for (i = 0; i < ARRAY_SIZE(at91sam9g45_periphck); i++) {
 		hw = at91_clk_register_peripheral(regmap,
 						  at91sam9g45_periphck[i].n,
-						  "masterck",
+						  "masterck_div",
 						  at91sam9g45_periphck[i].id);
 		if (IS_ERR(hw))
 			goto err_free;
diff --git a/drivers/clk/at91/at91sam9n12.c b/drivers/clk/at91/at91sam9n12.c
index 93f7eb216122..f9db5316a7f1 100644
--- a/drivers/clk/at91/at91sam9n12.c
+++ b/drivers/clk/at91/at91sam9n12.c
@@ -7,6 +7,8 @@
 
 #include "pmc.h"
 
+static DEFINE_SPINLOCK(at91sam9n12_mck_lock);
+
 static const struct clk_master_characteristics mck_characteristics = {
 	.output = { .min = 0, .max = 133333333 },
 	.divisors = { 1, 2, 4, 3 },
@@ -54,12 +56,12 @@ static const struct {
 	char *p;
 	u8 id;
 } at91sam9n12_systemck[] = {
-	{ .n = "ddrck", .p = "masterck", .id = 2 },
-	{ .n = "lcdck", .p = "masterck", .id = 3 },
-	{ .n = "uhpck", .p = "usbck",    .id = 6 },
-	{ .n = "udpck", .p = "usbck",    .id = 7 },
-	{ .n = "pck0",  .p = "prog0",    .id = 8 },
-	{ .n = "pck1",  .p = "prog1",    .id = 9 },
+	{ .n = "ddrck", .p = "masterck_div", .id = 2 },
+	{ .n = "lcdck", .p = "masterck_div", .id = 3 },
+	{ .n = "uhpck", .p = "usbck",        .id = 6 },
+	{ .n = "udpck", .p = "usbck",        .id = 7 },
+	{ .n = "pck0",  .p = "prog0",        .id = 8 },
+	{ .n = "pck1",  .p = "prog1",        .id = 9 },
 };
 
 static const struct clk_pcr_layout at91sam9n12_pcr_layout = {
@@ -175,9 +177,21 @@ static void __init at91sam9n12_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "pllbck";
-	hw = at91_clk_register_master(regmap, "masterck", 4, parent_names,
-				      &at91sam9x5_master_layout,
-				      &mck_characteristics);
+	hw = at91_clk_register_master_pres(regmap, "masterck_pres", 4,
+					   parent_names,
+					   &at91sam9x5_master_layout,
+					   &mck_characteristics,
+					   &at91sam9n12_mck_lock,
+					   CLK_SET_RATE_GATE, INT_MIN);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = at91_clk_register_master_div(regmap, "masterck_div",
+					  "masterck_pres",
+					  &at91sam9x5_master_layout,
+					  &mck_characteristics,
+					  &at91sam9n12_mck_lock,
+					  CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -191,7 +205,7 @@ static void __init at91sam9n12_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "pllbck";
-	parent_names[4] = "masterck";
+	parent_names[4] = "masterck_div";
 	for (i = 0; i < 2; i++) {
 		char name[6];
 
@@ -221,7 +235,7 @@ static void __init at91sam9n12_pmc_setup(struct device_node *np)
 		hw = at91_clk_register_sam9x5_peripheral(regmap, &pmc_pcr_lock,
 							 &at91sam9n12_pcr_layout,
 							 at91sam9n12_periphck[i].n,
-							 "masterck",
+							 "masterck_div",
 							 at91sam9n12_periphck[i].id,
 							 &range, INT_MIN);
 		if (IS_ERR(hw))
diff --git a/drivers/clk/at91/at91sam9rl.c b/drivers/clk/at91/at91sam9rl.c
index a343eb69bb35..66736e03cfef 100644
--- a/drivers/clk/at91/at91sam9rl.c
+++ b/drivers/clk/at91/at91sam9rl.c
@@ -7,6 +7,8 @@
 
 #include "pmc.h"
 
+static DEFINE_SPINLOCK(sam9rl_mck_lock);
+
 static const struct clk_master_characteristics sam9rl_mck_characteristics = {
 	.output = { .min = 0, .max = 94000000 },
 	.divisors = { 1, 2, 4, 0 },
@@ -117,9 +119,20 @@ static void __init at91sam9rl_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "pllack";
 	parent_names[3] = "utmick";
-	hw = at91_clk_register_master(regmap, "masterck", 4, parent_names,
-				      &at91rm9200_master_layout,
-				      &sam9rl_mck_characteristics);
+	hw = at91_clk_register_master_pres(regmap, "masterck_pres", 4,
+					   parent_names,
+					   &at91rm9200_master_layout,
+					   &sam9rl_mck_characteristics,
+					   &sam9rl_mck_lock, CLK_SET_RATE_GATE,
+					   INT_MIN);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = at91_clk_register_master_div(regmap, "masterck_div",
+					  "masterck_pres",
+					  &at91rm9200_master_layout,
+					  &sam9rl_mck_characteristics,
+					  &sam9rl_mck_lock, CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -129,7 +142,7 @@ static void __init at91sam9rl_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "pllack";
 	parent_names[3] = "utmick";
-	parent_names[4] = "masterck";
+	parent_names[4] = "masterck_div";
 	for (i = 0; i < 2; i++) {
 		char name[6];
 
@@ -158,7 +171,7 @@ static void __init at91sam9rl_pmc_setup(struct device_node *np)
 	for (i = 0; i < ARRAY_SIZE(at91sam9rl_periphck); i++) {
 		hw = at91_clk_register_peripheral(regmap,
 						  at91sam9rl_periphck[i].n,
-						  "masterck",
+						  "masterck_div",
 						  at91sam9rl_periphck[i].id);
 		if (IS_ERR(hw))
 			goto err_free;
diff --git a/drivers/clk/at91/at91sam9x5.c b/drivers/clk/at91/at91sam9x5.c
index 22b9aad9efb8..79b9d3667228 100644
--- a/drivers/clk/at91/at91sam9x5.c
+++ b/drivers/clk/at91/at91sam9x5.c
@@ -7,6 +7,8 @@
 
 #include "pmc.h"
 
+static DEFINE_SPINLOCK(mck_lock);
+
 static const struct clk_master_characteristics mck_characteristics = {
 	.output = { .min = 0, .max = 133333333 },
 	.divisors = { 1, 2, 4, 3 },
@@ -41,7 +43,7 @@ static const struct {
 	char *p;
 	u8 id;
 } at91sam9x5_systemck[] = {
-	{ .n = "ddrck", .p = "masterck", .id = 2 },
+	{ .n = "ddrck", .p = "masterck_div", .id = 2 },
 	{ .n = "smdck", .p = "smdclk",   .id = 4 },
 	{ .n = "uhpck", .p = "usbck",    .id = 6 },
 	{ .n = "udpck", .p = "usbck",    .id = 7 },
@@ -196,9 +198,19 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np,
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "utmick";
-	hw = at91_clk_register_master(regmap, "masterck", 4, parent_names,
-				      &at91sam9x5_master_layout,
-				      &mck_characteristics);
+	hw = at91_clk_register_master_pres(regmap, "masterck_pres", 4,
+					   parent_names,
+					   &at91sam9x5_master_layout,
+					   &mck_characteristics, &mck_lock,
+					   CLK_SET_RATE_GATE, INT_MIN);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = at91_clk_register_master_div(regmap, "masterck_div",
+					  "masterck_pres",
+					  &at91sam9x5_master_layout,
+					  &mck_characteristics, &mck_lock,
+					  CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -218,7 +230,7 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np,
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "utmick";
-	parent_names[4] = "masterck";
+	parent_names[4] = "masterck_div";
 	for (i = 0; i < 2; i++) {
 		char name[6];
 
@@ -245,7 +257,7 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np,
 	}
 
 	if (has_lcdck) {
-		hw = at91_clk_register_system(regmap, "lcdck", "masterck", 3);
+		hw = at91_clk_register_system(regmap, "lcdck", "masterck_div", 3);
 		if (IS_ERR(hw))
 			goto err_free;
 
@@ -256,7 +268,7 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np,
 		hw = at91_clk_register_sam9x5_peripheral(regmap, &pmc_pcr_lock,
 							 &at91sam9x5_pcr_layout,
 							 at91sam9x5_periphck[i].n,
-							 "masterck",
+							 "masterck_div",
 							 at91sam9x5_periphck[i].id,
 							 &range, INT_MIN);
 		if (IS_ERR(hw))
@@ -269,7 +281,7 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np,
 		hw = at91_clk_register_sam9x5_peripheral(regmap, &pmc_pcr_lock,
 							 &at91sam9x5_pcr_layout,
 							 extra_pcks[i].n,
-							 "masterck",
+							 "masterck_div",
 							 extra_pcks[i].id,
 							 &range, INT_MIN);
 		if (IS_ERR(hw))
diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index bd0d8a69a2cf..a80427980bf7 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -15,7 +15,7 @@
 #define MASTER_PRES_MASK	0x7
 #define MASTER_PRES_MAX		MASTER_PRES_MASK
 #define MASTER_DIV_SHIFT	8
-#define MASTER_DIV_MASK		0x3
+#define MASTER_DIV_MASK		0x7
 
 #define PMC_MCR			0x30
 #define PMC_MCR_ID_MSK		GENMASK(3, 0)
@@ -58,83 +58,309 @@ static inline bool clk_master_ready(struct clk_master *master)
 static int clk_master_prepare(struct clk_hw *hw)
 {
 	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+
+	spin_lock_irqsave(master->lock, flags);
 
 	while (!clk_master_ready(master))
 		cpu_relax();
 
+	spin_unlock_irqrestore(master->lock, flags);
+
 	return 0;
 }
 
 static int clk_master_is_prepared(struct clk_hw *hw)
 {
 	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+	bool status;
 
-	return clk_master_ready(master);
+	spin_lock_irqsave(master->lock, flags);
+	status = clk_master_ready(master);
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return status;
 }
 
-static unsigned long clk_master_recalc_rate(struct clk_hw *hw,
-					    unsigned long parent_rate)
+static unsigned long clk_master_div_recalc_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
 {
-	u8 pres;
 	u8 div;
-	unsigned long rate = parent_rate;
+	unsigned long flags, rate = parent_rate;
 	struct clk_master *master = to_clk_master(hw);
 	const struct clk_master_layout *layout = master->layout;
 	const struct clk_master_characteristics *characteristics =
 						master->characteristics;
 	unsigned int mckr;
 
+	spin_lock_irqsave(master->lock, flags);
 	regmap_read(master->regmap, master->layout->offset, &mckr);
+	spin_unlock_irqrestore(master->lock, flags);
+
 	mckr &= layout->mask;
 
-	pres = (mckr >> layout->pres_shift) & MASTER_PRES_MASK;
 	div = (mckr >> MASTER_DIV_SHIFT) & MASTER_DIV_MASK;
 
-	if (characteristics->have_div3_pres && pres == MASTER_PRES_MAX)
-		rate /= 3;
-	else
-		rate >>= pres;
-
 	rate /= characteristics->divisors[div];
 
 	if (rate < characteristics->output.min)
-		pr_warn("master clk is underclocked");
+		pr_warn("master clk div is underclocked");
 	else if (rate > characteristics->output.max)
-		pr_warn("master clk is overclocked");
+		pr_warn("master clk div is overclocked");
 
 	return rate;
 }
 
-static u8 clk_master_get_parent(struct clk_hw *hw)
+static const struct clk_ops master_div_ops = {
+	.prepare = clk_master_prepare,
+	.is_prepared = clk_master_is_prepared,
+	.recalc_rate = clk_master_div_recalc_rate,
+};
+
+static int clk_master_div_set_rate(struct clk_hw *hw, unsigned long rate,
+				   unsigned long parent_rate)
+{
+	struct clk_master *master = to_clk_master(hw);
+	const struct clk_master_characteristics *characteristics =
+						master->characteristics;
+	unsigned long flags;
+	int div, i;
+
+	div = DIV_ROUND_CLOSEST(parent_rate, rate);
+	if (div > ARRAY_SIZE(characteristics->divisors))
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(characteristics->divisors); i++) {
+		if (!characteristics->divisors[i])
+			break;
+
+		if (div == characteristics->divisors[i]) {
+			div = i;
+			break;
+		}
+	}
+
+	if (i == ARRAY_SIZE(characteristics->divisors))
+		return -EINVAL;
+
+	spin_lock_irqsave(master->lock, flags);
+	regmap_update_bits(master->regmap, master->layout->offset,
+			   (MASTER_DIV_MASK << MASTER_DIV_SHIFT),
+			   (div << MASTER_DIV_SHIFT));
+	while (!clk_master_ready(master))
+		cpu_relax();
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return 0;
+}
+
+static int clk_master_div_determine_rate(struct clk_hw *hw,
+					 struct clk_rate_request *req)
+{
+	struct clk_master *master = to_clk_master(hw);
+	const struct clk_master_characteristics *characteristics =
+						master->characteristics;
+	struct clk_hw *parent;
+	unsigned long parent_rate, tmp_rate, best_rate = 0;
+	int i, best_diff = INT_MIN, tmp_diff;
+
+	parent = clk_hw_get_parent(hw);
+	if (!parent)
+		return -EINVAL;
+
+	parent_rate = clk_hw_get_rate(parent);
+	if (!parent_rate)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(characteristics->divisors); i++) {
+		if (!characteristics->divisors[i])
+			break;
+
+		tmp_rate = DIV_ROUND_CLOSEST_ULL(parent_rate,
+						 characteristics->divisors[i]);
+		tmp_diff = abs(tmp_rate - req->rate);
+
+		if (!best_rate || best_diff > tmp_diff) {
+			best_diff = tmp_diff;
+			best_rate = tmp_rate;
+		}
+
+		if (!best_diff)
+			break;
+	}
+
+	req->best_parent_rate = best_rate;
+	req->best_parent_hw = parent;
+	req->rate = best_rate;
+
+	return 0;
+}
+
+static const struct clk_ops master_div_ops_chg = {
+	.prepare = clk_master_prepare,
+	.is_prepared = clk_master_is_prepared,
+	.recalc_rate = clk_master_div_recalc_rate,
+	.determine_rate = clk_master_div_determine_rate,
+	.set_rate = clk_master_div_set_rate,
+};
+
+static void clk_sama7g5_master_best_diff(struct clk_rate_request *req,
+					 struct clk_hw *parent,
+					 unsigned long parent_rate,
+					 long *best_rate,
+					 long *best_diff,
+					 u32 div)
+{
+	unsigned long tmp_rate, tmp_diff;
+
+	if (div == MASTER_PRES_MAX)
+		tmp_rate = parent_rate / 3;
+	else
+		tmp_rate = parent_rate >> div;
+
+	tmp_diff = abs(req->rate - tmp_rate);
+
+	if (*best_diff < 0 || *best_diff >= tmp_diff) {
+		*best_rate = tmp_rate;
+		*best_diff = tmp_diff;
+		req->best_parent_rate = parent_rate;
+		req->best_parent_hw = parent;
+	}
+}
+
+static int clk_master_pres_determine_rate(struct clk_hw *hw,
+					  struct clk_rate_request *req)
 {
 	struct clk_master *master = to_clk_master(hw);
+	struct clk_rate_request req_parent = *req;
+	const struct clk_master_characteristics *characteristics =
+							master->characteristics;
+	struct clk_hw *parent;
+	long best_rate = LONG_MIN, best_diff = LONG_MIN;
+	u32 pres;
+	int i;
+
+	if (master->chg_pid < 0)
+		return -EOPNOTSUPP;
+
+	parent = clk_hw_get_parent_by_index(hw, master->chg_pid);
+	if (!parent)
+		return -EOPNOTSUPP;
+
+	for (i = 0; i <= MASTER_PRES_MAX; i++) {
+		if (characteristics->have_div3_pres && i == MASTER_PRES_MAX)
+			pres = 3;
+		else
+			pres = 1 << i;
+
+		req_parent.rate = req->rate * pres;
+		if (__clk_determine_rate(parent, &req_parent))
+			continue;
+
+		clk_sama7g5_master_best_diff(req, parent, req_parent.rate,
+					     &best_diff, &best_rate, pres);
+		if (!best_diff)
+			break;
+	}
+
+	return 0;
+}
+
+static int clk_master_pres_set_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long parent_rate)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
+	unsigned int pres;
+
+	pres = DIV_ROUND_CLOSEST(parent_rate, rate);
+	if (pres > MASTER_PRES_MAX)
+		return -EINVAL;
+
+	else if (pres == 3)
+		pres = MASTER_PRES_MAX;
+	else
+		pres = ffs(pres) - 1;
+
+	spin_lock_irqsave(master->lock, flags);
+	regmap_update_bits(master->regmap, master->layout->offset,
+			   (MASTER_PRES_MASK << master->layout->pres_shift),
+			   (pres << master->layout->pres_shift));
+
+	while (!clk_master_ready(master))
+		cpu_relax();
+	spin_unlock_irqrestore(master->lock, flags);
+
+	return 0;
+}
+
+static unsigned long clk_master_pres_recalc_rate(struct clk_hw *hw,
+						 unsigned long parent_rate)
+{
+	struct clk_master *master = to_clk_master(hw);
+	const struct clk_master_characteristics *characteristics =
+						master->characteristics;
+	unsigned long flags;
+	unsigned int val, pres;
+
+	spin_lock_irqsave(master->lock, flags);
+	regmap_read(master->regmap, master->layout->offset, &val);
+	spin_unlock_irqrestore(master->lock, flags);
+
+	pres = (val >> master->layout->pres_shift) & MASTER_PRES_MASK;
+	if (pres == 3 && characteristics->have_div3_pres)
+		pres = 3;
+	else
+		pres = (1 << pres);
+
+	return DIV_ROUND_CLOSEST_ULL(parent_rate, pres);
+}
+
+static u8 clk_master_pres_get_parent(struct clk_hw *hw)
+{
+	struct clk_master *master = to_clk_master(hw);
+	unsigned long flags;
 	unsigned int mckr;
 
+	spin_lock_irqsave(master->lock, flags);
 	regmap_read(master->regmap, master->layout->offset, &mckr);
+	spin_unlock_irqrestore(master->lock, flags);
 
 	return mckr & AT91_PMC_CSS;
 }
 
-static const struct clk_ops master_ops = {
+static const struct clk_ops master_pres_ops = {
 	.prepare = clk_master_prepare,
 	.is_prepared = clk_master_is_prepared,
-	.recalc_rate = clk_master_recalc_rate,
-	.get_parent = clk_master_get_parent,
+	.recalc_rate = clk_master_pres_recalc_rate,
+	.get_parent = clk_master_pres_get_parent,
 };
 
-struct clk_hw * __init
-at91_clk_register_master(struct regmap *regmap,
+static const struct clk_ops master_pres_ops_chg = {
+	.prepare = clk_master_prepare,
+	.is_prepared = clk_master_is_prepared,
+	.determine_rate = clk_master_pres_determine_rate,
+	.recalc_rate = clk_master_pres_recalc_rate,
+	.get_parent = clk_master_pres_get_parent,
+	.set_rate = clk_master_pres_set_rate,
+};
+
+static struct clk_hw * __init
+at91_clk_register_master_internal(struct regmap *regmap,
 		const char *name, int num_parents,
 		const char **parent_names,
 		const struct clk_master_layout *layout,
-		const struct clk_master_characteristics *characteristics)
+		const struct clk_master_characteristics *characteristics,
+		const struct clk_ops *ops, spinlock_t *lock, u32 flags,
+		int chg_pid)
 {
 	struct clk_master *master;
 	struct clk_init_data init;
 	struct clk_hw *hw;
 	int ret;
 
-	if (!name || !num_parents || !parent_names)
+	if (!name || !num_parents || !parent_names || !lock)
 		return ERR_PTR(-EINVAL);
 
 	master = kzalloc(sizeof(*master), GFP_KERNEL);
@@ -142,15 +368,17 @@ at91_clk_register_master(struct regmap *regmap,
 		return ERR_PTR(-ENOMEM);
 
 	init.name = name;
-	init.ops = &master_ops;
+	init.ops = ops;
 	init.parent_names = parent_names;
 	init.num_parents = num_parents;
-	init.flags = 0;
+	init.flags = flags;
 
 	master->hw.init = &init;
 	master->layout = layout;
 	master->characteristics = characteristics;
 	master->regmap = regmap;
+	master->chg_pid = chg_pid;
+	master->lock = lock;
 
 	hw = &master->hw;
 	ret = clk_hw_register(NULL, &master->hw);
@@ -162,37 +390,54 @@ at91_clk_register_master(struct regmap *regmap,
 	return hw;
 }
 
-static unsigned long
-clk_sama7g5_master_recalc_rate(struct clk_hw *hw,
-			       unsigned long parent_rate)
+struct clk_hw * __init
+at91_clk_register_master_pres(struct regmap *regmap,
+		const char *name, int num_parents,
+		const char **parent_names,
+		const struct clk_master_layout *layout,
+		const struct clk_master_characteristics *characteristics,
+		spinlock_t *lock, u32 flags, int chg_pid)
 {
-	struct clk_master *master = to_clk_master(hw);
+	const struct clk_ops *ops;
 
-	return DIV_ROUND_CLOSEST_ULL(parent_rate, (1 << master->div));
+	if (flags & CLK_SET_RATE_GATE)
+		ops = &master_pres_ops;
+	else
+		ops = &master_pres_ops_chg;
+
+	return at91_clk_register_master_internal(regmap, name, num_parents,
+						 parent_names, layout,
+						 characteristics, ops,
+						 lock, flags, chg_pid);
 }
 
-static void clk_sama7g5_master_best_diff(struct clk_rate_request *req,
-					 struct clk_hw *parent,
-					 unsigned long parent_rate,
-					 long *best_rate,
-					 long *best_diff,
-					 u32 div)
+struct clk_hw * __init
+at91_clk_register_master_div(struct regmap *regmap,
+		const char *name, const char *parent_name,
+		const struct clk_master_layout *layout,
+		const struct clk_master_characteristics *characteristics,
+		spinlock_t *lock, u32 flags)
 {
-	unsigned long tmp_rate, tmp_diff;
+	const struct clk_ops *ops;
 
-	if (div == MASTER_PRES_MAX)
-		tmp_rate = parent_rate / 3;
+	if (flags & CLK_SET_RATE_GATE)
+		ops = &master_div_ops;
 	else
-		tmp_rate = parent_rate >> div;
+		ops = &master_div_ops_chg;
 
-	tmp_diff = abs(req->rate - tmp_rate);
+	return at91_clk_register_master_internal(regmap, name, 1,
+						 &parent_name, layout,
+						 characteristics, ops,
+						 lock, flags, -EINVAL);
+}
 
-	if (*best_diff < 0 || *best_diff >= tmp_diff) {
-		*best_rate = tmp_rate;
-		*best_diff = tmp_diff;
-		req->best_parent_rate = parent_rate;
-		req->best_parent_hw = parent;
-	}
+static unsigned long
+clk_sama7g5_master_recalc_rate(struct clk_hw *hw,
+			       unsigned long parent_rate)
+{
+	struct clk_master *master = to_clk_master(hw);
+
+	return DIV_ROUND_CLOSEST_ULL(parent_rate, (1 << master->div));
 }
 
 static int clk_sama7g5_master_determine_rate(struct clk_hw *hw,
diff --git a/drivers/clk/at91/clk-sam9x60-pll.c b/drivers/clk/at91/clk-sam9x60-pll.c
index 78f458a7b2ef..34e3ab13741a 100644
--- a/drivers/clk/at91/clk-sam9x60-pll.c
+++ b/drivers/clk/at91/clk-sam9x60-pll.c
@@ -229,6 +229,57 @@ static int sam9x60_frac_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	return sam9x60_frac_pll_compute_mul_frac(core, rate, parent_rate, true);
 }
 
+static int sam9x60_frac_pll_set_rate_chg(struct clk_hw *hw, unsigned long rate,
+					 unsigned long parent_rate)
+{
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+	struct sam9x60_frac *frac = to_sam9x60_frac(core);
+	struct regmap *regmap = core->regmap;
+	unsigned long irqflags;
+	unsigned int val, cfrac, cmul;
+	long ret;
+
+	ret = sam9x60_frac_pll_compute_mul_frac(core, rate, parent_rate, true);
+	if (ret <= 0)
+		return ret;
+
+	spin_lock_irqsave(core->lock, irqflags);
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT, AT91_PMC_PLL_UPDT_ID_MSK,
+			   core->id);
+	regmap_read(regmap, AT91_PMC_PLL_CTRL1, &val);
+	cmul = (val & core->layout->mul_mask) >> core->layout->mul_shift;
+	cfrac = (val & core->layout->frac_mask) >> core->layout->frac_shift;
+
+	if (cmul == frac->mul && cfrac == frac->frac)
+		goto unlock;
+
+	regmap_write(regmap, AT91_PMC_PLL_CTRL1,
+		     (frac->mul << core->layout->mul_shift) |
+		     (frac->frac << core->layout->frac_shift));
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_UPDATE | AT91_PMC_PLL_UPDT_ID_MSK,
+			   AT91_PMC_PLL_UPDT_UPDATE | core->id);
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_CTRL0,
+			   AT91_PMC_PLL_CTRL0_ENLOCK | AT91_PMC_PLL_CTRL0_ENPLL,
+			   AT91_PMC_PLL_CTRL0_ENLOCK |
+			   AT91_PMC_PLL_CTRL0_ENPLL);
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_UPDATE | AT91_PMC_PLL_UPDT_ID_MSK,
+			   AT91_PMC_PLL_UPDT_UPDATE | core->id);
+
+	while (!sam9x60_pll_ready(regmap, core->id))
+		cpu_relax();
+
+unlock:
+	spin_unlock_irqrestore(core->lock, irqflags);
+
+	return ret;
+}
+
 static const struct clk_ops sam9x60_frac_pll_ops = {
 	.prepare = sam9x60_frac_pll_prepare,
 	.unprepare = sam9x60_frac_pll_unprepare,
@@ -238,6 +289,15 @@ static const struct clk_ops sam9x60_frac_pll_ops = {
 	.set_rate = sam9x60_frac_pll_set_rate,
 };
 
+static const struct clk_ops sam9x60_frac_pll_ops_chg = {
+	.prepare = sam9x60_frac_pll_prepare,
+	.unprepare = sam9x60_frac_pll_unprepare,
+	.is_prepared = sam9x60_frac_pll_is_prepared,
+	.recalc_rate = sam9x60_frac_pll_recalc_rate,
+	.round_rate = sam9x60_frac_pll_round_rate,
+	.set_rate = sam9x60_frac_pll_set_rate_chg,
+};
+
 static int sam9x60_div_pll_prepare(struct clk_hw *hw)
 {
 	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
@@ -384,6 +444,44 @@ static int sam9x60_div_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
+static int sam9x60_div_pll_set_rate_chg(struct clk_hw *hw, unsigned long rate,
+					unsigned long parent_rate)
+{
+	struct sam9x60_pll_core *core = to_sam9x60_pll_core(hw);
+	struct sam9x60_div *div = to_sam9x60_div(core);
+	struct regmap *regmap = core->regmap;
+	unsigned long irqflags;
+	unsigned int val, cdiv;
+
+	div->div = DIV_ROUND_CLOSEST(parent_rate, rate) - 1;
+
+	spin_lock_irqsave(core->lock, irqflags);
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT, AT91_PMC_PLL_UPDT_ID_MSK,
+			   core->id);
+	regmap_read(regmap, AT91_PMC_PLL_CTRL0, &val);
+	cdiv = (val & core->layout->div_mask) >> core->layout->div_shift;
+
+	/* Stop if nothing changed. */
+	if (cdiv == div->div)
+		goto unlock;
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_CTRL0,
+			   core->layout->div_mask,
+			   (div->div << core->layout->div_shift));
+
+	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
+			   AT91_PMC_PLL_UPDT_UPDATE | AT91_PMC_PLL_UPDT_ID_MSK,
+			   AT91_PMC_PLL_UPDT_UPDATE | core->id);
+
+	while (!sam9x60_pll_ready(regmap, core->id))
+		cpu_relax();
+
+unlock:
+	spin_unlock_irqrestore(core->lock, irqflags);
+
+	return 0;
+}
+
 static const struct clk_ops sam9x60_div_pll_ops = {
 	.prepare = sam9x60_div_pll_prepare,
 	.unprepare = sam9x60_div_pll_unprepare,
@@ -393,17 +491,26 @@ static const struct clk_ops sam9x60_div_pll_ops = {
 	.set_rate = sam9x60_div_pll_set_rate,
 };
 
+static const struct clk_ops sam9x60_div_pll_ops_chg = {
+	.prepare = sam9x60_div_pll_prepare,
+	.unprepare = sam9x60_div_pll_unprepare,
+	.is_prepared = sam9x60_div_pll_is_prepared,
+	.recalc_rate = sam9x60_div_pll_recalc_rate,
+	.round_rate = sam9x60_div_pll_round_rate,
+	.set_rate = sam9x60_div_pll_set_rate_chg,
+};
+
 struct clk_hw * __init
 sam9x60_clk_register_frac_pll(struct regmap *regmap, spinlock_t *lock,
 			      const char *name, const char *parent_name,
 			      struct clk_hw *parent_hw, u8 id,
 			      const struct clk_pll_characteristics *characteristics,
-			      const struct clk_pll_layout *layout, bool critical)
+			      const struct clk_pll_layout *layout, u32 flags)
 {
 	struct sam9x60_frac *frac;
 	struct clk_hw *hw;
 	struct clk_init_data init;
-	unsigned long parent_rate, flags;
+	unsigned long parent_rate, irqflags;
 	unsigned int val;
 	int ret;
 
@@ -417,10 +524,12 @@ sam9x60_clk_register_frac_pll(struct regmap *regmap, spinlock_t *lock,
 	init.name = name;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
-	init.ops = &sam9x60_frac_pll_ops;
-	init.flags = CLK_SET_RATE_GATE;
-	if (critical)
-		init.flags |= CLK_IS_CRITICAL;
+	if (flags & CLK_SET_RATE_GATE)
+		init.ops = &sam9x60_frac_pll_ops;
+	else
+		init.ops = &sam9x60_frac_pll_ops_chg;
+
+	init.flags = flags;
 
 	frac->core.id = id;
 	frac->core.hw.init = &init;
@@ -429,7 +538,7 @@ sam9x60_clk_register_frac_pll(struct regmap *regmap, spinlock_t *lock,
 	frac->core.regmap = regmap;
 	frac->core.lock = lock;
 
-	spin_lock_irqsave(frac->core.lock, flags);
+	spin_lock_irqsave(frac->core.lock, irqflags);
 	if (sam9x60_pll_ready(regmap, id)) {
 		regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
 				   AT91_PMC_PLL_UPDT_ID_MSK, id);
@@ -457,7 +566,7 @@ sam9x60_clk_register_frac_pll(struct regmap *regmap, spinlock_t *lock,
 			goto free;
 		}
 	}
-	spin_unlock_irqrestore(frac->core.lock, flags);
+	spin_unlock_irqrestore(frac->core.lock, irqflags);
 
 	hw = &frac->core.hw;
 	ret = clk_hw_register(NULL, hw);
@@ -469,7 +578,7 @@ sam9x60_clk_register_frac_pll(struct regmap *regmap, spinlock_t *lock,
 	return hw;
 
 free:
-	spin_unlock_irqrestore(frac->core.lock, flags);
+	spin_unlock_irqrestore(frac->core.lock, irqflags);
 	kfree(frac);
 	return hw;
 }
@@ -478,12 +587,12 @@ struct clk_hw * __init
 sam9x60_clk_register_div_pll(struct regmap *regmap, spinlock_t *lock,
 			     const char *name, const char *parent_name, u8 id,
 			     const struct clk_pll_characteristics *characteristics,
-			     const struct clk_pll_layout *layout, bool critical)
+			     const struct clk_pll_layout *layout, u32 flags)
 {
 	struct sam9x60_div *div;
 	struct clk_hw *hw;
 	struct clk_init_data init;
-	unsigned long flags;
+	unsigned long irqflags;
 	unsigned int val;
 	int ret;
 
@@ -497,11 +606,11 @@ sam9x60_clk_register_div_pll(struct regmap *regmap, spinlock_t *lock,
 	init.name = name;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
-	init.ops = &sam9x60_div_pll_ops;
-	init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE |
-		     CLK_SET_RATE_PARENT;
-	if (critical)
-		init.flags |= CLK_IS_CRITICAL;
+	if (flags & CLK_SET_RATE_GATE)
+		init.ops = &sam9x60_div_pll_ops;
+	else
+		init.ops = &sam9x60_div_pll_ops_chg;
+	init.flags = flags;
 
 	div->core.id = id;
 	div->core.hw.init = &init;
@@ -510,14 +619,14 @@ sam9x60_clk_register_div_pll(struct regmap *regmap, spinlock_t *lock,
 	div->core.regmap = regmap;
 	div->core.lock = lock;
 
-	spin_lock_irqsave(div->core.lock, flags);
+	spin_lock_irqsave(div->core.lock, irqflags);
 
 	regmap_update_bits(regmap, AT91_PMC_PLL_UPDT,
 			   AT91_PMC_PLL_UPDT_ID_MSK, id);
 	regmap_read(regmap, AT91_PMC_PLL_CTRL0, &val);
 	div->div = FIELD_GET(PMC_PLL_CTRL0_DIV_MSK, val);
 
-	spin_unlock_irqrestore(div->core.lock, flags);
+	spin_unlock_irqrestore(div->core.lock, irqflags);
 
 	hw = &div->core.hw;
 	ret = clk_hw_register(NULL, hw);
diff --git a/drivers/clk/at91/dt-compat.c b/drivers/clk/at91/dt-compat.c
index a50084de97d4..a97b99c2dc12 100644
--- a/drivers/clk/at91/dt-compat.c
+++ b/drivers/clk/at91/dt-compat.c
@@ -24,6 +24,8 @@
 
 #define GCK_INDEX_DT_AUDIO_PLL	5
 
+static DEFINE_SPINLOCK(mck_lock);
+
 #ifdef CONFIG_HAVE_AT91_AUDIO_PLL
 static void __init of_sama5d2_clk_audio_pll_frac_setup(struct device_node *np)
 {
@@ -388,9 +390,16 @@ of_at91_clk_master_setup(struct device_node *np,
 	if (IS_ERR(regmap))
 		return;
 
-	hw = at91_clk_register_master(regmap, name, num_parents,
-				      parent_names, layout,
-				      characteristics);
+	hw = at91_clk_register_master_pres(regmap, "masterck_pres", num_parents,
+					   parent_names, layout,
+					   characteristics, &mck_lock,
+					   CLK_SET_RATE_GATE, INT_MIN);
+	if (IS_ERR(hw))
+		goto out_free_characteristics;
+
+	hw = at91_clk_register_master_div(regmap, name, "masterck_pres",
+					  layout, characteristics,
+					  &mck_lock, CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto out_free_characteristics;
 
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 7b86affc6d7c..a49076c804a9 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -48,7 +48,7 @@ extern const struct clk_master_layout at91sam9x5_master_layout;
 
 struct clk_master_characteristics {
 	struct clk_range output;
-	u32 divisors[4];
+	u32 divisors[5];
 	u8 have_div3_pres;
 };
 
@@ -155,10 +155,18 @@ at91_clk_register_sam9x5_main(struct regmap *regmap, const char *name,
 			      const char **parent_names, int num_parents);
 
 struct clk_hw * __init
-at91_clk_register_master(struct regmap *regmap, const char *name,
-			 int num_parents, const char **parent_names,
-			 const struct clk_master_layout *layout,
-			 const struct clk_master_characteristics *characteristics);
+at91_clk_register_master_pres(struct regmap *regmap, const char *name,
+			      int num_parents, const char **parent_names,
+			      const struct clk_master_layout *layout,
+			      const struct clk_master_characteristics *characteristics,
+			      spinlock_t *lock, u32 flags, int chg_pid);
+
+struct clk_hw * __init
+at91_clk_register_master_div(struct regmap *regmap, const char *name,
+			     const char *parent_names,
+			     const struct clk_master_layout *layout,
+			     const struct clk_master_characteristics *characteristics,
+			     spinlock_t *lock, u32 flags);
 
 struct clk_hw * __init
 at91_clk_sama7g5_register_master(struct regmap *regmap,
@@ -190,14 +198,14 @@ struct clk_hw * __init
 sam9x60_clk_register_div_pll(struct regmap *regmap, spinlock_t *lock,
 			     const char *name, const char *parent_name, u8 id,
 			     const struct clk_pll_characteristics *characteristics,
-			     const struct clk_pll_layout *layout, bool critical);
+			     const struct clk_pll_layout *layout, u32 flags);
 
 struct clk_hw * __init
 sam9x60_clk_register_frac_pll(struct regmap *regmap, spinlock_t *lock,
 			      const char *name, const char *parent_name,
 			      struct clk_hw *parent_hw, u8 id,
 			      const struct clk_pll_characteristics *characteristics,
-			      const struct clk_pll_layout *layout, bool critical);
+			      const struct clk_pll_layout *layout, u32 flags);
 
 struct clk_hw * __init
 at91_clk_register_programmable(struct regmap *regmap, const char *name,
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index 3c4c95603595..5f6fa89571b7 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -8,6 +8,7 @@
 #include "pmc.h"
 
 static DEFINE_SPINLOCK(pmc_pll_lock);
+static DEFINE_SPINLOCK(mck_lock);
 
 static const struct clk_master_characteristics mck_characteristics = {
 	.output = { .min = 140000000, .max = 200000000 },
@@ -76,11 +77,11 @@ static const struct {
 	char *p;
 	u8 id;
 } sam9x60_systemck[] = {
-	{ .n = "ddrck",  .p = "masterck", .id = 2 },
+	{ .n = "ddrck",  .p = "masterck_div", .id = 2 },
 	{ .n = "uhpck",  .p = "usbck",    .id = 6 },
 	{ .n = "pck0",   .p = "prog0",    .id = 8 },
 	{ .n = "pck1",   .p = "prog1",    .id = 9 },
-	{ .n = "qspick", .p = "masterck", .id = 19 },
+	{ .n = "qspick", .p = "masterck_div", .id = 19 },
 };
 
 static const struct {
@@ -174,7 +175,6 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 	struct regmap *regmap;
 	struct clk_hw *hw;
 	int i;
-	bool bypass;
 
 	i = of_property_match_string(np, "clock-names", "td_slck");
 	if (i < 0)
@@ -209,10 +209,7 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 	if (IS_ERR(hw))
 		goto err_free;
 
-	bypass = of_property_read_bool(np, "atmel,osc-bypass");
-
-	hw = at91_clk_register_main_osc(regmap, "main_osc", mainxtal_name,
-					bypass);
+	hw = at91_clk_register_main_osc(regmap, "main_osc", mainxtal_name, 0);
 	if (IS_ERR(hw))
 		goto err_free;
 	main_osc_hw = hw;
@@ -228,13 +225,24 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 	hw = sam9x60_clk_register_frac_pll(regmap, &pmc_pll_lock, "pllack_fracck",
 					   "mainck", sam9x60_pmc->chws[PMC_MAIN],
 					   0, &plla_characteristics,
-					   &pll_frac_layout, true);
+					   &pll_frac_layout,
+					   /*
+					    * This feeds pllack_divck which
+					    * feeds CPU. It should not be
+					    * disabled.
+					    */
+					   CLK_IS_CRITICAL | CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
 	hw = sam9x60_clk_register_div_pll(regmap, &pmc_pll_lock, "pllack_divck",
 					  "pllack_fracck", 0, &plla_characteristics,
-					  &pll_div_layout, true);
+					  &pll_div_layout,
+					   /*
+					    * This feeds CPU. It should not
+					    * be disabled.
+					    */
+					  CLK_IS_CRITICAL | CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -243,13 +251,16 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 	hw = sam9x60_clk_register_frac_pll(regmap, &pmc_pll_lock, "upllck_fracck",
 					   "main_osc", main_osc_hw, 1,
 					   &upll_characteristics,
-					   &pll_frac_layout, false);
+					   &pll_frac_layout, CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
 	hw = sam9x60_clk_register_div_pll(regmap, &pmc_pll_lock, "upllck_divck",
 					  "upllck_fracck", 1, &upll_characteristics,
-					  &pll_div_layout, false);
+					  &pll_div_layout,
+					  CLK_SET_RATE_GATE |
+					  CLK_SET_PARENT_GATE |
+					  CLK_SET_RATE_PARENT);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -258,9 +269,17 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 	parent_names[0] = md_slck_name;
 	parent_names[1] = "mainck";
 	parent_names[2] = "pllack_divck";
-	hw = at91_clk_register_master(regmap, "masterck", 3, parent_names,
-				      &sam9x60_master_layout,
-				      &mck_characteristics);
+	hw = at91_clk_register_master_pres(regmap, "masterck_pres", 3,
+					   parent_names, &sam9x60_master_layout,
+					   &mck_characteristics, &mck_lock,
+					   CLK_SET_RATE_GATE, INT_MIN);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = at91_clk_register_master_div(regmap, "masterck_div",
+					  "masterck_pres", &sam9x60_master_layout,
+					  &mck_characteristics, &mck_lock,
+					  CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -276,7 +295,7 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 	parent_names[0] = md_slck_name;
 	parent_names[1] = td_slck_name;
 	parent_names[2] = "mainck";
-	parent_names[3] = "masterck";
+	parent_names[3] = "masterck_div";
 	parent_names[4] = "pllack_divck";
 	parent_names[5] = "upllck_divck";
 	for (i = 0; i < 2; i++) {
@@ -308,7 +327,7 @@ static void __init sam9x60_pmc_setup(struct device_node *np)
 		hw = at91_clk_register_sam9x5_peripheral(regmap, &pmc_pcr_lock,
 							 &sam9x60_pcr_layout,
 							 sam9x60_periphck[i].n,
-							 "masterck",
+							 "masterck_div",
 							 sam9x60_periphck[i].id,
 							 &range, INT_MIN);
 		if (IS_ERR(hw))
diff --git a/drivers/clk/at91/sama5d2.c b/drivers/clk/at91/sama5d2.c
index 8b220762941a..9a5cbc7cd55a 100644
--- a/drivers/clk/at91/sama5d2.c
+++ b/drivers/clk/at91/sama5d2.c
@@ -7,6 +7,8 @@
 
 #include "pmc.h"
 
+static DEFINE_SPINLOCK(mck_lock);
+
 static const struct clk_master_characteristics mck_characteristics = {
 	.output = { .min = 124000000, .max = 166000000 },
 	.divisors = { 1, 2, 4, 3 },
@@ -40,14 +42,14 @@ static const struct {
 	char *p;
 	u8 id;
 } sama5d2_systemck[] = {
-	{ .n = "ddrck", .p = "masterck", .id = 2 },
-	{ .n = "lcdck", .p = "masterck", .id = 3 },
-	{ .n = "uhpck", .p = "usbck",    .id = 6 },
-	{ .n = "udpck", .p = "usbck",    .id = 7 },
-	{ .n = "pck0",  .p = "prog0",    .id = 8 },
-	{ .n = "pck1",  .p = "prog1",    .id = 9 },
-	{ .n = "pck2",  .p = "prog2",    .id = 10 },
-	{ .n = "iscck", .p = "masterck", .id = 18 },
+	{ .n = "ddrck", .p = "masterck_div", .id = 2 },
+	{ .n = "lcdck", .p = "masterck_div", .id = 3 },
+	{ .n = "uhpck", .p = "usbck",        .id = 6 },
+	{ .n = "udpck", .p = "usbck",        .id = 7 },
+	{ .n = "pck0",  .p = "prog0",        .id = 8 },
+	{ .n = "pck1",  .p = "prog1",        .id = 9 },
+	{ .n = "pck2",  .p = "prog2",        .id = 10 },
+	{ .n = "iscck", .p = "masterck_div", .id = 18 },
 };
 
 static const struct {
@@ -235,15 +237,25 @@ static void __init sama5d2_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "utmick";
-	hw = at91_clk_register_master(regmap, "masterck", 4, parent_names,
-				      &at91sam9x5_master_layout,
-				      &mck_characteristics);
+	hw = at91_clk_register_master_pres(regmap, "masterck_pres", 4,
+					   parent_names,
+					   &at91sam9x5_master_layout,
+					   &mck_characteristics, &mck_lock,
+					   CLK_SET_RATE_GATE, INT_MIN);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = at91_clk_register_master_div(regmap, "masterck_div",
+					  "masterck_pres",
+					  &at91sam9x5_master_layout,
+					  &mck_characteristics, &mck_lock,
+					  CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
 	sama5d2_pmc->chws[PMC_MCK] = hw;
 
-	hw = at91_clk_register_h32mx(regmap, "h32mxck", "masterck");
+	hw = at91_clk_register_h32mx(regmap, "h32mxck", "masterck_div");
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -259,7 +271,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "utmick";
-	parent_names[4] = "masterck";
+	parent_names[4] = "masterck_div";
 	parent_names[5] = "audiopll_pmcck";
 	for (i = 0; i < 3; i++) {
 		char name[6];
@@ -290,7 +302,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np)
 		hw = at91_clk_register_sam9x5_peripheral(regmap, &pmc_pcr_lock,
 							 &sama5d2_pcr_layout,
 							 sama5d2_periphck[i].n,
-							 "masterck",
+							 "masterck_div",
 							 sama5d2_periphck[i].id,
 							 &range, INT_MIN);
 		if (IS_ERR(hw))
@@ -317,7 +329,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "utmick";
-	parent_names[4] = "masterck";
+	parent_names[4] = "masterck_div";
 	parent_names[5] = "audiopll_pmcck";
 	for (i = 0; i < ARRAY_SIZE(sama5d2_gck); i++) {
 		hw = at91_clk_register_generated(regmap, &pmc_pcr_lock,
diff --git a/drivers/clk/at91/sama5d3.c b/drivers/clk/at91/sama5d3.c
index 7c6e0a5b9dc8..87009ee8effc 100644
--- a/drivers/clk/at91/sama5d3.c
+++ b/drivers/clk/at91/sama5d3.c
@@ -7,6 +7,8 @@
 
 #include "pmc.h"
 
+static DEFINE_SPINLOCK(mck_lock);
+
 static const struct clk_master_characteristics mck_characteristics = {
 	.output = { .min = 0, .max = 166000000 },
 	.divisors = { 1, 2, 4, 3 },
@@ -40,14 +42,14 @@ static const struct {
 	char *p;
 	u8 id;
 } sama5d3_systemck[] = {
-	{ .n = "ddrck", .p = "masterck", .id = 2 },
-	{ .n = "lcdck", .p = "masterck", .id = 3 },
-	{ .n = "smdck", .p = "smdclk",   .id = 4 },
-	{ .n = "uhpck", .p = "usbck",    .id = 6 },
-	{ .n = "udpck", .p = "usbck",    .id = 7 },
-	{ .n = "pck0",  .p = "prog0",    .id = 8 },
-	{ .n = "pck1",  .p = "prog1",    .id = 9 },
-	{ .n = "pck2",  .p = "prog2",    .id = 10 },
+	{ .n = "ddrck", .p = "masterck_div", .id = 2 },
+	{ .n = "lcdck", .p = "masterck_div", .id = 3 },
+	{ .n = "smdck", .p = "smdclk",       .id = 4 },
+	{ .n = "uhpck", .p = "usbck",        .id = 6 },
+	{ .n = "udpck", .p = "usbck",        .id = 7 },
+	{ .n = "pck0",  .p = "prog0",        .id = 8 },
+	{ .n = "pck1",  .p = "prog1",        .id = 9 },
+	{ .n = "pck2",  .p = "prog2",        .id = 10 },
 };
 
 static const struct {
@@ -170,9 +172,19 @@ static void __init sama5d3_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "utmick";
-	hw = at91_clk_register_master(regmap, "masterck", 4, parent_names,
-				      &at91sam9x5_master_layout,
-				      &mck_characteristics);
+	hw = at91_clk_register_master_pres(regmap, "masterck_pres", 4,
+					   parent_names,
+					   &at91sam9x5_master_layout,
+					   &mck_characteristics, &mck_lock,
+					   CLK_SET_RATE_GATE, INT_MIN);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = at91_clk_register_master_div(regmap, "masterck_div",
+					  "masterck_pres",
+					  &at91sam9x5_master_layout,
+					  &mck_characteristics, &mck_lock,
+					  CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -192,7 +204,7 @@ static void __init sama5d3_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "utmick";
-	parent_names[4] = "masterck";
+	parent_names[4] = "masterck_div";
 	for (i = 0; i < 3; i++) {
 		char name[6];
 
@@ -222,7 +234,7 @@ static void __init sama5d3_pmc_setup(struct device_node *np)
 		hw = at91_clk_register_sam9x5_peripheral(regmap, &pmc_pcr_lock,
 							 &sama5d3_pcr_layout,
 							 sama5d3_periphck[i].n,
-							 "masterck",
+							 "masterck_div",
 							 sama5d3_periphck[i].id,
 							 &sama5d3_periphck[i].r,
 							 INT_MIN);
diff --git a/drivers/clk/at91/sama5d4.c b/drivers/clk/at91/sama5d4.c
index 92d8d4141b43..57fff790188b 100644
--- a/drivers/clk/at91/sama5d4.c
+++ b/drivers/clk/at91/sama5d4.c
@@ -7,6 +7,8 @@
 
 #include "pmc.h"
 
+static DEFINE_SPINLOCK(mck_lock);
+
 static const struct clk_master_characteristics mck_characteristics = {
 	.output = { .min = 125000000, .max = 200000000 },
 	.divisors = { 1, 2, 4, 3 },
@@ -39,14 +41,14 @@ static const struct {
 	char *p;
 	u8 id;
 } sama5d4_systemck[] = {
-	{ .n = "ddrck", .p = "masterck", .id = 2 },
-	{ .n = "lcdck", .p = "masterck", .id = 3 },
-	{ .n = "smdck", .p = "smdclk",   .id = 4 },
-	{ .n = "uhpck", .p = "usbck",    .id = 6 },
-	{ .n = "udpck", .p = "usbck",    .id = 7 },
-	{ .n = "pck0",  .p = "prog0",    .id = 8 },
-	{ .n = "pck1",  .p = "prog1",    .id = 9 },
-	{ .n = "pck2",  .p = "prog2",    .id = 10 },
+	{ .n = "ddrck", .p = "masterck_div", .id = 2 },
+	{ .n = "lcdck", .p = "masterck_div", .id = 3 },
+	{ .n = "smdck", .p = "smdclk",       .id = 4 },
+	{ .n = "uhpck", .p = "usbck",        .id = 6 },
+	{ .n = "udpck", .p = "usbck",        .id = 7 },
+	{ .n = "pck0",  .p = "prog0",        .id = 8 },
+	{ .n = "pck1",  .p = "prog1",        .id = 9 },
+	{ .n = "pck2",  .p = "prog2",        .id = 10 },
 };
 
 static const struct {
@@ -185,15 +187,25 @@ static void __init sama5d4_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "utmick";
-	hw = at91_clk_register_master(regmap, "masterck", 4, parent_names,
-				      &at91sam9x5_master_layout,
-				      &mck_characteristics);
+	hw = at91_clk_register_master_pres(regmap, "masterck_pres", 4,
+					   parent_names,
+					   &at91sam9x5_master_layout,
+					   &mck_characteristics, &mck_lock,
+					   CLK_SET_RATE_GATE, INT_MIN);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	hw = at91_clk_register_master_div(regmap, "masterck_div",
+					  "masterck_pres",
+					  &at91sam9x5_master_layout,
+					  &mck_characteristics, &mck_lock,
+					  CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		goto err_free;
 
 	sama5d4_pmc->chws[PMC_MCK] = hw;
 
-	hw = at91_clk_register_h32mx(regmap, "h32mxck", "masterck");
+	hw = at91_clk_register_h32mx(regmap, "h32mxck", "masterck_div");
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -215,7 +227,7 @@ static void __init sama5d4_pmc_setup(struct device_node *np)
 	parent_names[1] = "mainck";
 	parent_names[2] = "plladivck";
 	parent_names[3] = "utmick";
-	parent_names[4] = "masterck";
+	parent_names[4] = "masterck_div";
 	for (i = 0; i < 3; i++) {
 		char name[6];
 
@@ -245,7 +257,7 @@ static void __init sama5d4_pmc_setup(struct device_node *np)
 		hw = at91_clk_register_sam9x5_peripheral(regmap, &pmc_pcr_lock,
 							 &sama5d4_pcr_layout,
 							 sama5d4_periphck[i].n,
-							 "masterck",
+							 "masterck_div",
 							 sama5d4_periphck[i].id,
 							 &range, INT_MIN);
 		if (IS_ERR(hw))
diff --git a/drivers/clk/at91/sama7g5.c b/drivers/clk/at91/sama7g5.c
index 0db2ab3eca14..a6e20b35960e 100644
--- a/drivers/clk/at91/sama7g5.c
+++ b/drivers/clk/at91/sama7g5.c
@@ -32,6 +32,7 @@
 	} while (0)
 
 static DEFINE_SPINLOCK(pmc_pll_lock);
+static DEFINE_SPINLOCK(pmc_mck0_lock);
 static DEFINE_SPINLOCK(pmc_mckX_lock);
 
 /**
@@ -89,118 +90,198 @@ static const struct clk_pll_layout pll_layout_divio = {
 	.endiv_shift	= 30,
 };
 
+/*
+ * CPU PLL output range.
+ * Notice: The upper limit has been setup to 1000000002 due to hardware
+ * block which cannot output exactly 1GHz.
+ */
+static const struct clk_range cpu_pll_outputs[] = {
+	{ .min = 2343750, .max = 1000000002 },
+};
+
+/* PLL output range. */
+static const struct clk_range pll_outputs[] = {
+	{ .min = 2343750, .max = 1200000000 },
+};
+
+/* CPU PLL characteristics. */
+static const struct clk_pll_characteristics cpu_pll_characteristics = {
+	.input = { .min = 12000000, .max = 50000000 },
+	.num_output = ARRAY_SIZE(cpu_pll_outputs),
+	.output = cpu_pll_outputs,
+};
+
+/* PLL characteristics. */
+static const struct clk_pll_characteristics pll_characteristics = {
+	.input = { .min = 12000000, .max = 50000000 },
+	.num_output = ARRAY_SIZE(pll_outputs),
+	.output = pll_outputs,
+};
+
 /**
  * PLL clocks description
  * @n:		clock name
  * @p:		clock parent
  * @l:		clock layout
+ * @c:		clock characteristics
  * @t:		clock type
- * @f:		true if clock is critical and cannot be disabled
+ * @f:		clock flags
  * @eid:	export index in sama7g5->chws[] array
  */
 static const struct {
 	const char *n;
 	const char *p;
 	const struct clk_pll_layout *l;
+	const struct clk_pll_characteristics *c;
+	unsigned long f;
 	u8 t;
-	u8 c;
 	u8 eid;
 } sama7g5_plls[][PLL_ID_MAX] = {
 	[PLL_ID_CPU] = {
 		{ .n = "cpupll_fracck",
 		  .p = "mainck",
 		  .l = &pll_layout_frac,
+		  .c = &cpu_pll_characteristics,
 		  .t = PLL_TYPE_FRAC,
-		  .c = 1, },
+		   /*
+		    * This feeds cpupll_divpmcck which feeds CPU. It should
+		    * not be disabled.
+		    */
+		  .f = CLK_IS_CRITICAL, },
 
 		{ .n = "cpupll_divpmcck",
 		  .p = "cpupll_fracck",
 		  .l = &pll_layout_divpmc,
+		  .c = &cpu_pll_characteristics,
 		  .t = PLL_TYPE_DIV,
-		  .c = 1, },
+		   /* This feeds CPU. It should not be disabled. */
+		  .f = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT,
+		  .eid = PMC_CPUPLL, },
 	},
 
 	[PLL_ID_SYS] = {
 		{ .n = "syspll_fracck",
 		  .p = "mainck",
 		  .l = &pll_layout_frac,
+		  .c = &pll_characteristics,
 		  .t = PLL_TYPE_FRAC,
-		  .c = 1, },
+		   /*
+		    * This feeds syspll_divpmcck which may feed critial parts
+		    * of the systems like timers. Therefore it should not be
+		    * disabled.
+		    */
+		  .f = CLK_IS_CRITICAL | CLK_SET_RATE_GATE, },
 
 		{ .n = "syspll_divpmcck",
 		  .p = "syspll_fracck",
 		  .l = &pll_layout_divpmc,
+		  .c = &pll_characteristics,
 		  .t = PLL_TYPE_DIV,
-		  .c = 1, },
+		   /*
+		    * This may feed critial parts of the systems like timers.
+		    * Therefore it should not be disabled.
+		    */
+		  .f = CLK_IS_CRITICAL | CLK_SET_RATE_GATE,
+		  .eid = PMC_SYSPLL, },
 	},
 
 	[PLL_ID_DDR] = {
 		{ .n = "ddrpll_fracck",
 		  .p = "mainck",
 		  .l = &pll_layout_frac,
+		  .c = &pll_characteristics,
 		  .t = PLL_TYPE_FRAC,
-		  .c = 1, },
+		   /*
+		    * This feeds ddrpll_divpmcck which feeds DDR. It should not
+		    * be disabled.
+		    */
+		  .f = CLK_IS_CRITICAL | CLK_SET_RATE_GATE, },
 
 		{ .n = "ddrpll_divpmcck",
 		  .p = "ddrpll_fracck",
 		  .l = &pll_layout_divpmc,
+		  .c = &pll_characteristics,
 		  .t = PLL_TYPE_DIV,
-		  .c = 1, },
+		   /* This feeds DDR. It should not be disabled. */
+		  .f = CLK_IS_CRITICAL | CLK_SET_RATE_GATE, },
 	},
 
 	[PLL_ID_IMG] = {
 		{ .n = "imgpll_fracck",
 		  .p = "mainck",
 		  .l = &pll_layout_frac,
-		  .t = PLL_TYPE_FRAC, },
+		  .c = &pll_characteristics,
+		  .t = PLL_TYPE_FRAC,
+		  .f = CLK_SET_RATE_GATE, },
 
 		{ .n = "imgpll_divpmcck",
 		  .p = "imgpll_fracck",
 		  .l = &pll_layout_divpmc,
-		  .t = PLL_TYPE_DIV, },
+		  .c = &pll_characteristics,
+		  .t = PLL_TYPE_DIV,
+		  .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE |
+		       CLK_SET_RATE_PARENT, },
 	},
 
 	[PLL_ID_BAUD] = {
 		{ .n = "baudpll_fracck",
 		  .p = "mainck",
 		  .l = &pll_layout_frac,
-		  .t = PLL_TYPE_FRAC, },
+		  .c = &pll_characteristics,
+		  .t = PLL_TYPE_FRAC,
+		  .f = CLK_SET_RATE_GATE, },
 
 		{ .n = "baudpll_divpmcck",
 		  .p = "baudpll_fracck",
 		  .l = &pll_layout_divpmc,
-		  .t = PLL_TYPE_DIV, },
+		  .c = &pll_characteristics,
+		  .t = PLL_TYPE_DIV,
+		  .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE |
+		       CLK_SET_RATE_PARENT, },
 	},
 
 	[PLL_ID_AUDIO] = {
 		{ .n = "audiopll_fracck",
 		  .p = "main_xtal",
 		  .l = &pll_layout_frac,
-		  .t = PLL_TYPE_FRAC, },
+		  .c = &pll_characteristics,
+		  .t = PLL_TYPE_FRAC,
+		  .f = CLK_SET_RATE_GATE, },
 
 		{ .n = "audiopll_divpmcck",
 		  .p = "audiopll_fracck",
 		  .l = &pll_layout_divpmc,
+		  .c = &pll_characteristics,
 		  .t = PLL_TYPE_DIV,
-		  .eid = PMC_I2S0_MUX, },
+		  .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE |
+		       CLK_SET_RATE_PARENT,
+		  .eid = PMC_AUDIOPMCPLL, },
 
 		{ .n = "audiopll_diviock",
 		  .p = "audiopll_fracck",
 		  .l = &pll_layout_divio,
+		  .c = &pll_characteristics,
 		  .t = PLL_TYPE_DIV,
-		  .eid = PMC_I2S1_MUX, },
+		  .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE |
+		       CLK_SET_RATE_PARENT,
+		  .eid = PMC_AUDIOIOPLL, },
 	},
 
 	[PLL_ID_ETH] = {
 		{ .n = "ethpll_fracck",
 		  .p = "main_xtal",
 		  .l = &pll_layout_frac,
-		  .t = PLL_TYPE_FRAC, },
+		  .c = &pll_characteristics,
+		  .t = PLL_TYPE_FRAC,
+		  .f = CLK_SET_RATE_GATE, },
 
 		{ .n = "ethpll_divpmcck",
 		  .p = "ethpll_fracck",
 		  .l = &pll_layout_divpmc,
-		  .t = PLL_TYPE_DIV, },
+		  .c = &pll_characteristics,
+		  .t = PLL_TYPE_DIV,
+		  .f = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE |
+		       CLK_SET_RATE_PARENT, },
 	},
 };
 
@@ -245,7 +326,7 @@ static const struct {
 	  .ep = { "syspll_divpmcck", "ddrpll_divpmcck", "imgpll_divpmcck", },
 	  .ep_mux_table = { 5, 6, 7, },
 	  .ep_count = 3,
-	  .ep_chg_id = 6, },
+	  .ep_chg_id = 5, },
 
 	{ .n = "mck4",
 	  .id = 4,
@@ -278,7 +359,7 @@ static const struct {
 };
 
 /* Mux table for programmable clocks. */
-static u32 sama7g5_prog_mux_table[] = { 0, 1, 2, 3, 5, 6, 7, 8, 9, 10, };
+static u32 sama7g5_prog_mux_table[] = { 0, 1, 2, 5, 6, 7, 8, 9, 10, };
 
 /**
  * Peripheral clock description
@@ -401,7 +482,7 @@ static const struct {
 	  .pp = { "audiopll_divpmcck", },
 	  .pp_mux_table = { 9, },
 	  .pp_count = 1,
-	  .pp_chg_id = 4, },
+	  .pp_chg_id = 3, },
 
 	{ .n  = "csi_gclk",
 	  .id = 33,
@@ -513,7 +594,7 @@ static const struct {
 	  .pp = { "ethpll_divpmcck", },
 	  .pp_mux_table = { 10, },
 	  .pp_count = 1,
-	  .pp_chg_id = 4, },
+	  .pp_chg_id = 3, },
 
 	{ .n  = "gmac1_gclk",
 	  .id = 52,
@@ -545,7 +626,7 @@ static const struct {
 	  .pp = { "syspll_divpmcck", "audiopll_divpmcck", },
 	  .pp_mux_table = { 5, 9, },
 	  .pp_count = 2,
-	  .pp_chg_id = 5, },
+	  .pp_chg_id = 4, },
 
 	{ .n  = "i2smcc1_gclk",
 	  .id = 58,
@@ -553,7 +634,7 @@ static const struct {
 	  .pp = { "syspll_divpmcck", "audiopll_divpmcck", },
 	  .pp_mux_table = { 5, 9, },
 	  .pp_count = 2,
-	  .pp_chg_id = 5, },
+	  .pp_chg_id = 4, },
 
 	{ .n  = "mcan0_gclk",
 	  .id = 61,
@@ -695,7 +776,7 @@ static const struct {
 	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
 	  .pp_mux_table = { 5, 8, },
 	  .pp_count = 2,
-	  .pp_chg_id = 5, },
+	  .pp_chg_id = 4, },
 
 	{ .n  = "sdmmc1_gclk",
 	  .id = 81,
@@ -703,7 +784,7 @@ static const struct {
 	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
 	  .pp_mux_table = { 5, 8, },
 	  .pp_count = 2,
-	  .pp_chg_id = 5, },
+	  .pp_chg_id = 4, },
 
 	{ .n  = "sdmmc2_gclk",
 	  .id = 82,
@@ -711,7 +792,7 @@ static const struct {
 	  .pp = { "syspll_divpmcck", "baudpll_divpmcck", },
 	  .pp_mux_table = { 5, 8, },
 	  .pp_count = 2,
-	  .pp_chg_id = 5, },
+	  .pp_chg_id = 4, },
 
 	{ .n  = "spdifrx_gclk",
 	  .id = 84,
@@ -719,7 +800,7 @@ static const struct {
 	  .pp = { "syspll_divpmcck", "audiopll_divpmcck", },
 	  .pp_mux_table = { 5, 9, },
 	  .pp_count = 2,
-	  .pp_chg_id = 5, },
+	  .pp_chg_id = 4, },
 
 	{ .n = "spdiftx_gclk",
 	  .id = 85,
@@ -727,7 +808,7 @@ static const struct {
 	  .pp = { "syspll_divpmcck", "audiopll_divpmcck", },
 	  .pp_mux_table = { 5, 9, },
 	  .pp_count = 2,
-	  .pp_chg_id = 5, },
+	  .pp_chg_id = 4, },
 
 	{ .n  = "tcb0_ch0_gclk",
 	  .id = 88,
@@ -758,28 +839,16 @@ static const struct {
 	  .pp_chg_id = INT_MIN, },
 };
 
-/* PLL output range. */
-static const struct clk_range pll_outputs[] = {
-	{ .min = 2343750, .max = 1200000000 },
-};
-
-/* PLL characteristics. */
-static const struct clk_pll_characteristics pll_characteristics = {
-	.input = { .min = 12000000, .max = 50000000 },
-	.num_output = ARRAY_SIZE(pll_outputs),
-	.output = pll_outputs,
-};
-
 /* MCK0 characteristics. */
 static const struct clk_master_characteristics mck0_characteristics = {
-	.output = { .min = 140000000, .max = 200000000 },
-	.divisors = { 1, 2, 4, 3 },
+	.output = { .min = 50000000, .max = 200000000 },
+	.divisors = { 1, 2, 4, 3, 5 },
 	.have_div3_pres = 1,
 };
 
 /* MCK0 layout. */
 static const struct clk_master_layout mck0_layout = {
-	.mask = 0x373,
+	.mask = 0x773,
 	.pres_shift = 4,
 	.offset = 0x28,
 };
@@ -835,10 +904,10 @@ static void __init sama7g5_pmc_setup(struct device_node *np)
 	if (IS_ERR(regmap))
 		return;
 
-	sama7g5_pmc = pmc_data_allocate(PMC_I2S1_MUX + 1,
+	sama7g5_pmc = pmc_data_allocate(PMC_CPU + 1,
 					nck(sama7g5_systemck),
 					nck(sama7g5_periphck),
-					nck(sama7g5_gck));
+					nck(sama7g5_gck), 8);
 	if (!sama7g5_pmc)
 		return;
 
@@ -886,18 +955,18 @@ static void __init sama7g5_pmc_setup(struct device_node *np)
 				hw = sam9x60_clk_register_frac_pll(regmap,
 					&pmc_pll_lock, sama7g5_plls[i][j].n,
 					sama7g5_plls[i][j].p, parent_hw, i,
-					&pll_characteristics,
+					sama7g5_plls[i][j].c,
 					sama7g5_plls[i][j].l,
-					sama7g5_plls[i][j].c);
+					sama7g5_plls[i][j].f);
 				break;
 
 			case PLL_TYPE_DIV:
 				hw = sam9x60_clk_register_div_pll(regmap,
 					&pmc_pll_lock, sama7g5_plls[i][j].n,
 					sama7g5_plls[i][j].p, i,
-					&pll_characteristics,
+					sama7g5_plls[i][j].c,
 					sama7g5_plls[i][j].l,
-					sama7g5_plls[i][j].c);
+					sama7g5_plls[i][j].f);
 				break;
 
 			default:
@@ -912,12 +981,19 @@ static void __init sama7g5_pmc_setup(struct device_node *np)
 		}
 	}
 
-	parent_names[0] = md_slck_name;
-	parent_names[1] = "mainck";
-	parent_names[2] = "cpupll_divpmcck";
-	parent_names[3] = "syspll_divpmcck";
-	hw = at91_clk_register_master(regmap, "mck0", 4, parent_names,
-				      &mck0_layout, &mck0_characteristics);
+	parent_names[0] = "cpupll_divpmcck";
+	hw = at91_clk_register_master_pres(regmap, "cpuck", 1, parent_names,
+					   &mck0_layout, &mck0_characteristics,
+					   &pmc_mck0_lock,
+					   CLK_SET_RATE_PARENT, 0);
+	if (IS_ERR(hw))
+		goto err_free;
+
+	sama7g5_pmc->chws[PMC_CPU] = hw;
+
+	hw = at91_clk_register_master_div(regmap, "mck0", "cpuck",
+					  &mck0_layout, &mck0_characteristics,
+					  &pmc_mck0_lock, 0);
 	if (IS_ERR(hw))
 		goto err_free;
 
@@ -926,9 +1002,8 @@ static void __init sama7g5_pmc_setup(struct device_node *np)
 	parent_names[0] = md_slck_name;
 	parent_names[1] = td_slck_name;
 	parent_names[2] = "mainck";
-	parent_names[3] = "mck0";
 	for (i = 0; i < ARRAY_SIZE(sama7g5_mckx); i++) {
-		u8 num_parents = 4 + sama7g5_mckx[i].ep_count;
+		u8 num_parents = 3 + sama7g5_mckx[i].ep_count;
 		u32 *mux_table;
 
 		mux_table = kmalloc_array(num_parents, sizeof(*mux_table),
@@ -936,10 +1011,10 @@ static void __init sama7g5_pmc_setup(struct device_node *np)
 		if (!mux_table)
 			goto err_free;
 
-		SAMA7G5_INIT_TABLE(mux_table, 4);
-		SAMA7G5_FILL_TABLE(&mux_table[4], sama7g5_mckx[i].ep_mux_table,
+		SAMA7G5_INIT_TABLE(mux_table, 3);
+		SAMA7G5_FILL_TABLE(&mux_table[3], sama7g5_mckx[i].ep_mux_table,
 				   sama7g5_mckx[i].ep_count);
-		SAMA7G5_FILL_TABLE(&parent_names[4], sama7g5_mckx[i].ep,
+		SAMA7G5_FILL_TABLE(&parent_names[3], sama7g5_mckx[i].ep,
 				   sama7g5_mckx[i].ep_count);
 
 		hw = at91_clk_sama7g5_register_master(regmap, sama7g5_mckx[i].n,
@@ -962,24 +1037,25 @@ static void __init sama7g5_pmc_setup(struct device_node *np)
 	parent_names[0] = md_slck_name;
 	parent_names[1] = td_slck_name;
 	parent_names[2] = "mainck";
-	parent_names[3] = "mck0";
-	parent_names[4] = "syspll_divpmcck";
-	parent_names[5] = "ddrpll_divpmcck";
-	parent_names[6] = "imgpll_divpmcck";
-	parent_names[7] = "baudpll_divpmcck";
-	parent_names[8] = "audiopll_divpmcck";
-	parent_names[9] = "ethpll_divpmcck";
+	parent_names[3] = "syspll_divpmcck";
+	parent_names[4] = "ddrpll_divpmcck";
+	parent_names[5] = "imgpll_divpmcck";
+	parent_names[6] = "baudpll_divpmcck";
+	parent_names[7] = "audiopll_divpmcck";
+	parent_names[8] = "ethpll_divpmcck";
 	for (i = 0; i < 8; i++) {
 		char name[6];
 
 		snprintf(name, sizeof(name), "prog%d", i);
 
 		hw = at91_clk_register_programmable(regmap, name, parent_names,
-						    10, i,
+						    9, i,
 						    &programmable_layout,
 						    sama7g5_prog_mux_table);
 		if (IS_ERR(hw))
 			goto err_free;
+
+		sama7g5_pmc->pchws[i] = hw;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(sama7g5_systemck); i++) {
@@ -1010,9 +1086,8 @@ static void __init sama7g5_pmc_setup(struct device_node *np)
 	parent_names[0] = md_slck_name;
 	parent_names[1] = td_slck_name;
 	parent_names[2] = "mainck";
-	parent_names[3] = "mck0";
 	for (i = 0; i < ARRAY_SIZE(sama7g5_gck); i++) {
-		u8 num_parents = 4 + sama7g5_gck[i].pp_count;
+		u8 num_parents = 3 + sama7g5_gck[i].pp_count;
 		u32 *mux_table;
 
 		mux_table = kmalloc_array(num_parents, sizeof(*mux_table),
@@ -1020,10 +1095,10 @@ static void __init sama7g5_pmc_setup(struct device_node *np)
 		if (!mux_table)
 			goto err_free;
 
-		SAMA7G5_INIT_TABLE(mux_table, 4);
-		SAMA7G5_FILL_TABLE(&mux_table[4], sama7g5_gck[i].pp_mux_table,
+		SAMA7G5_INIT_TABLE(mux_table, 3);
+		SAMA7G5_FILL_TABLE(&mux_table[3], sama7g5_gck[i].pp_mux_table,
 				   sama7g5_gck[i].pp_count);
-		SAMA7G5_FILL_TABLE(&parent_names[4], sama7g5_gck[i].pp,
+		SAMA7G5_FILL_TABLE(&parent_names[3], sama7g5_gck[i].pp,
 				   sama7g5_gck[i].pp_count);
 
 		hw = at91_clk_register_generated(regmap, &pmc_pcr_lock,
@@ -1052,7 +1127,7 @@ err_free:
 		kfree(alloc_mem);
 	}
 
-	pmc_data_free(sama7g5_pmc);
+	kfree(sama7g5_pmc);
 }
 
 /* Some clks are used for a clocksource */
diff --git a/drivers/clk/bcm/clk-bcm2711-dvp.c b/drivers/clk/bcm/clk-bcm2711-dvp.c
index 8333e20dc9d2..e63a42618ac2 100644
--- a/drivers/clk/bcm/clk-bcm2711-dvp.c
+++ b/drivers/clk/bcm/clk-bcm2711-dvp.c
@@ -25,7 +25,6 @@ static const struct clk_parent_data clk_dvp_parent = {
 static int clk_dvp_probe(struct platform_device *pdev)
 {
 	struct clk_hw_onecell_data *data;
-	struct resource *res;
 	struct clk_dvp *dvp;
 	void __iomem *base;
 	int ret;
@@ -42,7 +41,7 @@ static int clk_dvp_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	data = dvp->data;
 
-	base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
@@ -108,6 +107,7 @@ static const struct of_device_id clk_dvp_dt_ids[] = {
 	{ .compatible = "brcm,brcm2711-dvp", },
 	{ /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, clk_dvp_dt_ids);
 
 static struct platform_driver clk_dvp_driver = {
 	.probe	= clk_dvp_probe,
diff --git a/drivers/clk/clk-axi-clkgen.c b/drivers/clk/clk-axi-clkgen.c
index 14d803e6af62..ad86e031ba3e 100644
--- a/drivers/clk/clk-axi-clkgen.c
+++ b/drivers/clk/clk-axi-clkgen.c
@@ -46,9 +46,17 @@
 #define MMCM_CLK_DIV_DIVIDE	BIT(11)
 #define MMCM_CLK_DIV_NOCOUNT	BIT(12)
 
+struct axi_clkgen_limits {
+	unsigned int fpfd_min;
+	unsigned int fpfd_max;
+	unsigned int fvco_min;
+	unsigned int fvco_max;
+};
+
 struct axi_clkgen {
 	void __iomem *base;
 	struct clk_hw clk_hw;
+	struct axi_clkgen_limits limits;
 };
 
 static uint32_t axi_clkgen_lookup_filter(unsigned int m)
@@ -100,12 +108,15 @@ static uint32_t axi_clkgen_lookup_lock(unsigned int m)
 	return 0x1f1f00fa;
 }
 
-static const unsigned int fpfd_min = 10000;
-static const unsigned int fpfd_max = 300000;
-static const unsigned int fvco_min = 600000;
-static const unsigned int fvco_max = 1200000;
+static const struct axi_clkgen_limits axi_clkgen_zynq_default_limits = {
+	.fpfd_min = 10000,
+	.fpfd_max = 300000,
+	.fvco_min = 600000,
+	.fvco_max = 1200000,
+};
 
-static void axi_clkgen_calc_params(unsigned long fin, unsigned long fout,
+static void axi_clkgen_calc_params(const struct axi_clkgen_limits *limits,
+	unsigned long fin, unsigned long fout,
 	unsigned int *best_d, unsigned int *best_m, unsigned int *best_dout)
 {
 	unsigned long d, d_min, d_max, _d_min, _d_max;
@@ -122,12 +133,12 @@ static void axi_clkgen_calc_params(unsigned long fin, unsigned long fout,
 	*best_m = 0;
 	*best_dout = 0;
 
-	d_min = max_t(unsigned long, DIV_ROUND_UP(fin, fpfd_max), 1);
-	d_max = min_t(unsigned long, fin / fpfd_min, 80);
+	d_min = max_t(unsigned long, DIV_ROUND_UP(fin, limits->fpfd_max), 1);
+	d_max = min_t(unsigned long, fin / limits->fpfd_min, 80);
 
 again:
-	fvco_min_fract = fvco_min << fract_shift;
-	fvco_max_fract = fvco_max << fract_shift;
+	fvco_min_fract = limits->fvco_min << fract_shift;
+	fvco_max_fract = limits->fvco_max << fract_shift;
 
 	m_min = max_t(unsigned long, DIV_ROUND_UP(fvco_min_fract, fin) * d_min, 1);
 	m_max = min_t(unsigned long, fvco_max_fract * d_max / fin, 64 << fract_shift);
@@ -319,6 +330,7 @@ static int axi_clkgen_set_rate(struct clk_hw *clk_hw,
 	unsigned long rate, unsigned long parent_rate)
 {
 	struct axi_clkgen *axi_clkgen = clk_hw_to_axi_clkgen(clk_hw);
+	const struct axi_clkgen_limits *limits = &axi_clkgen->limits;
 	unsigned int d, m, dout;
 	struct axi_clkgen_div_params params;
 	uint32_t power = 0;
@@ -328,7 +340,7 @@ static int axi_clkgen_set_rate(struct clk_hw *clk_hw,
 	if (parent_rate == 0 || rate == 0)
 		return -EINVAL;
 
-	axi_clkgen_calc_params(parent_rate, rate, &d, &m, &dout);
+	axi_clkgen_calc_params(limits, parent_rate, rate, &d, &m, &dout);
 
 	if (d == 0 || dout == 0 || m == 0)
 		return -EINVAL;
@@ -368,10 +380,12 @@ static int axi_clkgen_set_rate(struct clk_hw *clk_hw,
 static long axi_clkgen_round_rate(struct clk_hw *hw, unsigned long rate,
 	unsigned long *parent_rate)
 {
+	struct axi_clkgen *axi_clkgen = clk_hw_to_axi_clkgen(hw);
+	const struct axi_clkgen_limits *limits = &axi_clkgen->limits;
 	unsigned int d, m, dout;
 	unsigned long long tmp;
 
-	axi_clkgen_calc_params(*parent_rate, rate, &d, &m, &dout);
+	axi_clkgen_calc_params(limits, *parent_rate, rate, &d, &m, &dout);
 
 	if (d == 0 || dout == 0 || m == 0)
 		return -EINVAL;
@@ -482,17 +496,9 @@ static const struct clk_ops axi_clkgen_ops = {
 	.get_parent = axi_clkgen_get_parent,
 };
 
-static const struct of_device_id axi_clkgen_ids[] = {
-	{
-		.compatible = "adi,axi-clkgen-2.00.a",
-	},
-	{ },
-};
-MODULE_DEVICE_TABLE(of, axi_clkgen_ids);
-
 static int axi_clkgen_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *id;
+	const struct axi_clkgen_limits *dflt_limits;
 	struct axi_clkgen *axi_clkgen;
 	struct clk_init_data init;
 	const char *parent_names[2];
@@ -501,11 +507,8 @@ static int axi_clkgen_probe(struct platform_device *pdev)
 	unsigned int i;
 	int ret;
 
-	if (!pdev->dev.of_node)
-		return -ENODEV;
-
-	id = of_match_node(axi_clkgen_ids, pdev->dev.of_node);
-	if (!id)
+	dflt_limits = device_get_match_data(&pdev->dev);
+	if (!dflt_limits)
 		return -ENODEV;
 
 	axi_clkgen = devm_kzalloc(&pdev->dev, sizeof(*axi_clkgen), GFP_KERNEL);
@@ -527,6 +530,8 @@ static int axi_clkgen_probe(struct platform_device *pdev)
 			return -EINVAL;
 	}
 
+	memcpy(&axi_clkgen->limits, dflt_limits, sizeof(axi_clkgen->limits));
+
 	clk_name = pdev->dev.of_node->name;
 	of_property_read_string(pdev->dev.of_node, "clock-output-names",
 		&clk_name);
@@ -554,6 +559,15 @@ static int axi_clkgen_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id axi_clkgen_ids[] = {
+	{
+		.compatible = "adi,axi-clkgen-2.00.a",
+		.data = &axi_clkgen_zynq_default_limits,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, axi_clkgen_ids);
+
 static struct platform_driver axi_clkgen_driver = {
 	.driver = {
 		.name = "adi-axi-clkgen",
diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c
index 2ddb54f7d3ab..0506046a5f4b 100644
--- a/drivers/clk/clk-composite.c
+++ b/drivers/clk/clk-composite.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/device.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
@@ -405,3 +406,52 @@ void clk_hw_unregister_composite(struct clk_hw *hw)
 	kfree(composite);
 }
 EXPORT_SYMBOL_GPL(clk_hw_unregister_composite);
+
+static void devm_clk_hw_release_composite(struct device *dev, void *res)
+{
+	clk_hw_unregister_composite(*(struct clk_hw **)res);
+}
+
+static struct clk_hw *__devm_clk_hw_register_composite(struct device *dev,
+			const char *name, const char * const *parent_names,
+			const struct clk_parent_data *pdata, int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	struct clk_hw **ptr, *hw;
+
+	ptr = devres_alloc(devm_clk_hw_release_composite, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	hw = __clk_hw_register_composite(dev, name, parent_names, pdata,
+					 num_parents, mux_hw, mux_ops, rate_hw,
+					 rate_ops, gate_hw, gate_ops, flags);
+
+	if (!IS_ERR(hw)) {
+		*ptr = hw;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return hw;
+}
+
+struct clk_hw *devm_clk_hw_register_composite_pdata(struct device *dev,
+			const char *name,
+			const struct clk_parent_data *parent_data,
+			int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	return __devm_clk_hw_register_composite(dev, name, NULL, parent_data,
+						num_parents, mux_hw, mux_ops,
+						rate_hw, rate_ops, gate_hw,
+						gate_ops, flags);
+}
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 8de12cb0c43d..c499799693cc 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/device.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/io.h>
@@ -578,3 +579,36 @@ void clk_hw_unregister_divider(struct clk_hw *hw)
 	kfree(div);
 }
 EXPORT_SYMBOL_GPL(clk_hw_unregister_divider);
+
+static void devm_clk_hw_release_divider(struct device *dev, void *res)
+{
+	clk_hw_unregister_divider(*(struct clk_hw **)res);
+}
+
+struct clk_hw *__devm_clk_hw_register_divider(struct device *dev,
+		struct device_node *np, const char *name,
+		const char *parent_name, const struct clk_hw *parent_hw,
+		const struct clk_parent_data *parent_data, unsigned long flags,
+		void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags,
+		const struct clk_div_table *table, spinlock_t *lock)
+{
+	struct clk_hw **ptr, *hw;
+
+	ptr = devres_alloc(devm_clk_hw_release_divider, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	hw = __clk_hw_register_divider(dev, np, name, parent_name, parent_hw,
+				       parent_data, flags, reg, shift, width,
+				       clk_divider_flags, table, lock);
+
+	if (!IS_ERR(hw)) {
+		*ptr = hw;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return hw;
+}
+EXPORT_SYMBOL_GPL(__devm_clk_hw_register_divider);
diff --git a/drivers/clk/clk-fsl-flexspi.c b/drivers/clk/clk-fsl-flexspi.c
new file mode 100644
index 000000000000..8432d681e2d9
--- /dev/null
+++ b/drivers/clk/clk-fsl-flexspi.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Layerscape FlexSPI clock driver
+ *
+ * Copyright 2020 Michael Walle <michael@walle.cc>
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+static const struct clk_div_table ls1028a_flexspi_divs[] = {
+	{ .val = 0, .div = 1, },
+	{ .val = 1, .div = 2, },
+	{ .val = 2, .div = 3, },
+	{ .val = 3, .div = 4, },
+	{ .val = 4, .div = 5, },
+	{ .val = 5, .div = 6, },
+	{ .val = 6, .div = 7, },
+	{ .val = 7, .div = 8, },
+	{ .val = 11, .div = 12, },
+	{ .val = 15, .div = 16, },
+	{ .val = 16, .div = 20, },
+	{ .val = 17, .div = 24, },
+	{ .val = 18, .div = 28, },
+	{ .val = 19, .div = 32, },
+	{ .val = 20, .div = 80, },
+	{}
+};
+
+static const struct clk_div_table lx2160a_flexspi_divs[] = {
+	{ .val = 1, .div = 2, },
+	{ .val = 3, .div = 4, },
+	{ .val = 5, .div = 6, },
+	{ .val = 7, .div = 8, },
+	{ .val = 11, .div = 12, },
+	{ .val = 15, .div = 16, },
+	{ .val = 16, .div = 20, },
+	{ .val = 17, .div = 24, },
+	{ .val = 18, .div = 28, },
+	{ .val = 19, .div = 32, },
+	{ .val = 20, .div = 80, },
+	{}
+};
+
+static int fsl_flexspi_clk_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	const char *clk_name = np->name;
+	const char *clk_parent;
+	struct resource *res;
+	void __iomem *reg;
+	struct clk_hw *hw;
+	const struct clk_div_table *divs;
+
+	divs = device_get_match_data(dev);
+	if (!divs)
+		return -ENOENT;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENOENT;
+
+	/*
+	 * Can't use devm_ioremap_resource() or devm_of_iomap() because the
+	 * resource might already be taken by the parent device.
+	 */
+	reg = devm_ioremap(dev, res->start, resource_size(res));
+	if (!reg)
+		return -ENOMEM;
+
+	clk_parent = of_clk_get_parent_name(np, 0);
+	if (!clk_parent)
+		return -EINVAL;
+
+	of_property_read_string(np, "clock-output-names", &clk_name);
+
+	hw = devm_clk_hw_register_divider_table(dev, clk_name, clk_parent, 0,
+						reg, 0, 5, 0, divs, NULL);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, hw);
+}
+
+static const struct of_device_id fsl_flexspi_clk_dt_ids[] = {
+	{ .compatible = "fsl,ls1028a-flexspi-clk", .data = &ls1028a_flexspi_divs },
+	{ .compatible = "fsl,lx2160a-flexspi-clk", .data = &lx2160a_flexspi_divs },
+	{}
+};
+MODULE_DEVICE_TABLE(of, fsl_flexspi_clk_dt_ids);
+
+static struct platform_driver fsl_flexspi_clk_driver = {
+	.driver = {
+		.name = "fsl-flexspi-clk",
+		.of_match_table = fsl_flexspi_clk_dt_ids,
+	},
+	.probe = fsl_flexspi_clk_probe,
+};
+module_platform_driver(fsl_flexspi_clk_driver);
+
+MODULE_DESCRIPTION("FlexSPI clock driver for Layerscape SoCs");
+MODULE_AUTHOR("Michael Walle <michael@walle.cc>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/clk/clk-fsl-sai.c b/drivers/clk/clk-fsl-sai.c
index 0221180a4dd7..6238fcea0467 100644
--- a/drivers/clk/clk-fsl-sai.c
+++ b/drivers/clk/clk-fsl-sai.c
@@ -58,13 +58,13 @@ static int fsl_sai_clk_probe(struct platform_device *pdev)
 	/* set clock direction, we are the BCLK master */
 	writel(CR2_BCD, base + I2S_CR2);
 
-	hw = clk_hw_register_composite_pdata(dev, dev->of_node->name,
-					     &pdata, 1, NULL, NULL,
-					     &sai_clk->div.hw,
-					     &clk_divider_ops,
-					     &sai_clk->gate.hw,
-					     &clk_gate_ops,
-					     CLK_SET_RATE_GATE);
+	hw = devm_clk_hw_register_composite_pdata(dev, dev->of_node->name,
+						  &pdata, 1, NULL, NULL,
+						  &sai_clk->div.hw,
+						  &clk_divider_ops,
+						  &sai_clk->gate.hw,
+						  &clk_gate_ops,
+						  CLK_SET_RATE_GATE);
 	if (IS_ERR(hw))
 		return PTR_ERR(hw);
 
diff --git a/drivers/clk/clk-pwm.c b/drivers/clk/clk-pwm.c
index 86f2e2d3fc02..da2c8eddfd9f 100644
--- a/drivers/clk/clk-pwm.c
+++ b/drivers/clk/clk-pwm.c
@@ -147,7 +147,7 @@ static struct platform_driver clk_pwm_driver = {
 	.remove = clk_pwm_remove,
 	.driver = {
 		.name = "pwm-clock",
-		.of_match_table = of_match_ptr(clk_pwm_dt_ids),
+		.of_match_table = clk_pwm_dt_ids,
 	},
 };
 
diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c
index 46101c6a20f2..70aa521e7e7f 100644
--- a/drivers/clk/clk-qoriq.c
+++ b/drivers/clk/clk-qoriq.c
@@ -7,6 +7,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <dt-bindings/clock/fsl,qoriq-clockgen.h>
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
@@ -1368,33 +1369,33 @@ static struct clk *clockgen_clk_get(struct of_phandle_args *clkspec, void *data)
 	idx = clkspec->args[1];
 
 	switch (type) {
-	case 0:
+	case QORIQ_CLK_SYSCLK:
 		if (idx != 0)
 			goto bad_args;
 		clk = cg->sysclk;
 		break;
-	case 1:
+	case QORIQ_CLK_CMUX:
 		if (idx >= ARRAY_SIZE(cg->cmux))
 			goto bad_args;
 		clk = cg->cmux[idx];
 		break;
-	case 2:
+	case QORIQ_CLK_HWACCEL:
 		if (idx >= ARRAY_SIZE(cg->hwaccel))
 			goto bad_args;
 		clk = cg->hwaccel[idx];
 		break;
-	case 3:
+	case QORIQ_CLK_FMAN:
 		if (idx >= ARRAY_SIZE(cg->fman))
 			goto bad_args;
 		clk = cg->fman[idx];
 		break;
-	case 4:
+	case QORIQ_CLK_PLATFORM_PLL:
 		pll = &cg->pll[PLATFORM_PLL];
 		if (idx >= ARRAY_SIZE(pll->div))
 			goto bad_args;
 		clk = pll->div[idx].clk;
 		break;
-	case 5:
+	case QORIQ_CLK_CORECLK:
 		if (idx != 0)
 			goto bad_args;
 		clk = cg->coreclk;
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
index aa21371f9104..a3e883a9f406 100644
--- a/drivers/clk/clk-s2mps11.c
+++ b/drivers/clk/clk-s2mps11.c
@@ -195,6 +195,7 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 	return ret;
 
 err_reg:
+	of_node_put(s2mps11_clks[0].clk_np);
 	while (--i >= 0)
 		clkdev_drop(s2mps11_clks[i].lookup);
 
diff --git a/drivers/clk/clk-scpi.c b/drivers/clk/clk-scpi.c
index 5a9b140dd8c8..a39af7616b13 100644
--- a/drivers/clk/clk-scpi.c
+++ b/drivers/clk/clk-scpi.c
@@ -129,7 +129,7 @@ static const struct clk_ops scpi_dvfs_ops = {
 	.set_rate = scpi_dvfs_set_rate,
 };
 
-static const struct of_device_id scpi_clk_match[] = {
+static const struct of_device_id scpi_clk_match[] __maybe_unused = {
 	{ .compatible = "arm,scpi-dvfs-clocks", .data = &scpi_dvfs_ops, },
 	{ .compatible = "arm,scpi-variable-clocks", .data = &scpi_clk_ops, },
 	{}
diff --git a/drivers/clk/clk-si5351.c b/drivers/clk/clk-si5351.c
index 1e1702e609cb..57e4597cdf4c 100644
--- a/drivers/clk/clk-si5351.c
+++ b/drivers/clk/clk-si5351.c
@@ -902,6 +902,10 @@ static int _si5351_clkout_set_disable_state(
 static void _si5351_clkout_reset_pll(struct si5351_driver_data *drvdata, int num)
 {
 	u8 val = si5351_reg_read(drvdata, SI5351_CLK0_CTRL + num);
+	u8 mask = val & SI5351_CLK_PLL_SELECT ? SI5351_PLL_RESET_B :
+						       SI5351_PLL_RESET_A;
+	unsigned int v;
+	int err;
 
 	switch (val & SI5351_CLK_INPUT_MASK) {
 	case SI5351_CLK_INPUT_XTAL:
@@ -909,9 +913,12 @@ static void _si5351_clkout_reset_pll(struct si5351_driver_data *drvdata, int num
 		return;  /* pll not used, no need to reset */
 	}
 
-	si5351_reg_write(drvdata, SI5351_PLL_RESET,
-			 val & SI5351_CLK_PLL_SELECT ? SI5351_PLL_RESET_B :
-						       SI5351_PLL_RESET_A);
+	si5351_reg_write(drvdata, SI5351_PLL_RESET, mask);
+
+	err = regmap_read_poll_timeout(drvdata->regmap, SI5351_PLL_RESET, v,
+				 !(v & mask), 0, 20000);
+	if (err < 0)
+		dev_err(&drvdata->client->dev, "Reset bit didn't clear\n");
 
 	dev_dbg(&drvdata->client->dev, "%s - %s: pll = %d\n",
 		__func__, clk_hw_get_name(&drvdata->clkout[num].hw),
diff --git a/drivers/clk/clk-versaclock5.c b/drivers/clk/clk-versaclock5.c
index c90460e7ef21..43db67337bc0 100644
--- a/drivers/clk/clk-versaclock5.c
+++ b/drivers/clk/clk-versaclock5.c
@@ -739,8 +739,8 @@ static int vc5_update_power(struct device_node *np_output,
 {
 	u32 value;
 
-	if (!of_property_read_u32(np_output,
-				  "idt,voltage-microvolts", &value)) {
+	if (!of_property_read_u32(np_output, "idt,voltage-microvolt",
+				  &value)) {
 		clk_out->clk_output_cfg0_mask |= VC5_CLK_OUTPUT_CFG0_PWR_MASK;
 		switch (value) {
 		case 1800000:
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index f83dac54ed85..8c1d04db990d 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -420,7 +420,7 @@ static struct clk_core *clk_core_get(struct clk_core *core, u8 p_index)
 static void clk_core_fill_parent_index(struct clk_core *core, u8 index)
 {
 	struct clk_parent_map *entry = &core->parents[index];
-	struct clk_core *parent = ERR_PTR(-ENOENT);
+	struct clk_core *parent;
 
 	if (entry->hw) {
 		parent = entry->hw->core;
@@ -2314,6 +2314,8 @@ int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max)
 	if (!clk)
 		return 0;
 
+	trace_clk_set_rate_range(clk->core, min, max);
+
 	if (min > max) {
 		pr_err("%s: clk %s dev %s con %s: invalid range [%lu, %lu]\n",
 		       __func__, clk->core->name, clk->dev_id, clk->con_id,
@@ -2381,6 +2383,8 @@ int clk_set_min_rate(struct clk *clk, unsigned long rate)
 	if (!clk)
 		return 0;
 
+	trace_clk_set_min_rate(clk->core, rate);
+
 	return clk_set_rate_range(clk, rate, clk->max_rate);
 }
 EXPORT_SYMBOL_GPL(clk_set_min_rate);
@@ -2397,6 +2401,8 @@ int clk_set_max_rate(struct clk *clk, unsigned long rate)
 	if (!clk)
 		return 0;
 
+	trace_clk_set_max_rate(clk->core, rate);
+
 	return clk_set_rate_range(clk, clk->min_rate, rate);
 }
 EXPORT_SYMBOL_GPL(clk_set_max_rate);
@@ -2931,7 +2937,14 @@ static void clk_summary_show_one(struct seq_file *s, struct clk_core *c,
 	else
 		seq_puts(s, "-----");
 
-	seq_printf(s, " %6d\n", clk_core_get_scaled_duty_cycle(c, 100000));
+	seq_printf(s, " %6d", clk_core_get_scaled_duty_cycle(c, 100000));
+
+	if (c->ops->is_enabled)
+		seq_printf(s, " %9c\n", clk_core_is_enabled(c) ? 'Y' : 'N');
+	else if (!c->ops->enable)
+		seq_printf(s, " %9c\n", 'Y');
+	else
+		seq_printf(s, " %9c\n", '?');
 }
 
 static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c,
@@ -2950,9 +2963,9 @@ static int clk_summary_show(struct seq_file *s, void *data)
 	struct clk_core *c;
 	struct hlist_head **lists = (struct hlist_head **)s->private;
 
-	seq_puts(s, "                                 enable  prepare  protect                                duty\n");
-	seq_puts(s, "   clock                          count    count    count        rate   accuracy phase  cycle\n");
-	seq_puts(s, "---------------------------------------------------------------------------------------------\n");
+	seq_puts(s, "                                 enable  prepare  protect                                duty  hardware\n");
+	seq_puts(s, "   clock                          count    count    count        rate   accuracy phase  cycle    enable\n");
+	seq_puts(s, "-------------------------------------------------------------------------------------------------------\n");
 
 	clk_prepare_lock();
 
@@ -3667,6 +3680,24 @@ struct clk *clk_hw_create_clk(struct device *dev, struct clk_hw *hw,
 	return clk;
 }
 
+/**
+ * clk_hw_get_clk - get clk consumer given an clk_hw
+ * @hw: clk_hw associated with the clk being consumed
+ * @con_id: connection ID string on device
+ *
+ * Returns: new clk consumer
+ * This is the function to be used by providers which need
+ * to get a consumer clk and act on the clock element
+ * Calls to this function must be balanced with calls clk_put()
+ */
+struct clk *clk_hw_get_clk(struct clk_hw *hw, const char *con_id)
+{
+	struct device *dev = hw->core->dev;
+
+	return clk_hw_create_clk(dev, hw, dev_name(dev), con_id);
+}
+EXPORT_SYMBOL(clk_hw_get_clk);
+
 static int clk_cpy_name(const char **dst_p, const char *src, bool must_exist)
 {
 	const char *dst;
@@ -4068,12 +4099,12 @@ void clk_hw_unregister(struct clk_hw *hw)
 }
 EXPORT_SYMBOL_GPL(clk_hw_unregister);
 
-static void devm_clk_release(struct device *dev, void *res)
+static void devm_clk_unregister_cb(struct device *dev, void *res)
 {
 	clk_unregister(*(struct clk **)res);
 }
 
-static void devm_clk_hw_release(struct device *dev, void *res)
+static void devm_clk_hw_unregister_cb(struct device *dev, void *res)
 {
 	clk_hw_unregister(*(struct clk_hw **)res);
 }
@@ -4093,7 +4124,7 @@ struct clk *devm_clk_register(struct device *dev, struct clk_hw *hw)
 	struct clk *clk;
 	struct clk **clkp;
 
-	clkp = devres_alloc(devm_clk_release, sizeof(*clkp), GFP_KERNEL);
+	clkp = devres_alloc(devm_clk_unregister_cb, sizeof(*clkp), GFP_KERNEL);
 	if (!clkp)
 		return ERR_PTR(-ENOMEM);
 
@@ -4123,7 +4154,7 @@ int devm_clk_hw_register(struct device *dev, struct clk_hw *hw)
 	struct clk_hw **hwp;
 	int ret;
 
-	hwp = devres_alloc(devm_clk_hw_release, sizeof(*hwp), GFP_KERNEL);
+	hwp = devres_alloc(devm_clk_hw_unregister_cb, sizeof(*hwp), GFP_KERNEL);
 	if (!hwp)
 		return -ENOMEM;
 
@@ -4167,7 +4198,7 @@ static int devm_clk_hw_match(struct device *dev, void *res, void *data)
  */
 void devm_clk_unregister(struct device *dev, struct clk *clk)
 {
-	WARN_ON(devres_release(dev, devm_clk_release, devm_clk_match, clk));
+	WARN_ON(devres_release(dev, devm_clk_unregister_cb, devm_clk_match, clk));
 }
 EXPORT_SYMBOL_GPL(devm_clk_unregister);
 
@@ -4182,11 +4213,54 @@ EXPORT_SYMBOL_GPL(devm_clk_unregister);
  */
 void devm_clk_hw_unregister(struct device *dev, struct clk_hw *hw)
 {
-	WARN_ON(devres_release(dev, devm_clk_hw_release, devm_clk_hw_match,
+	WARN_ON(devres_release(dev, devm_clk_hw_unregister_cb, devm_clk_hw_match,
 				hw));
 }
 EXPORT_SYMBOL_GPL(devm_clk_hw_unregister);
 
+static void devm_clk_release(struct device *dev, void *res)
+{
+	clk_put(*(struct clk **)res);
+}
+
+/**
+ * devm_clk_hw_get_clk - resource managed clk_hw_get_clk()
+ * @dev: device that is registering this clock
+ * @hw: clk_hw associated with the clk being consumed
+ * @con_id: connection ID string on device
+ *
+ * Managed clk_hw_get_clk(). Clocks got with this function are
+ * automatically clk_put() on driver detach. See clk_put()
+ * for more information.
+ */
+struct clk *devm_clk_hw_get_clk(struct device *dev, struct clk_hw *hw,
+				const char *con_id)
+{
+	struct clk *clk;
+	struct clk **clkp;
+
+	/* This should not happen because it would mean we have drivers
+	 * passing around clk_hw pointers instead of having the caller use
+	 * proper clk_get() style APIs
+	 */
+	WARN_ON_ONCE(dev != hw->core->dev);
+
+	clkp = devres_alloc(devm_clk_release, sizeof(*clkp), GFP_KERNEL);
+	if (!clkp)
+		return ERR_PTR(-ENOMEM);
+
+	clk = clk_hw_get_clk(hw, con_id);
+	if (!IS_ERR(clk)) {
+		*clkp = clk;
+		devres_add(dev, clkp);
+	} else {
+		devres_free(clkp);
+	}
+
+	return clk;
+}
+EXPORT_SYMBOL_GPL(devm_clk_hw_get_clk);
+
 /*
  * clkdev helpers
  */
@@ -4334,6 +4408,42 @@ int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(clk_notifier_unregister);
 
+struct clk_notifier_devres {
+	struct clk *clk;
+	struct notifier_block *nb;
+};
+
+static void devm_clk_notifier_release(struct device *dev, void *res)
+{
+	struct clk_notifier_devres *devres = res;
+
+	clk_notifier_unregister(devres->clk, devres->nb);
+}
+
+int devm_clk_notifier_register(struct device *dev, struct clk *clk,
+			       struct notifier_block *nb)
+{
+	struct clk_notifier_devres *devres;
+	int ret;
+
+	devres = devres_alloc(devm_clk_notifier_release,
+			      sizeof(*devres), GFP_KERNEL);
+
+	if (!devres)
+		return -ENOMEM;
+
+	ret = clk_notifier_register(clk, nb);
+	if (!ret) {
+		devres->clk = clk;
+		devres->nb = nb;
+	} else {
+		devres_free(devres);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devm_clk_notifier_register);
+
 #ifdef CONFIG_OF
 static void clk_core_reparent_orphans(void)
 {
diff --git a/drivers/clk/imx/clk-gate2.c b/drivers/clk/imx/clk-gate2.c
index 7eed7083f46e..f16c4019f402 100644
--- a/drivers/clk/imx/clk-gate2.c
+++ b/drivers/clk/imx/clk-gate2.c
@@ -30,6 +30,7 @@ struct clk_gate2 {
 	void __iomem	*reg;
 	u8		bit_idx;
 	u8		cgr_val;
+	u8		cgr_mask;
 	u8		flags;
 	spinlock_t	*lock;
 	unsigned int	*share_count;
@@ -37,37 +38,38 @@ struct clk_gate2 {
 
 #define to_clk_gate2(_hw) container_of(_hw, struct clk_gate2, hw)
 
-static int clk_gate2_enable(struct clk_hw *hw)
+static void clk_gate2_do_shared_clks(struct clk_hw *hw, bool enable)
 {
 	struct clk_gate2 *gate = to_clk_gate2(hw);
 	u32 reg;
+
+	reg = readl(gate->reg);
+	reg &= ~(gate->cgr_mask << gate->bit_idx);
+	if (enable)
+		reg |= (gate->cgr_val & gate->cgr_mask) << gate->bit_idx;
+	writel(reg, gate->reg);
+}
+
+static int clk_gate2_enable(struct clk_hw *hw)
+{
+	struct clk_gate2 *gate = to_clk_gate2(hw);
 	unsigned long flags;
-	int ret = 0;
 
 	spin_lock_irqsave(gate->lock, flags);
 
 	if (gate->share_count && (*gate->share_count)++ > 0)
 		goto out;
 
-	if (gate->flags & IMX_CLK_GATE2_SINGLE_BIT) {
-		ret = clk_gate_ops.enable(hw);
-	} else {
-		reg = readl(gate->reg);
-		reg &= ~(3 << gate->bit_idx);
-		reg |= gate->cgr_val << gate->bit_idx;
-		writel(reg, gate->reg);
-	}
-
+	clk_gate2_do_shared_clks(hw, true);
 out:
 	spin_unlock_irqrestore(gate->lock, flags);
 
-	return ret;
+	return 0;
 }
 
 static void clk_gate2_disable(struct clk_hw *hw)
 {
 	struct clk_gate2 *gate = to_clk_gate2(hw);
-	u32 reg;
 	unsigned long flags;
 
 	spin_lock_irqsave(gate->lock, flags);
@@ -79,23 +81,17 @@ static void clk_gate2_disable(struct clk_hw *hw)
 			goto out;
 	}
 
-	if (gate->flags & IMX_CLK_GATE2_SINGLE_BIT) {
-		clk_gate_ops.disable(hw);
-	} else {
-		reg = readl(gate->reg);
-		reg &= ~(3 << gate->bit_idx);
-		writel(reg, gate->reg);
-	}
-
+	clk_gate2_do_shared_clks(hw, false);
 out:
 	spin_unlock_irqrestore(gate->lock, flags);
 }
 
-static int clk_gate2_reg_is_enabled(void __iomem *reg, u8 bit_idx)
+static int clk_gate2_reg_is_enabled(void __iomem *reg, u8 bit_idx,
+					u8 cgr_val, u8 cgr_mask)
 {
 	u32 val = readl(reg);
 
-	if (((val >> bit_idx) & 1) == 1)
+	if (((val >> bit_idx) & cgr_mask) == cgr_val)
 		return 1;
 
 	return 0;
@@ -104,29 +100,28 @@ static int clk_gate2_reg_is_enabled(void __iomem *reg, u8 bit_idx)
 static int clk_gate2_is_enabled(struct clk_hw *hw)
 {
 	struct clk_gate2 *gate = to_clk_gate2(hw);
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(gate->lock, flags);
 
-	if (gate->flags & IMX_CLK_GATE2_SINGLE_BIT)
-		return clk_gate_ops.is_enabled(hw);
+	ret = clk_gate2_reg_is_enabled(gate->reg, gate->bit_idx,
+					gate->cgr_val, gate->cgr_mask);
 
-	return clk_gate2_reg_is_enabled(gate->reg, gate->bit_idx);
+	spin_unlock_irqrestore(gate->lock, flags);
+
+	return ret;
 }
 
 static void clk_gate2_disable_unused(struct clk_hw *hw)
 {
 	struct clk_gate2 *gate = to_clk_gate2(hw);
 	unsigned long flags;
-	u32 reg;
-
-	if (gate->flags & IMX_CLK_GATE2_SINGLE_BIT)
-		return;
 
 	spin_lock_irqsave(gate->lock, flags);
 
-	if (!gate->share_count || *gate->share_count == 0) {
-		reg = readl(gate->reg);
-		reg &= ~(3 << gate->bit_idx);
-		writel(reg, gate->reg);
-	}
+	if (!gate->share_count || *gate->share_count == 0)
+		clk_gate2_do_shared_clks(hw, false);
 
 	spin_unlock_irqrestore(gate->lock, flags);
 }
@@ -140,7 +135,7 @@ static const struct clk_ops clk_gate2_ops = {
 
 struct clk_hw *clk_hw_register_gate2(struct device *dev, const char *name,
 		const char *parent_name, unsigned long flags,
-		void __iomem *reg, u8 bit_idx, u8 cgr_val,
+		void __iomem *reg, u8 bit_idx, u8 cgr_val, u8 cgr_mask,
 		u8 clk_gate2_flags, spinlock_t *lock,
 		unsigned int *share_count)
 {
@@ -157,6 +152,7 @@ struct clk_hw *clk_hw_register_gate2(struct device *dev, const char *name,
 	gate->reg = reg;
 	gate->bit_idx = bit_idx;
 	gate->cgr_val = cgr_val;
+	gate->cgr_mask = cgr_mask;
 	gate->flags = clk_gate2_flags;
 	gate->lock = lock;
 	gate->share_count = share_count;
diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c
index f358ad907299..7c905861af5d 100644
--- a/drivers/clk/imx/clk-imx8mm.c
+++ b/drivers/clk/imx/clk-imx8mm.c
@@ -653,7 +653,7 @@ static struct platform_driver imx8mm_clk_driver = {
 		 * reloading the driver will crash or break devices.
 		 */
 		.suppress_bind_attrs = true,
-		.of_match_table = of_match_ptr(imx8mm_clk_of_match),
+		.of_match_table = imx8mm_clk_of_match,
 	},
 };
 module_platform_driver(imx8mm_clk_driver);
diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c
index f3c5e6cf55dd..3c21db942d5b 100644
--- a/drivers/clk/imx/clk-imx8mn.c
+++ b/drivers/clk/imx/clk-imx8mn.c
@@ -604,7 +604,7 @@ static struct platform_driver imx8mn_clk_driver = {
 		 * reloading the driver will crash or break devices.
 		 */
 		.suppress_bind_attrs = true,
-		.of_match_table = of_match_ptr(imx8mn_clk_of_match),
+		.of_match_table = imx8mn_clk_of_match,
 	},
 };
 module_platform_driver(imx8mn_clk_driver);
diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c
index 48e212477f52..2f4e1d674e1c 100644
--- a/drivers/clk/imx/clk-imx8mp.c
+++ b/drivers/clk/imx/clk-imx8mp.c
@@ -425,7 +425,7 @@ static struct clk **uart_clks[ARRAY_SIZE(uart_clk_ids) + 1];
 static int imx8mp_clocks_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct device_node *np = dev->of_node;
+	struct device_node *np;
 	void __iomem *anatop_base, *ccm_base;
 	int i;
 
@@ -763,7 +763,7 @@ static struct platform_driver imx8mp_clk_driver = {
 		 * reloading the driver will crash or break devices.
 		 */
 		.suppress_bind_attrs = true,
-		.of_match_table = of_match_ptr(imx8mp_clk_of_match),
+		.of_match_table = imx8mp_clk_of_match,
 	},
 };
 module_platform_driver(imx8mp_clk_driver);
diff --git a/drivers/clk/imx/clk-imx8mq.c b/drivers/clk/imx/clk-imx8mq.c
index 06292d4a98ff..779ea69e639c 100644
--- a/drivers/clk/imx/clk-imx8mq.c
+++ b/drivers/clk/imx/clk-imx8mq.c
@@ -639,7 +639,7 @@ static struct platform_driver imx8mq_clk_driver = {
 		 * reloading the driver will crash or break devices.
 		 */
 		.suppress_bind_attrs = true,
-		.of_match_table = of_match_ptr(imx8mq_clk_of_match),
+		.of_match_table = imx8mq_clk_of_match,
 	},
 };
 module_platform_driver(imx8mq_clk_driver);
diff --git a/drivers/clk/imx/clk-imx8qxp-lpcg.c b/drivers/clk/imx/clk-imx8qxp-lpcg.c
index e947a70054ac..d3e905cf867d 100644
--- a/drivers/clk/imx/clk-imx8qxp-lpcg.c
+++ b/drivers/clk/imx/clk-imx8qxp-lpcg.c
@@ -9,8 +9,10 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 
 #include "clk-scu.h"
@@ -157,6 +159,135 @@ static const struct imx8qxp_ss_lpcg imx8qxp_ss_lsio = {
 	.num_max = IMX_LSIO_LPCG_CLK_END,
 };
 
+#define IMX_LPCG_MAX_CLKS	8
+
+static struct clk_hw *imx_lpcg_of_clk_src_get(struct of_phandle_args *clkspec,
+					      void *data)
+{
+	struct clk_hw_onecell_data *hw_data = data;
+	unsigned int idx = clkspec->args[0] / 4;
+
+	if (idx >= hw_data->num) {
+		pr_err("%s: invalid index %u\n", __func__, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return hw_data->hws[idx];
+}
+
+static int imx_lpcg_parse_clks_from_dt(struct platform_device *pdev,
+				       struct device_node *np)
+{
+	const char *output_names[IMX_LPCG_MAX_CLKS];
+	const char *parent_names[IMX_LPCG_MAX_CLKS];
+	unsigned int bit_offset[IMX_LPCG_MAX_CLKS];
+	struct clk_hw_onecell_data *clk_data;
+	struct clk_hw **clk_hws;
+	struct resource *res;
+	void __iomem *base;
+	int count;
+	int idx;
+	int ret;
+	int i;
+
+	if (!of_device_is_compatible(np, "fsl,imx8qxp-lpcg"))
+		return -EINVAL;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	count = of_property_count_u32_elems(np, "clock-indices");
+	if (count < 0) {
+		dev_err(&pdev->dev, "failed to count clocks\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * A trick here is that we set the num of clks to the MAX instead
+	 * of the count from clock-indices because one LPCG supports up to
+	 * 8 clock outputs which each of them is fixed to 4 bits. Then we can
+	 * easily get the clock by clk-indices (bit-offset) / 4.
+	 * And the cost is very limited few pointers.
+	 */
+
+	clk_data = devm_kzalloc(&pdev->dev, struct_size(clk_data, hws,
+				IMX_LPCG_MAX_CLKS), GFP_KERNEL);
+	if (!clk_data)
+		return -ENOMEM;
+
+	clk_data->num = IMX_LPCG_MAX_CLKS;
+	clk_hws = clk_data->hws;
+
+	ret = of_property_read_u32_array(np, "clock-indices", bit_offset,
+					 count);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to read clock-indices\n");
+		return -EINVAL;
+	}
+
+	ret = of_clk_parent_fill(np, parent_names, count);
+	if (ret != count) {
+		dev_err(&pdev->dev, "failed to get clock parent names\n");
+		return count;
+	}
+
+	ret = of_property_read_string_array(np, "clock-output-names",
+					    output_names, count);
+	if (ret != count) {
+		dev_err(&pdev->dev, "failed to read clock-output-names\n");
+		return -EINVAL;
+	}
+
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, 500);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+	for (i = 0; i < count; i++) {
+		idx = bit_offset[i] / 4;
+		if (idx > IMX_LPCG_MAX_CLKS) {
+			dev_warn(&pdev->dev, "invalid bit offset of clock %d\n",
+				 i);
+			ret = -EINVAL;
+			goto unreg;
+		}
+
+		clk_hws[idx] = imx_clk_lpcg_scu_dev(&pdev->dev, output_names[i],
+						    parent_names[i], 0, base,
+						    bit_offset[i], false);
+		if (IS_ERR(clk_hws[idx])) {
+			dev_warn(&pdev->dev, "failed to register clock %d\n",
+				 idx);
+			ret = PTR_ERR(clk_hws[idx]);
+			goto unreg;
+		}
+	}
+
+	ret = devm_of_clk_add_hw_provider(&pdev->dev, imx_lpcg_of_clk_src_get,
+					  clk_data);
+	if (ret)
+		goto unreg;
+
+	pm_runtime_mark_last_busy(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
+
+	return 0;
+
+unreg:
+	while (--i >= 0) {
+		idx = bit_offset[i] / 4;
+		if (clk_hws[idx])
+			imx_clk_lpcg_scu_unregister(clk_hws[idx]);
+	}
+
+	pm_runtime_disable(&pdev->dev);
+
+	return ret;
+}
+
 static int imx8qxp_lpcg_clk_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -167,8 +298,14 @@ static int imx8qxp_lpcg_clk_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct clk_hw **clks;
 	void __iomem *base;
+	int ret;
 	int i;
 
+	/* try new binding to parse clocks from device tree first */
+	ret = imx_lpcg_parse_clks_from_dt(pdev, np);
+	if (!ret)
+		return 0;
+
 	ss_lpcg = of_device_get_match_data(dev);
 	if (!ss_lpcg)
 		return -ENODEV;
@@ -219,6 +356,7 @@ static const struct of_device_id imx8qxp_lpcg_match[] = {
 	{ .compatible = "fsl,imx8qxp-lpcg-adma", &imx8qxp_ss_adma, },
 	{ .compatible = "fsl,imx8qxp-lpcg-conn", &imx8qxp_ss_conn, },
 	{ .compatible = "fsl,imx8qxp-lpcg-lsio", &imx8qxp_ss_lsio, },
+	{ .compatible = "fsl,imx8qxp-lpcg", NULL },
 	{ /* sentinel */ }
 };
 
@@ -226,6 +364,7 @@ static struct platform_driver imx8qxp_lpcg_clk_driver = {
 	.driver = {
 		.name = "imx8qxp-lpcg-clk",
 		.of_match_table = imx8qxp_lpcg_match,
+		.pm = &imx_clk_lpcg_scu_pm_ops,
 		.suppress_bind_attrs = true,
 	},
 	.probe = imx8qxp_lpcg_clk_probe,
diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c
index d650ca33cdc8..5b3d4ede7c7c 100644
--- a/drivers/clk/imx/clk-imx8qxp.c
+++ b/drivers/clk/imx/clk-imx8qxp.c
@@ -22,9 +22,10 @@ static int imx8qxp_clk_probe(struct platform_device *pdev)
 	struct device_node *ccm_node = pdev->dev.of_node;
 	struct clk_hw_onecell_data *clk_data;
 	struct clk_hw **clks;
+	u32 clk_cells;
 	int ret, i;
 
-	ret = imx_clk_scu_init();
+	ret = imx_clk_scu_init(ccm_node);
 	if (ret)
 		return ret;
 
@@ -33,6 +34,9 @@ static int imx8qxp_clk_probe(struct platform_device *pdev)
 	if (!clk_data)
 		return -ENOMEM;
 
+	if (of_property_read_u32(ccm_node, "#clock-cells", &clk_cells))
+		return -EINVAL;
+
 	clk_data->num = IMX_SCU_CLK_END;
 	clks = clk_data->hws;
 
@@ -55,78 +59,78 @@ static int imx8qxp_clk_probe(struct platform_device *pdev)
 	clks[IMX_LSIO_BUS_CLK]		= clk_hw_register_fixed_rate(NULL, "lsio_bus_clk_root", NULL, 0, 100000000);
 
 	/* ARM core */
-	clks[IMX_A35_CLK]		= imx_clk_scu("a35_clk", IMX_SC_R_A35, IMX_SC_PM_CLK_CPU);
+	clks[IMX_A35_CLK]		= imx_clk_scu("a35_clk", IMX_SC_R_A35, IMX_SC_PM_CLK_CPU, clk_cells);
 
 	/* LSIO SS */
-	clks[IMX_LSIO_PWM0_CLK]		= imx_clk_scu("pwm0_clk", IMX_SC_R_PWM_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_PWM1_CLK]		= imx_clk_scu("pwm1_clk", IMX_SC_R_PWM_1, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_PWM2_CLK]		= imx_clk_scu("pwm2_clk", IMX_SC_R_PWM_2, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_PWM3_CLK]		= imx_clk_scu("pwm3_clk", IMX_SC_R_PWM_3, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_PWM4_CLK]		= imx_clk_scu("pwm4_clk", IMX_SC_R_PWM_4, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_PWM5_CLK]		= imx_clk_scu("pwm5_clk", IMX_SC_R_PWM_5, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_PWM6_CLK]		= imx_clk_scu("pwm6_clk", IMX_SC_R_PWM_6, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_PWM7_CLK]		= imx_clk_scu("pwm7_clk", IMX_SC_R_PWM_7, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_GPT0_CLK]		= imx_clk_scu("gpt0_clk", IMX_SC_R_GPT_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_GPT1_CLK]		= imx_clk_scu("gpt1_clk", IMX_SC_R_GPT_1, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_GPT2_CLK]		= imx_clk_scu("gpt2_clk", IMX_SC_R_GPT_2, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_GPT3_CLK]		= imx_clk_scu("gpt3_clk", IMX_SC_R_GPT_3, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_GPT4_CLK]		= imx_clk_scu("gpt4_clk", IMX_SC_R_GPT_4, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_FSPI0_CLK]	= imx_clk_scu("fspi0_clk", IMX_SC_R_FSPI_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_LSIO_FSPI1_CLK]	= imx_clk_scu("fspi1_clk", IMX_SC_R_FSPI_1, IMX_SC_PM_CLK_PER);
+	clks[IMX_LSIO_PWM0_CLK]		= imx_clk_scu("pwm0_clk", IMX_SC_R_PWM_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_PWM1_CLK]		= imx_clk_scu("pwm1_clk", IMX_SC_R_PWM_1, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_PWM2_CLK]		= imx_clk_scu("pwm2_clk", IMX_SC_R_PWM_2, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_PWM3_CLK]		= imx_clk_scu("pwm3_clk", IMX_SC_R_PWM_3, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_PWM4_CLK]		= imx_clk_scu("pwm4_clk", IMX_SC_R_PWM_4, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_PWM5_CLK]		= imx_clk_scu("pwm5_clk", IMX_SC_R_PWM_5, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_PWM6_CLK]		= imx_clk_scu("pwm6_clk", IMX_SC_R_PWM_6, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_PWM7_CLK]		= imx_clk_scu("pwm7_clk", IMX_SC_R_PWM_7, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_GPT0_CLK]		= imx_clk_scu("gpt0_clk", IMX_SC_R_GPT_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_GPT1_CLK]		= imx_clk_scu("gpt1_clk", IMX_SC_R_GPT_1, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_GPT2_CLK]		= imx_clk_scu("gpt2_clk", IMX_SC_R_GPT_2, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_GPT3_CLK]		= imx_clk_scu("gpt3_clk", IMX_SC_R_GPT_3, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_GPT4_CLK]		= imx_clk_scu("gpt4_clk", IMX_SC_R_GPT_4, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_FSPI0_CLK]	= imx_clk_scu("fspi0_clk", IMX_SC_R_FSPI_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_LSIO_FSPI1_CLK]	= imx_clk_scu("fspi1_clk", IMX_SC_R_FSPI_1, IMX_SC_PM_CLK_PER, clk_cells);
 
 	/* ADMA SS */
-	clks[IMX_ADMA_UART0_CLK]	= imx_clk_scu("uart0_clk", IMX_SC_R_UART_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_UART1_CLK]	= imx_clk_scu("uart1_clk", IMX_SC_R_UART_1, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_UART2_CLK]	= imx_clk_scu("uart2_clk", IMX_SC_R_UART_2, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_UART3_CLK]	= imx_clk_scu("uart3_clk", IMX_SC_R_UART_3, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_SPI0_CLK]		= imx_clk_scu("spi0_clk",  IMX_SC_R_SPI_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_SPI1_CLK]		= imx_clk_scu("spi1_clk",  IMX_SC_R_SPI_1, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_SPI2_CLK]		= imx_clk_scu("spi2_clk",  IMX_SC_R_SPI_2, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_SPI3_CLK]		= imx_clk_scu("spi3_clk",  IMX_SC_R_SPI_3, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_CAN0_CLK]		= imx_clk_scu("can0_clk",  IMX_SC_R_CAN_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_I2C0_CLK]		= imx_clk_scu("i2c0_clk",  IMX_SC_R_I2C_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_I2C1_CLK]		= imx_clk_scu("i2c1_clk",  IMX_SC_R_I2C_1, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_I2C2_CLK]		= imx_clk_scu("i2c2_clk",  IMX_SC_R_I2C_2, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_I2C3_CLK]		= imx_clk_scu("i2c3_clk",  IMX_SC_R_I2C_3, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_FTM0_CLK]		= imx_clk_scu("ftm0_clk",  IMX_SC_R_FTM_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_FTM1_CLK]		= imx_clk_scu("ftm1_clk",  IMX_SC_R_FTM_1, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_ADC0_CLK]		= imx_clk_scu("adc0_clk",  IMX_SC_R_ADC_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_PWM_CLK]		= imx_clk_scu("pwm_clk",   IMX_SC_R_LCD_0_PWM_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_ADMA_LCD_CLK]		= imx_clk_scu("lcd_clk",   IMX_SC_R_LCD_0, IMX_SC_PM_CLK_PER);
+	clks[IMX_ADMA_UART0_CLK]	= imx_clk_scu("uart0_clk", IMX_SC_R_UART_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_UART1_CLK]	= imx_clk_scu("uart1_clk", IMX_SC_R_UART_1, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_UART2_CLK]	= imx_clk_scu("uart2_clk", IMX_SC_R_UART_2, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_UART3_CLK]	= imx_clk_scu("uart3_clk", IMX_SC_R_UART_3, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_SPI0_CLK]		= imx_clk_scu("spi0_clk",  IMX_SC_R_SPI_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_SPI1_CLK]		= imx_clk_scu("spi1_clk",  IMX_SC_R_SPI_1, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_SPI2_CLK]		= imx_clk_scu("spi2_clk",  IMX_SC_R_SPI_2, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_SPI3_CLK]		= imx_clk_scu("spi3_clk",  IMX_SC_R_SPI_3, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_CAN0_CLK]		= imx_clk_scu("can0_clk",  IMX_SC_R_CAN_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_I2C0_CLK]		= imx_clk_scu("i2c0_clk",  IMX_SC_R_I2C_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_I2C1_CLK]		= imx_clk_scu("i2c1_clk",  IMX_SC_R_I2C_1, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_I2C2_CLK]		= imx_clk_scu("i2c2_clk",  IMX_SC_R_I2C_2, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_I2C3_CLK]		= imx_clk_scu("i2c3_clk",  IMX_SC_R_I2C_3, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_FTM0_CLK]		= imx_clk_scu("ftm0_clk",  IMX_SC_R_FTM_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_FTM1_CLK]		= imx_clk_scu("ftm1_clk",  IMX_SC_R_FTM_1, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_ADC0_CLK]		= imx_clk_scu("adc0_clk",  IMX_SC_R_ADC_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_PWM_CLK]		= imx_clk_scu("pwm_clk",   IMX_SC_R_LCD_0_PWM_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_ADMA_LCD_CLK]		= imx_clk_scu("lcd_clk",   IMX_SC_R_LCD_0, IMX_SC_PM_CLK_PER, clk_cells);
 
 	/* Connectivity */
-	clks[IMX_CONN_SDHC0_CLK]	= imx_clk_scu("sdhc0_clk", IMX_SC_R_SDHC_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_CONN_SDHC1_CLK]	= imx_clk_scu("sdhc1_clk", IMX_SC_R_SDHC_1, IMX_SC_PM_CLK_PER);
-	clks[IMX_CONN_SDHC2_CLK]	= imx_clk_scu("sdhc2_clk", IMX_SC_R_SDHC_2, IMX_SC_PM_CLK_PER);
-	clks[IMX_CONN_ENET0_ROOT_CLK]	= imx_clk_scu("enet0_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_CONN_ENET0_BYPASS_CLK]	= imx_clk_scu("enet0_bypass_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_BYPASS);
-	clks[IMX_CONN_ENET0_RGMII_CLK]	= imx_clk_scu("enet0_rgmii_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_MISC0);
-	clks[IMX_CONN_ENET1_ROOT_CLK]	= imx_clk_scu("enet1_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_PER);
-	clks[IMX_CONN_ENET1_BYPASS_CLK]	= imx_clk_scu("enet1_bypass_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_BYPASS);
-	clks[IMX_CONN_ENET1_RGMII_CLK]	= imx_clk_scu("enet1_rgmii_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_MISC0);
-	clks[IMX_CONN_GPMI_BCH_IO_CLK]	= imx_clk_scu("gpmi_io_clk", IMX_SC_R_NAND, IMX_SC_PM_CLK_MST_BUS);
-	clks[IMX_CONN_GPMI_BCH_CLK]	= imx_clk_scu("gpmi_bch_clk", IMX_SC_R_NAND, IMX_SC_PM_CLK_PER);
-	clks[IMX_CONN_USB2_ACLK]	= imx_clk_scu("usb3_aclk_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_PER);
-	clks[IMX_CONN_USB2_BUS_CLK]	= imx_clk_scu("usb3_bus_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_MST_BUS);
-	clks[IMX_CONN_USB2_LPM_CLK]	= imx_clk_scu("usb3_lpm_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_MISC);
+	clks[IMX_CONN_SDHC0_CLK]	= imx_clk_scu("sdhc0_clk", IMX_SC_R_SDHC_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_CONN_SDHC1_CLK]	= imx_clk_scu("sdhc1_clk", IMX_SC_R_SDHC_1, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_CONN_SDHC2_CLK]	= imx_clk_scu("sdhc2_clk", IMX_SC_R_SDHC_2, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_CONN_ENET0_ROOT_CLK]	= imx_clk_scu("enet0_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_CONN_ENET0_BYPASS_CLK]	= imx_clk_scu("enet0_bypass_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_BYPASS, clk_cells);
+	clks[IMX_CONN_ENET0_RGMII_CLK]	= imx_clk_scu("enet0_rgmii_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_MISC0, clk_cells);
+	clks[IMX_CONN_ENET1_ROOT_CLK]	= imx_clk_scu("enet1_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_CONN_ENET1_BYPASS_CLK]	= imx_clk_scu("enet1_bypass_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_BYPASS, clk_cells);
+	clks[IMX_CONN_ENET1_RGMII_CLK]	= imx_clk_scu("enet1_rgmii_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_MISC0, clk_cells);
+	clks[IMX_CONN_GPMI_BCH_IO_CLK]	= imx_clk_scu("gpmi_io_clk", IMX_SC_R_NAND, IMX_SC_PM_CLK_MST_BUS, clk_cells);
+	clks[IMX_CONN_GPMI_BCH_CLK]	= imx_clk_scu("gpmi_bch_clk", IMX_SC_R_NAND, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_CONN_USB2_ACLK]	= imx_clk_scu("usb3_aclk_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_CONN_USB2_BUS_CLK]	= imx_clk_scu("usb3_bus_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_MST_BUS, clk_cells);
+	clks[IMX_CONN_USB2_LPM_CLK]	= imx_clk_scu("usb3_lpm_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_MISC, clk_cells);
 
 	/* Display controller SS */
-	clks[IMX_DC0_DISP0_CLK]		= imx_clk_scu("dc0_disp0_clk", IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC0);
-	clks[IMX_DC0_DISP1_CLK]		= imx_clk_scu("dc0_disp1_clk", IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC1);
+	clks[IMX_DC0_DISP0_CLK]		= imx_clk_scu("dc0_disp0_clk", IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC0, clk_cells);
+	clks[IMX_DC0_DISP1_CLK]		= imx_clk_scu("dc0_disp1_clk", IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC1, clk_cells);
 
 	/* MIPI-LVDS SS */
-	clks[IMX_MIPI0_I2C0_CLK]	= imx_clk_scu("mipi0_i2c0_clk", IMX_SC_R_MIPI_0_I2C_0, IMX_SC_PM_CLK_MISC2);
-	clks[IMX_MIPI0_I2C1_CLK]	= imx_clk_scu("mipi0_i2c1_clk", IMX_SC_R_MIPI_0_I2C_1, IMX_SC_PM_CLK_MISC2);
+	clks[IMX_MIPI0_I2C0_CLK]	= imx_clk_scu("mipi0_i2c0_clk", IMX_SC_R_MIPI_0_I2C_0, IMX_SC_PM_CLK_MISC2, clk_cells);
+	clks[IMX_MIPI0_I2C1_CLK]	= imx_clk_scu("mipi0_i2c1_clk", IMX_SC_R_MIPI_0_I2C_1, IMX_SC_PM_CLK_MISC2, clk_cells);
 
 	/* MIPI CSI SS */
-	clks[IMX_CSI0_CORE_CLK]		= imx_clk_scu("mipi_csi0_core_clk", IMX_SC_R_CSI_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_CSI0_ESC_CLK]		= imx_clk_scu("mipi_csi0_esc_clk",  IMX_SC_R_CSI_0, IMX_SC_PM_CLK_MISC);
-	clks[IMX_CSI0_I2C0_CLK]		= imx_clk_scu("mipi_csi0_i2c0_clk", IMX_SC_R_CSI_0_I2C_0, IMX_SC_PM_CLK_PER);
-	clks[IMX_CSI0_PWM0_CLK]		= imx_clk_scu("mipi_csi0_pwm0_clk", IMX_SC_R_CSI_0_PWM_0, IMX_SC_PM_CLK_PER);
+	clks[IMX_CSI0_CORE_CLK]		= imx_clk_scu("mipi_csi0_core_clk", IMX_SC_R_CSI_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_CSI0_ESC_CLK]		= imx_clk_scu("mipi_csi0_esc_clk",  IMX_SC_R_CSI_0, IMX_SC_PM_CLK_MISC, clk_cells);
+	clks[IMX_CSI0_I2C0_CLK]		= imx_clk_scu("mipi_csi0_i2c0_clk", IMX_SC_R_CSI_0_I2C_0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_CSI0_PWM0_CLK]		= imx_clk_scu("mipi_csi0_pwm0_clk", IMX_SC_R_CSI_0_PWM_0, IMX_SC_PM_CLK_PER, clk_cells);
 
 	/* GPU SS */
-	clks[IMX_GPU0_CORE_CLK]		= imx_clk_scu("gpu_core0_clk",	 IMX_SC_R_GPU_0_PID0, IMX_SC_PM_CLK_PER);
-	clks[IMX_GPU0_SHADER_CLK]	= imx_clk_scu("gpu_shader0_clk", IMX_SC_R_GPU_0_PID0, IMX_SC_PM_CLK_MISC);
+	clks[IMX_GPU0_CORE_CLK]		= imx_clk_scu("gpu_core0_clk",	 IMX_SC_R_GPU_0_PID0, IMX_SC_PM_CLK_PER, clk_cells);
+	clks[IMX_GPU0_SHADER_CLK]	= imx_clk_scu("gpu_shader0_clk", IMX_SC_R_GPU_0_PID0, IMX_SC_PM_CLK_MISC, clk_cells);
 
 	for (i = 0; i < clk_data->num; i++) {
 		if (IS_ERR(clks[i]))
@@ -134,7 +138,19 @@ static int imx8qxp_clk_probe(struct platform_device *pdev)
 				i, PTR_ERR(clks[i]));
 	}
 
-	return of_clk_add_hw_provider(ccm_node, of_clk_hw_onecell_get, clk_data);
+	if (clk_cells == 2) {
+		ret = of_clk_add_hw_provider(ccm_node, imx_scu_of_clk_src_get, imx_scu_clks);
+		if (ret)
+			imx_clk_scu_unregister();
+	} else {
+		/*
+		 * legacy binding code path doesn't unregister here because
+		 * it will be removed later.
+		 */
+		ret = of_clk_add_hw_provider(ccm_node, of_clk_hw_onecell_get, clk_data);
+	}
+
+	return ret;
 }
 
 static const struct of_device_id imx8qxp_match[] = {
diff --git a/drivers/clk/imx/clk-lpcg-scu.c b/drivers/clk/imx/clk-lpcg-scu.c
index 1f0e44f921ae..77be7632866d 100644
--- a/drivers/clk/imx/clk-lpcg-scu.c
+++ b/drivers/clk/imx/clk-lpcg-scu.c
@@ -34,6 +34,9 @@ struct clk_lpcg_scu {
 	void __iomem *reg;
 	u8 bit_idx;
 	bool hw_gate;
+
+	/* for state save&restore */
+	u32 state;
 };
 
 #define to_clk_lpcg_scu(_hw) container_of(_hw, struct clk_lpcg_scu, hw)
@@ -81,9 +84,9 @@ static const struct clk_ops clk_lpcg_scu_ops = {
 	.disable = clk_lpcg_scu_disable,
 };
 
-struct clk_hw *imx_clk_lpcg_scu(const char *name, const char *parent_name,
-				unsigned long flags, void __iomem *reg,
-				u8 bit_idx, bool hw_gate)
+struct clk_hw *__imx_clk_lpcg_scu(struct device *dev, const char *name,
+				  const char *parent_name, unsigned long flags,
+				  void __iomem *reg, u8 bit_idx, bool hw_gate)
 {
 	struct clk_lpcg_scu *clk;
 	struct clk_init_data init;
@@ -107,11 +110,53 @@ struct clk_hw *imx_clk_lpcg_scu(const char *name, const char *parent_name,
 	clk->hw.init = &init;
 
 	hw = &clk->hw;
-	ret = clk_hw_register(NULL, hw);
+	ret = clk_hw_register(dev, hw);
 	if (ret) {
 		kfree(clk);
 		hw = ERR_PTR(ret);
 	}
 
+	if (dev)
+		dev_set_drvdata(dev, clk);
+
 	return hw;
 }
+
+void imx_clk_lpcg_scu_unregister(struct clk_hw *hw)
+{
+	struct clk_lpcg_scu *clk = to_clk_lpcg_scu(hw);
+
+	clk_hw_unregister(&clk->hw);
+	kfree(clk);
+}
+
+static int __maybe_unused imx_clk_lpcg_scu_suspend(struct device *dev)
+{
+	struct clk_lpcg_scu *clk = dev_get_drvdata(dev);
+
+	clk->state = readl_relaxed(clk->reg);
+	dev_dbg(dev, "save lpcg state 0x%x\n", clk->state);
+
+	return 0;
+}
+
+static int __maybe_unused imx_clk_lpcg_scu_resume(struct device *dev)
+{
+	struct clk_lpcg_scu *clk = dev_get_drvdata(dev);
+
+	/*
+	 * FIXME: Sometimes writes don't work unless the CPU issues
+	 * them twice
+	 */
+
+	writel(clk->state, clk->reg);
+	writel(clk->state, clk->reg);
+	dev_dbg(dev, "restore lpcg state 0x%x\n", clk->state);
+
+	return 0;
+}
+
+const struct dev_pm_ops imx_clk_lpcg_scu_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(imx_clk_lpcg_scu_suspend,
+				      imx_clk_lpcg_scu_resume)
+};
diff --git a/drivers/clk/imx/clk-pll14xx.c b/drivers/clk/imx/clk-pll14xx.c
index aba36e4217d2..2b5ed86b9dbb 100644
--- a/drivers/clk/imx/clk-pll14xx.c
+++ b/drivers/clk/imx/clk-pll14xx.c
@@ -416,7 +416,7 @@ struct clk_hw *imx_dev_clk_hw_pll14xx(struct device *dev, const char *name,
 		       __func__, name);
 		kfree(pll);
 		return ERR_PTR(-EINVAL);
-	};
+	}
 
 	pll->base = base;
 	pll->hw.init = &init;
diff --git a/drivers/clk/imx/clk-scu.c b/drivers/clk/imx/clk-scu.c
index b8b2072742a5..1f5518b7ab39 100644
--- a/drivers/clk/imx/clk-scu.c
+++ b/drivers/clk/imx/clk-scu.c
@@ -8,6 +8,10 @@
 #include <linux/arm-smccc.h>
 #include <linux/clk-provider.h>
 #include <linux/err.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 
 #include "clk-scu.h"
@@ -16,6 +20,21 @@
 #define IMX_SIP_SET_CPUFREQ		0x00
 
 static struct imx_sc_ipc *ccm_ipc_handle;
+static struct device_node *pd_np;
+static struct platform_driver imx_clk_scu_driver;
+
+struct imx_scu_clk_node {
+	const char *name;
+	u32 rsrc;
+	u8 clk_type;
+	const char * const *parents;
+	int num_parents;
+
+	struct clk_hw *hw;
+	struct list_head node;
+};
+
+struct list_head imx_scu_clks[IMX_SC_R_LAST];
 
 /*
  * struct clk_scu - Description of one SCU clock
@@ -27,6 +46,10 @@ struct clk_scu {
 	struct clk_hw hw;
 	u16 rsrc_id;
 	u8 clk_type;
+
+	/* for state save&restore */
+	bool is_enabled;
+	u32 rate;
 };
 
 /*
@@ -128,9 +151,28 @@ static inline struct clk_scu *to_clk_scu(struct clk_hw *hw)
 	return container_of(hw, struct clk_scu, hw);
 }
 
-int imx_clk_scu_init(void)
+int imx_clk_scu_init(struct device_node *np)
 {
-	return imx_scu_get_handle(&ccm_ipc_handle);
+	u32 clk_cells;
+	int ret, i;
+
+	ret = imx_scu_get_handle(&ccm_ipc_handle);
+	if (ret)
+		return ret;
+
+	of_property_read_u32(np, "#clock-cells", &clk_cells);
+
+	if (clk_cells == 2) {
+		for (i = 0; i < IMX_SC_R_LAST; i++)
+			INIT_LIST_HEAD(&imx_scu_clks[i]);
+
+		/* pd_np will be used to attach power domains later */
+		pd_np = of_find_compatible_node(NULL, NULL, "fsl,scu-pd");
+		if (!pd_np)
+			return -EINVAL;
+	}
+
+	return platform_driver_register(&imx_clk_scu_driver);
 }
 
 /*
@@ -344,8 +386,9 @@ static const struct clk_ops clk_scu_cpu_ops = {
 	.unprepare = clk_scu_unprepare,
 };
 
-struct clk_hw *__imx_clk_scu(const char *name, const char * const *parents,
-			     int num_parents, u32 rsrc_id, u8 clk_type)
+struct clk_hw *__imx_clk_scu(struct device *dev, const char *name,
+			     const char * const *parents, int num_parents,
+			     u32 rsrc_id, u8 clk_type)
 {
 	struct clk_init_data init;
 	struct clk_scu *clk;
@@ -379,11 +422,185 @@ struct clk_hw *__imx_clk_scu(const char *name, const char * const *parents,
 	clk->hw.init = &init;
 
 	hw = &clk->hw;
-	ret = clk_hw_register(NULL, hw);
+	ret = clk_hw_register(dev, hw);
 	if (ret) {
 		kfree(clk);
 		hw = ERR_PTR(ret);
 	}
 
+	if (dev)
+		dev_set_drvdata(dev, clk);
+
 	return hw;
 }
+
+struct clk_hw *imx_scu_of_clk_src_get(struct of_phandle_args *clkspec,
+				      void *data)
+{
+	unsigned int rsrc = clkspec->args[0];
+	unsigned int idx = clkspec->args[1];
+	struct list_head *scu_clks = data;
+	struct imx_scu_clk_node *clk;
+
+	list_for_each_entry(clk, &scu_clks[rsrc], node) {
+		if (clk->clk_type == idx)
+			return clk->hw;
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
+static int imx_clk_scu_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct imx_scu_clk_node *clk = dev_get_platdata(dev);
+	struct clk_hw *hw;
+	int ret;
+
+	pm_runtime_set_suspended(dev);
+	pm_runtime_set_autosuspend_delay(dev, 50);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_enable(dev);
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret) {
+		pm_runtime_disable(dev);
+		return ret;
+	}
+
+	hw = __imx_clk_scu(dev, clk->name, clk->parents, clk->num_parents,
+			   clk->rsrc, clk->clk_type);
+	if (IS_ERR(hw)) {
+		pm_runtime_disable(dev);
+		return PTR_ERR(hw);
+	}
+
+	clk->hw = hw;
+	list_add_tail(&clk->node, &imx_scu_clks[clk->rsrc]);
+
+	pm_runtime_mark_last_busy(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
+
+	dev_dbg(dev, "register SCU clock rsrc:%d type:%d\n", clk->rsrc,
+		clk->clk_type);
+
+	return 0;
+}
+
+static int __maybe_unused imx_clk_scu_suspend(struct device *dev)
+{
+	struct clk_scu *clk = dev_get_drvdata(dev);
+
+	clk->rate = clk_hw_get_rate(&clk->hw);
+	clk->is_enabled = clk_hw_is_enabled(&clk->hw);
+
+	if (clk->rate)
+		dev_dbg(dev, "save rate %d\n", clk->rate);
+
+	if (clk->is_enabled)
+		dev_dbg(dev, "save enabled state\n");
+
+	return 0;
+}
+
+static int __maybe_unused imx_clk_scu_resume(struct device *dev)
+{
+	struct clk_scu *clk = dev_get_drvdata(dev);
+	int ret = 0;
+
+	if (clk->rate) {
+		ret = clk_scu_set_rate(&clk->hw, clk->rate, 0);
+		dev_dbg(dev, "restore rate %d %s\n", clk->rate,
+			!ret ? "success" : "failed");
+	}
+
+	if (clk->is_enabled) {
+		ret = clk_scu_prepare(&clk->hw);
+		dev_dbg(dev, "restore enabled state %s\n",
+			!ret ? "success" : "failed");
+	}
+
+	return ret;
+}
+
+static const struct dev_pm_ops imx_clk_scu_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(imx_clk_scu_suspend,
+				      imx_clk_scu_resume)
+};
+
+static struct platform_driver imx_clk_scu_driver = {
+	.driver = {
+		.name = "imx-scu-clk",
+		.suppress_bind_attrs = true,
+		.pm = &imx_clk_scu_pm_ops,
+	},
+	.probe = imx_clk_scu_probe,
+};
+
+static int imx_clk_scu_attach_pd(struct device *dev, u32 rsrc_id)
+{
+	struct of_phandle_args genpdspec = {
+		.np = pd_np,
+		.args_count = 1,
+		.args[0] = rsrc_id,
+	};
+
+	if (rsrc_id == IMX_SC_R_A35 || rsrc_id == IMX_SC_R_A53 ||
+	    rsrc_id == IMX_SC_R_A72)
+		return 0;
+
+	return of_genpd_add_device(&genpdspec, dev);
+}
+
+struct clk_hw *imx_clk_scu_alloc_dev(const char *name,
+				     const char * const *parents,
+				     int num_parents, u32 rsrc_id, u8 clk_type)
+{
+	struct imx_scu_clk_node clk = {
+		.name = name,
+		.rsrc = rsrc_id,
+		.clk_type = clk_type,
+		.parents = parents,
+		.num_parents = num_parents,
+	};
+	struct platform_device *pdev;
+	int ret;
+
+	pdev = platform_device_alloc(name, PLATFORM_DEVID_NONE);
+	if (!pdev) {
+		pr_err("%s: failed to allocate scu clk dev rsrc %d type %d\n",
+		       name, rsrc_id, clk_type);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	ret = platform_device_add_data(pdev, &clk, sizeof(clk));
+	if (ret) {
+		platform_device_put(pdev);
+		return ERR_PTR(ret);
+	}
+
+	pdev->driver_override = "imx-scu-clk";
+
+	ret = imx_clk_scu_attach_pd(&pdev->dev, rsrc_id);
+	if (ret)
+		pr_warn("%s: failed to attached the power domain %d\n",
+			name, ret);
+
+	platform_device_add(pdev);
+
+	/* For API backwards compatiblilty, simply return NULL for success */
+	return NULL;
+}
+
+void imx_clk_scu_unregister(void)
+{
+	struct imx_scu_clk_node *clk;
+	int i;
+
+	for (i = 0; i < IMX_SC_R_LAST; i++) {
+		list_for_each_entry(clk, &imx_scu_clks[i], node) {
+			clk_hw_unregister(clk->hw);
+			kfree(clk);
+		}
+	}
+}
diff --git a/drivers/clk/imx/clk-scu.h b/drivers/clk/imx/clk-scu.h
index 2bcfaf06a458..e8352164923e 100644
--- a/drivers/clk/imx/clk-scu.h
+++ b/drivers/clk/imx/clk-scu.h
@@ -8,25 +8,61 @@
 #define __IMX_CLK_SCU_H
 
 #include <linux/firmware/imx/sci.h>
+#include <linux/of.h>
 
-int imx_clk_scu_init(void);
+extern struct list_head imx_scu_clks[];
+extern const struct dev_pm_ops imx_clk_lpcg_scu_pm_ops;
 
-struct clk_hw *__imx_clk_scu(const char *name, const char * const *parents,
-			     int num_parents, u32 rsrc_id, u8 clk_type);
+int imx_clk_scu_init(struct device_node *np);
+struct clk_hw *imx_scu_of_clk_src_get(struct of_phandle_args *clkspec,
+				      void *data);
+struct clk_hw *imx_clk_scu_alloc_dev(const char *name,
+				     const char * const *parents,
+				     int num_parents, u32 rsrc_id, u8 clk_type);
+
+struct clk_hw *__imx_clk_scu(struct device *dev, const char *name,
+			     const char * const *parents, int num_parents,
+			     u32 rsrc_id, u8 clk_type);
+
+void imx_clk_scu_unregister(void);
+
+struct clk_hw *__imx_clk_lpcg_scu(struct device *dev, const char *name,
+				  const char *parent_name, unsigned long flags,
+				  void __iomem *reg, u8 bit_idx, bool hw_gate);
+void imx_clk_lpcg_scu_unregister(struct clk_hw *hw);
 
 static inline struct clk_hw *imx_clk_scu(const char *name, u32 rsrc_id,
-					 u8 clk_type)
+					 u8 clk_type, u8 clk_cells)
 {
-	return __imx_clk_scu(name, NULL, 0, rsrc_id, clk_type);
+	if (clk_cells == 2)
+		return imx_clk_scu_alloc_dev(name, NULL, 0, rsrc_id, clk_type);
+	else
+		return __imx_clk_scu(NULL, name, NULL, 0, rsrc_id, clk_type);
 }
 
 static inline struct clk_hw *imx_clk_scu2(const char *name, const char * const *parents,
-					  int num_parents, u32 rsrc_id, u8 clk_type)
+					  int num_parents, u32 rsrc_id, u8 clk_type,
+					  u8 clk_cells)
+{
+	if (clk_cells == 2)
+		return imx_clk_scu_alloc_dev(name, parents, num_parents, rsrc_id, clk_type);
+	else
+		return __imx_clk_scu(NULL, name, parents, num_parents, rsrc_id, clk_type);
+}
+
+static inline struct clk_hw *imx_clk_lpcg_scu_dev(struct device *dev, const char *name,
+						  const char *parent_name, unsigned long flags,
+						  void __iomem *reg, u8 bit_idx, bool hw_gate)
 {
-	return __imx_clk_scu(name, parents, num_parents, rsrc_id, clk_type);
+	return __imx_clk_lpcg_scu(dev, name, parent_name, flags, reg,
+				  bit_idx, hw_gate);
 }
 
-struct clk_hw *imx_clk_lpcg_scu(const char *name, const char *parent_name,
-				unsigned long flags, void __iomem *reg,
-				u8 bit_idx, bool hw_gate);
+static inline struct clk_hw *imx_clk_lpcg_scu(const char *name, const char *parent_name,
+					      unsigned long flags, void __iomem *reg,
+					      u8 bit_idx, bool hw_gate)
+{
+	return __imx_clk_lpcg_scu(NULL, name, parent_name, flags, reg,
+				  bit_idx, hw_gate);
+}
 #endif
diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h
index 1d7be0c86538..4f04c8287286 100644
--- a/drivers/clk/imx/clk.h
+++ b/drivers/clk/imx/clk.h
@@ -6,8 +6,6 @@
 #include <linux/spinlock.h>
 #include <linux/clk-provider.h>
 
-#define IMX_CLK_GATE2_SINGLE_BIT	1
-
 extern spinlock_t imx_ccm_lock;
 
 void imx_check_clocks(struct clk *clks[], unsigned int count);
@@ -68,9 +66,9 @@ extern struct imx_pll14xx_clk imx_1443x_dram_pll;
 	to_clk(imx_clk_hw_cpu(name, parent_name, div, mux, pll, step))
 
 #define clk_register_gate2(dev, name, parent_name, flags, reg, bit_idx, \
-				cgr_val, clk_gate_flags, lock, share_count) \
+				cgr_val, cgr_mask, clk_gate_flags, lock, share_count) \
 	to_clk(clk_hw_register_gate2(dev, name, parent_name, flags, reg, bit_idx, \
-				cgr_val, clk_gate_flags, lock, share_count))
+				cgr_val, cgr_mask, clk_gate_flags, lock, share_count))
 
 #define imx_clk_pllv3(type, name, parent_name, base, div_mask) \
 	to_clk(imx_clk_hw_pllv3(type, name, parent_name, base, div_mask))
@@ -198,7 +196,7 @@ struct clk_hw *imx_clk_hw_pllv4(const char *name, const char *parent_name,
 
 struct clk_hw *clk_hw_register_gate2(struct device *dev, const char *name,
 		const char *parent_name, unsigned long flags,
-		void __iomem *reg, u8 bit_idx, u8 cgr_val,
+		void __iomem *reg, u8 bit_idx, u8 cgr_val, u8 cgr_mask,
 		u8 clk_gate_flags, spinlock_t *lock,
 		unsigned int *share_count);
 
@@ -351,14 +349,14 @@ static inline struct clk_hw *imx_clk_hw_gate2(const char *name, const char *pare
 		void __iomem *reg, u8 shift)
 {
 	return clk_hw_register_gate2(NULL, name, parent, CLK_SET_RATE_PARENT, reg,
-			shift, 0x3, 0, &imx_ccm_lock, NULL);
+			shift, 0x3, 0x3, 0, &imx_ccm_lock, NULL);
 }
 
 static inline struct clk_hw *imx_clk_hw_gate2_flags(const char *name, const char *parent,
 		void __iomem *reg, u8 shift, unsigned long flags)
 {
 	return clk_hw_register_gate2(NULL, name, parent, flags | CLK_SET_RATE_PARENT, reg,
-			shift, 0x3, 0, &imx_ccm_lock, NULL);
+			shift, 0x3, 0x3, 0, &imx_ccm_lock, NULL);
 }
 
 static inline struct clk_hw *imx_clk_hw_gate2_shared(const char *name,
@@ -366,7 +364,7 @@ static inline struct clk_hw *imx_clk_hw_gate2_shared(const char *name,
 		unsigned int *share_count)
 {
 	return clk_hw_register_gate2(NULL, name, parent, CLK_SET_RATE_PARENT, reg,
-			shift, 0x3, 0, &imx_ccm_lock, share_count);
+			shift, 0x3, 0x3, 0, &imx_ccm_lock, share_count);
 }
 
 static inline struct clk_hw *imx_clk_hw_gate2_shared2(const char *name,
@@ -374,7 +372,7 @@ static inline struct clk_hw *imx_clk_hw_gate2_shared2(const char *name,
 		unsigned int *share_count)
 {
 	return clk_hw_register_gate2(NULL, name, parent, CLK_SET_RATE_PARENT |
-				  CLK_OPS_PARENT_ENABLE, reg, shift, 0x3, 0,
+				  CLK_OPS_PARENT_ENABLE, reg, shift, 0x3, 0x3, 0,
 				  &imx_ccm_lock, share_count);
 }
 
@@ -384,16 +382,15 @@ static inline struct clk_hw *imx_dev_clk_hw_gate_shared(struct device *dev,
 				unsigned int *share_count)
 {
 	return clk_hw_register_gate2(NULL, name, parent, CLK_SET_RATE_PARENT |
-					CLK_OPS_PARENT_ENABLE, reg, shift, 0x3,
-					IMX_CLK_GATE2_SINGLE_BIT,
-					&imx_ccm_lock, share_count);
+					CLK_OPS_PARENT_ENABLE, reg, shift, 0x1,
+					0x1, 0, &imx_ccm_lock, share_count);
 }
 
 static inline struct clk *imx_clk_gate2_cgr(const char *name,
 		const char *parent, void __iomem *reg, u8 shift, u8 cgr_val)
 {
 	return clk_register_gate2(NULL, name, parent, CLK_SET_RATE_PARENT, reg,
-			shift, cgr_val, 0, &imx_ccm_lock, NULL);
+			shift, cgr_val, 0x3, 0, &imx_ccm_lock, NULL);
 }
 
 static inline struct clk_hw *imx_clk_hw_gate3(const char *name, const char *parent,
@@ -421,7 +418,7 @@ static inline struct clk_hw *imx_clk_hw_gate4(const char *name, const char *pare
 {
 	return clk_hw_register_gate2(NULL, name, parent,
 			CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
-			reg, shift, 0x3, 0, &imx_ccm_lock, NULL);
+			reg, shift, 0x3, 0x3, 0, &imx_ccm_lock, NULL);
 }
 
 static inline struct clk_hw *imx_clk_hw_gate4_flags(const char *name,
@@ -430,7 +427,7 @@ static inline struct clk_hw *imx_clk_hw_gate4_flags(const char *name,
 {
 	return clk_hw_register_gate2(NULL, name, parent,
 			flags | CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
-			reg, shift, 0x3, 0, &imx_ccm_lock, NULL);
+			reg, shift, 0x3, 0x3, 0, &imx_ccm_lock, NULL);
 }
 
 #define imx_clk_gate4_flags(name, parent, reg, shift, flags) \
diff --git a/drivers/clk/ingenic/cgu.c b/drivers/clk/ingenic/cgu.c
index dac6edc670cc..c8e9cb6c8e39 100644
--- a/drivers/clk/ingenic/cgu.c
+++ b/drivers/clk/ingenic/cgu.c
@@ -392,15 +392,21 @@ static unsigned int
 ingenic_clk_calc_hw_div(const struct ingenic_cgu_clk_info *clk_info,
 			unsigned int div)
 {
-	unsigned int i;
+	unsigned int i, best_i = 0, best = (unsigned int)-1;
 
 	for (i = 0; i < (1 << clk_info->div.bits)
 				&& clk_info->div.div_table[i]; i++) {
-		if (clk_info->div.div_table[i] >= div)
-			return i;
+		if (clk_info->div.div_table[i] >= div &&
+		    clk_info->div.div_table[i] < best) {
+			best = clk_info->div.div_table[i];
+			best_i = i;
+
+			if (div == best)
+				break;
+		}
 	}
 
-	return i - 1;
+	return best_i;
 }
 
 static unsigned
diff --git a/drivers/clk/mediatek/clk-mux.c b/drivers/clk/mediatek/clk-mux.c
index 14e127e9a740..dcc1352bf13c 100644
--- a/drivers/clk/mediatek/clk-mux.c
+++ b/drivers/clk/mediatek/clk-mux.c
@@ -155,7 +155,7 @@ const struct clk_ops mtk_mux_gate_clr_set_upd_ops = {
 	.set_parent = mtk_clk_mux_set_parent_setclr_lock,
 };
 
-struct clk *mtk_clk_register_mux(const struct mtk_mux *mux,
+static struct clk *mtk_clk_register_mux(const struct mtk_mux *mux,
 				 struct regmap *regmap,
 				 spinlock_t *lock)
 {
diff --git a/drivers/clk/mediatek/clk-mux.h b/drivers/clk/mediatek/clk-mux.h
index f5625f4d9e6c..8e2f927dd2ff 100644
--- a/drivers/clk/mediatek/clk-mux.h
+++ b/drivers/clk/mediatek/clk-mux.h
@@ -77,10 +77,6 @@ extern const struct clk_ops mtk_mux_gate_clr_set_upd_ops;
 			_width, _gate, _upd_ofs, _upd,			\
 			CLK_SET_RATE_PARENT)
 
-struct clk *mtk_clk_register_mux(const struct mtk_mux *mux,
-				 struct regmap *regmap,
-				 spinlock_t *lock);
-
 int mtk_clk_register_muxes(const struct mtk_mux *muxes,
 			   int num, struct device_node *node,
 			   spinlock_t *lock,
diff --git a/drivers/clk/meson/Kconfig b/drivers/clk/meson/Kconfig
index 034da203e8e0..fc002c155bc3 100644
--- a/drivers/clk/meson/Kconfig
+++ b/drivers/clk/meson/Kconfig
@@ -58,7 +58,7 @@ config COMMON_CLK_MESON8B
 	  want peripherals and CPU frequency scaling to work.
 
 config COMMON_CLK_GXBB
-	bool "GXBB and GXL SoC clock controllers support"
+	tristate "GXBB and GXL SoC clock controllers support"
 	depends on ARM64
 	default y
 	select COMMON_CLK_MESON_REGMAP
@@ -74,7 +74,7 @@ config COMMON_CLK_GXBB
 	  Say Y if you want peripherals and CPU frequency scaling to work.
 
 config COMMON_CLK_AXG
-	bool "AXG SoC clock controllers support"
+	tristate "AXG SoC clock controllers support"
 	depends on ARM64
 	default y
 	select COMMON_CLK_MESON_REGMAP
@@ -100,7 +100,7 @@ config COMMON_CLK_AXG_AUDIO
 	  aka axg, Say Y if you want audio subsystem to work.
 
 config COMMON_CLK_G12A
-	bool "G12 and SM1 SoC clock controllers support"
+	tristate "G12 and SM1 SoC clock controllers support"
 	depends on ARM64
 	default y
 	select COMMON_CLK_MESON_REGMAP
@@ -110,6 +110,7 @@ config COMMON_CLK_G12A
 	select COMMON_CLK_MESON_AO_CLKC
 	select COMMON_CLK_MESON_EE_CLKC
 	select COMMON_CLK_MESON_CPU_DYNDIV
+	select COMMON_CLK_MESON_VID_PLL_DIV
 	select MFD_SYSCON
 	help
 	  Support for the clock controller on Amlogic S905D2, S905X2 and S905Y2
diff --git a/drivers/clk/meson/axg-aoclk.c b/drivers/clk/meson/axg-aoclk.c
index b488b40c9d0e..af6db437bcd8 100644
--- a/drivers/clk/meson/axg-aoclk.c
+++ b/drivers/clk/meson/axg-aoclk.c
@@ -12,6 +12,7 @@
 #include <linux/platform_device.h>
 #include <linux/reset-controller.h>
 #include <linux/mfd/syscon.h>
+#include <linux/module.h>
 #include "meson-aoclk.h"
 #include "axg-aoclk.h"
 
@@ -326,6 +327,7 @@ static const struct of_device_id axg_aoclkc_match_table[] = {
 	},
 	{ }
 };
+MODULE_DEVICE_TABLE(of, axg_aoclkc_match_table);
 
 static struct platform_driver axg_aoclkc_driver = {
 	.probe		= meson_aoclkc_probe,
@@ -335,4 +337,5 @@ static struct platform_driver axg_aoclkc_driver = {
 	},
 };
 
-builtin_platform_driver(axg_aoclkc_driver);
+module_platform_driver(axg_aoclkc_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c
index 13fc0006f63d..0e44695b8772 100644
--- a/drivers/clk/meson/axg.c
+++ b/drivers/clk/meson/axg.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/module.h>
 
 #include "clk-regmap.h"
 #include "clk-pll.h"
@@ -1026,6 +1027,743 @@ static struct clk_regmap axg_sd_emmc_c_clk0 = {
 	},
 };
 
+/* VPU Clock */
+
+static const struct clk_hw *axg_vpu_parent_hws[] = {
+	&axg_fclk_div4.hw,
+	&axg_fclk_div3.hw,
+	&axg_fclk_div5.hw,
+	&axg_fclk_div7.hw,
+};
+
+static struct clk_regmap axg_vpu_0_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_VPU_CLK_CNTL,
+		.mask = 0x3,
+		.shift = 9,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vpu_0_sel",
+		.ops = &clk_regmap_mux_ops,
+		.parent_hws = axg_vpu_parent_hws,
+		.num_parents = ARRAY_SIZE(axg_vpu_parent_hws),
+		/* We need a specific parent for VPU clock source, let it be set in DT */
+		.flags = CLK_SET_RATE_NO_REPARENT,
+	},
+};
+
+static struct clk_regmap axg_vpu_0_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_VPU_CLK_CNTL,
+		.shift = 0,
+		.width = 7,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vpu_0_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vpu_0_sel.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_vpu_0 = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VPU_CLK_CNTL,
+		.bit_idx = 8,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vpu_0",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vpu_0_div.hw },
+		.num_parents = 1,
+		/*
+		 * We want to avoid CCF to disable the VPU clock if
+		 * display has been set by Bootloader
+		 */
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vpu_1_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_VPU_CLK_CNTL,
+		.mask = 0x3,
+		.shift = 25,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vpu_1_sel",
+		.ops = &clk_regmap_mux_ops,
+		.parent_hws = axg_vpu_parent_hws,
+		.num_parents = ARRAY_SIZE(axg_vpu_parent_hws),
+		/* We need a specific parent for VPU clock source, let it be set in DT */
+		.flags = CLK_SET_RATE_NO_REPARENT,
+	},
+};
+
+static struct clk_regmap axg_vpu_1_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_VPU_CLK_CNTL,
+		.shift = 16,
+		.width = 7,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vpu_1_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vpu_1_sel.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_vpu_1 = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VPU_CLK_CNTL,
+		.bit_idx = 24,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vpu_1",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vpu_1_div.hw },
+		.num_parents = 1,
+		/*
+		 * We want to avoid CCF to disable the VPU clock if
+		 * display has been set by Bootloader
+		 */
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vpu = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_VPU_CLK_CNTL,
+		.mask = 1,
+		.shift = 31,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vpu",
+		.ops = &clk_regmap_mux_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vpu_0.hw,
+			&axg_vpu_1.hw
+		},
+		.num_parents = 2,
+		.flags = CLK_SET_RATE_NO_REPARENT,
+	},
+};
+
+/* VAPB Clock */
+
+static struct clk_regmap axg_vapb_0_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_VAPBCLK_CNTL,
+		.mask = 0x3,
+		.shift = 9,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vapb_0_sel",
+		.ops = &clk_regmap_mux_ops,
+		.parent_hws = axg_vpu_parent_hws,
+		.num_parents = ARRAY_SIZE(axg_vpu_parent_hws),
+		.flags = CLK_SET_RATE_NO_REPARENT,
+	},
+};
+
+static struct clk_regmap axg_vapb_0_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_VAPBCLK_CNTL,
+		.shift = 0,
+		.width = 7,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vapb_0_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vapb_0_sel.hw
+		},
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_vapb_0 = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VAPBCLK_CNTL,
+		.bit_idx = 8,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vapb_0",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vapb_0_div.hw
+		},
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vapb_1_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_VAPBCLK_CNTL,
+		.mask = 0x3,
+		.shift = 25,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vapb_1_sel",
+		.ops = &clk_regmap_mux_ops,
+		.parent_hws = axg_vpu_parent_hws,
+		.num_parents = ARRAY_SIZE(axg_vpu_parent_hws),
+		.flags = CLK_SET_RATE_NO_REPARENT,
+	},
+};
+
+static struct clk_regmap axg_vapb_1_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_VAPBCLK_CNTL,
+		.shift = 16,
+		.width = 7,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vapb_1_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vapb_1_sel.hw
+		},
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_vapb_1 = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VAPBCLK_CNTL,
+		.bit_idx = 24,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vapb_1",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vapb_1_div.hw
+		},
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vapb_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_VAPBCLK_CNTL,
+		.mask = 1,
+		.shift = 31,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vapb_sel",
+		.ops = &clk_regmap_mux_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vapb_0.hw,
+			&axg_vapb_1.hw
+		},
+		.num_parents = 2,
+		.flags = CLK_SET_RATE_NO_REPARENT,
+	},
+};
+
+static struct clk_regmap axg_vapb = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VAPBCLK_CNTL,
+		.bit_idx = 30,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vapb",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vapb_sel.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+/* Video Clocks */
+
+static const struct clk_hw *axg_vclk_parent_hws[] = {
+	&axg_gp0_pll.hw,
+	&axg_fclk_div4.hw,
+	&axg_fclk_div3.hw,
+	&axg_fclk_div5.hw,
+	&axg_fclk_div2.hw,
+	&axg_fclk_div7.hw,
+	&axg_mpll1.hw,
+};
+
+static struct clk_regmap axg_vclk_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_VID_CLK_CNTL,
+		.mask = 0x7,
+		.shift = 16,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk_sel",
+		.ops = &clk_regmap_mux_ops,
+		.parent_hws = axg_vclk_parent_hws,
+		.num_parents = ARRAY_SIZE(axg_vclk_parent_hws),
+		.flags = CLK_SET_RATE_NO_REPARENT | CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct clk_regmap axg_vclk2_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_VIID_CLK_CNTL,
+		.mask = 0x7,
+		.shift = 16,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk2_sel",
+		.ops = &clk_regmap_mux_ops,
+		.parent_hws = axg_vclk_parent_hws,
+		.num_parents = ARRAY_SIZE(axg_vclk_parent_hws),
+		.flags = CLK_SET_RATE_NO_REPARENT | CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct clk_regmap axg_vclk_input = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VID_CLK_DIV,
+		.bit_idx = 16,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk_input",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk_sel.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk2_input = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VIID_CLK_DIV,
+		.bit_idx = 16,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk2_input",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk2_sel.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_VID_CLK_DIV,
+		.shift = 0,
+		.width = 8,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vclk_input.hw
+		},
+		.num_parents = 1,
+		.flags = CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct clk_regmap axg_vclk2_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_VIID_CLK_DIV,
+		.shift = 0,
+		.width = 8,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk2_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vclk2_input.hw
+		},
+		.num_parents = 1,
+		.flags = CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct clk_regmap axg_vclk = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VID_CLK_CNTL,
+		.bit_idx = 19,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk_div.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk2 = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VIID_CLK_CNTL,
+		.bit_idx = 19,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk2",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk2_div.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk_div1 = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VID_CLK_CNTL,
+		.bit_idx = 0,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk_div1",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk_div2_en = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VID_CLK_CNTL,
+		.bit_idx = 1,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk_div2_en",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk_div4_en = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VID_CLK_CNTL,
+		.bit_idx = 2,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk_div4_en",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk_div6_en = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VID_CLK_CNTL,
+		.bit_idx = 3,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk_div6_en",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk_div12_en = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VID_CLK_CNTL,
+		.bit_idx = 4,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk_div12_en",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk2_div1 = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VIID_CLK_CNTL,
+		.bit_idx = 0,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk2_div1",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk2.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk2_div2_en = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VIID_CLK_CNTL,
+		.bit_idx = 1,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk2_div2_en",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk2.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk2_div4_en = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VIID_CLK_CNTL,
+		.bit_idx = 2,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk2_div4_en",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk2.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk2_div6_en = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VIID_CLK_CNTL,
+		.bit_idx = 3,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk2_div6_en",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk2.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_regmap axg_vclk2_div12_en = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VIID_CLK_CNTL,
+		.bit_idx = 4,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vclk2_div12_en",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) { &axg_vclk2.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+static struct clk_fixed_factor axg_vclk_div2 = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk_div2",
+		.ops = &clk_fixed_factor_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vclk_div2_en.hw
+		},
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor axg_vclk_div4 = {
+	.mult = 1,
+	.div = 4,
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk_div4",
+		.ops = &clk_fixed_factor_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vclk_div4_en.hw
+		},
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor axg_vclk_div6 = {
+	.mult = 1,
+	.div = 6,
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk_div6",
+		.ops = &clk_fixed_factor_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vclk_div6_en.hw
+		},
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor axg_vclk_div12 = {
+	.mult = 1,
+	.div = 12,
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk_div12",
+		.ops = &clk_fixed_factor_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vclk_div12_en.hw
+		},
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor axg_vclk2_div2 = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk2_div2",
+		.ops = &clk_fixed_factor_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vclk2_div2_en.hw
+		},
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor axg_vclk2_div4 = {
+	.mult = 1,
+	.div = 4,
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk2_div4",
+		.ops = &clk_fixed_factor_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vclk2_div4_en.hw
+		},
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor axg_vclk2_div6 = {
+	.mult = 1,
+	.div = 6,
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk2_div6",
+		.ops = &clk_fixed_factor_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vclk2_div6_en.hw
+		},
+		.num_parents = 1,
+	},
+};
+
+static struct clk_fixed_factor axg_vclk2_div12 = {
+	.mult = 1,
+	.div = 12,
+	.hw.init = &(struct clk_init_data){
+		.name = "vclk2_div12",
+		.ops = &clk_fixed_factor_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vclk2_div12_en.hw
+		},
+		.num_parents = 1,
+	},
+};
+
+static u32 mux_table_cts_sel[] = { 0, 1, 2, 3, 4, 8, 9, 10, 11, 12 };
+static const struct clk_hw *axg_cts_parent_hws[] = {
+	&axg_vclk_div1.hw,
+	&axg_vclk_div2.hw,
+	&axg_vclk_div4.hw,
+	&axg_vclk_div6.hw,
+	&axg_vclk_div12.hw,
+	&axg_vclk2_div1.hw,
+	&axg_vclk2_div2.hw,
+	&axg_vclk2_div4.hw,
+	&axg_vclk2_div6.hw,
+	&axg_vclk2_div12.hw,
+};
+
+static struct clk_regmap axg_cts_encl_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_VIID_CLK_DIV,
+		.mask = 0xf,
+		.shift = 12,
+		.table = mux_table_cts_sel,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "cts_encl_sel",
+		.ops = &clk_regmap_mux_ops,
+		.parent_hws = axg_cts_parent_hws,
+		.num_parents = ARRAY_SIZE(axg_cts_parent_hws),
+		.flags = CLK_SET_RATE_NO_REPARENT | CLK_GET_RATE_NOCACHE,
+	},
+};
+
+static struct clk_regmap axg_cts_encl = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VID_CLK_CNTL2,
+		.bit_idx = 3,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "cts_encl",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_cts_encl_sel.hw
+		},
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+	},
+};
+
+/* MIPI DSI Host Clock */
+
+static u32 mux_table_axg_vdin_meas[]    = { 0, 1, 2, 3, 6, 7 };
+static const struct clk_parent_data axg_vdin_meas_parent_data[] = {
+	{ .fw_name = "xtal", },
+	{ .hw = &axg_fclk_div4.hw },
+	{ .hw = &axg_fclk_div3.hw },
+	{ .hw = &axg_fclk_div5.hw },
+	{ .hw = &axg_fclk_div2.hw },
+	{ .hw = &axg_fclk_div7.hw },
+};
+
+static struct clk_regmap axg_vdin_meas_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_VDIN_MEAS_CLK_CNTL,
+		.mask = 0x7,
+		.shift = 21,
+		.flags = CLK_MUX_ROUND_CLOSEST,
+		.table = mux_table_axg_vdin_meas,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vdin_meas_sel",
+		.ops = &clk_regmap_mux_ops,
+		.parent_data = axg_vdin_meas_parent_data,
+		.num_parents = ARRAY_SIZE(axg_vdin_meas_parent_data),
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_vdin_meas_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_VDIN_MEAS_CLK_CNTL,
+		.shift = 12,
+		.width = 7,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "vdin_meas_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vdin_meas_sel.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_vdin_meas = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_VDIN_MEAS_CLK_CNTL,
+		.bit_idx = 20,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "vdin_meas",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&axg_vdin_meas_div.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
 static u32 mux_table_gen_clk[]	= { 0, 4, 5, 6, 7, 8,
 				    9, 10, 11, 13, 14, };
 static const struct clk_parent_data gen_clk_parent_data[] = {
@@ -1246,6 +1984,52 @@ static struct clk_hw_onecell_data axg_hw_onecell_data = {
 		[CLKID_HIFI_PLL_DCO]		= &axg_hifi_pll_dco.hw,
 		[CLKID_PCIE_PLL_DCO]		= &axg_pcie_pll_dco.hw,
 		[CLKID_PCIE_PLL_OD]		= &axg_pcie_pll_od.hw,
+		[CLKID_VPU_0_DIV]		= &axg_vpu_0_div.hw,
+		[CLKID_VPU_0_SEL]		= &axg_vpu_0_sel.hw,
+		[CLKID_VPU_0]			= &axg_vpu_0.hw,
+		[CLKID_VPU_1_DIV]		= &axg_vpu_1_div.hw,
+		[CLKID_VPU_1_SEL]		= &axg_vpu_1_sel.hw,
+		[CLKID_VPU_1]			= &axg_vpu_1.hw,
+		[CLKID_VPU]			= &axg_vpu.hw,
+		[CLKID_VAPB_0_DIV]		= &axg_vapb_0_div.hw,
+		[CLKID_VAPB_0_SEL]		= &axg_vapb_0_sel.hw,
+		[CLKID_VAPB_0]			= &axg_vapb_0.hw,
+		[CLKID_VAPB_1_DIV]		= &axg_vapb_1_div.hw,
+		[CLKID_VAPB_1_SEL]		= &axg_vapb_1_sel.hw,
+		[CLKID_VAPB_1]			= &axg_vapb_1.hw,
+		[CLKID_VAPB_SEL]		= &axg_vapb_sel.hw,
+		[CLKID_VAPB]			= &axg_vapb.hw,
+		[CLKID_VCLK]			= &axg_vclk.hw,
+		[CLKID_VCLK2]			= &axg_vclk2.hw,
+		[CLKID_VCLK_SEL]		= &axg_vclk_sel.hw,
+		[CLKID_VCLK2_SEL]		= &axg_vclk2_sel.hw,
+		[CLKID_VCLK_INPUT]		= &axg_vclk_input.hw,
+		[CLKID_VCLK2_INPUT]		= &axg_vclk2_input.hw,
+		[CLKID_VCLK_DIV]		= &axg_vclk_div.hw,
+		[CLKID_VCLK2_DIV]		= &axg_vclk2_div.hw,
+		[CLKID_VCLK_DIV2_EN]		= &axg_vclk_div2_en.hw,
+		[CLKID_VCLK_DIV4_EN]		= &axg_vclk_div4_en.hw,
+		[CLKID_VCLK_DIV6_EN]		= &axg_vclk_div6_en.hw,
+		[CLKID_VCLK_DIV12_EN]		= &axg_vclk_div12_en.hw,
+		[CLKID_VCLK2_DIV2_EN]		= &axg_vclk2_div2_en.hw,
+		[CLKID_VCLK2_DIV4_EN]		= &axg_vclk2_div4_en.hw,
+		[CLKID_VCLK2_DIV6_EN]		= &axg_vclk2_div6_en.hw,
+		[CLKID_VCLK2_DIV12_EN]		= &axg_vclk2_div12_en.hw,
+		[CLKID_VCLK_DIV1]		= &axg_vclk_div1.hw,
+		[CLKID_VCLK_DIV2]		= &axg_vclk_div2.hw,
+		[CLKID_VCLK_DIV4]		= &axg_vclk_div4.hw,
+		[CLKID_VCLK_DIV6]		= &axg_vclk_div6.hw,
+		[CLKID_VCLK_DIV12]		= &axg_vclk_div12.hw,
+		[CLKID_VCLK2_DIV1]		= &axg_vclk2_div1.hw,
+		[CLKID_VCLK2_DIV2]		= &axg_vclk2_div2.hw,
+		[CLKID_VCLK2_DIV4]		= &axg_vclk2_div4.hw,
+		[CLKID_VCLK2_DIV6]		= &axg_vclk2_div6.hw,
+		[CLKID_VCLK2_DIV12]		= &axg_vclk2_div12.hw,
+		[CLKID_CTS_ENCL_SEL]		= &axg_cts_encl_sel.hw,
+		[CLKID_CTS_ENCL]		= &axg_cts_encl.hw,
+		[CLKID_VDIN_MEAS_SEL]		= &axg_vdin_meas_sel.hw,
+		[CLKID_VDIN_MEAS_DIV]		= &axg_vdin_meas_div.hw,
+		[CLKID_VDIN_MEAS]		= &axg_vdin_meas.hw,
 		[NR_CLKS]			= NULL,
 	},
 	.num = NR_CLKS,
@@ -1341,6 +2125,42 @@ static struct clk_regmap *const axg_clk_regmaps[] = {
 	&axg_hifi_pll_dco,
 	&axg_pcie_pll_dco,
 	&axg_pcie_pll_od,
+	&axg_vpu_0_div,
+	&axg_vpu_0_sel,
+	&axg_vpu_0,
+	&axg_vpu_1_div,
+	&axg_vpu_1_sel,
+	&axg_vpu_1,
+	&axg_vpu,
+	&axg_vapb_0_div,
+	&axg_vapb_0_sel,
+	&axg_vapb_0,
+	&axg_vapb_1_div,
+	&axg_vapb_1_sel,
+	&axg_vapb_1,
+	&axg_vapb_sel,
+	&axg_vapb,
+	&axg_vclk,
+	&axg_vclk2,
+	&axg_vclk_sel,
+	&axg_vclk2_sel,
+	&axg_vclk_input,
+	&axg_vclk2_input,
+	&axg_vclk_div,
+	&axg_vclk2_div,
+	&axg_vclk_div2_en,
+	&axg_vclk_div4_en,
+	&axg_vclk_div6_en,
+	&axg_vclk_div12_en,
+	&axg_vclk2_div2_en,
+	&axg_vclk2_div4_en,
+	&axg_vclk2_div6_en,
+	&axg_vclk2_div12_en,
+	&axg_cts_encl_sel,
+	&axg_cts_encl,
+	&axg_vdin_meas_sel,
+	&axg_vdin_meas_div,
+	&axg_vdin_meas,
 };
 
 static const struct meson_eeclkc_data axg_clkc_data = {
@@ -1354,6 +2174,7 @@ static const struct of_device_id clkc_match_table[] = {
 	{ .compatible = "amlogic,axg-clkc", .data = &axg_clkc_data },
 	{}
 };
+MODULE_DEVICE_TABLE(of, clkc_match_table);
 
 static struct platform_driver axg_driver = {
 	.probe		= meson_eeclkc_probe,
@@ -1363,4 +2184,5 @@ static struct platform_driver axg_driver = {
 	},
 };
 
-builtin_platform_driver(axg_driver);
+module_platform_driver(axg_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/meson/axg.h b/drivers/clk/meson/axg.h
index 0431dabac629..481b307ea3cb 100644
--- a/drivers/clk/meson/axg.h
+++ b/drivers/clk/meson/axg.h
@@ -139,8 +139,29 @@
 #define CLKID_HIFI_PLL_DCO			88
 #define CLKID_PCIE_PLL_DCO			89
 #define CLKID_PCIE_PLL_OD			90
+#define CLKID_VPU_0_DIV				91
+#define CLKID_VPU_1_DIV				94
+#define CLKID_VAPB_0_DIV			98
+#define CLKID_VAPB_1_DIV			101
+#define CLKID_VCLK_SEL				108
+#define CLKID_VCLK2_SEL				109
+#define CLKID_VCLK_INPUT			110
+#define CLKID_VCLK2_INPUT			111
+#define CLKID_VCLK_DIV				112
+#define CLKID_VCLK2_DIV				113
+#define CLKID_VCLK_DIV2_EN			114
+#define CLKID_VCLK_DIV4_EN			115
+#define CLKID_VCLK_DIV6_EN			116
+#define CLKID_VCLK_DIV12_EN			117
+#define CLKID_VCLK2_DIV2_EN			118
+#define CLKID_VCLK2_DIV4_EN			119
+#define CLKID_VCLK2_DIV6_EN			120
+#define CLKID_VCLK2_DIV12_EN			121
+#define CLKID_CTS_ENCL_SEL			132
+#define CLKID_VDIN_MEAS_SEL			134
+#define CLKID_VDIN_MEAS_DIV			135
 
-#define NR_CLKS					91
+#define NR_CLKS					137
 
 /* include the CLKIDs that have been made part of the DT binding */
 #include <dt-bindings/clock/axg-clkc.h>
diff --git a/drivers/clk/meson/g12a-aoclk.c b/drivers/clk/meson/g12a-aoclk.c
index 62499563e4f5..b52990e574d2 100644
--- a/drivers/clk/meson/g12a-aoclk.c
+++ b/drivers/clk/meson/g12a-aoclk.c
@@ -12,6 +12,7 @@
 #include <linux/platform_device.h>
 #include <linux/reset-controller.h>
 #include <linux/mfd/syscon.h>
+#include <linux/module.h>
 #include "meson-aoclk.h"
 #include "g12a-aoclk.h"
 
@@ -461,6 +462,7 @@ static const struct of_device_id g12a_aoclkc_match_table[] = {
 	},
 	{ }
 };
+MODULE_DEVICE_TABLE(of, g12a_aoclkc_match_table);
 
 static struct platform_driver g12a_aoclkc_driver = {
 	.probe		= meson_aoclkc_probe,
@@ -470,4 +472,5 @@ static struct platform_driver g12a_aoclkc_driver = {
 	},
 };
 
-builtin_platform_driver(g12a_aoclkc_driver);
+module_platform_driver(g12a_aoclkc_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c
index b814d44917a5..b080359b4645 100644
--- a/drivers/clk/meson/g12a.c
+++ b/drivers/clk/meson/g12a.c
@@ -15,6 +15,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/module.h>
 
 #include "clk-mpll.h"
 #include "clk-pll.h"
@@ -3657,6 +3658,68 @@ static struct clk_regmap g12a_hdmi_tx = {
 	},
 };
 
+/* MIPI DSI Host Clocks */
+
+static const struct clk_hw *g12a_mipi_dsi_pxclk_parent_hws[] = {
+	&g12a_vid_pll.hw,
+	&g12a_gp0_pll.hw,
+	&g12a_hifi_pll.hw,
+	&g12a_mpll1.hw,
+	&g12a_fclk_div2.hw,
+	&g12a_fclk_div2p5.hw,
+	&g12a_fclk_div3.hw,
+	&g12a_fclk_div7.hw,
+};
+
+static struct clk_regmap g12a_mipi_dsi_pxclk_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_MIPIDSI_PHY_CLK_CNTL,
+		.mask = 0x7,
+		.shift = 12,
+		.flags = CLK_MUX_ROUND_CLOSEST,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "mipi_dsi_pxclk_sel",
+		.ops = &clk_regmap_mux_ops,
+		.parent_hws = g12a_mipi_dsi_pxclk_parent_hws,
+		.num_parents = ARRAY_SIZE(g12a_mipi_dsi_pxclk_parent_hws),
+		.flags = CLK_SET_RATE_NO_REPARENT,
+	},
+};
+
+static struct clk_regmap g12a_mipi_dsi_pxclk_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_MIPIDSI_PHY_CLK_CNTL,
+		.shift = 0,
+		.width = 7,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "mipi_dsi_pxclk_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&g12a_mipi_dsi_pxclk_sel.hw
+		},
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap g12a_mipi_dsi_pxclk = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_MIPIDSI_PHY_CLK_CNTL,
+		.bit_idx = 8,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "mipi_dsi_pxclk",
+		.ops = &clk_regmap_gate_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&g12a_mipi_dsi_pxclk_div.hw
+		},
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
 /* HDMI Clocks */
 
 static const struct clk_parent_data g12a_hdmi_parent_data[] = {
@@ -4402,6 +4465,9 @@ static struct clk_hw_onecell_data g12a_hw_onecell_data = {
 		[CLKID_SPICC1_SCLK_SEL]		= &g12a_spicc1_sclk_sel.hw,
 		[CLKID_SPICC1_SCLK_DIV]		= &g12a_spicc1_sclk_div.hw,
 		[CLKID_SPICC1_SCLK]		= &g12a_spicc1_sclk.hw,
+		[CLKID_MIPI_DSI_PXCLK_SEL]	= &g12a_mipi_dsi_pxclk_sel.hw,
+		[CLKID_MIPI_DSI_PXCLK_DIV]	= &g12a_mipi_dsi_pxclk_div.hw,
+		[CLKID_MIPI_DSI_PXCLK]		= &g12a_mipi_dsi_pxclk.hw,
 		[NR_CLKS]			= NULL,
 	},
 	.num = NR_CLKS,
@@ -4657,6 +4723,9 @@ static struct clk_hw_onecell_data g12b_hw_onecell_data = {
 		[CLKID_SPICC1_SCLK_SEL]		= &g12a_spicc1_sclk_sel.hw,
 		[CLKID_SPICC1_SCLK_DIV]		= &g12a_spicc1_sclk_div.hw,
 		[CLKID_SPICC1_SCLK]		= &g12a_spicc1_sclk.hw,
+		[CLKID_MIPI_DSI_PXCLK_SEL]	= &g12a_mipi_dsi_pxclk_sel.hw,
+		[CLKID_MIPI_DSI_PXCLK_DIV]	= &g12a_mipi_dsi_pxclk_div.hw,
+		[CLKID_MIPI_DSI_PXCLK]		= &g12a_mipi_dsi_pxclk.hw,
 		[NR_CLKS]			= NULL,
 	},
 	.num = NR_CLKS,
@@ -4903,6 +4972,9 @@ static struct clk_hw_onecell_data sm1_hw_onecell_data = {
 		[CLKID_NNA_CORE_CLK_SEL]	= &sm1_nna_core_clk_sel.hw,
 		[CLKID_NNA_CORE_CLK_DIV]	= &sm1_nna_core_clk_div.hw,
 		[CLKID_NNA_CORE_CLK]		= &sm1_nna_core_clk.hw,
+		[CLKID_MIPI_DSI_PXCLK_SEL]	= &g12a_mipi_dsi_pxclk_sel.hw,
+		[CLKID_MIPI_DSI_PXCLK_DIV]	= &g12a_mipi_dsi_pxclk_div.hw,
+		[CLKID_MIPI_DSI_PXCLK]		= &g12a_mipi_dsi_pxclk.hw,
 		[NR_CLKS]			= NULL,
 	},
 	.num = NR_CLKS,
@@ -5150,16 +5222,20 @@ static struct clk_regmap *const g12a_clk_regmaps[] = {
 	&sm1_nna_core_clk_sel,
 	&sm1_nna_core_clk_div,
 	&sm1_nna_core_clk,
+	&g12a_mipi_dsi_pxclk_sel,
+	&g12a_mipi_dsi_pxclk_div,
+	&g12a_mipi_dsi_pxclk,
 };
 
 static const struct reg_sequence g12a_init_regs[] = {
 	{ .reg = HHI_MPLL_CNTL0,	.def = 0x00000543 },
 };
 
-static int meson_g12a_dvfs_setup_common(struct platform_device *pdev,
+#define DVFS_CON_ID "dvfs"
+
+static int meson_g12a_dvfs_setup_common(struct device *dev,
 					struct clk_hw **hws)
 {
-	const char *notifier_clk_name;
 	struct clk *notifier_clk;
 	struct clk_hw *xtal;
 	int ret;
@@ -5168,21 +5244,22 @@ static int meson_g12a_dvfs_setup_common(struct platform_device *pdev,
 
 	/* Setup clock notifier for cpu_clk_postmux0 */
 	g12a_cpu_clk_postmux0_nb_data.xtal = xtal;
-	notifier_clk_name = clk_hw_get_name(&g12a_cpu_clk_postmux0.hw);
-	notifier_clk = __clk_lookup(notifier_clk_name);
-	ret = clk_notifier_register(notifier_clk,
-				    &g12a_cpu_clk_postmux0_nb_data.nb);
+	notifier_clk = devm_clk_hw_get_clk(dev, &g12a_cpu_clk_postmux0.hw,
+					   DVFS_CON_ID);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_cpu_clk_postmux0_nb_data.nb);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register the cpu_clk_postmux0 notifier\n");
+		dev_err(dev, "failed to register the cpu_clk_postmux0 notifier\n");
 		return ret;
 	}
 
 	/* Setup clock notifier for cpu_clk_dyn mux */
-	notifier_clk_name = clk_hw_get_name(&g12a_cpu_clk_dyn.hw);
-	notifier_clk = __clk_lookup(notifier_clk_name);
-	ret = clk_notifier_register(notifier_clk, &g12a_cpu_clk_mux_nb);
+	notifier_clk = devm_clk_hw_get_clk(dev, &g12a_cpu_clk_dyn.hw,
+					   DVFS_CON_ID);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_cpu_clk_mux_nb);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register the cpu_clk_dyn notifier\n");
+		dev_err(dev, "failed to register the cpu_clk_dyn notifier\n");
 		return ret;
 	}
 
@@ -5192,33 +5269,34 @@ static int meson_g12a_dvfs_setup_common(struct platform_device *pdev,
 static int meson_g12b_dvfs_setup(struct platform_device *pdev)
 {
 	struct clk_hw **hws = g12b_hw_onecell_data.hws;
-	const char *notifier_clk_name;
+	struct device *dev = &pdev->dev;
 	struct clk *notifier_clk;
 	struct clk_hw *xtal;
 	int ret;
 
-	ret = meson_g12a_dvfs_setup_common(pdev, hws);
+	ret = meson_g12a_dvfs_setup_common(dev, hws);
 	if (ret)
 		return ret;
 
 	xtal = clk_hw_get_parent_by_index(hws[CLKID_CPU_CLK_DYN1_SEL], 0);
 
 	/* Setup clock notifier for cpu_clk mux */
-	notifier_clk_name = clk_hw_get_name(&g12b_cpu_clk.hw);
-	notifier_clk = __clk_lookup(notifier_clk_name);
-	ret = clk_notifier_register(notifier_clk, &g12a_cpu_clk_mux_nb);
+	notifier_clk = devm_clk_hw_get_clk(dev, &g12b_cpu_clk.hw,
+					   DVFS_CON_ID);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_cpu_clk_mux_nb);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register the cpu_clk notifier\n");
+		dev_err(dev, "failed to register the cpu_clk notifier\n");
 		return ret;
 	}
 
 	/* Setup clock notifier for sys1_pll */
-	notifier_clk_name = clk_hw_get_name(&g12b_sys1_pll.hw);
-	notifier_clk = __clk_lookup(notifier_clk_name);
-	ret = clk_notifier_register(notifier_clk,
-				    &g12b_cpu_clk_sys1_pll_nb_data.nb);
+	notifier_clk = devm_clk_hw_get_clk(dev, &g12b_sys1_pll.hw,
+					   DVFS_CON_ID);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12b_cpu_clk_sys1_pll_nb_data.nb);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register the sys1_pll notifier\n");
+		dev_err(dev, "failed to register the sys1_pll notifier\n");
 		return ret;
 	}
 
@@ -5226,40 +5304,39 @@ static int meson_g12b_dvfs_setup(struct platform_device *pdev)
 
 	/* Setup clock notifier for cpub_clk_postmux0 */
 	g12b_cpub_clk_postmux0_nb_data.xtal = xtal;
-	notifier_clk_name = clk_hw_get_name(&g12b_cpub_clk_postmux0.hw);
-	notifier_clk = __clk_lookup(notifier_clk_name);
-	ret = clk_notifier_register(notifier_clk,
-				    &g12b_cpub_clk_postmux0_nb_data.nb);
+	notifier_clk = devm_clk_hw_get_clk(dev, &g12b_cpub_clk_postmux0.hw,
+					   DVFS_CON_ID);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12b_cpub_clk_postmux0_nb_data.nb);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register the cpub_clk_postmux0 notifier\n");
+		dev_err(dev, "failed to register the cpub_clk_postmux0 notifier\n");
 		return ret;
 	}
 
 	/* Setup clock notifier for cpub_clk_dyn mux */
-	notifier_clk_name = clk_hw_get_name(&g12b_cpub_clk_dyn.hw);
-	notifier_clk = __clk_lookup(notifier_clk_name);
-	ret = clk_notifier_register(notifier_clk, &g12a_cpu_clk_mux_nb);
+	notifier_clk = devm_clk_hw_get_clk(dev, &g12b_cpub_clk_dyn.hw, "dvfs");
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_cpu_clk_mux_nb);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register the cpub_clk_dyn notifier\n");
+		dev_err(dev, "failed to register the cpub_clk_dyn notifier\n");
 		return ret;
 	}
 
 	/* Setup clock notifier for cpub_clk mux */
-	notifier_clk_name = clk_hw_get_name(&g12b_cpub_clk.hw);
-	notifier_clk = __clk_lookup(notifier_clk_name);
-	ret = clk_notifier_register(notifier_clk, &g12a_cpu_clk_mux_nb);
+	notifier_clk = devm_clk_hw_get_clk(dev, &g12b_cpub_clk.hw, DVFS_CON_ID);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_cpu_clk_mux_nb);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register the cpub_clk notifier\n");
+		dev_err(dev, "failed to register the cpub_clk notifier\n");
 		return ret;
 	}
 
 	/* Setup clock notifier for sys_pll */
-	notifier_clk_name = clk_hw_get_name(&g12a_sys_pll.hw);
-	notifier_clk = __clk_lookup(notifier_clk_name);
-	ret = clk_notifier_register(notifier_clk,
-				    &g12b_cpub_clk_sys_pll_nb_data.nb);
+	notifier_clk = devm_clk_hw_get_clk(dev, &g12a_sys_pll.hw, DVFS_CON_ID);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12b_cpub_clk_sys_pll_nb_data.nb);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register the sys_pll notifier\n");
+		dev_err(dev, "failed to register the sys_pll notifier\n");
 		return ret;
 	}
 
@@ -5269,29 +5346,29 @@ static int meson_g12b_dvfs_setup(struct platform_device *pdev)
 static int meson_g12a_dvfs_setup(struct platform_device *pdev)
 {
 	struct clk_hw **hws = g12a_hw_onecell_data.hws;
-	const char *notifier_clk_name;
+	struct device *dev = &pdev->dev;
 	struct clk *notifier_clk;
 	int ret;
 
-	ret = meson_g12a_dvfs_setup_common(pdev, hws);
+	ret = meson_g12a_dvfs_setup_common(dev, hws);
 	if (ret)
 		return ret;
 
 	/* Setup clock notifier for cpu_clk mux */
-	notifier_clk_name = clk_hw_get_name(&g12a_cpu_clk.hw);
-	notifier_clk = __clk_lookup(notifier_clk_name);
-	ret = clk_notifier_register(notifier_clk, &g12a_cpu_clk_mux_nb);
+	notifier_clk = devm_clk_hw_get_clk(dev, &g12a_cpu_clk.hw, DVFS_CON_ID);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+				    &g12a_cpu_clk_mux_nb);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register the cpu_clk notifier\n");
+		dev_err(dev, "failed to register the cpu_clk notifier\n");
 		return ret;
 	}
 
 	/* Setup clock notifier for sys_pll */
-	notifier_clk_name = clk_hw_get_name(&g12a_sys_pll.hw);
-	notifier_clk = __clk_lookup(notifier_clk_name);
-	ret = clk_notifier_register(notifier_clk, &g12a_sys_pll_nb_data.nb);
+	notifier_clk = devm_clk_hw_get_clk(dev, &g12a_sys_pll.hw, DVFS_CON_ID);
+	ret = devm_clk_notifier_register(dev, notifier_clk,
+					 &g12a_sys_pll_nb_data.nb);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to register the sys_pll notifier\n");
+		dev_err(dev, "failed to register the sys_pll notifier\n");
 		return ret;
 	}
 
@@ -5370,6 +5447,7 @@ static const struct of_device_id clkc_match_table[] = {
 	},
 	{}
 };
+MODULE_DEVICE_TABLE(of, clkc_match_table);
 
 static struct platform_driver g12a_driver = {
 	.probe		= meson_g12a_probe,
@@ -5379,4 +5457,5 @@ static struct platform_driver g12a_driver = {
 	},
 };
 
-builtin_platform_driver(g12a_driver);
+module_platform_driver(g12a_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/meson/g12a.h b/drivers/clk/meson/g12a.h
index 69b6a69549c7..a97613df38b3 100644
--- a/drivers/clk/meson/g12a.h
+++ b/drivers/clk/meson/g12a.h
@@ -264,8 +264,9 @@
 #define CLKID_NNA_AXI_CLK_DIV			263
 #define CLKID_NNA_CORE_CLK_SEL			265
 #define CLKID_NNA_CORE_CLK_DIV			266
+#define CLKID_MIPI_DSI_PXCLK_DIV		268
 
-#define NR_CLKS					268
+#define NR_CLKS					271
 
 /* include the CLKIDs that have been made part of the DT binding */
 #include <dt-bindings/clock/g12a-clkc.h>
diff --git a/drivers/clk/meson/gxbb-aoclk.c b/drivers/clk/meson/gxbb-aoclk.c
index e940861a396b..fce95cf89836 100644
--- a/drivers/clk/meson/gxbb-aoclk.c
+++ b/drivers/clk/meson/gxbb-aoclk.c
@@ -5,6 +5,7 @@
  */
 #include <linux/platform_device.h>
 #include <linux/mfd/syscon.h>
+#include <linux/module.h>
 #include "meson-aoclk.h"
 #include "gxbb-aoclk.h"
 
@@ -287,6 +288,7 @@ static const struct of_device_id gxbb_aoclkc_match_table[] = {
 	},
 	{ }
 };
+MODULE_DEVICE_TABLE(of, gxbb_aoclkc_match_table);
 
 static struct platform_driver gxbb_aoclkc_driver = {
 	.probe		= meson_aoclkc_probe,
@@ -295,4 +297,5 @@ static struct platform_driver gxbb_aoclkc_driver = {
 		.of_match_table = gxbb_aoclkc_match_table,
 	},
 };
-builtin_platform_driver(gxbb_aoclkc_driver);
+module_platform_driver(gxbb_aoclkc_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 0a68af6eec3d..d6eed760327d 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/module.h>
 
 #include "gxbb.h"
 #include "clk-regmap.h"
@@ -3519,6 +3520,7 @@ static const struct of_device_id clkc_match_table[] = {
 	{ .compatible = "amlogic,gxl-clkc", .data = &gxl_clkc_data },
 	{},
 };
+MODULE_DEVICE_TABLE(of, clkc_match_table);
 
 static struct platform_driver gxbb_driver = {
 	.probe		= meson_eeclkc_probe,
@@ -3528,4 +3530,5 @@ static struct platform_driver gxbb_driver = {
 	},
 };
 
-builtin_platform_driver(gxbb_driver);
+module_platform_driver(gxbb_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/meson/meson-aoclk.c b/drivers/clk/meson/meson-aoclk.c
index 3a6d84cd6601..27cd2c1f3f61 100644
--- a/drivers/clk/meson/meson-aoclk.c
+++ b/drivers/clk/meson/meson-aoclk.c
@@ -14,6 +14,8 @@
 #include <linux/reset-controller.h>
 #include <linux/mfd/syscon.h>
 #include <linux/of_device.h>
+#include <linux/module.h>
+
 #include <linux/slab.h>
 #include "meson-aoclk.h"
 
@@ -84,3 +86,5 @@ int meson_aoclkc_probe(struct platform_device *pdev)
 	return devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get,
 		(void *) data->hw_data);
 }
+EXPORT_SYMBOL_GPL(meson_aoclkc_probe);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/meson/meson-eeclk.c b/drivers/clk/meson/meson-eeclk.c
index a7cb1e7aedc4..8d5a5dab955a 100644
--- a/drivers/clk/meson/meson-eeclk.c
+++ b/drivers/clk/meson/meson-eeclk.c
@@ -9,6 +9,7 @@
 #include <linux/platform_device.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
+#include <linux/module.h>
 
 #include "clk-regmap.h"
 #include "meson-eeclk.h"
@@ -54,3 +55,5 @@ int meson_eeclkc_probe(struct platform_device *pdev)
 	return devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get,
 					   data->hw_onecell_data);
 }
+EXPORT_SYMBOL_GPL(meson_eeclkc_probe);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/mvebu/armada-37xx-xtal.c b/drivers/clk/mvebu/armada-37xx-xtal.c
index e9e306d4e9af..41271351cf1f 100644
--- a/drivers/clk/mvebu/armada-37xx-xtal.c
+++ b/drivers/clk/mvebu/armada-37xx-xtal.c
@@ -13,8 +13,8 @@
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 
-#define NB_GPIO1_LATCH	0xC
-#define XTAL_MODE	    BIT(31)
+#define NB_GPIO1_LATCH	0x8
+#define XTAL_MODE	    BIT(9)
 
 static int armada_3700_xtal_clock_probe(struct platform_device *pdev)
 {
diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index 3a965bd326d5..d32bb12cd8d0 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -44,7 +44,7 @@ config QCOM_CLK_APCC_MSM8996
 	help
 	  Support for the CPU clock controller on msm8996 devices.
 	  Say Y if you want to support CPU clock scaling using CPUfreq
-	  drivers for dyanmic power management.
+	  drivers for dynamic power management.
 
 config QCOM_CLK_RPM
 	tristate "RPM based Clock Controller"
@@ -290,6 +290,15 @@ config QCS_GCC_404
 	  Say Y if you want to use multimedia devices or peripheral
 	  devices such as UART, SPI, I2C, USB, SD/eMMC, PCIe etc.
 
+config SC_CAMCC_7180
+	tristate "SC7180 Camera Clock Controller"
+	select SC_GCC_7180
+	help
+	  Support for the camera clock controller on Qualcomm Technologies, Inc
+	  SC7180 devices.
+	  Say Y if you want to support camera devices and functionality such as
+	  capturing pictures.
+
 config SC_DISPCC_7180
 	tristate "SC7180 Display Clock Controller"
 	select SC_GCC_7180
@@ -413,6 +422,14 @@ config SDM_LPASSCC_845
 	  Say Y if you want to use the LPASS branch clocks of the LPASS clock
 	  controller to reset the LPASS subsystem.
 
+config SDX_GCC_55
+	tristate "SDX55 Global Clock Controller"
+	select QCOM_GDSC
+	help
+	  Support for the global clock controller on SDX55 devices.
+	  Say Y if you want to use peripheral devices such as UART,
+	  SPI, I2C, USB, SD/UFS, PCIe etc.
+
 config SM_DISPCC_8250
 	tristate "SM8150 and SM8250 Display Clock Controller"
 	depends on SM_GCC_8150 || SM_GCC_8250
@@ -502,4 +519,10 @@ config KRAITCC
 	  Support for the Krait CPU clocks on Qualcomm devices.
 	  Say Y if you want to support CPU frequency scaling.
 
+config CLK_GFM_LPASS_SM8250
+	tristate "SM8250 GFM LPASS Clocks"
+	help
+	  Support for the Glitch Free Mux (GFM) Low power audio
+          subsystem (LPASS) clocks found on SM8250 SoCs.
+
 endif
diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile
index 11ae86febe87..9e5e0e3cb7b4 100644
--- a/drivers/clk/qcom/Makefile
+++ b/drivers/clk/qcom/Makefile
@@ -19,6 +19,7 @@ clk-qcom-$(CONFIG_QCOM_GDSC) += gdsc.o
 # Keep alphabetically sorted by config
 obj-$(CONFIG_APQ_GCC_8084) += gcc-apq8084.o
 obj-$(CONFIG_APQ_MMCC_8084) += mmcc-apq8084.o
+obj-$(CONFIG_CLK_GFM_LPASS_SM8250) += lpass-gfm-sm8250.o
 obj-$(CONFIG_IPQ_APSS_PLL) += apss-ipq-pll.o
 obj-$(CONFIG_IPQ_APSS_6018) += apss-ipq6018.o
 obj-$(CONFIG_IPQ_GCC_4019) += gcc-ipq4019.o
@@ -51,6 +52,7 @@ obj-$(CONFIG_QCOM_CLK_SMD_RPM) += clk-smd-rpm.o
 obj-$(CONFIG_QCS_GCC_404) += gcc-qcs404.o
 obj-$(CONFIG_QCS_Q6SSTOP_404) += q6sstop-qcs404.o
 obj-$(CONFIG_QCS_TURING_404) += turingcc-qcs404.o
+obj-$(CONFIG_SC_CAMCC_7180) += camcc-sc7180.o
 obj-$(CONFIG_SC_DISPCC_7180) += dispcc-sc7180.o
 obj-$(CONFIG_SC_GCC_7180) += gcc-sc7180.o
 obj-$(CONFIG_SC_GPUCC_7180) += gpucc-sc7180.o
@@ -64,6 +66,7 @@ obj-$(CONFIG_SDM_GCC_845) += gcc-sdm845.o
 obj-$(CONFIG_SDM_GPUCC_845) += gpucc-sdm845.o
 obj-$(CONFIG_SDM_LPASSCC_845) += lpasscc-sdm845.o
 obj-$(CONFIG_SDM_VIDEOCC_845) += videocc-sdm845.o
+obj-$(CONFIG_SDX_GCC_55) += gcc-sdx55.o
 obj-$(CONFIG_SM_DISPCC_8250) += dispcc-sm8250.o
 obj-$(CONFIG_SM_GCC_8150) += gcc-sm8150.o
 obj-$(CONFIG_SM_GCC_8250) += gcc-sm8250.o
diff --git a/drivers/clk/qcom/camcc-sc7180.c b/drivers/clk/qcom/camcc-sc7180.c
new file mode 100644
index 000000000000..dbac5651ab85
--- /dev/null
+++ b/drivers/clk/qcom/camcc-sc7180.c
@@ -0,0 +1,1732 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pm_clock.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+
+#include <dt-bindings/clock/qcom,camcc-sc7180.h>
+
+#include "clk-alpha-pll.h"
+#include "clk-branch.h"
+#include "clk-rcg.h"
+#include "clk-regmap.h"
+#include "common.h"
+#include "gdsc.h"
+#include "reset.h"
+
+enum {
+	P_BI_TCXO,
+	P_CAM_CC_PLL0_OUT_EVEN,
+	P_CAM_CC_PLL1_OUT_EVEN,
+	P_CAM_CC_PLL2_OUT_AUX,
+	P_CAM_CC_PLL2_OUT_EARLY,
+	P_CAM_CC_PLL3_OUT_MAIN,
+	P_CORE_BI_PLL_TEST_SE,
+};
+
+static const struct pll_vco agera_vco[] = {
+	{ 600000000, 3300000000UL, 0 },
+};
+
+static const struct pll_vco fabia_vco[] = {
+	{ 249600000, 2000000000UL, 0 },
+};
+
+/* 600MHz configuration */
+static const struct alpha_pll_config cam_cc_pll0_config = {
+	.l = 0x1f,
+	.alpha = 0x4000,
+	.config_ctl_val = 0x20485699,
+	.config_ctl_hi_val = 0x00002067,
+	.test_ctl_val = 0x40000000,
+	.user_ctl_hi_val = 0x00004805,
+	.user_ctl_val = 0x00000001,
+};
+
+static struct clk_alpha_pll cam_cc_pll0 = {
+	.offset = 0x0,
+	.vco_table = fabia_vco,
+	.num_vco = ARRAY_SIZE(fabia_vco),
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_pll0",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fabia_ops,
+		},
+	},
+};
+
+/* 860MHz configuration */
+static const struct alpha_pll_config cam_cc_pll1_config = {
+	.l = 0x2a,
+	.alpha = 0x1555,
+	.config_ctl_val = 0x20485699,
+	.config_ctl_hi_val = 0x00002067,
+	.test_ctl_val = 0x40000000,
+	.user_ctl_hi_val = 0x00004805,
+};
+
+static struct clk_alpha_pll cam_cc_pll1 = {
+	.offset = 0x1000,
+	.vco_table = fabia_vco,
+	.num_vco = ARRAY_SIZE(fabia_vco),
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_pll1",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fabia_ops,
+		},
+	},
+};
+
+/* 1920MHz configuration */
+static const struct alpha_pll_config cam_cc_pll2_config = {
+	.l = 0x64,
+	.config_ctl_val = 0x20000800,
+	.config_ctl_hi_val = 0x400003D2,
+	.test_ctl_val = 0x04000400,
+	.test_ctl_hi_val = 0x00004000,
+	.user_ctl_val = 0x0000030F,
+};
+
+static struct clk_alpha_pll cam_cc_pll2 = {
+	.offset = 0x2000,
+	.vco_table = agera_vco,
+	.num_vco = ARRAY_SIZE(agera_vco),
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_AGERA],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_pll2",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_agera_ops,
+		},
+	},
+};
+
+static struct clk_fixed_factor cam_cc_pll2_out_early = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_pll2_out_early",
+		.parent_names = (const char *[]){ "cam_cc_pll2" },
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+	},
+};
+
+static const struct clk_div_table post_div_table_cam_cc_pll2_out_aux[] = {
+	{ 0x3, 4 },
+	{ }
+};
+
+static struct clk_alpha_pll_postdiv cam_cc_pll2_out_aux = {
+	.offset = 0x2000,
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_cam_cc_pll2_out_aux,
+	.num_post_div = ARRAY_SIZE(post_div_table_cam_cc_pll2_out_aux),
+	.width = 2,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_AGERA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_pll2_out_aux",
+		.parent_data = &(const struct clk_parent_data){
+			.hw = &cam_cc_pll2.clkr.hw,
+		},
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_alpha_pll_postdiv_ops,
+	},
+};
+
+/* 1080MHz configuration */
+static const struct alpha_pll_config cam_cc_pll3_config = {
+	.l = 0x38,
+	.alpha = 0x4000,
+	.config_ctl_val = 0x20485699,
+	.config_ctl_hi_val = 0x00002067,
+	.test_ctl_val = 0x40000000,
+	.user_ctl_hi_val = 0x00004805,
+};
+
+static struct clk_alpha_pll cam_cc_pll3 = {
+	.offset = 0x3000,
+	.vco_table = fabia_vco,
+	.num_vco = ARRAY_SIZE(fabia_vco),
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_pll3",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fabia_ops,
+		},
+	},
+};
+
+static const struct parent_map cam_cc_parent_map_0[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_CAM_CC_PLL1_OUT_EVEN, 2 },
+	{ P_CAM_CC_PLL0_OUT_EVEN, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data cam_cc_parent_data_0[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &cam_cc_pll1.clkr.hw },
+	{ .hw = &cam_cc_pll0.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map cam_cc_parent_map_1[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_CAM_CC_PLL2_OUT_AUX, 1 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data cam_cc_parent_data_1[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &cam_cc_pll2_out_aux.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map cam_cc_parent_map_2[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_CAM_CC_PLL2_OUT_EARLY, 4 },
+	{ P_CAM_CC_PLL3_OUT_MAIN, 5 },
+	{ P_CAM_CC_PLL0_OUT_EVEN, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data cam_cc_parent_data_2[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &cam_cc_pll2_out_early.hw },
+	{ .hw = &cam_cc_pll3.clkr.hw },
+	{ .hw = &cam_cc_pll0.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map cam_cc_parent_map_3[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_CAM_CC_PLL1_OUT_EVEN, 2 },
+	{ P_CAM_CC_PLL2_OUT_EARLY, 4 },
+	{ P_CAM_CC_PLL3_OUT_MAIN, 5 },
+	{ P_CAM_CC_PLL0_OUT_EVEN, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data cam_cc_parent_data_3[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &cam_cc_pll1.clkr.hw },
+	{ .hw = &cam_cc_pll2_out_early.hw },
+	{ .hw = &cam_cc_pll3.clkr.hw },
+	{ .hw = &cam_cc_pll0.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map cam_cc_parent_map_4[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_CAM_CC_PLL3_OUT_MAIN, 5 },
+	{ P_CAM_CC_PLL0_OUT_EVEN, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data cam_cc_parent_data_4[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &cam_cc_pll3.clkr.hw },
+	{ .hw = &cam_cc_pll0.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map cam_cc_parent_map_5[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_CAM_CC_PLL0_OUT_EVEN, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data cam_cc_parent_data_5[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &cam_cc_pll0.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map cam_cc_parent_map_6[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_CAM_CC_PLL1_OUT_EVEN, 2 },
+	{ P_CAM_CC_PLL3_OUT_MAIN, 5 },
+	{ P_CAM_CC_PLL0_OUT_EVEN, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data cam_cc_parent_data_6[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &cam_cc_pll1.clkr.hw },
+	{ .hw = &cam_cc_pll3.clkr.hw },
+	{ .hw = &cam_cc_pll0.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct freq_tbl ftbl_cam_cc_bps_clk_src[] = {
+	F(200000000, P_CAM_CC_PLL0_OUT_EVEN, 3, 0, 0),
+	F(360000000, P_CAM_CC_PLL3_OUT_MAIN, 3, 0, 0),
+	F(432000000, P_CAM_CC_PLL3_OUT_MAIN, 2.5, 0, 0),
+	F(480000000, P_CAM_CC_PLL2_OUT_EARLY, 2, 0, 0),
+	F(600000000, P_CAM_CC_PLL0_OUT_EVEN, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_bps_clk_src = {
+	.cmd_rcgr = 0x6010,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_2,
+	.freq_tbl = ftbl_cam_cc_bps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_bps_clk_src",
+		.parent_data = cam_cc_parent_data_2,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_cci_0_clk_src[] = {
+	F(37500000, P_CAM_CC_PLL0_OUT_EVEN, 16, 0, 0),
+	F(50000000, P_CAM_CC_PLL0_OUT_EVEN, 12, 0, 0),
+	F(100000000, P_CAM_CC_PLL0_OUT_EVEN, 6, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_cci_0_clk_src = {
+	.cmd_rcgr = 0xb0d8,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_5,
+	.freq_tbl = ftbl_cam_cc_cci_0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_cci_0_clk_src",
+		.parent_data = cam_cc_parent_data_5,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_cci_1_clk_src = {
+	.cmd_rcgr = 0xb14c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_5,
+	.freq_tbl = ftbl_cam_cc_cci_0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_cci_1_clk_src",
+		.parent_data = cam_cc_parent_data_5,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_cphy_rx_clk_src[] = {
+	F(150000000, P_CAM_CC_PLL0_OUT_EVEN, 4, 0, 0),
+	F(270000000, P_CAM_CC_PLL3_OUT_MAIN, 4, 0, 0),
+	F(360000000, P_CAM_CC_PLL3_OUT_MAIN, 3, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_cphy_rx_clk_src = {
+	.cmd_rcgr = 0x9064,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_3,
+	.freq_tbl = ftbl_cam_cc_cphy_rx_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_cphy_rx_clk_src",
+		.parent_data = cam_cc_parent_data_3,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_csi0phytimer_clk_src[] = {
+	F(300000000, P_CAM_CC_PLL0_OUT_EVEN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_csi0phytimer_clk_src = {
+	.cmd_rcgr = 0x5004,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_0,
+	.freq_tbl = ftbl_cam_cc_csi0phytimer_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_csi0phytimer_clk_src",
+		.parent_data = cam_cc_parent_data_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_csi1phytimer_clk_src = {
+	.cmd_rcgr = 0x5028,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_0,
+	.freq_tbl = ftbl_cam_cc_csi0phytimer_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_csi1phytimer_clk_src",
+		.parent_data = cam_cc_parent_data_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_csi2phytimer_clk_src = {
+	.cmd_rcgr = 0x504c,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_0,
+	.freq_tbl = ftbl_cam_cc_csi0phytimer_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_csi2phytimer_clk_src",
+		.parent_data = cam_cc_parent_data_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_csi3phytimer_clk_src = {
+	.cmd_rcgr = 0x5070,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_0,
+	.freq_tbl = ftbl_cam_cc_csi0phytimer_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_csi3phytimer_clk_src",
+		.parent_data = cam_cc_parent_data_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_fast_ahb_clk_src[] = {
+	F(100000000, P_CAM_CC_PLL0_OUT_EVEN, 6, 0, 0),
+	F(200000000, P_CAM_CC_PLL0_OUT_EVEN, 3, 0, 0),
+	F(300000000, P_CAM_CC_PLL0_OUT_EVEN, 2, 0, 0),
+	F(404000000, P_CAM_CC_PLL1_OUT_EVEN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_fast_ahb_clk_src = {
+	.cmd_rcgr = 0x603c,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_0,
+	.freq_tbl = ftbl_cam_cc_fast_ahb_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_fast_ahb_clk_src",
+		.parent_data = cam_cc_parent_data_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_icp_clk_src[] = {
+	F(240000000, P_CAM_CC_PLL0_OUT_EVEN, 2.5, 0, 0),
+	F(360000000, P_CAM_CC_PLL3_OUT_MAIN, 3, 0, 0),
+	F(432000000, P_CAM_CC_PLL3_OUT_MAIN, 2.5, 0, 0),
+	F(480000000, P_CAM_CC_PLL2_OUT_EARLY, 2, 0, 0),
+	F(600000000, P_CAM_CC_PLL0_OUT_EVEN, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_icp_clk_src = {
+	.cmd_rcgr = 0xb088,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_2,
+	.freq_tbl = ftbl_cam_cc_icp_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_icp_clk_src",
+		.parent_data = cam_cc_parent_data_2,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_ife_0_clk_src[] = {
+	F(240000000, P_CAM_CC_PLL0_OUT_EVEN, 2.5, 0, 0),
+	F(360000000, P_CAM_CC_PLL3_OUT_MAIN, 3, 0, 0),
+	F(432000000, P_CAM_CC_PLL3_OUT_MAIN, 2.5, 0, 0),
+	F(600000000, P_CAM_CC_PLL0_OUT_EVEN, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_ife_0_clk_src = {
+	.cmd_rcgr = 0x9010,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_4,
+	.freq_tbl = ftbl_cam_cc_ife_0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_ife_0_clk_src",
+		.parent_data = cam_cc_parent_data_4,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_ife_0_csid_clk_src[] = {
+	F(150000000, P_CAM_CC_PLL0_OUT_EVEN, 4, 0, 0),
+	F(270000000, P_CAM_CC_PLL3_OUT_MAIN, 4, 0, 0),
+	F(360000000, P_CAM_CC_PLL3_OUT_MAIN, 3, 0, 0),
+	F(480000000, P_CAM_CC_PLL2_OUT_EARLY, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_ife_0_csid_clk_src = {
+	.cmd_rcgr = 0x903c,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_3,
+	.freq_tbl = ftbl_cam_cc_ife_0_csid_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_ife_0_csid_clk_src",
+		.parent_data = cam_cc_parent_data_3,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_ife_1_clk_src = {
+	.cmd_rcgr = 0xa010,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_4,
+	.freq_tbl = ftbl_cam_cc_ife_0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_ife_1_clk_src",
+		.parent_data = cam_cc_parent_data_4,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_ife_1_csid_clk_src = {
+	.cmd_rcgr = 0xa034,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_3,
+	.freq_tbl = ftbl_cam_cc_ife_0_csid_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_ife_1_csid_clk_src",
+		.parent_data = cam_cc_parent_data_3,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_ife_lite_clk_src = {
+	.cmd_rcgr = 0xb004,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_4,
+	.freq_tbl = ftbl_cam_cc_ife_0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_ife_lite_clk_src",
+		.parent_data = cam_cc_parent_data_4,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_ife_lite_csid_clk_src = {
+	.cmd_rcgr = 0xb024,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_3,
+	.freq_tbl = ftbl_cam_cc_ife_0_csid_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_ife_lite_csid_clk_src",
+		.parent_data = cam_cc_parent_data_3,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_ipe_0_clk_src[] = {
+	F(240000000, P_CAM_CC_PLL0_OUT_EVEN, 2.5, 0, 0),
+	F(360000000, P_CAM_CC_PLL3_OUT_MAIN, 3, 0, 0),
+	F(432000000, P_CAM_CC_PLL3_OUT_MAIN, 2.5, 0, 0),
+	F(540000000, P_CAM_CC_PLL3_OUT_MAIN, 2, 0, 0),
+	F(600000000, P_CAM_CC_PLL0_OUT_EVEN, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_ipe_0_clk_src = {
+	.cmd_rcgr = 0x7010,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_2,
+	.freq_tbl = ftbl_cam_cc_ipe_0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_ipe_0_clk_src",
+		.parent_data = cam_cc_parent_data_2,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_jpeg_clk_src[] = {
+	F(66666667, P_CAM_CC_PLL0_OUT_EVEN, 9, 0, 0),
+	F(133333333, P_CAM_CC_PLL0_OUT_EVEN, 4.5, 0, 0),
+	F(216000000, P_CAM_CC_PLL3_OUT_MAIN, 5, 0, 0),
+	F(320000000, P_CAM_CC_PLL2_OUT_EARLY, 3, 0, 0),
+	F(600000000, P_CAM_CC_PLL0_OUT_EVEN, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_jpeg_clk_src = {
+	.cmd_rcgr = 0xb04c,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_2,
+	.freq_tbl = ftbl_cam_cc_jpeg_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_jpeg_clk_src",
+		.parent_data = cam_cc_parent_data_2,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_lrme_clk_src[] = {
+	F(200000000, P_CAM_CC_PLL0_OUT_EVEN, 3, 0, 0),
+	F(216000000, P_CAM_CC_PLL3_OUT_MAIN, 5, 0, 0),
+	F(300000000, P_CAM_CC_PLL0_OUT_EVEN, 2, 0, 0),
+	F(404000000, P_CAM_CC_PLL1_OUT_EVEN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_lrme_clk_src = {
+	.cmd_rcgr = 0xb0f8,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_6,
+	.freq_tbl = ftbl_cam_cc_lrme_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_lrme_clk_src",
+		.parent_data = cam_cc_parent_data_6,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_mclk0_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(24000000, P_CAM_CC_PLL2_OUT_AUX, 10, 1, 2),
+	F(64000000, P_CAM_CC_PLL2_OUT_AUX, 7.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_mclk0_clk_src = {
+	.cmd_rcgr = 0x4004,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_1,
+	.freq_tbl = ftbl_cam_cc_mclk0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_mclk0_clk_src",
+		.parent_data = cam_cc_parent_data_1,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_mclk1_clk_src = {
+	.cmd_rcgr = 0x4024,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_1,
+	.freq_tbl = ftbl_cam_cc_mclk0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_mclk1_clk_src",
+		.parent_data = cam_cc_parent_data_1,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_mclk2_clk_src = {
+	.cmd_rcgr = 0x4044,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_1,
+	.freq_tbl = ftbl_cam_cc_mclk0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_mclk2_clk_src",
+		.parent_data = cam_cc_parent_data_1,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_mclk3_clk_src = {
+	.cmd_rcgr = 0x4064,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_1,
+	.freq_tbl = ftbl_cam_cc_mclk0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_mclk3_clk_src",
+		.parent_data = cam_cc_parent_data_1,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 cam_cc_mclk4_clk_src = {
+	.cmd_rcgr = 0x4084,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_1,
+	.freq_tbl = ftbl_cam_cc_mclk0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_mclk4_clk_src",
+		.parent_data = cam_cc_parent_data_1,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cam_cc_slow_ahb_clk_src[] = {
+	F(80000000, P_CAM_CC_PLL0_OUT_EVEN, 7.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cam_cc_slow_ahb_clk_src = {
+	.cmd_rcgr = 0x6058,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = cam_cc_parent_map_0,
+	.freq_tbl = ftbl_cam_cc_slow_ahb_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cam_cc_slow_ahb_clk_src",
+		.parent_data = cam_cc_parent_data_0,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch cam_cc_bps_ahb_clk = {
+	.halt_reg = 0x6070,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x6070,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_bps_ahb_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_slow_ahb_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_bps_areg_clk = {
+	.halt_reg = 0x6054,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x6054,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_bps_areg_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_fast_ahb_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_bps_axi_clk = {
+	.halt_reg = 0x6038,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x6038,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_bps_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_bps_clk = {
+	.halt_reg = 0x6028,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x6028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_bps_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_bps_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_camnoc_axi_clk = {
+	.halt_reg = 0xb124,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb124,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_camnoc_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_cci_0_clk = {
+	.halt_reg = 0xb0f0,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb0f0,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_cci_0_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_cci_0_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_cci_1_clk = {
+	.halt_reg = 0xb164,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb164,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_cci_1_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_cci_1_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_core_ahb_clk = {
+	.halt_reg = 0xb144,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0xb144,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_core_ahb_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_slow_ahb_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_cpas_ahb_clk = {
+	.halt_reg = 0xb11c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb11c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_cpas_ahb_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_slow_ahb_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_csi0phytimer_clk = {
+	.halt_reg = 0x501c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x501c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_csi0phytimer_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_csi0phytimer_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_csi1phytimer_clk = {
+	.halt_reg = 0x5040,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x5040,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_csi1phytimer_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_csi1phytimer_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_csi2phytimer_clk = {
+	.halt_reg = 0x5064,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x5064,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_csi2phytimer_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_csi2phytimer_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_csi3phytimer_clk = {
+	.halt_reg = 0x5088,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x5088,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_csi3phytimer_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_csi3phytimer_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_csiphy0_clk = {
+	.halt_reg = 0x5020,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x5020,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_csiphy0_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_cphy_rx_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_csiphy1_clk = {
+	.halt_reg = 0x5044,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x5044,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_csiphy1_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_cphy_rx_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_csiphy2_clk = {
+	.halt_reg = 0x5068,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x5068,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_csiphy2_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_cphy_rx_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_csiphy3_clk = {
+	.halt_reg = 0x508c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x508c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_csiphy3_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_cphy_rx_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_icp_clk = {
+	.halt_reg = 0xb0a0,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb0a0,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_icp_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_icp_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_0_axi_clk = {
+	.halt_reg = 0x9080,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x9080,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_0_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_0_clk = {
+	.halt_reg = 0x9028,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x9028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_0_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_ife_0_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_0_cphy_rx_clk = {
+	.halt_reg = 0x907c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x907c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_0_cphy_rx_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_cphy_rx_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_0_csid_clk = {
+	.halt_reg = 0x9054,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x9054,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_0_csid_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_ife_0_csid_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_0_dsp_clk = {
+	.halt_reg = 0x9038,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x9038,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_0_dsp_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_ife_0_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_1_axi_clk = {
+	.halt_reg = 0xa058,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xa058,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_1_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_1_clk = {
+	.halt_reg = 0xa028,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xa028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_1_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_ife_1_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_1_cphy_rx_clk = {
+	.halt_reg = 0xa054,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xa054,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_1_cphy_rx_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_cphy_rx_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_1_csid_clk = {
+	.halt_reg = 0xa04c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xa04c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_1_csid_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_ife_1_csid_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_1_dsp_clk = {
+	.halt_reg = 0xa030,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xa030,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_1_dsp_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_ife_1_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_lite_clk = {
+	.halt_reg = 0xb01c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb01c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_lite_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_ife_lite_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_lite_cphy_rx_clk = {
+	.halt_reg = 0xb044,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb044,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_lite_cphy_rx_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_cphy_rx_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ife_lite_csid_clk = {
+	.halt_reg = 0xb03c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb03c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ife_lite_csid_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_ife_lite_csid_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ipe_0_ahb_clk = {
+	.halt_reg = 0x7040,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x7040,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ipe_0_ahb_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_slow_ahb_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ipe_0_areg_clk = {
+	.halt_reg = 0x703c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x703c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ipe_0_areg_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_fast_ahb_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ipe_0_axi_clk = {
+	.halt_reg = 0x7038,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x7038,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ipe_0_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_ipe_0_clk = {
+	.halt_reg = 0x7028,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x7028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_ipe_0_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_ipe_0_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_jpeg_clk = {
+	.halt_reg = 0xb064,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb064,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_jpeg_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_jpeg_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_lrme_clk = {
+	.halt_reg = 0xb110,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb110,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_lrme_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_lrme_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_mclk0_clk = {
+	.halt_reg = 0x401c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x401c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_mclk0_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_mclk0_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_mclk1_clk = {
+	.halt_reg = 0x403c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x403c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_mclk1_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_mclk1_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_mclk2_clk = {
+	.halt_reg = 0x405c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x405c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_mclk2_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_mclk2_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_mclk3_clk = {
+	.halt_reg = 0x407c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x407c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_mclk3_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_mclk3_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_mclk4_clk = {
+	.halt_reg = 0x409c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x409c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_mclk4_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &cam_cc_mclk4_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_soc_ahb_clk = {
+	.halt_reg = 0xb140,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb140,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_soc_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch cam_cc_sys_tmr_clk = {
+	.halt_reg = 0xb0a8,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb0a8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "cam_cc_sys_tmr_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct gdsc bps_gdsc = {
+	.gdscr = 0x6004,
+	.pd = {
+		.name = "bps_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = HW_CTRL,
+};
+
+static struct gdsc ife_0_gdsc = {
+	.gdscr = 0x9004,
+	.pd = {
+		.name = "ife_0_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc ife_1_gdsc = {
+	.gdscr = 0xa004,
+	.pd = {
+		.name = "ife_1_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc ipe_0_gdsc = {
+	.gdscr = 0x7004,
+	.pd = {
+		.name = "ipe_0_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = HW_CTRL,
+};
+
+static struct gdsc titan_top_gdsc = {
+	.gdscr = 0xb134,
+	.pd = {
+		.name = "titan_top_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct clk_hw *cam_cc_sc7180_hws[] = {
+	[CAM_CC_PLL2_OUT_EARLY] = &cam_cc_pll2_out_early.hw,
+};
+
+static struct clk_regmap *cam_cc_sc7180_clocks[] = {
+	[CAM_CC_BPS_AHB_CLK] = &cam_cc_bps_ahb_clk.clkr,
+	[CAM_CC_BPS_AREG_CLK] = &cam_cc_bps_areg_clk.clkr,
+	[CAM_CC_BPS_AXI_CLK] = &cam_cc_bps_axi_clk.clkr,
+	[CAM_CC_BPS_CLK] = &cam_cc_bps_clk.clkr,
+	[CAM_CC_BPS_CLK_SRC] = &cam_cc_bps_clk_src.clkr,
+	[CAM_CC_CAMNOC_AXI_CLK] = &cam_cc_camnoc_axi_clk.clkr,
+	[CAM_CC_CCI_0_CLK] = &cam_cc_cci_0_clk.clkr,
+	[CAM_CC_CCI_0_CLK_SRC] = &cam_cc_cci_0_clk_src.clkr,
+	[CAM_CC_CCI_1_CLK] = &cam_cc_cci_1_clk.clkr,
+	[CAM_CC_CCI_1_CLK_SRC] = &cam_cc_cci_1_clk_src.clkr,
+	[CAM_CC_CORE_AHB_CLK] = &cam_cc_core_ahb_clk.clkr,
+	[CAM_CC_CPAS_AHB_CLK] = &cam_cc_cpas_ahb_clk.clkr,
+	[CAM_CC_CPHY_RX_CLK_SRC] = &cam_cc_cphy_rx_clk_src.clkr,
+	[CAM_CC_CSI0PHYTIMER_CLK] = &cam_cc_csi0phytimer_clk.clkr,
+	[CAM_CC_CSI0PHYTIMER_CLK_SRC] = &cam_cc_csi0phytimer_clk_src.clkr,
+	[CAM_CC_CSI1PHYTIMER_CLK] = &cam_cc_csi1phytimer_clk.clkr,
+	[CAM_CC_CSI1PHYTIMER_CLK_SRC] = &cam_cc_csi1phytimer_clk_src.clkr,
+	[CAM_CC_CSI2PHYTIMER_CLK] = &cam_cc_csi2phytimer_clk.clkr,
+	[CAM_CC_CSI2PHYTIMER_CLK_SRC] = &cam_cc_csi2phytimer_clk_src.clkr,
+	[CAM_CC_CSI3PHYTIMER_CLK] = &cam_cc_csi3phytimer_clk.clkr,
+	[CAM_CC_CSI3PHYTIMER_CLK_SRC] = &cam_cc_csi3phytimer_clk_src.clkr,
+	[CAM_CC_CSIPHY0_CLK] = &cam_cc_csiphy0_clk.clkr,
+	[CAM_CC_CSIPHY1_CLK] = &cam_cc_csiphy1_clk.clkr,
+	[CAM_CC_CSIPHY2_CLK] = &cam_cc_csiphy2_clk.clkr,
+	[CAM_CC_CSIPHY3_CLK] = &cam_cc_csiphy3_clk.clkr,
+	[CAM_CC_FAST_AHB_CLK_SRC] = &cam_cc_fast_ahb_clk_src.clkr,
+	[CAM_CC_ICP_CLK] = &cam_cc_icp_clk.clkr,
+	[CAM_CC_ICP_CLK_SRC] = &cam_cc_icp_clk_src.clkr,
+	[CAM_CC_IFE_0_AXI_CLK] = &cam_cc_ife_0_axi_clk.clkr,
+	[CAM_CC_IFE_0_CLK] = &cam_cc_ife_0_clk.clkr,
+	[CAM_CC_IFE_0_CLK_SRC] = &cam_cc_ife_0_clk_src.clkr,
+	[CAM_CC_IFE_0_CPHY_RX_CLK] = &cam_cc_ife_0_cphy_rx_clk.clkr,
+	[CAM_CC_IFE_0_CSID_CLK] = &cam_cc_ife_0_csid_clk.clkr,
+	[CAM_CC_IFE_0_CSID_CLK_SRC] = &cam_cc_ife_0_csid_clk_src.clkr,
+	[CAM_CC_IFE_0_DSP_CLK] = &cam_cc_ife_0_dsp_clk.clkr,
+	[CAM_CC_IFE_1_AXI_CLK] = &cam_cc_ife_1_axi_clk.clkr,
+	[CAM_CC_IFE_1_CLK] = &cam_cc_ife_1_clk.clkr,
+	[CAM_CC_IFE_1_CLK_SRC] = &cam_cc_ife_1_clk_src.clkr,
+	[CAM_CC_IFE_1_CPHY_RX_CLK] = &cam_cc_ife_1_cphy_rx_clk.clkr,
+	[CAM_CC_IFE_1_CSID_CLK] = &cam_cc_ife_1_csid_clk.clkr,
+	[CAM_CC_IFE_1_CSID_CLK_SRC] = &cam_cc_ife_1_csid_clk_src.clkr,
+	[CAM_CC_IFE_1_DSP_CLK] = &cam_cc_ife_1_dsp_clk.clkr,
+	[CAM_CC_IFE_LITE_CLK] = &cam_cc_ife_lite_clk.clkr,
+	[CAM_CC_IFE_LITE_CLK_SRC] = &cam_cc_ife_lite_clk_src.clkr,
+	[CAM_CC_IFE_LITE_CPHY_RX_CLK] = &cam_cc_ife_lite_cphy_rx_clk.clkr,
+	[CAM_CC_IFE_LITE_CSID_CLK] = &cam_cc_ife_lite_csid_clk.clkr,
+	[CAM_CC_IFE_LITE_CSID_CLK_SRC] = &cam_cc_ife_lite_csid_clk_src.clkr,
+	[CAM_CC_IPE_0_AHB_CLK] = &cam_cc_ipe_0_ahb_clk.clkr,
+	[CAM_CC_IPE_0_AREG_CLK] = &cam_cc_ipe_0_areg_clk.clkr,
+	[CAM_CC_IPE_0_AXI_CLK] = &cam_cc_ipe_0_axi_clk.clkr,
+	[CAM_CC_IPE_0_CLK] = &cam_cc_ipe_0_clk.clkr,
+	[CAM_CC_IPE_0_CLK_SRC] = &cam_cc_ipe_0_clk_src.clkr,
+	[CAM_CC_JPEG_CLK] = &cam_cc_jpeg_clk.clkr,
+	[CAM_CC_JPEG_CLK_SRC] = &cam_cc_jpeg_clk_src.clkr,
+	[CAM_CC_LRME_CLK] = &cam_cc_lrme_clk.clkr,
+	[CAM_CC_LRME_CLK_SRC] = &cam_cc_lrme_clk_src.clkr,
+	[CAM_CC_MCLK0_CLK] = &cam_cc_mclk0_clk.clkr,
+	[CAM_CC_MCLK0_CLK_SRC] = &cam_cc_mclk0_clk_src.clkr,
+	[CAM_CC_MCLK1_CLK] = &cam_cc_mclk1_clk.clkr,
+	[CAM_CC_MCLK1_CLK_SRC] = &cam_cc_mclk1_clk_src.clkr,
+	[CAM_CC_MCLK2_CLK] = &cam_cc_mclk2_clk.clkr,
+	[CAM_CC_MCLK2_CLK_SRC] = &cam_cc_mclk2_clk_src.clkr,
+	[CAM_CC_MCLK3_CLK] = &cam_cc_mclk3_clk.clkr,
+	[CAM_CC_MCLK3_CLK_SRC] = &cam_cc_mclk3_clk_src.clkr,
+	[CAM_CC_MCLK4_CLK] = &cam_cc_mclk4_clk.clkr,
+	[CAM_CC_MCLK4_CLK_SRC] = &cam_cc_mclk4_clk_src.clkr,
+	[CAM_CC_PLL0] = &cam_cc_pll0.clkr,
+	[CAM_CC_PLL1] = &cam_cc_pll1.clkr,
+	[CAM_CC_PLL2] = &cam_cc_pll2.clkr,
+	[CAM_CC_PLL2_OUT_AUX] = &cam_cc_pll2_out_aux.clkr,
+	[CAM_CC_PLL3] = &cam_cc_pll3.clkr,
+	[CAM_CC_SLOW_AHB_CLK_SRC] = &cam_cc_slow_ahb_clk_src.clkr,
+	[CAM_CC_SOC_AHB_CLK] = &cam_cc_soc_ahb_clk.clkr,
+	[CAM_CC_SYS_TMR_CLK] = &cam_cc_sys_tmr_clk.clkr,
+};
+static struct gdsc *cam_cc_sc7180_gdscs[] = {
+	[BPS_GDSC] = &bps_gdsc,
+	[IFE_0_GDSC] = &ife_0_gdsc,
+	[IFE_1_GDSC] = &ife_1_gdsc,
+	[IPE_0_GDSC] = &ipe_0_gdsc,
+	[TITAN_TOP_GDSC] = &titan_top_gdsc,
+};
+
+static const struct regmap_config cam_cc_sc7180_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.max_register = 0xd028,
+	.fast_io = true,
+};
+
+static const struct qcom_cc_desc cam_cc_sc7180_desc = {
+	.config = &cam_cc_sc7180_regmap_config,
+	.clk_hws = cam_cc_sc7180_hws,
+	.num_clk_hws = ARRAY_SIZE(cam_cc_sc7180_hws),
+	.clks = cam_cc_sc7180_clocks,
+	.num_clks = ARRAY_SIZE(cam_cc_sc7180_clocks),
+	.gdscs = cam_cc_sc7180_gdscs,
+	.num_gdscs = ARRAY_SIZE(cam_cc_sc7180_gdscs),
+};
+
+static const struct of_device_id cam_cc_sc7180_match_table[] = {
+	{ .compatible = "qcom,sc7180-camcc" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, cam_cc_sc7180_match_table);
+
+static int cam_cc_sc7180_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+	int ret;
+
+	pm_runtime_enable(&pdev->dev);
+	ret = pm_clk_create(&pdev->dev);
+	if (ret < 0)
+		return ret;
+
+	ret = pm_clk_add(&pdev->dev, "xo");
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to acquire XO clock\n");
+		goto disable_pm_runtime;
+	}
+
+	ret = pm_clk_add(&pdev->dev, "iface");
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to acquire iface clock\n");
+		goto disable_pm_runtime;
+	}
+
+	ret = pm_runtime_get(&pdev->dev);
+	if (ret)
+		goto destroy_pm_clk;
+
+	regmap = qcom_cc_map(pdev, &cam_cc_sc7180_desc);
+	if (IS_ERR(regmap)) {
+		ret = PTR_ERR(regmap);
+		pm_runtime_put(&pdev->dev);
+		goto destroy_pm_clk;
+	}
+
+	clk_fabia_pll_configure(&cam_cc_pll0, regmap, &cam_cc_pll0_config);
+	clk_fabia_pll_configure(&cam_cc_pll1, regmap, &cam_cc_pll1_config);
+	clk_agera_pll_configure(&cam_cc_pll2, regmap, &cam_cc_pll2_config);
+	clk_fabia_pll_configure(&cam_cc_pll3, regmap, &cam_cc_pll3_config);
+
+	ret = qcom_cc_really_probe(pdev, &cam_cc_sc7180_desc, regmap);
+	pm_runtime_put(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to register CAM CC clocks\n");
+		goto destroy_pm_clk;
+	}
+
+	return 0;
+
+destroy_pm_clk:
+	pm_clk_destroy(&pdev->dev);
+
+disable_pm_runtime:
+	pm_runtime_disable(&pdev->dev);
+
+	return ret;
+}
+
+static const struct dev_pm_ops cam_cc_pm_ops = {
+	SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL)
+};
+
+static struct platform_driver cam_cc_sc7180_driver = {
+	.probe = cam_cc_sc7180_probe,
+	.driver = {
+		.name = "cam_cc-sc7180",
+		.of_match_table = cam_cc_sc7180_match_table,
+		.pm = &cam_cc_pm_ops,
+	},
+};
+
+static int __init cam_cc_sc7180_init(void)
+{
+	return platform_driver_register(&cam_cc_sc7180_driver);
+}
+subsys_initcall(cam_cc_sc7180_init);
+
+static void __exit cam_cc_sc7180_exit(void)
+{
+	platform_driver_unregister(&cam_cc_sc7180_driver);
+}
+module_exit(cam_cc_sc7180_exit);
+
+MODULE_DESCRIPTION("QTI CAM_CC SC7180 Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index 564431130a76..21c357c26ec4 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -116,6 +116,16 @@ const u8 clk_alpha_pll_regs[][PLL_OFF_MAX_REGS] = {
 		[PLL_OFF_OPMODE] = 0x38,
 		[PLL_OFF_ALPHA_VAL] = 0x40,
 	},
+	[CLK_ALPHA_PLL_TYPE_AGERA] =  {
+		[PLL_OFF_L_VAL] = 0x04,
+		[PLL_OFF_ALPHA_VAL] = 0x08,
+		[PLL_OFF_USER_CTL] = 0x0c,
+		[PLL_OFF_CONFIG_CTL] = 0x10,
+		[PLL_OFF_CONFIG_CTL_U] = 0x14,
+		[PLL_OFF_TEST_CTL] = 0x18,
+		[PLL_OFF_TEST_CTL_U] = 0x1c,
+		[PLL_OFF_STATUS] = 0x2c,
+	},
 };
 EXPORT_SYMBOL_GPL(clk_alpha_pll_regs);
 
@@ -207,6 +217,13 @@ static int wait_for_pll(struct clk_alpha_pll *pll, u32 mask, bool inverse,
 #define wait_for_pll_update_ack_clear(pll) \
 	wait_for_pll(pll, ALPHA_PLL_ACK_LATCH, 1, "update_ack_clear")
 
+static void clk_alpha_pll_write_config(struct regmap *regmap, unsigned int reg,
+					unsigned int val)
+{
+	if (val)
+		regmap_write(regmap, reg, val);
+}
+
 void clk_alpha_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 			     const struct alpha_pll_config *config)
 {
@@ -1004,33 +1021,19 @@ void clk_fabia_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 {
 	u32 val, mask;
 
-	if (config->l)
-		regmap_write(regmap, PLL_L_VAL(pll), config->l);
-
-	if (config->alpha)
-		regmap_write(regmap, PLL_FRAC(pll), config->alpha);
-
-	if (config->config_ctl_val)
-		regmap_write(regmap, PLL_CONFIG_CTL(pll),
+	clk_alpha_pll_write_config(regmap, PLL_L_VAL(pll), config->l);
+	clk_alpha_pll_write_config(regmap, PLL_FRAC(pll), config->alpha);
+	clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL(pll),
 						config->config_ctl_val);
-
-	if (config->config_ctl_hi_val)
-		regmap_write(regmap, PLL_CONFIG_CTL_U(pll),
+	clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U(pll),
 						config->config_ctl_hi_val);
-
-	if (config->user_ctl_val)
-		regmap_write(regmap, PLL_USER_CTL(pll), config->user_ctl_val);
-
-	if (config->user_ctl_hi_val)
-		regmap_write(regmap, PLL_USER_CTL_U(pll),
+	clk_alpha_pll_write_config(regmap, PLL_USER_CTL(pll),
+						config->user_ctl_val);
+	clk_alpha_pll_write_config(regmap, PLL_USER_CTL_U(pll),
 						config->user_ctl_hi_val);
-
-	if (config->test_ctl_val)
-		regmap_write(regmap, PLL_TEST_CTL(pll),
+	clk_alpha_pll_write_config(regmap, PLL_TEST_CTL(pll),
 						config->test_ctl_val);
-
-	if (config->test_ctl_hi_val)
-		regmap_write(regmap, PLL_TEST_CTL_U(pll),
+	clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U(pll),
 						config->test_ctl_hi_val);
 
 	if (config->post_div_mask) {
@@ -1145,25 +1148,38 @@ static unsigned long alpha_pll_fabia_recalc_rate(struct clk_hw *hw,
 	return alpha_pll_calc_rate(parent_rate, l, frac, alpha_width);
 }
 
+/*
+ * Due to limited number of bits for fractional rate programming, the
+ * rounded up rate could be marginally higher than the requested rate.
+ */
+static int alpha_pll_check_rate_margin(struct clk_hw *hw,
+			unsigned long rrate, unsigned long rate)
+{
+	unsigned long rate_margin = rate + PLL_RATE_MARGIN;
+
+	if (rrate > rate_margin || rrate < rate) {
+		pr_err("%s: Rounded rate %lu not within range [%lu, %lu)\n",
+		       clk_hw_get_name(hw), rrate, rate, rate_margin);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int alpha_pll_fabia_set_rate(struct clk_hw *hw, unsigned long rate,
 						unsigned long prate)
 {
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
 	u32 l, alpha_width = pll_alpha_width(pll);
+	unsigned long rrate;
+	int ret;
 	u64 a;
-	unsigned long rrate, max = rate + PLL_RATE_MARGIN;
 
 	rrate = alpha_pll_round_rate(rate, prate, &l, &a, alpha_width);
 
-	/*
-	 * Due to limited number of bits for fractional rate programming, the
-	 * rounded up rate could be marginally higher than the requested rate.
-	 */
-	if (rrate > (rate + PLL_RATE_MARGIN) || rrate < rate) {
-		pr_err("%s: Rounded rate %lu not within range [%lu, %lu)\n",
-		       clk_hw_get_name(hw), rrate, rate, max);
-		return -EINVAL;
-	}
+	ret = alpha_pll_check_rate_margin(hw, rrate, rate);
+	if (ret < 0)
+		return ret;
 
 	regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l);
 	regmap_write(pll->clkr.regmap, PLL_FRAC(pll), a);
@@ -1206,12 +1222,10 @@ static int alpha_pll_fabia_prepare(struct clk_hw *hw)
 
 	rrate = alpha_pll_round_rate(cal_freq, clk_hw_get_rate(parent_hw),
 					&cal_l, &a, alpha_width);
-	/*
-	 * Due to a limited number of bits for fractional rate programming, the
-	 * rounded up rate could be marginally higher than the requested rate.
-	 */
-	if (rrate > (cal_freq + PLL_RATE_MARGIN) || rrate < cal_freq)
-		return -EINVAL;
+
+	ret = alpha_pll_check_rate_margin(hw, rrate, cal_freq);
+	if (ret < 0)
+		return ret;
 
 	/* Setup PLL for calibration frequency */
 	regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), cal_l);
@@ -1388,49 +1402,27 @@ EXPORT_SYMBOL_GPL(clk_alpha_pll_postdiv_fabia_ops);
 void clk_trion_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 			     const struct alpha_pll_config *config)
 {
-	if (config->l)
-		regmap_write(regmap, PLL_L_VAL(pll), config->l);
-
+	clk_alpha_pll_write_config(regmap, PLL_L_VAL(pll), config->l);
 	regmap_write(regmap, PLL_CAL_L_VAL(pll), TRION_PLL_CAL_VAL);
-
-	if (config->alpha)
-		regmap_write(regmap, PLL_ALPHA_VAL(pll), config->alpha);
-
-	if (config->config_ctl_val)
-		regmap_write(regmap, PLL_CONFIG_CTL(pll),
-			     config->config_ctl_val);
-
-	if (config->config_ctl_hi_val)
-		regmap_write(regmap, PLL_CONFIG_CTL_U(pll),
-			     config->config_ctl_hi_val);
-
-	if (config->config_ctl_hi1_val)
-		regmap_write(regmap, PLL_CONFIG_CTL_U1(pll),
-			     config->config_ctl_hi1_val);
-
-	if (config->user_ctl_val)
-		regmap_write(regmap, PLL_USER_CTL(pll),
-			     config->user_ctl_val);
-
-	if (config->user_ctl_hi_val)
-		regmap_write(regmap, PLL_USER_CTL_U(pll),
-			     config->user_ctl_hi_val);
-
-	if (config->user_ctl_hi1_val)
-		regmap_write(regmap, PLL_USER_CTL_U1(pll),
-			     config->user_ctl_hi1_val);
-
-	if (config->test_ctl_val)
-		regmap_write(regmap, PLL_TEST_CTL(pll),
-			     config->test_ctl_val);
-
-	if (config->test_ctl_hi_val)
-		regmap_write(regmap, PLL_TEST_CTL_U(pll),
-			     config->test_ctl_hi_val);
-
-	if (config->test_ctl_hi1_val)
-		regmap_write(regmap, PLL_TEST_CTL_U1(pll),
-			     config->test_ctl_hi1_val);
+	clk_alpha_pll_write_config(regmap, PLL_ALPHA_VAL(pll), config->alpha);
+	clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL(pll),
+				     config->config_ctl_val);
+	clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U(pll),
+				     config->config_ctl_hi_val);
+	clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U1(pll),
+				     config->config_ctl_hi1_val);
+	clk_alpha_pll_write_config(regmap, PLL_USER_CTL(pll),
+					config->user_ctl_val);
+	clk_alpha_pll_write_config(regmap, PLL_USER_CTL_U(pll),
+					config->user_ctl_hi_val);
+	clk_alpha_pll_write_config(regmap, PLL_USER_CTL_U1(pll),
+					config->user_ctl_hi1_val);
+	clk_alpha_pll_write_config(regmap, PLL_TEST_CTL(pll),
+					config->test_ctl_val);
+	clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U(pll),
+					config->test_ctl_hi_val);
+	clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U1(pll),
+					config->test_ctl_hi1_val);
 
 	regmap_update_bits(regmap, PLL_MODE(pll), PLL_UPDATE_BYPASS,
 			   PLL_UPDATE_BYPASS);
@@ -1490,14 +1482,9 @@ static int alpha_pll_trion_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	rrate = alpha_pll_round_rate(rate, prate, &l, &a, alpha_width);
 
-	/*
-	 * Due to a limited number of bits for fractional rate programming, the
-	 * rounded up rate could be marginally higher than the requested rate.
-	 */
-	if (rrate > (rate + PLL_RATE_MARGIN) || rrate < rate) {
-		pr_err("Call set rate on the PLL with rounded rates!\n");
-		return -EINVAL;
-	}
+	ret = alpha_pll_check_rate_margin(hw, rrate, rate);
+	if (ret < 0)
+		return ret;
 
 	regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l);
 	regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), a);
@@ -1561,3 +1548,55 @@ const struct clk_ops clk_alpha_pll_postdiv_lucid_ops = {
 	.set_rate = clk_alpha_pll_postdiv_fabia_set_rate,
 };
 EXPORT_SYMBOL_GPL(clk_alpha_pll_postdiv_lucid_ops);
+
+void clk_agera_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
+			const struct alpha_pll_config *config)
+{
+	clk_alpha_pll_write_config(regmap, PLL_L_VAL(pll), config->l);
+	clk_alpha_pll_write_config(regmap, PLL_ALPHA_VAL(pll), config->alpha);
+	clk_alpha_pll_write_config(regmap, PLL_USER_CTL(pll),
+							config->user_ctl_val);
+	clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL(pll),
+						config->config_ctl_val);
+	clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U(pll),
+						config->config_ctl_hi_val);
+	clk_alpha_pll_write_config(regmap, PLL_TEST_CTL(pll),
+						config->test_ctl_val);
+	clk_alpha_pll_write_config(regmap,  PLL_TEST_CTL_U(pll),
+						config->test_ctl_hi_val);
+}
+EXPORT_SYMBOL_GPL(clk_agera_pll_configure);
+
+static int clk_alpha_pll_agera_set_rate(struct clk_hw *hw, unsigned long rate,
+							unsigned long prate)
+{
+	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
+	u32 l, alpha_width = pll_alpha_width(pll);
+	int ret;
+	unsigned long rrate;
+	u64 a;
+
+	rrate = alpha_pll_round_rate(rate, prate, &l, &a, alpha_width);
+	ret = alpha_pll_check_rate_margin(hw, rrate, rate);
+	if (ret < 0)
+		return ret;
+
+	/* change L_VAL without having to go through the power on sequence */
+	regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l);
+	regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), a);
+
+	if (clk_hw_is_enabled(hw))
+		return wait_for_pll_enable_lock(pll);
+
+	return 0;
+}
+
+const struct clk_ops clk_alpha_pll_agera_ops = {
+	.enable = clk_alpha_pll_enable,
+	.disable = clk_alpha_pll_disable,
+	.is_enabled = clk_alpha_pll_is_enabled,
+	.recalc_rate = alpha_pll_fabia_recalc_rate,
+	.round_rate = clk_alpha_pll_round_rate,
+	.set_rate = clk_alpha_pll_agera_set_rate,
+};
+EXPORT_SYMBOL_GPL(clk_alpha_pll_agera_ops);
diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h
index d3201b87c0cd..0ea30d2f3da1 100644
--- a/drivers/clk/qcom/clk-alpha-pll.h
+++ b/drivers/clk/qcom/clk-alpha-pll.h
@@ -15,6 +15,7 @@ enum {
 	CLK_ALPHA_PLL_TYPE_FABIA,
 	CLK_ALPHA_PLL_TYPE_TRION,
 	CLK_ALPHA_PLL_TYPE_LUCID = CLK_ALPHA_PLL_TYPE_TRION,
+	CLK_ALPHA_PLL_TYPE_AGERA,
 	CLK_ALPHA_PLL_TYPE_MAX,
 };
 
@@ -141,6 +142,7 @@ extern const struct clk_ops clk_alpha_pll_postdiv_trion_ops;
 extern const struct clk_ops clk_alpha_pll_lucid_ops;
 #define clk_alpha_pll_fixed_lucid_ops clk_alpha_pll_fixed_trion_ops
 extern const struct clk_ops clk_alpha_pll_postdiv_lucid_ops;
+extern const struct clk_ops clk_alpha_pll_agera_ops;
 
 void clk_alpha_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 			     const struct alpha_pll_config *config);
@@ -148,6 +150,8 @@ void clk_fabia_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 				const struct alpha_pll_config *config);
 void clk_trion_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 			     const struct alpha_pll_config *config);
+void clk_agera_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
+				const struct alpha_pll_config *config);
 #define clk_lucid_pll_configure(pll, regmap, config) \
 	clk_trion_pll_configure(pll, regmap, config)
 
diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c
index e2c669b08aff..6a2a13c5058e 100644
--- a/drivers/clk/qcom/clk-rpmh.c
+++ b/drivers/clk/qcom/clk-rpmh.c
@@ -349,6 +349,7 @@ DEFINE_CLK_RPMH_VRM(sdm845, rf_clk2, rf_clk2_ao, "rfclka2", 1);
 DEFINE_CLK_RPMH_VRM(sdm845, rf_clk3, rf_clk3_ao, "rfclka3", 1);
 DEFINE_CLK_RPMH_VRM(sm8150, rf_clk3, rf_clk3_ao, "rfclka3", 1);
 DEFINE_CLK_RPMH_BCM(sdm845, ipa, "IP0");
+DEFINE_CLK_RPMH_BCM(sdm845, ce, "CE0");
 
 static struct clk_hw *sdm845_rpmh_clocks[] = {
 	[RPMH_CXO_CLK]		= &sdm845_bi_tcxo.hw,
@@ -364,6 +365,7 @@ static struct clk_hw *sdm845_rpmh_clocks[] = {
 	[RPMH_RF_CLK3]		= &sdm845_rf_clk3.hw,
 	[RPMH_RF_CLK3_A]	= &sdm845_rf_clk3_ao.hw,
 	[RPMH_IPA_CLK]		= &sdm845_ipa.hw,
+	[RPMH_CE_CLK]		= &sdm845_ce.hw,
 };
 
 static const struct clk_rpmh_desc clk_rpmh_sdm845 = {
@@ -371,6 +373,25 @@ static const struct clk_rpmh_desc clk_rpmh_sdm845 = {
 	.num_clks = ARRAY_SIZE(sdm845_rpmh_clocks),
 };
 
+DEFINE_CLK_RPMH_VRM(sdx55, rf_clk1, rf_clk1_ao, "rfclkd1", 1);
+DEFINE_CLK_RPMH_VRM(sdx55, rf_clk2, rf_clk2_ao, "rfclkd2", 1);
+DEFINE_CLK_RPMH_BCM(sdx55, qpic_clk, "QP0");
+
+static struct clk_hw *sdx55_rpmh_clocks[] = {
+	[RPMH_CXO_CLK]		= &sdm845_bi_tcxo.hw,
+	[RPMH_CXO_CLK_A]	= &sdm845_bi_tcxo_ao.hw,
+	[RPMH_RF_CLK1]		= &sdx55_rf_clk1.hw,
+	[RPMH_RF_CLK1_A]	= &sdx55_rf_clk1_ao.hw,
+	[RPMH_RF_CLK2]		= &sdx55_rf_clk2.hw,
+	[RPMH_RF_CLK2_A]	= &sdx55_rf_clk2_ao.hw,
+	[RPMH_QPIC_CLK]		= &sdx55_qpic_clk.hw,
+};
+
+static const struct clk_rpmh_desc clk_rpmh_sdx55 = {
+	.clks = sdx55_rpmh_clocks,
+	.num_clks = ARRAY_SIZE(sdx55_rpmh_clocks),
+};
+
 static struct clk_hw *sm8150_rpmh_clocks[] = {
 	[RPMH_CXO_CLK]		= &sdm845_bi_tcxo.hw,
 	[RPMH_CXO_CLK_A]	= &sdm845_bi_tcxo_ao.hw,
@@ -432,6 +453,39 @@ static const struct clk_rpmh_desc clk_rpmh_sm8250 = {
 	.num_clks = ARRAY_SIZE(sm8250_rpmh_clocks),
 };
 
+DEFINE_CLK_RPMH_VRM(sm8350, div_clk1, div_clk1_ao, "divclka1", 2);
+DEFINE_CLK_RPMH_VRM(sm8350, rf_clk4, rf_clk4_ao, "rfclka4", 1);
+DEFINE_CLK_RPMH_VRM(sm8350, rf_clk5, rf_clk5_ao, "rfclka5", 1);
+DEFINE_CLK_RPMH_BCM(sm8350, pka, "PKA0");
+DEFINE_CLK_RPMH_BCM(sm8350, hwkm, "HK0");
+
+static struct clk_hw *sm8350_rpmh_clocks[] = {
+	[RPMH_CXO_CLK]		= &sdm845_bi_tcxo.hw,
+	[RPMH_CXO_CLK_A]	= &sdm845_bi_tcxo_ao.hw,
+	[RPMH_DIV_CLK1]		= &sm8350_div_clk1.hw,
+	[RPMH_DIV_CLK1_A]	= &sm8350_div_clk1_ao.hw,
+	[RPMH_LN_BB_CLK1]	= &sm8250_ln_bb_clk1.hw,
+	[RPMH_LN_BB_CLK1_A]	= &sm8250_ln_bb_clk1_ao.hw,
+	[RPMH_LN_BB_CLK2]	= &sdm845_ln_bb_clk2.hw,
+	[RPMH_LN_BB_CLK2_A]	= &sdm845_ln_bb_clk2_ao.hw,
+	[RPMH_RF_CLK1]		= &sdm845_rf_clk1.hw,
+	[RPMH_RF_CLK1_A]	= &sdm845_rf_clk1_ao.hw,
+	[RPMH_RF_CLK3]		= &sdm845_rf_clk3.hw,
+	[RPMH_RF_CLK3_A]	= &sdm845_rf_clk3_ao.hw,
+	[RPMH_RF_CLK4]		= &sm8350_rf_clk4.hw,
+	[RPMH_RF_CLK4_A]	= &sm8350_rf_clk4_ao.hw,
+	[RPMH_RF_CLK5]		= &sm8350_rf_clk5.hw,
+	[RPMH_RF_CLK5_A]	= &sm8350_rf_clk5_ao.hw,
+	[RPMH_IPA_CLK]		= &sdm845_ipa.hw,
+	[RPMH_PKA_CLK]		= &sm8350_pka.hw,
+	[RPMH_HWKM_CLK]		= &sm8350_hwkm.hw,
+};
+
+static const struct clk_rpmh_desc clk_rpmh_sm8350 = {
+	.clks = sm8350_rpmh_clocks,
+	.num_clks = ARRAY_SIZE(sm8350_rpmh_clocks),
+};
+
 static struct clk_hw *of_clk_rpmh_hw_get(struct of_phandle_args *clkspec,
 					 void *data)
 {
@@ -517,8 +571,10 @@ static int clk_rpmh_probe(struct platform_device *pdev)
 static const struct of_device_id clk_rpmh_match_table[] = {
 	{ .compatible = "qcom,sc7180-rpmh-clk", .data = &clk_rpmh_sc7180},
 	{ .compatible = "qcom,sdm845-rpmh-clk", .data = &clk_rpmh_sdm845},
+	{ .compatible = "qcom,sdx55-rpmh-clk",  .data = &clk_rpmh_sdx55},
 	{ .compatible = "qcom,sm8150-rpmh-clk", .data = &clk_rpmh_sm8150},
 	{ .compatible = "qcom,sm8250-rpmh-clk", .data = &clk_rpmh_sm8250},
+	{ .compatible = "qcom,sm8350-rpmh-clk", .data = &clk_rpmh_sm8350},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, clk_rpmh_match_table);
diff --git a/drivers/clk/qcom/dispcc-sm8250.c b/drivers/clk/qcom/dispcc-sm8250.c
index 07a98d3f882d..588575e1169d 100644
--- a/drivers/clk/qcom/dispcc-sm8250.c
+++ b/drivers/clk/qcom/dispcc-sm8250.c
@@ -963,6 +963,7 @@ static struct gdsc mdss_gdsc = {
 	},
 	.pwrsts = PWRSTS_OFF_ON,
 	.flags = HW_CTRL,
+	.supply = "mmcx",
 };
 
 static struct clk_regmap *disp_cc_sm8250_clocks[] = {
diff --git a/drivers/clk/qcom/gcc-sc7180.c b/drivers/clk/qcom/gcc-sc7180.c
index 68d8f7aaf64e..d82d725ac231 100644
--- a/drivers/clk/qcom/gcc-sc7180.c
+++ b/drivers/clk/qcom/gcc-sc7180.c
@@ -642,7 +642,7 @@ static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = {
 		.name = "gcc_sdcc1_ice_core_clk_src",
 		.parent_data = gcc_parent_data_0,
 		.num_parents = 4,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_floor_ops,
 	},
 };
 
@@ -651,6 +651,7 @@ static const struct freq_tbl ftbl_gcc_sdcc2_apps_clk_src[] = {
 	F(9600000, P_BI_TCXO, 2, 0, 0),
 	F(19200000, P_BI_TCXO, 1, 0, 0),
 	F(25000000, P_GPLL0_OUT_EVEN, 12, 0, 0),
+	F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0),
 	F(100000000, P_GPLL0_OUT_EVEN, 3, 0, 0),
 	F(202000000, P_GPLL7_OUT_MAIN, 4, 0, 0),
 	{ }
@@ -666,7 +667,7 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = {
 		.name = "gcc_sdcc2_apps_clk_src",
 		.parent_data = gcc_parent_data_5,
 		.num_parents = 5,
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_floor_ops,
 	},
 };
 
diff --git a/drivers/clk/qcom/gcc-sdx55.c b/drivers/clk/qcom/gcc-sdx55.c
new file mode 100644
index 000000000000..e3b9030b2bae
--- /dev/null
+++ b/drivers/clk/qcom/gcc-sdx55.c
@@ -0,0 +1,1659 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2020, Linaro Ltd.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include <dt-bindings/clock/qcom,gcc-sdx55.h>
+
+#include "common.h"
+#include "clk-alpha-pll.h"
+#include "clk-branch.h"
+#include "clk-pll.h"
+#include "clk-rcg.h"
+#include "clk-regmap.h"
+#include "gdsc.h"
+#include "reset.h"
+
+enum {
+	P_BI_TCXO,
+	P_CORE_BI_PLL_TEST_SE,
+	P_GPLL0_OUT_EVEN,
+	P_GPLL0_OUT_MAIN,
+	P_GPLL4_OUT_EVEN,
+	P_GPLL5_OUT_MAIN,
+	P_SLEEP_CLK,
+};
+
+static const struct pll_vco lucid_vco[] = {
+	{ 249600000, 2000000000, 0 },
+};
+
+static struct clk_alpha_pll gpll0 = {
+	.offset = 0x0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID],
+	.vco_table = lucid_vco,
+	.num_vco = ARRAY_SIZE(lucid_vco),
+	.clkr = {
+		.enable_reg = 0x6d000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpll0",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fixed_lucid_ops,
+		},
+	},
+};
+
+static const struct clk_div_table post_div_table_lucid_even[] = {
+	{ 0x0, 1 },
+	{ 0x1, 2 },
+	{ 0x3, 4 },
+	{ 0x7, 8 },
+	{ }
+};
+
+static struct clk_alpha_pll_postdiv gpll0_out_even = {
+	.offset = 0x0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID],
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_lucid_even,
+	.num_post_div = ARRAY_SIZE(post_div_table_lucid_even),
+	.width = 4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll0_out_even",
+		.parent_data = &(const struct clk_parent_data){
+			.hw = &gpll0.clkr.hw,
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_lucid_ops,
+	},
+};
+
+static struct clk_alpha_pll gpll4 = {
+	.offset = 0x76000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID],
+	.vco_table = lucid_vco,
+	.num_vco = ARRAY_SIZE(lucid_vco),
+	.clkr = {
+		.enable_reg = 0x6d000,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpll4",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fixed_lucid_ops,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv gpll4_out_even = {
+	.offset = 0x76000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID],
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_lucid_even,
+	.num_post_div = ARRAY_SIZE(post_div_table_lucid_even),
+	.width = 4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll4_out_even",
+		.parent_data = &(const struct clk_parent_data){
+			.hw = &gpll4.clkr.hw,
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_lucid_ops,
+	},
+};
+
+static struct clk_alpha_pll gpll5 = {
+	.offset = 0x74000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID],
+	.vco_table = lucid_vco,
+	.num_vco = ARRAY_SIZE(lucid_vco),
+	.clkr = {
+		.enable_reg = 0x6d000,
+		.enable_mask = BIT(5),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpll5",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fixed_lucid_ops,
+		},
+	},
+};
+
+static const struct parent_map gcc_parent_map_0[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_GPLL0_OUT_MAIN, 1 },
+	{ P_GPLL0_OUT_EVEN, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data gcc_parents_0[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll0_out_even.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se" },
+};
+
+static const struct clk_parent_data gcc_parents_0_ao[] = {
+	{ .fw_name = "bi_tcxo_ao" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll0_out_even.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map gcc_parent_map_2[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_GPLL0_OUT_MAIN, 1 },
+	{ P_GPLL4_OUT_EVEN, 2 },
+	{ P_GPLL5_OUT_MAIN, 5 },
+	{ P_GPLL0_OUT_EVEN, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data gcc_parents_2[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll4_out_even.clkr.hw },
+	{ .hw = &gpll5.clkr.hw },
+	{ .hw = &gpll0_out_even.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map gcc_parent_map_3[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_GPLL0_OUT_MAIN, 1 },
+	{ P_SLEEP_CLK, 5 },
+	{ P_GPLL0_OUT_EVEN, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data gcc_parents_3[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .fw_name = "sleep_clk", .name = "sleep_clk" },
+	{ .hw = &gpll0_out_even.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map gcc_parent_map_4[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_SLEEP_CLK, 5 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data gcc_parents_4[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .fw_name = "sleep_clk", .name = "sleep_clk" },
+	{ .fw_name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map gcc_parent_map_5[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_GPLL0_OUT_MAIN, 1 },
+	{ P_GPLL4_OUT_EVEN, 2 },
+	{ P_GPLL0_OUT_EVEN, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data gcc_parents_5[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll4_out_even.clkr.hw },
+	{ .hw = &gpll0_out_even.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se" },
+};
+
+static const struct freq_tbl ftbl_gcc_blsp1_qup1_i2c_apps_clk_src[] = {
+	F(9600000, P_BI_TCXO, 2, 0, 0),
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(50000000, P_GPLL0_OUT_MAIN, 12, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_blsp1_qup1_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x11024,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_qup1_i2c_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_qup1_i2c_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_blsp1_qup1_spi_apps_clk_src[] = {
+	F(960000, P_BI_TCXO, 10, 1, 2),
+	F(4800000, P_BI_TCXO, 4, 0, 0),
+	F(9600000, P_BI_TCXO, 2, 0, 0),
+	F(15000000, P_GPLL0_OUT_EVEN, 5, 1, 4),
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(24000000, P_GPLL0_OUT_MAIN, 12.5, 1, 2),
+	F(25000000, P_GPLL0_OUT_MAIN, 12, 1, 2),
+	F(50000000, P_GPLL0_OUT_MAIN, 12, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_blsp1_qup1_spi_apps_clk_src = {
+	.cmd_rcgr = 0x1100c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_qup1_spi_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_qup1_spi_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_blsp1_qup2_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x13024,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_qup1_i2c_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_qup2_i2c_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_blsp1_qup2_spi_apps_clk_src = {
+	.cmd_rcgr = 0x1300c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_qup1_spi_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_qup2_spi_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_blsp1_qup3_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x15024,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_qup1_i2c_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_qup3_i2c_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_blsp1_qup3_spi_apps_clk_src = {
+	.cmd_rcgr = 0x1500c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_qup1_spi_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_qup3_spi_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_blsp1_qup4_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x17024,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_qup1_i2c_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_qup4_i2c_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_blsp1_qup4_spi_apps_clk_src = {
+	.cmd_rcgr = 0x1700c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_qup1_spi_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_qup4_spi_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_blsp1_uart1_apps_clk_src[] = {
+	F(3686400, P_GPLL0_OUT_EVEN, 1, 192, 15625),
+	F(7372800, P_GPLL0_OUT_EVEN, 1, 384, 15625),
+	F(9600000, P_BI_TCXO, 2, 0, 0),
+	F(14745600, P_GPLL0_OUT_EVEN, 1, 768, 15625),
+	F(16000000, P_GPLL0_OUT_EVEN, 1, 4, 75),
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(19354839, P_GPLL0_OUT_MAIN, 15.5, 1, 2),
+	F(20000000, P_GPLL0_OUT_MAIN, 15, 1, 2),
+	F(20689655, P_GPLL0_OUT_MAIN, 14.5, 1, 2),
+	F(21428571, P_GPLL0_OUT_MAIN, 14, 1, 2),
+	F(22222222, P_GPLL0_OUT_MAIN, 13.5, 1, 2),
+	F(23076923, P_GPLL0_OUT_MAIN, 13, 1, 2),
+	F(24000000, P_GPLL0_OUT_MAIN, 5, 1, 5),
+	F(25000000, P_GPLL0_OUT_MAIN, 12, 1, 2),
+	F(26086957, P_GPLL0_OUT_MAIN, 11.5, 1, 2),
+	F(27272727, P_GPLL0_OUT_MAIN, 11, 1, 2),
+	F(28571429, P_GPLL0_OUT_MAIN, 10.5, 1, 2),
+	F(32000000, P_GPLL0_OUT_MAIN, 1, 4, 75),
+	F(40000000, P_GPLL0_OUT_MAIN, 15, 0, 0),
+	F(46400000, P_GPLL0_OUT_MAIN, 1, 29, 375),
+	F(48000000, P_GPLL0_OUT_MAIN, 12.5, 0, 0),
+	F(51200000, P_GPLL0_OUT_MAIN, 1, 32, 375),
+	F(56000000, P_GPLL0_OUT_MAIN, 1, 7, 75),
+	F(58982400, P_GPLL0_OUT_MAIN, 1, 1536, 15625),
+	F(60000000, P_GPLL0_OUT_MAIN, 10, 0, 0),
+	F(63157895, P_GPLL0_OUT_MAIN, 9.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_blsp1_uart1_apps_clk_src = {
+	.cmd_rcgr = 0x1200c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_uart1_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_uart1_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_blsp1_uart2_apps_clk_src = {
+	.cmd_rcgr = 0x1400c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_uart1_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_uart2_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_blsp1_uart3_apps_clk_src = {
+	.cmd_rcgr = 0x1600c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_uart1_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_uart3_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_blsp1_uart4_apps_clk_src = {
+	.cmd_rcgr = 0x1800c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_blsp1_uart1_apps_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_blsp1_uart4_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_cpuss_ahb_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0),
+	F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0),
+	F(133333333, P_GPLL0_OUT_MAIN, 4.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_cpuss_ahb_clk_src = {
+	.cmd_rcgr = 0x24010,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_cpuss_ahb_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_cpuss_ahb_clk_src",
+		.parent_data = gcc_parents_0_ao,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_cpuss_rbcpr_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_cpuss_rbcpr_clk_src = {
+	.cmd_rcgr = 0x2402c,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_cpuss_rbcpr_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_cpuss_rbcpr_clk_src",
+		.parent_data = gcc_parents_0_ao,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_emac_clk_src[] = {
+	F(2500000, P_BI_TCXO, 1, 25, 192),
+	F(5000000, P_BI_TCXO, 1, 25, 96),
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(25000000, P_GPLL0_OUT_EVEN, 12, 0, 0),
+	F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0),
+	F(250000000, P_GPLL4_OUT_EVEN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_emac_clk_src = {
+	.cmd_rcgr = 0x47020,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_5,
+	.freq_tbl = ftbl_gcc_emac_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_emac_clk_src",
+		.parent_data = gcc_parents_5,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_emac_ptp_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0),
+	F(230400000, P_GPLL5_OUT_MAIN, 3.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_emac_ptp_clk_src = {
+	.cmd_rcgr = 0x47038,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_2,
+	.freq_tbl = ftbl_gcc_emac_ptp_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_emac_ptp_clk_src",
+		.parent_data = gcc_parents_2,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_gp1_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(25000000, P_GPLL0_OUT_EVEN, 12, 0, 0),
+	F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0),
+	F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0),
+	F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_gp1_clk_src = {
+	.cmd_rcgr = 0x2b004,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_3,
+	.freq_tbl = ftbl_gcc_gp1_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_gp1_clk_src",
+		.parent_data = gcc_parents_3,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_gp2_clk_src = {
+	.cmd_rcgr = 0x2c004,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_3,
+	.freq_tbl = ftbl_gcc_gp1_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_gp2_clk_src",
+		.parent_data = gcc_parents_3,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_gp3_clk_src = {
+	.cmd_rcgr = 0x2d004,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_3,
+	.freq_tbl = ftbl_gcc_gp1_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_gp3_clk_src",
+		.parent_data = gcc_parents_3,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_pcie_aux_phy_clk_src = {
+	.cmd_rcgr = 0x37034,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_4,
+	.freq_tbl = ftbl_gcc_cpuss_rbcpr_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_pcie_aux_phy_clk_src",
+		.parent_data = gcc_parents_4,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_pcie_rchng_phy_clk_src[] = {
+	F(100000000, P_GPLL0_OUT_EVEN, 3, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_pcie_rchng_phy_clk_src = {
+	.cmd_rcgr = 0x37050,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_3,
+	.freq_tbl = ftbl_gcc_pcie_rchng_phy_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_pcie_rchng_phy_clk_src",
+		.parent_data = gcc_parents_3,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_pdm2_clk_src[] = {
+	F(9600000, P_BI_TCXO, 2, 0, 0),
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(60000000, P_GPLL0_OUT_MAIN, 10, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_pdm2_clk_src = {
+	.cmd_rcgr = 0x19010,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_pdm2_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_pdm2_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gcc_sdcc1_apps_clk_src = {
+	.cmd_rcgr = 0xf00c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_gp1_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_sdcc1_apps_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb30_master_clk_src[] = {
+	F(200000000, P_GPLL0_OUT_EVEN, 1.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_usb30_master_clk_src = {
+	.cmd_rcgr = 0xb024,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_usb30_master_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_usb30_master_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb30_mock_utmi_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_usb30_mock_utmi_clk_src = {
+	.cmd_rcgr = 0xb03c,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_0,
+	.freq_tbl = ftbl_gcc_usb30_mock_utmi_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_usb30_mock_utmi_clk_src",
+		.parent_data = gcc_parents_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb3_phy_aux_clk_src[] = {
+	F(1000000, P_BI_TCXO, 1, 5, 96),
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gcc_usb3_phy_aux_clk_src = {
+	.cmd_rcgr = 0xb064,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_parent_map_4,
+	.freq_tbl = ftbl_gcc_usb3_phy_aux_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gcc_usb3_phy_aux_clk_src",
+		.parent_data = gcc_parents_4,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gcc_ahb_pcie_link_clk = {
+	.halt_reg = 0x22004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x22004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ahb_pcie_link_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_ahb_clk = {
+	.halt_reg = 0x10004,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x6d008,
+		.enable_mask = BIT(14),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup1_i2c_apps_clk = {
+	.halt_reg = 0x11008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x11008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup1_i2c_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_qup1_i2c_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup1_spi_apps_clk = {
+	.halt_reg = 0x11004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x11004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup1_spi_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_qup1_spi_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup2_i2c_apps_clk = {
+	.halt_reg = 0x13008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x13008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup2_i2c_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_qup2_i2c_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup2_spi_apps_clk = {
+	.halt_reg = 0x13004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x13004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup2_spi_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_qup2_spi_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup3_i2c_apps_clk = {
+	.halt_reg = 0x15008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x15008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup3_i2c_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_qup3_i2c_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup3_spi_apps_clk = {
+	.halt_reg = 0x15004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x15004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup3_spi_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_qup3_spi_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup4_i2c_apps_clk = {
+	.halt_reg = 0x17008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x17008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup4_i2c_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_qup4_i2c_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup4_spi_apps_clk = {
+	.halt_reg = 0x17004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x17004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup4_spi_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_qup4_spi_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart1_apps_clk = {
+	.halt_reg = 0x12004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x12004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart1_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_uart1_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart2_apps_clk = {
+	.halt_reg = 0x14004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x14004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart2_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_uart2_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart3_apps_clk = {
+	.halt_reg = 0x16004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x16004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart3_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_uart3_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart4_apps_clk = {
+	.halt_reg = 0x18004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x18004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart4_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_blsp1_uart4_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_boot_rom_ahb_clk = {
+	.halt_reg = 0x1c004,
+	.halt_check = BRANCH_HALT_VOTED,
+	.hwcg_reg = 0x1c004,
+	.hwcg_bit = 1,
+	.clkr = {
+		.enable_reg = 0x6d008,
+		.enable_mask = BIT(10),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_boot_rom_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce1_ahb_clk = {
+	.halt_reg = 0x2100c,
+	.halt_check = BRANCH_HALT_VOTED,
+	.hwcg_reg = 0x2100c,
+	.hwcg_bit = 1,
+	.clkr = {
+		.enable_reg = 0x6d008,
+		.enable_mask = BIT(3),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce1_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce1_axi_clk = {
+	.halt_reg = 0x21008,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x6d008,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce1_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce1_clk = {
+	.halt_reg = 0x21004,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x6d008,
+		.enable_mask = BIT(5),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce1_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_cpuss_rbcpr_clk = {
+	.halt_reg = 0x24008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x24008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_cpuss_rbcpr_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_cpuss_rbcpr_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_eth_axi_clk = {
+	.halt_reg = 0x4701c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x4701c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_eth_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_eth_ptp_clk = {
+	.halt_reg = 0x47018,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x47018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_eth_ptp_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_emac_ptp_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_eth_rgmii_clk = {
+	.halt_reg = 0x47010,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x47010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_eth_rgmii_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_emac_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_eth_slave_ahb_clk = {
+	.halt_reg = 0x47014,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x47014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_eth_slave_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp1_clk = {
+	.halt_reg = 0x2b000,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2b000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp1_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_gp1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp2_clk = {
+	.halt_reg = 0x2c000,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2c000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp2_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_gp2_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp3_clk = {
+	.halt_reg = 0x2d000,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2d000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp3_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_gp3_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_0_clkref_clk = {
+	.halt_reg = 0x88004,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x88004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_0_clkref_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_aux_clk = {
+	.halt_reg = 0x37024,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x6d010,
+		.enable_mask = BIT(3),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_aux_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_cfg_ahb_clk = {
+	.halt_reg = 0x3701c,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x6d010,
+		.enable_mask = BIT(2),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_cfg_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_mstr_axi_clk = {
+	.halt_reg = 0x37018,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x6d010,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_mstr_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_pipe_clk = {
+	.halt_reg = 0x3702c,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x6d010,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_pipe_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_rchng_phy_clk = {
+	.halt_reg = 0x37020,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x6d010,
+		.enable_mask = BIT(7),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_rchng_phy_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_pcie_rchng_phy_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_sleep_clk = {
+	.halt_reg = 0x37028,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x6d010,
+		.enable_mask = BIT(6),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_sleep_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_pcie_aux_phy_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_slv_axi_clk = {
+	.halt_reg = 0x37014,
+	.halt_check = BRANCH_HALT_VOTED,
+	.hwcg_reg = 0x37014,
+	.hwcg_bit = 1,
+	.clkr = {
+		.enable_reg = 0x6d010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_slv_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_slv_q2a_axi_clk = {
+	.halt_reg = 0x37010,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x6d010,
+		.enable_mask = BIT(5),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_slv_q2a_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pdm2_clk = {
+	.halt_reg = 0x1900c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x1900c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pdm2_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_pdm2_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pdm_ahb_clk = {
+	.halt_reg = 0x19004,
+	.halt_check = BRANCH_HALT,
+	.hwcg_reg = 0x19004,
+	.hwcg_bit = 1,
+	.clkr = {
+		.enable_reg = 0x19004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pdm_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pdm_xo4_clk = {
+	.halt_reg = 0x19008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x19008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pdm_xo4_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_ahb_clk = {
+	.halt_reg = 0xf008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xf008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_apps_clk = {
+	.halt_reg = 0xf004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xf004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_sdcc1_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb30_master_clk = {
+	.halt_reg = 0xb010,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb30_master_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_usb30_master_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb30_mock_utmi_clk = {
+	.halt_reg = 0xb020,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb020,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb30_mock_utmi_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_usb30_mock_utmi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb30_mstr_axi_clk = {
+	.halt_reg = 0xb014,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb30_mstr_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb30_sleep_clk = {
+	.halt_reg = 0xb01c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb01c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb30_sleep_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb30_slv_ahb_clk = {
+	.halt_reg = 0xb018,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb30_slv_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb3_phy_aux_clk = {
+	.halt_reg = 0xb058,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xb058,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb3_phy_aux_clk",
+			.parent_hws = (const struct clk_hw *[]){
+				&gcc_usb3_phy_aux_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb3_phy_pipe_clk = {
+	.halt_reg = 0xb05c,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0xb05c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb3_phy_pipe_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb3_prim_clkref_clk = {
+	.halt_reg = 0x88000,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x88000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb3_prim_clkref_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb_phy_cfg_ahb2phy_clk = {
+	.halt_reg = 0xe004,
+	.halt_check = BRANCH_HALT,
+	.hwcg_reg = 0xe004,
+	.hwcg_bit = 1,
+	.clkr = {
+		.enable_reg = 0xe004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb_phy_cfg_ahb2phy_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_xo_pcie_link_clk = {
+	.halt_reg = 0x22008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x22008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_xo_pcie_link_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct gdsc usb30_gdsc = {
+	.gdscr = 0x0b004,
+	.pd = {
+		.name = "usb30_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc pcie_gdsc = {
+	.gdscr = 0x37004,
+	.pd = {
+		.name = "pcie_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc emac_gdsc = {
+	.gdscr = 0x47004,
+	.pd = {
+		.name = "emac_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct clk_regmap *gcc_sdx55_clocks[] = {
+	[GCC_AHB_PCIE_LINK_CLK] = &gcc_ahb_pcie_link_clk.clkr,
+	[GCC_BLSP1_AHB_CLK] = &gcc_blsp1_ahb_clk.clkr,
+	[GCC_BLSP1_QUP1_I2C_APPS_CLK] = &gcc_blsp1_qup1_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP1_I2C_APPS_CLK_SRC] =
+		&gcc_blsp1_qup1_i2c_apps_clk_src.clkr,
+	[GCC_BLSP1_QUP1_SPI_APPS_CLK] = &gcc_blsp1_qup1_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP1_SPI_APPS_CLK_SRC] =
+		&gcc_blsp1_qup1_spi_apps_clk_src.clkr,
+	[GCC_BLSP1_QUP2_I2C_APPS_CLK] = &gcc_blsp1_qup2_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP2_I2C_APPS_CLK_SRC] =
+		&gcc_blsp1_qup2_i2c_apps_clk_src.clkr,
+	[GCC_BLSP1_QUP2_SPI_APPS_CLK] = &gcc_blsp1_qup2_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP2_SPI_APPS_CLK_SRC] =
+		&gcc_blsp1_qup2_spi_apps_clk_src.clkr,
+	[GCC_BLSP1_QUP3_I2C_APPS_CLK] = &gcc_blsp1_qup3_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP3_I2C_APPS_CLK_SRC] =
+		&gcc_blsp1_qup3_i2c_apps_clk_src.clkr,
+	[GCC_BLSP1_QUP3_SPI_APPS_CLK] = &gcc_blsp1_qup3_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP3_SPI_APPS_CLK_SRC] =
+		&gcc_blsp1_qup3_spi_apps_clk_src.clkr,
+	[GCC_BLSP1_QUP4_I2C_APPS_CLK] = &gcc_blsp1_qup4_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP4_I2C_APPS_CLK_SRC] =
+		&gcc_blsp1_qup4_i2c_apps_clk_src.clkr,
+	[GCC_BLSP1_QUP4_SPI_APPS_CLK] = &gcc_blsp1_qup4_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP4_SPI_APPS_CLK_SRC] =
+		&gcc_blsp1_qup4_spi_apps_clk_src.clkr,
+	[GCC_BLSP1_UART1_APPS_CLK] = &gcc_blsp1_uart1_apps_clk.clkr,
+	[GCC_BLSP1_UART1_APPS_CLK_SRC] = &gcc_blsp1_uart1_apps_clk_src.clkr,
+	[GCC_BLSP1_UART2_APPS_CLK] = &gcc_blsp1_uart2_apps_clk.clkr,
+	[GCC_BLSP1_UART2_APPS_CLK_SRC] = &gcc_blsp1_uart2_apps_clk_src.clkr,
+	[GCC_BLSP1_UART3_APPS_CLK] = &gcc_blsp1_uart3_apps_clk.clkr,
+	[GCC_BLSP1_UART3_APPS_CLK_SRC] = &gcc_blsp1_uart3_apps_clk_src.clkr,
+	[GCC_BLSP1_UART4_APPS_CLK] = &gcc_blsp1_uart4_apps_clk.clkr,
+	[GCC_BLSP1_UART4_APPS_CLK_SRC] = &gcc_blsp1_uart4_apps_clk_src.clkr,
+	[GCC_BOOT_ROM_AHB_CLK] = &gcc_boot_rom_ahb_clk.clkr,
+	[GCC_CE1_AHB_CLK] = &gcc_ce1_ahb_clk.clkr,
+	[GCC_CE1_AXI_CLK] = &gcc_ce1_axi_clk.clkr,
+	[GCC_CE1_CLK] = &gcc_ce1_clk.clkr,
+	[GCC_CPUSS_AHB_CLK_SRC] = &gcc_cpuss_ahb_clk_src.clkr,
+	[GCC_CPUSS_RBCPR_CLK] = &gcc_cpuss_rbcpr_clk.clkr,
+	[GCC_CPUSS_RBCPR_CLK_SRC] = &gcc_cpuss_rbcpr_clk_src.clkr,
+	[GCC_EMAC_CLK_SRC] = &gcc_emac_clk_src.clkr,
+	[GCC_EMAC_PTP_CLK_SRC] = &gcc_emac_ptp_clk_src.clkr,
+	[GCC_ETH_AXI_CLK] = &gcc_eth_axi_clk.clkr,
+	[GCC_ETH_PTP_CLK] = &gcc_eth_ptp_clk.clkr,
+	[GCC_ETH_RGMII_CLK] = &gcc_eth_rgmii_clk.clkr,
+	[GCC_ETH_SLAVE_AHB_CLK] = &gcc_eth_slave_ahb_clk.clkr,
+	[GCC_GP1_CLK] = &gcc_gp1_clk.clkr,
+	[GCC_GP1_CLK_SRC] = &gcc_gp1_clk_src.clkr,
+	[GCC_GP2_CLK] = &gcc_gp2_clk.clkr,
+	[GCC_GP2_CLK_SRC] = &gcc_gp2_clk_src.clkr,
+	[GCC_GP3_CLK] = &gcc_gp3_clk.clkr,
+	[GCC_GP3_CLK_SRC] = &gcc_gp3_clk_src.clkr,
+	[GCC_PCIE_0_CLKREF_CLK] = &gcc_pcie_0_clkref_clk.clkr,
+	[GCC_PCIE_AUX_CLK] = &gcc_pcie_aux_clk.clkr,
+	[GCC_PCIE_AUX_PHY_CLK_SRC] = &gcc_pcie_aux_phy_clk_src.clkr,
+	[GCC_PCIE_CFG_AHB_CLK] = &gcc_pcie_cfg_ahb_clk.clkr,
+	[GCC_PCIE_MSTR_AXI_CLK] = &gcc_pcie_mstr_axi_clk.clkr,
+	[GCC_PCIE_PIPE_CLK] = &gcc_pcie_pipe_clk.clkr,
+	[GCC_PCIE_RCHNG_PHY_CLK] = &gcc_pcie_rchng_phy_clk.clkr,
+	[GCC_PCIE_RCHNG_PHY_CLK_SRC] = &gcc_pcie_rchng_phy_clk_src.clkr,
+	[GCC_PCIE_SLEEP_CLK] = &gcc_pcie_sleep_clk.clkr,
+	[GCC_PCIE_SLV_AXI_CLK] = &gcc_pcie_slv_axi_clk.clkr,
+	[GCC_PCIE_SLV_Q2A_AXI_CLK] = &gcc_pcie_slv_q2a_axi_clk.clkr,
+	[GCC_PDM2_CLK] = &gcc_pdm2_clk.clkr,
+	[GCC_PDM2_CLK_SRC] = &gcc_pdm2_clk_src.clkr,
+	[GCC_PDM_AHB_CLK] = &gcc_pdm_ahb_clk.clkr,
+	[GCC_PDM_XO4_CLK] = &gcc_pdm_xo4_clk.clkr,
+	[GCC_SDCC1_AHB_CLK] = &gcc_sdcc1_ahb_clk.clkr,
+	[GCC_SDCC1_APPS_CLK] = &gcc_sdcc1_apps_clk.clkr,
+	[GCC_SDCC1_APPS_CLK_SRC] = &gcc_sdcc1_apps_clk_src.clkr,
+	[GCC_USB30_MASTER_CLK] = &gcc_usb30_master_clk.clkr,
+	[GCC_USB30_MASTER_CLK_SRC] = &gcc_usb30_master_clk_src.clkr,
+	[GCC_USB30_MOCK_UTMI_CLK] = &gcc_usb30_mock_utmi_clk.clkr,
+	[GCC_USB30_MOCK_UTMI_CLK_SRC] = &gcc_usb30_mock_utmi_clk_src.clkr,
+	[GCC_USB30_MSTR_AXI_CLK] = &gcc_usb30_mstr_axi_clk.clkr,
+	[GCC_USB30_SLEEP_CLK] = &gcc_usb30_sleep_clk.clkr,
+	[GCC_USB30_SLV_AHB_CLK] = &gcc_usb30_slv_ahb_clk.clkr,
+	[GCC_USB3_PHY_AUX_CLK] = &gcc_usb3_phy_aux_clk.clkr,
+	[GCC_USB3_PHY_AUX_CLK_SRC] = &gcc_usb3_phy_aux_clk_src.clkr,
+	[GCC_USB3_PHY_PIPE_CLK] = &gcc_usb3_phy_pipe_clk.clkr,
+	[GCC_USB3_PRIM_CLKREF_CLK] = &gcc_usb3_prim_clkref_clk.clkr,
+	[GCC_USB_PHY_CFG_AHB2PHY_CLK] = &gcc_usb_phy_cfg_ahb2phy_clk.clkr,
+	[GCC_XO_PCIE_LINK_CLK] = &gcc_xo_pcie_link_clk.clkr,
+	[GPLL0] = &gpll0.clkr,
+	[GPLL0_OUT_EVEN] = &gpll0_out_even.clkr,
+	[GPLL4] = &gpll4.clkr,
+	[GPLL4_OUT_EVEN] = &gpll4_out_even.clkr,
+	[GPLL5] = &gpll5.clkr,
+};
+
+static const struct qcom_reset_map gcc_sdx55_resets[] = {
+	[GCC_EMAC_BCR] = { 0x47000 },
+	[GCC_PCIE_BCR] = { 0x37000 },
+	[GCC_PCIE_LINK_DOWN_BCR] = { 0x77000 },
+	[GCC_PCIE_PHY_BCR] = { 0x39000 },
+	[GCC_PCIE_PHY_COM_BCR] = { 0x78004 },
+	[GCC_QUSB2PHY_BCR] = { 0xd000 },
+	[GCC_USB30_BCR] = { 0xb000 },
+	[GCC_USB3_PHY_BCR] = { 0xc000 },
+	[GCC_USB3PHY_PHY_BCR] = { 0xc004 },
+	[GCC_USB_PHY_CFG_AHB2PHY_BCR] = { 0xe000 },
+};
+
+static struct gdsc *gcc_sdx55_gdscs[] = {
+	[USB30_GDSC] = &usb30_gdsc,
+	[PCIE_GDSC] = &pcie_gdsc,
+	[EMAC_GDSC] = &emac_gdsc,
+};
+
+static const struct regmap_config gcc_sdx55_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x9b040,
+	.fast_io	= true,
+};
+
+static const struct qcom_cc_desc gcc_sdx55_desc = {
+	.config = &gcc_sdx55_regmap_config,
+	.clks = gcc_sdx55_clocks,
+	.num_clks = ARRAY_SIZE(gcc_sdx55_clocks),
+	.resets = gcc_sdx55_resets,
+	.num_resets = ARRAY_SIZE(gcc_sdx55_resets),
+	.gdscs = gcc_sdx55_gdscs,
+	.num_gdscs = ARRAY_SIZE(gcc_sdx55_gdscs),
+};
+
+static const struct of_device_id gcc_sdx55_match_table[] = {
+	{ .compatible = "qcom,gcc-sdx55" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, gcc_sdx55_match_table);
+
+static int gcc_sdx55_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+
+	regmap = qcom_cc_map(pdev, &gcc_sdx55_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	/*
+	 * Keep the clocks always-ON as they are critical to the functioning
+	 * of the system:
+	 * GCC_SYS_NOC_CPUSS_AHB_CLK, GCC_CPUSS_AHB_CLK, GCC_CPUSS_GNOC_CLK
+	 */
+	regmap_update_bits(regmap, 0x6d008, BIT(0), BIT(0));
+	regmap_update_bits(regmap, 0x6d008, BIT(21), BIT(21));
+	regmap_update_bits(regmap, 0x6d008, BIT(22), BIT(22));
+
+	return qcom_cc_really_probe(pdev, &gcc_sdx55_desc, regmap);
+}
+
+static struct platform_driver gcc_sdx55_driver = {
+	.probe = gcc_sdx55_probe,
+	.driver = {
+		.name = "gcc-sdx55",
+		.of_match_table = gcc_sdx55_match_table,
+	},
+};
+
+static int __init gcc_sdx55_init(void)
+{
+	return platform_driver_register(&gcc_sdx55_driver);
+}
+subsys_initcall(gcc_sdx55_init);
+
+static void __exit gcc_sdx55_exit(void)
+{
+	platform_driver_unregister(&gcc_sdx55_driver);
+}
+module_exit(gcc_sdx55_exit);
+
+MODULE_DESCRIPTION("QTI GCC SDX55 Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/lpass-gfm-sm8250.c b/drivers/clk/qcom/lpass-gfm-sm8250.c
new file mode 100644
index 000000000000..d366c7c2abc7
--- /dev/null
+++ b/drivers/clk/qcom/lpass-gfm-sm8250.c
@@ -0,0 +1,320 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * LPASS Audio CC and Always ON CC Glitch Free Mux clock driver
+ *
+ * Copyright (c) 2020 Linaro Ltd.
+ * Author: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/clk-provider.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/pm_clock.h>
+#include <linux/pm_runtime.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/of_device.h>
+#include <dt-bindings/clock/qcom,sm8250-lpass-audiocc.h>
+#include <dt-bindings/clock/qcom,sm8250-lpass-aoncc.h>
+
+struct lpass_gfm {
+	struct device *dev;
+	void __iomem *base;
+};
+
+struct clk_gfm {
+	unsigned int mux_reg;
+	unsigned int mux_mask;
+	struct clk_hw	hw;
+	struct lpass_gfm *priv;
+	void __iomem *gfm_mux;
+};
+
+#define GFM_MASK	BIT(1)
+#define to_clk_gfm(_hw) container_of(_hw, struct clk_gfm, hw)
+
+static u8 clk_gfm_get_parent(struct clk_hw *hw)
+{
+	struct clk_gfm *clk = to_clk_gfm(hw);
+
+	return readl(clk->gfm_mux) & GFM_MASK;
+}
+
+static int clk_gfm_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_gfm *clk = to_clk_gfm(hw);
+	unsigned int val;
+
+	val = readl(clk->gfm_mux);
+
+	if (index)
+		val |= GFM_MASK;
+	else
+		val &= ~GFM_MASK;
+
+	writel(val, clk->gfm_mux);
+
+	return 0;
+}
+
+static const struct clk_ops clk_gfm_ops = {
+	.get_parent = clk_gfm_get_parent,
+	.set_parent = clk_gfm_set_parent,
+	.determine_rate = __clk_mux_determine_rate,
+};
+
+static struct clk_gfm lpass_gfm_va_mclk = {
+	.mux_reg = 0x20000,
+	.mux_mask = BIT(0),
+	.hw.init = &(struct clk_init_data) {
+		.name = "VA_MCLK",
+		.ops = &clk_gfm_ops,
+		.flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
+		.num_parents = 2,
+		.parent_data = (const struct clk_parent_data[]){
+			{
+				.index = 0,
+				.fw_name = "LPASS_CLK_ID_TX_CORE_MCLK",
+			}, {
+				.index = 1,
+				.fw_name = "LPASS_CLK_ID_VA_CORE_MCLK",
+			},
+		},
+	},
+};
+
+static struct clk_gfm lpass_gfm_tx_npl = {
+	.mux_reg = 0x20000,
+	.mux_mask = BIT(0),
+	.hw.init = &(struct clk_init_data) {
+		.name = "TX_NPL",
+		.ops = &clk_gfm_ops,
+		.flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
+		.parent_data = (const struct clk_parent_data[]){
+			{
+				.index = 0,
+				.fw_name = "LPASS_CLK_ID_TX_CORE_NPL_MCLK",
+			}, {
+				.index = 1,
+				.fw_name = "LPASS_CLK_ID_VA_CORE_2X_MCLK",
+			},
+		},
+		.num_parents = 2,
+	},
+};
+
+static struct clk_gfm lpass_gfm_wsa_mclk = {
+	.mux_reg = 0x220d8,
+	.mux_mask = BIT(0),
+	.hw.init = &(struct clk_init_data) {
+		.name = "WSA_MCLK",
+		.ops = &clk_gfm_ops,
+		.flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
+		.parent_data = (const struct clk_parent_data[]){
+			{
+				.index = 0,
+				.fw_name = "LPASS_CLK_ID_TX_CORE_MCLK",
+			}, {
+				.index = 1,
+				.fw_name = "LPASS_CLK_ID_WSA_CORE_MCLK",
+			},
+		},
+		.num_parents = 2,
+	},
+};
+
+static struct clk_gfm lpass_gfm_wsa_npl = {
+	.mux_reg = 0x220d8,
+	.mux_mask = BIT(0),
+	.hw.init = &(struct clk_init_data) {
+		.name = "WSA_NPL",
+		.ops = &clk_gfm_ops,
+		.flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
+		.parent_data = (const struct clk_parent_data[]){
+			{
+				.index = 0,
+				.fw_name = "LPASS_CLK_ID_TX_CORE_NPL_MCLK",
+			}, {
+				.index = 1,
+				.fw_name = "LPASS_CLK_ID_WSA_CORE_NPL_MCLK",
+			},
+		},
+		.num_parents = 2,
+	},
+};
+
+static struct clk_gfm lpass_gfm_rx_mclk_mclk2 = {
+	.mux_reg = 0x240d8,
+	.mux_mask = BIT(0),
+	.hw.init = &(struct clk_init_data) {
+		.name = "RX_MCLK_MCLK2",
+		.ops = &clk_gfm_ops,
+		.flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
+		.parent_data = (const struct clk_parent_data[]){
+			{
+				.index = 0,
+				.fw_name = "LPASS_CLK_ID_TX_CORE_MCLK",
+			}, {
+				.index = 1,
+				.fw_name = "LPASS_CLK_ID_RX_CORE_MCLK",
+			},
+		},
+		.num_parents = 2,
+	},
+};
+
+static struct clk_gfm lpass_gfm_rx_npl = {
+	.mux_reg = 0x240d8,
+	.mux_mask = BIT(0),
+	.hw.init = &(struct clk_init_data) {
+		.name = "RX_NPL",
+		.ops = &clk_gfm_ops,
+		.flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
+		.parent_data = (const struct clk_parent_data[]){
+			{
+				.index = 0,
+				.fw_name = "LPASS_CLK_ID_TX_CORE_NPL_MCLK",
+			}, {
+				.index = 1,
+				.fw_name = "LPASS_CLK_ID_RX_CORE_NPL_MCLK",
+			},
+		},
+		.num_parents = 2,
+	},
+};
+
+static struct clk_gfm *aoncc_gfm_clks[] = {
+	[LPASS_CDC_VA_MCLK]		= &lpass_gfm_va_mclk,
+	[LPASS_CDC_TX_NPL]		= &lpass_gfm_tx_npl,
+};
+
+static struct clk_hw_onecell_data aoncc_hw_onecell_data = {
+	.hws = {
+		[LPASS_CDC_VA_MCLK]	= &lpass_gfm_va_mclk.hw,
+		[LPASS_CDC_TX_NPL]	= &lpass_gfm_tx_npl.hw,
+	},
+	.num = ARRAY_SIZE(aoncc_gfm_clks),
+};
+
+static struct clk_gfm *audiocc_gfm_clks[] = {
+	[LPASS_CDC_WSA_NPL]		= &lpass_gfm_wsa_npl,
+	[LPASS_CDC_WSA_MCLK]		= &lpass_gfm_wsa_mclk,
+	[LPASS_CDC_RX_NPL]		= &lpass_gfm_rx_npl,
+	[LPASS_CDC_RX_MCLK_MCLK2]	= &lpass_gfm_rx_mclk_mclk2,
+};
+
+static struct clk_hw_onecell_data audiocc_hw_onecell_data = {
+	.hws = {
+		[LPASS_CDC_WSA_NPL]	= &lpass_gfm_wsa_npl.hw,
+		[LPASS_CDC_WSA_MCLK]	= &lpass_gfm_wsa_mclk.hw,
+		[LPASS_CDC_RX_NPL]	= &lpass_gfm_rx_npl.hw,
+		[LPASS_CDC_RX_MCLK_MCLK2] = &lpass_gfm_rx_mclk_mclk2.hw,
+	},
+	.num = ARRAY_SIZE(audiocc_gfm_clks),
+};
+
+struct lpass_gfm_data {
+	struct clk_hw_onecell_data *onecell_data;
+	struct clk_gfm **gfm_clks;
+};
+
+static struct lpass_gfm_data audiocc_data = {
+	.onecell_data = &audiocc_hw_onecell_data,
+	.gfm_clks = audiocc_gfm_clks,
+};
+
+static struct lpass_gfm_data aoncc_data = {
+	.onecell_data = &aoncc_hw_onecell_data,
+	.gfm_clks = aoncc_gfm_clks,
+};
+
+static int lpass_gfm_clk_driver_probe(struct platform_device *pdev)
+{
+	const struct lpass_gfm_data *data;
+	struct device *dev = &pdev->dev;
+	struct clk_gfm *gfm;
+	struct lpass_gfm *cc;
+	int err, i;
+
+	data = of_device_get_match_data(dev);
+	if (!data)
+		return -EINVAL;
+
+	cc = devm_kzalloc(dev, sizeof(*cc), GFP_KERNEL);
+	if (!cc)
+		return -ENOMEM;
+
+	cc->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(cc->base))
+		return PTR_ERR(cc->base);
+
+	pm_runtime_enable(dev);
+	err = pm_clk_create(dev);
+	if (err)
+		goto pm_clk_err;
+
+	err = of_pm_clk_add_clks(dev);
+	if (err < 0) {
+		dev_dbg(dev, "Failed to get lpass core voting clocks\n");
+		goto clk_reg_err;
+	}
+
+	for (i = 0; i < data->onecell_data->num; i++) {
+		if (!data->gfm_clks[i])
+			continue;
+
+		gfm = data->gfm_clks[i];
+		gfm->priv = cc;
+		gfm->gfm_mux = cc->base;
+		gfm->gfm_mux = gfm->gfm_mux + data->gfm_clks[i]->mux_reg;
+
+		err = devm_clk_hw_register(dev, &data->gfm_clks[i]->hw);
+		if (err)
+			goto clk_reg_err;
+
+	}
+
+	err = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get,
+					  data->onecell_data);
+	if (err)
+		goto clk_reg_err;
+
+	return 0;
+
+clk_reg_err:
+	pm_clk_destroy(dev);
+pm_clk_err:
+	pm_runtime_disable(dev);
+	return err;
+}
+
+static const struct of_device_id lpass_gfm_clk_match_table[] = {
+	{
+		.compatible = "qcom,sm8250-lpass-aoncc",
+		.data = &aoncc_data,
+	},
+	{
+		.compatible = "qcom,sm8250-lpass-audiocc",
+		.data = &audiocc_data,
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lpass_gfm_clk_match_table);
+
+static const struct dev_pm_ops lpass_gfm_pm_ops = {
+	SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL)
+};
+
+static struct platform_driver lpass_gfm_clk_driver = {
+	.probe		= lpass_gfm_clk_driver_probe,
+	.driver		= {
+		.name	= "lpass-gfm-clk",
+		.of_match_table = lpass_gfm_clk_match_table,
+		.pm = &lpass_gfm_pm_ops,
+	},
+};
+module_platform_driver(lpass_gfm_clk_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/lpasscorecc-sc7180.c b/drivers/clk/qcom/lpasscorecc-sc7180.c
index 228d08f5d26f..2e0ecc38efdd 100644
--- a/drivers/clk/qcom/lpasscorecc-sc7180.c
+++ b/drivers/clk/qcom/lpasscorecc-sc7180.c
@@ -356,12 +356,52 @@ static const struct qcom_cc_desc lpass_audio_hm_sc7180_desc = {
 	.num_gdscs = ARRAY_SIZE(lpass_audio_hm_sc7180_gdscs),
 };
 
+static void lpass_pm_runtime_disable(void *data)
+{
+	pm_runtime_disable(data);
+}
+
+static void lpass_pm_clk_destroy(void *data)
+{
+	pm_clk_destroy(data);
+}
+
+static int lpass_create_pm_clks(struct platform_device *pdev)
+{
+	int ret;
+
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, 500);
+	pm_runtime_enable(&pdev->dev);
+
+	ret = devm_add_action_or_reset(&pdev->dev, lpass_pm_runtime_disable, &pdev->dev);
+	if (ret)
+		return ret;
+
+	ret = pm_clk_create(&pdev->dev);
+	if (ret)
+		return ret;
+	ret = devm_add_action_or_reset(&pdev->dev, lpass_pm_clk_destroy, &pdev->dev);
+	if (ret)
+		return ret;
+
+	ret = pm_clk_add(&pdev->dev, "iface");
+	if (ret < 0)
+		dev_err(&pdev->dev, "failed to acquire iface clock\n");
+
+	return ret;
+}
+
 static int lpass_core_cc_sc7180_probe(struct platform_device *pdev)
 {
 	const struct qcom_cc_desc *desc;
 	struct regmap *regmap;
 	int ret;
 
+	ret = lpass_create_pm_clks(pdev);
+	if (ret)
+		return ret;
+
 	lpass_core_cc_sc7180_regmap_config.name = "lpass_audio_cc";
 	desc = &lpass_audio_hm_sc7180_desc;
 	ret = qcom_cc_probe_by_index(pdev, 1, desc);
@@ -386,12 +426,22 @@ static int lpass_core_cc_sc7180_probe(struct platform_device *pdev)
 	clk_fabia_pll_configure(&lpass_lpaaudio_dig_pll, regmap,
 				&lpass_lpaaudio_dig_pll_config);
 
-	return qcom_cc_really_probe(pdev, &lpass_core_cc_sc7180_desc, regmap);
+	ret = qcom_cc_really_probe(pdev, &lpass_core_cc_sc7180_desc, regmap);
+
+	pm_runtime_mark_last_busy(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
+
+	return ret;
 }
 
 static int lpass_hm_core_probe(struct platform_device *pdev)
 {
 	const struct qcom_cc_desc *desc;
+	int ret;
+
+	ret = lpass_create_pm_clks(pdev);
+	if (ret)
+		return ret;
 
 	lpass_core_cc_sc7180_regmap_config.name = "lpass_hm_core";
 	desc = &lpass_core_hm_sc7180_desc;
@@ -399,61 +449,28 @@ static int lpass_hm_core_probe(struct platform_device *pdev)
 	return qcom_cc_probe_by_index(pdev, 0, desc);
 }
 
-static const struct of_device_id lpass_core_cc_sc7180_match_table[] = {
+static const struct of_device_id lpass_hm_sc7180_match_table[] = {
 	{
 		.compatible = "qcom,sc7180-lpasshm",
-		.data = lpass_hm_core_probe,
 	},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lpass_hm_sc7180_match_table);
+
+static const struct of_device_id lpass_core_cc_sc7180_match_table[] = {
 	{
 		.compatible = "qcom,sc7180-lpasscorecc",
-		.data = lpass_core_cc_sc7180_probe,
 	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, lpass_core_cc_sc7180_match_table);
 
-static int lpass_core_sc7180_probe(struct platform_device *pdev)
-{
-	int (*clk_probe)(struct platform_device *p);
-	int ret;
-
-	pm_runtime_enable(&pdev->dev);
-	ret = pm_clk_create(&pdev->dev);
-	if (ret)
-		goto disable_pm_runtime;
-
-	ret = pm_clk_add(&pdev->dev, "iface");
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to acquire iface clock\n");
-		goto destroy_pm_clk;
-	}
-
-	ret = -EINVAL;
-	clk_probe = of_device_get_match_data(&pdev->dev);
-	if (!clk_probe)
-		goto destroy_pm_clk;
-
-	ret = clk_probe(pdev);
-	if (ret)
-		goto destroy_pm_clk;
-
-	return 0;
-
-destroy_pm_clk:
-	pm_clk_destroy(&pdev->dev);
-
-disable_pm_runtime:
-	pm_runtime_disable(&pdev->dev);
-
-	return ret;
-}
-
 static const struct dev_pm_ops lpass_core_cc_pm_ops = {
 	SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL)
 };
 
 static struct platform_driver lpass_core_cc_sc7180_driver = {
-	.probe = lpass_core_sc7180_probe,
+	.probe = lpass_core_cc_sc7180_probe,
 	.driver = {
 		.name = "lpass_core_cc-sc7180",
 		.of_match_table = lpass_core_cc_sc7180_match_table,
@@ -461,17 +478,43 @@ static struct platform_driver lpass_core_cc_sc7180_driver = {
 	},
 };
 
-static int __init lpass_core_cc_sc7180_init(void)
+static const struct dev_pm_ops lpass_hm_pm_ops = {
+	SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL)
+};
+
+static struct platform_driver lpass_hm_sc7180_driver = {
+	.probe = lpass_hm_core_probe,
+	.driver = {
+		.name = "lpass_hm-sc7180",
+		.of_match_table = lpass_hm_sc7180_match_table,
+		.pm = &lpass_hm_pm_ops,
+	},
+};
+
+static int __init lpass_sc7180_init(void)
 {
-	return platform_driver_register(&lpass_core_cc_sc7180_driver);
+	int ret;
+
+	ret = platform_driver_register(&lpass_core_cc_sc7180_driver);
+	if (ret)
+		return ret;
+
+	ret = platform_driver_register(&lpass_hm_sc7180_driver);
+	if (ret) {
+		platform_driver_unregister(&lpass_core_cc_sc7180_driver);
+		return ret;
+	}
+
+	return 0;
 }
-subsys_initcall(lpass_core_cc_sc7180_init);
+subsys_initcall(lpass_sc7180_init);
 
-static void __exit lpass_core_cc_sc7180_exit(void)
+static void __exit lpass_sc7180_exit(void)
 {
+	platform_driver_unregister(&lpass_hm_sc7180_driver);
 	platform_driver_unregister(&lpass_core_cc_sc7180_driver);
 }
-module_exit(lpass_core_cc_sc7180_exit);
+module_exit(lpass_sc7180_exit);
 
 MODULE_DESCRIPTION("QTI LPASS_CORE_CC SC7180 Driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/renesas/clk-sh73a0.c b/drivers/clk/renesas/clk-sh73a0.c
index 5f25a70bc61c..4146c1d717b9 100644
--- a/drivers/clk/renesas/clk-sh73a0.c
+++ b/drivers/clk/renesas/clk-sh73a0.c
@@ -121,7 +121,7 @@ sh73a0_cpg_register_clock(struct device_node *np, struct sh73a0_cpg *cpg,
 			(phy_no ? CPG_DSI1PHYCR : CPG_DSI0PHYCR);
 
 		parent_name = phy_no ? "dsi1pck" : "dsi0pck";
-		mult = __raw_readl(dsi_reg);
+		mult = readl(dsi_reg);
 		if (!(mult & 0x8000))
 			mult = 1;
 		else
diff --git a/drivers/clk/renesas/r8a774a1-cpg-mssr.c b/drivers/clk/renesas/r8a774a1-cpg-mssr.c
index fd54b9f625da..4a43ebec7d5e 100644
--- a/drivers/clk/renesas/r8a774a1-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a774a1-cpg-mssr.c
@@ -41,6 +41,7 @@ enum clk_ids {
 	CLK_S2,
 	CLK_S3,
 	CLK_SDSRC,
+	CLK_RPCSRC,
 	CLK_RINT,
 
 	/* Module Clocks */
@@ -67,6 +68,12 @@ static const struct cpg_core_clk r8a774a1_core_clks[] __initconst = {
 	DEF_FIXED(".s2",        CLK_S2,            CLK_PLL1_DIV2,  4, 1),
 	DEF_FIXED(".s3",        CLK_S3,            CLK_PLL1_DIV2,  6, 1),
 	DEF_FIXED(".sdsrc",     CLK_SDSRC,         CLK_PLL1_DIV2,  2, 1),
+	DEF_BASE(".rpcsrc",     CLK_RPCSRC, CLK_TYPE_GEN3_RPCSRC, CLK_PLL1),
+
+	DEF_BASE("rpc",         R8A774A1_CLK_RPC, CLK_TYPE_GEN3_RPC,
+		 CLK_RPCSRC),
+	DEF_BASE("rpcd2",       R8A774A1_CLK_RPCD2, CLK_TYPE_GEN3_RPCD2,
+		 R8A774A1_CLK_RPC),
 
 	DEF_GEN3_OSC(".r",      CLK_RINT,          CLK_EXTAL,      32),
 
@@ -200,6 +207,7 @@ static const struct mssr_mod_clk r8a774a1_mod_clks[] __initconst = {
 	DEF_MOD("can-fd",		 914,	R8A774A1_CLK_S3D2),
 	DEF_MOD("can-if1",		 915,	R8A774A1_CLK_S3D4),
 	DEF_MOD("can-if0",		 916,	R8A774A1_CLK_S3D4),
+	DEF_MOD("rpc-if",		 917,	R8A774A1_CLK_RPCD2),
 	DEF_MOD("i2c6",			 918,	R8A774A1_CLK_S0D6),
 	DEF_MOD("i2c5",			 919,	R8A774A1_CLK_S0D6),
 	DEF_MOD("i2c-dvfs",		 926,	R8A774A1_CLK_CP),
diff --git a/drivers/clk/renesas/r8a774b1-cpg-mssr.c b/drivers/clk/renesas/r8a774b1-cpg-mssr.c
index f436691271ec..6f04c40fe237 100644
--- a/drivers/clk/renesas/r8a774b1-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a774b1-cpg-mssr.c
@@ -40,6 +40,7 @@ enum clk_ids {
 	CLK_S2,
 	CLK_S3,
 	CLK_SDSRC,
+	CLK_RPCSRC,
 	CLK_RINT,
 
 	/* Module Clocks */
@@ -65,6 +66,12 @@ static const struct cpg_core_clk r8a774b1_core_clks[] __initconst = {
 	DEF_FIXED(".s2",        CLK_S2,            CLK_PLL1_DIV2,  4, 1),
 	DEF_FIXED(".s3",        CLK_S3,            CLK_PLL1_DIV2,  6, 1),
 	DEF_FIXED(".sdsrc",     CLK_SDSRC,         CLK_PLL1_DIV2,  2, 1),
+	DEF_BASE(".rpcsrc",     CLK_RPCSRC, CLK_TYPE_GEN3_RPCSRC, CLK_PLL1),
+
+	DEF_BASE("rpc",         R8A774B1_CLK_RPC, CLK_TYPE_GEN3_RPC,
+		 CLK_RPCSRC),
+	DEF_BASE("rpcd2",       R8A774B1_CLK_RPCD2, CLK_TYPE_GEN3_RPCD2,
+		 R8A774B1_CLK_RPC),
 
 	DEF_GEN3_OSC(".r",      CLK_RINT,          CLK_EXTAL,      32),
 
@@ -196,6 +203,7 @@ static const struct mssr_mod_clk r8a774b1_mod_clks[] __initconst = {
 	DEF_MOD("can-fd",		 914,	R8A774B1_CLK_S3D2),
 	DEF_MOD("can-if1",		 915,	R8A774B1_CLK_S3D4),
 	DEF_MOD("can-if0",		 916,	R8A774B1_CLK_S3D4),
+	DEF_MOD("rpc-if",		 917,	R8A774B1_CLK_RPCD2),
 	DEF_MOD("i2c6",			 918,	R8A774B1_CLK_S0D6),
 	DEF_MOD("i2c5",			 919,	R8A774B1_CLK_S0D6),
 	DEF_MOD("i2c-dvfs",		 926,	R8A774B1_CLK_CP),
diff --git a/drivers/clk/renesas/r8a774c0-cpg-mssr.c b/drivers/clk/renesas/r8a774c0-cpg-mssr.c
index 9fc9fa9e531a..ed3a2cf0e0bb 100644
--- a/drivers/clk/renesas/r8a774c0-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a774c0-cpg-mssr.c
@@ -44,6 +44,7 @@ enum clk_ids {
 	CLK_S2,
 	CLK_S3,
 	CLK_SDSRC,
+	CLK_RPCSRC,
 	CLK_RINT,
 	CLK_OCO,
 
@@ -74,6 +75,13 @@ static const struct cpg_core_clk r8a774c0_core_clks[] __initconst = {
 	DEF_FIXED(".s3",       CLK_S3,             CLK_PLL1,       6, 1),
 	DEF_FIXED(".sdsrc",    CLK_SDSRC,          CLK_PLL1,       2, 1),
 
+	DEF_FIXED_RPCSRC_E3(".rpcsrc", CLK_RPCSRC, CLK_PLL0, CLK_PLL1),
+
+	DEF_BASE("rpc",		R8A774C0_CLK_RPC, CLK_TYPE_GEN3_RPC,
+		 CLK_RPCSRC),
+	DEF_BASE("rpcd2",	R8A774C0_CLK_RPCD2, CLK_TYPE_GEN3_RPCD2,
+		 R8A774C0_CLK_RPC),
+
 	DEF_DIV6_RO(".r",      CLK_RINT,           CLK_EXTAL, CPG_RCKCR, 32),
 
 	DEF_RATE(".oco",       CLK_OCO,            8 * 1000 * 1000),
@@ -199,6 +207,7 @@ static const struct mssr_mod_clk r8a774c0_mod_clks[] __initconst = {
 	DEF_MOD("can-fd",		 914,	R8A774C0_CLK_S3D2),
 	DEF_MOD("can-if1",		 915,	R8A774C0_CLK_S3D4),
 	DEF_MOD("can-if0",		 916,	R8A774C0_CLK_S3D4),
+	DEF_MOD("rpc-if",		 917,	R8A774C0_CLK_RPCD2),
 	DEF_MOD("i2c6",			 918,	R8A774C0_CLK_S3D2),
 	DEF_MOD("i2c5",			 919,	R8A774C0_CLK_S3D2),
 	DEF_MOD("i2c-dvfs",		 926,	R8A774C0_CLK_CP),
diff --git a/drivers/clk/renesas/r8a779a0-cpg-mssr.c b/drivers/clk/renesas/r8a779a0-cpg-mssr.c
index 17ebbac7ddfb..aa5389b04d74 100644
--- a/drivers/clk/renesas/r8a779a0-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a779a0-cpg-mssr.c
@@ -26,7 +26,6 @@
 #include <dt-bindings/clock/r8a779a0-cpg-mssr.h>
 
 #include "renesas-cpg-mssr.h"
-#include "rcar-gen3-cpg.h"
 
 enum rcar_r8a779a0_clk_types {
 	CLK_TYPE_R8A779A0_MAIN = CLK_TYPE_CUSTOM,
@@ -84,6 +83,14 @@ enum clk_ids {
 	DEF_BASE(_name, _id, CLK_TYPE_R8A779A0_PLL2X_3X, CLK_MAIN, \
 		 .offset = _offset)
 
+#define DEF_MDSEL(_name, _id, _md, _parent0, _div0, _parent1, _div1) \
+	DEF_BASE(_name, _id, CLK_TYPE_R8A779A0_MDSEL,	\
+		 (_parent0) << 16 | (_parent1),		\
+		 .div = (_div0) << 16 | (_div1), .offset = _md)
+
+#define DEF_OSC(_name, _id, _parent, _div)		\
+	DEF_BASE(_name, _id, CLK_TYPE_R8A779A0_OSC, _parent, .div = _div)
+
 static const struct cpg_core_clk r8a779a0_core_clks[] __initconst = {
 	/* External Clock Inputs */
 	DEF_INPUT("extal",  CLK_EXTAL),
@@ -136,15 +143,51 @@ static const struct cpg_core_clk r8a779a0_core_clks[] __initconst = {
 	DEF_DIV6P1("canfd",	R8A779A0_CLK_CANFD,	CLK_PLL5_DIV4,	0x878),
 	DEF_DIV6P1("csi0",	R8A779A0_CLK_CSI0,	CLK_PLL5_DIV4,	0x880),
 
-	DEF_GEN3_OSC("osc",	R8A779A0_CLK_OSC,	CLK_EXTAL,	8),
-	DEF_GEN3_MDSEL("r",	R8A779A0_CLK_R, 29, CLK_EXTALR, 1, CLK_OCO, 1),
+	DEF_OSC("osc",		R8A779A0_CLK_OSC,	CLK_EXTAL,	8),
+	DEF_MDSEL("r",		R8A779A0_CLK_R, 29, CLK_EXTALR, 1, CLK_OCO, 1),
 };
 
 static const struct mssr_mod_clk r8a779a0_mod_clks[] __initconst = {
+	DEF_MOD("csi40",	331,	R8A779A0_CLK_CSI0),
+	DEF_MOD("csi41",	400,	R8A779A0_CLK_CSI0),
+	DEF_MOD("csi42",	401,	R8A779A0_CLK_CSI0),
+	DEF_MOD("csi43",	402,	R8A779A0_CLK_CSI0),
 	DEF_MOD("scif0",	702,	R8A779A0_CLK_S1D8),
 	DEF_MOD("scif1",	703,	R8A779A0_CLK_S1D8),
 	DEF_MOD("scif3",	704,	R8A779A0_CLK_S1D8),
 	DEF_MOD("scif4",	705,	R8A779A0_CLK_S1D8),
+	DEF_MOD("vin00",	730,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin01",	731,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin02",	800,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin03",	801,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin04",	802,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin05",	803,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin06",	804,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin07",	805,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin10",	806,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin11",	807,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin12",	808,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin13",	809,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin14",	810,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin15",	811,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin16",	812,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin17",	813,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin20",	814,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin21",	815,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin22",	816,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin23",	817,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin24",	818,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin25",	819,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin26",	820,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin27",	821,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin30",	822,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin31",	823,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin32",	824,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin33",	825,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin34",	826,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin35",	827,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin36",	828,	R8A779A0_CLK_S1D1),
+	DEF_MOD("vin37",	829,	R8A779A0_CLK_S1D1),
 };
 
 static spinlock_t cpg_lock;
@@ -153,7 +196,7 @@ static const struct rcar_r8a779a0_cpg_pll_config *cpg_pll_config __initdata;
 static unsigned int cpg_clk_extalr __initdata;
 static u32 cpg_mode __initdata;
 
-struct clk * __init rcar_r8a779a0_cpg_clk_register(struct device *dev,
+static struct clk * __init rcar_r8a779a0_cpg_clk_register(struct device *dev,
 	const struct cpg_core_clk *core, const struct cpg_mssr_info *info,
 	struct clk **clks, void __iomem *base,
 	struct raw_notifier_head *notifiers)
diff --git a/drivers/clk/renesas/rcar-gen3-cpg.c b/drivers/clk/renesas/rcar-gen3-cpg.c
index 488f8b3980c5..063b61151488 100644
--- a/drivers/clk/renesas/rcar-gen3-cpg.c
+++ b/drivers/clk/renesas/rcar-gen3-cpg.c
@@ -224,10 +224,9 @@ static struct clk * __init cpg_z_clk_register(const char *name,
 #define CPG_SD_STP_MASK		(CPG_SD_STP_HCK | CPG_SD_STP_CK)
 #define CPG_SD_FC_MASK		(0x7 << 2 | 0x3 << 0)
 
-#define CPG_SD_DIV_TABLE_DATA(stp_hck, stp_ck, sd_srcfc, sd_fc, sd_div) \
+#define CPG_SD_DIV_TABLE_DATA(stp_hck, sd_srcfc, sd_fc, sd_div) \
 { \
 	.val = ((stp_hck) ? CPG_SD_STP_HCK : 0) | \
-	       ((stp_ck) ? CPG_SD_STP_CK : 0) | \
 	       ((sd_srcfc) << 2) | \
 	       ((sd_fc) << 0), \
 	.div = (sd_div), \
@@ -247,36 +246,36 @@ struct sd_clock {
 };
 
 /* SDn divider
- *                     sd_srcfc   sd_fc   div
- * stp_hck   stp_ck    (div)      (div)     = sd_srcfc x sd_fc
- *-------------------------------------------------------------------
- *  0         0         0 (1)      1 (4)      4 : SDR104 / HS200 / HS400 (8 TAP)
- *  0         0         1 (2)      1 (4)      8 : SDR50
- *  1         0         2 (4)      1 (4)     16 : HS / SDR25
- *  1         0         3 (8)      1 (4)     32 : NS / SDR12
- *  1         0         4 (16)     1 (4)     64
- *  0         0         0 (1)      0 (2)      2
- *  0         0         1 (2)      0 (2)      4 : SDR104 / HS200 / HS400 (4 TAP)
- *  1         0         2 (4)      0 (2)      8
- *  1         0         3 (8)      0 (2)     16
- *  1         0         4 (16)     0 (2)     32
+ *           sd_srcfc   sd_fc   div
+ * stp_hck   (div)      (div)     = sd_srcfc x sd_fc
+ *---------------------------------------------------------
+ *  0         0 (1)      1 (4)      4 : SDR104 / HS200 / HS400 (8 TAP)
+ *  0         1 (2)      1 (4)      8 : SDR50
+ *  1         2 (4)      1 (4)     16 : HS / SDR25
+ *  1         3 (8)      1 (4)     32 : NS / SDR12
+ *  1         4 (16)     1 (4)     64
+ *  0         0 (1)      0 (2)      2
+ *  0         1 (2)      0 (2)      4 : SDR104 / HS200 / HS400 (4 TAP)
+ *  1         2 (4)      0 (2)      8
+ *  1         3 (8)      0 (2)     16
+ *  1         4 (16)     0 (2)     32
  *
  *  NOTE: There is a quirk option to ignore the first row of the dividers
  *  table when searching for suitable settings. This is because HS400 on
  *  early ES versions of H3 and M3-W requires a specific setting to work.
  */
 static const struct sd_div_table cpg_sd_div_table[] = {
-/*	CPG_SD_DIV_TABLE_DATA(stp_hck,  stp_ck,   sd_srcfc,   sd_fc,  sd_div) */
-	CPG_SD_DIV_TABLE_DATA(0,        0,        0,          1,        4),
-	CPG_SD_DIV_TABLE_DATA(0,        0,        1,          1,        8),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        2,          1,       16),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        3,          1,       32),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        4,          1,       64),
-	CPG_SD_DIV_TABLE_DATA(0,        0,        0,          0,        2),
-	CPG_SD_DIV_TABLE_DATA(0,        0,        1,          0,        4),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        2,          0,        8),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        3,          0,       16),
-	CPG_SD_DIV_TABLE_DATA(1,        0,        4,          0,       32),
+/*	CPG_SD_DIV_TABLE_DATA(stp_hck,  sd_srcfc,   sd_fc,  sd_div) */
+	CPG_SD_DIV_TABLE_DATA(0,        0,          1,        4),
+	CPG_SD_DIV_TABLE_DATA(0,        1,          1,        8),
+	CPG_SD_DIV_TABLE_DATA(1,        2,          1,       16),
+	CPG_SD_DIV_TABLE_DATA(1,        3,          1,       32),
+	CPG_SD_DIV_TABLE_DATA(1,        4,          1,       64),
+	CPG_SD_DIV_TABLE_DATA(0,        0,          0,        2),
+	CPG_SD_DIV_TABLE_DATA(0,        1,          0,        4),
+	CPG_SD_DIV_TABLE_DATA(1,        2,          0,        8),
+	CPG_SD_DIV_TABLE_DATA(1,        3,          0,       16),
+	CPG_SD_DIV_TABLE_DATA(1,        4,          0,       32),
 };
 
 #define to_sd_clock(_hw) container_of(_hw, struct sd_clock, hw)
@@ -696,6 +695,34 @@ struct clk * __init rcar_gen3_cpg_clk_register(struct device *dev,
 						  cpg_rpcsrc_div_table,
 						  &cpg_lock);
 
+	case CLK_TYPE_GEN3_E3_RPCSRC:
+		/*
+		 * Register RPCSRC as fixed factor clock based on the
+		 * MD[4:1] pins and CPG_RPCCKCR[4:3] register value for
+		 * which has been set prior to booting the kernel.
+		 */
+		value = (readl(base + CPG_RPCCKCR) & GENMASK(4, 3)) >> 3;
+
+		switch (value) {
+		case 0:
+			div = 5;
+			break;
+		case 1:
+			div = 3;
+			break;
+		case 2:
+			parent = clks[core->parent >> 16];
+			if (IS_ERR(parent))
+				return ERR_CAST(parent);
+			div = core->div;
+			break;
+		case 3:
+		default:
+			div = 2;
+			break;
+		}
+		break;
+
 	case CLK_TYPE_GEN3_RPC:
 		return cpg_rpc_clk_register(core->name, base,
 					    __clk_get_name(parent), notifiers);
diff --git a/drivers/clk/renesas/rcar-gen3-cpg.h b/drivers/clk/renesas/rcar-gen3-cpg.h
index c4ac80cac6a0..3d949c4a3244 100644
--- a/drivers/clk/renesas/rcar-gen3-cpg.h
+++ b/drivers/clk/renesas/rcar-gen3-cpg.h
@@ -24,6 +24,7 @@ enum rcar_gen3_clk_types {
 	CLK_TYPE_GEN3_OSC,	/* OSC EXTAL predivider and fixed divider */
 	CLK_TYPE_GEN3_RCKSEL,	/* Select parent/divider using RCKCR.CKSEL */
 	CLK_TYPE_GEN3_RPCSRC,
+	CLK_TYPE_GEN3_E3_RPCSRC,
 	CLK_TYPE_GEN3_RPC,
 	CLK_TYPE_GEN3_RPCD2,
 
@@ -54,6 +55,10 @@ enum rcar_gen3_clk_types {
 #define DEF_GEN3_Z(_name, _id, _type, _parent, _div, _offset)	\
 	DEF_BASE(_name, _id, _type, _parent, .div = _div, .offset = _offset)
 
+#define DEF_FIXED_RPCSRC_E3(_name, _id, _parent0, _parent1)	\
+	DEF_BASE(_name, _id, CLK_TYPE_GEN3_E3_RPCSRC,	\
+		 (_parent0) << 16 | (_parent1), .div = 8)
+
 struct rcar_gen3_cpg_pll_config {
 	u8 extal_div;
 	u8 pll1_mult;
diff --git a/drivers/clk/renesas/rcar-usb2-clock-sel.c b/drivers/clk/renesas/rcar-usb2-clock-sel.c
index d4c02986c34e..3abafd78f7c8 100644
--- a/drivers/clk/renesas/rcar-usb2-clock-sel.c
+++ b/drivers/clk/renesas/rcar-usb2-clock-sel.c
@@ -160,7 +160,7 @@ static int rcar_usb2_clock_sel_probe(struct platform_device *pdev)
 	if (ret < 0)
 		return ret;
 
-	priv->rsts = devm_reset_control_array_get(dev, true, false);
+	priv->rsts = devm_reset_control_array_get_shared(dev);
 	if (IS_ERR(priv->rsts))
 		return PTR_ERR(priv->rsts);
 
diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c
index 94db88370337..1c3215dc4877 100644
--- a/drivers/clk/renesas/renesas-cpg-mssr.c
+++ b/drivers/clk/renesas/renesas-cpg-mssr.c
@@ -119,7 +119,8 @@ static const u16 srstclr_for_v3u[] = {
 };
 
 /**
- * Clock Pulse Generator / Module Standby and Software Reset Private Data
+ * struct cpg_mssr_priv - Clock Pulse Generator / Module Standby
+ *                        and Software Reset Private Data
  *
  * @rcdev: Optional reset controller entity
  * @dev: CPG/MSSR device
diff --git a/drivers/clk/rockchip/Kconfig b/drivers/clk/rockchip/Kconfig
index 47cd6c5de837..effd05032e85 100644
--- a/drivers/clk/rockchip/Kconfig
+++ b/drivers/clk/rockchip/Kconfig
@@ -11,67 +11,77 @@ config COMMON_CLK_ROCKCHIP
 if COMMON_CLK_ROCKCHIP
 config CLK_PX30
 	bool "Rockchip PX30 clock controller support"
+	depends on (ARM64 || COMPILE_TEST)
 	default y
 	help
 	  Build the driver for PX30 Clock Driver.
 
 config CLK_RV110X
 	bool "Rockchip RV110x clock controller support"
+	depends on (ARM || COMPILE_TEST)
 	default y
 	help
 	  Build the driver for RV110x Clock Driver.
 
 config CLK_RK3036
 	bool "Rockchip RK3036 clock controller support"
+	depends on (ARM || COMPILE_TEST)
 	default y
 	help
 	  Build the driver for RK3036 Clock Driver.
 
 config CLK_RK312X
 	bool "Rockchip RK312x clock controller support"
+	depends on (ARM || COMPILE_TEST)
 	default y
 	help
 	  Build the driver for RK312x Clock Driver.
 
 config CLK_RK3188
 	bool "Rockchip RK3188 clock controller support"
+	depends on (ARM || COMPILE_TEST)
 	default y
 	help
 	  Build the driver for RK3188 Clock Driver.
 
 config CLK_RK322X
 	bool "Rockchip RK322x clock controller support"
+	depends on (ARM || COMPILE_TEST)
 	default y
 	help
 	  Build the driver for RK322x Clock Driver.
 
 config CLK_RK3288
 	bool "Rockchip RK3288 clock controller support"
-	depends on ARM
+	depends on (ARM || COMPILE_TEST)
 	default y
 	help
 	  Build the driver for RK3288 Clock Driver.
 
 config CLK_RK3308
 	bool "Rockchip RK3308 clock controller support"
+	depends on (ARM64 || COMPILE_TEST)
 	default y
 	help
 	  Build the driver for RK3308 Clock Driver.
 
 config CLK_RK3328
 	bool "Rockchip RK3328 clock controller support"
+	depends on (ARM64 || COMPILE_TEST)
 	default y
 	help
 	  Build the driver for RK3328 Clock Driver.
 
 config CLK_RK3368
 	bool "Rockchip RK3368 clock controller support"
+	depends on (ARM64 || COMPILE_TEST)
 	default y
 	help
 	  Build the driver for RK3368 Clock Driver.
 
 config CLK_RK3399
 	tristate "Rockchip RK3399 clock controller support"
+	depends on (ARM64 || COMPILE_TEST)
 	default y
 	help
 	  Build the driver for RK3399 Clock Driver.
diff --git a/drivers/clk/rockchip/clk-rk3188.c b/drivers/clk/rockchip/clk-rk3188.c
index 730020fcc7fe..0b76ad34de00 100644
--- a/drivers/clk/rockchip/clk-rk3188.c
+++ b/drivers/clk/rockchip/clk-rk3188.c
@@ -255,19 +255,19 @@ static struct rockchip_clk_branch common_spdif_fracmux __initdata =
 			RK2928_CLKSEL_CON(5), 8, 2, MFLAGS);
 
 static struct rockchip_clk_branch common_uart0_fracmux __initdata =
-	MUX(SCLK_UART0, "sclk_uart0", mux_sclk_uart0_p, 0,
+	MUX(SCLK_UART0, "sclk_uart0", mux_sclk_uart0_p, CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(13), 8, 2, MFLAGS);
 
 static struct rockchip_clk_branch common_uart1_fracmux __initdata =
-	MUX(SCLK_UART1, "sclk_uart1", mux_sclk_uart1_p, 0,
+	MUX(SCLK_UART1, "sclk_uart1", mux_sclk_uart1_p, CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(14), 8, 2, MFLAGS);
 
 static struct rockchip_clk_branch common_uart2_fracmux __initdata =
-	MUX(SCLK_UART2, "sclk_uart2", mux_sclk_uart2_p, 0,
+	MUX(SCLK_UART2, "sclk_uart2", mux_sclk_uart2_p, CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(15), 8, 2, MFLAGS);
 
 static struct rockchip_clk_branch common_uart3_fracmux __initdata =
-	MUX(SCLK_UART3, "sclk_uart3", mux_sclk_uart3_p, 0,
+	MUX(SCLK_UART3, "sclk_uart3", mux_sclk_uart3_p, CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(16), 8, 2, MFLAGS);
 
 static struct rockchip_clk_branch common_clk_branches[] __initdata = {
@@ -408,28 +408,28 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 	COMPOSITE_NOMUX(0, "uart0_pre", "uart_src", 0,
 			RK2928_CLKSEL_CON(13), 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(1), 8, GFLAGS),
-	COMPOSITE_FRACMUX(0, "uart0_frac", "uart0_pre", 0,
+	COMPOSITE_FRACMUX(0, "uart0_frac", "uart0_pre", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(17), 0,
 			RK2928_CLKGATE_CON(1), 9, GFLAGS,
 			&common_uart0_fracmux),
 	COMPOSITE_NOMUX(0, "uart1_pre", "uart_src", 0,
 			RK2928_CLKSEL_CON(14), 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(1), 10, GFLAGS),
-	COMPOSITE_FRACMUX(0, "uart1_frac", "uart1_pre", 0,
+	COMPOSITE_FRACMUX(0, "uart1_frac", "uart1_pre", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(18), 0,
 			RK2928_CLKGATE_CON(1), 11, GFLAGS,
 			&common_uart1_fracmux),
 	COMPOSITE_NOMUX(0, "uart2_pre", "uart_src", 0,
 			RK2928_CLKSEL_CON(15), 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(1), 12, GFLAGS),
-	COMPOSITE_FRACMUX(0, "uart2_frac", "uart2_pre", 0,
+	COMPOSITE_FRACMUX(0, "uart2_frac", "uart2_pre", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(19), 0,
 			RK2928_CLKGATE_CON(1), 13, GFLAGS,
 			&common_uart2_fracmux),
 	COMPOSITE_NOMUX(0, "uart3_pre", "uart_src", 0,
 			RK2928_CLKSEL_CON(16), 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(1), 14, GFLAGS),
-	COMPOSITE_FRACMUX(0, "uart3_frac", "uart3_pre", 0,
+	COMPOSITE_FRACMUX(0, "uart3_frac", "uart3_pre", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(20), 0,
 			RK2928_CLKGATE_CON(1), 15, GFLAGS,
 			&common_uart3_fracmux),
@@ -449,7 +449,6 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 
 	/* hclk_cpu gates */
 	GATE(HCLK_ROM, "hclk_rom", "hclk_cpu", 0, RK2928_CLKGATE_CON(5), 6, GFLAGS),
-	GATE(HCLK_I2S0, "hclk_i2s0", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 2, GFLAGS),
 	GATE(HCLK_SPDIF, "hclk_spdif", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 1, GFLAGS),
 	GATE(0, "hclk_cpubus", "hclk_cpu", 0, RK2928_CLKGATE_CON(4), 8, GFLAGS),
 	/* hclk_ahb2apb is part of a clk branch */
@@ -543,15 +542,15 @@ static struct clk_div_table div_aclk_cpu_t[] = {
 };
 
 static struct rockchip_clk_branch rk3066a_i2s0_fracmux __initdata =
-	MUX(SCLK_I2S0, "sclk_i2s0", mux_sclk_i2s0_p, 0,
+	MUX(SCLK_I2S0, "sclk_i2s0", mux_sclk_i2s0_p, CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(2), 8, 2, MFLAGS);
 
 static struct rockchip_clk_branch rk3066a_i2s1_fracmux __initdata =
-	MUX(SCLK_I2S1, "sclk_i2s1", mux_sclk_i2s1_p, 0,
+	MUX(SCLK_I2S1, "sclk_i2s1", mux_sclk_i2s1_p, CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(3), 8, 2, MFLAGS);
 
 static struct rockchip_clk_branch rk3066a_i2s2_fracmux __initdata =
-	MUX(SCLK_I2S2, "sclk_i2s2", mux_sclk_i2s2_p, 0,
+	MUX(SCLK_I2S2, "sclk_i2s2", mux_sclk_i2s2_p, CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(4), 8, 2, MFLAGS);
 
 static struct rockchip_clk_branch rk3066a_clk_branches[] __initdata = {
@@ -615,27 +614,28 @@ static struct rockchip_clk_branch rk3066a_clk_branches[] __initdata = {
 	COMPOSITE_NOMUX(0, "i2s0_pre", "i2s_src", 0,
 			RK2928_CLKSEL_CON(2), 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(0), 7, GFLAGS),
-	COMPOSITE_FRACMUX(0, "i2s0_frac", "i2s0_pre", 0,
+	COMPOSITE_FRACMUX(0, "i2s0_frac", "i2s0_pre", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(6), 0,
 			RK2928_CLKGATE_CON(0), 8, GFLAGS,
 			&rk3066a_i2s0_fracmux),
 	COMPOSITE_NOMUX(0, "i2s1_pre", "i2s_src", 0,
 			RK2928_CLKSEL_CON(3), 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(0), 9, GFLAGS),
-	COMPOSITE_FRACMUX(0, "i2s1_frac", "i2s1_pre", 0,
+	COMPOSITE_FRACMUX(0, "i2s1_frac", "i2s1_pre", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(7), 0,
 			RK2928_CLKGATE_CON(0), 10, GFLAGS,
 			&rk3066a_i2s1_fracmux),
 	COMPOSITE_NOMUX(0, "i2s2_pre", "i2s_src", 0,
 			RK2928_CLKSEL_CON(4), 0, 7, DFLAGS,
 			RK2928_CLKGATE_CON(0), 11, GFLAGS),
-	COMPOSITE_FRACMUX(0, "i2s2_frac", "i2s2_pre", 0,
+	COMPOSITE_FRACMUX(0, "i2s2_frac", "i2s2_pre", CLK_SET_RATE_PARENT,
 			RK2928_CLKSEL_CON(8), 0,
 			RK2928_CLKGATE_CON(0), 12, GFLAGS,
 			&rk3066a_i2s2_fracmux),
 
-	GATE(HCLK_I2S1, "hclk_i2s1", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 3, GFLAGS),
-	GATE(HCLK_I2S2, "hclk_i2s2", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 4, GFLAGS),
+	GATE(HCLK_I2S0, "hclk_i2s0", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 4, GFLAGS),
+	GATE(HCLK_I2S1, "hclk_i2s1", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 2, GFLAGS),
+	GATE(HCLK_I2S2, "hclk_i2s2", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 3, GFLAGS),
 	GATE(HCLK_CIF1, "hclk_cif1", "hclk_cpu", 0, RK2928_CLKGATE_CON(6), 6, GFLAGS),
 	GATE(HCLK_HDMI, "hclk_hdmi", "hclk_cpu", 0, RK2928_CLKGATE_CON(4), 14, GFLAGS),
 
@@ -728,6 +728,7 @@ static struct rockchip_clk_branch rk3188_clk_branches[] __initdata = {
 			RK2928_CLKGATE_CON(0), 10, GFLAGS,
 			&rk3188_i2s0_fracmux),
 
+	GATE(HCLK_I2S0, "hclk_i2s0", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 2, GFLAGS),
 	GATE(0, "hclk_imem0", "hclk_cpu", 0, RK2928_CLKGATE_CON(4), 14, GFLAGS),
 	GATE(0, "hclk_imem1", "hclk_cpu", 0, RK2928_CLKGATE_CON(4), 15, GFLAGS),
 
diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c
index b443169dd408..336481bc6cc7 100644
--- a/drivers/clk/rockchip/clk.c
+++ b/drivers/clk/rockchip/clk.c
@@ -603,8 +603,7 @@ void rockchip_clk_protect_critical(const char *const clocks[],
 	for (i = 0; i < nclocks; i++) {
 		struct clk *clk = __clk_lookup(clocks[i]);
 
-		if (clk)
-			clk_prepare_enable(clk);
+		clk_prepare_enable(clk);
 	}
 }
 EXPORT_SYMBOL_GPL(rockchip_clk_protect_critical);
diff --git a/drivers/clk/samsung/Kconfig b/drivers/clk/samsung/Kconfig
index 7e9c186e57ef..0441c4f73ac9 100644
--- a/drivers/clk/samsung/Kconfig
+++ b/drivers/clk/samsung/Kconfig
@@ -2,10 +2,73 @@
 # Recent Exynos platforms should just select COMMON_CLK_SAMSUNG:
 config COMMON_CLK_SAMSUNG
 	bool "Samsung Exynos clock controller support" if COMPILE_TEST
-	# Clocks on ARM64 SoCs (e.g. Exynos5433, Exynos7) are chosen by
-	# EXYNOS_ARM64_COMMON_CLK to avoid building them on ARMv7:
+	select S3C64XX_COMMON_CLK if ARM && ARCH_S3C64XX
+	select S5PV210_COMMON_CLK if ARM && ARCH_S5PV210
+	select EXYNOS_3250_COMMON_CLK if ARM && SOC_EXYNOS3250
+	select EXYNOS_4_COMMON_CLK if ARM && ARCH_EXYNOS4
+	select EXYNOS_5250_COMMON_CLK if ARM && SOC_EXYNOS5250
+	select EXYNOS_5260_COMMON_CLK if ARM && SOC_EXYNOS5260
+	select EXYNOS_5410_COMMON_CLK if ARM && SOC_EXYNOS5410
+	select EXYNOS_5420_COMMON_CLK if ARM && SOC_EXYNOS5420
 	select EXYNOS_ARM64_COMMON_CLK if ARM64 && ARCH_EXYNOS
 
+config S3C64XX_COMMON_CLK
+	bool "Samsung S3C64xx clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung S3C64xx SoCs.
+	  Choose Y here only if you build for this SoC.
+
+config S5PV210_COMMON_CLK
+	bool "Samsung S5Pv210 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung S5Pv210 SoCs.
+	  Choose Y here only if you build for this SoC.
+
+config EXYNOS_3250_COMMON_CLK
+	bool "Samsung Exynos3250 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos3250 SoCs. Choose Y here only if you build for this SoC.
+
+config EXYNOS_4_COMMON_CLK
+	bool "Samsung Exynos4 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos4212 and Exynos4412 SoCs. Choose Y here only if you build for
+	  this SoC.
+
+config EXYNOS_5250_COMMON_CLK
+	bool "Samsung Exynos5250 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos5250 SoCs. Choose Y here only if you build for this SoC.
+
+config EXYNOS_5260_COMMON_CLK
+	bool "Samsung Exynos5260 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos5260 SoCs. Choose Y here only if you build for this SoC.
+
+config EXYNOS_5410_COMMON_CLK
+	bool "Samsung Exynos5410 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos5410 SoCs. Choose Y here only if you build for this SoC.
+
+config EXYNOS_5420_COMMON_CLK
+	bool "Samsung Exynos5420 clock controller support" if COMPILE_TEST
+	depends on COMMON_CLK_SAMSUNG
+	help
+	  Support for the clock controller present on the Samsung
+	  Exynos5420 SoCs. Choose Y here only if you build for this SoC.
+
 config EXYNOS_ARM64_COMMON_CLK
 	bool "Samsung Exynos ARMv8-family clock controller support" if COMPILE_TEST
 	depends on COMMON_CLK_SAMSUNG
diff --git a/drivers/clk/samsung/Makefile b/drivers/clk/samsung/Makefile
index 6891b087acff..028b2e27a37e 100644
--- a/drivers/clk/samsung/Makefile
+++ b/drivers/clk/samsung/Makefile
@@ -4,15 +4,15 @@
 #
 
 obj-$(CONFIG_COMMON_CLK)	+= clk.o clk-pll.o clk-cpu.o
-obj-$(CONFIG_SOC_EXYNOS3250)	+= clk-exynos3250.o
-obj-$(CONFIG_ARCH_EXYNOS4)	+= clk-exynos4.o
-obj-$(CONFIG_ARCH_EXYNOS4)	+= clk-exynos4412-isp.o
-obj-$(CONFIG_SOC_EXYNOS5250)	+= clk-exynos5250.o
-obj-$(CONFIG_SOC_EXYNOS5250)	+= clk-exynos5-subcmu.o
-obj-$(CONFIG_SOC_EXYNOS5260)	+= clk-exynos5260.o
-obj-$(CONFIG_SOC_EXYNOS5410)	+= clk-exynos5410.o
-obj-$(CONFIG_SOC_EXYNOS5420)	+= clk-exynos5420.o
-obj-$(CONFIG_SOC_EXYNOS5420)	+= clk-exynos5-subcmu.o
+obj-$(CONFIG_EXYNOS_3250_COMMON_CLK)	+= clk-exynos3250.o
+obj-$(CONFIG_EXYNOS_4_COMMON_CLK)	+= clk-exynos4.o
+obj-$(CONFIG_EXYNOS_4_COMMON_CLK)	+= clk-exynos4412-isp.o
+obj-$(CONFIG_EXYNOS_5250_COMMON_CLK)	+= clk-exynos5250.o
+obj-$(CONFIG_EXYNOS_5250_COMMON_CLK)	+= clk-exynos5-subcmu.o
+obj-$(CONFIG_EXYNOS_5260_COMMON_CLK)	+= clk-exynos5260.o
+obj-$(CONFIG_EXYNOS_5410_COMMON_CLK)	+= clk-exynos5410.o
+obj-$(CONFIG_EXYNOS_5420_COMMON_CLK)	+= clk-exynos5420.o
+obj-$(CONFIG_EXYNOS_5420_COMMON_CLK)	+= clk-exynos5-subcmu.o
 obj-$(CONFIG_EXYNOS_ARM64_COMMON_CLK)	+= clk-exynos5433.o
 obj-$(CONFIG_EXYNOS_AUDSS_CLK_CON) += clk-exynos-audss.o
 obj-$(CONFIG_EXYNOS_CLKOUT)	+= clk-exynos-clkout.o
@@ -21,5 +21,5 @@ obj-$(CONFIG_S3C2410_COMMON_CLK)+= clk-s3c2410.o
 obj-$(CONFIG_S3C2410_COMMON_DCLK)+= clk-s3c2410-dclk.o
 obj-$(CONFIG_S3C2412_COMMON_CLK)+= clk-s3c2412.o
 obj-$(CONFIG_S3C2443_COMMON_CLK)+= clk-s3c2443.o
-obj-$(CONFIG_ARCH_S3C64XX)	+= clk-s3c64xx.o
-obj-$(CONFIG_ARCH_S5PV210)	+= clk-s5pv210.o clk-s5pv210-audss.o
+obj-$(CONFIG_S3C64XX_COMMON_CLK)	+= clk-s3c64xx.o
+obj-$(CONFIG_S5PV210_COMMON_CLK)	+= clk-s5pv210.o clk-s5pv210-audss.o
diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c
index ac70ad785d8e..5873a9354b50 100644
--- a/drivers/clk/samsung/clk-pll.c
+++ b/drivers/clk/samsung/clk-pll.c
@@ -8,14 +8,17 @@
 
 #include <linux/errno.h>
 #include <linux/hrtimer.h>
+#include <linux/iopoll.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/timekeeping.h>
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include "clk.h"
 #include "clk-pll.h"
 
-#define PLL_TIMEOUT_MS		10
+#define PLL_TIMEOUT_US		20000U
+#define PLL_TIMEOUT_LOOPS	1000000U
 
 struct samsung_clk_pll {
 	struct clk_hw		hw;
@@ -63,6 +66,53 @@ static long samsung_pll_round_rate(struct clk_hw *hw,
 	return rate_table[i - 1].rate;
 }
 
+static bool pll_early_timeout = true;
+
+static int __init samsung_pll_disable_early_timeout(void)
+{
+	pll_early_timeout = false;
+	return 0;
+}
+arch_initcall(samsung_pll_disable_early_timeout);
+
+/* Wait until the PLL is locked */
+static int samsung_pll_lock_wait(struct samsung_clk_pll *pll,
+				 unsigned int reg_mask)
+{
+	int i, ret;
+	u32 val;
+
+	/*
+	 * This function might be called when the timekeeping API can't be used
+	 * to detect timeouts. One situation is when the clocksource is not yet
+	 * initialized, another when the timekeeping is suspended. udelay() also
+	 * cannot be used when the clocksource is not running on arm64, since
+	 * the current timer is used as cycle counter. So a simple busy loop
+	 * is used here in that special cases. The limit of iterations has been
+	 * derived from experimental measurements of various PLLs on multiple
+	 * Exynos SoC variants. Single register read time was usually in range
+	 * 0.4...1.5 us, never less than 0.4 us.
+	 */
+	if (pll_early_timeout || timekeeping_suspended) {
+		i = PLL_TIMEOUT_LOOPS;
+		while (i-- > 0) {
+			if (readl_relaxed(pll->con_reg) & reg_mask)
+				return 0;
+
+			cpu_relax();
+		}
+		ret = -ETIMEDOUT;
+	} else {
+		ret = readl_relaxed_poll_timeout_atomic(pll->con_reg, val,
+					val & reg_mask, 0, PLL_TIMEOUT_US);
+	}
+
+	if (ret < 0)
+		pr_err("Could not lock PLL %s\n", clk_hw_get_name(&pll->hw));
+
+	return ret;
+}
+
 static int samsung_pll3xxx_enable(struct clk_hw *hw)
 {
 	struct samsung_clk_pll *pll = to_clk_pll(hw);
@@ -72,13 +122,7 @@ static int samsung_pll3xxx_enable(struct clk_hw *hw)
 	tmp |= BIT(pll->enable_offs);
 	writel_relaxed(tmp, pll->con_reg);
 
-	/* wait lock time */
-	do {
-		cpu_relax();
-		tmp = readl_relaxed(pll->con_reg);
-	} while (!(tmp & BIT(pll->lock_offs)));
-
-	return 0;
+	return samsung_pll_lock_wait(pll, BIT(pll->lock_offs));
 }
 
 static void samsung_pll3xxx_disable(struct clk_hw *hw)
@@ -240,13 +284,10 @@ static int samsung_pll35xx_set_rate(struct clk_hw *hw, unsigned long drate,
 			(rate->sdiv << PLL35XX_SDIV_SHIFT);
 	writel_relaxed(tmp, pll->con_reg);
 
-	/* Wait until the PLL is locked if it is enabled. */
-	if (tmp & BIT(pll->enable_offs)) {
-		do {
-			cpu_relax();
-			tmp = readl_relaxed(pll->con_reg);
-		} while (!(tmp & BIT(pll->lock_offs)));
-	}
+	/* Wait for PLL lock if the PLL is enabled */
+	if (tmp & BIT(pll->enable_offs))
+		return samsung_pll_lock_wait(pll, BIT(pll->lock_offs));
+
 	return 0;
 }
 
@@ -318,7 +359,7 @@ static int samsung_pll36xx_set_rate(struct clk_hw *hw, unsigned long drate,
 					unsigned long parent_rate)
 {
 	struct samsung_clk_pll *pll = to_clk_pll(hw);
-	u32 tmp, pll_con0, pll_con1;
+	u32 pll_con0, pll_con1;
 	const struct samsung_pll_rate_table *rate;
 
 	rate = samsung_get_pll_settings(pll, drate);
@@ -356,13 +397,8 @@ static int samsung_pll36xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	pll_con1 |= rate->kdiv << PLL36XX_KDIV_SHIFT;
 	writel_relaxed(pll_con1, pll->con_reg + 4);
 
-	/* wait_lock_time */
-	if (pll_con0 & BIT(pll->enable_offs)) {
-		do {
-			cpu_relax();
-			tmp = readl_relaxed(pll->con_reg);
-		} while (!(tmp & BIT(pll->lock_offs)));
-	}
+	if (pll_con0 & BIT(pll->enable_offs))
+		return samsung_pll_lock_wait(pll, BIT(pll->lock_offs));
 
 	return 0;
 }
@@ -437,7 +473,6 @@ static int samsung_pll45xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	struct samsung_clk_pll *pll = to_clk_pll(hw);
 	const struct samsung_pll_rate_table *rate;
 	u32 con0, con1;
-	ktime_t start;
 
 	/* Get required rate settings from table */
 	rate = samsung_get_pll_settings(pll, drate);
@@ -488,21 +523,8 @@ static int samsung_pll45xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	writel_relaxed(con1, pll->con_reg + 0x4);
 	writel_relaxed(con0, pll->con_reg);
 
-	/* Wait for locking. */
-	start = ktime_get();
-	while (!(readl_relaxed(pll->con_reg) & PLL45XX_LOCKED)) {
-		ktime_t delta = ktime_sub(ktime_get(), start);
-
-		if (ktime_to_ms(delta) > PLL_TIMEOUT_MS) {
-			pr_err("%s: could not lock PLL %s\n",
-					__func__, clk_hw_get_name(hw));
-			return -EFAULT;
-		}
-
-		cpu_relax();
-	}
-
-	return 0;
+	/* Wait for PLL lock */
+	return samsung_pll_lock_wait(pll, PLL45XX_LOCKED);
 }
 
 static const struct clk_ops samsung_pll45xx_clk_ops = {
@@ -588,7 +610,6 @@ static int samsung_pll46xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	struct samsung_clk_pll *pll = to_clk_pll(hw);
 	const struct samsung_pll_rate_table *rate;
 	u32 con0, con1, lock;
-	ktime_t start;
 
 	/* Get required rate settings from table */
 	rate = samsung_get_pll_settings(pll, drate);
@@ -647,21 +668,8 @@ static int samsung_pll46xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	writel_relaxed(con0, pll->con_reg);
 	writel_relaxed(con1, pll->con_reg + 0x4);
 
-	/* Wait for locking. */
-	start = ktime_get();
-	while (!(readl_relaxed(pll->con_reg) & PLL46XX_LOCKED)) {
-		ktime_t delta = ktime_sub(ktime_get(), start);
-
-		if (ktime_to_ms(delta) > PLL_TIMEOUT_MS) {
-			pr_err("%s: could not lock PLL %s\n",
-					__func__, clk_hw_get_name(hw));
-			return -EFAULT;
-		}
-
-		cpu_relax();
-	}
-
-	return 0;
+	/* Wait for PLL lock */
+	return samsung_pll_lock_wait(pll, PLL46XX_LOCKED);
 }
 
 static const struct clk_ops samsung_pll46xx_clk_ops = {
@@ -1035,14 +1043,9 @@ static int samsung_pll2550xx_set_rate(struct clk_hw *hw, unsigned long drate,
 			(rate->sdiv << PLL2550XX_S_SHIFT);
 	writel_relaxed(tmp, pll->con_reg);
 
-	/* wait_lock_time */
-	do {
-		cpu_relax();
-		tmp = readl_relaxed(pll->con_reg);
-	} while (!(tmp & (PLL2550XX_LOCK_STAT_MASK
-			<< PLL2550XX_LOCK_STAT_SHIFT)));
-
-	return 0;
+	/* Wait for PLL lock */
+	return samsung_pll_lock_wait(pll,
+			PLL2550XX_LOCK_STAT_MASK << PLL2550XX_LOCK_STAT_SHIFT);
 }
 
 static const struct clk_ops samsung_pll2550xx_clk_ops = {
@@ -1132,13 +1135,9 @@ static int samsung_pll2650x_set_rate(struct clk_hw *hw, unsigned long drate,
 	con1 |= ((rate->kdiv & PLL2650X_K_MASK) << PLL2650X_K_SHIFT);
 	writel_relaxed(con1, pll->con_reg + 4);
 
-	do {
-		cpu_relax();
-		con0 = readl_relaxed(pll->con_reg);
-	} while (!(con0 & (PLL2650X_LOCK_STAT_MASK
-			<< PLL2650X_LOCK_STAT_SHIFT)));
-
-	return 0;
+	/* Wait for PLL lock */
+	return samsung_pll_lock_wait(pll,
+			PLL2650X_LOCK_STAT_MASK << PLL2650X_LOCK_STAT_SHIFT);
 }
 
 static const struct clk_ops samsung_pll2650x_clk_ops = {
@@ -1196,7 +1195,7 @@ static int samsung_pll2650xx_set_rate(struct clk_hw *hw, unsigned long drate,
 					unsigned long parent_rate)
 {
 	struct samsung_clk_pll *pll = to_clk_pll(hw);
-	u32 tmp, pll_con0, pll_con2;
+	u32 pll_con0, pll_con2;
 	const struct samsung_pll_rate_table *rate;
 
 	rate = samsung_get_pll_settings(pll, drate);
@@ -1229,11 +1228,7 @@ static int samsung_pll2650xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	writel_relaxed(pll_con0, pll->con_reg);
 	writel_relaxed(pll_con2, pll->con_reg + 8);
 
-	do {
-		tmp = readl_relaxed(pll->con_reg);
-	} while (!(tmp & (0x1 << PLL2650XX_PLL_LOCKTIME_SHIFT)));
-
-	return 0;
+	return samsung_pll_lock_wait(pll, 0x1 << PLL2650XX_PLL_LOCKTIME_SHIFT);
 }
 
 static const struct clk_ops samsung_pll2650xx_clk_ops = {
diff --git a/drivers/clk/sifive/Kconfig b/drivers/clk/sifive/Kconfig
index f3b4eb9cb0f5..1c14eb20c066 100644
--- a/drivers/clk/sifive/Kconfig
+++ b/drivers/clk/sifive/Kconfig
@@ -8,12 +8,12 @@ menuconfig CLK_SIFIVE
 
 if CLK_SIFIVE
 
-config CLK_SIFIVE_FU540_PRCI
-	bool "PRCI driver for SiFive FU540 SoCs"
+config CLK_SIFIVE_PRCI
+	bool "PRCI driver for SiFive SoCs"
 	select CLK_ANALOGBITS_WRPLL_CLN28HPC
 	help
 	  Supports the Power Reset Clock interface (PRCI) IP block found in
-	  FU540 SoCs.  If this kernel is meant to run on a SiFive FU540 SoC,
-	  enable this driver.
+	  FU540/FU740 SoCs. If this kernel is meant to run on a SiFive FU540/
+	  FU740 SoCs, enable this driver.
 
 endif
diff --git a/drivers/clk/sifive/Makefile b/drivers/clk/sifive/Makefile
index 0797f14fef6b..7b06fc04e6b3 100644
--- a/drivers/clk/sifive/Makefile
+++ b/drivers/clk/sifive/Makefile
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_CLK_SIFIVE_FU540_PRCI)	+= fu540-prci.o
+obj-$(CONFIG_CLK_SIFIVE_PRCI)	+= sifive-prci.o fu540-prci.o fu740-prci.o
diff --git a/drivers/clk/sifive/fu540-prci.c b/drivers/clk/sifive/fu540-prci.c
index a8901f90a61a..29bab915003c 100644
--- a/drivers/clk/sifive/fu540-prci.c
+++ b/drivers/clk/sifive/fu540-prci.c
@@ -1,17 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2018-2019 SiFive, Inc.
- * Wesley Terpstra
- * Paul Walmsley
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2018-2019 Wesley Terpstra
+ * Copyright (C) 2018-2019 Paul Walmsley
+ * Copyright (C) 2020 Zong Li
  *
  * The FU540 PRCI implements clock and reset control for the SiFive
  * FU540-C000 chip.  This driver assumes that it has sole control
@@ -24,464 +16,53 @@
  * - SiFive FU540-C000 manual v1p0, Chapter 7 "Clocking and Reset"
  */
 
-#include <dt-bindings/clock/sifive-fu540-prci.h>
-#include <linux/clkdev.h>
-#include <linux/clk-provider.h>
-#include <linux/clk/analogbits-wrpll-cln28hpc.h>
-#include <linux/delay.h>
-#include <linux/err.h>
-#include <linux/io.h>
 #include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_clk.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-
-/*
- * EXPECTED_CLK_PARENT_COUNT: how many parent clocks this driver expects:
- *     hfclk and rtcclk
- */
-#define EXPECTED_CLK_PARENT_COUNT		2
-
-/*
- * Register offsets and bitmasks
- */
-
-/* COREPLLCFG0 */
-#define PRCI_COREPLLCFG0_OFFSET			0x4
-# define PRCI_COREPLLCFG0_DIVR_SHIFT		0
-# define PRCI_COREPLLCFG0_DIVR_MASK		(0x3f << PRCI_COREPLLCFG0_DIVR_SHIFT)
-# define PRCI_COREPLLCFG0_DIVF_SHIFT		6
-# define PRCI_COREPLLCFG0_DIVF_MASK		(0x1ff << PRCI_COREPLLCFG0_DIVF_SHIFT)
-# define PRCI_COREPLLCFG0_DIVQ_SHIFT		15
-# define PRCI_COREPLLCFG0_DIVQ_MASK		(0x7 << PRCI_COREPLLCFG0_DIVQ_SHIFT)
-# define PRCI_COREPLLCFG0_RANGE_SHIFT		18
-# define PRCI_COREPLLCFG0_RANGE_MASK		(0x7 << PRCI_COREPLLCFG0_RANGE_SHIFT)
-# define PRCI_COREPLLCFG0_BYPASS_SHIFT		24
-# define PRCI_COREPLLCFG0_BYPASS_MASK		(0x1 << PRCI_COREPLLCFG0_BYPASS_SHIFT)
-# define PRCI_COREPLLCFG0_FSE_SHIFT		25
-# define PRCI_COREPLLCFG0_FSE_MASK		(0x1 << PRCI_COREPLLCFG0_FSE_SHIFT)
-# define PRCI_COREPLLCFG0_LOCK_SHIFT		31
-# define PRCI_COREPLLCFG0_LOCK_MASK		(0x1 << PRCI_COREPLLCFG0_LOCK_SHIFT)
 
-/* DDRPLLCFG0 */
-#define PRCI_DDRPLLCFG0_OFFSET			0xc
-# define PRCI_DDRPLLCFG0_DIVR_SHIFT		0
-# define PRCI_DDRPLLCFG0_DIVR_MASK		(0x3f << PRCI_DDRPLLCFG0_DIVR_SHIFT)
-# define PRCI_DDRPLLCFG0_DIVF_SHIFT		6
-# define PRCI_DDRPLLCFG0_DIVF_MASK		(0x1ff << PRCI_DDRPLLCFG0_DIVF_SHIFT)
-# define PRCI_DDRPLLCFG0_DIVQ_SHIFT		15
-# define PRCI_DDRPLLCFG0_DIVQ_MASK		(0x7 << PRCI_DDRPLLCFG0_DIVQ_SHIFT)
-# define PRCI_DDRPLLCFG0_RANGE_SHIFT		18
-# define PRCI_DDRPLLCFG0_RANGE_MASK		(0x7 << PRCI_DDRPLLCFG0_RANGE_SHIFT)
-# define PRCI_DDRPLLCFG0_BYPASS_SHIFT		24
-# define PRCI_DDRPLLCFG0_BYPASS_MASK		(0x1 << PRCI_DDRPLLCFG0_BYPASS_SHIFT)
-# define PRCI_DDRPLLCFG0_FSE_SHIFT		25
-# define PRCI_DDRPLLCFG0_FSE_MASK		(0x1 << PRCI_DDRPLLCFG0_FSE_SHIFT)
-# define PRCI_DDRPLLCFG0_LOCK_SHIFT		31
-# define PRCI_DDRPLLCFG0_LOCK_MASK		(0x1 << PRCI_DDRPLLCFG0_LOCK_SHIFT)
-
-/* DDRPLLCFG1 */
-#define PRCI_DDRPLLCFG1_OFFSET			0x10
-# define PRCI_DDRPLLCFG1_CKE_SHIFT		24
-# define PRCI_DDRPLLCFG1_CKE_MASK		(0x1 << PRCI_DDRPLLCFG1_CKE_SHIFT)
-
-/* GEMGXLPLLCFG0 */
-#define PRCI_GEMGXLPLLCFG0_OFFSET		0x1c
-# define PRCI_GEMGXLPLLCFG0_DIVR_SHIFT		0
-# define PRCI_GEMGXLPLLCFG0_DIVR_MASK		(0x3f << PRCI_GEMGXLPLLCFG0_DIVR_SHIFT)
-# define PRCI_GEMGXLPLLCFG0_DIVF_SHIFT		6
-# define PRCI_GEMGXLPLLCFG0_DIVF_MASK		(0x1ff << PRCI_GEMGXLPLLCFG0_DIVF_SHIFT)
-# define PRCI_GEMGXLPLLCFG0_DIVQ_SHIFT		15
-# define PRCI_GEMGXLPLLCFG0_DIVQ_MASK		(0x7 << PRCI_GEMGXLPLLCFG0_DIVQ_SHIFT)
-# define PRCI_GEMGXLPLLCFG0_RANGE_SHIFT		18
-# define PRCI_GEMGXLPLLCFG0_RANGE_MASK		(0x7 << PRCI_GEMGXLPLLCFG0_RANGE_SHIFT)
-# define PRCI_GEMGXLPLLCFG0_BYPASS_SHIFT	24
-# define PRCI_GEMGXLPLLCFG0_BYPASS_MASK		(0x1 << PRCI_GEMGXLPLLCFG0_BYPASS_SHIFT)
-# define PRCI_GEMGXLPLLCFG0_FSE_SHIFT		25
-# define PRCI_GEMGXLPLLCFG0_FSE_MASK		(0x1 << PRCI_GEMGXLPLLCFG0_FSE_SHIFT)
-# define PRCI_GEMGXLPLLCFG0_LOCK_SHIFT		31
-# define PRCI_GEMGXLPLLCFG0_LOCK_MASK		(0x1 << PRCI_GEMGXLPLLCFG0_LOCK_SHIFT)
-
-/* GEMGXLPLLCFG1 */
-#define PRCI_GEMGXLPLLCFG1_OFFSET		0x20
-# define PRCI_GEMGXLPLLCFG1_CKE_SHIFT		24
-# define PRCI_GEMGXLPLLCFG1_CKE_MASK		(0x1 << PRCI_GEMGXLPLLCFG1_CKE_SHIFT)
-
-/* CORECLKSEL */
-#define PRCI_CORECLKSEL_OFFSET			0x24
-# define PRCI_CORECLKSEL_CORECLKSEL_SHIFT	0
-# define PRCI_CORECLKSEL_CORECLKSEL_MASK	(0x1 << PRCI_CORECLKSEL_CORECLKSEL_SHIFT)
-
-/* DEVICESRESETREG */
-#define PRCI_DEVICESRESETREG_OFFSET			0x28
-# define PRCI_DEVICESRESETREG_DDR_CTRL_RST_N_SHIFT	0
-# define PRCI_DEVICESRESETREG_DDR_CTRL_RST_N_MASK	(0x1 << PRCI_DEVICESRESETREG_DDR_CTRL_RST_N_SHIFT)
-# define PRCI_DEVICESRESETREG_DDR_AXI_RST_N_SHIFT	1
-# define PRCI_DEVICESRESETREG_DDR_AXI_RST_N_MASK	(0x1 << PRCI_DEVICESRESETREG_DDR_AXI_RST_N_SHIFT)
-# define PRCI_DEVICESRESETREG_DDR_AHB_RST_N_SHIFT	2
-# define PRCI_DEVICESRESETREG_DDR_AHB_RST_N_MASK	(0x1 << PRCI_DEVICESRESETREG_DDR_AHB_RST_N_SHIFT)
-# define PRCI_DEVICESRESETREG_DDR_PHY_RST_N_SHIFT	3
-# define PRCI_DEVICESRESETREG_DDR_PHY_RST_N_MASK	(0x1 << PRCI_DEVICESRESETREG_DDR_PHY_RST_N_SHIFT)
-# define PRCI_DEVICESRESETREG_GEMGXL_RST_N_SHIFT	5
-# define PRCI_DEVICESRESETREG_GEMGXL_RST_N_MASK		(0x1 << PRCI_DEVICESRESETREG_GEMGXL_RST_N_SHIFT)
+#include <dt-bindings/clock/sifive-fu540-prci.h>
 
-/* CLKMUXSTATUSREG */
-#define PRCI_CLKMUXSTATUSREG_OFFSET			0x2c
-# define PRCI_CLKMUXSTATUSREG_TLCLKSEL_STATUS_SHIFT	1
-# define PRCI_CLKMUXSTATUSREG_TLCLKSEL_STATUS_MASK	(0x1 << PRCI_CLKMUXSTATUSREG_TLCLKSEL_STATUS_SHIFT)
+#include "fu540-prci.h"
+#include "sifive-prci.h"
 
-/*
- * Private structures
- */
+/* PRCI integration data for each WRPLL instance */
 
-/**
- * struct __prci_data - per-device-instance data
- * @va: base virtual address of the PRCI IP block
- * @hw_clks: encapsulates struct clk_hw records
- *
- * PRCI per-device instance data
- */
-struct __prci_data {
-	void __iomem *va;
-	struct clk_hw_onecell_data hw_clks;
+static struct __prci_wrpll_data __prci_corepll_data = {
+	.cfg0_offs = PRCI_COREPLLCFG0_OFFSET,
+	.cfg1_offs = PRCI_COREPLLCFG1_OFFSET,
+	.enable_bypass = sifive_prci_coreclksel_use_hfclk,
+	.disable_bypass = sifive_prci_coreclksel_use_corepll,
 };
 
-/**
- * struct __prci_wrpll_data - WRPLL configuration and integration data
- * @c: WRPLL current configuration record
- * @enable_bypass: fn ptr to code to bypass the WRPLL (if applicable; else NULL)
- * @disable_bypass: fn ptr to code to not bypass the WRPLL (or NULL)
- * @cfg0_offs: WRPLL CFG0 register offset (in bytes) from the PRCI base address
- *
- * @enable_bypass and @disable_bypass are used for WRPLL instances
- * that contain a separate external glitchless clock mux downstream
- * from the PLL.  The WRPLL internal bypass mux is not glitchless.
- */
-struct __prci_wrpll_data {
-	struct wrpll_cfg c;
-	void (*enable_bypass)(struct __prci_data *pd);
-	void (*disable_bypass)(struct __prci_data *pd);
-	u8 cfg0_offs;
+static struct __prci_wrpll_data __prci_ddrpll_data = {
+	.cfg0_offs = PRCI_DDRPLLCFG0_OFFSET,
+	.cfg1_offs = PRCI_DDRPLLCFG1_OFFSET,
 };
 
-/**
- * struct __prci_clock - describes a clock device managed by PRCI
- * @name: user-readable clock name string - should match the manual
- * @parent_name: parent name for this clock
- * @ops: struct clk_ops for the Linux clock framework to use for control
- * @hw: Linux-private clock data
- * @pwd: WRPLL-specific data, associated with this clock (if not NULL)
- * @pd: PRCI-specific data associated with this clock (if not NULL)
- *
- * PRCI clock data.  Used by the PRCI driver to register PRCI-provided
- * clocks to the Linux clock infrastructure.
- */
-struct __prci_clock {
-	const char *name;
-	const char *parent_name;
-	const struct clk_ops *ops;
-	struct clk_hw hw;
-	struct __prci_wrpll_data *pwd;
-	struct __prci_data *pd;
+static struct __prci_wrpll_data __prci_gemgxlpll_data = {
+	.cfg0_offs = PRCI_GEMGXLPLLCFG0_OFFSET,
+	.cfg1_offs = PRCI_GEMGXLPLLCFG1_OFFSET,
 };
 
-#define clk_hw_to_prci_clock(pwd) container_of(pwd, struct __prci_clock, hw)
-
-/*
- * Private functions
- */
-
-/**
- * __prci_readl() - read from a PRCI register
- * @pd: PRCI context
- * @offs: register offset to read from (in bytes, from PRCI base address)
- *
- * Read the register located at offset @offs from the base virtual
- * address of the PRCI register target described by @pd, and return
- * the value to the caller.
- *
- * Context: Any context.
- *
- * Return: the contents of the register described by @pd and @offs.
- */
-static u32 __prci_readl(struct __prci_data *pd, u32 offs)
-{
-	return readl_relaxed(pd->va + offs);
-}
-
-static void __prci_writel(u32 v, u32 offs, struct __prci_data *pd)
-{
-	writel_relaxed(v, pd->va + offs);
-}
-
-/* WRPLL-related private functions */
-
-/**
- * __prci_wrpll_unpack() - unpack WRPLL configuration registers into parameters
- * @c: ptr to a struct wrpll_cfg record to write config into
- * @r: value read from the PRCI PLL configuration register
- *
- * Given a value @r read from an FU540 PRCI PLL configuration register,
- * split it into fields and populate it into the WRPLL configuration record
- * pointed to by @c.
- *
- * The COREPLLCFG0 macros are used below, but the other *PLLCFG0 macros
- * have the same register layout.
- *
- * Context: Any context.
- */
-static void __prci_wrpll_unpack(struct wrpll_cfg *c, u32 r)
-{
-	u32 v;
-
-	v = r & PRCI_COREPLLCFG0_DIVR_MASK;
-	v >>= PRCI_COREPLLCFG0_DIVR_SHIFT;
-	c->divr = v;
-
-	v = r & PRCI_COREPLLCFG0_DIVF_MASK;
-	v >>= PRCI_COREPLLCFG0_DIVF_SHIFT;
-	c->divf = v;
-
-	v = r & PRCI_COREPLLCFG0_DIVQ_MASK;
-	v >>= PRCI_COREPLLCFG0_DIVQ_SHIFT;
-	c->divq = v;
-
-	v = r & PRCI_COREPLLCFG0_RANGE_MASK;
-	v >>= PRCI_COREPLLCFG0_RANGE_SHIFT;
-	c->range = v;
-
-	c->flags &= (WRPLL_FLAGS_INT_FEEDBACK_MASK |
-		     WRPLL_FLAGS_EXT_FEEDBACK_MASK);
-
-	/* external feedback mode not supported */
-	c->flags |= WRPLL_FLAGS_INT_FEEDBACK_MASK;
-}
-
-/**
- * __prci_wrpll_pack() - pack PLL configuration parameters into a register value
- * @c: pointer to a struct wrpll_cfg record containing the PLL's cfg
- *
- * Using a set of WRPLL configuration values pointed to by @c,
- * assemble a PRCI PLL configuration register value, and return it to
- * the caller.
- *
- * Context: Any context.  Caller must ensure that the contents of the
- *          record pointed to by @c do not change during the execution
- *          of this function.
- *
- * Returns: a value suitable for writing into a PRCI PLL configuration
- *          register
- */
-static u32 __prci_wrpll_pack(const struct wrpll_cfg *c)
-{
-	u32 r = 0;
-
-	r |= c->divr << PRCI_COREPLLCFG0_DIVR_SHIFT;
-	r |= c->divf << PRCI_COREPLLCFG0_DIVF_SHIFT;
-	r |= c->divq << PRCI_COREPLLCFG0_DIVQ_SHIFT;
-	r |= c->range << PRCI_COREPLLCFG0_RANGE_SHIFT;
-
-	/* external feedback mode not supported */
-	r |= PRCI_COREPLLCFG0_FSE_MASK;
-
-	return r;
-}
-
-/**
- * __prci_wrpll_read_cfg() - read the WRPLL configuration from the PRCI
- * @pd: PRCI context
- * @pwd: PRCI WRPLL metadata
- *
- * Read the current configuration of the PLL identified by @pwd from
- * the PRCI identified by @pd, and store it into the local configuration
- * cache in @pwd.
- *
- * Context: Any context.  Caller must prevent the records pointed to by
- *          @pd and @pwd from changing during execution.
- */
-static void __prci_wrpll_read_cfg(struct __prci_data *pd,
-				  struct __prci_wrpll_data *pwd)
-{
-	__prci_wrpll_unpack(&pwd->c, __prci_readl(pd, pwd->cfg0_offs));
-}
-
-/**
- * __prci_wrpll_write_cfg() - write WRPLL configuration into the PRCI
- * @pd: PRCI context
- * @pwd: PRCI WRPLL metadata
- * @c: WRPLL configuration record to write
- *
- * Write the WRPLL configuration described by @c into the WRPLL
- * configuration register identified by @pwd in the PRCI instance
- * described by @c.  Make a cached copy of the WRPLL's current
- * configuration so it can be used by other code.
- *
- * Context: Any context.  Caller must prevent the records pointed to by
- *          @pd and @pwd from changing during execution.
- */
-static void __prci_wrpll_write_cfg(struct __prci_data *pd,
-				   struct __prci_wrpll_data *pwd,
-				   struct wrpll_cfg *c)
-{
-	__prci_writel(__prci_wrpll_pack(c), pwd->cfg0_offs, pd);
-
-	memcpy(&pwd->c, c, sizeof(*c));
-}
-
-/* Core clock mux control */
-
-/**
- * __prci_coreclksel_use_hfclk() - switch the CORECLK mux to output HFCLK
- * @pd: struct __prci_data * for the PRCI containing the CORECLK mux reg
- *
- * Switch the CORECLK mux to the HFCLK input source; return once complete.
- *
- * Context: Any context.  Caller must prevent concurrent changes to the
- *          PRCI_CORECLKSEL_OFFSET register.
- */
-static void __prci_coreclksel_use_hfclk(struct __prci_data *pd)
-{
-	u32 r;
-
-	r = __prci_readl(pd, PRCI_CORECLKSEL_OFFSET);
-	r |= PRCI_CORECLKSEL_CORECLKSEL_MASK;
-	__prci_writel(r, PRCI_CORECLKSEL_OFFSET, pd);
-
-	r = __prci_readl(pd, PRCI_CORECLKSEL_OFFSET); /* barrier */
-}
-
-/**
- * __prci_coreclksel_use_corepll() - switch the CORECLK mux to output COREPLL
- * @pd: struct __prci_data * for the PRCI containing the CORECLK mux reg
- *
- * Switch the CORECLK mux to the PLL output clock; return once complete.
- *
- * Context: Any context.  Caller must prevent concurrent changes to the
- *          PRCI_CORECLKSEL_OFFSET register.
- */
-static void __prci_coreclksel_use_corepll(struct __prci_data *pd)
-{
-	u32 r;
-
-	r = __prci_readl(pd, PRCI_CORECLKSEL_OFFSET);
-	r &= ~PRCI_CORECLKSEL_CORECLKSEL_MASK;
-	__prci_writel(r, PRCI_CORECLKSEL_OFFSET, pd);
-
-	r = __prci_readl(pd, PRCI_CORECLKSEL_OFFSET); /* barrier */
-}
-
-/*
- * Linux clock framework integration
- *
- * See the Linux clock framework documentation for more information on
- * these functions.
- */
-
-static unsigned long sifive_fu540_prci_wrpll_recalc_rate(struct clk_hw *hw,
-							 unsigned long parent_rate)
-{
-	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
-	struct __prci_wrpll_data *pwd = pc->pwd;
-
-	return wrpll_calc_output_rate(&pwd->c, parent_rate);
-}
-
-static long sifive_fu540_prci_wrpll_round_rate(struct clk_hw *hw,
-					       unsigned long rate,
-					       unsigned long *parent_rate)
-{
-	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
-	struct __prci_wrpll_data *pwd = pc->pwd;
-	struct wrpll_cfg c;
-
-	memcpy(&c, &pwd->c, sizeof(c));
-
-	wrpll_configure_for_rate(&c, rate, *parent_rate);
-
-	return wrpll_calc_output_rate(&c, *parent_rate);
-}
-
-static int sifive_fu540_prci_wrpll_set_rate(struct clk_hw *hw,
-					    unsigned long rate,
-					    unsigned long parent_rate)
-{
-	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
-	struct __prci_wrpll_data *pwd = pc->pwd;
-	struct __prci_data *pd = pc->pd;
-	int r;
-
-	r = wrpll_configure_for_rate(&pwd->c, rate, parent_rate);
-	if (r)
-		return r;
-
-	if (pwd->enable_bypass)
-		pwd->enable_bypass(pd);
-
-	__prci_wrpll_write_cfg(pd, pwd, &pwd->c);
-
-	udelay(wrpll_calc_max_lock_us(&pwd->c));
-
-	if (pwd->disable_bypass)
-		pwd->disable_bypass(pd);
-
-	return 0;
-}
+/* Linux clock framework integration */
 
 static const struct clk_ops sifive_fu540_prci_wrpll_clk_ops = {
-	.set_rate = sifive_fu540_prci_wrpll_set_rate,
-	.round_rate = sifive_fu540_prci_wrpll_round_rate,
-	.recalc_rate = sifive_fu540_prci_wrpll_recalc_rate,
+	.set_rate = sifive_prci_wrpll_set_rate,
+	.round_rate = sifive_prci_wrpll_round_rate,
+	.recalc_rate = sifive_prci_wrpll_recalc_rate,
+	.enable = sifive_prci_clock_enable,
+	.disable = sifive_prci_clock_disable,
+	.is_enabled = sifive_clk_is_enabled,
 };
 
 static const struct clk_ops sifive_fu540_prci_wrpll_ro_clk_ops = {
-	.recalc_rate = sifive_fu540_prci_wrpll_recalc_rate,
+	.recalc_rate = sifive_prci_wrpll_recalc_rate,
 };
 
-/* TLCLKSEL clock integration */
-
-static unsigned long sifive_fu540_prci_tlclksel_recalc_rate(struct clk_hw *hw,
-							    unsigned long parent_rate)
-{
-	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
-	struct __prci_data *pd = pc->pd;
-	u32 v;
-	u8 div;
-
-	v = __prci_readl(pd, PRCI_CLKMUXSTATUSREG_OFFSET);
-	v &= PRCI_CLKMUXSTATUSREG_TLCLKSEL_STATUS_MASK;
-	div = v ? 1 : 2;
-
-	return div_u64(parent_rate, div);
-}
-
 static const struct clk_ops sifive_fu540_prci_tlclksel_clk_ops = {
-	.recalc_rate = sifive_fu540_prci_tlclksel_recalc_rate,
-};
-
-/*
- * PRCI integration data for each WRPLL instance
- */
-
-static struct __prci_wrpll_data __prci_corepll_data = {
-	.cfg0_offs = PRCI_COREPLLCFG0_OFFSET,
-	.enable_bypass = __prci_coreclksel_use_hfclk,
-	.disable_bypass = __prci_coreclksel_use_corepll,
-};
-
-static struct __prci_wrpll_data __prci_ddrpll_data = {
-	.cfg0_offs = PRCI_DDRPLLCFG0_OFFSET,
+	.recalc_rate = sifive_prci_tlclksel_recalc_rate,
 };
 
-static struct __prci_wrpll_data __prci_gemgxlpll_data = {
-	.cfg0_offs = PRCI_GEMGXLPLLCFG0_OFFSET,
-};
-
-/*
- * List of clock controls provided by the PRCI
- */
-
-static struct __prci_clock __prci_init_clocks[] = {
+/* List of clock controls provided by the PRCI */
+struct __prci_clock __prci_init_clocks_fu540[] = {
 	[PRCI_CLK_COREPLL] = {
 		.name = "corepll",
 		.parent_name = "hfclk",
@@ -506,125 +87,3 @@ static struct __prci_clock __prci_init_clocks[] = {
 		.ops = &sifive_fu540_prci_tlclksel_clk_ops,
 	},
 };
-
-/**
- * __prci_register_clocks() - register clock controls in the PRCI with Linux
- * @dev: Linux struct device *
- *
- * Register the list of clock controls described in __prci_init_plls[] with
- * the Linux clock framework.
- *
- * Return: 0 upon success or a negative error code upon failure.
- */
-static int __prci_register_clocks(struct device *dev, struct __prci_data *pd)
-{
-	struct clk_init_data init = { };
-	struct __prci_clock *pic;
-	int parent_count, i, r;
-
-	parent_count = of_clk_get_parent_count(dev->of_node);
-	if (parent_count != EXPECTED_CLK_PARENT_COUNT) {
-		dev_err(dev, "expected only two parent clocks, found %d\n",
-			parent_count);
-		return -EINVAL;
-	}
-
-	/* Register PLLs */
-	for (i = 0; i < ARRAY_SIZE(__prci_init_clocks); ++i) {
-		pic = &__prci_init_clocks[i];
-
-		init.name = pic->name;
-		init.parent_names = &pic->parent_name;
-		init.num_parents = 1;
-		init.ops = pic->ops;
-		pic->hw.init = &init;
-
-		pic->pd = pd;
-
-		if (pic->pwd)
-			__prci_wrpll_read_cfg(pd, pic->pwd);
-
-		r = devm_clk_hw_register(dev, &pic->hw);
-		if (r) {
-			dev_warn(dev, "Failed to register clock %s: %d\n",
-				 init.name, r);
-			return r;
-		}
-
-		r = clk_hw_register_clkdev(&pic->hw, pic->name, dev_name(dev));
-		if (r) {
-			dev_warn(dev, "Failed to register clkdev for %s: %d\n",
-				 init.name, r);
-			return r;
-		}
-
-		pd->hw_clks.hws[i] = &pic->hw;
-	}
-
-	pd->hw_clks.num = i;
-
-	r = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get,
-					&pd->hw_clks);
-	if (r) {
-		dev_err(dev, "could not add hw_provider: %d\n", r);
-		return r;
-	}
-
-	return 0;
-}
-
-/*
- * Linux device model integration
- *
- * See the Linux device model documentation for more information about
- * these functions.
- */
-static int sifive_fu540_prci_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct resource *res;
-	struct __prci_data *pd;
-	int r;
-
-	pd = devm_kzalloc(dev,
-			  struct_size(pd, hw_clks.hws,
-				      ARRAY_SIZE(__prci_init_clocks)),
-			  GFP_KERNEL);
-	if (!pd)
-		return -ENOMEM;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	pd->va = devm_ioremap_resource(dev, res);
-	if (IS_ERR(pd->va))
-		return PTR_ERR(pd->va);
-
-	r = __prci_register_clocks(dev, pd);
-	if (r) {
-		dev_err(dev, "could not register clocks: %d\n", r);
-		return r;
-	}
-
-	dev_dbg(dev, "SiFive FU540 PRCI probed\n");
-
-	return 0;
-}
-
-static const struct of_device_id sifive_fu540_prci_of_match[] = {
-	{ .compatible = "sifive,fu540-c000-prci", },
-	{}
-};
-MODULE_DEVICE_TABLE(of, sifive_fu540_prci_of_match);
-
-static struct platform_driver sifive_fu540_prci_driver = {
-	.driver	= {
-		.name = "sifive-fu540-prci",
-		.of_match_table = sifive_fu540_prci_of_match,
-	},
-	.probe = sifive_fu540_prci_probe,
-};
-
-static int __init sifive_fu540_prci_init(void)
-{
-	return platform_driver_register(&sifive_fu540_prci_driver);
-}
-core_initcall(sifive_fu540_prci_init);
diff --git a/drivers/clk/sifive/fu540-prci.h b/drivers/clk/sifive/fu540-prci.h
new file mode 100644
index 000000000000..c8271efa7bdc
--- /dev/null
+++ b/drivers/clk/sifive/fu540-prci.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 SiFive, Inc.
+ * Zong Li
+ */
+
+#ifndef __SIFIVE_CLK_FU540_PRCI_H
+#define __SIFIVE_CLK_FU540_PRCI_H
+
+#include "sifive-prci.h"
+
+#define NUM_CLOCK_FU540	4
+
+extern struct __prci_clock __prci_init_clocks_fu540[NUM_CLOCK_FU540];
+
+static const struct prci_clk_desc prci_clk_fu540 = {
+	.clks = __prci_init_clocks_fu540,
+	.num_clks = ARRAY_SIZE(__prci_init_clocks_fu540),
+};
+
+#endif /* __SIFIVE_CLK_FU540_PRCI_H */
diff --git a/drivers/clk/sifive/fu740-prci.c b/drivers/clk/sifive/fu740-prci.c
new file mode 100644
index 000000000000..764d1097aa51
--- /dev/null
+++ b/drivers/clk/sifive/fu740-prci.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 SiFive, Inc.
+ * Copyright (C) 2020 Zong Li
+ */
+
+#include <linux/module.h>
+
+#include <dt-bindings/clock/sifive-fu740-prci.h>
+
+#include "fu540-prci.h"
+#include "sifive-prci.h"
+
+/* PRCI integration data for each WRPLL instance */
+
+static struct __prci_wrpll_data __prci_corepll_data = {
+	.cfg0_offs = PRCI_COREPLLCFG0_OFFSET,
+	.cfg1_offs = PRCI_COREPLLCFG1_OFFSET,
+	.enable_bypass = sifive_prci_coreclksel_use_hfclk,
+	.disable_bypass = sifive_prci_coreclksel_use_final_corepll,
+};
+
+static struct __prci_wrpll_data __prci_ddrpll_data = {
+	.cfg0_offs = PRCI_DDRPLLCFG0_OFFSET,
+	.cfg1_offs = PRCI_DDRPLLCFG1_OFFSET,
+};
+
+static struct __prci_wrpll_data __prci_gemgxlpll_data = {
+	.cfg0_offs = PRCI_GEMGXLPLLCFG0_OFFSET,
+	.cfg1_offs = PRCI_GEMGXLPLLCFG1_OFFSET,
+};
+
+static struct __prci_wrpll_data __prci_dvfscorepll_data = {
+	.cfg0_offs = PRCI_DVFSCOREPLLCFG0_OFFSET,
+	.cfg1_offs = PRCI_DVFSCOREPLLCFG1_OFFSET,
+	.enable_bypass = sifive_prci_corepllsel_use_corepll,
+	.disable_bypass = sifive_prci_corepllsel_use_dvfscorepll,
+};
+
+static struct __prci_wrpll_data __prci_hfpclkpll_data = {
+	.cfg0_offs = PRCI_HFPCLKPLLCFG0_OFFSET,
+	.cfg1_offs = PRCI_HFPCLKPLLCFG1_OFFSET,
+	.enable_bypass = sifive_prci_hfpclkpllsel_use_hfclk,
+	.disable_bypass = sifive_prci_hfpclkpllsel_use_hfpclkpll,
+};
+
+static struct __prci_wrpll_data __prci_cltxpll_data = {
+	.cfg0_offs = PRCI_CLTXPLLCFG0_OFFSET,
+	.cfg1_offs = PRCI_CLTXPLLCFG1_OFFSET,
+};
+
+/* Linux clock framework integration */
+
+static const struct clk_ops sifive_fu740_prci_wrpll_clk_ops = {
+	.set_rate = sifive_prci_wrpll_set_rate,
+	.round_rate = sifive_prci_wrpll_round_rate,
+	.recalc_rate = sifive_prci_wrpll_recalc_rate,
+	.enable = sifive_prci_clock_enable,
+	.disable = sifive_prci_clock_disable,
+	.is_enabled = sifive_clk_is_enabled,
+};
+
+static const struct clk_ops sifive_fu740_prci_wrpll_ro_clk_ops = {
+	.recalc_rate = sifive_prci_wrpll_recalc_rate,
+};
+
+static const struct clk_ops sifive_fu740_prci_tlclksel_clk_ops = {
+	.recalc_rate = sifive_prci_tlclksel_recalc_rate,
+};
+
+static const struct clk_ops sifive_fu740_prci_hfpclkplldiv_clk_ops = {
+	.recalc_rate = sifive_prci_hfpclkplldiv_recalc_rate,
+};
+
+/* List of clock controls provided by the PRCI */
+struct __prci_clock __prci_init_clocks_fu740[] = {
+	[PRCI_CLK_COREPLL] = {
+		.name = "corepll",
+		.parent_name = "hfclk",
+		.ops = &sifive_fu740_prci_wrpll_clk_ops,
+		.pwd = &__prci_corepll_data,
+	},
+	[PRCI_CLK_DDRPLL] = {
+		.name = "ddrpll",
+		.parent_name = "hfclk",
+		.ops = &sifive_fu740_prci_wrpll_ro_clk_ops,
+		.pwd = &__prci_ddrpll_data,
+	},
+	[PRCI_CLK_GEMGXLPLL] = {
+		.name = "gemgxlpll",
+		.parent_name = "hfclk",
+		.ops = &sifive_fu740_prci_wrpll_clk_ops,
+		.pwd = &__prci_gemgxlpll_data,
+	},
+	[PRCI_CLK_DVFSCOREPLL] = {
+		.name = "dvfscorepll",
+		.parent_name = "hfclk",
+		.ops = &sifive_fu740_prci_wrpll_clk_ops,
+		.pwd = &__prci_dvfscorepll_data,
+	},
+	[PRCI_CLK_HFPCLKPLL] = {
+		.name = "hfpclkpll",
+		.parent_name = "hfclk",
+		.ops = &sifive_fu740_prci_wrpll_clk_ops,
+		.pwd = &__prci_hfpclkpll_data,
+	},
+	[PRCI_CLK_CLTXPLL] = {
+		.name = "cltxpll",
+		.parent_name = "hfclk",
+		.ops = &sifive_fu740_prci_wrpll_clk_ops,
+		.pwd = &__prci_cltxpll_data,
+	},
+	[PRCI_CLK_TLCLK] = {
+		.name = "tlclk",
+		.parent_name = "corepll",
+		.ops = &sifive_fu740_prci_tlclksel_clk_ops,
+	},
+	[PRCI_CLK_PCLK] = {
+		.name = "pclk",
+		.parent_name = "hfpclkpll",
+		.ops = &sifive_fu740_prci_hfpclkplldiv_clk_ops,
+	},
+};
diff --git a/drivers/clk/sifive/fu740-prci.h b/drivers/clk/sifive/fu740-prci.h
new file mode 100644
index 000000000000..13ef971f7764
--- /dev/null
+++ b/drivers/clk/sifive/fu740-prci.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 SiFive, Inc.
+ * Zong Li
+ */
+
+#ifndef __SIFIVE_CLK_FU740_PRCI_H
+#define __SIFIVE_CLK_FU740_PRCI_H
+
+#include "sifive-prci.h"
+
+#define NUM_CLOCK_FU740	8
+
+extern struct __prci_clock __prci_init_clocks_fu740[NUM_CLOCK_FU740];
+
+static const struct prci_clk_desc prci_clk_fu740 = {
+	.clks = __prci_init_clocks_fu740,
+	.num_clks = ARRAY_SIZE(__prci_init_clocks_fu740),
+};
+
+#endif /* __SIFIVE_CLK_FU740_PRCI_H */
diff --git a/drivers/clk/sifive/sifive-prci.c b/drivers/clk/sifive/sifive-prci.c
new file mode 100644
index 000000000000..c78b042750e2
--- /dev/null
+++ b/drivers/clk/sifive/sifive-prci.c
@@ -0,0 +1,574 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 SiFive, Inc.
+ * Copyright (C) 2020 Zong Li
+ */
+
+#include <linux/clkdev.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/of_device.h>
+#include "sifive-prci.h"
+#include "fu540-prci.h"
+#include "fu740-prci.h"
+
+/*
+ * Private functions
+ */
+
+/**
+ * __prci_readl() - read from a PRCI register
+ * @pd: PRCI context
+ * @offs: register offset to read from (in bytes, from PRCI base address)
+ *
+ * Read the register located at offset @offs from the base virtual
+ * address of the PRCI register target described by @pd, and return
+ * the value to the caller.
+ *
+ * Context: Any context.
+ *
+ * Return: the contents of the register described by @pd and @offs.
+ */
+static u32 __prci_readl(struct __prci_data *pd, u32 offs)
+{
+	return readl_relaxed(pd->va + offs);
+}
+
+static void __prci_writel(u32 v, u32 offs, struct __prci_data *pd)
+{
+	writel_relaxed(v, pd->va + offs);
+}
+
+/* WRPLL-related private functions */
+
+/**
+ * __prci_wrpll_unpack() - unpack WRPLL configuration registers into parameters
+ * @c: ptr to a struct wrpll_cfg record to write config into
+ * @r: value read from the PRCI PLL configuration register
+ *
+ * Given a value @r read from an FU740 PRCI PLL configuration register,
+ * split it into fields and populate it into the WRPLL configuration record
+ * pointed to by @c.
+ *
+ * The COREPLLCFG0 macros are used below, but the other *PLLCFG0 macros
+ * have the same register layout.
+ *
+ * Context: Any context.
+ */
+static void __prci_wrpll_unpack(struct wrpll_cfg *c, u32 r)
+{
+	u32 v;
+
+	v = r & PRCI_COREPLLCFG0_DIVR_MASK;
+	v >>= PRCI_COREPLLCFG0_DIVR_SHIFT;
+	c->divr = v;
+
+	v = r & PRCI_COREPLLCFG0_DIVF_MASK;
+	v >>= PRCI_COREPLLCFG0_DIVF_SHIFT;
+	c->divf = v;
+
+	v = r & PRCI_COREPLLCFG0_DIVQ_MASK;
+	v >>= PRCI_COREPLLCFG0_DIVQ_SHIFT;
+	c->divq = v;
+
+	v = r & PRCI_COREPLLCFG0_RANGE_MASK;
+	v >>= PRCI_COREPLLCFG0_RANGE_SHIFT;
+	c->range = v;
+
+	c->flags &=
+	    (WRPLL_FLAGS_INT_FEEDBACK_MASK | WRPLL_FLAGS_EXT_FEEDBACK_MASK);
+
+	/* external feedback mode not supported */
+	c->flags |= WRPLL_FLAGS_INT_FEEDBACK_MASK;
+}
+
+/**
+ * __prci_wrpll_pack() - pack PLL configuration parameters into a register value
+ * @c: pointer to a struct wrpll_cfg record containing the PLL's cfg
+ *
+ * Using a set of WRPLL configuration values pointed to by @c,
+ * assemble a PRCI PLL configuration register value, and return it to
+ * the caller.
+ *
+ * Context: Any context.  Caller must ensure that the contents of the
+ *          record pointed to by @c do not change during the execution
+ *          of this function.
+ *
+ * Returns: a value suitable for writing into a PRCI PLL configuration
+ *          register
+ */
+static u32 __prci_wrpll_pack(const struct wrpll_cfg *c)
+{
+	u32 r = 0;
+
+	r |= c->divr << PRCI_COREPLLCFG0_DIVR_SHIFT;
+	r |= c->divf << PRCI_COREPLLCFG0_DIVF_SHIFT;
+	r |= c->divq << PRCI_COREPLLCFG0_DIVQ_SHIFT;
+	r |= c->range << PRCI_COREPLLCFG0_RANGE_SHIFT;
+
+	/* external feedback mode not supported */
+	r |= PRCI_COREPLLCFG0_FSE_MASK;
+
+	return r;
+}
+
+/**
+ * __prci_wrpll_read_cfg0() - read the WRPLL configuration from the PRCI
+ * @pd: PRCI context
+ * @pwd: PRCI WRPLL metadata
+ *
+ * Read the current configuration of the PLL identified by @pwd from
+ * the PRCI identified by @pd, and store it into the local configuration
+ * cache in @pwd.
+ *
+ * Context: Any context.  Caller must prevent the records pointed to by
+ *          @pd and @pwd from changing during execution.
+ */
+static void __prci_wrpll_read_cfg0(struct __prci_data *pd,
+				   struct __prci_wrpll_data *pwd)
+{
+	__prci_wrpll_unpack(&pwd->c, __prci_readl(pd, pwd->cfg0_offs));
+}
+
+/**
+ * __prci_wrpll_write_cfg0() - write WRPLL configuration into the PRCI
+ * @pd: PRCI context
+ * @pwd: PRCI WRPLL metadata
+ * @c: WRPLL configuration record to write
+ *
+ * Write the WRPLL configuration described by @c into the WRPLL
+ * configuration register identified by @pwd in the PRCI instance
+ * described by @c.  Make a cached copy of the WRPLL's current
+ * configuration so it can be used by other code.
+ *
+ * Context: Any context.  Caller must prevent the records pointed to by
+ *          @pd and @pwd from changing during execution.
+ */
+static void __prci_wrpll_write_cfg0(struct __prci_data *pd,
+				    struct __prci_wrpll_data *pwd,
+				    struct wrpll_cfg *c)
+{
+	__prci_writel(__prci_wrpll_pack(c), pwd->cfg0_offs, pd);
+
+	memcpy(&pwd->c, c, sizeof(*c));
+}
+
+/**
+ * __prci_wrpll_write_cfg1() - write Clock enable/disable configuration
+ * into the PRCI
+ * @pd: PRCI context
+ * @pwd: PRCI WRPLL metadata
+ * @enable: Clock enable or disable value
+ */
+static void __prci_wrpll_write_cfg1(struct __prci_data *pd,
+				    struct __prci_wrpll_data *pwd,
+				    u32 enable)
+{
+	__prci_writel(enable, pwd->cfg1_offs, pd);
+}
+
+/*
+ * Linux clock framework integration
+ *
+ * See the Linux clock framework documentation for more information on
+ * these functions.
+ */
+
+unsigned long sifive_prci_wrpll_recalc_rate(struct clk_hw *hw,
+					    unsigned long parent_rate)
+{
+	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
+	struct __prci_wrpll_data *pwd = pc->pwd;
+
+	return wrpll_calc_output_rate(&pwd->c, parent_rate);
+}
+
+long sifive_prci_wrpll_round_rate(struct clk_hw *hw,
+				  unsigned long rate,
+				  unsigned long *parent_rate)
+{
+	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
+	struct __prci_wrpll_data *pwd = pc->pwd;
+	struct wrpll_cfg c;
+
+	memcpy(&c, &pwd->c, sizeof(c));
+
+	wrpll_configure_for_rate(&c, rate, *parent_rate);
+
+	return wrpll_calc_output_rate(&c, *parent_rate);
+}
+
+int sifive_prci_wrpll_set_rate(struct clk_hw *hw,
+			       unsigned long rate, unsigned long parent_rate)
+{
+	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
+	struct __prci_wrpll_data *pwd = pc->pwd;
+	struct __prci_data *pd = pc->pd;
+	int r;
+
+	r = wrpll_configure_for_rate(&pwd->c, rate, parent_rate);
+	if (r)
+		return r;
+
+	if (pwd->enable_bypass)
+		pwd->enable_bypass(pd);
+
+	__prci_wrpll_write_cfg0(pd, pwd, &pwd->c);
+
+	udelay(wrpll_calc_max_lock_us(&pwd->c));
+
+	return 0;
+}
+
+int sifive_clk_is_enabled(struct clk_hw *hw)
+{
+	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
+	struct __prci_wrpll_data *pwd = pc->pwd;
+	struct __prci_data *pd = pc->pd;
+	u32 r;
+
+	r = __prci_readl(pd, pwd->cfg1_offs);
+
+	if (r & PRCI_COREPLLCFG1_CKE_MASK)
+		return 1;
+	else
+		return 0;
+}
+
+int sifive_prci_clock_enable(struct clk_hw *hw)
+{
+	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
+	struct __prci_wrpll_data *pwd = pc->pwd;
+	struct __prci_data *pd = pc->pd;
+
+	if (sifive_clk_is_enabled(hw))
+		return 0;
+
+	__prci_wrpll_write_cfg1(pd, pwd, PRCI_COREPLLCFG1_CKE_MASK);
+
+	if (pwd->disable_bypass)
+		pwd->disable_bypass(pd);
+
+	return 0;
+}
+
+void sifive_prci_clock_disable(struct clk_hw *hw)
+{
+	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
+	struct __prci_wrpll_data *pwd = pc->pwd;
+	struct __prci_data *pd = pc->pd;
+	u32 r;
+
+	if (pwd->enable_bypass)
+		pwd->enable_bypass(pd);
+
+	r = __prci_readl(pd, pwd->cfg1_offs);
+	r &= ~PRCI_COREPLLCFG1_CKE_MASK;
+
+	__prci_wrpll_write_cfg1(pd, pwd, r);
+}
+
+/* TLCLKSEL clock integration */
+
+unsigned long sifive_prci_tlclksel_recalc_rate(struct clk_hw *hw,
+					       unsigned long parent_rate)
+{
+	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
+	struct __prci_data *pd = pc->pd;
+	u32 v;
+	u8 div;
+
+	v = __prci_readl(pd, PRCI_CLKMUXSTATUSREG_OFFSET);
+	v &= PRCI_CLKMUXSTATUSREG_TLCLKSEL_STATUS_MASK;
+	div = v ? 1 : 2;
+
+	return div_u64(parent_rate, div);
+}
+
+/* HFPCLK clock integration */
+
+unsigned long sifive_prci_hfpclkplldiv_recalc_rate(struct clk_hw *hw,
+						   unsigned long parent_rate)
+{
+	struct __prci_clock *pc = clk_hw_to_prci_clock(hw);
+	struct __prci_data *pd = pc->pd;
+	u32 div = __prci_readl(pd, PRCI_HFPCLKPLLDIV_OFFSET);
+
+	return div_u64(parent_rate, div + 2);
+}
+
+/*
+ * Core clock mux control
+ */
+
+/**
+ * sifive_prci_coreclksel_use_hfclk() - switch the CORECLK mux to output HFCLK
+ * @pd: struct __prci_data * for the PRCI containing the CORECLK mux reg
+ *
+ * Switch the CORECLK mux to the HFCLK input source; return once complete.
+ *
+ * Context: Any context.  Caller must prevent concurrent changes to the
+ *          PRCI_CORECLKSEL_OFFSET register.
+ */
+void sifive_prci_coreclksel_use_hfclk(struct __prci_data *pd)
+{
+	u32 r;
+
+	r = __prci_readl(pd, PRCI_CORECLKSEL_OFFSET);
+	r |= PRCI_CORECLKSEL_CORECLKSEL_MASK;
+	__prci_writel(r, PRCI_CORECLKSEL_OFFSET, pd);
+
+	r = __prci_readl(pd, PRCI_CORECLKSEL_OFFSET);	/* barrier */
+}
+
+/**
+ * sifive_prci_coreclksel_use_corepll() - switch the CORECLK mux to output
+ * COREPLL
+ * @pd: struct __prci_data * for the PRCI containing the CORECLK mux reg
+ *
+ * Switch the CORECLK mux to the COREPLL output clock; return once complete.
+ *
+ * Context: Any context.  Caller must prevent concurrent changes to the
+ *          PRCI_CORECLKSEL_OFFSET register.
+ */
+void sifive_prci_coreclksel_use_corepll(struct __prci_data *pd)
+{
+	u32 r;
+
+	r = __prci_readl(pd, PRCI_CORECLKSEL_OFFSET);
+	r &= ~PRCI_CORECLKSEL_CORECLKSEL_MASK;
+	__prci_writel(r, PRCI_CORECLKSEL_OFFSET, pd);
+
+	r = __prci_readl(pd, PRCI_CORECLKSEL_OFFSET);	/* barrier */
+}
+
+/**
+ * sifive_prci_coreclksel_use_final_corepll() - switch the CORECLK mux to output
+ * FINAL_COREPLL
+ * @pd: struct __prci_data * for the PRCI containing the CORECLK mux reg
+ *
+ * Switch the CORECLK mux to the final COREPLL output clock; return once
+ * complete.
+ *
+ * Context: Any context.  Caller must prevent concurrent changes to the
+ *          PRCI_CORECLKSEL_OFFSET register.
+ */
+void sifive_prci_coreclksel_use_final_corepll(struct __prci_data *pd)
+{
+	u32 r;
+
+	r = __prci_readl(pd, PRCI_CORECLKSEL_OFFSET);
+	r &= ~PRCI_CORECLKSEL_CORECLKSEL_MASK;
+	__prci_writel(r, PRCI_CORECLKSEL_OFFSET, pd);
+
+	r = __prci_readl(pd, PRCI_CORECLKSEL_OFFSET);	/* barrier */
+}
+
+/**
+ * sifive_prci_corepllsel_use_dvfscorepll() - switch the COREPLL mux to
+ * output DVFS_COREPLL
+ * @pd: struct __prci_data * for the PRCI containing the COREPLL mux reg
+ *
+ * Switch the COREPLL mux to the DVFSCOREPLL output clock; return once complete.
+ *
+ * Context: Any context.  Caller must prevent concurrent changes to the
+ *          PRCI_COREPLLSEL_OFFSET register.
+ */
+void sifive_prci_corepllsel_use_dvfscorepll(struct __prci_data *pd)
+{
+	u32 r;
+
+	r = __prci_readl(pd, PRCI_COREPLLSEL_OFFSET);
+	r |= PRCI_COREPLLSEL_COREPLLSEL_MASK;
+	__prci_writel(r, PRCI_COREPLLSEL_OFFSET, pd);
+
+	r = __prci_readl(pd, PRCI_COREPLLSEL_OFFSET);	/* barrier */
+}
+
+/**
+ * sifive_prci_corepllsel_use_corepll() - switch the COREPLL mux to
+ * output COREPLL
+ * @pd: struct __prci_data * for the PRCI containing the COREPLL mux reg
+ *
+ * Switch the COREPLL mux to the COREPLL output clock; return once complete.
+ *
+ * Context: Any context.  Caller must prevent concurrent changes to the
+ *          PRCI_COREPLLSEL_OFFSET register.
+ */
+void sifive_prci_corepllsel_use_corepll(struct __prci_data *pd)
+{
+	u32 r;
+
+	r = __prci_readl(pd, PRCI_COREPLLSEL_OFFSET);
+	r &= ~PRCI_COREPLLSEL_COREPLLSEL_MASK;
+	__prci_writel(r, PRCI_COREPLLSEL_OFFSET, pd);
+
+	r = __prci_readl(pd, PRCI_COREPLLSEL_OFFSET);	/* barrier */
+}
+
+/**
+ * sifive_prci_hfpclkpllsel_use_hfclk() - switch the HFPCLKPLL mux to
+ * output HFCLK
+ * @pd: struct __prci_data * for the PRCI containing the HFPCLKPLL mux reg
+ *
+ * Switch the HFPCLKPLL mux to the HFCLK input source; return once complete.
+ *
+ * Context: Any context.  Caller must prevent concurrent changes to the
+ *          PRCI_HFPCLKPLLSEL_OFFSET register.
+ */
+void sifive_prci_hfpclkpllsel_use_hfclk(struct __prci_data *pd)
+{
+	u32 r;
+
+	r = __prci_readl(pd, PRCI_HFPCLKPLLSEL_OFFSET);
+	r |= PRCI_HFPCLKPLLSEL_HFPCLKPLLSEL_MASK;
+	__prci_writel(r, PRCI_HFPCLKPLLSEL_OFFSET, pd);
+
+	r = __prci_readl(pd, PRCI_HFPCLKPLLSEL_OFFSET);	/* barrier */
+}
+
+/**
+ * sifive_prci_hfpclkpllsel_use_hfpclkpll() - switch the HFPCLKPLL mux to
+ * output HFPCLKPLL
+ * @pd: struct __prci_data * for the PRCI containing the HFPCLKPLL mux reg
+ *
+ * Switch the HFPCLKPLL mux to the HFPCLKPLL output clock; return once complete.
+ *
+ * Context: Any context.  Caller must prevent concurrent changes to the
+ *          PRCI_HFPCLKPLLSEL_OFFSET register.
+ */
+void sifive_prci_hfpclkpllsel_use_hfpclkpll(struct __prci_data *pd)
+{
+	u32 r;
+
+	r = __prci_readl(pd, PRCI_HFPCLKPLLSEL_OFFSET);
+	r &= ~PRCI_HFPCLKPLLSEL_HFPCLKPLLSEL_MASK;
+	__prci_writel(r, PRCI_HFPCLKPLLSEL_OFFSET, pd);
+
+	r = __prci_readl(pd, PRCI_HFPCLKPLLSEL_OFFSET);	/* barrier */
+}
+
+/**
+ * __prci_register_clocks() - register clock controls in the PRCI
+ * @dev: Linux struct device
+ * @pd: The pointer for PRCI per-device instance data
+ * @desc: The pointer for the information of clocks of each SoCs
+ *
+ * Register the list of clock controls described in __prci_init_clocks[] with
+ * the Linux clock framework.
+ *
+ * Return: 0 upon success or a negative error code upon failure.
+ */
+static int __prci_register_clocks(struct device *dev, struct __prci_data *pd,
+				  const struct prci_clk_desc *desc)
+{
+	struct clk_init_data init = { };
+	struct __prci_clock *pic;
+	int parent_count, i, r;
+
+	parent_count = of_clk_get_parent_count(dev->of_node);
+	if (parent_count != EXPECTED_CLK_PARENT_COUNT) {
+		dev_err(dev, "expected only two parent clocks, found %d\n",
+			parent_count);
+		return -EINVAL;
+	}
+
+	/* Register PLLs */
+	for (i = 0; i < desc->num_clks; ++i) {
+		pic = &(desc->clks[i]);
+
+		init.name = pic->name;
+		init.parent_names = &pic->parent_name;
+		init.num_parents = 1;
+		init.ops = pic->ops;
+		pic->hw.init = &init;
+
+		pic->pd = pd;
+
+		if (pic->pwd)
+			__prci_wrpll_read_cfg0(pd, pic->pwd);
+
+		r = devm_clk_hw_register(dev, &pic->hw);
+		if (r) {
+			dev_warn(dev, "Failed to register clock %s: %d\n",
+				 init.name, r);
+			return r;
+		}
+
+		r = clk_hw_register_clkdev(&pic->hw, pic->name, dev_name(dev));
+		if (r) {
+			dev_warn(dev, "Failed to register clkdev for %s: %d\n",
+				 init.name, r);
+			return r;
+		}
+
+		pd->hw_clks.hws[i] = &pic->hw;
+	}
+
+	pd->hw_clks.num = i;
+
+	r = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get,
+					&pd->hw_clks);
+	if (r) {
+		dev_err(dev, "could not add hw_provider: %d\n", r);
+		return r;
+	}
+
+	return 0;
+}
+
+/**
+ * sifive_prci_init() - initialize prci data and check parent count
+ * @pdev: platform device pointer for the prci
+ *
+ * Return: 0 upon success or a negative error code upon failure.
+ */
+static int sifive_prci_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct __prci_data *pd;
+	const struct prci_clk_desc *desc;
+	int r;
+
+	desc = of_device_get_match_data(&pdev->dev);
+
+	pd = devm_kzalloc(dev, struct_size(pd, hw_clks.hws, desc->num_clks), GFP_KERNEL);
+	if (!pd)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	pd->va = devm_ioremap_resource(dev, res);
+	if (IS_ERR(pd->va))
+		return PTR_ERR(pd->va);
+
+	r = __prci_register_clocks(dev, pd, desc);
+	if (r) {
+		dev_err(dev, "could not register clocks: %d\n", r);
+		return r;
+	}
+
+	dev_dbg(dev, "SiFive PRCI probed\n");
+
+	return 0;
+}
+
+static const struct of_device_id sifive_prci_of_match[] = {
+	{.compatible = "sifive,fu540-c000-prci", .data = &prci_clk_fu540},
+	{.compatible = "sifive,fu740-c000-prci", .data = &prci_clk_fu740},
+	{}
+};
+
+static struct platform_driver sifive_prci_driver = {
+	.driver = {
+		.name = "sifive-clk-prci",
+		.of_match_table = sifive_prci_of_match,
+	},
+	.probe = sifive_prci_probe,
+};
+
+static int __init sifive_prci_init(void)
+{
+	return platform_driver_register(&sifive_prci_driver);
+}
+core_initcall(sifive_prci_init);
diff --git a/drivers/clk/sifive/sifive-prci.h b/drivers/clk/sifive/sifive-prci.h
new file mode 100644
index 000000000000..dbdbd1722688
--- /dev/null
+++ b/drivers/clk/sifive/sifive-prci.h
@@ -0,0 +1,299 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018-2019 SiFive, Inc.
+ * Wesley Terpstra
+ * Paul Walmsley
+ * Zong Li
+ */
+
+#ifndef __SIFIVE_CLK_SIFIVE_PRCI_H
+#define __SIFIVE_CLK_SIFIVE_PRCI_H
+
+#include <linux/clk/analogbits-wrpll-cln28hpc.h>
+#include <linux/clk-provider.h>
+#include <linux/platform_device.h>
+
+/*
+ * EXPECTED_CLK_PARENT_COUNT: how many parent clocks this driver expects:
+ *     hfclk and rtcclk
+ */
+#define EXPECTED_CLK_PARENT_COUNT 2
+
+/*
+ * Register offsets and bitmasks
+ */
+
+/* COREPLLCFG0 */
+#define PRCI_COREPLLCFG0_OFFSET		0x4
+#define PRCI_COREPLLCFG0_DIVR_SHIFT	0
+#define PRCI_COREPLLCFG0_DIVR_MASK	(0x3f << PRCI_COREPLLCFG0_DIVR_SHIFT)
+#define PRCI_COREPLLCFG0_DIVF_SHIFT	6
+#define PRCI_COREPLLCFG0_DIVF_MASK	(0x1ff << PRCI_COREPLLCFG0_DIVF_SHIFT)
+#define PRCI_COREPLLCFG0_DIVQ_SHIFT	15
+#define PRCI_COREPLLCFG0_DIVQ_MASK	(0x7 << PRCI_COREPLLCFG0_DIVQ_SHIFT)
+#define PRCI_COREPLLCFG0_RANGE_SHIFT	18
+#define PRCI_COREPLLCFG0_RANGE_MASK	(0x7 << PRCI_COREPLLCFG0_RANGE_SHIFT)
+#define PRCI_COREPLLCFG0_BYPASS_SHIFT	24
+#define PRCI_COREPLLCFG0_BYPASS_MASK	(0x1 << PRCI_COREPLLCFG0_BYPASS_SHIFT)
+#define PRCI_COREPLLCFG0_FSE_SHIFT	25
+#define PRCI_COREPLLCFG0_FSE_MASK	(0x1 << PRCI_COREPLLCFG0_FSE_SHIFT)
+#define PRCI_COREPLLCFG0_LOCK_SHIFT	31
+#define PRCI_COREPLLCFG0_LOCK_MASK	(0x1 << PRCI_COREPLLCFG0_LOCK_SHIFT)
+
+/* COREPLLCFG1 */
+#define PRCI_COREPLLCFG1_OFFSET		0x8
+#define PRCI_COREPLLCFG1_CKE_SHIFT	31
+#define PRCI_COREPLLCFG1_CKE_MASK	(0x1 << PRCI_COREPLLCFG1_CKE_SHIFT)
+
+/* DDRPLLCFG0 */
+#define PRCI_DDRPLLCFG0_OFFSET		0xc
+#define PRCI_DDRPLLCFG0_DIVR_SHIFT	0
+#define PRCI_DDRPLLCFG0_DIVR_MASK	(0x3f << PRCI_DDRPLLCFG0_DIVR_SHIFT)
+#define PRCI_DDRPLLCFG0_DIVF_SHIFT	6
+#define PRCI_DDRPLLCFG0_DIVF_MASK	(0x1ff << PRCI_DDRPLLCFG0_DIVF_SHIFT)
+#define PRCI_DDRPLLCFG0_DIVQ_SHIFT	15
+#define PRCI_DDRPLLCFG0_DIVQ_MASK	(0x7 << PRCI_DDRPLLCFG0_DIVQ_SHIFT)
+#define PRCI_DDRPLLCFG0_RANGE_SHIFT	18
+#define PRCI_DDRPLLCFG0_RANGE_MASK	(0x7 << PRCI_DDRPLLCFG0_RANGE_SHIFT)
+#define PRCI_DDRPLLCFG0_BYPASS_SHIFT	24
+#define PRCI_DDRPLLCFG0_BYPASS_MASK	(0x1 << PRCI_DDRPLLCFG0_BYPASS_SHIFT)
+#define PRCI_DDRPLLCFG0_FSE_SHIFT	25
+#define PRCI_DDRPLLCFG0_FSE_MASK	(0x1 << PRCI_DDRPLLCFG0_FSE_SHIFT)
+#define PRCI_DDRPLLCFG0_LOCK_SHIFT	31
+#define PRCI_DDRPLLCFG0_LOCK_MASK	(0x1 << PRCI_DDRPLLCFG0_LOCK_SHIFT)
+
+/* DDRPLLCFG1 */
+#define PRCI_DDRPLLCFG1_OFFSET		0x10
+#define PRCI_DDRPLLCFG1_CKE_SHIFT	31
+#define PRCI_DDRPLLCFG1_CKE_MASK	(0x1 << PRCI_DDRPLLCFG1_CKE_SHIFT)
+
+/* GEMGXLPLLCFG0 */
+#define PRCI_GEMGXLPLLCFG0_OFFSET	0x1c
+#define PRCI_GEMGXLPLLCFG0_DIVR_SHIFT	0
+#define PRCI_GEMGXLPLLCFG0_DIVR_MASK	(0x3f << PRCI_GEMGXLPLLCFG0_DIVR_SHIFT)
+#define PRCI_GEMGXLPLLCFG0_DIVF_SHIFT	6
+#define PRCI_GEMGXLPLLCFG0_DIVF_MASK	(0x1ff << PRCI_GEMGXLPLLCFG0_DIVF_SHIFT)
+#define PRCI_GEMGXLPLLCFG0_DIVQ_SHIFT	15
+#define PRCI_GEMGXLPLLCFG0_DIVQ_MASK	(0x7 << PRCI_GEMGXLPLLCFG0_DIVQ_SHIFT)
+#define PRCI_GEMGXLPLLCFG0_RANGE_SHIFT	18
+#define PRCI_GEMGXLPLLCFG0_RANGE_MASK	(0x7 << PRCI_GEMGXLPLLCFG0_RANGE_SHIFT)
+#define PRCI_GEMGXLPLLCFG0_BYPASS_SHIFT	24
+#define PRCI_GEMGXLPLLCFG0_BYPASS_MASK	(0x1 << PRCI_GEMGXLPLLCFG0_BYPASS_SHIFT)
+#define PRCI_GEMGXLPLLCFG0_FSE_SHIFT	25
+#define PRCI_GEMGXLPLLCFG0_FSE_MASK	(0x1 << PRCI_GEMGXLPLLCFG0_FSE_SHIFT)
+#define PRCI_GEMGXLPLLCFG0_LOCK_SHIFT	31
+#define PRCI_GEMGXLPLLCFG0_LOCK_MASK	(0x1 << PRCI_GEMGXLPLLCFG0_LOCK_SHIFT)
+
+/* GEMGXLPLLCFG1 */
+#define PRCI_GEMGXLPLLCFG1_OFFSET	0x20
+#define PRCI_GEMGXLPLLCFG1_CKE_SHIFT	31
+#define PRCI_GEMGXLPLLCFG1_CKE_MASK	(0x1 << PRCI_GEMGXLPLLCFG1_CKE_SHIFT)
+
+/* CORECLKSEL */
+#define PRCI_CORECLKSEL_OFFSET			0x24
+#define PRCI_CORECLKSEL_CORECLKSEL_SHIFT	0
+#define PRCI_CORECLKSEL_CORECLKSEL_MASK					\
+		(0x1 << PRCI_CORECLKSEL_CORECLKSEL_SHIFT)
+
+/* DEVICESRESETREG */
+#define PRCI_DEVICESRESETREG_OFFSET				0x28
+#define PRCI_DEVICESRESETREG_DDR_CTRL_RST_N_SHIFT		0
+#define PRCI_DEVICESRESETREG_DDR_CTRL_RST_N_MASK			\
+		(0x1 << PRCI_DEVICESRESETREG_DDR_CTRL_RST_N_SHIFT)
+#define PRCI_DEVICESRESETREG_DDR_AXI_RST_N_SHIFT		1
+#define PRCI_DEVICESRESETREG_DDR_AXI_RST_N_MASK				\
+		(0x1 << PRCI_DEVICESRESETREG_DDR_AXI_RST_N_SHIFT)
+#define PRCI_DEVICESRESETREG_DDR_AHB_RST_N_SHIFT		2
+#define PRCI_DEVICESRESETREG_DDR_AHB_RST_N_MASK				\
+		(0x1 << PRCI_DEVICESRESETREG_DDR_AHB_RST_N_SHIFT)
+#define PRCI_DEVICESRESETREG_DDR_PHY_RST_N_SHIFT		3
+#define PRCI_DEVICESRESETREG_DDR_PHY_RST_N_MASK				\
+		(0x1 << PRCI_DEVICESRESETREG_DDR_PHY_RST_N_SHIFT)
+#define PRCI_DEVICESRESETREG_GEMGXL_RST_N_SHIFT			5
+#define PRCI_DEVICESRESETREG_GEMGXL_RST_N_MASK				\
+		(0x1 << PRCI_DEVICESRESETREG_GEMGXL_RST_N_SHIFT)
+#define PRCI_DEVICESRESETREG_CHIPLINK_RST_N_SHIFT		6
+#define PRCI_DEVICESRESETREG_CHIPLINK_RST_N_MASK			\
+		(0x1 << PRCI_DEVICESRESETREG_CHIPLINK_RST_N_SHIFT)
+
+/* CLKMUXSTATUSREG */
+#define PRCI_CLKMUXSTATUSREG_OFFSET				0x2c
+#define PRCI_CLKMUXSTATUSREG_TLCLKSEL_STATUS_SHIFT		1
+#define PRCI_CLKMUXSTATUSREG_TLCLKSEL_STATUS_MASK			\
+		(0x1 << PRCI_CLKMUXSTATUSREG_TLCLKSEL_STATUS_SHIFT)
+
+/* CLTXPLLCFG0 */
+#define PRCI_CLTXPLLCFG0_OFFSET		0x30
+#define PRCI_CLTXPLLCFG0_DIVR_SHIFT	0
+#define PRCI_CLTXPLLCFG0_DIVR_MASK	(0x3f << PRCI_CLTXPLLCFG0_DIVR_SHIFT)
+#define PRCI_CLTXPLLCFG0_DIVF_SHIFT	6
+#define PRCI_CLTXPLLCFG0_DIVF_MASK	(0x1ff << PRCI_CLTXPLLCFG0_DIVF_SHIFT)
+#define PRCI_CLTXPLLCFG0_DIVQ_SHIFT	15
+#define PRCI_CLTXPLLCFG0_DIVQ_MASK	(0x7 << PRCI_CLTXPLLCFG0_DIVQ_SHIFT)
+#define PRCI_CLTXPLLCFG0_RANGE_SHIFT	18
+#define PRCI_CLTXPLLCFG0_RANGE_MASK	(0x7 << PRCI_CLTXPLLCFG0_RANGE_SHIFT)
+#define PRCI_CLTXPLLCFG0_BYPASS_SHIFT	24
+#define PRCI_CLTXPLLCFG0_BYPASS_MASK	(0x1 << PRCI_CLTXPLLCFG0_BYPASS_SHIFT)
+#define PRCI_CLTXPLLCFG0_FSE_SHIFT	25
+#define PRCI_CLTXPLLCFG0_FSE_MASK	(0x1 << PRCI_CLTXPLLCFG0_FSE_SHIFT)
+#define PRCI_CLTXPLLCFG0_LOCK_SHIFT	31
+#define PRCI_CLTXPLLCFG0_LOCK_MASK	(0x1 << PRCI_CLTXPLLCFG0_LOCK_SHIFT)
+
+/* CLTXPLLCFG1 */
+#define PRCI_CLTXPLLCFG1_OFFSET		0x34
+#define PRCI_CLTXPLLCFG1_CKE_SHIFT	31
+#define PRCI_CLTXPLLCFG1_CKE_MASK	(0x1 << PRCI_CLTXPLLCFG1_CKE_SHIFT)
+
+/* DVFSCOREPLLCFG0 */
+#define PRCI_DVFSCOREPLLCFG0_OFFSET	0x38
+
+/* DVFSCOREPLLCFG1 */
+#define PRCI_DVFSCOREPLLCFG1_OFFSET	0x3c
+#define PRCI_DVFSCOREPLLCFG1_CKE_SHIFT	31
+#define PRCI_DVFSCOREPLLCFG1_CKE_MASK	(0x1 << PRCI_DVFSCOREPLLCFG1_CKE_SHIFT)
+
+/* COREPLLSEL */
+#define PRCI_COREPLLSEL_OFFSET			0x40
+#define PRCI_COREPLLSEL_COREPLLSEL_SHIFT	0
+#define PRCI_COREPLLSEL_COREPLLSEL_MASK					\
+		(0x1 << PRCI_COREPLLSEL_COREPLLSEL_SHIFT)
+
+/* HFPCLKPLLCFG0 */
+#define PRCI_HFPCLKPLLCFG0_OFFSET		0x50
+#define PRCI_HFPCLKPLL_CFG0_DIVR_SHIFT		0
+#define PRCI_HFPCLKPLL_CFG0_DIVR_MASK					\
+		(0x3f << PRCI_HFPCLKPLLCFG0_DIVR_SHIFT)
+#define PRCI_HFPCLKPLL_CFG0_DIVF_SHIFT		6
+#define PRCI_HFPCLKPLL_CFG0_DIVF_MASK					\
+		(0x1ff << PRCI_HFPCLKPLLCFG0_DIVF_SHIFT)
+#define PRCI_HFPCLKPLL_CFG0_DIVQ_SHIFT		15
+#define PRCI_HFPCLKPLL_CFG0_DIVQ_MASK					\
+		(0x7 << PRCI_HFPCLKPLLCFG0_DIVQ_SHIFT)
+#define PRCI_HFPCLKPLL_CFG0_RANGE_SHIFT		18
+#define PRCI_HFPCLKPLL_CFG0_RANGE_MASK					\
+		(0x7 << PRCI_HFPCLKPLLCFG0_RANGE_SHIFT)
+#define PRCI_HFPCLKPLL_CFG0_BYPASS_SHIFT	24
+#define PRCI_HFPCLKPLL_CFG0_BYPASS_MASK					\
+		(0x1 << PRCI_HFPCLKPLLCFG0_BYPASS_SHIFT)
+#define PRCI_HFPCLKPLL_CFG0_FSE_SHIFT		25
+#define PRCI_HFPCLKPLL_CFG0_FSE_MASK					\
+		(0x1 << PRCI_HFPCLKPLLCFG0_FSE_SHIFT)
+#define PRCI_HFPCLKPLL_CFG0_LOCK_SHIFT		31
+#define PRCI_HFPCLKPLL_CFG0_LOCK_MASK					\
+		(0x1 << PRCI_HFPCLKPLLCFG0_LOCK_SHIFT)
+
+/* HFPCLKPLLCFG1 */
+#define PRCI_HFPCLKPLLCFG1_OFFSET		0x54
+#define PRCI_HFPCLKPLLCFG1_CKE_SHIFT		31
+#define PRCI_HFPCLKPLLCFG1_CKE_MASK					\
+		(0x1 << PRCI_HFPCLKPLLCFG1_CKE_SHIFT)
+
+/* HFPCLKPLLSEL */
+#define PRCI_HFPCLKPLLSEL_OFFSET		0x58
+#define PRCI_HFPCLKPLLSEL_HFPCLKPLLSEL_SHIFT	0
+#define PRCI_HFPCLKPLLSEL_HFPCLKPLLSEL_MASK				\
+		(0x1 << PRCI_HFPCLKPLLSEL_HFPCLKPLLSEL_SHIFT)
+
+/* HFPCLKPLLDIV */
+#define PRCI_HFPCLKPLLDIV_OFFSET		0x5c
+
+/* PRCIPLL */
+#define PRCI_PRCIPLL_OFFSET			0xe0
+
+/* PROCMONCFG */
+#define PRCI_PROCMONCFG_OFFSET			0xf0
+
+/*
+ * Private structures
+ */
+
+/**
+ * struct __prci_data - per-device-instance data
+ * @va: base virtual address of the PRCI IP block
+ * @hw_clks: encapsulates struct clk_hw records
+ *
+ * PRCI per-device instance data
+ */
+struct __prci_data {
+	void __iomem *va;
+	struct clk_hw_onecell_data hw_clks;
+};
+
+/**
+ * struct __prci_wrpll_data - WRPLL configuration and integration data
+ * @c: WRPLL current configuration record
+ * @enable_bypass: fn ptr to code to bypass the WRPLL (if applicable; else NULL)
+ * @disable_bypass: fn ptr to code to not bypass the WRPLL (or NULL)
+ * @cfg0_offs: WRPLL CFG0 register offset (in bytes) from the PRCI base address
+ * @cfg1_offs: WRPLL CFG1 register offset (in bytes) from the PRCI base address
+ *
+ * @enable_bypass and @disable_bypass are used for WRPLL instances
+ * that contain a separate external glitchless clock mux downstream
+ * from the PLL.  The WRPLL internal bypass mux is not glitchless.
+ */
+struct __prci_wrpll_data {
+	struct wrpll_cfg c;
+	void (*enable_bypass)(struct __prci_data *pd);
+	void (*disable_bypass)(struct __prci_data *pd);
+	u8 cfg0_offs;
+	u8 cfg1_offs;
+};
+
+/**
+ * struct __prci_clock - describes a clock device managed by PRCI
+ * @name: user-readable clock name string - should match the manual
+ * @parent_name: parent name for this clock
+ * @ops: struct clk_ops for the Linux clock framework to use for control
+ * @hw: Linux-private clock data
+ * @pwd: WRPLL-specific data, associated with this clock (if not NULL)
+ * @pd: PRCI-specific data associated with this clock (if not NULL)
+ *
+ * PRCI clock data.  Used by the PRCI driver to register PRCI-provided
+ * clocks to the Linux clock infrastructure.
+ */
+struct __prci_clock {
+	const char *name;
+	const char *parent_name;
+	const struct clk_ops *ops;
+	struct clk_hw hw;
+	struct __prci_wrpll_data *pwd;
+	struct __prci_data *pd;
+};
+
+#define clk_hw_to_prci_clock(pwd) container_of(pwd, struct __prci_clock, hw)
+
+/*
+ * struct prci_clk_desc - describes the information of clocks of each SoCs
+ * @clks: point to a array of __prci_clock
+ * @num_clks: the number of element of clks
+ */
+struct prci_clk_desc {
+	struct __prci_clock *clks;
+	size_t num_clks;
+};
+
+/* Core clock mux control */
+void sifive_prci_coreclksel_use_hfclk(struct __prci_data *pd);
+void sifive_prci_coreclksel_use_corepll(struct __prci_data *pd);
+void sifive_prci_coreclksel_use_final_corepll(struct __prci_data *pd);
+void sifive_prci_corepllsel_use_dvfscorepll(struct __prci_data *pd);
+void sifive_prci_corepllsel_use_corepll(struct __prci_data *pd);
+void sifive_prci_hfpclkpllsel_use_hfclk(struct __prci_data *pd);
+void sifive_prci_hfpclkpllsel_use_hfpclkpll(struct __prci_data *pd);
+
+/* Linux clock framework integration */
+long sifive_prci_wrpll_round_rate(struct clk_hw *hw, unsigned long rate,
+				  unsigned long *parent_rate);
+int sifive_prci_wrpll_set_rate(struct clk_hw *hw, unsigned long rate,
+			       unsigned long parent_rate);
+int sifive_clk_is_enabled(struct clk_hw *hw);
+int sifive_prci_clock_enable(struct clk_hw *hw);
+void sifive_prci_clock_disable(struct clk_hw *hw);
+unsigned long sifive_prci_wrpll_recalc_rate(struct clk_hw *hw,
+					    unsigned long parent_rate);
+unsigned long sifive_prci_tlclksel_recalc_rate(struct clk_hw *hw,
+					       unsigned long parent_rate);
+unsigned long sifive_prci_hfpclkplldiv_recalc_rate(struct clk_hw *hw,
+						   unsigned long parent_rate);
+
+#endif /* __SIFIVE_CLK_SIFIVE_PRCI_H */
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
index 5f66bf879772..149cfde817cb 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
@@ -389,6 +389,7 @@ static struct clk_div_table ths_div_table[] = {
 	{ .val = 1, .div = 2 },
 	{ .val = 2, .div = 4 },
 	{ .val = 3, .div = 6 },
+	{ /* Sentinel */ },
 };
 static const char * const ths_parents[] = { "osc24M" };
 static struct ccu_div ths_clk = {
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-h3.c b/drivers/clk/sunxi-ng/ccu-sun8i-h3.c
index 6b636362379e..7e629a4493af 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-h3.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-h3.c
@@ -322,6 +322,7 @@ static struct clk_div_table ths_div_table[] = {
 	{ .val = 1, .div = 2 },
 	{ .val = 2, .div = 4 },
 	{ .val = 3, .div = 6 },
+	{ /* Sentinel */ },
 };
 static SUNXI_CCU_DIV_TABLE_WITH_GATE(ths_clk, "ths", "osc24M",
 				     0x074, 0, 2, ths_div_table, BIT(31), 0);
diff --git a/drivers/clk/tegra/clk-bpmp.c b/drivers/clk/tegra/clk-bpmp.c
index a66263b6490d..6ecf18f71c32 100644
--- a/drivers/clk/tegra/clk-bpmp.c
+++ b/drivers/clk/tegra/clk-bpmp.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2016 NVIDIA Corporation
+ * Copyright (C) 2016-2020 NVIDIA Corporation
  */
 
 #include <linux/clk-provider.h>
@@ -174,7 +174,7 @@ static long tegra_bpmp_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 	int err;
 
 	memset(&request, 0, sizeof(request));
-	request.rate = rate;
+	request.rate = min_t(u64, rate, S64_MAX);
 
 	memset(&msg, 0, sizeof(msg));
 	msg.cmd = CMD_CLK_ROUND_RATE;
@@ -256,7 +256,7 @@ static int tegra_bpmp_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 	struct tegra_bpmp_clk_message msg;
 
 	memset(&request, 0, sizeof(request));
-	request.rate = rate;
+	request.rate = min_t(u64, rate, S64_MAX);
 
 	memset(&msg, 0, sizeof(msg));
 	msg.cmd = CMD_CLK_SET_RATE;
diff --git a/drivers/clk/tegra/clk-dfll.c b/drivers/clk/tegra/clk-dfll.c
index cfbaa90c7adb..a5f526bb0483 100644
--- a/drivers/clk/tegra/clk-dfll.c
+++ b/drivers/clk/tegra/clk-dfll.c
@@ -1856,13 +1856,13 @@ static int dfll_fetch_pwm_params(struct tegra_dfll *td)
 			    &td->reg_init_uV);
 	if (!ret) {
 		dev_err(td->dev, "couldn't get initialized voltage\n");
-		return ret;
+		return -EINVAL;
 	}
 
 	ret = read_dt_param(td, "nvidia,pwm-period-nanoseconds", &pwm_period);
 	if (!ret) {
 		dev_err(td->dev, "couldn't get PWM period\n");
-		return ret;
+		return -EINVAL;
 	}
 	td->pwm_rate = (NSEC_PER_SEC / pwm_period) * (MAX_DFLL_VOLTAGES - 1);
 
diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h
index ff7da2d3e94d..24413812ec5b 100644
--- a/drivers/clk/tegra/clk-id.h
+++ b/drivers/clk/tegra/clk-id.h
@@ -227,6 +227,7 @@ enum clk_id {
 	tegra_clk_sdmmc4,
 	tegra_clk_sdmmc4_8,
 	tegra_clk_se,
+	tegra_clk_se_10,
 	tegra_clk_soc_therm,
 	tegra_clk_soc_therm_8,
 	tegra_clk_sor0,
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 2b2a3b81c16b..60cc34f90cb9 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -630,7 +630,7 @@ static struct tegra_periph_init_data periph_clks[] = {
 	INT8("host1x", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_HOST1X, 28, 0, tegra_clk_host1x_8),
 	INT8("host1x", mux_pllc4_out1_pllc_pllc4_out2_pllp_clkm_plla_pllc4_out0, CLK_SOURCE_HOST1X, 28, 0, tegra_clk_host1x_9),
 	INT8("se", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SE, 127, TEGRA_PERIPH_ON_APB, tegra_clk_se),
-	INT8("se", mux_pllp_pllc2_c_c3_clkm, CLK_SOURCE_SE, 127, TEGRA_PERIPH_ON_APB, tegra_clk_se),
+	INT8("se", mux_pllp_pllc2_c_c3_clkm, CLK_SOURCE_SE, 127, TEGRA_PERIPH_ON_APB, tegra_clk_se_10),
 	INT8("2d", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_2D, 21, 0, tegra_clk_gr2d_8),
 	INT8("3d", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_3D, 24, 0, tegra_clk_gr3d_8),
 	INT8("vic03", mux_pllm_pllc_pllp_plla_pllc2_c3_clkm, CLK_SOURCE_VIC03, 178, 0, tegra_clk_vic03),
diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c
index 37244a7e68c2..9cf249c344d9 100644
--- a/drivers/clk/tegra/clk-tegra30.c
+++ b/drivers/clk/tegra/clk-tegra30.c
@@ -1256,6 +1256,8 @@ static struct tegra_clk_init_table init_table[] __initdata = {
 	{ TEGRA30_CLK_I2S3_SYNC, TEGRA30_CLK_CLK_MAX, 24000000, 0 },
 	{ TEGRA30_CLK_I2S4_SYNC, TEGRA30_CLK_CLK_MAX, 24000000, 0 },
 	{ TEGRA30_CLK_VIMCLK_SYNC, TEGRA30_CLK_CLK_MAX, 24000000, 0 },
+	{ TEGRA30_CLK_HDA, TEGRA30_CLK_PLL_P, 102000000, 0 },
+	{ TEGRA30_CLK_HDA2CODEC_2X, TEGRA30_CLK_PLL_P, 48000000, 0 },
 	/* must be the last entry */
 	{ TEGRA30_CLK_CLK_MAX, TEGRA30_CLK_CLK_MAX, 0, 0 },
 };
diff --git a/drivers/clk/ti/clk-54xx.c b/drivers/clk/ti/clk-54xx.c
index 8694bc9f5fc7..f0542391ca4b 100644
--- a/drivers/clk/ti/clk-54xx.c
+++ b/drivers/clk/ti/clk-54xx.c
@@ -605,7 +605,7 @@ static struct ti_dt_clk omap54xx_clks[] = {
 int __init omap5xxx_dt_clk_init(void)
 {
 	int rc;
-	struct clk *abe_dpll_ref, *abe_dpll, *sys_32k_ck, *usb_dpll;
+	struct clk *abe_dpll_ref, *abe_dpll, *abe_dpll_byp, *sys_32k_ck, *usb_dpll;
 
 	ti_dt_clocks_register(omap54xx_clks);
 
@@ -616,6 +616,16 @@ int __init omap5xxx_dt_clk_init(void)
 	abe_dpll_ref = clk_get_sys(NULL, "abe_dpll_clk_mux");
 	sys_32k_ck = clk_get_sys(NULL, "sys_32k_ck");
 	rc = clk_set_parent(abe_dpll_ref, sys_32k_ck);
+
+	/*
+	 * This must also be set to sys_32k_ck to match or
+	 * the ABE DPLL will not lock on a warm reboot when
+	 * ABE timers are used.
+	 */
+	abe_dpll_byp = clk_get_sys(NULL, "abe_dpll_bypass_clk_mux");
+	if (!rc)
+		rc = clk_set_parent(abe_dpll_byp, sys_32k_ck);
+
 	abe_dpll = clk_get_sys(NULL, "dpll_abe_ck");
 	if (!rc)
 		rc = clk_set_rate(abe_dpll, OMAP5_DPLL_ABE_DEFFREQ);
diff --git a/drivers/clk/ti/fapll.c b/drivers/clk/ti/fapll.c
index 95e36ba64acc..8024c6d2b9e9 100644
--- a/drivers/clk/ti/fapll.c
+++ b/drivers/clk/ti/fapll.c
@@ -498,6 +498,7 @@ static struct clk * __init ti_fapll_synth_setup(struct fapll_data *fd,
 {
 	struct clk_init_data *init;
 	struct fapll_synth *synth;
+	struct clk *clk = ERR_PTR(-ENOMEM);
 
 	init = kzalloc(sizeof(*init), GFP_KERNEL);
 	if (!init)
@@ -520,13 +521,19 @@ static struct clk * __init ti_fapll_synth_setup(struct fapll_data *fd,
 	synth->hw.init = init;
 	synth->clk_pll = pll_clk;
 
-	return clk_register(NULL, &synth->hw);
+	clk = clk_register(NULL, &synth->hw);
+	if (IS_ERR(clk)) {
+		pr_err("failed to register clock\n");
+		goto free;
+	}
+
+	return clk;
 
 free:
 	kfree(synth);
 	kfree(init);
 
-	return ERR_PTR(-ENOMEM);
+	return clk;
 }
 
 static void __init ti_fapll_setup(struct device_node *node)
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 7cc9bd8568de..8a482c434ea6 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -30,13 +30,13 @@
 #define DMI_PROCESSOR_MAX_SPEED		0x14
 
 /*
- * These structs contain information parsed from per CPU
- * ACPI _CPC structures.
- * e.g. For each CPU the highest, lowest supported
- * performance capabilities, desired performance level
- * requested etc.
+ * This list contains information parsed from per CPU ACPI _CPC and _PSD
+ * structures: e.g. the highest and lowest supported performance, capabilities,
+ * desired performance, level requested etc. Depending on the share_type, not
+ * all CPUs will have an entry in the list.
  */
-static struct cppc_cpudata **all_cpu_data;
+static LIST_HEAD(cpu_data_list);
+
 static bool boost_supported;
 
 struct cppc_workaround_oem_info {
@@ -148,8 +148,10 @@ static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data,
 static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 				   unsigned int target_freq,
 				   unsigned int relation)
+
 {
-	struct cppc_cpudata *cpu_data = all_cpu_data[policy->cpu];
+	struct cppc_cpudata *cpu_data = policy->driver_data;
+	unsigned int cpu = policy->cpu;
 	struct cpufreq_freqs freqs;
 	u32 desired_perf;
 	int ret = 0;
@@ -164,12 +166,12 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 	freqs.new = target_freq;
 
 	cpufreq_freq_transition_begin(policy, &freqs);
-	ret = cppc_set_perf(cpu_data->cpu, &cpu_data->perf_ctrls);
+	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
 	cpufreq_freq_transition_end(policy, &freqs, ret != 0);
 
 	if (ret)
 		pr_debug("Failed to set target on CPU:%d. ret:%d\n",
-			 cpu_data->cpu, ret);
+			 cpu, ret);
 
 	return ret;
 }
@@ -182,7 +184,7 @@ static int cppc_verify_policy(struct cpufreq_policy_data *policy)
 
 static void cppc_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 {
-	struct cppc_cpudata *cpu_data = all_cpu_data[policy->cpu];
+	struct cppc_cpudata *cpu_data = policy->driver_data;
 	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
 	unsigned int cpu = policy->cpu;
 	int ret;
@@ -193,6 +195,12 @@ static void cppc_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 	if (ret)
 		pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
 			 caps->lowest_perf, cpu, ret);
+
+	/* Remove CPU node from list and free driver data for policy */
+	free_cpumask_var(cpu_data->shared_cpu_map);
+	list_del(&cpu_data->node);
+	kfree(policy->driver_data);
+	policy->driver_data = NULL;
 }
 
 /*
@@ -238,25 +246,61 @@ static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu)
 }
 #endif
 
-static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
+
+static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu)
 {
-	struct cppc_cpudata *cpu_data = all_cpu_data[policy->cpu];
-	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
-	unsigned int cpu = policy->cpu;
-	int ret = 0;
+	struct cppc_cpudata *cpu_data;
+	int ret;
 
-	cpu_data->cpu = cpu;
-	ret = cppc_get_perf_caps(cpu, caps);
+	cpu_data = kzalloc(sizeof(struct cppc_cpudata), GFP_KERNEL);
+	if (!cpu_data)
+		goto out;
 
+	if (!zalloc_cpumask_var(&cpu_data->shared_cpu_map, GFP_KERNEL))
+		goto free_cpu;
+
+	ret = acpi_get_psd_map(cpu, cpu_data);
 	if (ret) {
-		pr_debug("Err reading CPU%d perf capabilities. ret:%d\n",
-			 cpu, ret);
-		return ret;
+		pr_debug("Err parsing CPU%d PSD data: ret:%d\n", cpu, ret);
+		goto free_mask;
+	}
+
+	ret = cppc_get_perf_caps(cpu, &cpu_data->perf_caps);
+	if (ret) {
+		pr_debug("Err reading CPU%d perf caps: ret:%d\n", cpu, ret);
+		goto free_mask;
 	}
 
 	/* Convert the lowest and nominal freq from MHz to KHz */
-	caps->lowest_freq *= 1000;
-	caps->nominal_freq *= 1000;
+	cpu_data->perf_caps.lowest_freq *= 1000;
+	cpu_data->perf_caps.nominal_freq *= 1000;
+
+	list_add(&cpu_data->node, &cpu_data_list);
+
+	return cpu_data;
+
+free_mask:
+	free_cpumask_var(cpu_data->shared_cpu_map);
+free_cpu:
+	kfree(cpu_data);
+out:
+	return NULL;
+}
+
+static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+	unsigned int cpu = policy->cpu;
+	struct cppc_cpudata *cpu_data;
+	struct cppc_perf_caps *caps;
+	int ret;
+
+	cpu_data = cppc_cpufreq_get_cpu_data(cpu);
+	if (!cpu_data) {
+		pr_err("Error in acquiring _CPC/_PSD data for CPU%d.\n", cpu);
+		return -ENODEV;
+	}
+	caps = &cpu_data->perf_caps;
+	policy->driver_data = cpu_data;
 
 	/*
 	 * Set min to lowest nonlinear perf to avoid any efficiency penalty (see
@@ -280,26 +324,25 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu);
 	policy->shared_type = cpu_data->shared_type;
 
-	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
-		int i;
-
+	switch (policy->shared_type) {
+	case CPUFREQ_SHARED_TYPE_HW:
+	case CPUFREQ_SHARED_TYPE_NONE:
+		/* Nothing to be done - we'll have a policy for each CPU */
+		break;
+	case CPUFREQ_SHARED_TYPE_ANY:
+		/*
+		 * All CPUs in the domain will share a policy and all cpufreq
+		 * operations will use a single cppc_cpudata structure stored
+		 * in policy->driver_data.
+		 */
 		cpumask_copy(policy->cpus, cpu_data->shared_cpu_map);
-
-		for_each_cpu(i, policy->cpus) {
-			if (unlikely(i == cpu))
-				continue;
-
-			memcpy(&all_cpu_data[i]->perf_caps, caps,
-			       sizeof(cpu_data->perf_caps));
-		}
-	} else if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL) {
-		/* Support only SW_ANY for now. */
-		pr_debug("Unsupported CPU co-ord type\n");
+		break;
+	default:
+		pr_debug("Unsupported CPU co-ord type: %d\n",
+			 policy->shared_type);
 		return -EFAULT;
 	}
 
-	cpu_data->cur_policy = policy;
-
 	/*
 	 * If 'highest_perf' is greater than 'nominal_perf', we assume CPU Boost
 	 * is supported.
@@ -354,9 +397,12 @@ static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data,
 static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 {
 	struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0};
-	struct cppc_cpudata *cpu_data = all_cpu_data[cpu];
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct cppc_cpudata *cpu_data = policy->driver_data;
 	int ret;
 
+	cpufreq_cpu_put(policy);
+
 	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0);
 	if (ret)
 		return ret;
@@ -372,7 +418,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 
 static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
 {
-	struct cppc_cpudata *cpu_data = all_cpu_data[policy->cpu];
+	struct cppc_cpudata *cpu_data = policy->driver_data;
 	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
 	int ret;
 
@@ -396,6 +442,19 @@ static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
 	return 0;
 }
 
+static ssize_t show_freqdomain_cpus(struct cpufreq_policy *policy, char *buf)
+{
+	struct cppc_cpudata *cpu_data = policy->driver_data;
+
+	return cpufreq_show_cpus(cpu_data->shared_cpu_map, buf);
+}
+cpufreq_freq_attr_ro(freqdomain_cpus);
+
+static struct freq_attr *cppc_cpufreq_attr[] = {
+	&freqdomain_cpus,
+	NULL,
+};
+
 static struct cpufreq_driver cppc_cpufreq_driver = {
 	.flags = CPUFREQ_CONST_LOOPS,
 	.verify = cppc_verify_policy,
@@ -404,6 +463,7 @@ static struct cpufreq_driver cppc_cpufreq_driver = {
 	.init = cppc_cpufreq_cpu_init,
 	.stop_cpu = cppc_cpufreq_stop_cpu,
 	.set_boost = cppc_cpufreq_set_boost,
+	.attr = cppc_cpufreq_attr,
 	.name = "cppc_cpufreq",
 };
 
@@ -415,10 +475,13 @@ static struct cpufreq_driver cppc_cpufreq_driver = {
  */
 static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu)
 {
-	struct cppc_cpudata *cpu_data = all_cpu_data[cpu];
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct cppc_cpudata *cpu_data = policy->driver_data;
 	u64 desired_perf;
 	int ret;
 
+	cpufreq_cpu_put(policy);
+
 	ret = cppc_get_desired_perf(cpu, &desired_perf);
 	if (ret < 0)
 		return -EIO;
@@ -451,68 +514,33 @@ static void cppc_check_hisi_workaround(void)
 
 static int __init cppc_cpufreq_init(void)
 {
-	struct cppc_cpudata *cpu_data;
-	int i, ret = 0;
-
-	if (acpi_disabled)
+	if ((acpi_disabled) || !acpi_cpc_valid())
 		return -ENODEV;
 
-	all_cpu_data = kcalloc(num_possible_cpus(), sizeof(void *),
-			       GFP_KERNEL);
-	if (!all_cpu_data)
-		return -ENOMEM;
-
-	for_each_possible_cpu(i) {
-		all_cpu_data[i] = kzalloc(sizeof(struct cppc_cpudata), GFP_KERNEL);
-		if (!all_cpu_data[i])
-			goto out;
-
-		cpu_data = all_cpu_data[i];
-		if (!zalloc_cpumask_var(&cpu_data->shared_cpu_map, GFP_KERNEL))
-			goto out;
-	}
-
-	ret = acpi_get_psd_map(all_cpu_data);
-	if (ret) {
-		pr_debug("Error parsing PSD data. Aborting cpufreq registration.\n");
-		goto out;
-	}
+	INIT_LIST_HEAD(&cpu_data_list);
 
 	cppc_check_hisi_workaround();
 
-	ret = cpufreq_register_driver(&cppc_cpufreq_driver);
-	if (ret)
-		goto out;
+	return cpufreq_register_driver(&cppc_cpufreq_driver);
+}
 
-	return ret;
+static inline void free_cpu_data(void)
+{
+	struct cppc_cpudata *iter, *tmp;
 
-out:
-	for_each_possible_cpu(i) {
-		cpu_data = all_cpu_data[i];
-		if (!cpu_data)
-			break;
-		free_cpumask_var(cpu_data->shared_cpu_map);
-		kfree(cpu_data);
+	list_for_each_entry_safe(iter, tmp, &cpu_data_list, node) {
+		free_cpumask_var(iter->shared_cpu_map);
+		list_del(&iter->node);
+		kfree(iter);
 	}
 
-	kfree(all_cpu_data);
-	return -ENODEV;
 }
 
 static void __exit cppc_cpufreq_exit(void)
 {
-	struct cppc_cpudata *cpu_data;
-	int i;
-
 	cpufreq_unregister_driver(&cppc_cpufreq_driver);
 
-	for_each_possible_cpu(i) {
-		cpu_data = all_cpu_data[i];
-		free_cpumask_var(cpu_data->shared_cpu_map);
-		kfree(cpu_data);
-	}
-
-	kfree(all_cpu_data);
+	free_cpu_data();
 }
 
 module_exit(cppc_cpufreq_exit);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index c17aa2973c44..d0a3525ce27f 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2097,6 +2097,46 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
 
+/**
+ * cpufreq_driver_adjust_perf - Adjust CPU performance level in one go.
+ * @cpu: Target CPU.
+ * @min_perf: Minimum (required) performance level (units of @capacity).
+ * @target_perf: Terget (desired) performance level (units of @capacity).
+ * @capacity: Capacity of the target CPU.
+ *
+ * Carry out a fast performance level switch of @cpu without sleeping.
+ *
+ * The driver's ->adjust_perf() callback invoked by this function must be
+ * suitable for being called from within RCU-sched read-side critical sections
+ * and it is expected to select a suitable performance level equal to or above
+ * @min_perf and preferably equal to or below @target_perf.
+ *
+ * This function must not be called if policy->fast_switch_enabled is unset.
+ *
+ * Governors calling this function must guarantee that it will never be invoked
+ * twice in parallel for the same CPU and that it will never be called in
+ * parallel with either ->target() or ->target_index() or ->fast_switch() for
+ * the same CPU.
+ */
+void cpufreq_driver_adjust_perf(unsigned int cpu,
+				 unsigned long min_perf,
+				 unsigned long target_perf,
+				 unsigned long capacity)
+{
+	cpufreq_driver->adjust_perf(cpu, min_perf, target_perf, capacity);
+}
+
+/**
+ * cpufreq_driver_has_adjust_perf - Check "direct fast switch" callback.
+ *
+ * Return 'true' if the ->adjust_perf callback is present for the
+ * current driver or 'false' otherwise.
+ */
+bool cpufreq_driver_has_adjust_perf(void)
+{
+	return !!cpufreq_driver->adjust_perf;
+}
+
 /* Must set freqs->new to intermediate frequency */
 static int __target_intermediate(struct cpufreq_policy *policy,
 				 struct cpufreq_freqs *freqs, int index)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2a4db856222f..be05e038d956 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -76,11 +76,6 @@ static inline int ceiling_fp(int32_t x)
 	return ret;
 }
 
-static inline int32_t percent_fp(int percent)
-{
-	return div_fp(percent, 100);
-}
-
 static inline u64 mul_ext_fp(u64 x, u64 y)
 {
 	return (x * y) >> EXT_FRAC_BITS;
@@ -91,11 +86,6 @@ static inline u64 div_ext_fp(u64 x, u64 y)
 	return div64_u64(x << EXT_FRAC_BITS, y);
 }
 
-static inline int32_t percent_ext_fp(int percent)
-{
-	return div_ext_fp(percent, 100);
-}
-
 /**
  * struct sample -	Store performance sample
  * @core_avg_perf:	Ratio of APERF/MPERF which is the actual average
@@ -2207,9 +2197,9 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu,
 					    unsigned int policy_min,
 					    unsigned int policy_max)
 {
-	int max_freq = intel_pstate_get_max_freq(cpu);
 	int32_t max_policy_perf, min_policy_perf;
 	int max_state, turbo_max;
+	int max_freq;
 
 	/*
 	 * HWP needs some special consideration, because on BDX the
@@ -2223,6 +2213,7 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu,
 			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 		turbo_max = cpu->pstate.turbo_pstate;
 	}
+	max_freq = max_state * cpu->pstate.scaling;
 
 	max_policy_perf = max_state * policy_max / max_freq;
 	if (policy_max == policy_min) {
@@ -2325,9 +2316,18 @@ static void intel_pstate_adjust_policy_max(struct cpudata *cpu,
 static void intel_pstate_verify_cpu_policy(struct cpudata *cpu,
 					   struct cpufreq_policy_data *policy)
 {
+	int max_freq;
+
 	update_turbo_state();
-	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-				     intel_pstate_get_max_freq(cpu));
+	if (hwp_active) {
+		int max_state, turbo_max;
+
+		intel_pstate_get_hwp_max(cpu->cpu, &turbo_max, &max_state);
+		max_freq = max_state * cpu->pstate.scaling;
+	} else {
+		max_freq = intel_pstate_get_max_freq(cpu);
+	}
+	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, max_freq);
 
 	intel_pstate_adjust_policy_max(cpu, policy);
 }
@@ -2526,20 +2526,19 @@ static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, in
 		fp_toint(cpu->iowait_boost * 100));
 }
 
-static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate,
-				     bool strict, bool fast_switch)
+static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 min, u32 max,
+				     u32 desired, bool fast_switch)
 {
 	u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev;
 
 	value &= ~HWP_MIN_PERF(~0L);
-	value |= HWP_MIN_PERF(target_pstate);
+	value |= HWP_MIN_PERF(min);
 
-	/*
-	 * The entire MSR needs to be updated in order to update the HWP min
-	 * field in it, so opportunistically update the max too if needed.
-	 */
 	value &= ~HWP_MAX_PERF(~0L);
-	value |= HWP_MAX_PERF(strict ? target_pstate : cpu->max_perf_ratio);
+	value |= HWP_MAX_PERF(max);
+
+	value &= ~HWP_DESIRED_PERF(~0L);
+	value |= HWP_DESIRED_PERF(desired);
 
 	if (value == prev)
 		return;
@@ -2569,11 +2568,15 @@ static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy,
 	int old_pstate = cpu->pstate.current_pstate;
 
 	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
-	if (hwp_active)
-		intel_cpufreq_adjust_hwp(cpu, target_pstate,
-					 policy->strict_target, fast_switch);
-	else if (target_pstate != old_pstate)
+	if (hwp_active) {
+		int max_pstate = policy->strict_target ?
+					target_pstate : cpu->max_perf_ratio;
+
+		intel_cpufreq_adjust_hwp(cpu, target_pstate, max_pstate, 0,
+					 fast_switch);
+	} else if (target_pstate != old_pstate) {
 		intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch);
+	}
 
 	cpu->pstate.current_pstate = target_pstate;
 
@@ -2634,6 +2637,48 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 	return target_pstate * cpu->pstate.scaling;
 }
 
+static void intel_cpufreq_adjust_perf(unsigned int cpunum,
+				      unsigned long min_perf,
+				      unsigned long target_perf,
+				      unsigned long capacity)
+{
+	struct cpudata *cpu = all_cpu_data[cpunum];
+	u64 hwp_cap = READ_ONCE(cpu->hwp_cap_cached);
+	int old_pstate = cpu->pstate.current_pstate;
+	int cap_pstate, min_pstate, max_pstate, target_pstate;
+
+	update_turbo_state();
+	cap_pstate = global.turbo_disabled ? HWP_GUARANTEED_PERF(hwp_cap) :
+					     HWP_HIGHEST_PERF(hwp_cap);
+
+	/* Optimization: Avoid unnecessary divisions. */
+
+	target_pstate = cap_pstate;
+	if (target_perf < capacity)
+		target_pstate = DIV_ROUND_UP(cap_pstate * target_perf, capacity);
+
+	min_pstate = cap_pstate;
+	if (min_perf < capacity)
+		min_pstate = DIV_ROUND_UP(cap_pstate * min_perf, capacity);
+
+	if (min_pstate < cpu->pstate.min_pstate)
+		min_pstate = cpu->pstate.min_pstate;
+
+	if (min_pstate < cpu->min_perf_ratio)
+		min_pstate = cpu->min_perf_ratio;
+
+	max_pstate = min(cap_pstate, cpu->max_perf_ratio);
+	if (max_pstate < min_pstate)
+		max_pstate = min_pstate;
+
+	target_pstate = clamp_t(int, target_pstate, min_pstate, max_pstate);
+
+	intel_cpufreq_adjust_hwp(cpu, min_pstate, max_pstate, target_pstate, true);
+
+	cpu->pstate.current_pstate = target_pstate;
+	intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_FAST_SWITCH, old_pstate);
+}
+
 static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
 	int max_state, turbo_max, min_freq, max_freq, ret;
@@ -3032,6 +3077,7 @@ static int __init intel_pstate_init(void)
 			intel_pstate.attr = hwp_cpufreq_attrs;
 			intel_cpufreq.attr = hwp_cpufreq_attrs;
 			intel_cpufreq.flags |= CPUFREQ_NEED_UPDATE_LIMITS;
+			intel_cpufreq.adjust_perf = intel_cpufreq_adjust_perf;
 			if (!default_driver)
 				default_driver = &intel_pstate;
 
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index 0acc9e241cd7..b9ccb6a3dad9 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -878,9 +878,9 @@ static int get_transition_latency(struct powernow_k8_data *data)
 
 /* Take a frequency, and issue the fid/vid transition command */
 static int transition_frequency_fidvid(struct powernow_k8_data *data,
-		unsigned int index)
+		unsigned int index,
+		struct cpufreq_policy *policy)
 {
-	struct cpufreq_policy *policy;
 	u32 fid = 0;
 	u32 vid = 0;
 	int res;
@@ -912,9 +912,6 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data,
 	freqs.old = find_khz_freq_from_fid(data->currfid);
 	freqs.new = find_khz_freq_from_fid(fid);
 
-	policy = cpufreq_cpu_get(smp_processor_id());
-	cpufreq_cpu_put(policy);
-
 	cpufreq_freq_transition_begin(policy, &freqs);
 	res = transition_fid_vid(data, fid, vid);
 	cpufreq_freq_transition_end(policy, &freqs, res);
@@ -969,7 +966,7 @@ static long powernowk8_target_fn(void *arg)
 
 	powernow_k8_acpi_pst_values(data, newstate);
 
-	ret = transition_frequency_fidvid(data, newstate);
+	ret = transition_frequency_fidvid(data, newstate, pol);
 
 	if (ret) {
 		pr_err("transition frequency failed\n");
diff --git a/drivers/crypto/keembay/Kconfig b/drivers/crypto/keembay/Kconfig
index 3c16797b25b9..f2e17b0c4fa0 100644
--- a/drivers/crypto/keembay/Kconfig
+++ b/drivers/crypto/keembay/Kconfig
@@ -1,12 +1,13 @@
 config CRYPTO_DEV_KEEMBAY_OCS_AES_SM4
 	tristate "Support for Intel Keem Bay OCS AES/SM4 HW acceleration"
-	depends on OF || COMPILE_TEST
+	depends on HAS_IOMEM
+	depends on ARCH_KEEMBAY || COMPILE_TEST
 	select CRYPTO_SKCIPHER
 	select CRYPTO_AEAD
 	select CRYPTO_ENGINE
 	help
 	  Support for Intel Keem Bay Offload and Crypto Subsystem (OCS) AES and
-	  SM4 cihper hardware acceleration for use with Crypto API.
+	  SM4 cipher hardware acceleration for use with Crypto API.
 
 	  Provides HW acceleration for the following transformations:
 	  cbc(aes), ctr(aes), ccm(aes), gcm(aes), cbc(sm4), ctr(sm4), ccm(sm4)
diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/qat/Kconfig
index beb379b23dc3..846a3d90b41a 100644
--- a/drivers/crypto/qat/Kconfig
+++ b/drivers/crypto/qat/Kconfig
@@ -11,6 +11,7 @@ config CRYPTO_DEV_QAT
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
+	select CRYPTO_AES
 	select FW_LOADER
 
 config CRYPTO_DEV_QAT_DH895xCC
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 27513d311242..737b207c9e30 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -367,19 +367,28 @@ void kill_dev_dax(struct dev_dax *dev_dax)
 }
 EXPORT_SYMBOL_GPL(kill_dev_dax);
 
-static void free_dev_dax_ranges(struct dev_dax *dev_dax)
+static void trim_dev_dax_range(struct dev_dax *dev_dax)
 {
+	int i = dev_dax->nr_range - 1;
+	struct range *range = &dev_dax->ranges[i].range;
 	struct dax_region *dax_region = dev_dax->region;
-	int i;
 
 	device_lock_assert(dax_region->dev);
-	for (i = 0; i < dev_dax->nr_range; i++) {
-		struct range *range = &dev_dax->ranges[i].range;
-
-		__release_region(&dax_region->res, range->start,
-				range_len(range));
+	dev_dbg(&dev_dax->dev, "delete range[%d]: %#llx:%#llx\n", i,
+		(unsigned long long)range->start,
+		(unsigned long long)range->end);
+
+	__release_region(&dax_region->res, range->start, range_len(range));
+	if (--dev_dax->nr_range == 0) {
+		kfree(dev_dax->ranges);
+		dev_dax->ranges = NULL;
 	}
-	dev_dax->nr_range = 0;
+}
+
+static void free_dev_dax_ranges(struct dev_dax *dev_dax)
+{
+	while (dev_dax->nr_range)
+		trim_dev_dax_range(dev_dax);
 }
 
 static void unregister_dev_dax(void *dev)
@@ -763,22 +772,14 @@ static int alloc_dev_dax_range(struct dev_dax *dev_dax, u64 start,
 		return 0;
 	}
 
-	ranges = krealloc(dev_dax->ranges, sizeof(*ranges)
-			* (dev_dax->nr_range + 1), GFP_KERNEL);
-	if (!ranges)
+	alloc = __request_region(res, start, size, dev_name(dev), 0);
+	if (!alloc)
 		return -ENOMEM;
 
-	alloc = __request_region(res, start, size, dev_name(dev), 0);
-	if (!alloc) {
-		/*
-		 * If this was an empty set of ranges nothing else
-		 * will release @ranges, so do it now.
-		 */
-		if (!dev_dax->nr_range) {
-			kfree(ranges);
-			ranges = NULL;
-		}
-		dev_dax->ranges = ranges;
+	ranges = krealloc(dev_dax->ranges, sizeof(*ranges)
+			* (dev_dax->nr_range + 1), GFP_KERNEL);
+	if (!ranges) {
+		__release_region(res, alloc->start, resource_size(alloc));
 		return -ENOMEM;
 	}
 
@@ -804,15 +805,10 @@ static int alloc_dev_dax_range(struct dev_dax *dev_dax, u64 start,
 		return 0;
 
 	rc = devm_register_dax_mapping(dev_dax, dev_dax->nr_range - 1);
-	if (rc) {
-		dev_dbg(dev, "delete range[%d]: %pa:%pa\n", dev_dax->nr_range - 1,
-				&alloc->start, &alloc->end);
-		dev_dax->nr_range--;
-		__release_region(res, alloc->start, resource_size(alloc));
-		return rc;
-	}
+	if (rc)
+		trim_dev_dax_range(dev_dax);
 
-	return 0;
+	return rc;
 }
 
 static int adjust_dev_dax_range(struct dev_dax *dev_dax, struct resource *res, resource_size_t size)
@@ -885,12 +881,7 @@ static int dev_dax_shrink(struct dev_dax *dev_dax, resource_size_t size)
 		if (shrink >= range_len(range)) {
 			devm_release_action(dax_region->dev,
 					unregister_dax_mapping, &mapping->dev);
-			__release_region(&dax_region->res, range->start,
-					range_len(range));
-			dev_dax->nr_range--;
-			dev_dbg(dev, "delete range[%d]: %#llx:%#llx\n", i,
-					(unsigned long long) range->start,
-					(unsigned long long) range->end);
+			trim_dev_dax_range(dev_dax);
 			to_shrink -= shrink;
 			if (!to_shrink)
 				break;
@@ -1114,16 +1105,9 @@ static ssize_t align_show(struct device *dev,
 
 static ssize_t dev_dax_validate_align(struct dev_dax *dev_dax)
 {
-	resource_size_t dev_size = dev_dax_size(dev_dax);
 	struct device *dev = &dev_dax->dev;
 	int i;
 
-	if (dev_size > 0 && !alloc_is_aligned(dev_dax, dev_size)) {
-		dev_dbg(dev, "%s: align %u invalid for size %pa\n",
-			__func__, dev_dax->align, &dev_size);
-		return -EINVAL;
-	}
-
 	for (i = 0; i < dev_dax->nr_range; i++) {
 		size_t len = range_len(&dev_dax->ranges[i].range);
 
@@ -1274,7 +1258,6 @@ static void dev_dax_release(struct device *dev)
 	put_dax(dax_dev);
 	free_dev_dax_id(dev_dax);
 	dax_region_put(dax_region);
-	kfree(dev_dax->ranges);
 	kfree(dev_dax->pgmap);
 	kfree(dev_dax);
 }
diff --git a/drivers/dax/pmem/core.c b/drivers/dax/pmem/core.c
index 62b26bfceab1..062e8bc14223 100644
--- a/drivers/dax/pmem/core.c
+++ b/drivers/dax/pmem/core.c
@@ -52,7 +52,7 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 
 	/* adjust the dax_region range to the start of data */
 	range = pgmap.range;
-	range.start += offset,
+	range.start += offset;
 	dax_region = alloc_dax_region(dev, region_id, &range,
 			nd_region->target_node, le32_to_cpu(pfn_sb->align),
 			IORESOURCE_DAX_STATIC);
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index edc279be3e59..cadbd0a1a1ef 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -752,6 +752,7 @@ err_chrdev:
 
 static void __exit dax_core_exit(void)
 {
+	dax_bus_exit();
 	unregister_chrdev_region(dax_devt, MINORMASK+1);
 	ida_destroy(&dax_minor_ida);
 	dax_fs_exit();
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index e63684d4cd90..9ad6397aaa97 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -76,10 +76,6 @@ static void dma_buf_release(struct dentry *dentry)
 
 	dmabuf->ops->release(dmabuf);
 
-	mutex_lock(&db_list.lock);
-	list_del(&dmabuf->list_node);
-	mutex_unlock(&db_list.lock);
-
 	if (dmabuf->resv == (struct dma_resv *)&dmabuf[1])
 		dma_resv_fini(dmabuf->resv);
 
@@ -88,6 +84,22 @@ static void dma_buf_release(struct dentry *dentry)
 	kfree(dmabuf);
 }
 
+static int dma_buf_file_release(struct inode *inode, struct file *file)
+{
+	struct dma_buf *dmabuf;
+
+	if (!is_dma_buf_file(file))
+		return -EINVAL;
+
+	dmabuf = file->private_data;
+
+	mutex_lock(&db_list.lock);
+	list_del(&dmabuf->list_node);
+	mutex_unlock(&db_list.lock);
+
+	return 0;
+}
+
 static const struct dentry_operations dma_buf_dentry_ops = {
 	.d_dname = dmabuffs_dname,
 	.d_release = dma_buf_release,
@@ -413,6 +425,7 @@ static void dma_buf_show_fdinfo(struct seq_file *m, struct file *file)
 }
 
 static const struct file_operations dma_buf_fops = {
+	.release	= dma_buf_file_release,
 	.mmap		= dma_buf_mmap_internal,
 	.llseek		= dma_buf_llseek,
 	.poll		= dma_buf_poll,
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
index 5e7c3436310c..364fc2f3e499 100644
--- a/drivers/dma-buf/heaps/cma_heap.c
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 
 struct cma_heap {
@@ -250,6 +251,9 @@ static void cma_heap_dma_buf_release(struct dma_buf *dmabuf)
 		buffer->vaddr = NULL;
 	}
 
+	/* free page list */
+	kfree(buffer->pages);
+	/* release memory */
 	cma_release(cma_heap->cma, buffer->cma_pages, buffer->pagecount);
 	kfree(buffer);
 }
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index b971505b8715..08d71dafa001 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -86,12 +86,12 @@ static struct dw_edma_chunk *dw_edma_alloc_chunk(struct dw_edma_desc *desc)
 
 	if (desc->chunk) {
 		/* Create and add new element into the linked list */
-		desc->chunks_alloc++;
-		list_add_tail(&chunk->list, &desc->chunk->list);
 		if (!dw_edma_alloc_burst(chunk)) {
 			kfree(chunk);
 			return NULL;
 		}
+		desc->chunks_alloc++;
+		list_add_tail(&chunk->list, &desc->chunk->list);
 	} else {
 		/* List head */
 		chunk->burst = NULL;
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 266423a2cabc..4dbb03c545e4 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -434,7 +434,7 @@ int idxd_register_driver(void)
 	return 0;
 
 drv_fail:
-	for (; i > 0; i--)
+	while (--i >= 0)
 		driver_unregister(&idxd_drvs[i]->drv);
 	return rc;
 }
@@ -1840,7 +1840,7 @@ int idxd_register_bus_type(void)
 	return 0;
 
 bus_err:
-	for (; i > 0; i--)
+	while (--i >= 0)
 		bus_unregister(idxd_bus_types[i]);
 	return rc;
 }
diff --git a/drivers/dma/mediatek/mtk-hsdma.c b/drivers/dma/mediatek/mtk-hsdma.c
index f133ae8dece1..6ad8afbb95f2 100644
--- a/drivers/dma/mediatek/mtk-hsdma.c
+++ b/drivers/dma/mediatek/mtk-hsdma.c
@@ -1007,6 +1007,7 @@ static int mtk_hsdma_probe(struct platform_device *pdev)
 	return 0;
 
 err_free:
+	mtk_hsdma_hw_deinit(hsdma);
 	of_dma_controller_free(pdev->dev.of_node);
 err_unregister:
 	dma_async_device_unregister(dd);
diff --git a/drivers/dma/milbeaut-xdmac.c b/drivers/dma/milbeaut-xdmac.c
index 584c931e807a..d29d01e730aa 100644
--- a/drivers/dma/milbeaut-xdmac.c
+++ b/drivers/dma/milbeaut-xdmac.c
@@ -350,7 +350,7 @@ static int milbeaut_xdmac_probe(struct platform_device *pdev)
 
 	ret = dma_async_device_register(ddev);
 	if (ret)
-		return ret;
+		goto disable_xdmac;
 
 	ret = of_dma_controller_register(dev->of_node,
 					 of_dma_simple_xlate, mdev);
@@ -363,6 +363,8 @@ static int milbeaut_xdmac_probe(struct platform_device *pdev)
 
 unregister_dmac:
 	dma_async_device_unregister(ddev);
+disable_xdmac:
+	disable_xdmac(mdev);
 	return ret;
 }
 
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index d5773d474d8f..88579857ca1d 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -630,7 +630,7 @@ static struct dma_async_tx_descriptor *bam_prep_slave_sg(struct dma_chan *chan,
 			     GFP_NOWAIT);
 
 	if (!async_desc)
-		goto err_out;
+		return NULL;
 
 	if (flags & DMA_PREP_FENCE)
 		async_desc->flags |= DESC_FLAG_NWD;
@@ -670,10 +670,6 @@ static struct dma_async_tx_descriptor *bam_prep_slave_sg(struct dma_chan *chan,
 	}
 
 	return vchan_tx_prep(&bchan->vc, &async_desc->vd, flags);
-
-err_out:
-	kfree(async_desc);
-	return NULL;
 }
 
 /**
diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c
index d2334f535de2..1a0bf6b0567a 100644
--- a/drivers/dma/qcom/gpi.c
+++ b/drivers/dma/qcom/gpi.c
@@ -1416,7 +1416,7 @@ static int gpi_alloc_ring(struct gpi_ring *ring, u32 elements,
 	len = 1 << bit;
 	ring->alloc_size = (len + (len - 1));
 	dev_dbg(gpii->gpi_dev->dev,
-		"#el:%u el_size:%u len:%u actual_len:%llu alloc_size:%lu\n",
+		"#el:%u el_size:%u len:%u actual_len:%llu alloc_size:%zu\n",
 		  elements, el_size, (elements * el_size), len,
 		  ring->alloc_size);
 
@@ -1424,7 +1424,7 @@ static int gpi_alloc_ring(struct gpi_ring *ring, u32 elements,
 					       ring->alloc_size,
 					       &ring->dma_handle, GFP_KERNEL);
 	if (!ring->pre_aligned) {
-		dev_err(gpii->gpi_dev->dev, "could not alloc size:%lu mem for ring\n",
+		dev_err(gpii->gpi_dev->dev, "could not alloc size:%zu mem for ring\n",
 			ring->alloc_size);
 		return -ENOMEM;
 	}
@@ -1444,8 +1444,8 @@ static int gpi_alloc_ring(struct gpi_ring *ring, u32 elements,
 	smp_wmb();
 
 	dev_dbg(gpii->gpi_dev->dev,
-		"phy_pre:0x%0llx phy_alig:0x%0llx len:%u el_size:%u elements:%u\n",
-		ring->dma_handle, ring->phys_addr, ring->len,
+		"phy_pre:%pad phy_alig:%pa len:%u el_size:%u elements:%u\n",
+		&ring->dma_handle, &ring->phys_addr, ring->len,
 		ring->el_size, ring->elements);
 
 	return 0;
@@ -1948,7 +1948,7 @@ static int gpi_ch_init(struct gchan *gchan)
 	return ret;
 
 error_start_chan:
-	for (i = i - 1; i >= 0; i++) {
+	for (i = i - 1; i >= 0; i--) {
 		gpi_stop_chan(&gpii->gchan[i]);
 		gpi_send_cmd(gpii, gchan, GPI_CH_CMD_RESET);
 	}
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index e4637ec786d3..36ba8b43e78d 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -199,7 +199,7 @@
 #define STM32_MDMA_MAX_CHANNELS		63
 #define STM32_MDMA_MAX_REQUESTS		256
 #define STM32_MDMA_MAX_BURST		128
-#define STM32_MDMA_VERY_HIGH_PRIORITY	0x11
+#define STM32_MDMA_VERY_HIGH_PRIORITY	0x3
 
 enum stm32_mdma_trigger_mode {
 	STM32_MDMA_BUFFER,
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 87157cbae1b8..298460438bb4 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -4698,9 +4698,9 @@ static int pktdma_setup_resources(struct udma_dev *ud)
 		ud->tchan_tpl.levels = 1;
 	}
 
-	ud->tchan_tpl.levels = ud->tchan_tpl.levels;
-	ud->tchan_tpl.start_idx[0] = ud->tchan_tpl.start_idx[0];
-	ud->tchan_tpl.start_idx[1] = ud->tchan_tpl.start_idx[1];
+	ud->rchan_tpl.levels = ud->tchan_tpl.levels;
+	ud->rchan_tpl.start_idx[0] = ud->tchan_tpl.start_idx[0];
+	ud->rchan_tpl.start_idx[1] = ud->tchan_tpl.start_idx[1];
 
 	ud->tchan_map = devm_kmalloc_array(dev, BITS_TO_LONGS(ud->tchan_cnt),
 					   sizeof(unsigned long), GFP_KERNEL);
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 22faea653ea8..79777550a6ff 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -2781,7 +2781,7 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 		has_dre = false;
 
 	if (!has_dre)
-		xdev->common.copy_align = fls(width - 1);
+		xdev->common.copy_align = (enum dmaengine_alignment)fls(width - 1);
 
 	if (of_device_is_compatible(node, "xlnx,axi-vdma-mm2s-channel") ||
 	    of_device_is_compatible(node, "xlnx,axi-dma-mm2s-channel") ||
@@ -2900,7 +2900,8 @@ static int xilinx_dma_chan_probe(struct xilinx_dma_device *xdev,
 static int xilinx_dma_child_probe(struct xilinx_dma_device *xdev,
 				    struct device_node *node)
 {
-	int ret, i, nr_channels = 1;
+	int ret, i;
+	u32 nr_channels = 1;
 
 	ret = of_property_read_u32(node, "dma-channels", &nr_channels);
 	if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA && ret < 0)
@@ -3112,7 +3113,11 @@ static int xilinx_dma_probe(struct platform_device *pdev)
 	}
 
 	/* Register the DMA engine with the core */
-	dma_async_device_register(&xdev->common);
+	err = dma_async_device_register(&xdev->common);
+	if (err) {
+		dev_err(xdev->dev, "failed to register the dma device\n");
+		goto error;
+	}
 
 	err = of_dma_controller_register(node, of_dma_xilinx_xlate,
 					 xdev);
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index d9895491ff34..2c3dac5ecb36 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -122,7 +122,7 @@ config EFI_ARMSTUB_DTB_LOADER
 config EFI_GENERIC_STUB_INITRD_CMDLINE_LOADER
 	bool "Enable the command line initrd loader" if !X86
 	depends on EFI_STUB && (EFI_GENERIC_STUB || X86)
-	default y
+	default y if X86
 	depends on !RISCV
 	help
 	  Select this config option to add support for the initrd= command
@@ -147,7 +147,7 @@ config EFI_BOOTLOADER_CONTROL
 
 config EFI_CAPSULE_LOADER
 	tristate "EFI capsule loader"
-	depends on EFI
+	depends on EFI && !IA64
 	help
 	  This option exposes a loader interface "/dev/efi_capsule_loader" for
 	  users to load EFI capsules. This driver requires working runtime
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index d6ca2da19339..467e94259679 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -12,7 +12,10 @@ KASAN_SANITIZE_runtime-wrappers.o	:= n
 
 obj-$(CONFIG_ACPI_BGRT) 		+= efi-bgrt.o
 obj-$(CONFIG_EFI)			+= efi.o vars.o reboot.o memattr.o tpm.o
-obj-$(CONFIG_EFI)			+= capsule.o memmap.o
+obj-$(CONFIG_EFI)			+= memmap.o
+ifneq ($(CONFIG_EFI_CAPSULE_LOADER),)
+obj-$(CONFIG_EFI)			+= capsule.o
+endif
 obj-$(CONFIG_EFI_PARAMS_FROM_FDT)	+= fdtparams.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
 obj-$(CONFIG_EFI_ESRT)			+= esrt.o
diff --git a/drivers/firmware/efi/capsule.c b/drivers/firmware/efi/capsule.c
index 598b7800d14e..768430293669 100644
--- a/drivers/firmware/efi/capsule.c
+++ b/drivers/firmware/efi/capsule.c
@@ -12,6 +12,7 @@
 #include <linux/highmem.h>
 #include <linux/efi.h>
 #include <linux/vmalloc.h>
+#include <asm/efi.h>
 #include <asm/io.h>
 
 typedef struct {
@@ -244,7 +245,7 @@ int efi_capsule_update(efi_capsule_header_t *capsule, phys_addr_t *pages)
 	for (i = 0; i < sg_count; i++) {
 		efi_capsule_block_desc_t *sglist;
 
-		sglist = kmap(sg_pages[i]);
+		sglist = kmap_atomic(sg_pages[i]);
 
 		for (j = 0; j < SGLIST_PER_PAGE && count > 0; j++) {
 			u64 sz = min_t(u64, imagesize,
@@ -265,7 +266,18 @@ int efi_capsule_update(efi_capsule_header_t *capsule, phys_addr_t *pages)
 		else
 			sglist[j].data = page_to_phys(sg_pages[i + 1]);
 
-		kunmap(sg_pages[i]);
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+		/*
+		 * At runtime, the firmware has no way to find out where the
+		 * sglist elements are mapped, if they are mapped in the first
+		 * place. Therefore, on architectures that can only perform
+		 * cache maintenance by virtual address, the firmware is unable
+		 * to perform this maintenance, and so it is up to the OS to do
+		 * it instead.
+		 */
+		efi_capsule_flush_cache_range(sglist, PAGE_SIZE);
+#endif
+		kunmap_atomic(sglist);
 	}
 
 	mutex_lock(&capsule_mutex);
diff --git a/drivers/firmware/efi/libstub/efi-stub.c b/drivers/firmware/efi/libstub/efi-stub.c
index 914a343c7785..ec2f3985bef3 100644
--- a/drivers/firmware/efi/libstub/efi-stub.c
+++ b/drivers/firmware/efi/libstub/efi-stub.c
@@ -273,7 +273,6 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
 	install_memreserve_table();
 
 	status = allocate_new_fdt_and_exit_boot(handle, &fdt_addr,
-						efi_get_max_fdt_addr(image_addr),
 						initrd_addr, initrd_size,
 						cmdline_ptr, fdt_addr, fdt_size);
 	if (status != EFI_SUCCESS)
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 2d7abcd99de9..b50a6c67d9bd 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -750,7 +750,6 @@ efi_status_t efi_exit_boot_services(void *handle,
 
 efi_status_t allocate_new_fdt_and_exit_boot(void *handle,
 					    unsigned long *new_fdt_addr,
-					    unsigned long max_addr,
 					    u64 initrd_addr, u64 initrd_size,
 					    char *cmdline_ptr,
 					    unsigned long fdt_addr,
@@ -848,4 +847,6 @@ asmlinkage void __noreturn efi_enter_kernel(unsigned long entrypoint,
 
 void efi_handle_post_ebs_state(void);
 
+enum efi_secureboot_mode efi_get_secureboot(void);
+
 #endif
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index 368cd60000ee..365c3a43a198 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -238,7 +238,6 @@ static efi_status_t exit_boot_func(struct efi_boot_memmap *map,
 
 efi_status_t allocate_new_fdt_and_exit_boot(void *handle,
 					    unsigned long *new_fdt_addr,
-					    unsigned long max_addr,
 					    u64 initrd_addr, u64 initrd_size,
 					    char *cmdline_ptr,
 					    unsigned long fdt_addr,
@@ -275,7 +274,7 @@ efi_status_t allocate_new_fdt_and_exit_boot(void *handle,
 	efi_info("Exiting boot services and installing virtual address map...\n");
 
 	map.map = &memory_map;
-	status = efi_allocate_pages(MAX_FDT_SIZE, new_fdt_addr, max_addr);
+	status = efi_allocate_pages(MAX_FDT_SIZE, new_fdt_addr, ULONG_MAX);
 	if (status != EFI_SUCCESS) {
 		efi_err("Unable to allocate memory for new device tree.\n");
 		goto fail;
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
index 5efc524b14be..8a18930f3eb6 100644
--- a/drivers/firmware/efi/libstub/secureboot.c
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -12,44 +12,34 @@
 
 #include "efistub.h"
 
-/* BIOS variables */
-static const efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
-static const efi_char16_t efi_SecureBoot_name[] = L"SecureBoot";
-static const efi_char16_t efi_SetupMode_name[] = L"SetupMode";
-
 /* SHIM variables */
 static const efi_guid_t shim_guid = EFI_SHIM_LOCK_GUID;
 static const efi_char16_t shim_MokSBState_name[] = L"MokSBState";
 
+static efi_status_t get_var(efi_char16_t *name, efi_guid_t *vendor, u32 *attr,
+			    unsigned long *data_size, void *data)
+{
+	return get_efi_var(name, vendor, attr, data_size, data);
+}
+
 /*
  * Determine whether we're in secure boot mode.
- *
- * Please keep the logic in sync with
- * arch/x86/xen/efi.c:xen_efi_get_secureboot().
  */
 enum efi_secureboot_mode efi_get_secureboot(void)
 {
 	u32 attr;
-	u8 secboot, setupmode, moksbstate;
 	unsigned long size;
+	enum efi_secureboot_mode mode;
 	efi_status_t status;
+	u8 moksbstate;
 
-	size = sizeof(secboot);
-	status = get_efi_var(efi_SecureBoot_name, &efi_variable_guid,
-			     NULL, &size, &secboot);
-	if (status == EFI_NOT_FOUND)
-		return efi_secureboot_mode_disabled;
-	if (status != EFI_SUCCESS)
-		goto out_efi_err;
-
-	size = sizeof(setupmode);
-	status = get_efi_var(efi_SetupMode_name, &efi_variable_guid,
-			     NULL, &size, &setupmode);
-	if (status != EFI_SUCCESS)
-		goto out_efi_err;
-
-	if (secboot == 0 || setupmode == 1)
-		return efi_secureboot_mode_disabled;
+	mode = efi_get_secureboot_mode(get_var);
+	if (mode == efi_secureboot_mode_unknown) {
+		efi_err("Could not determine UEFI Secure Boot status.\n");
+		return efi_secureboot_mode_unknown;
+	}
+	if (mode != efi_secureboot_mode_enabled)
+		return mode;
 
 	/*
 	 * See if a user has put the shim into insecure mode. If so, and if the
@@ -69,8 +59,4 @@ enum efi_secureboot_mode efi_get_secureboot(void)
 secure_boot_enabled:
 	efi_info("UEFI Secure Boot is enabled.\n");
 	return efi_secureboot_mode_enabled;
-
-out_efi_err:
-	efi_err("Could not determine UEFI Secure Boot status.\n");
-	return efi_secureboot_mode_unknown;
 }
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 3672539cb96e..f14c4ff5839f 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -715,8 +715,11 @@ unsigned long efi_main(efi_handle_t handle,
 	    (IS_ENABLED(CONFIG_X86_32) && buffer_end > KERNEL_IMAGE_SIZE)    ||
 	    (IS_ENABLED(CONFIG_X86_64) && buffer_end > MAXMEM_X86_64_4LEVEL) ||
 	    (image_offset == 0)) {
+		extern char _bss[];
+
 		status = efi_relocate_kernel(&bzimage_addr,
-					     hdr->init_size, hdr->init_size,
+					     (unsigned long)_bss - bzimage_addr,
+					     hdr->init_size,
 					     hdr->pref_address,
 					     hdr->kernel_alignment,
 					     LOAD_PHYSICAL_ADDR);
diff --git a/drivers/firmware/efi/test/efi_test.c b/drivers/firmware/efi/test/efi_test.c
index ddf9eae396fe..47d67bb0a516 100644
--- a/drivers/firmware/efi/test/efi_test.c
+++ b/drivers/firmware/efi/test/efi_test.c
@@ -663,6 +663,19 @@ out:
 	return rv;
 }
 
+static long efi_runtime_get_supported_mask(unsigned long arg)
+{
+	unsigned int __user *supported_mask;
+	int rv = 0;
+
+	supported_mask = (unsigned int *)arg;
+
+	if (put_user(efi.runtime_supported_mask, supported_mask))
+		rv = -EFAULT;
+
+	return rv;
+}
+
 static long efi_test_ioctl(struct file *file, unsigned int cmd,
 							unsigned long arg)
 {
@@ -699,6 +712,9 @@ static long efi_test_ioctl(struct file *file, unsigned int cmd,
 
 	case EFI_RUNTIME_RESET_SYSTEM:
 		return efi_runtime_reset_system(arg);
+
+	case EFI_RUNTIME_GET_SUPPORTED_MASK:
+		return efi_runtime_get_supported_mask(arg);
 	}
 
 	return -ENOTTY;
diff --git a/drivers/firmware/efi/test/efi_test.h b/drivers/firmware/efi/test/efi_test.h
index f2446aa1c2e3..117349e57993 100644
--- a/drivers/firmware/efi/test/efi_test.h
+++ b/drivers/firmware/efi/test/efi_test.h
@@ -118,4 +118,7 @@ struct efi_resetsystem {
 #define EFI_RUNTIME_RESET_SYSTEM \
 	_IOW('p', 0x0B, struct efi_resetsystem)
 
+#define EFI_RUNTIME_GET_SUPPORTED_MASK \
+	_IOR('p', 0x0C, unsigned int)
+
 #endif /* _DRIVERS_FIRMWARE_EFI_TEST_H_ */
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index 00af99b6f97c..f5fc429cae3f 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -58,15 +58,12 @@ typedef unsigned long (psci_fn)(unsigned long, unsigned long,
 				unsigned long, unsigned long);
 static psci_fn *invoke_psci_fn;
 
-enum psci_function {
-	PSCI_FN_CPU_SUSPEND,
-	PSCI_FN_CPU_ON,
-	PSCI_FN_CPU_OFF,
-	PSCI_FN_MIGRATE,
-	PSCI_FN_MAX,
-};
+static struct psci_0_1_function_ids psci_0_1_function_ids;
 
-static u32 psci_function_id[PSCI_FN_MAX];
+struct psci_0_1_function_ids get_psci_0_1_function_ids(void)
+{
+	return psci_0_1_function_ids;
+}
 
 #define PSCI_0_2_POWER_STATE_MASK		\
 				(PSCI_0_2_POWER_STATE_ID_MASK | \
@@ -146,7 +143,12 @@ static int psci_to_linux_errno(int errno)
 	return -EINVAL;
 }
 
-static u32 psci_get_version(void)
+static u32 psci_0_1_get_version(void)
+{
+	return PSCI_VERSION(0, 1);
+}
+
+static u32 psci_0_2_get_version(void)
 {
 	return invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
 }
@@ -163,46 +165,80 @@ int psci_set_osi_mode(bool enable)
 	return psci_to_linux_errno(err);
 }
 
-static int psci_cpu_suspend(u32 state, unsigned long entry_point)
+static int __psci_cpu_suspend(u32 fn, u32 state, unsigned long entry_point)
 {
 	int err;
-	u32 fn;
 
-	fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
 	err = invoke_psci_fn(fn, state, entry_point, 0);
 	return psci_to_linux_errno(err);
 }
 
-static int psci_cpu_off(u32 state)
+static int psci_0_1_cpu_suspend(u32 state, unsigned long entry_point)
+{
+	return __psci_cpu_suspend(psci_0_1_function_ids.cpu_suspend,
+				  state, entry_point);
+}
+
+static int psci_0_2_cpu_suspend(u32 state, unsigned long entry_point)
+{
+	return __psci_cpu_suspend(PSCI_FN_NATIVE(0_2, CPU_SUSPEND),
+				  state, entry_point);
+}
+
+static int __psci_cpu_off(u32 fn, u32 state)
 {
 	int err;
-	u32 fn;
 
-	fn = psci_function_id[PSCI_FN_CPU_OFF];
 	err = invoke_psci_fn(fn, state, 0, 0);
 	return psci_to_linux_errno(err);
 }
 
-static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point)
+static int psci_0_1_cpu_off(u32 state)
+{
+	return __psci_cpu_off(psci_0_1_function_ids.cpu_off, state);
+}
+
+static int psci_0_2_cpu_off(u32 state)
+{
+	return __psci_cpu_off(PSCI_0_2_FN_CPU_OFF, state);
+}
+
+static int __psci_cpu_on(u32 fn, unsigned long cpuid, unsigned long entry_point)
 {
 	int err;
-	u32 fn;
 
-	fn = psci_function_id[PSCI_FN_CPU_ON];
 	err = invoke_psci_fn(fn, cpuid, entry_point, 0);
 	return psci_to_linux_errno(err);
 }
 
-static int psci_migrate(unsigned long cpuid)
+static int psci_0_1_cpu_on(unsigned long cpuid, unsigned long entry_point)
+{
+	return __psci_cpu_on(psci_0_1_function_ids.cpu_on, cpuid, entry_point);
+}
+
+static int psci_0_2_cpu_on(unsigned long cpuid, unsigned long entry_point)
+{
+	return __psci_cpu_on(PSCI_FN_NATIVE(0_2, CPU_ON), cpuid, entry_point);
+}
+
+static int __psci_migrate(u32 fn, unsigned long cpuid)
 {
 	int err;
-	u32 fn;
 
-	fn = psci_function_id[PSCI_FN_MIGRATE];
 	err = invoke_psci_fn(fn, cpuid, 0, 0);
 	return psci_to_linux_errno(err);
 }
 
+static int psci_0_1_migrate(unsigned long cpuid)
+{
+	return __psci_migrate(psci_0_1_function_ids.migrate, cpuid);
+}
+
+static int psci_0_2_migrate(unsigned long cpuid)
+{
+	return __psci_migrate(PSCI_FN_NATIVE(0_2, MIGRATE), cpuid);
+}
+
 static int psci_affinity_info(unsigned long target_affinity,
 		unsigned long lowest_affinity_level)
 {
@@ -347,7 +383,7 @@ static void __init psci_init_system_suspend(void)
 
 static void __init psci_init_cpu_suspend(void)
 {
-	int feature = psci_features(psci_function_id[PSCI_FN_CPU_SUSPEND]);
+	int feature = psci_features(PSCI_FN_NATIVE(0_2, CPU_SUSPEND));
 
 	if (feature != PSCI_RET_NOT_SUPPORTED)
 		psci_cpu_suspend_feature = feature;
@@ -421,24 +457,16 @@ static void __init psci_init_smccc(void)
 static void __init psci_0_2_set_functions(void)
 {
 	pr_info("Using standard PSCI v0.2 function IDs\n");
-	psci_ops.get_version = psci_get_version;
-
-	psci_function_id[PSCI_FN_CPU_SUSPEND] =
-					PSCI_FN_NATIVE(0_2, CPU_SUSPEND);
-	psci_ops.cpu_suspend = psci_cpu_suspend;
-
-	psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
-	psci_ops.cpu_off = psci_cpu_off;
-
-	psci_function_id[PSCI_FN_CPU_ON] = PSCI_FN_NATIVE(0_2, CPU_ON);
-	psci_ops.cpu_on = psci_cpu_on;
 
-	psci_function_id[PSCI_FN_MIGRATE] = PSCI_FN_NATIVE(0_2, MIGRATE);
-	psci_ops.migrate = psci_migrate;
-
-	psci_ops.affinity_info = psci_affinity_info;
-
-	psci_ops.migrate_info_type = psci_migrate_info_type;
+	psci_ops = (struct psci_operations){
+		.get_version = psci_0_2_get_version,
+		.cpu_suspend = psci_0_2_cpu_suspend,
+		.cpu_off = psci_0_2_cpu_off,
+		.cpu_on = psci_0_2_cpu_on,
+		.migrate = psci_0_2_migrate,
+		.affinity_info = psci_affinity_info,
+		.migrate_info_type = psci_migrate_info_type,
+	};
 
 	arm_pm_restart = psci_sys_reset;
 
@@ -450,7 +478,7 @@ static void __init psci_0_2_set_functions(void)
  */
 static int __init psci_probe(void)
 {
-	u32 ver = psci_get_version();
+	u32 ver = psci_0_2_get_version();
 
 	pr_info("PSCIv%d.%d detected in firmware.\n",
 			PSCI_VERSION_MAJOR(ver),
@@ -514,24 +542,26 @@ static int __init psci_0_1_init(struct device_node *np)
 
 	pr_info("Using PSCI v0.1 Function IDs from DT\n");
 
+	psci_ops.get_version = psci_0_1_get_version;
+
 	if (!of_property_read_u32(np, "cpu_suspend", &id)) {
-		psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
-		psci_ops.cpu_suspend = psci_cpu_suspend;
+		psci_0_1_function_ids.cpu_suspend = id;
+		psci_ops.cpu_suspend = psci_0_1_cpu_suspend;
 	}
 
 	if (!of_property_read_u32(np, "cpu_off", &id)) {
-		psci_function_id[PSCI_FN_CPU_OFF] = id;
-		psci_ops.cpu_off = psci_cpu_off;
+		psci_0_1_function_ids.cpu_off = id;
+		psci_ops.cpu_off = psci_0_1_cpu_off;
 	}
 
 	if (!of_property_read_u32(np, "cpu_on", &id)) {
-		psci_function_id[PSCI_FN_CPU_ON] = id;
-		psci_ops.cpu_on = psci_cpu_on;
+		psci_0_1_function_ids.cpu_on = id;
+		psci_ops.cpu_on = psci_0_1_cpu_on;
 	}
 
 	if (!of_property_read_u32(np, "migrate", &id)) {
-		psci_function_id[PSCI_FN_MIGRATE] = id;
-		psci_ops.migrate = psci_migrate;
+		psci_0_1_function_ids.migrate = id;
+		psci_ops.migrate = psci_0_1_migrate;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 306077884a67..6107ac91db25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -112,6 +112,7 @@ int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev)
 union igp_info {
 	struct atom_integrated_system_info_v1_11 v11;
 	struct atom_integrated_system_info_v1_12 v12;
+	struct atom_integrated_system_info_v2_1 v21;
 };
 
 union umc_info {
@@ -209,24 +210,42 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 		if (adev->flags & AMD_IS_APU) {
 			igp_info = (union igp_info *)
 				(mode_info->atom_context->bios + data_offset);
-			switch (crev) {
-			case 11:
-				mem_channel_number = igp_info->v11.umachannelnumber;
-				/* channel width is 64 */
-				if (vram_width)
-					*vram_width = mem_channel_number * 64;
-				mem_type = igp_info->v11.memorytype;
-				if (vram_type)
-					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+			switch (frev) {
+			case 1:
+				switch (crev) {
+				case 11:
+				case 12:
+					mem_channel_number = igp_info->v11.umachannelnumber;
+					if (!mem_channel_number)
+						mem_channel_number = 1;
+					/* channel width is 64 */
+					if (vram_width)
+						*vram_width = mem_channel_number * 64;
+					mem_type = igp_info->v11.memorytype;
+					if (vram_type)
+						*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+					break;
+				default:
+					return -EINVAL;
+				}
 				break;
-			case 12:
-				mem_channel_number = igp_info->v12.umachannelnumber;
-				/* channel width is 64 */
-				if (vram_width)
-					*vram_width = mem_channel_number * 64;
-				mem_type = igp_info->v12.memorytype;
-				if (vram_type)
-					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+			case 2:
+				switch (crev) {
+				case 1:
+				case 2:
+					mem_channel_number = igp_info->v21.umachannelnumber;
+					if (!mem_channel_number)
+						mem_channel_number = 1;
+					/* channel width is 64 */
+					if (vram_width)
+						*vram_width = mem_channel_number * 64;
+					mem_type = igp_info->v21.memorytype;
+					if (vram_type)
+						*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+					break;
+				default:
+					return -EINVAL;
+				}
 				break;
 			default:
 				return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 65d1b23d7e74..b9c11c2b2885 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -1414,10 +1414,12 @@ out:
 		pm_runtime_put_autosuspend(connector->dev->dev);
 	}
 
-	drm_dp_set_subconnector_property(&amdgpu_connector->base,
-					 ret,
-					 amdgpu_dig_connector->dpcd,
-					 amdgpu_dig_connector->downstream_ports);
+	if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort ||
+	    connector->connector_type == DRM_MODE_CONNECTOR_eDP)
+		drm_dp_set_subconnector_property(&amdgpu_connector->base,
+						 ret,
+						 amdgpu_dig_connector->dpcd,
+						 amdgpu_dig_connector->downstream_ports);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7d2f7a2240b8..087afab67e22 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2548,11 +2548,11 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 	if (adev->gmc.xgmi.num_physical_nodes > 1)
 		amdgpu_xgmi_remove_device(adev);
 
-	amdgpu_amdkfd_device_fini(adev);
-
 	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
 
+	amdgpu_amdkfd_device_fini(adev);
+
 	/* need to disable SMC first */
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.hw)
@@ -3034,7 +3034,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 #endif
 	default:
 		if (amdgpu_dc > 0)
-			DRM_INFO("Display Core has been requested via kernel parameter "
+			DRM_INFO_ONCE("Display Core has been requested via kernel parameter "
 					 "but isn't supported by ASIC, ignoring\n");
 		return false;
 	}
@@ -5069,8 +5069,7 @@ out:
  * @pdev: pointer to PCI device
  *
  * Called when the error recovery driver tells us that its
- * OK to resume normal operation. Use completion to allow
- * halted scsi ops to resume.
+ * OK to resume normal operation.
  */
 void amdgpu_pci_resume(struct pci_dev *pdev)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 72efd579ec5e..7169fb5e3d9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1085,6 +1085,8 @@ static const struct pci_device_id pciidlist[] = {
 
 	/* Renoir */
 	{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
+	{0x1002, 0x1638, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
+	{0x1002, 0x164C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
 
 	/* Navi12 */
 	{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12},
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index c2ced5be6d7b..6e679db5e46f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -496,7 +496,8 @@ void amdgpu_gmc_get_vbios_allocations(struct amdgpu_device *adev)
 		break;
 	}
 
-	if (!amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_DCE)) {
+	if (amdgpu_sriov_vf(adev) ||
+	    !amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_DCE)) {
 		size = 0;
 	} else {
 		size = amdgpu_gmc_get_vbios_fb_size(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 523d22db094b..347fec669424 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -563,7 +563,7 @@ static int psp_asd_load(struct psp_context *psp)
 	 * add workaround to bypass it for sriov now.
 	 * TODO: add version check to make it common
 	 */
-	if (amdgpu_sriov_vf(psp->adev) || !psp->asd_fw)
+	if (amdgpu_sriov_vf(psp->adev) || !psp->asd_ucode_size)
 		return 0;
 
 	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
@@ -1315,8 +1315,12 @@ static int psp_hdcp_terminate(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	if (!psp->hdcp_context.hdcp_initialized)
-		return 0;
+	if (!psp->hdcp_context.hdcp_initialized) {
+		if (psp->hdcp_context.hdcp_shared_buf)
+			goto out;
+		else
+			return 0;
+	}
 
 	ret = psp_hdcp_unload(psp);
 	if (ret)
@@ -1324,6 +1328,7 @@ static int psp_hdcp_terminate(struct psp_context *psp)
 
 	psp->hdcp_context.hdcp_initialized = false;
 
+out:
 	/* free hdcp shared memory */
 	amdgpu_bo_free_kernel(&psp->hdcp_context.hdcp_shared_bo,
 			      &psp->hdcp_context.hdcp_shared_mc_addr,
@@ -1462,8 +1467,12 @@ static int psp_dtm_terminate(struct psp_context *psp)
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	if (!psp->dtm_context.dtm_initialized)
-		return 0;
+	if (!psp->dtm_context.dtm_initialized) {
+		if (psp->dtm_context.dtm_shared_buf)
+			goto out;
+		else
+			return 0;
+	}
 
 	ret = psp_dtm_unload(psp);
 	if (ret)
@@ -1471,6 +1480,7 @@ static int psp_dtm_terminate(struct psp_context *psp)
 
 	psp->dtm_context.dtm_initialized = false;
 
+out:
 	/* free hdcp shared memory */
 	amdgpu_bo_free_kernel(&psp->dtm_context.dtm_shared_bo,
 			      &psp->dtm_context.dtm_shared_mc_addr,
@@ -2589,11 +2599,10 @@ static int parse_ta_bin_descriptor(struct psp_context *psp,
 
 	switch (desc->fw_type) {
 	case TA_FW_TYPE_PSP_ASD:
-		psp->asd_fw_version	   = le32_to_cpu(desc->fw_version);
+		psp->asd_fw_version        = le32_to_cpu(desc->fw_version);
 		psp->asd_feature_version   = le32_to_cpu(desc->fw_version);
-		psp->asd_ucode_size	   = le32_to_cpu(desc->size_bytes);
+		psp->asd_ucode_size        = le32_to_cpu(desc->size_bytes);
 		psp->asd_start_addr 	   = ucode_start_addr;
-		psp->asd_fw                = psp->ta_fw;
 		break;
 	case TA_FW_TYPE_PSP_XGMI:
 		psp->ta_xgmi_ucode_version = le32_to_cpu(desc->fw_version);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index c136bd449744..82e952696d24 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1518,7 +1518,7 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data *data;
 	int i = 0;
-	int ret = 0;
+	int ret = 0, status;
 
 	if (!con || !con->eh_data || !bps || !count)
 		return -EINVAL;
@@ -1543,12 +1543,12 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 			.size = AMDGPU_GPU_PAGE_SIZE,
 			.flags = AMDGPU_RAS_RETIRE_PAGE_RESERVED,
 		};
-		ret = amdgpu_vram_mgr_query_page_status(
+		status = amdgpu_vram_mgr_query_page_status(
 				ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM),
 				data->bps[i].retired_page);
-		if (ret == -EBUSY)
+		if (status == -EBUSY)
 			(*bps)[i].flags = AMDGPU_RAS_RETIRE_PAGE_PENDING;
-		else if (ret == -ENOENT)
+		else if (status == -ENOENT)
 			(*bps)[i].flags = AMDGPU_RAS_RETIRE_PAGE_FAULT;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 1dd040166c63..19d9aa76cfbf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -30,6 +30,7 @@
 #define EEPROM_I2C_TARGET_ADDR_VEGA20		0xA0
 #define EEPROM_I2C_TARGET_ADDR_ARCTURUS		0xA8
 #define EEPROM_I2C_TARGET_ADDR_ARCTURUS_D342	0xA0
+#define EEPROM_I2C_TARGET_ADDR_SIENNA_CICHLID   0xA0
 
 /*
  * The 2 macros bellow represent the actual size in bytes that
@@ -62,7 +63,8 @@
 static bool __is_ras_eeprom_supported(struct amdgpu_device *adev)
 {
 	if ((adev->asic_type == CHIP_VEGA20) ||
-	    (adev->asic_type == CHIP_ARCTURUS))
+	    (adev->asic_type == CHIP_ARCTURUS) ||
+	    (adev->asic_type == CHIP_SIENNA_CICHLID))
 		return true;
 
 	return false;
@@ -100,6 +102,10 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 	case CHIP_ARCTURUS:
 		return __get_eeprom_i2c_addr_arct(adev, i2c_addr);
 
+	case CHIP_SIENNA_CICHLID:
+		*i2c_addr = EEPROM_I2C_TARGET_ADDR_SIENNA_CICHLID;
+		break;
+
 	default:
 		return false;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index ba1086784525..619d34c041ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -99,6 +99,10 @@
 #define mmGCR_GENERAL_CNTL_Sienna_Cichlid			0x1580
 #define mmGCR_GENERAL_CNTL_Sienna_Cichlid_BASE_IDX	0
 
+#define mmGOLDEN_TSC_COUNT_UPPER_Vangogh                0x0025
+#define mmGOLDEN_TSC_COUNT_UPPER_Vangogh_BASE_IDX       1
+#define mmGOLDEN_TSC_COUNT_LOWER_Vangogh                0x0026
+#define mmGOLDEN_TSC_COUNT_LOWER_Vangogh_BASE_IDX       1
 #define mmSPI_CONFIG_CNTL_1_Vangogh		 0x2441
 #define mmSPI_CONFIG_CNTL_1_Vangogh_BASE_IDX	 1
 #define mmVGT_TF_MEMORY_BASE_HI_Vangogh          0x2261
@@ -160,6 +164,9 @@
 #define mmGCVM_L2_CGTT_CLK_CTRL_Sienna_Cichlid          0x15db
 #define mmGCVM_L2_CGTT_CLK_CTRL_Sienna_Cichlid_BASE_IDX	0
 
+#define mmGC_THROTTLE_CTRL_Sienna_Cichlid              0x2030
+#define mmGC_THROTTLE_CTRL_Sienna_Cichlid_BASE_IDX     0
+
 MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
 MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
 MODULE_FIRMWARE("amdgpu/navi10_me.bin");
@@ -3324,6 +3331,7 @@ static void gfx_v10_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume);
 static void gfx_v10_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, bool secure);
 static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev);
 static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev);
+static void gfx_v10_3_set_power_brake_sequence(struct amdgpu_device *adev);
 
 static void gfx10_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask)
 {
@@ -7192,6 +7200,9 @@ static int gfx_v10_0_hw_init(void *handle)
 	if (adev->asic_type == CHIP_SIENNA_CICHLID)
 		gfx_v10_3_program_pbb_mode(adev);
 
+	if (adev->asic_type >= CHIP_SIENNA_CICHLID)
+		gfx_v10_3_set_power_brake_sequence(adev);
+
 	return r;
 }
 
@@ -7377,8 +7388,16 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 
 	amdgpu_gfx_off_ctrl(adev, false);
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
-	clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
-		((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
+	switch (adev->asic_type) {
+	case CHIP_VANGOGH:
+		clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh) |
+			((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh) << 32ULL);
+		break;
+	default:
+		clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
+			((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
+		break;
+	}
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
 	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
@@ -9169,6 +9188,31 @@ static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev)
 	}
 }
 
+static void gfx_v10_3_set_power_brake_sequence(struct amdgpu_device *adev)
+{
+	WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX,
+		     (0x1 << GRBM_GFX_INDEX__SA_BROADCAST_WRITES__SHIFT) |
+		     (0x1 << GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES__SHIFT) |
+		     (0x1 << GRBM_GFX_INDEX__SE_BROADCAST_WRITES__SHIFT));
+
+	WREG32_SOC15(GC, 0, mmGC_CAC_IND_INDEX, ixPWRBRK_STALL_PATTERN_CTRL);
+	WREG32_SOC15(GC, 0, mmGC_CAC_IND_DATA,
+		     (0x1 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_STEP_INTERVAL__SHIFT) |
+		     (0x12 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_BEGIN_STEP__SHIFT) |
+		     (0x13 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_END_STEP__SHIFT) |
+		     (0xf << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_THROTTLE_PATTERN_BIT_NUMS__SHIFT));
+
+	WREG32_SOC15(GC, 0, mmGC_THROTTLE_CTRL_Sienna_Cichlid,
+		     (0x1 << GC_THROTTLE_CTRL__PWRBRK_STALL_EN__SHIFT) |
+		     (0x1 << GC_THROTTLE_CTRL__PATTERN_MODE__SHIFT) |
+		     (0x5 << GC_THROTTLE_CTRL__RELEASE_STEP_INTERVAL__SHIFT));
+
+	WREG32_SOC15(GC, 0, mmDIDT_IND_INDEX, ixDIDT_SQ_THROTTLE_CTRL);
+
+	WREG32_SOC15(GC, 0, mmDIDT_IND_DATA,
+		     (0x1 << DIDT_SQ_THROTTLE_CTRL__PWRBRK_STALL_EN__SHIFT));
+}
+
 const struct amdgpu_ip_block_version gfx_v10_0_ip_block =
 {
 	.type = AMD_IP_BLOCK_TYPE_GFX,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index fc9bb94eaaf4..5f4805e4d04a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1647,7 +1647,7 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev)
 	}
 
 	/* No CPG in Arcturus */
-	if (adev->asic_type != CHIP_ARCTURUS) {
+	if (adev->gfx.num_gfx_rings) {
 		r = gfx_v9_0_init_cp_gfx_microcode(adev, chip_name);
 		if (r)
 			return r;
@@ -2633,7 +2633,14 @@ static void gfx_v9_0_wait_for_rlc_serdes(struct amdgpu_device *adev)
 static void gfx_v9_0_enable_gui_idle_interrupt(struct amdgpu_device *adev,
 					       bool enable)
 {
-	u32 tmp = RREG32_SOC15(GC, 0, mmCP_INT_CNTL_RING0);
+	u32 tmp;
+
+	/* don't toggle interrupts that are only applicable
+	 * to me0 pipe0 on AISCs that have me0 removed */
+	if (!adev->gfx.num_gfx_rings)
+		return;
+
+	tmp= RREG32_SOC15(GC, 0, mmCP_INT_CNTL_RING0);
 
 	tmp = REG_SET_FIELD(tmp, CP_INT_CNTL_RING0, CNTX_BUSY_INT_ENABLE, enable ? 1 : 0);
 	tmp = REG_SET_FIELD(tmp, CP_INT_CNTL_RING0, CNTX_EMPTY_INT_ENABLE, enable ? 1 : 0);
@@ -3822,7 +3829,7 @@ static int gfx_v9_0_cp_resume(struct amdgpu_device *adev)
 		gfx_v9_0_enable_gui_idle_interrupt(adev, false);
 
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
-		if (adev->asic_type != CHIP_ARCTURUS) {
+		if (adev->gfx.num_gfx_rings) {
 			/* legacy firmware loading */
 			r = gfx_v9_0_cp_gfx_load_microcode(adev);
 			if (r)
@@ -3838,7 +3845,7 @@ static int gfx_v9_0_cp_resume(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	if (adev->asic_type != CHIP_ARCTURUS) {
+	if (adev->gfx.num_gfx_rings) {
 		r = gfx_v9_0_cp_gfx_resume(adev);
 		if (r)
 			return r;
@@ -3848,7 +3855,7 @@ static int gfx_v9_0_cp_resume(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	if (adev->asic_type != CHIP_ARCTURUS) {
+	if (adev->gfx.num_gfx_rings) {
 		ring = &adev->gfx.gfx_ring[0];
 		r = amdgpu_ring_test_helper(ring);
 		if (r)
@@ -3884,7 +3891,7 @@ static void gfx_v9_0_init_tcp_config(struct amdgpu_device *adev)
 
 static void gfx_v9_0_cp_enable(struct amdgpu_device *adev, bool enable)
 {
-	if (adev->asic_type != CHIP_ARCTURUS)
+	if (adev->gfx.num_gfx_rings)
 		gfx_v9_0_cp_gfx_enable(adev, enable);
 	gfx_v9_0_cp_compute_enable(adev, enable);
 }
@@ -4025,7 +4032,7 @@ static int gfx_v9_0_soft_reset(void *handle)
 		/* stop the rlc */
 		adev->gfx.rlc.funcs->stop(adev);
 
-		if (adev->asic_type != CHIP_ARCTURUS)
+		if (adev->gfx.num_gfx_rings)
 			/* Disable GFX parsing/prefetching */
 			gfx_v9_0_cp_gfx_enable(adev, false);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index e1531d97f486..e22268f9dba7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1577,13 +1577,10 @@ static int gmc_v9_0_hw_init(void *handle)
 	gmc_v9_0_init_golden_registers(adev);
 
 	if (adev->mode_info.num_crtc) {
-		if (adev->asic_type != CHIP_ARCTURUS) {
-			/* Lockout access through VGA aperture*/
-			WREG32_FIELD15(DCE, 0, VGA_HDP_CONTROL, VGA_MEMORY_DISABLE, 1);
-
-			/* disable VGA render */
-			WREG32_FIELD15(DCE, 0, VGA_RENDER_CONTROL, VGA_VSTATUS_CNTL, 0);
-		}
+		/* Lockout access through VGA aperture*/
+		WREG32_FIELD15(DCE, 0, VGA_HDP_CONTROL, VGA_MEMORY_DISABLE, 1);
+		/* disable VGA render */
+		WREG32_FIELD15(DCE, 0, VGA_RENDER_CONTROL, VGA_VSTATUS_CNTL, 0);
 	}
 
 	amdgpu_device_program_register_sequence(adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
index b72c8e4ca36b..07104a1de308 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
@@ -310,7 +310,7 @@ static void mmhub_v2_3_setup_vmid_config(struct amdgpu_device *adev)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index d65a5339d354..3ba7bdfde65d 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -47,7 +47,7 @@ enum psp_gfx_crtl_cmd_id
     GFX_CTRL_CMD_ID_DISABLE_INT     = 0x00060000,   /* disable PSP-to-Gfx interrupt */
     GFX_CTRL_CMD_ID_MODE1_RST       = 0x00070000,   /* trigger the Mode 1 reset */
     GFX_CTRL_CMD_ID_GBR_IH_SET      = 0x00080000,   /* set Gbr IH_RB_CNTL registers */
-    GFX_CTRL_CMD_ID_CONSUME_CMD     = 0x000A0000,   /* send interrupt to psp for updating write pointer of vf */
+    GFX_CTRL_CMD_ID_CONSUME_CMD     = 0x00090000,   /* send interrupt to psp for updating write pointer of vf */
     GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING = 0x000C0000, /* destroy GPCOM ring */
 
     GFX_CTRL_CMD_ID_MAX             = 0x000F0000,   /* max command ID */
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 8a23636ecc27..0b3516c4eefb 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1239,7 +1239,8 @@ static int soc15_common_early_init(void *handle)
 		break;
 	case CHIP_RENOIR:
 		adev->asic_funcs = &soc15_asic_funcs;
-		if (adev->pdev->device == 0x1636)
+		if ((adev->pdev->device == 0x1636) ||
+		    (adev->pdev->device == 0x164c))
 			adev->apu_flags |= AMD_APU_IS_RENOIR;
 		else
 			adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 8cac497c2c45..a5640a6138cf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -1040,11 +1040,14 @@ static int kfd_create_vcrat_image_cpu(void *pcrat_image, size_t *size)
 				(struct crat_subtype_iolink *)sub_type_hdr);
 		if (ret < 0)
 			return ret;
-		crat_table->length += (sub_type_hdr->length * entries);
-		crat_table->total_entries += entries;
 
-		sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
-				sub_type_hdr->length * entries);
+		if (entries) {
+			crat_table->length += (sub_type_hdr->length * entries);
+			crat_table->total_entries += entries;
+
+			sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
+					sub_type_hdr->length * entries);
+		}
 #else
 		pr_info("IO link not available for non x86 platforms\n");
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 50922ff2927b..72c893fff61a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -422,7 +422,7 @@ static const struct kfd_device_info navi10_device_info = {
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
-	.needs_pci_atomics = false,
+	.needs_pci_atomics = true,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -440,7 +440,7 @@ static const struct kfd_device_info navi12_device_info = {
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
-	.needs_pci_atomics = false,
+	.needs_pci_atomics = true,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -458,7 +458,7 @@ static const struct kfd_device_info navi14_device_info = {
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
-	.needs_pci_atomics = false,
+	.needs_pci_atomics = true,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -476,7 +476,7 @@ static const struct kfd_device_info sienna_cichlid_device_info = {
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
-	.needs_pci_atomics = false,
+	.needs_pci_atomics = true,
 	.num_sdma_engines = 4,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -494,7 +494,7 @@ static const struct kfd_device_info navy_flounder_device_info = {
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
-	.needs_pci_atomics = false,
+	.needs_pci_atomics = true,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
@@ -530,7 +530,7 @@ static const struct kfd_device_info dimgrey_cavefish_device_info = {
 	.mqd_size_aligned = MQD_SIZE_ALIGNED,
 	.needs_iommu_device = false,
 	.supports_cwsr = true,
-	.needs_pci_atomics = false,
+	.needs_pci_atomics = true,
 	.num_sdma_engines = 2,
 	.num_xgmi_sdma_engines = 0,
 	.num_sdma_queues_per_engine = 8,
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 797b5d4b43e5..e509a175ed17 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -6,7 +6,7 @@ config DRM_AMD_DC
 	bool "AMD DC - Enable new display engine"
 	default y
 	select SND_HDA_COMPONENT if SND_HDA_CORE
-	select DRM_AMD_DC_DCN if (X86 || PPC64 || (ARM64 && KERNEL_MODE_NEON)) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
+	select DRM_AMD_DC_DCN if (X86 || PPC64) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
 	help
 	  Choose this option if you want to use the new display engine
 	  support for AMDGPU. This adds required support for Vega and
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 2c4dbdeec46a..c6da89df055d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -939,41 +939,6 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 }
 #endif
 
-#ifdef CONFIG_DEBUG_FS
-static int create_crtc_crc_properties(struct amdgpu_display_manager *dm)
-{
-	dm->crc_win_x_start_property =
-		drm_property_create_range(adev_to_drm(dm->adev),
-					  DRM_MODE_PROP_ATOMIC,
-					  "AMD_CRC_WIN_X_START", 0, U16_MAX);
-	if (!dm->crc_win_x_start_property)
-		return -ENOMEM;
-
-	dm->crc_win_y_start_property =
-		drm_property_create_range(adev_to_drm(dm->adev),
-					  DRM_MODE_PROP_ATOMIC,
-					  "AMD_CRC_WIN_Y_START", 0, U16_MAX);
-	if (!dm->crc_win_y_start_property)
-		return -ENOMEM;
-
-	dm->crc_win_x_end_property =
-		drm_property_create_range(adev_to_drm(dm->adev),
-					  DRM_MODE_PROP_ATOMIC,
-					  "AMD_CRC_WIN_X_END", 0, U16_MAX);
-	if (!dm->crc_win_x_end_property)
-		return -ENOMEM;
-
-	dm->crc_win_y_end_property =
-		drm_property_create_range(adev_to_drm(dm->adev),
-					  DRM_MODE_PROP_ATOMIC,
-					  "AMD_CRC_WIN_Y_END", 0, U16_MAX);
-	if (!dm->crc_win_y_end_property)
-		return -ENOMEM;
-
-	return 0;
-}
-#endif
-
 static int amdgpu_dm_init(struct amdgpu_device *adev)
 {
 	struct dc_init_data init_data;
@@ -1121,10 +1086,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 		dc_init_callbacks(adev->dm.dc, &init_params);
 	}
 #endif
-#ifdef CONFIG_DEBUG_FS
-	if (create_crtc_crc_properties(&adev->dm))
-		DRM_ERROR("amdgpu: failed to create crc property.\n");
-#endif
 	if (amdgpu_dm_initialize_drm_device(adev)) {
 		DRM_ERROR(
 		"amdgpu: failed to initialize sw for display support.\n");
@@ -5333,64 +5294,12 @@ dm_crtc_duplicate_state(struct drm_crtc *crtc)
 	state->crc_src = cur->crc_src;
 	state->cm_has_degamma = cur->cm_has_degamma;
 	state->cm_is_degamma_srgb = cur->cm_is_degamma_srgb;
-#ifdef CONFIG_DEBUG_FS
-	state->crc_window = cur->crc_window;
-#endif
+
 	/* TODO Duplicate dc_stream after objects are stream object is flattened */
 
 	return &state->base;
 }
 
-#ifdef CONFIG_DEBUG_FS
-static int amdgpu_dm_crtc_atomic_set_property(struct drm_crtc *crtc,
-					    struct drm_crtc_state *crtc_state,
-					    struct drm_property *property,
-					    uint64_t val)
-{
-	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = drm_to_adev(dev);
-	struct dm_crtc_state *dm_new_state =
-		to_dm_crtc_state(crtc_state);
-
-	if (property == adev->dm.crc_win_x_start_property)
-		dm_new_state->crc_window.x_start = val;
-	else if (property == adev->dm.crc_win_y_start_property)
-		dm_new_state->crc_window.y_start = val;
-	else if (property == adev->dm.crc_win_x_end_property)
-		dm_new_state->crc_window.x_end = val;
-	else if (property == adev->dm.crc_win_y_end_property)
-		dm_new_state->crc_window.y_end = val;
-	else
-		return -EINVAL;
-
-	return 0;
-}
-
-static int amdgpu_dm_crtc_atomic_get_property(struct drm_crtc *crtc,
-					    const struct drm_crtc_state *state,
-					    struct drm_property *property,
-					    uint64_t *val)
-{
-	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = drm_to_adev(dev);
-	struct dm_crtc_state *dm_state =
-		to_dm_crtc_state(state);
-
-	if (property == adev->dm.crc_win_x_start_property)
-		*val = dm_state->crc_window.x_start;
-	else if (property == adev->dm.crc_win_y_start_property)
-		*val = dm_state->crc_window.y_start;
-	else if (property == adev->dm.crc_win_x_end_property)
-		*val = dm_state->crc_window.x_end;
-	else if (property == adev->dm.crc_win_y_end_property)
-		*val = dm_state->crc_window.y_end;
-	else
-		return -EINVAL;
-
-	return 0;
-}
-#endif
-
 static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable)
 {
 	enum dc_irq_source irq_source;
@@ -5457,10 +5366,6 @@ static const struct drm_crtc_funcs amdgpu_dm_crtc_funcs = {
 	.enable_vblank = dm_enable_vblank,
 	.disable_vblank = dm_disable_vblank,
 	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
-#ifdef CONFIG_DEBUG_FS
-	.atomic_set_property = amdgpu_dm_crtc_atomic_set_property,
-	.atomic_get_property = amdgpu_dm_crtc_atomic_get_property,
-#endif
 };
 
 static enum drm_connector_status
@@ -6662,25 +6567,6 @@ static int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm,
 	return 0;
 }
 
-#ifdef CONFIG_DEBUG_FS
-static void attach_crtc_crc_properties(struct amdgpu_display_manager *dm,
-				struct amdgpu_crtc *acrtc)
-{
-	drm_object_attach_property(&acrtc->base.base,
-				   dm->crc_win_x_start_property,
-				   0);
-	drm_object_attach_property(&acrtc->base.base,
-				   dm->crc_win_y_start_property,
-				   0);
-	drm_object_attach_property(&acrtc->base.base,
-				   dm->crc_win_x_end_property,
-				   0);
-	drm_object_attach_property(&acrtc->base.base,
-				   dm->crc_win_y_end_property,
-				   0);
-}
-#endif
-
 static int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
 			       struct drm_plane *plane,
 			       uint32_t crtc_index)
@@ -6728,9 +6614,7 @@ static int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
 	drm_crtc_enable_color_mgmt(&acrtc->base, MAX_COLOR_LUT_ENTRIES,
 				   true, MAX_COLOR_LUT_ENTRIES);
 	drm_mode_crtc_set_gamma_size(&acrtc->base, MAX_COLOR_LEGACY_LUT_ENTRIES);
-#ifdef CONFIG_DEBUG_FS
-	attach_crtc_crc_properties(dm, acrtc);
-#endif
+
 	return 0;
 
 fail:
@@ -8367,7 +8251,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	 */
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
-		bool configure_crc = false;
 
 		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
 
@@ -8377,30 +8260,21 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 			dc_stream_retain(dm_new_crtc_state->stream);
 			acrtc->dm_irq_params.stream = dm_new_crtc_state->stream;
 			manage_dm_interrupts(adev, acrtc, true);
-		}
+
 #ifdef CONFIG_DEBUG_FS
-		if (new_crtc_state->active &&
-			amdgpu_dm_is_valid_crc_source(dm_new_crtc_state->crc_src)) {
 			/**
 			 * Frontend may have changed so reapply the CRC capture
 			 * settings for the stream.
 			 */
 			dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
-			dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
-
-			if (amdgpu_dm_crc_window_is_default(dm_new_crtc_state)) {
-				if (!old_crtc_state->active || drm_atomic_crtc_needs_modeset(new_crtc_state))
-					configure_crc = true;
-			} else {
-				if (amdgpu_dm_crc_window_changed(dm_new_crtc_state, dm_old_crtc_state))
-					configure_crc = true;
-			}
 
-			if (configure_crc)
+			if (amdgpu_dm_is_valid_crc_source(dm_new_crtc_state->crc_src)) {
 				amdgpu_dm_crtc_configure_crc_source(
-					crtc, dm_new_crtc_state, dm_new_crtc_state->crc_src);
-		}
+					crtc, dm_new_crtc_state,
+					dm_new_crtc_state->crc_src);
+			}
 #endif
+		}
 	}
 
 	for_each_new_crtc_in_state(state, crtc, new_crtc_state, j)
@@ -9367,7 +9241,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 		if (ret)
 			goto fail;
 
-		if (dm_old_crtc_state->dsc_force_changed && new_crtc_state)
+		if (dm_old_crtc_state->dsc_force_changed)
 			new_crtc_state->mode_changed = true;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 2ee6edb3df93..1182dafcef02 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -336,32 +336,6 @@ struct amdgpu_display_manager {
 	 */
 	const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
 
-#ifdef CONFIG_DEBUG_FS
-	/**
-	 * @crc_win_x_start_property:
-	 *
-	 * X start of the crc calculation window
-	 */
-	struct drm_property *crc_win_x_start_property;
-	/**
-	 * @crc_win_y_start_property:
-	 *
-	 * Y start of the crc calculation window
-	 */
-	struct drm_property *crc_win_y_start_property;
-	/**
-	 * @crc_win_x_end_property:
-	 *
-	 * X end of the crc calculation window
-	 */
-	struct drm_property *crc_win_x_end_property;
-	/**
-	 * @crc_win_y_end_property:
-	 *
-	 * Y end of the crc calculation window
-	 */
-	struct drm_property *crc_win_y_end_property;
-#endif
 	/**
 	 * @mst_encoders:
 	 *
@@ -448,15 +422,6 @@ struct dm_plane_state {
 	struct dc_plane_state *dc_state;
 };
 
-#ifdef CONFIG_DEBUG_FS
-struct crc_rec {
-	uint16_t x_start;
-	uint16_t y_start;
-	uint16_t x_end;
-	uint16_t y_end;
-	};
-#endif
-
 struct dm_crtc_state {
 	struct drm_crtc_state base;
 	struct dc_stream_state *stream;
@@ -479,9 +444,6 @@ struct dm_crtc_state {
 	struct dc_info_packet vrr_infopacket;
 
 	int abm_level;
-#ifdef CONFIG_DEBUG_FS
-	struct crc_rec crc_window;
-#endif
 };
 
 #define to_dm_crtc_state(x) container_of(x, struct dm_crtc_state, base)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
index 7b886a779a8c..66cb8730586b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
@@ -81,41 +81,6 @@ const char *const *amdgpu_dm_crtc_get_crc_sources(struct drm_crtc *crtc,
 	return pipe_crc_sources;
 }
 
-static void amdgpu_dm_set_crc_window_default(struct dm_crtc_state *dm_crtc_state)
-{
-	dm_crtc_state->crc_window.x_start = 0;
-	dm_crtc_state->crc_window.y_start = 0;
-	dm_crtc_state->crc_window.x_end = 0;
-	dm_crtc_state->crc_window.y_end = 0;
-}
-
-bool amdgpu_dm_crc_window_is_default(struct dm_crtc_state *dm_crtc_state)
-{
-	bool ret = true;
-
-	if ((dm_crtc_state->crc_window.x_start != 0) ||
-		(dm_crtc_state->crc_window.y_start != 0) ||
-		(dm_crtc_state->crc_window.x_end != 0) ||
-		(dm_crtc_state->crc_window.y_end != 0))
-		ret = false;
-
-	return ret;
-}
-
-bool amdgpu_dm_crc_window_changed(struct dm_crtc_state *dm_new_crtc_state,
-					struct dm_crtc_state *dm_old_crtc_state)
-{
-	bool ret = false;
-
-	if ((dm_new_crtc_state->crc_window.x_start != dm_old_crtc_state->crc_window.x_start) ||
-		(dm_new_crtc_state->crc_window.y_start != dm_old_crtc_state->crc_window.y_start) ||
-		(dm_new_crtc_state->crc_window.x_end != dm_old_crtc_state->crc_window.x_end) ||
-		(dm_new_crtc_state->crc_window.y_end != dm_old_crtc_state->crc_window.y_end))
-		ret = true;
-
-	return ret;
-}
-
 int
 amdgpu_dm_crtc_verify_crc_source(struct drm_crtc *crtc, const char *src_name,
 				 size_t *values_cnt)
@@ -140,7 +105,6 @@ int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
 	struct dc_stream_state *stream_state = dm_crtc_state->stream;
 	bool enable = amdgpu_dm_is_valid_crc_source(source);
 	int ret = 0;
-	struct crc_params *crc_window = NULL, tmp_window;
 
 	/* Configuration will be deferred to stream enable. */
 	if (!stream_state)
@@ -150,24 +114,8 @@ int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
 
 	/* Enable CRTC CRC generation if necessary. */
 	if (dm_is_crc_source_crtc(source) || source == AMDGPU_DM_PIPE_CRC_SOURCE_NONE) {
-		if (!enable)
-			amdgpu_dm_set_crc_window_default(dm_crtc_state);
-
-		if (!amdgpu_dm_crc_window_is_default(dm_crtc_state)) {
-			crc_window = &tmp_window;
-
-			tmp_window.windowa_x_start = dm_crtc_state->crc_window.x_start;
-			tmp_window.windowa_y_start = dm_crtc_state->crc_window.y_start;
-			tmp_window.windowa_x_end = dm_crtc_state->crc_window.x_end;
-			tmp_window.windowa_y_end = dm_crtc_state->crc_window.y_end;
-			tmp_window.windowb_x_start = dm_crtc_state->crc_window.x_start;
-			tmp_window.windowb_y_start = dm_crtc_state->crc_window.y_start;
-			tmp_window.windowb_x_end = dm_crtc_state->crc_window.x_end;
-			tmp_window.windowb_y_end = dm_crtc_state->crc_window.y_end;
-		}
-
 		if (!dc_stream_configure_crc(stream_state->ctx->dc,
-					     stream_state, crc_window, enable, enable)) {
+					     stream_state, NULL, enable, enable)) {
 			ret = -EINVAL;
 			goto unlock;
 		}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
index 0235bfb246e5..f7d731797d3f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
@@ -47,9 +47,6 @@ static inline bool amdgpu_dm_is_valid_crc_source(enum amdgpu_dm_pipe_crc_source
 
 /* amdgpu_dm_crc.c */
 #ifdef CONFIG_DEBUG_FS
-bool amdgpu_dm_crc_window_is_default(struct dm_crtc_state *dm_crtc_state);
-bool amdgpu_dm_crc_window_changed(struct dm_crtc_state *dm_new_crtc_state,
-					struct dm_crtc_state *dm_old_crtc_state);
 int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
 					struct dm_crtc_state *dm_crtc_state,
 					enum amdgpu_dm_pipe_crc_source source);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 357778556b06..26ed70e5538a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -165,7 +165,10 @@ static struct list_head *remove_irq_handler(struct amdgpu_device *adev,
 		handler = list_entry(entry, struct amdgpu_dm_irq_handler_data,
 				     list);
 
-		if (ih == handler) {
+		if (handler == NULL)
+			continue;
+
+		if (ih == handler->handler) {
 			/* Found our handler. Remove it from the list. */
 			list_del(&handler->list);
 			handler_removed = true;
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 64f515d74410..f3c00f479e1c 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -33,10 +33,6 @@ ifdef CONFIG_PPC64
 calcs_ccflags := -mhard-float -maltivec
 endif
 
-ifdef CONFIG_ARM64
-calcs_rcflags := -mgeneral-regs-only
-endif
-
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
index d59b380e7b7f..ff96bee57bfc 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
@@ -104,13 +104,6 @@ ifdef CONFIG_PPC64
 CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn21/rn_clk_mgr.o := $(call cc-option,-mno-gnu-attribute)
 endif
 
-# prevent build errors:
-# ...: '-mgeneral-regs-only' is incompatible with the use of floating-point types
-# this file is unused on arm64, just like on ppc64
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/clk_mgr/dcn21/rn_clk_mgr.o := -mgeneral-regs-only
-endif
-
 AMD_DAL_CLK_MGR_DCN21 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn21/,$(CLK_MGR_DCN21))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN21)
@@ -125,13 +118,6 @@ ifdef CONFIG_PPC64
 CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn30/dcn30_clk_mgr.o := $(call cc-option,-mno-gnu-attribute)
 endif
 
-# prevent build errors:
-# ...: '-mgeneral-regs-only' is incompatible with the use of floating-point types
-# this file is unused on arm64, just like on ppc64
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/clk_mgr/dcn30/dcn30_clk_mgr.o := -mgeneral-regs-only
-endif
-
 AMD_DAL_CLK_MGR_DCN30 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn30/,$(CLK_MGR_DCN30))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN30)
@@ -146,13 +132,6 @@ ifdef CONFIG_PPC64
 CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn301/vg_clk_mgr.o := $(call cc-option,-mno-gnu-attribute)
 endif
 
-# prevent build errors:
-# ...: '-mgeneral-regs-only' is incompatible with the use of floating-point types
-# this file is unused on arm64, just like on ppc64
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/clk_mgr/dcn301/vg_clk_mgr.o := -mgeneral-regs-only
-endif
-
 AMD_DAL_CLK_MGR_DCN301 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn301/,$(CLK_MGR_DCN301))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN301)
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 d00b02553d62..01b1853b7750 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
@@ -75,15 +75,8 @@ int rn_get_active_display_cnt_wa(
 	for (i = 0; i < dc->link_count; i++) {
 		const struct dc_link *link = dc->links[i];
 
-		/*
-		 * Only notify active stream or virtual stream.
-		 * Need to notify virtual stream to work around
-		 * headless case. HPD does not fire when system is in
-		 * S0i2.
-		 */
 		/* abusing the fact that the dig and phy are coupled to see if the phy is enabled */
-		if (link->connector_signal == SIGNAL_TYPE_VIRTUAL ||
-				link->link_enc->funcs->is_dig_enabled(link->link_enc))
+		if (link->link_enc->funcs->is_dig_enabled(link->link_enc))
 			display_count++;
 	}
 
@@ -234,12 +227,11 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base,
 					rn_vbios_smu_set_dppclk(clk_mgr, clk_mgr_base->clks.dppclk_khz);
 
 		// always update dtos unless clock is lowered and not safe to lower
-		if (new_clocks->dppclk_khz >= dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz)
-			rn_update_clocks_update_dpp_dto(
-					clk_mgr,
-					context,
-					clk_mgr_base->clks.actual_dppclk_khz,
-					safe_to_lower);
+		rn_update_clocks_update_dpp_dto(
+				clk_mgr,
+				context,
+				clk_mgr_base->clks.actual_dppclk_khz,
+				safe_to_lower);
 	}
 
 	if (update_dispclk &&
@@ -738,32 +730,32 @@ static struct wm_table ddr4_wm_table_rn = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9.09,
-			.sr_enter_plus_exit_time_us = 10.14,
+			.sr_exit_time_us = 11.90,
+			.sr_enter_plus_exit_time_us = 12.80,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 11.12,
-			.sr_enter_plus_exit_time_us = 12.48,
+			.sr_exit_time_us = 13.18,
+			.sr_enter_plus_exit_time_us = 14.30,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 11.12,
-			.sr_enter_plus_exit_time_us = 12.48,
+			.sr_exit_time_us = 13.18,
+			.sr_enter_plus_exit_time_us = 14.30,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 11.12,
-			.sr_enter_plus_exit_time_us = 12.48,
+			.sr_exit_time_us = 13.18,
+			.sr_enter_plus_exit_time_us = 14.30,
 			.valid = true,
 		},
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
index 11a7b583d561..7deeec9d1c7c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
@@ -99,7 +99,7 @@ int rn_vbios_smu_send_msg_with_param(struct clk_mgr_internal *clk_mgr, unsigned
 	/* Trigger the message transaction by writing the message ID */
 	REG_WRITE(MP1_SMN_C2PMSG_67, msg_id);
 
-	result = rn_smu_wait_for_response(clk_mgr, 10, 1000);
+	result = rn_smu_wait_for_response(clk_mgr, 10, 200000);
 
 	ASSERT(result == VBIOSSMC_Result_OK || result == VBIOSSMC_Result_UnknownCmd);
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
index 9a8e66bba9c0..991b9c5beaa3 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
@@ -74,15 +74,8 @@ int vg_get_active_display_cnt_wa(
 	for (i = 0; i < dc->link_count; i++) {
 		const struct dc_link *link = dc->links[i];
 
-		/*
-		 * Only notify active stream or virtual stream.
-		 * Need to notify virtual stream to work around
-		 * headless case. HPD does not fire when system is in
-		 * S0i2.
-		 */
 		/* abusing the fact that the dig and phy are coupled to see if the phy is enabled */
-		if (link->connector_signal == SIGNAL_TYPE_VIRTUAL ||
-				link->link_enc->funcs->is_dig_enabled(link->link_enc))
+		if (link->link_enc->funcs->is_dig_enabled(link->link_enc))
 			display_count++;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 7339d9855ec8..58eb0d69873a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2625,26 +2625,6 @@ static void commit_planes_for_stream(struct dc *dc,
 		}
 	}
 
-	if (update_type != UPDATE_TYPE_FAST) {
-		// If changing VTG FP2: wait until back in vactive to program FP2
-		// Need to ensure that pipe unlock happens soon after to minimize race condition
-		for (i = 0; i < dc->res_pool->pipe_count; i++) {
-			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
-
-			if (pipe_ctx->top_pipe || pipe_ctx->stream != stream)
-				continue;
-
-			if (!pipe_ctx->update_flags.bits.global_sync)
-				continue;
-
-			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK);
-			pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE);
-
-			pipe_ctx->stream_res.tg->funcs->set_vtg_params(
-					pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing, true);
-		}
-	}
-
 	if ((update_type != UPDATE_TYPE_FAST) && dc->hwss.interdependent_update_lock)
 		dc->hwss.interdependent_update_lock(dc, context, false);
 	else
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 9e1071b2181f..f4a2088ab179 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -2487,9 +2487,14 @@ enum dc_status dc_link_validate_mode_timing(
 static struct abm *get_abm_from_stream_res(const struct dc_link *link)
 {
 	int i;
-	struct dc *dc = link->ctx->dc;
+	struct dc *dc = NULL;
 	struct abm *abm = NULL;
 
+	if (!link || !link->ctx)
+		return NULL;
+
+	dc = link->ctx->dc;
+
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct pipe_ctx pipe_ctx = dc->current_state->res_ctx.pipe_ctx[i];
 		struct dc_stream_state *stream = pipe_ctx.stream;
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 6b11d4af54af..1bd1a0935290 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
@@ -3173,13 +3173,7 @@ static void get_active_converter_info(
 	}
 
 	/* DPCD 0x5 bit 0 = 1, it indicate it's branch device */
-	if (ds_port.fields.PORT_TYPE == DOWNSTREAM_DP) {
-		link->dpcd_caps.is_branch_dev = false;
-	}
-
-	else {
-		link->dpcd_caps.is_branch_dev = ds_port.fields.PORT_PRESENT;
-	}
+	link->dpcd_caps.is_branch_dev = ds_port.fields.PORT_PRESENT;
 
 	switch (ds_port.fields.PORT_TYPE) {
 	case DOWNSTREAM_VGA:
@@ -3998,7 +3992,7 @@ bool dc_link_dp_set_test_pattern(
 	unsigned int cust_pattern_size)
 {
 	struct pipe_ctx *pipes = link->dc->current_state->res_ctx.pipe_ctx;
-	struct pipe_ctx *pipe_ctx = &pipes[0];
+	struct pipe_ctx *pipe_ctx = NULL;
 	unsigned int lane;
 	unsigned int i;
 	unsigned char link_qual_pattern[LANE_COUNT_DP_MAX] = {0};
@@ -4008,12 +4002,18 @@ bool dc_link_dp_set_test_pattern(
 	memset(&training_pattern, 0, sizeof(training_pattern));
 
 	for (i = 0; i < MAX_PIPES; i++) {
+		if (pipes[i].stream == NULL)
+			continue;
+
 		if (pipes[i].stream->link == link && !pipes[i].top_pipe && !pipes[i].prev_odm_pipe) {
 			pipe_ctx = &pipes[i];
 			break;
 		}
 	}
 
+	if (pipe_ctx == NULL)
+		return false;
+
 	/* Reset CRTC Test Pattern if it is currently running and request is VideoMode */
 	if (link->test_pattern_enabled && test_pattern ==
 			DP_TEST_PATTERN_VIDEO_MODE) {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
index 733e6e6e43bd..62ad1a11bff9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
@@ -31,11 +31,4 @@ DCN10 = dcn10_init.o dcn10_resource.o dcn10_ipp.o dcn10_hw_sequencer.o \
 
 AMD_DAL_DCN10 = $(addprefix $(AMDDALPATH)/dc/dcn10/,$(DCN10))
 
-# fix:
-# ...: '-mgeneral-regs-only' is incompatible with the use of floating-point types
-# aarch64 does not support soft-float, so use hard-float and handle this in code
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn10/dcn10_resource.o := -mgeneral-regs-only
-endif
-
 AMD_DISPLAY_FILES += $(AMD_DAL_DCN10)
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 41679ad531c5..9e796dfeac20 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -1241,6 +1241,22 @@ void hubp1_vtg_sel(struct hubp *hubp, uint32_t otg_inst)
 	REG_UPDATE(DCHUBP_CNTL, HUBP_VTG_SEL, otg_inst);
 }
 
+bool hubp1_in_blank(struct hubp *hubp)
+{
+	uint32_t in_blank;
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+
+	REG_GET(DCHUBP_CNTL, HUBP_IN_BLANK, &in_blank);
+	return in_blank ? true : false;
+}
+
+void hubp1_soft_reset(struct hubp *hubp, bool reset)
+{
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+
+	REG_UPDATE(DCHUBP_CNTL, HUBP_DISABLE, reset ? 1 : 0);
+}
+
 void hubp1_init(struct hubp *hubp)
 {
 	//do nothing
@@ -1272,6 +1288,8 @@ static const struct hubp_funcs dcn10_hubp_funcs = {
 
 	.dmdata_set_attributes = NULL,
 	.dmdata_load = NULL,
+	.hubp_soft_reset = hubp1_soft_reset,
+	.hubp_in_blank = hubp1_in_blank,
 };
 
 /*****************************************/
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
index 780af5b3c16f..a9a6ed7f4f99 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -260,6 +260,7 @@
 	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_NO_OUTSTANDING_REQ, mask_sh),\
 	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_VTG_SEL, mask_sh),\
 	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_DISABLE, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_IN_BLANK, mask_sh),\
 	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_PIPES, mask_sh),\
 	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, NUM_BANKS, mask_sh),\
 	HUBP_SF(HUBP0_DCSURF_ADDR_CONFIG, PIPE_INTERLEAVE, mask_sh),\
@@ -455,6 +456,7 @@
 	type HUBP_VTG_SEL;\
 	type HUBP_UNDERFLOW_STATUS;\
 	type HUBP_UNDERFLOW_CLEAR;\
+	type HUBP_IN_BLANK;\
 	type NUM_PIPES;\
 	type NUM_BANKS;\
 	type PIPE_INTERLEAVE;\
@@ -772,5 +774,7 @@ void hubp1_vready_workaround(struct hubp *hubp,
 
 void hubp1_init(struct hubp *hubp);
 void hubp1_read_state_common(struct hubp *hubp);
+bool hubp1_in_blank(struct hubp *hubp);
+void hubp1_soft_reset(struct hubp *hubp, bool reset);
 
 #endif
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 3fcd408e9103..b096011acb49 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -467,6 +467,17 @@ void mpc1_cursor_lock(struct mpc *mpc, int opp_id, bool lock)
 	REG_SET(CUR[opp_id], 0, CUR_VUPDATE_LOCK_SET, lock ? 1 : 0);
 }
 
+unsigned int mpc1_get_mpc_out_mux(struct mpc *mpc, int opp_id)
+{
+	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+	uint32_t val = 0xf;
+
+	if (opp_id < MAX_OPP && REG(MUX[opp_id]))
+		REG_GET(MUX[opp_id], MPC_OUT_MUX, &val);
+
+	return val;
+}
+
 static const struct mpc_funcs dcn10_mpc_funcs = {
 	.read_mpcc_state = mpc1_read_mpcc_state,
 	.insert_plane = mpc1_insert_plane,
@@ -483,6 +494,7 @@ static const struct mpc_funcs dcn10_mpc_funcs = {
 	.set_denorm_clamp = NULL,
 	.set_output_csc = NULL,
 	.set_output_gamma = NULL,
+	.get_mpc_out_mux = mpc1_get_mpc_out_mux,
 };
 
 void dcn10_mpc_construct(struct dcn10_mpc *mpc10,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
index 66a4719c22a0..dbfffc6383dc 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
@@ -200,4 +200,5 @@ void mpc1_read_mpcc_state(
 
 void mpc1_cursor_lock(struct mpc *mpc, int opp_id, bool lock);
 
+unsigned int mpc1_get_mpc_out_mux(struct mpc *mpc, int opp_id);
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index bdc37831535e..90e912fef2b3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -608,8 +608,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.disable_pplib_clock_request = false,
 		.disable_pplib_wm_range = false,
 		.pplib_wm_report_mode = WM_REPORT_DEFAULT,
-		.pipe_split_policy = MPC_SPLIT_DYNAMIC,
-		.force_single_disp_pipe_split = true,
+		.pipe_split_policy = MPC_SPLIT_AVOID,
+		.force_single_disp_pipe_split = false,
 		.disable_dcc = DCC_ENABLE,
 		.voltage_align_fclk = true,
 		.disable_stereo_support = true,
@@ -1534,15 +1534,8 @@ static bool dcn10_resource_construct(
 	memcpy(dc->dcn_ip, &dcn10_ip_defaults, sizeof(dcn10_ip_defaults));
 	memcpy(dc->dcn_soc, &dcn10_soc_defaults, sizeof(dcn10_soc_defaults));
 
-#if defined(CONFIG_ARM64)
-	/* Aarch64 does not support -msoft-float/-mfloat-abi=soft */
-	DC_FP_START();
-	dcn10_resource_construct_fp(dc);
-	DC_FP_END();
-#else
 	/* Other architectures we build for build this with soft-float */
 	dcn10_resource_construct_fp(dc);
-#endif
 
 	pool->base.pp_smu = dcn10_pp_smu_create(ctx);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
index 624cb1341ef1..5fcaf78334ff 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
@@ -17,10 +17,6 @@ ifdef CONFIG_PPC64
 CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -maltivec
 endif
 
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mgeneral-regs-only
-endif
-
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
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 b7e44e53a342..0df0da2e6a4d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -1595,6 +1595,8 @@ static struct hubp_funcs dcn20_hubp_funcs = {
 	.hubp_set_flip_control_surface_gsl = hubp2_set_flip_control_surface_gsl,
 	.hubp_init = hubp1_init,
 	.validate_dml_output = hubp2_validate_dml_output,
+	.hubp_in_blank = hubp1_in_blank,
+	.hubp_soft_reset = hubp1_soft_reset,
 };
 
 
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 31a477194d3b..cb822df21b7c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1586,7 +1586,10 @@ static void dcn20_program_pipe(
 			&& !pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe)
 		hws->funcs.blank_pixel_data(dc, pipe_ctx, !pipe_ctx->plane_state->visible);
 
-	if (pipe_ctx->update_flags.bits.global_sync) {
+	/* Only update TG on top pipe */
+	if (pipe_ctx->update_flags.bits.global_sync && !pipe_ctx->top_pipe
+			&& !pipe_ctx->prev_odm_pipe) {
+
 		pipe_ctx->stream_res.tg->funcs->program_global_sync(
 				pipe_ctx->stream_res.tg,
 				pipe_ctx->pipe_dlg_param.vready_offset,
@@ -1594,8 +1597,11 @@ static void dcn20_program_pipe(
 				pipe_ctx->pipe_dlg_param.vupdate_offset,
 				pipe_ctx->pipe_dlg_param.vupdate_width);
 
+		pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VBLANK);
+		pipe_ctx->stream_res.tg->funcs->wait_for_state(pipe_ctx->stream_res.tg, CRTC_STATE_VACTIVE);
+
 		pipe_ctx->stream_res.tg->funcs->set_vtg_params(
-				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing, false);
+				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing, true);
 
 		if (hws->funcs.setup_vupdate_interrupt)
 			hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx);
@@ -2570,4 +2576,4 @@ void dcn20_set_disp_pattern_generator(const struct dc *dc,
 {
 	pipe_ctx->stream_res.opp->funcs->opp_set_disp_pattern_generator(pipe_ctx->stream_res.opp, test_pattern,
 			color_space, color_depth, solid_color, width, height, offset);
-}
\ No newline at end of file
+}
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 99cc095dc33c..6a99fdd55e8c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
@@ -556,6 +556,7 @@ const struct mpc_funcs dcn20_mpc_funcs = {
 	.set_ocsc_default = mpc2_set_ocsc_default,
 	.set_output_gamma = mpc2_set_output_gamma,
 	.power_on_mpc_mem_pwr = mpc20_power_on_ogam_lut,
+	.get_mpc_out_mux = mpc1_get_mpc_out_mux,
 };
 
 void dcn20_mpc_construct(struct dcn20_mpc *mpc20,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index ff36db5edf6c..e04ecf0fc0db 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -1933,7 +1933,7 @@ bool dcn20_split_stream_for_odm(
 		next_odm_pipe->stream_res.opp = pool->opps[next_odm_pipe->pipe_idx];
 	else
 		next_odm_pipe->stream_res.opp = next_odm_pipe->top_pipe->stream_res.opp;
-	if (next_odm_pipe->stream->timing.flags.DSC == 1) {
+	if (next_odm_pipe->stream->timing.flags.DSC == 1 && !next_odm_pipe->top_pipe) {
 		dcn20_acquire_dsc(dc, res_ctx, &next_odm_pipe->stream_res.dsc, next_odm_pipe->pipe_idx);
 		ASSERT(next_odm_pipe->stream_res.dsc);
 		if (next_odm_pipe->stream_res.dsc == NULL)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index 1ee5fc03b7b3..bb8c95141082 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -13,10 +13,6 @@ ifdef CONFIG_PPC64
 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -maltivec
 endif
 
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mgeneral-regs-only
-endif
-
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
index 248c2711aace..c20331eb62e0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
@@ -41,11 +41,6 @@ CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -maltivec
 CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -maltivec
 endif
 
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mgeneral-regs-only
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mgeneral-regs-only
-endif
-
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
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 af462fe4260d..88ffa9ff1ed1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c
@@ -509,6 +509,8 @@ static struct hubp_funcs dcn30_hubp_funcs = {
 	.hubp_clear_underflow = hubp2_clear_underflow,
 	.hubp_set_flip_control_surface_gsl = hubp2_set_flip_control_surface_gsl,
 	.hubp_init = hubp3_init,
+	.hubp_in_blank = hubp1_in_blank,
+	.hubp_soft_reset = hubp1_soft_reset,
 };
 
 bool hubp3_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
index d7d053fc6e91..3e6f76096119 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_mpc.c
@@ -1428,6 +1428,7 @@ const struct mpc_funcs dcn30_mpc_funcs = {
 	.program_3dlut = mpc3_program_3dlut,
 	.release_rmu = mpcc3_release_rmu,
 	.power_on_mpc_mem_pwr = mpc20_power_on_ogam_lut,
+	.get_mpc_out_mux = mpc1_get_mpc_out_mux,
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
index 2fd5d34e4ba6..3ca7d911d25c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
@@ -21,10 +21,6 @@ ifdef CONFIG_PPC64
 CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -mhard-float -maltivec
 endif
 
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -mgeneral-regs-only
-endif
-
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
index 4825c5c1c6ed..35f5bf08ae96 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
@@ -1731,6 +1731,7 @@ static struct resource_funcs dcn301_res_pool_funcs = {
 	.populate_dml_pipes = dcn30_populate_dml_pipes_from_context,
 	.acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer,
 	.add_stream_to_ctx = dcn30_add_stream_to_ctx,
+	.add_dsc_to_stream_resource = dcn20_add_dsc_to_stream_resource,
 	.remove_stream_from_ctx = dcn20_remove_stream_from_ctx,
 	.populate_dml_writeback_from_context = dcn30_populate_dml_writeback_from_context,
 	.set_mcif_arb_params = dcn30_set_mcif_arb_params,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/Makefile b/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
index 36e44e1b07fa..8d4924b7dc22 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
@@ -20,10 +20,6 @@ ifdef CONFIG_PPC64
 CFLAGS_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o := -mhard-float -maltivec
 endif
 
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o := -mgeneral-regs-only
-endif
-
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index a02a33dcd70b..6bb7f2905821 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -33,10 +33,6 @@ ifdef CONFIG_PPC64
 dml_ccflags := -mhard-float -maltivec
 endif
 
-ifdef CONFIG_ARM64
-dml_rcflags := -mgeneral-regs-only
-endif
-
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
index 860e72a51534..80170f9721ce 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
@@ -2635,14 +2635,15 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP
 	}
 
 	if (mode_lib->vba.DRAMClockChangeSupportsVActive &&
-			mode_lib->vba.MinActiveDRAMClockChangeMargin > 60 &&
-			mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) {
+			mode_lib->vba.MinActiveDRAMClockChangeMargin > 60) {
 		mode_lib->vba.DRAMClockChangeWatermark += 25;
 
 		for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) {
-			if (mode_lib->vba.DRAMClockChangeWatermark >
-			dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
-				mode_lib->vba.MinTTUVBlank[k] += 25;
+			if (mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) {
+				if (mode_lib->vba.DRAMClockChangeWatermark >
+				dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
+					mode_lib->vba.MinTTUVBlank[k] += 25;
+			}
 		}
 
 		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
index f2624a1156e5..8d31eb75c6a6 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -10,10 +10,6 @@ ifdef CONFIG_PPC64
 dsc_ccflags := -mhard-float -maltivec
 endif
 
-ifdef CONFIG_ARM64
-dsc_rcflags := -mgeneral-regs-only
-endif
-
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 315e3061c592..22f3f643ed1b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -188,6 +188,8 @@ struct hubp_funcs {
 	void (*set_unbounded_requesting)(
 		struct hubp *hubp,
 		bool enable);
+	bool (*hubp_in_blank)(struct hubp *hubp);
+	void (*hubp_soft_reset)(struct hubp *hubp, bool reset);
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
index 879f502ae530..75c77ad9cbfe 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@@ -359,6 +359,10 @@ struct mpc_funcs {
 
 	int (*release_rmu)(struct mpc *mpc, int mpcc_id);
 
+	unsigned int (*get_mpc_out_mux)(
+			struct mpc *mpc,
+			int opp_id);
+
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index 95cb56929e79..126c2f3a4dd3 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -55,10 +55,6 @@
 #include <asm/fpu/api.h>
 #define DC_FP_START() kernel_fpu_begin()
 #define DC_FP_END() kernel_fpu_end()
-#elif defined(CONFIG_ARM64)
-#include <asm/neon.h>
-#define DC_FP_START() kernel_neon_begin()
-#define DC_FP_END() kernel_neon_end()
 #elif defined(CONFIG_PPC64)
 #include <asm/switch_to.h>
 #include <asm/cputable.h>
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index f512bda96917..249a076d6f69 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -47,10 +47,10 @@
 
 /* Firmware versioning. */
 #ifdef DMUB_EXPOSE_VERSION
-#define DMUB_FW_VERSION_GIT_HASH 0xa18e25995
+#define DMUB_FW_VERSION_GIT_HASH 0xf51b86a
 #define DMUB_FW_VERSION_MAJOR 0
 #define DMUB_FW_VERSION_MINOR 0
-#define DMUB_FW_VERSION_REVISION 46
+#define DMUB_FW_VERSION_REVISION 47
 #define DMUB_FW_VERSION_TEST 0
 #define DMUB_FW_VERSION_VBIOS 0
 #define DMUB_FW_VERSION_HOTFIX 0
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
index f244b72e74e0..73ca49f05bd3 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
@@ -128,8 +128,12 @@ static inline uint8_t get_device_count(struct mod_hdcp *hdcp)
 
 static inline enum mod_hdcp_status check_device_count(struct mod_hdcp *hdcp)
 {
-	/* device count must be greater than or equal to tracked hdcp displays */
-	return (get_device_count(hdcp) < get_active_display_count(hdcp)) ?
+	/* Some MST display may choose to report the internal panel as an HDCP RX.
+	 * To update this condition with 1(because the immediate repeater's internal
+	 * panel is possibly not included in DEVICE_COUNT) + get_device_count(hdcp).
+	 * Device count must be greater than or equal to tracked hdcp displays.
+	 */
+	return ((1 + get_device_count(hdcp)) < get_active_display_count(hdcp)) ?
 			MOD_HDCP_STATUS_HDCP1_DEVICE_COUNT_MISMATCH_FAILURE :
 			MOD_HDCP_STATUS_SUCCESS;
 }
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
index 549c113abcf7..a0895a7efda2 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
@@ -207,8 +207,11 @@ static inline uint8_t get_device_count(struct mod_hdcp *hdcp)
 
 static enum mod_hdcp_status check_device_count(struct mod_hdcp *hdcp)
 {
-	/* device count must be greater than or equal to tracked hdcp displays */
-	return (get_device_count(hdcp) < get_active_display_count(hdcp)) ?
+	/* Some MST display may choose to report the internal panel as an HDCP RX.   */
+	/* To update this condition with 1(because the immediate repeater's internal */
+	/* panel is possibly not included in DEVICE_COUNT) + get_device_count(hdcp). */
+	/* Device count must be greater than or equal to tracked hdcp displays.      */
+	return ((1 + get_device_count(hdcp)) < get_active_display_count(hdcp)) ?
 			MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE :
 			MOD_HDCP_STATUS_SUCCESS;
 }
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index cc983f662157..4fd8bce95d84 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -82,22 +82,24 @@ struct abm_parameters {
 	unsigned char deviation_gain;
 	unsigned char min_knee;
 	unsigned char max_knee;
+	unsigned short blRampReduction;
+	unsigned short blRampStart;
 };
 
 static const struct abm_parameters abm_settings_config0[abm_defines_max_level] = {
-//  min_red  max_red  bright_pos  dark_pos  brightness_gain  contrast  deviation  min_knee  max_knee
-	{0xff,   0xbf,    0x20,       0x00,     0xff,            0x99,     0xb3,      0x40,     0xe0},
-	{0xde,   0x85,    0x20,       0x00,     0xff,            0x90,     0xa8,      0x40,     0xdf},
-	{0xb0,   0x50,    0x20,       0x00,     0xc0,            0x88,     0x78,      0x70,     0xa0},
-	{0x82,   0x40,    0x20,       0x00,     0x00,            0xff,     0xb3,      0x70,     0x70},
+//  min_red  max_red  bright_pos  dark_pos  bright_gain  contrast  dev   min_knee  max_knee  blStart  blRed
+	{0xff,   0xbf,    0x20,   0x00,     0xff,        0x99,     0xb3, 0x40,     0xe0,     0xCCCC,  0xCCCC},
+	{0xde,   0x85,    0x20,   0x00,     0xff,        0x90,     0xa8, 0x40,     0xdf,     0xCCCC,  0xCCCC},
+	{0xb0,   0x50,    0x20,   0x00,     0xc0,        0x88,     0x78, 0x70,     0xa0,     0xCCCC,  0xCCCC},
+	{0x82,   0x40,    0x20,   0x00,     0x00,        0xff,     0xb3, 0x70,     0x70,     0xCCCC,  0xCCCC},
 };
 
 static const struct abm_parameters abm_settings_config1[abm_defines_max_level] = {
-//  min_red  max_red  bright_pos  dark_pos  brightness_gain  contrast  deviation  min_knee  max_knee
-	{0xf0,   0xd9,    0x20,       0x00,     0x00,            0xff,     0xb3,      0x70,     0x70},
-	{0xcd,   0xa5,    0x20,       0x00,     0x00,            0xff,     0xb3,      0x70,     0x70},
-	{0x99,   0x65,    0x20,       0x00,     0x00,            0xff,     0xb3,      0x70,     0x70},
-	{0x82,   0x4d,    0x20,       0x00,     0x00,            0xff,     0xb3,      0x70,     0x70},
+//  min_red  max_red  bright_pos  dark_pos  bright_gain  contrast  dev   min_knee  max_knee  blStart  blRed
+	{0xf0,   0xd9,    0x20,   0x00,     0x00,        0xff,     0xb3, 0x70,     0x70,     0xCCCC,  0xCCCC},
+	{0xcd,   0xa5,    0x20,   0x00,     0x00,        0xff,     0xb3, 0x70,     0x70,     0xCCCC,  0xCCCC},
+	{0x99,   0x65,    0x20,   0x00,     0x00,        0xff,     0xb3, 0x70,     0x70,     0xCCCC,  0xCCCC},
+	{0x82,   0x4d,    0x20,   0x00,     0x00,        0xff,     0xb3, 0x70,     0x70,     0xCCCC,  0xCCCC},
 };
 
 static const struct abm_parameters * const abm_settings[] = {
@@ -662,6 +664,7 @@ bool dmub_init_abm_config(struct resource_pool *res_pool,
 {
 	struct iram_table_v_2_2 ram_table;
 	struct abm_config_table config;
+	unsigned int set = params.set;
 	bool result = false;
 	uint32_t i, j = 0;
 
@@ -710,6 +713,18 @@ bool dmub_init_abm_config(struct resource_pool *res_pool,
 		config.max_knee[i] = ram_table.max_knee[i];
 	}
 
+	if (params.backlight_ramping_override) {
+		for (i = 0; i < NUM_AGGR_LEVEL; i++) {
+			config.blRampReduction[i] = params.backlight_ramping_reduction;
+			config.blRampStart[i] = params.backlight_ramping_start;
+			}
+		} else {
+			for (i = 0; i < NUM_AGGR_LEVEL; i++) {
+				config.blRampReduction[i] = abm_settings[set][i].blRampReduction;
+				config.blRampStart[i] = abm_settings[set][i].blRampStart;
+				}
+			}
+
 	config.min_abm_backlight = ram_table.min_abm_backlight;
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
index fa4728d88092..6f2eecce6baa 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
@@ -39,6 +39,7 @@ enum abm_defines {
 struct dmcu_iram_parameters {
 	unsigned int *backlight_lut_array;
 	unsigned int backlight_lut_array_size;
+	bool backlight_ramping_override;
 	unsigned int backlight_ramping_reduction;
 	unsigned int backlight_ramping_start;
 	unsigned int min_abm_backlight;
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
index e5aa0725147c..13de692a4213 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
@@ -30,7 +30,7 @@
 #define SMU11_DRIVER_IF_VERSION_NV10 0x36
 #define SMU11_DRIVER_IF_VERSION_NV12 0x36
 #define SMU11_DRIVER_IF_VERSION_NV14 0x36
-#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x3B
+#define SMU11_DRIVER_IF_VERSION_Sienna_Cichlid 0x3D
 #define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0xC
 #define SMU11_DRIVER_IF_VERSION_VANGOGH 0x02
 #define SMU11_DRIVER_IF_VERSION_Dimgrey_Cavefish 0xF
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index e57e64bbacdc..88322781e447 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@@ -251,7 +251,7 @@ static int smu10_set_hard_min_gfxclk_by_freq(struct pp_hwmgr *hwmgr, uint32_t cl
 		smu10_data->gfx_actual_soft_min_freq = clock;
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 					PPSMC_MSG_SetHardMinGfxClk,
-					smu10_data->gfx_actual_soft_min_freq,
+					clock,
 					NULL);
 	}
 	return 0;
@@ -558,7 +558,8 @@ static int smu10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 
 	/* enable the pp_od_clk_voltage sysfs file */
 	hwmgr->od_enabled = 1;
-
+	/* disabled fine grain tuning function by default */
+	data->fine_grain_enabled = 0;
 	return result;
 }
 
@@ -597,6 +598,7 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 	uint32_t min_mclk = hwmgr->display_config->min_mem_set_clock/100;
 	uint32_t index_fclk = data->clock_vol_info.vdd_dep_on_fclk->count - 1;
 	uint32_t index_socclk = data->clock_vol_info.vdd_dep_on_socclk->count - 1;
+	uint32_t fine_grain_min_freq = 0, fine_grain_max_freq = 0;
 
 	if (hwmgr->smu_version < 0x1E3700) {
 		pr_info("smu firmware version too old, can not set dpm level\n");
@@ -613,6 +615,14 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 	switch (level) {
 	case AMD_DPM_FORCED_LEVEL_HIGH:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
+		data->fine_grain_enabled = 0;
+
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+		data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+		data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinGfxClk,
 						data->gfx_max_freq_limit/100,
@@ -648,6 +658,14 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 						NULL);
 		break;
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
+		data->fine_grain_enabled = 0;
+
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+		data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+		data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinGfxClk,
 						min_sclk,
@@ -658,6 +676,14 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 						NULL);
 		break;
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
+		data->fine_grain_enabled = 0;
+
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+		data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+		data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinFclkByFreq,
 						min_mclk,
@@ -668,6 +694,14 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 						NULL);
 		break;
 	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
+		data->fine_grain_enabled = 0;
+
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+		data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+		data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinGfxClk,
 						SMU10_UMD_PSTATE_GFXCLK,
@@ -703,6 +737,14 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 						NULL);
 		break;
 	case AMD_DPM_FORCED_LEVEL_AUTO:
+		data->fine_grain_enabled = 0;
+
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+		data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+		data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinGfxClk,
 						min_sclk,
@@ -741,6 +783,14 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 						NULL);
 		break;
 	case AMD_DPM_FORCED_LEVEL_LOW:
+		data->fine_grain_enabled = 0;
+
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+		data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+		data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetHardMinGfxClk,
 						data->gfx_min_freq_limit/100,
@@ -759,6 +809,7 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 						NULL);
 		break;
 	case AMD_DPM_FORCED_LEVEL_MANUAL:
+		data->fine_grain_enabled = 1;
 	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
 	default:
 		break;
@@ -948,6 +999,8 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 	struct smu10_voltage_dependency_table *mclk_table =
 			data->clock_vol_info.vdd_dep_on_fclk;
 	uint32_t i, now, size = 0;
+	uint32_t min_freq, max_freq = 0;
+	uint32_t ret = 0;
 
 	switch (type) {
 	case PP_SCLK:
@@ -983,18 +1036,28 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_SCLK:
 		if (hwmgr->od_enabled) {
-			size = sprintf(buf, "%s:\n", "OD_SCLK");
+			ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
+			if (ret)
+				return ret;
+			ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+			if (ret)
+				return ret;
 
+			size = sprintf(buf, "%s:\n", "OD_SCLK");
 			size += sprintf(buf + size, "0: %10uMhz\n",
-			(data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : data->gfx_min_freq_limit/100);
-			size += sprintf(buf + size, "1: %10uMhz\n", data->gfx_max_freq_limit/100);
+			(data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : min_freq);
+			size += sprintf(buf + size, "1: %10uMhz\n",
+			(data->gfx_actual_soft_max_freq > 0) ? data->gfx_actual_soft_max_freq : max_freq);
 		}
 		break;
 	case OD_RANGE:
 		if (hwmgr->od_enabled) {
-			uint32_t min_freq, max_freq = 0;
-			smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
-			smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+			ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
+			if (ret)
+				return ret;
+			ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+			if (ret)
+				return ret;
 
 			size = sprintf(buf, "%s:\n", "OD_RANGE");
 			size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n",
@@ -1414,23 +1477,96 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr,
 					enum PP_OD_DPM_TABLE_COMMAND type,
 					long *input, uint32_t size)
 {
+	uint32_t min_freq, max_freq = 0;
+	struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
 	if (!hwmgr->od_enabled) {
 		pr_err("Fine grain not support\n");
 		return -EINVAL;
 	}
 
-	if (size != 2) {
-		pr_err("Input parameter number not correct\n");
+	if (!smu10_data->fine_grain_enabled) {
+		pr_err("Fine grain not started\n");
 		return -EINVAL;
 	}
 
 	if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) {
-		if (input[0] == 0)
-			smu10_set_hard_min_gfxclk_by_freq(hwmgr, input[1]);
-		else if (input[0] == 1)
-			smu10_set_soft_max_gfxclk_by_freq(hwmgr, input[1]);
-		else
+		if (size != 2) {
+			pr_err("Input parameter number not correct\n");
 			return -EINVAL;
+		}
+
+		if (input[0] == 0) {
+			smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
+			if (input[1] < min_freq) {
+				pr_err("Fine grain setting minimum sclk (%ld) MHz is less than the minimum allowed (%d) MHz\n",
+					input[1], min_freq);
+				return -EINVAL;
+			}
+			smu10_data->gfx_actual_soft_min_freq = input[1];
+		} else if (input[0] == 1) {
+			smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+			if (input[1] > max_freq) {
+				pr_err("Fine grain setting maximum sclk (%ld) MHz is greater than the maximum allowed (%d) MHz\n",
+					input[1], max_freq);
+				return -EINVAL;
+			}
+			smu10_data->gfx_actual_soft_max_freq = input[1];
+		} else {
+			return -EINVAL;
+		}
+	} else if (type == PP_OD_RESTORE_DEFAULT_TABLE) {
+		if (size != 0) {
+			pr_err("Input parameter number not correct\n");
+			return -EINVAL;
+		}
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
+		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+
+		smu10_data->gfx_actual_soft_min_freq = min_freq;
+		smu10_data->gfx_actual_soft_max_freq = max_freq;
+
+		ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+					PPSMC_MSG_SetHardMinGfxClk,
+					min_freq,
+					NULL);
+		if (ret)
+			return ret;
+
+		ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+					PPSMC_MSG_SetSoftMaxGfxClk,
+					max_freq,
+					NULL);
+		if (ret)
+			return ret;
+	} else if (type == PP_OD_COMMIT_DPM_TABLE) {
+		if (size != 0) {
+			pr_err("Input parameter number not correct\n");
+			return -EINVAL;
+		}
+
+		if (smu10_data->gfx_actual_soft_min_freq > smu10_data->gfx_actual_soft_max_freq) {
+			pr_err("The setting minimun sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
+					smu10_data->gfx_actual_soft_min_freq, smu10_data->gfx_actual_soft_max_freq);
+			return -EINVAL;
+		}
+
+		ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+					PPSMC_MSG_SetHardMinGfxClk,
+					smu10_data->gfx_actual_soft_min_freq,
+					NULL);
+		if (ret)
+			return ret;
+
+		ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+					PPSMC_MSG_SetSoftMaxGfxClk,
+					smu10_data->gfx_actual_soft_max_freq,
+					NULL);
+		if (ret)
+			return ret;
+	} else {
+		return -EINVAL;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h
index 6c9b5f060902..808e0ecbe1f0 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.h
@@ -283,6 +283,7 @@ struct smu10_hwmgr {
 	uint32_t                        vclk_soft_min;
 	uint32_t                        dclk_soft_min;
 	uint32_t                        gfx_actual_soft_min_freq;
+	uint32_t                        gfx_actual_soft_max_freq;
 	uint32_t                        gfx_min_freq_limit;
 	uint32_t                        gfx_max_freq_limit; /* in 10Khz*/
 
@@ -299,6 +300,8 @@ struct smu10_hwmgr {
 	bool need_min_deep_sleep_dcefclk;
 	uint32_t                             deep_sleep_dcefclk;
 	uint32_t                             num_active_display;
+
+	bool							fine_grain_enabled;
 };
 
 struct pp_hwmgr;
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 9608745d732f..12b36eb0ff6a 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
@@ -2372,7 +2372,7 @@ static void sienna_cichlid_fill_i2c_req(SwI2cRequest_t  *req, bool write,
 {
 	int i;
 
-	req->I2CcontrollerPort = 0;
+	req->I2CcontrollerPort = 1;
 	req->I2CSpeed = 2;
 	req->SlaveAddress = address;
 	req->NumCmds = numbytes;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 9bccf2ad038c..5c1482d4ca43 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -252,7 +252,8 @@ static int vangogh_get_smu_metrics_data(struct smu_context *smu,
 		*value = metrics->UvdActivity;
 		break;
 	case METRICS_AVERAGE_SOCKETPOWER:
-		*value = metrics->CurrentSocketPower;
+		*value = (metrics->CurrentSocketPower << 8) /
+		1000 ;
 		break;
 	case METRICS_TEMPERATURE_EDGE:
 		*value = metrics->GfxTemperature / 100 *
@@ -724,8 +725,13 @@ static int vangogh_set_fine_grain_gfx_freq_parameters(struct smu_context *smu)
 
 static int vangogh_system_features_control(struct smu_context *smu, bool en)
 {
-	return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_RlcPowerNotify,
-					en ? RLC_STATUS_NORMAL : RLC_STATUS_OFF, NULL);
+	struct amdgpu_device *adev = smu->adev;
+
+	if (adev->pm.fw_version >= 0x43f1700)
+		return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_RlcPowerNotify,
+						en ? RLC_STATUS_NORMAL : RLC_STATUS_OFF, NULL);
+	else
+		return 0;
 }
 
 static const struct pptable_funcs vangogh_ppt_funcs = {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index dc75db8af371..f743685a20e8 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -188,6 +188,7 @@ static int renoir_get_dpm_clk_limited(struct smu_context *smu, enum smu_clk_type
 			return -EINVAL;
 		*freq = clk_table->SocClocks[dpm_level].Freq;
 		break;
+	case SMU_UCLK:
 	case SMU_MCLK:
 		if (dpm_level >= NUM_FCLK_DPM_LEVELS)
 			return -EINVAL;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
index 522d55004655..06abf2a7ce9e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
@@ -225,6 +225,7 @@ int smu_v12_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_
 	break;
 	case SMU_FCLK:
 	case SMU_MCLK:
+	case SMU_UCLK:
 		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinFclkByFreq, min, NULL);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
index 1f8195bad536..ca891ae14d36 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
@@ -152,7 +152,6 @@ static int komeda_parse_dt(struct device *dev, struct komeda_dev *mdev)
 	ret = of_reserved_mem_device_init(dev);
 	if (ret && ret != -ENODEV)
 		return ret;
-	ret = 0;
 
 	for_each_available_child_of_node(np, child) {
 		if (of_node_name_eq(child, "pipeline")) {
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
index 6b99df696384..034ee08482e0 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
@@ -81,10 +81,10 @@ static void komeda_kms_commit_tail(struct drm_atomic_state *old_state)
 
 	drm_atomic_helper_commit_modeset_enables(dev, old_state);
 
-	drm_atomic_helper_wait_for_flip_done(dev, old_state);
-
 	drm_atomic_helper_commit_hw_done(old_state);
 
+	drm_atomic_helper_wait_for_flip_done(dev, old_state);
+
 	drm_atomic_helper_cleanup_planes(dev, old_state);
 }
 
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.c
index 452e505a1fd3..719a79728e24 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.c
@@ -137,9 +137,10 @@ komeda_pipeline_get_first_component(struct komeda_pipeline *pipe,
 				    u32 comp_mask)
 {
 	struct komeda_component *c = NULL;
+	unsigned long comp_mask_local = (unsigned long)comp_mask;
 	int id;
 
-	id = find_first_bit((unsigned long *)&comp_mask, 32);
+	id = find_first_bit(&comp_mask_local, 32);
 	if (id < 32)
 		c = komeda_pipeline_get_component(pipe, id);
 
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
index 8f32ae7c25d0..5c085116de3f 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
@@ -704,10 +704,10 @@ komeda_compiz_set_input(struct komeda_compiz *compiz,
 	cin->layer_alpha = dflow->layer_alpha;
 
 	old_st = komeda_component_get_old_state(&compiz->base, drm_st);
-	WARN_ON(!old_st);
 
 	/* compare with old to check if this input has been changed */
-	if (memcmp(&(to_compiz_st(old_st)->cins[idx]), cin, sizeof(*cin)))
+	if (WARN_ON(!old_st) ||
+	    memcmp(&(to_compiz_st(old_st)->cins[idx]), cin, sizeof(*cin)))
 		c_st->changed_active_inputs |= BIT(idx);
 
 	komeda_component_add_input(c_st, &dflow->input, idx);
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index e6231947f987..a0cb746bcb0a 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -1163,7 +1163,14 @@ retry:
 	if (ret)
 		goto out;
 
-	if (old_fb->format != fb->format) {
+	/*
+	 * Only check the FOURCC format code, excluding modifiers. This is
+	 * enough for all legacy drivers. Atomic drivers have their own
+	 * checks in their ->atomic_check implementation, which will
+	 * return -EINVAL if any hw or driver constraint is violated due
+	 * to modifier changes.
+	 */
+	if (old_fb->format->format != fb->format->format) {
 		DRM_DEBUG_KMS("Page flip is not allowed to change frame buffer format.\n");
 		ret = -EINVAL;
 		goto out;
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index e5574e506a5c..6d9e81ea67f4 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -38,6 +38,7 @@ i915-y += i915_drv.o \
 	  i915_config.o \
 	  i915_irq.o \
 	  i915_getparam.o \
+	  i915_mitigations.o \
 	  i915_params.o \
 	  i915_pci.o \
 	  i915_scatterlist.o \
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index a9439b415603..b3533a32f8ba 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1616,10 +1616,6 @@ static void gen11_dsi_get_power_domains(struct intel_encoder *encoder,
 
 	get_dsi_io_power_domains(i915,
 				 enc_to_intel_dsi(encoder));
-
-	if (crtc_state->dsc.compression_enable)
-		intel_display_power_get(i915,
-					intel_dsc_power_domain(crtc_state));
 }
 
 static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index ce82d654d0f2..34d78c654df3 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1436,6 +1436,9 @@ struct intel_dp {
 		bool ycbcr_444_to_420;
 	} dfp;
 
+	/* To control wakeup latency, e.g. for irq-driven dp aux transfers. */
+	struct pm_qos_request pm_qos;
+
 	/* Display stream compression testing */
 	bool force_dsc_en;
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 2165398d2c7c..37f1a10fd021 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1489,7 +1489,7 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 	 * lowest possible wakeup latency and so prevent the cpu from going into
 	 * deep sleep states.
 	 */
-	cpu_latency_qos_update_request(&i915->pm_qos, 0);
+	cpu_latency_qos_update_request(&intel_dp->pm_qos, 0);
 
 	intel_dp_check_edp(intel_dp);
 
@@ -1622,7 +1622,7 @@ done:
 
 	ret = recv_bytes;
 out:
-	cpu_latency_qos_update_request(&i915->pm_qos, PM_QOS_DEFAULT_VALUE);
+	cpu_latency_qos_update_request(&intel_dp->pm_qos, PM_QOS_DEFAULT_VALUE);
 
 	if (vdd)
 		edp_panel_vdd_off(intel_dp, false);
@@ -1898,6 +1898,9 @@ static i915_reg_t tgl_aux_data_reg(struct intel_dp *intel_dp, int index)
 static void
 intel_dp_aux_fini(struct intel_dp *intel_dp)
 {
+	if (cpu_latency_qos_request_active(&intel_dp->pm_qos))
+		cpu_latency_qos_remove_request(&intel_dp->pm_qos);
+
 	kfree(intel_dp->aux.name);
 }
 
@@ -1950,6 +1953,7 @@ intel_dp_aux_init(struct intel_dp *intel_dp)
 					       encoder->base.name);
 
 	intel_dp->aux.transfer = intel_dp_aux_transfer;
+	cpu_latency_qos_add_request(&intel_dp->pm_qos, PM_QOS_DEFAULT_VALUE);
 }
 
 bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp)
diff --git a/drivers/gpu/drm/i915/display/intel_lpe_audio.c b/drivers/gpu/drm/i915/display/intel_lpe_audio.c
index ad5cc13037ae..1c939f9c9bc9 100644
--- a/drivers/gpu/drm/i915/display/intel_lpe_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_lpe_audio.c
@@ -297,13 +297,9 @@ int intel_lpe_audio_init(struct drm_i915_private *dev_priv)
  */
 void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv)
 {
-	struct irq_desc *desc;
-
 	if (!HAS_LPE_AUDIO(dev_priv))
 		return;
 
-	desc = irq_to_desc(dev_priv->lpe_audio.irq);
-
 	lpe_audio_platdev_destroy(dev_priv);
 
 	irq_free_desc(dev_priv->lpe_audio.irq);
diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c
index 9f23bac0d792..d64fce1a17cb 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.c
+++ b/drivers/gpu/drm/i915/display/intel_panel.c
@@ -1650,16 +1650,13 @@ static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unus
 		val = pch_get_backlight(connector);
 	else
 		val = lpt_get_backlight(connector);
-	val = intel_panel_compute_brightness(connector, val);
-	panel->backlight.level = clamp(val, panel->backlight.min,
-				       panel->backlight.max);
 
 	if (cpu_mode) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "CPU backlight register was enabled, switching to PCH override\n");
 
 		/* Write converted CPU PWM value to PCH override register */
-		lpt_set_backlight(connector->base.state, panel->backlight.level);
+		lpt_set_backlight(connector->base.state, val);
 		intel_de_write(dev_priv, BLC_PWM_PCH_CTL1,
 			       pch_ctl1 | BLM_PCH_OVERRIDE_ENABLE);
 
@@ -1667,6 +1664,10 @@ static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unus
 			       cpu_ctl2 & ~BLM_PWM_ENABLE);
 	}
 
+	val = intel_panel_compute_brightness(connector, val);
+	panel->backlight.level = clamp(val, panel->backlight.min,
+				       panel->backlight.max);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index d52f9c177908..f94025ec603a 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -812,10 +812,20 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state,
 		intel_dsi_prepare(encoder, pipe_config);
 
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON);
-	intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
 
-	/* Deassert reset */
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
+	/*
+	 * Give the panel time to power-on and then deassert its reset.
+	 * Depending on the VBT MIPI sequences version the deassert-seq
+	 * may contain the necessary delay, intel_dsi_msleep() will skip
+	 * the delay in that case. If there is no deassert-seq, then an
+	 * unconditional msleep is used to give the panel time to power-on.
+	 */
+	if (dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]) {
+		intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
+		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
+	} else {
+		msleep(intel_dsi->panel_on_delay);
+	}
 
 	if (IS_GEMINILAKE(dev_priv)) {
 		glk_cold_boot = glk_dsi_enable_io(encoder);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index bcc80f428172..bd3046e5a934 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1046,7 +1046,7 @@ static void reloc_gpu_flush(struct i915_execbuffer *eb, struct reloc_cache *cach
 	GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
 	cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END;
 
-	__i915_gem_object_flush_map(obj, 0, sizeof(u32) * (cache->rq_size + 1));
+	i915_gem_object_flush_map(obj);
 	i915_gem_object_unpin_map(obj);
 
 	intel_gt_chipset_flush(cache->rq->engine->gt);
@@ -1296,6 +1296,8 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 		goto err_pool;
 	}
 
+	memset32(cmd, 0, pool->obj->base.size / sizeof(u32));
+
 	batch = i915_vma_instance(pool->obj, vma->vm, NULL);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
diff --git a/drivers/gpu/drm/i915/gt/gen7_renderclear.c b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
index d93d85cd3027..94465374ca2f 100644
--- a/drivers/gpu/drm/i915/gt/gen7_renderclear.c
+++ b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
@@ -7,8 +7,6 @@
 #include "i915_drv.h"
 #include "intel_gpu_commands.h"
 
-#define MAX_URB_ENTRIES 64
-#define STATE_SIZE (4 * 1024)
 #define GT3_INLINE_DATA_DELAYS 0x1E00
 #define batch_advance(Y, CS) GEM_BUG_ON((Y)->end != (CS))
 
@@ -34,38 +32,59 @@ struct batch_chunk {
 };
 
 struct batch_vals {
-	u32 max_primitives;
-	u32 max_urb_entries;
-	u32 cmd_size;
-	u32 state_size;
+	u32 max_threads;
 	u32 state_start;
-	u32 batch_size;
+	u32 surface_start;
 	u32 surface_height;
 	u32 surface_width;
-	u32 scratch_size;
-	u32 max_size;
+	u32 size;
 };
 
+static inline int num_primitives(const struct batch_vals *bv)
+{
+	/*
+	 * We need to saturate the GPU with work in order to dispatch
+	 * a shader on every HW thread, and clear the thread-local registers.
+	 * In short, we have to dispatch work faster than the shaders can
+	 * run in order to fill the EU and occupy each HW thread.
+	 */
+	return bv->max_threads;
+}
+
 static void
 batch_get_defaults(struct drm_i915_private *i915, struct batch_vals *bv)
 {
 	if (IS_HASWELL(i915)) {
-		bv->max_primitives = 280;
-		bv->max_urb_entries = MAX_URB_ENTRIES;
+		switch (INTEL_INFO(i915)->gt) {
+		default:
+		case 1:
+			bv->max_threads = 70;
+			break;
+		case 2:
+			bv->max_threads = 140;
+			break;
+		case 3:
+			bv->max_threads = 280;
+			break;
+		}
 		bv->surface_height = 16 * 16;
 		bv->surface_width = 32 * 2 * 16;
 	} else {
-		bv->max_primitives = 128;
-		bv->max_urb_entries = MAX_URB_ENTRIES / 2;
+		switch (INTEL_INFO(i915)->gt) {
+		default:
+		case 1: /* including vlv */
+			bv->max_threads = 36;
+			break;
+		case 2:
+			bv->max_threads = 128;
+			break;
+		}
 		bv->surface_height = 16 * 8;
 		bv->surface_width = 32 * 16;
 	}
-	bv->cmd_size = bv->max_primitives * 4096;
-	bv->state_size = STATE_SIZE;
-	bv->state_start = bv->cmd_size;
-	bv->batch_size = bv->cmd_size + bv->state_size;
-	bv->scratch_size = bv->surface_height * bv->surface_width;
-	bv->max_size = bv->batch_size + bv->scratch_size;
+	bv->state_start = round_up(SZ_1K + num_primitives(bv) * 64, SZ_4K);
+	bv->surface_start = bv->state_start + SZ_4K;
+	bv->size = bv->surface_start + bv->surface_height * bv->surface_width;
 }
 
 static void batch_init(struct batch_chunk *bc,
@@ -155,7 +174,8 @@ static u32
 gen7_fill_binding_table(struct batch_chunk *state,
 			const struct batch_vals *bv)
 {
-	u32 surface_start = gen7_fill_surface_state(state, bv->batch_size, bv);
+	u32 surface_start =
+		gen7_fill_surface_state(state, bv->surface_start, bv);
 	u32 *cs = batch_alloc_items(state, 32, 8);
 	u32 offset = batch_offset(state, cs);
 
@@ -214,9 +234,9 @@ static void
 gen7_emit_state_base_address(struct batch_chunk *batch,
 			     u32 surface_state_base)
 {
-	u32 *cs = batch_alloc_items(batch, 0, 12);
+	u32 *cs = batch_alloc_items(batch, 0, 10);
 
-	*cs++ = STATE_BASE_ADDRESS | (12 - 2);
+	*cs++ = STATE_BASE_ADDRESS | (10 - 2);
 	/* general */
 	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
 	/* surface */
@@ -233,8 +253,6 @@ gen7_emit_state_base_address(struct batch_chunk *batch,
 	*cs++ = BASE_ADDRESS_MODIFY;
 	*cs++ = 0;
 	*cs++ = BASE_ADDRESS_MODIFY;
-	*cs++ = 0;
-	*cs++ = 0;
 	batch_advance(batch, cs);
 }
 
@@ -244,8 +262,7 @@ gen7_emit_vfe_state(struct batch_chunk *batch,
 		    u32 urb_size, u32 curbe_size,
 		    u32 mode)
 {
-	u32 urb_entries = bv->max_urb_entries;
-	u32 threads = bv->max_primitives - 1;
+	u32 threads = bv->max_threads - 1;
 	u32 *cs = batch_alloc_items(batch, 32, 8);
 
 	*cs++ = MEDIA_VFE_STATE | (8 - 2);
@@ -254,7 +271,7 @@ gen7_emit_vfe_state(struct batch_chunk *batch,
 	*cs++ = 0;
 
 	/* number of threads & urb entries for GPGPU vs Media Mode */
-	*cs++ = threads << 16 | urb_entries << 8 | mode << 2;
+	*cs++ = threads << 16 | 1 << 8 | mode << 2;
 
 	*cs++ = 0;
 
@@ -293,17 +310,12 @@ gen7_emit_media_object(struct batch_chunk *batch,
 {
 	unsigned int x_offset = (media_object_index % 16) * 64;
 	unsigned int y_offset = (media_object_index / 16) * 16;
-	unsigned int inline_data_size;
-	unsigned int media_batch_size;
-	unsigned int i;
+	unsigned int pkt = 6 + 3;
 	u32 *cs;
 
-	inline_data_size = 112 * 8;
-	media_batch_size = inline_data_size + 6;
-
-	cs = batch_alloc_items(batch, 8, media_batch_size);
+	cs = batch_alloc_items(batch, 8, pkt);
 
-	*cs++ = MEDIA_OBJECT | (media_batch_size - 2);
+	*cs++ = MEDIA_OBJECT | (pkt - 2);
 
 	/* interface descriptor offset */
 	*cs++ = 0;
@@ -317,25 +329,44 @@ gen7_emit_media_object(struct batch_chunk *batch,
 	*cs++ = 0;
 
 	/* inline */
-	*cs++ = (y_offset << 16) | (x_offset);
+	*cs++ = y_offset << 16 | x_offset;
 	*cs++ = 0;
 	*cs++ = GT3_INLINE_DATA_DELAYS;
-	for (i = 3; i < inline_data_size; i++)
-		*cs++ = 0;
 
 	batch_advance(batch, cs);
 }
 
 static void gen7_emit_pipeline_flush(struct batch_chunk *batch)
 {
-	u32 *cs = batch_alloc_items(batch, 0, 5);
+	u32 *cs = batch_alloc_items(batch, 0, 4);
 
-	*cs++ = GFX_OP_PIPE_CONTROL(5);
-	*cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE |
-		PIPE_CONTROL_GLOBAL_GTT_IVB;
+	*cs++ = GFX_OP_PIPE_CONTROL(4);
+	*cs++ = PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+		PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+		PIPE_CONTROL_DC_FLUSH_ENABLE |
+		PIPE_CONTROL_CS_STALL;
 	*cs++ = 0;
 	*cs++ = 0;
+
+	batch_advance(batch, cs);
+}
+
+static void gen7_emit_pipeline_invalidate(struct batch_chunk *batch)
+{
+	u32 *cs = batch_alloc_items(batch, 0, 8);
+
+	/* ivb: Stall before STATE_CACHE_INVALIDATE */
+	*cs++ = GFX_OP_PIPE_CONTROL(4);
+	*cs++ = PIPE_CONTROL_STALL_AT_SCOREBOARD |
+		PIPE_CONTROL_CS_STALL;
+	*cs++ = 0;
+	*cs++ = 0;
+
+	*cs++ = GFX_OP_PIPE_CONTROL(4);
+	*cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 	*cs++ = 0;
+	*cs++ = 0;
+
 	batch_advance(batch, cs);
 }
 
@@ -344,34 +375,34 @@ static void emit_batch(struct i915_vma * const vma,
 		       const struct batch_vals *bv)
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
-	unsigned int desc_count = 64;
-	const u32 urb_size = 112;
+	const unsigned int desc_count = 1;
+	const unsigned int urb_size = 1;
 	struct batch_chunk cmds, state;
-	u32 interface_descriptor;
+	u32 descriptors;
 	unsigned int i;
 
-	batch_init(&cmds, vma, start, 0, bv->cmd_size);
-	batch_init(&state, vma, start, bv->state_start, bv->state_size);
+	batch_init(&cmds, vma, start, 0, bv->state_start);
+	batch_init(&state, vma, start, bv->state_start, SZ_4K);
 
-	interface_descriptor =
-		gen7_fill_interface_descriptor(&state, bv,
-					       IS_HASWELL(i915) ?
-					       &cb_kernel_hsw :
-					       &cb_kernel_ivb,
-					       desc_count);
-	gen7_emit_pipeline_flush(&cmds);
+	descriptors = gen7_fill_interface_descriptor(&state, bv,
+						     IS_HASWELL(i915) ?
+						     &cb_kernel_hsw :
+						     &cb_kernel_ivb,
+						     desc_count);
+
+	gen7_emit_pipeline_invalidate(&cmds);
 	batch_add(&cmds, PIPELINE_SELECT | PIPELINE_SELECT_MEDIA);
 	batch_add(&cmds, MI_NOOP);
-	gen7_emit_state_base_address(&cmds, interface_descriptor);
+	gen7_emit_pipeline_invalidate(&cmds);
+
 	gen7_emit_pipeline_flush(&cmds);
+	gen7_emit_state_base_address(&cmds, descriptors);
+	gen7_emit_pipeline_invalidate(&cmds);
 
 	gen7_emit_vfe_state(&cmds, bv, urb_size - 1, 0, 0);
+	gen7_emit_interface_descriptor_load(&cmds, descriptors, desc_count);
 
-	gen7_emit_interface_descriptor_load(&cmds,
-					    interface_descriptor,
-					    desc_count);
-
-	for (i = 0; i < bv->max_primitives; i++)
+	for (i = 0; i < num_primitives(bv); i++)
 		gen7_emit_media_object(&cmds, i);
 
 	batch_add(&cmds, MI_BATCH_BUFFER_END);
@@ -385,15 +416,15 @@ int gen7_setup_clear_gpr_bb(struct intel_engine_cs * const engine,
 
 	batch_get_defaults(engine->i915, &bv);
 	if (!vma)
-		return bv.max_size;
+		return bv.size;
 
-	GEM_BUG_ON(vma->obj->base.size < bv.max_size);
+	GEM_BUG_ON(vma->obj->base.size < bv.size);
 
 	batch = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
 	if (IS_ERR(batch))
 		return PTR_ERR(batch);
 
-	emit_batch(vma, memset(batch, 0, bv.max_size), &bv);
+	emit_batch(vma, memset(batch, 0, bv.size), &bv);
 
 	i915_gem_object_flush_map(vma->obj);
 	__i915_gem_object_release_map(vma->obj);
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index a41b43f445b8..ecf3a6118a6d 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -32,6 +32,7 @@
 #include "gen6_ppgtt.h"
 #include "gen7_renderclear.h"
 #include "i915_drv.h"
+#include "i915_mitigations.h"
 #include "intel_breadcrumbs.h"
 #include "intel_context.h"
 #include "intel_gt.h"
@@ -886,7 +887,8 @@ static int switch_context(struct i915_request *rq)
 	GEM_BUG_ON(HAS_EXECLISTS(engine->i915));
 
 	if (engine->wa_ctx.vma && ce != engine->kernel_context) {
-		if (engine->wa_ctx.vma->private != ce) {
+		if (engine->wa_ctx.vma->private != ce &&
+		    i915_mitigate_clear_residuals()) {
 			ret = clear_residuals(rq);
 			if (ret)
 				return ret;
@@ -1290,7 +1292,7 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine)
 
 	GEM_BUG_ON(timeline->hwsp_ggtt != engine->status_page.vma);
 
-	if (IS_HASWELL(engine->i915) && engine->class == RENDER_CLASS) {
+	if (IS_GEN(engine->i915, 7) && engine->class == RENDER_CLASS) {
 		err = gen7_ctx_switch_bb_init(engine);
 		if (err)
 			goto err_ring_unpin;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 180c23e2e25e..602f1a0bc587 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -53,6 +53,7 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
 	fw_def(ELKHARTLAKE, 0, guc_def(ehl, 49, 0, 1), huc_def(ehl,  9, 0, 0)) \
 	fw_def(ICELAKE,     0, guc_def(icl, 49, 0, 1), huc_def(icl,  9, 0, 0)) \
 	fw_def(COMETLAKE,   5, guc_def(cml, 49, 0, 1), huc_def(cml,  4, 0, 0)) \
+	fw_def(COMETLAKE,   0, guc_def(kbl, 49, 0, 1), huc_def(kbl,  4, 0, 0)) \
 	fw_def(COFFEELAKE,  0, guc_def(kbl, 49, 0, 1), huc_def(kbl,  4, 0, 0)) \
 	fw_def(GEMINILAKE,  0, guc_def(glk, 49, 0, 1), huc_def(glk,  4, 0, 0)) \
 	fw_def(KABYLAKE,    0, guc_def(kbl, 49, 0, 1), huc_def(kbl,  4, 0, 0)) \
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index a15f87539657..62a5b0dd2003 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -217,6 +217,15 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 				  DDI_BUF_CTL_ENABLE);
 			vgpu_vreg_t(vgpu, DDI_BUF_CTL(port)) |= DDI_BUF_IS_IDLE;
 		}
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+			~(PORTA_HOTPLUG_ENABLE | PORTA_HOTPLUG_STATUS_MASK);
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+			~(PORTB_HOTPLUG_ENABLE | PORTB_HOTPLUG_STATUS_MASK);
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+			~(PORTC_HOTPLUG_ENABLE | PORTC_HOTPLUG_STATUS_MASK);
+		/* No hpd_invert set in vgpu vbt, need to clear invert mask */
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= ~BXT_DDI_HPD_INVERT_MASK;
+		vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= ~BXT_DE_PORT_HOTPLUG_MASK;
 
 		vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) &= ~(BIT(0) | BIT(1));
 		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) &=
@@ -273,6 +282,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)) |=
 				(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
 				 TRANS_DDI_FUNC_ENABLE);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTA_HOTPLUG_ENABLE;
 			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 				GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
 		}
@@ -301,6 +312,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 				(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
 				 (PORT_B << TRANS_DDI_PORT_SHIFT) |
 				 TRANS_DDI_FUNC_ENABLE);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTB_HOTPLUG_ENABLE;
 			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 				GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
 		}
@@ -329,6 +342,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 				(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
 				 (PORT_B << TRANS_DDI_PORT_SHIFT) |
 				 TRANS_DDI_FUNC_ENABLE);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTC_HOTPLUG_ENABLE;
 			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 				GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
 		}
@@ -661,44 +676,62 @@ void intel_vgpu_emulate_hotplug(struct intel_vgpu *vgpu, bool connected)
 				PORTD_HOTPLUG_STATUS_MASK;
 		intel_vgpu_trigger_virtual_event(vgpu, DP_D_HOTPLUG);
 	} else if (IS_BROXTON(i915)) {
-		if (connected) {
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+			if (connected) {
 				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 					GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
+			} else {
+				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
+					~GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
 			}
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
-				vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
-					SFUSE_STRAP_DDIB_DETECTED;
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+				GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+				~PORTA_HOTPLUG_STATUS_MASK;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTA_HOTPLUG_LONG_DETECT;
+			intel_vgpu_trigger_virtual_event(vgpu, DP_A_HOTPLUG);
+		}
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+			if (connected) {
 				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 					GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
-			}
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
 				vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
-					SFUSE_STRAP_DDIC_DETECTED;
-				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
-					GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
-			}
-		} else {
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+					SFUSE_STRAP_DDIB_DETECTED;
+			} else {
 				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
-					~GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
-			}
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+					~GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
 				vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
 					~SFUSE_STRAP_DDIB_DETECTED;
-				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
-					~GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
 			}
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
-				vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
-					~SFUSE_STRAP_DDIC_DETECTED;
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+				GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+				~PORTB_HOTPLUG_STATUS_MASK;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTB_HOTPLUG_LONG_DETECT;
+			intel_vgpu_trigger_virtual_event(vgpu, DP_B_HOTPLUG);
+		}
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+			if (connected) {
+				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+					GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+				vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
+					SFUSE_STRAP_DDIC_DETECTED;
+			} else {
 				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
 					~GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+				vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
+					~SFUSE_STRAP_DDIC_DETECTED;
 			}
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+				GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+				~PORTC_HOTPLUG_STATUS_MASK;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTC_HOTPLUG_LONG_DETECT;
+			intel_vgpu_trigger_virtual_event(vgpu, DP_C_HOTPLUG);
 		}
-		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
-			PORTB_HOTPLUG_STATUS_MASK;
-		intel_vgpu_trigger_virtual_event(vgpu, DP_B_HOTPLUG);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index e49944fde333..cbe5931906e0 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -437,10 +437,9 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	if (ret)
 		goto out_clean_sched_policy;
 
-	if (IS_BROADWELL(dev_priv))
+	if (IS_BROADWELL(dev_priv) || IS_BROXTON(dev_priv))
 		ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B);
-	/* FixMe: Re-enable APL/BXT once vfio_edid enabled */
-	else if (!IS_BROXTON(dev_priv))
+	else
 		ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D);
 	if (ret)
 		goto out_clean_sched_policy;
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 93265951fdbb..b0899b665e85 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1166,7 +1166,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 		}
 	}
 	if (IS_ERR(src)) {
-		unsigned long x, n;
+		unsigned long x, n, remain;
 		void *ptr;
 
 		/*
@@ -1177,14 +1177,15 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 		 * We don't care about copying too much here as we only
 		 * validate up to the end of the batch.
 		 */
+		remain = length;
 		if (!(dst_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
-			length = round_up(length,
+			remain = round_up(remain,
 					  boot_cpu_data.x86_clflush_size);
 
 		ptr = dst;
 		x = offset_in_page(offset);
-		for (n = offset >> PAGE_SHIFT; length; n++) {
-			int len = min(length, PAGE_SIZE - x);
+		for (n = offset >> PAGE_SHIFT; remain; n++) {
+			int len = min(remain, PAGE_SIZE - x);
 
 			src = kmap_atomic(i915_gem_object_get_page(src_obj, n));
 			if (needs_clflush)
@@ -1193,13 +1194,15 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 			kunmap_atomic(src);
 
 			ptr += len;
-			length -= len;
+			remain -= len;
 			x = 0;
 		}
 	}
 
 	i915_gem_object_unpin_pages(src_obj);
 
+	memset32(dst + length, 0, (dst_obj->base.size - length) / sizeof(u32));
+
 	/* dst_obj is returned with vmap pinned */
 	return dst;
 }
@@ -1392,11 +1395,6 @@ static unsigned long *alloc_whitelist(u32 batch_length)
 
 #define LENGTH_BIAS 2
 
-static bool shadow_needs_clflush(struct drm_i915_gem_object *obj)
-{
-	return !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE);
-}
-
 /**
  * intel_engine_cmd_parser() - parse a batch buffer for privilege violations
  * @engine: the engine on which the batch is to execute
@@ -1538,16 +1536,9 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 				ret = 0; /* allow execution */
 			}
 		}
-
-		if (shadow_needs_clflush(shadow->obj))
-			drm_clflush_virt_range(batch_end, 8);
 	}
 
-	if (shadow_needs_clflush(shadow->obj)) {
-		void *ptr = page_mask_bits(shadow->obj->mm.mapping);
-
-		drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr);
-	}
+	i915_gem_object_flush_map(shadow->obj);
 
 	if (!IS_ERR_OR_NULL(jump_whitelist))
 		kfree(jump_whitelist);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 320856b665a1..99eb0d7bbc44 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -578,8 +578,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 
 	pci_set_master(pdev);
 
-	cpu_latency_qos_add_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE);
-
 	intel_gt_init_workarounds(dev_priv);
 
 	/* On the 945G/GM, the chipset reports the MSI capability on the
@@ -626,7 +624,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 err_msi:
 	if (pdev->msi_enabled)
 		pci_disable_msi(pdev);
-	cpu_latency_qos_remove_request(&dev_priv->pm_qos);
 err_mem_regions:
 	intel_memory_regions_driver_release(dev_priv);
 err_ggtt:
@@ -648,8 +645,6 @@ static void i915_driver_hw_remove(struct drm_i915_private *dev_priv)
 
 	if (pdev->msi_enabled)
 		pci_disable_msi(pdev);
-
-	cpu_latency_qos_remove_request(&dev_priv->pm_qos);
 }
 
 /**
@@ -1052,6 +1047,8 @@ static void intel_shutdown_encoders(struct drm_i915_private *dev_priv)
 
 void i915_driver_shutdown(struct drm_i915_private *i915)
 {
+	disable_rpm_wakeref_asserts(&i915->runtime_pm);
+
 	i915_gem_suspend(i915);
 
 	drm_kms_helper_poll_disable(&i915->drm);
@@ -1065,6 +1062,8 @@ void i915_driver_shutdown(struct drm_i915_private *i915)
 
 	intel_suspend_encoders(i915);
 	intel_shutdown_encoders(i915);
+
+	enable_rpm_wakeref_asserts(&i915->runtime_pm);
 }
 
 static bool suspend_to_idle(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0a3ee4f9dc0a..632c713227dc 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -891,9 +891,6 @@ struct drm_i915_private {
 
 	bool display_irqs_enabled;
 
-	/* To control wakeup latency, e.g. for irq-driven dp aux transfers. */
-	struct pm_qos_request pm_qos;
-
 	/* Sideband mailbox protection */
 	struct mutex sb_lock;
 	struct pm_qos_request sb_qos;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index c80eeac53952..6cdb052e3850 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -60,6 +60,24 @@
  * and related files, but that will be described in separate chapters.
  */
 
+/*
+ * Interrupt statistic for PMU. Increments the counter only if the
+ * interrupt originated from the the GPU so interrupts from a device which
+ * shares the interrupt line are not accounted.
+ */
+static inline void pmu_irq_stats(struct drm_i915_private *i915,
+				 irqreturn_t res)
+{
+	if (unlikely(res != IRQ_HANDLED))
+		return;
+
+	/*
+	 * A clever compiler translates that into INC. A not so clever one
+	 * should at least prevent store tearing.
+	 */
+	WRITE_ONCE(i915->pmu.irq_count, i915->pmu.irq_count + 1);
+}
+
 typedef bool (*long_pulse_detect_func)(enum hpd_pin pin, u32 val);
 typedef u32 (*hotplug_enables_func)(struct drm_i915_private *i915,
 				    enum hpd_pin pin);
@@ -1668,6 +1686,8 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 		valleyview_pipestat_irq_handler(dev_priv, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -1745,6 +1765,8 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 		valleyview_pipestat_irq_handler(dev_priv, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -2155,6 +2177,8 @@ static irqreturn_t ilk_irq_handler(int irq, void *arg)
 	if (sde_ier)
 		raw_reg_write(regs, SDEIER, sde_ier);
 
+	pmu_irq_stats(i915, ret);
+
 	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
 	enable_rpm_wakeref_asserts(&i915->runtime_pm);
 
@@ -2541,6 +2565,8 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 
 	gen8_master_intr_enable(regs);
 
+	pmu_irq_stats(dev_priv, IRQ_HANDLED);
+
 	return IRQ_HANDLED;
 }
 
@@ -2636,6 +2662,8 @@ __gen11_irq_handler(struct drm_i915_private * const i915,
 
 	gen11_gu_misc_irq_handler(gt, gu_misc_iir);
 
+	pmu_irq_stats(i915, IRQ_HANDLED);
+
 	return IRQ_HANDLED;
 }
 
@@ -3934,6 +3962,8 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		i8xx_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -4043,6 +4073,8 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		i915_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -4189,6 +4221,8 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		i965_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, IRQ_HANDLED);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/i915_mitigations.c b/drivers/gpu/drm/i915/i915_mitigations.c
new file mode 100644
index 000000000000..84f12598d145
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_mitigations.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include "i915_drv.h"
+#include "i915_mitigations.h"
+
+static unsigned long mitigations __read_mostly = ~0UL;
+
+enum {
+	CLEAR_RESIDUALS = 0,
+};
+
+static const char * const names[] = {
+	[CLEAR_RESIDUALS] = "residuals",
+};
+
+bool i915_mitigate_clear_residuals(void)
+{
+	return READ_ONCE(mitigations) & BIT(CLEAR_RESIDUALS);
+}
+
+static int mitigations_set(const char *val, const struct kernel_param *kp)
+{
+	unsigned long new = ~0UL;
+	char *str, *sep, *tok;
+	bool first = true;
+	int err = 0;
+
+	BUILD_BUG_ON(ARRAY_SIZE(names) >= BITS_PER_TYPE(mitigations));
+
+	str = kstrdup(val, GFP_KERNEL);
+	if (!str)
+		return -ENOMEM;
+
+	for (sep = str; (tok = strsep(&sep, ","));) {
+		bool enable = true;
+		int i;
+
+		/* Be tolerant of leading/trailing whitespace */
+		tok = strim(tok);
+
+		if (first) {
+			first = false;
+
+			if (!strcmp(tok, "auto"))
+				continue;
+
+			new = 0;
+			if (!strcmp(tok, "off"))
+				continue;
+		}
+
+		if (*tok == '!') {
+			enable = !enable;
+			tok++;
+		}
+
+		if (!strncmp(tok, "no", 2)) {
+			enable = !enable;
+			tok += 2;
+		}
+
+		if (*tok == '\0')
+			continue;
+
+		for (i = 0; i < ARRAY_SIZE(names); i++) {
+			if (!strcmp(tok, names[i])) {
+				if (enable)
+					new |= BIT(i);
+				else
+					new &= ~BIT(i);
+				break;
+			}
+		}
+		if (i == ARRAY_SIZE(names)) {
+			pr_err("Bad \"%s.mitigations=%s\", '%s' is unknown\n",
+			       DRIVER_NAME, val, tok);
+			err = -EINVAL;
+			break;
+		}
+	}
+	kfree(str);
+	if (err)
+		return err;
+
+	WRITE_ONCE(mitigations, new);
+	return 0;
+}
+
+static int mitigations_get(char *buffer, const struct kernel_param *kp)
+{
+	unsigned long local = READ_ONCE(mitigations);
+	int count, i;
+	bool enable;
+
+	if (!local)
+		return scnprintf(buffer, PAGE_SIZE, "%s\n", "off");
+
+	if (local & BIT(BITS_PER_LONG - 1)) {
+		count = scnprintf(buffer, PAGE_SIZE, "%s,", "auto");
+		enable = false;
+	} else {
+		enable = true;
+		count = 0;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(names); i++) {
+		if ((local & BIT(i)) != enable)
+			continue;
+
+		count += scnprintf(buffer + count, PAGE_SIZE - count,
+				   "%s%s,", enable ? "" : "!", names[i]);
+	}
+
+	buffer[count - 1] = '\n';
+	return count;
+}
+
+static const struct kernel_param_ops ops = {
+	.set = mitigations_set,
+	.get = mitigations_get,
+};
+
+module_param_cb_unsafe(mitigations, &ops, NULL, 0600);
+MODULE_PARM_DESC(mitigations,
+"Selectively enable security mitigations for all Intel® GPUs in the system.\n"
+"\n"
+"  auto -- enables all mitigations required for the platform [default]\n"
+"  off  -- disables all mitigations\n"
+"\n"
+"Individual mitigations can be enabled by passing a comma-separated string,\n"
+"e.g. mitigations=residuals to enable only clearing residuals or\n"
+"mitigations=auto,noresiduals to disable only the clear residual mitigation.\n"
+"Either '!' or 'no' may be used to switch from enabling the mitigation to\n"
+"disabling it.\n"
+"\n"
+"Active mitigations for Ivybridge, Baytrail, Haswell:\n"
+"  residuals -- clear all thread-local registers between contexts"
+);
diff --git a/drivers/gpu/drm/i915/i915_mitigations.h b/drivers/gpu/drm/i915/i915_mitigations.h
new file mode 100644
index 000000000000..1359d8135287
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_mitigations.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __I915_MITIGATIONS_H__
+#define __I915_MITIGATIONS_H__
+
+#include <linux/types.h>
+
+bool i915_mitigate_clear_residuals(void);
+
+#endif /* __I915_MITIGATIONS_H__ */
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index cd786ad12be7..d76685ce0399 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -4,7 +4,6 @@
  * Copyright © 2017-2018 Intel Corporation
  */
 
-#include <linux/irq.h>
 #include <linux/pm_runtime.h>
 
 #include "gt/intel_engine.h"
@@ -424,22 +423,6 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
-static u64 count_interrupts(struct drm_i915_private *i915)
-{
-	/* open-coded kstat_irqs() */
-	struct irq_desc *desc = irq_to_desc(i915->drm.pdev->irq);
-	u64 sum = 0;
-	int cpu;
-
-	if (!desc || !desc->kstat_irqs)
-		return 0;
-
-	for_each_possible_cpu(cpu)
-		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
-
-	return sum;
-}
-
 static void i915_pmu_event_destroy(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -590,7 +573,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 				   USEC_PER_SEC /* to MHz */);
 			break;
 		case I915_PMU_INTERRUPTS:
-			val = count_interrupts(i915);
+			val = READ_ONCE(pmu->irq_count);
 			break;
 		case I915_PMU_RC6_RESIDENCY:
 			val = get_rc6(&i915->gt);
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index a24885ab415c..8405d6da5b9a 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -112,6 +112,14 @@ struct i915_pmu {
 	 */
 	ktime_t sleep_last;
 	/**
+	 * @irq_count: Number of interrupts
+	 *
+	 * Intentionally unsigned long to avoid atomics or heuristics on 32bit.
+	 * 4e9 interrupts are a lot and postprocessing can really deal with an
+	 * occasional wraparound easily. It's 32bit after all.
+	 */
+	unsigned long irq_count;
+	/**
 	 * @events_attr_group: Device events attribute group.
 	 */
 	struct attribute_group events_attr_group;
diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
index 7e82c41a85f1..bdc989183c64 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
@@ -534,8 +534,10 @@ struct msm_gpu *a2xx_gpu_init(struct drm_device *dev)
 
 	if (!gpu->aspace) {
 		dev_err(dev->dev, "No memory protection without MMU\n");
-		ret = -ENXIO;
-		goto fail;
+		if (!allow_vram_carveout) {
+			ret = -ENXIO;
+			goto fail;
+		}
 	}
 
 	return gpu;
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 93da6683a866..4534633fe7cd 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -564,8 +564,10 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 		 * implement a cmdstream validator.
 		 */
 		DRM_DEV_ERROR(dev->dev, "No memory protection without IOMMU\n");
-		ret = -ENXIO;
-		goto fail;
+		if (!allow_vram_carveout) {
+			ret = -ENXIO;
+			goto fail;
+		}
 	}
 
 	icc_path = devm_of_icc_get(&pdev->dev, "gfx-mem");
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index c0be3a0f36b2..82bebb40234d 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -692,8 +692,10 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 		 * implement a cmdstream validator.
 		 */
 		DRM_DEV_ERROR(dev->dev, "No memory protection without IOMMU\n");
-		ret = -ENXIO;
-		goto fail;
+		if (!allow_vram_carveout) {
+			ret = -ENXIO;
+			goto fail;
+		}
 	}
 
 	icc_path = devm_of_icc_get(&pdev->dev, "gfx-mem");
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 87c8b033ad1a..12e75ba360f9 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -18,6 +18,10 @@ bool snapshot_debugbus = false;
 MODULE_PARM_DESC(snapshot_debugbus, "Include debugbus sections in GPU devcoredump (if not fused off)");
 module_param_named(snapshot_debugbus, snapshot_debugbus, bool, 0600);
 
+bool allow_vram_carveout = false;
+MODULE_PARM_DESC(allow_vram_carveout, "Allow using VRAM Carveout, in place of IOMMU");
+module_param_named(allow_vram_carveout, allow_vram_carveout, bool, 0600);
+
 static const struct adreno_info gpulist[] = {
 	{
 		.rev   = ADRENO_REV(2, 0, 0, 0),
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 6cf9975e951e..f09175698827 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -191,8 +191,6 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu,
 		struct platform_device *pdev)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-	struct io_pgtable_domain_attr pgtbl_cfg;
 	struct iommu_domain *iommu;
 	struct msm_mmu *mmu;
 	struct msm_gem_address_space *aspace;
@@ -202,13 +200,18 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu,
 	if (!iommu)
 		return NULL;
 
-	/*
-	 * This allows GPU to set the bus attributes required to use system
-	 * cache on behalf of the iommu page table walker.
-	 */
-	if (!IS_ERR(a6xx_gpu->htw_llc_slice)) {
-		pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA;
-		iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg);
+
+	if (adreno_is_a6xx(adreno_gpu)) {
+		struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+		struct io_pgtable_domain_attr pgtbl_cfg;
+		/*
+		* This allows GPU to set the bus attributes required to use system
+		* cache on behalf of the iommu page table walker.
+		*/
+		if (!IS_ERR(a6xx_gpu->htw_llc_slice)) {
+			pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA;
+			iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg);
+		}
 	}
 
 	mmu = msm_iommu_new(&pdev->dev, iommu);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index c3775f79525a..b3d9a333591b 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -18,6 +18,7 @@
 #include "adreno_pm4.xml.h"
 
 extern bool snapshot_debugbus;
+extern bool allow_vram_carveout;
 
 enum {
 	ADRENO_FW_PM4 = 0,
@@ -211,6 +212,11 @@ static inline int adreno_is_a540(struct adreno_gpu *gpu)
 	return gpu->revn == 540;
 }
 
+static inline bool adreno_is_a6xx(struct adreno_gpu *gpu)
+{
+	return ((gpu->revn < 700 && gpu->revn > 599));
+}
+
 static inline int adreno_is_a618(struct adreno_gpu *gpu)
 {
        return gpu->revn == 618;
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index 6e971d552911..3bc7ed21de28 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -693,6 +693,13 @@ static int dp_irq_hpd_handle(struct dp_display_private *dp, u32 data)
 		return 0;
 	}
 
+	if (state == ST_CONNECT_PENDING) {
+		/* wait until ST_CONNECTED */
+		dp_add_event(dp, EV_IRQ_HPD_INT, 0, 1); /* delay = 1 */
+		mutex_unlock(&dp->event_mutex);
+		return 0;
+	}
+
 	ret = dp_display_usbpd_attention_cb(&dp->pdev->dev);
 	if (ret == -ECONNRESET) { /* cable unplugged */
 		dp->core_initialized = false;
diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c
index 97dca3e378b7..d1780bcac8cc 100644
--- a/drivers/gpu/drm/msm/dp/dp_panel.c
+++ b/drivers/gpu/drm/msm/dp/dp_panel.c
@@ -167,12 +167,18 @@ int dp_panel_read_sink_caps(struct dp_panel *dp_panel,
 	panel = container_of(dp_panel, struct dp_panel_private, dp_panel);
 
 	rc = dp_panel_read_dpcd(dp_panel);
+	if (rc) {
+		DRM_ERROR("read dpcd failed %d\n", rc);
+		return rc;
+	}
+
 	bw_code = drm_dp_link_rate_to_bw_code(dp_panel->link_info.rate);
-	if (rc || !is_link_rate_valid(bw_code) ||
+	if (!is_link_rate_valid(bw_code) ||
 			!is_lane_count_valid(dp_panel->link_info.num_lanes) ||
 			(bw_code > dp_panel->max_bw_code)) {
-		DRM_ERROR("read dpcd failed %d\n", rc);
-		return rc;
+		DRM_ERROR("Illegal link rate=%d lane=%d\n", dp_panel->link_info.rate,
+				dp_panel->link_info.num_lanes);
+		return -EINVAL;
 	}
 
 	if (dp_panel->dfp_present) {
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 535a0263ceeb..108c405e03dd 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -457,14 +457,14 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 
 	drm_mode_config_init(ddev);
 
-	/* Bind all our sub-components: */
-	ret = component_bind_all(dev, ddev);
+	ret = msm_init_vram(ddev);
 	if (ret)
 		goto err_destroy_mdss;
 
-	ret = msm_init_vram(ddev);
+	/* Bind all our sub-components: */
+	ret = component_bind_all(dev, ddev);
 	if (ret)
-		goto err_msm_uninit;
+		goto err_destroy_mdss;
 
 	dma_set_max_seg_size(dev, UINT_MAX);
 
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 9a7c49bc394f..9d10739c4eb2 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -96,6 +96,8 @@ static struct page **get_pages(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
+	WARN_ON(!msm_gem_is_locked(obj));
+
 	if (!msm_obj->pages) {
 		struct drm_device *dev = obj->dev;
 		struct page **p;
@@ -988,6 +990,8 @@ void msm_gem_free_object(struct drm_gem_object *obj)
 		if (msm_obj->pages)
 			kvfree(msm_obj->pages);
 
+		put_iova_vmas(obj);
+
 		/* dma_buf_detach() grabs resv lock, so we need to unlock
 		 * prior to drm_prime_gem_destroy
 		 */
@@ -997,11 +1001,10 @@ void msm_gem_free_object(struct drm_gem_object *obj)
 	} else {
 		msm_gem_vunmap(obj);
 		put_pages(obj);
+		put_iova_vmas(obj);
 		msm_gem_unlock(obj);
 	}
 
-	put_iova_vmas(obj);
-
 	drm_gem_object_release(obj);
 
 	kfree(msm_obj);
@@ -1115,6 +1118,8 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 		struct msm_gem_vma *vma;
 		struct page **pages;
 
+		drm_gem_private_object_init(dev, obj, size);
+
 		msm_gem_lock(obj);
 
 		vma = add_vma(obj, NULL);
@@ -1126,9 +1131,9 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 
 		to_msm_bo(obj)->vram_node = &vma->node;
 
-		drm_gem_private_object_init(dev, obj, size);
-
+		msm_gem_lock(obj);
 		pages = get_pages(obj);
+		msm_gem_unlock(obj);
 		if (IS_ERR(pages)) {
 			ret = PTR_ERR(pages);
 			goto fail;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/Kbuild b/drivers/gpu/drm/nouveau/dispnv50/Kbuild
index 6fdddb266fb1..4488e1c061b3 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/Kbuild
+++ b/drivers/gpu/drm/nouveau/dispnv50/Kbuild
@@ -37,6 +37,7 @@ nouveau-y += dispnv50/wimmc37b.o
 nouveau-y += dispnv50/wndw.o
 nouveau-y += dispnv50/wndwc37e.o
 nouveau-y += dispnv50/wndwc57e.o
+nouveau-y += dispnv50/wndwc67e.o
 
 nouveau-y += dispnv50/base.o
 nouveau-y += dispnv50/base507c.o
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core.c b/drivers/gpu/drm/nouveau/dispnv50/core.c
index 27ea3f34706d..abefc2343443 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/core.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/core.c
@@ -42,6 +42,7 @@ nv50_core_new(struct nouveau_drm *drm, struct nv50_core **pcore)
 		int version;
 		int (*new)(struct nouveau_drm *, s32, struct nv50_core **);
 	} cores[] = {
+		{ GA102_DISP_CORE_CHANNEL_DMA, 0, corec57d_new },
 		{ TU102_DISP_CORE_CHANNEL_DMA, 0, corec57d_new },
 		{ GV100_DISP_CORE_CHANNEL_DMA, 0, corec37d_new },
 		{ GP102_DISP_CORE_CHANNEL_DMA, 0, core917d_new },
diff --git a/drivers/gpu/drm/nouveau/dispnv50/curs.c b/drivers/gpu/drm/nouveau/dispnv50/curs.c
index 121c24a18f11..31d8b2e4791d 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/curs.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/curs.c
@@ -31,6 +31,7 @@ nv50_curs_new(struct nouveau_drm *drm, int head, struct nv50_wndw **pwndw)
 		int version;
 		int (*new)(struct nouveau_drm *, int, s32, struct nv50_wndw **);
 	} curses[] = {
+		{ GA102_DISP_CURSOR, 0, cursc37a_new },
 		{ TU102_DISP_CURSOR, 0, cursc37a_new },
 		{ GV100_DISP_CURSOR, 0, cursc37a_new },
 		{ GK104_DISP_CURSOR, 0, curs907a_new },
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 33fff388dd83..c6367035970e 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -222,7 +222,7 @@ nv50_dmac_wait(struct nvif_push *push, u32 size)
 
 int
 nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
-		 const s32 *oclass, u8 head, void *data, u32 size, u64 syncbuf,
+		 const s32 *oclass, u8 head, void *data, u32 size, s64 syncbuf,
 		 struct nv50_dmac *dmac)
 {
 	struct nouveau_cli *cli = (void *)device->object.client;
@@ -271,7 +271,7 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
 	if (ret)
 		return ret;
 
-	if (!syncbuf)
+	if (syncbuf < 0)
 		return 0;
 
 	ret = nvif_object_ctor(&dmac->base.user, "kmsSyncCtxDma", NV50_DISP_HANDLE_SYNCBUF,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h
index 92bddc083617..38dec11e7dda 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h
@@ -95,7 +95,7 @@ struct nv50_outp_atom {
 
 int nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
 		     const s32 *oclass, u8 head, void *data, u32 size,
-		     u64 syncbuf, struct nv50_dmac *dmac);
+		     s64 syncbuf, struct nv50_dmac *dmac);
 void nv50_dmac_destroy(struct nv50_dmac *);
 
 /*
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wimm.c b/drivers/gpu/drm/nouveau/dispnv50/wimm.c
index a1ac153d5e98..566fbddfc8d7 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wimm.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wimm.c
@@ -31,6 +31,7 @@ nv50_wimm_init(struct nouveau_drm *drm, struct nv50_wndw *wndw)
 		int version;
 		int (*init)(struct nouveau_drm *, s32, struct nv50_wndw *);
 	} wimms[] = {
+		{ GA102_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
 		{ TU102_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
 		{ GV100_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
 		{}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
index 685b70871324..b390029c69ec 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
@@ -76,7 +76,7 @@ wimmc37b_init_(const struct nv50_wimm_func *func, struct nouveau_drm *drm,
 	int ret;
 
 	ret = nv50_dmac_create(&drm->client.device, &disp->disp->object,
-			       &oclass, 0, &args, sizeof(args), 0,
+			       &oclass, 0, &args, sizeof(args), -1,
 			       &wndw->wimm);
 	if (ret) {
 		NV_ERROR(drm, "wimm%04x allocation failed: %d\n", oclass, ret);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 0356474ad6f6..ce451242f79e 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -784,6 +784,7 @@ nv50_wndw_new(struct nouveau_drm *drm, enum drm_plane_type type, int index,
 		int (*new)(struct nouveau_drm *, enum drm_plane_type,
 			   int, s32, struct nv50_wndw **);
 	} wndws[] = {
+		{ GA102_DISP_WINDOW_CHANNEL_DMA, 0, wndwc67e_new },
 		{ TU102_DISP_WINDOW_CHANNEL_DMA, 0, wndwc57e_new },
 		{ GV100_DISP_WINDOW_CHANNEL_DMA, 0, wndwc37e_new },
 		{}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.h b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
index 3278e2880034..f4e0c5080034 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
@@ -129,6 +129,14 @@ int wndwc37e_update(struct nv50_wndw *, u32 *);
 
 int wndwc57e_new(struct nouveau_drm *, enum drm_plane_type, int, s32,
 		 struct nv50_wndw **);
+bool wndwc57e_ilut(struct nv50_wndw *, struct nv50_wndw_atom *, int);
+int wndwc57e_ilut_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+int wndwc57e_ilut_clr(struct nv50_wndw *);
+int wndwc57e_csc_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+int wndwc57e_csc_clr(struct nv50_wndw *);
+
+int wndwc67e_new(struct nouveau_drm *, enum drm_plane_type, int, s32,
+		 struct nv50_wndw **);
 
 int nv50_wndw_new(struct nouveau_drm *, enum drm_plane_type, int index,
 		  struct nv50_wndw **);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
index 429be0bb0222..abdd3bb658b3 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
@@ -80,7 +80,7 @@ wndwc57e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 	return 0;
 }
 
-static int
+int
 wndwc57e_csc_clr(struct nv50_wndw *wndw)
 {
 	struct nvif_push *push = wndw->wndw.push;
@@ -98,7 +98,7 @@ wndwc57e_csc_clr(struct nv50_wndw *wndw)
 	return 0;
 }
 
-static int
+int
 wndwc57e_csc_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 {
 	struct nvif_push *push = wndw->wndw.push;
@@ -111,7 +111,7 @@ wndwc57e_csc_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 	return 0;
 }
 
-static int
+int
 wndwc57e_ilut_clr(struct nv50_wndw *wndw)
 {
 	struct nvif_push *push = wndw->wndw.push;
@@ -124,7 +124,7 @@ wndwc57e_ilut_clr(struct nv50_wndw *wndw)
 	return 0;
 }
 
-static int
+int
 wndwc57e_ilut_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 {
 	struct nvif_push *push = wndw->wndw.push;
@@ -179,7 +179,7 @@ wndwc57e_ilut_load(struct drm_color_lut *in, int size, void __iomem *mem)
 	writew(readw(mem - 4), mem + 4);
 }
 
-static bool
+bool
 wndwc57e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw, int size)
 {
 	if (size = size ? size : 1024, size != 256 && size != 1024)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc67e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc67e.c
new file mode 100644
index 000000000000..7a370fa1df20
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc67e.c
@@ -0,0 +1,106 @@
+/*
+ * Copyright 2021 Red Hat 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.
+ */
+#include "wndw.h"
+#include "atom.h"
+
+#include <nvif/pushc37b.h>
+
+#include <nvhw/class/clc57e.h>
+
+static int
+wndwc67e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	struct nvif_push *push = wndw->wndw.push;
+	int ret;
+
+	if ((ret = PUSH_WAIT(push, 17)))
+		return ret;
+
+	PUSH_MTHD(push, NVC57E, SET_PRESENT_CONTROL,
+		  NVVAL(NVC57E, SET_PRESENT_CONTROL, MIN_PRESENT_INTERVAL, asyw->image.interval) |
+		  NVVAL(NVC57E, SET_PRESENT_CONTROL, BEGIN_MODE, asyw->image.mode) |
+		  NVDEF(NVC57E, SET_PRESENT_CONTROL, TIMESTAMP_MODE, DISABLE));
+
+	PUSH_MTHD(push, NVC57E, SET_SIZE,
+		  NVVAL(NVC57E, SET_SIZE, WIDTH, asyw->image.w) |
+		  NVVAL(NVC57E, SET_SIZE, HEIGHT, asyw->image.h),
+
+				SET_STORAGE,
+		  NVVAL(NVC57E, SET_STORAGE, BLOCK_HEIGHT, asyw->image.blockh),
+
+				SET_PARAMS,
+		  NVVAL(NVC57E, SET_PARAMS, FORMAT, asyw->image.format) |
+		  NVDEF(NVC57E, SET_PARAMS, CLAMP_BEFORE_BLEND, DISABLE) |
+		  NVDEF(NVC57E, SET_PARAMS, SWAP_UV, DISABLE) |
+		  NVDEF(NVC57E, SET_PARAMS, FMT_ROUNDING_MODE, ROUND_TO_NEAREST),
+
+				SET_PLANAR_STORAGE(0),
+		  NVVAL(NVC57E, SET_PLANAR_STORAGE, PITCH, asyw->image.blocks[0]) |
+		  NVVAL(NVC57E, SET_PLANAR_STORAGE, PITCH, asyw->image.pitch[0] >> 6));
+
+	PUSH_MTHD(push, NVC57E, SET_CONTEXT_DMA_ISO(0), asyw->image.handle, 1);
+	PUSH_MTHD(push, NVC57E, SET_OFFSET(0), asyw->image.offset[0] >> 8);
+
+	PUSH_MTHD(push, NVC57E, SET_POINT_IN(0),
+		  NVVAL(NVC57E, SET_POINT_IN, X, asyw->state.src_x >> 16) |
+		  NVVAL(NVC57E, SET_POINT_IN, Y, asyw->state.src_y >> 16));
+
+	PUSH_MTHD(push, NVC57E, SET_SIZE_IN,
+		  NVVAL(NVC57E, SET_SIZE_IN, WIDTH, asyw->state.src_w >> 16) |
+		  NVVAL(NVC57E, SET_SIZE_IN, HEIGHT, asyw->state.src_h >> 16));
+
+	PUSH_MTHD(push, NVC57E, SET_SIZE_OUT,
+		  NVVAL(NVC57E, SET_SIZE_OUT, WIDTH, asyw->state.crtc_w) |
+		  NVVAL(NVC57E, SET_SIZE_OUT, HEIGHT, asyw->state.crtc_h));
+	return 0;
+}
+
+static const struct nv50_wndw_func
+wndwc67e = {
+	.acquire = wndwc37e_acquire,
+	.release = wndwc37e_release,
+	.sema_set = wndwc37e_sema_set,
+	.sema_clr = wndwc37e_sema_clr,
+	.ntfy_set = wndwc37e_ntfy_set,
+	.ntfy_clr = wndwc37e_ntfy_clr,
+	.ntfy_reset = corec37d_ntfy_init,
+	.ntfy_wait_begun = base507c_ntfy_wait_begun,
+	.ilut = wndwc57e_ilut,
+	.ilut_identity = true,
+	.ilut_size = 1024,
+	.xlut_set = wndwc57e_ilut_set,
+	.xlut_clr = wndwc57e_ilut_clr,
+	.csc = base907c_csc,
+	.csc_set = wndwc57e_csc_set,
+	.csc_clr = wndwc57e_csc_clr,
+	.image_set = wndwc67e_image_set,
+	.image_clr = wndwc37e_image_clr,
+	.blend_set = wndwc37e_blend_set,
+	.update = wndwc37e_update,
+};
+
+int
+wndwc67e_new(struct nouveau_drm *drm, enum drm_plane_type type, int index,
+	     s32 oclass, struct nv50_wndw **pwndw)
+{
+	return wndwc37e_new_(&wndwc67e, drm, type, index, oclass, BIT(index >> 1), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
index cd9a2e687bb6..57d4f457a7d4 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
@@ -33,6 +33,7 @@ struct nv_device_info_v0 {
 #define NV_DEVICE_INFO_V0_PASCAL                                           0x0a
 #define NV_DEVICE_INFO_V0_VOLTA                                            0x0b
 #define NV_DEVICE_INFO_V0_TURING                                           0x0c
+#define NV_DEVICE_INFO_V0_AMPERE                                           0x0d
 	__u8  family;
 	__u8  pad06[2];
 	__u64 ram_size;
diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h
index 2c79beb41126..ba2c28ea43d2 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/class.h
@@ -88,6 +88,7 @@
 #define GP102_DISP                                    /* cl5070.h */ 0x00009870
 #define GV100_DISP                                    /* cl5070.h */ 0x0000c370
 #define TU102_DISP                                    /* cl5070.h */ 0x0000c570
+#define GA102_DISP                                    /* cl5070.h */ 0x0000c670
 
 #define GV100_DISP_CAPS                                              0x0000c373
 
@@ -103,6 +104,7 @@
 #define GK104_DISP_CURSOR                             /* cl507a.h */ 0x0000917a
 #define GV100_DISP_CURSOR                             /* cl507a.h */ 0x0000c37a
 #define TU102_DISP_CURSOR                             /* cl507a.h */ 0x0000c57a
+#define GA102_DISP_CURSOR                             /* cl507a.h */ 0x0000c67a
 
 #define NV50_DISP_OVERLAY                             /* cl507b.h */ 0x0000507b
 #define G82_DISP_OVERLAY                              /* cl507b.h */ 0x0000827b
@@ -112,6 +114,7 @@
 
 #define GV100_DISP_WINDOW_IMM_CHANNEL_DMA             /* clc37b.h */ 0x0000c37b
 #define TU102_DISP_WINDOW_IMM_CHANNEL_DMA             /* clc37b.h */ 0x0000c57b
+#define GA102_DISP_WINDOW_IMM_CHANNEL_DMA             /* clc37b.h */ 0x0000c67b
 
 #define NV50_DISP_BASE_CHANNEL_DMA                    /* cl507c.h */ 0x0000507c
 #define G82_DISP_BASE_CHANNEL_DMA                     /* cl507c.h */ 0x0000827c
@@ -135,6 +138,7 @@
 #define GP102_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000987d
 #define GV100_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000c37d
 #define TU102_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000c57d
+#define GA102_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000c67d
 
 #define NV50_DISP_OVERLAY_CHANNEL_DMA                 /* cl507e.h */ 0x0000507e
 #define G82_DISP_OVERLAY_CHANNEL_DMA                  /* cl507e.h */ 0x0000827e
@@ -145,6 +149,7 @@
 
 #define GV100_DISP_WINDOW_CHANNEL_DMA                 /* clc37e.h */ 0x0000c37e
 #define TU102_DISP_WINDOW_CHANNEL_DMA                 /* clc37e.h */ 0x0000c57e
+#define GA102_DISP_WINDOW_CHANNEL_DMA                 /* clc37e.h */ 0x0000c67e
 
 #define NV50_TESLA                                                   0x00005097
 #define G82_TESLA                                                    0x00008297
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
index 5c007ce62fc3..c920939a1467 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
@@ -120,6 +120,7 @@ struct nvkm_device {
 		GP100    = 0x130,
 		GV100    = 0x140,
 		TU100    = 0x160,
+		GA100    = 0x170,
 	} card_type;
 	u32 chipset;
 	u8  chiprev;
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
index 5a96c942d912..0f6fa6631a19 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
@@ -37,4 +37,5 @@ int gp100_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int gp102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int gv100_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int tu102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
+int ga102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
index 1a39e52e09e3..50cc7c05eac4 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
@@ -32,4 +32,5 @@ int gm107_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 int gm200_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 int gv100_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 int tu102_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
+int ga100_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
index 34b56b10218a..2ecd52aec1d1 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
@@ -86,6 +86,8 @@ int gp100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gp102_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gp10b_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gv100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int ga100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int ga102_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 
 #include <subdev/bios.h>
 #include <subdev/bios/ramcfg.h>
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h
index eaacf8d80527..cdcce5ece6ff 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h
@@ -37,4 +37,5 @@ int nv50_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
 int g94_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
 int gf119_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
 int gk104_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
+int ga102_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h
index 81b977319640..640f649ce497 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h
@@ -92,6 +92,7 @@ int g94_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
 int gf117_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
 int gf119_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
 int gk104_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
+int gk110_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
 int gm200_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
 
 static inline int
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
index 6641fe4c252c..e45ca4583967 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
@@ -32,4 +32,5 @@ int gk20a_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 int gp100_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 int gp10b_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 int tu102_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
+int ga100_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index c7a94c94dbf3..72f35a2babcb 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -256,6 +256,7 @@ nouveau_backlight_init(struct drm_connector *connector)
 	case NV_DEVICE_INFO_V0_PASCAL:
 	case NV_DEVICE_INFO_V0_VOLTA:
 	case NV_DEVICE_INFO_V0_TURING:
+	case NV_DEVICE_INFO_V0_AMPERE: //XXX: not confirmed
 		ret = nv50_backlight_init(nv_encoder, &props, &ops);
 		break;
 	default:
diff --git a/drivers/gpu/drm/nouveau/nvif/disp.c b/drivers/gpu/drm/nouveau/nvif/disp.c
index 8d0d30e08f57..529cb60d5efb 100644
--- a/drivers/gpu/drm/nouveau/nvif/disp.c
+++ b/drivers/gpu/drm/nouveau/nvif/disp.c
@@ -35,6 +35,7 @@ nvif_disp_ctor(struct nvif_device *device, const char *name, s32 oclass,
 	       struct nvif_disp *disp)
 {
 	static const struct nvif_mclass disps[] = {
+		{ GA102_DISP, -1 },
 		{ TU102_DISP, -1 },
 		{ GV100_DISP, -1 },
 		{ GP102_DISP, -1 },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 7851bec5f0e5..cdcc851e06f9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -1815,7 +1815,7 @@ nvf0_chipset = {
 	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -1853,7 +1853,7 @@ nvf1_chipset = {
 	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -1891,7 +1891,7 @@ nv106_chipset = {
 	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -1929,7 +1929,7 @@ nv108_chipset = {
 	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -1967,7 +1967,7 @@ nv117_chipset = {
 	.fb = gm107_fb_new,
 	.fuse = gm107_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -2003,7 +2003,7 @@ nv118_chipset = {
 	.fb = gm107_fb_new,
 	.fuse = gm107_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -2652,6 +2652,61 @@ nv168_chipset = {
 	.sec2 = tu102_sec2_new,
 };
 
+static const struct nvkm_device_chip
+nv170_chipset = {
+	.name = "GA100",
+	.bar = tu102_bar_new,
+	.bios = nvkm_bios_new,
+	.devinit = ga100_devinit_new,
+	.fb = ga100_fb_new,
+	.gpio = gk104_gpio_new,
+	.i2c = gm200_i2c_new,
+	.ibus = gm200_ibus_new,
+	.imem = nv50_instmem_new,
+	.mc = ga100_mc_new,
+	.mmu = tu102_mmu_new,
+	.pci = gp100_pci_new,
+	.timer = gk20a_timer_new,
+};
+
+static const struct nvkm_device_chip
+nv172_chipset = {
+	.name = "GA102",
+	.bar = tu102_bar_new,
+	.bios = nvkm_bios_new,
+	.devinit = ga100_devinit_new,
+	.fb = ga102_fb_new,
+	.gpio = ga102_gpio_new,
+	.i2c = gm200_i2c_new,
+	.ibus = gm200_ibus_new,
+	.imem = nv50_instmem_new,
+	.mc = ga100_mc_new,
+	.mmu = tu102_mmu_new,
+	.pci = gp100_pci_new,
+	.timer = gk20a_timer_new,
+	.disp = ga102_disp_new,
+	.dma = gv100_dma_new,
+};
+
+static const struct nvkm_device_chip
+nv174_chipset = {
+	.name = "GA104",
+	.bar = tu102_bar_new,
+	.bios = nvkm_bios_new,
+	.devinit = ga100_devinit_new,
+	.fb = ga102_fb_new,
+	.gpio = ga102_gpio_new,
+	.i2c = gm200_i2c_new,
+	.ibus = gm200_ibus_new,
+	.imem = nv50_instmem_new,
+	.mc = ga100_mc_new,
+	.mmu = tu102_mmu_new,
+	.pci = gp100_pci_new,
+	.timer = gk20a_timer_new,
+	.disp = ga102_disp_new,
+	.dma = gv100_dma_new,
+};
+
 static int
 nvkm_device_event_ctor(struct nvkm_object *object, void *data, u32 size,
 		       struct nvkm_notify *notify)
@@ -3063,6 +3118,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 			case 0x130: device->card_type = GP100; break;
 			case 0x140: device->card_type = GV100; break;
 			case 0x160: device->card_type = TU100; break;
+			case 0x170: device->card_type = GA100; break;
 			default:
 				break;
 			}
@@ -3160,10 +3216,23 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		case 0x166: device->chip = &nv166_chipset; break;
 		case 0x167: device->chip = &nv167_chipset; break;
 		case 0x168: device->chip = &nv168_chipset; break;
+		case 0x172: device->chip = &nv172_chipset; break;
+		case 0x174: device->chip = &nv174_chipset; break;
 		default:
-			nvdev_error(device, "unknown chipset (%08x)\n", boot0);
-			ret = -ENODEV;
-			goto done;
+			if (nvkm_boolopt(device->cfgopt, "NvEnableUnsupportedChipsets", false)) {
+				switch (device->chipset) {
+				case 0x170: device->chip = &nv170_chipset; break;
+				default:
+					break;
+				}
+			}
+
+			if (!device->chip) {
+				nvdev_error(device, "unknown chipset (%08x)\n", boot0);
+				ret = -ENODEV;
+				goto done;
+			}
+			break;
 		}
 
 		nvdev_info(device, "NVIDIA %s (%08x)\n",
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
index 03c6d9aef075..147894798786 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
@@ -176,6 +176,7 @@ nvkm_udevice_info(struct nvkm_udevice *udev, void *data, u32 size)
 	case GP100: args->v0.family = NV_DEVICE_INFO_V0_PASCAL; break;
 	case GV100: args->v0.family = NV_DEVICE_INFO_V0_VOLTA; break;
 	case TU100: args->v0.family = NV_DEVICE_INFO_V0_TURING; break;
+	case GA100: args->v0.family = NV_DEVICE_INFO_V0_AMPERE; break;
 	default:
 		args->v0.family = 0;
 		break;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
index cf075311cdd2..b03f043efe26 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
@@ -17,6 +17,7 @@ nvkm-y += nvkm/engine/disp/gp100.o
 nvkm-y += nvkm/engine/disp/gp102.o
 nvkm-y += nvkm/engine/disp/gv100.o
 nvkm-y += nvkm/engine/disp/tu102.o
+nvkm-y += nvkm/engine/disp/ga102.o
 nvkm-y += nvkm/engine/disp/vga.o
 
 nvkm-y += nvkm/engine/disp/head.o
@@ -42,6 +43,7 @@ nvkm-y += nvkm/engine/disp/sorgm200.o
 nvkm-y += nvkm/engine/disp/sorgp100.o
 nvkm-y += nvkm/engine/disp/sorgv100.o
 nvkm-y += nvkm/engine/disp/sortu102.o
+nvkm-y += nvkm/engine/disp/sorga102.o
 
 nvkm-y += nvkm/engine/disp/outp.o
 nvkm-y += nvkm/engine/disp/dp.o
@@ -75,6 +77,7 @@ nvkm-y += nvkm/engine/disp/rootgp100.o
 nvkm-y += nvkm/engine/disp/rootgp102.o
 nvkm-y += nvkm/engine/disp/rootgv100.o
 nvkm-y += nvkm/engine/disp/roottu102.o
+nvkm-y += nvkm/engine/disp/rootga102.o
 
 nvkm-y += nvkm/engine/disp/capsgv100.o
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
index 3800aeb507d0..55fbfe28c6dc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
@@ -33,6 +33,12 @@
 
 #include <nvif/event.h>
 
+/* IED scripts are no longer used by UEFI/RM from Ampere, but have been updated for
+ * the x86 option ROM.  However, the relevant VBIOS table versions weren't modified,
+ * so we're unable to detect this in a nice way.
+ */
+#define AMPERE_IED_HACK(disp) ((disp)->engine.subdev.device->card_type >= GA100)
+
 struct lt_state {
 	struct nvkm_dp *dp;
 	u8  stat[6];
@@ -238,6 +244,19 @@ nvkm_dp_train_links(struct nvkm_dp *dp)
 		dp->dpcd[DPCD_RC02] &= ~DPCD_RC02_TPS3_SUPPORTED;
 	lt.pc2 = dp->dpcd[DPCD_RC02] & DPCD_RC02_TPS3_SUPPORTED;
 
+	if (AMPERE_IED_HACK(disp) && (lnkcmp = lt.dp->info.script[0])) {
+		/* Execute BeforeLinkTraining script from DP Info table. */
+		while (ior->dp.bw < nvbios_rd08(bios, lnkcmp))
+			lnkcmp += 3;
+		lnkcmp = nvbios_rd16(bios, lnkcmp + 1);
+
+		nvbios_init(&dp->outp.disp->engine.subdev, lnkcmp,
+			init.outp = &dp->outp.info;
+			init.or   = ior->id;
+			init.link = ior->asy.link;
+		);
+	}
+
 	/* Set desired link configuration on the source. */
 	if ((lnkcmp = lt.dp->info.lnkcmp)) {
 		if (dp->version < 0x30) {
@@ -316,12 +335,14 @@ nvkm_dp_train_init(struct nvkm_dp *dp)
 		);
 	}
 
-	/* Execute BeforeLinkTraining script from DP Info table. */
-	nvbios_init(&dp->outp.disp->engine.subdev, dp->info.script[0],
-		init.outp = &dp->outp.info;
-		init.or   = dp->outp.ior->id;
-		init.link = dp->outp.ior->asy.link;
-	);
+	if (!AMPERE_IED_HACK(dp->outp.disp)) {
+		/* Execute BeforeLinkTraining script from DP Info table. */
+		nvbios_init(&dp->outp.disp->engine.subdev, dp->info.script[0],
+			init.outp = &dp->outp.info;
+			init.or   = dp->outp.ior->id;
+			init.link = dp->outp.ior->asy.link;
+		);
+	}
 }
 
 static const struct dp_rates {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c
new file mode 100644
index 000000000000..aa2e5645fe36
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c
@@ -0,0 +1,46 @@
+/*
+ * Copyright 2021 Red Hat 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.
+ */
+#include "nv50.h"
+#include "head.h"
+#include "ior.h"
+#include "channv50.h"
+#include "rootnv50.h"
+
+static const struct nv50_disp_func
+ga102_disp = {
+	.init = tu102_disp_init,
+	.fini = gv100_disp_fini,
+	.intr = gv100_disp_intr,
+	.uevent = &gv100_disp_chan_uevent,
+	.super = gv100_disp_super,
+	.root = &ga102_disp_root_oclass,
+	.wndw = { .cnt = gv100_disp_wndw_cnt },
+	.head = { .cnt = gv100_head_cnt, .new = gv100_head_new },
+	.sor = { .cnt = gv100_sor_cnt, .new = ga102_sor_new },
+	.ramht_size = 0x2000,
+};
+
+int
+ga102_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
+{
+	return nv50_disp_new_(&ga102_disp, device, index, pdisp);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
index 09f3038eff26..9f0bb7c6b010 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
@@ -150,6 +150,8 @@ void gv100_sor_dp_audio(struct nvkm_ior *, int, bool);
 void gv100_sor_dp_audio_sym(struct nvkm_ior *, int, u16, u32);
 void gv100_sor_dp_watermark(struct nvkm_ior *, int, u8);
 
+void tu102_sor_dp_vcpi(struct nvkm_ior *, int, u8, u8, u16, u16);
+
 void g84_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
 void gt215_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
 void gf119_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
@@ -207,4 +209,6 @@ int gv100_sor_cnt(struct nvkm_disp *, unsigned long *);
 int gv100_sor_new(struct nvkm_disp *, int);
 
 int tu102_sor_new(struct nvkm_disp *, int);
+
+int ga102_sor_new(struct nvkm_disp *, int);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
index a677161c7f3a..db31b37752a2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
@@ -86,6 +86,8 @@ void gv100_disp_intr(struct nv50_disp *);
 void gv100_disp_super(struct work_struct *);
 int gv100_disp_wndw_cnt(struct nvkm_disp *, unsigned long *);
 
+int tu102_disp_init(struct nv50_disp *);
+
 void nv50_disp_dptmds_war_2(struct nv50_disp *, struct dcb_output *);
 void nv50_disp_dptmds_war_3(struct nv50_disp *, struct dcb_output *);
 void nv50_disp_update_sppll1(struct nv50_disp *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootga102.c
new file mode 100644
index 000000000000..9af07c3cf9fc
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootga102.c
@@ -0,0 +1,52 @@
+/*
+ * Copyright 2021 Red Hat 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.
+ */
+#include "rootnv50.h"
+#include "channv50.h"
+
+#include <nvif/class.h>
+
+static const struct nv50_disp_root_func
+ga102_disp_root = {
+	.user = {
+		{{-1,-1,GV100_DISP_CAPS                }, gv100_disp_caps_new },
+		{{0,0,GA102_DISP_CURSOR                }, gv100_disp_curs_new },
+		{{0,0,GA102_DISP_WINDOW_IMM_CHANNEL_DMA}, gv100_disp_wimm_new },
+		{{0,0,GA102_DISP_CORE_CHANNEL_DMA      }, gv100_disp_core_new },
+		{{0,0,GA102_DISP_WINDOW_CHANNEL_DMA    }, gv100_disp_wndw_new },
+		{}
+	},
+};
+
+static int
+ga102_disp_root_new(struct nvkm_disp *disp, const struct nvkm_oclass *oclass,
+		    void *data, u32 size, struct nvkm_object **pobject)
+{
+	return nv50_disp_root_new_(&ga102_disp_root, disp, oclass, data, size, pobject);
+}
+
+const struct nvkm_disp_oclass
+ga102_disp_root_oclass = {
+	.base.oclass = GA102_DISP,
+	.base.minver = -1,
+	.base.maxver = -1,
+	.ctor = ga102_disp_root_new,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
index 7070f5408d92..27bb170d0293 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
@@ -41,4 +41,5 @@ extern const struct nvkm_disp_oclass gp100_disp_root_oclass;
 extern const struct nvkm_disp_oclass gp102_disp_root_oclass;
 extern const struct nvkm_disp_oclass gv100_disp_root_oclass;
 extern const struct nvkm_disp_oclass tu102_disp_root_oclass;
+extern const struct nvkm_disp_oclass ga102_disp_root_oclass;
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorga102.c
new file mode 100644
index 000000000000..033827de9116
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorga102.c
@@ -0,0 +1,140 @@
+/*
+ * Copyright 2021 Red Hat 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.
+ */
+#include "ior.h"
+
+#include <subdev/timer.h>
+
+static int
+ga102_sor_dp_links(struct nvkm_ior *sor, struct nvkm_i2c_aux *aux)
+{
+	struct nvkm_device *device = sor->disp->engine.subdev.device;
+	const u32 soff = nv50_ior_base(sor);
+	const u32 loff = nv50_sor_link(sor);
+	u32 dpctrl = 0x00000000;
+	u32 clksor = 0x00000000;
+
+	switch (sor->dp.bw) {
+	case 0x06: clksor |= 0x00000000; break;
+	case 0x0a: clksor |= 0x00040000; break;
+	case 0x14: clksor |= 0x00080000; break;
+	case 0x1e: clksor |= 0x000c0000; break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	dpctrl |= ((1 << sor->dp.nr) - 1) << 16;
+	if (sor->dp.mst)
+		dpctrl |= 0x40000000;
+	if (sor->dp.ef)
+		dpctrl |= 0x00004000;
+
+	nvkm_mask(device, 0x612300 + soff, 0x007c0000, clksor);
+
+	/*XXX*/
+	nvkm_msec(device, 40, NVKM_DELAY);
+	nvkm_mask(device, 0x612300 + soff, 0x00030000, 0x00010000);
+	nvkm_mask(device, 0x61c10c + loff, 0x00000003, 0x00000001);
+
+	nvkm_mask(device, 0x61c10c + loff, 0x401f4000, dpctrl);
+	return 0;
+}
+
+static void
+ga102_sor_clock(struct nvkm_ior *sor)
+{
+	struct nvkm_device *device = sor->disp->engine.subdev.device;
+	u32 div2 = 0;
+	if (sor->asy.proto == TMDS) {
+		if (sor->tmds.high_speed)
+			div2 = 1;
+	}
+	nvkm_wr32(device, 0x00ec08 + (sor->id * 0x10), 0x00000000);
+	nvkm_wr32(device, 0x00ec04 + (sor->id * 0x10), div2);
+}
+
+static const struct nvkm_ior_func
+ga102_sor_hda = {
+	.route = {
+		.get = gm200_sor_route_get,
+		.set = gm200_sor_route_set,
+	},
+	.state = gv100_sor_state,
+	.power = nv50_sor_power,
+	.clock = ga102_sor_clock,
+	.hdmi = {
+		.ctrl = gv100_hdmi_ctrl,
+		.scdc = gm200_hdmi_scdc,
+	},
+	.dp = {
+		.lanes = { 0, 1, 2, 3 },
+		.links = ga102_sor_dp_links,
+		.power = g94_sor_dp_power,
+		.pattern = gm107_sor_dp_pattern,
+		.drive = gm200_sor_dp_drive,
+		.vcpi = tu102_sor_dp_vcpi,
+		.audio = gv100_sor_dp_audio,
+		.audio_sym = gv100_sor_dp_audio_sym,
+		.watermark = gv100_sor_dp_watermark,
+	},
+	.hda = {
+		.hpd = gf119_hda_hpd,
+		.eld = gf119_hda_eld,
+		.device_entry = gv100_hda_device_entry,
+	},
+};
+
+static const struct nvkm_ior_func
+ga102_sor = {
+	.route = {
+		.get = gm200_sor_route_get,
+		.set = gm200_sor_route_set,
+	},
+	.state = gv100_sor_state,
+	.power = nv50_sor_power,
+	.clock = ga102_sor_clock,
+	.hdmi = {
+		.ctrl = gv100_hdmi_ctrl,
+		.scdc = gm200_hdmi_scdc,
+	},
+	.dp = {
+		.lanes = { 0, 1, 2, 3 },
+		.links = ga102_sor_dp_links,
+		.power = g94_sor_dp_power,
+		.pattern = gm107_sor_dp_pattern,
+		.drive = gm200_sor_dp_drive,
+		.vcpi = tu102_sor_dp_vcpi,
+		.audio = gv100_sor_dp_audio,
+		.audio_sym = gv100_sor_dp_audio_sym,
+		.watermark = gv100_sor_dp_watermark,
+	},
+};
+
+int
+ga102_sor_new(struct nvkm_disp *disp, int id)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	u32 hda = nvkm_rd32(device, 0x08a15c);
+	if (hda & BIT(id))
+		return nvkm_ior_new_(&ga102_sor_hda, disp, SOR, id);
+	return nvkm_ior_new_(&ga102_sor, disp, SOR, id);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c
index 59865a934c4b..0cf9e8752d25 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c
@@ -23,7 +23,7 @@
 
 #include <subdev/timer.h>
 
-static void
+void
 tu102_sor_dp_vcpi(struct nvkm_ior *sor, int head,
 		  u8 slot, u8 slot_nr, u16 pbn, u16 aligned)
 {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c
index 883ae4151ff8..4c85d1d4fbd4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c
@@ -28,7 +28,7 @@
 #include <core/gpuobj.h>
 #include <subdev/timer.h>
 
-static int
+int
 tu102_disp_init(struct nv50_disp *disp)
 {
 	struct nvkm_device *device = disp->base.engine.subdev.device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
index 7deb81b6dbac..4b571cc6bc70 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
@@ -75,7 +75,7 @@ shadow_image(struct nvkm_bios *bios, int idx, u32 offset, struct shadow *mthd)
 	nvkm_debug(subdev, "%08x: type %02x, %d bytes\n",
 		   image.base, image.type, image.size);
 
-	if (!shadow_fetch(bios, mthd, image.size)) {
+	if (!shadow_fetch(bios, mthd, image.base + image.size)) {
 		nvkm_debug(subdev, "%08x: fetch failed\n", image.base);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
index 3634cd0630b8..023ddc7c5399 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
@@ -64,6 +64,9 @@ pramin_init(struct nvkm_bios *bios, const char *name)
 		return NULL;
 
 	/* we can't get the bios image pointer without PDISP */
+	if (device->card_type >= GA100)
+		addr = device->chipset == 0x170; /*XXX: find the fuse reg for this */
+	else
 	if (device->card_type >= GM100)
 		addr = nvkm_rd32(device, 0x021c04);
 	else
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
index b3429371ed82..d1abb64841da 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
@@ -15,3 +15,4 @@ nvkm-y += nvkm/subdev/devinit/gm107.o
 nvkm-y += nvkm/subdev/devinit/gm200.o
 nvkm-y += nvkm/subdev/devinit/gv100.o
 nvkm-y += nvkm/subdev/devinit/tu102.o
+nvkm-y += nvkm/subdev/devinit/ga100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/ga100.c
new file mode 100644
index 000000000000..636a92128f6c
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/ga100.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright 2021 Red Hat 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.
+ */
+#include "nv50.h"
+
+#include <subdev/bios.h>
+#include <subdev/bios/pll.h>
+#include <subdev/clk/pll.h>
+
+static int
+ga100_devinit_pll_set(struct nvkm_devinit *init, u32 type, u32 freq)
+{
+	struct nvkm_subdev *subdev = &init->subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvbios_pll info;
+	int head = type - PLL_VPLL0;
+	int N, fN, M, P;
+	int ret;
+
+	ret = nvbios_pll_parse(device->bios, type, &info);
+	if (ret)
+		return ret;
+
+	ret = gt215_pll_calc(subdev, &info, freq, &N, &fN, &M, &P);
+	if (ret < 0)
+		return ret;
+
+	switch (info.type) {
+	case PLL_VPLL0:
+	case PLL_VPLL1:
+	case PLL_VPLL2:
+	case PLL_VPLL3:
+		nvkm_wr32(device, 0x00ef00 + (head * 0x40), 0x02080004);
+		nvkm_wr32(device, 0x00ef18 + (head * 0x40), (N << 16) | fN);
+		nvkm_wr32(device, 0x00ef04 + (head * 0x40), (P << 16) | M);
+		nvkm_wr32(device, 0x00e9c0 + (head * 0x04), 0x00000001);
+		break;
+	default:
+		nvkm_warn(subdev, "%08x/%dKhz unimplemented\n", type, freq);
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static const struct nvkm_devinit_func
+ga100_devinit = {
+	.init = nv50_devinit_init,
+	.post = tu102_devinit_post,
+	.pll_set = ga100_devinit_pll_set,
+};
+
+int
+ga100_devinit_new(struct nvkm_device *device, int index, struct nvkm_devinit **pinit)
+{
+	return nv50_devinit_new_(&ga100_devinit, device, index, pinit);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h
index 94723352137a..05961e624264 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h
@@ -19,4 +19,5 @@ void nvkm_devinit_ctor(const struct nvkm_devinit_func *, struct nvkm_device *,
 		       int index, struct nvkm_devinit *);
 
 int nv04_devinit_post(struct nvkm_devinit *, bool);
+int tu102_devinit_post(struct nvkm_devinit *, bool);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c
index 397670e72fff..9a469bf482f2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c
@@ -65,7 +65,7 @@ tu102_devinit_pll_set(struct nvkm_devinit *init, u32 type, u32 freq)
 	return ret;
 }
 
-static int
+int
 tu102_devinit_post(struct nvkm_devinit *base, bool post)
 {
 	struct nv50_devinit *init = nv50_devinit(base);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
index 43a42159a3d0..5d0bab8ecb43 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
@@ -32,6 +32,8 @@ nvkm-y += nvkm/subdev/fb/gp100.o
 nvkm-y += nvkm/subdev/fb/gp102.o
 nvkm-y += nvkm/subdev/fb/gp10b.o
 nvkm-y += nvkm/subdev/fb/gv100.o
+nvkm-y += nvkm/subdev/fb/ga100.o
+nvkm-y += nvkm/subdev/fb/ga102.o
 
 nvkm-y += nvkm/subdev/fb/ram.o
 nvkm-y += nvkm/subdev/fb/ramnv04.o
@@ -52,6 +54,7 @@ nvkm-y += nvkm/subdev/fb/ramgk104.o
 nvkm-y += nvkm/subdev/fb/ramgm107.o
 nvkm-y += nvkm/subdev/fb/ramgm200.o
 nvkm-y += nvkm/subdev/fb/ramgp100.o
+nvkm-y += nvkm/subdev/fb/ramga102.o
 nvkm-y += nvkm/subdev/fb/sddr2.o
 nvkm-y += nvkm/subdev/fb/sddr3.o
 nvkm-y += nvkm/subdev/fb/gddr3.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c
new file mode 100644
index 000000000000..bf82686851cd
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright 2021 Red Hat 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.
+ */
+#include "gf100.h"
+#include "ram.h"
+
+static const struct nvkm_fb_func
+ga100_fb = {
+	.dtor = gf100_fb_dtor,
+	.oneinit = gf100_fb_oneinit,
+	.init = gp100_fb_init,
+	.init_page = gv100_fb_init_page,
+	.init_unkn = gp100_fb_init_unkn,
+	.ram_new = gp100_ram_new,
+	.default_bigpage = 16,
+};
+
+int
+ga100_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+	return gp102_fb_new_(&ga100_fb, device, index, pfb);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c
new file mode 100644
index 000000000000..bcecf84a6e67
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright 2021 Red Hat 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.
+ */
+#include "gf100.h"
+#include "ram.h"
+
+static const struct nvkm_fb_func
+ga102_fb = {
+	.dtor = gf100_fb_dtor,
+	.oneinit = gf100_fb_oneinit,
+	.init = gp100_fb_init,
+	.init_page = gv100_fb_init_page,
+	.init_unkn = gp100_fb_init_unkn,
+	.ram_new = ga102_ram_new,
+	.default_bigpage = 16,
+};
+
+int
+ga102_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+	return gp102_fb_new_(&ga102_fb, device, index, pfb);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
index 10ff5d053f7e..feda86a5fba8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
@@ -22,7 +22,7 @@
 #include "gf100.h"
 #include "ram.h"
 
-static int
+int
 gv100_fb_init_page(struct nvkm_fb *fb)
 {
 	return (fb->page == 16) ? 0 : -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
index 5be9c563350d..66932ac10d15 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
@@ -82,4 +82,6 @@ int gp102_fb_new_(const struct nvkm_fb_func *, struct nvkm_device *, int,
 		  struct nvkm_fb **);
 bool gp102_fb_vpr_scrub_required(struct nvkm_fb *);
 int gp102_fb_vpr_scrub(struct nvkm_fb *);
+
+int gv100_fb_init_page(struct nvkm_fb *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
index d723a9b4e3c4..ea7d66f3dd82 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
@@ -70,4 +70,5 @@ int gk104_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 int gm107_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 int gm200_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 int gp100_ram_new(struct nvkm_fb *, struct nvkm_ram **);
+int ga102_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramga102.c
new file mode 100644
index 000000000000..298c136cefe0
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramga102.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright 2021 Red Hat 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.
+ */
+#include "ram.h"
+
+#include <subdev/bios.h>
+#include <subdev/bios/init.h>
+#include <subdev/bios/rammap.h>
+
+static const struct nvkm_ram_func
+ga102_ram = {
+};
+
+int
+ga102_ram_new(struct nvkm_fb *fb, struct nvkm_ram **pram)
+{
+	struct nvkm_device *device = fb->subdev.device;
+	enum nvkm_ram_type type = nvkm_fb_bios_memtype(device->bios);
+	u32 size = nvkm_rd32(device, 0x1183a4);
+
+	return nvkm_ram_new_(&ga102_ram, fb, type, (u64)size << 20, pram);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
index b2ad5922a1c2..efbbaa080de5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
@@ -5,3 +5,4 @@ nvkm-y += nvkm/subdev/gpio/nv50.o
 nvkm-y += nvkm/subdev/gpio/g94.o
 nvkm-y += nvkm/subdev/gpio/gf119.o
 nvkm-y += nvkm/subdev/gpio/gk104.o
+nvkm-y += nvkm/subdev/gpio/ga102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/ga102.c
new file mode 100644
index 000000000000..62c791baf400
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/ga102.c
@@ -0,0 +1,118 @@
+/*
+ * Copyright 2021 Red Hat 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.
+ */
+#include "priv.h"
+
+static void
+ga102_gpio_reset(struct nvkm_gpio *gpio, u8 match)
+{
+	struct nvkm_device *device = gpio->subdev.device;
+	struct nvkm_bios *bios = device->bios;
+	u8 ver, len;
+	u16 entry;
+	int ent = -1;
+
+	while ((entry = dcb_gpio_entry(bios, 0, ++ent, &ver, &len))) {
+		u32 data = nvbios_rd32(bios, entry);
+		u8  line =   (data & 0x0000003f);
+		u8  defs = !!(data & 0x00000080);
+		u8  func =   (data & 0x0000ff00) >> 8;
+		u8  unk0 =   (data & 0x00ff0000) >> 16;
+		u8  unk1 =   (data & 0x1f000000) >> 24;
+
+		if ( func  == DCB_GPIO_UNUSED ||
+		    (match != DCB_GPIO_UNUSED && match != func))
+			continue;
+
+		nvkm_gpio_set(gpio, 0, func, line, defs);
+
+		nvkm_mask(device, 0x021200 + (line * 4), 0xff, unk0);
+		if (unk1--)
+			nvkm_mask(device, 0x00d740 + (unk1 * 4), 0xff, line);
+	}
+}
+
+static int
+ga102_gpio_drive(struct nvkm_gpio *gpio, int line, int dir, int out)
+{
+	struct nvkm_device *device = gpio->subdev.device;
+	u32 data = ((dir ^ 1) << 13) | (out << 12);
+	nvkm_mask(device, 0x021200 + (line * 4), 0x00003000, data);
+	nvkm_mask(device, 0x00d604, 0x00000001, 0x00000001); /* update? */
+	return 0;
+}
+
+static int
+ga102_gpio_sense(struct nvkm_gpio *gpio, int line)
+{
+	struct nvkm_device *device = gpio->subdev.device;
+	return !!(nvkm_rd32(device, 0x021200 + (line * 4)) & 0x00004000);
+}
+
+static void
+ga102_gpio_intr_stat(struct nvkm_gpio *gpio, u32 *hi, u32 *lo)
+{
+	struct nvkm_device *device = gpio->subdev.device;
+	u32 intr0 = nvkm_rd32(device, 0x021640);
+	u32 intr1 = nvkm_rd32(device, 0x02164c);
+	u32 stat0 = nvkm_rd32(device, 0x021648) & intr0;
+	u32 stat1 = nvkm_rd32(device, 0x021654) & intr1;
+	*lo = (stat1 & 0xffff0000) | (stat0 >> 16);
+	*hi = (stat1 << 16) | (stat0 & 0x0000ffff);
+	nvkm_wr32(device, 0x021640, intr0);
+	nvkm_wr32(device, 0x02164c, intr1);
+}
+
+static void
+ga102_gpio_intr_mask(struct nvkm_gpio *gpio, u32 type, u32 mask, u32 data)
+{
+	struct nvkm_device *device = gpio->subdev.device;
+	u32 inte0 = nvkm_rd32(device, 0x021648);
+	u32 inte1 = nvkm_rd32(device, 0x021654);
+	if (type & NVKM_GPIO_LO)
+		inte0 = (inte0 & ~(mask << 16)) | (data << 16);
+	if (type & NVKM_GPIO_HI)
+		inte0 = (inte0 & ~(mask & 0xffff)) | (data & 0xffff);
+	mask >>= 16;
+	data >>= 16;
+	if (type & NVKM_GPIO_LO)
+		inte1 = (inte1 & ~(mask << 16)) | (data << 16);
+	if (type & NVKM_GPIO_HI)
+		inte1 = (inte1 & ~mask) | data;
+	nvkm_wr32(device, 0x021648, inte0);
+	nvkm_wr32(device, 0x021654, inte1);
+}
+
+static const struct nvkm_gpio_func
+ga102_gpio = {
+	.lines = 32,
+	.intr_stat = ga102_gpio_intr_stat,
+	.intr_mask = ga102_gpio_intr_mask,
+	.drive = ga102_gpio_drive,
+	.sense = ga102_gpio_sense,
+	.reset = ga102_gpio_reset,
+};
+
+int
+ga102_gpio_new(struct nvkm_device *device, int index, struct nvkm_gpio **pgpio)
+{
+	return nvkm_gpio_new_(&ga102_gpio, device, index, pgpio);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
index 723d0284caef..819703913a00 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
@@ -7,6 +7,7 @@ nvkm-y += nvkm/subdev/i2c/g94.o
 nvkm-y += nvkm/subdev/i2c/gf117.o
 nvkm-y += nvkm/subdev/i2c/gf119.o
 nvkm-y += nvkm/subdev/i2c/gk104.o
+nvkm-y += nvkm/subdev/i2c/gk110.o
 nvkm-y += nvkm/subdev/i2c/gm200.o
 
 nvkm-y += nvkm/subdev/i2c/pad.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h
index 30b48896965e..f920eabf8628 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h
@@ -3,6 +3,13 @@
 #define __NVKM_I2C_AUX_H__
 #include "pad.h"
 
+static inline void
+nvkm_i2c_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+	if (i2c->func->aux_autodpcd)
+		i2c->func->aux_autodpcd(i2c, aux, false);
+}
+
 struct nvkm_i2c_aux_func {
 	bool address_only;
 	int  (*xfer)(struct nvkm_i2c_aux *, bool retry, u8 type,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
index db7769cb33eb..47068f6f9c55 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
@@ -77,7 +77,8 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		 u8 type, u32 addr, u8 *data, u8 *size)
 {
 	struct g94_i2c_aux *aux = g94_i2c_aux(obj);
-	struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
+	struct nvkm_i2c *i2c = aux->base.pad->i2c;
+	struct nvkm_device *device = i2c->subdev.device;
 	const u32 base = aux->ch * 0x50;
 	u32 ctrl, stat, timeout, retries = 0;
 	u32 xbuf[4] = {};
@@ -96,6 +97,8 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		goto out;
 	}
 
+	nvkm_i2c_aux_autodpcd(i2c, aux->ch, false);
+
 	if (!(type & 1)) {
 		memcpy(xbuf, data, *size);
 		for (i = 0; i < 16; i += 4) {
@@ -128,7 +131,7 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 			if (!timeout--) {
 				AUX_ERR(&aux->base, "timeout %08x", ctrl);
 				ret = -EIO;
-				goto out;
+				goto out_err;
 			}
 		} while (ctrl & 0x00010000);
 		ret = 0;
@@ -154,7 +157,8 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		memcpy(data, xbuf, *size);
 		*size = stat & 0x0000001f;
 	}
-
+out_err:
+	nvkm_i2c_aux_autodpcd(i2c, aux->ch, true);
 out:
 	g94_i2c_aux_fini(aux);
 	return ret < 0 ? ret : (stat & 0x000f0000) >> 16;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
index edb6148cbca0..8bd1d442e465 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
@@ -33,7 +33,7 @@ static void
 gm200_i2c_aux_fini(struct gm200_i2c_aux *aux)
 {
 	struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
-	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00310000, 0x00000000);
+	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00710000, 0x00000000);
 }
 
 static int
@@ -54,10 +54,10 @@ gm200_i2c_aux_init(struct gm200_i2c_aux *aux)
 			AUX_ERR(&aux->base, "begin idle timeout %08x", ctrl);
 			return -EBUSY;
 		}
-	} while (ctrl & 0x03010000);
+	} while (ctrl & 0x07010000);
 
 	/* set some magic, and wait up to 1ms for it to appear */
-	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00300000, ureq);
+	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00700000, ureq);
 	timeout = 1000;
 	do {
 		ctrl = nvkm_rd32(device, 0x00d954 + (aux->ch * 0x50));
@@ -67,7 +67,7 @@ gm200_i2c_aux_init(struct gm200_i2c_aux *aux)
 			gm200_i2c_aux_fini(aux);
 			return -EBUSY;
 		}
-	} while ((ctrl & 0x03000000) != urep);
+	} while ((ctrl & 0x07000000) != urep);
 
 	return 0;
 }
@@ -77,7 +77,8 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		   u8 type, u32 addr, u8 *data, u8 *size)
 {
 	struct gm200_i2c_aux *aux = gm200_i2c_aux(obj);
-	struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
+	struct nvkm_i2c *i2c = aux->base.pad->i2c;
+	struct nvkm_device *device = i2c->subdev.device;
 	const u32 base = aux->ch * 0x50;
 	u32 ctrl, stat, timeout, retries = 0;
 	u32 xbuf[4] = {};
@@ -96,6 +97,8 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		goto out;
 	}
 
+	nvkm_i2c_aux_autodpcd(i2c, aux->ch, false);
+
 	if (!(type & 1)) {
 		memcpy(xbuf, data, *size);
 		for (i = 0; i < 16; i += 4) {
@@ -128,7 +131,7 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 			if (!timeout--) {
 				AUX_ERR(&aux->base, "timeout %08x", ctrl);
 				ret = -EIO;
-				goto out;
+				goto out_err;
 			}
 		} while (ctrl & 0x00010000);
 		ret = 0;
@@ -155,6 +158,8 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		*size = stat & 0x0000001f;
 	}
 
+out_err:
+	nvkm_i2c_aux_autodpcd(i2c, aux->ch, true);
 out:
 	gm200_i2c_aux_fini(aux);
 	return ret < 0 ? ret : (stat & 0x000f0000) >> 16;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gk110.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gk110.c
new file mode 100644
index 000000000000..8e3bfa1af52a
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gk110.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2021 Red Hat 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.
+ */
+#include "priv.h"
+#include "pad.h"
+
+static void
+gk110_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+	nvkm_mask(i2c->subdev.device, 0x00e4f8 + (aux * 0x50), 0x00010000, enable << 16);
+}
+
+static const struct nvkm_i2c_func
+gk110_i2c = {
+	.pad_x_new = gf119_i2c_pad_x_new,
+	.pad_s_new = gf119_i2c_pad_s_new,
+	.aux = 4,
+	.aux_stat = gk104_aux_stat,
+	.aux_mask = gk104_aux_mask,
+	.aux_autodpcd = gk110_aux_autodpcd,
+};
+
+int
+gk110_i2c_new(struct nvkm_device *device, int index, struct nvkm_i2c **pi2c)
+{
+	return nvkm_i2c_new_(&gk110_i2c, device, index, pi2c);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c
index a23c5f315221..7b2375bff8a9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c
@@ -24,6 +24,12 @@
 #include "priv.h"
 #include "pad.h"
 
+static void
+gm200_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+	nvkm_mask(i2c->subdev.device, 0x00d968 + (aux * 0x50), 0x00010000, enable << 16);
+}
+
 static const struct nvkm_i2c_func
 gm200_i2c = {
 	.pad_x_new = gf119_i2c_pad_x_new,
@@ -31,6 +37,7 @@ gm200_i2c = {
 	.aux = 8,
 	.aux_stat = gk104_aux_stat,
 	.aux_mask = gk104_aux_mask,
+	.aux_autodpcd = gm200_aux_autodpcd,
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h
index 461016814f4f..44b7bb7d4777 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: MIT */
 #ifndef __NVKM_I2C_PAD_H__
 #define __NVKM_I2C_PAD_H__
-#include <subdev/i2c.h>
+#include "priv.h"
 
 struct nvkm_i2c_pad {
 	const struct nvkm_i2c_pad_func *func;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h
index bd86bc298ebe..e35f6036fcfc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h
@@ -23,6 +23,10 @@ struct nvkm_i2c_func {
 	/* mask on/off interrupt types for a given set of auxch
 	 */
 	void (*aux_mask)(struct nvkm_i2c *, u32, u32, u32);
+
+	/* enable/disable HW-initiated DPCD reads
+	 */
+	void (*aux_autodpcd)(struct nvkm_i2c *, int aux, bool enable);
 };
 
 void g94_aux_stat(struct nvkm_i2c *, u32 *, u32 *, u32 *, u32 *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
index 2340040942c9..1115376bc85f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
@@ -22,6 +22,7 @@
  * Authors: Ben Skeggs
  */
 #include "priv.h"
+#include <subdev/timer.h>
 
 static void
 gf100_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
@@ -31,7 +32,6 @@ gf100_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x122124 + (i * 0x0400));
 	u32 stat = nvkm_rd32(device, 0x122128 + (i * 0x0400));
 	nvkm_debug(ibus, "HUB%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x122128 + (i * 0x0400), 0x00000200, 0x00000000);
 }
 
 static void
@@ -42,7 +42,6 @@ gf100_ibus_intr_rop(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x124124 + (i * 0x0400));
 	u32 stat = nvkm_rd32(device, 0x124128 + (i * 0x0400));
 	nvkm_debug(ibus, "ROP%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x124128 + (i * 0x0400), 0x00000200, 0x00000000);
 }
 
 static void
@@ -53,7 +52,6 @@ gf100_ibus_intr_gpc(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x128124 + (i * 0x0400));
 	u32 stat = nvkm_rd32(device, 0x128128 + (i * 0x0400));
 	nvkm_debug(ibus, "GPC%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x128128 + (i * 0x0400), 0x00000200, 0x00000000);
 }
 
 void
@@ -90,6 +88,12 @@ gf100_ibus_intr(struct nvkm_subdev *ibus)
 			intr1 &= ~stat;
 		}
 	}
+
+	nvkm_mask(device, 0x121c4c, 0x0000003f, 0x00000002);
+	nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x121c4c) & 0x0000003f))
+			break;
+	);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
index f3915f85838e..22e487b493ad 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
@@ -22,6 +22,7 @@
  * Authors: Ben Skeggs
  */
 #include "priv.h"
+#include <subdev/timer.h>
 
 static void
 gk104_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
@@ -31,7 +32,6 @@ gk104_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x122124 + (i * 0x0800));
 	u32 stat = nvkm_rd32(device, 0x122128 + (i * 0x0800));
 	nvkm_debug(ibus, "HUB%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x122128 + (i * 0x0800), 0x00000200, 0x00000000);
 }
 
 static void
@@ -42,7 +42,6 @@ gk104_ibus_intr_rop(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x124124 + (i * 0x0800));
 	u32 stat = nvkm_rd32(device, 0x124128 + (i * 0x0800));
 	nvkm_debug(ibus, "ROP%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x124128 + (i * 0x0800), 0x00000200, 0x00000000);
 }
 
 static void
@@ -53,7 +52,6 @@ gk104_ibus_intr_gpc(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x128124 + (i * 0x0800));
 	u32 stat = nvkm_rd32(device, 0x128128 + (i * 0x0800));
 	nvkm_debug(ibus, "GPC%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x128128 + (i * 0x0800), 0x00000200, 0x00000000);
 }
 
 void
@@ -90,6 +88,12 @@ gk104_ibus_intr(struct nvkm_subdev *ibus)
 			intr1 &= ~stat;
 		}
 	}
+
+	nvkm_mask(device, 0x12004c, 0x0000003f, 0x00000002);
+	nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x12004c) & 0x0000003f))
+			break;
+	);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
index 2585ef07532a..ac2b34e9ac6a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
@@ -14,3 +14,4 @@ nvkm-y += nvkm/subdev/mc/gk20a.o
 nvkm-y += nvkm/subdev/mc/gp100.o
 nvkm-y += nvkm/subdev/mc/gp10b.o
 nvkm-y += nvkm/subdev/mc/tu102.o
+nvkm-y += nvkm/subdev/mc/ga100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/ga100.c
new file mode 100644
index 000000000000..967eb3af11eb
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/ga100.c
@@ -0,0 +1,74 @@
+/*
+ * Copyright 2021 Red Hat 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.
+ */
+#include "priv.h"
+
+static void
+ga100_mc_intr_unarm(struct nvkm_mc *mc)
+{
+	nvkm_wr32(mc->subdev.device, 0xb81610, 0x00000004);
+}
+
+static void
+ga100_mc_intr_rearm(struct nvkm_mc *mc)
+{
+	nvkm_wr32(mc->subdev.device, 0xb81608, 0x00000004);
+}
+
+static void
+ga100_mc_intr_mask(struct nvkm_mc *mc, u32 mask, u32 intr)
+{
+	nvkm_wr32(mc->subdev.device, 0xb81210,          mask & intr );
+	nvkm_wr32(mc->subdev.device, 0xb81410, mask & ~(mask & intr));
+}
+
+static u32
+ga100_mc_intr_stat(struct nvkm_mc *mc)
+{
+	u32 intr_top = nvkm_rd32(mc->subdev.device, 0xb81600), intr = 0x00000000;
+	if (intr_top & 0x00000004)
+		intr = nvkm_mask(mc->subdev.device, 0xb81010, 0x00000000, 0x00000000);
+	return intr;
+}
+
+static void
+ga100_mc_init(struct nvkm_mc *mc)
+{
+	nv50_mc_init(mc);
+	nvkm_wr32(mc->subdev.device, 0xb81210, 0xffffffff);
+}
+
+static const struct nvkm_mc_func
+ga100_mc = {
+	.init = ga100_mc_init,
+	.intr = gp100_mc_intr,
+	.intr_unarm = ga100_mc_intr_unarm,
+	.intr_rearm = ga100_mc_intr_rearm,
+	.intr_mask = ga100_mc_intr_mask,
+	.intr_stat = ga100_mc_intr_stat,
+	.reset = gk104_mc_reset,
+};
+
+int
+ga100_mc_new(struct nvkm_device *device, int index, struct nvkm_mc **pmc)
+{
+	return nvkm_mc_new_(&ga100_mc, device, index, pmc);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
index de91e9a26172..6d5212ae2fd5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
@@ -316,9 +316,9 @@ nvkm_mmu_vram(struct nvkm_mmu *mmu)
 {
 	struct nvkm_device *device = mmu->subdev.device;
 	struct nvkm_mm *mm = &device->fb->ram->vram;
-	const u32 sizeN = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NORMAL);
-	const u32 sizeU = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NOMAP);
-	const u32 sizeM = nvkm_mm_heap_size(mm, NVKM_RAM_MM_MIXED);
+	const u64 sizeN = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NORMAL);
+	const u64 sizeU = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NOMAP);
+	const u64 sizeM = nvkm_mm_heap_size(mm, NVKM_RAM_MM_MIXED);
 	u8 type = NVKM_MEM_KIND * !!mmu->func->kind;
 	u8 heap = NVKM_MEM_VRAM;
 	int heapM, heapN, heapU;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index d59ef6e92a40..23195d5d4e91 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -730,9 +730,6 @@ int radeon_ttm_init(struct radeon_device *rdev)
 	}
 	rdev->mman.initialized = true;
 
-	ttm_pool_init(&rdev->mman.bdev.pool, rdev->dev, rdev->need_swiotlb,
-		      dma_addressing_limited(&rdev->pdev->dev));
-
 	r = radeon_ttm_init_vram(rdev);
 	if (r) {
 		DRM_ERROR("Failed initializing VRAM heap.\n");
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 5455b2044759..8cd776adc592 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -66,7 +66,7 @@ static struct ttm_pool_type global_uncached[MAX_ORDER];
 static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER];
 static struct ttm_pool_type global_dma32_uncached[MAX_ORDER];
 
-static spinlock_t shrinker_lock;
+static struct mutex shrinker_lock;
 static struct list_head shrinker_list;
 static struct shrinker mm_shrinker;
 
@@ -190,7 +190,7 @@ static int ttm_pool_map(struct ttm_pool *pool, unsigned int order,
 		size_t size = (1ULL << order) * PAGE_SIZE;
 
 		addr = dma_map_page(pool->dev, p, 0, size, DMA_BIDIRECTIONAL);
-		if (dma_mapping_error(pool->dev, **dma_addr))
+		if (dma_mapping_error(pool->dev, addr))
 			return -EFAULT;
 	}
 
@@ -239,21 +239,6 @@ static struct page *ttm_pool_type_take(struct ttm_pool_type *pt)
 	return p;
 }
 
-/* Count the number of pages available in a pool_type */
-static unsigned int ttm_pool_type_count(struct ttm_pool_type *pt)
-{
-	unsigned int count = 0;
-	struct page *p;
-
-	spin_lock(&pt->lock);
-	/* Only used for debugfs, the overhead doesn't matter */
-	list_for_each_entry(p, &pt->pages, lru)
-		++count;
-	spin_unlock(&pt->lock);
-
-	return count;
-}
-
 /* Initialize and add a pool type to the global shrinker list */
 static void ttm_pool_type_init(struct ttm_pool_type *pt, struct ttm_pool *pool,
 			       enum ttm_caching caching, unsigned int order)
@@ -264,9 +249,9 @@ static void ttm_pool_type_init(struct ttm_pool_type *pt, struct ttm_pool *pool,
 	spin_lock_init(&pt->lock);
 	INIT_LIST_HEAD(&pt->pages);
 
-	spin_lock(&shrinker_lock);
+	mutex_lock(&shrinker_lock);
 	list_add_tail(&pt->shrinker_list, &shrinker_list);
-	spin_unlock(&shrinker_lock);
+	mutex_unlock(&shrinker_lock);
 }
 
 /* Remove a pool_type from the global shrinker list and free all pages */
@@ -274,9 +259,9 @@ static void ttm_pool_type_fini(struct ttm_pool_type *pt)
 {
 	struct page *p, *tmp;
 
-	spin_lock(&shrinker_lock);
+	mutex_lock(&shrinker_lock);
 	list_del(&pt->shrinker_list);
-	spin_unlock(&shrinker_lock);
+	mutex_unlock(&shrinker_lock);
 
 	list_for_each_entry_safe(p, tmp, &pt->pages, lru)
 		ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
@@ -317,7 +302,7 @@ static unsigned int ttm_pool_shrink(void)
 	unsigned int num_freed;
 	struct page *p;
 
-	spin_lock(&shrinker_lock);
+	mutex_lock(&shrinker_lock);
 	pt = list_first_entry(&shrinker_list, typeof(*pt), shrinker_list);
 
 	p = ttm_pool_type_take(pt);
@@ -329,7 +314,7 @@ static unsigned int ttm_pool_shrink(void)
 	}
 
 	list_move_tail(&pt->shrinker_list, &shrinker_list);
-	spin_unlock(&shrinker_lock);
+	mutex_unlock(&shrinker_lock);
 
 	return num_freed;
 }
@@ -522,7 +507,6 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
 			ttm_pool_type_init(&pool->caching[i].orders[j],
 					   pool, i, j);
 }
-EXPORT_SYMBOL(ttm_pool_init);
 
 /**
  * ttm_pool_fini - Cleanup a pool
@@ -540,9 +524,22 @@ void ttm_pool_fini(struct ttm_pool *pool)
 		for (j = 0; j < MAX_ORDER; ++j)
 			ttm_pool_type_fini(&pool->caching[i].orders[j]);
 }
-EXPORT_SYMBOL(ttm_pool_fini);
 
 #ifdef CONFIG_DEBUG_FS
+/* Count the number of pages available in a pool_type */
+static unsigned int ttm_pool_type_count(struct ttm_pool_type *pt)
+{
+	unsigned int count = 0;
+	struct page *p;
+
+	spin_lock(&pt->lock);
+	/* Only used for debugfs, the overhead doesn't matter */
+	list_for_each_entry(p, &pt->pages, lru)
+		++count;
+	spin_unlock(&pt->lock);
+
+	return count;
+}
 
 /* Dump information about the different pool types */
 static void ttm_pool_debugfs_orders(struct ttm_pool_type *pt,
@@ -567,7 +564,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
 {
 	unsigned int i;
 
-	spin_lock(&shrinker_lock);
+	mutex_lock(&shrinker_lock);
 
 	seq_puts(m, "\t ");
 	for (i = 0; i < MAX_ORDER; ++i)
@@ -603,7 +600,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
 	seq_printf(m, "\ntotal\t: %8lu of %8lu\n",
 		   atomic_long_read(&allocated_pages), page_pool_size);
 
-	spin_unlock(&shrinker_lock);
+	mutex_unlock(&shrinker_lock);
 
 	return 0;
 }
@@ -647,7 +644,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
 	if (!page_pool_size)
 		page_pool_size = num_pages;
 
-	spin_lock_init(&shrinker_lock);
+	mutex_init(&shrinker_lock);
 	INIT_LIST_HEAD(&shrinker_list);
 
 	for (i = 0; i < MAX_ORDER; ++i) {
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 7bdda1b5b221..09fa75a2b289 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -899,6 +899,7 @@ config HID_SONY
 	depends on NEW_LEDS
 	depends on LEDS_CLASS
 	select POWER_SUPPLY
+	select CRC32
 	help
 	Support for
 
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c
index 3d1ccac5d99a..2ab38b715347 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c
@@ -154,7 +154,7 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata)
 
 	for (i = 0; i < cl_data->num_hid_devices; i++) {
 		cl_data->sensor_virt_addr[i] = dma_alloc_coherent(dev, sizeof(int) * 8,
-								  &cl_data->sensor_phys_addr[i],
+								  &cl_data->sensor_dma_addr[i],
 								  GFP_KERNEL);
 		cl_data->sensor_sts[i] = 0;
 		cl_data->sensor_requested_cnt[i] = 0;
@@ -187,7 +187,7 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata)
 		}
 		info.period = msecs_to_jiffies(AMD_SFH_IDLE_LOOP);
 		info.sensor_idx = cl_idx;
-		info.phys_address = cl_data->sensor_phys_addr[i];
+		info.dma_address = cl_data->sensor_dma_addr[i];
 
 		cl_data->report_descr[i] = kzalloc(cl_data->report_descr_sz[i], GFP_KERNEL);
 		if (!cl_data->report_descr[i]) {
@@ -212,7 +212,7 @@ cleanup:
 		if (cl_data->sensor_virt_addr[i]) {
 			dma_free_coherent(&privdata->pdev->dev, 8 * sizeof(int),
 					  cl_data->sensor_virt_addr[i],
-					  cl_data->sensor_phys_addr[i]);
+					  cl_data->sensor_dma_addr[i]);
 		}
 		kfree(cl_data->feature_report[i]);
 		kfree(cl_data->input_report[i]);
@@ -238,7 +238,7 @@ int amd_sfh_hid_client_deinit(struct amd_mp2_dev *privdata)
 		if (cl_data->sensor_virt_addr[i]) {
 			dma_free_coherent(&privdata->pdev->dev, 8 * sizeof(int),
 					  cl_data->sensor_virt_addr[i],
-					  cl_data->sensor_phys_addr[i]);
+					  cl_data->sensor_dma_addr[i]);
 		}
 	}
 	kfree(cl_data);
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_hid.h b/drivers/hid/amd-sfh-hid/amd_sfh_hid.h
index 6be0783d885c..d7eac1728e31 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_hid.h
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_hid.h
@@ -27,7 +27,7 @@ struct amdtp_cl_data {
 	int hid_descr_size[MAX_HID_DEVICES];
 	phys_addr_t phys_addr_base;
 	u32 *sensor_virt_addr[MAX_HID_DEVICES];
-	phys_addr_t sensor_phys_addr[MAX_HID_DEVICES];
+	dma_addr_t sensor_dma_addr[MAX_HID_DEVICES];
 	u32 sensor_sts[MAX_HID_DEVICES];
 	u32 sensor_requested_cnt[MAX_HID_DEVICES];
 	u8 report_type[MAX_HID_DEVICES];
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index a51c7b76283b..dbac16641662 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -41,7 +41,7 @@ void amd_start_sensor(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info i
 	cmd_param.s.buf_layout = 1;
 	cmd_param.s.buf_length = 16;
 
-	writeq(info.phys_address, privdata->mmio + AMD_C2P_MSG2);
+	writeq(info.dma_address, privdata->mmio + AMD_C2P_MSG2);
 	writel(cmd_param.ul, privdata->mmio + AMD_C2P_MSG1);
 	writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0);
 }
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h
index e8be94f935b7..8f8d19b2cfe5 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h
@@ -67,7 +67,7 @@ struct amd_mp2_dev {
 struct amd_mp2_sensor_info {
 	u8 sensor_idx;
 	u32 period;
-	phys_addr_t phys_address;
+	dma_addr_t dma_address;
 };
 
 void amd_start_sensor(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info info);
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 4c5f23640f9c..5ba0aa1d2335 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -389,6 +389,7 @@
 #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W	0x0401
 #define USB_DEVICE_ID_HP_X2		0x074d
 #define USB_DEVICE_ID_HP_X2_10_COVER	0x0755
+#define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN	0x2706
 
 #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 dc7f6b4a775c..f23027d2795b 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -322,6 +322,8 @@ static const struct hid_device_id hid_battery_quirks[] = {
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH,
 		USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD),
 	  HID_BATTERY_QUIRK_IGNORE },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN),
+	  HID_BATTERY_QUIRK_IGNORE },
 	{}
 };
 
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 1ffcfc9a1e03..45e7e0bdd382 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -1869,6 +1869,10 @@ static const struct hid_device_id logi_dj_receivers[] = {
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
 		0xc531),
 	 .driver_data = recvr_type_gaming_hidpp},
+	{ /* Logitech G602 receiver (0xc537) */
+	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
+		0xc537),
+	 .driver_data = recvr_type_gaming_hidpp},
 	{ /* Logitech lightspeed receiver (0xc539) */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
 		USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1),
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index f85781464807..7eb9a6ddb46a 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -4053,6 +4053,8 @@ static const struct hid_device_id hidpp_devices[] = {
 	{ /* MX Master mouse over Bluetooth */
 	  HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb012),
 	  .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 },
+	{ /* MX Ergo trackball over Bluetooth */
+	  HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb01d) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb01e),
 	  .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 },
 	{ /* MX Master 3 mouse over Bluetooth */
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index d670bcd57bde..0743ef51d3b2 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -2054,6 +2054,10 @@ static const struct hid_device_id mt_devices[] = {
 		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
 			USB_VENDOR_ID_SYNAPTICS, 0xce08) },
 
+	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_SYNAPTICS, 0xce09) },
+
 	/* TopSeed panels */
 	{ .driver_data = MT_CLS_TOPSEED,
 		MT_USB_DEVICE(USB_VENDOR_ID_TOPSEED2,
diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c
index d26d8cd98efc..56406cee401f 100644
--- a/drivers/hid/hid-uclogic-params.c
+++ b/drivers/hid/hid-uclogic-params.c
@@ -90,7 +90,7 @@ static int uclogic_params_get_str_desc(__u8 **pbuf, struct hid_device *hdev,
 		goto cleanup;
 	} else if (rc < 0) {
 		hid_err(hdev,
-			"failed retrieving string descriptor #%hhu: %d\n",
+			"failed retrieving string descriptor #%u: %d\n",
 			idx, rc);
 		goto cleanup;
 	}
diff --git a/drivers/hid/hid-wiimote-core.c b/drivers/hid/hid-wiimote-core.c
index 41012681cafd..4399d6c6afef 100644
--- a/drivers/hid/hid-wiimote-core.c
+++ b/drivers/hid/hid-wiimote-core.c
@@ -1482,7 +1482,7 @@ static void handler_return(struct wiimote_data *wdata, const __u8 *payload)
 		wdata->state.cmd_err = err;
 		wiimote_cmd_complete(wdata);
 	} else if (err) {
-		hid_warn(wdata->hdev, "Remote error %hhu on req %hhu\n", err,
+		hid_warn(wdata->hdev, "Remote error %u on req %u\n", err,
 									cmd);
 	}
 }
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 045c464228d9..e8acd235db2a 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -1270,6 +1270,37 @@ static int wacom_devm_sysfs_create_group(struct wacom *wacom,
 					       group);
 }
 
+static void wacom_devm_kfifo_release(struct device *dev, void *res)
+{
+	struct kfifo_rec_ptr_2 *devres = res;
+
+	kfifo_free(devres);
+}
+
+static int wacom_devm_kfifo_alloc(struct wacom *wacom)
+{
+	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+	struct kfifo_rec_ptr_2 *pen_fifo = &wacom_wac->pen_fifo;
+	int error;
+
+	pen_fifo = devres_alloc(wacom_devm_kfifo_release,
+			      sizeof(struct kfifo_rec_ptr_2),
+			      GFP_KERNEL);
+
+	if (!pen_fifo)
+		return -ENOMEM;
+
+	error = kfifo_alloc(pen_fifo, WACOM_PKGLEN_MAX, GFP_KERNEL);
+	if (error) {
+		devres_free(pen_fifo);
+		return error;
+	}
+
+	devres_add(&wacom->hdev->dev, pen_fifo);
+
+	return 0;
+}
+
 enum led_brightness wacom_leds_brightness_get(struct wacom_led *led)
 {
 	struct wacom *wacom = led->wacom;
@@ -2724,7 +2755,7 @@ static int wacom_probe(struct hid_device *hdev,
 	if (features->check_for_hid_type && features->hid_type != hdev->type)
 		return -ENODEV;
 
-	error = kfifo_alloc(&wacom_wac->pen_fifo, WACOM_PKGLEN_MAX, GFP_KERNEL);
+	error = wacom_devm_kfifo_alloc(wacom);
 	if (error)
 		return error;
 
@@ -2786,8 +2817,6 @@ static void wacom_remove(struct hid_device *hdev)
 
 	if (wacom->wacom_wac.features.type != REMOTE)
 		wacom_release_resources(wacom);
-
-	kfifo_free(&wacom_wac->pen_fifo);
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 502f8cd95f6d..d491fdcee61f 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2550,7 +2550,6 @@ static void hv_kexec_handler(void)
 	/* Make sure conn_state is set as hv_synic_cleanup checks for it */
 	mb();
 	cpuhp_remove_state(hyperv_cpuhp_online);
-	hyperv_cleanup();
 };
 
 static void hv_crash_handler(struct pt_regs *regs)
@@ -2566,7 +2565,6 @@ static void hv_crash_handler(struct pt_regs *regs)
 	cpu = smp_processor_id();
 	hv_stimer_cleanup(cpu);
 	hv_synic_disable_regs(cpu);
-	hyperv_cleanup();
 };
 
 static int hv_synic_suspend(void)
diff --git a/drivers/hwmon/amd_energy.c b/drivers/hwmon/amd_energy.c
index 9b306448b7a0..822c2e74b98d 100644
--- a/drivers/hwmon/amd_energy.c
+++ b/drivers/hwmon/amd_energy.c
@@ -222,7 +222,7 @@ static int amd_create_sensor(struct device *dev,
 	 */
 	cpus = num_present_cpus() / num_siblings;
 
-	s_config = devm_kcalloc(dev, cpus + sockets,
+	s_config = devm_kcalloc(dev, cpus + sockets + 1,
 				sizeof(u32), GFP_KERNEL);
 	if (!s_config)
 		return -ENOMEM;
@@ -254,6 +254,7 @@ static int amd_create_sensor(struct device *dev,
 			scnprintf(label_l[i], 10, "Esocket%u", (i - cpus));
 	}
 
+	s_config[i] = 0;
 	return 0;
 }
 
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index a250481b5a97..3bc2551577a3 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -11,13 +11,6 @@
  *   convert raw register values is from https://github.com/ocerman/zenpower.
  *   The information is not confirmed from chip datasheets, but experiments
  *   suggest that it provides reasonable temperature values.
- * - Register addresses to read chip voltage and current are also from
- *   https://github.com/ocerman/zenpower, and not confirmed from chip
- *   datasheets. Current calibration is board specific and not typically
- *   shared by board vendors. For this reason, current values are
- *   normalized to report 1A/LSB for core current and and 0.25A/LSB for SoC
- *   current. Reported values can be adjusted using the sensors configuration
- *   file.
  */
 
 #include <linux/bitops.h>
@@ -109,10 +102,7 @@ struct k10temp_data {
 	int temp_offset;
 	u32 temp_adjust_mask;
 	u32 show_temp;
-	u32 svi_addr[2];
 	bool is_zen;
-	bool show_current;
-	int cfactor[2];
 };
 
 #define TCTL_BIT	0
@@ -137,16 +127,6 @@ static const struct tctl_offset tctl_offset_table[] = {
 	{ 0x17, "AMD Ryzen Threadripper 29", 27000 }, /* 29{20,50,70,90}[W]X */
 };
 
-static bool is_threadripper(void)
-{
-	return strstr(boot_cpu_data.x86_model_id, "Threadripper");
-}
-
-static bool is_epyc(void)
-{
-	return strstr(boot_cpu_data.x86_model_id, "EPYC");
-}
-
 static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval)
 {
 	pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL, regval);
@@ -211,16 +191,6 @@ static const char *k10temp_temp_label[] = {
 	"Tccd8",
 };
 
-static const char *k10temp_in_label[] = {
-	"Vcore",
-	"Vsoc",
-};
-
-static const char *k10temp_curr_label[] = {
-	"Icore",
-	"Isoc",
-};
-
 static int k10temp_read_labels(struct device *dev,
 			       enum hwmon_sensor_types type,
 			       u32 attr, int channel, const char **str)
@@ -229,50 +199,6 @@ static int k10temp_read_labels(struct device *dev,
 	case hwmon_temp:
 		*str = k10temp_temp_label[channel];
 		break;
-	case hwmon_in:
-		*str = k10temp_in_label[channel];
-		break;
-	case hwmon_curr:
-		*str = k10temp_curr_label[channel];
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
-static int k10temp_read_curr(struct device *dev, u32 attr, int channel,
-			     long *val)
-{
-	struct k10temp_data *data = dev_get_drvdata(dev);
-	u32 regval;
-
-	switch (attr) {
-	case hwmon_curr_input:
-		amd_smn_read(amd_pci_dev_to_node_id(data->pdev),
-			     data->svi_addr[channel], &regval);
-		*val = DIV_ROUND_CLOSEST(data->cfactor[channel] *
-					 (regval & 0xff),
-					 1000);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
-static int k10temp_read_in(struct device *dev, u32 attr, int channel, long *val)
-{
-	struct k10temp_data *data = dev_get_drvdata(dev);
-	u32 regval;
-
-	switch (attr) {
-	case hwmon_in_input:
-		amd_smn_read(amd_pci_dev_to_node_id(data->pdev),
-			     data->svi_addr[channel], &regval);
-		regval = (regval >> 16) & 0xff;
-		*val = DIV_ROUND_CLOSEST(155000 - regval * 625, 100);
-		break;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -331,10 +257,6 @@ static int k10temp_read(struct device *dev, enum hwmon_sensor_types type,
 	switch (type) {
 	case hwmon_temp:
 		return k10temp_read_temp(dev, attr, channel, val);
-	case hwmon_in:
-		return k10temp_read_in(dev, attr, channel, val);
-	case hwmon_curr:
-		return k10temp_read_curr(dev, attr, channel, val);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -383,11 +305,6 @@ static umode_t k10temp_is_visible(const void *_data,
 			return 0;
 		}
 		break;
-	case hwmon_in:
-	case hwmon_curr:
-		if (!data->show_current)
-			return 0;
-		break;
 	default:
 		return 0;
 	}
@@ -517,20 +434,10 @@ static int k10temp_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		case 0x8:	/* Zen+ */
 		case 0x11:	/* Zen APU */
 		case 0x18:	/* Zen+ APU */
-			data->show_current = !is_threadripper() && !is_epyc();
-			data->svi_addr[0] = F17H_M01H_SVI_TEL_PLANE0;
-			data->svi_addr[1] = F17H_M01H_SVI_TEL_PLANE1;
-			data->cfactor[0] = F17H_M01H_CFACTOR_ICORE;
-			data->cfactor[1] = F17H_M01H_CFACTOR_ISOC;
 			k10temp_get_ccd_support(pdev, data, 4);
 			break;
 		case 0x31:	/* Zen2 Threadripper */
 		case 0x71:	/* Zen2 */
-			data->show_current = !is_threadripper() && !is_epyc();
-			data->cfactor[0] = F17H_M31H_CFACTOR_ICORE;
-			data->cfactor[1] = F17H_M31H_CFACTOR_ISOC;
-			data->svi_addr[0] = F17H_M31H_SVI_TEL_PLANE0;
-			data->svi_addr[1] = F17H_M31H_SVI_TEL_PLANE1;
 			k10temp_get_ccd_support(pdev, data, 8);
 			break;
 		}
@@ -542,11 +449,6 @@ static int k10temp_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 		switch (boot_cpu_data.x86_model) {
 		case 0x0 ... 0x1:	/* Zen3 */
-			data->show_current = true;
-			data->svi_addr[0] = F19H_M01_SVI_TEL_PLANE0;
-			data->svi_addr[1] = F19H_M01_SVI_TEL_PLANE1;
-			data->cfactor[0] = F19H_M01H_CFACTOR_ICORE;
-			data->cfactor[1] = F19H_M01H_CFACTOR_ISOC;
 			k10temp_get_ccd_support(pdev, data, 8);
 			break;
 		}
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index 777439f48c14..111a91dc6b79 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -334,8 +334,18 @@ static int pwm_fan_probe(struct platform_device *pdev)
 
 	ctx->pwm_value = MAX_PWM;
 
-	/* Set duty cycle to maximum allowed and enable PWM output */
 	pwm_init_state(ctx->pwm, &state);
+	/*
+	 * __set_pwm assumes that MAX_PWM * (period - 1) fits into an unsigned
+	 * long. Check this here to prevent the fan running at a too low
+	 * frequency.
+	 */
+	if (state.period > ULONG_MAX / MAX_PWM + 1) {
+		dev_err(dev, "Configured period too big\n");
+		return -EINVAL;
+	}
+
+	/* Set duty cycle to maximum allowed and enable PWM output */
 	state.duty_cycle = ctx->pwm->args.period - 1;
 	state.enabled = true;
 
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index ae90713443fa..877fe3733a42 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1449,7 +1449,7 @@ static int i801_add_mux(struct i801_priv *priv)
 
 	/* Register GPIO descriptor lookup table */
 	lookup = devm_kzalloc(dev,
-			      struct_size(lookup, table, mux_config->n_gpios),
+			      struct_size(lookup, table, mux_config->n_gpios + 1),
 			      GFP_KERNEL);
 	if (!lookup)
 		return -ENOMEM;
diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index 33de99b7bc20..0818d3e50734 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -38,6 +38,7 @@
 #define I2C_IO_CONFIG_OPEN_DRAIN	0x0003
 #define I2C_IO_CONFIG_PUSH_PULL		0x0000
 #define I2C_SOFT_RST			0x0001
+#define I2C_HANDSHAKE_RST		0x0020
 #define I2C_FIFO_ADDR_CLR		0x0001
 #define I2C_DELAY_LEN			0x0002
 #define I2C_TIME_CLR_VALUE		0x0000
@@ -45,6 +46,7 @@
 #define I2C_WRRD_TRANAC_VALUE		0x0002
 #define I2C_RD_TRANAC_VALUE		0x0001
 #define I2C_SCL_MIS_COMP_VALUE		0x0000
+#define I2C_CHN_CLR_FLAG		0x0000
 
 #define I2C_DMA_CON_TX			0x0000
 #define I2C_DMA_CON_RX			0x0001
@@ -54,7 +56,9 @@
 #define I2C_DMA_START_EN		0x0001
 #define I2C_DMA_INT_FLAG_NONE		0x0000
 #define I2C_DMA_CLR_FLAG		0x0000
+#define I2C_DMA_WARM_RST		0x0001
 #define I2C_DMA_HARD_RST		0x0002
+#define I2C_DMA_HANDSHAKE_RST		0x0004
 
 #define MAX_SAMPLE_CNT_DIV		8
 #define MAX_STEP_CNT_DIV		64
@@ -475,11 +479,24 @@ static void mtk_i2c_init_hw(struct mtk_i2c *i2c)
 {
 	u16 control_reg;
 
-	writel(I2C_DMA_HARD_RST, i2c->pdmabase + OFFSET_RST);
-	udelay(50);
-	writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
-
-	mtk_i2c_writew(i2c, I2C_SOFT_RST, OFFSET_SOFTRESET);
+	if (i2c->dev_comp->dma_sync) {
+		writel(I2C_DMA_WARM_RST, i2c->pdmabase + OFFSET_RST);
+		udelay(10);
+		writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
+		udelay(10);
+		writel(I2C_DMA_HANDSHAKE_RST | I2C_DMA_HARD_RST,
+		       i2c->pdmabase + OFFSET_RST);
+		mtk_i2c_writew(i2c, I2C_HANDSHAKE_RST | I2C_SOFT_RST,
+			       OFFSET_SOFTRESET);
+		udelay(10);
+		writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
+		mtk_i2c_writew(i2c, I2C_CHN_CLR_FLAG, OFFSET_SOFTRESET);
+	} else {
+		writel(I2C_DMA_HARD_RST, i2c->pdmabase + OFFSET_RST);
+		udelay(50);
+		writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
+		mtk_i2c_writew(i2c, I2C_SOFT_RST, OFFSET_SOFTRESET);
+	}
 
 	/* Set ioconfig */
 	if (i2c->use_push_pull)
diff --git a/drivers/i2c/busses/i2c-sprd.c b/drivers/i2c/busses/i2c-sprd.c
index 19cda6742423..2917fecf6c80 100644
--- a/drivers/i2c/busses/i2c-sprd.c
+++ b/drivers/i2c/busses/i2c-sprd.c
@@ -72,6 +72,8 @@
 
 /* timeout (ms) for pm runtime autosuspend */
 #define SPRD_I2C_PM_TIMEOUT	1000
+/* timeout (ms) for transfer message */
+#define I2C_XFER_TIMEOUT	1000
 
 /* SPRD i2c data structure */
 struct sprd_i2c {
@@ -244,6 +246,7 @@ static int sprd_i2c_handle_msg(struct i2c_adapter *i2c_adap,
 			       struct i2c_msg *msg, bool is_last_msg)
 {
 	struct sprd_i2c *i2c_dev = i2c_adap->algo_data;
+	unsigned long time_left;
 
 	i2c_dev->msg = msg;
 	i2c_dev->buf = msg->buf;
@@ -273,7 +276,10 @@ static int sprd_i2c_handle_msg(struct i2c_adapter *i2c_adap,
 
 	sprd_i2c_opt_start(i2c_dev);
 
-	wait_for_completion(&i2c_dev->complete);
+	time_left = wait_for_completion_timeout(&i2c_dev->complete,
+				msecs_to_jiffies(I2C_XFER_TIMEOUT));
+	if (!time_left)
+		return -ETIMEDOUT;
 
 	return i2c_dev->err;
 }
diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index 2162bc80f09e..013ad33fbbc8 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -223,7 +223,6 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 	sense_rq->rq_disk = rq->rq_disk;
 	sense_rq->cmd_flags = REQ_OP_DRV_IN;
 	ide_req(sense_rq)->type = ATA_PRIV_SENSE;
-	sense_rq->rq_flags |= RQF_PREEMPT;
 
 	req->cmd[0] = GPCMD_REQUEST_SENSE;
 	req->cmd[4] = cmd_len;
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 1a53c7a75224..4867b67b60d6 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -515,15 +515,10 @@ repeat:
 		 * above to return us whatever is in the queue. Since we call
 		 * ide_do_request() ourselves, we end up taking requests while
 		 * the queue is blocked...
-		 * 
-		 * We let requests forced at head of queue with ide-preempt
-		 * though. I hope that doesn't happen too much, hopefully not
-		 * unless the subdriver triggers such a thing in its own PM
-		 * state machine.
 		 */
 		if ((drive->dev_flags & IDE_DFLAG_BLOCKED) &&
 		    ata_pm_request(rq) == 0 &&
-		    (rq->rq_flags & RQF_PREEMPT) == 0) {
+		    (rq->rq_flags & RQF_PM) == 0) {
 			/* there should be no pending command at this point */
 			ide_unlock_port(hwif);
 			goto plug_device;
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index 192e6c65d34e..82ab308f1aaf 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -77,7 +77,7 @@ int generic_ide_resume(struct device *dev)
 	}
 
 	memset(&rqpm, 0, sizeof(rqpm));
-	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, BLK_MQ_REQ_PREEMPT);
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, BLK_MQ_REQ_PM);
 	ide_req(rq)->type = ATA_PRIV_PM_RESUME;
 	ide_req(rq)->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_RESUME;
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index d79335506ecd..28f93b9aa51b 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -963,6 +963,39 @@ static struct cpuidle_state dnv_cstates[] __initdata = {
 		.enter = NULL }
 };
 
+/*
+ * Note, depending on HW and FW revision, SnowRidge SoC may or may not support
+ * C6, and this is indicated in the CPUID mwait leaf.
+ */
+static struct cpuidle_state snr_cstates[] __initdata = {
+	{
+		.name = "C1",
+		.desc = "MWAIT 0x00",
+		.flags = MWAIT2flg(0x00),
+		.exit_latency = 2,
+		.target_residency = 2,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C1E",
+		.desc = "MWAIT 0x01",
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+		.exit_latency = 15,
+		.target_residency = 25,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.name = "C6",
+		.desc = "MWAIT 0x20",
+		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 130,
+		.target_residency = 500,
+		.enter = &intel_idle,
+		.enter_s2idle = intel_idle_s2idle, },
+	{
+		.enter = NULL }
+};
+
 static const struct idle_cpu idle_cpu_nehalem __initconst = {
 	.state_table = nehalem_cstates,
 	.auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE,
@@ -1084,6 +1117,12 @@ static const struct idle_cpu idle_cpu_dnv __initconst = {
 	.use_acpi = true,
 };
 
+static const struct idle_cpu idle_cpu_snr __initconst = {
+	.state_table = snr_cstates,
+	.disable_promotion_to_c1e = true,
+	.use_acpi = true,
+};
+
 static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP,		&idle_cpu_nhx),
 	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM,		&idle_cpu_nehalem),
@@ -1122,7 +1161,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	&idle_cpu_bxt),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&idle_cpu_bxt),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D,	&idle_cpu_dnv),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&idle_cpu_dnv),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&idle_cpu_snr),
 	{}
 };
 
diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c
index 7f70e5a7de10..97a77ea8d3c9 100644
--- a/drivers/infiniband/core/cma_configfs.c
+++ b/drivers/infiniband/core/cma_configfs.c
@@ -131,8 +131,10 @@ static ssize_t default_roce_mode_store(struct config_item *item,
 		return ret;
 
 	gid_type = ib_cache_gid_parse_type_str(buf);
-	if (gid_type < 0)
+	if (gid_type < 0) {
+		cma_configfs_params_put(cma_dev);
 		return -EINVAL;
+	}
 
 	ret = cma_set_default_gid_type(cma_dev, group->port_num, gid_type);
 
diff --git a/drivers/infiniband/core/restrack.c b/drivers/infiniband/core/restrack.c
index e0a41c867002..ff1551b3cf61 100644
--- a/drivers/infiniband/core/restrack.c
+++ b/drivers/infiniband/core/restrack.c
@@ -254,6 +254,7 @@ void rdma_restrack_add(struct rdma_restrack_entry *res)
 	} else {
 		ret = xa_alloc_cyclic(&rt->xa, &res->id, res, xa_limit_32b,
 				      &rt->next_id, GFP_KERNEL);
+		ret = (ret < 0) ? ret : 0;
 	}
 
 out:
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 7dab9a27a145..da2512c30ffd 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -95,8 +95,6 @@ struct ucma_context {
 	u64			uid;
 
 	struct list_head	list;
-	/* sync between removal event and id destroy, protected by file mut */
-	int			destroying;
 	struct work_struct	close_work;
 };
 
@@ -122,7 +120,7 @@ static DEFINE_XARRAY_ALLOC(ctx_table);
 static DEFINE_XARRAY_ALLOC(multicast_table);
 
 static const struct file_operations ucma_fops;
-static int __destroy_id(struct ucma_context *ctx);
+static int ucma_destroy_private_ctx(struct ucma_context *ctx);
 
 static inline struct ucma_context *_ucma_find_context(int id,
 						      struct ucma_file *file)
@@ -179,19 +177,14 @@ static void ucma_close_id(struct work_struct *work)
 
 	/* once all inflight tasks are finished, we close all underlying
 	 * resources. The context is still alive till its explicit destryoing
-	 * by its creator.
+	 * by its creator. This puts back the xarray's reference.
 	 */
 	ucma_put_ctx(ctx);
 	wait_for_completion(&ctx->comp);
 	/* No new events will be generated after destroying the id. */
 	rdma_destroy_id(ctx->cm_id);
 
-	/*
-	 * At this point ctx->ref is zero so the only place the ctx can be is in
-	 * a uevent or in __destroy_id(). Since the former doesn't touch
-	 * ctx->cm_id and the latter sync cancels this, there is no races with
-	 * this store.
-	 */
+	/* Reading the cm_id without holding a positive ref is not allowed */
 	ctx->cm_id = NULL;
 }
 
@@ -204,7 +197,6 @@ static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file)
 		return NULL;
 
 	INIT_WORK(&ctx->close_work, ucma_close_id);
-	refcount_set(&ctx->ref, 1);
 	init_completion(&ctx->comp);
 	/* So list_del() will work if we don't do ucma_finish_ctx() */
 	INIT_LIST_HEAD(&ctx->list);
@@ -218,6 +210,13 @@ static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file)
 	return ctx;
 }
 
+static void ucma_set_ctx_cm_id(struct ucma_context *ctx,
+			       struct rdma_cm_id *cm_id)
+{
+	refcount_set(&ctx->ref, 1);
+	ctx->cm_id = cm_id;
+}
+
 static void ucma_finish_ctx(struct ucma_context *ctx)
 {
 	lockdep_assert_held(&ctx->file->mut);
@@ -303,7 +302,7 @@ static int ucma_connect_event_handler(struct rdma_cm_id *cm_id,
 	ctx = ucma_alloc_ctx(listen_ctx->file);
 	if (!ctx)
 		goto err_backlog;
-	ctx->cm_id = cm_id;
+	ucma_set_ctx_cm_id(ctx, cm_id);
 
 	uevent = ucma_create_uevent(listen_ctx, event);
 	if (!uevent)
@@ -321,8 +320,7 @@ static int ucma_connect_event_handler(struct rdma_cm_id *cm_id,
 	return 0;
 
 err_alloc:
-	xa_erase(&ctx_table, ctx->id);
-	kfree(ctx);
+	ucma_destroy_private_ctx(ctx);
 err_backlog:
 	atomic_inc(&listen_ctx->backlog);
 	/* Returning error causes the new ID to be destroyed */
@@ -356,8 +354,12 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id,
 		wake_up_interruptible(&ctx->file->poll_wait);
 	}
 
-	if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL && !ctx->destroying)
-		queue_work(system_unbound_wq, &ctx->close_work);
+	if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) {
+		xa_lock(&ctx_table);
+		if (xa_load(&ctx_table, ctx->id) == ctx)
+			queue_work(system_unbound_wq, &ctx->close_work);
+		xa_unlock(&ctx_table);
+	}
 	return 0;
 }
 
@@ -461,13 +463,12 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
 		ret = PTR_ERR(cm_id);
 		goto err1;
 	}
-	ctx->cm_id = cm_id;
+	ucma_set_ctx_cm_id(ctx, cm_id);
 
 	resp.id = ctx->id;
 	if (copy_to_user(u64_to_user_ptr(cmd.response),
 			 &resp, sizeof(resp))) {
-		xa_erase(&ctx_table, ctx->id);
-		__destroy_id(ctx);
+		ucma_destroy_private_ctx(ctx);
 		return -EFAULT;
 	}
 
@@ -477,8 +478,7 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
 	return 0;
 
 err1:
-	xa_erase(&ctx_table, ctx->id);
-	kfree(ctx);
+	ucma_destroy_private_ctx(ctx);
 	return ret;
 }
 
@@ -516,68 +516,73 @@ static void ucma_cleanup_mc_events(struct ucma_multicast *mc)
 	rdma_unlock_handler(mc->ctx->cm_id);
 }
 
-/*
- * ucma_free_ctx is called after the underlying rdma CM-ID is destroyed. At
- * this point, no new events will be reported from the hardware. However, we
- * still need to cleanup the UCMA context for this ID. Specifically, there
- * might be events that have not yet been consumed by the user space software.
- * mutex. After that we release them as needed.
- */
-static int ucma_free_ctx(struct ucma_context *ctx)
+static int ucma_cleanup_ctx_events(struct ucma_context *ctx)
 {
 	int events_reported;
 	struct ucma_event *uevent, *tmp;
 	LIST_HEAD(list);
 
-	ucma_cleanup_multicast(ctx);
-
-	/* Cleanup events not yet reported to the user. */
+	/* Cleanup events not yet reported to the user.*/
 	mutex_lock(&ctx->file->mut);
 	list_for_each_entry_safe(uevent, tmp, &ctx->file->event_list, list) {
-		if (uevent->ctx == ctx || uevent->conn_req_ctx == ctx)
+		if (uevent->ctx != ctx)
+			continue;
+
+		if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST &&
+		    xa_cmpxchg(&ctx_table, uevent->conn_req_ctx->id,
+			       uevent->conn_req_ctx, XA_ZERO_ENTRY,
+			       GFP_KERNEL) == uevent->conn_req_ctx) {
 			list_move_tail(&uevent->list, &list);
+			continue;
+		}
+		list_del(&uevent->list);
+		kfree(uevent);
 	}
 	list_del(&ctx->list);
 	events_reported = ctx->events_reported;
 	mutex_unlock(&ctx->file->mut);
 
 	/*
-	 * If this was a listening ID then any connections spawned from it
-	 * that have not been delivered to userspace are cleaned up too.
-	 * Must be done outside any locks.
+	 * If this was a listening ID then any connections spawned from it that
+	 * have not been delivered to userspace are cleaned up too. Must be done
+	 * outside any locks.
 	 */
 	list_for_each_entry_safe(uevent, tmp, &list, list) {
-		list_del(&uevent->list);
-		if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST &&
-		    uevent->conn_req_ctx != ctx)
-			__destroy_id(uevent->conn_req_ctx);
+		ucma_destroy_private_ctx(uevent->conn_req_ctx);
 		kfree(uevent);
 	}
-
-	mutex_destroy(&ctx->mutex);
-	kfree(ctx);
 	return events_reported;
 }
 
-static int __destroy_id(struct ucma_context *ctx)
+/*
+ * When this is called the xarray must have a XA_ZERO_ENTRY in the ctx->id (ie
+ * the ctx is not public to the user). This either because:
+ *  - ucma_finish_ctx() hasn't been called
+ *  - xa_cmpxchg() succeed to remove the entry (only one thread can succeed)
+ */
+static int ucma_destroy_private_ctx(struct ucma_context *ctx)
 {
+	int events_reported;
+
 	/*
-	 * If the refcount is already 0 then ucma_close_id() has already
-	 * destroyed the cm_id, otherwise holding the refcount keeps cm_id
-	 * valid. Prevent queue_work() from being called.
+	 * Destroy the underlying cm_id. New work queuing is prevented now by
+	 * the removal from the xarray. Once the work is cancled ref will either
+	 * be 0 because the work ran to completion and consumed the ref from the
+	 * xarray, or it will be positive because we still have the ref from the
+	 * xarray. This can also be 0 in cases where cm_id was never set
 	 */
-	if (refcount_inc_not_zero(&ctx->ref)) {
-		rdma_lock_handler(ctx->cm_id);
-		ctx->destroying = 1;
-		rdma_unlock_handler(ctx->cm_id);
-		ucma_put_ctx(ctx);
-	}
-
 	cancel_work_sync(&ctx->close_work);
-	/* At this point it's guaranteed that there is no inflight closing task */
-	if (ctx->cm_id)
+	if (refcount_read(&ctx->ref))
 		ucma_close_id(&ctx->close_work);
-	return ucma_free_ctx(ctx);
+
+	events_reported = ucma_cleanup_ctx_events(ctx);
+	ucma_cleanup_multicast(ctx);
+
+	WARN_ON(xa_cmpxchg(&ctx_table, ctx->id, XA_ZERO_ENTRY, NULL,
+			   GFP_KERNEL) != NULL);
+	mutex_destroy(&ctx->mutex);
+	kfree(ctx);
+	return events_reported;
 }
 
 static ssize_t ucma_destroy_id(struct ucma_file *file, const char __user *inbuf,
@@ -596,14 +601,17 @@ static ssize_t ucma_destroy_id(struct ucma_file *file, const char __user *inbuf,
 
 	xa_lock(&ctx_table);
 	ctx = _ucma_find_context(cmd.id, file);
-	if (!IS_ERR(ctx))
-		__xa_erase(&ctx_table, ctx->id);
+	if (!IS_ERR(ctx)) {
+		if (__xa_cmpxchg(&ctx_table, ctx->id, ctx, XA_ZERO_ENTRY,
+				 GFP_KERNEL) != ctx)
+			ctx = ERR_PTR(-ENOENT);
+	}
 	xa_unlock(&ctx_table);
 
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	resp.events_reported = __destroy_id(ctx);
+	resp.events_reported = ucma_destroy_private_ctx(ctx);
 	if (copy_to_user(u64_to_user_ptr(cmd.response),
 			 &resp, sizeof(resp)))
 		ret = -EFAULT;
@@ -1777,15 +1785,16 @@ static int ucma_close(struct inode *inode, struct file *filp)
 	 * prevented by this being a FD release function. The list_add_tail() in
 	 * ucma_connect_event_handler() can run concurrently, however it only
 	 * adds to the list *after* a listening ID. By only reading the first of
-	 * the list, and relying on __destroy_id() to block
+	 * the list, and relying on ucma_destroy_private_ctx() to block
 	 * ucma_connect_event_handler(), no additional locking is needed.
 	 */
 	while (!list_empty(&file->ctx_list)) {
 		struct ucma_context *ctx = list_first_entry(
 			&file->ctx_list, struct ucma_context, list);
 
-		xa_erase(&ctx_table, ctx->id);
-		__destroy_id(ctx);
+		WARN_ON(xa_cmpxchg(&ctx_table, ctx->id, ctx, XA_ZERO_ENTRY,
+				   GFP_KERNEL) != ctx);
+		ucma_destroy_private_ctx(ctx);
 	}
 	kfree(file);
 	return 0;
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 7ca4112e3e8f..917338db7ac1 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -135,7 +135,7 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 	 */
 	if (mask)
 		pgsz_bitmap &= GENMASK(count_trailing_zeros(mask), 0);
-	return rounddown_pow_of_two(pgsz_bitmap);
+	return pgsz_bitmap ? rounddown_pow_of_two(pgsz_bitmap) : 0;
 }
 EXPORT_SYMBOL(ib_umem_find_best_pgsz);
 
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 3bae9ba0ead8..d26f3f3e0462 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3956,7 +3956,7 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 
 	err = set_has_smi_cap(dev);
 	if (err)
-		return err;
+		goto err_mp;
 
 	if (!mlx5_core_mp_enabled(mdev)) {
 		for (i = 1; i <= dev->num_ports; i++) {
@@ -4319,7 +4319,7 @@ static int mlx5_ib_stage_bfrag_init(struct mlx5_ib_dev *dev)
 
 	err = mlx5_alloc_bfreg(dev->mdev, &dev->fp_bfreg, false, true);
 	if (err)
-		mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg);
+		mlx5_free_bfreg(dev->mdev, &dev->bfreg);
 
 	return err;
 }
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index bc98bd950d99..3acb5c10b155 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -434,9 +434,9 @@ static void ocrdma_dealloc_ucontext_pd(struct ocrdma_ucontext *uctx)
 		pr_err("%s(%d) Freeing in use pdid=0x%x.\n",
 		       __func__, dev->id, pd->id);
 	}
-	kfree(uctx->cntxt_pd);
 	uctx->cntxt_pd = NULL;
 	_ocrdma_dealloc_pd(dev, pd);
+	kfree(pd);
 }
 
 static struct ocrdma_pd *ocrdma_get_ucontext_pd(struct ocrdma_ucontext *uctx)
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index 38a37770c016..3705c6b8b223 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -214,6 +214,7 @@ find_free_vf_and_create_qp_grp(struct usnic_ib_dev *us_ibdev,
 
 		}
 		usnic_uiom_free_dev_list(dev_list);
+		dev_list = NULL;
 	}
 
 	/* Try to find resources on an unused vf */
@@ -239,6 +240,8 @@ find_free_vf_and_create_qp_grp(struct usnic_ib_dev *us_ibdev,
 qp_grp_check:
 	if (IS_ERR_OR_NULL(qp_grp)) {
 		usnic_err("Failed to allocate qp_grp\n");
+		if (usnic_ib_share_vf)
+			usnic_uiom_free_dev_list(dev_list);
 		return ERR_PTR(qp_grp ? PTR_ERR(qp_grp) : -ENOMEM);
 	}
 	return qp_grp;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 560865f65dc4..67f86c405a26 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -157,12 +157,6 @@ void rtrs_clt_put_permit(struct rtrs_clt *clt, struct rtrs_permit *permit)
 }
 EXPORT_SYMBOL(rtrs_clt_put_permit);
 
-void *rtrs_permit_to_pdu(struct rtrs_permit *permit)
-{
-	return permit + 1;
-}
-EXPORT_SYMBOL(rtrs_permit_to_pdu);
-
 /**
  * rtrs_permit_to_clt_con() - returns RDMA connection pointer by the permit
  * @sess: client session pointer
diff --git a/drivers/infiniband/ulp/rtrs/rtrs.h b/drivers/infiniband/ulp/rtrs/rtrs.h
index 9af750f4d783..8738e90e715a 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs.h
@@ -63,13 +63,6 @@ struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
 
 void rtrs_clt_close(struct rtrs_clt *sess);
 
-/**
- * rtrs_permit_to_pdu() - converts rtrs_permit to opaque pdu pointer
- * @permit: RTRS permit pointer, it associates the memory allocation for future
- *          RDMA operation.
- */
-void *rtrs_permit_to_pdu(struct rtrs_permit *permit);
-
 enum {
 	RTRS_PERMIT_NOWAIT = 0,
 	RTRS_PERMIT_WAIT   = 1,
diff --git a/drivers/interconnect/imx/imx.c b/drivers/interconnect/imx/imx.c
index 41dba7090c2a..c770951a909c 100644
--- a/drivers/interconnect/imx/imx.c
+++ b/drivers/interconnect/imx/imx.c
@@ -96,9 +96,10 @@ static int imx_icc_node_init_qos(struct icc_provider *provider,
 			return -ENODEV;
 		}
 		/* Allow scaling to be disabled on a per-node basis */
-		if (!dn || !of_device_is_available(dn)) {
+		if (!of_device_is_available(dn)) {
 			dev_warn(dev, "Missing property %s, skip scaling %s\n",
 				 adj->phandle_name, node->name);
+			of_node_put(dn);
 			return 0;
 		}
 
diff --git a/drivers/interconnect/imx/imx8mq.c b/drivers/interconnect/imx/imx8mq.c
index ba43a15aefec..d7768d3c6d8a 100644
--- a/drivers/interconnect/imx/imx8mq.c
+++ b/drivers/interconnect/imx/imx8mq.c
@@ -7,6 +7,7 @@
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/interconnect-provider.h>
 #include <dt-bindings/interconnect/imx8mq.h>
 
 #include "imx.h"
@@ -94,6 +95,7 @@ static struct platform_driver imx8mq_icc_driver = {
 	.remove = imx8mq_icc_remove,
 	.driver = {
 		.name = "imx8mq-interconnect",
+		.sync_state = icc_sync_state,
 	},
 };
 
diff --git a/drivers/interconnect/qcom/Kconfig b/drivers/interconnect/qcom/Kconfig
index a8f93ba265f8..b3fb5b02bcf1 100644
--- a/drivers/interconnect/qcom/Kconfig
+++ b/drivers/interconnect/qcom/Kconfig
@@ -42,13 +42,23 @@ config INTERCONNECT_QCOM_QCS404
 	  This is a driver for the Qualcomm Network-on-Chip on qcs404-based
 	  platforms.
 
+config INTERCONNECT_QCOM_RPMH_POSSIBLE
+	tristate
+	default INTERCONNECT_QCOM
+	depends on QCOM_RPMH || (COMPILE_TEST && !QCOM_RPMH)
+	depends on QCOM_COMMAND_DB || (COMPILE_TEST && !QCOM_COMMAND_DB)
+	depends on OF || COMPILE_TEST
+	help
+	  Compile-testing RPMH drivers is possible on other platforms,
+	  but in order to avoid link failures, drivers must not be built-in
+	  when QCOM_RPMH or QCOM_COMMAND_DB are loadable modules
+
 config INTERCONNECT_QCOM_RPMH
 	tristate
 
 config INTERCONNECT_QCOM_SC7180
 	tristate "Qualcomm SC7180 interconnect driver"
-	depends on INTERCONNECT_QCOM
-	depends on (QCOM_RPMH && QCOM_COMMAND_DB && OF) || COMPILE_TEST
+	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
 	select INTERCONNECT_QCOM_RPMH
 	select INTERCONNECT_QCOM_BCM_VOTER
 	help
@@ -57,8 +67,7 @@ config INTERCONNECT_QCOM_SC7180
 
 config INTERCONNECT_QCOM_SDM845
 	tristate "Qualcomm SDM845 interconnect driver"
-	depends on INTERCONNECT_QCOM
-	depends on (QCOM_RPMH && QCOM_COMMAND_DB && OF) || COMPILE_TEST
+	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
 	select INTERCONNECT_QCOM_RPMH
 	select INTERCONNECT_QCOM_BCM_VOTER
 	help
@@ -67,8 +76,7 @@ config INTERCONNECT_QCOM_SDM845
 
 config INTERCONNECT_QCOM_SM8150
 	tristate "Qualcomm SM8150 interconnect driver"
-	depends on INTERCONNECT_QCOM
-	depends on (QCOM_RPMH && QCOM_COMMAND_DB && OF) || COMPILE_TEST
+	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
 	select INTERCONNECT_QCOM_RPMH
 	select INTERCONNECT_QCOM_BCM_VOTER
 	help
@@ -77,8 +85,7 @@ config INTERCONNECT_QCOM_SM8150
 
 config INTERCONNECT_QCOM_SM8250
 	tristate "Qualcomm SM8250 interconnect driver"
-	depends on INTERCONNECT_QCOM
-	depends on (QCOM_RPMH && QCOM_COMMAND_DB && OF) || COMPILE_TEST
+	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
 	select INTERCONNECT_QCOM_RPMH
 	select INTERCONNECT_QCOM_BCM_VOTER
 	help
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index f54cd79b43e4..6a1f7048dacc 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -1973,8 +1973,6 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
 		return r;
 	}
 
-	iommu->int_enabled = true;
-
 	return 0;
 }
 
@@ -2169,6 +2167,7 @@ static int iommu_init_irq(struct amd_iommu *iommu)
 	if (ret)
 		return ret;
 
+	iommu->int_enabled = true;
 enable_faults:
 	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
 
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 7e2c445a1fae..f0adbc48fd17 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3854,6 +3854,9 @@ static int irq_remapping_select(struct irq_domain *d, struct irq_fwspec *fwspec,
 	struct amd_iommu *iommu;
 	int devid = -1;
 
+	if (!amd_iommu_irq_remap)
+		return 0;
+
 	if (x86_fwspec_is_ioapic(fwspec))
 		devid = get_ioapic_devid(fwspec->param[0]);
 	else if (x86_fwspec_is_hpet(fwspec))
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 5dff7ffbef11..bcda17012aee 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -196,6 +196,8 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 
 		set_bit(qsmmu->bypass_cbndx, smmu->context_map);
 
+		arm_smmu_cb_write(smmu, qsmmu->bypass_cbndx, ARM_SMMU_CB_SCTLR, 0);
+
 		reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, CBAR_TYPE_S1_TRANS_S2_BYPASS);
 		arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(qsmmu->bypass_cbndx), reg);
 	}
@@ -323,7 +325,9 @@ static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
 }
 
 static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
+	{ .compatible = "qcom,msm8998-smmu-v2" },
 	{ .compatible = "qcom,sc7180-smmu-500" },
+	{ .compatible = "qcom,sdm630-smmu-v2" },
 	{ .compatible = "qcom,sdm845-smmu-500" },
 	{ .compatible = "qcom,sm8150-smmu-500" },
 	{ .compatible = "qcom,sm8250-smmu-500" },
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f0305e6aac1b..4078358ed66e 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -863,33 +863,6 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
 	unsigned int cur_len = 0, max_len = dma_get_max_seg_size(dev);
 	int i, count = 0;
 
-	/*
-	 * The Intel graphic driver is used to assume that the returned
-	 * sg list is not combound. This blocks the efforts of converting
-	 * Intel IOMMU driver to dma-iommu api's. Add this quirk to make the
-	 * device driver work and should be removed once it's fixed in i915
-	 * driver.
-	 */
-	if (IS_ENABLED(CONFIG_DRM_I915) && dev_is_pci(dev) &&
-	    to_pci_dev(dev)->vendor == PCI_VENDOR_ID_INTEL &&
-	    (to_pci_dev(dev)->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
-		for_each_sg(sg, s, nents, i) {
-			unsigned int s_iova_off = sg_dma_address(s);
-			unsigned int s_length = sg_dma_len(s);
-			unsigned int s_iova_len = s->length;
-
-			s->offset += s_iova_off;
-			s->length = s_length;
-			sg_dma_address(s) = dma_addr + s_iova_off;
-			sg_dma_len(s) = s_length;
-			dma_addr += s_iova_len;
-
-			pr_info_once("sg combining disabled due to i915 driver\n");
-		}
-
-		return nents;
-	}
-
 	for_each_sg(sg, s, nents, i) {
 		/* Restore this segment's original unaligned fields first */
 		unsigned int s_iova_off = sg_dma_address(s);
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index b46dbfa6d0ed..004feaed3c72 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1461,8 +1461,8 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
 		int mask = ilog2(__roundup_pow_of_two(npages));
 		unsigned long align = (1ULL << (VTD_PAGE_SHIFT + mask));
 
-		if (WARN_ON_ONCE(!ALIGN(addr, align)))
-			addr &= ~(align - 1);
+		if (WARN_ON_ONCE(!IS_ALIGNED(addr, align)))
+			addr = ALIGN_DOWN(addr, align);
 
 		desc.qw0 = QI_EIOTLB_PASID(pasid) |
 				QI_EIOTLB_DID(did) |
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 788119c5b021..f665322a0991 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -38,7 +38,6 @@
 #include <linux/dmi.h>
 #include <linux/pci-ats.h>
 #include <linux/memblock.h>
-#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/crash_dump.h>
 #include <linux/numa.h>
@@ -719,6 +718,8 @@ static int domain_update_device_node(struct dmar_domain *domain)
 	return nid;
 }
 
+static void domain_update_iotlb(struct dmar_domain *domain);
+
 /* Some capabilities may be different across iommus */
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
@@ -744,6 +745,8 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
 		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw - 1);
 	else
 		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw);
+
+	domain_update_iotlb(domain);
 }
 
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
@@ -1464,17 +1467,22 @@ static void domain_update_iotlb(struct dmar_domain *domain)
 
 	assert_spin_locked(&device_domain_lock);
 
-	list_for_each_entry(info, &domain->devices, link) {
-		struct pci_dev *pdev;
-
-		if (!info->dev || !dev_is_pci(info->dev))
-			continue;
-
-		pdev = to_pci_dev(info->dev);
-		if (pdev->ats_enabled) {
+	list_for_each_entry(info, &domain->devices, link)
+		if (info->ats_enabled) {
 			has_iotlb_device = true;
 			break;
 		}
+
+	if (!has_iotlb_device) {
+		struct subdev_domain_info *sinfo;
+
+		list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+			info = get_domain_info(sinfo->pdev);
+			if (info && info->ats_enabled) {
+				has_iotlb_device = true;
+				break;
+			}
+		}
 	}
 
 	domain->has_iotlb_device = has_iotlb_device;
@@ -1555,25 +1563,37 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info)
 #endif
 }
 
+static void __iommu_flush_dev_iotlb(struct device_domain_info *info,
+				    u64 addr, unsigned int mask)
+{
+	u16 sid, qdep;
+
+	if (!info || !info->ats_enabled)
+		return;
+
+	sid = info->bus << 8 | info->devfn;
+	qdep = info->ats_qdep;
+	qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+			   qdep, addr, mask);
+}
+
 static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 				  u64 addr, unsigned mask)
 {
-	u16 sid, qdep;
 	unsigned long flags;
 	struct device_domain_info *info;
+	struct subdev_domain_info *sinfo;
 
 	if (!domain->has_iotlb_device)
 		return;
 
 	spin_lock_irqsave(&device_domain_lock, flags);
-	list_for_each_entry(info, &domain->devices, link) {
-		if (!info->ats_enabled)
-			continue;
+	list_for_each_entry(info, &domain->devices, link)
+		__iommu_flush_dev_iotlb(info, addr, mask);
 
-		sid = info->bus << 8 | info->devfn;
-		qdep = info->ats_qdep;
-		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
-				qdep, addr, mask);
+	list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+		info = get_domain_info(sinfo->pdev);
+		__iommu_flush_dev_iotlb(info, addr, mask);
 	}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
@@ -1877,6 +1897,7 @@ static struct dmar_domain *alloc_domain(int flags)
 		domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
+	INIT_LIST_HEAD(&domain->subdevices);
 
 	return domain;
 }
@@ -2547,7 +2568,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 	info->iommu = iommu;
 	info->pasid_table = NULL;
 	info->auxd_enabled = 0;
-	INIT_LIST_HEAD(&info->auxiliary_domains);
+	INIT_LIST_HEAD(&info->subdevices);
 
 	if (dev && dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(info->dev);
@@ -4475,33 +4496,61 @@ is_aux_domain(struct device *dev, struct iommu_domain *domain)
 			domain->type == IOMMU_DOMAIN_UNMANAGED;
 }
 
-static void auxiliary_link_device(struct dmar_domain *domain,
-				  struct device *dev)
+static inline struct subdev_domain_info *
+lookup_subdev_info(struct dmar_domain *domain, struct device *dev)
+{
+	struct subdev_domain_info *sinfo;
+
+	if (!list_empty(&domain->subdevices)) {
+		list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+			if (sinfo->pdev == dev)
+				return sinfo;
+		}
+	}
+
+	return NULL;
+}
+
+static int auxiliary_link_device(struct dmar_domain *domain,
+				 struct device *dev)
 {
 	struct device_domain_info *info = get_domain_info(dev);
+	struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
 
 	assert_spin_locked(&device_domain_lock);
 	if (WARN_ON(!info))
-		return;
+		return -EINVAL;
 
-	domain->auxd_refcnt++;
-	list_add(&domain->auxd, &info->auxiliary_domains);
+	if (!sinfo) {
+		sinfo = kzalloc(sizeof(*sinfo), GFP_ATOMIC);
+		sinfo->domain = domain;
+		sinfo->pdev = dev;
+		list_add(&sinfo->link_phys, &info->subdevices);
+		list_add(&sinfo->link_domain, &domain->subdevices);
+	}
+
+	return ++sinfo->users;
 }
 
-static void auxiliary_unlink_device(struct dmar_domain *domain,
-				    struct device *dev)
+static int auxiliary_unlink_device(struct dmar_domain *domain,
+				   struct device *dev)
 {
 	struct device_domain_info *info = get_domain_info(dev);
+	struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
+	int ret;
 
 	assert_spin_locked(&device_domain_lock);
-	if (WARN_ON(!info))
-		return;
+	if (WARN_ON(!info || !sinfo || sinfo->users <= 0))
+		return -EINVAL;
 
-	list_del(&domain->auxd);
-	domain->auxd_refcnt--;
+	ret = --sinfo->users;
+	if (!ret) {
+		list_del(&sinfo->link_phys);
+		list_del(&sinfo->link_domain);
+		kfree(sinfo);
+	}
 
-	if (!domain->auxd_refcnt && domain->default_pasid > 0)
-		ioasid_put(domain->default_pasid);
+	return ret;
 }
 
 static int aux_domain_add_dev(struct dmar_domain *domain,
@@ -4530,6 +4579,19 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 	}
 
 	spin_lock_irqsave(&device_domain_lock, flags);
+	ret = auxiliary_link_device(domain, dev);
+	if (ret <= 0)
+		goto link_failed;
+
+	/*
+	 * Subdevices from the same physical device can be attached to the
+	 * same domain. For such cases, only the first subdevice attachment
+	 * needs to go through the full steps in this function. So if ret >
+	 * 1, just goto out.
+	 */
+	if (ret > 1)
+		goto out;
+
 	/*
 	 * iommu->lock must be held to attach domain to iommu and setup the
 	 * pasid entry for second level translation.
@@ -4548,10 +4610,9 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 						     domain->default_pasid);
 	if (ret)
 		goto table_failed;
-	spin_unlock(&iommu->lock);
-
-	auxiliary_link_device(domain, dev);
 
+	spin_unlock(&iommu->lock);
+out:
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	return 0;
@@ -4560,8 +4621,10 @@ table_failed:
 	domain_detach_iommu(domain, iommu);
 attach_failed:
 	spin_unlock(&iommu->lock);
+	auxiliary_unlink_device(domain, dev);
+link_failed:
 	spin_unlock_irqrestore(&device_domain_lock, flags);
-	if (!domain->auxd_refcnt && domain->default_pasid > 0)
+	if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
 		ioasid_put(domain->default_pasid);
 
 	return ret;
@@ -4581,14 +4644,18 @@ static void aux_domain_remove_dev(struct dmar_domain *domain,
 	info = get_domain_info(dev);
 	iommu = info->iommu;
 
-	auxiliary_unlink_device(domain, dev);
-
-	spin_lock(&iommu->lock);
-	intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid, false);
-	domain_detach_iommu(domain, iommu);
-	spin_unlock(&iommu->lock);
+	if (!auxiliary_unlink_device(domain, dev)) {
+		spin_lock(&iommu->lock);
+		intel_pasid_tear_down_entry(iommu, dev,
+					    domain->default_pasid, false);
+		domain_detach_iommu(domain, iommu);
+		spin_unlock(&iommu->lock);
+	}
 
 	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
+		ioasid_put(domain->default_pasid);
 }
 
 static int prepare_domain_attach_device(struct iommu_domain *domain,
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index aeffda92b10b..685200a5cff0 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -1353,6 +1353,8 @@ static int intel_irq_remapping_alloc(struct irq_domain *domain,
 		irq_data = irq_domain_get_irq_data(domain, virq + i);
 		irq_cfg = irqd_cfg(irq_data);
 		if (!irq_data || !irq_cfg) {
+			if (!i)
+				kfree(data);
 			ret = -EINVAL;
 			goto out_free_data;
 		}
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 4fa248b98031..18a9f05df407 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -118,8 +118,10 @@ void intel_svm_check(struct intel_iommu *iommu)
 	iommu->flags |= VTD_FLAG_SVM_CAPABLE;
 }
 
-static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_dev *sdev,
-				unsigned long address, unsigned long pages, int ih)
+static void __flush_svm_range_dev(struct intel_svm *svm,
+				  struct intel_svm_dev *sdev,
+				  unsigned long address,
+				  unsigned long pages, int ih)
 {
 	struct qi_desc desc;
 
@@ -142,7 +144,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 	}
 	desc.qw2 = 0;
 	desc.qw3 = 0;
-	qi_submit_sync(svm->iommu, &desc, 1, 0);
+	qi_submit_sync(sdev->iommu, &desc, 1, 0);
 
 	if (sdev->dev_iotlb) {
 		desc.qw0 = QI_DEV_EIOTLB_PASID(svm->pasid) |
@@ -166,7 +168,23 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 		}
 		desc.qw2 = 0;
 		desc.qw3 = 0;
-		qi_submit_sync(svm->iommu, &desc, 1, 0);
+		qi_submit_sync(sdev->iommu, &desc, 1, 0);
+	}
+}
+
+static void intel_flush_svm_range_dev(struct intel_svm *svm,
+				      struct intel_svm_dev *sdev,
+				      unsigned long address,
+				      unsigned long pages, int ih)
+{
+	unsigned long shift = ilog2(__roundup_pow_of_two(pages));
+	unsigned long align = (1ULL << (VTD_PAGE_SHIFT + shift));
+	unsigned long start = ALIGN_DOWN(address, align);
+	unsigned long end = ALIGN(address + (pages << VTD_PAGE_SHIFT), align);
+
+	while (start < end) {
+		__flush_svm_range_dev(svm, sdev, start, align >> VTD_PAGE_SHIFT, ih);
+		start += align;
 	}
 }
 
@@ -211,7 +229,7 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(sdev, &svm->devs, list)
-		intel_pasid_tear_down_entry(svm->iommu, sdev->dev,
+		intel_pasid_tear_down_entry(sdev->iommu, sdev->dev,
 					    svm->pasid, true);
 	rcu_read_unlock();
 
@@ -281,6 +299,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	struct dmar_domain *dmar_domain;
 	struct device_domain_info *info;
 	struct intel_svm *svm = NULL;
+	unsigned long iflags;
 	int ret = 0;
 
 	if (WARN_ON(!iommu) || !data)
@@ -363,6 +382,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	}
 	sdev->dev = dev;
 	sdev->sid = PCI_DEVID(info->bus, info->devfn);
+	sdev->iommu = iommu;
 
 	/* Only count users if device has aux domains */
 	if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
@@ -381,12 +401,12 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	 * each bind of a new device even with an existing PASID, we need to
 	 * call the nested mode setup function here.
 	 */
-	spin_lock(&iommu->lock);
+	spin_lock_irqsave(&iommu->lock, iflags);
 	ret = intel_pasid_setup_nested(iommu, dev,
 				       (pgd_t *)(uintptr_t)data->gpgd,
 				       data->hpasid, &data->vendor.vtd, dmar_domain,
 				       data->addr_width);
-	spin_unlock(&iommu->lock);
+	spin_unlock_irqrestore(&iommu->lock, iflags);
 	if (ret) {
 		dev_err_ratelimited(dev, "Failed to set up PASID %llu in nested mode, Err %d\n",
 				    data->hpasid, ret);
@@ -486,6 +506,7 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 	struct device_domain_info *info;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm = NULL;
+	unsigned long iflags;
 	int pasid_max;
 	int ret;
 
@@ -546,6 +567,7 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 		goto out;
 	}
 	sdev->dev = dev;
+	sdev->iommu = iommu;
 
 	ret = intel_iommu_enable_pasid(iommu, dev);
 	if (ret) {
@@ -575,7 +597,6 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 			kfree(sdev);
 			goto out;
 		}
-		svm->iommu = iommu;
 
 		if (pasid_max > intel_pasid_max_id)
 			pasid_max = intel_pasid_max_id;
@@ -605,14 +626,14 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 			}
 		}
 
-		spin_lock(&iommu->lock);
+		spin_lock_irqsave(&iommu->lock, iflags);
 		ret = intel_pasid_setup_first_level(iommu, dev,
 				mm ? mm->pgd : init_mm.pgd,
 				svm->pasid, FLPT_DEFAULT_DID,
 				(mm ? 0 : PASID_FLAG_SUPERVISOR_MODE) |
 				(cpu_feature_enabled(X86_FEATURE_LA57) ?
 				 PASID_FLAG_FL5LP : 0));
-		spin_unlock(&iommu->lock);
+		spin_unlock_irqrestore(&iommu->lock, iflags);
 		if (ret) {
 			if (mm)
 				mmu_notifier_unregister(&svm->notifier, mm);
@@ -632,14 +653,14 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 		 * Binding a new device with existing PASID, need to setup
 		 * the PASID entry.
 		 */
-		spin_lock(&iommu->lock);
+		spin_lock_irqsave(&iommu->lock, iflags);
 		ret = intel_pasid_setup_first_level(iommu, dev,
 						mm ? mm->pgd : init_mm.pgd,
 						svm->pasid, FLPT_DEFAULT_DID,
 						(mm ? 0 : PASID_FLAG_SUPERVISOR_MODE) |
 						(cpu_feature_enabled(X86_FEATURE_LA57) ?
 						PASID_FLAG_FL5LP : 0));
-		spin_unlock(&iommu->lock);
+		spin_unlock_irqrestore(&iommu->lock, iflags);
 		if (ret) {
 			kfree(sdev);
 			goto out;
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 4bb3293ae4d7..d20b8b333d30 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -358,7 +358,7 @@ static void private_free_iova(struct iova_domain *iovad, struct iova *iova)
  * @iovad: - iova domain in question.
  * @pfn: - page frame number
  * This function finds and returns an iova belonging to the
- * given doamin which matches the given pfn.
+ * given domain which matches the given pfn.
  */
 struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
 {
@@ -601,7 +601,7 @@ void queue_iova(struct iova_domain *iovad,
 EXPORT_SYMBOL_GPL(queue_iova);
 
 /**
- * put_iova_domain - destroys the iova doamin
+ * put_iova_domain - destroys the iova domain
  * @iovad: - iova domain in question.
  * All the iova's in that domain are destroyed.
  */
@@ -712,9 +712,9 @@ EXPORT_SYMBOL_GPL(reserve_iova);
 
 /**
  * copy_reserved_iova - copies the reserved between domains
- * @from: - source doamin from where to copy
+ * @from: - source domain from where to copy
  * @to: - destination domin where to copy
- * This function copies reserved iova's from one doamin to
+ * This function copies reserved iova's from one domain to
  * other.
  */
 void
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index c951ad24d377..ed46e6057e33 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3844,8 +3844,6 @@ static void its_vpe_schedule(struct its_vpe *vpe)
 	val |= vpe->idai ? GICR_VPENDBASER_IDAI : 0;
 	val |= GICR_VPENDBASER_Valid;
 	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
-
-	its_wait_vpt_parse_complete();
 }
 
 static void its_vpe_deschedule(struct its_vpe *vpe)
@@ -3893,6 +3891,10 @@ static int its_vpe_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
 		its_vpe_deschedule(vpe);
 		return 0;
 
+	case COMMIT_VPE:
+		its_wait_vpt_parse_complete();
+		return 0;
+
 	case INVALL_VPE:
 		its_vpe_invall(vpe);
 		return 0;
@@ -4054,8 +4056,6 @@ static void its_vpe_4_1_schedule(struct its_vpe *vpe,
 	val |= FIELD_PREP(GICR_VPENDBASER_4_1_VPEID, vpe->vpe_id);
 
 	gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER);
-
-	its_wait_vpt_parse_complete();
 }
 
 static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
@@ -4130,6 +4130,10 @@ static int its_vpe_4_1_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
 		its_vpe_4_1_deschedule(vpe, info);
 		return 0;
 
+	case COMMIT_VPE:
+		its_wait_vpt_parse_complete();
+		return 0;
+
 	case INVALL_VPE:
 		its_vpe_4_1_invall(vpe);
 		return 0;
diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 0c18714ae13e..5d1dc9915272 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -232,6 +232,8 @@ int its_make_vpe_non_resident(struct its_vpe *vpe, bool db)
 	if (!ret)
 		vpe->resident = false;
 
+	vpe->ready = false;
+
 	return ret;
 }
 
@@ -258,6 +260,23 @@ int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en)
 	return ret;
 }
 
+int its_commit_vpe(struct its_vpe *vpe)
+{
+	struct its_cmd_info info = {
+		.cmd_type = COMMIT_VPE,
+	};
+	int ret;
+
+	WARN_ON(preemptible());
+
+	ret = its_send_vpe_cmd(vpe, &info);
+	if (!ret)
+		vpe->ready = true;
+
+	return ret;
+}
+
+
 int its_invall_vpe(struct its_vpe *vpe)
 {
 	struct its_cmd_info info = {
diff --git a/drivers/isdn/mISDN/Kconfig b/drivers/isdn/mISDN/Kconfig
index 26cf0ac9c4ad..c9a53c222472 100644
--- a/drivers/isdn/mISDN/Kconfig
+++ b/drivers/isdn/mISDN/Kconfig
@@ -13,6 +13,7 @@ if MISDN != n
 config MISDN_DSP
 	tristate "Digital Audio Processing of transparent data"
 	depends on MISDN
+	select BITREVERSE
 	help
 	  Enable support for digital audio processing capability.
 
diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index 8f39f9ba5c80..4c2ce210c123 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -19,6 +19,7 @@ if NVM
 
 config NVM_PBLK
 	tristate "Physical Block Device Open-Channel SSD target"
+	select CRC32
 	help
 	  Allows an open-channel SSD to be exposed as a block device to the
 	  host. The target assumes the device exposes raw flash and must be
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 30ba3573626c..9e44c09f6410 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -463,6 +463,15 @@ config DM_MULTIPATH_HST
 
 	  If unsure, say N.
 
+config DM_MULTIPATH_IOA
+	tristate "I/O Path Selector based on CPU submission"
+	depends on DM_MULTIPATH
+	help
+	  This path selector selects the path based on the CPU the IO is
+	  executed on and the CPU to path mapping setup at path addition time.
+
+	  If unsure, say N.
+
 config DM_DELAY
 	tristate "I/O delaying target"
 	depends on BLK_DEV_DM
@@ -530,11 +539,22 @@ config DM_VERITY_VERIFY_ROOTHASH_SIG
 	bool "Verity data device root hash signature verification support"
 	depends on DM_VERITY
 	select SYSTEM_DATA_VERIFICATION
-	  help
+	help
 	  Add ability for dm-verity device to be validated if the
 	  pre-generated tree of cryptographic checksums passed has a pkcs#7
 	  signature file that can validate the roothash of the tree.
 
+	  By default, rely on the builtin trusted keyring.
+
+	  If unsure, say N.
+
+config DM_VERITY_VERIFY_ROOTHASH_SIG_SECONDARY_KEYRING
+	bool "Verity data device root hash signature verification with secondary keyring"
+	depends on DM_VERITY_VERIFY_ROOTHASH_SIG
+	depends on SECONDARY_TRUSTED_KEYRING
+	help
+	  Rely on the secondary trusted keyring to verify dm-verity signatures.
+
 	  If unsure, say N.
 
 config DM_VERITY_FEC
@@ -585,6 +605,7 @@ config DM_INTEGRITY
 	select BLK_DEV_INTEGRITY
 	select DM_BUFIO
 	select CRYPTO
+	select CRYPTO_SKCIPHER
 	select ASYNC_XOR
 	help
 	  This device-mapper target emulates a block device that has
@@ -602,6 +623,7 @@ config DM_ZONED
 	tristate "Drive-managed zoned block device target support"
 	depends on BLK_DEV_DM
 	depends on BLK_DEV_ZONED
+	select CRC32
 	help
 	  This device-mapper target takes a host-managed or host-aware zoned
 	  block device and exposes most of its capacity as a regular block
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 6d3e234dc46a..ef7ddc27685c 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -7,23 +7,28 @@ dm-mod-y	+= dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \
 		   dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o dm-stats.o \
 		   dm-rq.o
 dm-multipath-y	+= dm-path-selector.o dm-mpath.o
+dm-historical-service-time-y += dm-ps-historical-service-time.o
+dm-io-affinity-y += dm-ps-io-affinity.o
+dm-queue-length-y += dm-ps-queue-length.o
+dm-round-robin-y += dm-ps-round-robin.o
+dm-service-time-y += dm-ps-service-time.o
 dm-snapshot-y	+= dm-snap.o dm-exception-store.o dm-snap-transient.o \
 		    dm-snap-persistent.o
 dm-mirror-y	+= dm-raid1.o
-dm-log-userspace-y \
-		+= dm-log-userspace-base.o dm-log-userspace-transfer.o
+dm-log-userspace-y += dm-log-userspace-base.o dm-log-userspace-transfer.o
 dm-bio-prison-y += dm-bio-prison-v1.o dm-bio-prison-v2.o
 dm-thin-pool-y	+= dm-thin.o dm-thin-metadata.o
 dm-cache-y	+= dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o \
 		    dm-cache-background-tracker.o
-dm-cache-smq-y   += dm-cache-policy-smq.o
+dm-cache-smq-y	+= dm-cache-policy-smq.o
 dm-ebs-y	+= dm-ebs-target.o
 dm-era-y	+= dm-era-target.o
 dm-clone-y	+= dm-clone-target.o dm-clone-metadata.o
 dm-verity-y	+= dm-verity-target.o
+dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
+
 md-mod-y	+= md.o md-bitmap.o
 raid456-y	+= raid5.o raid5-cache.o raid5-ppl.o
-dm-zoned-y	+= dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o
 linear-y	+= md-linear.o
 multipath-y	+= md-multipath.o
 faulty-y	+= md-faulty.o
@@ -59,14 +64,15 @@ obj-$(CONFIG_DM_MULTIPATH)	+= dm-multipath.o dm-round-robin.o
 obj-$(CONFIG_DM_MULTIPATH_QL)	+= dm-queue-length.o
 obj-$(CONFIG_DM_MULTIPATH_ST)	+= dm-service-time.o
 obj-$(CONFIG_DM_MULTIPATH_HST)	+= dm-historical-service-time.o
+obj-$(CONFIG_DM_MULTIPATH_IOA)	+= dm-io-affinity.o
 obj-$(CONFIG_DM_SWITCH)		+= dm-switch.o
 obj-$(CONFIG_DM_SNAPSHOT)	+= dm-snapshot.o
-obj-$(CONFIG_DM_PERSISTENT_DATA)	+= persistent-data/
+obj-$(CONFIG_DM_PERSISTENT_DATA) += persistent-data/
 obj-$(CONFIG_DM_MIRROR)		+= dm-mirror.o dm-log.o dm-region-hash.o
 obj-$(CONFIG_DM_LOG_USERSPACE)	+= dm-log-userspace.o
 obj-$(CONFIG_DM_ZERO)		+= dm-zero.o
-obj-$(CONFIG_DM_RAID)	+= dm-raid.o
-obj-$(CONFIG_DM_THIN_PROVISIONING)	+= dm-thin-pool.o
+obj-$(CONFIG_DM_RAID)		+= dm-raid.o
+obj-$(CONFIG_DM_THIN_PROVISIONING) += dm-thin-pool.o
 obj-$(CONFIG_DM_VERITY)		+= dm-verity.o
 obj-$(CONFIG_DM_CACHE)		+= dm-cache.o
 obj-$(CONFIG_DM_CACHE_SMQ)	+= dm-cache-smq.o
diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c
index 6469223f0b77..d636b7b2d070 100644
--- a/drivers/md/bcache/features.c
+++ b/drivers/md/bcache/features.c
@@ -17,7 +17,7 @@ struct feature {
 };
 
 static struct feature feature_list[] = {
-	{BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LARGE_BUCKET,
+	{BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE,
 		"large_bucket"},
 	{0, 0, 0 },
 };
diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h
index a1653c478041..84fc2c0f0101 100644
--- a/drivers/md/bcache/features.h
+++ b/drivers/md/bcache/features.h
@@ -13,11 +13,15 @@
 
 /* Feature set definition */
 /* Incompat feature set */
-#define BCH_FEATURE_INCOMPAT_LARGE_BUCKET	0x0001 /* 32bit bucket size */
+/* 32bit bucket size, obsoleted */
+#define BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET		0x0001
+/* real bucket size is (1 << bucket_size) */
+#define BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE	0x0002
 
-#define BCH_FEATURE_COMPAT_SUUP		0
-#define BCH_FEATURE_RO_COMPAT_SUUP	0
-#define BCH_FEATURE_INCOMPAT_SUUP	BCH_FEATURE_INCOMPAT_LARGE_BUCKET
+#define BCH_FEATURE_COMPAT_SUPP		0
+#define BCH_FEATURE_RO_COMPAT_SUPP	0
+#define BCH_FEATURE_INCOMPAT_SUPP	(BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET| \
+					 BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE)
 
 #define BCH_HAS_COMPAT_FEATURE(sb, mask) \
 		((sb)->feature_compat & (mask))
@@ -77,7 +81,23 @@ static inline void bch_clear_feature_##name(struct cache_sb *sb) \
 		~BCH##_FEATURE_INCOMPAT_##flagname; \
 }
 
-BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LARGE_BUCKET);
+BCH_FEATURE_INCOMPAT_FUNCS(obso_large_bucket, OBSO_LARGE_BUCKET);
+BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LOG_LARGE_BUCKET_SIZE);
+
+static inline bool bch_has_unknown_compat_features(struct cache_sb *sb)
+{
+	return ((sb->feature_compat & ~BCH_FEATURE_COMPAT_SUPP) != 0);
+}
+
+static inline bool bch_has_unknown_ro_compat_features(struct cache_sb *sb)
+{
+	return ((sb->feature_ro_compat & ~BCH_FEATURE_RO_COMPAT_SUPP) != 0);
+}
+
+static inline bool bch_has_unknown_incompat_features(struct cache_sb *sb)
+{
+	return ((sb->feature_incompat & ~BCH_FEATURE_INCOMPAT_SUPP) != 0);
+}
 
 int bch_print_cache_set_feature_compat(struct cache_set *c, char *buf, int size);
 int bch_print_cache_set_feature_ro_compat(struct cache_set *c, char *buf, int size);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 0e06d721cd8e..2047a9cccdb5 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -64,9 +64,25 @@ static unsigned int get_bucket_size(struct cache_sb *sb, struct cache_sb_disk *s
 {
 	unsigned int bucket_size = le16_to_cpu(s->bucket_size);
 
-	if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES &&
-	     bch_has_feature_large_bucket(sb))
-		bucket_size |= le16_to_cpu(s->bucket_size_hi) << 16;
+	if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES) {
+		if (bch_has_feature_large_bucket(sb)) {
+			unsigned int max, order;
+
+			max = sizeof(unsigned int) * BITS_PER_BYTE - 1;
+			order = le16_to_cpu(s->bucket_size);
+			/*
+			 * bcache tool will make sure the overflow won't
+			 * happen, an error message here is enough.
+			 */
+			if (order > max)
+				pr_err("Bucket size (1 << %u) overflows\n",
+					order);
+			bucket_size = 1 << order;
+		} else if (bch_has_feature_obso_large_bucket(sb)) {
+			bucket_size +=
+				le16_to_cpu(s->obso_bucket_size_hi) << 16;
+		}
+	}
 
 	return bucket_size;
 }
@@ -228,6 +244,20 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 		sb->feature_compat = le64_to_cpu(s->feature_compat);
 		sb->feature_incompat = le64_to_cpu(s->feature_incompat);
 		sb->feature_ro_compat = le64_to_cpu(s->feature_ro_compat);
+
+		/* Check incompatible features */
+		err = "Unsupported compatible feature found";
+		if (bch_has_unknown_compat_features(sb))
+			goto err;
+
+		err = "Unsupported read-only compatible feature found";
+		if (bch_has_unknown_ro_compat_features(sb))
+			goto err;
+
+		err = "Unsupported incompatible feature found";
+		if (bch_has_unknown_incompat_features(sb))
+			goto err;
+
 		err = read_super_common(sb, bdev, s);
 		if (err)
 			goto err;
@@ -1302,6 +1332,12 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	bcache_device_link(&dc->disk, c, "bdev");
 	atomic_inc(&c->attached_dev_nr);
 
+	if (bch_has_feature_obso_large_bucket(&(c->cache->sb))) {
+		pr_err("The obsoleted large bucket layout is unsupported, set the bcache device into read-only\n");
+		pr_err("Please update to the latest bcache-tools to create the cache device\n");
+		set_disk_ro(dc->disk.disk, 1);
+	}
+
 	/* Allow the writeback thread to proceed */
 	up_write(&dc->writeback_lock);
 
@@ -1524,6 +1560,12 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
 
 	bcache_device_link(d, c, "volume");
 
+	if (bch_has_feature_obso_large_bucket(&c->cache->sb)) {
+		pr_err("The obsoleted large bucket layout is unsupported, set the bcache device into read-only\n");
+		pr_err("Please update to the latest bcache-tools to create the cache device\n");
+		set_disk_ro(d->disk, 1);
+	}
+
 	return 0;
 err:
 	kobject_put(&d->kobj);
@@ -2083,6 +2125,9 @@ static int run_cache_set(struct cache_set *c)
 	c->cache->sb.last_mount = (u32)ktime_get_real_seconds();
 	bcache_write_super(c);
 
+	if (bch_has_feature_obso_large_bucket(&c->cache->sb))
+		pr_err("Detect obsoleted large bucket layout, all attached bcache device will be read-only\n");
+
 	list_for_each_entry_safe(dc, t, &uncached_devices, list)
 		bch_cached_dev_attach(dc, c, NULL);
 
@@ -2535,8 +2580,6 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 			else
 				err = "device busy";
 			mutex_unlock(&bch_register_lock);
-			if (!IS_ERR(bdev))
-				bdput(bdev);
 			if (attr == &ksysfs_register_quiet)
 				goto done;
 		}
@@ -2646,8 +2689,8 @@ static ssize_t bch_pending_bdevs_cleanup(struct kobject *k,
 	}
 
 	list_for_each_entry_safe(pdev, tpdev, &pending_devs, list) {
+		char *pdev_set_uuid = pdev->dc->sb.set_uuid;
 		list_for_each_entry_safe(c, tc, &bch_cache_sets, list) {
-			char *pdev_set_uuid = pdev->dc->sb.set_uuid;
 			char *set_uuid = c->set_uuid;
 
 			if (!memcmp(pdev_set_uuid, set_uuid, 16)) {
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 554e3afc9b68..00a520c03f41 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -404,7 +404,7 @@ STORE(__cached_dev)
 		if (!env)
 			return -ENOMEM;
 		add_uevent_var(env, "DRIVER=bcache");
-		add_uevent_var(env, "CACHED_UUID=%pU", dc->sb.uuid),
+		add_uevent_var(env, "CACHED_UUID=%pU", dc->sb.uuid);
 		add_uevent_var(env, "CACHED_LABEL=%s", buf);
 		kobject_uevent_env(&disk_to_dev(dc->disk.disk)->kobj,
 				   KOBJ_CHANGE,
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 9c1a86bde658..fce4cbf9529d 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1534,6 +1534,12 @@ sector_t dm_bufio_get_device_size(struct dm_bufio_client *c)
 }
 EXPORT_SYMBOL_GPL(dm_bufio_get_device_size);
 
+struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c)
+{
+	return c->dm_io;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_dm_io_client);
+
 sector_t dm_bufio_get_block_number(struct dm_buffer *b)
 {
 	return b->block;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 4bc453f5bbaa..541c45027cc8 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -2840,7 +2840,6 @@ static void cache_postsuspend(struct dm_target *ti)
 static int load_mapping(void *context, dm_oblock_t oblock, dm_cblock_t cblock,
 			bool dirty, uint32_t hint, bool hint_valid)
 {
-	int r;
 	struct cache *cache = context;
 
 	if (dirty) {
@@ -2849,11 +2848,7 @@ static int load_mapping(void *context, dm_oblock_t oblock, dm_cblock_t cblock,
 	} else
 		clear_bit(from_cblock(cblock), cache->dirty_bitset);
 
-	r = policy_load_mapping(cache->policy, oblock, cblock, dirty, hint, hint_valid);
-	if (r)
-		return r;
-
-	return 0;
+	return policy_load_mapping(cache->policy, oblock, cblock, dirty, hint, hint_valid);
 }
 
 /*
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 392337f16ecf..8c874710f0bc 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1090,16 +1090,16 @@ static const struct crypt_iv_operations crypt_iv_tcw_ops = {
 	.post	   = crypt_iv_tcw_post
 };
 
-static struct crypt_iv_operations crypt_iv_random_ops = {
+static const struct crypt_iv_operations crypt_iv_random_ops = {
 	.generator = crypt_iv_random_gen
 };
 
-static struct crypt_iv_operations crypt_iv_eboiv_ops = {
+static const struct crypt_iv_operations crypt_iv_eboiv_ops = {
 	.ctr	   = crypt_iv_eboiv_ctr,
 	.generator = crypt_iv_eboiv_gen
 };
 
-static struct crypt_iv_operations crypt_iv_elephant_ops = {
+static const struct crypt_iv_operations crypt_iv_elephant_ops = {
 	.ctr	   = crypt_iv_elephant_ctr,
 	.dtr	   = crypt_iv_elephant_dtr,
 	.init	   = crypt_iv_elephant_init,
@@ -1454,13 +1454,16 @@ static int crypt_convert_block_skcipher(struct crypt_config *cc,
 static void kcryptd_async_done(struct crypto_async_request *async_req,
 			       int error);
 
-static void crypt_alloc_req_skcipher(struct crypt_config *cc,
+static int crypt_alloc_req_skcipher(struct crypt_config *cc,
 				     struct convert_context *ctx)
 {
 	unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
 
-	if (!ctx->r.req)
-		ctx->r.req = mempool_alloc(&cc->req_pool, GFP_NOIO);
+	if (!ctx->r.req) {
+		ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO);
+		if (!ctx->r.req)
+			return -ENOMEM;
+	}
 
 	skcipher_request_set_tfm(ctx->r.req, cc->cipher_tfm.tfms[key_index]);
 
@@ -1471,13 +1474,18 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc,
 	skcipher_request_set_callback(ctx->r.req,
 	    CRYPTO_TFM_REQ_MAY_BACKLOG,
 	    kcryptd_async_done, dmreq_of_req(cc, ctx->r.req));
+
+	return 0;
 }
 
-static void crypt_alloc_req_aead(struct crypt_config *cc,
+static int crypt_alloc_req_aead(struct crypt_config *cc,
 				 struct convert_context *ctx)
 {
-	if (!ctx->r.req_aead)
-		ctx->r.req_aead = mempool_alloc(&cc->req_pool, GFP_NOIO);
+	if (!ctx->r.req) {
+		ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO);
+		if (!ctx->r.req)
+			return -ENOMEM;
+	}
 
 	aead_request_set_tfm(ctx->r.req_aead, cc->cipher_tfm.tfms_aead[0]);
 
@@ -1488,15 +1496,17 @@ static void crypt_alloc_req_aead(struct crypt_config *cc,
 	aead_request_set_callback(ctx->r.req_aead,
 	    CRYPTO_TFM_REQ_MAY_BACKLOG,
 	    kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead));
+
+	return 0;
 }
 
-static void crypt_alloc_req(struct crypt_config *cc,
+static int crypt_alloc_req(struct crypt_config *cc,
 			    struct convert_context *ctx)
 {
 	if (crypt_integrity_aead(cc))
-		crypt_alloc_req_aead(cc, ctx);
+		return crypt_alloc_req_aead(cc, ctx);
 	else
-		crypt_alloc_req_skcipher(cc, ctx);
+		return crypt_alloc_req_skcipher(cc, ctx);
 }
 
 static void crypt_free_req_skcipher(struct crypt_config *cc,
@@ -1529,17 +1539,28 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_
  * Encrypt / decrypt data from one bio to another one (can be the same one)
  */
 static blk_status_t crypt_convert(struct crypt_config *cc,
-			 struct convert_context *ctx, bool atomic)
+			 struct convert_context *ctx, bool atomic, bool reset_pending)
 {
 	unsigned int tag_offset = 0;
 	unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT;
 	int r;
 
-	atomic_set(&ctx->cc_pending, 1);
+	/*
+	 * if reset_pending is set we are dealing with the bio for the first time,
+	 * else we're continuing to work on the previous bio, so don't mess with
+	 * the cc_pending counter
+	 */
+	if (reset_pending)
+		atomic_set(&ctx->cc_pending, 1);
 
 	while (ctx->iter_in.bi_size && ctx->iter_out.bi_size) {
 
-		crypt_alloc_req(cc, ctx);
+		r = crypt_alloc_req(cc, ctx);
+		if (r) {
+			complete(&ctx->restart);
+			return BLK_STS_DEV_RESOURCE;
+		}
+
 		atomic_inc(&ctx->cc_pending);
 
 		if (crypt_integrity_aead(cc))
@@ -1553,7 +1574,25 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		 * but the driver request queue is full, let's wait.
 		 */
 		case -EBUSY:
-			wait_for_completion(&ctx->restart);
+			if (in_interrupt()) {
+				if (try_wait_for_completion(&ctx->restart)) {
+					/*
+					 * we don't have to block to wait for completion,
+					 * so proceed
+					 */
+				} else {
+					/*
+					 * we can't wait for completion without blocking
+					 * exit and continue processing in a workqueue
+					 */
+					ctx->r.req = NULL;
+					ctx->cc_sector += sector_step;
+					tag_offset++;
+					return BLK_STS_DEV_RESOURCE;
+				}
+			} else {
+				wait_for_completion(&ctx->restart);
+			}
 			reinit_completion(&ctx->restart);
 			fallthrough;
 		/*
@@ -1691,6 +1730,12 @@ static void crypt_inc_pending(struct dm_crypt_io *io)
 	atomic_inc(&io->io_pending);
 }
 
+static void kcryptd_io_bio_endio(struct work_struct *work)
+{
+	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+	bio_endio(io->base_bio);
+}
+
 /*
  * One of the bios was finished. Check for completion of
  * the whole request and correctly clean up the buffer.
@@ -1713,7 +1758,23 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 		kfree(io->integrity_metadata);
 
 	base_bio->bi_status = error;
-	bio_endio(base_bio);
+
+	/*
+	 * If we are running this function from our tasklet,
+	 * we can't call bio_endio() here, because it will call
+	 * clone_endio() from dm.c, which in turn will
+	 * free the current struct dm_crypt_io structure with
+	 * our tasklet. In this case we need to delay bio_endio()
+	 * execution to after the tasklet is done and dequeued.
+	 */
+	if (tasklet_trylock(&io->tasklet)) {
+		tasklet_unlock(&io->tasklet);
+		bio_endio(base_bio);
+		return;
+	}
+
+	INIT_WORK(&io->work, kcryptd_io_bio_endio);
+	queue_work(cc->io_queue, &io->work);
 }
 
 /*
@@ -1945,6 +2006,37 @@ static bool kcryptd_crypt_write_inline(struct crypt_config *cc,
 	}
 }
 
+static void kcryptd_crypt_write_continue(struct work_struct *work)
+{
+	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+	struct crypt_config *cc = io->cc;
+	struct convert_context *ctx = &io->ctx;
+	int crypt_finished;
+	sector_t sector = io->sector;
+	blk_status_t r;
+
+	wait_for_completion(&ctx->restart);
+	reinit_completion(&ctx->restart);
+
+	r = crypt_convert(cc, &io->ctx, true, false);
+	if (r)
+		io->error = r;
+	crypt_finished = atomic_dec_and_test(&ctx->cc_pending);
+	if (!crypt_finished && kcryptd_crypt_write_inline(cc, ctx)) {
+		/* Wait for completion signaled by kcryptd_async_done() */
+		wait_for_completion(&ctx->restart);
+		crypt_finished = 1;
+	}
+
+	/* Encryption was already finished, submit io now */
+	if (crypt_finished) {
+		kcryptd_crypt_write_io_submit(io, 0);
+		io->sector = sector;
+	}
+
+	crypt_dec_pending(io);
+}
+
 static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
@@ -1973,7 +2065,17 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 
 	crypt_inc_pending(io);
 	r = crypt_convert(cc, ctx,
-			  test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags));
+			  test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true);
+	/*
+	 * Crypto API backlogged the request, because its queue was full
+	 * and we're in softirq context, so continue from a workqueue
+	 * (TODO: is it actually possible to be in softirq in the write path?)
+	 */
+	if (r == BLK_STS_DEV_RESOURCE) {
+		INIT_WORK(&io->work, kcryptd_crypt_write_continue);
+		queue_work(cc->crypt_queue, &io->work);
+		return;
+	}
 	if (r)
 		io->error = r;
 	crypt_finished = atomic_dec_and_test(&ctx->cc_pending);
@@ -1998,6 +2100,25 @@ static void kcryptd_crypt_read_done(struct dm_crypt_io *io)
 	crypt_dec_pending(io);
 }
 
+static void kcryptd_crypt_read_continue(struct work_struct *work)
+{
+	struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+	struct crypt_config *cc = io->cc;
+	blk_status_t r;
+
+	wait_for_completion(&io->ctx.restart);
+	reinit_completion(&io->ctx.restart);
+
+	r = crypt_convert(cc, &io->ctx, true, false);
+	if (r)
+		io->error = r;
+
+	if (atomic_dec_and_test(&io->ctx.cc_pending))
+		kcryptd_crypt_read_done(io);
+
+	crypt_dec_pending(io);
+}
+
 static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
@@ -2009,7 +2130,16 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 			   io->sector);
 
 	r = crypt_convert(cc, &io->ctx,
-			  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags));
+			  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+	/*
+	 * Crypto API backlogged the request, because its queue was full
+	 * and we're in softirq context, so continue from a workqueue
+	 */
+	if (r == BLK_STS_DEV_RESOURCE) {
+		INIT_WORK(&io->work, kcryptd_crypt_read_continue);
+		queue_work(cc->crypt_queue, &io->work);
+		return;
+	}
 	if (r)
 		io->error = r;
 
@@ -2091,8 +2221,12 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io)
 
 	if ((bio_data_dir(io->base_bio) == READ && test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags)) ||
 	    (bio_data_dir(io->base_bio) == WRITE && test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags))) {
-		if (in_irq()) {
-			/* Crypto API's "skcipher_walk_first() refuses to work in hard IRQ context */
+		/*
+		 * in_irq(): Crypto API's skcipher_walk_first() refuses to work in hard IRQ context.
+		 * irqs_disabled(): the kernel may run some IO completion from the idle thread, but
+		 * it is being executed with irqs disabled.
+		 */
+		if (in_irq() || irqs_disabled()) {
 			tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work);
 			tasklet_schedule(&io->tasklet);
 			return;
diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c
index cb85610527c2..55bcfb74f51f 100644
--- a/drivers/md/dm-ebs-target.c
+++ b/drivers/md/dm-ebs-target.c
@@ -86,7 +86,7 @@ static int __ebs_rw_bvec(struct ebs_c *ec, int rw, struct bio_vec *bv, struct bv
 		else
 			ba = dm_bufio_new(ec->bufio, block, &b);
 
-		if (unlikely(IS_ERR(ba))) {
+		if (IS_ERR(ba)) {
 			/*
 			 * Carry on with next buffer, if any, to issue all possible
 			 * data but return error.
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 5a7a1b90e671..81df019ab284 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -1379,12 +1379,52 @@ thorough_test:
 #undef MAY_BE_HASH
 }
 
-static void dm_integrity_flush_buffers(struct dm_integrity_c *ic)
+struct flush_request {
+	struct dm_io_request io_req;
+	struct dm_io_region io_reg;
+	struct dm_integrity_c *ic;
+	struct completion comp;
+};
+
+static void flush_notify(unsigned long error, void *fr_)
+{
+	struct flush_request *fr = fr_;
+	if (unlikely(error != 0))
+		dm_integrity_io_error(fr->ic, "flusing disk cache", -EIO);
+	complete(&fr->comp);
+}
+
+static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_data)
 {
 	int r;
+
+	struct flush_request fr;
+
+	if (!ic->meta_dev)
+		flush_data = false;
+	if (flush_data) {
+		fr.io_req.bi_op = REQ_OP_WRITE,
+		fr.io_req.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
+		fr.io_req.mem.type = DM_IO_KMEM,
+		fr.io_req.mem.ptr.addr = NULL,
+		fr.io_req.notify.fn = flush_notify,
+		fr.io_req.notify.context = &fr;
+		fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio),
+		fr.io_reg.bdev = ic->dev->bdev,
+		fr.io_reg.sector = 0,
+		fr.io_reg.count = 0,
+		fr.ic = ic;
+		init_completion(&fr.comp);
+		r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL);
+		BUG_ON(r);
+	}
+
 	r = dm_bufio_write_dirty_buffers(ic->bufio);
 	if (unlikely(r))
 		dm_integrity_io_error(ic, "writing tags", r);
+
+	if (flush_data)
+		wait_for_completion(&fr.comp);
 }
 
 static void sleep_on_endio_wait(struct dm_integrity_c *ic)
@@ -2110,7 +2150,7 @@ offload_to_thread:
 
 	if (unlikely(dio->op == REQ_OP_DISCARD) && likely(ic->mode != 'D')) {
 		integrity_metadata(&dio->work);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, false);
 
 		dio->in_flight = (atomic_t)ATOMIC_INIT(1);
 		dio->completion = NULL;
@@ -2195,7 +2235,7 @@ static void integrity_commit(struct work_struct *w)
 	flushes = bio_list_get(&ic->flush_bio_list);
 	if (unlikely(ic->mode != 'J')) {
 		spin_unlock_irq(&ic->endio_wait.lock);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 		goto release_flush_bios;
 	}
 
@@ -2409,7 +2449,7 @@ skip_io:
 	complete_journal_op(&comp);
 	wait_for_completion_io(&comp.comp);
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, true);
 }
 
 static void integrity_writer(struct work_struct *w)
@@ -2451,7 +2491,7 @@ static void recalc_write_super(struct dm_integrity_c *ic)
 {
 	int r;
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, false);
 	if (dm_integrity_failed(ic))
 		return;
 
@@ -2654,7 +2694,7 @@ static void bitmap_flush_work(struct work_struct *work)
 	unsigned long limit;
 	struct bio *bio;
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, false);
 
 	range.logical_sector = 0;
 	range.n_sectors = ic->provided_data_sectors;
@@ -2663,9 +2703,7 @@ static void bitmap_flush_work(struct work_struct *work)
 	add_new_range_and_wait(ic, &range);
 	spin_unlock_irq(&ic->endio_wait.lock);
 
-	dm_integrity_flush_buffers(ic);
-	if (ic->meta_dev)
-		blkdev_issue_flush(ic->dev->bdev, GFP_NOIO);
+	dm_integrity_flush_buffers(ic, true);
 
 	limit = ic->provided_data_sectors;
 	if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
@@ -2934,11 +2972,11 @@ static void dm_integrity_postsuspend(struct dm_target *ti)
 		if (ic->meta_dev)
 			queue_work(ic->writer_wq, &ic->writer_work);
 		drain_workqueue(ic->writer_wq);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 	}
 
 	if (ic->mode == 'B') {
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 #if 1
 		/* set to 0 to test bitmap replay code */
 		init_journal(ic, 0, ic->journal_sections, 0);
@@ -3754,7 +3792,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	unsigned extra_args;
 	struct dm_arg_set as;
 	static const struct dm_arg _args[] = {
-		{0, 9, "Invalid number of feature args"},
+		{0, 15, "Invalid number of feature args"},
 	};
 	unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec;
 	bool should_write_sb;
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index cd0478d44058..5e306bba4375 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1600,6 +1600,7 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para
 
 	if (!argc) {
 		DMWARN("Empty message received.");
+		r = -EINVAL;
 		goto out_argv;
 	}
 
diff --git a/drivers/md/dm-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c
index 186f91e2752c..186f91e2752c 100644
--- a/drivers/md/dm-historical-service-time.c
+++ b/drivers/md/dm-ps-historical-service-time.c
diff --git a/drivers/md/dm-ps-io-affinity.c b/drivers/md/dm-ps-io-affinity.c
new file mode 100644
index 000000000000..077655cd4fae
--- /dev/null
+++ b/drivers/md/dm-ps-io-affinity.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Oracle Corporation
+ *
+ * Module Author: Mike Christie
+ */
+#include "dm-path-selector.h"
+
+#include <linux/device-mapper.h>
+#include <linux/module.h>
+
+#define DM_MSG_PREFIX "multipath io-affinity"
+
+struct path_info {
+	struct dm_path *path;
+	cpumask_var_t cpumask;
+	refcount_t refcount;
+	bool failed;
+};
+
+struct selector {
+	struct path_info **path_map;
+	cpumask_var_t path_mask;
+	atomic_t map_misses;
+};
+
+static void ioa_free_path(struct selector *s, unsigned int cpu)
+{
+	struct path_info *pi = s->path_map[cpu];
+
+	if (!pi)
+		return;
+
+	if (refcount_dec_and_test(&pi->refcount)) {
+		cpumask_clear_cpu(cpu, s->path_mask);
+		free_cpumask_var(pi->cpumask);
+		kfree(pi);
+
+		s->path_map[cpu] = NULL;
+	}
+}
+
+static int ioa_add_path(struct path_selector *ps, struct dm_path *path,
+			int argc, char **argv, char **error)
+{
+	struct selector *s = ps->context;
+	struct path_info *pi = NULL;
+	unsigned int cpu;
+	int ret;
+
+	if (argc != 1) {
+		*error = "io-affinity ps: invalid number of arguments";
+		return -EINVAL;
+	}
+
+	pi = kzalloc(sizeof(*pi), GFP_KERNEL);
+	if (!pi) {
+		*error = "io-affinity ps: Error allocating path context";
+		return -ENOMEM;
+	}
+
+	pi->path = path;
+	path->pscontext = pi;
+	refcount_set(&pi->refcount, 1);
+
+	if (!zalloc_cpumask_var(&pi->cpumask, GFP_KERNEL)) {
+		*error = "io-affinity ps: Error allocating cpumask context";
+		ret = -ENOMEM;
+		goto free_pi;
+	}
+
+	ret = cpumask_parse(argv[0], pi->cpumask);
+	if (ret) {
+		*error = "io-affinity ps: invalid cpumask";
+		ret = -EINVAL;
+		goto free_mask;
+	}
+
+	for_each_cpu(cpu, pi->cpumask) {
+		if (cpu >= nr_cpu_ids) {
+			DMWARN_LIMIT("Ignoring mapping for CPU %u. Max CPU is %u",
+				     cpu, nr_cpu_ids);
+			break;
+		}
+
+		if (s->path_map[cpu]) {
+			DMWARN("CPU mapping for %u exists. Ignoring.", cpu);
+			continue;
+		}
+
+		cpumask_set_cpu(cpu, s->path_mask);
+		s->path_map[cpu] = pi;
+		refcount_inc(&pi->refcount);
+		continue;
+	}
+
+	if (refcount_dec_and_test(&pi->refcount)) {
+		*error = "io-affinity ps: No new/valid CPU mapping found";
+		ret = -EINVAL;
+		goto free_mask;
+	}
+
+	return 0;
+
+free_mask:
+	free_cpumask_var(pi->cpumask);
+free_pi:
+	kfree(pi);
+	return ret;
+}
+
+static int ioa_create(struct path_selector *ps, unsigned argc, char **argv)
+{
+	struct selector *s;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	s->path_map = kzalloc(nr_cpu_ids * sizeof(struct path_info *),
+			      GFP_KERNEL);
+	if (!s->path_map)
+		goto free_selector;
+
+	if (!zalloc_cpumask_var(&s->path_mask, GFP_KERNEL))
+		goto free_map;
+
+	atomic_set(&s->map_misses, 0);
+	ps->context = s;
+	return 0;
+
+free_map:
+	kfree(s->path_map);
+free_selector:
+	kfree(s);
+	return -ENOMEM;
+}
+
+static void ioa_destroy(struct path_selector *ps)
+{
+	struct selector *s = ps->context;
+	unsigned cpu;
+
+	for_each_cpu(cpu, s->path_mask)
+		ioa_free_path(s, cpu);
+
+	free_cpumask_var(s->path_mask);
+	kfree(s->path_map);
+	kfree(s);
+
+	ps->context = NULL;
+}
+
+static int ioa_status(struct path_selector *ps, struct dm_path *path,
+		      status_type_t type, char *result, unsigned int maxlen)
+{
+	struct selector *s = ps->context;
+	struct path_info *pi;
+	int sz = 0;
+
+	if (!path) {
+		DMEMIT("0 ");
+		return sz;
+	}
+
+	switch(type) {
+	case STATUSTYPE_INFO:
+		DMEMIT("%d ", atomic_read(&s->map_misses));
+		break;
+	case STATUSTYPE_TABLE:
+		pi = path->pscontext;
+		DMEMIT("%*pb ", cpumask_pr_args(pi->cpumask));
+		break;
+	}
+
+	return sz;
+}
+
+static void ioa_fail_path(struct path_selector *ps, struct dm_path *p)
+{
+	struct path_info *pi = p->pscontext;
+
+	pi->failed = true;
+}
+
+static int ioa_reinstate_path(struct path_selector *ps, struct dm_path *p)
+{
+	struct path_info *pi = p->pscontext;
+
+	pi->failed = false;
+	return 0;
+}
+
+static struct dm_path *ioa_select_path(struct path_selector *ps,
+				       size_t nr_bytes)
+{
+	unsigned int cpu, node;
+	struct selector *s = ps->context;
+	const struct cpumask *cpumask;
+	struct path_info *pi;
+	int i;
+
+	cpu = get_cpu();
+
+	pi = s->path_map[cpu];
+	if (pi && !pi->failed)
+		goto done;
+
+	/*
+	 * Perf is not optimal, but we at least try the local node then just
+	 * try not to fail.
+	 */
+	if (!pi)
+		atomic_inc(&s->map_misses);
+
+	node = cpu_to_node(cpu);
+	cpumask = cpumask_of_node(node);
+	for_each_cpu(i, cpumask) {
+		pi = s->path_map[i];
+		if (pi && !pi->failed)
+			goto done;
+	}
+
+	for_each_cpu(i, s->path_mask) {
+		pi = s->path_map[i];
+		if (pi && !pi->failed)
+			goto done;
+	}
+	pi = NULL;
+
+done:
+	put_cpu();
+	return pi ? pi->path : NULL;
+}
+
+static struct path_selector_type ioa_ps = {
+	.name		= "io-affinity",
+	.module		= THIS_MODULE,
+	.table_args	= 1,
+	.info_args	= 1,
+	.create		= ioa_create,
+	.destroy	= ioa_destroy,
+	.status		= ioa_status,
+	.add_path	= ioa_add_path,
+	.fail_path	= ioa_fail_path,
+	.reinstate_path	= ioa_reinstate_path,
+	.select_path	= ioa_select_path,
+};
+
+static int __init dm_ioa_init(void)
+{
+	int ret = dm_register_path_selector(&ioa_ps);
+
+	if (ret < 0)
+		DMERR("register failed %d", ret);
+	return ret;
+}
+
+static void __exit dm_ioa_exit(void)
+{
+	int ret = dm_unregister_path_selector(&ioa_ps);
+
+	if (ret < 0)
+		DMERR("unregister failed %d", ret);
+}
+
+module_init(dm_ioa_init);
+module_exit(dm_ioa_exit);
+
+MODULE_DESCRIPTION(DM_NAME " multipath path selector that selects paths based on the CPU IO is being executed on");
+MODULE_AUTHOR("Mike Christie <michael.christie@oracle.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm-queue-length.c b/drivers/md/dm-ps-queue-length.c
index 5fd018d18418..5fd018d18418 100644
--- a/drivers/md/dm-queue-length.c
+++ b/drivers/md/dm-ps-queue-length.c
diff --git a/drivers/md/dm-round-robin.c b/drivers/md/dm-ps-round-robin.c
index bdbb7e6e8212..bdbb7e6e8212 100644
--- a/drivers/md/dm-round-robin.c
+++ b/drivers/md/dm-ps-round-robin.c
diff --git a/drivers/md/dm-service-time.c b/drivers/md/dm-ps-service-time.c
index 9cfda665e9eb..9cfda665e9eb 100644
--- a/drivers/md/dm-service-time.c
+++ b/drivers/md/dm-ps-service-time.c
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 23c38777e8f6..cab12b2251ba 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3729,10 +3729,10 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs));
 
 	/*
-	 * RAID1 and RAID10 personalities require bio splitting,
-	 * RAID0/4/5/6 don't and process large discard bios properly.
+	 * RAID0 and RAID10 personalities require bio splitting,
+	 * RAID1/4/5/6 don't and process large discard bios properly.
 	 */
-	if (rs_is_raid1(rs) || rs_is_raid10(rs)) {
+	if (rs_is_raid0(rs) || rs_is_raid10(rs)) {
 		limits->discard_granularity = chunk_size_bytes;
 		limits->max_discard_sectors = rs->md.chunk_sectors;
 	}
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 4668b2cd98f4..11890db71f3f 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -141,6 +141,11 @@ struct dm_snapshot {
 	 * for them to be committed.
 	 */
 	struct bio_list bios_queued_during_merge;
+
+	/*
+	 * Flush data after merge.
+	 */
+	struct bio flush_bio;
 };
 
 /*
@@ -1121,6 +1126,17 @@ shut:
 
 static void error_bios(struct bio *bio);
 
+static int flush_data(struct dm_snapshot *s)
+{
+	struct bio *flush_bio = &s->flush_bio;
+
+	bio_reset(flush_bio);
+	bio_set_dev(flush_bio, s->origin->bdev);
+	flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+
+	return submit_bio_wait(flush_bio);
+}
+
 static void merge_callback(int read_err, unsigned long write_err, void *context)
 {
 	struct dm_snapshot *s = context;
@@ -1134,6 +1150,11 @@ static void merge_callback(int read_err, unsigned long write_err, void *context)
 		goto shut;
 	}
 
+	if (flush_data(s) < 0) {
+		DMERR("Flush after merge failed: shutting down merge");
+		goto shut;
+	}
+
 	if (s->store->type->commit_merge(s->store,
 					 s->num_merging_chunks) < 0) {
 		DMERR("Write error in exception store: shutting down merge");
@@ -1318,6 +1339,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	s->first_merging_chunk = 0;
 	s->num_merging_chunks = 0;
 	bio_list_init(&s->bios_queued_during_merge);
+	bio_init(&s->flush_bio, NULL, 0);
 
 	/* Allocate hash table for COW data */
 	if (init_hash_tables(s)) {
@@ -1504,6 +1526,8 @@ static void snapshot_dtr(struct dm_target *ti)
 
 	dm_exception_store_destroy(s->store);
 
+	bio_uninit(&s->flush_bio);
+
 	dm_put_device(ti, s->cow);
 
 	dm_put_device(ti, s->origin);
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 151d022b032d..df359d33cda8 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -496,7 +496,7 @@ static void stripe_io_hints(struct dm_target *ti,
 static struct target_type stripe_target = {
 	.name   = "striped",
 	.version = {1, 6, 0},
-	.features = DM_TARGET_PASSES_INTEGRITY,
+	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT,
 	.module = THIS_MODULE,
 	.ctr    = stripe_ctr,
 	.dtr    = stripe_dtr,
diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c
index bff4c7fa1cd2..262e2b0fd975 100644
--- a/drivers/md/dm-switch.c
+++ b/drivers/md/dm-switch.c
@@ -550,6 +550,7 @@ static int switch_iterate_devices(struct dm_target *ti,
 static struct target_type switch_target = {
 	.name = "switch",
 	.version = {1, 1, 0},
+	.features = DM_TARGET_NOWAIT,
 	.module = THIS_MODULE,
 	.ctr = switch_ctr,
 	.dtr = switch_dtr,
diff --git a/drivers/md/dm-unstripe.c b/drivers/md/dm-unstripe.c
index e673dacf6418..7357c1bd5863 100644
--- a/drivers/md/dm-unstripe.c
+++ b/drivers/md/dm-unstripe.c
@@ -178,6 +178,7 @@ static void unstripe_io_hints(struct dm_target *ti,
 static struct target_type unstripe_target = {
 	.name = "unstriped",
 	.version = {1, 1, 0},
+	.features = DM_TARGET_NOWAIT,
 	.module = THIS_MODULE,
 	.ctr = unstripe_ctr,
 	.dtr = unstripe_dtr,
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index f74982dcbea0..6b8e5bdd8526 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -538,6 +538,15 @@ static int verity_verify_io(struct dm_verity_io *io)
 }
 
 /*
+ * Skip verity work in response to I/O error when system is shutting down.
+ */
+static inline bool verity_is_system_shutting_down(void)
+{
+	return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF
+		|| system_state == SYSTEM_RESTART;
+}
+
+/*
  * End one "io" structure with a given error.
  */
 static void verity_finish_io(struct dm_verity_io *io, blk_status_t status)
@@ -564,7 +573,8 @@ static void verity_end_io(struct bio *bio)
 {
 	struct dm_verity_io *io = bio->bi_private;
 
-	if (bio->bi_status && !verity_fec_is_enabled(io->v)) {
+	if (bio->bi_status &&
+	    (!verity_fec_is_enabled(io->v) || verity_is_system_shutting_down())) {
 		verity_finish_io(io, bio->bi_status);
 		return;
 	}
diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c
index 614e43db93aa..29385dc470d5 100644
--- a/drivers/md/dm-verity-verify-sig.c
+++ b/drivers/md/dm-verity-verify-sig.c
@@ -119,8 +119,13 @@ int verity_verify_root_hash(const void *root_hash, size_t root_hash_len,
 	}
 
 	ret = verify_pkcs7_signature(root_hash, root_hash_len, sig_data,
-				sig_len, NULL, VERIFYING_UNSPECIFIED_SIGNATURE,
-				NULL, NULL);
+				sig_len,
+#ifdef CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG_SECONDARY_KEYRING
+				VERIFY_USE_SECONDARY_KEYRING,
+#else
+				NULL,
+#endif
+				VERIFYING_UNSPECIFIED_SIGNATURE, NULL, NULL);
 
 	return ret;
 }
diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c
index b65ca8dcfbdc..faa1dbffc8b4 100644
--- a/drivers/md/dm-zero.c
+++ b/drivers/md/dm-zero.c
@@ -59,6 +59,7 @@ static int zero_map(struct dm_target *ti, struct bio *bio)
 static struct target_type zero_target = {
 	.name   = "zero",
 	.version = {1, 1, 0},
+	.features = DM_TARGET_NOWAIT,
 	.module = THIS_MODULE,
 	.ctr    = zero_ctr,
 	.map    = zero_map,
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5b2f371ec4bb..7bac564f3faa 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -562,7 +562,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 		 * subset of the parent bdev; require extra privileges.
 		 */
 		if (!capable(CAP_SYS_RAWIO)) {
-			DMWARN_LIMIT(
+			DMDEBUG_LIMIT(
 	"%s: sending ioctl %x to DM device without required privilege.",
 				current->comm, cmd);
 			r = -ENOIOCTLCMD;
@@ -1586,7 +1586,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 		ci.sector_count = bio_sectors(bio);
 		while (ci.sector_count && !error) {
 			error = __split_and_process_non_flush(&ci);
-			if (current->bio_list && ci.sector_count && !error) {
+			if (ci.sector_count && !error) {
 				/*
 				 * Remainder must be passed to submit_bio_noacct()
 				 * so that it gets handled *after* bios already submitted
diff --git a/drivers/mfd/ab8500-debugfs.c b/drivers/mfd/ab8500-debugfs.c
index 6d1bf7c3ca3b..e43dea89b094 100644
--- a/drivers/mfd/ab8500-debugfs.c
+++ b/drivers/mfd/ab8500-debugfs.c
@@ -1513,26 +1513,14 @@ static int ab8500_interrupts_show(struct seq_file *s, void *p)
 {
 	int line;
 
-	seq_puts(s, "name: number:  number of: wake:\n");
+	seq_puts(s, "name: number: irq: number of: wake:\n");
 
 	for (line = 0; line < num_interrupt_lines; line++) {
-		struct irq_desc *desc = irq_to_desc(line + irq_first);
-
-		seq_printf(s, "%3i:  %6i %4i",
+		seq_printf(s, "%3i:  %4i %6i %4i\n",
 			   line,
+			   line + irq_first,
 			   num_interrupts[line],
 			   num_wake_interrupts[line]);
-
-		if (desc && desc->name)
-			seq_printf(s, "-%-8s", desc->name);
-		if (desc && desc->action) {
-			struct irqaction *action = desc->action;
-
-			seq_printf(s, "  %s", action->name);
-			while ((action = action->next) != NULL)
-				seq_printf(s, ", %s", action->name);
-		}
-		seq_putc(s, '\n');
 	}
 
 	return 0;
diff --git a/drivers/mfd/menelaus.c b/drivers/mfd/menelaus.c
index b64d3315a5e1..07e0ca2e467c 100644
--- a/drivers/mfd/menelaus.c
+++ b/drivers/mfd/menelaus.c
@@ -1119,7 +1119,7 @@ static inline void menelaus_rtc_init(struct menelaus_chip *m)
 		menelaus_write_reg(MENELAUS_RTC_CTRL, m->rtc_control);
 	}
 
-	err = rtc_register_device(m->rtc);
+	err = devm_rtc_register_device(m->rtc);
 	if (err) {
 		if (alarm) {
 			menelaus_remove_irq_work(MENELAUS_RTCALM_IRQ);
diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index beb482310a58..b2b3d2b0f808 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -472,8 +472,11 @@ static int allocate_cs(struct hl_device *hdev, struct hl_ctx *ctx,
 	cntr = &hdev->aggregated_cs_counters;
 
 	cs = kzalloc(sizeof(*cs), GFP_ATOMIC);
-	if (!cs)
+	if (!cs) {
+		atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
+		atomic64_inc(&cntr->out_of_mem_drop_cnt);
 		return -ENOMEM;
+	}
 
 	cs->ctx = ctx;
 	cs->submitted = false;
@@ -486,6 +489,8 @@ static int allocate_cs(struct hl_device *hdev, struct hl_ctx *ctx,
 
 	cs_cmpl = kmalloc(sizeof(*cs_cmpl), GFP_ATOMIC);
 	if (!cs_cmpl) {
+		atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
+		atomic64_inc(&cntr->out_of_mem_drop_cnt);
 		rc = -ENOMEM;
 		goto free_cs;
 	}
@@ -513,6 +518,8 @@ static int allocate_cs(struct hl_device *hdev, struct hl_ctx *ctx,
 	cs->jobs_in_queue_cnt = kcalloc(hdev->asic_prop.max_queues,
 			sizeof(*cs->jobs_in_queue_cnt), GFP_ATOMIC);
 	if (!cs->jobs_in_queue_cnt) {
+		atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
+		atomic64_inc(&cntr->out_of_mem_drop_cnt);
 		rc = -ENOMEM;
 		goto free_fence;
 	}
@@ -562,7 +569,7 @@ void hl_cs_rollback_all(struct hl_device *hdev)
 	for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++)
 		flush_workqueue(hdev->cq_wq[i]);
 
-	/* Make sure we don't have leftovers in the H/W queues mirror list */
+	/* Make sure we don't have leftovers in the CS mirror list */
 	list_for_each_entry_safe(cs, tmp, &hdev->cs_mirror_list, mirror_node) {
 		cs_get(cs);
 		cs->aborted = true;
@@ -764,11 +771,14 @@ static int hl_cs_sanity_checks(struct hl_fpriv *hpriv, union hl_cs_args *args)
 
 static int hl_cs_copy_chunk_array(struct hl_device *hdev,
 					struct hl_cs_chunk **cs_chunk_array,
-					void __user *chunks, u32 num_chunks)
+					void __user *chunks, u32 num_chunks,
+					struct hl_ctx *ctx)
 {
 	u32 size_to_copy;
 
 	if (num_chunks > HL_MAX_JOBS_PER_CS) {
+		atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+		atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt);
 		dev_err(hdev->dev,
 			"Number of chunks can NOT be larger than %d\n",
 			HL_MAX_JOBS_PER_CS);
@@ -777,11 +787,16 @@ static int hl_cs_copy_chunk_array(struct hl_device *hdev,
 
 	*cs_chunk_array = kmalloc_array(num_chunks, sizeof(**cs_chunk_array),
 					GFP_ATOMIC);
-	if (!*cs_chunk_array)
+	if (!*cs_chunk_array) {
+		atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
+		atomic64_inc(&hdev->aggregated_cs_counters.out_of_mem_drop_cnt);
 		return -ENOMEM;
+	}
 
 	size_to_copy = num_chunks * sizeof(struct hl_cs_chunk);
 	if (copy_from_user(*cs_chunk_array, chunks, size_to_copy)) {
+		atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+		atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt);
 		dev_err(hdev->dev, "Failed to copy cs chunk array from user\n");
 		kfree(*cs_chunk_array);
 		return -EFAULT;
@@ -797,6 +812,7 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks,
 	struct hl_device *hdev = hpriv->hdev;
 	struct hl_cs_chunk *cs_chunk_array;
 	struct hl_cs_counters_atomic *cntr;
+	struct hl_ctx *ctx = hpriv->ctx;
 	struct hl_cs_job *job;
 	struct hl_cs *cs;
 	struct hl_cb *cb;
@@ -805,7 +821,8 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks,
 	cntr = &hdev->aggregated_cs_counters;
 	*cs_seq = ULLONG_MAX;
 
-	rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks);
+	rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks,
+			hpriv->ctx);
 	if (rc)
 		goto out;
 
@@ -832,8 +849,8 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks,
 		rc = validate_queue_index(hdev, chunk, &queue_type,
 						&is_kernel_allocated_cb);
 		if (rc) {
-			atomic64_inc(&hpriv->ctx->cs_counters.parsing_drop_cnt);
-			atomic64_inc(&cntr->parsing_drop_cnt);
+			atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+			atomic64_inc(&cntr->validation_drop_cnt);
 			goto free_cs_object;
 		}
 
@@ -841,8 +858,8 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks,
 			cb = get_cb_from_cs_chunk(hdev, &hpriv->cb_mgr, chunk);
 			if (!cb) {
 				atomic64_inc(
-				&hpriv->ctx->cs_counters.parsing_drop_cnt);
-				atomic64_inc(&cntr->parsing_drop_cnt);
+					&ctx->cs_counters.validation_drop_cnt);
+				atomic64_inc(&cntr->validation_drop_cnt);
 				rc = -EINVAL;
 				goto free_cs_object;
 			}
@@ -856,8 +873,7 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks,
 		job = hl_cs_allocate_job(hdev, queue_type,
 						is_kernel_allocated_cb);
 		if (!job) {
-			atomic64_inc(
-			&hpriv->ctx->cs_counters.out_of_mem_drop_cnt);
+			atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
 			atomic64_inc(&cntr->out_of_mem_drop_cnt);
 			dev_err(hdev->dev, "Failed to allocate a new job\n");
 			rc = -ENOMEM;
@@ -891,7 +907,7 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks,
 
 		rc = cs_parser(hpriv, job);
 		if (rc) {
-			atomic64_inc(&hpriv->ctx->cs_counters.parsing_drop_cnt);
+			atomic64_inc(&ctx->cs_counters.parsing_drop_cnt);
 			atomic64_inc(&cntr->parsing_drop_cnt);
 			dev_err(hdev->dev,
 				"Failed to parse JOB %d.%llu.%d, err %d, rejecting the CS\n",
@@ -901,8 +917,8 @@ static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks,
 	}
 
 	if (int_queues_only) {
-		atomic64_inc(&hpriv->ctx->cs_counters.parsing_drop_cnt);
-		atomic64_inc(&cntr->parsing_drop_cnt);
+		atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+		atomic64_inc(&cntr->validation_drop_cnt);
 		dev_err(hdev->dev,
 			"Reject CS %d.%llu because only internal queues jobs are present\n",
 			cs->ctx->asid, cs->sequence);
@@ -1042,7 +1058,7 @@ out:
 }
 
 static int cs_ioctl_extract_signal_seq(struct hl_device *hdev,
-		struct hl_cs_chunk *chunk, u64 *signal_seq)
+		struct hl_cs_chunk *chunk, u64 *signal_seq, struct hl_ctx *ctx)
 {
 	u64 *signal_seq_arr = NULL;
 	u32 size_to_copy, signal_seq_arr_len;
@@ -1052,6 +1068,8 @@ static int cs_ioctl_extract_signal_seq(struct hl_device *hdev,
 
 	/* currently only one signal seq is supported */
 	if (signal_seq_arr_len != 1) {
+		atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+		atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt);
 		dev_err(hdev->dev,
 			"Wait for signal CS supports only one signal CS seq\n");
 		return -EINVAL;
@@ -1060,13 +1078,18 @@ static int cs_ioctl_extract_signal_seq(struct hl_device *hdev,
 	signal_seq_arr = kmalloc_array(signal_seq_arr_len,
 					sizeof(*signal_seq_arr),
 					GFP_ATOMIC);
-	if (!signal_seq_arr)
+	if (!signal_seq_arr) {
+		atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
+		atomic64_inc(&hdev->aggregated_cs_counters.out_of_mem_drop_cnt);
 		return -ENOMEM;
+	}
 
 	size_to_copy = chunk->num_signal_seq_arr * sizeof(*signal_seq_arr);
 	if (copy_from_user(signal_seq_arr,
 				u64_to_user_ptr(chunk->signal_seq_arr),
 				size_to_copy)) {
+		atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+		atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt);
 		dev_err(hdev->dev,
 			"Failed to copy signal seq array from user\n");
 		rc = -EFAULT;
@@ -1153,6 +1176,7 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
 	struct hl_device *hdev = hpriv->hdev;
 	struct hl_cs_compl *sig_waitcs_cmpl;
 	u32 q_idx, collective_engine_id = 0;
+	struct hl_cs_counters_atomic *cntr;
 	struct hl_fence *sig_fence = NULL;
 	struct hl_ctx *ctx = hpriv->ctx;
 	enum hl_queue_type q_type;
@@ -1160,9 +1184,11 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
 	u64 signal_seq;
 	int rc;
 
+	cntr = &hdev->aggregated_cs_counters;
 	*cs_seq = ULLONG_MAX;
 
-	rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks);
+	rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks,
+			ctx);
 	if (rc)
 		goto out;
 
@@ -1170,6 +1196,8 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
 	chunk = &cs_chunk_array[0];
 
 	if (chunk->queue_index >= hdev->asic_prop.max_queues) {
+		atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+		atomic64_inc(&cntr->validation_drop_cnt);
 		dev_err(hdev->dev, "Queue index %d is invalid\n",
 			chunk->queue_index);
 		rc = -EINVAL;
@@ -1181,6 +1209,8 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
 	q_type = hw_queue_prop->type;
 
 	if (!hw_queue_prop->supports_sync_stream) {
+		atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+		atomic64_inc(&cntr->validation_drop_cnt);
 		dev_err(hdev->dev,
 			"Queue index %d does not support sync stream operations\n",
 			q_idx);
@@ -1190,6 +1220,8 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
 
 	if (cs_type == CS_TYPE_COLLECTIVE_WAIT) {
 		if (!(hw_queue_prop->collective_mode == HL_COLLECTIVE_MASTER)) {
+			atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+			atomic64_inc(&cntr->validation_drop_cnt);
 			dev_err(hdev->dev,
 				"Queue index %d is invalid\n", q_idx);
 			rc = -EINVAL;
@@ -1200,12 +1232,14 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
 	}
 
 	if (cs_type == CS_TYPE_WAIT || cs_type == CS_TYPE_COLLECTIVE_WAIT) {
-		rc = cs_ioctl_extract_signal_seq(hdev, chunk, &signal_seq);
+		rc = cs_ioctl_extract_signal_seq(hdev, chunk, &signal_seq, ctx);
 		if (rc)
 			goto free_cs_chunk_array;
 
 		sig_fence = hl_ctx_get_fence(ctx, signal_seq);
 		if (IS_ERR(sig_fence)) {
+			atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+			atomic64_inc(&cntr->validation_drop_cnt);
 			dev_err(hdev->dev,
 				"Failed to get signal CS with seq 0x%llx\n",
 				signal_seq);
@@ -1223,6 +1257,8 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
 			container_of(sig_fence, struct hl_cs_compl, base_fence);
 
 		if (sig_waitcs_cmpl->type != CS_TYPE_SIGNAL) {
+			atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+			atomic64_inc(&cntr->validation_drop_cnt);
 			dev_err(hdev->dev,
 				"CS seq 0x%llx is not of a signal CS\n",
 				signal_seq);
@@ -1270,8 +1306,11 @@ static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
 	else if (cs_type == CS_TYPE_COLLECTIVE_WAIT)
 		rc = hdev->asic_funcs->collective_wait_create_jobs(hdev, ctx,
 				cs, q_idx, collective_engine_id);
-	else
+	else {
+		atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+		atomic64_inc(&cntr->validation_drop_cnt);
 		rc = -EINVAL;
+	}
 
 	if (rc)
 		goto free_cs_object;
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 5871162a8442..1456eabf9601 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -17,12 +17,12 @@ enum hl_device_status hl_device_status(struct hl_device *hdev)
 {
 	enum hl_device_status status;
 
-	if (hdev->disabled)
-		status = HL_DEVICE_STATUS_MALFUNCTION;
-	else if (atomic_read(&hdev->in_reset))
+	if (atomic_read(&hdev->in_reset))
 		status = HL_DEVICE_STATUS_IN_RESET;
 	else if (hdev->needs_reset)
 		status = HL_DEVICE_STATUS_NEEDS_RESET;
+	else if (hdev->disabled)
+		status = HL_DEVICE_STATUS_MALFUNCTION;
 	else
 		status = HL_DEVICE_STATUS_OPERATIONAL;
 
@@ -1092,6 +1092,7 @@ kill_processes:
 						GFP_KERNEL);
 		if (!hdev->kernel_ctx) {
 			rc = -ENOMEM;
+			hl_mmu_fini(hdev);
 			goto out_err;
 		}
 
@@ -1103,6 +1104,7 @@ kill_processes:
 				"failed to init kernel ctx in hard reset\n");
 			kfree(hdev->kernel_ctx);
 			hdev->kernel_ctx = NULL;
+			hl_mmu_fini(hdev);
 			goto out_err;
 		}
 	}
diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 0e1c629e9800..20f77f58edef 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -627,25 +627,38 @@ int hl_fw_read_preboot_status(struct hl_device *hdev, u32 cpu_boot_status_reg,
 	security_status = RREG32(cpu_security_boot_status_reg);
 
 	/* We read security status multiple times during boot:
-	 * 1. preboot - we check if fw security feature is supported
-	 * 2. boot cpu - we get boot cpu security status
-	 * 3. FW application - we get FW application security status
+	 * 1. preboot - a. Check whether the security status bits are valid
+	 *              b. Check whether fw security is enabled
+	 *              c. Check whether hard reset is done by preboot
+	 * 2. boot cpu - a. Fetch boot cpu security status
+	 *               b. Check whether hard reset is done by boot cpu
+	 * 3. FW application - a. Fetch fw application security status
+	 *                     b. Check whether hard reset is done by fw app
 	 *
 	 * Preboot:
 	 * Check security status bit (CPU_BOOT_DEV_STS0_ENABLED), if it is set
 	 * check security enabled bit (CPU_BOOT_DEV_STS0_SECURITY_EN)
 	 */
 	if (security_status & CPU_BOOT_DEV_STS0_ENABLED) {
-		hdev->asic_prop.fw_security_status_valid = 1;
-		prop->fw_security_disabled =
-			!(security_status & CPU_BOOT_DEV_STS0_SECURITY_EN);
+		prop->fw_security_status_valid = 1;
+
+		if (security_status & CPU_BOOT_DEV_STS0_SECURITY_EN)
+			prop->fw_security_disabled = false;
+		else
+			prop->fw_security_disabled = true;
+
+		if (security_status & CPU_BOOT_DEV_STS0_FW_HARD_RST_EN)
+			prop->hard_reset_done_by_fw = true;
 	} else {
-		hdev->asic_prop.fw_security_status_valid = 0;
+		prop->fw_security_status_valid = 0;
 		prop->fw_security_disabled = true;
 	}
 
+	dev_dbg(hdev->dev, "Firmware preboot hard-reset is %s\n",
+			prop->hard_reset_done_by_fw ? "enabled" : "disabled");
+
 	dev_info(hdev->dev, "firmware-level security is %s\n",
-		prop->fw_security_disabled ? "disabled" : "enabled");
+			prop->fw_security_disabled ? "disabled" : "enabled");
 
 	return 0;
 }
@@ -655,6 +668,7 @@ int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
 			u32 cpu_security_boot_status_reg, u32 boot_err0_reg,
 			bool skip_bmc, u32 cpu_timeout, u32 boot_fit_timeout)
 {
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	u32 status;
 	int rc;
 
@@ -723,11 +737,22 @@ int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
 	/* Read U-Boot version now in case we will later fail */
 	hdev->asic_funcs->read_device_fw_version(hdev, FW_COMP_UBOOT);
 
+	/* Clear reset status since we need to read it again from boot CPU */
+	prop->hard_reset_done_by_fw = false;
+
 	/* Read boot_cpu security bits */
-	if (hdev->asic_prop.fw_security_status_valid)
-		hdev->asic_prop.fw_boot_cpu_security_map =
+	if (prop->fw_security_status_valid) {
+		prop->fw_boot_cpu_security_map =
 				RREG32(cpu_security_boot_status_reg);
 
+		if (prop->fw_boot_cpu_security_map &
+				CPU_BOOT_DEV_STS0_FW_HARD_RST_EN)
+			prop->hard_reset_done_by_fw = true;
+	}
+
+	dev_dbg(hdev->dev, "Firmware boot CPU hard-reset is %s\n",
+			prop->hard_reset_done_by_fw ? "enabled" : "disabled");
+
 	if (rc) {
 		detect_cpu_boot_status(hdev, status);
 		rc = -EIO;
@@ -796,18 +821,21 @@ int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
 		goto out;
 	}
 
+	/* Clear reset status since we need to read again from app */
+	prop->hard_reset_done_by_fw = false;
+
 	/* Read FW application security bits */
-	if (hdev->asic_prop.fw_security_status_valid) {
-		hdev->asic_prop.fw_app_security_map =
+	if (prop->fw_security_status_valid) {
+		prop->fw_app_security_map =
 				RREG32(cpu_security_boot_status_reg);
 
-		if (hdev->asic_prop.fw_app_security_map &
+		if (prop->fw_app_security_map &
 				CPU_BOOT_DEV_STS0_FW_HARD_RST_EN)
-			hdev->asic_prop.hard_reset_done_by_fw = true;
+			prop->hard_reset_done_by_fw = true;
 	}
 
-	dev_dbg(hdev->dev, "Firmware hard-reset is %s\n",
-		hdev->asic_prop.hard_reset_done_by_fw ? "enabled" : "disabled");
+	dev_dbg(hdev->dev, "Firmware application CPU hard-reset is %s\n",
+			prop->hard_reset_done_by_fw ? "enabled" : "disabled");
 
 	dev_info(hdev->dev, "Successfully loaded firmware to device\n");
 
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 571eda6ef5ab..e0d7f5fbaa5c 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -944,7 +944,7 @@ struct hl_asic_funcs {
 	u32 (*get_signal_cb_size)(struct hl_device *hdev);
 	u32 (*get_wait_cb_size)(struct hl_device *hdev);
 	u32 (*gen_signal_cb)(struct hl_device *hdev, void *data, u16 sob_id,
-			u32 size);
+			u32 size, bool eb);
 	u32 (*gen_wait_cb)(struct hl_device *hdev,
 			struct hl_gen_wait_properties *prop);
 	void (*reset_sob)(struct hl_device *hdev, void *data);
@@ -1000,6 +1000,7 @@ struct hl_va_range {
  * @queue_full_drop_cnt: dropped due to queue full
  * @device_in_reset_drop_cnt: dropped due to device in reset
  * @max_cs_in_flight_drop_cnt: dropped due to maximum CS in-flight
+ * @validation_drop_cnt: dropped due to error in validation
  */
 struct hl_cs_counters_atomic {
 	atomic64_t out_of_mem_drop_cnt;
@@ -1007,6 +1008,7 @@ struct hl_cs_counters_atomic {
 	atomic64_t queue_full_drop_cnt;
 	atomic64_t device_in_reset_drop_cnt;
 	atomic64_t max_cs_in_flight_drop_cnt;
+	atomic64_t validation_drop_cnt;
 };
 
 /**
diff --git a/drivers/misc/habanalabs/common/habanalabs_drv.c b/drivers/misc/habanalabs/common/habanalabs_drv.c
index 6bbb6bca6860..032d114f01ea 100644
--- a/drivers/misc/habanalabs/common/habanalabs_drv.c
+++ b/drivers/misc/habanalabs/common/habanalabs_drv.c
@@ -544,6 +544,7 @@ static struct pci_driver hl_pci_driver = {
 	.id_table = ids,
 	.probe = hl_pci_probe,
 	.remove = hl_pci_remove,
+	.shutdown = hl_pci_remove,
 	.driver.pm = &hl_pm_ops,
 	.err_handler = &hl_pci_err_handler,
 };
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index 32e6af1db4e3..12efbd9d2e3a 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -335,6 +335,8 @@ static int cs_counters_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 			atomic64_read(&cntr->device_in_reset_drop_cnt);
 	cs_counters.total_max_cs_in_flight_drop_cnt =
 			atomic64_read(&cntr->max_cs_in_flight_drop_cnt);
+	cs_counters.total_validation_drop_cnt =
+			atomic64_read(&cntr->validation_drop_cnt);
 
 	if (hpriv->ctx) {
 		cs_counters.ctx_out_of_mem_drop_cnt =
@@ -352,6 +354,9 @@ static int cs_counters_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 		cs_counters.ctx_max_cs_in_flight_drop_cnt =
 				atomic64_read(
 			&hpriv->ctx->cs_counters.max_cs_in_flight_drop_cnt);
+		cs_counters.ctx_validation_drop_cnt =
+				atomic64_read(
+				&hpriv->ctx->cs_counters.validation_drop_cnt);
 	}
 
 	return copy_to_user(out, &cs_counters,
@@ -406,7 +411,7 @@ static int total_energy_consumption_info(struct hl_fpriv *hpriv,
 static int pll_frequency_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 {
 	struct hl_device *hdev = hpriv->hdev;
-	struct hl_pll_frequency_info freq_info = {0};
+	struct hl_pll_frequency_info freq_info = { {0} };
 	u32 max_size = args->return_size;
 	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
 	int rc;
diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c
index 7caf868d1585..76217258780a 100644
--- a/drivers/misc/habanalabs/common/hw_queue.c
+++ b/drivers/misc/habanalabs/common/hw_queue.c
@@ -418,8 +418,11 @@ static void init_signal_cs(struct hl_device *hdev,
 		"generate signal CB, sob_id: %d, sob val: 0x%x, q_idx: %d\n",
 		cs_cmpl->hw_sob->sob_id, cs_cmpl->sob_val, q_idx);
 
+	/* we set an EB since we must make sure all oeprations are done
+	 * when sending the signal
+	 */
 	hdev->asic_funcs->gen_signal_cb(hdev, job->patched_cb,
-				cs_cmpl->hw_sob->sob_id, 0);
+				cs_cmpl->hw_sob->sob_id, 0, true);
 
 	kref_get(&hw_sob->kref);
 
diff --git a/drivers/misc/habanalabs/common/pci.c b/drivers/misc/habanalabs/common/pci.c
index 923b2606e29f..b4725e6101f6 100644
--- a/drivers/misc/habanalabs/common/pci.c
+++ b/drivers/misc/habanalabs/common/pci.c
@@ -130,10 +130,8 @@ static int hl_pci_elbi_write(struct hl_device *hdev, u64 addr, u32 data)
 	if ((val & PCI_CONFIG_ELBI_STS_MASK) == PCI_CONFIG_ELBI_STS_DONE)
 		return 0;
 
-	if (val & PCI_CONFIG_ELBI_STS_ERR) {
-		dev_err(hdev->dev, "Error writing to ELBI\n");
+	if (val & PCI_CONFIG_ELBI_STS_ERR)
 		return -EIO;
-	}
 
 	if (!(val & PCI_CONFIG_ELBI_STS_MASK)) {
 		dev_err(hdev->dev, "ELBI write didn't finish in time\n");
@@ -160,8 +158,12 @@ int hl_pci_iatu_write(struct hl_device *hdev, u32 addr, u32 data)
 
 	dbi_offset = addr & 0xFFF;
 
-	rc = hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0x00300000);
-	rc |= hl_pci_elbi_write(hdev, prop->pcie_dbi_base_address + dbi_offset,
+	/* Ignore result of writing to pcie_aux_dbi_reg_addr as it could fail
+	 * in case the firmware security is enabled
+	 */
+	hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0x00300000);
+
+	rc = hl_pci_elbi_write(hdev, prop->pcie_dbi_base_address + dbi_offset,
 				data);
 
 	if (rc)
@@ -244,9 +246,11 @@ int hl_pci_set_inbound_region(struct hl_device *hdev, u8 region,
 
 	rc |= hl_pci_iatu_write(hdev, offset + 0x4, ctrl_reg_val);
 
-	/* Return the DBI window to the default location */
-	rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0);
-	rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr + 4, 0);
+	/* Return the DBI window to the default location
+	 * Ignore result of writing to pcie_aux_dbi_reg_addr as it could fail
+	 * in case the firmware security is enabled
+	 */
+	hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0);
 
 	if (rc)
 		dev_err(hdev->dev, "failed to map bar %u to 0x%08llx\n",
@@ -294,9 +298,11 @@ int hl_pci_set_outbound_region(struct hl_device *hdev,
 	/* Enable */
 	rc |= hl_pci_iatu_write(hdev, 0x004, 0x80000000);
 
-	/* Return the DBI window to the default location */
-	rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0);
-	rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr + 4, 0);
+	/* Return the DBI window to the default location
+	 * Ignore result of writing to pcie_aux_dbi_reg_addr as it could fail
+	 * in case the firmware security is enabled
+	 */
+	hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0);
 
 	return rc;
 }
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 1f1926607c5e..8c09e4466af8 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -151,19 +151,6 @@ static const u16 gaudi_packet_sizes[MAX_PACKET_ID] = {
 	[PACKET_LOAD_AND_EXE]	= sizeof(struct packet_load_and_exe)
 };
 
-static const u32 gaudi_pll_base_addresses[GAUDI_PLL_MAX] = {
-	[CPU_PLL] = mmPSOC_CPU_PLL_NR,
-	[PCI_PLL] = mmPSOC_PCI_PLL_NR,
-	[SRAM_PLL] = mmSRAM_W_PLL_NR,
-	[HBM_PLL] = mmPSOC_HBM_PLL_NR,
-	[NIC_PLL] = mmNIC0_PLL_NR,
-	[DMA_PLL] = mmDMA_W_PLL_NR,
-	[MESH_PLL] = mmMESH_W_PLL_NR,
-	[MME_PLL] = mmPSOC_MME_PLL_NR,
-	[TPC_PLL] = mmPSOC_TPC_PLL_NR,
-	[IF_PLL] = mmIF_W_PLL_NR
-};
-
 static inline bool validate_packet_id(enum packet_id id)
 {
 	switch (id) {
@@ -374,7 +361,7 @@ static int gaudi_cpucp_info_get(struct hl_device *hdev);
 static void gaudi_disable_clock_gating(struct hl_device *hdev);
 static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid);
 static u32 gaudi_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id,
-				u32 size);
+				u32 size, bool eb);
 static u32 gaudi_gen_wait_cb(struct hl_device *hdev,
 				struct hl_gen_wait_properties *prop);
 
@@ -667,12 +654,6 @@ static int gaudi_early_init(struct hl_device *hdev)
 	if (rc)
 		goto free_queue_props;
 
-	if (gaudi_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
-		dev_info(hdev->dev,
-			"H/W state is dirty, must reset before initializing\n");
-		hdev->asic_funcs->hw_fini(hdev, true);
-	}
-
 	/* Before continuing in the initialization, we need to read the preboot
 	 * version to determine whether we run with a security-enabled firmware
 	 */
@@ -685,6 +666,12 @@ static int gaudi_early_init(struct hl_device *hdev)
 		goto pci_fini;
 	}
 
+	if (gaudi_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
+		dev_info(hdev->dev,
+			"H/W state is dirty, must reset before initializing\n");
+		hdev->asic_funcs->hw_fini(hdev, true);
+	}
+
 	return 0;
 
 pci_fini:
@@ -703,93 +690,60 @@ static int gaudi_early_fini(struct hl_device *hdev)
 }
 
 /**
- * gaudi_fetch_pll_frequency - Fetch PLL frequency values
+ * gaudi_fetch_psoc_frequency - Fetch PSOC frequency values
  *
  * @hdev: pointer to hl_device structure
- * @pll_index: index of the pll to fetch frequency from
- * @pll_freq: pointer to store the pll frequency in MHz in each of the available
- *            outputs. if a certain output is not available a 0 will be set
  *
  */
-static int gaudi_fetch_pll_frequency(struct hl_device *hdev,
-				enum gaudi_pll_index pll_index,
-				u16 *pll_freq_arr)
+static int gaudi_fetch_psoc_frequency(struct hl_device *hdev)
 {
-	u32 nr = 0, nf = 0, od = 0, pll_clk = 0, div_fctr, div_sel,
-			pll_base_addr = gaudi_pll_base_addresses[pll_index];
-	u16 freq = 0;
-	int i, rc;
-
-	if (hdev->asic_prop.fw_security_status_valid &&
-			(hdev->asic_prop.fw_app_security_map &
-					CPU_BOOT_DEV_STS0_PLL_INFO_EN)) {
-		rc = hl_fw_cpucp_pll_info_get(hdev, pll_index, pll_freq_arr);
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
+	u32 nr = 0, nf = 0, od = 0, div_fctr = 0, pll_clk, div_sel;
+	u16 pll_freq_arr[HL_PLL_NUM_OUTPUTS], freq;
+	int rc;
 
-		if (rc)
-			return rc;
-	} else if (hdev->asic_prop.fw_security_disabled) {
+	if (hdev->asic_prop.fw_security_disabled) {
 		/* Backward compatibility */
-		nr = RREG32(pll_base_addr + PLL_NR_OFFSET);
-		nf = RREG32(pll_base_addr + PLL_NF_OFFSET);
-		od = RREG32(pll_base_addr + PLL_OD_OFFSET);
-
-		for (i = 0; i < HL_PLL_NUM_OUTPUTS; i++) {
-			div_fctr = RREG32(pll_base_addr +
-					PLL_DIV_FACTOR_0_OFFSET + i * 4);
-			div_sel = RREG32(pll_base_addr +
-					PLL_DIV_SEL_0_OFFSET + i * 4);
+		div_fctr = RREG32(mmPSOC_CPU_PLL_DIV_FACTOR_2);
+		div_sel = RREG32(mmPSOC_CPU_PLL_DIV_SEL_2);
+		nr = RREG32(mmPSOC_CPU_PLL_NR);
+		nf = RREG32(mmPSOC_CPU_PLL_NF);
+		od = RREG32(mmPSOC_CPU_PLL_OD);
 
-			if (div_sel == DIV_SEL_REF_CLK ||
+		if (div_sel == DIV_SEL_REF_CLK ||
 				div_sel == DIV_SEL_DIVIDED_REF) {
-				if (div_sel == DIV_SEL_REF_CLK)
-					freq = PLL_REF_CLK;
-				else
-					freq = PLL_REF_CLK / (div_fctr + 1);
-			} else if (div_sel == DIV_SEL_PLL_CLK ||
-					div_sel == DIV_SEL_DIVIDED_PLL) {
-				pll_clk = PLL_REF_CLK * (nf + 1) /
-						((nr + 1) * (od + 1));
-				if (div_sel == DIV_SEL_PLL_CLK)
-					freq = pll_clk;
-				else
-					freq = pll_clk / (div_fctr + 1);
-			} else {
-				dev_warn(hdev->dev,
-					"Received invalid div select value: %d",
-					div_sel);
-			}
-
-			pll_freq_arr[i] = freq;
+			if (div_sel == DIV_SEL_REF_CLK)
+				freq = PLL_REF_CLK;
+			else
+				freq = PLL_REF_CLK / (div_fctr + 1);
+		} else if (div_sel == DIV_SEL_PLL_CLK ||
+			div_sel == DIV_SEL_DIVIDED_PLL) {
+			pll_clk = PLL_REF_CLK * (nf + 1) /
+					((nr + 1) * (od + 1));
+			if (div_sel == DIV_SEL_PLL_CLK)
+				freq = pll_clk;
+			else
+				freq = pll_clk / (div_fctr + 1);
+		} else {
+			dev_warn(hdev->dev,
+				"Received invalid div select value: %d",
+				div_sel);
+			freq = 0;
 		}
 	} else {
-		dev_err(hdev->dev, "Failed to fetch PLL frequency values\n");
-		return -EIO;
-	}
+		rc = hl_fw_cpucp_pll_info_get(hdev, CPU_PLL, pll_freq_arr);
 
-	return 0;
-}
-
-/**
- * gaudi_fetch_psoc_frequency - Fetch PSOC frequency values
- *
- * @hdev: pointer to hl_device structure
- *
- */
-static int gaudi_fetch_psoc_frequency(struct hl_device *hdev)
-{
-	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	u16 pll_freq[HL_PLL_NUM_OUTPUTS];
-	int rc;
+		if (rc)
+			return rc;
 
-	rc = gaudi_fetch_pll_frequency(hdev, CPU_PLL, pll_freq);
-	if (rc)
-		return rc;
+		freq = pll_freq_arr[2];
+	}
 
-	prop->psoc_timestamp_frequency = pll_freq[2];
-	prop->psoc_pci_pll_nr = 0;
-	prop->psoc_pci_pll_nf = 0;
-	prop->psoc_pci_pll_od = 0;
-	prop->psoc_pci_pll_div_factor = 0;
+	prop->psoc_timestamp_frequency = freq;
+	prop->psoc_pci_pll_nr = nr;
+	prop->psoc_pci_pll_nf = nf;
+	prop->psoc_pci_pll_od = od;
+	prop->psoc_pci_pll_div_factor = div_fctr;
 
 	return 0;
 }
@@ -884,11 +838,17 @@ static int gaudi_init_tpc_mem(struct hl_device *hdev)
 	size_t fw_size;
 	void *cpu_addr;
 	dma_addr_t dma_handle;
-	int rc;
+	int rc, count = 5;
 
+again:
 	rc = request_firmware(&fw, GAUDI_TPC_FW_FILE, hdev->dev);
+	if (rc == -EINTR && count-- > 0) {
+		msleep(50);
+		goto again;
+	}
+
 	if (rc) {
-		dev_err(hdev->dev, "Firmware file %s is not found!\n",
+		dev_err(hdev->dev, "Failed to load firmware file %s\n",
 				GAUDI_TPC_FW_FILE);
 		goto out;
 	}
@@ -1110,7 +1070,7 @@ static void gaudi_collective_slave_init_job(struct hl_device *hdev,
 		prop->collective_sob_id, queue_id);
 
 	cb_size += gaudi_gen_signal_cb(hdev, job->user_cb,
-			prop->collective_sob_id, cb_size);
+			prop->collective_sob_id, cb_size, false);
 }
 
 static void gaudi_collective_wait_init_cs(struct hl_cs *cs)
@@ -2449,8 +2409,6 @@ static void gaudi_init_golden_registers(struct hl_device *hdev)
 	gaudi_init_e2e(hdev);
 	gaudi_init_hbm_cred(hdev);
 
-	hdev->asic_funcs->disable_clock_gating(hdev);
-
 	for (tpc_id = 0, tpc_offset = 0;
 				tpc_id < TPC_NUMBER_OF_ENGINES;
 				tpc_id++, tpc_offset += TPC_CFG_OFFSET) {
@@ -3462,6 +3420,9 @@ static void gaudi_set_clock_gating(struct hl_device *hdev)
 	if (hdev->in_debug)
 		return;
 
+	if (!hdev->asic_prop.fw_security_disabled)
+		return;
+
 	for (i = GAUDI_PCI_DMA_1, qman_offset = 0 ; i < GAUDI_HBM_DMA_1 ; i++) {
 		enable = !!(hdev->clock_gating_mask &
 				(BIT_ULL(gaudi_dma_assignment[i])));
@@ -3513,7 +3474,7 @@ static void gaudi_disable_clock_gating(struct hl_device *hdev)
 	u32 qman_offset;
 	int i;
 
-	if (!(gaudi->hw_cap_initialized & HW_CAP_CLK_GATE))
+	if (!hdev->asic_prop.fw_security_disabled)
 		return;
 
 	for (i = 0, qman_offset = 0 ; i < DMA_NUMBER_OF_CHANNELS ; i++) {
@@ -3806,7 +3767,7 @@ static int gaudi_init_cpu_queues(struct hl_device *hdev, u32 cpu_timeout)
 static void gaudi_pre_hw_init(struct hl_device *hdev)
 {
 	/* Perform read from the device to make sure device is up */
-	RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG);
+	RREG32(mmHW_STATE);
 
 	if (hdev->asic_prop.fw_security_disabled) {
 		/* Set the access through PCI bars (Linux driver only) as
@@ -3847,6 +3808,13 @@ static int gaudi_hw_init(struct hl_device *hdev)
 		return rc;
 	}
 
+	/* In case the clock gating was enabled in preboot we need to disable
+	 * it here before touching the MME/TPC registers.
+	 * There is no need to take clk gating mutex because when this function
+	 * runs, no other relevant code can run
+	 */
+	hdev->asic_funcs->disable_clock_gating(hdev);
+
 	/* SRAM scrambler must be initialized after CPU is running from HBM */
 	gaudi_init_scrambler_sram(hdev);
 
@@ -3885,7 +3853,7 @@ static int gaudi_hw_init(struct hl_device *hdev)
 	}
 
 	/* Perform read from the device to flush all configuration */
-	RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG);
+	RREG32(mmHW_STATE);
 
 	return 0;
 
@@ -3927,7 +3895,10 @@ static void gaudi_hw_fini(struct hl_device *hdev, bool hard_reset)
 	/* I don't know what is the state of the CPU so make sure it is
 	 * stopped in any means necessary
 	 */
-	WREG32(mmPSOC_GLOBAL_CONF_KMD_MSG_TO_CPU, KMD_MSG_GOTO_WFE);
+	if (hdev->asic_prop.hard_reset_done_by_fw)
+		WREG32(mmPSOC_GLOBAL_CONF_KMD_MSG_TO_CPU, KMD_MSG_RST_DEV);
+	else
+		WREG32(mmPSOC_GLOBAL_CONF_KMD_MSG_TO_CPU, KMD_MSG_GOTO_WFE);
 
 	WREG32(mmGIC_DISTRIBUTOR__5_GICD_SETSPI_NSR, GAUDI_EVENT_HALT_MACHINE);
 
@@ -3971,11 +3942,15 @@ static void gaudi_hw_fini(struct hl_device *hdev, bool hard_reset)
 
 		WREG32(mmPSOC_GLOBAL_CONF_SW_ALL_RST,
 			1 << PSOC_GLOBAL_CONF_SW_ALL_RST_IND_SHIFT);
-	}
 
-	dev_info(hdev->dev,
-		"Issued HARD reset command, going to wait %dms\n",
-		reset_timeout_ms);
+		dev_info(hdev->dev,
+			"Issued HARD reset command, going to wait %dms\n",
+			reset_timeout_ms);
+	} else {
+		dev_info(hdev->dev,
+			"Firmware performs HARD reset, going to wait %dms\n",
+			reset_timeout_ms);
+	}
 
 	/*
 	 * After hard reset, we can't poll the BTM_FSM register because the PSOC
@@ -7936,7 +7911,7 @@ static u32 gaudi_get_wait_cb_size(struct hl_device *hdev)
 }
 
 static u32 gaudi_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id,
-				u32 size)
+				u32 size, bool eb)
 {
 	struct hl_cb *cb = (struct hl_cb *) data;
 	struct packet_msg_short *pkt;
@@ -7953,7 +7928,7 @@ static u32 gaudi_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id,
 	ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_OP_MASK, 0); /* write the value */
 	ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_BASE_MASK, 3); /* W_S SOB base */
 	ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_OPCODE_MASK, PACKET_MSG_SHORT);
-	ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_EB_MASK, 1);
+	ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_EB_MASK, eb);
 	ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_RB_MASK, 1);
 	ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_MB_MASK, 1);
 
diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h
index f2d91f4fcffe..a7ab2d7e57d4 100644
--- a/drivers/misc/habanalabs/gaudi/gaudiP.h
+++ b/drivers/misc/habanalabs/gaudi/gaudiP.h
@@ -105,13 +105,6 @@
 #define MME_ACC_OFFSET		(mmMME1_ACC_BASE - mmMME0_ACC_BASE)
 #define SRAM_BANK_OFFSET	(mmSRAM_Y0_X1_RTR_BASE - mmSRAM_Y0_X0_RTR_BASE)
 
-#define PLL_NR_OFFSET		0
-#define PLL_NF_OFFSET		(mmPSOC_CPU_PLL_NF - mmPSOC_CPU_PLL_NR)
-#define PLL_OD_OFFSET		(mmPSOC_CPU_PLL_OD - mmPSOC_CPU_PLL_NR)
-#define PLL_DIV_FACTOR_0_OFFSET	(mmPSOC_CPU_PLL_DIV_FACTOR_0 - \
-				mmPSOC_CPU_PLL_NR)
-#define PLL_DIV_SEL_0_OFFSET	(mmPSOC_CPU_PLL_DIV_SEL_0 - mmPSOC_CPU_PLL_NR)
-
 #define NUM_OF_SOB_IN_BLOCK		\
 	(((mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_2047 - \
 	mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_0) + 4) >> 2)
diff --git a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
index 2e3612e1ee28..88a09d42e111 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
@@ -9,6 +9,7 @@
 #include "../include/gaudi/gaudi_coresight.h"
 #include "../include/gaudi/asic_reg/gaudi_regs.h"
 #include "../include/gaudi/gaudi_masks.h"
+#include "../include/gaudi/gaudi_reg_map.h"
 
 #include <uapi/misc/habanalabs.h>
 #define SPMU_SECTION_SIZE		MME0_ACC_SPMU_MAX_OFFSET
@@ -874,7 +875,7 @@ int gaudi_debug_coresight(struct hl_device *hdev, void *data)
 	}
 
 	/* Perform read from the device to flush all configuration */
-	RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG);
+	RREG32(mmHW_STATE);
 
 	return rc;
 }
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 3e5eb9e3d7bd..b8b4aa636b7c 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -613,12 +613,6 @@ static int goya_early_init(struct hl_device *hdev)
 	if (rc)
 		goto free_queue_props;
 
-	if (goya_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
-		dev_info(hdev->dev,
-			"H/W state is dirty, must reset before initializing\n");
-		hdev->asic_funcs->hw_fini(hdev, true);
-	}
-
 	/* Before continuing in the initialization, we need to read the preboot
 	 * version to determine whether we run with a security-enabled firmware
 	 */
@@ -631,6 +625,12 @@ static int goya_early_init(struct hl_device *hdev)
 		goto pci_fini;
 	}
 
+	if (goya_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
+		dev_info(hdev->dev,
+			"H/W state is dirty, must reset before initializing\n");
+		hdev->asic_funcs->hw_fini(hdev, true);
+	}
+
 	if (!hdev->pldm) {
 		val = RREG32(mmPSOC_GLOBAL_CONF_BOOT_STRAP_PINS);
 		if (val & PSOC_GLOBAL_CONF_BOOT_STRAP_PINS_SRIOV_EN_MASK)
@@ -694,32 +694,47 @@ static void goya_qman0_set_security(struct hl_device *hdev, bool secure)
 static void goya_fetch_psoc_frequency(struct hl_device *hdev)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
-	u32 trace_freq = 0;
-	u32 pll_clk = 0;
-	u32 div_fctr = RREG32(mmPSOC_PCI_PLL_DIV_FACTOR_1);
-	u32 div_sel = RREG32(mmPSOC_PCI_PLL_DIV_SEL_1);
-	u32 nr = RREG32(mmPSOC_PCI_PLL_NR);
-	u32 nf = RREG32(mmPSOC_PCI_PLL_NF);
-	u32 od = RREG32(mmPSOC_PCI_PLL_OD);
-
-	if (div_sel == DIV_SEL_REF_CLK || div_sel == DIV_SEL_DIVIDED_REF) {
-		if (div_sel == DIV_SEL_REF_CLK)
-			trace_freq = PLL_REF_CLK;
-		else
-			trace_freq = PLL_REF_CLK / (div_fctr + 1);
-	} else if (div_sel == DIV_SEL_PLL_CLK ||
-					div_sel == DIV_SEL_DIVIDED_PLL) {
-		pll_clk = PLL_REF_CLK * (nf + 1) / ((nr + 1) * (od + 1));
-		if (div_sel == DIV_SEL_PLL_CLK)
-			trace_freq = pll_clk;
-		else
-			trace_freq = pll_clk / (div_fctr + 1);
+	u32 nr = 0, nf = 0, od = 0, div_fctr = 0, pll_clk, div_sel;
+	u16 pll_freq_arr[HL_PLL_NUM_OUTPUTS], freq;
+	int rc;
+
+	if (hdev->asic_prop.fw_security_disabled) {
+		div_fctr = RREG32(mmPSOC_PCI_PLL_DIV_FACTOR_1);
+		div_sel = RREG32(mmPSOC_PCI_PLL_DIV_SEL_1);
+		nr = RREG32(mmPSOC_PCI_PLL_NR);
+		nf = RREG32(mmPSOC_PCI_PLL_NF);
+		od = RREG32(mmPSOC_PCI_PLL_OD);
+
+		if (div_sel == DIV_SEL_REF_CLK ||
+				div_sel == DIV_SEL_DIVIDED_REF) {
+			if (div_sel == DIV_SEL_REF_CLK)
+				freq = PLL_REF_CLK;
+			else
+				freq = PLL_REF_CLK / (div_fctr + 1);
+		} else if (div_sel == DIV_SEL_PLL_CLK ||
+				div_sel == DIV_SEL_DIVIDED_PLL) {
+			pll_clk = PLL_REF_CLK * (nf + 1) /
+					((nr + 1) * (od + 1));
+			if (div_sel == DIV_SEL_PLL_CLK)
+				freq = pll_clk;
+			else
+				freq = pll_clk / (div_fctr + 1);
+		} else {
+			dev_warn(hdev->dev,
+				"Received invalid div select value: %d",
+				div_sel);
+			freq = 0;
+		}
 	} else {
-		dev_warn(hdev->dev,
-			"Received invalid div select value: %d", div_sel);
+		rc = hl_fw_cpucp_pll_info_get(hdev, PCI_PLL, pll_freq_arr);
+
+		if (rc)
+			return;
+
+		freq = pll_freq_arr[1];
 	}
 
-	prop->psoc_timestamp_frequency = trace_freq;
+	prop->psoc_timestamp_frequency = freq;
 	prop->psoc_pci_pll_nr = nr;
 	prop->psoc_pci_pll_nf = nf;
 	prop->psoc_pci_pll_od = od;
@@ -5324,7 +5339,7 @@ static u32 goya_get_wait_cb_size(struct hl_device *hdev)
 }
 
 static u32 goya_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id,
-		u32 size)
+				u32 size, bool eb)
 {
 	return 0;
 }
diff --git a/drivers/misc/habanalabs/include/common/hl_boot_if.h b/drivers/misc/habanalabs/include/common/hl_boot_if.h
index e5801ecf0cb2..b637dfd69f6e 100644
--- a/drivers/misc/habanalabs/include/common/hl_boot_if.h
+++ b/drivers/misc/habanalabs/include/common/hl_boot_if.h
@@ -145,11 +145,15 @@
  *					implemented. This means that FW will
  *					perform hard reset procedure on
  *					receiving the halt-machine event.
- *					Initialized in: linux
+ *					Initialized in: preboot, u-boot, linux
  *
  * CPU_BOOT_DEV_STS0_PLL_INFO_EN	FW retrieval of PLL info is enabled.
  *					Initialized in: linux
  *
+ * CPU_BOOT_DEV_STS0_CLK_GATE_EN	Clock Gating enabled.
+ *					FW initialized Clock Gating.
+ *					Initialized in: preboot
+ *
  * CPU_BOOT_DEV_STS0_ENABLED		Device status register enabled.
  *					This is a main indication that the
  *					running FW populates the device status
@@ -171,6 +175,7 @@
 #define CPU_BOOT_DEV_STS0_DRAM_SCR_EN			(1 << 9)
 #define CPU_BOOT_DEV_STS0_FW_HARD_RST_EN		(1 << 10)
 #define CPU_BOOT_DEV_STS0_PLL_INFO_EN			(1 << 11)
+#define CPU_BOOT_DEV_STS0_CLK_GATE_EN			(1 << 13)
 #define CPU_BOOT_DEV_STS0_ENABLED			(1 << 31)
 
 enum cpu_boot_status {
@@ -204,6 +209,8 @@ enum kmd_msg {
 	KMD_MSG_GOTO_WFE,
 	KMD_MSG_FIT_RDY,
 	KMD_MSG_SKIP_BMC,
+	RESERVED,
+	KMD_MSG_RST_DEV,
 };
 
 enum cpu_msg_status {
diff --git a/drivers/misc/pvpanic.c b/drivers/misc/pvpanic.c
index 951b37da5e3c..41cab297d66e 100644
--- a/drivers/misc/pvpanic.c
+++ b/drivers/misc/pvpanic.c
@@ -55,12 +55,23 @@ static int pvpanic_mmio_probe(struct platform_device *pdev)
 	struct resource *res;
 
 	res = platform_get_mem_or_io(pdev, 0);
-	if (res && resource_type(res) == IORESOURCE_IO)
+	if (!res)
+		return -EINVAL;
+
+	switch (resource_type(res)) {
+	case IORESOURCE_IO:
 		base = devm_ioport_map(dev, res->start, resource_size(res));
-	else
+		if (!base)
+			return -ENOMEM;
+		break;
+	case IORESOURCE_MEM:
 		base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(base))
-		return PTR_ERR(base);
+		if (IS_ERR(base))
+			return PTR_ERR(base);
+		break;
+	default:
+		return -EINVAL;
+	}
 
 	atomic_notifier_chain_register(&panic_notifier_list,
 				       &pvpanic_panic_nb);
diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index 85ebd2b7e446..85de5f96c02b 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -380,7 +380,7 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 		goto free_dst;
 
 	min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len +
-		BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr);
+		BAREUDP_BASE_HLEN + info->options_len + sizeof(struct ipv6hdr);
 
 	err = skb_cow_head(skb, min_headroom);
 	if (unlikely(err))
@@ -534,6 +534,7 @@ static void bareudp_setup(struct net_device *dev)
 	SET_NETDEV_DEVTYPE(dev, &bareudp_type);
 	dev->features    |= NETIF_F_SG | NETIF_F_HW_CSUM;
 	dev->features    |= NETIF_F_RXCSUM;
+	dev->features    |= NETIF_F_LLTX;
 	dev->features    |= NETIF_F_GSO_SOFTWARE;
 	dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
@@ -644,11 +645,20 @@ static int bareudp_link_config(struct net_device *dev,
 	return 0;
 }
 
+static void bareudp_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct bareudp_dev *bareudp = netdev_priv(dev);
+
+	list_del(&bareudp->next);
+	unregister_netdevice_queue(dev, head);
+}
+
 static int bareudp_newlink(struct net *net, struct net_device *dev,
 			   struct nlattr *tb[], struct nlattr *data[],
 			   struct netlink_ext_ack *extack)
 {
 	struct bareudp_conf conf;
+	LIST_HEAD(list_kill);
 	int err;
 
 	err = bareudp2info(data, &conf, extack);
@@ -661,17 +671,14 @@ static int bareudp_newlink(struct net *net, struct net_device *dev,
 
 	err = bareudp_link_config(dev, tb);
 	if (err)
-		return err;
+		goto err_unconfig;
 
 	return 0;
-}
-
-static void bareudp_dellink(struct net_device *dev, struct list_head *head)
-{
-	struct bareudp_dev *bareudp = netdev_priv(dev);
 
-	list_del(&bareudp->next);
-	unregister_netdevice_queue(dev, head);
+err_unconfig:
+	bareudp_dellink(dev, &list_kill);
+	unregister_netdevice_many(&list_kill);
+	return err;
 }
 
 static size_t bareudp_get_size(const struct net_device *dev)
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 424970939fd4..1c28eade6bec 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -123,6 +123,7 @@ config CAN_JANZ_ICAN3
 config CAN_KVASER_PCIEFD
 	depends on PCI
 	tristate "Kvaser PCIe FD cards"
+	select CRC32
 	  help
 	  This is a driver for the Kvaser PCI Express CAN FD family.
 
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 2c9f12401276..da551fd0f502 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1852,8 +1852,6 @@ EXPORT_SYMBOL_GPL(m_can_class_register);
 void m_can_class_unregister(struct m_can_classdev *cdev)
 {
 	unregister_candev(cdev->net);
-
-	m_can_clk_stop(cdev);
 }
 EXPORT_SYMBOL_GPL(m_can_class_unregister);
 
diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c
index 24c737c4fc44..970f0e9d19bf 100644
--- a/drivers/net/can/m_can/tcan4x5x.c
+++ b/drivers/net/can/m_can/tcan4x5x.c
@@ -131,30 +131,6 @@ static inline struct tcan4x5x_priv *cdev_to_priv(struct m_can_classdev *cdev)
 
 }
 
-static struct can_bittiming_const tcan4x5x_bittiming_const = {
-	.name = DEVICE_NAME,
-	.tseg1_min = 2,
-	.tseg1_max = 31,
-	.tseg2_min = 2,
-	.tseg2_max = 16,
-	.sjw_max = 16,
-	.brp_min = 1,
-	.brp_max = 32,
-	.brp_inc = 1,
-};
-
-static struct can_bittiming_const tcan4x5x_data_bittiming_const = {
-	.name = DEVICE_NAME,
-	.tseg1_min = 1,
-	.tseg1_max = 32,
-	.tseg2_min = 1,
-	.tseg2_max = 16,
-	.sjw_max = 16,
-	.brp_min = 1,
-	.brp_max = 32,
-	.brp_inc = 1,
-};
-
 static void tcan4x5x_check_wake(struct tcan4x5x_priv *priv)
 {
 	int wake_state = 0;
@@ -469,8 +445,6 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 	mcan_class->dev = &spi->dev;
 	mcan_class->ops = &tcan4x5x_ops;
 	mcan_class->is_peripheral = true;
-	mcan_class->bit_timing = &tcan4x5x_bittiming_const;
-	mcan_class->data_timing = &tcan4x5x_data_bittiming_const;
 	mcan_class->net->irq = spi->irq;
 
 	spi_set_drvdata(spi, priv);
diff --git a/drivers/net/can/rcar/Kconfig b/drivers/net/can/rcar/Kconfig
index 8d36101b78e3..29cabc20109e 100644
--- a/drivers/net/can/rcar/Kconfig
+++ b/drivers/net/can/rcar/Kconfig
@@ -1,10 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 config CAN_RCAR
-	tristate "Renesas R-Car CAN controller"
+	tristate "Renesas R-Car and RZ/G CAN controller"
 	depends on ARCH_RENESAS || ARM
 	help
 	  Say Y here if you want to use CAN controller found on Renesas R-Car
-	  SoCs.
+	  or RZ/G SoCs.
 
 	  To compile this driver as a module, choose M here: the module will
 	  be called rcar_can.
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 77129d5f410b..f07e8b737d31 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -1368,13 +1368,10 @@ static int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
 		struct mcp251xfd_tx_ring *tx_ring = priv->tx;
 		struct spi_transfer *last_xfer;
 
-		tx_ring->tail += len;
-
 		/* Increment the TEF FIFO tail pointer 'len' times in
 		 * a single SPI message.
-		 */
-
-		/* Note:
+		 *
+		 * Note:
 		 *
 		 * "cs_change == 1" on the last transfer results in an
 		 * active chip select after the complete SPI
@@ -1391,6 +1388,8 @@ static int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
 		if (err)
 			return err;
 
+		tx_ring->tail += len;
+
 		err = mcp251xfd_check_tef_tail(priv);
 		if (err)
 			return err;
@@ -1492,7 +1491,7 @@ mcp251xfd_handle_rxif_one(struct mcp251xfd_priv *priv,
 	else
 		skb = alloc_can_skb(priv->ndev, (struct can_frame **)&cfd);
 
-	if (!cfd) {
+	if (!skb) {
 		stats->rx_dropped++;
 		return 0;
 	}
@@ -1553,10 +1552,8 @@ mcp251xfd_handle_rxif_ring(struct mcp251xfd_priv *priv,
 
 		/* Increment the RX FIFO tail pointer 'len' times in a
 		 * single SPI message.
-		 */
-		ring->tail += len;
-
-		/* Note:
+		 *
+		 * Note:
 		 *
 		 * "cs_change == 1" on the last transfer results in an
 		 * active chip select after the complete SPI
@@ -1572,6 +1569,8 @@ mcp251xfd_handle_rxif_ring(struct mcp251xfd_priv *priv,
 		last_xfer->cs_change = 1;
 		if (err)
 			return err;
+
+		ring->tail += len;
 	}
 
 	return 0;
diff --git a/drivers/net/dsa/hirschmann/Kconfig b/drivers/net/dsa/hirschmann/Kconfig
index 222dd35e2c9d..e01191107a4b 100644
--- a/drivers/net/dsa/hirschmann/Kconfig
+++ b/drivers/net/dsa/hirschmann/Kconfig
@@ -4,6 +4,7 @@ config NET_DSA_HIRSCHMANN_HELLCREEK
 	depends on HAS_IOMEM
 	depends on NET_DSA
 	depends on PTP_1588_CLOCK
+	depends on LEDS_CLASS
 	select NET_DSA_TAG_HELLCREEK
 	help
 	  This driver adds support for Hirschmann Hellcreek TSN switches.
diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
index 09701c17f3f6..662e68a0e7e6 100644
--- a/drivers/net/dsa/lantiq_gswip.c
+++ b/drivers/net/dsa/lantiq_gswip.c
@@ -92,9 +92,7 @@
 					 GSWIP_MDIO_PHY_FDUP_MASK)
 
 /* GSWIP MII Registers */
-#define GSWIP_MII_CFG0			0x00
-#define GSWIP_MII_CFG1			0x02
-#define GSWIP_MII_CFG5			0x04
+#define GSWIP_MII_CFGp(p)		(0x2 * (p))
 #define  GSWIP_MII_CFG_EN		BIT(14)
 #define  GSWIP_MII_CFG_LDCLKDIS		BIT(12)
 #define  GSWIP_MII_CFG_MODE_MIIP	0x0
@@ -392,17 +390,9 @@ static void gswip_mii_mask(struct gswip_priv *priv, u32 clear, u32 set,
 static void gswip_mii_mask_cfg(struct gswip_priv *priv, u32 clear, u32 set,
 			       int port)
 {
-	switch (port) {
-	case 0:
-		gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG0);
-		break;
-	case 1:
-		gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG1);
-		break;
-	case 5:
-		gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG5);
-		break;
-	}
+	/* There's no MII_CFG register for the CPU port */
+	if (!dsa_is_cpu_port(priv->ds, port))
+		gswip_mii_mask(priv, clear, set, GSWIP_MII_CFGp(port));
 }
 
 static void gswip_mii_mask_pcdu(struct gswip_priv *priv, u32 clear, u32 set,
@@ -822,9 +812,8 @@ static int gswip_setup(struct dsa_switch *ds)
 	gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1);
 
 	/* Disable the xMII link */
-	gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 0);
-	gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 1);
-	gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 5);
+	for (i = 0; i < priv->hw_info->max_ports; i++)
+		gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, i);
 
 	/* enable special tag insertion on cpu port */
 	gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN,
@@ -1447,11 +1436,12 @@ static void gswip_phylink_validate(struct dsa_switch *ds, int port,
 	phylink_set(mask, Pause);
 	phylink_set(mask, Asym_Pause);
 
-	/* With the exclusion of MII and Reverse MII, we support Gigabit,
-	 * including Half duplex
+	/* With the exclusion of MII, Reverse MII and Reduced MII, we
+	 * support Gigabit, including Half duplex
 	 */
 	if (state->interface != PHY_INTERFACE_MODE_MII &&
-	    state->interface != PHY_INTERFACE_MODE_REVMII) {
+	    state->interface != PHY_INTERFACE_MODE_REVMII &&
+	    state->interface != PHY_INTERFACE_MODE_RMII) {
 		phylink_set(mask, 1000baseT_Full);
 		phylink_set(mask, 1000baseT_Half);
 	}
@@ -1541,9 +1531,7 @@ static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port,
 {
 	struct gswip_priv *priv = ds->priv;
 
-	/* Enable the xMII interface only for the external PHY */
-	if (interface != PHY_INTERFACE_MODE_INTERNAL)
-		gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port);
+	gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port);
 }
 
 static void gswip_get_strings(struct dsa_switch *ds, int port, u32 stringset,
diff --git a/drivers/net/ethernet/aquantia/Kconfig b/drivers/net/ethernet/aquantia/Kconfig
index efb33c078a3c..cec2018c84a9 100644
--- a/drivers/net/ethernet/aquantia/Kconfig
+++ b/drivers/net/ethernet/aquantia/Kconfig
@@ -19,7 +19,6 @@ if NET_VENDOR_AQUANTIA
 config AQTION
 	tristate "aQuantia AQtion(tm) Support"
 	depends on PCI
-	depends on X86_64 || ARM64 || COMPILE_TEST
 	depends on MACSEC || MACSEC=n
 	help
 	  This enables the support for the aQuantia AQtion(tm) Ethernet card.
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 0fdd19d99d99..b1ae9eb8f247 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2577,6 +2577,7 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 			 NETIF_F_HW_VLAN_CTAG_TX;
 	dev->hw_features |= dev->features;
 	dev->vlan_features |= dev->features;
+	dev->max_mtu = UMAC_MAX_MTU_SIZE;
 
 	/* Request the WOL interrupt and advertise suspend if available */
 	priv->wol_irq_disabled = 1;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4edd6f8e017e..d10e4f85dd11 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6790,8 +6790,10 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 		ctx->tqm_fp_rings_count = resp->tqm_fp_rings_count;
 		if (!ctx->tqm_fp_rings_count)
 			ctx->tqm_fp_rings_count = bp->max_q;
+		else if (ctx->tqm_fp_rings_count > BNXT_MAX_TQM_FP_RINGS)
+			ctx->tqm_fp_rings_count = BNXT_MAX_TQM_FP_RINGS;
 
-		tqm_rings = ctx->tqm_fp_rings_count + 1;
+		tqm_rings = ctx->tqm_fp_rings_count + BNXT_MAX_TQM_SP_RINGS;
 		ctx_pg = kcalloc(tqm_rings, sizeof(*ctx_pg), GFP_KERNEL);
 		if (!ctx_pg) {
 			kfree(ctx);
@@ -6925,7 +6927,8 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 	     pg_attr = &req.tqm_sp_pg_size_tqm_sp_lvl,
 	     pg_dir = &req.tqm_sp_page_dir,
 	     ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP;
-	     i < 9; i++, num_entries++, pg_attr++, pg_dir++, ena <<= 1) {
+	     i < BNXT_MAX_TQM_RINGS;
+	     i++, num_entries++, pg_attr++, pg_dir++, ena <<= 1) {
 		if (!(enables & ena))
 			continue;
 
@@ -12887,10 +12890,10 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
  */
 static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 {
+	pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT;
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct bnxt *bp = netdev_priv(netdev);
 	int err = 0, off;
-	pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT;
 
 	netdev_info(bp->dev, "PCI Slot Reset\n");
 
@@ -12919,22 +12922,8 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 		pci_save_state(pdev);
 
 		err = bnxt_hwrm_func_reset(bp);
-		if (!err) {
-			err = bnxt_hwrm_func_qcaps(bp);
-			if (!err && netif_running(netdev))
-				err = bnxt_open(netdev);
-		}
-		bnxt_ulp_start(bp, err);
-		if (!err) {
-			bnxt_reenable_sriov(bp);
+		if (!err)
 			result = PCI_ERS_RESULT_RECOVERED;
-		}
-	}
-
-	if (result != PCI_ERS_RESULT_RECOVERED) {
-		if (netif_running(netdev))
-			dev_close(netdev);
-		pci_disable_device(pdev);
 	}
 
 	rtnl_unlock();
@@ -12952,10 +12941,21 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 static void bnxt_io_resume(struct pci_dev *pdev)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct bnxt *bp = netdev_priv(netdev);
+	int err;
 
+	netdev_info(bp->dev, "PCI Slot Resume\n");
 	rtnl_lock();
 
-	netif_device_attach(netdev);
+	err = bnxt_hwrm_func_qcaps(bp);
+	if (!err && netif_running(netdev))
+		err = bnxt_open(netdev);
+
+	bnxt_ulp_start(bp, err);
+	if (!err) {
+		bnxt_reenable_sriov(bp);
+		netif_device_attach(netdev);
+	}
 
 	rtnl_unlock();
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 950ea26ae0d2..51996c85547e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1436,6 +1436,11 @@ struct bnxt_ctx_pg_info {
 	struct bnxt_ctx_pg_info **ctx_pg_tbl;
 };
 
+#define BNXT_MAX_TQM_SP_RINGS		1
+#define BNXT_MAX_TQM_FP_RINGS		8
+#define BNXT_MAX_TQM_RINGS		\
+	(BNXT_MAX_TQM_SP_RINGS + BNXT_MAX_TQM_FP_RINGS)
+
 struct bnxt_ctx_mem_info {
 	u32	qp_max_entries;
 	u16	qp_min_qp1_entries;
@@ -1474,7 +1479,7 @@ struct bnxt_ctx_mem_info {
 	struct bnxt_ctx_pg_info stat_mem;
 	struct bnxt_ctx_pg_info mrav_mem;
 	struct bnxt_ctx_pg_info tim_mem;
-	struct bnxt_ctx_pg_info *tqm_mem[9];
+	struct bnxt_ctx_pg_info *tqm_mem[BNXT_MAX_TQM_RINGS];
 };
 
 struct bnxt_fw_health {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 9ff79d5d14c4..2f8b193a772d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2532,7 +2532,7 @@ int bnxt_flash_package_from_fw_obj(struct net_device *dev, const struct firmware
 
 		if (rc && ((struct hwrm_err_output *)&resp)->cmd_err ==
 		    NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
-			install.flags |=
+			install.flags =
 				cpu_to_le16(NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG);
 
 			rc = _hwrm_send_message_silent(bp, &install,
@@ -2546,6 +2546,7 @@ int bnxt_flash_package_from_fw_obj(struct net_device *dev, const struct firmware
 				 * UPDATE directory and try the flash again
 				 */
 				defrag_attempted = true;
+				install.flags = 0;
 				rc = __bnxt_flash_nvram(bp->dev,
 							BNX_DIR_TYPE_UPDATE,
 							BNX_DIR_ORDINAL_FIRST,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 8c8368c2f335..64dbbb04b043 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -222,8 +222,12 @@ int bnxt_get_ulp_msix_base(struct bnxt *bp)
 
 int bnxt_get_ulp_stat_ctxs(struct bnxt *bp)
 {
-	if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP))
-		return BNXT_MIN_ROCE_STAT_CTXS;
+	if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) {
+		struct bnxt_en_dev *edev = bp->edev;
+
+		if (edev->ulp_tbl[BNXT_ROCE_ULP].msix_requested)
+			return BNXT_MIN_ROCE_STAT_CTXS;
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index d5d910916c2e..814a5b10141d 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -467,7 +467,7 @@ static void macb_set_tx_clk(struct macb *bp, int speed)
 {
 	long ferr, rate, rate_rounded;
 
-	if (!bp->tx_clk || !(bp->caps & MACB_CAPS_CLK_HW_CHG))
+	if (!bp->tx_clk || (bp->caps & MACB_CAPS_CLK_HW_CHG))
 		return;
 
 	switch (speed) {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
index 92473dda55d9..22a0220123ad 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
@@ -40,6 +40,13 @@
 #define TCB_L2T_IX_M		0xfffULL
 #define TCB_L2T_IX_V(x)		((x) << TCB_L2T_IX_S)
 
+#define TCB_T_FLAGS_W           1
+#define TCB_T_FLAGS_S           0
+#define TCB_T_FLAGS_M           0xffffffffffffffffULL
+#define TCB_T_FLAGS_V(x)        ((__u64)(x) << TCB_T_FLAGS_S)
+
+#define TCB_FIELD_COOKIE_TFLAG	1
+
 #define TCB_SMAC_SEL_W		0
 #define TCB_SMAC_SEL_S		24
 #define TCB_SMAC_SEL_M		0xffULL
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
index 72bb123d53db..9e2378013642 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h
@@ -575,7 +575,11 @@ int send_tx_flowc_wr(struct sock *sk, int compl,
 void chtls_tcp_push(struct sock *sk, int flags);
 int chtls_push_frames(struct chtls_sock *csk, int comp);
 int chtls_set_tcb_tflag(struct sock *sk, unsigned int bit_pos, int val);
+void chtls_set_tcb_field_rpl_skb(struct sock *sk, u16 word,
+				 u64 mask, u64 val, u8 cookie,
+				 int through_l2t);
 int chtls_setkey(struct chtls_sock *csk, u32 keylen, u32 mode, int cipher_type);
+void chtls_set_quiesce_ctrl(struct sock *sk, int val);
 void skb_entail(struct sock *sk, struct sk_buff *skb, int flags);
 unsigned int keyid_to_addr(int start_addr, int keyid);
 void free_tls_keyid(struct sock *sk);
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
index a0e0d8a83681..e5cfbe196ba6 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
@@ -32,6 +32,7 @@
 #include "chtls.h"
 #include "chtls_cm.h"
 #include "clip_tbl.h"
+#include "t4_tcb.h"
 
 /*
  * State transitions and actions for close.  Note that if we are in SYN_SENT
@@ -267,7 +268,9 @@ static void chtls_send_reset(struct sock *sk, int mode, struct sk_buff *skb)
 	if (sk->sk_state != TCP_SYN_RECV)
 		chtls_send_abort(sk, mode, skb);
 	else
-		goto out;
+		chtls_set_tcb_field_rpl_skb(sk, TCB_T_FLAGS_W,
+					    TCB_T_FLAGS_V(TCB_T_FLAGS_M), 0,
+					    TCB_FIELD_COOKIE_TFLAG, 1);
 
 	return;
 out:
@@ -621,7 +624,7 @@ static void chtls_reset_synq(struct listen_ctx *listen_ctx)
 
 	while (!skb_queue_empty(&listen_ctx->synq)) {
 		struct chtls_sock *csk =
-			container_of((struct synq *)__skb_dequeue
+			container_of((struct synq *)skb_peek
 				(&listen_ctx->synq), struct chtls_sock, synq);
 		struct sock *child = csk->sk;
 
@@ -1109,6 +1112,7 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 				    const struct cpl_pass_accept_req *req,
 				    struct chtls_dev *cdev)
 {
+	struct adapter *adap = pci_get_drvdata(cdev->pdev);
 	struct neighbour *n = NULL;
 	struct inet_sock *newinet;
 	const struct iphdr *iph;
@@ -1118,9 +1122,10 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 	struct dst_entry *dst;
 	struct tcp_sock *tp;
 	struct sock *newsk;
+	bool found = false;
 	u16 port_id;
 	int rxq_idx;
-	int step;
+	int step, i;
 
 	iph = (const struct iphdr *)network_hdr;
 	newsk = tcp_create_openreq_child(lsk, oreq, cdev->askb);
@@ -1152,7 +1157,7 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 		n = dst_neigh_lookup(dst, &ip6h->saddr);
 #endif
 	}
-	if (!n)
+	if (!n || !n->dev)
 		goto free_sk;
 
 	ndev = n->dev;
@@ -1161,6 +1166,13 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 	if (is_vlan_dev(ndev))
 		ndev = vlan_dev_real_dev(ndev);
 
+	for_each_port(adap, i)
+		if (cdev->ports[i] == ndev)
+			found = true;
+
+	if (!found)
+		goto free_dst;
+
 	port_id = cxgb4_port_idx(ndev);
 
 	csk = chtls_sock_create(cdev);
@@ -1238,6 +1250,7 @@ static struct sock *chtls_recv_sock(struct sock *lsk,
 free_csk:
 	chtls_sock_release(&csk->kref);
 free_dst:
+	neigh_release(n);
 	dst_release(dst);
 free_sk:
 	inet_csk_prepare_forced_close(newsk);
@@ -1387,7 +1400,7 @@ static void chtls_pass_accept_request(struct sock *sk,
 
 	newsk = chtls_recv_sock(sk, oreq, network_hdr, req, cdev);
 	if (!newsk)
-		goto free_oreq;
+		goto reject;
 
 	if (chtls_get_module(newsk))
 		goto reject;
@@ -1403,8 +1416,6 @@ static void chtls_pass_accept_request(struct sock *sk,
 	kfree_skb(skb);
 	return;
 
-free_oreq:
-	chtls_reqsk_free(oreq);
 reject:
 	mk_tid_release(reply_skb, 0, tid);
 	cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb);
@@ -1589,6 +1600,11 @@ static int chtls_pass_establish(struct chtls_dev *cdev, struct sk_buff *skb)
 			sk_wake_async(sk, 0, POLL_OUT);
 
 		data = lookup_stid(cdev->tids, stid);
+		if (!data) {
+			/* listening server close */
+			kfree_skb(skb);
+			goto unlock;
+		}
 		lsk = ((struct listen_ctx *)data)->lsk;
 
 		bh_lock_sock(lsk);
@@ -1936,6 +1952,8 @@ static void chtls_close_con_rpl(struct sock *sk, struct sk_buff *skb)
 		else if (tcp_sk(sk)->linger2 < 0 &&
 			 !csk_flag_nochk(csk, CSK_ABORT_SHUTDOWN))
 			chtls_abort_conn(sk, skb);
+		else if (csk_flag_nochk(csk, CSK_TX_DATA_SENT))
+			chtls_set_quiesce_ctrl(sk, 0);
 		break;
 	default:
 		pr_info("close_con_rpl in bad state %d\n", sk->sk_state);
@@ -1997,39 +2015,6 @@ static void t4_defer_reply(struct sk_buff *skb, struct chtls_dev *cdev,
 	spin_unlock_bh(&cdev->deferq.lock);
 }
 
-static void send_abort_rpl(struct sock *sk, struct sk_buff *skb,
-			   struct chtls_dev *cdev, int status, int queue)
-{
-	struct cpl_abort_req_rss *req = cplhdr(skb);
-	struct sk_buff *reply_skb;
-	struct chtls_sock *csk;
-
-	csk = rcu_dereference_sk_user_data(sk);
-
-	reply_skb = alloc_skb(sizeof(struct cpl_abort_rpl),
-			      GFP_KERNEL);
-
-	if (!reply_skb) {
-		req->status = (queue << 1);
-		t4_defer_reply(skb, cdev, send_defer_abort_rpl);
-		return;
-	}
-
-	set_abort_rpl_wr(reply_skb, GET_TID(req), status);
-	kfree_skb(skb);
-
-	set_wr_txq(reply_skb, CPL_PRIORITY_DATA, queue);
-	if (csk_conn_inline(csk)) {
-		struct l2t_entry *e = csk->l2t_entry;
-
-		if (e && sk->sk_state != TCP_SYN_RECV) {
-			cxgb4_l2t_send(csk->egress_dev, reply_skb, e);
-			return;
-		}
-	}
-	cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb);
-}
-
 static void chtls_send_abort_rpl(struct sock *sk, struct sk_buff *skb,
 				 struct chtls_dev *cdev,
 				 int status, int queue)
@@ -2078,9 +2063,9 @@ static void bl_abort_syn_rcv(struct sock *lsk, struct sk_buff *skb)
 	queue = csk->txq_idx;
 
 	skb->sk	= NULL;
+	chtls_send_abort_rpl(child, skb, BLOG_SKB_CB(skb)->cdev,
+			     CPL_ABORT_NO_RST, queue);
 	do_abort_syn_rcv(child, lsk);
-	send_abort_rpl(child, skb, BLOG_SKB_CB(skb)->cdev,
-		       CPL_ABORT_NO_RST, queue);
 }
 
 static int abort_syn_rcv(struct sock *sk, struct sk_buff *skb)
@@ -2110,8 +2095,8 @@ static int abort_syn_rcv(struct sock *sk, struct sk_buff *skb)
 	if (!sock_owned_by_user(psk)) {
 		int queue = csk->txq_idx;
 
+		chtls_send_abort_rpl(sk, skb, cdev, CPL_ABORT_NO_RST, queue);
 		do_abort_syn_rcv(sk, psk);
-		send_abort_rpl(sk, skb, cdev, CPL_ABORT_NO_RST, queue);
 	} else {
 		skb->sk = sk;
 		BLOG_SKB_CB(skb)->backlog_rcv = bl_abort_syn_rcv;
@@ -2129,9 +2114,6 @@ static void chtls_abort_req_rss(struct sock *sk, struct sk_buff *skb)
 	int queue = csk->txq_idx;
 
 	if (is_neg_adv(req->status)) {
-		if (sk->sk_state == TCP_SYN_RECV)
-			chtls_set_tcb_tflag(sk, 0, 0);
-
 		kfree_skb(skb);
 		return;
 	}
@@ -2158,12 +2140,12 @@ static void chtls_abort_req_rss(struct sock *sk, struct sk_buff *skb)
 		if (sk->sk_state == TCP_SYN_RECV && !abort_syn_rcv(sk, skb))
 			return;
 
-		chtls_release_resources(sk);
-		chtls_conn_done(sk);
 	}
 
 	chtls_send_abort_rpl(sk, skb, BLOG_SKB_CB(skb)->cdev,
 			     rst_status, queue);
+	chtls_release_resources(sk);
+	chtls_conn_done(sk);
 }
 
 static void chtls_abort_rpl_rss(struct sock *sk, struct sk_buff *skb)
@@ -2315,6 +2297,28 @@ static int chtls_wr_ack(struct chtls_dev *cdev, struct sk_buff *skb)
 	return 0;
 }
 
+static int chtls_set_tcb_rpl(struct chtls_dev *cdev, struct sk_buff *skb)
+{
+	struct cpl_set_tcb_rpl *rpl = cplhdr(skb) + RSS_HDR;
+	unsigned int hwtid = GET_TID(rpl);
+	struct sock *sk;
+
+	sk = lookup_tid(cdev->tids, hwtid);
+
+	/* return EINVAL if socket doesn't exist */
+	if (!sk)
+		return -EINVAL;
+
+	/* Reusing the skb as size of cpl_set_tcb_field structure
+	 * is greater than cpl_abort_req
+	 */
+	if (TCB_COOKIE_G(rpl->cookie) == TCB_FIELD_COOKIE_TFLAG)
+		chtls_send_abort(sk, CPL_ABORT_SEND_RST, NULL);
+
+	kfree_skb(skb);
+	return 0;
+}
+
 chtls_handler_func chtls_handlers[NUM_CPL_CMDS] = {
 	[CPL_PASS_OPEN_RPL]     = chtls_pass_open_rpl,
 	[CPL_CLOSE_LISTSRV_RPL] = chtls_close_listsrv_rpl,
@@ -2327,5 +2331,6 @@ chtls_handler_func chtls_handlers[NUM_CPL_CMDS] = {
 	[CPL_CLOSE_CON_RPL]     = chtls_conn_cpl,
 	[CPL_ABORT_REQ_RSS]     = chtls_conn_cpl,
 	[CPL_ABORT_RPL_RSS]     = chtls_conn_cpl,
-	[CPL_FW4_ACK]           = chtls_wr_ack,
+	[CPL_FW4_ACK]		= chtls_wr_ack,
+	[CPL_SET_TCB_RPL]	= chtls_set_tcb_rpl,
 };
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c
index a4fb463af22a..1e67140b0f80 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c
@@ -88,6 +88,24 @@ static int chtls_set_tcb_field(struct sock *sk, u16 word, u64 mask, u64 val)
 	return ret < 0 ? ret : 0;
 }
 
+void chtls_set_tcb_field_rpl_skb(struct sock *sk, u16 word,
+				 u64 mask, u64 val, u8 cookie,
+				 int through_l2t)
+{
+	struct sk_buff *skb;
+	unsigned int wrlen;
+
+	wrlen = sizeof(struct cpl_set_tcb_field) + sizeof(struct ulptx_idata);
+	wrlen = roundup(wrlen, 16);
+
+	skb = alloc_skb(wrlen, GFP_KERNEL | __GFP_NOFAIL);
+	if (!skb)
+		return;
+
+	__set_tcb_field(sk, skb, word, mask, val, cookie, 0);
+	send_or_defer(sk, tcp_sk(sk), skb, through_l2t);
+}
+
 /*
  * Set one of the t_flags bits in the TCB.
  */
@@ -113,6 +131,29 @@ static int chtls_set_tcb_quiesce(struct sock *sk, int val)
 				   TF_RX_QUIESCE_V(val));
 }
 
+void chtls_set_quiesce_ctrl(struct sock *sk, int val)
+{
+	struct chtls_sock *csk;
+	struct sk_buff *skb;
+	unsigned int wrlen;
+	int ret;
+
+	wrlen = sizeof(struct cpl_set_tcb_field) + sizeof(struct ulptx_idata);
+	wrlen = roundup(wrlen, 16);
+
+	skb = alloc_skb(wrlen, GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	csk = rcu_dereference_sk_user_data(sk);
+
+	__set_tcb_field(sk, skb, 1, TF_RX_QUIESCE_V(1), 0, 0, 1);
+	set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->port_id);
+	ret = cxgb4_ofld_send(csk->egress_dev, skb);
+	if (ret < 0)
+		kfree_skb(skb);
+}
+
 /* TLS Key bitmap processing */
 int chtls_init_kmap(struct chtls_dev *cdev, struct cxgb4_lld_info *lldi)
 {
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 0981fe9652e5..3d9b0b161e24 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1211,7 +1211,7 @@ static int ethoc_probe(struct platform_device *pdev)
 	ret = mdiobus_register(priv->mdio);
 	if (ret) {
 		dev_err(&netdev->dev, "failed to register MDIO bus\n");
-		goto free2;
+		goto free3;
 	}
 
 	ret = ethoc_mdio_probe(netdev);
@@ -1243,6 +1243,7 @@ error2:
 	netif_napi_del(&priv->napi);
 error:
 	mdiobus_unregister(priv->mdio);
+free3:
 	mdiobus_free(priv->mdio);
 free2:
 	clk_disable_unprepare(priv->clk);
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
index c8e5d889bd81..21de56345503 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
@@ -223,3 +223,4 @@ static struct platform_driver fs_enet_bb_mdio_driver = {
 };
 
 module_platform_driver(fs_enet_bb_mdio_driver);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
index 8b51ee142fa3..152f4d83765a 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
@@ -224,3 +224,4 @@ static struct platform_driver fs_enet_fec_mdio_driver = {
 };
 
 module_platform_driver(fs_enet_fec_mdio_driver);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index ba8869c3d891..6d853f018d53 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -3889,6 +3889,7 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 	INIT_WORK(&ugeth->timeout_work, ucc_geth_timeout_work);
 	netif_napi_add(dev, &ugeth->napi, ucc_geth_poll, 64);
 	dev->mtu = 1500;
+	dev->max_mtu = 1518;
 
 	ugeth->msg_enable = netif_msg_init(debug.msg_enable, UGETH_MSG_DEFAULT);
 	ugeth->phy_interface = phy_interface;
@@ -3934,12 +3935,12 @@ static int ucc_geth_remove(struct platform_device* ofdev)
 	struct device_node *np = ofdev->dev.of_node;
 
 	unregister_netdev(dev);
-	free_netdev(dev);
 	ucc_geth_memclean(ugeth);
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 	of_node_put(ugeth->ug_info->tbi_node);
 	of_node_put(ugeth->ug_info->phy_node);
+	free_netdev(dev);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/freescale/ucc_geth.h b/drivers/net/ethernet/freescale/ucc_geth.h
index 1a9bdf66a7d8..11d4bf5dc21f 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.h
+++ b/drivers/net/ethernet/freescale/ucc_geth.h
@@ -575,7 +575,14 @@ struct ucc_geth_tx_global_pram {
 	u32 vtagtable[0x8];	/* 8 4-byte VLAN tags */
 	u32 tqptr;		/* a base pointer to the Tx Queues Memory
 				   Region */
-	u8 res2[0x80 - 0x74];
+	u8 res2[0x78 - 0x74];
+	u64 snums_en;
+	u32 l2l3baseptr;	/* top byte consists of a few other bit fields */
+
+	u16 mtu[8];
+	u8 res3[0xa8 - 0x94];
+	u32 wrrtablebase;	/* top byte is reserved */
+	u8 res4[0xc0 - 0xac];
 } __packed;
 
 /* structure representing Extended Filtering Global Parameters in PRAM */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 7165da0ee9aa..a6e3f07caf99 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -415,6 +415,10 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data,
 	/* for mutl buffer*/
 	new_skb = skb_copy(skb, GFP_ATOMIC);
 	dev_kfree_skb_any(skb);
+	if (!new_skb) {
+		netdev_err(ndev, "skb alloc failed\n");
+		return;
+	}
 	skb = new_skb;
 
 	check_ok = 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index fb5e8842983c..33defa4c180a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -169,7 +169,7 @@ struct hclgevf_mbx_arq_ring {
 #define hclge_mbx_ring_ptr_move_crq(crq) \
 	(crq->next_to_use = (crq->next_to_use + 1) % crq->desc_num)
 #define hclge_mbx_tail_ptr_move_arq(arq) \
-	(arq.tail = (arq.tail + 1) % HCLGE_MBX_MAX_ARQ_MSG_SIZE)
+		(arq.tail = (arq.tail + 1) % HCLGE_MBX_MAX_ARQ_MSG_NUM)
 #define hclge_mbx_head_ptr_move_arq(arq) \
-		(arq.head = (arq.head + 1) % HCLGE_MBX_MAX_ARQ_MSG_SIZE)
+		(arq.head = (arq.head + 1) % HCLGE_MBX_MAX_ARQ_MSG_NUM)
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index e6f37f91c489..c242883fea5d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -752,7 +752,8 @@ static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset)
 		handle->flags |= HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK;
 		handle->flags |= HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK;
 
-		if (hdev->hw.mac.phydev) {
+		if (hdev->hw.mac.phydev && hdev->hw.mac.phydev->drv &&
+		    hdev->hw.mac.phydev->drv->set_loopback) {
 			count += 1;
 			handle->flags |= HNAE3_SUPPORT_PHY_LOOPBACK;
 		}
@@ -4537,8 +4538,8 @@ static int hclge_set_rss_tuple(struct hnae3_handle *handle,
 		req->ipv4_sctp_en = tuple_sets;
 		break;
 	case SCTP_V6_FLOW:
-		if ((nfc->data & RXH_L4_B_0_1) ||
-		    (nfc->data & RXH_L4_B_2_3))
+		if (hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 &&
+		    (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)))
 			return -EINVAL;
 
 		req->ipv6_sctp_en = tuple_sets;
@@ -4730,6 +4731,8 @@ static void hclge_rss_init_cfg(struct hclge_dev *hdev)
 		vport[i].rss_tuple_sets.ipv6_udp_en =
 			HCLGE_RSS_INPUT_TUPLE_OTHER;
 		vport[i].rss_tuple_sets.ipv6_sctp_en =
+			hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 ?
+			HCLGE_RSS_INPUT_TUPLE_SCTP_NO_PORT :
 			HCLGE_RSS_INPUT_TUPLE_SCTP;
 		vport[i].rss_tuple_sets.ipv6_fragment_en =
 			HCLGE_RSS_INPUT_TUPLE_OTHER;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 50a294dfaff5..ca46bc9110d7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -107,6 +107,8 @@
 #define HCLGE_D_IP_BIT			BIT(2)
 #define HCLGE_S_IP_BIT			BIT(3)
 #define HCLGE_V_TAG_BIT			BIT(4)
+#define HCLGE_RSS_INPUT_TUPLE_SCTP_NO_PORT	\
+		(HCLGE_D_IP_BIT | HCLGE_S_IP_BIT | HCLGE_V_TAG_BIT)
 
 #define HCLGE_RSS_TC_SIZE_0		1
 #define HCLGE_RSS_TC_SIZE_1		2
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 145757cb70f9..674b3a22e91f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -917,8 +917,8 @@ static int hclgevf_set_rss_tuple(struct hnae3_handle *handle,
 		req->ipv4_sctp_en = tuple_sets;
 		break;
 	case SCTP_V6_FLOW:
-		if ((nfc->data & RXH_L4_B_0_1) ||
-		    (nfc->data & RXH_L4_B_2_3))
+		if (hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 &&
+		    (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)))
 			return -EINVAL;
 
 		req->ipv6_sctp_en = tuple_sets;
@@ -2502,7 +2502,10 @@ static void hclgevf_rss_init_cfg(struct hclgevf_dev *hdev)
 		tuple_sets->ipv4_fragment_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
 		tuple_sets->ipv6_tcp_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
 		tuple_sets->ipv6_udp_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
-		tuple_sets->ipv6_sctp_en = HCLGEVF_RSS_INPUT_TUPLE_SCTP;
+		tuple_sets->ipv6_sctp_en =
+			hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 ?
+					HCLGEVF_RSS_INPUT_TUPLE_SCTP_NO_PORT :
+					HCLGEVF_RSS_INPUT_TUPLE_SCTP;
 		tuple_sets->ipv6_fragment_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 1b183bc35604..f6d817a3edcb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -122,6 +122,8 @@
 #define HCLGEVF_D_IP_BIT		BIT(2)
 #define HCLGEVF_S_IP_BIT		BIT(3)
 #define HCLGEVF_V_TAG_BIT		BIT(4)
+#define HCLGEVF_RSS_INPUT_TUPLE_SCTP_NO_PORT	\
+	(HCLGEVF_D_IP_BIT | HCLGEVF_S_IP_BIT | HCLGEVF_V_TAG_BIT)
 
 #define HCLGEVF_STATS_TIMER_INTERVAL	36U
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index f302504faa8a..9778c83150f1 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -955,6 +955,7 @@ static void release_resources(struct ibmvnic_adapter *adapter)
 	release_rx_pools(adapter);
 
 	release_napi(adapter);
+	release_login_buffer(adapter);
 	release_login_rsp_buffer(adapter);
 }
 
@@ -2341,8 +2342,7 @@ static void __ibmvnic_reset(struct work_struct *work)
 				set_current_state(TASK_UNINTERRUPTIBLE);
 				schedule_timeout(60 * HZ);
 			}
-		} else if (!(rwi->reset_reason == VNIC_RESET_FATAL &&
-				adapter->from_passive_init)) {
+		} else {
 			rc = do_reset(adapter, rwi, reset_state);
 		}
 		kfree(rwi);
@@ -2981,9 +2981,7 @@ static int reset_one_sub_crq_queue(struct ibmvnic_adapter *adapter,
 	int rc;
 
 	if (!scrq) {
-		netdev_dbg(adapter->netdev,
-			   "Invalid scrq reset. irq (%d) or msgs (%p).\n",
-			   scrq->irq, scrq->msgs);
+		netdev_dbg(adapter->netdev, "Invalid scrq reset.\n");
 		return -EINVAL;
 	}
 
@@ -3873,7 +3871,9 @@ static int send_login(struct ibmvnic_adapter *adapter)
 		return -1;
 	}
 
+	release_login_buffer(adapter);
 	release_login_rsp_buffer(adapter);
+
 	client_data_len = vnic_client_data_len(adapter);
 
 	buffer_size =
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index ba7a0f8f6937..5b2143f4b1f8 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -436,6 +436,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca);
 #define FLAG2_DFLT_CRC_STRIPPING          BIT(12)
 #define FLAG2_CHECK_RX_HWTSTAMP           BIT(13)
 #define FLAG2_CHECK_SYSTIM_OVERFLOW       BIT(14)
+#define FLAG2_ENABLE_S0IX_FLOWS           BIT(15)
 
 #define E1000_RX_DESC_PS(R, i)	    \
 	(&(((union e1000_rx_desc_packet_split *)((R).desc))[i]))
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 03215b0aee4b..06442e6bef73 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -23,6 +23,13 @@ struct e1000_stats {
 	int stat_offset;
 };
 
+static const char e1000e_priv_flags_strings[][ETH_GSTRING_LEN] = {
+#define E1000E_PRIV_FLAGS_S0IX_ENABLED	BIT(0)
+	"s0ix-enabled",
+};
+
+#define E1000E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(e1000e_priv_flags_strings)
+
 #define E1000_STAT(str, m) { \
 		.stat_string = str, \
 		.type = E1000_STATS, \
@@ -1776,6 +1783,8 @@ static int e1000e_get_sset_count(struct net_device __always_unused *netdev,
 		return E1000_TEST_LEN;
 	case ETH_SS_STATS:
 		return E1000_STATS_LEN;
+	case ETH_SS_PRIV_FLAGS:
+		return E1000E_PRIV_FLAGS_STR_LEN;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -2097,6 +2106,10 @@ static void e1000_get_strings(struct net_device __always_unused *netdev,
 			p += ETH_GSTRING_LEN;
 		}
 		break;
+	case ETH_SS_PRIV_FLAGS:
+		memcpy(data, e1000e_priv_flags_strings,
+		       E1000E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
+		break;
 	}
 }
 
@@ -2305,6 +2318,37 @@ static int e1000e_get_ts_info(struct net_device *netdev,
 	return 0;
 }
 
+static u32 e1000e_get_priv_flags(struct net_device *netdev)
+{
+	struct e1000_adapter *adapter = netdev_priv(netdev);
+	u32 priv_flags = 0;
+
+	if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS)
+		priv_flags |= E1000E_PRIV_FLAGS_S0IX_ENABLED;
+
+	return priv_flags;
+}
+
+static int e1000e_set_priv_flags(struct net_device *netdev, u32 priv_flags)
+{
+	struct e1000_adapter *adapter = netdev_priv(netdev);
+	unsigned int flags2 = adapter->flags2;
+
+	flags2 &= ~FLAG2_ENABLE_S0IX_FLOWS;
+	if (priv_flags & E1000E_PRIV_FLAGS_S0IX_ENABLED) {
+		struct e1000_hw *hw = &adapter->hw;
+
+		if (hw->mac.type < e1000_pch_cnp)
+			return -EINVAL;
+		flags2 |= FLAG2_ENABLE_S0IX_FLOWS;
+	}
+
+	if (flags2 != adapter->flags2)
+		adapter->flags2 = flags2;
+
+	return 0;
+}
+
 static const struct ethtool_ops e1000_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS,
 	.get_drvinfo		= e1000_get_drvinfo,
@@ -2336,6 +2380,8 @@ static const struct ethtool_ops e1000_ethtool_ops = {
 	.set_eee		= e1000e_set_eee,
 	.get_link_ksettings	= e1000_get_link_ksettings,
 	.set_link_ksettings	= e1000_set_link_ksettings,
+	.get_priv_flags		= e1000e_get_priv_flags,
+	.set_priv_flags		= e1000e_set_priv_flags,
 };
 
 void e1000e_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 9aa6fad8ed47..6fb46682b058 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -1240,6 +1240,9 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force)
 		return 0;
 
 	if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) {
+		struct e1000_adapter *adapter = hw->adapter;
+		bool firmware_bug = false;
+
 		if (force) {
 			/* Request ME un-configure ULP mode in the PHY */
 			mac_reg = er32(H2ME);
@@ -1248,16 +1251,24 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force)
 			ew32(H2ME, mac_reg);
 		}
 
-		/* Poll up to 300msec for ME to clear ULP_CFG_DONE. */
+		/* Poll up to 2.5 seconds for ME to clear ULP_CFG_DONE.
+		 * If this takes more than 1 second, show a warning indicating a
+		 * firmware bug
+		 */
 		while (er32(FWSM) & E1000_FWSM_ULP_CFG_DONE) {
-			if (i++ == 30) {
+			if (i++ == 250) {
 				ret_val = -E1000_ERR_PHY;
 				goto out;
 			}
+			if (i > 100 && !firmware_bug)
+				firmware_bug = true;
 
 			usleep_range(10000, 11000);
 		}
-		e_dbg("ULP_CONFIG_DONE cleared after %dmsec\n", i * 10);
+		if (firmware_bug)
+			e_warn("ULP_CONFIG_DONE took %dmsec.  This is a firmware bug\n", i * 10);
+		else
+			e_dbg("ULP_CONFIG_DONE cleared after %dmsec\n", i * 10);
 
 		if (force) {
 			mac_reg = er32(H2ME);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 128ab6898070..e9b82c209c2d 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -103,45 +103,6 @@ static const struct e1000_reg_info e1000_reg_info_tbl[] = {
 	{0, NULL}
 };
 
-struct e1000e_me_supported {
-	u16 device_id;		/* supported device ID */
-};
-
-static const struct e1000e_me_supported me_supported[] = {
-	{E1000_DEV_ID_PCH_LPT_I217_LM},
-	{E1000_DEV_ID_PCH_LPTLP_I218_LM},
-	{E1000_DEV_ID_PCH_I218_LM2},
-	{E1000_DEV_ID_PCH_I218_LM3},
-	{E1000_DEV_ID_PCH_SPT_I219_LM},
-	{E1000_DEV_ID_PCH_SPT_I219_LM2},
-	{E1000_DEV_ID_PCH_LBG_I219_LM3},
-	{E1000_DEV_ID_PCH_SPT_I219_LM4},
-	{E1000_DEV_ID_PCH_SPT_I219_LM5},
-	{E1000_DEV_ID_PCH_CNP_I219_LM6},
-	{E1000_DEV_ID_PCH_CNP_I219_LM7},
-	{E1000_DEV_ID_PCH_ICP_I219_LM8},
-	{E1000_DEV_ID_PCH_ICP_I219_LM9},
-	{E1000_DEV_ID_PCH_CMP_I219_LM10},
-	{E1000_DEV_ID_PCH_CMP_I219_LM11},
-	{E1000_DEV_ID_PCH_CMP_I219_LM12},
-	{E1000_DEV_ID_PCH_TGP_I219_LM13},
-	{E1000_DEV_ID_PCH_TGP_I219_LM14},
-	{E1000_DEV_ID_PCH_TGP_I219_LM15},
-	{0}
-};
-
-static bool e1000e_check_me(u16 device_id)
-{
-	struct e1000e_me_supported *id;
-
-	for (id = (struct e1000e_me_supported *)me_supported;
-	     id->device_id; id++)
-		if (device_id == id->device_id)
-			return true;
-
-	return false;
-}
-
 /**
  * __ew32_prepare - prepare to write to MAC CSR register on certain parts
  * @hw: pointer to the HW structure
@@ -6962,7 +6923,6 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev)
 	struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct e1000_hw *hw = &adapter->hw;
 	int rc;
 
 	e1000e_flush_lpic(pdev);
@@ -6970,13 +6930,13 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev)
 	e1000e_pm_freeze(dev);
 
 	rc = __e1000_shutdown(pdev, false);
-	if (rc)
+	if (rc) {
 		e1000e_pm_thaw(dev);
-
-	/* Introduce S0ix implementation */
-	if (hw->mac.type >= e1000_pch_cnp &&
-	    !e1000e_check_me(hw->adapter->pdev->device))
-		e1000e_s0ix_entry_flow(adapter);
+	} else {
+		/* Introduce S0ix implementation */
+		if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS)
+			e1000e_s0ix_entry_flow(adapter);
+	}
 
 	return rc;
 }
@@ -6986,12 +6946,10 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev)
 	struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct e1000_hw *hw = &adapter->hw;
 	int rc;
 
 	/* Introduce S0ix implementation */
-	if (hw->mac.type >= e1000_pch_cnp &&
-	    !e1000e_check_me(hw->adapter->pdev->device))
+	if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS)
 		e1000e_s0ix_exit_flow(adapter);
 
 	rc = __e1000_resume(pdev);
@@ -7655,6 +7613,9 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!(adapter->flags & FLAG_HAS_AMT))
 		e1000e_get_hw_control(adapter);
 
+	if (hw->mac.type >= e1000_pch_cnp)
+		adapter->flags2 |= FLAG2_ENABLE_S0IX_FLOWS;
+
 	strlcpy(netdev->name, "eth%d", sizeof(netdev->name));
 	err = register_netdev(netdev);
 	if (err)
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index d231a2cdd98f..118473dfdcbd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -120,6 +120,7 @@ enum i40e_state_t {
 	__I40E_RESET_INTR_RECEIVED,
 	__I40E_REINIT_REQUESTED,
 	__I40E_PF_RESET_REQUESTED,
+	__I40E_PF_RESET_AND_REBUILD_REQUESTED,
 	__I40E_CORE_RESET_REQUESTED,
 	__I40E_GLOBAL_RESET_REQUESTED,
 	__I40E_EMP_RESET_INTR_RECEIVED,
@@ -146,6 +147,8 @@ enum i40e_state_t {
 };
 
 #define I40E_PF_RESET_FLAG	BIT_ULL(__I40E_PF_RESET_REQUESTED)
+#define I40E_PF_RESET_AND_REBUILD_FLAG	\
+	BIT_ULL(__I40E_PF_RESET_AND_REBUILD_REQUESTED)
 
 /* VSI state flags */
 enum i40e_vsi_state_t {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 1337686bd099..1db482d310c2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -36,6 +36,8 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf);
 static void i40e_determine_queue_usage(struct i40e_pf *pf);
 static int i40e_setup_pf_filter_control(struct i40e_pf *pf);
 static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired);
+static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit,
+				   bool lock_acquired);
 static int i40e_reset(struct i40e_pf *pf);
 static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired);
 static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf);
@@ -8536,6 +8538,14 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired)
 			 "FW LLDP is disabled\n" :
 			 "FW LLDP is enabled\n");
 
+	} else if (reset_flags & I40E_PF_RESET_AND_REBUILD_FLAG) {
+		/* Request a PF Reset
+		 *
+		 * Resets PF and reinitializes PFs VSI.
+		 */
+		i40e_prep_for_reset(pf, lock_acquired);
+		i40e_reset_and_rebuild(pf, true, lock_acquired);
+
 	} else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) {
 		int v;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 729c4f0d5ac5..21ee56420c3a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1772,7 +1772,7 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	if (num_vfs) {
 		if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
 			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
-			i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
+			i40e_do_reset_safe(pf, I40E_PF_RESET_AND_REBUILD_FLAG);
 		}
 		ret = i40e_pci_sriov_enable(pdev, num_vfs);
 		goto sriov_configure_out;
@@ -1781,7 +1781,7 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	if (!pci_vfs_assigned(pf->pdev)) {
 		i40e_free_vfs(pf);
 		pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
-		i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
+		i40e_do_reset_safe(pf, I40E_PF_RESET_AND_REBUILD_FLAG);
 	} else {
 		dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n");
 		ret = -EINVAL;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 47eb9c584a12..492ce213208d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -348,12 +348,12 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		 * SBP is *not* set in PRT_SBPVSI (default not set).
 		 */
 		skb = i40e_construct_skb_zc(rx_ring, *bi);
-		*bi = NULL;
 		if (!skb) {
 			rx_ring->rx_stats.alloc_buff_failed++;
 			break;
 		}
 
+		*bi = NULL;
 		cleaned_count++;
 		i40e_inc_ntc(rx_ring);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 95543dfd4fe7..0a867d64d467 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1834,11 +1834,9 @@ static int iavf_init_get_resources(struct iavf_adapter *adapter)
 	netif_tx_stop_all_queues(netdev);
 	if (CLIENT_ALLOWED(adapter)) {
 		err = iavf_lan_add_device(adapter);
-		if (err) {
-			rtnl_unlock();
+		if (err)
 			dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n",
 				 err);
-		}
 	}
 	dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr);
 	if (netdev->features & NETIF_F_GRO)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 563ceac3060f..bc4d8d144401 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4432,7 +4432,7 @@ static int mvneta_xdp_setup(struct net_device *dev, struct bpf_prog *prog,
 	struct bpf_prog *old_prog;
 
 	if (prog && dev->mtu > MVNETA_MAX_RX_BUF_SIZE) {
-		NL_SET_ERR_MSG_MOD(extack, "Jumbo frames not supported on XDP");
+		NL_SET_ERR_MSG_MOD(extack, "MTU too large for XDP");
 		return -EOPNOTSUPP;
 	}
 
@@ -5255,7 +5255,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	err = mvneta_port_power_up(pp, pp->phy_interface);
 	if (err < 0) {
 		dev_err(&pdev->dev, "can't power up port\n");
-		return err;
+		goto err_netdev;
 	}
 
 	/* Armada3700 network controller does not support per-cpu
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index afdd22827223..358119d98358 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1231,7 +1231,7 @@ static void mvpp22_gop_init_rgmii(struct mvpp2_port *port)
 
 	regmap_read(priv->sysctrl_base, GENCONF_CTRL0, &val);
 	if (port->gop_id == 2)
-		val |= GENCONF_CTRL0_PORT0_RGMII | GENCONF_CTRL0_PORT1_RGMII;
+		val |= GENCONF_CTRL0_PORT0_RGMII;
 	else if (port->gop_id == 3)
 		val |= GENCONF_CTRL0_PORT1_RGMII_MII;
 	regmap_write(priv->sysctrl_base, GENCONF_CTRL0, val);
@@ -2370,17 +2370,18 @@ static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port,
 static void mvpp2_tx_pkts_coal_set(struct mvpp2_port *port,
 				   struct mvpp2_tx_queue *txq)
 {
-	unsigned int thread = mvpp2_cpu_to_thread(port->priv, get_cpu());
+	unsigned int thread;
 	u32 val;
 
 	if (txq->done_pkts_coal > MVPP2_TXQ_THRESH_MASK)
 		txq->done_pkts_coal = MVPP2_TXQ_THRESH_MASK;
 
 	val = (txq->done_pkts_coal << MVPP2_TXQ_THRESH_OFFSET);
-	mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_NUM_REG, txq->id);
-	mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_THRESH_REG, val);
-
-	put_cpu();
+	/* PKT-coalescing registers are per-queue + per-thread */
+	for (thread = 0; thread < MVPP2_MAX_THREADS; thread++) {
+		mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_NUM_REG, txq->id);
+		mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_THRESH_REG, val);
+	}
 }
 
 static u32 mvpp2_usec_to_cycles(u32 usec, unsigned long clk_hz)
@@ -5487,7 +5488,7 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	struct mvpp2 *priv = port->priv;
 	struct mvpp2_txq_pcpu *txq_pcpu;
 	unsigned int thread;
-	int queue, err;
+	int queue, err, val;
 
 	/* Checks for hardware constraints */
 	if (port->first_rxq + port->nrxqs >
@@ -5501,6 +5502,18 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	mvpp2_egress_disable(port);
 	mvpp2_port_disable(port);
 
+	if (mvpp2_is_xlg(port->phy_interface)) {
+		val = readl(port->base + MVPP22_XLG_CTRL0_REG);
+		val &= ~MVPP22_XLG_CTRL0_FORCE_LINK_PASS;
+		val |= MVPP22_XLG_CTRL0_FORCE_LINK_DOWN;
+		writel(val, port->base + MVPP22_XLG_CTRL0_REG);
+	} else {
+		val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+		val &= ~MVPP2_GMAC_FORCE_LINK_PASS;
+		val |= MVPP2_GMAC_FORCE_LINK_DOWN;
+		writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+	}
+
 	port->tx_time_coal = MVPP2_TXDONE_COAL_USEC;
 
 	port->txqs = devm_kcalloc(dev, port->ntxqs, sizeof(*port->txqs),
@@ -5869,8 +5882,6 @@ static void mvpp2_phylink_validate(struct phylink_config *config,
 
 	phylink_set(mask, Autoneg);
 	phylink_set_port_modes(mask);
-	phylink_set(mask, Pause);
-	phylink_set(mask, Asym_Pause);
 
 	switch (state->interface) {
 	case PHY_INTERFACE_MODE_10GBASER:
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 5692c6087bbb..a30eb90ba3d2 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -405,6 +405,38 @@ static int mvpp2_prs_tcam_first_free(struct mvpp2 *priv, unsigned char start,
 	return -EINVAL;
 }
 
+/* Drop flow control pause frames */
+static void mvpp2_prs_drop_fc(struct mvpp2 *priv)
+{
+	unsigned char da[ETH_ALEN] = { 0x01, 0x80, 0xC2, 0x00, 0x00, 0x01 };
+	struct mvpp2_prs_entry pe;
+	unsigned int len;
+
+	memset(&pe, 0, sizeof(pe));
+
+	/* For all ports - drop flow control frames */
+	pe.index = MVPP2_PE_FC_DROP;
+	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
+
+	/* Set match on DA */
+	len = ETH_ALEN;
+	while (len--)
+		mvpp2_prs_tcam_data_byte_set(&pe, len, da[len], 0xff);
+
+	mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_DROP_MASK,
+				 MVPP2_PRS_RI_DROP_MASK);
+
+	mvpp2_prs_sram_bits_set(&pe, MVPP2_PRS_SRAM_LU_GEN_BIT, 1);
+	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
+
+	/* Mask all ports */
+	mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
+
+	/* Update shadow table and hw entry */
+	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_MAC);
+	mvpp2_prs_hw_write(priv, &pe);
+}
+
 /* Enable/disable dropping all mac da's */
 static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add)
 {
@@ -1162,6 +1194,7 @@ static void mvpp2_prs_mac_init(struct mvpp2 *priv)
 	mvpp2_prs_hw_write(priv, &pe);
 
 	/* Create dummy entries for drop all and promiscuous modes */
+	mvpp2_prs_drop_fc(priv);
 	mvpp2_prs_mac_drop_all_set(priv, 0, false);
 	mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false);
 	mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false);
@@ -1647,8 +1680,9 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv)
 	mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_IP6);
 	mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP6,
 				 MVPP2_PRS_RI_L3_PROTO_MASK);
-	/* Skip eth_type + 4 bytes of IPv6 header */
-	mvpp2_prs_sram_shift_set(&pe, MVPP2_ETH_TYPE_LEN + 4,
+	/* Jump to DIP of IPV6 header */
+	mvpp2_prs_sram_shift_set(&pe, MVPP2_ETH_TYPE_LEN + 8 +
+				 MVPP2_MAX_L3_ADDR_SIZE,
 				 MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD);
 	/* Set L3 offset */
 	mvpp2_prs_sram_offset_set(&pe, MVPP2_PRS_SRAM_UDF_TYPE_L3,
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
index e22f6c85d380..4b68dd374733 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
@@ -129,7 +129,7 @@
 #define MVPP2_PE_VID_EDSA_FLTR_DEFAULT	(MVPP2_PRS_TCAM_SRAM_SIZE - 7)
 #define MVPP2_PE_VLAN_DBL		(MVPP2_PRS_TCAM_SRAM_SIZE - 6)
 #define MVPP2_PE_VLAN_NONE		(MVPP2_PRS_TCAM_SRAM_SIZE - 5)
-/* reserved */
+#define MVPP2_PE_FC_DROP		(MVPP2_PRS_TCAM_SRAM_SIZE - 4)
 #define MVPP2_PE_MAC_MC_PROMISCUOUS	(MVPP2_PRS_TCAM_SRAM_SIZE - 3)
 #define MVPP2_PE_MAC_UC_PROMISCUOUS	(MVPP2_PRS_TCAM_SRAM_SIZE - 2)
 #define MVPP2_PE_MAC_NON_PROMISCUOUS	(MVPP2_PRS_TCAM_SRAM_SIZE - 1)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 7d0f96290943..1a8f5a039d50 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -871,8 +871,10 @@ static int cgx_lmac_init(struct cgx *cgx)
 		if (!lmac)
 			return -ENOMEM;
 		lmac->name = kcalloc(1, sizeof("cgx_fwi_xxx_yyy"), GFP_KERNEL);
-		if (!lmac->name)
-			return -ENOMEM;
+		if (!lmac->name) {
+			err = -ENOMEM;
+			goto err_lmac_free;
+		}
 		sprintf(lmac->name, "cgx_fwi_%d_%d", cgx->cgx_id, i);
 		lmac->lmac_id = i;
 		lmac->cgx = cgx;
@@ -883,7 +885,7 @@ static int cgx_lmac_init(struct cgx *cgx)
 						 CGX_LMAC_FWI + i * 9),
 				   cgx_fwi_event_handler, 0, lmac->name, lmac);
 		if (err)
-			return err;
+			goto err_irq;
 
 		/* Enable interrupt */
 		cgx_write(cgx, lmac->lmac_id, CGXX_CMRX_INT_ENA_W1S,
@@ -895,6 +897,12 @@ static int cgx_lmac_init(struct cgx *cgx)
 	}
 
 	return cgx_lmac_verify_fwi_version(cgx);
+
+err_irq:
+	kfree(lmac->name);
+err_lmac_free:
+	kfree(lmac);
+	return err;
 }
 
 static int cgx_lmac_exit(struct cgx *cgx)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 74d466796b7c..d5fc72b1a36f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -90,7 +90,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 			int cq_idx)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
-	int err = 0;
+	int irq, err = 0;
 	int timestamp_en = 0;
 	bool assigned_eq = false;
 
@@ -116,10 +116,8 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 
 			assigned_eq = true;
 		}
-
-		cq->irq_desc =
-			irq_to_desc(mlx4_eq_get_irq(mdev->dev,
-						    cq->vector));
+		irq = mlx4_eq_get_irq(mdev->dev, cq->vector);
+		cq->aff_mask = irq_get_effective_affinity_mask(irq);
 	} else {
 		/* For TX we use the same irq per
 		ring we assigned for the RX    */
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 7954c1daf2b6..c1c9118a66c9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -958,18 +958,14 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 
 	/* If we used up all the quota - we're probably not done yet... */
 	if (done == budget || !clean_complete) {
-		const struct cpumask *aff;
-		struct irq_data *idata;
 		int cpu_curr;
 
 		/* in case we got here because of !clean_complete */
 		done = budget;
 
 		cpu_curr = smp_processor_id();
-		idata = irq_desc_get_irq_data(cq->irq_desc);
-		aff = irq_data_get_affinity_mask(idata);
 
-		if (likely(cpumask_test_cpu(cpu_curr, aff)))
+		if (likely(cpumask_test_cpu(cpu_curr, cq->aff_mask)))
 			return budget;
 
 		/* Current cpu is not according to smp_irq_affinity -
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 17f2b1919378..e8ed23190de0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -47,6 +47,7 @@
 #endif
 #include <linux/cpu_rmap.h>
 #include <linux/ptp_clock_kernel.h>
+#include <linux/irq.h>
 #include <net/xdp.h>
 
 #include <linux/mlx4/device.h>
@@ -365,7 +366,7 @@ struct mlx4_en_cq {
 	struct mlx4_cqe *buf;
 #define MLX4_EN_OPCODE_ERROR	0x1e
 
-	struct irq_desc *irq_desc;
+	const struct cpumask *aff_mask;
 };
 
 struct mlx4_en_port_profile {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index a1a81cfeb607..055baf3b6cb1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -684,7 +684,7 @@ struct mlx5e_channel {
 	spinlock_t                 async_icosq_lock;
 
 	/* data path - accessed per napi poll */
-	struct irq_desc *irq_desc;
+	const struct cpumask	  *aff_mask;
 	struct mlx5e_ch_stats     *stats;
 
 	/* control */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index 351118985a57..2a2bac30daaa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -479,7 +479,6 @@ int mlx5e_port_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
 	c->num_tc   = params->num_tc;
 	c->stats    = &priv->port_ptp_stats.ch;
-	c->irq_desc = irq_to_desc(irq);
 	c->lag_port = lag_port;
 
 	netif_napi_add(netdev, &c->napi, mlx5e_ptp_napi_poll, 64);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index 28aa5ae118f4..90c98ea63b7f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -28,7 +28,6 @@ struct mlx5e_port_ptp {
 	u8                         lag_port;
 
 	/* data path - accessed per napi poll */
-	struct irq_desc *irq_desc;
 	struct mlx5e_ch_stats     *stats;
 
 	/* control */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index d29af7b9c695..76177f7c5ec2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -626,6 +626,11 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 	if (!reg_c0)
 		return true;
 
+	/* If reg_c0 is not equal to the default flow tag then skb->mark
+	 * is not supported and must be reset back to 0.
+	 */
+	skb->mark = 0;
+
 	priv = netdev_priv(skb->dev);
 	esw = priv->mdev->priv.eswitch;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index e521254d886e..072363e73f1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -118,16 +118,17 @@ struct mlx5_ct_tuple {
 	u16 zone;
 };
 
-struct mlx5_ct_shared_counter {
+struct mlx5_ct_counter {
 	struct mlx5_fc *counter;
 	refcount_t refcount;
+	bool is_shared;
 };
 
 struct mlx5_ct_entry {
 	struct rhash_head node;
 	struct rhash_head tuple_node;
 	struct rhash_head tuple_nat_node;
-	struct mlx5_ct_shared_counter *shared_counter;
+	struct mlx5_ct_counter *counter;
 	unsigned long cookie;
 	unsigned long restore_cookie;
 	struct mlx5_ct_tuple tuple;
@@ -394,13 +395,14 @@ mlx5_tc_ct_set_tuple_match(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec,
 }
 
 static void
-mlx5_tc_ct_shared_counter_put(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_entry *entry)
+mlx5_tc_ct_counter_put(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_entry *entry)
 {
-	if (!refcount_dec_and_test(&entry->shared_counter->refcount))
+	if (entry->counter->is_shared &&
+	    !refcount_dec_and_test(&entry->counter->refcount))
 		return;
 
-	mlx5_fc_destroy(ct_priv->dev, entry->shared_counter->counter);
-	kfree(entry->shared_counter);
+	mlx5_fc_destroy(ct_priv->dev, entry->counter->counter);
+	kfree(entry->counter);
 }
 
 static void
@@ -699,7 +701,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 	attr->dest_ft = ct_priv->post_ct;
 	attr->ft = nat ? ct_priv->ct_nat : ct_priv->ct;
 	attr->outer_match_level = MLX5_MATCH_L4;
-	attr->counter = entry->shared_counter->counter;
+	attr->counter = entry->counter->counter;
 	attr->flags |= MLX5_ESW_ATTR_FLAG_NO_IN_PORT;
 
 	mlx5_tc_ct_set_tuple_match(netdev_priv(ct_priv->netdev), spec, flow_rule);
@@ -732,13 +734,34 @@ err_attr:
 	return err;
 }
 
-static struct mlx5_ct_shared_counter *
+static struct mlx5_ct_counter *
+mlx5_tc_ct_counter_create(struct mlx5_tc_ct_priv *ct_priv)
+{
+	struct mlx5_ct_counter *counter;
+	int ret;
+
+	counter = kzalloc(sizeof(*counter), GFP_KERNEL);
+	if (!counter)
+		return ERR_PTR(-ENOMEM);
+
+	counter->is_shared = false;
+	counter->counter = mlx5_fc_create(ct_priv->dev, true);
+	if (IS_ERR(counter->counter)) {
+		ct_dbg("Failed to create counter for ct entry");
+		ret = PTR_ERR(counter->counter);
+		kfree(counter);
+		return ERR_PTR(ret);
+	}
+
+	return counter;
+}
+
+static struct mlx5_ct_counter *
 mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv,
 			      struct mlx5_ct_entry *entry)
 {
 	struct mlx5_ct_tuple rev_tuple = entry->tuple;
-	struct mlx5_ct_shared_counter *shared_counter;
-	struct mlx5_core_dev *dev = ct_priv->dev;
+	struct mlx5_ct_counter *shared_counter;
 	struct mlx5_ct_entry *rev_entry;
 	__be16 tmp_port;
 	int ret;
@@ -767,25 +790,20 @@ mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv,
 	rev_entry = rhashtable_lookup_fast(&ct_priv->ct_tuples_ht, &rev_tuple,
 					   tuples_ht_params);
 	if (rev_entry) {
-		if (refcount_inc_not_zero(&rev_entry->shared_counter->refcount)) {
+		if (refcount_inc_not_zero(&rev_entry->counter->refcount)) {
 			mutex_unlock(&ct_priv->shared_counter_lock);
-			return rev_entry->shared_counter;
+			return rev_entry->counter;
 		}
 	}
 	mutex_unlock(&ct_priv->shared_counter_lock);
 
-	shared_counter = kzalloc(sizeof(*shared_counter), GFP_KERNEL);
-	if (!shared_counter)
-		return ERR_PTR(-ENOMEM);
-
-	shared_counter->counter = mlx5_fc_create(dev, true);
-	if (IS_ERR(shared_counter->counter)) {
-		ct_dbg("Failed to create counter for ct entry");
-		ret = PTR_ERR(shared_counter->counter);
-		kfree(shared_counter);
+	shared_counter = mlx5_tc_ct_counter_create(ct_priv);
+	if (IS_ERR(shared_counter)) {
+		ret = PTR_ERR(shared_counter);
 		return ERR_PTR(ret);
 	}
 
+	shared_counter->is_shared = true;
 	refcount_set(&shared_counter->refcount, 1);
 	return shared_counter;
 }
@@ -798,10 +816,13 @@ mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv,
 {
 	int err;
 
-	entry->shared_counter = mlx5_tc_ct_shared_counter_get(ct_priv, entry);
-	if (IS_ERR(entry->shared_counter)) {
-		err = PTR_ERR(entry->shared_counter);
-		ct_dbg("Failed to create counter for ct entry");
+	if (nf_ct_acct_enabled(dev_net(ct_priv->netdev)))
+		entry->counter = mlx5_tc_ct_counter_create(ct_priv);
+	else
+		entry->counter = mlx5_tc_ct_shared_counter_get(ct_priv, entry);
+
+	if (IS_ERR(entry->counter)) {
+		err = PTR_ERR(entry->counter);
 		return err;
 	}
 
@@ -820,7 +841,7 @@ mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv,
 err_nat:
 	mlx5_tc_ct_entry_del_rule(ct_priv, entry, false);
 err_orig:
-	mlx5_tc_ct_shared_counter_put(ct_priv, entry);
+	mlx5_tc_ct_counter_put(ct_priv, entry);
 	return err;
 }
 
@@ -918,7 +939,7 @@ mlx5_tc_ct_del_ft_entry(struct mlx5_tc_ct_priv *ct_priv,
 	rhashtable_remove_fast(&ct_priv->ct_tuples_ht, &entry->tuple_node,
 			       tuples_ht_params);
 	mutex_unlock(&ct_priv->shared_counter_lock);
-	mlx5_tc_ct_shared_counter_put(ct_priv, entry);
+	mlx5_tc_ct_counter_put(ct_priv, entry);
 
 }
 
@@ -956,7 +977,7 @@ mlx5_tc_ct_block_flow_offload_stats(struct mlx5_ct_ft *ft,
 	if (!entry)
 		return -ENOENT;
 
-	mlx5_fc_query_cached(entry->shared_counter->counter, &bytes, &packets, &lastuse);
+	mlx5_fc_query_cached(entry->counter->counter, &bytes, &packets, &lastuse);
 	flow_stats_update(&f->stats, bytes, packets, 0, lastuse,
 			  FLOW_ACTION_HW_STATS_DELAYED);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 7943eb30b837..4880f2179273 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -371,6 +371,15 @@ struct mlx5e_swp_spec {
 	u8 tun_l4_proto;
 };
 
+static inline void mlx5e_eseg_swp_offsets_add_vlan(struct mlx5_wqe_eth_seg *eseg)
+{
+	/* SWP offsets are in 2-bytes words */
+	eseg->swp_outer_l3_offset += VLAN_HLEN / 2;
+	eseg->swp_outer_l4_offset += VLAN_HLEN / 2;
+	eseg->swp_inner_l3_offset += VLAN_HLEN / 2;
+	eseg->swp_inner_l4_offset += VLAN_HLEN / 2;
+}
+
 static inline void
 mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg,
 		   struct mlx5e_swp_spec *swp_spec)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index 899b98aca0d3..1fae7fab8297 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -51,7 +51,7 @@ static inline bool mlx5_geneve_tx_allowed(struct mlx5_core_dev *mdev)
 }
 
 static inline void
-mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
+mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
 	struct mlx5e_swp_spec swp_spec = {};
 	unsigned int offset = 0;
@@ -85,6 +85,8 @@ mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
 	}
 
 	mlx5e_set_eseg_swp(skb, eseg, &swp_spec);
+	if (skb_vlan_tag_present(skb) &&  ihs)
+		mlx5e_eseg_swp_offsets_add_vlan(eseg);
 }
 
 #else
@@ -163,7 +165,7 @@ static inline unsigned int mlx5e_accel_tx_ids_len(struct mlx5e_txqsq *sq,
 
 static inline bool mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
 				       struct sk_buff *skb,
-				       struct mlx5_wqe_eth_seg *eseg)
+				       struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (xfrm_offload(skb))
@@ -172,7 +174,7 @@ static inline bool mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
 
 #if IS_ENABLED(CONFIG_GENEVE)
 	if (skb->encapsulation)
-		mlx5e_tx_tunnel_accel(skb, eseg);
+		mlx5e_tx_tunnel_accel(skb, eseg, ihs);
 #endif
 
 	return true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index d9076d543104..2d37742a888c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1010,6 +1010,22 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 	return mlx5e_ethtool_get_link_ksettings(priv, link_ksettings);
 }
 
+static int mlx5e_speed_validate(struct net_device *netdev, bool ext,
+				const unsigned long link_modes, u8 autoneg)
+{
+	/* Extended link-mode has no speed limitations. */
+	if (ext)
+		return 0;
+
+	if ((link_modes & MLX5E_PROT_MASK(MLX5E_56GBASE_R4)) &&
+	    autoneg != AUTONEG_ENABLE) {
+		netdev_err(netdev, "%s: 56G link speed requires autoneg enabled\n",
+			   __func__);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 {
 	u32 i, ptys_modes = 0;
@@ -1103,13 +1119,9 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) :
 		mlx5e_port_speed2linkmodes(mdev, speed, !ext);
 
-	if ((link_modes & MLX5E_PROT_MASK(MLX5E_56GBASE_R4)) &&
-	    autoneg != AUTONEG_ENABLE) {
-		netdev_err(priv->netdev, "%s: 56G link speed requires autoneg enabled\n",
-			   __func__);
-		err = -EINVAL;
+	err = mlx5e_speed_validate(priv->netdev, ext, link_modes, autoneg);
+	if (err)
 		goto out;
-	}
 
 	link_modes = link_modes & eproto.cap;
 	if (!link_modes) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index fa8149f6eb08..e02e5895703d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -942,6 +942,7 @@ static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc,
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		kfree(ft->g);
+		ft->g = NULL;
 		return -ENOMEM;
 	}
 
@@ -1087,6 +1088,7 @@ static int mlx5e_create_inner_ttc_table_groups(struct mlx5e_ttc_table *ttc)
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		kfree(ft->g);
+		ft->g = NULL;
 		return -ENOMEM;
 	}
 
@@ -1390,6 +1392,7 @@ err_destroy_groups:
 	ft->g[ft->num_groups] = NULL;
 	mlx5e_destroy_groups(ft);
 	kvfree(in);
+	kfree(ft->g);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 03831650f655..6a852b4901aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1987,7 +1987,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->num_tc   = params->num_tc;
 	c->xdp      = !!params->xdp_prog;
 	c->stats    = &priv->channel_stats[ix].ch;
-	c->irq_desc = irq_to_desc(irq);
+	c->aff_mask = irq_get_effective_affinity_mask(irq);
 	c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix);
 
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
@@ -3161,7 +3161,8 @@ static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev,
 
 	mlx5_set_port_admin_status(mdev, state);
 
-	if (mlx5_eswitch_mode(mdev) != MLX5_ESWITCH_LEGACY)
+	if (mlx5_eswitch_mode(mdev) == MLX5_ESWITCH_OFFLOADS ||
+	    !MLX5_CAP_GEN(mdev, uplink_follow))
 		return;
 
 	if (state == MLX5_PORT_UP)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index e47e2a0059d0..61ed671fe741 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -682,9 +682,9 @@ void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq)
 
 static bool mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq,
 				   struct sk_buff *skb, struct mlx5e_accel_tx_state *accel,
-				   struct mlx5_wqe_eth_seg *eseg)
+				   struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
-	if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg)))
+	if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg, ihs)))
 		return false;
 
 	mlx5e_txwqe_build_eseg_csum(sq, skb, accel, eseg);
@@ -714,7 +714,8 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 		if (mlx5e_tx_skb_supports_mpwqe(skb, &attr)) {
 			struct mlx5_wqe_eth_seg eseg = {};
 
-			if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg)))
+			if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg,
+							     attr.ihs)))
 				return NETDEV_TX_OK;
 
 			mlx5e_sq_xmit_mpwqe(sq, skb, &eseg, netdev_xmit_more());
@@ -731,7 +732,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* May update the WQE, but may not post other WQEs. */
 	mlx5e_accel_tx_finish(sq, wqe, &accel,
 			      (struct mlx5_wqe_inline_seg *)(wqe->data + wqe_attr.ds_cnt_inl));
-	if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth)))
+	if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth, attr.ihs)))
 		return NETDEV_TX_OK;
 
 	mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, netdev_xmit_more());
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 1ec3d62f026d..a3cfe06d5116 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -40,12 +40,8 @@
 static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
 {
 	int current_cpu = smp_processor_id();
-	const struct cpumask *aff;
-	struct irq_data *idata;
 
-	idata = irq_desc_get_irq_data(c->irq_desc);
-	aff = irq_data_get_affinity_mask(idata);
-	return cpumask_test_cpu(current_cpu, aff);
+	return cpumask_test_cpu(current_cpu, c->aff_mask);
 }
 
 static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
index 2b85d4777303..3e19b1721303 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
@@ -95,22 +95,21 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
 		return 0;
 	}
 
-	if (!IS_ERR_OR_NULL(vport->egress.acl))
-		return 0;
-
-	vport->egress.acl = esw_acl_table_create(esw, vport->vport,
-						 MLX5_FLOW_NAMESPACE_ESW_EGRESS,
-						 table_size);
-	if (IS_ERR(vport->egress.acl)) {
-		err = PTR_ERR(vport->egress.acl);
-		vport->egress.acl = NULL;
-		goto out;
+	if (!vport->egress.acl) {
+		vport->egress.acl = esw_acl_table_create(esw, vport->vport,
+							 MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+							 table_size);
+		if (IS_ERR(vport->egress.acl)) {
+			err = PTR_ERR(vport->egress.acl);
+			vport->egress.acl = NULL;
+			goto out;
+		}
+
+		err = esw_acl_egress_lgcy_groups_create(esw, vport);
+		if (err)
+			goto out;
 	}
 
-	err = esw_acl_egress_lgcy_groups_create(esw, vport);
-	if (err)
-		goto out;
-
 	esw_debug(esw->dev,
 		  "vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
 		  vport->vport, vport->info.vlan, vport->info.qos);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index f3d45ef082cd..83a05371e2aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -564,7 +564,9 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
 	struct mlx5_core_dev *tmp_dev;
 	int i, err;
 
-	if (!MLX5_CAP_GEN(dev, vport_group_manager))
+	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
+	    !MLX5_CAP_GEN(dev, lag_master) ||
+	    MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_MAX_PORTS)
 		return;
 
 	tmp_dev = mlx5_get_next_phys_dev(dev);
@@ -582,12 +584,9 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
 	if (mlx5_lag_dev_add_pf(ldev, dev, netdev) < 0)
 		return;
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++) {
-		tmp_dev = ldev->pf[i].dev;
-		if (!tmp_dev || !MLX5_CAP_GEN(tmp_dev, lag_master) ||
-		    MLX5_CAP_GEN(tmp_dev, num_lag_ports) != MLX5_MAX_PORTS)
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (!ldev->pf[i].dev)
 			break;
-	}
 
 	if (i >= MLX5_MAX_PORTS)
 		ldev->flags |= MLX5_LAG_FLAG_READY;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c08315b51fd3..ca6f2fc39ea0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1368,8 +1368,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 			 MLX5_COREDEV_VF : MLX5_COREDEV_PF;
 
 	dev->priv.adev_idx = mlx5_adev_idx_alloc();
-	if (dev->priv.adev_idx < 0)
-		return dev->priv.adev_idx;
+	if (dev->priv.adev_idx < 0) {
+		err = dev->priv.adev_idx;
+		goto adev_init_err;
+	}
 
 	err = mlx5_mdev_init(dev, prof_sel);
 	if (err)
@@ -1403,6 +1405,7 @@ pci_init_err:
 	mlx5_mdev_uninit(dev);
 mdev_init_err:
 	mlx5_adev_idx_free(dev->priv.adev_idx);
+adev_init_err:
 	mlx5_devlink_free(devlink);
 
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index 0fc7de4aa572..8e0dddc6383f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -116,7 +116,7 @@ free:
 static void mlx5_rdma_del_roce_addr(struct mlx5_core_dev *dev)
 {
 	mlx5_core_roce_gid_set(dev, 0, 0, 0,
-			       NULL, NULL, false, 0, 0);
+			       NULL, NULL, false, 0, 1);
 }
 
 static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *gid)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 8fa286ccdd6b..bf85ce9835d7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -19,7 +19,7 @@
 #define MLXSW_THERMAL_ASIC_TEMP_NORM	75000	/* 75C */
 #define MLXSW_THERMAL_ASIC_TEMP_HIGH	85000	/* 85C */
 #define MLXSW_THERMAL_ASIC_TEMP_HOT	105000	/* 105C */
-#define MLXSW_THERMAL_ASIC_TEMP_CRIT	110000	/* 110C */
+#define MLXSW_THERMAL_ASIC_TEMP_CRIT	140000	/* 140C */
 #define MLXSW_THERMAL_HYSTERESIS_TEMP	5000	/* 5C */
 #define MLXSW_THERMAL_MODULE_TEMP_SHIFT	(MLXSW_THERMAL_HYSTERESIS_TEMP * 2)
 #define MLXSW_THERMAL_ZONE_MAX_NAME	16
@@ -176,6 +176,12 @@ mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core,
 	if (err)
 		return err;
 
+	if (crit_temp > emerg_temp) {
+		dev_warn(dev, "%s : Critical threshold %d is above emergency threshold %d\n",
+			 tz->tzdev->type, crit_temp, emerg_temp);
+		return 0;
+	}
+
 	/* According to the system thermal requirements, the thermal zones are
 	 * defined with four trip points. The critical and emergency
 	 * temperature thresholds, provided by QSFP module are set as "active"
@@ -190,11 +196,8 @@ mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core,
 		tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp;
 	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = crit_temp;
 	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = emerg_temp;
-	if (emerg_temp > crit_temp)
-		tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp +
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp +
 					MLXSW_THERMAL_MODULE_TEMP_SHIFT;
-	else
-		tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c
index 776b7d264dc3..2289e1fe3741 100644
--- a/drivers/net/ethernet/natsemi/macsonic.c
+++ b/drivers/net/ethernet/natsemi/macsonic.c
@@ -506,10 +506,14 @@ static int mac_sonic_platform_probe(struct platform_device *pdev)
 
 	err = register_netdev(dev);
 	if (err)
-		goto out;
+		goto undo_probe;
 
 	return 0;
 
+undo_probe:
+	dma_free_coherent(lp->device,
+			  SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+			  lp->descriptors, lp->descriptors_laddr);
 out:
 	free_netdev(dev);
 
@@ -584,12 +588,16 @@ static int mac_sonic_nubus_probe(struct nubus_board *board)
 
 	err = register_netdev(ndev);
 	if (err)
-		goto out;
+		goto undo_probe;
 
 	nubus_set_drvdata(board, ndev);
 
 	return 0;
 
+undo_probe:
+	dma_free_coherent(lp->device,
+			  SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+			  lp->descriptors, lp->descriptors_laddr);
 out:
 	free_netdev(ndev);
 	return err;
diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c
index afa166ff7aef..28d9e98db81a 100644
--- a/drivers/net/ethernet/natsemi/xtsonic.c
+++ b/drivers/net/ethernet/natsemi/xtsonic.c
@@ -229,11 +229,14 @@ int xtsonic_probe(struct platform_device *pdev)
 	sonic_msg_init(dev);
 
 	if ((err = register_netdev(dev)))
-		goto out1;
+		goto undo_probe1;
 
 	return 0;
 
-out1:
+undo_probe1:
+	dma_free_coherent(lp->device,
+			  SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+			  lp->descriptors, lp->descriptors_laddr);
 	release_region(dev->base_addr, SONIC_MEM_SIZE);
 out:
 	free_netdev(dev);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 9156c9825a16..ac4cd5d82e69 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -337,7 +337,7 @@ void ionic_rx_fill(struct ionic_queue *q)
 	unsigned int i, j;
 	unsigned int len;
 
-	len = netdev->mtu + ETH_HLEN;
+	len = netdev->mtu + ETH_HLEN + VLAN_HLEN;
 	nfrags = round_up(len, PAGE_SIZE) / PAGE_SIZE;
 
 	for (i = ionic_q_space_avail(q); i; i--) {
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index 4366c7a8de95..6b5ddb07ee83 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -78,6 +78,7 @@ config QED
 	depends on PCI
 	select ZLIB_INFLATE
 	select CRC8
+	select CRC32
 	select NET_DEVLINK
 	help
 	  This enables the support for Marvell FastLinQ adapters family.
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index f21847739ef1..d258e0ccf946 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -564,11 +564,6 @@ static const struct net_device_ops netxen_netdev_ops = {
 	.ndo_set_features = netxen_set_features,
 };
 
-static inline bool netxen_function_zero(struct pci_dev *pdev)
-{
-	return (PCI_FUNC(pdev->devfn) == 0) ? true : false;
-}
-
 static inline void netxen_set_interrupt_mode(struct netxen_adapter *adapter,
 					     u32 mode)
 {
@@ -664,7 +659,7 @@ static int netxen_setup_intr(struct netxen_adapter *adapter)
 	netxen_initialize_interrupt_registers(adapter);
 	netxen_set_msix_bit(pdev, 0);
 
-	if (netxen_function_zero(pdev)) {
+	if (adapter->portnum == 0) {
 		if (!netxen_setup_msi_interrupts(adapter, num_msix))
 			netxen_set_interrupt_mode(adapter, NETXEN_MSI_MODE);
 		else
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index a2494bf85007..ca0ee29a57b5 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1799,6 +1799,11 @@ netdev_features_t qede_features_check(struct sk_buff *skb,
 			      ntohs(udp_hdr(skb)->dest) != gnv_port))
 				return features & ~(NETIF_F_CSUM_MASK |
 						    NETIF_F_GSO_MASK);
+		} else if (l4_proto == IPPROTO_IPIP) {
+			/* IPIP tunnels are unknown to the device or at least unsupported natively,
+			 * offloads for them can't be done trivially, so disable them for such skb.
+			 */
+			return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
 		}
 	}
 
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 46d8510b2fe2..a569abe7f5ef 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2207,7 +2207,8 @@ static void rtl_pll_power_down(struct rtl8169_private *tp)
 	}
 
 	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
+	case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_26:
+	case RTL_GIGA_MAC_VER_32 ... RTL_GIGA_MAC_VER_33:
 	case RTL_GIGA_MAC_VER_37:
 	case RTL_GIGA_MAC_VER_39:
 	case RTL_GIGA_MAC_VER_43:
@@ -2233,7 +2234,8 @@ static void rtl_pll_power_down(struct rtl8169_private *tp)
 static void rtl_pll_power_up(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
+	case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_26:
+	case RTL_GIGA_MAC_VER_32 ... RTL_GIGA_MAC_VER_33:
 	case RTL_GIGA_MAC_VER_37:
 	case RTL_GIGA_MAC_VER_39:
 	case RTL_GIGA_MAC_VER_43:
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index a2e80c89de2d..9a6a519426a0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -721,6 +721,8 @@ static SIMPLE_DEV_PM_OPS(intel_eth_pm_ops, intel_eth_pci_suspend,
 #define PCI_DEVICE_ID_INTEL_EHL_PSE1_RGMII1G_ID		0x4bb0
 #define PCI_DEVICE_ID_INTEL_EHL_PSE1_SGMII1G_ID		0x4bb1
 #define PCI_DEVICE_ID_INTEL_EHL_PSE1_SGMII2G5_ID	0x4bb2
+#define PCI_DEVICE_ID_INTEL_TGLH_SGMII1G_0_ID		0x43ac
+#define PCI_DEVICE_ID_INTEL_TGLH_SGMII1G_1_ID		0x43a2
 #define PCI_DEVICE_ID_INTEL_TGL_SGMII1G_ID		0xa0ac
 
 static const struct pci_device_id intel_eth_pci_id_table[] = {
@@ -735,6 +737,8 @@ static const struct pci_device_id intel_eth_pci_id_table[] = {
 	{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII1G_ID, &ehl_pse1_sgmii1g_info) },
 	{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII2G5_ID, &ehl_pse1_sgmii1g_info) },
 	{ PCI_DEVICE_DATA(INTEL, TGL_SGMII1G_ID, &tgl_sgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_0_ID, &tgl_sgmii1g_info) },
+	{ PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_1_ID, &tgl_sgmii1g_info) },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, intel_eth_pci_id_table);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 459ae715b33d..f184b00f5116 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -135,7 +135,7 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac)
 	struct device *dev = dwmac->dev;
 	static const struct clk_parent_data mux_parents[] = {
 		{ .fw_name = "clkin0", },
-		{ .fw_name = "clkin1", },
+		{ .index = -1, },
 	};
 	static const struct clk_div_table div_table[] = {
 		{ .div = 2, .val = 2, },
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 58e0511badba..a5e0eff4a387 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -64,6 +64,7 @@ struct emac_variant {
  * @variant:	reference to the current board variant
  * @regmap:	regmap for using the syscon
  * @internal_phy_powered: Does the internal PHY is enabled
+ * @use_internal_phy: Is the internal PHY selected for use
  * @mux_handle:	Internal pointer used by mdio-mux lib
  */
 struct sunxi_priv_data {
@@ -74,6 +75,7 @@ struct sunxi_priv_data {
 	const struct emac_variant *variant;
 	struct regmap_field *regmap_field;
 	bool internal_phy_powered;
+	bool use_internal_phy;
 	void *mux_handle;
 };
 
@@ -539,8 +541,11 @@ static const struct stmmac_dma_ops sun8i_dwmac_dma_ops = {
 	.dma_interrupt = sun8i_dwmac_dma_interrupt,
 };
 
+static int sun8i_dwmac_power_internal_phy(struct stmmac_priv *priv);
+
 static int sun8i_dwmac_init(struct platform_device *pdev, void *priv)
 {
+	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct sunxi_priv_data *gmac = priv;
 	int ret;
 
@@ -554,13 +559,25 @@ static int sun8i_dwmac_init(struct platform_device *pdev, void *priv)
 
 	ret = clk_prepare_enable(gmac->tx_clk);
 	if (ret) {
-		if (gmac->regulator)
-			regulator_disable(gmac->regulator);
 		dev_err(&pdev->dev, "Could not enable AHB clock\n");
-		return ret;
+		goto err_disable_regulator;
+	}
+
+	if (gmac->use_internal_phy) {
+		ret = sun8i_dwmac_power_internal_phy(netdev_priv(ndev));
+		if (ret)
+			goto err_disable_clk;
 	}
 
 	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(gmac->tx_clk);
+err_disable_regulator:
+	if (gmac->regulator)
+		regulator_disable(gmac->regulator);
+
+	return ret;
 }
 
 static void sun8i_dwmac_core_init(struct mac_device_info *hw,
@@ -831,7 +848,6 @@ static int mdio_mux_syscon_switch_fn(int current_child, int desired_child,
 	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
 	u32 reg, val;
 	int ret = 0;
-	bool need_power_ephy = false;
 
 	if (current_child ^ desired_child) {
 		regmap_field_read(gmac->regmap_field, &reg);
@@ -839,13 +855,12 @@ static int mdio_mux_syscon_switch_fn(int current_child, int desired_child,
 		case DWMAC_SUN8I_MDIO_MUX_INTERNAL_ID:
 			dev_info(priv->device, "Switch mux to internal PHY");
 			val = (reg & ~H3_EPHY_MUX_MASK) | H3_EPHY_SELECT;
-
-			need_power_ephy = true;
+			gmac->use_internal_phy = true;
 			break;
 		case DWMAC_SUN8I_MDIO_MUX_EXTERNAL_ID:
 			dev_info(priv->device, "Switch mux to external PHY");
 			val = (reg & ~H3_EPHY_MUX_MASK) | H3_EPHY_SHUTDOWN;
-			need_power_ephy = false;
+			gmac->use_internal_phy = false;
 			break;
 		default:
 			dev_err(priv->device, "Invalid child ID %x\n",
@@ -853,7 +868,7 @@ static int mdio_mux_syscon_switch_fn(int current_child, int desired_child,
 			return -EINVAL;
 		}
 		regmap_field_write(gmac->regmap_field, val);
-		if (need_power_ephy) {
+		if (gmac->use_internal_phy) {
 			ret = sun8i_dwmac_power_internal_phy(priv);
 			if (ret)
 				return ret;
@@ -883,22 +898,23 @@ static int sun8i_dwmac_register_mdio_mux(struct stmmac_priv *priv)
 	return ret;
 }
 
-static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
+static int sun8i_dwmac_set_syscon(struct device *dev,
+				  struct plat_stmmacenet_data *plat)
 {
-	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
-	struct device_node *node = priv->device->of_node;
+	struct sunxi_priv_data *gmac = plat->bsp_priv;
+	struct device_node *node = dev->of_node;
 	int ret;
 	u32 reg, val;
 
 	ret = regmap_field_read(gmac->regmap_field, &val);
 	if (ret) {
-		dev_err(priv->device, "Fail to read from regmap field.\n");
+		dev_err(dev, "Fail to read from regmap field.\n");
 		return ret;
 	}
 
 	reg = gmac->variant->default_syscon_value;
 	if (reg != val)
-		dev_warn(priv->device,
+		dev_warn(dev,
 			 "Current syscon value is not the default %x (expect %x)\n",
 			 val, reg);
 
@@ -911,9 +927,9 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 		/* Force EPHY xtal frequency to 24MHz. */
 		reg |= H3_EPHY_CLK_SEL;
 
-		ret = of_mdio_parse_addr(priv->device, priv->plat->phy_node);
+		ret = of_mdio_parse_addr(dev, plat->phy_node);
 		if (ret < 0) {
-			dev_err(priv->device, "Could not parse MDIO addr\n");
+			dev_err(dev, "Could not parse MDIO addr\n");
 			return ret;
 		}
 		/* of_mdio_parse_addr returns a valid (0 ~ 31) PHY
@@ -929,17 +945,17 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 
 	if (!of_property_read_u32(node, "allwinner,tx-delay-ps", &val)) {
 		if (val % 100) {
-			dev_err(priv->device, "tx-delay must be a multiple of 100\n");
+			dev_err(dev, "tx-delay must be a multiple of 100\n");
 			return -EINVAL;
 		}
 		val /= 100;
-		dev_dbg(priv->device, "set tx-delay to %x\n", val);
+		dev_dbg(dev, "set tx-delay to %x\n", val);
 		if (val <= gmac->variant->tx_delay_max) {
 			reg &= ~(gmac->variant->tx_delay_max <<
 				 SYSCON_ETXDC_SHIFT);
 			reg |= (val << SYSCON_ETXDC_SHIFT);
 		} else {
-			dev_err(priv->device, "Invalid TX clock delay: %d\n",
+			dev_err(dev, "Invalid TX clock delay: %d\n",
 				val);
 			return -EINVAL;
 		}
@@ -947,17 +963,17 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 
 	if (!of_property_read_u32(node, "allwinner,rx-delay-ps", &val)) {
 		if (val % 100) {
-			dev_err(priv->device, "rx-delay must be a multiple of 100\n");
+			dev_err(dev, "rx-delay must be a multiple of 100\n");
 			return -EINVAL;
 		}
 		val /= 100;
-		dev_dbg(priv->device, "set rx-delay to %x\n", val);
+		dev_dbg(dev, "set rx-delay to %x\n", val);
 		if (val <= gmac->variant->rx_delay_max) {
 			reg &= ~(gmac->variant->rx_delay_max <<
 				 SYSCON_ERXDC_SHIFT);
 			reg |= (val << SYSCON_ERXDC_SHIFT);
 		} else {
-			dev_err(priv->device, "Invalid RX clock delay: %d\n",
+			dev_err(dev, "Invalid RX clock delay: %d\n",
 				val);
 			return -EINVAL;
 		}
@@ -968,7 +984,7 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 	if (gmac->variant->support_rmii)
 		reg &= ~SYSCON_RMII_EN;
 
-	switch (priv->plat->interface) {
+	switch (plat->interface) {
 	case PHY_INTERFACE_MODE_MII:
 		/* default */
 		break;
@@ -982,8 +998,8 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 		reg |= SYSCON_RMII_EN | SYSCON_ETCS_EXT_GMII;
 		break;
 	default:
-		dev_err(priv->device, "Unsupported interface mode: %s",
-			phy_modes(priv->plat->interface));
+		dev_err(dev, "Unsupported interface mode: %s",
+			phy_modes(plat->interface));
 		return -EINVAL;
 	}
 
@@ -1004,17 +1020,10 @@ static void sun8i_dwmac_exit(struct platform_device *pdev, void *priv)
 	struct sunxi_priv_data *gmac = priv;
 
 	if (gmac->variant->soc_has_internal_phy) {
-		/* sun8i_dwmac_exit could be called with mdiomux uninit */
-		if (gmac->mux_handle)
-			mdio_mux_uninit(gmac->mux_handle);
 		if (gmac->internal_phy_powered)
 			sun8i_dwmac_unpower_internal_phy(gmac);
 	}
 
-	sun8i_dwmac_unset_syscon(gmac);
-
-	reset_control_put(gmac->rst_ephy);
-
 	clk_disable_unprepare(gmac->tx_clk);
 
 	if (gmac->regulator)
@@ -1049,16 +1058,11 @@ static struct mac_device_info *sun8i_dwmac_setup(void *ppriv)
 {
 	struct mac_device_info *mac;
 	struct stmmac_priv *priv = ppriv;
-	int ret;
 
 	mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL);
 	if (!mac)
 		return NULL;
 
-	ret = sun8i_dwmac_set_syscon(priv);
-	if (ret)
-		return NULL;
-
 	mac->pcsr = priv->ioaddr;
 	mac->mac = &sun8i_dwmac_ops;
 	mac->dma = &sun8i_dwmac_dma_ops;
@@ -1134,10 +1138,6 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
-	if (IS_ERR(plat_dat))
-		return PTR_ERR(plat_dat);
-
 	gmac = devm_kzalloc(dev, sizeof(*gmac), GFP_KERNEL);
 	if (!gmac)
 		return -ENOMEM;
@@ -1201,11 +1201,15 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	ret = of_get_phy_mode(dev->of_node, &interface);
 	if (ret)
 		return -EINVAL;
-	plat_dat->interface = interface;
+
+	plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
+	if (IS_ERR(plat_dat))
+		return PTR_ERR(plat_dat);
 
 	/* platform data specifying hardware features and callbacks.
 	 * hardware features were copied from Allwinner drivers.
 	 */
+	plat_dat->interface = interface;
 	plat_dat->rx_coe = STMMAC_RX_COE_TYPE2;
 	plat_dat->tx_coe = 1;
 	plat_dat->has_sun8i = true;
@@ -1214,9 +1218,13 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	plat_dat->exit = sun8i_dwmac_exit;
 	plat_dat->setup = sun8i_dwmac_setup;
 
+	ret = sun8i_dwmac_set_syscon(&pdev->dev, plat_dat);
+	if (ret)
+		goto dwmac_deconfig;
+
 	ret = sun8i_dwmac_init(pdev, plat_dat->bsp_priv);
 	if (ret)
-		return ret;
+		goto dwmac_syscon;
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
@@ -1230,7 +1238,7 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	if (gmac->variant->soc_has_internal_phy) {
 		ret = get_ephy_nodes(priv);
 		if (ret)
-			goto dwmac_exit;
+			goto dwmac_remove;
 		ret = sun8i_dwmac_register_mdio_mux(priv);
 		if (ret) {
 			dev_err(&pdev->dev, "Failed to register mux\n");
@@ -1239,15 +1247,42 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	} else {
 		ret = sun8i_dwmac_reset(priv);
 		if (ret)
-			goto dwmac_exit;
+			goto dwmac_remove;
 	}
 
 	return ret;
 dwmac_mux:
-	sun8i_dwmac_unset_syscon(gmac);
+	reset_control_put(gmac->rst_ephy);
+	clk_put(gmac->ephy_clk);
+dwmac_remove:
+	stmmac_dvr_remove(&pdev->dev);
 dwmac_exit:
+	sun8i_dwmac_exit(pdev, gmac);
+dwmac_syscon:
+	sun8i_dwmac_unset_syscon(gmac);
+dwmac_deconfig:
+	stmmac_remove_config_dt(pdev, plat_dat);
+
+	return ret;
+}
+
+static int sun8i_dwmac_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
+
+	if (gmac->variant->soc_has_internal_phy) {
+		mdio_mux_uninit(gmac->mux_handle);
+		sun8i_dwmac_unpower_internal_phy(gmac);
+		reset_control_put(gmac->rst_ephy);
+		clk_put(gmac->ephy_clk);
+	}
+
 	stmmac_pltfr_remove(pdev);
-return ret;
+	sun8i_dwmac_unset_syscon(gmac);
+
+	return 0;
 }
 
 static const struct of_device_id sun8i_dwmac_match[] = {
@@ -1269,7 +1304,7 @@ MODULE_DEVICE_TABLE(of, sun8i_dwmac_match);
 
 static struct platform_driver sun8i_dwmac_driver = {
 	.probe  = sun8i_dwmac_probe,
-	.remove = stmmac_pltfr_remove,
+	.remove = sun8i_dwmac_remove,
 	.driver = {
 		.name           = "dwmac-sun8i",
 		.pm		= &stmmac_pltfr_pm_ops,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index 03e79a677c8b..8f7ac24545ef 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -568,68 +568,24 @@ static int dwmac5_est_write(void __iomem *ioaddr, u32 reg, u32 val, bool gcl)
 int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg,
 			 unsigned int ptp_rate)
 {
-	u32 speed, total_offset, offset, ctrl, ctr_low;
-	u32 extcfg = readl(ioaddr + GMAC_EXT_CONFIG);
-	u32 mac_cfg = readl(ioaddr + GMAC_CONFIG);
 	int i, ret = 0x0;
-	u64 total_ctr;
-
-	if (extcfg & GMAC_CONFIG_EIPG_EN) {
-		offset = (extcfg & GMAC_CONFIG_EIPG) >> GMAC_CONFIG_EIPG_SHIFT;
-		offset = 104 + (offset * 8);
-	} else {
-		offset = (mac_cfg & GMAC_CONFIG_IPG) >> GMAC_CONFIG_IPG_SHIFT;
-		offset = 96 - (offset * 8);
-	}
-
-	speed = mac_cfg & (GMAC_CONFIG_PS | GMAC_CONFIG_FES);
-	speed = speed >> GMAC_CONFIG_FES_SHIFT;
-
-	switch (speed) {
-	case 0x0:
-		offset = offset * 1000; /* 1G */
-		break;
-	case 0x1:
-		offset = offset * 400; /* 2.5G */
-		break;
-	case 0x2:
-		offset = offset * 100000; /* 10M */
-		break;
-	case 0x3:
-		offset = offset * 10000; /* 100M */
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	offset = offset / 1000;
+	u32 ctrl;
 
 	ret |= dwmac5_est_write(ioaddr, BTR_LOW, cfg->btr[0], false);
 	ret |= dwmac5_est_write(ioaddr, BTR_HIGH, cfg->btr[1], false);
 	ret |= dwmac5_est_write(ioaddr, TER, cfg->ter, false);
 	ret |= dwmac5_est_write(ioaddr, LLR, cfg->gcl_size, false);
+	ret |= dwmac5_est_write(ioaddr, CTR_LOW, cfg->ctr[0], false);
+	ret |= dwmac5_est_write(ioaddr, CTR_HIGH, cfg->ctr[1], false);
 	if (ret)
 		return ret;
 
-	total_offset = 0;
 	for (i = 0; i < cfg->gcl_size; i++) {
-		ret = dwmac5_est_write(ioaddr, i, cfg->gcl[i] + offset, true);
+		ret = dwmac5_est_write(ioaddr, i, cfg->gcl[i], true);
 		if (ret)
 			return ret;
-
-		total_offset += offset;
 	}
 
-	total_ctr = cfg->ctr[0] + cfg->ctr[1] * 1000000000ULL;
-	total_ctr += total_offset;
-
-	ctr_low = do_div(total_ctr, 1000000000);
-
-	ret |= dwmac5_est_write(ioaddr, CTR_LOW, ctr_low, false);
-	ret |= dwmac5_est_write(ioaddr, CTR_HIGH, total_ctr, false);
-	if (ret)
-		return ret;
-
 	ctrl = readl(ioaddr + MTL_EST_CONTROL);
 	ctrl &= ~PTOV;
 	ctrl |= ((1000000000 / ptp_rate) * 6) << PTOV_SHIFT;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 5b1c12ff98c0..26b971cd4da5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2184,7 +2184,7 @@ static int stmmac_napi_check(struct stmmac_priv *priv, u32 chan)
 			spin_lock_irqsave(&ch->lock, flags);
 			stmmac_disable_dma_irq(priv, priv->ioaddr, chan, 1, 0);
 			spin_unlock_irqrestore(&ch->lock, flags);
-			__napi_schedule_irqoff(&ch->rx_napi);
+			__napi_schedule(&ch->rx_napi);
 		}
 	}
 
@@ -2193,7 +2193,7 @@ static int stmmac_napi_check(struct stmmac_priv *priv, u32 chan)
 			spin_lock_irqsave(&ch->lock, flags);
 			stmmac_disable_dma_irq(priv, priv->ioaddr, chan, 0, 1);
 			spin_unlock_irqrestore(&ch->lock, flags);
-			__napi_schedule_irqoff(&ch->tx_napi);
+			__napi_schedule(&ch->tx_napi);
 		}
 	}
 
@@ -4026,6 +4026,7 @@ static int stmmac_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	int txfifosz = priv->plat->tx_fifo_size;
+	const int mtu = new_mtu;
 
 	if (txfifosz == 0)
 		txfifosz = priv->dma_cap.tx_fifo_size;
@@ -4043,7 +4044,7 @@ static int stmmac_change_mtu(struct net_device *dev, int new_mtu)
 	if ((txfifosz < new_mtu) || (new_mtu > BUF_SIZE_16KiB))
 		return -EINVAL;
 
-	dev->mtu = new_mtu;
+	dev->mtu = mtu;
 
 	netdev_update_features(dev);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index f5bed4d26e80..8ed3b2c834a0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -599,7 +599,8 @@ static int tc_setup_taprio(struct stmmac_priv *priv,
 {
 	u32 size, wid = priv->dma_cap.estwid, dep = priv->dma_cap.estdep;
 	struct plat_stmmacenet_data *plat = priv->plat;
-	struct timespec64 time;
+	struct timespec64 time, current_time;
+	ktime_t current_time_ns;
 	bool fpe = false;
 	int i, ret = 0;
 	u64 ctr;
@@ -694,7 +695,22 @@ static int tc_setup_taprio(struct stmmac_priv *priv,
 	}
 
 	/* Adjust for real system time */
-	time = ktime_to_timespec64(qopt->base_time);
+	priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, &current_time);
+	current_time_ns = timespec64_to_ktime(current_time);
+	if (ktime_after(qopt->base_time, current_time_ns)) {
+		time = ktime_to_timespec64(qopt->base_time);
+	} else {
+		ktime_t base_time;
+		s64 n;
+
+		n = div64_s64(ktime_sub_ns(current_time_ns, qopt->base_time),
+			      qopt->cycle_time);
+		base_time = ktime_add_ns(qopt->base_time,
+					 (n + 1) * qopt->cycle_time);
+
+		time = ktime_to_timespec64(base_time);
+	}
+
 	priv->plat->est->btr[0] = (u32)time.tv_nsec;
 	priv->plat->est->btr[1] = (u32)time.tv_sec;
 
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index d1fc7955d422..43222a34cba0 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -599,6 +599,7 @@ void cpts_unregister(struct cpts *cpts)
 
 	ptp_clock_unregister(cpts->clock);
 	cpts->clock = NULL;
+	cpts->phc_index = -1;
 
 	cpts_write32(cpts, 0, int_enable);
 	cpts_write32(cpts, 0, control);
@@ -784,6 +785,7 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 	cpts->cc.read = cpts_systim_read;
 	cpts->cc.mask = CLOCKSOURCE_MASK(32);
 	cpts->info = cpts_info;
+	cpts->phc_index = -1;
 
 	if (n_ext_ts)
 		cpts->info.n_ext_ts = n_ext_ts;
diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c
index c4795249719d..14d9a791924b 100644
--- a/drivers/net/ipa/gsi.c
+++ b/drivers/net/ipa/gsi.c
@@ -326,8 +326,8 @@ gsi_evt_ring_state(struct gsi *gsi, u32 evt_ring_id)
 }
 
 /* Issue an event ring command and wait for it to complete */
-static int evt_ring_command(struct gsi *gsi, u32 evt_ring_id,
-			    enum gsi_evt_cmd_opcode opcode)
+static void evt_ring_command(struct gsi *gsi, u32 evt_ring_id,
+			     enum gsi_evt_cmd_opcode opcode)
 {
 	struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id];
 	struct completion *completion = &evt_ring->completion;
@@ -340,7 +340,13 @@ static int evt_ring_command(struct gsi *gsi, u32 evt_ring_id,
 	 * is issued here.  Only permit *this* event ring to trigger
 	 * an interrupt, and only enable the event control IRQ type
 	 * when we expect it to occur.
+	 *
+	 * There's a small chance that a previous command completed
+	 * after the interrupt was disabled, so make sure we have no
+	 * pending interrupts before we enable them.
 	 */
+	iowrite32(~0, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_CLR_OFFSET);
+
 	val = BIT(evt_ring_id);
 	iowrite32(val, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET);
 	gsi_irq_type_enable(gsi, GSI_EV_CTRL);
@@ -355,19 +361,16 @@ static int evt_ring_command(struct gsi *gsi, u32 evt_ring_id,
 	iowrite32(0, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET);
 
 	if (success)
-		return 0;
+		return;
 
 	dev_err(dev, "GSI command %u for event ring %u timed out, state %u\n",
 		opcode, evt_ring_id, evt_ring->state);
-
-	return -ETIMEDOUT;
 }
 
 /* Allocate an event ring in NOT_ALLOCATED state */
 static int gsi_evt_ring_alloc_command(struct gsi *gsi, u32 evt_ring_id)
 {
 	struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id];
-	int ret;
 
 	/* Get initial event ring state */
 	evt_ring->state = gsi_evt_ring_state(gsi, evt_ring_id);
@@ -377,14 +380,16 @@ static int gsi_evt_ring_alloc_command(struct gsi *gsi, u32 evt_ring_id)
 		return -EINVAL;
 	}
 
-	ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_ALLOCATE);
-	if (!ret && evt_ring->state != GSI_EVT_RING_STATE_ALLOCATED) {
-		dev_err(gsi->dev, "event ring %u bad state %u after alloc\n",
-			evt_ring_id, evt_ring->state);
-		ret = -EIO;
-	}
+	evt_ring_command(gsi, evt_ring_id, GSI_EVT_ALLOCATE);
 
-	return ret;
+	/* If successful the event ring state will have changed */
+	if (evt_ring->state == GSI_EVT_RING_STATE_ALLOCATED)
+		return 0;
+
+	dev_err(gsi->dev, "event ring %u bad state %u after alloc\n",
+		evt_ring_id, evt_ring->state);
+
+	return -EIO;
 }
 
 /* Reset a GSI event ring in ALLOCATED or ERROR state. */
@@ -392,7 +397,6 @@ static void gsi_evt_ring_reset_command(struct gsi *gsi, u32 evt_ring_id)
 {
 	struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id];
 	enum gsi_evt_ring_state state = evt_ring->state;
-	int ret;
 
 	if (state != GSI_EVT_RING_STATE_ALLOCATED &&
 	    state != GSI_EVT_RING_STATE_ERROR) {
@@ -401,17 +405,20 @@ static void gsi_evt_ring_reset_command(struct gsi *gsi, u32 evt_ring_id)
 		return;
 	}
 
-	ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_RESET);
-	if (!ret && evt_ring->state != GSI_EVT_RING_STATE_ALLOCATED)
-		dev_err(gsi->dev, "event ring %u bad state %u after reset\n",
-			evt_ring_id, evt_ring->state);
+	evt_ring_command(gsi, evt_ring_id, GSI_EVT_RESET);
+
+	/* If successful the event ring state will have changed */
+	if (evt_ring->state == GSI_EVT_RING_STATE_ALLOCATED)
+		return;
+
+	dev_err(gsi->dev, "event ring %u bad state %u after reset\n",
+		evt_ring_id, evt_ring->state);
 }
 
 /* Issue a hardware de-allocation request for an allocated event ring */
 static void gsi_evt_ring_de_alloc_command(struct gsi *gsi, u32 evt_ring_id)
 {
 	struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id];
-	int ret;
 
 	if (evt_ring->state != GSI_EVT_RING_STATE_ALLOCATED) {
 		dev_err(gsi->dev, "event ring %u state %u before dealloc\n",
@@ -419,10 +426,14 @@ static void gsi_evt_ring_de_alloc_command(struct gsi *gsi, u32 evt_ring_id)
 		return;
 	}
 
-	ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_DE_ALLOC);
-	if (!ret && evt_ring->state != GSI_EVT_RING_STATE_NOT_ALLOCATED)
-		dev_err(gsi->dev, "event ring %u bad state %u after dealloc\n",
-			evt_ring_id, evt_ring->state);
+	evt_ring_command(gsi, evt_ring_id, GSI_EVT_DE_ALLOC);
+
+	/* If successful the event ring state will have changed */
+	if (evt_ring->state == GSI_EVT_RING_STATE_NOT_ALLOCATED)
+		return;
+
+	dev_err(gsi->dev, "event ring %u bad state %u after dealloc\n",
+		evt_ring_id, evt_ring->state);
 }
 
 /* Fetch the current state of a channel from hardware */
@@ -438,7 +449,7 @@ static enum gsi_channel_state gsi_channel_state(struct gsi_channel *channel)
 }
 
 /* Issue a channel command and wait for it to complete */
-static int
+static void
 gsi_channel_command(struct gsi_channel *channel, enum gsi_ch_cmd_opcode opcode)
 {
 	struct completion *completion = &channel->completion;
@@ -453,7 +464,13 @@ gsi_channel_command(struct gsi_channel *channel, enum gsi_ch_cmd_opcode opcode)
 	 * issued here.  So we only permit *this* channel to trigger
 	 * an interrupt and only enable the channel control IRQ type
 	 * when we expect it to occur.
+	 *
+	 * There's a small chance that a previous command completed
+	 * after the interrupt was disabled, so make sure we have no
+	 * pending interrupts before we enable them.
 	 */
+	iowrite32(~0, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_CLR_OFFSET);
+
 	val = BIT(channel_id);
 	iowrite32(val, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET);
 	gsi_irq_type_enable(gsi, GSI_CH_CTRL);
@@ -467,12 +484,10 @@ gsi_channel_command(struct gsi_channel *channel, enum gsi_ch_cmd_opcode opcode)
 	iowrite32(0, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET);
 
 	if (success)
-		return 0;
+		return;
 
 	dev_err(dev, "GSI command %u for channel %u timed out, state %u\n",
 		opcode, channel_id, gsi_channel_state(channel));
-
-	return -ETIMEDOUT;
 }
 
 /* Allocate GSI channel in NOT_ALLOCATED state */
@@ -481,7 +496,6 @@ static int gsi_channel_alloc_command(struct gsi *gsi, u32 channel_id)
 	struct gsi_channel *channel = &gsi->channel[channel_id];
 	struct device *dev = gsi->dev;
 	enum gsi_channel_state state;
-	int ret;
 
 	/* Get initial channel state */
 	state = gsi_channel_state(channel);
@@ -491,17 +505,17 @@ static int gsi_channel_alloc_command(struct gsi *gsi, u32 channel_id)
 		return -EINVAL;
 	}
 
-	ret = gsi_channel_command(channel, GSI_CH_ALLOCATE);
+	gsi_channel_command(channel, GSI_CH_ALLOCATE);
 
-	/* Channel state will normally have been updated */
+	/* If successful the channel state will have changed */
 	state = gsi_channel_state(channel);
-	if (!ret && state != GSI_CHANNEL_STATE_ALLOCATED) {
-		dev_err(dev, "channel %u bad state %u after alloc\n",
-			channel_id, state);
-		ret = -EIO;
-	}
+	if (state == GSI_CHANNEL_STATE_ALLOCATED)
+		return 0;
 
-	return ret;
+	dev_err(dev, "channel %u bad state %u after alloc\n",
+		channel_id, state);
+
+	return -EIO;
 }
 
 /* Start an ALLOCATED channel */
@@ -509,7 +523,6 @@ static int gsi_channel_start_command(struct gsi_channel *channel)
 {
 	struct device *dev = channel->gsi->dev;
 	enum gsi_channel_state state;
-	int ret;
 
 	state = gsi_channel_state(channel);
 	if (state != GSI_CHANNEL_STATE_ALLOCATED &&
@@ -519,17 +532,17 @@ static int gsi_channel_start_command(struct gsi_channel *channel)
 		return -EINVAL;
 	}
 
-	ret = gsi_channel_command(channel, GSI_CH_START);
+	gsi_channel_command(channel, GSI_CH_START);
 
-	/* Channel state will normally have been updated */
+	/* If successful the channel state will have changed */
 	state = gsi_channel_state(channel);
-	if (!ret && state != GSI_CHANNEL_STATE_STARTED) {
-		dev_err(dev, "channel %u bad state %u after start\n",
-			gsi_channel_id(channel), state);
-		ret = -EIO;
-	}
+	if (state == GSI_CHANNEL_STATE_STARTED)
+		return 0;
 
-	return ret;
+	dev_err(dev, "channel %u bad state %u after start\n",
+		gsi_channel_id(channel), state);
+
+	return -EIO;
 }
 
 /* Stop a GSI channel in STARTED state */
@@ -537,7 +550,6 @@ static int gsi_channel_stop_command(struct gsi_channel *channel)
 {
 	struct device *dev = channel->gsi->dev;
 	enum gsi_channel_state state;
-	int ret;
 
 	state = gsi_channel_state(channel);
 
@@ -554,12 +566,12 @@ static int gsi_channel_stop_command(struct gsi_channel *channel)
 		return -EINVAL;
 	}
 
-	ret = gsi_channel_command(channel, GSI_CH_STOP);
+	gsi_channel_command(channel, GSI_CH_STOP);
 
-	/* Channel state will normally have been updated */
+	/* If successful the channel state will have changed */
 	state = gsi_channel_state(channel);
-	if (ret || state == GSI_CHANNEL_STATE_STOPPED)
-		return ret;
+	if (state == GSI_CHANNEL_STATE_STOPPED)
+		return 0;
 
 	/* We may have to try again if stop is in progress */
 	if (state == GSI_CHANNEL_STATE_STOP_IN_PROC)
@@ -576,7 +588,6 @@ static void gsi_channel_reset_command(struct gsi_channel *channel)
 {
 	struct device *dev = channel->gsi->dev;
 	enum gsi_channel_state state;
-	int ret;
 
 	msleep(1);	/* A short delay is required before a RESET command */
 
@@ -590,11 +601,11 @@ static void gsi_channel_reset_command(struct gsi_channel *channel)
 		return;
 	}
 
-	ret = gsi_channel_command(channel, GSI_CH_RESET);
+	gsi_channel_command(channel, GSI_CH_RESET);
 
-	/* Channel state will normally have been updated */
+	/* If successful the channel state will have changed */
 	state = gsi_channel_state(channel);
-	if (!ret && state != GSI_CHANNEL_STATE_ALLOCATED)
+	if (state != GSI_CHANNEL_STATE_ALLOCATED)
 		dev_err(dev, "channel %u bad state %u after reset\n",
 			gsi_channel_id(channel), state);
 }
@@ -605,7 +616,6 @@ static void gsi_channel_de_alloc_command(struct gsi *gsi, u32 channel_id)
 	struct gsi_channel *channel = &gsi->channel[channel_id];
 	struct device *dev = gsi->dev;
 	enum gsi_channel_state state;
-	int ret;
 
 	state = gsi_channel_state(channel);
 	if (state != GSI_CHANNEL_STATE_ALLOCATED) {
@@ -614,11 +624,12 @@ static void gsi_channel_de_alloc_command(struct gsi *gsi, u32 channel_id)
 		return;
 	}
 
-	ret = gsi_channel_command(channel, GSI_CH_DE_ALLOC);
+	gsi_channel_command(channel, GSI_CH_DE_ALLOC);
 
-	/* Channel state will normally have been updated */
+	/* If successful the channel state will have changed */
 	state = gsi_channel_state(channel);
-	if (!ret && state != GSI_CHANNEL_STATE_NOT_ALLOCATED)
+
+	if (state != GSI_CHANNEL_STATE_NOT_ALLOCATED)
 		dev_err(dev, "channel %u bad state %u after dealloc\n",
 			channel_id, state);
 }
diff --git a/drivers/net/ipa/ipa_clock.c b/drivers/net/ipa/ipa_clock.c
index 9dcf16f399b7..135c393437f1 100644
--- a/drivers/net/ipa/ipa_clock.c
+++ b/drivers/net/ipa/ipa_clock.c
@@ -115,13 +115,13 @@ static int ipa_interconnect_enable(struct ipa *ipa)
 		return ret;
 
 	data = &clock->interconnect_data[IPA_INTERCONNECT_IMEM];
-	ret = icc_set_bw(clock->memory_path, data->average_rate,
+	ret = icc_set_bw(clock->imem_path, data->average_rate,
 			 data->peak_rate);
 	if (ret)
 		goto err_memory_path_disable;
 
 	data = &clock->interconnect_data[IPA_INTERCONNECT_CONFIG];
-	ret = icc_set_bw(clock->memory_path, data->average_rate,
+	ret = icc_set_bw(clock->config_path, data->average_rate,
 			 data->peak_rate);
 	if (ret)
 		goto err_imem_path_disable;
diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c
index e34fe2d77324..9b08eb823984 100644
--- a/drivers/net/ipa/ipa_modem.c
+++ b/drivers/net/ipa/ipa_modem.c
@@ -216,6 +216,7 @@ int ipa_modem_start(struct ipa *ipa)
 	ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]->netdev = netdev;
 	ipa->name_map[IPA_ENDPOINT_AP_MODEM_RX]->netdev = netdev;
 
+	SET_NETDEV_DEV(netdev, &ipa->pdev->dev);
 	priv = netdev_priv(netdev);
 	priv->ipa = ipa;
 
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 33372756a451..ddb78fb4d6dc 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -317,7 +317,8 @@ static int smsc_phy_probe(struct phy_device *phydev)
 	/* Make clk optional to keep DTB backward compatibility. */
 	priv->refclk = clk_get_optional(dev, NULL);
 	if (IS_ERR(priv->refclk))
-		dev_err_probe(dev, PTR_ERR(priv->refclk), "Failed to request clock\n");
+		return dev_err_probe(dev, PTR_ERR(priv->refclk),
+				     "Failed to request clock\n");
 
 	ret = clk_prepare_enable(priv->refclk);
 	if (ret)
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 09c27f7773f9..d445ecb1d0c7 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -623,6 +623,7 @@ static int ppp_bridge_channels(struct channel *pch, struct channel *pchb)
 		write_unlock_bh(&pch->upl);
 		return -EALREADY;
 	}
+	refcount_inc(&pchb->file.refcnt);
 	rcu_assign_pointer(pch->bridge, pchb);
 	write_unlock_bh(&pch->upl);
 
@@ -632,19 +633,24 @@ static int ppp_bridge_channels(struct channel *pch, struct channel *pchb)
 		write_unlock_bh(&pchb->upl);
 		goto err_unset;
 	}
+	refcount_inc(&pch->file.refcnt);
 	rcu_assign_pointer(pchb->bridge, pch);
 	write_unlock_bh(&pchb->upl);
 
-	refcount_inc(&pch->file.refcnt);
-	refcount_inc(&pchb->file.refcnt);
-
 	return 0;
 
 err_unset:
 	write_lock_bh(&pch->upl);
+	/* Re-read pch->bridge with upl held in case it was modified concurrently */
+	pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl));
 	RCU_INIT_POINTER(pch->bridge, NULL);
 	write_unlock_bh(&pch->upl);
 	synchronize_rcu();
+
+	if (pchb)
+		if (refcount_dec_and_test(&pchb->file.refcnt))
+			ppp_destroy_channel(pchb);
+
 	return -EALREADY;
 }
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index fbed05ae7b0f..978ac0981d16 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1365,7 +1365,7 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile,
 	int i;
 
 	if (it->nr_segs > MAX_SKB_FRAGS + 1)
-		return ERR_PTR(-ENOMEM);
+		return ERR_PTR(-EMSGSIZE);
 
 	local_bh_disable();
 	skb = napi_get_frags(&tfile->napi);
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 1e3719028780..fbbe78643631 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -631,7 +631,6 @@ config USB_NET_AQC111
 config USB_RTL8153_ECM
 	tristate "RTL8153 ECM support"
 	depends on USB_NET_CDCETHER && (USB_RTL8152 || USB_RTL8152=n)
-	default y
 	help
 	  This option supports ECM mode for RTL8153 ethernet adapter, when
 	  CONFIG_USB_RTL8152 is not set, or the RTL8153 device is not
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 8c1d61c2cbac..6aaa0675c28a 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -793,6 +793,13 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* Lenovo Powered USB-C Travel Hub (4X90S92381, based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x721e, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* ThinkPad USB-C Dock Gen 2 (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0xa387, USB_CLASS_COMM,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 2bac57d5e8d5..5a78848db93f 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1199,7 +1199,10 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	 * accordingly. Otherwise, we should check here.
 	 */
 	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)
-		delayed_ndp_size = ALIGN(ctx->max_ndp_size, ctx->tx_ndp_modulus);
+		delayed_ndp_size = ctx->max_ndp_size +
+			max_t(u32,
+			      ctx->tx_ndp_modulus,
+			      ctx->tx_modulus + ctx->tx_remainder) - 1;
 	else
 		delayed_ndp_size = 0;
 
@@ -1410,7 +1413,8 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	if (!(dev->driver_info->flags & FLAG_SEND_ZLP) &&
 	    skb_out->len > ctx->min_tx_pkt) {
 		padding_count = ctx->tx_curr_size - skb_out->len;
-		skb_put_zero(skb_out, padding_count);
+		if (!WARN_ON(padding_count > ctx->tx_curr_size))
+			skb_put_zero(skb_out, padding_count);
 	} else if (skb_out->len < ctx->tx_curr_size &&
 		   (skb_out->len % dev->maxpacket) == 0) {
 		skb_put_u8(skb_out, 0);	/* force short packet */
@@ -1863,9 +1867,6 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 		 * USB_CDC_NOTIFY_NETWORK_CONNECTION notification shall be
 		 * sent by device after USB_CDC_NOTIFY_SPEED_CHANGE.
 		 */
-		netif_info(dev, link, dev->net,
-			   "network connection: %sconnected\n",
-			   !!event->wValue ? "" : "dis");
 		usbnet_link_change(dev, !!event->wValue, 0);
 		break;
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index d166c321ee9b..af19513a9f75 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1013,6 +1013,7 @@ static const struct usb_device_id products[] = {
 	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0125)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
 	{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0306)},	/* Quectel EP06/EG06/EM06 */
 	{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 */
 
 	/* 3. Combined interface devices matching on interface number */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index c448d6089821..67cd6986634f 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -6877,6 +6877,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7205)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x720c)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7214)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x721e)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0xa387)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff)},
diff --git a/drivers/net/usb/r8153_ecm.c b/drivers/net/usb/r8153_ecm.c
index 2c3fabd38b16..20b2df8d74ae 100644
--- a/drivers/net/usb/r8153_ecm.c
+++ b/drivers/net/usb/r8153_ecm.c
@@ -122,12 +122,20 @@ static const struct driver_info r8153_info = {
 };
 
 static const struct usb_device_id products[] = {
+/* Realtek RTL8153 Based USB 3.0 Ethernet Adapters */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(VENDOR_ID_REALTEK, 0x8153, USB_CLASS_COMM,
 				      USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
 	.driver_info = (unsigned long)&r8153_info,
 },
 
+/* Lenovo Powered USB-C Travel Hub (4X90S92381, based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(VENDOR_ID_LENOVO, 0x721e, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = (unsigned long)&r8153_info,
+},
+
 	{ },		/* END */
 };
 MODULE_DEVICE_TABLE(usb, products);
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index 6609d21ef894..f813ca9dec53 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -387,7 +387,7 @@ generic_rndis_bind(struct usbnet *dev, struct usb_interface *intf, int flags)
 	reply_len = sizeof *phym;
 	retval = rndis_query(dev, intf, u.buf,
 			     RNDIS_OID_GEN_PHYSICAL_MEDIUM,
-			     0, (void **) &phym, &reply_len);
+			     reply_len, (void **)&phym, &reply_len);
 	if (retval != 0 || !phym) {
 		/* OID is optional so don't fail here. */
 		phym_unspec = cpu_to_le32(RNDIS_PHYSICAL_MEDIUM_UNSPECIFIED);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 052975ea0af4..508408fbe78f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2093,14 +2093,16 @@ static int virtnet_set_channels(struct net_device *dev,
 
 	get_online_cpus();
 	err = _virtnet_set_queues(vi, queue_pairs);
-	if (!err) {
-		netif_set_real_num_tx_queues(dev, queue_pairs);
-		netif_set_real_num_rx_queues(dev, queue_pairs);
-
-		virtnet_set_affinity(vi);
+	if (err) {
+		put_online_cpus();
+		goto err;
 	}
+	virtnet_set_affinity(vi);
 	put_online_cpus();
 
+	netif_set_real_num_tx_queues(dev, queue_pairs);
+	netif_set_real_num_rx_queues(dev, queue_pairs);
+ err:
 	return err;
 }
 
@@ -3072,6 +3074,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 			dev_err(&vdev->dev,
 				"device MTU appears to have changed it is now %d < %d",
 				mtu, dev->min_mtu);
+			err = -EINVAL;
 			goto free;
 		}
 
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index 4029fde71a9e..83c9481995dd 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -282,6 +282,7 @@ config SLIC_DS26522
 	tristate "Slic Maxim ds26522 card support"
 	depends on SPI
 	depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE || COMPILE_TEST
+	select BITREVERSE
 	help
 	  This module initializes and configures the slic maxim card
 	  in T1 or E1 mode.
diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index 64f855651336..261b53fc8e04 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -569,6 +569,13 @@ static void ppp_timer(struct timer_list *t)
 	unsigned long flags;
 
 	spin_lock_irqsave(&ppp->lock, flags);
+	/* mod_timer could be called after we entered this function but
+	 * before we got the lock.
+	 */
+	if (timer_pending(&proto->timer)) {
+		spin_unlock_irqrestore(&ppp->lock, flags);
+		return;
+	}
 	switch (proto->state) {
 	case STOPPING:
 	case REQ_SENT:
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index b97c38b9a270..350b7913622c 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -185,7 +185,7 @@ int ath11k_core_suspend(struct ath11k_base *ab)
 	ath11k_hif_ce_irq_disable(ab);
 
 	ret = ath11k_hif_suspend(ab);
-	if (!ret) {
+	if (ret) {
 		ath11k_warn(ab, "failed to suspend hif: %d\n", ret);
 		return ret;
 	}
diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 205c0f1a40e9..920e5026a635 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -2294,6 +2294,7 @@ static void ath11k_dp_rx_h_ppdu(struct ath11k *ar, struct hal_rx_desc *rx_desc,
 {
 	u8 channel_num;
 	u32 center_freq;
+	struct ieee80211_channel *channel;
 
 	rx_status->freq = 0;
 	rx_status->rate_idx = 0;
@@ -2314,9 +2315,12 @@ static void ath11k_dp_rx_h_ppdu(struct ath11k *ar, struct hal_rx_desc *rx_desc,
 		rx_status->band = NL80211_BAND_5GHZ;
 	} else {
 		spin_lock_bh(&ar->data_lock);
-		rx_status->band = ar->rx_channel->band;
-		channel_num =
-			ieee80211_frequency_to_channel(ar->rx_channel->center_freq);
+		channel = ar->rx_channel;
+		if (channel) {
+			rx_status->band = channel->band;
+			channel_num =
+				ieee80211_frequency_to_channel(channel->center_freq);
+		}
 		spin_unlock_bh(&ar->data_lock);
 		ath11k_dbg_dump(ar->ab, ATH11K_DBG_DATA, NULL, "rx_desc: ",
 				rx_desc, sizeof(struct hal_rx_desc));
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 5c175e3e09b2..c1608f64ea95 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -3021,6 +3021,7 @@ static int ath11k_mac_station_add(struct ath11k *ar,
 	}
 
 	if (ab->hw_params.vdev_start_delay &&
+	    !arvif->is_started &&
 	    arvif->vdev_type != WMI_VDEV_TYPE_AP) {
 		ret = ath11k_start_vdev_delay(ar->hw, vif);
 		if (ret) {
@@ -5284,7 +5285,8 @@ ath11k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 	/* for QCA6390 bss peer must be created before vdev_start */
 	if (ab->hw_params.vdev_start_delay &&
 	    arvif->vdev_type != WMI_VDEV_TYPE_AP &&
-	    arvif->vdev_type != WMI_VDEV_TYPE_MONITOR) {
+	    arvif->vdev_type != WMI_VDEV_TYPE_MONITOR &&
+	    !ath11k_peer_find_by_vdev_id(ab, arvif->vdev_id)) {
 		memcpy(&arvif->chanctx, ctx, sizeof(*ctx));
 		ret = 0;
 		goto out;
@@ -5295,7 +5297,9 @@ ath11k_mac_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	if (ab->hw_params.vdev_start_delay) {
+	if (ab->hw_params.vdev_start_delay &&
+	    (arvif->vdev_type == WMI_VDEV_TYPE_AP ||
+	    arvif->vdev_type == WMI_VDEV_TYPE_MONITOR)) {
 		param.vdev_id = arvif->vdev_id;
 		param.peer_type = WMI_PEER_TYPE_DEFAULT;
 		param.peer_addr = ar->mac_addr;
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index 857647aa57c8..20b415cd96c4 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -274,7 +274,7 @@ static int ath11k_pci_fix_l1ss(struct ath11k_base *ab)
 				      PCIE_QSERDES_COM_SYSCLK_EN_SEL_REG,
 				      PCIE_QSERDES_COM_SYSCLK_EN_SEL_VAL,
 				      PCIE_QSERDES_COM_SYSCLK_EN_SEL_MSK);
-	if (!ret) {
+	if (ret) {
 		ath11k_warn(ab, "failed to set sysclk: %d\n", ret);
 		return ret;
 	}
@@ -283,7 +283,7 @@ static int ath11k_pci_fix_l1ss(struct ath11k_base *ab)
 				      PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG1_REG,
 				      PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG1_VAL,
 				      PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG_MSK);
-	if (!ret) {
+	if (ret) {
 		ath11k_warn(ab, "failed to set dtct config1 error: %d\n", ret);
 		return ret;
 	}
@@ -292,7 +292,7 @@ static int ath11k_pci_fix_l1ss(struct ath11k_base *ab)
 				      PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG2_REG,
 				      PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG2_VAL,
 				      PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG_MSK);
-	if (!ret) {
+	if (ret) {
 		ath11k_warn(ab, "failed to set dtct config2: %d\n", ret);
 		return ret;
 	}
@@ -301,7 +301,7 @@ static int ath11k_pci_fix_l1ss(struct ath11k_base *ab)
 				      PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG4_REG,
 				      PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG4_VAL,
 				      PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG_MSK);
-	if (!ret) {
+	if (ret) {
 		ath11k_warn(ab, "failed to set dtct config4: %d\n", ret);
 		return ret;
 	}
@@ -886,6 +886,32 @@ static void ath11k_pci_free_region(struct ath11k_pci *ab_pci)
 		pci_disable_device(pci_dev);
 }
 
+static void ath11k_pci_aspm_disable(struct ath11k_pci *ab_pci)
+{
+	struct ath11k_base *ab = ab_pci->ab;
+
+	pcie_capability_read_word(ab_pci->pdev, PCI_EXP_LNKCTL,
+				  &ab_pci->link_ctl);
+
+	ath11k_dbg(ab, ATH11K_DBG_PCI, "pci link_ctl 0x%04x L0s %d L1 %d\n",
+		   ab_pci->link_ctl,
+		   u16_get_bits(ab_pci->link_ctl, PCI_EXP_LNKCTL_ASPM_L0S),
+		   u16_get_bits(ab_pci->link_ctl, PCI_EXP_LNKCTL_ASPM_L1));
+
+	/* disable L0s and L1 */
+	pcie_capability_write_word(ab_pci->pdev, PCI_EXP_LNKCTL,
+				   ab_pci->link_ctl & ~PCI_EXP_LNKCTL_ASPMC);
+
+	set_bit(ATH11K_PCI_ASPM_RESTORE, &ab_pci->flags);
+}
+
+static void ath11k_pci_aspm_restore(struct ath11k_pci *ab_pci)
+{
+	if (test_and_clear_bit(ATH11K_PCI_ASPM_RESTORE, &ab_pci->flags))
+		pcie_capability_write_word(ab_pci->pdev, PCI_EXP_LNKCTL,
+					   ab_pci->link_ctl);
+}
+
 static int ath11k_pci_power_up(struct ath11k_base *ab)
 {
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
@@ -895,6 +921,11 @@ static int ath11k_pci_power_up(struct ath11k_base *ab)
 	clear_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags);
 	ath11k_pci_sw_reset(ab_pci->ab, true);
 
+	/* Disable ASPM during firmware download due to problems switching
+	 * to AMSS state.
+	 */
+	ath11k_pci_aspm_disable(ab_pci);
+
 	ret = ath11k_mhi_start(ab_pci);
 	if (ret) {
 		ath11k_err(ab, "failed to start mhi: %d\n", ret);
@@ -908,6 +939,9 @@ static void ath11k_pci_power_down(struct ath11k_base *ab)
 {
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
 
+	/* restore aspm in case firmware bootup fails */
+	ath11k_pci_aspm_restore(ab_pci);
+
 	ath11k_pci_force_wake(ab_pci->ab);
 	ath11k_mhi_stop(ab_pci);
 	clear_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags);
@@ -965,6 +999,8 @@ static int ath11k_pci_start(struct ath11k_base *ab)
 
 	set_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags);
 
+	ath11k_pci_aspm_restore(ab_pci);
+
 	ath11k_pci_ce_irqs_enable(ab);
 	ath11k_ce_rx_post_buf(ab);
 
diff --git a/drivers/net/wireless/ath/ath11k/pci.h b/drivers/net/wireless/ath/ath11k/pci.h
index 0432a702416b..fe44d0dfce19 100644
--- a/drivers/net/wireless/ath/ath11k/pci.h
+++ b/drivers/net/wireless/ath/ath11k/pci.h
@@ -63,6 +63,7 @@ struct ath11k_msi_config {
 enum ath11k_pci_flags {
 	ATH11K_PCI_FLAG_INIT_DONE,
 	ATH11K_PCI_FLAG_IS_MSI_64,
+	ATH11K_PCI_ASPM_RESTORE,
 };
 
 struct ath11k_pci {
@@ -80,6 +81,7 @@ struct ath11k_pci {
 
 	/* enum ath11k_pci_flags */
 	unsigned long flags;
+	u16 link_ctl;
 };
 
 static inline struct ath11k_pci *ath11k_pci_priv(struct ath11k_base *ab)
diff --git a/drivers/net/wireless/ath/ath11k/peer.c b/drivers/net/wireless/ath/ath11k/peer.c
index 1866d82678fa..b69e7ebfa930 100644
--- a/drivers/net/wireless/ath/ath11k/peer.c
+++ b/drivers/net/wireless/ath/ath11k/peer.c
@@ -76,6 +76,23 @@ struct ath11k_peer *ath11k_peer_find_by_id(struct ath11k_base *ab,
 	return NULL;
 }
 
+struct ath11k_peer *ath11k_peer_find_by_vdev_id(struct ath11k_base *ab,
+						int vdev_id)
+{
+	struct ath11k_peer *peer;
+
+	spin_lock_bh(&ab->base_lock);
+
+	list_for_each_entry(peer, &ab->peers, list) {
+		if (vdev_id == peer->vdev_id) {
+			spin_unlock_bh(&ab->base_lock);
+			return peer;
+		}
+	}
+	spin_unlock_bh(&ab->base_lock);
+	return NULL;
+}
+
 void ath11k_peer_unmap_event(struct ath11k_base *ab, u16 peer_id)
 {
 	struct ath11k_peer *peer;
diff --git a/drivers/net/wireless/ath/ath11k/peer.h b/drivers/net/wireless/ath/ath11k/peer.h
index bba2e00b6944..8553ed061aea 100644
--- a/drivers/net/wireless/ath/ath11k/peer.h
+++ b/drivers/net/wireless/ath/ath11k/peer.h
@@ -43,5 +43,7 @@ int ath11k_peer_create(struct ath11k *ar, struct ath11k_vif *arvif,
 		       struct ieee80211_sta *sta, struct peer_create_params *param);
 int ath11k_wait_for_peer_delete_done(struct ath11k *ar, u32 vdev_id,
 				     const u8 *addr);
+struct ath11k_peer *ath11k_peer_find_by_vdev_id(struct ath11k_base *ab,
+						int vdev_id);
 
 #endif /* _PEER_H_ */
diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index f0b5c50974f3..0db623ff4bb9 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -1660,6 +1660,7 @@ static int ath11k_qmi_respond_fw_mem_request(struct ath11k_base *ab)
 	struct qmi_wlanfw_respond_mem_resp_msg_v01 resp;
 	struct qmi_txn txn = {};
 	int ret = 0, i;
+	bool delayed;
 
 	req = kzalloc(sizeof(*req), GFP_KERNEL);
 	if (!req)
@@ -1672,11 +1673,13 @@ static int ath11k_qmi_respond_fw_mem_request(struct ath11k_base *ab)
 	 * failure to FW and FW will then request mulitple blocks of small
 	 * chunk size memory.
 	 */
-	if (!ab->bus_params.fixed_mem_region && ab->qmi.mem_seg_count <= 2) {
+	if (!ab->bus_params.fixed_mem_region && ab->qmi.target_mem_delayed) {
+		delayed = true;
 		ath11k_dbg(ab, ATH11K_DBG_QMI, "qmi delays mem_request %d\n",
 			   ab->qmi.mem_seg_count);
 		memset(req, 0, sizeof(*req));
 	} else {
+		delayed = false;
 		req->mem_seg_len = ab->qmi.mem_seg_count;
 
 		for (i = 0; i < req->mem_seg_len ; i++) {
@@ -1708,6 +1711,12 @@ static int ath11k_qmi_respond_fw_mem_request(struct ath11k_base *ab)
 	}
 
 	if (resp.resp.result != QMI_RESULT_SUCCESS_V01) {
+		/* the error response is expected when
+		 * target_mem_delayed is true.
+		 */
+		if (delayed && resp.resp.error == 0)
+			goto out;
+
 		ath11k_warn(ab, "Respond mem req failed, result: %d, err: %d\n",
 			    resp.resp.result, resp.resp.error);
 		ret = -EINVAL;
@@ -1742,6 +1751,8 @@ static int ath11k_qmi_alloc_target_mem_chunk(struct ath11k_base *ab)
 	int i;
 	struct target_mem_chunk *chunk;
 
+	ab->qmi.target_mem_delayed = false;
+
 	for (i = 0; i < ab->qmi.mem_seg_count; i++) {
 		chunk = &ab->qmi.target_mem[i];
 		chunk->vaddr = dma_alloc_coherent(ab->dev,
@@ -1749,6 +1760,15 @@ static int ath11k_qmi_alloc_target_mem_chunk(struct ath11k_base *ab)
 						  &chunk->paddr,
 						  GFP_KERNEL);
 		if (!chunk->vaddr) {
+			if (ab->qmi.mem_seg_count <= 2) {
+				ath11k_dbg(ab, ATH11K_DBG_QMI,
+					   "qmi dma allocation failed (%d B type %u), will try later with small size\n",
+					    chunk->size,
+					    chunk->type);
+				ath11k_qmi_free_target_mem_chunk(ab);
+				ab->qmi.target_mem_delayed = true;
+				return 0;
+			}
 			ath11k_err(ab, "failed to alloc memory, size: 0x%x, type: %u\n",
 				   chunk->size,
 				   chunk->type);
@@ -2517,7 +2537,7 @@ static void ath11k_qmi_msg_mem_request_cb(struct qmi_handle *qmi_hdl,
 				    ret);
 			return;
 		}
-	} else if (msg->mem_seg_len > 2) {
+	} else {
 		ret = ath11k_qmi_alloc_target_mem_chunk(ab);
 		if (ret) {
 			ath11k_warn(ab, "qmi failed to alloc target memory: %d\n",
diff --git a/drivers/net/wireless/ath/ath11k/qmi.h b/drivers/net/wireless/ath/ath11k/qmi.h
index 92925c9eac67..7bad374cc23a 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.h
+++ b/drivers/net/wireless/ath/ath11k/qmi.h
@@ -125,6 +125,7 @@ struct ath11k_qmi {
 	struct target_mem_chunk target_mem[ATH11K_QMI_WLANFW_MAX_NUM_MEM_SEG_V01];
 	u32 mem_seg_count;
 	u32 target_mem_mode;
+	bool target_mem_delayed;
 	u8 cal_done;
 	struct target_info target;
 	struct m3_mem_region m3_mem;
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index da4b546b62cb..73869d445c5b 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -3460,6 +3460,9 @@ int ath11k_wmi_set_hw_mode(struct ath11k_base *ab,
 	len = sizeof(*cmd);
 
 	skb = ath11k_wmi_alloc_skb(wmi_ab, len);
+	if (!skb)
+		return -ENOMEM;
+
 	cmd = (struct wmi_pdev_set_hw_mode_cmd_param *)skb->data;
 
 	cmd->tlv_header = FIELD_PREP(WMI_TLV_TAG, WMI_TAG_PDEV_SET_HW_MODE_CMD) |
diff --git a/drivers/net/wireless/ath/wil6210/Kconfig b/drivers/net/wireless/ath/wil6210/Kconfig
index 6a95b199bf62..f074e9c31aa2 100644
--- a/drivers/net/wireless/ath/wil6210/Kconfig
+++ b/drivers/net/wireless/ath/wil6210/Kconfig
@@ -2,6 +2,7 @@
 config WIL6210
 	tristate "Wilocity 60g WiFi card wil6210 support"
 	select WANT_DEV_COREDUMP
+	select CRC32
 	depends on CFG80211
 	depends on PCI
 	default n
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index ed4635bd151a..102a8f14c22d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -40,9 +40,9 @@ static const struct ieee80211_iface_limit if_limits[] = {
 		.types = BIT(NL80211_IFTYPE_ADHOC)
 	}, {
 		.max = 16,
-		.types = BIT(NL80211_IFTYPE_AP) |
+		.types = BIT(NL80211_IFTYPE_AP)
 #ifdef CONFIG_MAC80211_MESH
-			 BIT(NL80211_IFTYPE_MESH_POINT)
+			 | BIT(NL80211_IFTYPE_MESH_POINT)
 #endif
 	}, {
 		.max = MT7915_MAX_INTERFACES,
diff --git a/drivers/net/wireless/mediatek/mt76/sdio.c b/drivers/net/wireless/mediatek/mt76/sdio.c
index 62b5b912818f..0b6facb17ff7 100644
--- a/drivers/net/wireless/mediatek/mt76/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/sdio.c
@@ -157,10 +157,14 @@ static void mt76s_net_worker(struct mt76_worker *w)
 
 static int mt76s_process_tx_queue(struct mt76_dev *dev, struct mt76_queue *q)
 {
-	bool wake, mcu = q == dev->q_mcu[MT_MCUQ_WM];
 	struct mt76_queue_entry entry;
 	int nframes = 0;
+	bool mcu;
 
+	if (!q)
+		return 0;
+
+	mcu = q == dev->q_mcu[MT_MCUQ_WM];
 	while (q->queued > 0) {
 		if (!q->entry[q->tail].done)
 			break;
@@ -177,21 +181,12 @@ static int mt76s_process_tx_queue(struct mt76_dev *dev, struct mt76_queue *q)
 		nframes++;
 	}
 
-	wake = q->stopped && q->queued < q->ndesc - 8;
-	if (wake)
-		q->stopped = false;
-
 	if (!q->queued)
 		wake_up(&dev->tx_wait);
 
-	if (mcu)
-		goto out;
-
-	mt76_txq_schedule(&dev->phy, q->qid);
+	if (!mcu)
+		mt76_txq_schedule(&dev->phy, q->qid);
 
-	if (wake)
-		ieee80211_wake_queue(dev->hw, q->qid);
-out:
 	return nframes;
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index dc850109de22..b95d093728b9 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -811,11 +811,12 @@ static void mt76u_status_worker(struct mt76_worker *w)
 	struct mt76_dev *dev = container_of(usb, struct mt76_dev, usb);
 	struct mt76_queue_entry entry;
 	struct mt76_queue *q;
-	bool wake;
 	int i;
 
 	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
 		q = dev->phy.q_tx[i];
+		if (!q)
+			continue;
 
 		while (q->queued > 0) {
 			if (!q->entry[q->tail].done)
@@ -827,10 +828,6 @@ static void mt76u_status_worker(struct mt76_worker *w)
 			mt76_queue_tx_complete(dev, q, &entry);
 		}
 
-		wake = q->stopped && q->queued < q->ndesc - 8;
-		if (wake)
-			q->stopped = false;
-
 		if (!q->queued)
 			wake_up(&dev->tx_wait);
 
@@ -839,8 +836,6 @@ static void mt76u_status_worker(struct mt76_worker *w)
 		if (dev->drv->tx_status_data &&
 		    !test_and_set_bit(MT76_READING_STATS, &dev->phy.state))
 			queue_work(dev->wq, &dev->usb.stat_work);
-		if (wake)
-			ieee80211_wake_queue(dev->hw, i);
 	}
 }
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index a7259dbc953d..965bd9589045 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -78,7 +78,6 @@ static void rtl_fw_do_work(const struct firmware *firmware, void *context,
 
 	rtl_dbg(rtlpriv, COMP_ERR, DBG_LOUD,
 		"Firmware callback routine entered!\n");
-	complete(&rtlpriv->firmware_loading_complete);
 	if (!firmware) {
 		if (rtlpriv->cfg->alt_fw_name) {
 			err = request_firmware(&firmware,
@@ -91,13 +90,13 @@ static void rtl_fw_do_work(const struct firmware *firmware, void *context,
 		}
 		pr_err("Selected firmware is not available\n");
 		rtlpriv->max_fw_size = 0;
-		return;
+		goto exit;
 	}
 found_alt:
 	if (firmware->size > rtlpriv->max_fw_size) {
 		pr_err("Firmware is too big!\n");
 		release_firmware(firmware);
-		return;
+		goto exit;
 	}
 	if (!is_wow) {
 		memcpy(rtlpriv->rtlhal.pfirmware, firmware->data,
@@ -109,6 +108,9 @@ found_alt:
 		rtlpriv->rtlhal.wowlan_fwsize = firmware->size;
 	}
 	release_firmware(firmware);
+
+exit:
+	complete(&rtlpriv->firmware_loading_complete);
 }
 
 void rtl_fw_cb(const struct firmware *firmware, void *context)
diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.c b/drivers/ntb/hw/idt/ntb_hw_idt.c
index d54261f50851..e7a4c2aa8baa 100644
--- a/drivers/ntb/hw/idt/ntb_hw_idt.c
+++ b/drivers/ntb/hw/idt/ntb_hw_idt.c
@@ -2511,7 +2511,7 @@ static int idt_init_dbgfs(struct idt_ntb_dev *ndev)
 	/* If the top directory is not created then do nothing */
 	if (IS_ERR_OR_NULL(dbgfs_topdir)) {
 		dev_info(&ndev->ntb.pdev->dev, "Top DebugFS directory absent");
-		return PTR_ERR(dbgfs_topdir);
+		return PTR_ERR_OR_ZERO(dbgfs_topdir);
 	}
 
 	/* Create the info file node */
@@ -2756,7 +2756,7 @@ static int idt_pci_probe(struct pci_dev *pdev,
 
 	/* Allocate the memory for IDT NTB device data */
 	ndev = idt_create_dev(pdev, id);
-	if (IS_ERR_OR_NULL(ndev))
+	if (IS_ERR(ndev))
 		return PTR_ERR(ndev);
 
 	/* Initialize the basic PCI subsystem of the device */
diff --git a/drivers/ntb/hw/intel/ntb_hw_gen1.h b/drivers/ntb/hw/intel/ntb_hw_gen1.h
index 1b759942d8af..344249fc18d1 100644
--- a/drivers/ntb/hw/intel/ntb_hw_gen1.h
+++ b/drivers/ntb/hw/intel/ntb_hw_gen1.h
@@ -141,6 +141,7 @@
 #define NTB_HWERR_B2BDOORBELL_BIT14	BIT_ULL(2)
 #define NTB_HWERR_MSIX_VECTOR32_BAD	BIT_ULL(3)
 #define NTB_HWERR_BAR_ALIGN		BIT_ULL(4)
+#define NTB_HWERR_LTR_BAD		BIT_ULL(5)
 
 extern struct intel_b2b_addr xeon_b2b_usd_addr;
 extern struct intel_b2b_addr xeon_b2b_dsd_addr;
diff --git a/drivers/ntb/hw/intel/ntb_hw_gen4.c b/drivers/ntb/hw/intel/ntb_hw_gen4.c
index bc4541cbf8c6..fede05151f69 100644
--- a/drivers/ntb/hw/intel/ntb_hw_gen4.c
+++ b/drivers/ntb/hw/intel/ntb_hw_gen4.c
@@ -177,8 +177,10 @@ int gen4_init_dev(struct intel_ntb_dev *ndev)
 
 	ndev->reg = &gen4_reg;
 
-	if (pdev_is_ICX(pdev))
+	if (pdev_is_ICX(pdev)) {
 		ndev->hwerr_flags |= NTB_HWERR_BAR_ALIGN;
+		ndev->hwerr_flags |= NTB_HWERR_LTR_BAD;
+	}
 
 	ppd1 = ioread32(ndev->self_mmio + GEN4_PPD1_OFFSET);
 	ndev->ntb.topo = gen4_ppd_topo(ndev, ppd1);
@@ -431,6 +433,25 @@ static int intel_ntb4_link_enable(struct ntb_dev *ntb,
 		dev_dbg(&ntb->pdev->dev,
 				"ignoring max_width %d\n", max_width);
 
+	if (!(ndev->hwerr_flags & NTB_HWERR_LTR_BAD)) {
+		u32 ltr;
+
+		/* Setup active snoop LTR values */
+		ltr = NTB_LTR_ACTIVE_REQMNT | NTB_LTR_ACTIVE_VAL | NTB_LTR_ACTIVE_LATSCALE;
+		/* Setup active non-snoop values */
+		ltr = (ltr << NTB_LTR_NS_SHIFT) | ltr;
+		iowrite32(ltr, ndev->self_mmio + GEN4_LTR_ACTIVE_OFFSET);
+
+		/* Setup idle snoop LTR values */
+		ltr = NTB_LTR_IDLE_VAL | NTB_LTR_IDLE_LATSCALE | NTB_LTR_IDLE_REQMNT;
+		/* Setup idle non-snoop values */
+		ltr = (ltr << NTB_LTR_NS_SHIFT) | ltr;
+		iowrite32(ltr, ndev->self_mmio + GEN4_LTR_IDLE_OFFSET);
+
+		/* setup PCIe LTR to active */
+		iowrite8(NTB_LTR_SWSEL_ACTIVE, ndev->self_mmio + GEN4_LTR_SWSEL_OFFSET);
+	}
+
 	ntb_ctl = NTB_CTL_E2I_BAR23_SNOOP | NTB_CTL_I2E_BAR23_SNOOP;
 	ntb_ctl |= NTB_CTL_E2I_BAR45_SNOOP | NTB_CTL_I2E_BAR45_SNOOP;
 	iowrite32(ntb_ctl, ndev->self_mmio + ndev->reg->ntb_ctl);
@@ -476,6 +497,10 @@ static int intel_ntb4_link_disable(struct ntb_dev *ntb)
 	lnkctl |= GEN4_LINK_CTRL_LINK_DISABLE;
 	iowrite16(lnkctl, ndev->self_mmio + GEN4_LINK_CTRL_OFFSET);
 
+	/* set LTR to idle */
+	if (!(ndev->hwerr_flags & NTB_HWERR_LTR_BAD))
+		iowrite8(NTB_LTR_SWSEL_IDLE, ndev->self_mmio + GEN4_LTR_SWSEL_OFFSET);
+
 	ndev->dev_up = 0;
 
 	return 0;
diff --git a/drivers/ntb/hw/intel/ntb_hw_gen4.h b/drivers/ntb/hw/intel/ntb_hw_gen4.h
index a868c788de02..3fcd3fdce9ed 100644
--- a/drivers/ntb/hw/intel/ntb_hw_gen4.h
+++ b/drivers/ntb/hw/intel/ntb_hw_gen4.h
@@ -35,6 +35,9 @@
 #define GEN4_IM_SPAD_SEM_OFFSET		0x00c0	/* SPAD hw semaphore */
 #define GEN4_IM_SPAD_STICKY_OFFSET	0x00c4  /* sticky SPAD */
 #define GEN4_IM_DOORBELL_OFFSET		0x0100  /* 0-31 doorbells */
+#define GEN4_LTR_SWSEL_OFFSET		0x30ec
+#define GEN4_LTR_ACTIVE_OFFSET		0x30f0
+#define GEN4_LTR_IDLE_OFFSET		0x30f4
 #define GEN4_EM_SPAD_OFFSET		0x8080
 /* note, link status is now in MMIO and not config space for NTB */
 #define GEN4_LINK_CTRL_OFFSET		0xb050
@@ -80,6 +83,18 @@
 
 #define NTB_SJC_FORCEDETECT		0x000004
 
+#define NTB_LTR_SWSEL_ACTIVE		0x0
+#define NTB_LTR_SWSEL_IDLE		0x1
+
+#define NTB_LTR_NS_SHIFT		16
+#define NTB_LTR_ACTIVE_VAL		0x0000  /* 0 us */
+#define NTB_LTR_ACTIVE_LATSCALE		0x0800  /* 1us scale */
+#define NTB_LTR_ACTIVE_REQMNT		0x8000  /* snoop req enable */
+
+#define NTB_LTR_IDLE_VAL		0x0258  /* 600 us */
+#define NTB_LTR_IDLE_LATSCALE		0x0800  /* 1us scale */
+#define NTB_LTR_IDLE_REQMNT		0x8000  /* snoop req enable */
+
 ssize_t ndev_ntb4_debugfs_read(struct file *filp, char __user *ubuf,
 				      size_t count, loff_t *offp);
 int gen4_init_dev(struct intel_ntb_dev *ndev);
diff --git a/drivers/ntb/msi.c b/drivers/ntb/msi.c
index 0a5e884a920c..3f05cfbc73af 100644
--- a/drivers/ntb/msi.c
+++ b/drivers/ntb/msi.c
@@ -282,15 +282,13 @@ int ntbm_msi_request_threaded_irq(struct ntb_dev *ntb, irq_handler_t handler,
 				  struct ntb_msi_desc *msi_desc)
 {
 	struct msi_desc *entry;
-	struct irq_desc *desc;
 	int ret;
 
 	if (!ntb->msi)
 		return -EINVAL;
 
 	for_each_pci_msi_entry(entry, ntb->pdev) {
-		desc = irq_to_desc(entry->irq);
-		if (desc->action)
+		if (irq_has_action(entry->irq))
 			continue;
 
 		ret = devm_request_threaded_irq(&ntb->dev, entry->irq, handler,
diff --git a/drivers/nvdimm/btt.h b/drivers/nvdimm/btt.h
index 2e258bee7db2..aa53e0b769bd 100644
--- a/drivers/nvdimm/btt.h
+++ b/drivers/nvdimm/btt.h
@@ -7,7 +7,6 @@
 #ifndef _LINUX_BTT_H
 #define _LINUX_BTT_H
 
-#include <linux/badblocks.h>
 #include <linux/types.h>
 
 #define BTT_SIG_LEN 16
@@ -197,6 +196,8 @@ struct arena_info {
 	int log_index[2];
 };
 
+struct badblocks;
+
 /**
  * struct btt - handle for a BTT instance
  * @btt_disk:		Pointer to the gendisk for BTT device
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 5a7c80053c62..030dbde6b088 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -4,6 +4,7 @@
  */
 #include <linux/device.h>
 #include <linux/sizes.h>
+#include <linux/badblocks.h>
 #include "nd-core.h"
 #include "pmem.h"
 #include "pfn.h"
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index c21ba0602029..7de592d7eff4 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -3,7 +3,6 @@
  * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
  */
 #include <linux/libnvdimm.h>
-#include <linux/badblocks.h>
 #include <linux/suspend.h>
 #include <linux/export.h>
 #include <linux/module.h>
diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c
index 47a4828b8b31..9251441fd8a3 100644
--- a/drivers/nvdimm/label.c
+++ b/drivers/nvdimm/label.c
@@ -980,6 +980,15 @@ static int __blk_label_update(struct nd_region *nd_region,
 		}
 	}
 
+	/* release slots associated with any invalidated UUIDs */
+	mutex_lock(&nd_mapping->lock);
+	list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list)
+		if (test_and_clear_bit(ND_LABEL_REAP, &label_ent->flags)) {
+			reap_victim(nd_mapping, label_ent);
+			list_move(&label_ent->list, &list);
+		}
+	mutex_unlock(&nd_mapping->lock);
+
 	/*
 	 * Find the resource associated with the first label in the set
 	 * per the v1.2 namespace specification.
@@ -999,8 +1008,10 @@ static int __blk_label_update(struct nd_region *nd_region,
 		if (is_old_resource(res, old_res_list, old_num_resources))
 			continue; /* carry-over */
 		slot = nd_label_alloc_slot(ndd);
-		if (slot == UINT_MAX)
+		if (slot == UINT_MAX) {
+			rc = -ENXIO;
 			goto abort;
+		}
 		dev_dbg(ndd->dev, "allocated: %d\n", slot);
 
 		nd_label = to_label(ndd, slot);
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index ce1b61519441..200bdd672c28 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -179,7 +179,7 @@ int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_reset_ctrl);
 
-int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
+static int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 {
 	int ret;
 
@@ -192,7 +192,6 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync);
 
 static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
 {
@@ -331,7 +330,7 @@ static inline void nvme_end_req(struct request *req)
 		req->__sector = nvme_lba_to_sect(req->q->queuedata,
 			le64_to_cpu(nvme_req(req)->result.u64));
 
-	nvme_trace_bio_complete(req, status);
+	nvme_trace_bio_complete(req);
 	blk_mq_end_request(req, status);
 }
 
@@ -578,7 +577,7 @@ struct request *nvme_alloc_request(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(nvme_alloc_request);
 
-struct request *nvme_alloc_request_qid(struct request_queue *q,
+static struct request *nvme_alloc_request_qid(struct request_queue *q,
 		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
 {
 	struct request *req;
@@ -589,7 +588,6 @@ struct request *nvme_alloc_request_qid(struct request_queue *q,
 		nvme_init_request(req, cmd);
 	return req;
 }
-EXPORT_SYMBOL_GPL(nvme_alloc_request_qid);
 
 static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
 {
@@ -2858,6 +2856,11 @@ static const struct attribute_group *nvme_subsys_attrs_groups[] = {
 	NULL,
 };
 
+static inline bool nvme_discovery_ctrl(struct nvme_ctrl *ctrl)
+{
+	return ctrl->opts && ctrl->opts->discovery_nqn;
+}
+
 static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
 		struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 {
@@ -2877,7 +2880,7 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
 		}
 
 		if ((id->cmic & NVME_CTRL_CMIC_MULTI_CTRL) ||
-		    (ctrl->opts && ctrl->opts->discovery_nqn))
+		    nvme_discovery_ctrl(ctrl))
 			continue;
 
 		dev_err(ctrl->device,
@@ -3146,7 +3149,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 			goto out_free;
 		}
 
-		if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
+		if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) {
 			dev_err(ctrl->device,
 				"keep-alive support is mandatory for fabrics\n");
 			ret = -EINVAL;
@@ -3186,7 +3189,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	if (ret < 0)
 		return ret;
 
-	if (!ctrl->identified) {
+	if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) {
 		ret = nvme_hwmon_init(ctrl);
 		if (ret < 0)
 			return ret;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 38373a0e86ef..5f36cfa8136c 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -166,6 +166,7 @@ struct nvme_fc_ctrl {
 	struct blk_mq_tag_set	admin_tag_set;
 	struct blk_mq_tag_set	tag_set;
 
+	struct work_struct	ioerr_work;
 	struct delayed_work	connect_work;
 
 	struct kref		ref;
@@ -1889,6 +1890,15 @@ __nvme_fc_fcpop_chk_teardowns(struct nvme_fc_ctrl *ctrl,
 }
 
 static void
+nvme_fc_ctrl_ioerr_work(struct work_struct *work)
+{
+	struct nvme_fc_ctrl *ctrl =
+			container_of(work, struct nvme_fc_ctrl, ioerr_work);
+
+	nvme_fc_error_recovery(ctrl, "transport detected io error");
+}
+
+static void
 nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 {
 	struct nvme_fc_fcp_op *op = fcp_req_to_fcp_op(req);
@@ -2046,7 +2056,7 @@ done:
 
 check_error:
 	if (terminate_assoc)
-		nvme_fc_error_recovery(ctrl, "transport detected io error");
+		queue_work(nvme_reset_wq, &ctrl->ioerr_work);
 }
 
 static int
@@ -3233,6 +3243,7 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 
+	cancel_work_sync(&ctrl->ioerr_work);
 	cancel_delayed_work_sync(&ctrl->connect_work);
 	/*
 	 * kill the association on the link side.  this will block
@@ -3449,6 +3460,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_fc_reset_ctrl_work);
 	INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work);
+	INIT_WORK(&ctrl->ioerr_work, nvme_fc_ctrl_ioerr_work);
 	spin_lock_init(&ctrl->lock);
 
 	/* io queue count */
@@ -3540,6 +3552,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 fail_ctrl:
 	nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING);
+	cancel_work_sync(&ctrl->ioerr_work);
 	cancel_work_sync(&ctrl->ctrl.reset_work);
 	cancel_delayed_work_sync(&ctrl->connect_work);
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 7e49f61f81df..88a6b97247f5 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -610,8 +610,6 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl);
 #define NVME_QID_ANY -1
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, blk_mq_req_flags_t flags);
-struct request *nvme_alloc_request_qid(struct request_queue *q,
-		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid);
 void nvme_cleanup_cmd(struct request *req);
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd);
@@ -630,7 +628,6 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid,
 int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count);
 void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
 int nvme_reset_ctrl(struct nvme_ctrl *ctrl);
-int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
 int nvme_try_sched_reset(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 
@@ -675,8 +672,7 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 		kblockd_schedule_work(&head->requeue_work);
 }
 
-static inline void nvme_trace_bio_complete(struct request *req,
-        blk_status_t status)
+static inline void nvme_trace_bio_complete(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
 
@@ -731,8 +727,7 @@ static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 {
 }
-static inline void nvme_trace_bio_complete(struct request *req,
-        blk_status_t status)
+static inline void nvme_trace_bio_complete(struct request *req)
 {
 }
 static inline int nvme_mpath_init(struct nvme_ctrl *ctrl,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index b4385cb0ff60..50d9a20568a2 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -967,6 +967,7 @@ static inline struct blk_mq_tags *nvme_queue_tagset(struct nvme_queue *nvmeq)
 static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 {
 	struct nvme_completion *cqe = &nvmeq->cqes[idx];
+	__u16 command_id = READ_ONCE(cqe->command_id);
 	struct request *req;
 
 	/*
@@ -975,17 +976,17 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
 	 * aborts.  We don't even bother to allocate a struct request
 	 * for them but rather special case them here.
 	 */
-	if (unlikely(nvme_is_aen_req(nvmeq->qid, cqe->command_id))) {
+	if (unlikely(nvme_is_aen_req(nvmeq->qid, command_id))) {
 		nvme_complete_async_event(&nvmeq->dev->ctrl,
 				cqe->status, &cqe->result);
 		return;
 	}
 
-	req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id);
+	req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), command_id);
 	if (unlikely(!req)) {
 		dev_warn(nvmeq->dev->ctrl.device,
 			"invalid id %d completed on queue %d\n",
-			cqe->command_id, le16_to_cpu(cqe->sq_id));
+			command_id, le16_to_cpu(cqe->sq_id));
 		return;
 	}
 
@@ -3196,7 +3197,8 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_DEVICE(0x144d, 0xa821),   /* Samsung PM1725 */
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE(0x144d, 0xa822),   /* Samsung PM1725a */
-		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
+		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x1d1d, 0x1f1f),	/* LighNVM qemu device */
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE(0x1d1d, 0x2807),	/* CNEX WL */
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 1ba659927442..216619926563 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -201,7 +201,7 @@ static inline size_t nvme_tcp_req_cur_offset(struct nvme_tcp_request *req)
 
 static inline size_t nvme_tcp_req_cur_length(struct nvme_tcp_request *req)
 {
-	return min_t(size_t, req->iter.bvec->bv_len - req->iter.iov_offset,
+	return min_t(size_t, iov_iter_single_seg_count(&req->iter),
 			req->pdu_len - req->pdu_sent);
 }
 
@@ -262,6 +262,16 @@ static inline void nvme_tcp_advance_req(struct nvme_tcp_request *req,
 	}
 }
 
+static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue)
+{
+	int ret;
+
+	/* drain the send queue as much as we can... */
+	do {
+		ret = nvme_tcp_try_send(queue);
+	} while (ret > 0);
+}
+
 static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 		bool sync, bool last)
 {
@@ -276,10 +286,10 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 	 * directly, otherwise queue io_work. Also, only do that if we
 	 * are on the same cpu, so we don't introduce contention.
 	 */
-	if (queue->io_cpu == smp_processor_id() &&
+	if (queue->io_cpu == __smp_processor_id() &&
 	    sync && empty && mutex_trylock(&queue->send_mutex)) {
 		queue->more_requests = !last;
-		nvme_tcp_try_send(queue);
+		nvme_tcp_send_all(queue);
 		queue->more_requests = false;
 		mutex_unlock(&queue->send_mutex);
 	} else if (last) {
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index 733d9363900e..68213f0a052b 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -1501,7 +1501,8 @@ static ssize_t
 fcloop_set_cmd_drop(struct device *dev, struct device_attribute *attr,
 		const char *buf, size_t count)
 {
-	int opcode, starting, amount;
+	unsigned int opcode;
+	int starting, amount;
 
 	if (sscanf(buf, "%x:%d:%d", &opcode, &starting, &amount) != 3)
 		return -EBADRQC;
@@ -1588,8 +1589,8 @@ out_destroy_class:
 
 static void __exit fcloop_exit(void)
 {
-	struct fcloop_lport *lport;
-	struct fcloop_nport *nport;
+	struct fcloop_lport *lport = NULL;
+	struct fcloop_nport *nport = NULL;
 	struct fcloop_tport *tport;
 	struct fcloop_rport *rport;
 	unsigned long flags;
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 5c1e7cb7fe0d..06b6b742bb21 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1220,6 +1220,14 @@ nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
 	}
 	ndev->inline_data_size = nport->inline_data_size;
 	ndev->inline_page_count = inline_page_count;
+
+	if (nport->pi_enable && !(cm_id->device->attrs.device_cap_flags &
+				  IB_DEVICE_INTEGRITY_HANDOVER)) {
+		pr_warn("T10-PI is not supported by device %s. Disabling it\n",
+			cm_id->device->name);
+		nport->pi_enable = false;
+	}
+
 	ndev->device = cm_id->device;
 	kref_init(&ndev->ref);
 
@@ -1641,6 +1649,16 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
 	spin_lock_irqsave(&queue->state_lock, flags);
 	switch (queue->state) {
 	case NVMET_RDMA_Q_CONNECTING:
+		while (!list_empty(&queue->rsp_wait_list)) {
+			struct nvmet_rdma_rsp *rsp;
+
+			rsp = list_first_entry(&queue->rsp_wait_list,
+					       struct nvmet_rdma_rsp,
+					       wait_list);
+			list_del(&rsp->wait_list);
+			nvmet_rdma_put_rsp(rsp);
+		}
+		fallthrough;
 	case NVMET_RDMA_Q_LIVE:
 		queue->state = NVMET_RDMA_Q_DISCONNECTING;
 		disconnect = true;
@@ -1845,14 +1863,6 @@ static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port)
 		goto out_destroy_id;
 	}
 
-	if (port->nport->pi_enable &&
-	    !(cm_id->device->attrs.device_cap_flags &
-	      IB_DEVICE_INTEGRITY_HANDOVER)) {
-		pr_err("T10-PI is not supported for %pISpcs\n", addr);
-		ret = -EINVAL;
-		goto out_destroy_id;
-	}
-
 	port->cm_id = cm_id;
 	return 0;
 
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 4268eb359915..8c905aabacc0 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -1092,7 +1092,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index)
 	if (IS_ERR(opp_table->clk)) {
 		ret = PTR_ERR(opp_table->clk);
 		if (ret == -EPROBE_DEFER)
-			goto err;
+			goto remove_opp_dev;
 
 		dev_dbg(dev, "%s: Couldn't find clock: %d\n", __func__, ret);
 	}
@@ -1101,7 +1101,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index)
 	ret = dev_pm_opp_of_find_icc_paths(dev, opp_table);
 	if (ret) {
 		if (ret == -EPROBE_DEFER)
-			goto err;
+			goto put_clk;
 
 		dev_warn(dev, "%s: Error finding interconnect paths: %d\n",
 			 __func__, ret);
@@ -1113,6 +1113,11 @@ static struct opp_table *_allocate_opp_table(struct device *dev, int index)
 
 	return opp_table;
 
+put_clk:
+	if (!IS_ERR(opp_table->clk))
+		clk_put(opp_table->clk);
+remove_opp_dev:
+	_remove_opp_dev(opp_dev, opp_table);
 err:
 	kfree(opp_table);
 	return ERR_PTR(ret);
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 516b151e0ef3..8a84c005f32b 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -397,12 +397,8 @@ int dw_pcie_host_init(struct pcie_port *pp)
 							    pp);
 
 			ret = dma_set_mask(pci->dev, DMA_BIT_MASK(32));
-			if (!ret) {
-				dev_warn(pci->dev,
-					 "Failed to set DMA mask to 32-bit. "
-					 "Devices with only 32-bit MSI support"
-					 " may not work properly\n");
-			}
+			if (ret)
+				dev_warn(pci->dev, "Failed to set DMA mask to 32-bit. Devices with only 32-bit MSI support may not work properly\n");
 
 			pp->msi_data = dma_map_single_attrs(pci->dev, &pp->msi_msg,
 						      sizeof(pp->msi_msg),
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index 5597b2a49598..6fa216e52d14 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -853,12 +853,14 @@ static void config_gen3_gen4_eq_presets(struct tegra_pcie_dw *pcie)
 	dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val);
 }
 
-static void tegra_pcie_prepare_host(struct pcie_port *pp)
+static int tegra_pcie_dw_host_init(struct pcie_port *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 	u32 val;
 
+	pp->bridge->ops = &tegra_pci_ops;
+
 	if (!pcie->pcie_cap_base)
 		pcie->pcie_cap_base = dw_pcie_find_capability(&pcie->pci,
 							      PCI_CAP_ID_EXP);
@@ -907,10 +909,24 @@ static void tegra_pcie_prepare_host(struct pcie_port *pp)
 		dw_pcie_writel_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF, val);
 	}
 
-	dw_pcie_setup_rc(pp);
-
 	clk_set_rate(pcie->core_clk, GEN4_CORE_CLK_FREQ);
 
+	return 0;
+}
+
+static int tegra_pcie_dw_start_link(struct dw_pcie *pci)
+{
+	u32 val, offset, speed, tmp;
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+	struct pcie_port *pp = &pci->pp;
+	bool retry = true;
+
+	if (pcie->mode == DW_PCIE_EP_TYPE) {
+		enable_irq(pcie->pex_rst_irq);
+		return 0;
+	}
+
+retry_link:
 	/* Assert RST */
 	val = appl_readl(pcie, APPL_PINMUX);
 	val &= ~APPL_PINMUX_PEX_RST;
@@ -929,19 +945,10 @@ static void tegra_pcie_prepare_host(struct pcie_port *pp)
 	appl_writel(pcie, val, APPL_PINMUX);
 
 	msleep(100);
-}
-
-static int tegra_pcie_dw_host_init(struct pcie_port *pp)
-{
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
-	u32 val, tmp, offset, speed;
-
-	pp->bridge->ops = &tegra_pci_ops;
-
-	tegra_pcie_prepare_host(pp);
 
 	if (dw_pcie_wait_for_link(pci)) {
+		if (!retry)
+			return 0;
 		/*
 		 * There are some endpoints which can't get the link up if
 		 * root port has Data Link Feature (DLF) enabled.
@@ -975,10 +982,11 @@ static int tegra_pcie_dw_host_init(struct pcie_port *pp)
 		val &= ~PCI_DLF_EXCHANGE_ENABLE;
 		dw_pcie_writel_dbi(pci, offset, val);
 
-		tegra_pcie_prepare_host(pp);
+		tegra_pcie_dw_host_init(pp);
+		dw_pcie_setup_rc(pp);
 
-		if (dw_pcie_wait_for_link(pci))
-			return 0;
+		retry = false;
+		goto retry_link;
 	}
 
 	speed = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA) &
@@ -998,15 +1006,6 @@ static int tegra_pcie_dw_link_up(struct dw_pcie *pci)
 	return !!(val & PCI_EXP_LNKSTA_DLLLA);
 }
 
-static int tegra_pcie_dw_start_link(struct dw_pcie *pci)
-{
-	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
-
-	enable_irq(pcie->pex_rst_irq);
-
-	return 0;
-}
-
 static void tegra_pcie_dw_stop_link(struct dw_pcie *pci)
 {
 	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
@@ -2215,6 +2214,10 @@ static int tegra_pcie_dw_resume_noirq(struct device *dev)
 		goto fail_host_init;
 	}
 
+	ret = tegra_pcie_dw_start_link(&pcie->pci);
+	if (ret < 0)
+		goto fail_host_init;
+
 	/* Restore MSI interrupt vector */
 	dw_pcie_writel_dbi(&pcie->pci, PORT_LOGIC_MSI_CTRL_INT_0_EN,
 			   pcie->msi_ctrl_int);
diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c
index a2632d02ce8f..c637de3a389b 100644
--- a/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c
+++ b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c
@@ -306,13 +306,11 @@ int mobiveil_host_init(struct mobiveil_pcie *pcie, bool reinit)
 
 static void mobiveil_mask_intx_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(data->irq);
-	struct mobiveil_pcie *pcie;
+	struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(data);
 	struct mobiveil_root_port *rp;
 	unsigned long flags;
 	u32 mask, shifted_val;
 
-	pcie = irq_desc_get_chip_data(desc);
 	rp = &pcie->rp;
 	mask = 1 << ((data->hwirq + PAB_INTX_START) - 1);
 	raw_spin_lock_irqsave(&rp->intx_mask_lock, flags);
@@ -324,13 +322,11 @@ static void mobiveil_mask_intx_irq(struct irq_data *data)
 
 static void mobiveil_unmask_intx_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(data->irq);
-	struct mobiveil_pcie *pcie;
+	struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(data);
 	struct mobiveil_root_port *rp;
 	unsigned long flags;
 	u32 shifted_val, mask;
 
-	pcie = irq_desc_get_chip_data(desc);
 	rp = &pcie->rp;
 	mask = 1 << ((data->hwirq + PAB_INTX_START) - 1);
 	raw_spin_lock_irqsave(&rp->intx_mask_lock, flags);
diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
index 7f29c2fdcd51..07e36661bbc2 100644
--- a/drivers/pci/controller/pcie-xilinx-nwl.c
+++ b/drivers/pci/controller/pcie-xilinx-nwl.c
@@ -374,13 +374,11 @@ static void nwl_pcie_msi_handler_low(struct irq_desc *desc)
 
 static void nwl_mask_leg_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(data->irq);
-	struct nwl_pcie *pcie;
+	struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data);
 	unsigned long flags;
 	u32 mask;
 	u32 val;
 
-	pcie = irq_desc_get_chip_data(desc);
 	mask = 1 << (data->hwirq - 1);
 	raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags);
 	val = nwl_bridge_readl(pcie, MSGF_LEG_MASK);
@@ -390,13 +388,11 @@ static void nwl_mask_leg_irq(struct irq_data *data)
 
 static void nwl_unmask_leg_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(data->irq);
-	struct nwl_pcie *pcie;
+	struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data);
 	unsigned long flags;
 	u32 mask;
 	u32 val;
 
-	pcie = irq_desc_get_chip_data(desc);
 	mask = 1 << (data->hwirq - 1);
 	raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags);
 	val = nwl_bridge_readl(pcie, MSGF_LEG_MASK);
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 794a37d50853..cb2f55f450e4 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -726,11 +726,6 @@ static int armpmu_get_cpu_irq(struct arm_pmu *pmu, int cpu)
 	return per_cpu(hw_events->irq, cpu);
 }
 
-bool arm_pmu_irq_is_nmi(void)
-{
-	return has_nmi;
-}
-
 /*
  * PMU hardware loses all context when a CPU goes offline.
  * When a CPU is hotplugged back in, since some hardware registers are
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index 657e35a75d84..d4ea10803fd9 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -948,8 +948,8 @@ static void nmk_gpio_dbg_show_one(struct seq_file *s,
 			   (mode < 0) ? "unknown" : modes[mode]);
 	} else {
 		int irq = chip->to_irq(chip, offset);
-		struct irq_desc	*desc = irq_to_desc(irq);
 		const int pullidx = pull ? 1 : 0;
+		bool wake;
 		int val;
 		static const char * const pulls[] = {
 			"none        ",
@@ -969,8 +969,9 @@ static void nmk_gpio_dbg_show_one(struct seq_file *s,
 		 * This races with request_irq(), set_irq_type(),
 		 * and set_irq_wake() ... but those are "rare".
 		 */
-		if (irq > 0 && desc && desc->action) {
+		if (irq > 0 && irq_has_action(irq)) {
 			char *trigger;
+			bool wake;
 
 			if (nmk_chip->edge_rising & BIT(offset))
 				trigger = "edge-rising";
@@ -979,10 +980,10 @@ static void nmk_gpio_dbg_show_one(struct seq_file *s,
 			else
 				trigger = "edge-undefined";
 
+			wake = !!(nmk_chip->real_wake & BIT(offset));
+
 			seq_printf(s, " irq-%d %s%s",
-				   irq, trigger,
-				   irqd_is_wakeup_set(&desc->irq_data)
-				   ? " wakeup" : "");
+				   irq, trigger, wake ? " wakeup" : "");
 		}
 	}
 	clk_disable(nmk_chip->clk);
diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index 0ecee8b8773d..7c92a6e22d75 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -742,12 +742,16 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev,
 		 * Sensor events need to be parsed by the sensor sub-device.
 		 * Defer them, and don't report the wakeup here.
 		 */
-		if (event_type == EC_MKBP_EVENT_SENSOR_FIFO)
-			*wake_event = false;
-		/* Masked host-events should not count as wake events. */
-		else if (host_event &&
-			 !(host_event & ec_dev->host_event_wake_mask))
+		if (event_type == EC_MKBP_EVENT_SENSOR_FIFO) {
 			*wake_event = false;
+		} else if (host_event) {
+			/* rtc_update_irq() already handles wakeup events. */
+			if (host_event & EC_HOST_EVENT_MASK(EC_HOST_EVENT_RTC))
+				*wake_event = false;
+			/* Masked host-events should not count as wake events. */
+			if (!(host_event & ec_dev->host_event_wake_mask))
+				*wake_event = false;
+		}
 	}
 
 	return ret;
diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c
index 8111ed1fc574..c43868615790 100644
--- a/drivers/platform/chrome/cros_ec_typec.c
+++ b/drivers/platform/chrome/cros_ec_typec.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/list.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_data/cros_ec_commands.h>
@@ -14,6 +15,7 @@
 #include <linux/platform_data/cros_usbpd_notify.h>
 #include <linux/platform_device.h>
 #include <linux/usb/pd.h>
+#include <linux/usb/pd_vdo.h>
 #include <linux/usb/typec.h>
 #include <linux/usb/typec_altmode.h>
 #include <linux/usb/typec_dp.h>
@@ -30,6 +32,12 @@ enum {
 	CROS_EC_ALTMODE_MAX,
 };
 
+/* Container for altmode pointer nodes. */
+struct cros_typec_altmode_node {
+	struct typec_altmode *amode;
+	struct list_head list;
+};
+
 /* Per port data. */
 struct cros_typec_port {
 	struct typec_port *port;
@@ -48,6 +56,11 @@ struct cros_typec_port {
 
 	/* Port alt modes. */
 	struct typec_altmode p_altmode[CROS_EC_ALTMODE_MAX];
+
+	/* Flag indicating that PD discovery data parsing is completed. */
+	bool disc_done;
+	struct ec_response_typec_discovery *sop_disc;
+	struct list_head partner_mode_list;
 };
 
 /* Platform-specific data for the Chrome OS EC Type C controller. */
@@ -60,6 +73,7 @@ struct cros_typec_data {
 	struct cros_typec_port *ports[EC_USB_PD_MAX_PORTS];
 	struct notifier_block nb;
 	struct work_struct port_work;
+	bool typec_cmd_supported;
 };
 
 static int cros_typec_parse_port_props(struct typec_capability *cap,
@@ -166,11 +180,25 @@ static int cros_typec_add_partner(struct cros_typec_data *typec, int port_num,
 	return ret;
 }
 
+static void cros_typec_unregister_altmodes(struct cros_typec_data *typec, int port_num)
+{
+	struct cros_typec_port *port = typec->ports[port_num];
+	struct cros_typec_altmode_node *node, *tmp;
+
+	list_for_each_entry_safe(node, tmp, &port->partner_mode_list, list) {
+		list_del(&node->list);
+		typec_unregister_altmode(node->amode);
+		devm_kfree(typec->dev, node);
+	}
+}
+
 static void cros_typec_remove_partner(struct cros_typec_data *typec,
 				     int port_num)
 {
 	struct cros_typec_port *port = typec->ports[port_num];
 
+	cros_typec_unregister_altmodes(typec, port_num);
+
 	port->state.alt = NULL;
 	port->state.mode = TYPEC_STATE_USB;
 	port->state.data = NULL;
@@ -181,6 +209,8 @@ static void cros_typec_remove_partner(struct cros_typec_data *typec,
 
 	typec_unregister_partner(port->partner);
 	port->partner = NULL;
+	memset(&port->p_identity, 0, sizeof(port->p_identity));
+	port->disc_done = false;
 }
 
 static void cros_unregister_ports(struct cros_typec_data *typec)
@@ -190,7 +220,10 @@ static void cros_unregister_ports(struct cros_typec_data *typec)
 	for (i = 0; i < typec->num_ports; i++) {
 		if (!typec->ports[i])
 			continue;
-		cros_typec_remove_partner(typec, i);
+
+		if (typec->ports[i]->partner)
+			cros_typec_remove_partner(typec, i);
+
 		usb_role_switch_put(typec->ports[i]->role_sw);
 		typec_switch_put(typec->ports[i]->ori_sw);
 		typec_mux_put(typec->ports[i]->mux);
@@ -289,6 +322,14 @@ static int cros_typec_init_ports(struct cros_typec_data *typec)
 				port_num);
 
 		cros_typec_register_port_altmodes(typec, port_num);
+
+		cros_port->sop_disc = devm_kzalloc(dev, EC_PROTO2_MAX_RESPONSE_SIZE, GFP_KERNEL);
+		if (!cros_port->sop_disc) {
+			ret = -ENOMEM;
+			goto unregister_ports;
+		}
+
+		INIT_LIST_HEAD(&cros_port->partner_mode_list);
 	}
 
 	return 0;
@@ -329,74 +370,6 @@ static int cros_typec_ec_command(struct cros_typec_data *typec,
 	return ret;
 }
 
-static void cros_typec_set_port_params_v0(struct cros_typec_data *typec,
-		int port_num, struct ec_response_usb_pd_control *resp)
-{
-	struct typec_port *port = typec->ports[port_num]->port;
-	enum typec_orientation polarity;
-
-	if (!resp->enabled)
-		polarity = TYPEC_ORIENTATION_NONE;
-	else if (!resp->polarity)
-		polarity = TYPEC_ORIENTATION_NORMAL;
-	else
-		polarity = TYPEC_ORIENTATION_REVERSE;
-
-	typec_set_pwr_role(port, resp->role ? TYPEC_SOURCE : TYPEC_SINK);
-	typec_set_orientation(port, polarity);
-}
-
-static void cros_typec_set_port_params_v1(struct cros_typec_data *typec,
-		int port_num, struct ec_response_usb_pd_control_v1 *resp)
-{
-	struct typec_port *port = typec->ports[port_num]->port;
-	enum typec_orientation polarity;
-	bool pd_en;
-	int ret;
-
-	if (!(resp->enabled & PD_CTRL_RESP_ENABLED_CONNECTED))
-		polarity = TYPEC_ORIENTATION_NONE;
-	else if (!resp->polarity)
-		polarity = TYPEC_ORIENTATION_NORMAL;
-	else
-		polarity = TYPEC_ORIENTATION_REVERSE;
-	typec_set_orientation(port, polarity);
-	typec_set_data_role(port, resp->role & PD_CTRL_RESP_ROLE_DATA ?
-			TYPEC_HOST : TYPEC_DEVICE);
-	typec_set_pwr_role(port, resp->role & PD_CTRL_RESP_ROLE_POWER ?
-			TYPEC_SOURCE : TYPEC_SINK);
-	typec_set_vconn_role(port, resp->role & PD_CTRL_RESP_ROLE_VCONN ?
-			TYPEC_SOURCE : TYPEC_SINK);
-
-	/* Register/remove partners when a connect/disconnect occurs. */
-	if (resp->enabled & PD_CTRL_RESP_ENABLED_CONNECTED) {
-		if (typec->ports[port_num]->partner)
-			return;
-
-		pd_en = resp->enabled & PD_CTRL_RESP_ENABLED_PD_CAPABLE;
-		ret = cros_typec_add_partner(typec, port_num, pd_en);
-		if (ret)
-			dev_warn(typec->dev,
-				 "Failed to register partner on port: %d\n",
-				 port_num);
-	} else {
-		if (!typec->ports[port_num]->partner)
-			return;
-		cros_typec_remove_partner(typec, port_num);
-	}
-}
-
-static int cros_typec_get_mux_info(struct cros_typec_data *typec, int port_num,
-				   struct ec_response_usb_pd_mux_info *resp)
-{
-	struct ec_params_usb_pd_mux_info req = {
-		.port = port_num,
-	};
-
-	return cros_typec_ec_command(typec, 0, EC_CMD_USB_PD_MUX_INFO, &req,
-				     sizeof(req), resp, sizeof(*resp));
-}
-
 static int cros_typec_usb_safe_state(struct cros_typec_port *port)
 {
 	port->state.mode = TYPEC_STATE_SAFE;
@@ -563,15 +536,210 @@ static int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num,
 		port->state.mode = TYPEC_STATE_USB;
 		ret = typec_mux_set(port->mux, &port->state);
 	} else {
-		dev_info(typec->dev,
-			 "Unsupported mode requested, mux flags: %x\n",
-			 mux_flags);
-		ret = -ENOTSUPP;
+		dev_dbg(typec->dev,
+			"Unrecognized mode requested, mux flags: %x\n",
+			mux_flags);
+	}
+
+	return ret;
+}
+
+static void cros_typec_set_port_params_v0(struct cros_typec_data *typec,
+		int port_num, struct ec_response_usb_pd_control *resp)
+{
+	struct typec_port *port = typec->ports[port_num]->port;
+	enum typec_orientation polarity;
+
+	if (!resp->enabled)
+		polarity = TYPEC_ORIENTATION_NONE;
+	else if (!resp->polarity)
+		polarity = TYPEC_ORIENTATION_NORMAL;
+	else
+		polarity = TYPEC_ORIENTATION_REVERSE;
+
+	typec_set_pwr_role(port, resp->role ? TYPEC_SOURCE : TYPEC_SINK);
+	typec_set_orientation(port, polarity);
+}
+
+static void cros_typec_set_port_params_v1(struct cros_typec_data *typec,
+		int port_num, struct ec_response_usb_pd_control_v1 *resp)
+{
+	struct typec_port *port = typec->ports[port_num]->port;
+	enum typec_orientation polarity;
+	bool pd_en;
+	int ret;
+
+	if (!(resp->enabled & PD_CTRL_RESP_ENABLED_CONNECTED))
+		polarity = TYPEC_ORIENTATION_NONE;
+	else if (!resp->polarity)
+		polarity = TYPEC_ORIENTATION_NORMAL;
+	else
+		polarity = TYPEC_ORIENTATION_REVERSE;
+	typec_set_orientation(port, polarity);
+	typec_set_data_role(port, resp->role & PD_CTRL_RESP_ROLE_DATA ?
+			TYPEC_HOST : TYPEC_DEVICE);
+	typec_set_pwr_role(port, resp->role & PD_CTRL_RESP_ROLE_POWER ?
+			TYPEC_SOURCE : TYPEC_SINK);
+	typec_set_vconn_role(port, resp->role & PD_CTRL_RESP_ROLE_VCONN ?
+			TYPEC_SOURCE : TYPEC_SINK);
+
+	/* Register/remove partners when a connect/disconnect occurs. */
+	if (resp->enabled & PD_CTRL_RESP_ENABLED_CONNECTED) {
+		if (typec->ports[port_num]->partner)
+			return;
+
+		pd_en = resp->enabled & PD_CTRL_RESP_ENABLED_PD_CAPABLE;
+		ret = cros_typec_add_partner(typec, port_num, pd_en);
+		if (ret)
+			dev_warn(typec->dev,
+				 "Failed to register partner on port: %d\n",
+				 port_num);
+	} else {
+		if (!typec->ports[port_num]->partner)
+			return;
+		cros_typec_remove_partner(typec, port_num);
 	}
+}
+
+static int cros_typec_get_mux_info(struct cros_typec_data *typec, int port_num,
+				   struct ec_response_usb_pd_mux_info *resp)
+{
+	struct ec_params_usb_pd_mux_info req = {
+		.port = port_num,
+	};
+
+	return cros_typec_ec_command(typec, 0, EC_CMD_USB_PD_MUX_INFO, &req,
+				     sizeof(req), resp, sizeof(*resp));
+}
+
+static int cros_typec_register_altmodes(struct cros_typec_data *typec, int port_num)
+{
+	struct cros_typec_port *port = typec->ports[port_num];
+	struct ec_response_typec_discovery *sop_disc = port->sop_disc;
+	struct cros_typec_altmode_node *node;
+	struct typec_altmode_desc desc;
+	struct typec_altmode *amode;
+	int ret = 0;
+	int i, j;
+
+	for (i = 0; i < sop_disc->svid_count; i++) {
+		for (j = 0; j < sop_disc->svids[i].mode_count; j++) {
+			memset(&desc, 0, sizeof(desc));
+			desc.svid = sop_disc->svids[i].svid;
+			desc.mode = j;
+			desc.vdo = sop_disc->svids[i].mode_vdo[j];
+
+			amode = typec_partner_register_altmode(port->partner, &desc);
+			if (IS_ERR(amode)) {
+				ret = PTR_ERR(amode);
+				goto err_cleanup;
+			}
+
+			/* If no memory is available we should unregister and exit. */
+			node = devm_kzalloc(typec->dev, sizeof(*node), GFP_KERNEL);
+			if (!node) {
+				ret = -ENOMEM;
+				typec_unregister_altmode(amode);
+				goto err_cleanup;
+			}
+
+			node->amode = amode;
+			list_add_tail(&node->list, &port->partner_mode_list);
+		}
+	}
+
+	return 0;
 
+err_cleanup:
+	cros_typec_unregister_altmodes(typec, port_num);
 	return ret;
 }
 
+static int cros_typec_handle_sop_disc(struct cros_typec_data *typec, int port_num)
+{
+	struct cros_typec_port *port = typec->ports[port_num];
+	struct ec_response_typec_discovery *sop_disc = port->sop_disc;
+	struct ec_params_typec_discovery req = {
+		.port = port_num,
+		.partner_type = TYPEC_PARTNER_SOP,
+	};
+	int ret = 0;
+	int i;
+
+	if (!port->partner) {
+		dev_err(typec->dev,
+			"SOP Discovery received without partner registered, port: %d\n",
+			port_num);
+		ret = -EINVAL;
+		goto disc_exit;
+	}
+
+	memset(sop_disc, 0, EC_PROTO2_MAX_RESPONSE_SIZE);
+	ret = cros_typec_ec_command(typec, 0, EC_CMD_TYPEC_DISCOVERY, &req, sizeof(req),
+				    sop_disc, EC_PROTO2_MAX_RESPONSE_SIZE);
+	if (ret < 0) {
+		dev_err(typec->dev, "Failed to get SOP discovery data for port: %d\n", port_num);
+		goto disc_exit;
+	}
+
+	/* First, update the PD identity VDOs for the partner. */
+	if (sop_disc->identity_count > 0)
+		port->p_identity.id_header = sop_disc->discovery_vdo[0];
+	if (sop_disc->identity_count > 1)
+		port->p_identity.cert_stat = sop_disc->discovery_vdo[1];
+	if (sop_disc->identity_count > 2)
+		port->p_identity.product = sop_disc->discovery_vdo[2];
+
+	/* Copy the remaining identity VDOs till a maximum of 6. */
+	for (i = 3; i < sop_disc->identity_count && i < VDO_MAX_OBJECTS; i++)
+		port->p_identity.vdo[i - 3] = sop_disc->discovery_vdo[i];
+
+	ret = typec_partner_set_identity(port->partner);
+	if (ret < 0) {
+		dev_err(typec->dev, "Failed to update partner PD identity, port: %d\n", port_num);
+		goto disc_exit;
+	}
+
+	ret = cros_typec_register_altmodes(typec, port_num);
+	if (ret < 0) {
+		dev_err(typec->dev, "Failed to register partner altmodes, port: %d\n", port_num);
+		goto disc_exit;
+	}
+
+disc_exit:
+	return ret;
+}
+
+static void cros_typec_handle_status(struct cros_typec_data *typec, int port_num)
+{
+	struct ec_response_typec_status resp;
+	struct ec_params_typec_status req = {
+		.port = port_num,
+	};
+	int ret;
+
+	ret = cros_typec_ec_command(typec, 0, EC_CMD_TYPEC_STATUS, &req, sizeof(req),
+				    &resp, sizeof(resp));
+	if (ret < 0) {
+		dev_warn(typec->dev, "EC_CMD_TYPEC_STATUS failed for port: %d\n", port_num);
+		return;
+	}
+
+	if (typec->ports[port_num]->disc_done)
+		return;
+
+	/* Handle any events appropriately. */
+	if (resp.events & PD_STATUS_EVENT_SOP_DISC_DONE) {
+		ret = cros_typec_handle_sop_disc(typec, port_num);
+		if (ret < 0) {
+			dev_err(typec->dev, "Couldn't parse SOP Disc data, port: %d\n", port_num);
+			return;
+		}
+
+		typec->ports[port_num]->disc_done = true;
+	}
+}
+
 static int cros_typec_port_update(struct cros_typec_data *typec, int port_num)
 {
 	struct ec_params_usb_pd_control req;
@@ -608,6 +776,9 @@ static int cros_typec_port_update(struct cros_typec_data *typec, int port_num)
 		cros_typec_set_port_params_v0(typec, port_num,
 			(struct ec_response_usb_pd_control *) &resp);
 
+	if (typec->typec_cmd_supported)
+		cros_typec_handle_status(typec, port_num);
+
 	/* Update the switches if they exist, according to requested state */
 	ret = cros_typec_get_mux_info(typec, port_num, &mux_resp);
 	if (ret < 0) {
@@ -656,6 +827,23 @@ static int cros_typec_get_cmd_version(struct cros_typec_data *typec)
 	return 0;
 }
 
+/* Check the EC feature flags to see if TYPEC_* commands are supported. */
+static int cros_typec_cmds_supported(struct cros_typec_data *typec)
+{
+	struct ec_response_get_features resp = {};
+	int ret;
+
+	ret = cros_typec_ec_command(typec, 0, EC_CMD_GET_FEATURES, NULL, 0,
+				    &resp, sizeof(resp));
+	if (ret < 0) {
+		dev_warn(typec->dev,
+			 "Failed to get features, assuming typec commands unsupported.\n");
+		return 0;
+	}
+
+	return resp.flags[EC_FEATURE_TYPEC_CMD / 32] & EC_FEATURE_MASK_1(EC_FEATURE_TYPEC_CMD);
+}
+
 static void cros_typec_port_work(struct work_struct *work)
 {
 	struct cros_typec_data *typec = container_of(work, struct cros_typec_data, port_work);
@@ -715,6 +903,8 @@ static int cros_typec_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	typec->typec_cmd_supported = !!cros_typec_cmds_supported(typec);
+
 	ret = cros_typec_ec_command(typec, 0, EC_CMD_USB_PD_PORTS, NULL, 0,
 				    &resp, sizeof(resp));
 	if (ret < 0)
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 476d7c7fe70a..f2edef0df40f 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -64,6 +64,7 @@ config DP83640_PHY
 	depends on NETWORK_PHY_TIMESTAMPING
 	depends on PHYLIB
 	depends on PTP_1588_CLOCK
+	select CRC32
 	help
 	  Supports the DP83640 PHYTER with IEEE 1588 features.
 
@@ -78,6 +79,7 @@ config DP83640_PHY
 config PTP_1588_CLOCK_INES
 	tristate "ZHAW InES PTP time stamping IP core"
 	depends on NETWORK_PHY_TIMESTAMPING
+	depends on HAS_IOMEM
 	depends on PHYLIB
 	depends on PTP_1588_CLOCK
 	help
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 53fa84f4d1e1..5abdd29fb9f3 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -881,6 +881,7 @@ config REGULATOR_QCOM_RPM
 config REGULATOR_QCOM_RPMH
 	tristate "Qualcomm Technologies, Inc. RPMh regulator driver"
 	depends on QCOM_RPMH || (QCOM_RPMH=n && COMPILE_TEST)
+	depends on QCOM_COMMAND_DB || (QCOM_COMMAND_DB=n && COMPILE_TEST)
 	help
 	  This driver supports control of PMIC regulators via the RPMh hardware
 	  block found on Qualcomm Technologies Inc. SoCs.  RPMh regulator
diff --git a/drivers/regulator/bd718x7-regulator.c b/drivers/regulator/bd718x7-regulator.c
index e6d5d98c3cea..9309765d0450 100644
--- a/drivers/regulator/bd718x7-regulator.c
+++ b/drivers/regulator/bd718x7-regulator.c
@@ -15,6 +15,36 @@
 #include <linux/regulator/of_regulator.h>
 #include <linux/slab.h>
 
+/* Typical regulator startup times as per data sheet in uS */
+#define BD71847_BUCK1_STARTUP_TIME 144
+#define BD71847_BUCK2_STARTUP_TIME 162
+#define BD71847_BUCK3_STARTUP_TIME 162
+#define BD71847_BUCK4_STARTUP_TIME 240
+#define BD71847_BUCK5_STARTUP_TIME 270
+#define BD71847_BUCK6_STARTUP_TIME 200
+#define BD71847_LDO1_STARTUP_TIME  440
+#define BD71847_LDO2_STARTUP_TIME  370
+#define BD71847_LDO3_STARTUP_TIME  310
+#define BD71847_LDO4_STARTUP_TIME  400
+#define BD71847_LDO5_STARTUP_TIME  530
+#define BD71847_LDO6_STARTUP_TIME  400
+
+#define BD71837_BUCK1_STARTUP_TIME 160
+#define BD71837_BUCK2_STARTUP_TIME 180
+#define BD71837_BUCK3_STARTUP_TIME 180
+#define BD71837_BUCK4_STARTUP_TIME 180
+#define BD71837_BUCK5_STARTUP_TIME 160
+#define BD71837_BUCK6_STARTUP_TIME 240
+#define BD71837_BUCK7_STARTUP_TIME 220
+#define BD71837_BUCK8_STARTUP_TIME 200
+#define BD71837_LDO1_STARTUP_TIME  440
+#define BD71837_LDO2_STARTUP_TIME  370
+#define BD71837_LDO3_STARTUP_TIME  310
+#define BD71837_LDO4_STARTUP_TIME  400
+#define BD71837_LDO5_STARTUP_TIME  310
+#define BD71837_LDO6_STARTUP_TIME  400
+#define BD71837_LDO7_STARTUP_TIME  530
+
 /*
  * BD718(37/47/50) have two "enable control modes". ON/OFF can either be
  * controlled by software - or by PMIC internal HW state machine. Whether
@@ -613,6 +643,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD718XX_REG_BUCK1_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK1_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -646,6 +677,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD718XX_REG_BUCK2_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK2_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -680,6 +712,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.linear_range_selectors = bd71847_buck3_volt_range_sel,
 			.enable_reg = BD718XX_REG_1ST_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK3_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -706,6 +739,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.vsel_range_mask = BD71847_BUCK4_RANGE_MASK,
 			.linear_range_selectors = bd71847_buck4_volt_range_sel,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK4_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -727,6 +761,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.vsel_mask = BD718XX_3RD_NODVS_BUCK_MASK,
 			.enable_reg = BD718XX_REG_3RD_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK5_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -750,6 +785,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.vsel_mask = BD718XX_4TH_NODVS_BUCK_MASK,
 			.enable_reg = BD718XX_REG_4TH_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK6_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -775,6 +811,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.linear_range_selectors = bd718xx_ldo1_volt_range_sel,
 			.enable_reg = BD718XX_REG_LDO1_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO1_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -796,6 +833,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.n_voltages = ARRAY_SIZE(ldo_2_volts),
 			.enable_reg = BD718XX_REG_LDO2_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO2_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -818,6 +856,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.vsel_mask = BD718XX_LDO3_MASK,
 			.enable_reg = BD718XX_REG_LDO3_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO3_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -840,6 +879,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.vsel_mask = BD718XX_LDO4_MASK,
 			.enable_reg = BD718XX_REG_LDO4_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO4_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -865,6 +905,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.linear_range_selectors = bd71847_ldo5_volt_range_sel,
 			.enable_reg = BD718XX_REG_LDO5_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO5_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -889,6 +930,7 @@ static struct bd718xx_regulator_data bd71847_regulators[] = {
 			.vsel_mask = BD718XX_LDO6_MASK,
 			.enable_reg = BD718XX_REG_LDO6_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO6_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -942,6 +984,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD718XX_REG_BUCK1_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK1_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -975,6 +1018,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD718XX_REG_BUCK2_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK2_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -1005,6 +1049,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD71837_REG_BUCK3_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK3_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -1033,6 +1078,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD71837_REG_BUCK4_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK4_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -1065,6 +1111,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.linear_range_selectors = bd71837_buck5_volt_range_sel,
 			.enable_reg = BD718XX_REG_1ST_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK5_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1088,6 +1135,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = BD71837_BUCK6_MASK,
 			.enable_reg = BD718XX_REG_2ND_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK6_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1109,6 +1157,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = BD718XX_3RD_NODVS_BUCK_MASK,
 			.enable_reg = BD718XX_REG_3RD_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK7_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1132,6 +1181,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = BD718XX_4TH_NODVS_BUCK_MASK,
 			.enable_reg = BD718XX_REG_4TH_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK8_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1157,6 +1207,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.linear_range_selectors = bd718xx_ldo1_volt_range_sel,
 			.enable_reg = BD718XX_REG_LDO1_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO1_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1178,6 +1229,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.n_voltages = ARRAY_SIZE(ldo_2_volts),
 			.enable_reg = BD718XX_REG_LDO2_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO2_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1200,6 +1252,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = BD718XX_LDO3_MASK,
 			.enable_reg = BD718XX_REG_LDO3_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO3_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1222,6 +1275,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = BD718XX_LDO4_MASK,
 			.enable_reg = BD718XX_REG_LDO4_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO4_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1246,6 +1300,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = BD71837_LDO5_MASK,
 			.enable_reg = BD718XX_REG_LDO5_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO5_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1272,6 +1327,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = BD718XX_LDO6_MASK,
 			.enable_reg = BD718XX_REG_LDO6_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO6_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1296,6 +1352,7 @@ static struct bd718xx_regulator_data bd71837_regulators[] = {
 			.vsel_mask = BD71837_LDO7_MASK,
 			.enable_reg = BD71837_REG_LDO7_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO7_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
diff --git a/drivers/regulator/pf8x00-regulator.c b/drivers/regulator/pf8x00-regulator.c
index 308c27fa6ea8..af9918cd27aa 100644
--- a/drivers/regulator/pf8x00-regulator.c
+++ b/drivers/regulator/pf8x00-regulator.c
@@ -469,13 +469,17 @@ static int pf8x00_i2c_probe(struct i2c_client *client)
 }
 
 static const struct of_device_id pf8x00_dt_ids[] = {
-	{ .compatible = "nxp,pf8x00",},
+	{ .compatible = "nxp,pf8100",},
+	{ .compatible = "nxp,pf8121a",},
+	{ .compatible = "nxp,pf8200",},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, pf8x00_dt_ids);
 
 static const struct i2c_device_id pf8x00_i2c_id[] = {
-	{ "pf8x00", 0 },
+	{ "pf8100", 0 },
+	{ "pf8121a", 0 },
+	{ "pf8200", 0 },
 	{},
 };
 MODULE_DEVICE_TABLE(i2c, pf8x00_i2c_id);
diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
index fe030ec4b7db..c395a8dda6f7 100644
--- a/drivers/regulator/qcom-rpmh-regulator.c
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -726,7 +726,7 @@ static const struct rpmh_vreg_hw_data pmic5_ftsmps510 = {
 static const struct rpmh_vreg_hw_data pmic5_hfsmps515 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(2800000, 0, 4, 1600),
+	.voltage_range = REGULATOR_LINEAR_RANGE(2800000, 0, 4, 16000),
 	.n_voltages = 5,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 65ad9d0b47ab..6123f9f4fbc9 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -13,7 +13,7 @@ config RTC_MC146818_LIB
 menuconfig RTC_CLASS
 	bool "Real Time Clock"
 	default n
-	depends on !S390 && !UML
+	depends on !S390
 	select RTC_LIB
 	help
 	  Generic RTC class support. If you say yes here, you will
@@ -817,15 +817,6 @@ config RTC_DRV_RX4581
 	  This driver can also be built as a module. If so the module
 	  will be called rtc-rx4581.
 
-config RTC_DRV_RX6110
-	tristate "Epson RX-6110"
-	select REGMAP_SPI
-	help
-	  If you say yes here you will get support for the Epson RX-6610.
-
-	  This driver can also be built as a module. If so the module
-	  will be called rtc-rx6110.
-
 config RTC_DRV_RS5C348
 	tristate "Ricoh RS5C348A/B"
 	help
@@ -936,6 +927,17 @@ config RTC_DRV_RV3029_HWMON
 	  Say Y here if you want to expose temperature sensor data on
 	  rtc-rv3029.
 
+config RTC_DRV_RX6110
+	tristate "Epson RX-6110"
+	depends on RTC_I2C_AND_SPI
+	select REGMAP_SPI if SPI_MASTER
+	select REGMAP_I2C if I2C
+	help
+	  If you say yes here you will get support for the Epson RX-6110.
+
+	  This driver can also be built as a module. If so the module
+	  will be called rtc-rx6110.
+
 comment "Platform RTC drivers"
 
 # this 'CMOS' RTC driver is arch dependent because it requires
@@ -1017,6 +1019,7 @@ config RTC_DRV_DS1553
 
 config RTC_DRV_DS1685_FAMILY
 	tristate "Dallas/Maxim DS1685 Family"
+	depends on HAS_IOMEM
 	help
 	  If you say yes here you get support for the Dallas/Maxim DS1685
 	  family of real time chips.  This family includes the DS1685/DS1687,
@@ -1150,6 +1153,7 @@ config RTC_DRV_STK17TA8
 
 config RTC_DRV_M48T86
 	tristate "ST M48T86/Dallas DS12887"
+	depends on HAS_IOMEM
 	help
 	  If you say Y here you will get support for the
 	  ST M48T86 and Dallas DS12887 RTC chips.
@@ -1752,7 +1756,9 @@ config RTC_DRV_LOONGSON1
 
 config RTC_DRV_MXC
 	tristate "Freescale MXC Real Time Clock"
-	depends on ARCH_MXC
+	depends on ARCH_MXC || COMPILE_TEST
+	depends on HAS_IOMEM
+	depends on OF
 	help
 	   If you say yes here you get support for the Freescale MXC
 	   RTC module.
@@ -1762,7 +1768,9 @@ config RTC_DRV_MXC
 
 config RTC_DRV_MXC_V2
 	tristate "Freescale MXC Real Time Clock for i.MX53"
-	depends on ARCH_MXC
+	depends on ARCH_MXC || COMPILE_TEST
+	depends on HAS_IOMEM
+	depends on OF
 	help
 	   If you say yes here you get support for the Freescale MXC
 	   SRTC module in i.MX53 processor.
@@ -1935,7 +1943,6 @@ config RTC_DRV_HID_SENSOR_TIME
 config RTC_DRV_GOLDFISH
 	tristate "Goldfish Real Time Clock"
 	depends on OF && HAS_IOMEM
-	depends on GOLDFISH || COMPILE_TEST
 	help
 	  Say yes to enable RTC driver for the Goldfish based virtual platform.
 
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index 5855aa2eef62..7e470fbd5e4d 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -28,6 +28,7 @@ static void rtc_device_release(struct device *dev)
 	struct rtc_device *rtc = to_rtc_device(dev);
 
 	ida_simple_remove(&rtc_ida, rtc->id);
+	mutex_destroy(&rtc->ops_lock);
 	kfree(rtc);
 }
 
@@ -326,8 +327,10 @@ static void rtc_device_get_offset(struct rtc_device *rtc)
  *
  * @rtc: the RTC class device to destroy
  */
-static void rtc_device_unregister(struct rtc_device *rtc)
+static void devm_rtc_unregister_device(void *data)
 {
+	struct rtc_device *rtc = data;
+
 	mutex_lock(&rtc->ops_lock);
 	/*
 	 * Remove innards of this RTC, then disable it, before
@@ -337,60 +340,43 @@ static void rtc_device_unregister(struct rtc_device *rtc)
 	cdev_device_del(&rtc->char_dev, &rtc->dev);
 	rtc->ops = NULL;
 	mutex_unlock(&rtc->ops_lock);
-	put_device(&rtc->dev);
 }
 
-static void devm_rtc_release_device(struct device *dev, void *res)
+static void devm_rtc_release_device(void *res)
 {
-	struct rtc_device *rtc = *(struct rtc_device **)res;
+	struct rtc_device *rtc = res;
 
-	rtc_nvmem_unregister(rtc);
-
-	if (rtc->registered)
-		rtc_device_unregister(rtc);
-	else
-		put_device(&rtc->dev);
+	put_device(&rtc->dev);
 }
 
 struct rtc_device *devm_rtc_allocate_device(struct device *dev)
 {
-	struct rtc_device **ptr, *rtc;
+	struct rtc_device *rtc;
 	int id, err;
 
 	id = rtc_device_get_id(dev);
 	if (id < 0)
 		return ERR_PTR(id);
 
-	ptr = devres_alloc(devm_rtc_release_device, sizeof(*ptr), GFP_KERNEL);
-	if (!ptr) {
-		err = -ENOMEM;
-		goto exit_ida;
-	}
-
 	rtc = rtc_allocate_device();
 	if (!rtc) {
-		err = -ENOMEM;
-		goto exit_devres;
+		ida_simple_remove(&rtc_ida, id);
+		return ERR_PTR(-ENOMEM);
 	}
 
-	*ptr = rtc;
-	devres_add(dev, ptr);
-
 	rtc->id = id;
 	rtc->dev.parent = dev;
 	dev_set_name(&rtc->dev, "rtc%d", id);
 
-	return rtc;
+	err = devm_add_action_or_reset(dev, devm_rtc_release_device, rtc);
+	if (err)
+		return ERR_PTR(err);
 
-exit_devres:
-	devres_free(ptr);
-exit_ida:
-	ida_simple_remove(&rtc_ida, id);
-	return ERR_PTR(err);
+	return rtc;
 }
 EXPORT_SYMBOL_GPL(devm_rtc_allocate_device);
 
-int __rtc_register_device(struct module *owner, struct rtc_device *rtc)
+int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc)
 {
 	struct rtc_wkalrm alrm;
 	int err;
@@ -420,7 +406,6 @@ int __rtc_register_device(struct module *owner, struct rtc_device *rtc)
 
 	rtc_proc_add_device(rtc);
 
-	rtc->registered = true;
 	dev_info(rtc->dev.parent, "registered as %s\n",
 		 dev_name(&rtc->dev));
 
@@ -429,9 +414,10 @@ int __rtc_register_device(struct module *owner, struct rtc_device *rtc)
 		rtc_hctosys(rtc);
 #endif
 
-	return 0;
+	return devm_add_action_or_reset(rtc->dev.parent,
+					devm_rtc_unregister_device, rtc);
 }
-EXPORT_SYMBOL_GPL(__rtc_register_device);
+EXPORT_SYMBOL_GPL(__devm_rtc_register_device);
 
 /**
  * devm_rtc_device_register - resource managed rtc_device_register()
@@ -461,7 +447,7 @@ struct rtc_device *devm_rtc_device_register(struct device *dev,
 
 	rtc->ops = ops;
 
-	err = __rtc_register_device(owner, rtc);
+	err = __devm_rtc_register_device(owner, rtc);
 	if (err)
 		return ERR_PTR(err);
 
diff --git a/drivers/rtc/nvmem.c b/drivers/rtc/nvmem.c
index 4312096c7738..07ede21cee34 100644
--- a/drivers/rtc/nvmem.c
+++ b/drivers/rtc/nvmem.c
@@ -9,99 +9,22 @@
 #include <linux/types.h>
 #include <linux/nvmem-consumer.h>
 #include <linux/rtc.h>
-#include <linux/slab.h>
-#include <linux/sysfs.h>
 
-/*
- * Deprecated ABI compatibility, this should be removed at some point
- */
-
-static const char nvram_warning[] = "Deprecated ABI, please use nvmem";
-
-static ssize_t
-rtc_nvram_read(struct file *filp, struct kobject *kobj,
-	       struct bin_attribute *attr,
-	       char *buf, loff_t off, size_t count)
-{
-	dev_warn_once(kobj_to_dev(kobj), nvram_warning);
-
-	return nvmem_device_read(attr->private, off, count, buf);
-}
-
-static ssize_t
-rtc_nvram_write(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr,
-		char *buf, loff_t off, size_t count)
-{
-	dev_warn_once(kobj_to_dev(kobj), nvram_warning);
-
-	return nvmem_device_write(attr->private, off, count, buf);
-}
-
-static int rtc_nvram_register(struct rtc_device *rtc,
-			      struct nvmem_device *nvmem, size_t size)
-{
-	int err;
-
-	rtc->nvram = kzalloc(sizeof(*rtc->nvram), GFP_KERNEL);
-	if (!rtc->nvram)
-		return -ENOMEM;
-
-	rtc->nvram->attr.name = "nvram";
-	rtc->nvram->attr.mode = 0644;
-	rtc->nvram->private = nvmem;
-
-	sysfs_bin_attr_init(rtc->nvram);
-
-	rtc->nvram->read = rtc_nvram_read;
-	rtc->nvram->write = rtc_nvram_write;
-	rtc->nvram->size = size;
-
-	err = sysfs_create_bin_file(&rtc->dev.parent->kobj,
-				    rtc->nvram);
-	if (err) {
-		kfree(rtc->nvram);
-		rtc->nvram = NULL;
-	}
-
-	return err;
-}
-
-static void rtc_nvram_unregister(struct rtc_device *rtc)
-{
-	sysfs_remove_bin_file(&rtc->dev.parent->kobj, rtc->nvram);
-	kfree(rtc->nvram);
-	rtc->nvram = NULL;
-}
-
-/*
- * New ABI, uses nvmem
- */
-int rtc_nvmem_register(struct rtc_device *rtc,
+int devm_rtc_nvmem_register(struct rtc_device *rtc,
 		       struct nvmem_config *nvmem_config)
 {
+	struct device *dev = rtc->dev.parent;
 	struct nvmem_device *nvmem;
 
 	if (!nvmem_config)
 		return -ENODEV;
 
-	nvmem_config->dev = rtc->dev.parent;
+	nvmem_config->dev = dev;
 	nvmem_config->owner = rtc->owner;
-	nvmem = devm_nvmem_register(rtc->dev.parent, nvmem_config);
+	nvmem = devm_nvmem_register(dev, nvmem_config);
 	if (IS_ERR(nvmem))
-		return PTR_ERR(nvmem);
-
-	/* Register the old ABI */
-	if (rtc->nvram_old_abi)
-		rtc_nvram_register(rtc, nvmem, nvmem_config->size);
+		dev_err(dev, "failed to register nvmem device for RTC\n");
 
-	return 0;
-}
-EXPORT_SYMBOL_GPL(rtc_nvmem_register);
-
-void rtc_nvmem_unregister(struct rtc_device *rtc)
-{
-	/* unregister the old ABI */
-	if (rtc->nvram)
-		rtc_nvram_unregister(rtc);
+	return PTR_ERR_OR_ZERO(nvmem);
 }
+EXPORT_SYMBOL_GPL(devm_rtc_nvmem_register);
diff --git a/drivers/rtc/rtc-88pm80x.c b/drivers/rtc/rtc-88pm80x.c
index 75779e8501a3..6a3f44cf6ebe 100644
--- a/drivers/rtc/rtc-88pm80x.c
+++ b/drivers/rtc/rtc-88pm80x.c
@@ -294,7 +294,7 @@ static int pm80x_rtc_probe(struct platform_device *pdev)
 	info->rtc_dev->ops = &pm80x_rtc_ops;
 	info->rtc_dev->range_max = U32_MAX;
 
-	ret = rtc_register_device(info->rtc_dev);
+	ret = devm_rtc_register_device(info->rtc_dev);
 	if (ret)
 		goto out_rtc;
 
diff --git a/drivers/rtc/rtc-88pm860x.c b/drivers/rtc/rtc-88pm860x.c
index c90457d001e9..2c809a1a445e 100644
--- a/drivers/rtc/rtc-88pm860x.c
+++ b/drivers/rtc/rtc-88pm860x.c
@@ -307,7 +307,7 @@ static int pm860x_rtc_probe(struct platform_device *pdev)
 	info->rtc_dev->ops = &pm860x_rtc_ops;
 	info->rtc_dev->range_max = U32_MAX;
 
-	ret = rtc_register_device(info->rtc_dev);
+	ret = devm_rtc_register_device(info->rtc_dev);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-ab-b5ze-s3.c b/drivers/rtc/rtc-ab-b5ze-s3.c
index 2370ac0cdb5f..6e3e320dc727 100644
--- a/drivers/rtc/rtc-ab-b5ze-s3.c
+++ b/drivers/rtc/rtc-ab-b5ze-s3.c
@@ -892,7 +892,7 @@ static int abb5zes3_probe(struct i2c_client *client,
 		}
 	}
 
-	ret = rtc_register_device(data->rtc);
+	ret = devm_rtc_register_device(data->rtc);
 
 err:
 	if (ret && data->irq)
diff --git a/drivers/rtc/rtc-ab-eoz9.c b/drivers/rtc/rtc-ab-eoz9.c
index d690985caa4c..b20d8f26dcdb 100644
--- a/drivers/rtc/rtc-ab-eoz9.c
+++ b/drivers/rtc/rtc-ab-eoz9.c
@@ -420,7 +420,7 @@ static int abeoz9_probe(struct i2c_client *client,
 	data->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	data->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	ret = rtc_register_device(data->rtc);
+	ret = devm_rtc_register_device(data->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-ab3100.c b/drivers/rtc/rtc-ab3100.c
index 2ed6def90975..e4fd961e8bf6 100644
--- a/drivers/rtc/rtc-ab3100.c
+++ b/drivers/rtc/rtc-ab3100.c
@@ -238,7 +238,7 @@ static int __init ab3100_rtc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtc);
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver ab3100_rtc_driver = {
diff --git a/drivers/rtc/rtc-ab8500.c b/drivers/rtc/rtc-ab8500.c
index 3d60f3283f11..b40048871295 100644
--- a/drivers/rtc/rtc-ab8500.c
+++ b/drivers/rtc/rtc-ab8500.c
@@ -404,7 +404,7 @@ static int ab8500_rtc_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static int ab8500_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-abx80x.c b/drivers/rtc/rtc-abx80x.c
index 803725b3a02c..6733bb0df674 100644
--- a/drivers/rtc/rtc-abx80x.c
+++ b/drivers/rtc/rtc-abx80x.c
@@ -851,7 +851,7 @@ static int abx80x_probe(struct i2c_client *client,
 		return err;
 	}
 
-	return rtc_register_device(priv->rtc);
+	return devm_rtc_register_device(priv->rtc);
 }
 
 static const struct i2c_device_id abx80x_id[] = {
diff --git a/drivers/rtc/rtc-ac100.c b/drivers/rtc/rtc-ac100.c
index 29223931aba7..1ddbef99e38f 100644
--- a/drivers/rtc/rtc-ac100.c
+++ b/drivers/rtc/rtc-ac100.c
@@ -610,7 +610,7 @@ static int ac100_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	return rtc_register_device(chip->rtc);
+	return devm_rtc_register_device(chip->rtc);
 }
 
 static int ac100_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c
index 94d7c22fc4f3..807a79c07f08 100644
--- a/drivers/rtc/rtc-armada38x.c
+++ b/drivers/rtc/rtc-armada38x.c
@@ -556,7 +556,7 @@ static __init int armada38x_rtc_probe(struct platform_device *pdev)
 
 	rtc->rtc_dev->range_max = U32_MAX;
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-aspeed.c b/drivers/rtc/rtc-aspeed.c
index eacdd0637cce..a93352ed3aec 100644
--- a/drivers/rtc/rtc-aspeed.c
+++ b/drivers/rtc/rtc-aspeed.c
@@ -104,7 +104,7 @@ static int aspeed_rtc_probe(struct platform_device *pdev)
 	rtc->rtc_dev->range_min = RTC_TIMESTAMP_BEGIN_1900;
 	rtc->rtc_dev->range_max = 38814989399LL; /* 3199-12-31 23:59:59 */
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 static const struct of_device_id aspeed_rtc_match[] = {
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index 5e811e04cb21..fe396d27ebb7 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -36,6 +36,10 @@
 #define		AT91_RTC_UPDCAL		BIT(1)		/* Update Request Calendar Register */
 
 #define	AT91_RTC_MR		0x04			/* Mode Register */
+#define		AT91_RTC_HRMOD		BIT(0)		/* 12/24 hour mode */
+#define		AT91_RTC_NEGPPM		BIT(4)		/* Negative PPM correction */
+#define		AT91_RTC_CORRECTION	GENMASK(14, 8)	/* Slow clock correction */
+#define		AT91_RTC_HIGHPPM	BIT(15)		/* High PPM correction */
 
 #define	AT91_RTC_TIMR		0x08			/* Time Register */
 #define		AT91_RTC_SEC		GENMASK(6, 0)	/* Current Second */
@@ -77,6 +81,9 @@
 #define		AT91_RTC_NVTIMALR	BIT(2)		/* Non valid Time Alarm */
 #define		AT91_RTC_NVCALALR	BIT(3)		/* Non valid Calendar Alarm */
 
+#define AT91_RTC_CORR_DIVIDEND		3906000
+#define AT91_RTC_CORR_LOW_RATIO		20
+
 #define at91_rtc_read(field) \
 	readl_relaxed(at91_rtc_regs + field)
 #define at91_rtc_write(field, val) \
@@ -84,6 +91,7 @@
 
 struct at91_rtc_config {
 	bool use_shadow_imr;
+	bool has_correction;
 };
 
 static const struct at91_rtc_config *at91_rtc_config;
@@ -293,6 +301,75 @@ static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	return 0;
 }
 
+static int at91_rtc_readoffset(struct device *dev, long *offset)
+{
+	u32 mr = at91_rtc_read(AT91_RTC_MR);
+	long val = FIELD_GET(AT91_RTC_CORRECTION, mr);
+
+	if (!val) {
+		*offset = 0;
+		return 0;
+	}
+
+	val++;
+
+	if (!(mr & AT91_RTC_NEGPPM))
+		val = -val;
+
+	if (!(mr & AT91_RTC_HIGHPPM))
+		val *= AT91_RTC_CORR_LOW_RATIO;
+
+	*offset = DIV_ROUND_CLOSEST(AT91_RTC_CORR_DIVIDEND, val);
+
+	return 0;
+}
+
+static int at91_rtc_setoffset(struct device *dev, long offset)
+{
+	long corr;
+	u32 mr;
+
+	if (offset > AT91_RTC_CORR_DIVIDEND / 2)
+		return -ERANGE;
+	if (offset < -AT91_RTC_CORR_DIVIDEND / 2)
+		return -ERANGE;
+
+	mr = at91_rtc_read(AT91_RTC_MR);
+	mr &= ~(AT91_RTC_NEGPPM | AT91_RTC_CORRECTION | AT91_RTC_HIGHPPM);
+
+	if (offset > 0)
+		mr |= AT91_RTC_NEGPPM;
+	else
+		offset = -offset;
+
+	/* offset less than 764 ppb, disable correction*/
+	if (offset < 764) {
+		at91_rtc_write(AT91_RTC_MR, mr & ~AT91_RTC_NEGPPM);
+
+		return 0;
+	}
+
+	/*
+	 * 29208 ppb is the perfect cutoff between low range and high range
+	 * low range values are never better than high range value after that.
+	 */
+	if (offset < 29208) {
+		corr = DIV_ROUND_CLOSEST(AT91_RTC_CORR_DIVIDEND, offset * AT91_RTC_CORR_LOW_RATIO);
+	} else {
+		corr = DIV_ROUND_CLOSEST(AT91_RTC_CORR_DIVIDEND, offset);
+		mr |= AT91_RTC_HIGHPPM;
+	}
+
+	if (corr > 128)
+		corr = 128;
+
+	mr |= FIELD_PREP(AT91_RTC_CORRECTION, corr - 1);
+
+	at91_rtc_write(AT91_RTC_MR, mr);
+
+	return 0;
+}
+
 /*
  * IRQ handler for the RTC
  */
@@ -343,6 +420,10 @@ static const struct at91_rtc_config at91sam9x5_config = {
 	.use_shadow_imr	= true,
 };
 
+static const struct at91_rtc_config sama5d4_config = {
+	.has_correction = true,
+};
+
 static const struct of_device_id at91_rtc_dt_ids[] = {
 	{
 		.compatible = "atmel,at91rm9200-rtc",
@@ -352,10 +433,13 @@ static const struct of_device_id at91_rtc_dt_ids[] = {
 		.data = &at91sam9x5_config,
 	}, {
 		.compatible = "atmel,sama5d4-rtc",
-		.data = &at91rm9200_config,
+		.data = &sama5d4_config,
 	}, {
 		.compatible = "atmel,sama5d2-rtc",
-		.data = &at91rm9200_config,
+		.data = &sama5d4_config,
+	}, {
+		.compatible = "microchip,sam9x60-rtc",
+		.data = &sama5d4_config,
 	}, {
 		/* sentinel */
 	}
@@ -370,6 +454,16 @@ static const struct rtc_class_ops at91_rtc_ops = {
 	.alarm_irq_enable = at91_rtc_alarm_irq_enable,
 };
 
+static const struct rtc_class_ops sama5d4_rtc_ops = {
+	.read_time	= at91_rtc_readtime,
+	.set_time	= at91_rtc_settime,
+	.read_alarm	= at91_rtc_readalarm,
+	.set_alarm	= at91_rtc_setalarm,
+	.alarm_irq_enable = at91_rtc_alarm_irq_enable,
+	.set_offset	= at91_rtc_setoffset,
+	.read_offset	= at91_rtc_readoffset,
+};
+
 /*
  * Initialize and install RTC driver
  */
@@ -416,7 +510,7 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 	}
 
 	at91_rtc_write(AT91_RTC_CR, 0);
-	at91_rtc_write(AT91_RTC_MR, 0);		/* 24 hour mode */
+	at91_rtc_write(AT91_RTC_MR, at91_rtc_read(AT91_RTC_MR) & ~AT91_RTC_HRMOD);
 
 	/* Disable all interrupts */
 	at91_rtc_write_idr(AT91_RTC_ACKUPD | AT91_RTC_ALARM |
@@ -437,10 +531,14 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 	if (!device_can_wakeup(&pdev->dev))
 		device_init_wakeup(&pdev->dev, 1);
 
-	rtc->ops = &at91_rtc_ops;
+	if (at91_rtc_config->has_correction)
+		rtc->ops = &sama5d4_rtc_ops;
+	else
+		rtc->ops = &at91_rtc_ops;
+
 	rtc->range_min = RTC_TIMESTAMP_BEGIN_1900;
 	rtc->range_max = RTC_TIMESTAMP_END_2099;
-	ret = rtc_register_device(rtc);
+	ret = devm_rtc_register_device(rtc);
 	if (ret)
 		goto err_clk;
 
diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c
index e39e89867d29..2216be429ab7 100644
--- a/drivers/rtc/rtc-at91sam9.c
+++ b/drivers/rtc/rtc-at91sam9.c
@@ -431,7 +431,7 @@ static int at91_rtc_probe(struct platform_device *pdev)
 		dev_warn(&pdev->dev, "%s: SET TIME!\n",
 			 dev_name(&rtc->rtcdev->dev));
 
-	return rtc_register_device(rtc->rtcdev);
+	return devm_rtc_register_device(rtc->rtcdev);
 
 err_clk:
 	clk_disable_unprepare(rtc->sclk);
diff --git a/drivers/rtc/rtc-au1xxx.c b/drivers/rtc/rtc-au1xxx.c
index 791bebcb6f47..e6428b27b5d4 100644
--- a/drivers/rtc/rtc-au1xxx.c
+++ b/drivers/rtc/rtc-au1xxx.c
@@ -104,7 +104,7 @@ static int au1xtoy_rtc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtcdev);
 
-	return rtc_register_device(rtcdev);
+	return devm_rtc_register_device(rtcdev);
 }
 
 static struct platform_driver au1xrtc_driver = {
diff --git a/drivers/rtc/rtc-bd70528.c b/drivers/rtc/rtc-bd70528.c
index 4492b770422c..17cb67f5bf6e 100644
--- a/drivers/rtc/rtc-bd70528.c
+++ b/drivers/rtc/rtc-bd70528.c
@@ -604,7 +604,7 @@ static int bd70528_probe(struct platform_device *pdev)
 		}
 	}
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static const struct platform_device_id bd718x7_rtc_id[] = {
diff --git a/drivers/rtc/rtc-brcmstb-waketimer.c b/drivers/rtc/rtc-brcmstb-waketimer.c
index 4fee57c51280..0366e2ff04ae 100644
--- a/drivers/rtc/rtc-brcmstb-waketimer.c
+++ b/drivers/rtc/rtc-brcmstb-waketimer.c
@@ -252,7 +252,7 @@ static int brcmstb_waketmr_probe(struct platform_device *pdev)
 	timer->rtc->ops = &brcmstb_waketmr_ops;
 	timer->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(timer->rtc);
+	ret = devm_rtc_register_device(timer->rtc);
 	if (ret)
 		goto err_notifier;
 
@@ -264,8 +264,7 @@ err_notifier:
 	unregister_reboot_notifier(&timer->reboot_notifier);
 
 err_clk:
-	if (timer->clk)
-		clk_disable_unprepare(timer->clk);
+	clk_disable_unprepare(timer->clk);
 
 	return ret;
 }
diff --git a/drivers/rtc/rtc-cadence.c b/drivers/rtc/rtc-cadence.c
index 595d5d252850..1edf7f16d73a 100644
--- a/drivers/rtc/rtc-cadence.c
+++ b/drivers/rtc/rtc-cadence.c
@@ -336,7 +336,7 @@ static int cdns_rtc_probe(struct platform_device *pdev)
 	writel(0, crtc->regs + CDNS_RTC_HMR);
 	writel(CDNS_RTC_KRTCR_KRTC, crtc->regs + CDNS_RTC_KRTCR);
 
-	ret = rtc_register_device(crtc->rtc_dev);
+	ret = devm_rtc_register_device(crtc->rtc_dev);
 	if (ret)
 		goto err_disable_wakeup;
 
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index c5bcd2adc9fe..51e80bc70d42 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -863,8 +863,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
 		cmos_rtc.rtc->ops = &cmos_rtc_ops_no_alarm;
 	}
 
-	cmos_rtc.rtc->nvram_old_abi = true;
-	retval = rtc_register_device(cmos_rtc.rtc);
+	retval = devm_rtc_register_device(cmos_rtc.rtc);
 	if (retval)
 		goto cleanup2;
 
@@ -873,8 +872,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
 
 	/* export at least the first block of NVRAM */
 	nvmem_cfg.size = address_space - NVRAM_OFFSET;
-	if (rtc_nvmem_register(cmos_rtc.rtc, &nvmem_cfg))
-		dev_err(dev, "nvmem registration failed\n");
+	devm_rtc_nvmem_register(cmos_rtc.rtc, &nvmem_cfg);
 
 	dev_info(dev, "%s%s, %d bytes nvram%s\n",
 		 !is_valid_irq(rtc_irq) ? "no alarms" :
diff --git a/drivers/rtc/rtc-coh901331.c b/drivers/rtc/rtc-coh901331.c
index da59917c9ee8..168ced87d93a 100644
--- a/drivers/rtc/rtc-coh901331.c
+++ b/drivers/rtc/rtc-coh901331.c
@@ -203,7 +203,7 @@ static int __init coh901331_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtap);
 
-	ret = rtc_register_device(rtap->rtc);
+	ret = devm_rtc_register_device(rtap->rtc);
 	if (ret)
 		goto out_no_rtc;
 
diff --git a/drivers/rtc/rtc-cpcap.c b/drivers/rtc/rtc-cpcap.c
index 800667d73a6f..afc8fcba8f88 100644
--- a/drivers/rtc/rtc-cpcap.c
+++ b/drivers/rtc/rtc-cpcap.c
@@ -269,7 +269,8 @@ static int cpcap_rtc_probe(struct platform_device *pdev)
 
 	rtc->alarm_irq = platform_get_irq(pdev, 0);
 	err = devm_request_threaded_irq(dev, rtc->alarm_irq, NULL,
-					cpcap_rtc_alarm_irq, IRQF_TRIGGER_NONE,
+					cpcap_rtc_alarm_irq,
+					IRQF_TRIGGER_NONE | IRQF_ONESHOT,
 					"rtc_alarm", rtc);
 	if (err) {
 		dev_err(dev, "Could not request alarm irq: %d\n", err);
@@ -285,7 +286,8 @@ static int cpcap_rtc_probe(struct platform_device *pdev)
 	 */
 	rtc->update_irq = platform_get_irq(pdev, 1);
 	err = devm_request_threaded_irq(dev, rtc->update_irq, NULL,
-					cpcap_rtc_update_irq, IRQF_TRIGGER_NONE,
+					cpcap_rtc_update_irq,
+					IRQF_TRIGGER_NONE | IRQF_ONESHOT,
 					"rtc_1hz", rtc);
 	if (err) {
 		dev_err(dev, "Could not request update irq: %d\n", err);
@@ -299,7 +301,7 @@ static int cpcap_rtc_probe(struct platform_device *pdev)
 		/* ignore error and continue without wakeup support */
 	}
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 static const struct of_device_id cpcap_rtc_of_match[] = {
diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c
index f7343c289cab..70626793ca69 100644
--- a/drivers/rtc/rtc-cros-ec.c
+++ b/drivers/rtc/rtc-cros-ec.c
@@ -350,7 +350,7 @@ static int cros_ec_rtc_probe(struct platform_device *pdev)
 	cros_ec_rtc->rtc->ops = &cros_ec_rtc_ops;
 	cros_ec_rtc->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(cros_ec_rtc->rtc);
+	ret = devm_rtc_register_device(cros_ec_rtc->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-da9052.c b/drivers/rtc/rtc-da9052.c
index 58de10da37b1..9ca99bd35702 100644
--- a/drivers/rtc/rtc-da9052.c
+++ b/drivers/rtc/rtc-da9052.c
@@ -304,7 +304,7 @@ static int da9052_rtc_probe(struct platform_device *pdev)
 	rtc->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rtc->rtc->range_max = RTC_TIMESTAMP_END_2063;
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c
index 046b1d4c3dae..d4b72a9fa2ba 100644
--- a/drivers/rtc/rtc-da9063.c
+++ b/drivers/rtc/rtc-da9063.c
@@ -243,7 +243,7 @@ static int da9063_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	al_secs = rtc_tm_to_time64(&rtc->alarm_time);
 
 	/* handle the rtc synchronisation delay */
-	if (rtc->rtc_sync == true && al_secs - tm_secs == 1)
+	if (rtc->rtc_sync && al_secs - tm_secs == 1)
 		memcpy(tm, &rtc->alarm_time, sizeof(struct rtc_time));
 	else
 		rtc->rtc_sync = false;
@@ -494,7 +494,7 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "Failed to request ALARM IRQ %d: %d\n",
 			irq_alarm, ret);
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 static struct platform_driver da9063_rtc_driver = {
diff --git a/drivers/rtc/rtc-davinci.c b/drivers/rtc/rtc-davinci.c
index 73f87a17cdf3..6bef0f2353da 100644
--- a/drivers/rtc/rtc-davinci.c
+++ b/drivers/rtc/rtc-davinci.c
@@ -484,7 +484,7 @@ static int __init davinci_rtc_probe(struct platform_device *pdev)
 
 	device_init_wakeup(&pdev->dev, 0);
 
-	return rtc_register_device(davinci_rtc->rtc);
+	return devm_rtc_register_device(davinci_rtc->rtc);
 }
 
 static int __exit davinci_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-digicolor.c b/drivers/rtc/rtc-digicolor.c
index 200d85b01e8b..4fdfa5b6feb2 100644
--- a/drivers/rtc/rtc-digicolor.c
+++ b/drivers/rtc/rtc-digicolor.c
@@ -202,7 +202,7 @@ static int __init dc_rtc_probe(struct platform_device *pdev)
 	rtc->rtc_dev->ops = &dc_rtc_ops;
 	rtc->rtc_dev->range_max = U32_MAX;
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 static const struct of_device_id dc_dt_ids[] = {
diff --git a/drivers/rtc/rtc-dm355evm.c b/drivers/rtc/rtc-dm355evm.c
index cd947a20843b..94fb16ac3e0f 100644
--- a/drivers/rtc/rtc-dm355evm.c
+++ b/drivers/rtc/rtc-dm355evm.c
@@ -132,7 +132,7 @@ static int dm355evm_rtc_probe(struct platform_device *pdev)
 	rtc->ops = &dm355evm_rtc_ops;
 	rtc->range_max = U32_MAX;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 /*
diff --git a/drivers/rtc/rtc-ds1305.c b/drivers/rtc/rtc-ds1305.c
index a3d790889eea..8c2ab29c3d91 100644
--- a/drivers/rtc/rtc-ds1305.c
+++ b/drivers/rtc/rtc-ds1305.c
@@ -694,12 +694,11 @@ static int ds1305_probe(struct spi_device *spi)
 	ds1305->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
 	ds1305_nvmem_cfg.priv = ds1305;
-	ds1305->rtc->nvram_old_abi = true;
-	status = rtc_register_device(ds1305->rtc);
+	status = devm_rtc_register_device(ds1305->rtc);
 	if (status)
 		return status;
 
-	rtc_nvmem_register(ds1305->rtc, &ds1305_nvmem_cfg);
+	devm_rtc_nvmem_register(ds1305->rtc, &ds1305_nvmem_cfg);
 
 	/* Maybe set up alarm IRQ; be ready to handle it triggering right
 	 * away.  NOTE that we don't share this.  The signal is active low,
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index 9f5f54ca039d..183cf7c01364 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -8,12 +8,12 @@
  *  Copyright (C) 2012 Bertrand Achard (nvram access fixes)
  */
 
-#include <linux/acpi.h>
 #include <linux/bcd.h>
 #include <linux/i2c.h>
 #include <linux/init.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/property.h>
 #include <linux/rtc/ds1307.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
@@ -31,6 +31,7 @@
  * That's a natural job for a factory or repair bench.
  */
 enum ds_type {
+	unknown_ds_type, /* always first and 0 */
 	ds_1307,
 	ds_1308,
 	ds_1337,
@@ -1090,7 +1091,6 @@ static const struct i2c_device_id ds1307_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ds1307_id);
 
-#ifdef CONFIG_OF
 static const struct of_device_id ds1307_of_match[] = {
 	{
 		.compatible = "dallas,ds1307",
@@ -1167,32 +1167,6 @@ static const struct of_device_id ds1307_of_match[] = {
 	{ }
 };
 MODULE_DEVICE_TABLE(of, ds1307_of_match);
-#endif
-
-#ifdef CONFIG_ACPI
-static const struct acpi_device_id ds1307_acpi_ids[] = {
-	{ .id = "DS1307", .driver_data = ds_1307 },
-	{ .id = "DS1308", .driver_data = ds_1308 },
-	{ .id = "DS1337", .driver_data = ds_1337 },
-	{ .id = "DS1338", .driver_data = ds_1338 },
-	{ .id = "DS1339", .driver_data = ds_1339 },
-	{ .id = "DS1388", .driver_data = ds_1388 },
-	{ .id = "DS1340", .driver_data = ds_1340 },
-	{ .id = "DS1341", .driver_data = ds_1341 },
-	{ .id = "DS3231", .driver_data = ds_3231 },
-	{ .id = "M41T0", .driver_data = m41t0 },
-	{ .id = "M41T00", .driver_data = m41t00 },
-	{ .id = "M41T11", .driver_data = m41t11 },
-	{ .id = "MCP7940X", .driver_data = mcp794xx },
-	{ .id = "MCP7941X", .driver_data = mcp794xx },
-	{ .id = "PT7C4338", .driver_data = ds_1307 },
-	{ .id = "RX8025", .driver_data = rx_8025 },
-	{ .id = "ISL12057", .driver_data = ds_1337 },
-	{ .id = "RX8130", .driver_data = rx_8130 },
-	{ }
-};
-MODULE_DEVICE_TABLE(acpi, ds1307_acpi_ids);
-#endif
 
 /*
  * The ds1337 and ds1339 both have two alarms, but we only use the first
@@ -1626,13 +1600,16 @@ static const struct clk_ops ds3231_clk_32khz_ops = {
 	.recalc_rate = ds3231_clk_32khz_recalc_rate,
 };
 
+static const char *ds3231_clks_names[] = {
+	[DS3231_CLK_SQW] = "ds3231_clk_sqw",
+	[DS3231_CLK_32KHZ] = "ds3231_clk_32khz",
+};
+
 static struct clk_init_data ds3231_clks_init[] = {
 	[DS3231_CLK_SQW] = {
-		.name = "ds3231_clk_sqw",
 		.ops = &ds3231_clk_sqw_ops,
 	},
 	[DS3231_CLK_32KHZ] = {
-		.name = "ds3231_clk_32khz",
 		.ops = &ds3231_clk_32khz_ops,
 	},
 };
@@ -1653,6 +1630,11 @@ static int ds3231_clks_register(struct ds1307 *ds1307)
 	if (!onecell->clks)
 		return -ENOMEM;
 
+	/* optional override of the clockname */
+	device_property_read_string_array(ds1307->dev, "clock-output-names",
+					  ds3231_clks_names,
+					  ARRAY_SIZE(ds3231_clks_names));
+
 	for (i = 0; i < ARRAY_SIZE(ds3231_clks_init); i++) {
 		struct clk_init_data init = ds3231_clks_init[i];
 
@@ -1663,9 +1645,7 @@ static int ds3231_clks_register(struct ds1307 *ds1307)
 		if (i == DS3231_CLK_SQW && test_bit(HAS_ALARM, &ds1307->flags))
 			continue;
 
-		/* optional override of the clockname */
-		of_property_read_string_index(node, "clock-output-names", i,
-					      &init.name);
+		init.name = ds3231_clks_names[i];
 		ds1307->clks[i].init = &init;
 
 		onecell->clks[i] = devm_clk_register(ds1307->dev,
@@ -1674,10 +1654,8 @@ static int ds3231_clks_register(struct ds1307 *ds1307)
 			return PTR_ERR(onecell->clks[i]);
 	}
 
-	if (!node)
-		return 0;
-
-	of_clk_add_provider(node, of_clk_src_onecell_get, onecell);
+	if (node)
+		of_clk_add_provider(node, of_clk_src_onecell_get, onecell);
 
 	return 0;
 }
@@ -1761,6 +1739,7 @@ static int ds1307_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
 	struct ds1307		*ds1307;
+	const void		*match;
 	int			err = -ENODEV;
 	int			tmp;
 	const struct chip_desc	*chip;
@@ -1786,22 +1765,15 @@ static int ds1307_probe(struct i2c_client *client,
 
 	i2c_set_clientdata(client, ds1307);
 
-	if (client->dev.of_node) {
-		ds1307->type = (enum ds_type)
-			of_device_get_match_data(&client->dev);
+	match = device_get_match_data(&client->dev);
+	if (match) {
+		ds1307->type = (enum ds_type)match;
 		chip = &chips[ds1307->type];
 	} else if (id) {
 		chip = &chips[id->driver_data];
 		ds1307->type = id->driver_data;
 	} else {
-		const struct acpi_device_id *acpi_id;
-
-		acpi_id = acpi_match_device(ACPI_PTR(ds1307_acpi_ids),
-					    ds1307->dev);
-		if (!acpi_id)
-			return -ENODEV;
-		chip = &chips[acpi_id->driver_data];
-		ds1307->type = acpi_id->driver_data;
+		return -ENODEV;
 	}
 
 	want_irq = client->irq > 0 && chip->alarm;
@@ -1819,7 +1791,6 @@ static int ds1307_probe(struct i2c_client *client,
 			     trickle_charger_setup);
 	}
 
-#ifdef CONFIG_OF
 /*
  * For devices with no IRQ directly connected to the SoC, the RTC chip
  * can be forced as a wakeup source by stating that explicitly in
@@ -1828,10 +1799,8 @@ static int ds1307_probe(struct i2c_client *client,
  * This will guarantee the 'wakealarm' sysfs entry is available on the device,
  * if supported by the RTC.
  */
-	if (chip->alarm && of_property_read_bool(client->dev.of_node,
-						 "wakeup-source"))
+	if (chip->alarm && device_property_read_bool(&client->dev, "wakeup-source"))
 		ds1307_can_wakeup_device = true;
-#endif
 
 	switch (ds1307->type) {
 	case ds_1337:
@@ -2032,7 +2001,7 @@ static int ds1307_probe(struct i2c_client *client,
 	if (err)
 		return err;
 
-	err = rtc_register_device(ds1307->rtc);
+	err = devm_rtc_register_device(ds1307->rtc);
 	if (err)
 		return err;
 
@@ -2047,8 +2016,7 @@ static int ds1307_probe(struct i2c_client *client,
 			.priv = ds1307,
 		};
 
-		ds1307->rtc->nvram_old_abi = true;
-		rtc_nvmem_register(ds1307->rtc, &nvmem_cfg);
+		devm_rtc_nvmem_register(ds1307->rtc, &nvmem_cfg);
 	}
 
 	ds1307_hwmon_register(ds1307);
@@ -2064,8 +2032,7 @@ exit:
 static struct i2c_driver ds1307_driver = {
 	.driver = {
 		.name	= "rtc-ds1307",
-		.of_match_table = of_match_ptr(ds1307_of_match),
-		.acpi_match_table = ACPI_PTR(ds1307_acpi_ids),
+		.of_match_table = ds1307_of_match,
 	},
 	.probe		= ds1307_probe,
 	.id_table	= ds1307_id,
diff --git a/drivers/rtc/rtc-ds1343.c b/drivers/rtc/rtc-ds1343.c
index ba143423875b..f14ed6c96437 100644
--- a/drivers/rtc/rtc-ds1343.c
+++ b/drivers/rtc/rtc-ds1343.c
@@ -399,7 +399,6 @@ static int ds1343_probe(struct spi_device *spi)
 	if (IS_ERR(priv->rtc))
 		return PTR_ERR(priv->rtc);
 
-	priv->rtc->nvram_old_abi = true;
 	priv->rtc->ops = &ds1343_rtc_ops;
 	priv->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	priv->rtc->range_max = RTC_TIMESTAMP_END_2099;
@@ -409,12 +408,12 @@ static int ds1343_probe(struct spi_device *spi)
 		dev_err(&spi->dev,
 			"unable to create sysfs entries for rtc ds1343\n");
 
-	res = rtc_register_device(priv->rtc);
+	res = devm_rtc_register_device(priv->rtc);
 	if (res)
 		return res;
 
 	nvmem_cfg.priv = priv;
-	rtc_nvmem_register(priv->rtc, &nvmem_cfg);
+	devm_rtc_nvmem_register(priv->rtc, &nvmem_cfg);
 
 	priv->irq = spi->irq;
 
diff --git a/drivers/rtc/rtc-ds1347.c b/drivers/rtc/rtc-ds1347.c
index 7025cf3fb9f8..157bf5209ac4 100644
--- a/drivers/rtc/rtc-ds1347.c
+++ b/drivers/rtc/rtc-ds1347.c
@@ -166,7 +166,7 @@ static int ds1347_probe(struct spi_device *spi)
 	rtc->range_min = RTC_TIMESTAMP_BEGIN_0000;
 	rtc->range_max = RTC_TIMESTAMP_END_9999;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct spi_driver ds1347_driver = {
diff --git a/drivers/rtc/rtc-ds1374.c b/drivers/rtc/rtc-ds1374.c
index 177d870bda0d..fab79921a712 100644
--- a/drivers/rtc/rtc-ds1374.c
+++ b/drivers/rtc/rtc-ds1374.c
@@ -508,7 +508,7 @@ static int ds1374_probe(struct i2c_client *client,
 	ds1374->rtc->ops = &ds1374_rtc_ops;
 	ds1374->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(ds1374->rtc);
+	ret = devm_rtc_register_device(ds1374->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-ds1511.c b/drivers/rtc/rtc-ds1511.c
index a63872c4c76d..bda884333082 100644
--- a/drivers/rtc/rtc-ds1511.c
+++ b/drivers/rtc/rtc-ds1511.c
@@ -466,13 +466,11 @@ static int ds1511_rtc_probe(struct platform_device *pdev)
 
 	pdata->rtc->ops = &ds1511_rtc_ops;
 
-	pdata->rtc->nvram_old_abi = true;
-
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (ret)
 		return ret;
 
-	rtc_nvmem_register(pdata->rtc, &ds1511_nvmem_cfg);
+	devm_rtc_nvmem_register(pdata->rtc, &ds1511_nvmem_cfg);
 
 	/*
 	 * if the platform has an interrupt in mind for this device,
diff --git a/drivers/rtc/rtc-ds1553.c b/drivers/rtc/rtc-ds1553.c
index cdf5e05b9489..dbff5b621ef5 100644
--- a/drivers/rtc/rtc-ds1553.c
+++ b/drivers/rtc/rtc-ds1553.c
@@ -294,9 +294,8 @@ static int ds1553_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(pdata->rtc);
 
 	pdata->rtc->ops = &ds1553_rtc_ops;
-	pdata->rtc->nvram_old_abi = true;
 
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (ret)
 		return ret;
 
@@ -310,8 +309,7 @@ static int ds1553_rtc_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (rtc_nvmem_register(pdata->rtc, &nvmem_cfg))
-		dev_err(&pdev->dev, "unable to register nvmem\n");
+	devm_rtc_nvmem_register(pdata->rtc, &nvmem_cfg);
 
 	return 0;
 }
diff --git a/drivers/rtc/rtc-ds1672.c b/drivers/rtc/rtc-ds1672.c
index 9da84df9f152..630493759d15 100644
--- a/drivers/rtc/rtc-ds1672.c
+++ b/drivers/rtc/rtc-ds1672.c
@@ -124,7 +124,7 @@ static int ds1672_probe(struct i2c_client *client,
 	rtc->ops = &ds1672_rtc_ops;
 	rtc->range_max = U32_MAX;
 
-	err = rtc_register_device(rtc);
+	err = devm_rtc_register_device(rtc);
 	if (err)
 		return err;
 
diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c
index dfbd7b88b2b9..d69c807af29b 100644
--- a/drivers/rtc/rtc-ds1685.c
+++ b/drivers/rtc/rtc-ds1685.c
@@ -1316,13 +1316,12 @@ ds1685_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	rtc_dev->nvram_old_abi = true;
 	nvmem_cfg.priv = rtc;
-	ret = rtc_nvmem_register(rtc_dev, &nvmem_cfg);
+	ret = devm_rtc_nvmem_register(rtc_dev, &nvmem_cfg);
 	if (ret)
 		return ret;
 
-	return rtc_register_device(rtc_dev);
+	return devm_rtc_register_device(rtc_dev);
 }
 
 /**
diff --git a/drivers/rtc/rtc-ds1742.c b/drivers/rtc/rtc-ds1742.c
index 2b949f0dbaa9..13d45c697da6 100644
--- a/drivers/rtc/rtc-ds1742.c
+++ b/drivers/rtc/rtc-ds1742.c
@@ -190,14 +190,12 @@ static int ds1742_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(rtc);
 
 	rtc->ops = &ds1742_rtc_ops;
-	rtc->nvram_old_abi = true;
 
-	ret = rtc_register_device(rtc);
+	ret = devm_rtc_register_device(rtc);
 	if (ret)
 		return ret;
 
-	if (rtc_nvmem_register(rtc, &nvmem_cfg))
-		dev_err(&pdev->dev, "Unable to register nvmem\n");
+	devm_rtc_nvmem_register(rtc, &nvmem_cfg);
 
 	return 0;
 }
diff --git a/drivers/rtc/rtc-ds2404.c b/drivers/rtc/rtc-ds2404.c
index 9df0c44512b8..0480f592307e 100644
--- a/drivers/rtc/rtc-ds2404.c
+++ b/drivers/rtc/rtc-ds2404.c
@@ -234,7 +234,7 @@ static int rtc_probe(struct platform_device *pdev)
 	chip->rtc->ops = &ds2404_rtc_ops;
 	chip->rtc->range_max = U32_MAX;
 
-	retval = rtc_register_device(chip->rtc);
+	retval = devm_rtc_register_device(chip->rtc);
 	if (retval)
 		return retval;
 
diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c
index 69c37ab64352..16b89035d135 100644
--- a/drivers/rtc/rtc-ds3232.c
+++ b/drivers/rtc/rtc-ds3232.c
@@ -518,7 +518,7 @@ static int ds3232_probe(struct device *dev, struct regmap *regmap, int irq,
 	if (IS_ERR(ds3232->rtc))
 		return PTR_ERR(ds3232->rtc);
 
-	ret = rtc_nvmem_register(ds3232->rtc, &nvmem_cfg);
+	ret = devm_rtc_nvmem_register(ds3232->rtc, &nvmem_cfg);
 	if(ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-ep93xx.c b/drivers/rtc/rtc-ep93xx.c
index 8ec9ea1ca72e..acae7f16808f 100644
--- a/drivers/rtc/rtc-ep93xx.c
+++ b/drivers/rtc/rtc-ep93xx.c
@@ -33,7 +33,7 @@ struct ep93xx_rtc {
 static int ep93xx_rtc_get_swcomp(struct device *dev, unsigned short *preload,
 				 unsigned short *delete)
 {
-	struct ep93xx_rtc *ep93xx_rtc = dev_get_platdata(dev);
+	struct ep93xx_rtc *ep93xx_rtc = dev_get_drvdata(dev);
 	unsigned long comp;
 
 	comp = readl(ep93xx_rtc->mmio_base + EP93XX_RTC_SWCOMP);
@@ -51,7 +51,7 @@ static int ep93xx_rtc_get_swcomp(struct device *dev, unsigned short *preload,
 
 static int ep93xx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
-	struct ep93xx_rtc *ep93xx_rtc = dev_get_platdata(dev);
+	struct ep93xx_rtc *ep93xx_rtc = dev_get_drvdata(dev);
 	unsigned long time;
 
 	time = readl(ep93xx_rtc->mmio_base + EP93XX_RTC_DATA);
@@ -62,7 +62,7 @@ static int ep93xx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 
 static int ep93xx_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
-	struct ep93xx_rtc *ep93xx_rtc = dev_get_platdata(dev);
+	struct ep93xx_rtc *ep93xx_rtc = dev_get_drvdata(dev);
 	unsigned long secs = rtc_tm_to_time64(tm);
 
 	writel(secs + 1, ep93xx_rtc->mmio_base + EP93XX_RTC_LOAD);
@@ -145,7 +145,7 @@ static int ep93xx_rtc_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	return rtc_register_device(ep93xx_rtc->rtc);
+	return devm_rtc_register_device(ep93xx_rtc->rtc);
 }
 
 static struct platform_driver ep93xx_rtc_driver = {
diff --git a/drivers/rtc/rtc-fsl-ftm-alarm.c b/drivers/rtc/rtc-fsl-ftm-alarm.c
index 48d3b38ea348..57cc09d0a806 100644
--- a/drivers/rtc/rtc-fsl-ftm-alarm.c
+++ b/drivers/rtc/rtc-fsl-ftm-alarm.c
@@ -290,7 +290,7 @@ static int ftm_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		dev_err(&pdev->dev, "failed to enable irq wake\n");
 
-	ret = rtc_register_device(rtc->rtc_dev);
+	ret = devm_rtc_register_device(rtc->rtc_dev);
 	if (ret) {
 		dev_err(&pdev->dev, "can't register rtc device\n");
 		return ret;
diff --git a/drivers/rtc/rtc-ftrtc010.c b/drivers/rtc/rtc-ftrtc010.c
index 0919f7dc94a3..ad3add5db4c8 100644
--- a/drivers/rtc/rtc-ftrtc010.c
+++ b/drivers/rtc/rtc-ftrtc010.c
@@ -176,7 +176,7 @@ static int ftrtc010_rtc_probe(struct platform_device *pdev)
 	if (unlikely(ret))
 		return ret;
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 static int ftrtc010_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-goldfish.c b/drivers/rtc/rtc-goldfish.c
index 6349d2cd3680..7ab95d052644 100644
--- a/drivers/rtc/rtc-goldfish.c
+++ b/drivers/rtc/rtc-goldfish.c
@@ -194,7 +194,7 @@ static int goldfish_rtc_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	return rtc_register_device(rtcdrv->rtc);
+	return devm_rtc_register_device(rtcdrv->rtc);
 }
 
 static const struct of_device_id goldfish_rtc_of_match[] = {
diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c
index 0fb79c4afb46..24e0095be058 100644
--- a/drivers/rtc/rtc-hym8563.c
+++ b/drivers/rtc/rtc-hym8563.c
@@ -527,8 +527,6 @@ static int hym8563_probe(struct i2c_client *client,
 	hym8563->client = client;
 	i2c_set_clientdata(client, hym8563);
 
-	device_set_wakeup_capable(&client->dev, true);
-
 	ret = hym8563_init_device(client);
 	if (ret) {
 		dev_err(&client->dev, "could not init device, %d\n", ret);
@@ -547,6 +545,11 @@ static int hym8563_probe(struct i2c_client *client,
 		}
 	}
 
+	if (client->irq > 0 ||
+	    device_property_read_bool(&client->dev, "wakeup-source")) {
+		device_init_wakeup(&client->dev, true);
+	}
+
 	/* check state of calendar information */
 	ret = i2c_smbus_read_byte_data(client, HYM8563_SEC);
 	if (ret < 0)
diff --git a/drivers/rtc/rtc-imx-sc.c b/drivers/rtc/rtc-imx-sc.c
index a5f59e6f862e..cc9fbab49999 100644
--- a/drivers/rtc/rtc-imx-sc.c
+++ b/drivers/rtc/rtc-imx-sc.c
@@ -166,7 +166,7 @@ static int imx_sc_rtc_probe(struct platform_device *pdev)
 	imx_sc_rtc->range_min = 0;
 	imx_sc_rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(imx_sc_rtc);
+	ret = devm_rtc_register_device(imx_sc_rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-imxdi.c b/drivers/rtc/rtc-imxdi.c
index 8d141d8a5490..c2692da74e09 100644
--- a/drivers/rtc/rtc-imxdi.c
+++ b/drivers/rtc/rtc-imxdi.c
@@ -814,7 +814,7 @@ static int __init dryice_rtc_probe(struct platform_device *pdev)
 	imxdi->rtc->ops = &dryice_rtc_ops;
 	imxdi->rtc->range_max = U32_MAX;
 
-	rc = rtc_register_device(imxdi->rtc);
+	rc = devm_rtc_register_device(imxdi->rtc);
 	if (rc)
 		goto err;
 
diff --git a/drivers/rtc/rtc-isl12026.c b/drivers/rtc/rtc-isl12026.c
index 5b6b17fb6d62..1fc6627d854d 100644
--- a/drivers/rtc/rtc-isl12026.c
+++ b/drivers/rtc/rtc-isl12026.c
@@ -465,11 +465,11 @@ static int isl12026_probe_new(struct i2c_client *client)
 
 	priv->rtc->ops = &isl12026_rtc_ops;
 	nvm_cfg.priv = priv;
-	ret = rtc_nvmem_register(priv->rtc, &nvm_cfg);
+	ret = devm_rtc_nvmem_register(priv->rtc, &nvm_cfg);
 	if (ret)
 		return ret;
 
-	return rtc_register_device(priv->rtc);
+	return devm_rtc_register_device(priv->rtc);
 }
 
 static int isl12026_remove(struct i2c_client *client)
diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c
index ebb691fa48a6..563a6d9c9fcf 100644
--- a/drivers/rtc/rtc-isl1208.c
+++ b/drivers/rtc/rtc-isl1208.c
@@ -890,11 +890,11 @@ isl1208_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	if (rc)
 		return rc;
 
-	rc = rtc_nvmem_register(isl1208->rtc, &isl1208->nvmem_config);
+	rc = devm_rtc_nvmem_register(isl1208->rtc, &isl1208->nvmem_config);
 	if (rc)
 		return rc;
 
-	return rtc_register_device(isl1208->rtc);
+	return devm_rtc_register_device(isl1208->rtc);
 }
 
 static struct i2c_driver isl1208_driver = {
diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index 9607e6b6e0b3..6e51df72fd65 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -375,7 +375,7 @@ static int jz4740_rtc_probe(struct platform_device *pdev)
 	/* Each 1 Hz pulse should happen after (rate) ticks */
 	jz4740_rtc_reg_write(rtc, JZ_REG_RTC_REGULATOR, rate - 1);
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-lpc32xx.c b/drivers/rtc/rtc-lpc32xx.c
index 15d8abda81fe..76ad7031a13d 100644
--- a/drivers/rtc/rtc-lpc32xx.c
+++ b/drivers/rtc/rtc-lpc32xx.c
@@ -239,7 +239,7 @@ static int lpc32xx_rtc_probe(struct platform_device *pdev)
 	rtc->rtc->ops = &lpc32xx_rtc_ops;
 	rtc->rtc->range_max = U32_MAX;
 
-	err = rtc_register_device(rtc->rtc);
+	err = devm_rtc_register_device(rtc->rtc);
 	if (err)
 		return err;
 
diff --git a/drivers/rtc/rtc-ls1x.c b/drivers/rtc/rtc-ls1x.c
index 8bd34056fea0..5af26dc5c2a3 100644
--- a/drivers/rtc/rtc-ls1x.c
+++ b/drivers/rtc/rtc-ls1x.c
@@ -176,7 +176,7 @@ static int ls1x_rtc_probe(struct platform_device *pdev)
 	rtcdev->range_min = RTC_TIMESTAMP_BEGIN_1900;
 	rtcdev->range_max = RTC_TIMESTAMP_END_2099;
 
-	return rtc_register_device(rtcdev);
+	return devm_rtc_register_device(rtcdev);
 }
 
 static struct platform_driver  ls1x_rtc_driver = {
diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c
index 8a89bc52b0d4..160dcf68e64e 100644
--- a/drivers/rtc/rtc-m41t80.c
+++ b/drivers/rtc/rtc-m41t80.c
@@ -977,7 +977,7 @@ static int m41t80_probe(struct i2c_client *client,
 		m41t80_sqw_register_clk(m41t80_data);
 #endif
 
-	rc = rtc_register_device(m41t80_data->rtc);
+	rc = devm_rtc_register_device(m41t80_data->rtc);
 	if (rc)
 		return rc;
 
diff --git a/drivers/rtc/rtc-m48t59.c b/drivers/rtc/rtc-m48t59.c
index 67e218758a8b..5f5898d3b055 100644
--- a/drivers/rtc/rtc-m48t59.c
+++ b/drivers/rtc/rtc-m48t59.c
@@ -463,15 +463,14 @@ static int m48t59_rtc_probe(struct platform_device *pdev)
 	if (IS_ERR(m48t59->rtc))
 		return PTR_ERR(m48t59->rtc);
 
-	m48t59->rtc->nvram_old_abi = true;
 	m48t59->rtc->ops = ops;
 
 	nvmem_cfg.size = pdata->offset;
-	ret = rtc_nvmem_register(m48t59->rtc, &nvmem_cfg);
+	ret = devm_rtc_nvmem_register(m48t59->rtc, &nvmem_cfg);
 	if (ret)
 		return ret;
 
-	ret = rtc_register_device(m48t59->rtc);
+	ret = devm_rtc_register_device(m48t59->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-m48t86.c b/drivers/rtc/rtc-m48t86.c
index 75a0e73071d8..481c9525b1dd 100644
--- a/drivers/rtc/rtc-m48t86.c
+++ b/drivers/rtc/rtc-m48t86.c
@@ -254,13 +254,12 @@ static int m48t86_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(info->rtc);
 
 	info->rtc->ops = &m48t86_rtc_ops;
-	info->rtc->nvram_old_abi = true;
 
-	err = rtc_register_device(info->rtc);
+	err = devm_rtc_register_device(info->rtc);
 	if (err)
 		return err;
 
-	rtc_nvmem_register(info->rtc, &m48t86_nvmem_cfg);
+	devm_rtc_nvmem_register(info->rtc, &m48t86_nvmem_cfg);
 
 	/* read battery status */
 	reg = m48t86_readb(&pdev->dev, M48T86_D);
diff --git a/drivers/rtc/rtc-mc13xxx.c b/drivers/rtc/rtc-mc13xxx.c
index d6802e6191cb..d4234e78497e 100644
--- a/drivers/rtc/rtc-mc13xxx.c
+++ b/drivers/rtc/rtc-mc13xxx.c
@@ -307,7 +307,7 @@ static int __init mc13xxx_rtc_probe(struct platform_device *pdev)
 
 	mc13xxx_unlock(mc13xxx);
 
-	ret = rtc_register_device(priv->rtc);
+	ret = devm_rtc_register_device(priv->rtc);
 	if (ret) {
 		mc13xxx_lock(mc13xxx);
 		goto err_irq_request;
diff --git a/drivers/rtc/rtc-meson-vrtc.c b/drivers/rtc/rtc-meson-vrtc.c
index e6bd0808a092..1463c8621561 100644
--- a/drivers/rtc/rtc-meson-vrtc.c
+++ b/drivers/rtc/rtc-meson-vrtc.c
@@ -83,7 +83,7 @@ static int meson_vrtc_probe(struct platform_device *pdev)
 		return PTR_ERR(vrtc->rtc);
 
 	vrtc->rtc->ops = &meson_vrtc_ops;
-	return rtc_register_device(vrtc->rtc);
+	return devm_rtc_register_device(vrtc->rtc);
 }
 
 static int __maybe_unused meson_vrtc_suspend(struct device *dev)
diff --git a/drivers/rtc/rtc-meson.c b/drivers/rtc/rtc-meson.c
index 47ebcf834cc2..8642c06565ea 100644
--- a/drivers/rtc/rtc-meson.c
+++ b/drivers/rtc/rtc-meson.c
@@ -365,11 +365,11 @@ static int meson_rtc_probe(struct platform_device *pdev)
 	}
 
 	meson_rtc_nvmem_config.priv = rtc;
-	ret = rtc_nvmem_register(rtc->rtc, &meson_rtc_nvmem_config);
+	ret = devm_rtc_nvmem_register(rtc->rtc, &meson_rtc_nvmem_config);
 	if (ret)
 		goto out_disable_vdd;
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
 		goto out_disable_vdd;
 
diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c
index 5c2ce71aa044..bb2ea9bc56f2 100644
--- a/drivers/rtc/rtc-mpc5121.c
+++ b/drivers/rtc/rtc-mpc5121.c
@@ -371,7 +371,7 @@ static int mpc5121_rtc_probe(struct platform_device *op)
 		rtc->rtc->range_max = U32_MAX;
 	}
 
-	err = rtc_register_device(rtc->rtc);
+	err = devm_rtc_register_device(rtc->rtc);
 	if (err)
 		goto out_dispose2;
 
diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c
index 17bf5394e1e5..421b3b6071b6 100644
--- a/drivers/rtc/rtc-mrst.c
+++ b/drivers/rtc/rtc-mrst.c
@@ -361,7 +361,7 @@ static int vrtc_mrst_do_probe(struct device *dev, struct resource *iomem,
 		}
 	}
 
-	retval = rtc_register_device(mrst_rtc.rtc);
+	retval = devm_rtc_register_device(mrst_rtc.rtc);
 	if (retval)
 		goto cleanup0;
 
diff --git a/drivers/rtc/rtc-mt2712.c b/drivers/rtc/rtc-mt2712.c
index d5f691c8a035..cd92a9788351 100644
--- a/drivers/rtc/rtc-mt2712.c
+++ b/drivers/rtc/rtc-mt2712.c
@@ -352,7 +352,7 @@ static int mt2712_rtc_probe(struct platform_device *pdev)
 	mt2712_rtc->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	mt2712_rtc->rtc->range_max = MT2712_RTC_TIMESTAMP_END_2127;
 
-	return rtc_register_device(mt2712_rtc->rtc);
+	return devm_rtc_register_device(mt2712_rtc->rtc);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index 1894aded4c85..6655035e5164 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -301,7 +301,7 @@ static int mtk_rtc_probe(struct platform_device *pdev)
 
 	rtc->rtc_dev->ops = &mtk_rtc_ops;
 
-	return rtc_register_device(rtc->rtc_dev);
+	return devm_rtc_register_device(rtc->rtc_dev);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-mv.c b/drivers/rtc/rtc-mv.c
index d5f190e578e4..f8e2ecea1d8d 100644
--- a/drivers/rtc/rtc-mv.c
+++ b/drivers/rtc/rtc-mv.c
@@ -278,7 +278,7 @@ static int __init mv_rtc_probe(struct platform_device *pdev)
 	pdata->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	pdata->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (!ret)
 		return 0;
 out:
diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c
index a8cfbde048f4..65b29b0fa548 100644
--- a/drivers/rtc/rtc-mxc.c
+++ b/drivers/rtc/rtc-mxc.c
@@ -70,27 +70,12 @@ struct rtc_plat_data {
 	enum imx_rtc_type devtype;
 };
 
-static const struct platform_device_id imx_rtc_devtype[] = {
-	{
-		.name = "imx1-rtc",
-		.driver_data = IMX1_RTC,
-	}, {
-		.name = "imx21-rtc",
-		.driver_data = IMX21_RTC,
-	}, {
-		/* sentinel */
-	}
-};
-MODULE_DEVICE_TABLE(platform, imx_rtc_devtype);
-
-#ifdef CONFIG_OF
 static const struct of_device_id imx_rtc_dt_ids[] = {
 	{ .compatible = "fsl,imx1-rtc", .data = (const void *)IMX1_RTC },
 	{ .compatible = "fsl,imx21-rtc", .data = (const void *)IMX21_RTC },
 	{}
 };
 MODULE_DEVICE_TABLE(of, imx_rtc_dt_ids);
-#endif
 
 static inline int is_imx1_rtc(struct rtc_plat_data *data)
 {
@@ -322,17 +307,12 @@ static int mxc_rtc_probe(struct platform_device *pdev)
 	u32 reg;
 	unsigned long rate;
 	int ret;
-	const struct of_device_id *of_id;
 
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return -ENOMEM;
 
-	of_id = of_match_device(imx_rtc_dt_ids, &pdev->dev);
-	if (of_id)
-		pdata->devtype = (enum imx_rtc_type)of_id->data;
-	else
-		pdata->devtype = pdev->id_entry->driver_data;
+	pdata->devtype = (enum imx_rtc_type)of_device_get_match_data(&pdev->dev);
 
 	pdata->ioaddr = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(pdata->ioaddr))
@@ -428,7 +408,7 @@ static int mxc_rtc_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "failed to enable irq wake\n");
 	}
 
-	ret = rtc_register_device(rtc);
+	ret = devm_rtc_register_device(rtc);
 
 	return ret;
 }
@@ -438,7 +418,6 @@ static struct platform_driver mxc_rtc_driver = {
 		   .name	= "mxc_rtc",
 		   .of_match_table = of_match_ptr(imx_rtc_dt_ids),
 	},
-	.id_table = imx_rtc_devtype,
 	.probe = mxc_rtc_probe,
 };
 
diff --git a/drivers/rtc/rtc-mxc_v2.c b/drivers/rtc/rtc-mxc_v2.c
index 91534560fe2a..0d73f6f0cf9e 100644
--- a/drivers/rtc/rtc-mxc_v2.c
+++ b/drivers/rtc/rtc-mxc_v2.c
@@ -354,7 +354,7 @@ static int mxc_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (ret < 0)
 		clk_unprepare(pdata->clk);
 
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index c20fc7937dfa..dc7db2477f88 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -879,18 +879,18 @@ static int omap_rtc_probe(struct platform_device *pdev)
 	/* Support ext_wakeup pinconf */
 	rtc_pinctrl_desc.name = dev_name(&pdev->dev);
 
-	rtc->pctldev = pinctrl_register(&rtc_pinctrl_desc, &pdev->dev, rtc);
+	rtc->pctldev = devm_pinctrl_register(&pdev->dev, &rtc_pinctrl_desc, rtc);
 	if (IS_ERR(rtc->pctldev)) {
 		dev_err(&pdev->dev, "Couldn't register pinctrl driver\n");
 		ret = PTR_ERR(rtc->pctldev);
 		goto err;
 	}
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
-		goto err_deregister_pinctrl;
+		goto err;
 
-	rtc_nvmem_register(rtc->rtc, &omap_rtc_nvmem_config);
+	devm_rtc_nvmem_register(rtc->rtc, &omap_rtc_nvmem_config);
 
 	if (rtc->is_pmic_controller) {
 		if (!pm_power_off) {
@@ -901,8 +901,6 @@ static int omap_rtc_probe(struct platform_device *pdev)
 
 	return 0;
 
-err_deregister_pinctrl:
-	pinctrl_unregister(rtc->pctldev);
 err:
 	clk_disable_unprepare(rtc->clk);
 	device_init_wakeup(&pdev->dev, false);
@@ -945,9 +943,6 @@ static int omap_rtc_remove(struct platform_device *pdev)
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
-	/* Remove ext_wakeup pinconf */
-	pinctrl_unregister(rtc->pctldev);
-
 	return 0;
 }
 
diff --git a/drivers/rtc/rtc-pcap.c b/drivers/rtc/rtc-pcap.c
index 178bfb1dea21..8c7a98a5452c 100644
--- a/drivers/rtc/rtc-pcap.c
+++ b/drivers/rtc/rtc-pcap.c
@@ -163,7 +163,7 @@ static int __init pcap_rtc_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	return rtc_register_device(pcap_rtc->rtc);
+	return devm_rtc_register_device(pcap_rtc->rtc);
 }
 
 static int __exit pcap_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-pcf2123.c b/drivers/rtc/rtc-pcf2123.c
index c3691fa4210e..534ffc91eec1 100644
--- a/drivers/rtc/rtc-pcf2123.c
+++ b/drivers/rtc/rtc-pcf2123.c
@@ -434,7 +434,7 @@ static int pcf2123_probe(struct spi_device *spi)
 	rtc->range_max = RTC_TIMESTAMP_END_2099;
 	rtc->set_start_time = true;
 
-	ret = rtc_register_device(rtc);
+	ret = devm_rtc_register_device(rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 07a5630ec841..39a7b5116aa4 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -243,10 +243,8 @@ static int pcf2127_nvmem_read(void *priv, unsigned int offset,
 	if (ret)
 		return ret;
 
-	ret = regmap_bulk_read(pcf2127->regmap, PCF2127_REG_RAM_RD_CMD,
-			       val, bytes);
-
-	return ret ?: bytes;
+	return regmap_bulk_read(pcf2127->regmap, PCF2127_REG_RAM_RD_CMD,
+				val, bytes);
 }
 
 static int pcf2127_nvmem_write(void *priv, unsigned int offset,
@@ -261,10 +259,8 @@ static int pcf2127_nvmem_write(void *priv, unsigned int offset,
 	if (ret)
 		return ret;
 
-	ret = regmap_bulk_write(pcf2127->regmap, PCF2127_REG_RAM_WRT_CMD,
-				val, bytes);
-
-	return ret ?: bytes;
+	return regmap_bulk_write(pcf2127->regmap, PCF2127_REG_RAM_WRT_CMD,
+				 val, bytes);
 }
 
 /* watchdog driver */
@@ -335,6 +331,37 @@ static const struct watchdog_ops pcf2127_watchdog_ops = {
 	.set_timeout = pcf2127_wdt_set_timeout,
 };
 
+static int pcf2127_watchdog_init(struct device *dev, struct pcf2127 *pcf2127)
+{
+	u32 wdd_timeout;
+	int ret;
+
+	if (!IS_ENABLED(CONFIG_WATCHDOG) ||
+	    !device_property_read_bool(dev, "reset-source"))
+		return 0;
+
+	pcf2127->wdd.parent = dev;
+	pcf2127->wdd.info = &pcf2127_wdt_info;
+	pcf2127->wdd.ops = &pcf2127_watchdog_ops;
+	pcf2127->wdd.min_timeout = PCF2127_WD_VAL_MIN;
+	pcf2127->wdd.max_timeout = PCF2127_WD_VAL_MAX;
+	pcf2127->wdd.timeout = PCF2127_WD_VAL_DEFAULT;
+	pcf2127->wdd.min_hw_heartbeat_ms = 500;
+	pcf2127->wdd.status = WATCHDOG_NOWAYOUT_INIT_STATUS;
+
+	watchdog_set_drvdata(&pcf2127->wdd, pcf2127);
+
+	/* Test if watchdog timer is started by bootloader */
+	ret = regmap_read(pcf2127->regmap, PCF2127_REG_WD_VAL, &wdd_timeout);
+	if (ret)
+		return ret;
+
+	if (wdd_timeout)
+		set_bit(WDOG_HW_RUNNING, &pcf2127->wdd.status);
+
+	return devm_watchdog_register_device(dev, &pcf2127->wdd);
+}
+
 /* Alarm */
 static int pcf2127_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 {
@@ -536,7 +563,6 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 			 int alarm_irq, const char *name, bool has_nvmem)
 {
 	struct pcf2127 *pcf2127;
-	u32 wdd_timeout;
 	int ret = 0;
 
 	dev_dbg(dev, "%s\n", __func__);
@@ -575,17 +601,6 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 		pcf2127->rtc->ops = &pcf2127_rtc_alrm_ops;
 	}
 
-	pcf2127->wdd.parent = dev;
-	pcf2127->wdd.info = &pcf2127_wdt_info;
-	pcf2127->wdd.ops = &pcf2127_watchdog_ops;
-	pcf2127->wdd.min_timeout = PCF2127_WD_VAL_MIN;
-	pcf2127->wdd.max_timeout = PCF2127_WD_VAL_MAX;
-	pcf2127->wdd.timeout = PCF2127_WD_VAL_DEFAULT;
-	pcf2127->wdd.min_hw_heartbeat_ms = 500;
-	pcf2127->wdd.status = WATCHDOG_NOWAYOUT_INIT_STATUS;
-
-	watchdog_set_drvdata(&pcf2127->wdd, pcf2127);
-
 	if (has_nvmem) {
 		struct nvmem_config nvmem_cfg = {
 			.priv = pcf2127,
@@ -594,7 +609,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 			.size = 512,
 		};
 
-		ret = rtc_nvmem_register(pcf2127->rtc, &nvmem_cfg);
+		ret = devm_rtc_nvmem_register(pcf2127->rtc, &nvmem_cfg);
 	}
 
 	/*
@@ -615,19 +630,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 		return ret;
 	}
 
-	/* Test if watchdog timer is started by bootloader */
-	ret = regmap_read(pcf2127->regmap, PCF2127_REG_WD_VAL, &wdd_timeout);
-	if (ret)
-		return ret;
-
-	if (wdd_timeout)
-		set_bit(WDOG_HW_RUNNING, &pcf2127->wdd.status);
-
-#ifdef CONFIG_WATCHDOG
-	ret = devm_watchdog_register_device(dev, &pcf2127->wdd);
-	if (ret)
-		return ret;
-#endif /* CONFIG_WATCHDOG */
+	pcf2127_watchdog_init(dev, pcf2127);
 
 	/*
 	 * Disable battery low/switch-over timestamp and interrupts.
@@ -680,7 +683,7 @@ static int pcf2127_probe(struct device *dev, struct regmap *regmap,
 		return ret;
 	}
 
-	return rtc_register_device(pcf2127->rtc);
+	return devm_rtc_register_device(pcf2127->rtc);
 }
 
 #ifdef CONFIG_OF
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index f8b99cb72959..e19cf2adbc35 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -607,14 +607,14 @@ static int pcf85063_probe(struct i2c_client *client)
 	}
 
 	nvmem_cfg.priv = pcf85063->regmap;
-	rtc_nvmem_register(pcf85063->rtc, &nvmem_cfg);
+	devm_rtc_nvmem_register(pcf85063->rtc, &nvmem_cfg);
 
 #ifdef CONFIG_COMMON_CLK
 	/* register clk in common clk framework */
 	pcf85063_clkout_register_clk(pcf85063);
 #endif
 
-	return rtc_register_device(pcf85063->rtc);
+	return devm_rtc_register_device(pcf85063->rtc);
 }
 
 #ifdef CONFIG_OF
diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c
index 57d351dfe272..5e1e7b2a8c9a 100644
--- a/drivers/rtc/rtc-pcf8523.c
+++ b/drivers/rtc/rtc-pcf8523.c
@@ -12,18 +12,18 @@
 #define DRIVER_NAME "rtc-pcf8523"
 
 #define REG_CONTROL1 0x00
-#define REG_CONTROL1_CAP_SEL (1 << 7)
-#define REG_CONTROL1_STOP    (1 << 5)
+#define REG_CONTROL1_CAP_SEL BIT(7)
+#define REG_CONTROL1_STOP    BIT(5)
 
 #define REG_CONTROL3 0x02
-#define REG_CONTROL3_PM_BLD (1 << 7) /* battery low detection disabled */
-#define REG_CONTROL3_PM_VDD (1 << 6) /* switch-over disabled */
-#define REG_CONTROL3_PM_DSM (1 << 5) /* direct switching mode */
+#define REG_CONTROL3_PM_BLD BIT(7) /* battery low detection disabled */
+#define REG_CONTROL3_PM_VDD BIT(6) /* switch-over disabled */
+#define REG_CONTROL3_PM_DSM BIT(5) /* direct switching mode */
 #define REG_CONTROL3_PM_MASK 0xe0
-#define REG_CONTROL3_BLF (1 << 2) /* battery low bit, read-only */
+#define REG_CONTROL3_BLF BIT(2) /* battery low bit, read-only */
 
 #define REG_SECONDS  0x03
-#define REG_SECONDS_OS (1 << 7)
+#define REG_SECONDS_OS BIT(7)
 
 #define REG_MINUTES  0x04
 #define REG_HOURS    0x05
@@ -226,17 +226,6 @@ static int pcf8523_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	u8 regs[8];
 	int err;
 
-	/*
-	 * The hardware can only store values between 0 and 99 in it's YEAR
-	 * register (with 99 overflowing to 0 on increment).
-	 * After 2100-02-28 we could start interpreting the year to be in the
-	 * interval [2100, 2199], but there is no path to switch in a smooth way
-	 * because the chip handles YEAR=0x00 (and the out-of-spec
-	 * YEAR=0xa0) as a leap year, but 2100 isn't.
-	 */
-	if (tm->tm_year < 100 || tm->tm_year >= 200)
-		return -EINVAL;
-
 	err = pcf8523_stop_rtc(client);
 	if (err < 0)
 		return err;
@@ -356,12 +345,15 @@ static int pcf8523_probe(struct i2c_client *client,
 	if (err < 0)
 		return err;
 
-	rtc = devm_rtc_device_register(&client->dev, DRIVER_NAME,
-				       &pcf8523_rtc_ops, THIS_MODULE);
+	rtc = devm_rtc_allocate_device(&client->dev);
 	if (IS_ERR(rtc))
 		return PTR_ERR(rtc);
 
-	return 0;
+	rtc->ops = &pcf8523_rtc_ops;
+	rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
+	rtc->range_max = RTC_TIMESTAMP_END_2099;
+
+	return devm_rtc_register_device(rtc);
 }
 
 static const struct i2c_device_id pcf8523_id[] = {
diff --git a/drivers/rtc/rtc-pcf85363.c b/drivers/rtc/rtc-pcf85363.c
index 3450d615974d..a574c8d15a5c 100644
--- a/drivers/rtc/rtc-pcf85363.c
+++ b/drivers/rtc/rtc-pcf85363.c
@@ -418,11 +418,11 @@ static int pcf85363_probe(struct i2c_client *client,
 			pcf85363->rtc->ops = &rtc_ops_alarm;
 	}
 
-	ret = rtc_register_device(pcf85363->rtc);
+	ret = devm_rtc_register_device(pcf85363->rtc);
 
 	for (i = 0; i < config->num_nvram; i++) {
 		nvmem_cfg[i].priv = pcf85363;
-		rtc_nvmem_register(pcf85363->rtc, &nvmem_cfg[i]);
+		devm_rtc_nvmem_register(pcf85363->rtc, &nvmem_cfg[i]);
 	}
 
 	return ret;
diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c
index 2dc30eafa639..de3e6c355f2e 100644
--- a/drivers/rtc/rtc-pcf8563.c
+++ b/drivers/rtc/rtc-pcf8563.c
@@ -582,7 +582,7 @@ static int pcf8563_probe(struct i2c_client *client,
 		}
 	}
 
-	err = rtc_register_device(pcf8563->rtc);
+	err = devm_rtc_register_device(pcf8563->rtc);
 	if (err)
 		return err;
 
diff --git a/drivers/rtc/rtc-pic32.c b/drivers/rtc/rtc-pic32.c
index 2b6946744654..7fb9145c43bd 100644
--- a/drivers/rtc/rtc-pic32.c
+++ b/drivers/rtc/rtc-pic32.c
@@ -338,7 +338,7 @@ static int pic32_rtc_probe(struct platform_device *pdev)
 	pdata->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	pdata->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (ret)
 		goto err_nortc;
 
diff --git a/drivers/rtc/rtc-pl030.c b/drivers/rtc/rtc-pl030.c
index ebe03eba8f5f..5a880516f3e8 100644
--- a/drivers/rtc/rtc-pl030.c
+++ b/drivers/rtc/rtc-pl030.c
@@ -121,7 +121,7 @@ static int pl030_probe(struct amba_device *dev, const struct amba_id *id)
 	if (ret)
 		goto err_irq;
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
 		goto err_reg;
 
diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c
index c6b89273feba..224bbf096262 100644
--- a/drivers/rtc/rtc-pl031.c
+++ b/drivers/rtc/rtc-pl031.c
@@ -361,14 +361,16 @@ static int pl031_probe(struct amba_device *adev, const struct amba_id *id)
 
 	device_init_wakeup(&adev->dev, true);
 	ldata->rtc = devm_rtc_allocate_device(&adev->dev);
-	if (IS_ERR(ldata->rtc))
-		return PTR_ERR(ldata->rtc);
+	if (IS_ERR(ldata->rtc)) {
+		ret = PTR_ERR(ldata->rtc);
+		goto out;
+	}
 
 	ldata->rtc->ops = ops;
 	ldata->rtc->range_min = vendor->range_min;
 	ldata->rtc->range_max = vendor->range_max;
 
-	ret = rtc_register_device(ldata->rtc);
+	ret = devm_rtc_register_device(ldata->rtc);
 	if (ret)
 		goto out;
 
diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c
index b45ee2cb2c04..0d9dd6faabba 100644
--- a/drivers/rtc/rtc-pm8xxx.c
+++ b/drivers/rtc/rtc-pm8xxx.c
@@ -508,7 +508,7 @@ static int pm8xxx_rtc_probe(struct platform_device *pdev)
 		return rc;
 	}
 
-	return rtc_register_device(rtc_dd->rtc);
+	return devm_rtc_register_device(rtc_dd->rtc);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-ps3.c b/drivers/rtc/rtc-ps3.c
index f0336d691e6c..6b098734c715 100644
--- a/drivers/rtc/rtc-ps3.c
+++ b/drivers/rtc/rtc-ps3.c
@@ -56,7 +56,7 @@ static int __init ps3_rtc_probe(struct platform_device *dev)
 
 	platform_set_drvdata(dev, rtc);
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver ps3_rtc_driver = {
diff --git a/drivers/rtc/rtc-r9701.c b/drivers/rtc/rtc-r9701.c
index 7ceb968f0e44..60a3c3d7499b 100644
--- a/drivers/rtc/rtc-r9701.c
+++ b/drivers/rtc/rtc-r9701.c
@@ -127,7 +127,7 @@ static int r9701_probe(struct spi_device *spi)
 	rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct spi_driver r9701_driver = {
diff --git a/drivers/rtc/rtc-rc5t619.c b/drivers/rtc/rtc-rc5t619.c
index dd1a20977478..e73102a39f1b 100644
--- a/drivers/rtc/rtc-rc5t619.c
+++ b/drivers/rtc/rtc-rc5t619.c
@@ -426,7 +426,7 @@ static int rc5t619_rtc_probe(struct platform_device *pdev)
 		dev_warn(&pdev->dev, "rc5t619 interrupt is disabled\n");
 	}
 
-	return rtc_register_device(rtc->rtc);
+	return devm_rtc_register_device(rtc->rtc);
 }
 
 static struct platform_driver rc5t619_rtc_driver = {
diff --git a/drivers/rtc/rtc-rk808.c b/drivers/rtc/rtc-rk808.c
index c0334c602e88..e920da8c08da 100644
--- a/drivers/rtc/rtc-rk808.c
+++ b/drivers/rtc/rtc-rk808.c
@@ -447,7 +447,7 @@ static int rk808_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	return rtc_register_device(rk808_rtc->rtc);
+	return devm_rtc_register_device(rk808_rtc->rtc);
 }
 
 static struct platform_driver rk808_rtc_driver = {
diff --git a/drivers/rtc/rtc-rp5c01.c b/drivers/rtc/rtc-rp5c01.c
index 8776eadbdd3a..44afa6d996e7 100644
--- a/drivers/rtc/rtc-rp5c01.c
+++ b/drivers/rtc/rtc-rp5c01.c
@@ -251,16 +251,15 @@ static int __init rp5c01_rtc_probe(struct platform_device *dev)
 		return PTR_ERR(rtc);
 
 	rtc->ops = &rp5c01_rtc_ops;
-	rtc->nvram_old_abi = true;
 
 	priv->rtc = rtc;
 
 	nvmem_cfg.priv = priv;
-	error = rtc_nvmem_register(rtc, &nvmem_cfg);
+	error = devm_rtc_nvmem_register(rtc, &nvmem_cfg);
 	if (error)
 		return error;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver rp5c01_rtc_driver = {
diff --git a/drivers/rtc/rtc-rs5c348.c b/drivers/rtc/rtc-rs5c348.c
index 47c13678449e..fec633f80789 100644
--- a/drivers/rtc/rtc-rs5c348.c
+++ b/drivers/rtc/rtc-rs5c348.c
@@ -197,7 +197,7 @@ static int rs5c348_probe(struct spi_device *spi)
 
 	rtc->ops = &rs5c348_rtc_ops;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct spi_driver rs5c348_driver = {
diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c
index fa226f0fe67d..979407a51c7a 100644
--- a/drivers/rtc/rtc-rv3028.c
+++ b/drivers/rtc/rtc-rv3028.c
@@ -886,14 +886,14 @@ static int rv3028_probe(struct i2c_client *client)
 	rv3028->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rv3028->rtc->range_max = RTC_TIMESTAMP_END_2099;
 	rv3028->rtc->ops = &rv3028_rtc_ops;
-	ret = rtc_register_device(rv3028->rtc);
+	ret = devm_rtc_register_device(rv3028->rtc);
 	if (ret)
 		return ret;
 
 	nvmem_cfg.priv = rv3028->regmap;
-	rtc_nvmem_register(rv3028->rtc, &nvmem_cfg);
+	devm_rtc_nvmem_register(rv3028->rtc, &nvmem_cfg);
 	eeprom_cfg.priv = rv3028;
-	rtc_nvmem_register(rv3028->rtc, &eeprom_cfg);
+	devm_rtc_nvmem_register(rv3028->rtc, &eeprom_cfg);
 
 	rv3028->rtc->max_user_freq = 1;
 
diff --git a/drivers/rtc/rtc-rv3029c2.c b/drivers/rtc/rtc-rv3029c2.c
index 62718231731b..dc1bda62095e 100644
--- a/drivers/rtc/rtc-rv3029c2.c
+++ b/drivers/rtc/rtc-rv3029c2.c
@@ -750,12 +750,12 @@ static int rv3029_probe(struct device *dev, struct regmap *regmap, int irq,
 	rv3029->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rv3029->rtc->range_max = RTC_TIMESTAMP_END_2079;
 
-	rc = rtc_register_device(rv3029->rtc);
+	rc = devm_rtc_register_device(rv3029->rtc);
 	if (rc)
 		return rc;
 
 	nvmem_cfg.priv = rv3029->regmap;
-	rtc_nvmem_register(rv3029->rtc, &nvmem_cfg);
+	devm_rtc_nvmem_register(rv3029->rtc, &nvmem_cfg);
 
 	return 0;
 }
diff --git a/drivers/rtc/rtc-rv3032.c b/drivers/rtc/rtc-rv3032.c
index 3e67f71f4261..c9bcea727757 100644
--- a/drivers/rtc/rtc-rv3032.c
+++ b/drivers/rtc/rtc-rv3032.c
@@ -885,14 +885,14 @@ static int rv3032_probe(struct i2c_client *client)
 	rv3032->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rv3032->rtc->range_max = RTC_TIMESTAMP_END_2099;
 	rv3032->rtc->ops = &rv3032_rtc_ops;
-	ret = rtc_register_device(rv3032->rtc);
+	ret = devm_rtc_register_device(rv3032->rtc);
 	if (ret)
 		return ret;
 
-	nvmem_cfg.priv = rv3032;
-	rtc_nvmem_register(rv3032->rtc, &nvmem_cfg);
+	nvmem_cfg.priv = rv3032->regmap;
+	devm_rtc_nvmem_register(rv3032->rtc, &nvmem_cfg);
 	eeprom_cfg.priv = rv3032;
-	rtc_nvmem_register(rv3032->rtc, &eeprom_cfg);
+	devm_rtc_nvmem_register(rv3032->rtc, &eeprom_cfg);
 
 	rv3032->rtc->max_user_freq = 1;
 
diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index c6d8e3425688..d4ea6db51b26 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -585,14 +585,13 @@ static int rv8803_probe(struct i2c_client *client,
 	}
 
 	rv8803->rtc->ops = &rv8803_rtc_ops;
-	rv8803->rtc->nvram_old_abi = true;
 	rv8803->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rv8803->rtc->range_max = RTC_TIMESTAMP_END_2099;
-	err = rtc_register_device(rv8803->rtc);
+	err = devm_rtc_register_device(rv8803->rtc);
 	if (err)
 		return err;
 
-	rtc_nvmem_register(rv8803->rtc, &nvmem_cfg);
+	devm_rtc_nvmem_register(rv8803->rtc, &nvmem_cfg);
 
 	rv8803->rtc->max_user_freq = 1;
 
diff --git a/drivers/rtc/rtc-rx6110.c b/drivers/rtc/rtc-rx6110.c
index 3a9eb7043f01..a7b671a21022 100644
--- a/drivers/rtc/rtc-rx6110.c
+++ b/drivers/rtc/rtc-rx6110.c
@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/spi/spi.h>
+#include <linux/i2c.h>
 
 /* RX-6110 Register definitions */
 #define RX6110_REG_SEC		0x10
@@ -310,6 +311,27 @@ static const struct rtc_class_ops rx6110_rtc_ops = {
 	.set_time = rx6110_set_time,
 };
 
+static int rx6110_probe(struct rx6110_data *rx6110, struct device *dev)
+{
+	int err;
+
+	rx6110->rtc = devm_rtc_device_register(dev,
+					       RX6110_DRIVER_NAME,
+					       &rx6110_rtc_ops, THIS_MODULE);
+
+	if (IS_ERR(rx6110->rtc))
+		return PTR_ERR(rx6110->rtc);
+
+	err = rx6110_init(rx6110);
+	if (err)
+		return err;
+
+	rx6110->rtc->max_user_freq = 1;
+
+	return 0;
+}
+
+#ifdef CONFIG_SPI_MASTER
 static struct regmap_config regmap_spi_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
@@ -318,13 +340,12 @@ static struct regmap_config regmap_spi_config = {
 };
 
 /**
- * rx6110_probe - initialize rtc driver
+ * rx6110_spi_probe - initialize rtc driver
  * @spi: pointer to spi device
  */
-static int rx6110_probe(struct spi_device *spi)
+static int rx6110_spi_probe(struct spi_device *spi)
 {
 	struct rx6110_data *rx6110;
-	int err;
 
 	if ((spi->bits_per_word && spi->bits_per_word != 8) ||
 	    (spi->max_speed_hz > 2000000) ||
@@ -346,27 +367,14 @@ static int rx6110_probe(struct spi_device *spi)
 
 	spi_set_drvdata(spi, rx6110);
 
-	rx6110->rtc = devm_rtc_device_register(&spi->dev,
-					       RX6110_DRIVER_NAME,
-					       &rx6110_rtc_ops, THIS_MODULE);
-
-	if (IS_ERR(rx6110->rtc))
-		return PTR_ERR(rx6110->rtc);
-
-	err = rx6110_init(rx6110);
-	if (err)
-		return err;
-
-	rx6110->rtc->max_user_freq = 1;
-
-	return 0;
+	return rx6110_probe(rx6110, &spi->dev);
 }
 
-static const struct spi_device_id rx6110_id[] = {
+static const struct spi_device_id rx6110_spi_id[] = {
 	{ "rx6110", 0 },
 	{ }
 };
-MODULE_DEVICE_TABLE(spi, rx6110_id);
+MODULE_DEVICE_TABLE(spi, rx6110_spi_id);
 
 static const struct of_device_id rx6110_spi_of_match[] = {
 	{ .compatible = "epson,rx6110" },
@@ -374,16 +382,127 @@ static const struct of_device_id rx6110_spi_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, rx6110_spi_of_match);
 
-static struct spi_driver rx6110_driver = {
+static struct spi_driver rx6110_spi_driver = {
 	.driver = {
 		.name = RX6110_DRIVER_NAME,
 		.of_match_table = of_match_ptr(rx6110_spi_of_match),
 	},
-	.probe		= rx6110_probe,
-	.id_table	= rx6110_id,
+	.probe		= rx6110_spi_probe,
+	.id_table	= rx6110_spi_id,
+};
+
+static int rx6110_spi_register(void)
+{
+	return spi_register_driver(&rx6110_spi_driver);
+}
+
+static void rx6110_spi_unregister(void)
+{
+	spi_unregister_driver(&rx6110_spi_driver);
+}
+#else
+static int rx6110_spi_register(void)
+{
+	return 0;
+}
+
+static void rx6110_spi_unregister(void)
+{
+}
+#endif /* CONFIG_SPI_MASTER */
+
+#ifdef CONFIG_I2C
+static struct regmap_config regmap_i2c_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = RX6110_REG_IRQ,
+	.read_flag_mask = 0x80,
 };
 
-module_spi_driver(rx6110_driver);
+static int rx6110_i2c_probe(struct i2c_client *client,
+			    const struct i2c_device_id *id)
+{
+	struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
+	struct rx6110_data *rx6110;
+
+	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA
+				| I2C_FUNC_SMBUS_I2C_BLOCK)) {
+		dev_err(&adapter->dev,
+			"doesn't support required functionality\n");
+		return -EIO;
+	}
+
+	rx6110 = devm_kzalloc(&client->dev, sizeof(*rx6110), GFP_KERNEL);
+	if (!rx6110)
+		return -ENOMEM;
+
+	rx6110->regmap = devm_regmap_init_i2c(client, &regmap_i2c_config);
+	if (IS_ERR(rx6110->regmap)) {
+		dev_err(&client->dev, "regmap init failed for rtc rx6110\n");
+		return PTR_ERR(rx6110->regmap);
+	}
+
+	i2c_set_clientdata(client, rx6110);
+
+	return rx6110_probe(rx6110, &client->dev);
+}
+
+static const struct i2c_device_id rx6110_i2c_id[] = {
+	{ "rx6110", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, rx6110_i2c_id);
+
+static struct i2c_driver rx6110_i2c_driver = {
+	.driver = {
+		.name = RX6110_DRIVER_NAME,
+	},
+	.probe		= rx6110_i2c_probe,
+	.id_table	= rx6110_i2c_id,
+};
+
+static int rx6110_i2c_register(void)
+{
+	return i2c_add_driver(&rx6110_i2c_driver);
+}
+
+static void rx6110_i2c_unregister(void)
+{
+	i2c_del_driver(&rx6110_i2c_driver);
+}
+#else
+static int rx6110_i2c_register(void)
+{
+	return 0;
+}
+
+static void rx6110_i2c_unregister(void)
+{
+}
+#endif /* CONFIG_I2C */
+
+static int __init rx6110_module_init(void)
+{
+	int ret;
+
+	ret = rx6110_spi_register();
+	if (ret)
+		return ret;
+
+	ret = rx6110_i2c_register();
+	if (ret)
+		rx6110_spi_unregister();
+
+	return ret;
+}
+module_init(rx6110_module_init);
+
+static void __exit rx6110_module_exit(void)
+{
+	rx6110_spi_unregister();
+	rx6110_i2c_unregister();
+}
+module_exit(rx6110_module_exit);
 
 MODULE_AUTHOR("Val Krutov <val.krutov@erd.epson.com>");
 MODULE_DESCRIPTION("RX-6110 SA RTC driver");
diff --git a/drivers/rtc/rtc-rx8010.c b/drivers/rtc/rtc-rx8010.c
index dca41a2a39b2..8340ab47a059 100644
--- a/drivers/rtc/rtc-rx8010.c
+++ b/drivers/rtc/rtc-rx8010.c
@@ -419,7 +419,7 @@ static int rx8010_probe(struct i2c_client *client)
 	rx8010->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rx8010->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	return rtc_register_device(rx8010->rtc);
+	return devm_rtc_register_device(rx8010->rtc);
 }
 
 static struct i2c_driver rx8010_driver = {
diff --git a/drivers/rtc/rtc-rx8581.c b/drivers/rtc/rtc-rx8581.c
index 490f70f57636..de109139529b 100644
--- a/drivers/rtc/rtc-rx8581.c
+++ b/drivers/rtc/rtc-rx8581.c
@@ -298,11 +298,11 @@ static int rx8581_probe(struct i2c_client *client,
 	rx8581->rtc->start_secs = 0;
 	rx8581->rtc->set_start_time = true;
 
-	ret = rtc_register_device(rx8581->rtc);
+	ret = devm_rtc_register_device(rx8581->rtc);
 
 	for (i = 0; i < config->num_nvram; i++) {
 		nvmem_cfg[i].priv = rx8581;
-		rtc_nvmem_register(rx8581->rtc, &nvmem_cfg[i]);
+		devm_rtc_nvmem_register(rx8581->rtc, &nvmem_cfg[i]);
 	}
 
 	return ret;
diff --git a/drivers/rtc/rtc-s35390a.c b/drivers/rtc/rtc-s35390a.c
index 03672a246356..ea15d0392bb9 100644
--- a/drivers/rtc/rtc-s35390a.c
+++ b/drivers/rtc/rtc-s35390a.c
@@ -497,7 +497,7 @@ static int s35390a_probe(struct i2c_client *client,
 	if (status1 & S35390A_FLAG_INT2)
 		rtc_update_irq(s35390a->rtc, 1, RTC_AF);
 
-	return rtc_register_device(s35390a->rtc);
+	return devm_rtc_register_device(s35390a->rtc);
 }
 
 static struct i2c_driver s35390a_driver = {
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index 24a41909f049..fab326ba9cec 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -42,26 +42,15 @@ struct s3c_rtc {
 	const struct s3c_rtc_data *data;
 
 	int irq_alarm;
-	int irq_tick;
-
-	spinlock_t pie_lock;
 	spinlock_t alarm_lock;
 
-	int ticnt_save;
-	int ticnt_en_save;
 	bool wake_en;
 };
 
 struct s3c_rtc_data {
-	int max_user_freq;
 	bool needs_src_clk;
 
 	void (*irq_handler) (struct s3c_rtc *info, int mask);
-	void (*set_freq) (struct s3c_rtc *info, int freq);
-	void (*enable_tick) (struct s3c_rtc *info, struct seq_file *seq);
-	void (*select_tick_clk) (struct s3c_rtc *info);
-	void (*save_tick_cnt) (struct s3c_rtc *info);
-	void (*restore_tick_cnt) (struct s3c_rtc *info);
 	void (*enable) (struct s3c_rtc *info);
 	void (*disable) (struct s3c_rtc *info);
 };
@@ -91,17 +80,7 @@ static void s3c_rtc_disable_clk(struct s3c_rtc *info)
 	clk_disable(info->rtc_clk);
 }
 
-/* IRQ Handlers */
-static irqreturn_t s3c_rtc_tickirq(int irq, void *id)
-{
-	struct s3c_rtc *info = (struct s3c_rtc *)id;
-
-	if (info->data->irq_handler)
-		info->data->irq_handler(info, S3C2410_INTP_TIC);
-
-	return IRQ_HANDLED;
-}
-
+/* IRQ Handler */
 static irqreturn_t s3c_rtc_alarmirq(int irq, void *id)
 {
 	struct s3c_rtc *info = (struct s3c_rtc *)id;
@@ -148,28 +127,6 @@ static int s3c_rtc_setaie(struct device *dev, unsigned int enabled)
 	return ret;
 }
 
-/* Set RTC frequency */
-static int s3c_rtc_setfreq(struct s3c_rtc *info, int freq)
-{
-	int ret;
-
-	if (!is_power_of_2(freq))
-		return -EINVAL;
-
-	ret = s3c_rtc_enable_clk(info);
-	if (ret)
-		return ret;
-	spin_lock_irq(&info->pie_lock);
-
-	if (info->data->set_freq)
-		info->data->set_freq(info, freq);
-
-	spin_unlock_irq(&info->pie_lock);
-	s3c_rtc_disable_clk(info);
-
-	return 0;
-}
-
 /* Time read/write */
 static int s3c_rtc_gettime(struct device *dev, struct rtc_time *rtc_tm)
 {
@@ -348,29 +305,11 @@ static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	return 0;
 }
 
-static int s3c_rtc_proc(struct device *dev, struct seq_file *seq)
-{
-	struct s3c_rtc *info = dev_get_drvdata(dev);
-	int ret;
-
-	ret = s3c_rtc_enable_clk(info);
-	if (ret)
-		return ret;
-
-	if (info->data->enable_tick)
-		info->data->enable_tick(info, seq);
-
-	s3c_rtc_disable_clk(info);
-
-	return 0;
-}
-
 static const struct rtc_class_ops s3c_rtcops = {
 	.read_time	= s3c_rtc_gettime,
 	.set_time	= s3c_rtc_settime,
 	.read_alarm	= s3c_rtc_getalarm,
 	.set_alarm	= s3c_rtc_setalarm,
-	.proc		= s3c_rtc_proc,
 	.alarm_irq_enable = s3c_rtc_setaie,
 };
 
@@ -450,18 +389,12 @@ static int s3c_rtc_probe(struct platform_device *pdev)
 	if (!info)
 		return -ENOMEM;
 
-	/* find the IRQs */
-	info->irq_tick = platform_get_irq(pdev, 1);
-	if (info->irq_tick < 0)
-		return info->irq_tick;
-
 	info->dev = &pdev->dev;
 	info->data = of_device_get_match_data(&pdev->dev);
 	if (!info->data) {
 		dev_err(&pdev->dev, "failed getting s3c_rtc_data\n");
 		return -EINVAL;
 	}
-	spin_lock_init(&info->pie_lock);
 	spin_lock_init(&info->alarm_lock);
 
 	platform_set_drvdata(pdev, info);
@@ -470,8 +403,7 @@ static int s3c_rtc_probe(struct platform_device *pdev)
 	if (info->irq_alarm < 0)
 		return info->irq_alarm;
 
-	dev_dbg(&pdev->dev, "s3c2410_rtc: tick irq %d, alarm irq %d\n",
-		info->irq_tick, info->irq_alarm);
+	dev_dbg(&pdev->dev, "s3c2410_rtc: alarm irq %d\n", info->irq_alarm);
 
 	/* get the memory region */
 	info->base = devm_platform_ioremap_resource(pdev, 0);
@@ -503,6 +435,10 @@ static int s3c_rtc_probe(struct platform_device *pdev)
 			goto err_src_clk;
 	}
 
+	/* disable RTC enable bits potentially set by the bootloader */
+	if (info->data->disable)
+		info->data->disable(info);
+
 	/* check to see if everything is setup correctly */
 	if (info->data->enable)
 		info->data->enable(info);
@@ -542,18 +478,6 @@ static int s3c_rtc_probe(struct platform_device *pdev)
 		goto err_nortc;
 	}
 
-	ret = devm_request_irq(&pdev->dev, info->irq_tick, s3c_rtc_tickirq,
-			       0, "s3c2410-rtc tick", info);
-	if (ret) {
-		dev_err(&pdev->dev, "IRQ%d error %d\n", info->irq_tick, ret);
-		goto err_nortc;
-	}
-
-	if (info->data->select_tick_clk)
-		info->data->select_tick_clk(info);
-
-	s3c_rtc_setfreq(info, 1);
-
 	s3c_rtc_disable_clk(info);
 
 	return 0;
@@ -581,10 +505,6 @@ static int s3c_rtc_suspend(struct device *dev)
 	if (ret)
 		return ret;
 
-	/* save TICNT for anyone using periodic interrupts */
-	if (info->data->save_tick_cnt)
-		info->data->save_tick_cnt(info);
-
 	if (info->data->disable)
 		info->data->disable(info);
 
@@ -605,9 +525,6 @@ static int s3c_rtc_resume(struct device *dev)
 	if (info->data->enable)
 		info->data->enable(info);
 
-	if (info->data->restore_tick_cnt)
-		info->data->restore_tick_cnt(info);
-
 	s3c_rtc_disable_clk(info);
 
 	if (device_may_wakeup(dev) && info->wake_en) {
@@ -631,162 +548,27 @@ static void s3c6410_rtc_irq(struct s3c_rtc *info, int mask)
 	writeb(mask, info->base + S3C2410_INTP);
 }
 
-static void s3c2410_rtc_setfreq(struct s3c_rtc *info, int freq)
-{
-	unsigned int tmp = 0;
-	int val;
-
-	tmp = readb(info->base + S3C2410_TICNT);
-	tmp &= S3C2410_TICNT_ENABLE;
-
-	val = (info->rtc->max_user_freq / freq) - 1;
-	tmp |= val;
-
-	writel(tmp, info->base + S3C2410_TICNT);
-}
-
-static void s3c2416_rtc_setfreq(struct s3c_rtc *info, int freq)
-{
-	unsigned int tmp = 0;
-	int val;
-
-	tmp = readb(info->base + S3C2410_TICNT);
-	tmp &= S3C2410_TICNT_ENABLE;
-
-	val = (info->rtc->max_user_freq / freq) - 1;
-
-	tmp |= S3C2443_TICNT_PART(val);
-	writel(S3C2443_TICNT1_PART(val), info->base + S3C2443_TICNT1);
-
-	writel(S3C2416_TICNT2_PART(val), info->base + S3C2416_TICNT2);
-
-	writel(tmp, info->base + S3C2410_TICNT);
-}
-
-static void s3c2443_rtc_setfreq(struct s3c_rtc *info, int freq)
-{
-	unsigned int tmp = 0;
-	int val;
-
-	tmp = readb(info->base + S3C2410_TICNT);
-	tmp &= S3C2410_TICNT_ENABLE;
-
-	val = (info->rtc->max_user_freq / freq) - 1;
-
-	tmp |= S3C2443_TICNT_PART(val);
-	writel(S3C2443_TICNT1_PART(val), info->base + S3C2443_TICNT1);
-
-	writel(tmp, info->base + S3C2410_TICNT);
-}
-
-static void s3c6410_rtc_setfreq(struct s3c_rtc *info, int freq)
-{
-	int val;
-
-	val = (info->rtc->max_user_freq / freq) - 1;
-	writel(val, info->base + S3C2410_TICNT);
-}
-
-static void s3c24xx_rtc_enable_tick(struct s3c_rtc *info, struct seq_file *seq)
-{
-	unsigned int ticnt;
-
-	ticnt = readb(info->base + S3C2410_TICNT);
-	ticnt &= S3C2410_TICNT_ENABLE;
-
-	seq_printf(seq, "periodic_IRQ\t: %s\n", ticnt  ? "yes" : "no");
-}
-
-static void s3c2416_rtc_select_tick_clk(struct s3c_rtc *info)
-{
-	unsigned int con;
-
-	con = readw(info->base + S3C2410_RTCCON);
-	con |= S3C2443_RTCCON_TICSEL;
-	writew(con, info->base + S3C2410_RTCCON);
-}
-
-static void s3c6410_rtc_enable_tick(struct s3c_rtc *info, struct seq_file *seq)
-{
-	unsigned int ticnt;
-
-	ticnt = readw(info->base + S3C2410_RTCCON);
-	ticnt &= S3C64XX_RTCCON_TICEN;
-
-	seq_printf(seq, "periodic_IRQ\t: %s\n", ticnt  ? "yes" : "no");
-}
-
-static void s3c24xx_rtc_save_tick_cnt(struct s3c_rtc *info)
-{
-	info->ticnt_save = readb(info->base + S3C2410_TICNT);
-}
-
-static void s3c24xx_rtc_restore_tick_cnt(struct s3c_rtc *info)
-{
-	writeb(info->ticnt_save, info->base + S3C2410_TICNT);
-}
-
-static void s3c6410_rtc_save_tick_cnt(struct s3c_rtc *info)
-{
-	info->ticnt_en_save = readw(info->base + S3C2410_RTCCON);
-	info->ticnt_en_save &= S3C64XX_RTCCON_TICEN;
-	info->ticnt_save = readl(info->base + S3C2410_TICNT);
-}
-
-static void s3c6410_rtc_restore_tick_cnt(struct s3c_rtc *info)
-{
-	unsigned int con;
-
-	writel(info->ticnt_save, info->base + S3C2410_TICNT);
-	if (info->ticnt_en_save) {
-		con = readw(info->base + S3C2410_RTCCON);
-		writew(con | info->ticnt_en_save, info->base + S3C2410_RTCCON);
-	}
-}
-
 static struct s3c_rtc_data const s3c2410_rtc_data = {
-	.max_user_freq		= 128,
 	.irq_handler		= s3c24xx_rtc_irq,
-	.set_freq		= s3c2410_rtc_setfreq,
-	.enable_tick		= s3c24xx_rtc_enable_tick,
-	.save_tick_cnt		= s3c24xx_rtc_save_tick_cnt,
-	.restore_tick_cnt	= s3c24xx_rtc_restore_tick_cnt,
 	.enable			= s3c24xx_rtc_enable,
 	.disable		= s3c24xx_rtc_disable,
 };
 
 static struct s3c_rtc_data const s3c2416_rtc_data = {
-	.max_user_freq		= 32768,
 	.irq_handler		= s3c24xx_rtc_irq,
-	.set_freq		= s3c2416_rtc_setfreq,
-	.enable_tick		= s3c24xx_rtc_enable_tick,
-	.select_tick_clk	= s3c2416_rtc_select_tick_clk,
-	.save_tick_cnt		= s3c24xx_rtc_save_tick_cnt,
-	.restore_tick_cnt	= s3c24xx_rtc_restore_tick_cnt,
 	.enable			= s3c24xx_rtc_enable,
 	.disable		= s3c24xx_rtc_disable,
 };
 
 static struct s3c_rtc_data const s3c2443_rtc_data = {
-	.max_user_freq		= 32768,
 	.irq_handler		= s3c24xx_rtc_irq,
-	.set_freq		= s3c2443_rtc_setfreq,
-	.enable_tick		= s3c24xx_rtc_enable_tick,
-	.select_tick_clk	= s3c2416_rtc_select_tick_clk,
-	.save_tick_cnt		= s3c24xx_rtc_save_tick_cnt,
-	.restore_tick_cnt	= s3c24xx_rtc_restore_tick_cnt,
 	.enable			= s3c24xx_rtc_enable,
 	.disable		= s3c24xx_rtc_disable,
 };
 
 static struct s3c_rtc_data const s3c6410_rtc_data = {
-	.max_user_freq		= 32768,
 	.needs_src_clk		= true,
 	.irq_handler		= s3c6410_rtc_irq,
-	.set_freq		= s3c6410_rtc_setfreq,
-	.enable_tick		= s3c6410_rtc_enable_tick,
-	.save_tick_cnt		= s3c6410_rtc_save_tick_cnt,
-	.restore_tick_cnt	= s3c6410_rtc_restore_tick_cnt,
 	.enable			= s3c24xx_rtc_enable,
 	.disable		= s3c6410_rtc_disable,
 };
diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c
index 9ccc97cf5e09..1250887e4382 100644
--- a/drivers/rtc/rtc-sa1100.c
+++ b/drivers/rtc/rtc-sa1100.c
@@ -205,7 +205,7 @@ int sa1100_rtc_init(struct platform_device *pdev, struct sa1100_rtc *info)
 	info->rtc->max_user_freq = RTC_FREQ;
 	info->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(info->rtc);
+	ret = devm_rtc_register_device(info->rtc);
 	if (ret) {
 		clk_disable_unprepare(info->clk);
 		return ret;
diff --git a/drivers/rtc/rtc-sc27xx.c b/drivers/rtc/rtc-sc27xx.c
index 36810dd40cd3..187aa955b79c 100644
--- a/drivers/rtc/rtc-sc27xx.c
+++ b/drivers/rtc/rtc-sc27xx.c
@@ -299,33 +299,6 @@ static int sprd_rtc_set_secs(struct sprd_rtc *rtc, enum sprd_rtc_reg_types type,
 			    sts_mask);
 }
 
-static int sprd_rtc_read_aux_alarm(struct device *dev, struct rtc_wkalrm *alrm)
-{
-	struct sprd_rtc *rtc = dev_get_drvdata(dev);
-	time64_t secs;
-	u32 val;
-	int ret;
-
-	ret = sprd_rtc_get_secs(rtc, SPRD_RTC_AUX_ALARM, &secs);
-	if (ret)
-		return ret;
-
-	rtc_time64_to_tm(secs, &alrm->time);
-
-	ret = regmap_read(rtc->regmap, rtc->base + SPRD_RTC_INT_EN, &val);
-	if (ret)
-		return ret;
-
-	alrm->enabled = !!(val & SPRD_RTC_AUXALM_EN);
-
-	ret = regmap_read(rtc->regmap, rtc->base + SPRD_RTC_INT_RAW_STS, &val);
-	if (ret)
-		return ret;
-
-	alrm->pending = !!(val & SPRD_RTC_AUXALM_EN);
-	return 0;
-}
-
 static int sprd_rtc_set_aux_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 {
 	struct sprd_rtc *rtc = dev_get_drvdata(dev);
@@ -415,16 +388,9 @@ static int sprd_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	u32 val;
 
 	/*
-	 * Before RTC device is registered, it will check to see if there is an
-	 * alarm already set in RTC hardware, and we always read the normal
-	 * alarm at this time.
-	 *
-	 * Or if aie_timer is enabled, we should get the normal alarm time.
-	 * Otherwise we should get auxiliary alarm time.
+	 * The RTC core checks to see if there is an alarm already set in RTC
+	 * hardware, and we always read the normal alarm at this time.
 	 */
-	if (rtc->rtc && rtc->rtc->registered && rtc->rtc->aie_timer.enabled == 0)
-		return sprd_rtc_read_aux_alarm(dev, alrm);
-
 	ret = sprd_rtc_get_secs(rtc, SPRD_RTC_ALARM, &secs);
 	if (ret)
 		return ret;
@@ -563,7 +529,7 @@ static int sprd_rtc_check_power_down(struct sprd_rtc *rtc)
 	 * means the RTC has been powered down, so the RTC time values are
 	 * invalid.
 	 */
-	rtc->valid = val == SPRD_RTC_POWER_RESET_VALUE ? false : true;
+	rtc->valid = val != SPRD_RTC_POWER_RESET_VALUE;
 	return 0;
 }
 
@@ -652,7 +618,7 @@ static int sprd_rtc_probe(struct platform_device *pdev)
 	rtc->rtc->ops = &sprd_rtc_ops;
 	rtc->rtc->range_min = 0;
 	rtc->rtc->range_max = 5662310399LL;
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret) {
 		device_init_wakeup(&pdev->dev, 0);
 		return ret;
diff --git a/drivers/rtc/rtc-sd3078.c b/drivers/rtc/rtc-sd3078.c
index a7aa943c1183..f6bee69ba017 100644
--- a/drivers/rtc/rtc-sd3078.c
+++ b/drivers/rtc/rtc-sd3078.c
@@ -192,7 +192,7 @@ static int sd3078_probe(struct i2c_client *client,
 	sd3078->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	sd3078->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	ret = rtc_register_device(sd3078->rtc);
+	ret = devm_rtc_register_device(sd3078->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c
index 9167b48014a1..cd146b574143 100644
--- a/drivers/rtc/rtc-sh.c
+++ b/drivers/rtc/rtc-sh.c
@@ -607,7 +607,7 @@ static int __init sh_rtc_probe(struct platform_device *pdev)
 		rtc->rtc_dev->range_max = mktime64(2098, 12, 31, 23, 59, 59);
 	}
 
-	ret = rtc_register_device(rtc->rtc_dev);
+	ret = devm_rtc_register_device(rtc->rtc_dev);
 	if (ret)
 		goto err_unmap;
 
diff --git a/drivers/rtc/rtc-sirfsoc.c b/drivers/rtc/rtc-sirfsoc.c
index abf19435dbad..03a6cca23201 100644
--- a/drivers/rtc/rtc-sirfsoc.c
+++ b/drivers/rtc/rtc-sirfsoc.c
@@ -356,7 +356,7 @@ static int sirfsoc_rtc_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	return rtc_register_device(rtcdrv->rtc);
+	return devm_rtc_register_device(rtcdrv->rtc);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-snvs.c b/drivers/rtc/rtc-snvs.c
index 0263d996b8a8..bd929b0e7d7d 100644
--- a/drivers/rtc/rtc-snvs.c
+++ b/drivers/rtc/rtc-snvs.c
@@ -151,17 +151,14 @@ static int snvs_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	unsigned long time;
 	int ret;
 
-	if (data->clk) {
-		ret = clk_enable(data->clk);
-		if (ret)
-			return ret;
-	}
+	ret = clk_enable(data->clk);
+	if (ret)
+		return ret;
 
 	time = rtc_read_lp_counter(data);
 	rtc_time64_to_tm(time, tm);
 
-	if (data->clk)
-		clk_disable(data->clk);
+	clk_disable(data->clk);
 
 	return 0;
 }
@@ -172,11 +169,9 @@ static int snvs_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	unsigned long time = rtc_tm_to_time64(tm);
 	int ret;
 
-	if (data->clk) {
-		ret = clk_enable(data->clk);
-		if (ret)
-			return ret;
-	}
+	ret = clk_enable(data->clk);
+	if (ret)
+		return ret;
 
 	/* Disable RTC first */
 	ret = snvs_rtc_enable(data, false);
@@ -190,8 +185,7 @@ static int snvs_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	/* Enable RTC again */
 	ret = snvs_rtc_enable(data, true);
 
-	if (data->clk)
-		clk_disable(data->clk);
+	clk_disable(data->clk);
 
 	return ret;
 }
@@ -202,11 +196,9 @@ static int snvs_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	u32 lptar, lpsr;
 	int ret;
 
-	if (data->clk) {
-		ret = clk_enable(data->clk);
-		if (ret)
-			return ret;
-	}
+	ret = clk_enable(data->clk);
+	if (ret)
+		return ret;
 
 	regmap_read(data->regmap, data->offset + SNVS_LPTAR, &lptar);
 	rtc_time64_to_tm(lptar, &alrm->time);
@@ -214,8 +206,7 @@ static int snvs_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	regmap_read(data->regmap, data->offset + SNVS_LPSR, &lpsr);
 	alrm->pending = (lpsr & SNVS_LPSR_LPTA) ? 1 : 0;
 
-	if (data->clk)
-		clk_disable(data->clk);
+	clk_disable(data->clk);
 
 	return 0;
 }
@@ -225,11 +216,9 @@ static int snvs_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 	struct snvs_rtc_data *data = dev_get_drvdata(dev);
 	int ret;
 
-	if (data->clk) {
-		ret = clk_enable(data->clk);
-		if (ret)
-			return ret;
-	}
+	ret = clk_enable(data->clk);
+	if (ret)
+		return ret;
 
 	regmap_update_bits(data->regmap, data->offset + SNVS_LPCR,
 			   (SNVS_LPCR_LPTA_EN | SNVS_LPCR_LPWUI_EN),
@@ -237,8 +226,7 @@ static int snvs_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 
 	ret = rtc_write_sync_lp(data);
 
-	if (data->clk)
-		clk_disable(data->clk);
+	clk_disable(data->clk);
 
 	return ret;
 }
@@ -249,11 +237,9 @@ static int snvs_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	unsigned long time = rtc_tm_to_time64(&alrm->time);
 	int ret;
 
-	if (data->clk) {
-		ret = clk_enable(data->clk);
-		if (ret)
-			return ret;
-	}
+	ret = clk_enable(data->clk);
+	if (ret)
+		return ret;
 
 	regmap_update_bits(data->regmap, data->offset + SNVS_LPCR, SNVS_LPCR_LPTA_EN, 0);
 	ret = rtc_write_sync_lp(data);
@@ -264,8 +250,7 @@ static int snvs_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	/* Clear alarm interrupt status bit */
 	regmap_write(data->regmap, data->offset + SNVS_LPSR, SNVS_LPSR_LPTA);
 
-	if (data->clk)
-		clk_disable(data->clk);
+	clk_disable(data->clk);
 
 	return snvs_rtc_alarm_irq_enable(dev, alrm->enabled);
 }
@@ -285,8 +270,7 @@ static irqreturn_t snvs_rtc_irq_handler(int irq, void *dev_id)
 	u32 lpsr;
 	u32 events = 0;
 
-	if (data->clk)
-		clk_enable(data->clk);
+	clk_enable(data->clk);
 
 	regmap_read(data->regmap, data->offset + SNVS_LPSR, &lpsr);
 
@@ -302,8 +286,7 @@ static irqreturn_t snvs_rtc_irq_handler(int irq, void *dev_id)
 	/* clear interrupt status */
 	regmap_write(data->regmap, data->offset + SNVS_LPSR, lpsr);
 
-	if (data->clk)
-		clk_disable(data->clk);
+	clk_disable(data->clk);
 
 	return events ? IRQ_HANDLED : IRQ_NONE;
 }
@@ -316,8 +299,7 @@ static const struct regmap_config snvs_rtc_config = {
 
 static void snvs_rtc_action(void *data)
 {
-	if (data)
-		clk_disable_unprepare(data);
+	clk_disable_unprepare(data);
 }
 
 static int snvs_rtc_probe(struct platform_device *pdev)
@@ -405,15 +387,14 @@ static int snvs_rtc_probe(struct platform_device *pdev)
 	data->rtc->ops = &snvs_rtc_ops;
 	data->rtc->range_max = U32_MAX;
 
-	return rtc_register_device(data->rtc);
+	return devm_rtc_register_device(data->rtc);
 }
 
 static int __maybe_unused snvs_rtc_suspend_noirq(struct device *dev)
 {
 	struct snvs_rtc_data *data = dev_get_drvdata(dev);
 
-	if (data->clk)
-		clk_disable(data->clk);
+	clk_disable(data->clk);
 
 	return 0;
 }
diff --git a/drivers/rtc/rtc-st-lpc.c b/drivers/rtc/rtc-st-lpc.c
index 0c65448b85ee..bdb20f63254e 100644
--- a/drivers/rtc/rtc-st-lpc.c
+++ b/drivers/rtc/rtc-st-lpc.c
@@ -250,7 +250,7 @@ static int st_rtc_probe(struct platform_device *pdev)
 	rtc->rtc_dev->range_max = U64_MAX;
 	do_div(rtc->rtc_dev->range_max, rtc->clkrate);
 
-	ret = rtc_register_device(rtc->rtc_dev);
+	ret = devm_rtc_register_device(rtc->rtc_dev);
 	if (ret) {
 		clk_disable_unprepare(rtc->clk);
 		return ret;
diff --git a/drivers/rtc/rtc-starfire.c b/drivers/rtc/rtc-starfire.c
index 37a26279e107..fbd1ed41cbf1 100644
--- a/drivers/rtc/rtc-starfire.c
+++ b/drivers/rtc/rtc-starfire.c
@@ -48,7 +48,7 @@ static int __init starfire_rtc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtc);
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver starfire_rtc_driver = {
diff --git a/drivers/rtc/rtc-stk17ta8.c b/drivers/rtc/rtc-stk17ta8.c
index 01a45044f468..7cb6be1b7815 100644
--- a/drivers/rtc/rtc-stk17ta8.c
+++ b/drivers/rtc/rtc-stk17ta8.c
@@ -311,14 +311,13 @@ static int stk17ta8_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(pdata->rtc);
 
 	pdata->rtc->ops = &stk17ta8_rtc_ops;
-	pdata->rtc->nvram_old_abi = true;
 
 	nvmem_cfg.priv = pdata;
-	ret = rtc_nvmem_register(pdata->rtc, &nvmem_cfg);
+	ret = devm_rtc_nvmem_register(pdata->rtc, &nvmem_cfg);
 	if (ret)
 		return ret;
 
-	return rtc_register_device(pdata->rtc);
+	return devm_rtc_register_device(pdata->rtc);
 }
 
 /* work with hotplug and coldplug */
diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c
index 0a969af80af7..40c0f7ed36e0 100644
--- a/drivers/rtc/rtc-stmp3xxx.c
+++ b/drivers/rtc/rtc-stmp3xxx.c
@@ -366,7 +366,7 @@ static int stmp3xxx_rtc_probe(struct platform_device *pdev)
 	rtc_data->rtc->ops = &stmp3xxx_rtc_ops;
 	rtc_data->rtc->range_max = U32_MAX;
 
-	err = rtc_register_device(rtc_data->rtc);
+	err = devm_rtc_register_device(rtc_data->rtc);
 	if (err)
 		return err;
 
diff --git a/drivers/rtc/rtc-sun4v.c b/drivers/rtc/rtc-sun4v.c
index 036463dfa103..a86e27de8c06 100644
--- a/drivers/rtc/rtc-sun4v.c
+++ b/drivers/rtc/rtc-sun4v.c
@@ -86,7 +86,7 @@ static int __init sun4v_rtc_probe(struct platform_device *pdev)
 	rtc->range_max = U64_MAX;
 	platform_set_drvdata(pdev, rtc);
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver sun4v_rtc_driver = {
diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c
index e2b8b150bcb4..adec1b14a8de 100644
--- a/drivers/rtc/rtc-sun6i.c
+++ b/drivers/rtc/rtc-sun6i.c
@@ -272,7 +272,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node,
 								300000000);
 	if (IS_ERR(rtc->int_osc)) {
 		pr_crit("Couldn't register the internal oscillator\n");
-		return;
+		goto err;
 	}
 
 	parents[0] = clk_hw_get_name(rtc->int_osc);
@@ -290,7 +290,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node,
 	rtc->losc = clk_register(NULL, &rtc->hw);
 	if (IS_ERR(rtc->losc)) {
 		pr_crit("Couldn't register the LOSC clock\n");
-		return;
+		goto err_register;
 	}
 
 	of_property_read_string_index(node, "clock-output-names", 1,
@@ -301,7 +301,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node,
 					  &rtc->lock);
 	if (IS_ERR(rtc->ext_losc)) {
 		pr_crit("Couldn't register the LOSC external gate\n");
-		return;
+		goto err_register;
 	}
 
 	clk_data->num = 2;
@@ -314,6 +314,8 @@ static void __init sun6i_rtc_clk_init(struct device_node *node,
 	of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data);
 	return;
 
+err_register:
+	clk_hw_unregister_fixed_rate(rtc->int_osc);
 err:
 	kfree(clk_data);
 }
@@ -724,7 +726,7 @@ static int sun6i_rtc_probe(struct platform_device *pdev)
 	chip->rtc->ops = &sun6i_rtc_ops;
 	chip->rtc->range_max = 2019686399LL; /* 2033-12-31 23:59:59 */
 
-	ret = rtc_register_device(chip->rtc);
+	ret = devm_rtc_register_device(chip->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-sunxi.c b/drivers/rtc/rtc-sunxi.c
index f5d7f44550ce..5d019e3a835a 100644
--- a/drivers/rtc/rtc-sunxi.c
+++ b/drivers/rtc/rtc-sunxi.c
@@ -470,7 +470,7 @@ static int sunxi_rtc_probe(struct platform_device *pdev)
 
 	chip->rtc->ops = &sunxi_rtc_ops;
 
-	return rtc_register_device(chip->rtc);
+	return devm_rtc_register_device(chip->rtc);
 }
 
 static struct platform_driver sunxi_rtc_driver = {
diff --git a/drivers/rtc/rtc-tegra.c b/drivers/rtc/rtc-tegra.c
index 7fbb1741692f..8925015cc698 100644
--- a/drivers/rtc/rtc-tegra.c
+++ b/drivers/rtc/rtc-tegra.c
@@ -329,7 +329,7 @@ static int tegra_rtc_probe(struct platform_device *pdev)
 		goto disable_clk;
 	}
 
-	ret = rtc_register_device(info->rtc);
+	ret = devm_rtc_register_device(info->rtc);
 	if (ret)
 		goto disable_clk;
 
diff --git a/drivers/rtc/rtc-test.c b/drivers/rtc/rtc-test.c
index 74b3a0603b73..7e0d8fb26465 100644
--- a/drivers/rtc/rtc-test.c
+++ b/drivers/rtc/rtc-test.c
@@ -50,7 +50,6 @@ static int test_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	if (expires > U32_MAX)
 		expires = U32_MAX;
 
-	pr_err("ABE: %s +%d %s\n", __FILE__, __LINE__, __func__);
 	rtd->alarm.expires = expires;
 
 	if (alrm->enabled)
@@ -139,7 +138,7 @@ static int test_probe(struct platform_device *plat_dev)
 	timer_setup(&rtd->alarm, test_rtc_alarm_handler, 0);
 	rtd->alarm.expires = 0;
 
-	return rtc_register_device(rtd->rtc);
+	return devm_rtc_register_device(rtd->rtc);
 }
 
 static struct platform_driver test_driver = {
diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c
index e39af2d67051..a980337c3065 100644
--- a/drivers/rtc/rtc-tps6586x.c
+++ b/drivers/rtc/rtc-tps6586x.c
@@ -280,7 +280,7 @@ static int tps6586x_rtc_probe(struct platform_device *pdev)
 		goto fail_rtc_register;
 	}
 
-	ret = rtc_register_device(rtc->rtc);
+	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret)
 		goto fail_rtc_register;
 
diff --git a/drivers/rtc/rtc-tps65910.c b/drivers/rtc/rtc-tps65910.c
index e3840386f430..2d87b62826a8 100644
--- a/drivers/rtc/rtc-tps65910.c
+++ b/drivers/rtc/rtc-tps65910.c
@@ -434,7 +434,7 @@ static int tps65910_rtc_probe(struct platform_device *pdev)
 	tps_rtc->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	tps_rtc->rtc->range_max = RTC_TIMESTAMP_END_2099;
 
-	return rtc_register_device(tps_rtc->rtc);
+	return devm_rtc_register_device(tps_rtc->rtc);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-tx4939.c b/drivers/rtc/rtc-tx4939.c
index 715b82981279..c3309db5448d 100644
--- a/drivers/rtc/rtc-tx4939.c
+++ b/drivers/rtc/rtc-tx4939.c
@@ -266,17 +266,16 @@ static int __init tx4939_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(rtc);
 
 	rtc->ops = &tx4939_rtc_ops;
-	rtc->nvram_old_abi = true;
 	rtc->range_max = U32_MAX;
 
 	pdata->rtc = rtc;
 
 	nvmem_cfg.priv = pdata;
-	ret = rtc_nvmem_register(rtc, &nvmem_cfg);
+	ret = devm_rtc_nvmem_register(rtc, &nvmem_cfg);
 	if (ret)
 		return ret;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static int __exit tx4939_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c
index c3671043ace7..5a9f9ad86d32 100644
--- a/drivers/rtc/rtc-vr41xx.c
+++ b/drivers/rtc/rtc-vr41xx.c
@@ -335,7 +335,7 @@ static int rtc_probe(struct platform_device *pdev)
 
 	dev_info(&pdev->dev, "Real Time Clock of NEC VR4100 series\n");
 
-	retval = rtc_register_device(rtc);
+	retval = devm_rtc_register_device(rtc);
 	if (retval)
 		goto err_iounmap_all;
 
diff --git a/drivers/rtc/rtc-vt8500.c b/drivers/rtc/rtc-vt8500.c
index e2588625025f..197b649cd629 100644
--- a/drivers/rtc/rtc-vt8500.c
+++ b/drivers/rtc/rtc-vt8500.c
@@ -232,7 +232,7 @@ static int vt8500_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	return rtc_register_device(vt8500_rtc->rtc);
+	return devm_rtc_register_device(vt8500_rtc->rtc);
 }
 
 static int vt8500_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/rtc-wilco-ec.c b/drivers/rtc/rtc-wilco-ec.c
index ff46066a68a4..2a205a646452 100644
--- a/drivers/rtc/rtc-wilco-ec.c
+++ b/drivers/rtc/rtc-wilco-ec.c
@@ -176,7 +176,7 @@ static int wilco_ec_rtc_probe(struct platform_device *pdev)
 	rtc->range_max = RTC_TIMESTAMP_END_2099;
 	rtc->owner = THIS_MODULE;
 
-	return rtc_register_device(rtc);
+	return devm_rtc_register_device(rtc);
 }
 
 static struct platform_driver wilco_ec_rtc_driver = {
diff --git a/drivers/rtc/rtc-wm831x.c b/drivers/rtc/rtc-wm831x.c
index ccef887d2690..640833e21057 100644
--- a/drivers/rtc/rtc-wm831x.c
+++ b/drivers/rtc/rtc-wm831x.c
@@ -429,7 +429,7 @@ static int wm831x_rtc_probe(struct platform_device *pdev)
 	wm831x_rtc->rtc->ops = &wm831x_rtc_ops;
 	wm831x_rtc->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(wm831x_rtc->rtc);
+	ret = devm_rtc_register_device(wm831x_rtc->rtc);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rtc/rtc-xgene.c b/drivers/rtc/rtc-xgene.c
index 96db441f92b3..cf68a9b1c9eb 100644
--- a/drivers/rtc/rtc-xgene.c
+++ b/drivers/rtc/rtc-xgene.c
@@ -185,7 +185,7 @@ static int xgene_rtc_probe(struct platform_device *pdev)
 	pdata->rtc->ops = &xgene_rtc_ops;
 	pdata->rtc->range_max = U32_MAX;
 
-	ret = rtc_register_device(pdata->rtc);
+	ret = devm_rtc_register_device(pdata->rtc);
 	if (ret) {
 		clk_disable_unprepare(pdata->clk);
 		return ret;
diff --git a/drivers/rtc/rtc-zynqmp.c b/drivers/rtc/rtc-zynqmp.c
index 4b1077e2f826..f440bb52be92 100644
--- a/drivers/rtc/rtc-zynqmp.c
+++ b/drivers/rtc/rtc-zynqmp.c
@@ -264,7 +264,7 @@ static int xlnx_rtc_probe(struct platform_device *pdev)
 
 	device_init_wakeup(&pdev->dev, 1);
 
-	return rtc_register_device(xrtcdev->rtc);
+	return devm_rtc_register_device(xrtcdev->rtc);
 }
 
 static int xlnx_rtc_remove(struct platform_device *pdev)
diff --git a/drivers/rtc/sysfs.c b/drivers/rtc/sysfs.c
index 950fac0d41ff..8a957d31a1a4 100644
--- a/drivers/rtc/sysfs.c
+++ b/drivers/rtc/sysfs.c
@@ -317,8 +317,6 @@ int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps)
 	size_t old_cnt = 0, add_cnt = 0, new_cnt;
 	const struct attribute_group **groups, **old;
 
-	if (rtc->registered)
-		return -EINVAL;
 	if (!grps)
 		return -EINVAL;
 
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index 99f86612f775..dc78a523a69f 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -256,7 +256,6 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device)
 		return;
 	device->discipline->get_uid(device, &uid);
 	spin_lock_irqsave(&lcu->lock, flags);
-	list_del_init(&device->alias_list);
 	/* make sure that the workers don't use this device */
 	if (device == lcu->suc_data.device) {
 		spin_unlock_irqrestore(&lcu->lock, flags);
@@ -283,6 +282,7 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device)
 
 	spin_lock_irqsave(&aliastree.lock, flags);
 	spin_lock(&lcu->lock);
+	list_del_init(&device->alias_list);
 	if (list_empty(&lcu->grouplist) &&
 	    list_empty(&lcu->active_devices) &&
 	    list_empty(&lcu->inactive_devices)) {
@@ -462,11 +462,19 @@ static int read_unit_address_configuration(struct dasd_device *device,
 	spin_unlock_irqrestore(&lcu->lock, flags);
 
 	rc = dasd_sleep_on(cqr);
-	if (rc && !suborder_not_supported(cqr)) {
+	if (!rc)
+		goto out;
+
+	if (suborder_not_supported(cqr)) {
+		/* suborder not supported or device unusable for IO */
+		rc = -EOPNOTSUPP;
+	} else {
+		/* IO failed but should be retried */
 		spin_lock_irqsave(&lcu->lock, flags);
 		lcu->flags |= NEED_UAC_UPDATE;
 		spin_unlock_irqrestore(&lcu->lock, flags);
 	}
+out:
 	dasd_sfree_request(cqr, cqr->memdev);
 	return rc;
 }
@@ -503,6 +511,14 @@ static int _lcu_update(struct dasd_device *refdev, struct alias_lcu *lcu)
 		return rc;
 
 	spin_lock_irqsave(&lcu->lock, flags);
+	/*
+	 * there is another update needed skip the remaining handling
+	 * the data might already be outdated
+	 * but especially do not add the device to an LCU with pending
+	 * update
+	 */
+	if (lcu->flags & NEED_UAC_UPDATE)
+		goto out;
 	lcu->pav = NO_PAV;
 	for (i = 0; i < MAX_DEVICES_PER_LCU; ++i) {
 		switch (lcu->uac->unit[i].ua_type) {
@@ -521,6 +537,7 @@ static int _lcu_update(struct dasd_device *refdev, struct alias_lcu *lcu)
 				 alias_list) {
 		_add_device_to_lcu(lcu, device, refdev);
 	}
+out:
 	spin_unlock_irqrestore(&lcu->lock, flags);
 	return 0;
 }
@@ -625,6 +642,7 @@ int dasd_alias_add_device(struct dasd_device *device)
 	}
 	if (lcu->flags & UPDATE_PENDING) {
 		list_move(&device->alias_list, &lcu->active_devices);
+		private->pavgroup = NULL;
 		_schedule_lcu_update(lcu, device);
 	}
 	spin_unlock_irqrestore(&lcu->lock, flags);
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 6f5ddc3eab8c..28f637042d44 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -1079,7 +1079,8 @@ struct qeth_card *qeth_get_card_by_busid(char *bus_id);
 void qeth_set_allowed_threads(struct qeth_card *card, unsigned long threads,
 			      int clear_start_mask);
 int qeth_threads_running(struct qeth_card *, unsigned long);
-int qeth_set_offline(struct qeth_card *card, bool resetting);
+int qeth_set_offline(struct qeth_card *card, const struct qeth_discipline *disc,
+		     bool resetting);
 
 int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *,
 		  int (*reply_cb)
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index f4b60294a969..cf18d87da41e 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5507,12 +5507,12 @@ out:
 	return rc;
 }
 
-static int qeth_set_online(struct qeth_card *card)
+static int qeth_set_online(struct qeth_card *card,
+			   const struct qeth_discipline *disc)
 {
 	bool carrier_ok;
 	int rc;
 
-	mutex_lock(&card->discipline_mutex);
 	mutex_lock(&card->conf_mutex);
 	QETH_CARD_TEXT(card, 2, "setonlin");
 
@@ -5529,7 +5529,7 @@ static int qeth_set_online(struct qeth_card *card)
 		/* no need for locking / error handling at this early stage: */
 		qeth_set_real_num_tx_queues(card, qeth_tx_actual_queues(card));
 
-	rc = card->discipline->set_online(card, carrier_ok);
+	rc = disc->set_online(card, carrier_ok);
 	if (rc)
 		goto err_online;
 
@@ -5537,7 +5537,6 @@ static int qeth_set_online(struct qeth_card *card)
 	kobject_uevent(&card->gdev->dev.kobj, KOBJ_CHANGE);
 
 	mutex_unlock(&card->conf_mutex);
-	mutex_unlock(&card->discipline_mutex);
 	return 0;
 
 err_online:
@@ -5552,15 +5551,14 @@ err_hardsetup:
 	qdio_free(CARD_DDEV(card));
 
 	mutex_unlock(&card->conf_mutex);
-	mutex_unlock(&card->discipline_mutex);
 	return rc;
 }
 
-int qeth_set_offline(struct qeth_card *card, bool resetting)
+int qeth_set_offline(struct qeth_card *card, const struct qeth_discipline *disc,
+		     bool resetting)
 {
 	int rc, rc2, rc3;
 
-	mutex_lock(&card->discipline_mutex);
 	mutex_lock(&card->conf_mutex);
 	QETH_CARD_TEXT(card, 3, "setoffl");
 
@@ -5581,7 +5579,7 @@ int qeth_set_offline(struct qeth_card *card, bool resetting)
 
 	cancel_work_sync(&card->rx_mode_work);
 
-	card->discipline->set_offline(card);
+	disc->set_offline(card);
 
 	qeth_qdio_clear_card(card, 0);
 	qeth_drain_output_queues(card);
@@ -5602,16 +5600,19 @@ int qeth_set_offline(struct qeth_card *card, bool resetting)
 	kobject_uevent(&card->gdev->dev.kobj, KOBJ_CHANGE);
 
 	mutex_unlock(&card->conf_mutex);
-	mutex_unlock(&card->discipline_mutex);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(qeth_set_offline);
 
 static int qeth_do_reset(void *data)
 {
+	const struct qeth_discipline *disc;
 	struct qeth_card *card = data;
 	int rc;
 
+	/* Lock-free, other users will block until we are done. */
+	disc = card->discipline;
+
 	QETH_CARD_TEXT(card, 2, "recover1");
 	if (!qeth_do_run_thread(card, QETH_RECOVER_THREAD))
 		return 0;
@@ -5619,8 +5620,8 @@ static int qeth_do_reset(void *data)
 	dev_warn(&card->gdev->dev,
 		 "A recovery process has been started for the device\n");
 
-	qeth_set_offline(card, true);
-	rc = qeth_set_online(card);
+	qeth_set_offline(card, disc, true);
+	rc = qeth_set_online(card, disc);
 	if (!rc) {
 		dev_info(&card->gdev->dev,
 			 "Device successfully recovered!\n");
@@ -6584,6 +6585,7 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 		break;
 	default:
 		card->info.layer_enforced = true;
+		/* It's so early that we don't need the discipline_mutex yet. */
 		rc = qeth_core_load_discipline(card, enforced_disc);
 		if (rc)
 			goto err_load;
@@ -6616,10 +6618,12 @@ static void qeth_core_remove_device(struct ccwgroup_device *gdev)
 
 	QETH_CARD_TEXT(card, 2, "removedv");
 
+	mutex_lock(&card->discipline_mutex);
 	if (card->discipline) {
 		card->discipline->remove(gdev);
 		qeth_core_free_discipline(card);
 	}
+	mutex_unlock(&card->discipline_mutex);
 
 	qeth_free_qdio_queues(card);
 
@@ -6634,6 +6638,7 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev)
 	int rc = 0;
 	enum qeth_discipline_id def_discipline;
 
+	mutex_lock(&card->discipline_mutex);
 	if (!card->discipline) {
 		def_discipline = IS_IQD(card) ? QETH_DISCIPLINE_LAYER3 :
 						QETH_DISCIPLINE_LAYER2;
@@ -6647,16 +6652,23 @@ static int qeth_core_set_online(struct ccwgroup_device *gdev)
 		}
 	}
 
-	rc = qeth_set_online(card);
+	rc = qeth_set_online(card, card->discipline);
+
 err:
+	mutex_unlock(&card->discipline_mutex);
 	return rc;
 }
 
 static int qeth_core_set_offline(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
 
-	return qeth_set_offline(card, false);
+	mutex_lock(&card->discipline_mutex);
+	rc = qeth_set_offline(card, card->discipline, false);
+	mutex_unlock(&card->discipline_mutex);
+
+	return rc;
 }
 
 static void qeth_core_shutdown(struct ccwgroup_device *gdev)
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 4ed0fb0705a5..4254caf1d9b6 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -2208,7 +2208,7 @@ static void qeth_l2_remove_device(struct ccwgroup_device *gdev)
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 
 	if (gdev->state == CCWGROUP_ONLINE)
-		qeth_set_offline(card, false);
+		qeth_set_offline(card, card->discipline, false);
 
 	cancel_work_sync(&card->close_dev_work);
 	if (card->dev->reg_state == NETREG_REGISTERED)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index d138ac432d01..4c2cae7ae9a7 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1813,7 +1813,7 @@ static netdev_features_t qeth_l3_osa_features_check(struct sk_buff *skb,
 						    struct net_device *dev,
 						    netdev_features_t features)
 {
-	if (qeth_get_ip_version(skb) != 4)
+	if (vlan_get_protocol(skb) != htons(ETH_P_IP))
 		features &= ~NETIF_F_HW_VLAN_CTAG_TX;
 	return qeth_features_check(skb, dev, features);
 }
@@ -1971,7 +1971,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 
 	if (cgdev->state == CCWGROUP_ONLINE)
-		qeth_set_offline(card, false);
+		qeth_set_offline(card, card->discipline, false);
 
 	cancel_work_sync(&card->close_dev_work);
 	if (card->dev->reg_state == NETREG_REGISTERED)
diff --git a/drivers/scsi/cxgbi/cxgb4i/Kconfig b/drivers/scsi/cxgbi/cxgb4i/Kconfig
index b206e266b4e7..8b0deece9758 100644
--- a/drivers/scsi/cxgbi/cxgb4i/Kconfig
+++ b/drivers/scsi/cxgbi/cxgb4i/Kconfig
@@ -4,6 +4,7 @@ config SCSI_CXGB4_ISCSI
 	depends on PCI && INET && (IPV6 || IPV6=n)
 	depends on THERMAL || !THERMAL
 	depends on ETHERNET
+	depends on TLS || TLS=n
 	select NET_VENDOR_CHELSIO
 	select CHELSIO_T4
 	select CHELSIO_LIB
diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 2b28dd405600..e821dd32dd28 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -14,6 +14,7 @@
 #include <linux/debugfs.h>
 #include <linux/dmapool.h>
 #include <linux/iopoll.h>
+#include <linux/irq.h>
 #include <linux/lcm.h>
 #include <linux/libata.h>
 #include <linux/mfd/syscon.h>
@@ -294,6 +295,7 @@ enum {
 
 struct hisi_sas_hw {
 	int (*hw_init)(struct hisi_hba *hisi_hba);
+	int (*interrupt_preinit)(struct hisi_hba *hisi_hba);
 	void (*setup_itct)(struct hisi_hba *hisi_hba,
 			   struct hisi_sas_device *device);
 	int (*slot_index_alloc)(struct hisi_hba *hisi_hba,
@@ -393,6 +395,8 @@ struct hisi_hba {
 	u32 refclk_frequency_mhz;
 	u8 sas_addr[SAS_ADDR_SIZE];
 
+	int *irq_map; /* v2 hw */
+
 	int n_phy;
 	spinlock_t lock;
 	struct semaphore sem;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index b6d4419c32f2..cf0bfac920a8 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2614,6 +2614,13 @@ err_out:
 	return NULL;
 }
 
+static int hisi_sas_interrupt_preinit(struct hisi_hba *hisi_hba)
+{
+	if (hisi_hba->hw->interrupt_preinit)
+		return hisi_hba->hw->interrupt_preinit(hisi_hba);
+	return 0;
+}
+
 int hisi_sas_probe(struct platform_device *pdev,
 		   const struct hisi_sas_hw *hw)
 {
@@ -2671,6 +2678,10 @@ int hisi_sas_probe(struct platform_device *pdev,
 		sha->sas_port[i] = &hisi_hba->port[i].sas_port;
 	}
 
+	rc = hisi_sas_interrupt_preinit(hisi_hba);
+	if (rc)
+		goto err_out_ha;
+
 	rc = scsi_add_host(shost, &pdev->dev);
 	if (rc)
 		goto err_out_ha;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index b57177b52fac..9adfdefef9ca 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -3302,6 +3302,28 @@ static irq_handler_t fatal_interrupts[HISI_SAS_FATAL_INT_NR] = {
 	fatal_axi_int_v2_hw
 };
 
+#define CQ0_IRQ_INDEX (96)
+
+static int hisi_sas_v2_interrupt_preinit(struct hisi_hba *hisi_hba)
+{
+	struct platform_device *pdev = hisi_hba->platform_dev;
+	struct Scsi_Host *shost = hisi_hba->shost;
+	struct irq_affinity desc = {
+		.pre_vectors = CQ0_IRQ_INDEX,
+		.post_vectors = 16,
+	};
+	int resv = desc.pre_vectors + desc.post_vectors, minvec = resv + 1, nvec;
+
+	nvec = devm_platform_get_irqs_affinity(pdev, &desc, minvec, 128,
+					       &hisi_hba->irq_map);
+	if (nvec < 0)
+		return nvec;
+
+	shost->nr_hw_queues = hisi_hba->cq_nvecs = nvec - resv;
+
+	return 0;
+}
+
 /*
  * There is a limitation in the hip06 chipset that we need
  * to map in all mbigen interrupts, even if they are not used.
@@ -3310,14 +3332,11 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 {
 	struct platform_device *pdev = hisi_hba->platform_dev;
 	struct device *dev = &pdev->dev;
-	int irq, rc = 0, irq_map[128];
+	int irq, rc = 0;
 	int i, phy_no, fatal_no, queue_no;
 
-	for (i = 0; i < 128; i++)
-		irq_map[i] = platform_get_irq(pdev, i);
-
 	for (i = 0; i < HISI_SAS_PHY_INT_NR; i++) {
-		irq = irq_map[i + 1]; /* Phy up/down is irq1 */
+		irq = hisi_hba->irq_map[i + 1]; /* Phy up/down is irq1 */
 		rc = devm_request_irq(dev, irq, phy_interrupts[i], 0,
 				      DRV_NAME " phy", hisi_hba);
 		if (rc) {
@@ -3331,7 +3350,7 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 	for (phy_no = 0; phy_no < hisi_hba->n_phy; phy_no++) {
 		struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 
-		irq = irq_map[phy_no + 72];
+		irq = hisi_hba->irq_map[phy_no + 72];
 		rc = devm_request_irq(dev, irq, sata_int_v2_hw, 0,
 				      DRV_NAME " sata", phy);
 		if (rc) {
@@ -3343,7 +3362,7 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 	}
 
 	for (fatal_no = 0; fatal_no < HISI_SAS_FATAL_INT_NR; fatal_no++) {
-		irq = irq_map[fatal_no + 81];
+		irq = hisi_hba->irq_map[fatal_no + 81];
 		rc = devm_request_irq(dev, irq, fatal_interrupts[fatal_no], 0,
 				      DRV_NAME " fatal", hisi_hba);
 		if (rc) {
@@ -3354,24 +3373,22 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 		}
 	}
 
-	for (queue_no = 0; queue_no < hisi_hba->queue_count; queue_no++) {
+	for (queue_no = 0; queue_no < hisi_hba->cq_nvecs; queue_no++) {
 		struct hisi_sas_cq *cq = &hisi_hba->cq[queue_no];
 
-		cq->irq_no = irq_map[queue_no + 96];
+		cq->irq_no = hisi_hba->irq_map[queue_no + 96];
 		rc = devm_request_threaded_irq(dev, cq->irq_no,
 					       cq_interrupt_v2_hw,
 					       cq_thread_v2_hw, IRQF_ONESHOT,
 					       DRV_NAME " cq", cq);
 		if (rc) {
 			dev_err(dev, "irq init: could not request cq interrupt %d, rc=%d\n",
-				irq, rc);
+					cq->irq_no, rc);
 			rc = -ENOENT;
 			goto err_out;
 		}
+		cq->irq_mask = irq_get_affinity_mask(cq->irq_no);
 	}
-
-	hisi_hba->cq_nvecs = hisi_hba->queue_count;
-
 err_out:
 	return rc;
 }
@@ -3529,6 +3546,26 @@ static struct device_attribute *host_attrs_v2_hw[] = {
 	NULL
 };
 
+static int map_queues_v2_hw(struct Scsi_Host *shost)
+{
+	struct hisi_hba *hisi_hba = shost_priv(shost);
+	struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
+	const struct cpumask *mask;
+	unsigned int queue, cpu;
+
+	for (queue = 0; queue < qmap->nr_queues; queue++) {
+		mask = irq_get_affinity_mask(hisi_hba->irq_map[96 + queue]);
+		if (!mask)
+			continue;
+
+		for_each_cpu(cpu, mask)
+			qmap->mq_map[cpu] = qmap->queue_offset + queue;
+	}
+
+	return 0;
+
+}
+
 static struct scsi_host_template sht_v2_hw = {
 	.name			= DRV_NAME,
 	.proc_name		= DRV_NAME,
@@ -3553,10 +3590,13 @@ static struct scsi_host_template sht_v2_hw = {
 #endif
 	.shost_attrs		= host_attrs_v2_hw,
 	.host_reset		= hisi_sas_host_reset,
+	.map_queues		= map_queues_v2_hw,
+	.host_tagset		= 1,
 };
 
 static const struct hisi_sas_hw hisi_sas_v2_hw = {
 	.hw_init = hisi_sas_v2_init,
+	.interrupt_preinit = hisi_sas_v2_interrupt_preinit,
 	.setup_itct = setup_itct_v2_hw,
 	.slot_index_alloc = slot_index_alloc_quirk_v2_hw,
 	.alloc_dev = alloc_dev_quirk_v2_hw,
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 6e4bf05c6d77..af192096a82b 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -37,6 +37,7 @@
 #include <linux/poll.h>
 #include <linux/vmalloc.h>
 #include <linux/irq_poll.h>
+#include <linux/blk-mq-pci.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -113,6 +114,10 @@ unsigned int enable_sdev_max_qd;
 module_param(enable_sdev_max_qd, int, 0444);
 MODULE_PARM_DESC(enable_sdev_max_qd, "Enable sdev max qd as can_queue. Default: 0");
 
+int host_tagset_enable = 1;
+module_param(host_tagset_enable, int, 0444);
+MODULE_PARM_DESC(host_tagset_enable, "Shared host tagset enable/disable Default: enable(1)");
+
 MODULE_LICENSE("GPL");
 MODULE_VERSION(MEGASAS_VERSION);
 MODULE_AUTHOR("megaraidlinux.pdl@broadcom.com");
@@ -3119,6 +3124,19 @@ megasas_bios_param(struct scsi_device *sdev, struct block_device *bdev,
 	return 0;
 }
 
+static int megasas_map_queues(struct Scsi_Host *shost)
+{
+	struct megasas_instance *instance;
+
+	instance = (struct megasas_instance *)shost->hostdata;
+
+	if (shost->nr_hw_queues == 1)
+		return 0;
+
+	return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
+			instance->pdev, instance->low_latency_index_start);
+}
+
 static void megasas_aen_polling(struct work_struct *work);
 
 /**
@@ -3427,6 +3445,7 @@ static struct scsi_host_template megasas_template = {
 	.eh_timed_out = megasas_reset_timer,
 	.shost_attrs = megaraid_host_attrs,
 	.bios_param = megasas_bios_param,
+	.map_queues = megasas_map_queues,
 	.change_queue_depth = scsi_change_queue_depth,
 	.max_segment_size = 0xffffffff,
 };
@@ -6808,6 +6827,26 @@ static int megasas_io_attach(struct megasas_instance *instance)
 	host->max_lun = MEGASAS_MAX_LUN;
 	host->max_cmd_len = 16;
 
+	/* Use shared host tagset only for fusion adaptors
+	 * if there are managed interrupts (smp affinity enabled case).
+	 * Single msix_vectors in kdump, so shared host tag is also disabled.
+	 */
+
+	host->host_tagset = 0;
+	host->nr_hw_queues = 1;
+
+	if ((instance->adapter_type != MFI_SERIES) &&
+		(instance->msix_vectors > instance->low_latency_index_start) &&
+		host_tagset_enable &&
+		instance->smp_affinity_enable) {
+		host->host_tagset = 1;
+		host->nr_hw_queues = instance->msix_vectors -
+			instance->low_latency_index_start;
+	}
+
+	dev_info(&instance->pdev->dev,
+		"Max firmware commands: %d shared with nr_hw_queues = %d\n",
+		instance->max_fw_cmds, host->nr_hw_queues);
 	/*
 	 * Notify the mid-layer about the new controller
 	 */
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index b0c01cf0428f..fd607287608e 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -359,24 +359,29 @@ megasas_get_msix_index(struct megasas_instance *instance,
 {
 	int sdev_busy;
 
-	/* nr_hw_queue = 1 for MegaRAID */
-	struct blk_mq_hw_ctx *hctx =
-		scmd->device->request_queue->queue_hw_ctx[0];
-
-	sdev_busy = atomic_read(&hctx->nr_active);
+	/* TBD - if sml remove device_busy in future, driver
+	 * should track counter in internal structure.
+	 */
+	sdev_busy = atomic_read(&scmd->device->device_busy);
 
 	if (instance->perf_mode == MR_BALANCED_PERF_MODE &&
-	    sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH))
+	    sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH)) {
 		cmd->request_desc->SCSIIO.MSIxIndex =
 			mega_mod64((atomic64_add_return(1, &instance->high_iops_outstanding) /
 					MR_HIGH_IOPS_BATCH_COUNT), instance->low_latency_index_start);
-	else if (instance->msix_load_balance)
+	} else if (instance->msix_load_balance) {
 		cmd->request_desc->SCSIIO.MSIxIndex =
 			(mega_mod64(atomic64_add_return(1, &instance->total_io_count),
 				instance->msix_vectors));
-	else
+	} else if (instance->host->nr_hw_queues > 1) {
+		u32 tag = blk_mq_unique_tag(scmd->request);
+
+		cmd->request_desc->SCSIIO.MSIxIndex = blk_mq_unique_tag_to_hwq(tag) +
+			instance->low_latency_index_start;
+	} else {
 		cmd->request_desc->SCSIIO.MSIxIndex =
 			instance->reply_map[raw_smp_processor_id()];
+	}
 }
 
 /**
@@ -956,9 +961,6 @@ megasas_alloc_cmds_fusion(struct megasas_instance *instance)
 	if (megasas_alloc_cmdlist_fusion(instance))
 		goto fail_exit;
 
-	dev_info(&instance->pdev->dev, "Configured max firmware commands: %d\n",
-		 instance->max_fw_cmds);
-
 	/* The first 256 bytes (SMID 0) is not used. Don't add to the cmd list */
 	io_req_base = fusion->io_request_frames + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE;
 	io_req_base_phys = fusion->io_request_frames_phys + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE;
@@ -1102,8 +1104,9 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 		MR_HIGH_IOPS_QUEUE_COUNT) && cur_intr_coalescing)
 		instance->perf_mode = MR_BALANCED_PERF_MODE;
 
-	dev_info(&instance->pdev->dev, "Performance mode :%s\n",
-		MEGASAS_PERF_MODE_2STR(instance->perf_mode));
+	dev_info(&instance->pdev->dev, "Performance mode :%s (latency index = %d)\n",
+		MEGASAS_PERF_MODE_2STR(instance->perf_mode),
+		instance->low_latency_index_start);
 
 	instance->fw_sync_cache_support = (scratch_pad_1 &
 		MR_CAN_HANDLE_SYNC_CACHE_OFFSET) ? 1 : 0;
diff --git a/drivers/scsi/mpt3sas/Kconfig b/drivers/scsi/mpt3sas/Kconfig
index 86209455172d..c299f7e078fb 100644
--- a/drivers/scsi/mpt3sas/Kconfig
+++ b/drivers/scsi/mpt3sas/Kconfig
@@ -79,5 +79,5 @@ config SCSI_MPT2SAS
 	select SCSI_MPT3SAS
 	depends on PCI && SCSI
 	help
-	Dummy config option for backwards compatiblity: configure the MPT3SAS
+	Dummy config option for backwards compatibility: configure the MPT3SAS
 	driver instead.
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 969baf4cd3f5..6e23dc3209fe 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -5034,7 +5034,7 @@ _base_check_for_trigger_pages_support(struct MPT3SAS_ADAPTER *ioc)
 static void
 _base_get_diag_triggers(struct MPT3SAS_ADAPTER *ioc)
 {
-	u16 trigger_flags;
+	int trigger_flags;
 
 	/*
 	 * Default setting of master trigger.
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index f5fc7f518f8a..47ad64b06623 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -2245,7 +2245,7 @@ qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type,
 			     chap_name);
 		break;
 	case ISCSI_BOOT_TGT_CHAP_SECRET:
-		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN,
 			     chap_secret);
 		break;
 	case ISCSI_BOOT_TGT_REV_CHAP_NAME:
@@ -2253,7 +2253,7 @@ qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type,
 			     mchap_name);
 		break;
 	case ISCSI_BOOT_TGT_REV_CHAP_SECRET:
-		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN,
 			     mchap_secret);
 		break;
 	case ISCSI_BOOT_TGT_FLAGS:
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 24c0f7ec0351..4a08c450b756 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -6740,7 +6740,7 @@ static int __init scsi_debug_init(void)
 		k = sdeb_zbc_model_str(sdeb_zbc_model_s);
 		if (k < 0) {
 			ret = k;
-			goto free_vm;
+			goto free_q_arr;
 		}
 		sdeb_zbc_model = k;
 		switch (sdeb_zbc_model) {
@@ -6753,7 +6753,8 @@ static int __init scsi_debug_init(void)
 			break;
 		default:
 			pr_err("Invalid ZBC model\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto free_q_arr;
 		}
 	}
 	if (sdeb_zbc_model != BLK_ZONED_NONE) {
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 4848ae3c7b56..b3f14f05340a 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -249,7 +249,8 @@ int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 
 	req = blk_get_request(sdev->request_queue,
 			data_direction == DMA_TO_DEVICE ?
-			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, BLK_MQ_REQ_PREEMPT);
+			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
+			rq_flags & RQF_PM ? BLK_MQ_REQ_PM : 0);
 	if (IS_ERR(req))
 		return ret;
 	rq = scsi_req(req);
@@ -1206,6 +1207,8 @@ static blk_status_t
 scsi_device_state_check(struct scsi_device *sdev, struct request *req)
 {
 	switch (sdev->sdev_state) {
+	case SDEV_CREATED:
+		return BLK_STS_OK;
 	case SDEV_OFFLINE:
 	case SDEV_TRANSPORT_OFFLINE:
 		/*
@@ -1232,18 +1235,18 @@ scsi_device_state_check(struct scsi_device *sdev, struct request *req)
 		return BLK_STS_RESOURCE;
 	case SDEV_QUIESCE:
 		/*
-		 * If the devices is blocked we defer normal commands.
+		 * If the device is blocked we only accept power management
+		 * commands.
 		 */
-		if (req && !(req->rq_flags & RQF_PREEMPT))
+		if (req && WARN_ON_ONCE(!(req->rq_flags & RQF_PM)))
 			return BLK_STS_RESOURCE;
 		return BLK_STS_OK;
 	default:
 		/*
 		 * For any other not fully online state we only allow
-		 * special commands.  In particular any user initiated
-		 * command is not allowed.
+		 * power management commands.
 		 */
-		if (req && !(req->rq_flags & RQF_PREEMPT))
+		if (req && !(req->rq_flags & RQF_PM))
 			return BLK_STS_IOERR;
 		return BLK_STS_OK;
 	}
@@ -2516,15 +2519,13 @@ void sdev_evt_send_simple(struct scsi_device *sdev,
 EXPORT_SYMBOL_GPL(sdev_evt_send_simple);
 
 /**
- *	scsi_device_quiesce - Block user issued commands.
+ *	scsi_device_quiesce - Block all commands except power management.
  *	@sdev:	scsi device to quiesce.
  *
  *	This works by trying to transition to the SDEV_QUIESCE state
  *	(which must be a legal transition).  When the device is in this
- *	state, only special requests will be accepted, all others will
- *	be deferred.  Since special requests may also be requeued requests,
- *	a successful return doesn't guarantee the device will be
- *	totally quiescent.
+ *	state, only power management requests will be accepted, all others will
+ *	be deferred.
  *
  *	Must be called with user context, may sleep.
  *
@@ -2586,12 +2587,12 @@ void scsi_device_resume(struct scsi_device *sdev)
 	 * device deleted during suspend)
 	 */
 	mutex_lock(&sdev->state_mutex);
+	if (sdev->sdev_state == SDEV_QUIESCE)
+		scsi_device_set_state(sdev, SDEV_RUNNING);
 	if (sdev->quiesced_by) {
 		sdev->quiesced_by = NULL;
 		blk_clear_pm_only(sdev->request_queue);
 	}
-	if (sdev->sdev_state == SDEV_QUIESCE)
-		scsi_device_set_state(sdev, SDEV_RUNNING);
 	mutex_unlock(&sdev->state_mutex);
 }
 EXPORT_SYMBOL(scsi_device_resume);
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index f3d5b1bbd5aa..c37dd15d16d2 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -117,12 +117,16 @@ static int spi_execute(struct scsi_device *sdev, const void *cmd,
 		sshdr = &sshdr_tmp;
 
 	for(i = 0; i < DV_RETRIES; i++) {
+		/*
+		 * The purpose of the RQF_PM flag below is to bypass the
+		 * SDEV_QUIESCE state.
+		 */
 		result = scsi_execute(sdev, cmd, dir, buffer, bufflen, sense,
 				      sshdr, DV_TIMEOUT, /* retries */ 1,
 				      REQ_FAILFAST_DEV |
 				      REQ_FAILFAST_TRANSPORT |
 				      REQ_FAILFAST_DRIVER,
-				      0, NULL);
+				      RQF_PM, NULL);
 		if (driver_byte(result) != DRIVER_SENSE ||
 		    sshdr->sense_key != UNIT_ATTENTION)
 			break;
@@ -1005,23 +1009,26 @@ spi_dv_device(struct scsi_device *sdev)
 	 */
 	lock_system_sleep();
 
+	if (scsi_autopm_get_device(sdev))
+		goto unlock_system_sleep;
+
 	if (unlikely(spi_dv_in_progress(starget)))
-		goto unlock;
+		goto put_autopm;
 
 	if (unlikely(scsi_device_get(sdev)))
-		goto unlock;
+		goto put_autopm;
 
 	spi_dv_in_progress(starget) = 1;
 
 	buffer = kzalloc(len, GFP_KERNEL);
 
 	if (unlikely(!buffer))
-		goto out_put;
+		goto put_sdev;
 
 	/* We need to verify that the actual device will quiesce; the
 	 * later target quiesce is just a nice to have */
 	if (unlikely(scsi_device_quiesce(sdev)))
-		goto out_free;
+		goto free_buffer;
 
 	scsi_target_quiesce(starget);
 
@@ -1041,12 +1048,16 @@ spi_dv_device(struct scsi_device *sdev)
 
 	spi_initial_dv(starget) = 1;
 
- out_free:
+free_buffer:
 	kfree(buffer);
- out_put:
+
+put_sdev:
 	spi_dv_in_progress(starget) = 0;
 	scsi_device_put(sdev);
-unlock:
+put_autopm:
+	scsi_autopm_put_device(sdev);
+
+unlock_system_sleep:
 	unlock_system_sleep();
 }
 EXPORT_SYMBOL(spi_dv_device);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 679c2c025047..a3d2d4bc4a3d 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -984,8 +984,10 @@ static blk_status_t sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
 		}
 	}
 
-	if (sdp->no_write_same)
+	if (sdp->no_write_same) {
+		rq->rq_flags |= RQF_QUIET;
 		return BLK_STS_TARGET;
+	}
 
 	if (sdkp->ws16 || lba > 0xffffffff || nr_blocks > 0xffff)
 		return sd_setup_write_same16_cmnd(cmd, false);
@@ -3510,10 +3512,8 @@ static int sd_probe(struct device *dev)
 static int sd_remove(struct device *dev)
 {
 	struct scsi_disk *sdkp;
-	dev_t devt;
 
 	sdkp = dev_get_drvdata(dev);
-	devt = disk_devt(sdkp->disk);
 	scsi_autopm_get_device(sdkp->device);
 
 	async_synchronize_full_domain(&scsi_sd_pm_domain);
diff --git a/drivers/scsi/ufs/ufs-mediatek-trace.h b/drivers/scsi/ufs/ufs-mediatek-trace.h
index fd6f84c1b4e2..895e82ea6ece 100644
--- a/drivers/scsi/ufs/ufs-mediatek-trace.h
+++ b/drivers/scsi/ufs/ufs-mediatek-trace.h
@@ -31,6 +31,6 @@ TRACE_EVENT(ufs_mtk_event,
 
 #undef TRACE_INCLUDE_PATH
 #undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_PATH ../../drivers/scsi/ufs/
 #define TRACE_INCLUDE_FILE ufs-mediatek-trace
 #include <trace/define_trace.h>
diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c
index 3522458db3bb..80618af7c872 100644
--- a/drivers/scsi/ufs/ufs-mediatek.c
+++ b/drivers/scsi/ufs/ufs-mediatek.c
@@ -70,6 +70,13 @@ static bool ufs_mtk_is_va09_supported(struct ufs_hba *hba)
 	return !!(host->caps & UFS_MTK_CAP_VA09_PWR_CTRL);
 }
 
+static bool ufs_mtk_is_broken_vcc(struct ufs_hba *hba)
+{
+	struct ufs_mtk_host *host = ufshcd_get_variant(hba);
+
+	return !!(host->caps & UFS_MTK_CAP_BROKEN_VCC);
+}
+
 static void ufs_mtk_cfg_unipro_cg(struct ufs_hba *hba, bool enable)
 {
 	u32 tmp;
@@ -514,6 +521,9 @@ static void ufs_mtk_init_host_caps(struct ufs_hba *hba)
 	if (of_property_read_bool(np, "mediatek,ufs-disable-ah8"))
 		host->caps |= UFS_MTK_CAP_DISABLE_AH8;
 
+	if (of_property_read_bool(np, "mediatek,ufs-broken-vcc"))
+		host->caps |= UFS_MTK_CAP_BROKEN_VCC;
+
 	dev_info(hba->dev, "caps: 0x%x", host->caps);
 }
 
@@ -1003,6 +1013,17 @@ static int ufs_mtk_apply_dev_quirks(struct ufs_hba *hba)
 static void ufs_mtk_fixup_dev_quirks(struct ufs_hba *hba)
 {
 	ufshcd_fixup_dev_quirks(hba, ufs_mtk_dev_fixups);
+
+	if (ufs_mtk_is_broken_vcc(hba) && hba->vreg_info.vcc &&
+	    (hba->dev_quirks & UFS_DEVICE_QUIRK_DELAY_AFTER_LPM)) {
+		hba->vreg_info.vcc->always_on = true;
+		/*
+		 * VCC will be kept always-on thus we don't
+		 * need any delay during regulator operations
+		 */
+		hba->dev_quirks &= ~(UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM |
+			UFS_DEVICE_QUIRK_DELAY_AFTER_LPM);
+	}
 }
 
 static void ufs_mtk_event_notify(struct ufs_hba *hba,
diff --git a/drivers/scsi/ufs/ufs-mediatek.h b/drivers/scsi/ufs/ufs-mediatek.h
index 93d35097dfb0..3f0d3bb769e8 100644
--- a/drivers/scsi/ufs/ufs-mediatek.h
+++ b/drivers/scsi/ufs/ufs-mediatek.h
@@ -81,6 +81,7 @@ enum ufs_mtk_host_caps {
 	UFS_MTK_CAP_BOOST_CRYPT_ENGINE         = 1 << 0,
 	UFS_MTK_CAP_VA09_PWR_CTRL              = 1 << 1,
 	UFS_MTK_CAP_DISABLE_AH8                = 1 << 2,
+	UFS_MTK_CAP_BROKEN_VCC                 = 1 << 3,
 };
 
 struct ufs_mtk_crypt_cfg {
diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h
index d593edb48767..14dfda735adf 100644
--- a/drivers/scsi/ufs/ufs.h
+++ b/drivers/scsi/ufs/ufs.h
@@ -330,7 +330,6 @@ enum {
 	UFS_DEV_WRITE_BOOSTER_SUP	= BIT(8),
 };
 
-#define POWER_DESC_MAX_SIZE			0x62
 #define POWER_DESC_MAX_ACTV_ICC_LVLS		16
 
 /* Attribute  bActiveICCLevel parameter bit masks definitions */
@@ -513,6 +512,7 @@ struct ufs_query_res {
 struct ufs_vreg {
 	struct regulator *reg;
 	const char *name;
+	bool always_on;
 	bool enabled;
 	int min_uV;
 	int max_uV;
diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c
index df3a564c3e33..fadd566025b8 100644
--- a/drivers/scsi/ufs/ufshcd-pci.c
+++ b/drivers/scsi/ufs/ufshcd-pci.c
@@ -148,6 +148,8 @@ static int ufs_intel_common_init(struct ufs_hba *hba)
 {
 	struct intel_host *host;
 
+	hba->caps |= UFSHCD_CAP_RPM_AUTOSUSPEND;
+
 	host = devm_kzalloc(hba->dev, sizeof(*host), GFP_KERNEL);
 	if (!host)
 		return -ENOMEM;
@@ -163,6 +165,41 @@ static void ufs_intel_common_exit(struct ufs_hba *hba)
 	intel_ltr_hide(hba->dev);
 }
 
+static int ufs_intel_resume(struct ufs_hba *hba, enum ufs_pm_op op)
+{
+	/*
+	 * To support S4 (suspend-to-disk) with spm_lvl other than 5, the base
+	 * address registers must be restored because the restore kernel can
+	 * have used different addresses.
+	 */
+	ufshcd_writel(hba, lower_32_bits(hba->utrdl_dma_addr),
+		      REG_UTP_TRANSFER_REQ_LIST_BASE_L);
+	ufshcd_writel(hba, upper_32_bits(hba->utrdl_dma_addr),
+		      REG_UTP_TRANSFER_REQ_LIST_BASE_H);
+	ufshcd_writel(hba, lower_32_bits(hba->utmrdl_dma_addr),
+		      REG_UTP_TASK_REQ_LIST_BASE_L);
+	ufshcd_writel(hba, upper_32_bits(hba->utmrdl_dma_addr),
+		      REG_UTP_TASK_REQ_LIST_BASE_H);
+
+	if (ufshcd_is_link_hibern8(hba)) {
+		int ret = ufshcd_uic_hibern8_exit(hba);
+
+		if (!ret) {
+			ufshcd_set_link_active(hba);
+		} else {
+			dev_err(hba->dev, "%s: hibern8 exit failed %d\n",
+				__func__, ret);
+			/*
+			 * Force reset and restore. Any other actions can lead
+			 * to an unrecoverable state.
+			 */
+			ufshcd_set_link_off(hba);
+		}
+	}
+
+	return 0;
+}
+
 static int ufs_intel_ehl_init(struct ufs_hba *hba)
 {
 	hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8;
@@ -174,6 +211,7 @@ static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = {
 	.init			= ufs_intel_common_init,
 	.exit			= ufs_intel_common_exit,
 	.link_startup_notify	= ufs_intel_link_startup_notify,
+	.resume			= ufs_intel_resume,
 };
 
 static struct ufs_hba_variant_ops ufs_intel_ehl_hba_vops = {
@@ -181,6 +219,7 @@ static struct ufs_hba_variant_ops ufs_intel_ehl_hba_vops = {
 	.init			= ufs_intel_ehl_init,
 	.exit			= ufs_intel_common_exit,
 	.link_startup_notify	= ufs_intel_link_startup_notify,
+	.resume			= ufs_intel_resume,
 };
 
 #ifdef CONFIG_PM_SLEEP
@@ -207,6 +246,30 @@ static int ufshcd_pci_resume(struct device *dev)
 {
 	return ufshcd_system_resume(dev_get_drvdata(dev));
 }
+
+/**
+ * ufshcd_pci_poweroff - suspend-to-disk poweroff function
+ * @dev: pointer to PCI device handle
+ *
+ * Returns 0 if successful
+ * Returns non-zero otherwise
+ */
+static int ufshcd_pci_poweroff(struct device *dev)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	int spm_lvl = hba->spm_lvl;
+	int ret;
+
+	/*
+	 * For poweroff we need to set the UFS device to PowerDown mode.
+	 * Force spm_lvl to ensure that.
+	 */
+	hba->spm_lvl = 5;
+	ret = ufshcd_system_suspend(hba);
+	hba->spm_lvl = spm_lvl;
+	return ret;
+}
+
 #endif /* !CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM
@@ -302,8 +365,14 @@ ufshcd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 }
 
 static const struct dev_pm_ops ufshcd_pci_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(ufshcd_pci_suspend,
-				ufshcd_pci_resume)
+#ifdef CONFIG_PM_SLEEP
+	.suspend	= ufshcd_pci_suspend,
+	.resume		= ufshcd_pci_resume,
+	.freeze		= ufshcd_pci_suspend,
+	.thaw		= ufshcd_pci_resume,
+	.poweroff	= ufshcd_pci_poweroff,
+	.restore	= ufshcd_pci_resume,
+#endif
 	SET_RUNTIME_PM_OPS(ufshcd_pci_runtime_suspend,
 			   ufshcd_pci_runtime_resume,
 			   ufshcd_pci_runtime_idle)
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 9902b7e3aa4a..e31d2c5c7b23 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -225,6 +225,7 @@ static int ufshcd_reset_and_restore(struct ufs_hba *hba);
 static int ufshcd_eh_host_reset_handler(struct scsi_cmnd *cmd);
 static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag);
 static void ufshcd_hba_exit(struct ufs_hba *hba);
+static int ufshcd_clear_ua_wluns(struct ufs_hba *hba);
 static int ufshcd_probe_hba(struct ufs_hba *hba, bool async);
 static int ufshcd_setup_clocks(struct ufs_hba *hba, bool on);
 static int ufshcd_uic_hibern8_enter(struct ufs_hba *hba);
@@ -288,7 +289,8 @@ static inline void ufshcd_wb_config(struct ufs_hba *hba)
 	if (ret)
 		dev_err(hba->dev, "%s: En WB flush during H8: failed: %d\n",
 			__func__, ret);
-	ufshcd_wb_toggle_flush(hba, true);
+	if (!(hba->quirks & UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL))
+		ufshcd_wb_toggle_flush(hba, true);
 }
 
 static void ufshcd_scsi_unblock_requests(struct ufs_hba *hba)
@@ -580,6 +582,23 @@ static void ufshcd_print_pwr_info(struct ufs_hba *hba)
 		 hba->pwr_info.hs_rate);
 }
 
+static void ufshcd_device_reset(struct ufs_hba *hba)
+{
+	int err;
+
+	err = ufshcd_vops_device_reset(hba);
+
+	if (!err) {
+		ufshcd_set_ufs_dev_active(hba);
+		if (ufshcd_is_wb_allowed(hba)) {
+			hba->wb_enabled = false;
+			hba->wb_buf_flush_enabled = false;
+		}
+	}
+	if (err != -EOPNOTSUPP)
+		ufshcd_update_evt_hist(hba, UFS_EVT_DEV_RESET, err);
+}
+
 void ufshcd_delay_us(unsigned long us, unsigned long tolerance)
 {
 	if (!us)
@@ -3665,7 +3684,7 @@ static int ufshcd_dme_enable(struct ufs_hba *hba)
 	ret = ufshcd_send_uic_cmd(hba, &uic_cmd);
 	if (ret)
 		dev_err(hba->dev,
-			"dme-reset: error code %d\n", ret);
+			"dme-enable: error code %d\n", ret);
 
 	return ret;
 }
@@ -3964,7 +3983,7 @@ int ufshcd_link_recovery(struct ufs_hba *hba)
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
 	/* Reset the attached device */
-	ufshcd_vops_device_reset(hba);
+	ufshcd_device_reset(hba);
 
 	ret = ufshcd_host_reset_and_restore(hba);
 
@@ -5418,9 +5437,6 @@ static int ufshcd_wb_toggle_flush_during_h8(struct ufs_hba *hba, bool set)
 
 static inline void ufshcd_wb_toggle_flush(struct ufs_hba *hba, bool enable)
 {
-	if (hba->quirks & UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL)
-		return;
-
 	if (enable)
 		ufshcd_wb_buf_flush_enable(hba);
 	else
@@ -6643,19 +6659,16 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd)
 {
 	struct Scsi_Host *host;
 	struct ufs_hba *hba;
-	unsigned int tag;
 	u32 pos;
 	int err;
-	u8 resp = 0xF;
-	struct ufshcd_lrb *lrbp;
+	u8 resp = 0xF, lun;
 	unsigned long flags;
 
 	host = cmd->device->host;
 	hba = shost_priv(host);
-	tag = cmd->request->tag;
 
-	lrbp = &hba->lrb[tag];
-	err = ufshcd_issue_tm_cmd(hba, lrbp->lun, 0, UFS_LOGICAL_RESET, &resp);
+	lun = ufshcd_scsi_to_upiu_lun(cmd->device->lun);
+	err = ufshcd_issue_tm_cmd(hba, lun, 0, UFS_LOGICAL_RESET, &resp);
 	if (err || resp != UPIU_TASK_MANAGEMENT_FUNC_COMPL) {
 		if (!err)
 			err = resp;
@@ -6664,7 +6677,7 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd)
 
 	/* clear the commands that were pending for corresponding LUN */
 	for_each_set_bit(pos, &hba->outstanding_reqs, hba->nutrs) {
-		if (hba->lrb[pos].lun == lrbp->lun) {
+		if (hba->lrb[pos].lun == lun) {
 			err = ufshcd_clear_cmd(hba, pos);
 			if (err)
 				break;
@@ -6930,7 +6943,8 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)
 
 	/* Establish the link again and restore the device */
 	err = ufshcd_probe_hba(hba, false);
-
+	if (!err)
+		ufshcd_clear_ua_wluns(hba);
 out:
 	if (err)
 		dev_err(hba->dev, "%s: Host init failed %d\n", __func__, err);
@@ -6968,7 +6982,7 @@ static int ufshcd_reset_and_restore(struct ufs_hba *hba)
 
 	do {
 		/* Reset the attached device */
-		ufshcd_vops_device_reset(hba);
+		ufshcd_device_reset(hba);
 
 		err = ufshcd_host_reset_and_restore(hba);
 	} while (err && --retries);
@@ -8045,7 +8059,7 @@ static int ufshcd_disable_vreg(struct device *dev, struct ufs_vreg *vreg)
 {
 	int ret = 0;
 
-	if (!vreg || !vreg->enabled)
+	if (!vreg || !vreg->enabled || vreg->always_on)
 		goto out;
 
 	ret = regulator_disable(vreg->reg);
@@ -8414,13 +8428,7 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 	 * handling context.
 	 */
 	hba->host->eh_noresume = 1;
-	if (hba->wlun_dev_clr_ua) {
-		ret = ufshcd_send_request_sense(hba, sdp);
-		if (ret)
-			goto out;
-		/* Unit attention condition is cleared now */
-		hba->wlun_dev_clr_ua = false;
-	}
+	ufshcd_clear_ua_wluns(hba);
 
 	cmd[4] = pwr_mode << 4;
 
@@ -8441,7 +8449,7 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 
 	if (!ret)
 		hba->curr_dev_pwr_mode = pwr_mode;
-out:
+
 	scsi_device_put(sdp);
 	hba->host->eh_noresume = 0;
 	return ret;
@@ -8685,6 +8693,8 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 			ufshcd_wb_need_flush(hba));
 	}
 
+	flush_work(&hba->eeh_work);
+
 	if (req_dev_pwr_mode != hba->curr_dev_pwr_mode) {
 		if (!ufshcd_is_runtime_pm(pm_op))
 			/* ensure that bkops is disabled */
@@ -8697,8 +8707,6 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		}
 	}
 
-	flush_work(&hba->eeh_work);
-
 	/*
 	 * In the case of DeepSleep, the device is expected to remain powered
 	 * with the link off, so do not check for bkops.
@@ -8747,7 +8755,7 @@ set_link_active:
 	 * further below.
 	 */
 	if (ufshcd_is_ufs_dev_deepsleep(hba)) {
-		ufshcd_vops_device_reset(hba);
+		ufshcd_device_reset(hba);
 		WARN_ON(!ufshcd_is_link_off(hba));
 	}
 	if (ufshcd_is_link_hibern8(hba) && !ufshcd_uic_hibern8_exit(hba))
@@ -8757,7 +8765,7 @@ set_link_active:
 set_dev_active:
 	/* Can also get here needing to exit DeepSleep */
 	if (ufshcd_is_ufs_dev_deepsleep(hba)) {
-		ufshcd_vops_device_reset(hba);
+		ufshcd_device_reset(hba);
 		ufshcd_host_reset_and_restore(hba);
 	}
 	if (!ufshcd_set_dev_pwr_mode(hba, UFS_ACTIVE_PWR_MODE))
@@ -8925,7 +8933,8 @@ int ufshcd_system_suspend(struct ufs_hba *hba)
 	if ((ufs_get_pm_lvl_to_dev_pwr_mode(hba->spm_lvl) ==
 	     hba->curr_dev_pwr_mode) &&
 	    (ufs_get_pm_lvl_to_link_pwr_state(hba->spm_lvl) ==
-	     hba->uic_link_state))
+	     hba->uic_link_state) &&
+	     !hba->dev_info.b_rpm_dev_flush_capable)
 		goto out;
 
 	if (pm_runtime_suspended(hba->dev)) {
@@ -9353,7 +9362,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	}
 
 	/* Reset the attached device */
-	ufshcd_vops_device_reset(hba);
+	ufshcd_device_reset(hba);
 
 	ufshcd_init_crypto(hba);
 
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index f8c2467dc014..aa9ea3552323 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -1218,16 +1218,12 @@ static inline void ufshcd_vops_dbg_register_dump(struct ufs_hba *hba)
 		hba->vops->dbg_register_dump(hba);
 }
 
-static inline void ufshcd_vops_device_reset(struct ufs_hba *hba)
+static inline int ufshcd_vops_device_reset(struct ufs_hba *hba)
 {
-	if (hba->vops && hba->vops->device_reset) {
-		int err = hba->vops->device_reset(hba);
-
-		if (!err)
-			ufshcd_set_ufs_dev_active(hba);
-		if (err != -EOPNOTSUPP)
-			ufshcd_update_evt_hist(hba, UFS_EVT_DEV_RESET, err);
-	}
+	if (hba->vops && hba->vops->device_reset)
+		return hba->vops->device_reset(hba);
+
+	return -EOPNOTSUPP;
 }
 
 static inline void ufshcd_vops_config_scaling_param(struct ufs_hba *hba,
diff --git a/drivers/spi/spi-altera.c b/drivers/spi/spi-altera.c
index 809bfff3690a..cbc4c28c1541 100644
--- a/drivers/spi/spi-altera.c
+++ b/drivers/spi/spi-altera.c
@@ -189,24 +189,26 @@ static int altera_spi_txrx(struct spi_master *master,
 
 		/* send the first byte */
 		altera_spi_tx_word(hw);
-	} else {
-		while (hw->count < hw->len) {
-			altera_spi_tx_word(hw);
 
-			for (;;) {
-				altr_spi_readl(hw, ALTERA_SPI_STATUS, &val);
-				if (val & ALTERA_SPI_STATUS_RRDY_MSK)
-					break;
+		return 1;
+	}
+
+	while (hw->count < hw->len) {
+		altera_spi_tx_word(hw);
 
-				cpu_relax();
-			}
+		for (;;) {
+			altr_spi_readl(hw, ALTERA_SPI_STATUS, &val);
+			if (val & ALTERA_SPI_STATUS_RRDY_MSK)
+				break;
 
-			altera_spi_rx_word(hw);
+			cpu_relax();
 		}
-		spi_finalize_current_transfer(master);
+
+		altera_spi_rx_word(hw);
 	}
+	spi_finalize_current_transfer(master);
 
-	return t->len;
+	return 0;
 }
 
 static irqreturn_t altera_spi_irq(int irq, void *dev)
diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index 512e925d5ea4..881f645661cc 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -83,6 +83,7 @@ struct spi_geni_master {
 	spinlock_t lock;
 	int irq;
 	bool cs_flag;
+	bool abort_failed;
 };
 
 static int get_spi_clk_cfg(unsigned int speed_hz,
@@ -141,8 +142,49 @@ static void handle_fifo_timeout(struct spi_master *spi,
 	spin_unlock_irq(&mas->lock);
 
 	time_left = wait_for_completion_timeout(&mas->abort_done, HZ);
-	if (!time_left)
+	if (!time_left) {
 		dev_err(mas->dev, "Failed to cancel/abort m_cmd\n");
+
+		/*
+		 * No need for a lock since SPI core has a lock and we never
+		 * access this from an interrupt.
+		 */
+		mas->abort_failed = true;
+	}
+}
+
+static bool spi_geni_is_abort_still_pending(struct spi_geni_master *mas)
+{
+	struct geni_se *se = &mas->se;
+	u32 m_irq, m_irq_en;
+
+	if (!mas->abort_failed)
+		return false;
+
+	/*
+	 * The only known case where a transfer times out and then a cancel
+	 * times out then an abort times out is if something is blocking our
+	 * interrupt handler from running.  Avoid starting any new transfers
+	 * until that sorts itself out.
+	 */
+	spin_lock_irq(&mas->lock);
+	m_irq = readl(se->base + SE_GENI_M_IRQ_STATUS);
+	m_irq_en = readl(se->base + SE_GENI_M_IRQ_EN);
+	spin_unlock_irq(&mas->lock);
+
+	if (m_irq & m_irq_en) {
+		dev_err(mas->dev, "Interrupts pending after abort: %#010x\n",
+			m_irq & m_irq_en);
+		return true;
+	}
+
+	/*
+	 * If we're here the problem resolved itself so no need to check more
+	 * on future transfers.
+	 */
+	mas->abort_failed = false;
+
+	return false;
 }
 
 static void spi_geni_set_cs(struct spi_device *slv, bool set_flag)
@@ -158,10 +200,21 @@ static void spi_geni_set_cs(struct spi_device *slv, bool set_flag)
 	if (set_flag == mas->cs_flag)
 		return;
 
-	mas->cs_flag = set_flag;
-
 	pm_runtime_get_sync(mas->dev);
+
+	if (spi_geni_is_abort_still_pending(mas)) {
+		dev_err(mas->dev, "Can't set chip select\n");
+		goto exit;
+	}
+
 	spin_lock_irq(&mas->lock);
+	if (mas->cur_xfer) {
+		dev_err(mas->dev, "Can't set CS when prev xfer running\n");
+		spin_unlock_irq(&mas->lock);
+		goto exit;
+	}
+
+	mas->cs_flag = set_flag;
 	reinit_completion(&mas->cs_done);
 	if (set_flag)
 		geni_se_setup_m_cmd(se, SPI_CS_ASSERT, 0);
@@ -170,9 +223,12 @@ static void spi_geni_set_cs(struct spi_device *slv, bool set_flag)
 	spin_unlock_irq(&mas->lock);
 
 	time_left = wait_for_completion_timeout(&mas->cs_done, HZ);
-	if (!time_left)
+	if (!time_left) {
+		dev_warn(mas->dev, "Timeout setting chip select\n");
 		handle_fifo_timeout(spi, NULL);
+	}
 
+exit:
 	pm_runtime_put(mas->dev);
 }
 
@@ -280,6 +336,9 @@ static int spi_geni_prepare_message(struct spi_master *spi,
 	int ret;
 	struct spi_geni_master *mas = spi_master_get_devdata(spi);
 
+	if (spi_geni_is_abort_still_pending(mas))
+		return -EBUSY;
+
 	ret = setup_fifo_params(spi_msg->spi, spi);
 	if (ret)
 		dev_err(mas->dev, "Couldn't select mode %d\n", ret);
@@ -354,6 +413,12 @@ static bool geni_spi_handle_tx(struct spi_geni_master *mas)
 	unsigned int bytes_per_fifo_word = geni_byte_per_fifo_word(mas);
 	unsigned int i = 0;
 
+	/* Stop the watermark IRQ if nothing to send */
+	if (!mas->cur_xfer) {
+		writel(0, se->base + SE_GENI_TX_WATERMARK_REG);
+		return false;
+	}
+
 	max_bytes = (mas->tx_fifo_depth - mas->tx_wm) * bytes_per_fifo_word;
 	if (mas->tx_rem_bytes < max_bytes)
 		max_bytes = mas->tx_rem_bytes;
@@ -396,6 +461,14 @@ static void geni_spi_handle_rx(struct spi_geni_master *mas)
 		if (rx_last_byte_valid && rx_last_byte_valid < 4)
 			rx_bytes -= bytes_per_fifo_word - rx_last_byte_valid;
 	}
+
+	/* Clear out the FIFO and bail if nowhere to put it */
+	if (!mas->cur_xfer) {
+		for (i = 0; i < DIV_ROUND_UP(rx_bytes, bytes_per_fifo_word); i++)
+			readl(se->base + SE_GENI_RX_FIFOn);
+		return;
+	}
+
 	if (mas->rx_rem_bytes < rx_bytes)
 		rx_bytes = mas->rx_rem_bytes;
 
@@ -495,6 +568,9 @@ static int spi_geni_transfer_one(struct spi_master *spi,
 {
 	struct spi_geni_master *mas = spi_master_get_devdata(spi);
 
+	if (spi_geni_is_abort_still_pending(mas))
+		return -EBUSY;
+
 	/* Terminate and return success for 0 byte length transfer */
 	if (!xfer->len)
 		return 0;
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index 471dedf3d339..6017209c6d2f 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -493,9 +493,9 @@ static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi, u32 xfer_len)
 
 	/* align packet size with data registers access */
 	if (spi->cur_bpw > 8)
-		fthlv -= (fthlv % 2); /* multiple of 2 */
+		fthlv += (fthlv % 2) ? 1 : 0;
 	else
-		fthlv -= (fthlv % 4); /* multiple of 4 */
+		fthlv += (fthlv % 4) ? (4 - (fthlv % 4)) : 0;
 
 	if (!fthlv)
 		fthlv = 1;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 51d7c004fbab..720ab34784c1 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1108,6 +1108,7 @@ static int spi_transfer_wait(struct spi_controller *ctlr,
 {
 	struct spi_statistics *statm = &ctlr->statistics;
 	struct spi_statistics *stats = &msg->spi->statistics;
+	u32 speed_hz = xfer->speed_hz;
 	unsigned long long ms;
 
 	if (spi_controller_is_slave(ctlr)) {
@@ -1116,8 +1117,11 @@ static int spi_transfer_wait(struct spi_controller *ctlr,
 			return -EINTR;
 		}
 	} else {
+		if (!speed_hz)
+			speed_hz = 100000;
+
 		ms = 8LL * 1000LL * xfer->len;
-		do_div(ms, xfer->speed_hz);
+		do_div(ms, speed_hz);
 		ms += ms + 200; /* some tolerance */
 
 		if (ms > UINT_MAX)
@@ -3378,8 +3382,9 @@ int spi_setup(struct spi_device *spi)
 	if (status)
 		return status;
 
-	if (!spi->max_speed_hz ||
-	    spi->max_speed_hz > spi->controller->max_speed_hz)
+	if (spi->controller->max_speed_hz &&
+	    (!spi->max_speed_hz ||
+	     spi->max_speed_hz > spi->controller->max_speed_hz))
 		spi->max_speed_hz = spi->controller->max_speed_hz;
 
 	mutex_lock(&spi->controller->io_mutex);
diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index d99231c737fb..80d74cce2a01 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -2987,7 +2987,9 @@ static int put_compat_cmd(struct comedi32_cmd_struct __user *cmd32,
 	v32.chanlist_len = cmd->chanlist_len;
 	v32.data = ptr_to_compat(cmd->data);
 	v32.data_len = cmd->data_len;
-	return copy_to_user(cmd32, &v32, sizeof(v32));
+	if (copy_to_user(cmd32, &v32, sizeof(v32)))
+		return -EFAULT;
+	return 0;
 }
 
 /* Handle 32-bit COMEDI_CMD ioctl. */
diff --git a/drivers/staging/hikey9xx/hisi-spmi-controller.c b/drivers/staging/hikey9xx/hisi-spmi-controller.c
index 861aedd5de48..0d42bc65f39b 100644
--- a/drivers/staging/hikey9xx/hisi-spmi-controller.c
+++ b/drivers/staging/hikey9xx/hisi-spmi-controller.c
@@ -278,21 +278,24 @@ static int spmi_controller_probe(struct platform_device *pdev)
 	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!iores) {
 		dev_err(&pdev->dev, "can not get resource!\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_put_controller;
 	}
 
 	spmi_controller->base = devm_ioremap(&pdev->dev, iores->start,
 					     resource_size(iores));
 	if (!spmi_controller->base) {
 		dev_err(&pdev->dev, "can not remap base addr!\n");
-		return -EADDRNOTAVAIL;
+		ret = -EADDRNOTAVAIL;
+		goto err_put_controller;
 	}
 
 	ret = of_property_read_u32(pdev->dev.of_node, "spmi-channel",
 				   &spmi_controller->channel);
 	if (ret) {
 		dev_err(&pdev->dev, "can not get channel\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err_put_controller;
 	}
 
 	platform_set_drvdata(pdev, spmi_controller);
@@ -309,9 +312,15 @@ static int spmi_controller_probe(struct platform_device *pdev)
 	ctrl->write_cmd = spmi_write_cmd;
 
 	ret = spmi_controller_add(ctrl);
-	if (ret)
-		dev_err(&pdev->dev, "spmi_add_controller failed with error %d!\n", ret);
+	if (ret) {
+		dev_err(&pdev->dev, "spmi_controller_add failed with error %d!\n", ret);
+		goto err_put_controller;
+	}
+
+	return 0;
 
+err_put_controller:
+	spmi_controller_put(ctrl);
 	return ret;
 }
 
@@ -320,7 +329,7 @@ static int spmi_del_controller(struct platform_device *pdev)
 	struct spmi_controller *ctrl = platform_get_drvdata(pdev);
 
 	spmi_controller_remove(ctrl);
-	kfree(ctrl);
+	spmi_controller_put(ctrl);
 	return 0;
 }
 
diff --git a/drivers/staging/media/atomisp/pci/atomisp_subdev.c b/drivers/staging/media/atomisp/pci/atomisp_subdev.c
index 52b9fb18c87f..b666cb23e5ca 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_subdev.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_subdev.c
@@ -1062,26 +1062,6 @@ static const struct v4l2_ctrl_config ctrl_select_isp_version = {
 	.def = 0,
 };
 
-#if 0 /* #ifdef CONFIG_ION */
-/*
- * Control for ISP ion device fd
- *
- * userspace will open ion device and pass the fd to kernel.
- * this fd will be used to map shared fd to buffer.
- */
-/* V4L2_CID_ATOMISP_ION_DEVICE_FD is not defined */
-static const struct v4l2_ctrl_config ctrl_ion_dev_fd = {
-	.ops = &ctrl_ops,
-	.id = V4L2_CID_ATOMISP_ION_DEVICE_FD,
-	.type = V4L2_CTRL_TYPE_INTEGER,
-	.name = "Ion Device Fd",
-	.min = -1,
-	.max = 1024,
-	.step = 1,
-	.def = ION_FD_UNSET
-};
-#endif
-
 static void atomisp_init_subdev_pipe(struct atomisp_sub_device *asd,
 				     struct atomisp_video_pipe *pipe, enum v4l2_buf_type buf_type)
 {
diff --git a/drivers/staging/mt7621-dma/mtk-hsdma.c b/drivers/staging/mt7621-dma/mtk-hsdma.c
index d241349214e7..bc4bb4374313 100644
--- a/drivers/staging/mt7621-dma/mtk-hsdma.c
+++ b/drivers/staging/mt7621-dma/mtk-hsdma.c
@@ -712,7 +712,7 @@ static int mtk_hsdma_probe(struct platform_device *pdev)
 	ret = dma_async_device_register(dd);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register dma device\n");
-		return ret;
+		goto err_uninit_hsdma;
 	}
 
 	ret = of_dma_controller_register(pdev->dev.of_node,
@@ -728,6 +728,8 @@ static int mtk_hsdma_probe(struct platform_device *pdev)
 
 err_unregister:
 	dma_async_device_unregister(dd);
+err_uninit_hsdma:
+	mtk_hsdma_uninit(hsdma);
 	return ret;
 }
 
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 44e15d7fb2f0..66d6f1d06f21 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -46,60 +46,83 @@ static int target_xcopy_gen_naa_ieee(struct se_device *dev, unsigned char *buf)
 	return 0;
 }
 
-struct xcopy_dev_search_info {
-	const unsigned char *dev_wwn;
-	struct se_device *found_dev;
-};
-
+/**
+ * target_xcopy_locate_se_dev_e4_iter - compare XCOPY NAA device identifiers
+ *
+ * @se_dev: device being considered for match
+ * @dev_wwn: XCOPY requested NAA dev_wwn
+ * @return: 1 on match, 0 on no-match
+ */
 static int target_xcopy_locate_se_dev_e4_iter(struct se_device *se_dev,
-					      void *data)
+					      const unsigned char *dev_wwn)
 {
-	struct xcopy_dev_search_info *info = data;
 	unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN];
 	int rc;
 
-	if (!se_dev->dev_attrib.emulate_3pc)
+	if (!se_dev->dev_attrib.emulate_3pc) {
+		pr_debug("XCOPY: emulate_3pc disabled on se_dev %p\n", se_dev);
 		return 0;
+	}
 
 	memset(&tmp_dev_wwn[0], 0, XCOPY_NAA_IEEE_REGEX_LEN);
 	target_xcopy_gen_naa_ieee(se_dev, &tmp_dev_wwn[0]);
 
-	rc = memcmp(&tmp_dev_wwn[0], info->dev_wwn, XCOPY_NAA_IEEE_REGEX_LEN);
-	if (rc != 0)
-		return 0;
-
-	info->found_dev = se_dev;
-	pr_debug("XCOPY 0xe4: located se_dev: %p\n", se_dev);
-
-	rc = target_depend_item(&se_dev->dev_group.cg_item);
+	rc = memcmp(&tmp_dev_wwn[0], dev_wwn, XCOPY_NAA_IEEE_REGEX_LEN);
 	if (rc != 0) {
-		pr_err("configfs_depend_item attempt failed: %d for se_dev: %p\n",
-		       rc, se_dev);
-		return rc;
+		pr_debug("XCOPY: skip non-matching: %*ph\n",
+			 XCOPY_NAA_IEEE_REGEX_LEN, tmp_dev_wwn);
+		return 0;
 	}
+	pr_debug("XCOPY 0xe4: located se_dev: %p\n", se_dev);
 
-	pr_debug("Called configfs_depend_item for se_dev: %p se_dev->se_dev_group: %p\n",
-		 se_dev, &se_dev->dev_group);
 	return 1;
 }
 
-static int target_xcopy_locate_se_dev_e4(const unsigned char *dev_wwn,
-					struct se_device **found_dev)
+static int target_xcopy_locate_se_dev_e4(struct se_session *sess,
+					const unsigned char *dev_wwn,
+					struct se_device **_found_dev,
+					struct percpu_ref **_found_lun_ref)
 {
-	struct xcopy_dev_search_info info;
-	int ret;
-
-	memset(&info, 0, sizeof(info));
-	info.dev_wwn = dev_wwn;
-
-	ret = target_for_each_device(target_xcopy_locate_se_dev_e4_iter, &info);
-	if (ret == 1) {
-		*found_dev = info.found_dev;
-		return 0;
-	} else {
-		pr_debug_ratelimited("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n");
-		return -EINVAL;
+	struct se_dev_entry *deve;
+	struct se_node_acl *nacl;
+	struct se_lun *this_lun = NULL;
+	struct se_device *found_dev = NULL;
+
+	/* cmd with NULL sess indicates no associated $FABRIC_MOD */
+	if (!sess)
+		goto err_out;
+
+	pr_debug("XCOPY 0xe4: searching for: %*ph\n",
+		 XCOPY_NAA_IEEE_REGEX_LEN, dev_wwn);
+
+	nacl = sess->se_node_acl;
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link) {
+		struct se_device *this_dev;
+		int rc;
+
+		this_lun = rcu_dereference(deve->se_lun);
+		this_dev = rcu_dereference_raw(this_lun->lun_se_dev);
+
+		rc = target_xcopy_locate_se_dev_e4_iter(this_dev, dev_wwn);
+		if (rc) {
+			if (percpu_ref_tryget_live(&this_lun->lun_ref))
+				found_dev = this_dev;
+			break;
+		}
 	}
+	rcu_read_unlock();
+	if (found_dev == NULL)
+		goto err_out;
+
+	pr_debug("lun_ref held for se_dev: %p se_dev->se_dev_group: %p\n",
+		 found_dev, &found_dev->dev_group);
+	*_found_dev = found_dev;
+	*_found_lun_ref = &this_lun->lun_ref;
+	return 0;
+err_out:
+	pr_debug_ratelimited("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n");
+	return -EINVAL;
 }
 
 static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op *xop,
@@ -246,12 +269,16 @@ static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
 
 	switch (xop->op_origin) {
 	case XCOL_SOURCE_RECV_OP:
-		rc = target_xcopy_locate_se_dev_e4(xop->dst_tid_wwn,
-						&xop->dst_dev);
+		rc = target_xcopy_locate_se_dev_e4(se_cmd->se_sess,
+						xop->dst_tid_wwn,
+						&xop->dst_dev,
+						&xop->remote_lun_ref);
 		break;
 	case XCOL_DEST_RECV_OP:
-		rc = target_xcopy_locate_se_dev_e4(xop->src_tid_wwn,
-						&xop->src_dev);
+		rc = target_xcopy_locate_se_dev_e4(se_cmd->se_sess,
+						xop->src_tid_wwn,
+						&xop->src_dev,
+						&xop->remote_lun_ref);
 		break;
 	default:
 		pr_err("XCOPY CSCD descriptor IDs not found in CSCD list - "
@@ -391,18 +418,12 @@ static int xcopy_pt_get_cmd_state(struct se_cmd *se_cmd)
 
 static void xcopy_pt_undepend_remotedev(struct xcopy_op *xop)
 {
-	struct se_device *remote_dev;
-
 	if (xop->op_origin == XCOL_SOURCE_RECV_OP)
-		remote_dev = xop->dst_dev;
+		pr_debug("putting dst lun_ref for %p\n", xop->dst_dev);
 	else
-		remote_dev = xop->src_dev;
-
-	pr_debug("Calling configfs_undepend_item for"
-		  " remote_dev: %p remote_dev->dev_group: %p\n",
-		  remote_dev, &remote_dev->dev_group.cg_item);
+		pr_debug("putting src lun_ref for %p\n", xop->src_dev);
 
-	target_undepend_item(&remote_dev->dev_group.cg_item);
+	percpu_ref_put(xop->remote_lun_ref);
 }
 
 static void xcopy_pt_release_cmd(struct se_cmd *se_cmd)
diff --git a/drivers/target/target_core_xcopy.h b/drivers/target/target_core_xcopy.h
index c56a1bde9417..e5f20005179a 100644
--- a/drivers/target/target_core_xcopy.h
+++ b/drivers/target/target_core_xcopy.h
@@ -27,6 +27,7 @@ struct xcopy_op {
 	struct se_device *dst_dev;
 	unsigned char dst_tid_wwn[XCOPY_NAA_IEEE_REGEX_LEN];
 	unsigned char local_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN];
+	struct percpu_ref *remote_lun_ref;
 
 	sector_t src_lba;
 	sector_t dst_lba;
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index 47a6e42f0d04..e15cd6b5bb99 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -401,6 +401,20 @@ config MIPS_EJTAG_FDC_KGDB_CHAN
 	help
 	  FDC channel number to use for KGDB.
 
+config NULL_TTY
+	tristate "NULL TTY driver"
+	help
+	  Say Y here if you want a NULL TTY which simply discards messages.
+
+	  This is useful to allow userspace applications which expect a console
+	  device to work without modifications even when no console is
+	  available or desired.
+
+	  In order to use this driver, you should redirect the console to this
+	  TTY, or boot the kernel with console=ttynull.
+
+	  If unsure, say N.
+
 config TRACE_ROUTER
 	tristate "Trace data router for MIPI P1149.7 cJTAG standard"
 	depends on TRACE_SINK
diff --git a/drivers/tty/Makefile b/drivers/tty/Makefile
index 3c1c5a9240a7..b3ccae932660 100644
--- a/drivers/tty/Makefile
+++ b/drivers/tty/Makefile
@@ -2,7 +2,7 @@
 obj-$(CONFIG_TTY)		+= tty_io.o n_tty.o tty_ioctl.o tty_ldisc.o \
 				   tty_buffer.o tty_port.o tty_mutex.o \
 				   tty_ldsem.o tty_baudrate.o tty_jobctrl.o \
-				   n_null.o ttynull.o
+				   n_null.o
 obj-$(CONFIG_LEGACY_PTYS)	+= pty.o
 obj-$(CONFIG_UNIX98_PTYS)	+= pty.o
 obj-$(CONFIG_AUDIT)		+= tty_audit.o
@@ -25,6 +25,7 @@ obj-$(CONFIG_ISI)		+= isicom.o
 obj-$(CONFIG_MOXA_INTELLIO)	+= moxa.o
 obj-$(CONFIG_MOXA_SMARTIO)	+= mxser.o
 obj-$(CONFIG_NOZOMI)		+= nozomi.o
+obj-$(CONFIG_NULL_TTY)	        += ttynull.o
 obj-$(CONFIG_ROCKETPORT)	+= rocket.o
 obj-$(CONFIG_SYNCLINK_GT)	+= synclink_gt.o
 obj-$(CONFIG_PPC_EPAPR_HV_BYTECHAN) += ehv_bytechan.o
diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index 1066eebe3b28..328d5a78792f 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -1000,6 +1000,7 @@ static int sifive_serial_probe(struct platform_device *pdev)
 	/* Set up clock divider */
 	ssp->clkin_rate = clk_get_rate(ssp->clk);
 	ssp->baud_rate = SIFIVE_DEFAULT_BAUD_RATE;
+	ssp->port.uartclk = ssp->baud_rate * 16;
 	__ssp_update_div(ssp);
 
 	platform_set_drvdata(pdev, ssp);
diff --git a/drivers/tty/ttynull.c b/drivers/tty/ttynull.c
index eced70ec54e1..17f05b7eb6d3 100644
--- a/drivers/tty/ttynull.c
+++ b/drivers/tty/ttynull.c
@@ -2,13 +2,6 @@
 /*
  * Copyright (C) 2019 Axis Communications AB
  *
- * The console is useful for userspace applications which expect a console
- * device to work without modifications even when no console is available
- * or desired.
- *
- * In order to use this driver, you should redirect the console to this
- * TTY, or boot the kernel with console=ttynull.
- *
  * Based on ttyprintk.c:
  *  Copyright (C) 2010 Samo Pogacnik
  */
@@ -66,17 +59,6 @@ static struct console ttynull_console = {
 	.device = ttynull_device,
 };
 
-void __init register_ttynull_console(void)
-{
-	if (!ttynull_driver)
-		return;
-
-	if (add_preferred_console(ttynull_console.name, 0, NULL))
-		return;
-
-	register_console(&ttynull_console);
-}
-
 static int __init ttynull_init(void)
 {
 	struct tty_driver *driver;
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 9e12152ea46b..8b7bc10b6e8b 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -139,9 +139,13 @@ static struct imx_usbmisc_data *usbmisc_get_init_data(struct device *dev)
 	misc_pdev = of_find_device_by_node(args.np);
 	of_node_put(args.np);
 
-	if (!misc_pdev || !platform_get_drvdata(misc_pdev))
+	if (!misc_pdev)
 		return ERR_PTR(-EPROBE_DEFER);
 
+	if (!platform_get_drvdata(misc_pdev)) {
+		put_device(&misc_pdev->dev);
+		return ERR_PTR(-EPROBE_DEFER);
+	}
 	data->dev = &misc_pdev->dev;
 
 	/*
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index f52f1bc0559f..781905745812 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1895,6 +1895,10 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x04d8, 0xfd08),
 	.driver_info = IGNORE_DEVICE,
 	},
+
+	{ USB_DEVICE(0x04d8, 0xf58b),
+	.driver_info = IGNORE_DEVICE,
+	},
 #endif
 
 	/*Samsung phone in firmware update mode */
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 02d0cfd23bb2..508b1c3f8b73 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -465,13 +465,23 @@ static int service_outstanding_interrupt(struct wdm_device *desc)
 	if (!desc->resp_count || !--desc->resp_count)
 		goto out;
 
+	if (test_bit(WDM_DISCONNECTING, &desc->flags)) {
+		rv = -ENODEV;
+		goto out;
+	}
+	if (test_bit(WDM_RESETTING, &desc->flags)) {
+		rv = -EIO;
+		goto out;
+	}
+
 	set_bit(WDM_RESPONDING, &desc->flags);
 	spin_unlock_irq(&desc->iuspin);
 	rv = usb_submit_urb(desc->response, GFP_KERNEL);
 	spin_lock_irq(&desc->iuspin);
 	if (rv) {
-		dev_err(&desc->intf->dev,
-			"usb_submit_urb failed with result %d\n", rv);
+		if (!test_bit(WDM_DISCONNECTING, &desc->flags))
+			dev_err(&desc->intf->dev,
+				"usb_submit_urb failed with result %d\n", rv);
 
 		/* make sure the next notification trigger a submit */
 		clear_bit(WDM_RESPONDING, &desc->flags);
@@ -1027,9 +1037,9 @@ static void wdm_disconnect(struct usb_interface *intf)
 	wake_up_all(&desc->wait);
 	mutex_lock(&desc->rlock);
 	mutex_lock(&desc->wlock);
-	kill_urbs(desc);
 	cancel_work_sync(&desc->rxwork);
 	cancel_work_sync(&desc->service_outs_intr);
+	kill_urbs(desc);
 	mutex_unlock(&desc->wlock);
 	mutex_unlock(&desc->rlock);
 
diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index 67cbd42421be..134dc2005ce9 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -274,8 +274,25 @@ static int usblp_ctrl_msg(struct usblp *usblp, int request, int type, int dir, i
 #define usblp_reset(usblp)\
 	usblp_ctrl_msg(usblp, USBLP_REQ_RESET, USB_TYPE_CLASS, USB_DIR_OUT, USB_RECIP_OTHER, 0, NULL, 0)
 
-#define usblp_hp_channel_change_request(usblp, channel, buffer) \
-	usblp_ctrl_msg(usblp, USBLP_REQ_HP_CHANNEL_CHANGE_REQUEST, USB_TYPE_VENDOR, USB_DIR_IN, USB_RECIP_INTERFACE, channel, buffer, 1)
+static int usblp_hp_channel_change_request(struct usblp *usblp, int channel, u8 *new_channel)
+{
+	u8 *buf;
+	int ret;
+
+	buf = kzalloc(1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usblp_ctrl_msg(usblp, USBLP_REQ_HP_CHANNEL_CHANGE_REQUEST,
+			USB_TYPE_VENDOR, USB_DIR_IN, USB_RECIP_INTERFACE,
+			channel, buf, 1);
+	if (ret == 0)
+		*new_channel = buf[0];
+
+	kfree(buf);
+
+	return ret;
+}
 
 /*
  * See the description for usblp_select_alts() below for the usage
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 60886a7464c3..ad5a0f405a75 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1649,14 +1649,12 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
 	urb->status = status;
 	/*
 	 * This function can be called in task context inside another remote
-	 * coverage collection section, but KCOV doesn't support that kind of
+	 * coverage collection section, but kcov doesn't support that kind of
 	 * recursion yet. Only collect coverage in softirq context for now.
 	 */
-	if (in_serving_softirq())
-		kcov_remote_start_usb((u64)urb->dev->bus->busnum);
+	kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum);
 	urb->complete(urb);
-	if (in_serving_softirq())
-		kcov_remote_stop();
+	kcov_remote_stop_softirq();
 
 	usb_anchor_resume_wakeups(anchor);
 	atomic_dec(&urb->use_count);
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 2f95f08ca511..1b241f937d8f 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -285,6 +285,7 @@
 
 /* Global USB2 PHY Vendor Control Register */
 #define DWC3_GUSB2PHYACC_NEWREGREQ	BIT(25)
+#define DWC3_GUSB2PHYACC_DONE		BIT(24)
 #define DWC3_GUSB2PHYACC_BUSY		BIT(23)
 #define DWC3_GUSB2PHYACC_WRITE		BIT(22)
 #define DWC3_GUSB2PHYACC_ADDR(n)	(n << 16)
diff --git a/drivers/usb/dwc3/dwc3-meson-g12a.c b/drivers/usb/dwc3/dwc3-meson-g12a.c
index 417e05381b5d..bdf1f98dfad8 100644
--- a/drivers/usb/dwc3/dwc3-meson-g12a.c
+++ b/drivers/usb/dwc3/dwc3-meson-g12a.c
@@ -754,7 +754,7 @@ static int dwc3_meson_g12a_probe(struct platform_device *pdev)
 
 	ret = priv->drvdata->setup_regmaps(priv, base);
 	if (ret)
-		return ret;
+		goto err_disable_clks;
 
 	if (priv->vbus) {
 		ret = regulator_enable(priv->vbus);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 78cb4db8a6e4..ee44321fee38 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1763,6 +1763,8 @@ static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
 			list_for_each_entry_safe(r, t, &dep->started_list, list)
 				dwc3_gadget_move_cancelled_request(r);
 
+			dep->flags &= ~DWC3_EP_WAIT_TRANSFER_COMPLETE;
+
 			goto out;
 		}
 	}
@@ -2083,6 +2085,7 @@ static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on, int suspend)
 
 static void dwc3_gadget_disable_irq(struct dwc3 *dwc);
 static void __dwc3_gadget_stop(struct dwc3 *dwc);
+static int __dwc3_gadget_start(struct dwc3 *dwc);
 
 static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on)
 {
@@ -2145,6 +2148,8 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on)
 			dwc->ev_buf->lpos = (dwc->ev_buf->lpos + count) %
 						dwc->ev_buf->length;
 		}
+	} else {
+		__dwc3_gadget_start(dwc);
 	}
 
 	ret = dwc3_gadget_run_stop(dwc, is_on, false);
@@ -2319,10 +2324,6 @@ static int dwc3_gadget_start(struct usb_gadget *g,
 	}
 
 	dwc->gadget_driver	= driver;
-
-	if (pm_runtime_active(dwc->dev))
-		__dwc3_gadget_start(dwc);
-
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return 0;
@@ -2348,13 +2349,6 @@ static int dwc3_gadget_stop(struct usb_gadget *g)
 	unsigned long		flags;
 
 	spin_lock_irqsave(&dwc->lock, flags);
-
-	if (pm_runtime_suspended(dwc->dev))
-		goto out;
-
-	__dwc3_gadget_stop(dwc);
-
-out:
 	dwc->gadget_driver	= NULL;
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
diff --git a/drivers/usb/dwc3/ulpi.c b/drivers/usb/dwc3/ulpi.c
index aa213c9815f6..f23f4c9a557e 100644
--- a/drivers/usb/dwc3/ulpi.c
+++ b/drivers/usb/dwc3/ulpi.c
@@ -7,6 +7,8 @@
  * Author: Heikki Krogerus <heikki.krogerus@linux.intel.com>
  */
 
+#include <linux/delay.h>
+#include <linux/time64.h>
 #include <linux/ulpi/regs.h>
 
 #include "core.h"
@@ -17,14 +19,28 @@
 		DWC3_GUSB2PHYACC_ADDR(ULPI_ACCESS_EXTENDED) | \
 		DWC3_GUSB2PHYACC_EXTEND_ADDR(a) : DWC3_GUSB2PHYACC_ADDR(a))
 
-static int dwc3_ulpi_busyloop(struct dwc3 *dwc)
+#define DWC3_ULPI_BASE_DELAY	DIV_ROUND_UP(NSEC_PER_SEC, 60000000L)
+
+static int dwc3_ulpi_busyloop(struct dwc3 *dwc, u8 addr, bool read)
 {
-	unsigned int count = 1000;
+	unsigned long ns = 5L * DWC3_ULPI_BASE_DELAY;
+	unsigned int count = 10000;
 	u32 reg;
 
+	if (addr >= ULPI_EXT_VENDOR_SPECIFIC)
+		ns += DWC3_ULPI_BASE_DELAY;
+
+	if (read)
+		ns += DWC3_ULPI_BASE_DELAY;
+
+	reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
+	if (reg & DWC3_GUSB2PHYCFG_SUSPHY)
+		usleep_range(1000, 1200);
+
 	while (count--) {
+		ndelay(ns);
 		reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYACC(0));
-		if (!(reg & DWC3_GUSB2PHYACC_BUSY))
+		if (reg & DWC3_GUSB2PHYACC_DONE)
 			return 0;
 		cpu_relax();
 	}
@@ -38,16 +54,10 @@ static int dwc3_ulpi_read(struct device *dev, u8 addr)
 	u32 reg;
 	int ret;
 
-	reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
-	if (reg & DWC3_GUSB2PHYCFG_SUSPHY) {
-		reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
-		dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
-	}
-
 	reg = DWC3_GUSB2PHYACC_NEWREGREQ | DWC3_ULPI_ADDR(addr);
 	dwc3_writel(dwc->regs, DWC3_GUSB2PHYACC(0), reg);
 
-	ret = dwc3_ulpi_busyloop(dwc);
+	ret = dwc3_ulpi_busyloop(dwc, addr, true);
 	if (ret)
 		return ret;
 
@@ -61,17 +71,11 @@ static int dwc3_ulpi_write(struct device *dev, u8 addr, u8 val)
 	struct dwc3 *dwc = dev_get_drvdata(dev);
 	u32 reg;
 
-	reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
-	if (reg & DWC3_GUSB2PHYCFG_SUSPHY) {
-		reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
-		dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
-	}
-
 	reg = DWC3_GUSB2PHYACC_NEWREGREQ | DWC3_ULPI_ADDR(addr);
 	reg |= DWC3_GUSB2PHYACC_WRITE | val;
 	dwc3_writel(dwc->regs, DWC3_GUSB2PHYACC(0), reg);
 
-	return dwc3_ulpi_busyloop(dwc);
+	return dwc3_ulpi_busyloop(dwc, addr, false);
 }
 
 static const struct ulpi_ops dwc3_ulpi_ops = {
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index 7e47e6223089..2d152571a7de 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -265,6 +265,7 @@ config USB_CONFIGFS_NCM
 	depends on NET
 	select USB_U_ETHER
 	select USB_F_NCM
+	select CRC32
 	help
 	  NCM is an advanced protocol for Ethernet encapsulation, allows
 	  grouping of several ethernet frames into one USB transfer and
@@ -314,6 +315,7 @@ config USB_CONFIGFS_EEM
 	depends on NET
 	select USB_U_ETHER
 	select USB_F_EEM
+	select CRC32
 	help
 	  CDC EEM is a newer USB standard that is somewhat simpler than CDC ECM
 	  and therefore can be supported by more hardware.  Technically ECM and
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index c6d455f2bb92..1a556a628971 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -392,8 +392,11 @@ int usb_function_deactivate(struct usb_function *function)
 
 	spin_lock_irqsave(&cdev->lock, flags);
 
-	if (cdev->deactivations == 0)
+	if (cdev->deactivations == 0) {
+		spin_unlock_irqrestore(&cdev->lock, flags);
 		status = usb_gadget_deactivate(cdev->gadget);
+		spin_lock_irqsave(&cdev->lock, flags);
+	}
 	if (status == 0)
 		cdev->deactivations++;
 
@@ -424,8 +427,11 @@ int usb_function_activate(struct usb_function *function)
 		status = -EINVAL;
 	else {
 		cdev->deactivations--;
-		if (cdev->deactivations == 0)
+		if (cdev->deactivations == 0) {
+			spin_unlock_irqrestore(&cdev->lock, flags);
 			status = usb_gadget_activate(cdev->gadget);
+			spin_lock_irqsave(&cdev->lock, flags);
+		}
 	}
 
 	spin_unlock_irqrestore(&cdev->lock, flags);
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 56051bb97349..36ffb43f9c1a 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -221,9 +221,16 @@ static ssize_t gadget_dev_desc_bcdUSB_store(struct config_item *item,
 
 static ssize_t gadget_dev_desc_UDC_show(struct config_item *item, char *page)
 {
-	char *udc_name = to_gadget_info(item)->composite.gadget_driver.udc_name;
+	struct gadget_info *gi = to_gadget_info(item);
+	char *udc_name;
+	int ret;
+
+	mutex_lock(&gi->lock);
+	udc_name = gi->composite.gadget_driver.udc_name;
+	ret = sprintf(page, "%s\n", udc_name ?: "");
+	mutex_unlock(&gi->lock);
 
-	return sprintf(page, "%s\n", udc_name ?: "");
+	return ret;
 }
 
 static int unregister_gadget(struct gadget_info *gi)
@@ -1248,9 +1255,9 @@ static void purge_configs_funcs(struct gadget_info *gi)
 
 		cfg = container_of(c, struct config_usb_cfg, c);
 
-		list_for_each_entry_safe(f, tmp, &c->functions, list) {
+		list_for_each_entry_safe_reverse(f, tmp, &c->functions, list) {
 
-			list_move_tail(&f->list, &cfg->func_list);
+			list_move(&f->list, &cfg->func_list);
 			if (f->unbind) {
 				dev_dbg(&gi->cdev.gadget->dev,
 					"unbind function '%s'/%p\n",
@@ -1536,7 +1543,7 @@ static const struct usb_gadget_driver configfs_driver_template = {
 	.suspend	= configfs_composite_suspend,
 	.resume		= configfs_composite_resume,
 
-	.max_speed	= USB_SPEED_SUPER,
+	.max_speed	= USB_SPEED_SUPER_PLUS,
 	.driver = {
 		.owner          = THIS_MODULE,
 		.name		= "configfs-gadget",
@@ -1576,7 +1583,7 @@ static struct config_group *gadgets_make(
 	gi->composite.unbind = configfs_do_nothing;
 	gi->composite.suspend = NULL;
 	gi->composite.resume = NULL;
-	gi->composite.max_speed = USB_SPEED_SUPER;
+	gi->composite.max_speed = USB_SPEED_SUPER_PLUS;
 
 	spin_lock_init(&gi->spinlock);
 	mutex_init(&gi->lock);
diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c
index 64a4112068fc..2f1eb2e81d30 100644
--- a/drivers/usb/gadget/function/f_printer.c
+++ b/drivers/usb/gadget/function/f_printer.c
@@ -1162,6 +1162,7 @@ fail_tx_reqs:
 		printer_req_free(dev->in_ep, req);
 	}
 
+	usb_free_all_descriptors(f);
 	return ret;
 
 }
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index 3633df6d7610..5d960b6603b6 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -271,7 +271,7 @@ static struct usb_endpoint_descriptor fs_epout_desc = {
 
 	.bEndpointAddress = USB_DIR_OUT,
 	.bmAttributes = USB_ENDPOINT_XFER_ISOC | USB_ENDPOINT_SYNC_ASYNC,
-	.wMaxPacketSize = cpu_to_le16(1023),
+	/* .wMaxPacketSize = DYNAMIC */
 	.bInterval = 1,
 };
 
@@ -280,7 +280,7 @@ static struct usb_endpoint_descriptor hs_epout_desc = {
 	.bDescriptorType = USB_DT_ENDPOINT,
 
 	.bmAttributes = USB_ENDPOINT_XFER_ISOC | USB_ENDPOINT_SYNC_ASYNC,
-	.wMaxPacketSize = cpu_to_le16(1024),
+	/* .wMaxPacketSize = DYNAMIC */
 	.bInterval = 4,
 };
 
@@ -348,7 +348,7 @@ static struct usb_endpoint_descriptor fs_epin_desc = {
 
 	.bEndpointAddress = USB_DIR_IN,
 	.bmAttributes = USB_ENDPOINT_XFER_ISOC | USB_ENDPOINT_SYNC_ASYNC,
-	.wMaxPacketSize = cpu_to_le16(1023),
+	/* .wMaxPacketSize = DYNAMIC */
 	.bInterval = 1,
 };
 
@@ -357,7 +357,7 @@ static struct usb_endpoint_descriptor hs_epin_desc = {
 	.bDescriptorType = USB_DT_ENDPOINT,
 
 	.bmAttributes = USB_ENDPOINT_XFER_ISOC | USB_ENDPOINT_SYNC_ASYNC,
-	.wMaxPacketSize = cpu_to_le16(1024),
+	/* .wMaxPacketSize = DYNAMIC */
 	.bInterval = 4,
 };
 
@@ -444,12 +444,28 @@ struct cntrl_range_lay3 {
 	__le32	dRES;
 } __packed;
 
-static void set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts,
+static int set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts,
 	struct usb_endpoint_descriptor *ep_desc,
-	unsigned int factor, bool is_playback)
+	enum usb_device_speed speed, bool is_playback)
 {
 	int chmask, srate, ssize;
-	u16 max_packet_size;
+	u16 max_size_bw, max_size_ep;
+	unsigned int factor;
+
+	switch (speed) {
+	case USB_SPEED_FULL:
+		max_size_ep = 1023;
+		factor = 1000;
+		break;
+
+	case USB_SPEED_HIGH:
+		max_size_ep = 1024;
+		factor = 8000;
+		break;
+
+	default:
+		return -EINVAL;
+	}
 
 	if (is_playback) {
 		chmask = uac2_opts->p_chmask;
@@ -461,10 +477,12 @@ static void set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts,
 		ssize = uac2_opts->c_ssize;
 	}
 
-	max_packet_size = num_channels(chmask) * ssize *
+	max_size_bw = num_channels(chmask) * ssize *
 		DIV_ROUND_UP(srate, factor / (1 << (ep_desc->bInterval - 1)));
-	ep_desc->wMaxPacketSize = cpu_to_le16(min_t(u16, max_packet_size,
-				le16_to_cpu(ep_desc->wMaxPacketSize)));
+	ep_desc->wMaxPacketSize = cpu_to_le16(min_t(u16, max_size_bw,
+						    max_size_ep));
+
+	return 0;
 }
 
 /* Use macro to overcome line length limitation */
@@ -670,10 +688,33 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn)
 	}
 
 	/* Calculate wMaxPacketSize according to audio bandwidth */
-	set_ep_max_packet_size(uac2_opts, &fs_epin_desc, 1000, true);
-	set_ep_max_packet_size(uac2_opts, &fs_epout_desc, 1000, false);
-	set_ep_max_packet_size(uac2_opts, &hs_epin_desc, 8000, true);
-	set_ep_max_packet_size(uac2_opts, &hs_epout_desc, 8000, false);
+	ret = set_ep_max_packet_size(uac2_opts, &fs_epin_desc, USB_SPEED_FULL,
+				     true);
+	if (ret < 0) {
+		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
+		return ret;
+	}
+
+	ret = set_ep_max_packet_size(uac2_opts, &fs_epout_desc, USB_SPEED_FULL,
+				     false);
+	if (ret < 0) {
+		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
+		return ret;
+	}
+
+	ret = set_ep_max_packet_size(uac2_opts, &hs_epin_desc, USB_SPEED_HIGH,
+				     true);
+	if (ret < 0) {
+		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
+		return ret;
+	}
+
+	ret = set_ep_max_packet_size(uac2_opts, &hs_epout_desc, USB_SPEED_HIGH,
+				     false);
+	if (ret < 0) {
+		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
+		return ret;
+	}
 
 	if (EPOUT_EN(uac2_opts)) {
 		agdev->out_ep = usb_ep_autoconfig(gadget, &fs_epout_desc);
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 31ea76adcc0d..c019f2b0c0af 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -45,9 +45,10 @@
 #define UETH__VERSION	"29-May-2008"
 
 /* Experiments show that both Linux and Windows hosts allow up to 16k
- * frame sizes. Set the max size to 15k+52 to prevent allocating 32k
+ * frame sizes. Set the max MTU size to 15k+52 to prevent allocating 32k
  * blocks and still have efficient handling. */
-#define GETHER_MAX_ETH_FRAME_LEN 15412
+#define GETHER_MAX_MTU_SIZE 15412
+#define GETHER_MAX_ETH_FRAME_LEN (GETHER_MAX_MTU_SIZE + ETH_HLEN)
 
 struct eth_dev {
 	/* lock is held while accessing port_usb
@@ -786,7 +787,7 @@ struct eth_dev *gether_setup_name(struct usb_gadget *g,
 
 	/* MTU range: 14 - 15412 */
 	net->min_mtu = ETH_HLEN;
-	net->max_mtu = GETHER_MAX_ETH_FRAME_LEN;
+	net->max_mtu = GETHER_MAX_MTU_SIZE;
 
 	dev->gadget = g;
 	SET_NETDEV_DEV(net, &g->dev);
@@ -848,7 +849,7 @@ struct net_device *gether_setup_name_default(const char *netname)
 
 	/* MTU range: 14 - 15412 */
 	net->min_mtu = ETH_HLEN;
-	net->max_mtu = GETHER_MAX_ETH_FRAME_LEN;
+	net->max_mtu = GETHER_MAX_MTU_SIZE;
 
 	return net;
 }
diff --git a/drivers/usb/gadget/legacy/acm_ms.c b/drivers/usb/gadget/legacy/acm_ms.c
index 59be2d8417c9..e8033e5f0c18 100644
--- a/drivers/usb/gadget/legacy/acm_ms.c
+++ b/drivers/usb/gadget/legacy/acm_ms.c
@@ -200,8 +200,10 @@ static int acm_ms_bind(struct usb_composite_dev *cdev)
 		struct usb_descriptor_header *usb_desc;
 
 		usb_desc = usb_otg_descriptor_alloc(gadget);
-		if (!usb_desc)
+		if (!usb_desc) {
+			status = -ENOMEM;
 			goto fail_string_ids;
+		}
 		usb_otg_descriptor_init(gadget, usb_desc);
 		otg_desc[0] = usb_desc;
 		otg_desc[1] = NULL;
diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig
index 1a12aab208b4..8c614bb86c66 100644
--- a/drivers/usb/gadget/udc/Kconfig
+++ b/drivers/usb/gadget/udc/Kconfig
@@ -90,7 +90,7 @@ config USB_BCM63XX_UDC
 
 config USB_FSL_USB2
 	tristate "Freescale Highspeed USB DR Peripheral Controller"
-	depends on FSL_SOC || ARCH_MXC
+	depends on FSL_SOC
 	help
 	   Some of Freescale PowerPC and i.MX processors have a High Speed
 	   Dual-Role(DR) USB controller, which supports device mode.
diff --git a/drivers/usb/gadget/udc/Makefile b/drivers/usb/gadget/udc/Makefile
index f5a7ce28aecd..a21f2224e7eb 100644
--- a/drivers/usb/gadget/udc/Makefile
+++ b/drivers/usb/gadget/udc/Makefile
@@ -23,7 +23,6 @@ obj-$(CONFIG_USB_ATMEL_USBA)	+= atmel_usba_udc.o
 obj-$(CONFIG_USB_BCM63XX_UDC)	+= bcm63xx_udc.o
 obj-$(CONFIG_USB_FSL_USB2)	+= fsl_usb2_udc.o
 fsl_usb2_udc-y			:= fsl_udc_core.o
-fsl_usb2_udc-$(CONFIG_ARCH_MXC)	+= fsl_mxc_udc.o
 obj-$(CONFIG_USB_TEGRA_XUDC)	+= tegra-xudc.o
 obj-$(CONFIG_USB_M66592)	+= m66592-udc.o
 obj-$(CONFIG_USB_R8A66597)	+= r8a66597-udc.o
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 5b5cfeb6c14a..6a62bbd01324 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -659,8 +659,7 @@ EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect);
  *
  * Enables the D+ (or potentially D-) pullup.  The host will start
  * enumerating this gadget when the pullup is active and a VBUS session
- * is active (the link is powered).  This pullup is always enabled unless
- * usb_gadget_disconnect() has been used to disable it.
+ * is active (the link is powered).
  *
  * Returns zero on success, else negative errno.
  */
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index ab5e978b5052..1a953f44183a 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -2118,9 +2118,21 @@ static int dummy_hub_control(
 				dum_hcd->port_status &= ~USB_PORT_STAT_POWER;
 			set_link_state(dum_hcd);
 			break;
-		default:
+		case USB_PORT_FEAT_ENABLE:
+		case USB_PORT_FEAT_C_ENABLE:
+		case USB_PORT_FEAT_C_SUSPEND:
+			/* Not allowed for USB-3 */
+			if (hcd->speed == HCD_USB3)
+				goto error;
+			fallthrough;
+		case USB_PORT_FEAT_C_CONNECTION:
+		case USB_PORT_FEAT_C_RESET:
 			dum_hcd->port_status &= ~(1 << wValue);
 			set_link_state(dum_hcd);
+			break;
+		default:
+		/* Disallow INDICATOR and C_OVER_CURRENT */
+			goto error;
 		}
 		break;
 	case GetHubDescriptor:
@@ -2281,18 +2293,17 @@ static int dummy_hub_control(
 			 */
 			dum_hcd->re_timeout = jiffies + msecs_to_jiffies(50);
 			fallthrough;
+		case USB_PORT_FEAT_C_CONNECTION:
+		case USB_PORT_FEAT_C_RESET:
+		case USB_PORT_FEAT_C_ENABLE:
+		case USB_PORT_FEAT_C_SUSPEND:
+			/* Not allowed for USB-3, and ignored for USB-2 */
+			if (hcd->speed == HCD_USB3)
+				goto error;
+			break;
 		default:
-			if (hcd->speed == HCD_USB3) {
-				if ((dum_hcd->port_status &
-				     USB_SS_PORT_STAT_POWER) != 0) {
-					dum_hcd->port_status |= (1 << wValue);
-				}
-			} else
-				if ((dum_hcd->port_status &
-				     USB_PORT_STAT_POWER) != 0) {
-					dum_hcd->port_status |= (1 << wValue);
-				}
-			set_link_state(dum_hcd);
+		/* Disallow TEST, INDICATOR, and C_OVER_CURRENT */
+			goto error;
 		}
 		break;
 	case GetPortErrorCount:
diff --git a/drivers/usb/gadget/udc/fsl_mxc_udc.c b/drivers/usb/gadget/udc/fsl_mxc_udc.c
deleted file mode 100644
index 5a321992decc..000000000000
--- a/drivers/usb/gadget/udc/fsl_mxc_udc.c
+++ /dev/null
@@ -1,122 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * Copyright (C) 2009
- * Guennadi Liakhovetski, DENX Software Engineering, <lg@denx.de>
- *
- * Description:
- * Helper routines for i.MX3x SoCs from Freescale, needed by the fsl_usb2_udc.c
- * driver to function correctly on these systems.
- */
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/err.h>
-#include <linux/fsl_devices.h>
-#include <linux/mod_devicetable.h>
-#include <linux/platform_device.h>
-#include <linux/io.h>
-
-#include "fsl_usb2_udc.h"
-
-static struct clk *mxc_ahb_clk;
-static struct clk *mxc_per_clk;
-static struct clk *mxc_ipg_clk;
-
-/* workaround ENGcm09152 for i.MX35 */
-#define MX35_USBPHYCTRL_OFFSET		0x600
-#define USBPHYCTRL_OTGBASE_OFFSET	0x8
-#define USBPHYCTRL_EVDO			(1 << 23)
-
-int fsl_udc_clk_init(struct platform_device *pdev)
-{
-	struct fsl_usb2_platform_data *pdata;
-	unsigned long freq;
-	int ret;
-
-	pdata = dev_get_platdata(&pdev->dev);
-
-	mxc_ipg_clk = devm_clk_get(&pdev->dev, "ipg");
-	if (IS_ERR(mxc_ipg_clk)) {
-		dev_err(&pdev->dev, "clk_get(\"ipg\") failed\n");
-		return PTR_ERR(mxc_ipg_clk);
-	}
-
-	mxc_ahb_clk = devm_clk_get(&pdev->dev, "ahb");
-	if (IS_ERR(mxc_ahb_clk)) {
-		dev_err(&pdev->dev, "clk_get(\"ahb\") failed\n");
-		return PTR_ERR(mxc_ahb_clk);
-	}
-
-	mxc_per_clk = devm_clk_get(&pdev->dev, "per");
-	if (IS_ERR(mxc_per_clk)) {
-		dev_err(&pdev->dev, "clk_get(\"per\") failed\n");
-		return PTR_ERR(mxc_per_clk);
-	}
-
-	clk_prepare_enable(mxc_ipg_clk);
-	clk_prepare_enable(mxc_ahb_clk);
-	clk_prepare_enable(mxc_per_clk);
-
-	/* make sure USB_CLK is running at 60 MHz +/- 1000 Hz */
-	if (!strcmp(pdev->id_entry->name, "imx-udc-mx27")) {
-		freq = clk_get_rate(mxc_per_clk);
-		if (pdata->phy_mode != FSL_USB2_PHY_ULPI &&
-		    (freq < 59999000 || freq > 60001000)) {
-			dev_err(&pdev->dev, "USB_CLK=%lu, should be 60MHz\n", freq);
-			ret = -EINVAL;
-			goto eclkrate;
-		}
-	}
-
-	return 0;
-
-eclkrate:
-	clk_disable_unprepare(mxc_ipg_clk);
-	clk_disable_unprepare(mxc_ahb_clk);
-	clk_disable_unprepare(mxc_per_clk);
-	mxc_per_clk = NULL;
-	return ret;
-}
-
-int fsl_udc_clk_finalize(struct platform_device *pdev)
-{
-	struct fsl_usb2_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	int ret = 0;
-
-	/* workaround ENGcm09152 for i.MX35 */
-	if (pdata->workaround & FLS_USB2_WORKAROUND_ENGCM09152) {
-		unsigned int v;
-		struct resource *res = platform_get_resource
-			(pdev, IORESOURCE_MEM, 0);
-		void __iomem *phy_regs = ioremap(res->start +
-						MX35_USBPHYCTRL_OFFSET, 512);
-		if (!phy_regs) {
-			dev_err(&pdev->dev, "ioremap for phy address fails\n");
-			ret = -EINVAL;
-			goto ioremap_err;
-		}
-
-		v = readl(phy_regs + USBPHYCTRL_OTGBASE_OFFSET);
-		writel(v | USBPHYCTRL_EVDO,
-			phy_regs + USBPHYCTRL_OTGBASE_OFFSET);
-
-		iounmap(phy_regs);
-	}
-
-
-ioremap_err:
-	/* ULPI transceivers don't need usbpll */
-	if (pdata->phy_mode == FSL_USB2_PHY_ULPI) {
-		clk_disable_unprepare(mxc_per_clk);
-		mxc_per_clk = NULL;
-	}
-
-	return ret;
-}
-
-void fsl_udc_clk_release(void)
-{
-	if (mxc_per_clk)
-		clk_disable_unprepare(mxc_per_clk);
-	clk_disable_unprepare(mxc_ahb_clk);
-	clk_disable_unprepare(mxc_ipg_clk);
-}
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 91ab81c3fc79..e86940571b4c 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4770,19 +4770,19 @@ static u16 xhci_calculate_u1_timeout(struct xhci_hcd *xhci,
 {
 	unsigned long long timeout_ns;
 
+	if (xhci->quirks & XHCI_INTEL_HOST)
+		timeout_ns = xhci_calculate_intel_u1_timeout(udev, desc);
+	else
+		timeout_ns = udev->u1_params.sel;
+
 	/* Prevent U1 if service interval is shorter than U1 exit latency */
 	if (usb_endpoint_xfer_int(desc) || usb_endpoint_xfer_isoc(desc)) {
-		if (xhci_service_interval_to_ns(desc) <= udev->u1_params.mel) {
+		if (xhci_service_interval_to_ns(desc) <= timeout_ns) {
 			dev_dbg(&udev->dev, "Disable U1, ESIT shorter than exit latency\n");
 			return USB3_LPM_DISABLED;
 		}
 	}
 
-	if (xhci->quirks & XHCI_INTEL_HOST)
-		timeout_ns = xhci_calculate_intel_u1_timeout(udev, desc);
-	else
-		timeout_ns = udev->u1_params.sel;
-
 	/* The U1 timeout is encoded in 1us intervals.
 	 * Don't return a timeout of zero, because that's USB3_LPM_DISABLED.
 	 */
@@ -4834,19 +4834,19 @@ static u16 xhci_calculate_u2_timeout(struct xhci_hcd *xhci,
 {
 	unsigned long long timeout_ns;
 
+	if (xhci->quirks & XHCI_INTEL_HOST)
+		timeout_ns = xhci_calculate_intel_u2_timeout(udev, desc);
+	else
+		timeout_ns = udev->u2_params.sel;
+
 	/* Prevent U2 if service interval is shorter than U2 exit latency */
 	if (usb_endpoint_xfer_int(desc) || usb_endpoint_xfer_isoc(desc)) {
-		if (xhci_service_interval_to_ns(desc) <= udev->u2_params.mel) {
+		if (xhci_service_interval_to_ns(desc) <= timeout_ns) {
 			dev_dbg(&udev->dev, "Disable U2, ESIT shorter than exit latency\n");
 			return USB3_LPM_DISABLED;
 		}
 	}
 
-	if (xhci->quirks & XHCI_INTEL_HOST)
-		timeout_ns = xhci_calculate_intel_u2_timeout(udev, desc);
-	else
-		timeout_ns = udev->u2_params.sel;
-
 	/* The U2 timeout is encoded in 256us intervals */
 	timeout_ns = DIV_ROUND_UP_ULL(timeout_ns, 256 * 1000);
 	/* If the necessary timeout value is bigger than what we can set in the
diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 73ebfa6e9715..c640f98d20c5 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -496,6 +496,9 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer,
 		timeout = schedule_timeout(YUREX_WRITE_TIMEOUT);
 	finish_wait(&dev->waitq, &wait);
 
+	/* make sure URB is idle after timeout or (spurious) CMD_ACK */
+	usb_kill_urb(dev->cntl_urb);
+
 	mutex_unlock(&dev->io_mutex);
 
 	if (retval < 0) {
diff --git a/drivers/usb/serial/iuu_phoenix.c b/drivers/usb/serial/iuu_phoenix.c
index f1201d4de297..e8f06b41a503 100644
--- a/drivers/usb/serial/iuu_phoenix.c
+++ b/drivers/usb/serial/iuu_phoenix.c
@@ -532,23 +532,29 @@ static int iuu_uart_flush(struct usb_serial_port *port)
 	struct device *dev = &port->dev;
 	int i;
 	int status;
-	u8 rxcmd = IUU_UART_RX;
+	u8 *rxcmd;
 	struct iuu_private *priv = usb_get_serial_port_data(port);
 
 	if (iuu_led(port, 0xF000, 0, 0, 0xFF) < 0)
 		return -EIO;
 
+	rxcmd = kmalloc(1, GFP_KERNEL);
+	if (!rxcmd)
+		return -ENOMEM;
+
+	rxcmd[0] = IUU_UART_RX;
+
 	for (i = 0; i < 2; i++) {
-		status = bulk_immediate(port, &rxcmd, 1);
+		status = bulk_immediate(port, rxcmd, 1);
 		if (status != IUU_OPERATION_OK) {
 			dev_dbg(dev, "%s - uart_flush_write error\n", __func__);
-			return status;
+			goto out_free;
 		}
 
 		status = read_immediate(port, &priv->len, 1);
 		if (status != IUU_OPERATION_OK) {
 			dev_dbg(dev, "%s - uart_flush_read error\n", __func__);
-			return status;
+			goto out_free;
 		}
 
 		if (priv->len > 0) {
@@ -556,12 +562,16 @@ static int iuu_uart_flush(struct usb_serial_port *port)
 			status = read_immediate(port, priv->buf, priv->len);
 			if (status != IUU_OPERATION_OK) {
 				dev_dbg(dev, "%s - uart_flush_read error\n", __func__);
-				return status;
+				goto out_free;
 			}
 		}
 	}
 	dev_dbg(dev, "%s - uart_flush_read OK!\n", __func__);
 	iuu_led(port, 0, 0xF000, 0, 0xFF);
+
+out_free:
+	kfree(rxcmd);
+
 	return status;
 }
 
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 2c21e34235bb..3fe959104311 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1117,6 +1117,8 @@ static const struct usb_device_id option_ids[] = {
 	{ 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) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, 0x0620, 0xff, 0xff, 0x30) },	/* EM160R-GL */
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, 0x0620, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x30) },
 	{ 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),
@@ -2057,6 +2059,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff),			/* Fibocom NL678 series */
 	  .driver_info = RSVD(6) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) },			/* Fibocom NL668-AM/NL652-EU (laptop MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) },			/* LongSung M5710 */
 	{ 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 */
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 870e9cf3d5dc..f9677a5ec31b 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -91,6 +91,13 @@ UNUSUAL_DEV(0x152d, 0x0578, 0x0000, 0x9999,
 		US_FL_BROKEN_FUA),
 
 /* Reported-by: Thinh Nguyen <thinhn@synopsys.com> */
+UNUSUAL_DEV(0x154b, 0xf00b, 0x0000, 0x9999,
+		"PNY",
+		"Pro Elite SSD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
+/* Reported-by: Thinh Nguyen <thinhn@synopsys.com> */
 UNUSUAL_DEV(0x154b, 0xf00d, 0x0000, 0x9999,
 		"PNY",
 		"Pro Elite SSD",
diff --git a/drivers/usb/typec/altmodes/Kconfig b/drivers/usb/typec/altmodes/Kconfig
index 187690fd1a5b..60d375e9c3c7 100644
--- a/drivers/usb/typec/altmodes/Kconfig
+++ b/drivers/usb/typec/altmodes/Kconfig
@@ -20,6 +20,6 @@ config TYPEC_NVIDIA_ALTMODE
 	  to enable support for VirtualLink devices with NVIDIA GPUs.
 
 	  To compile this driver as a module, choose M here: the
-	  module will be called typec_displayport.
+	  module will be called typec_nvidia.
 
 endmenu
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index ebfd3113a9a8..8f77669f9cf4 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -766,6 +766,7 @@ int typec_partner_set_num_altmodes(struct typec_partner *partner, int num_altmod
 		return ret;
 
 	sysfs_notify(&partner->dev.kobj, NULL, "number_of_alternate_modes");
+	kobject_uevent(&partner->dev.kobj, KOBJ_CHANGE);
 
 	return 0;
 }
@@ -923,6 +924,7 @@ int typec_plug_set_num_altmodes(struct typec_plug *plug, int num_altmodes)
 		return ret;
 
 	sysfs_notify(&plug->dev.kobj, NULL, "number_of_alternate_modes");
+	kobject_uevent(&plug->dev.kobj, KOBJ_CHANGE);
 
 	return 0;
 }
diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c
index cf37a59ce130..46a25b8db72e 100644
--- a/drivers/usb/typec/mux/intel_pmc_mux.c
+++ b/drivers/usb/typec/mux/intel_pmc_mux.c
@@ -207,10 +207,21 @@ static int
 pmc_usb_mux_dp_hpd(struct pmc_usb_port *port, struct typec_displayport_data *dp)
 {
 	u8 msg[2] = { };
+	int ret;
 
 	msg[0] = PMC_USB_DP_HPD;
 	msg[0] |= port->usb3_port << PMC_USB_MSG_USB3_PORT_SHIFT;
 
+	/* Configure HPD first if HPD,IRQ comes together */
+	if (!IOM_PORT_HPD_ASSERTED(port->iom_status) &&
+	    dp->status & DP_STATUS_IRQ_HPD &&
+	    dp->status & DP_STATUS_HPD_STATE) {
+		msg[1] = PMC_USB_DP_HPD_LVL;
+		ret = pmc_usb_command(port, msg, sizeof(msg));
+		if (ret)
+			return ret;
+	}
+
 	if (dp->status & DP_STATUS_IRQ_HPD)
 		msg[1] = PMC_USB_DP_HPD_IRQ;
 
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index 66cde5e5f796..3209b5ddd30c 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -396,6 +396,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
 		default:
 			usbip_dbg_vhci_rh(" ClearPortFeature: default %x\n",
 					  wValue);
+			if (wValue >= 32)
+				goto error;
 			vhci_hcd->port_status[rhport] &= ~(1 << wValue);
 			break;
 		}
diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index 6caf539091e5..92a6396f8a73 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -9,21 +9,24 @@ menuconfig VDPA
 if VDPA
 
 config VDPA_SIM
-	tristate "vDPA device simulator"
+	tristate "vDPA device simulator core"
 	depends on RUNTIME_TESTING_MENU && HAS_DMA
 	select DMA_OPS
 	select VHOST_RING
+	help
+	  Enable this module to support vDPA device simulators. These devices
+	  are used for testing, prototyping and development of vDPA.
+
+config VDPA_SIM_NET
+	tristate "vDPA simulator for networking device"
+	depends on VDPA_SIM
 	select GENERIC_NET_UTILS
-	default n
 	help
-	  vDPA networking device simulator which loop TX traffic back
-	  to RX. This device is used for testing, prototyping and
-	  development of vDPA.
+	  vDPA networking device simulator which loops TX traffic back to RX.
 
 config IFCVF
 	tristate "Intel IFC VF vDPA driver"
 	depends on PCI_MSI
-	default n
 	help
 	  This kernel module can drive Intel IFC VF NIC to offload
 	  virtio dataplane traffic to hardware.
@@ -42,7 +45,6 @@ config MLX5_VDPA_NET
 	tristate "vDPA driver for ConnectX devices"
 	select MLX5_VDPA
 	depends on MLX5_CORE
-	default n
 	help
 	  VDPA network driver for ConnectX6 and newer. Provides offloading
 	  of virtio net datapath such that descriptors put on the ring will
diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index 8b4028556cb6..fa1af301cf55 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -417,16 +417,9 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return ret;
 	}
 
-	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (ret) {
-		IFCVF_ERR(pdev, "No usable DMA confiugration\n");
-		return ret;
-	}
-
-	ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (ret) {
-		IFCVF_ERR(pdev,
-			  "No usable coherent DMA confiugration\n");
+		IFCVF_ERR(pdev, "No usable DMA configuration\n");
 		return ret;
 	}
 
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index f1d54814db97..88dde3455bfd 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -479,6 +479,11 @@ static int mlx5_vdpa_poll_one(struct mlx5_vdpa_cq *vcq)
 static void mlx5_vdpa_handle_completions(struct mlx5_vdpa_virtqueue *mvq, int num)
 {
 	mlx5_cq_set_ci(&mvq->cq.mcq);
+
+	/* make sure CQ cosumer update is visible to the hardware before updating
+	 * RX doorbell record.
+	 */
+	dma_wmb();
 	rx_post(&mvq->vqqp, num);
 	if (mvq->event_cb.callback)
 		mvq->event_cb.callback(mvq->event_cb.private);
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index a69ffc991e13..c0825650c055 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -89,7 +89,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 	if (!vdev)
 		goto err;
 
-	err = ida_simple_get(&vdpa_index_ida, 0, 0, GFP_KERNEL);
+	err = ida_alloc(&vdpa_index_ida, GFP_KERNEL);
 	if (err < 0)
 		goto err_ida;
 
diff --git a/drivers/vdpa/vdpa_sim/Makefile b/drivers/vdpa/vdpa_sim/Makefile
index b40278f65e04..79d4536d347e 100644
--- a/drivers/vdpa/vdpa_sim/Makefile
+++ b/drivers/vdpa/vdpa_sim/Makefile
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_VDPA_SIM) += vdpa_sim.o
+obj-$(CONFIG_VDPA_SIM_NET) += vdpa_sim_net.o
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 6a90fdb9cbfc..b3fcc67bfdf0 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * VDPA networking device simulator.
+ * VDPA device simulator core.
  *
  * Copyright (c) 2020, Red Hat Inc. All rights reserved.
  *     Author: Jason Wang <jasowang@redhat.com>
@@ -11,97 +11,32 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
-#include <linux/fs.h>
-#include <linux/poll.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
-#include <linux/wait.h>
-#include <linux/uuid.h>
-#include <linux/iommu.h>
 #include <linux/dma-map-ops.h>
-#include <linux/sysfs.h>
-#include <linux/file.h>
-#include <linux/etherdevice.h>
 #include <linux/vringh.h>
 #include <linux/vdpa.h>
-#include <linux/virtio_byteorder.h>
 #include <linux/vhost_iotlb.h>
-#include <uapi/linux/virtio_config.h>
-#include <uapi/linux/virtio_net.h>
+
+#include "vdpa_sim.h"
 
 #define DRV_VERSION  "0.1"
 #define DRV_AUTHOR   "Jason Wang <jasowang@redhat.com>"
-#define DRV_DESC     "vDPA Device Simulator"
+#define DRV_DESC     "vDPA Device Simulator core"
 #define DRV_LICENSE  "GPL v2"
 
 static int batch_mapping = 1;
 module_param(batch_mapping, int, 0444);
 MODULE_PARM_DESC(batch_mapping, "Batched mapping 1 -Enable; 0 - Disable");
 
-static char *macaddr;
-module_param(macaddr, charp, 0);
-MODULE_PARM_DESC(macaddr, "Ethernet MAC address");
-
-struct vdpasim_virtqueue {
-	struct vringh vring;
-	struct vringh_kiov iov;
-	unsigned short head;
-	bool ready;
-	u64 desc_addr;
-	u64 device_addr;
-	u64 driver_addr;
-	u32 num;
-	void *private;
-	irqreturn_t (*cb)(void *data);
-};
+static int max_iotlb_entries = 2048;
+module_param(max_iotlb_entries, int, 0444);
+MODULE_PARM_DESC(max_iotlb_entries,
+		 "Maximum number of iotlb entries. 0 means unlimited. (default: 2048)");
 
 #define VDPASIM_QUEUE_ALIGN PAGE_SIZE
 #define VDPASIM_QUEUE_MAX 256
-#define VDPASIM_DEVICE_ID 0x1
 #define VDPASIM_VENDOR_ID 0
-#define VDPASIM_VQ_NUM 0x2
-#define VDPASIM_NAME "vdpasim-netdev"
-
-static u64 vdpasim_features = (1ULL << VIRTIO_F_ANY_LAYOUT) |
-			      (1ULL << VIRTIO_F_VERSION_1)  |
-			      (1ULL << VIRTIO_F_ACCESS_PLATFORM) |
-			      (1ULL << VIRTIO_NET_F_MAC);
-
-/* State of each vdpasim device */
-struct vdpasim {
-	struct vdpa_device vdpa;
-	struct vdpasim_virtqueue vqs[VDPASIM_VQ_NUM];
-	struct work_struct work;
-	/* spinlock to synchronize virtqueue state */
-	spinlock_t lock;
-	struct virtio_net_config config;
-	struct vhost_iotlb *iommu;
-	void *buffer;
-	u32 status;
-	u32 generation;
-	u64 features;
-	/* spinlock to synchronize iommu table */
-	spinlock_t iommu_lock;
-};
-
-/* TODO: cross-endian support */
-static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim)
-{
-	return virtio_legacy_is_little_endian() ||
-		(vdpasim->features & (1ULL << VIRTIO_F_VERSION_1));
-}
-
-static inline u16 vdpasim16_to_cpu(struct vdpasim *vdpasim, __virtio16 val)
-{
-	return __virtio16_to_cpu(vdpasim_is_little_endian(vdpasim), val);
-}
-
-static inline __virtio16 cpu_to_vdpasim16(struct vdpasim *vdpasim, u16 val)
-{
-	return __cpu_to_virtio16(vdpasim_is_little_endian(vdpasim), val);
-}
-
-static struct vdpasim *vdpasim_dev;
 
 static struct vdpasim *vdpa_to_sim(struct vdpa_device *vdpa)
 {
@@ -115,20 +50,34 @@ static struct vdpasim *dev_to_sim(struct device *dev)
 	return vdpa_to_sim(vdpa);
 }
 
+static void vdpasim_vq_notify(struct vringh *vring)
+{
+	struct vdpasim_virtqueue *vq =
+		container_of(vring, struct vdpasim_virtqueue, vring);
+
+	if (!vq->cb)
+		return;
+
+	vq->cb(vq->private);
+}
+
 static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx)
 {
 	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
 
-	vringh_init_iotlb(&vq->vring, vdpasim_features,
+	vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features,
 			  VDPASIM_QUEUE_MAX, false,
 			  (struct vring_desc *)(uintptr_t)vq->desc_addr,
 			  (struct vring_avail *)
 			  (uintptr_t)vq->driver_addr,
 			  (struct vring_used *)
 			  (uintptr_t)vq->device_addr);
+
+	vq->vring.notify = vdpasim_vq_notify;
 }
 
-static void vdpasim_vq_reset(struct vdpasim_virtqueue *vq)
+static void vdpasim_vq_reset(struct vdpasim *vdpasim,
+			     struct vdpasim_virtqueue *vq)
 {
 	vq->ready = false;
 	vq->desc_addr = 0;
@@ -136,16 +85,18 @@ static void vdpasim_vq_reset(struct vdpasim_virtqueue *vq)
 	vq->device_addr = 0;
 	vq->cb = NULL;
 	vq->private = NULL;
-	vringh_init_iotlb(&vq->vring, vdpasim_features, VDPASIM_QUEUE_MAX,
-			  false, NULL, NULL, NULL);
+	vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features,
+			  VDPASIM_QUEUE_MAX, false, NULL, NULL, NULL);
+
+	vq->vring.notify = NULL;
 }
 
 static void vdpasim_reset(struct vdpasim *vdpasim)
 {
 	int i;
 
-	for (i = 0; i < VDPASIM_VQ_NUM; i++)
-		vdpasim_vq_reset(&vdpasim->vqs[i]);
+	for (i = 0; i < vdpasim->dev_attr.nvqs; i++)
+		vdpasim_vq_reset(vdpasim, &vdpasim->vqs[i]);
 
 	spin_lock(&vdpasim->iommu_lock);
 	vhost_iotlb_reset(vdpasim->iommu);
@@ -156,80 +107,6 @@ static void vdpasim_reset(struct vdpasim *vdpasim)
 	++vdpasim->generation;
 }
 
-static void vdpasim_work(struct work_struct *work)
-{
-	struct vdpasim *vdpasim = container_of(work, struct
-						 vdpasim, work);
-	struct vdpasim_virtqueue *txq = &vdpasim->vqs[1];
-	struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0];
-	ssize_t read, write;
-	size_t total_write;
-	int pkts = 0;
-	int err;
-
-	spin_lock(&vdpasim->lock);
-
-	if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK))
-		goto out;
-
-	if (!txq->ready || !rxq->ready)
-		goto out;
-
-	while (true) {
-		total_write = 0;
-		err = vringh_getdesc_iotlb(&txq->vring, &txq->iov, NULL,
-					   &txq->head, GFP_ATOMIC);
-		if (err <= 0)
-			break;
-
-		err = vringh_getdesc_iotlb(&rxq->vring, NULL, &rxq->iov,
-					   &rxq->head, GFP_ATOMIC);
-		if (err <= 0) {
-			vringh_complete_iotlb(&txq->vring, txq->head, 0);
-			break;
-		}
-
-		while (true) {
-			read = vringh_iov_pull_iotlb(&txq->vring, &txq->iov,
-						     vdpasim->buffer,
-						     PAGE_SIZE);
-			if (read <= 0)
-				break;
-
-			write = vringh_iov_push_iotlb(&rxq->vring, &rxq->iov,
-						      vdpasim->buffer, read);
-			if (write <= 0)
-				break;
-
-			total_write += write;
-		}
-
-		/* Make sure data is wrote before advancing index */
-		smp_wmb();
-
-		vringh_complete_iotlb(&txq->vring, txq->head, 0);
-		vringh_complete_iotlb(&rxq->vring, rxq->head, total_write);
-
-		/* Make sure used is visible before rasing the interrupt. */
-		smp_wmb();
-
-		local_bh_disable();
-		if (txq->cb)
-			txq->cb(txq->private);
-		if (rxq->cb)
-			rxq->cb(rxq->private);
-		local_bh_enable();
-
-		if (++pkts > 4) {
-			schedule_work(&vdpasim->work);
-			goto out;
-		}
-	}
-
-out:
-	spin_unlock(&vdpasim->lock);
-}
-
 static int dir_to_perm(enum dma_data_direction dir)
 {
 	int perm = -EFAULT;
@@ -342,26 +219,28 @@ static const struct dma_map_ops vdpasim_dma_ops = {
 	.free = vdpasim_free_coherent,
 };
 
-static const struct vdpa_config_ops vdpasim_net_config_ops;
-static const struct vdpa_config_ops vdpasim_net_batch_config_ops;
+static const struct vdpa_config_ops vdpasim_config_ops;
+static const struct vdpa_config_ops vdpasim_batch_config_ops;
 
-static struct vdpasim *vdpasim_create(void)
+struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)
 {
 	const struct vdpa_config_ops *ops;
 	struct vdpasim *vdpasim;
 	struct device *dev;
-	int ret = -ENOMEM;
+	int i, ret = -ENOMEM;
 
 	if (batch_mapping)
-		ops = &vdpasim_net_batch_config_ops;
+		ops = &vdpasim_batch_config_ops;
 	else
-		ops = &vdpasim_net_config_ops;
+		ops = &vdpasim_config_ops;
 
-	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, VDPASIM_VQ_NUM);
+	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops,
+				    dev_attr->nvqs);
 	if (!vdpasim)
 		goto err_alloc;
 
-	INIT_WORK(&vdpasim->work, vdpasim_work);
+	vdpasim->dev_attr = *dev_attr;
+	INIT_WORK(&vdpasim->work, dev_attr->work_fn);
 	spin_lock_init(&vdpasim->lock);
 	spin_lock_init(&vdpasim->iommu_lock);
 
@@ -371,31 +250,27 @@ static struct vdpasim *vdpasim_create(void)
 		goto err_iommu;
 	set_dma_ops(dev, &vdpasim_dma_ops);
 
-	vdpasim->iommu = vhost_iotlb_alloc(2048, 0);
+	vdpasim->config = kzalloc(dev_attr->config_size, GFP_KERNEL);
+	if (!vdpasim->config)
+		goto err_iommu;
+
+	vdpasim->vqs = kcalloc(dev_attr->nvqs, sizeof(struct vdpasim_virtqueue),
+			       GFP_KERNEL);
+	if (!vdpasim->vqs)
+		goto err_iommu;
+
+	vdpasim->iommu = vhost_iotlb_alloc(max_iotlb_entries, 0);
 	if (!vdpasim->iommu)
 		goto err_iommu;
 
-	vdpasim->buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	vdpasim->buffer = kvmalloc(dev_attr->buffer_size, GFP_KERNEL);
 	if (!vdpasim->buffer)
 		goto err_iommu;
 
-	if (macaddr) {
-		mac_pton(macaddr, vdpasim->config.mac);
-		if (!is_valid_ether_addr(vdpasim->config.mac)) {
-			ret = -EADDRNOTAVAIL;
-			goto err_iommu;
-		}
-	} else {
-		eth_random_addr(vdpasim->config.mac);
-	}
-
-	vringh_set_iotlb(&vdpasim->vqs[0].vring, vdpasim->iommu);
-	vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu);
+	for (i = 0; i < dev_attr->nvqs; i++)
+		vringh_set_iotlb(&vdpasim->vqs[i].vring, vdpasim->iommu);
 
 	vdpasim->vdpa.dma_dev = dev;
-	ret = vdpa_register_device(&vdpasim->vdpa);
-	if (ret)
-		goto err_iommu;
 
 	return vdpasim;
 
@@ -404,6 +279,7 @@ err_iommu:
 err_alloc:
 	return ERR_PTR(ret);
 }
+EXPORT_SYMBOL_GPL(vdpasim_create);
 
 static int vdpasim_set_vq_address(struct vdpa_device *vdpa, u16 idx,
 				  u64 desc_area, u64 driver_area,
@@ -498,28 +374,21 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)
 
 static u64 vdpasim_get_features(struct vdpa_device *vdpa)
 {
-	return vdpasim_features;
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	return vdpasim->dev_attr.supported_features;
 }
 
 static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
-	struct virtio_net_config *config = &vdpasim->config;
 
 	/* DMA mapping must be done by driver */
 	if (!(features & (1ULL << VIRTIO_F_ACCESS_PLATFORM)))
 		return -EINVAL;
 
-	vdpasim->features = features & vdpasim_features;
-
-	/* We generally only know whether guest is using the legacy interface
-	 * here, so generally that's the earliest we can set config fields.
-	 * Note: We actually require VIRTIO_F_ACCESS_PLATFORM above which
-	 * implies VIRTIO_F_VERSION_1, but let's not try to be clever here.
-	 */
+	vdpasim->features = features & vdpasim->dev_attr.supported_features;
 
-	config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
-	config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP);
 	return 0;
 }
 
@@ -536,7 +405,9 @@ static u16 vdpasim_get_vq_num_max(struct vdpa_device *vdpa)
 
 static u32 vdpasim_get_device_id(struct vdpa_device *vdpa)
 {
-	return VDPASIM_DEVICE_ID;
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	return vdpasim->dev_attr.id;
 }
 
 static u32 vdpasim_get_vendor_id(struct vdpa_device *vdpa)
@@ -572,14 +443,27 @@ static void vdpasim_get_config(struct vdpa_device *vdpa, unsigned int offset,
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 
-	if (offset + len < sizeof(struct virtio_net_config))
-		memcpy(buf, (u8 *)&vdpasim->config + offset, len);
+	if (offset + len > vdpasim->dev_attr.config_size)
+		return;
+
+	if (vdpasim->dev_attr.get_config)
+		vdpasim->dev_attr.get_config(vdpasim, vdpasim->config);
+
+	memcpy(buf, vdpasim->config + offset, len);
 }
 
 static void vdpasim_set_config(struct vdpa_device *vdpa, unsigned int offset,
 			     const void *buf, unsigned int len)
 {
-	/* No writable config supportted by vdpasim */
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	if (offset + len > vdpasim->dev_attr.config_size)
+		return;
+
+	memcpy(vdpasim->config + offset, buf, len);
+
+	if (vdpasim->dev_attr.set_config)
+		vdpasim->dev_attr.set_config(vdpasim, vdpasim->config);
 }
 
 static u32 vdpasim_get_generation(struct vdpa_device *vdpa)
@@ -656,12 +540,14 @@ static void vdpasim_free(struct vdpa_device *vdpa)
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 
 	cancel_work_sync(&vdpasim->work);
-	kfree(vdpasim->buffer);
+	kvfree(vdpasim->buffer);
 	if (vdpasim->iommu)
 		vhost_iotlb_free(vdpasim->iommu);
+	kfree(vdpasim->vqs);
+	kfree(vdpasim->config);
 }
 
-static const struct vdpa_config_ops vdpasim_net_config_ops = {
+static const struct vdpa_config_ops vdpasim_config_ops = {
 	.set_vq_address         = vdpasim_set_vq_address,
 	.set_vq_num             = vdpasim_set_vq_num,
 	.kick_vq                = vdpasim_kick_vq,
@@ -688,7 +574,7 @@ static const struct vdpa_config_ops vdpasim_net_config_ops = {
 	.free                   = vdpasim_free,
 };
 
-static const struct vdpa_config_ops vdpasim_net_batch_config_ops = {
+static const struct vdpa_config_ops vdpasim_batch_config_ops = {
 	.set_vq_address         = vdpasim_set_vq_address,
 	.set_vq_num             = vdpasim_set_vq_num,
 	.kick_vq                = vdpasim_kick_vq,
@@ -714,26 +600,6 @@ static const struct vdpa_config_ops vdpasim_net_batch_config_ops = {
 	.free                   = vdpasim_free,
 };
 
-static int __init vdpasim_dev_init(void)
-{
-	vdpasim_dev = vdpasim_create();
-
-	if (!IS_ERR(vdpasim_dev))
-		return 0;
-
-	return PTR_ERR(vdpasim_dev);
-}
-
-static void __exit vdpasim_dev_exit(void)
-{
-	struct vdpa_device *vdpa = &vdpasim_dev->vdpa;
-
-	vdpa_unregister_device(vdpa);
-}
-
-module_init(vdpasim_dev_init)
-module_exit(vdpasim_dev_exit)
-
 MODULE_VERSION(DRV_VERSION);
 MODULE_LICENSE(DRV_LICENSE);
 MODULE_AUTHOR(DRV_AUTHOR);
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h
new file mode 100644
index 000000000000..b02142293d5b
--- /dev/null
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2020, Red Hat Inc. All rights reserved.
+ */
+
+#ifndef _VDPA_SIM_H
+#define _VDPA_SIM_H
+
+#include <linux/vringh.h>
+#include <linux/vdpa.h>
+#include <linux/virtio_byteorder.h>
+#include <linux/vhost_iotlb.h>
+#include <uapi/linux/virtio_config.h>
+
+#define VDPASIM_FEATURES	((1ULL << VIRTIO_F_ANY_LAYOUT) | \
+				 (1ULL << VIRTIO_F_VERSION_1)  | \
+				 (1ULL << VIRTIO_F_ACCESS_PLATFORM))
+
+struct vdpasim;
+
+struct vdpasim_virtqueue {
+	struct vringh vring;
+	struct vringh_kiov in_iov;
+	struct vringh_kiov out_iov;
+	unsigned short head;
+	bool ready;
+	u64 desc_addr;
+	u64 device_addr;
+	u64 driver_addr;
+	u32 num;
+	void *private;
+	irqreturn_t (*cb)(void *data);
+};
+
+struct vdpasim_dev_attr {
+	u64 supported_features;
+	size_t config_size;
+	size_t buffer_size;
+	int nvqs;
+	u32 id;
+
+	work_func_t work_fn;
+	void (*get_config)(struct vdpasim *vdpasim, void *config);
+	void (*set_config)(struct vdpasim *vdpasim, const void *config);
+};
+
+/* State of each vdpasim device */
+struct vdpasim {
+	struct vdpa_device vdpa;
+	struct vdpasim_virtqueue *vqs;
+	struct work_struct work;
+	struct vdpasim_dev_attr dev_attr;
+	/* spinlock to synchronize virtqueue state */
+	spinlock_t lock;
+	/* virtio config according to device type */
+	void *config;
+	struct vhost_iotlb *iommu;
+	void *buffer;
+	u32 status;
+	u32 generation;
+	u64 features;
+	/* spinlock to synchronize iommu table */
+	spinlock_t iommu_lock;
+};
+
+struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *attr);
+
+/* TODO: cross-endian support */
+static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim)
+{
+	return virtio_legacy_is_little_endian() ||
+		(vdpasim->features & (1ULL << VIRTIO_F_VERSION_1));
+}
+
+static inline u16 vdpasim16_to_cpu(struct vdpasim *vdpasim, __virtio16 val)
+{
+	return __virtio16_to_cpu(vdpasim_is_little_endian(vdpasim), val);
+}
+
+static inline __virtio16 cpu_to_vdpasim16(struct vdpasim *vdpasim, u16 val)
+{
+	return __cpu_to_virtio16(vdpasim_is_little_endian(vdpasim), val);
+}
+
+static inline u32 vdpasim32_to_cpu(struct vdpasim *vdpasim, __virtio32 val)
+{
+	return __virtio32_to_cpu(vdpasim_is_little_endian(vdpasim), val);
+}
+
+static inline __virtio32 cpu_to_vdpasim32(struct vdpasim *vdpasim, u32 val)
+{
+	return __cpu_to_virtio32(vdpasim_is_little_endian(vdpasim), val);
+}
+
+static inline u64 vdpasim64_to_cpu(struct vdpasim *vdpasim, __virtio64 val)
+{
+	return __virtio64_to_cpu(vdpasim_is_little_endian(vdpasim), val);
+}
+
+static inline __virtio64 cpu_to_vdpasim64(struct vdpasim *vdpasim, u64 val)
+{
+	return __cpu_to_virtio64(vdpasim_is_little_endian(vdpasim), val);
+}
+
+#endif
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
new file mode 100644
index 000000000000..c10b6981fdab
--- /dev/null
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VDPA simulator for networking device.
+ *
+ * Copyright (c) 2020, Red Hat Inc. All rights reserved.
+ *     Author: Jason Wang <jasowang@redhat.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/etherdevice.h>
+#include <linux/vringh.h>
+#include <linux/vdpa.h>
+#include <uapi/linux/virtio_net.h>
+
+#include "vdpa_sim.h"
+
+#define DRV_VERSION  "0.1"
+#define DRV_AUTHOR   "Jason Wang <jasowang@redhat.com>"
+#define DRV_DESC     "vDPA Device Simulator for networking device"
+#define DRV_LICENSE  "GPL v2"
+
+#define VDPASIM_NET_FEATURES	(VDPASIM_FEATURES | \
+				 (1ULL << VIRTIO_NET_F_MAC))
+
+#define VDPASIM_NET_VQ_NUM	2
+
+static char *macaddr;
+module_param(macaddr, charp, 0);
+MODULE_PARM_DESC(macaddr, "Ethernet MAC address");
+
+u8 macaddr_buf[ETH_ALEN];
+
+static struct vdpasim *vdpasim_net_dev;
+
+static void vdpasim_net_work(struct work_struct *work)
+{
+	struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);
+	struct vdpasim_virtqueue *txq = &vdpasim->vqs[1];
+	struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0];
+	ssize_t read, write;
+	size_t total_write;
+	int pkts = 0;
+	int err;
+
+	spin_lock(&vdpasim->lock);
+
+	if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK))
+		goto out;
+
+	if (!txq->ready || !rxq->ready)
+		goto out;
+
+	while (true) {
+		total_write = 0;
+		err = vringh_getdesc_iotlb(&txq->vring, &txq->out_iov, NULL,
+					   &txq->head, GFP_ATOMIC);
+		if (err <= 0)
+			break;
+
+		err = vringh_getdesc_iotlb(&rxq->vring, NULL, &rxq->in_iov,
+					   &rxq->head, GFP_ATOMIC);
+		if (err <= 0) {
+			vringh_complete_iotlb(&txq->vring, txq->head, 0);
+			break;
+		}
+
+		while (true) {
+			read = vringh_iov_pull_iotlb(&txq->vring, &txq->out_iov,
+						     vdpasim->buffer,
+						     PAGE_SIZE);
+			if (read <= 0)
+				break;
+
+			write = vringh_iov_push_iotlb(&rxq->vring, &rxq->in_iov,
+						      vdpasim->buffer, read);
+			if (write <= 0)
+				break;
+
+			total_write += write;
+		}
+
+		/* Make sure data is wrote before advancing index */
+		smp_wmb();
+
+		vringh_complete_iotlb(&txq->vring, txq->head, 0);
+		vringh_complete_iotlb(&rxq->vring, rxq->head, total_write);
+
+		/* Make sure used is visible before rasing the interrupt. */
+		smp_wmb();
+
+		local_bh_disable();
+		if (vringh_need_notify_iotlb(&txq->vring) > 0)
+			vringh_notify(&txq->vring);
+		if (vringh_need_notify_iotlb(&rxq->vring) > 0)
+			vringh_notify(&rxq->vring);
+		local_bh_enable();
+
+		if (++pkts > 4) {
+			schedule_work(&vdpasim->work);
+			goto out;
+		}
+	}
+
+out:
+	spin_unlock(&vdpasim->lock);
+}
+
+static void vdpasim_net_get_config(struct vdpasim *vdpasim, void *config)
+{
+	struct virtio_net_config *net_config =
+		(struct virtio_net_config *)config;
+
+	net_config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
+	net_config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP);
+	memcpy(net_config->mac, macaddr_buf, ETH_ALEN);
+}
+
+static int __init vdpasim_net_init(void)
+{
+	struct vdpasim_dev_attr dev_attr = {};
+	int ret;
+
+	if (macaddr) {
+		mac_pton(macaddr, macaddr_buf);
+		if (!is_valid_ether_addr(macaddr_buf)) {
+			ret = -EADDRNOTAVAIL;
+			goto out;
+		}
+	} else {
+		eth_random_addr(macaddr_buf);
+	}
+
+	dev_attr.id = VIRTIO_ID_NET;
+	dev_attr.supported_features = VDPASIM_NET_FEATURES;
+	dev_attr.nvqs = VDPASIM_NET_VQ_NUM;
+	dev_attr.config_size = sizeof(struct virtio_net_config);
+	dev_attr.get_config = vdpasim_net_get_config;
+	dev_attr.work_fn = vdpasim_net_work;
+	dev_attr.buffer_size = PAGE_SIZE;
+
+	vdpasim_net_dev = vdpasim_create(&dev_attr);
+	if (IS_ERR(vdpasim_net_dev)) {
+		ret = PTR_ERR(vdpasim_net_dev);
+		goto out;
+	}
+
+	ret = vdpa_register_device(&vdpasim_net_dev->vdpa);
+	if (ret)
+		goto put_dev;
+
+	return 0;
+
+put_dev:
+	put_device(&vdpasim_net_dev->vdpa.dev);
+out:
+	return ret;
+}
+
+static void __exit vdpasim_net_exit(void)
+{
+	struct vdpa_device *vdpa = &vdpasim_net_dev->vdpa;
+
+	vdpa_unregister_device(vdpa);
+}
+
+module_init(vdpasim_net_init);
+module_exit(vdpasim_net_exit);
+
+MODULE_VERSION(DRV_VERSION);
+MODULE_LICENSE(DRV_LICENSE);
+MODULE_AUTHOR(DRV_AUTHOR);
+MODULE_DESCRIPTION(DRV_DESC);
diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c
index 997cb5d0a657..414e98d82b02 100644
--- a/drivers/vfio/virqfd.c
+++ b/drivers/vfio/virqfd.c
@@ -46,6 +46,9 @@ static int virqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void
 	__poll_t flags = key_to_poll(key);
 
 	if (flags & EPOLLIN) {
+		u64 cnt;
+		eventfd_ctx_do_read(virqfd->eventfd, &cnt);
+
 		/* An event has been signaled, call function */
 		if ((!virqfd->handler ||
 		     virqfd->handler(virqfd->opaque, virqfd->data)) &&
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 531a00d703cd..c8784dfafdd7 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -863,6 +863,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
 	size_t len, total_len = 0;
 	int err;
 	struct vhost_net_ubuf_ref *ubufs;
+	struct ubuf_info *ubuf;
 	bool zcopy_used;
 	int sent_pkts = 0;
 
@@ -895,9 +896,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
 
 		/* use msg_control to pass vhost zerocopy ubuf info to skb */
 		if (zcopy_used) {
-			struct ubuf_info *ubuf;
 			ubuf = nvq->ubuf_info + nvq->upend_idx;
-
 			vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head);
 			vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS;
 			ubuf->callback = vhost_zerocopy_callback;
@@ -927,7 +926,8 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
 		err = sock->ops->sendmsg(sock, &msg, len);
 		if (unlikely(err < 0)) {
 			if (zcopy_used) {
-				vhost_net_ubuf_put(ubufs);
+				if (vq->heads[ubuf->desc].len == VHOST_DMA_IN_PROGRESS)
+					vhost_net_ubuf_put(ubufs);
 				nvq->upend_idx = ((unsigned)nvq->upend_idx - 1)
 					% UIO_MAXIOV;
 			}
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 6ff8a5096691..4ce9f00ae10e 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1643,7 +1643,8 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 			if (!vhost_vq_is_setup(vq))
 				continue;
 
-			if (vhost_scsi_setup_vq_cmds(vq, vq->num))
+			ret = vhost_scsi_setup_vq_cmds(vq, vq->num);
+			if (ret)
 				goto destroy_vq_cmds;
 		}
 
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 29ed4173f04e..ef688c8c0e0e 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -245,14 +245,10 @@ static long vhost_vdpa_set_config(struct vhost_vdpa *v,
 		return -EFAULT;
 	if (vhost_vdpa_config_validate(v, &config))
 		return -EINVAL;
-	buf = kvzalloc(config.len, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
 
-	if (copy_from_user(buf, c->buf, config.len)) {
-		kvfree(buf);
-		return -EFAULT;
-	}
+	buf = vmemdup_user(c->buf, config.len);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	ops->set_config(vdpa, config.off, buf, config.len);
 
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index a483cec31d5c..5e78fb719602 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -30,7 +30,12 @@
 #define VHOST_VSOCK_PKT_WEIGHT 256
 
 enum {
-	VHOST_VSOCK_FEATURES = VHOST_FEATURES,
+	VHOST_VSOCK_FEATURES = VHOST_FEATURES |
+			       (1ULL << VIRTIO_F_ACCESS_PLATFORM)
+};
+
+enum {
+	VHOST_VSOCK_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2)
 };
 
 /* Used to track all the vhost_vsock instances on the system. */
@@ -94,6 +99,9 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 	if (!vhost_vq_get_backend(vq))
 		goto out;
 
+	if (!vq_meta_prefetch(vq))
+		goto out;
+
 	/* Avoid further vmexits, we're already processing the virtqueue */
 	vhost_disable_notify(&vsock->dev, vq);
 
@@ -449,6 +457,9 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 	if (!vhost_vq_get_backend(vq))
 		goto out;
 
+	if (!vq_meta_prefetch(vq))
+		goto out;
+
 	vhost_disable_notify(&vsock->dev, vq);
 	do {
 		u32 len;
@@ -766,8 +777,12 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
 	mutex_lock(&vsock->dev.mutex);
 	if ((features & (1 << VHOST_F_LOG_ALL)) &&
 	    !vhost_log_access_ok(&vsock->dev)) {
-		mutex_unlock(&vsock->dev.mutex);
-		return -EFAULT;
+		goto err;
+	}
+
+	if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) {
+		if (vhost_init_device_iotlb(&vsock->dev, true))
+			goto err;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
@@ -778,6 +793,10 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
 	}
 	mutex_unlock(&vsock->dev.mutex);
 	return 0;
+
+err:
+	mutex_unlock(&vsock->dev.mutex);
+	return -EFAULT;
 }
 
 static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
@@ -811,6 +830,18 @@ static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
 		if (copy_from_user(&features, argp, sizeof(features)))
 			return -EFAULT;
 		return vhost_vsock_set_features(vsock, features);
+	case VHOST_GET_BACKEND_FEATURES:
+		features = VHOST_VSOCK_BACKEND_FEATURES;
+		if (copy_to_user(argp, &features, sizeof(features)))
+			return -EFAULT;
+		return 0;
+	case VHOST_SET_BACKEND_FEATURES:
+		if (copy_from_user(&features, argp, sizeof(features)))
+			return -EFAULT;
+		if (features & ~VHOST_VSOCK_BACKEND_FEATURES)
+			return -EOPNOTSUPP;
+		vhost_set_backend_features(&vsock->dev, features);
+		return 0;
 	default:
 		mutex_lock(&vsock->dev.mutex);
 		r = vhost_dev_ioctl(&vsock->dev, ioctl, argp);
@@ -823,6 +854,34 @@ static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
 	}
 }
 
+static ssize_t vhost_vsock_chr_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct vhost_vsock *vsock = file->private_data;
+	struct vhost_dev *dev = &vsock->dev;
+	int noblock = file->f_flags & O_NONBLOCK;
+
+	return vhost_chr_read_iter(dev, to, noblock);
+}
+
+static ssize_t vhost_vsock_chr_write_iter(struct kiocb *iocb,
+					struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct vhost_vsock *vsock = file->private_data;
+	struct vhost_dev *dev = &vsock->dev;
+
+	return vhost_chr_write_iter(dev, from);
+}
+
+static __poll_t vhost_vsock_chr_poll(struct file *file, poll_table *wait)
+{
+	struct vhost_vsock *vsock = file->private_data;
+	struct vhost_dev *dev = &vsock->dev;
+
+	return vhost_chr_poll(file, dev, wait);
+}
+
 static const struct file_operations vhost_vsock_fops = {
 	.owner          = THIS_MODULE,
 	.open           = vhost_vsock_dev_open,
@@ -830,6 +889,9 @@ static const struct file_operations vhost_vsock_fops = {
 	.llseek		= noop_llseek,
 	.unlocked_ioctl = vhost_vsock_dev_ioctl,
 	.compat_ioctl   = compat_ptr_ioctl,
+	.read_iter      = vhost_vsock_chr_read_iter,
+	.write_iter     = vhost_vsock_chr_write_iter,
+	.poll           = vhost_vsock_chr_poll,
 };
 
 static struct miscdevice vhost_vsock_misc = {
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 181e2f18beae..9fc9ec4a25f5 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -27,20 +27,74 @@ static bool unplug_online = true;
 module_param(unplug_online, bool, 0644);
 MODULE_PARM_DESC(unplug_online, "Try to unplug online memory");
 
-enum virtio_mem_mb_state {
+static bool force_bbm;
+module_param(force_bbm, bool, 0444);
+MODULE_PARM_DESC(force_bbm,
+		"Force Big Block Mode. Default is 0 (auto-selection)");
+
+static unsigned long bbm_block_size;
+module_param(bbm_block_size, ulong, 0444);
+MODULE_PARM_DESC(bbm_block_size,
+		 "Big Block size in bytes. Default is 0 (auto-detection).");
+
+static bool bbm_safe_unplug = true;
+module_param(bbm_safe_unplug, bool, 0444);
+MODULE_PARM_DESC(bbm_safe_unplug,
+	     "Use a safe unplug mechanism in BBM, avoiding long/endless loops");
+
+/*
+ * virtio-mem currently supports the following modes of operation:
+ *
+ * * Sub Block Mode (SBM): A Linux memory block spans 2..X subblocks (SB). The
+ *   size of a Sub Block (SB) is determined based on the device block size, the
+ *   pageblock size, and the maximum allocation granularity of the buddy.
+ *   Subblocks within a Linux memory block might either be plugged or unplugged.
+ *   Memory is added/removed to Linux MM in Linux memory block granularity.
+ *
+ * * Big Block Mode (BBM): A Big Block (BB) spans 1..X Linux memory blocks.
+ *   Memory is added/removed to Linux MM in Big Block granularity.
+ *
+ * The mode is determined automatically based on the Linux memory block size
+ * and the device block size.
+ *
+ * User space / core MM (auto onlining) is responsible for onlining added
+ * Linux memory blocks - and for selecting a zone. Linux Memory Blocks are
+ * always onlined separately, and all memory within a Linux memory block is
+ * onlined to the same zone - virtio-mem relies on this behavior.
+ */
+
+/*
+ * State of a Linux memory block in SBM.
+ */
+enum virtio_mem_sbm_mb_state {
 	/* Unplugged, not added to Linux. Can be reused later. */
-	VIRTIO_MEM_MB_STATE_UNUSED = 0,
+	VIRTIO_MEM_SBM_MB_UNUSED = 0,
 	/* (Partially) plugged, not added to Linux. Error on add_memory(). */
-	VIRTIO_MEM_MB_STATE_PLUGGED,
+	VIRTIO_MEM_SBM_MB_PLUGGED,
 	/* Fully plugged, fully added to Linux, offline. */
-	VIRTIO_MEM_MB_STATE_OFFLINE,
+	VIRTIO_MEM_SBM_MB_OFFLINE,
 	/* Partially plugged, fully added to Linux, offline. */
-	VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL,
+	VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL,
 	/* Fully plugged, fully added to Linux, online. */
-	VIRTIO_MEM_MB_STATE_ONLINE,
+	VIRTIO_MEM_SBM_MB_ONLINE,
 	/* Partially plugged, fully added to Linux, online. */
-	VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL,
-	VIRTIO_MEM_MB_STATE_COUNT
+	VIRTIO_MEM_SBM_MB_ONLINE_PARTIAL,
+	VIRTIO_MEM_SBM_MB_COUNT
+};
+
+/*
+ * State of a Big Block (BB) in BBM, covering 1..X Linux memory blocks.
+ */
+enum virtio_mem_bbm_bb_state {
+	/* Unplugged, not added to Linux. Can be reused later. */
+	VIRTIO_MEM_BBM_BB_UNUSED = 0,
+	/* Plugged, not added to Linux. Error on add_memory(). */
+	VIRTIO_MEM_BBM_BB_PLUGGED,
+	/* Plugged and added to Linux. */
+	VIRTIO_MEM_BBM_BB_ADDED,
+	/* All online parts are fake-offline, ready to remove. */
+	VIRTIO_MEM_BBM_BB_FAKE_OFFLINE,
+	VIRTIO_MEM_BBM_BB_COUNT
 };
 
 struct virtio_mem {
@@ -51,6 +105,7 @@ struct virtio_mem {
 
 	/* Workqueue that processes the plug/unplug requests. */
 	struct work_struct wq;
+	atomic_t wq_active;
 	atomic_t config_changed;
 
 	/* Virtqueue for guest->host requests. */
@@ -70,27 +125,13 @@ struct virtio_mem {
 
 	/* The device block size (for communicating with the device). */
 	uint64_t device_block_size;
-	/* The translated node id. NUMA_NO_NODE in case not specified. */
+	/* The determined node id for all memory of the device. */
 	int nid;
 	/* Physical start address of the memory region. */
 	uint64_t addr;
 	/* Maximum region size in bytes. */
 	uint64_t region_size;
 
-	/* The subblock size. */
-	uint64_t subblock_size;
-	/* The number of subblocks per memory block. */
-	uint32_t nb_sb_per_mb;
-
-	/* Id of the first memory block of this device. */
-	unsigned long first_mb_id;
-	/* Id of the last memory block of this device. */
-	unsigned long last_mb_id;
-	/* Id of the last usable memory block of this device. */
-	unsigned long last_usable_mb_id;
-	/* Id of the next memory bock to prepare when needed. */
-	unsigned long next_mb_id;
-
 	/* The parent resource for all memory added via this device. */
 	struct resource *parent_resource;
 	/*
@@ -99,31 +140,79 @@ struct virtio_mem {
 	 */
 	const char *resource_name;
 
-	/* Summary of all memory block states. */
-	unsigned long nb_mb_state[VIRTIO_MEM_MB_STATE_COUNT];
-#define VIRTIO_MEM_NB_OFFLINE_THRESHOLD		10
-
-	/*
-	 * One byte state per memory block.
-	 *
-	 * Allocated via vmalloc(). When preparing new blocks, resized
-	 * (alloc+copy+free) when needed (crossing pages with the next mb).
-	 * (when crossing pages).
-	 *
-	 * With 128MB memory blocks, we have states for 512GB of memory in one
-	 * page.
-	 */
-	uint8_t *mb_state;
-
 	/*
-	 * $nb_sb_per_mb bit per memory block. Handled similar to mb_state.
-	 *
-	 * With 4MB subblocks, we manage 128GB of memory in one page.
+	 * We don't want to add too much memory if it's not getting onlined,
+	 * to avoid running OOM. Besides this threshold, we allow to have at
+	 * least two offline blocks at a time (whatever is bigger).
 	 */
-	unsigned long *sb_bitmap;
+#define VIRTIO_MEM_DEFAULT_OFFLINE_THRESHOLD		(1024 * 1024 * 1024)
+	atomic64_t offline_size;
+	uint64_t offline_threshold;
+
+	/* If set, the driver is in SBM, otherwise in BBM. */
+	bool in_sbm;
+
+	union {
+		struct {
+			/* Id of the first memory block of this device. */
+			unsigned long first_mb_id;
+			/* Id of the last usable memory block of this device. */
+			unsigned long last_usable_mb_id;
+			/* Id of the next memory bock to prepare when needed. */
+			unsigned long next_mb_id;
+
+			/* The subblock size. */
+			uint64_t sb_size;
+			/* The number of subblocks per Linux memory block. */
+			uint32_t sbs_per_mb;
+
+			/* Summary of all memory block states. */
+			unsigned long mb_count[VIRTIO_MEM_SBM_MB_COUNT];
+
+			/*
+			 * One byte state per memory block. Allocated via
+			 * vmalloc(). Resized (alloc+copy+free) on demand.
+			 *
+			 * With 128 MiB memory blocks, we have states for 512
+			 * GiB of memory in one 4 KiB page.
+			 */
+			uint8_t *mb_states;
+
+			/*
+			 * Bitmap: one bit per subblock. Allocated similar to
+			 * sbm.mb_states.
+			 *
+			 * A set bit means the corresponding subblock is
+			 * plugged, otherwise it's unblocked.
+			 *
+			 * With 4 MiB subblocks, we manage 128 GiB of memory
+			 * in one 4 KiB page.
+			 */
+			unsigned long *sb_states;
+		} sbm;
+
+		struct {
+			/* Id of the first big block of this device. */
+			unsigned long first_bb_id;
+			/* Id of the last usable big block of this device. */
+			unsigned long last_usable_bb_id;
+			/* Id of the next device bock to prepare when needed. */
+			unsigned long next_bb_id;
+
+			/* Summary of all big block states. */
+			unsigned long bb_count[VIRTIO_MEM_BBM_BB_COUNT];
+
+			/* One byte state per big block. See sbm.mb_states. */
+			uint8_t *bb_states;
+
+			/* The block size used for plugging/adding/removing. */
+			uint64_t bb_size;
+		} bbm;
+	};
 
 	/*
-	 * Mutex that protects the nb_mb_state, mb_state, and sb_bitmap.
+	 * Mutex that protects the sbm.mb_count, sbm.mb_states,
+	 * sbm.sb_states, bbm.bb_count, and bbm.bb_states
 	 *
 	 * When this lock is held the pointers can't change, ONLINE and
 	 * OFFLINE blocks can't change the state and no subblocks will get
@@ -160,6 +249,11 @@ static DEFINE_MUTEX(virtio_mem_mutex);
 static LIST_HEAD(virtio_mem_devices);
 
 static void virtio_mem_online_page_cb(struct page *page, unsigned int order);
+static void virtio_mem_fake_offline_going_offline(unsigned long pfn,
+						  unsigned long nr_pages);
+static void virtio_mem_fake_offline_cancel_offline(unsigned long pfn,
+						   unsigned long nr_pages);
+static void virtio_mem_retry(struct virtio_mem *vm);
 
 /*
  * Register a virtio-mem device so it will be considered for the online_page
@@ -213,6 +307,24 @@ static unsigned long virtio_mem_mb_id_to_phys(unsigned long mb_id)
 }
 
 /*
+ * Calculate the big block id of a given address.
+ */
+static unsigned long virtio_mem_phys_to_bb_id(struct virtio_mem *vm,
+					      uint64_t addr)
+{
+	return addr / vm->bbm.bb_size;
+}
+
+/*
+ * Calculate the physical start address of a given big block id.
+ */
+static uint64_t virtio_mem_bb_id_to_phys(struct virtio_mem *vm,
+					 unsigned long bb_id)
+{
+	return bb_id * vm->bbm.bb_size;
+}
+
+/*
  * Calculate the subblock id of a given address.
  */
 static unsigned long virtio_mem_phys_to_sb_id(struct virtio_mem *vm,
@@ -221,89 +333,164 @@ static unsigned long virtio_mem_phys_to_sb_id(struct virtio_mem *vm,
 	const unsigned long mb_id = virtio_mem_phys_to_mb_id(addr);
 	const unsigned long mb_addr = virtio_mem_mb_id_to_phys(mb_id);
 
-	return (addr - mb_addr) / vm->subblock_size;
+	return (addr - mb_addr) / vm->sbm.sb_size;
+}
+
+/*
+ * Set the state of a big block, taking care of the state counter.
+ */
+static void virtio_mem_bbm_set_bb_state(struct virtio_mem *vm,
+					unsigned long bb_id,
+					enum virtio_mem_bbm_bb_state state)
+{
+	const unsigned long idx = bb_id - vm->bbm.first_bb_id;
+	enum virtio_mem_bbm_bb_state old_state;
+
+	old_state = vm->bbm.bb_states[idx];
+	vm->bbm.bb_states[idx] = state;
+
+	BUG_ON(vm->bbm.bb_count[old_state] == 0);
+	vm->bbm.bb_count[old_state]--;
+	vm->bbm.bb_count[state]++;
+}
+
+/*
+ * Get the state of a big block.
+ */
+static enum virtio_mem_bbm_bb_state virtio_mem_bbm_get_bb_state(struct virtio_mem *vm,
+								unsigned long bb_id)
+{
+	return vm->bbm.bb_states[bb_id - vm->bbm.first_bb_id];
+}
+
+/*
+ * Prepare the big block state array for the next big block.
+ */
+static int virtio_mem_bbm_bb_states_prepare_next_bb(struct virtio_mem *vm)
+{
+	unsigned long old_bytes = vm->bbm.next_bb_id - vm->bbm.first_bb_id;
+	unsigned long new_bytes = old_bytes + 1;
+	int old_pages = PFN_UP(old_bytes);
+	int new_pages = PFN_UP(new_bytes);
+	uint8_t *new_array;
+
+	if (vm->bbm.bb_states && old_pages == new_pages)
+		return 0;
+
+	new_array = vzalloc(new_pages * PAGE_SIZE);
+	if (!new_array)
+		return -ENOMEM;
+
+	mutex_lock(&vm->hotplug_mutex);
+	if (vm->bbm.bb_states)
+		memcpy(new_array, vm->bbm.bb_states, old_pages * PAGE_SIZE);
+	vfree(vm->bbm.bb_states);
+	vm->bbm.bb_states = new_array;
+	mutex_unlock(&vm->hotplug_mutex);
+
+	return 0;
 }
 
+#define virtio_mem_bbm_for_each_bb(_vm, _bb_id, _state) \
+	for (_bb_id = vm->bbm.first_bb_id; \
+	     _bb_id < vm->bbm.next_bb_id && _vm->bbm.bb_count[_state]; \
+	     _bb_id++) \
+		if (virtio_mem_bbm_get_bb_state(_vm, _bb_id) == _state)
+
+#define virtio_mem_bbm_for_each_bb_rev(_vm, _bb_id, _state) \
+	for (_bb_id = vm->bbm.next_bb_id - 1; \
+	     _bb_id >= vm->bbm.first_bb_id && _vm->bbm.bb_count[_state]; \
+	     _bb_id--) \
+		if (virtio_mem_bbm_get_bb_state(_vm, _bb_id) == _state)
+
 /*
  * Set the state of a memory block, taking care of the state counter.
  */
-static void virtio_mem_mb_set_state(struct virtio_mem *vm, unsigned long mb_id,
-				    enum virtio_mem_mb_state state)
+static void virtio_mem_sbm_set_mb_state(struct virtio_mem *vm,
+					unsigned long mb_id, uint8_t state)
 {
-	const unsigned long idx = mb_id - vm->first_mb_id;
-	enum virtio_mem_mb_state old_state;
+	const unsigned long idx = mb_id - vm->sbm.first_mb_id;
+	uint8_t old_state;
 
-	old_state = vm->mb_state[idx];
-	vm->mb_state[idx] = state;
+	old_state = vm->sbm.mb_states[idx];
+	vm->sbm.mb_states[idx] = state;
 
-	BUG_ON(vm->nb_mb_state[old_state] == 0);
-	vm->nb_mb_state[old_state]--;
-	vm->nb_mb_state[state]++;
+	BUG_ON(vm->sbm.mb_count[old_state] == 0);
+	vm->sbm.mb_count[old_state]--;
+	vm->sbm.mb_count[state]++;
 }
 
 /*
  * Get the state of a memory block.
  */
-static enum virtio_mem_mb_state virtio_mem_mb_get_state(struct virtio_mem *vm,
-							unsigned long mb_id)
+static uint8_t virtio_mem_sbm_get_mb_state(struct virtio_mem *vm,
+					   unsigned long mb_id)
 {
-	const unsigned long idx = mb_id - vm->first_mb_id;
+	const unsigned long idx = mb_id - vm->sbm.first_mb_id;
 
-	return vm->mb_state[idx];
+	return vm->sbm.mb_states[idx];
 }
 
 /*
  * Prepare the state array for the next memory block.
  */
-static int virtio_mem_mb_state_prepare_next_mb(struct virtio_mem *vm)
+static int virtio_mem_sbm_mb_states_prepare_next_mb(struct virtio_mem *vm)
 {
-	unsigned long old_bytes = vm->next_mb_id - vm->first_mb_id + 1;
-	unsigned long new_bytes = vm->next_mb_id - vm->first_mb_id + 2;
-	int old_pages = PFN_UP(old_bytes);
-	int new_pages = PFN_UP(new_bytes);
-	uint8_t *new_mb_state;
+	int old_pages = PFN_UP(vm->sbm.next_mb_id - vm->sbm.first_mb_id);
+	int new_pages = PFN_UP(vm->sbm.next_mb_id - vm->sbm.first_mb_id + 1);
+	uint8_t *new_array;
 
-	if (vm->mb_state && old_pages == new_pages)
+	if (vm->sbm.mb_states && old_pages == new_pages)
 		return 0;
 
-	new_mb_state = vzalloc(new_pages * PAGE_SIZE);
-	if (!new_mb_state)
+	new_array = vzalloc(new_pages * PAGE_SIZE);
+	if (!new_array)
 		return -ENOMEM;
 
 	mutex_lock(&vm->hotplug_mutex);
-	if (vm->mb_state)
-		memcpy(new_mb_state, vm->mb_state, old_pages * PAGE_SIZE);
-	vfree(vm->mb_state);
-	vm->mb_state = new_mb_state;
+	if (vm->sbm.mb_states)
+		memcpy(new_array, vm->sbm.mb_states, old_pages * PAGE_SIZE);
+	vfree(vm->sbm.mb_states);
+	vm->sbm.mb_states = new_array;
 	mutex_unlock(&vm->hotplug_mutex);
 
 	return 0;
 }
 
-#define virtio_mem_for_each_mb_state(_vm, _mb_id, _state) \
-	for (_mb_id = _vm->first_mb_id; \
-	     _mb_id < _vm->next_mb_id && _vm->nb_mb_state[_state]; \
+#define virtio_mem_sbm_for_each_mb(_vm, _mb_id, _state) \
+	for (_mb_id = _vm->sbm.first_mb_id; \
+	     _mb_id < _vm->sbm.next_mb_id && _vm->sbm.mb_count[_state]; \
 	     _mb_id++) \
-		if (virtio_mem_mb_get_state(_vm, _mb_id) == _state)
+		if (virtio_mem_sbm_get_mb_state(_vm, _mb_id) == _state)
 
-#define virtio_mem_for_each_mb_state_rev(_vm, _mb_id, _state) \
-	for (_mb_id = _vm->next_mb_id - 1; \
-	     _mb_id >= _vm->first_mb_id && _vm->nb_mb_state[_state]; \
+#define virtio_mem_sbm_for_each_mb_rev(_vm, _mb_id, _state) \
+	for (_mb_id = _vm->sbm.next_mb_id - 1; \
+	     _mb_id >= _vm->sbm.first_mb_id && _vm->sbm.mb_count[_state]; \
 	     _mb_id--) \
-		if (virtio_mem_mb_get_state(_vm, _mb_id) == _state)
+		if (virtio_mem_sbm_get_mb_state(_vm, _mb_id) == _state)
+
+/*
+ * Calculate the bit number in the subblock bitmap for the given subblock
+ * inside the given memory block.
+ */
+static int virtio_mem_sbm_sb_state_bit_nr(struct virtio_mem *vm,
+					  unsigned long mb_id, int sb_id)
+{
+	return (mb_id - vm->sbm.first_mb_id) * vm->sbm.sbs_per_mb + sb_id;
+}
 
 /*
  * Mark all selected subblocks plugged.
  *
  * Will not modify the state of the memory block.
  */
-static void virtio_mem_mb_set_sb_plugged(struct virtio_mem *vm,
-					 unsigned long mb_id, int sb_id,
-					 int count)
+static void virtio_mem_sbm_set_sb_plugged(struct virtio_mem *vm,
+					  unsigned long mb_id, int sb_id,
+					  int count)
 {
-	const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
+	const int bit = virtio_mem_sbm_sb_state_bit_nr(vm, mb_id, sb_id);
 
-	__bitmap_set(vm->sb_bitmap, bit, count);
+	__bitmap_set(vm->sbm.sb_states, bit, count);
 }
 
 /*
@@ -311,105 +498,114 @@ static void virtio_mem_mb_set_sb_plugged(struct virtio_mem *vm,
  *
  * Will not modify the state of the memory block.
  */
-static void virtio_mem_mb_set_sb_unplugged(struct virtio_mem *vm,
-					   unsigned long mb_id, int sb_id,
-					   int count)
+static void virtio_mem_sbm_set_sb_unplugged(struct virtio_mem *vm,
+					    unsigned long mb_id, int sb_id,
+					    int count)
 {
-	const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
+	const int bit = virtio_mem_sbm_sb_state_bit_nr(vm, mb_id, sb_id);
 
-	__bitmap_clear(vm->sb_bitmap, bit, count);
+	__bitmap_clear(vm->sbm.sb_states, bit, count);
 }
 
 /*
  * Test if all selected subblocks are plugged.
  */
-static bool virtio_mem_mb_test_sb_plugged(struct virtio_mem *vm,
-					  unsigned long mb_id, int sb_id,
-					  int count)
+static bool virtio_mem_sbm_test_sb_plugged(struct virtio_mem *vm,
+					   unsigned long mb_id, int sb_id,
+					   int count)
 {
-	const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
+	const int bit = virtio_mem_sbm_sb_state_bit_nr(vm, mb_id, sb_id);
 
 	if (count == 1)
-		return test_bit(bit, vm->sb_bitmap);
+		return test_bit(bit, vm->sbm.sb_states);
 
 	/* TODO: Helper similar to bitmap_set() */
-	return find_next_zero_bit(vm->sb_bitmap, bit + count, bit) >=
+	return find_next_zero_bit(vm->sbm.sb_states, bit + count, bit) >=
 	       bit + count;
 }
 
 /*
  * Test if all selected subblocks are unplugged.
  */
-static bool virtio_mem_mb_test_sb_unplugged(struct virtio_mem *vm,
-					    unsigned long mb_id, int sb_id,
-					    int count)
+static bool virtio_mem_sbm_test_sb_unplugged(struct virtio_mem *vm,
+					     unsigned long mb_id, int sb_id,
+					     int count)
 {
-	const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
+	const int bit = virtio_mem_sbm_sb_state_bit_nr(vm, mb_id, sb_id);
 
 	/* TODO: Helper similar to bitmap_set() */
-	return find_next_bit(vm->sb_bitmap, bit + count, bit) >= bit + count;
+	return find_next_bit(vm->sbm.sb_states, bit + count, bit) >=
+	       bit + count;
 }
 
 /*
- * Find the first unplugged subblock. Returns vm->nb_sb_per_mb in case there is
+ * Find the first unplugged subblock. Returns vm->sbm.sbs_per_mb in case there is
  * none.
  */
-static int virtio_mem_mb_first_unplugged_sb(struct virtio_mem *vm,
+static int virtio_mem_sbm_first_unplugged_sb(struct virtio_mem *vm,
 					    unsigned long mb_id)
 {
-	const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb;
+	const int bit = virtio_mem_sbm_sb_state_bit_nr(vm, mb_id, 0);
 
-	return find_next_zero_bit(vm->sb_bitmap, bit + vm->nb_sb_per_mb, bit) -
-	       bit;
+	return find_next_zero_bit(vm->sbm.sb_states,
+				  bit + vm->sbm.sbs_per_mb, bit) - bit;
 }
 
 /*
  * Prepare the subblock bitmap for the next memory block.
  */
-static int virtio_mem_sb_bitmap_prepare_next_mb(struct virtio_mem *vm)
+static int virtio_mem_sbm_sb_states_prepare_next_mb(struct virtio_mem *vm)
 {
-	const unsigned long old_nb_mb = vm->next_mb_id - vm->first_mb_id;
-	const unsigned long old_nb_bits = old_nb_mb * vm->nb_sb_per_mb;
-	const unsigned long new_nb_bits = (old_nb_mb + 1) * vm->nb_sb_per_mb;
+	const unsigned long old_nb_mb = vm->sbm.next_mb_id - vm->sbm.first_mb_id;
+	const unsigned long old_nb_bits = old_nb_mb * vm->sbm.sbs_per_mb;
+	const unsigned long new_nb_bits = (old_nb_mb + 1) * vm->sbm.sbs_per_mb;
 	int old_pages = PFN_UP(BITS_TO_LONGS(old_nb_bits) * sizeof(long));
 	int new_pages = PFN_UP(BITS_TO_LONGS(new_nb_bits) * sizeof(long));
-	unsigned long *new_sb_bitmap, *old_sb_bitmap;
+	unsigned long *new_bitmap, *old_bitmap;
 
-	if (vm->sb_bitmap && old_pages == new_pages)
+	if (vm->sbm.sb_states && old_pages == new_pages)
 		return 0;
 
-	new_sb_bitmap = vzalloc(new_pages * PAGE_SIZE);
-	if (!new_sb_bitmap)
+	new_bitmap = vzalloc(new_pages * PAGE_SIZE);
+	if (!new_bitmap)
 		return -ENOMEM;
 
 	mutex_lock(&vm->hotplug_mutex);
-	if (new_sb_bitmap)
-		memcpy(new_sb_bitmap, vm->sb_bitmap, old_pages * PAGE_SIZE);
+	if (new_bitmap)
+		memcpy(new_bitmap, vm->sbm.sb_states, old_pages * PAGE_SIZE);
 
-	old_sb_bitmap = vm->sb_bitmap;
-	vm->sb_bitmap = new_sb_bitmap;
+	old_bitmap = vm->sbm.sb_states;
+	vm->sbm.sb_states = new_bitmap;
 	mutex_unlock(&vm->hotplug_mutex);
 
-	vfree(old_sb_bitmap);
+	vfree(old_bitmap);
 	return 0;
 }
 
 /*
- * Try to add a memory block to Linux. This will usually only fail
- * if out of memory.
+ * Test if we could add memory without creating too much offline memory -
+ * to avoid running OOM if memory is getting onlined deferred.
+ */
+static bool virtio_mem_could_add_memory(struct virtio_mem *vm, uint64_t size)
+{
+	if (WARN_ON_ONCE(size > vm->offline_threshold))
+		return false;
+
+	return atomic64_read(&vm->offline_size) + size <= vm->offline_threshold;
+}
+
+/*
+ * Try adding memory to Linux. Will usually only fail if out of memory.
  *
  * Must not be called with the vm->hotplug_mutex held (possible deadlock with
  * onlining code).
  *
- * Will not modify the state of the memory block.
+ * Will not modify the state of memory blocks in virtio-mem.
  */
-static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
+static int virtio_mem_add_memory(struct virtio_mem *vm, uint64_t addr,
+				 uint64_t size)
 {
-	const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
-	int nid = vm->nid;
-
-	if (nid == NUMA_NO_NODE)
-		nid = memory_add_physaddr_to_nid(addr);
+	int rc;
 
 	/*
 	 * When force-unloading the driver and we still have memory added to
@@ -422,53 +618,155 @@ static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
 			return -ENOMEM;
 	}
 
-	dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id);
-	return add_memory_driver_managed(nid, addr, memory_block_size_bytes(),
-					 vm->resource_name,
-					 MEMHP_MERGE_RESOURCE);
+	dev_dbg(&vm->vdev->dev, "adding memory: 0x%llx - 0x%llx\n", addr,
+		addr + size - 1);
+	/* Memory might get onlined immediately. */
+	atomic64_add(size, &vm->offline_size);
+	rc = add_memory_driver_managed(vm->nid, addr, size, vm->resource_name,
+				       MEMHP_MERGE_RESOURCE);
+	if (rc) {
+		atomic64_sub(size, &vm->offline_size);
+		dev_warn(&vm->vdev->dev, "adding memory failed: %d\n", rc);
+		/*
+		 * TODO: Linux MM does not properly clean up yet in all cases
+		 * where adding of memory failed - especially on -ENOMEM.
+		 */
+	}
+	return rc;
+}
+
+/*
+ * See virtio_mem_add_memory(): Try adding a single Linux memory block.
+ */
+static int virtio_mem_sbm_add_mb(struct virtio_mem *vm, unsigned long mb_id)
+{
+	const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
+	const uint64_t size = memory_block_size_bytes();
+
+	return virtio_mem_add_memory(vm, addr, size);
+}
+
+/*
+ * See virtio_mem_add_memory(): Try adding a big block.
+ */
+static int virtio_mem_bbm_add_bb(struct virtio_mem *vm, unsigned long bb_id)
+{
+	const uint64_t addr = virtio_mem_bb_id_to_phys(vm, bb_id);
+	const uint64_t size = vm->bbm.bb_size;
+
+	return virtio_mem_add_memory(vm, addr, size);
 }
 
 /*
- * Try to remove a memory block from Linux. Will only fail if the memory block
- * is not offline.
+ * Try removing memory from Linux. Will only fail if memory blocks aren't
+ * offline.
  *
  * Must not be called with the vm->hotplug_mutex held (possible deadlock with
  * onlining code).
  *
- * Will not modify the state of the memory block.
+ * Will not modify the state of memory blocks in virtio-mem.
  */
-static int virtio_mem_mb_remove(struct virtio_mem *vm, unsigned long mb_id)
+static int virtio_mem_remove_memory(struct virtio_mem *vm, uint64_t addr,
+				    uint64_t size)
+{
+	int rc;
+
+	dev_dbg(&vm->vdev->dev, "removing memory: 0x%llx - 0x%llx\n", addr,
+		addr + size - 1);
+	rc = remove_memory(vm->nid, addr, size);
+	if (!rc) {
+		atomic64_sub(size, &vm->offline_size);
+		/*
+		 * We might have freed up memory we can now unplug, retry
+		 * immediately instead of waiting.
+		 */
+		virtio_mem_retry(vm);
+	} else {
+		dev_dbg(&vm->vdev->dev, "removing memory failed: %d\n", rc);
+	}
+	return rc;
+}
+
+/*
+ * See virtio_mem_remove_memory(): Try removing a single Linux memory block.
+ */
+static int virtio_mem_sbm_remove_mb(struct virtio_mem *vm, unsigned long mb_id)
 {
 	const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
-	int nid = vm->nid;
+	const uint64_t size = memory_block_size_bytes();
 
-	if (nid == NUMA_NO_NODE)
-		nid = memory_add_physaddr_to_nid(addr);
+	return virtio_mem_remove_memory(vm, addr, size);
+}
 
-	dev_dbg(&vm->vdev->dev, "removing memory block: %lu\n", mb_id);
-	return remove_memory(nid, addr, memory_block_size_bytes());
+/*
+ * See virtio_mem_remove_memory(): Try to remove all Linux memory blocks covered
+ * by the big block.
+ */
+static int virtio_mem_bbm_remove_bb(struct virtio_mem *vm, unsigned long bb_id)
+{
+	const uint64_t addr = virtio_mem_bb_id_to_phys(vm, bb_id);
+	const uint64_t size = vm->bbm.bb_size;
+
+	return virtio_mem_remove_memory(vm, addr, size);
 }
 
 /*
- * Try to offline and remove a memory block from Linux.
+ * Try offlining and removing memory from Linux.
  *
  * Must not be called with the vm->hotplug_mutex held (possible deadlock with
  * onlining code).
  *
- * Will not modify the state of the memory block.
+ * Will not modify the state of memory blocks in virtio-mem.
  */
-static int virtio_mem_mb_offline_and_remove(struct virtio_mem *vm,
-					    unsigned long mb_id)
+static int virtio_mem_offline_and_remove_memory(struct virtio_mem *vm,
+						uint64_t addr,
+						uint64_t size)
+{
+	int rc;
+
+	dev_dbg(&vm->vdev->dev,
+		"offlining and removing memory: 0x%llx - 0x%llx\n", addr,
+		addr + size - 1);
+
+	rc = offline_and_remove_memory(vm->nid, addr, size);
+	if (!rc) {
+		atomic64_sub(size, &vm->offline_size);
+		/*
+		 * We might have freed up memory we can now unplug, retry
+		 * immediately instead of waiting.
+		 */
+		virtio_mem_retry(vm);
+	} else {
+		dev_dbg(&vm->vdev->dev,
+			"offlining and removing memory failed: %d\n", rc);
+	}
+	return rc;
+}
+
+/*
+ * See virtio_mem_offline_and_remove_memory(): Try offlining and removing
+ * a single Linux memory block.
+ */
+static int virtio_mem_sbm_offline_and_remove_mb(struct virtio_mem *vm,
+						unsigned long mb_id)
 {
 	const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
-	int nid = vm->nid;
+	const uint64_t size = memory_block_size_bytes();
+
+	return virtio_mem_offline_and_remove_memory(vm, addr, size);
+}
 
-	if (nid == NUMA_NO_NODE)
-		nid = memory_add_physaddr_to_nid(addr);
+/*
+ * See virtio_mem_offline_and_remove_memory(): Try to offline and remove a
+ * all Linux memory blocks covered by the big block.
+ */
+static int virtio_mem_bbm_offline_and_remove_bb(struct virtio_mem *vm,
+						unsigned long bb_id)
+{
+	const uint64_t addr = virtio_mem_bb_id_to_phys(vm, bb_id);
+	const uint64_t size = vm->bbm.bb_size;
 
-	dev_dbg(&vm->vdev->dev, "offlining and removing memory block: %lu\n",
-		mb_id);
-	return offline_and_remove_memory(nid, addr, memory_block_size_bytes());
+	return virtio_mem_offline_and_remove_memory(vm, addr, size);
 }
 
 /*
@@ -499,31 +797,28 @@ static int virtio_mem_translate_node_id(struct virtio_mem *vm, uint16_t node_id)
  * Test if a virtio-mem device overlaps with the given range. Can be called
  * from (notifier) callbacks lockless.
  */
-static bool virtio_mem_overlaps_range(struct virtio_mem *vm,
-				      unsigned long start, unsigned long size)
+static bool virtio_mem_overlaps_range(struct virtio_mem *vm, uint64_t start,
+				      uint64_t size)
 {
-	unsigned long dev_start = virtio_mem_mb_id_to_phys(vm->first_mb_id);
-	unsigned long dev_end = virtio_mem_mb_id_to_phys(vm->last_mb_id) +
-				memory_block_size_bytes();
-
-	return start < dev_end && dev_start < start + size;
+	return start < vm->addr + vm->region_size && vm->addr < start + size;
 }
 
 /*
- * Test if a virtio-mem device owns a memory block. Can be called from
+ * Test if a virtio-mem device contains a given range. Can be called from
  * (notifier) callbacks lockless.
  */
-static bool virtio_mem_owned_mb(struct virtio_mem *vm, unsigned long mb_id)
+static bool virtio_mem_contains_range(struct virtio_mem *vm, uint64_t start,
+				      uint64_t size)
 {
-	return mb_id >= vm->first_mb_id && mb_id <= vm->last_mb_id;
+	return start >= vm->addr && start + size <= vm->addr + vm->region_size;
 }
 
-static int virtio_mem_notify_going_online(struct virtio_mem *vm,
-					  unsigned long mb_id)
+static int virtio_mem_sbm_notify_going_online(struct virtio_mem *vm,
+					      unsigned long mb_id)
 {
-	switch (virtio_mem_mb_get_state(vm, mb_id)) {
-	case VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL:
-	case VIRTIO_MEM_MB_STATE_OFFLINE:
+	switch (virtio_mem_sbm_get_mb_state(vm, mb_id)) {
+	case VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL:
+	case VIRTIO_MEM_SBM_MB_OFFLINE:
 		return NOTIFY_OK;
 	default:
 		break;
@@ -533,108 +828,100 @@ static int virtio_mem_notify_going_online(struct virtio_mem *vm,
 	return NOTIFY_BAD;
 }
 
-static void virtio_mem_notify_offline(struct virtio_mem *vm,
-				      unsigned long mb_id)
+static void virtio_mem_sbm_notify_offline(struct virtio_mem *vm,
+					  unsigned long mb_id)
 {
-	switch (virtio_mem_mb_get_state(vm, mb_id)) {
-	case VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL:
-		virtio_mem_mb_set_state(vm, mb_id,
-					VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL);
+	switch (virtio_mem_sbm_get_mb_state(vm, mb_id)) {
+	case VIRTIO_MEM_SBM_MB_ONLINE_PARTIAL:
+		virtio_mem_sbm_set_mb_state(vm, mb_id,
+					    VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL);
 		break;
-	case VIRTIO_MEM_MB_STATE_ONLINE:
-		virtio_mem_mb_set_state(vm, mb_id,
-					VIRTIO_MEM_MB_STATE_OFFLINE);
+	case VIRTIO_MEM_SBM_MB_ONLINE:
+		virtio_mem_sbm_set_mb_state(vm, mb_id,
+					    VIRTIO_MEM_SBM_MB_OFFLINE);
 		break;
 	default:
 		BUG();
 		break;
 	}
-
-	/*
-	 * Trigger the workqueue, maybe we can now unplug memory. Also,
-	 * when we offline and remove a memory block, this will re-trigger
-	 * us immediately - which is often nice because the removal of
-	 * the memory block (e.g., memmap) might have freed up memory
-	 * on other memory blocks we manage.
-	 */
-	virtio_mem_retry(vm);
 }
 
-static void virtio_mem_notify_online(struct virtio_mem *vm, unsigned long mb_id)
+static void virtio_mem_sbm_notify_online(struct virtio_mem *vm,
+					 unsigned long mb_id)
 {
-	unsigned long nb_offline;
-
-	switch (virtio_mem_mb_get_state(vm, mb_id)) {
-	case VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL:
-		virtio_mem_mb_set_state(vm, mb_id,
-					VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL);
+	switch (virtio_mem_sbm_get_mb_state(vm, mb_id)) {
+	case VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL:
+		virtio_mem_sbm_set_mb_state(vm, mb_id,
+					VIRTIO_MEM_SBM_MB_ONLINE_PARTIAL);
 		break;
-	case VIRTIO_MEM_MB_STATE_OFFLINE:
-		virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_ONLINE);
+	case VIRTIO_MEM_SBM_MB_OFFLINE:
+		virtio_mem_sbm_set_mb_state(vm, mb_id,
+					    VIRTIO_MEM_SBM_MB_ONLINE);
 		break;
 	default:
 		BUG();
 		break;
 	}
-	nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] +
-		     vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL];
-
-	/* see if we can add new blocks now that we onlined one block */
-	if (nb_offline == VIRTIO_MEM_NB_OFFLINE_THRESHOLD - 1)
-		virtio_mem_retry(vm);
 }
 
-static void virtio_mem_notify_going_offline(struct virtio_mem *vm,
-					    unsigned long mb_id)
+static void virtio_mem_sbm_notify_going_offline(struct virtio_mem *vm,
+						unsigned long mb_id)
 {
-	const unsigned long nr_pages = PFN_DOWN(vm->subblock_size);
-	struct page *page;
+	const unsigned long nr_pages = PFN_DOWN(vm->sbm.sb_size);
 	unsigned long pfn;
-	int sb_id, i;
+	int sb_id;
 
-	for (sb_id = 0; sb_id < vm->nb_sb_per_mb; sb_id++) {
-		if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+	for (sb_id = 0; sb_id < vm->sbm.sbs_per_mb; sb_id++) {
+		if (virtio_mem_sbm_test_sb_plugged(vm, mb_id, sb_id, 1))
 			continue;
-		/*
-		 * Drop our reference to the pages so the memory can get
-		 * offlined and add the unplugged pages to the managed
-		 * page counters (so offlining code can correctly subtract
-		 * them again).
-		 */
 		pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
-			       sb_id * vm->subblock_size);
-		adjust_managed_page_count(pfn_to_page(pfn), nr_pages);
-		for (i = 0; i < nr_pages; i++) {
-			page = pfn_to_page(pfn + i);
-			if (WARN_ON(!page_ref_dec_and_test(page)))
-				dump_page(page, "unplugged page referenced");
-		}
+			       sb_id * vm->sbm.sb_size);
+		virtio_mem_fake_offline_going_offline(pfn, nr_pages);
 	}
 }
 
-static void virtio_mem_notify_cancel_offline(struct virtio_mem *vm,
-					     unsigned long mb_id)
+static void virtio_mem_sbm_notify_cancel_offline(struct virtio_mem *vm,
+						 unsigned long mb_id)
 {
-	const unsigned long nr_pages = PFN_DOWN(vm->subblock_size);
+	const unsigned long nr_pages = PFN_DOWN(vm->sbm.sb_size);
 	unsigned long pfn;
-	int sb_id, i;
+	int sb_id;
 
-	for (sb_id = 0; sb_id < vm->nb_sb_per_mb; sb_id++) {
-		if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+	for (sb_id = 0; sb_id < vm->sbm.sbs_per_mb; sb_id++) {
+		if (virtio_mem_sbm_test_sb_plugged(vm, mb_id, sb_id, 1))
 			continue;
-		/*
-		 * Get the reference we dropped when going offline and
-		 * subtract the unplugged pages from the managed page
-		 * counters.
-		 */
 		pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
-			       sb_id * vm->subblock_size);
-		adjust_managed_page_count(pfn_to_page(pfn), -nr_pages);
-		for (i = 0; i < nr_pages; i++)
-			page_ref_inc(pfn_to_page(pfn + i));
+			       sb_id * vm->sbm.sb_size);
+		virtio_mem_fake_offline_cancel_offline(pfn, nr_pages);
 	}
 }
 
+static void virtio_mem_bbm_notify_going_offline(struct virtio_mem *vm,
+						unsigned long bb_id,
+						unsigned long pfn,
+						unsigned long nr_pages)
+{
+	/*
+	 * When marked as "fake-offline", all online memory of this device block
+	 * is allocated by us. Otherwise, we don't have any memory allocated.
+	 */
+	if (virtio_mem_bbm_get_bb_state(vm, bb_id) !=
+	    VIRTIO_MEM_BBM_BB_FAKE_OFFLINE)
+		return;
+	virtio_mem_fake_offline_going_offline(pfn, nr_pages);
+}
+
+static void virtio_mem_bbm_notify_cancel_offline(struct virtio_mem *vm,
+						 unsigned long bb_id,
+						 unsigned long pfn,
+						 unsigned long nr_pages)
+{
+	if (virtio_mem_bbm_get_bb_state(vm, bb_id) !=
+	    VIRTIO_MEM_BBM_BB_FAKE_OFFLINE)
+		return;
+	virtio_mem_fake_offline_cancel_offline(pfn, nr_pages);
+}
+
 /*
  * This callback will either be called synchronously from add_memory() or
  * asynchronously (e.g., triggered via user space). We have to be careful
@@ -648,20 +935,33 @@ static int virtio_mem_memory_notifier_cb(struct notifier_block *nb,
 	struct memory_notify *mhp = arg;
 	const unsigned long start = PFN_PHYS(mhp->start_pfn);
 	const unsigned long size = PFN_PHYS(mhp->nr_pages);
-	const unsigned long mb_id = virtio_mem_phys_to_mb_id(start);
 	int rc = NOTIFY_OK;
+	unsigned long id;
 
 	if (!virtio_mem_overlaps_range(vm, start, size))
 		return NOTIFY_DONE;
 
-	/*
-	 * Memory is onlined/offlined in memory block granularity. We cannot
-	 * cross virtio-mem device boundaries and memory block boundaries. Bail
-	 * out if this ever changes.
-	 */
-	if (WARN_ON_ONCE(size != memory_block_size_bytes() ||
-			 !IS_ALIGNED(start, memory_block_size_bytes())))
-		return NOTIFY_BAD;
+	if (vm->in_sbm) {
+		id = virtio_mem_phys_to_mb_id(start);
+		/*
+		 * In SBM, we add memory in separate memory blocks - we expect
+		 * it to be onlined/offlined in the same granularity. Bail out
+		 * if this ever changes.
+		 */
+		if (WARN_ON_ONCE(size != memory_block_size_bytes() ||
+				 !IS_ALIGNED(start, memory_block_size_bytes())))
+			return NOTIFY_BAD;
+	} else {
+		id = virtio_mem_phys_to_bb_id(vm, start);
+		/*
+		 * In BBM, we only care about onlining/offlining happening
+		 * within a single big block, we don't care about the
+		 * actual granularity as we don't track individual Linux
+		 * memory blocks.
+		 */
+		if (WARN_ON_ONCE(id != virtio_mem_phys_to_bb_id(vm, start + size - 1)))
+			return NOTIFY_BAD;
+	}
 
 	/*
 	 * Avoid circular locking lockdep warnings. We lock the mutex
@@ -680,7 +980,12 @@ static int virtio_mem_memory_notifier_cb(struct notifier_block *nb,
 			break;
 		}
 		vm->hotplug_active = true;
-		virtio_mem_notify_going_offline(vm, mb_id);
+		if (vm->in_sbm)
+			virtio_mem_sbm_notify_going_offline(vm, id);
+		else
+			virtio_mem_bbm_notify_going_offline(vm, id,
+							    mhp->start_pfn,
+							    mhp->nr_pages);
 		break;
 	case MEM_GOING_ONLINE:
 		mutex_lock(&vm->hotplug_mutex);
@@ -690,22 +995,51 @@ static int virtio_mem_memory_notifier_cb(struct notifier_block *nb,
 			break;
 		}
 		vm->hotplug_active = true;
-		rc = virtio_mem_notify_going_online(vm, mb_id);
+		if (vm->in_sbm)
+			rc = virtio_mem_sbm_notify_going_online(vm, id);
 		break;
 	case MEM_OFFLINE:
-		virtio_mem_notify_offline(vm, mb_id);
+		if (vm->in_sbm)
+			virtio_mem_sbm_notify_offline(vm, id);
+
+		atomic64_add(size, &vm->offline_size);
+		/*
+		 * Trigger the workqueue. Now that we have some offline memory,
+		 * maybe we can handle pending unplug requests.
+		 */
+		if (!unplug_online)
+			virtio_mem_retry(vm);
+
 		vm->hotplug_active = false;
 		mutex_unlock(&vm->hotplug_mutex);
 		break;
 	case MEM_ONLINE:
-		virtio_mem_notify_online(vm, mb_id);
+		if (vm->in_sbm)
+			virtio_mem_sbm_notify_online(vm, id);
+
+		atomic64_sub(size, &vm->offline_size);
+		/*
+		 * Start adding more memory once we onlined half of our
+		 * threshold. Don't trigger if it's possibly due to our actipn
+		 * (e.g., us adding memory which gets onlined immediately from
+		 * the core).
+		 */
+		if (!atomic_read(&vm->wq_active) &&
+		    virtio_mem_could_add_memory(vm, vm->offline_threshold / 2))
+			virtio_mem_retry(vm);
+
 		vm->hotplug_active = false;
 		mutex_unlock(&vm->hotplug_mutex);
 		break;
 	case MEM_CANCEL_OFFLINE:
 		if (!vm->hotplug_active)
 			break;
-		virtio_mem_notify_cancel_offline(vm, mb_id);
+		if (vm->in_sbm)
+			virtio_mem_sbm_notify_cancel_offline(vm, id);
+		else
+			virtio_mem_bbm_notify_cancel_offline(vm, id,
+							     mhp->start_pfn,
+							     mhp->nr_pages);
 		vm->hotplug_active = false;
 		mutex_unlock(&vm->hotplug_mutex);
 		break;
@@ -729,7 +1063,7 @@ static int virtio_mem_memory_notifier_cb(struct notifier_block *nb,
  * (via generic_online_page()) using PageDirty().
  */
 static void virtio_mem_set_fake_offline(unsigned long pfn,
-					unsigned int nr_pages, bool onlined)
+					unsigned long nr_pages, bool onlined)
 {
 	for (; nr_pages--; pfn++) {
 		struct page *page = pfn_to_page(pfn);
@@ -748,7 +1082,7 @@ static void virtio_mem_set_fake_offline(unsigned long pfn,
  * (via generic_online_page()), clear PageDirty().
  */
 static void virtio_mem_clear_fake_offline(unsigned long pfn,
-					  unsigned int nr_pages, bool onlined)
+					  unsigned long nr_pages, bool onlined)
 {
 	for (; nr_pages--; pfn++) {
 		struct page *page = pfn_to_page(pfn);
@@ -763,16 +1097,17 @@ static void virtio_mem_clear_fake_offline(unsigned long pfn,
  * Release a range of fake-offline pages to the buddy, effectively
  * fake-onlining them.
  */
-static void virtio_mem_fake_online(unsigned long pfn, unsigned int nr_pages)
+static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages)
 {
-	const int order = MAX_ORDER - 1;
-	int i;
+	const unsigned long max_nr_pages = MAX_ORDER_NR_PAGES;
+	unsigned long i;
 
 	/*
-	 * We are always called with subblock granularity, which is at least
-	 * aligned to MAX_ORDER - 1.
+	 * We are always called at least with MAX_ORDER_NR_PAGES
+	 * granularity/alignment (e.g., the way subblocks work). All pages
+	 * inside such a block are alike.
 	 */
-	for (i = 0; i < nr_pages; i += 1 << order) {
+	for (i = 0; i < nr_pages; i += max_nr_pages) {
 		struct page *page = pfn_to_page(pfn + i);
 
 		/*
@@ -782,42 +1117,128 @@ static void virtio_mem_fake_online(unsigned long pfn, unsigned int nr_pages)
 		 * alike.
 		 */
 		if (PageDirty(page)) {
-			virtio_mem_clear_fake_offline(pfn + i, 1 << order,
+			virtio_mem_clear_fake_offline(pfn + i, max_nr_pages,
 						      false);
-			generic_online_page(page, order);
+			generic_online_page(page, MAX_ORDER - 1);
 		} else {
-			virtio_mem_clear_fake_offline(pfn + i, 1 << order,
+			virtio_mem_clear_fake_offline(pfn + i, max_nr_pages,
 						      true);
-			free_contig_range(pfn + i, 1 << order);
-			adjust_managed_page_count(page, 1 << order);
+			free_contig_range(pfn + i, max_nr_pages);
+			adjust_managed_page_count(page, max_nr_pages);
 		}
 	}
 }
 
+/*
+ * Try to allocate a range, marking pages fake-offline, effectively
+ * fake-offlining them.
+ */
+static int virtio_mem_fake_offline(unsigned long pfn, unsigned long nr_pages)
+{
+	const bool is_movable = zone_idx(page_zone(pfn_to_page(pfn))) ==
+				ZONE_MOVABLE;
+	int rc, retry_count;
+
+	/*
+	 * TODO: We want an alloc_contig_range() mode that tries to allocate
+	 * harder (e.g., dealing with temporarily pinned pages, PCP), especially
+	 * with ZONE_MOVABLE. So for now, retry a couple of times with
+	 * ZONE_MOVABLE before giving up - because that zone is supposed to give
+	 * some guarantees.
+	 */
+	for (retry_count = 0; retry_count < 5; retry_count++) {
+		rc = alloc_contig_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE,
+					GFP_KERNEL);
+		if (rc == -ENOMEM)
+			/* whoops, out of memory */
+			return rc;
+		else if (rc && !is_movable)
+			break;
+		else if (rc)
+			continue;
+
+		virtio_mem_set_fake_offline(pfn, nr_pages, true);
+		adjust_managed_page_count(pfn_to_page(pfn), -nr_pages);
+		return 0;
+	}
+
+	return -EBUSY;
+}
+
+/*
+ * Handle fake-offline pages when memory is going offline - such that the
+ * pages can be skipped by mm-core when offlining.
+ */
+static void virtio_mem_fake_offline_going_offline(unsigned long pfn,
+						  unsigned long nr_pages)
+{
+	struct page *page;
+	unsigned long i;
+
+	/*
+	 * Drop our reference to the pages so the memory can get offlined
+	 * and add the unplugged pages to the managed page counters (so
+	 * offlining code can correctly subtract them again).
+	 */
+	adjust_managed_page_count(pfn_to_page(pfn), nr_pages);
+	/* Drop our reference to the pages so the memory can get offlined. */
+	for (i = 0; i < nr_pages; i++) {
+		page = pfn_to_page(pfn + i);
+		if (WARN_ON(!page_ref_dec_and_test(page)))
+			dump_page(page, "fake-offline page referenced");
+	}
+}
+
+/*
+ * Handle fake-offline pages when memory offlining is canceled - to undo
+ * what we did in virtio_mem_fake_offline_going_offline().
+ */
+static void virtio_mem_fake_offline_cancel_offline(unsigned long pfn,
+						   unsigned long nr_pages)
+{
+	unsigned long i;
+
+	/*
+	 * Get the reference we dropped when going offline and subtract the
+	 * unplugged pages from the managed page counters.
+	 */
+	adjust_managed_page_count(pfn_to_page(pfn), -nr_pages);
+	for (i = 0; i < nr_pages; i++)
+		page_ref_inc(pfn_to_page(pfn + i));
+}
+
 static void virtio_mem_online_page_cb(struct page *page, unsigned int order)
 {
 	const unsigned long addr = page_to_phys(page);
-	const unsigned long mb_id = virtio_mem_phys_to_mb_id(addr);
+	unsigned long id, sb_id;
 	struct virtio_mem *vm;
-	int sb_id;
+	bool do_online;
 
-	/*
-	 * We exploit here that subblocks have at least MAX_ORDER - 1
-	 * size/alignment and that this callback is is called with such a
-	 * size/alignment. So we cannot cross subblocks and therefore
-	 * also not memory blocks.
-	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(vm, &virtio_mem_devices, next) {
-		if (!virtio_mem_owned_mb(vm, mb_id))
+		if (!virtio_mem_contains_range(vm, addr, PFN_PHYS(1 << order)))
 			continue;
 
-		sb_id = virtio_mem_phys_to_sb_id(vm, addr);
-		/*
-		 * If plugged, online the pages, otherwise, set them fake
-		 * offline (PageOffline).
-		 */
-		if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+		if (vm->in_sbm) {
+			/*
+			 * We exploit here that subblocks have at least
+			 * MAX_ORDER_NR_PAGES size/alignment - so we cannot
+			 * cross subblocks within one call.
+			 */
+			id = virtio_mem_phys_to_mb_id(addr);
+			sb_id = virtio_mem_phys_to_sb_id(vm, addr);
+			do_online = virtio_mem_sbm_test_sb_plugged(vm, id,
+								   sb_id, 1);
+		} else {
+			/*
+			 * If the whole block is marked fake offline, keep
+			 * everything that way.
+			 */
+			id = virtio_mem_phys_to_bb_id(vm, addr);
+			do_online = virtio_mem_bbm_get_bb_state(vm, id) !=
+				    VIRTIO_MEM_BBM_BB_FAKE_OFFLINE;
+		}
+		if (do_online)
 			generic_online_page(page, order);
 		else
 			virtio_mem_set_fake_offline(PFN_DOWN(addr), 1 << order,
@@ -870,23 +1291,33 @@ static int virtio_mem_send_plug_request(struct virtio_mem *vm, uint64_t addr,
 		.u.plug.addr = cpu_to_virtio64(vm->vdev, addr),
 		.u.plug.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks),
 	};
+	int rc = -ENOMEM;
 
 	if (atomic_read(&vm->config_changed))
 		return -EAGAIN;
 
+	dev_dbg(&vm->vdev->dev, "plugging memory: 0x%llx - 0x%llx\n", addr,
+		addr + size - 1);
+
 	switch (virtio_mem_send_request(vm, &req)) {
 	case VIRTIO_MEM_RESP_ACK:
 		vm->plugged_size += size;
 		return 0;
 	case VIRTIO_MEM_RESP_NACK:
-		return -EAGAIN;
+		rc = -EAGAIN;
+		break;
 	case VIRTIO_MEM_RESP_BUSY:
-		return -ETXTBSY;
+		rc = -ETXTBSY;
+		break;
 	case VIRTIO_MEM_RESP_ERROR:
-		return -EINVAL;
+		rc = -EINVAL;
+		break;
 	default:
-		return -ENOMEM;
+		break;
 	}
+
+	dev_dbg(&vm->vdev->dev, "plugging memory failed: %d\n", rc);
+	return rc;
 }
 
 static int virtio_mem_send_unplug_request(struct virtio_mem *vm, uint64_t addr,
@@ -898,21 +1329,30 @@ static int virtio_mem_send_unplug_request(struct virtio_mem *vm, uint64_t addr,
 		.u.unplug.addr = cpu_to_virtio64(vm->vdev, addr),
 		.u.unplug.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks),
 	};
+	int rc = -ENOMEM;
 
 	if (atomic_read(&vm->config_changed))
 		return -EAGAIN;
 
+	dev_dbg(&vm->vdev->dev, "unplugging memory: 0x%llx - 0x%llx\n", addr,
+		addr + size - 1);
+
 	switch (virtio_mem_send_request(vm, &req)) {
 	case VIRTIO_MEM_RESP_ACK:
 		vm->plugged_size -= size;
 		return 0;
 	case VIRTIO_MEM_RESP_BUSY:
-		return -ETXTBSY;
+		rc = -ETXTBSY;
+		break;
 	case VIRTIO_MEM_RESP_ERROR:
-		return -EINVAL;
+		rc = -EINVAL;
+		break;
 	default:
-		return -ENOMEM;
+		break;
 	}
+
+	dev_dbg(&vm->vdev->dev, "unplugging memory failed: %d\n", rc);
+	return rc;
 }
 
 static int virtio_mem_send_unplug_all_request(struct virtio_mem *vm)
@@ -920,6 +1360,9 @@ static int virtio_mem_send_unplug_all_request(struct virtio_mem *vm)
 	const struct virtio_mem_req req = {
 		.type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_UNPLUG_ALL),
 	};
+	int rc = -ENOMEM;
+
+	dev_dbg(&vm->vdev->dev, "unplugging all memory");
 
 	switch (virtio_mem_send_request(vm, &req)) {
 	case VIRTIO_MEM_RESP_ACK:
@@ -929,30 +1372,31 @@ static int virtio_mem_send_unplug_all_request(struct virtio_mem *vm)
 		atomic_set(&vm->config_changed, 1);
 		return 0;
 	case VIRTIO_MEM_RESP_BUSY:
-		return -ETXTBSY;
+		rc = -ETXTBSY;
+		break;
 	default:
-		return -ENOMEM;
+		break;
 	}
+
+	dev_dbg(&vm->vdev->dev, "unplugging all memory failed: %d\n", rc);
+	return rc;
 }
 
 /*
  * Plug selected subblocks. Updates the plugged state, but not the state
  * of the memory block.
  */
-static int virtio_mem_mb_plug_sb(struct virtio_mem *vm, unsigned long mb_id,
-				 int sb_id, int count)
+static int virtio_mem_sbm_plug_sb(struct virtio_mem *vm, unsigned long mb_id,
+				  int sb_id, int count)
 {
 	const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id) +
-			      sb_id * vm->subblock_size;
-	const uint64_t size = count * vm->subblock_size;
+			      sb_id * vm->sbm.sb_size;
+	const uint64_t size = count * vm->sbm.sb_size;
 	int rc;
 
-	dev_dbg(&vm->vdev->dev, "plugging memory block: %lu : %i - %i\n", mb_id,
-		sb_id, sb_id + count - 1);
-
 	rc = virtio_mem_send_plug_request(vm, addr, size);
 	if (!rc)
-		virtio_mem_mb_set_sb_plugged(vm, mb_id, sb_id, count);
+		virtio_mem_sbm_set_sb_plugged(vm, mb_id, sb_id, count);
 	return rc;
 }
 
@@ -960,24 +1404,47 @@ static int virtio_mem_mb_plug_sb(struct virtio_mem *vm, unsigned long mb_id,
  * Unplug selected subblocks. Updates the plugged state, but not the state
  * of the memory block.
  */
-static int virtio_mem_mb_unplug_sb(struct virtio_mem *vm, unsigned long mb_id,
-				   int sb_id, int count)
+static int virtio_mem_sbm_unplug_sb(struct virtio_mem *vm, unsigned long mb_id,
+				    int sb_id, int count)
 {
 	const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id) +
-			      sb_id * vm->subblock_size;
-	const uint64_t size = count * vm->subblock_size;
+			      sb_id * vm->sbm.sb_size;
+	const uint64_t size = count * vm->sbm.sb_size;
 	int rc;
 
-	dev_dbg(&vm->vdev->dev, "unplugging memory block: %lu : %i - %i\n",
-		mb_id, sb_id, sb_id + count - 1);
-
 	rc = virtio_mem_send_unplug_request(vm, addr, size);
 	if (!rc)
-		virtio_mem_mb_set_sb_unplugged(vm, mb_id, sb_id, count);
+		virtio_mem_sbm_set_sb_unplugged(vm, mb_id, sb_id, count);
 	return rc;
 }
 
 /*
+ * Request to unplug a big block.
+ *
+ * Will not modify the state of the big block.
+ */
+static int virtio_mem_bbm_unplug_bb(struct virtio_mem *vm, unsigned long bb_id)
+{
+	const uint64_t addr = virtio_mem_bb_id_to_phys(vm, bb_id);
+	const uint64_t size = vm->bbm.bb_size;
+
+	return virtio_mem_send_unplug_request(vm, addr, size);
+}
+
+/*
+ * Request to plug a big block.
+ *
+ * Will not modify the state of the big block.
+ */
+static int virtio_mem_bbm_plug_bb(struct virtio_mem *vm, unsigned long bb_id)
+{
+	const uint64_t addr = virtio_mem_bb_id_to_phys(vm, bb_id);
+	const uint64_t size = vm->bbm.bb_size;
+
+	return virtio_mem_send_plug_request(vm, addr, size);
+}
+
+/*
  * Unplug the desired number of plugged subblocks of a offline or not-added
  * memory block. Will fail if any subblock cannot get unplugged (instead of
  * skipping it).
@@ -986,29 +1453,29 @@ static int virtio_mem_mb_unplug_sb(struct virtio_mem *vm, unsigned long mb_id,
  *
  * Note: can fail after some subblocks were unplugged.
  */
-static int virtio_mem_mb_unplug_any_sb(struct virtio_mem *vm,
-				       unsigned long mb_id, uint64_t *nb_sb)
+static int virtio_mem_sbm_unplug_any_sb(struct virtio_mem *vm,
+					unsigned long mb_id, uint64_t *nb_sb)
 {
 	int sb_id, count;
 	int rc;
 
-	sb_id = vm->nb_sb_per_mb - 1;
+	sb_id = vm->sbm.sbs_per_mb - 1;
 	while (*nb_sb) {
 		/* Find the next candidate subblock */
 		while (sb_id >= 0 &&
-		       virtio_mem_mb_test_sb_unplugged(vm, mb_id, sb_id, 1))
+		       virtio_mem_sbm_test_sb_unplugged(vm, mb_id, sb_id, 1))
 			sb_id--;
 		if (sb_id < 0)
 			break;
 		/* Try to unplug multiple subblocks at a time */
 		count = 1;
 		while (count < *nb_sb && sb_id > 0 &&
-		       virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id - 1, 1)) {
+		       virtio_mem_sbm_test_sb_plugged(vm, mb_id, sb_id - 1, 1)) {
 			count++;
 			sb_id--;
 		}
 
-		rc = virtio_mem_mb_unplug_sb(vm, mb_id, sb_id, count);
+		rc = virtio_mem_sbm_unplug_sb(vm, mb_id, sb_id, count);
 		if (rc)
 			return rc;
 		*nb_sb -= count;
@@ -1025,63 +1492,50 @@ static int virtio_mem_mb_unplug_any_sb(struct virtio_mem *vm,
  *
  * Note: can fail after some subblocks were unplugged.
  */
-static int virtio_mem_mb_unplug(struct virtio_mem *vm, unsigned long mb_id)
+static int virtio_mem_sbm_unplug_mb(struct virtio_mem *vm, unsigned long mb_id)
 {
-	uint64_t nb_sb = vm->nb_sb_per_mb;
+	uint64_t nb_sb = vm->sbm.sbs_per_mb;
 
-	return virtio_mem_mb_unplug_any_sb(vm, mb_id, &nb_sb);
+	return virtio_mem_sbm_unplug_any_sb(vm, mb_id, &nb_sb);
 }
 
 /*
  * Prepare tracking data for the next memory block.
  */
-static int virtio_mem_prepare_next_mb(struct virtio_mem *vm,
-				      unsigned long *mb_id)
+static int virtio_mem_sbm_prepare_next_mb(struct virtio_mem *vm,
+					  unsigned long *mb_id)
 {
 	int rc;
 
-	if (vm->next_mb_id > vm->last_usable_mb_id)
+	if (vm->sbm.next_mb_id > vm->sbm.last_usable_mb_id)
 		return -ENOSPC;
 
 	/* Resize the state array if required. */
-	rc = virtio_mem_mb_state_prepare_next_mb(vm);
+	rc = virtio_mem_sbm_mb_states_prepare_next_mb(vm);
 	if (rc)
 		return rc;
 
 	/* Resize the subblock bitmap if required. */
-	rc = virtio_mem_sb_bitmap_prepare_next_mb(vm);
+	rc = virtio_mem_sbm_sb_states_prepare_next_mb(vm);
 	if (rc)
 		return rc;
 
-	vm->nb_mb_state[VIRTIO_MEM_MB_STATE_UNUSED]++;
-	*mb_id = vm->next_mb_id++;
+	vm->sbm.mb_count[VIRTIO_MEM_SBM_MB_UNUSED]++;
+	*mb_id = vm->sbm.next_mb_id++;
 	return 0;
 }
 
 /*
- * Don't add too many blocks that are not onlined yet to avoid running OOM.
- */
-static bool virtio_mem_too_many_mb_offline(struct virtio_mem *vm)
-{
-	unsigned long nb_offline;
-
-	nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] +
-		     vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL];
-	return nb_offline >= VIRTIO_MEM_NB_OFFLINE_THRESHOLD;
-}
-
-/*
  * Try to plug the desired number of subblocks and add the memory block
  * to Linux.
  *
  * Will modify the state of the memory block.
  */
-static int virtio_mem_mb_plug_and_add(struct virtio_mem *vm,
-				      unsigned long mb_id,
-				      uint64_t *nb_sb)
+static int virtio_mem_sbm_plug_and_add_mb(struct virtio_mem *vm,
+					  unsigned long mb_id, uint64_t *nb_sb)
 {
-	const int count = min_t(int, *nb_sb, vm->nb_sb_per_mb);
-	int rc, rc2;
+	const int count = min_t(int, *nb_sb, vm->sbm.sbs_per_mb);
+	int rc;
 
 	if (WARN_ON_ONCE(!count))
 		return -EINVAL;
@@ -1090,7 +1544,7 @@ static int virtio_mem_mb_plug_and_add(struct virtio_mem *vm,
 	 * Plug the requested number of subblocks before adding it to linux,
 	 * so that onlining will directly online all plugged subblocks.
 	 */
-	rc = virtio_mem_mb_plug_sb(vm, mb_id, 0, count);
+	rc = virtio_mem_sbm_plug_sb(vm, mb_id, 0, count);
 	if (rc)
 		return rc;
 
@@ -1098,29 +1552,21 @@ static int virtio_mem_mb_plug_and_add(struct virtio_mem *vm,
 	 * Mark the block properly offline before adding it to Linux,
 	 * so the memory notifiers will find the block in the right state.
 	 */
-	if (count == vm->nb_sb_per_mb)
-		virtio_mem_mb_set_state(vm, mb_id,
-					VIRTIO_MEM_MB_STATE_OFFLINE);
+	if (count == vm->sbm.sbs_per_mb)
+		virtio_mem_sbm_set_mb_state(vm, mb_id,
+					    VIRTIO_MEM_SBM_MB_OFFLINE);
 	else
-		virtio_mem_mb_set_state(vm, mb_id,
-					VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL);
+		virtio_mem_sbm_set_mb_state(vm, mb_id,
+					    VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL);
 
 	/* Add the memory block to linux - if that fails, try to unplug. */
-	rc = virtio_mem_mb_add(vm, mb_id);
+	rc = virtio_mem_sbm_add_mb(vm, mb_id);
 	if (rc) {
-		enum virtio_mem_mb_state new_state = VIRTIO_MEM_MB_STATE_UNUSED;
+		int new_state = VIRTIO_MEM_SBM_MB_UNUSED;
 
-		dev_err(&vm->vdev->dev,
-			"adding memory block %lu failed with %d\n", mb_id, rc);
-		rc2 = virtio_mem_mb_unplug_sb(vm, mb_id, 0, count);
-
-		/*
-		 * TODO: Linux MM does not properly clean up yet in all cases
-		 * where adding of memory failed - especially on -ENOMEM.
-		 */
-		if (rc2)
-			new_state = VIRTIO_MEM_MB_STATE_PLUGGED;
-		virtio_mem_mb_set_state(vm, mb_id, new_state);
+		if (virtio_mem_sbm_unplug_sb(vm, mb_id, 0, count))
+			new_state = VIRTIO_MEM_SBM_MB_PLUGGED;
+		virtio_mem_sbm_set_mb_state(vm, mb_id, new_state);
 		return rc;
 	}
 
@@ -1136,8 +1582,9 @@ static int virtio_mem_mb_plug_and_add(struct virtio_mem *vm,
  *
  * Note: Can fail after some subblocks were successfully plugged.
  */
-static int virtio_mem_mb_plug_any_sb(struct virtio_mem *vm, unsigned long mb_id,
-				     uint64_t *nb_sb, bool online)
+static int virtio_mem_sbm_plug_any_sb(struct virtio_mem *vm,
+				      unsigned long mb_id, uint64_t *nb_sb,
+				      bool online)
 {
 	unsigned long pfn, nr_pages;
 	int sb_id, count;
@@ -1147,17 +1594,16 @@ static int virtio_mem_mb_plug_any_sb(struct virtio_mem *vm, unsigned long mb_id,
 		return -EINVAL;
 
 	while (*nb_sb) {
-		sb_id = virtio_mem_mb_first_unplugged_sb(vm, mb_id);
-		if (sb_id >= vm->nb_sb_per_mb)
+		sb_id = virtio_mem_sbm_first_unplugged_sb(vm, mb_id);
+		if (sb_id >= vm->sbm.sbs_per_mb)
 			break;
 		count = 1;
 		while (count < *nb_sb &&
-		       sb_id + count < vm->nb_sb_per_mb &&
-		       !virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id + count,
-						      1))
+		       sb_id + count < vm->sbm.sbs_per_mb &&
+		       !virtio_mem_sbm_test_sb_plugged(vm, mb_id, sb_id + count, 1))
 			count++;
 
-		rc = virtio_mem_mb_plug_sb(vm, mb_id, sb_id, count);
+		rc = virtio_mem_sbm_plug_sb(vm, mb_id, sb_id, count);
 		if (rc)
 			return rc;
 		*nb_sb -= count;
@@ -1166,29 +1612,26 @@ static int virtio_mem_mb_plug_any_sb(struct virtio_mem *vm, unsigned long mb_id,
 
 		/* fake-online the pages if the memory block is online */
 		pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
-			       sb_id * vm->subblock_size);
-		nr_pages = PFN_DOWN(count * vm->subblock_size);
+			       sb_id * vm->sbm.sb_size);
+		nr_pages = PFN_DOWN(count * vm->sbm.sb_size);
 		virtio_mem_fake_online(pfn, nr_pages);
 	}
 
-	if (virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb)) {
+	if (virtio_mem_sbm_test_sb_plugged(vm, mb_id, 0, vm->sbm.sbs_per_mb)) {
 		if (online)
-			virtio_mem_mb_set_state(vm, mb_id,
-						VIRTIO_MEM_MB_STATE_ONLINE);
+			virtio_mem_sbm_set_mb_state(vm, mb_id,
+						    VIRTIO_MEM_SBM_MB_ONLINE);
 		else
-			virtio_mem_mb_set_state(vm, mb_id,
-						VIRTIO_MEM_MB_STATE_OFFLINE);
+			virtio_mem_sbm_set_mb_state(vm, mb_id,
+						    VIRTIO_MEM_SBM_MB_OFFLINE);
 	}
 
 	return 0;
 }
 
-/*
- * Try to plug the requested amount of memory.
- */
-static int virtio_mem_plug_request(struct virtio_mem *vm, uint64_t diff)
+static int virtio_mem_sbm_plug_request(struct virtio_mem *vm, uint64_t diff)
 {
-	uint64_t nb_sb = diff / vm->subblock_size;
+	uint64_t nb_sb = diff / vm->sbm.sb_size;
 	unsigned long mb_id;
 	int rc;
 
@@ -1199,18 +1642,18 @@ static int virtio_mem_plug_request(struct virtio_mem *vm, uint64_t diff)
 	mutex_lock(&vm->hotplug_mutex);
 
 	/* Try to plug subblocks of partially plugged online blocks. */
-	virtio_mem_for_each_mb_state(vm, mb_id,
-				     VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL) {
-		rc = virtio_mem_mb_plug_any_sb(vm, mb_id, &nb_sb, true);
+	virtio_mem_sbm_for_each_mb(vm, mb_id,
+				   VIRTIO_MEM_SBM_MB_ONLINE_PARTIAL) {
+		rc = virtio_mem_sbm_plug_any_sb(vm, mb_id, &nb_sb, true);
 		if (rc || !nb_sb)
 			goto out_unlock;
 		cond_resched();
 	}
 
 	/* Try to plug subblocks of partially plugged offline blocks. */
-	virtio_mem_for_each_mb_state(vm, mb_id,
-				     VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) {
-		rc = virtio_mem_mb_plug_any_sb(vm, mb_id, &nb_sb, false);
+	virtio_mem_sbm_for_each_mb(vm, mb_id,
+				   VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL) {
+		rc = virtio_mem_sbm_plug_any_sb(vm, mb_id, &nb_sb, false);
 		if (rc || !nb_sb)
 			goto out_unlock;
 		cond_resched();
@@ -1223,11 +1666,11 @@ static int virtio_mem_plug_request(struct virtio_mem *vm, uint64_t diff)
 	mutex_unlock(&vm->hotplug_mutex);
 
 	/* Try to plug and add unused blocks */
-	virtio_mem_for_each_mb_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED) {
-		if (virtio_mem_too_many_mb_offline(vm))
+	virtio_mem_sbm_for_each_mb(vm, mb_id, VIRTIO_MEM_SBM_MB_UNUSED) {
+		if (!virtio_mem_could_add_memory(vm, memory_block_size_bytes()))
 			return -ENOSPC;
 
-		rc = virtio_mem_mb_plug_and_add(vm, mb_id, &nb_sb);
+		rc = virtio_mem_sbm_plug_and_add_mb(vm, mb_id, &nb_sb);
 		if (rc || !nb_sb)
 			return rc;
 		cond_resched();
@@ -1235,13 +1678,13 @@ static int virtio_mem_plug_request(struct virtio_mem *vm, uint64_t diff)
 
 	/* Try to prepare, plug and add new blocks */
 	while (nb_sb) {
-		if (virtio_mem_too_many_mb_offline(vm))
+		if (!virtio_mem_could_add_memory(vm, memory_block_size_bytes()))
 			return -ENOSPC;
 
-		rc = virtio_mem_prepare_next_mb(vm, &mb_id);
+		rc = virtio_mem_sbm_prepare_next_mb(vm, &mb_id);
 		if (rc)
 			return rc;
-		rc = virtio_mem_mb_plug_and_add(vm, mb_id, &nb_sb);
+		rc = virtio_mem_sbm_plug_and_add_mb(vm, mb_id, &nb_sb);
 		if (rc)
 			return rc;
 		cond_resched();
@@ -1254,6 +1697,112 @@ out_unlock:
 }
 
 /*
+ * Plug a big block and add it to Linux.
+ *
+ * Will modify the state of the big block.
+ */
+static int virtio_mem_bbm_plug_and_add_bb(struct virtio_mem *vm,
+					  unsigned long bb_id)
+{
+	int rc;
+
+	if (WARN_ON_ONCE(virtio_mem_bbm_get_bb_state(vm, bb_id) !=
+			 VIRTIO_MEM_BBM_BB_UNUSED))
+		return -EINVAL;
+
+	rc = virtio_mem_bbm_plug_bb(vm, bb_id);
+	if (rc)
+		return rc;
+	virtio_mem_bbm_set_bb_state(vm, bb_id, VIRTIO_MEM_BBM_BB_ADDED);
+
+	rc = virtio_mem_bbm_add_bb(vm, bb_id);
+	if (rc) {
+		if (!virtio_mem_bbm_unplug_bb(vm, bb_id))
+			virtio_mem_bbm_set_bb_state(vm, bb_id,
+						    VIRTIO_MEM_BBM_BB_UNUSED);
+		else
+			/* Retry from the main loop. */
+			virtio_mem_bbm_set_bb_state(vm, bb_id,
+						    VIRTIO_MEM_BBM_BB_PLUGGED);
+		return rc;
+	}
+	return 0;
+}
+
+/*
+ * Prepare tracking data for the next big block.
+ */
+static int virtio_mem_bbm_prepare_next_bb(struct virtio_mem *vm,
+					  unsigned long *bb_id)
+{
+	int rc;
+
+	if (vm->bbm.next_bb_id > vm->bbm.last_usable_bb_id)
+		return -ENOSPC;
+
+	/* Resize the big block state array if required. */
+	rc = virtio_mem_bbm_bb_states_prepare_next_bb(vm);
+	if (rc)
+		return rc;
+
+	vm->bbm.bb_count[VIRTIO_MEM_BBM_BB_UNUSED]++;
+	*bb_id = vm->bbm.next_bb_id;
+	vm->bbm.next_bb_id++;
+	return 0;
+}
+
+static int virtio_mem_bbm_plug_request(struct virtio_mem *vm, uint64_t diff)
+{
+	uint64_t nb_bb = diff / vm->bbm.bb_size;
+	unsigned long bb_id;
+	int rc;
+
+	if (!nb_bb)
+		return 0;
+
+	/* Try to plug and add unused big blocks */
+	virtio_mem_bbm_for_each_bb(vm, bb_id, VIRTIO_MEM_BBM_BB_UNUSED) {
+		if (!virtio_mem_could_add_memory(vm, vm->bbm.bb_size))
+			return -ENOSPC;
+
+		rc = virtio_mem_bbm_plug_and_add_bb(vm, bb_id);
+		if (!rc)
+			nb_bb--;
+		if (rc || !nb_bb)
+			return rc;
+		cond_resched();
+	}
+
+	/* Try to prepare, plug and add new big blocks */
+	while (nb_bb) {
+		if (!virtio_mem_could_add_memory(vm, vm->bbm.bb_size))
+			return -ENOSPC;
+
+		rc = virtio_mem_bbm_prepare_next_bb(vm, &bb_id);
+		if (rc)
+			return rc;
+		rc = virtio_mem_bbm_plug_and_add_bb(vm, bb_id);
+		if (!rc)
+			nb_bb--;
+		if (rc)
+			return rc;
+		cond_resched();
+	}
+
+	return 0;
+}
+
+/*
+ * Try to plug the requested amount of memory.
+ */
+static int virtio_mem_plug_request(struct virtio_mem *vm, uint64_t diff)
+{
+	if (vm->in_sbm)
+		return virtio_mem_sbm_plug_request(vm, diff);
+	return virtio_mem_bbm_plug_request(vm, diff);
+}
+
+/*
  * Unplug the desired number of plugged subblocks of an offline memory block.
  * Will fail if any subblock cannot get unplugged (instead of skipping it).
  *
@@ -1262,33 +1811,33 @@ out_unlock:
  *
  * Note: Can fail after some subblocks were successfully unplugged.
  */
-static int virtio_mem_mb_unplug_any_sb_offline(struct virtio_mem *vm,
-					       unsigned long mb_id,
-					       uint64_t *nb_sb)
+static int virtio_mem_sbm_unplug_any_sb_offline(struct virtio_mem *vm,
+						unsigned long mb_id,
+						uint64_t *nb_sb)
 {
 	int rc;
 
-	rc = virtio_mem_mb_unplug_any_sb(vm, mb_id, nb_sb);
+	rc = virtio_mem_sbm_unplug_any_sb(vm, mb_id, nb_sb);
 
 	/* some subblocks might have been unplugged even on failure */
-	if (!virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb))
-		virtio_mem_mb_set_state(vm, mb_id,
-					VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL);
+	if (!virtio_mem_sbm_test_sb_plugged(vm, mb_id, 0, vm->sbm.sbs_per_mb))
+		virtio_mem_sbm_set_mb_state(vm, mb_id,
+					    VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL);
 	if (rc)
 		return rc;
 
-	if (virtio_mem_mb_test_sb_unplugged(vm, mb_id, 0, vm->nb_sb_per_mb)) {
+	if (virtio_mem_sbm_test_sb_unplugged(vm, mb_id, 0, vm->sbm.sbs_per_mb)) {
 		/*
 		 * Remove the block from Linux - this should never fail.
 		 * Hinder the block from getting onlined by marking it
 		 * unplugged. Temporarily drop the mutex, so
 		 * any pending GOING_ONLINE requests can be serviced/rejected.
 		 */
-		virtio_mem_mb_set_state(vm, mb_id,
-					VIRTIO_MEM_MB_STATE_UNUSED);
+		virtio_mem_sbm_set_mb_state(vm, mb_id,
+					    VIRTIO_MEM_SBM_MB_UNUSED);
 
 		mutex_unlock(&vm->hotplug_mutex);
-		rc = virtio_mem_mb_remove(vm, mb_id);
+		rc = virtio_mem_sbm_remove_mb(vm, mb_id);
 		BUG_ON(rc);
 		mutex_lock(&vm->hotplug_mutex);
 	}
@@ -1300,38 +1849,31 @@ static int virtio_mem_mb_unplug_any_sb_offline(struct virtio_mem *vm,
  *
  * Will modify the state of the memory block.
  */
-static int virtio_mem_mb_unplug_sb_online(struct virtio_mem *vm,
-					  unsigned long mb_id, int sb_id,
-					  int count)
+static int virtio_mem_sbm_unplug_sb_online(struct virtio_mem *vm,
+					   unsigned long mb_id, int sb_id,
+					   int count)
 {
-	const unsigned long nr_pages = PFN_DOWN(vm->subblock_size) * count;
+	const unsigned long nr_pages = PFN_DOWN(vm->sbm.sb_size) * count;
 	unsigned long start_pfn;
 	int rc;
 
 	start_pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
-			     sb_id * vm->subblock_size);
-	rc = alloc_contig_range(start_pfn, start_pfn + nr_pages,
-				MIGRATE_MOVABLE, GFP_KERNEL);
-	if (rc == -ENOMEM)
-		/* whoops, out of memory */
-		return rc;
-	if (rc)
-		return -EBUSY;
+			     sb_id * vm->sbm.sb_size);
 
-	/* Mark it as fake-offline before unplugging it */
-	virtio_mem_set_fake_offline(start_pfn, nr_pages, true);
-	adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages);
+	rc = virtio_mem_fake_offline(start_pfn, nr_pages);
+	if (rc)
+		return rc;
 
 	/* Try to unplug the allocated memory */
-	rc = virtio_mem_mb_unplug_sb(vm, mb_id, sb_id, count);
+	rc = virtio_mem_sbm_unplug_sb(vm, mb_id, sb_id, count);
 	if (rc) {
 		/* Return the memory to the buddy. */
 		virtio_mem_fake_online(start_pfn, nr_pages);
 		return rc;
 	}
 
-	virtio_mem_mb_set_state(vm, mb_id,
-				VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL);
+	virtio_mem_sbm_set_mb_state(vm, mb_id,
+				    VIRTIO_MEM_SBM_MB_ONLINE_PARTIAL);
 	return 0;
 }
 
@@ -1345,34 +1887,34 @@ static int virtio_mem_mb_unplug_sb_online(struct virtio_mem *vm,
  * Note: Can fail after some subblocks were successfully unplugged. Can
  *       return 0 even if subblocks were busy and could not get unplugged.
  */
-static int virtio_mem_mb_unplug_any_sb_online(struct virtio_mem *vm,
-					      unsigned long mb_id,
-					      uint64_t *nb_sb)
+static int virtio_mem_sbm_unplug_any_sb_online(struct virtio_mem *vm,
+					       unsigned long mb_id,
+					       uint64_t *nb_sb)
 {
 	int rc, sb_id;
 
 	/* If possible, try to unplug the complete block in one shot. */
-	if (*nb_sb >= vm->nb_sb_per_mb &&
-	    virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb)) {
-		rc = virtio_mem_mb_unplug_sb_online(vm, mb_id, 0,
-						    vm->nb_sb_per_mb);
+	if (*nb_sb >= vm->sbm.sbs_per_mb &&
+	    virtio_mem_sbm_test_sb_plugged(vm, mb_id, 0, vm->sbm.sbs_per_mb)) {
+		rc = virtio_mem_sbm_unplug_sb_online(vm, mb_id, 0,
+						     vm->sbm.sbs_per_mb);
 		if (!rc) {
-			*nb_sb -= vm->nb_sb_per_mb;
+			*nb_sb -= vm->sbm.sbs_per_mb;
 			goto unplugged;
 		} else if (rc != -EBUSY)
 			return rc;
 	}
 
 	/* Fallback to single subblocks. */
-	for (sb_id = vm->nb_sb_per_mb - 1; sb_id >= 0 && *nb_sb; sb_id--) {
+	for (sb_id = vm->sbm.sbs_per_mb - 1; sb_id >= 0 && *nb_sb; sb_id--) {
 		/* Find the next candidate subblock */
 		while (sb_id >= 0 &&
-		       !virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+		       !virtio_mem_sbm_test_sb_plugged(vm, mb_id, sb_id, 1))
 			sb_id--;
 		if (sb_id < 0)
 			break;
 
-		rc = virtio_mem_mb_unplug_sb_online(vm, mb_id, sb_id, 1);
+		rc = virtio_mem_sbm_unplug_sb_online(vm, mb_id, sb_id, 1);
 		if (rc == -EBUSY)
 			continue;
 		else if (rc)
@@ -1386,24 +1928,21 @@ unplugged:
 	 * remove it. This will usually not fail, as no memory is in use
 	 * anymore - however some other notifiers might NACK the request.
 	 */
-	if (virtio_mem_mb_test_sb_unplugged(vm, mb_id, 0, vm->nb_sb_per_mb)) {
+	if (virtio_mem_sbm_test_sb_unplugged(vm, mb_id, 0, vm->sbm.sbs_per_mb)) {
 		mutex_unlock(&vm->hotplug_mutex);
-		rc = virtio_mem_mb_offline_and_remove(vm, mb_id);
+		rc = virtio_mem_sbm_offline_and_remove_mb(vm, mb_id);
 		mutex_lock(&vm->hotplug_mutex);
 		if (!rc)
-			virtio_mem_mb_set_state(vm, mb_id,
-						VIRTIO_MEM_MB_STATE_UNUSED);
+			virtio_mem_sbm_set_mb_state(vm, mb_id,
+						    VIRTIO_MEM_SBM_MB_UNUSED);
 	}
 
 	return 0;
 }
 
-/*
- * Try to unplug the requested amount of memory.
- */
-static int virtio_mem_unplug_request(struct virtio_mem *vm, uint64_t diff)
+static int virtio_mem_sbm_unplug_request(struct virtio_mem *vm, uint64_t diff)
 {
-	uint64_t nb_sb = diff / vm->subblock_size;
+	uint64_t nb_sb = diff / vm->sbm.sb_size;
 	unsigned long mb_id;
 	int rc;
 
@@ -1418,20 +1957,17 @@ static int virtio_mem_unplug_request(struct virtio_mem *vm, uint64_t diff)
 	mutex_lock(&vm->hotplug_mutex);
 
 	/* Try to unplug subblocks of partially plugged offline blocks. */
-	virtio_mem_for_each_mb_state_rev(vm, mb_id,
-					 VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) {
-		rc = virtio_mem_mb_unplug_any_sb_offline(vm, mb_id,
-							 &nb_sb);
+	virtio_mem_sbm_for_each_mb_rev(vm, mb_id,
+				       VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL) {
+		rc = virtio_mem_sbm_unplug_any_sb_offline(vm, mb_id, &nb_sb);
 		if (rc || !nb_sb)
 			goto out_unlock;
 		cond_resched();
 	}
 
 	/* Try to unplug subblocks of plugged offline blocks. */
-	virtio_mem_for_each_mb_state_rev(vm, mb_id,
-					 VIRTIO_MEM_MB_STATE_OFFLINE) {
-		rc = virtio_mem_mb_unplug_any_sb_offline(vm, mb_id,
-							 &nb_sb);
+	virtio_mem_sbm_for_each_mb_rev(vm, mb_id, VIRTIO_MEM_SBM_MB_OFFLINE) {
+		rc = virtio_mem_sbm_unplug_any_sb_offline(vm, mb_id, &nb_sb);
 		if (rc || !nb_sb)
 			goto out_unlock;
 		cond_resched();
@@ -1443,10 +1979,9 @@ static int virtio_mem_unplug_request(struct virtio_mem *vm, uint64_t diff)
 	}
 
 	/* Try to unplug subblocks of partially plugged online blocks. */
-	virtio_mem_for_each_mb_state_rev(vm, mb_id,
-					 VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL) {
-		rc = virtio_mem_mb_unplug_any_sb_online(vm, mb_id,
-							&nb_sb);
+	virtio_mem_sbm_for_each_mb_rev(vm, mb_id,
+				       VIRTIO_MEM_SBM_MB_ONLINE_PARTIAL) {
+		rc = virtio_mem_sbm_unplug_any_sb_online(vm, mb_id, &nb_sb);
 		if (rc || !nb_sb)
 			goto out_unlock;
 		mutex_unlock(&vm->hotplug_mutex);
@@ -1455,10 +1990,8 @@ static int virtio_mem_unplug_request(struct virtio_mem *vm, uint64_t diff)
 	}
 
 	/* Try to unplug subblocks of plugged online blocks. */
-	virtio_mem_for_each_mb_state_rev(vm, mb_id,
-					 VIRTIO_MEM_MB_STATE_ONLINE) {
-		rc = virtio_mem_mb_unplug_any_sb_online(vm, mb_id,
-							&nb_sb);
+	virtio_mem_sbm_for_each_mb_rev(vm, mb_id, VIRTIO_MEM_SBM_MB_ONLINE) {
+		rc = virtio_mem_sbm_unplug_any_sb_online(vm, mb_id, &nb_sb);
 		if (rc || !nb_sb)
 			goto out_unlock;
 		mutex_unlock(&vm->hotplug_mutex);
@@ -1474,19 +2007,211 @@ out_unlock:
 }
 
 /*
+ * Try to offline and remove a big block from Linux and unplug it. Will fail
+ * with -EBUSY if some memory is busy and cannot get unplugged.
+ *
+ * Will modify the state of the memory block. Might temporarily drop the
+ * hotplug_mutex.
+ */
+static int virtio_mem_bbm_offline_remove_and_unplug_bb(struct virtio_mem *vm,
+						       unsigned long bb_id)
+{
+	const unsigned long start_pfn = PFN_DOWN(virtio_mem_bb_id_to_phys(vm, bb_id));
+	const unsigned long nr_pages = PFN_DOWN(vm->bbm.bb_size);
+	unsigned long end_pfn = start_pfn + nr_pages;
+	unsigned long pfn;
+	struct page *page;
+	int rc;
+
+	if (WARN_ON_ONCE(virtio_mem_bbm_get_bb_state(vm, bb_id) !=
+			 VIRTIO_MEM_BBM_BB_ADDED))
+		return -EINVAL;
+
+	if (bbm_safe_unplug) {
+		/*
+		 * Start by fake-offlining all memory. Once we marked the device
+		 * block as fake-offline, all newly onlined memory will
+		 * automatically be kept fake-offline. Protect from concurrent
+		 * onlining/offlining until we have a consistent state.
+		 */
+		mutex_lock(&vm->hotplug_mutex);
+		virtio_mem_bbm_set_bb_state(vm, bb_id,
+					    VIRTIO_MEM_BBM_BB_FAKE_OFFLINE);
+
+		for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+			page = pfn_to_online_page(pfn);
+			if (!page)
+				continue;
+
+			rc = virtio_mem_fake_offline(pfn, PAGES_PER_SECTION);
+			if (rc) {
+				end_pfn = pfn;
+				goto rollback_safe_unplug;
+			}
+		}
+		mutex_unlock(&vm->hotplug_mutex);
+	}
+
+	rc = virtio_mem_bbm_offline_and_remove_bb(vm, bb_id);
+	if (rc) {
+		if (bbm_safe_unplug) {
+			mutex_lock(&vm->hotplug_mutex);
+			goto rollback_safe_unplug;
+		}
+		return rc;
+	}
+
+	rc = virtio_mem_bbm_unplug_bb(vm, bb_id);
+	if (rc)
+		virtio_mem_bbm_set_bb_state(vm, bb_id,
+					    VIRTIO_MEM_BBM_BB_PLUGGED);
+	else
+		virtio_mem_bbm_set_bb_state(vm, bb_id,
+					    VIRTIO_MEM_BBM_BB_UNUSED);
+	return rc;
+
+rollback_safe_unplug:
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		page = pfn_to_online_page(pfn);
+		if (!page)
+			continue;
+		virtio_mem_fake_online(pfn, PAGES_PER_SECTION);
+	}
+	virtio_mem_bbm_set_bb_state(vm, bb_id, VIRTIO_MEM_BBM_BB_ADDED);
+	mutex_unlock(&vm->hotplug_mutex);
+	return rc;
+}
+
+/*
+ * Try to remove a big block from Linux and unplug it. Will fail with
+ * -EBUSY if some memory is online.
+ *
+ * Will modify the state of the memory block.
+ */
+static int virtio_mem_bbm_remove_and_unplug_bb(struct virtio_mem *vm,
+					       unsigned long bb_id)
+{
+	int rc;
+
+	if (WARN_ON_ONCE(virtio_mem_bbm_get_bb_state(vm, bb_id) !=
+			 VIRTIO_MEM_BBM_BB_ADDED))
+		return -EINVAL;
+
+	rc = virtio_mem_bbm_remove_bb(vm, bb_id);
+	if (rc)
+		return -EBUSY;
+
+	rc = virtio_mem_bbm_unplug_bb(vm, bb_id);
+	if (rc)
+		virtio_mem_bbm_set_bb_state(vm, bb_id,
+					    VIRTIO_MEM_BBM_BB_PLUGGED);
+	else
+		virtio_mem_bbm_set_bb_state(vm, bb_id,
+					    VIRTIO_MEM_BBM_BB_UNUSED);
+	return rc;
+}
+
+/*
+ * Test if a big block is completely offline.
+ */
+static bool virtio_mem_bbm_bb_is_offline(struct virtio_mem *vm,
+					 unsigned long bb_id)
+{
+	const unsigned long start_pfn = PFN_DOWN(virtio_mem_bb_id_to_phys(vm, bb_id));
+	const unsigned long nr_pages = PFN_DOWN(vm->bbm.bb_size);
+	unsigned long pfn;
+
+	for (pfn = start_pfn; pfn < start_pfn + nr_pages;
+	     pfn += PAGES_PER_SECTION) {
+		if (pfn_to_online_page(pfn))
+			return false;
+	}
+
+	return true;
+}
+
+static int virtio_mem_bbm_unplug_request(struct virtio_mem *vm, uint64_t diff)
+{
+	uint64_t nb_bb = diff / vm->bbm.bb_size;
+	uint64_t bb_id;
+	int rc;
+
+	if (!nb_bb)
+		return 0;
+
+	/* Try to unplug completely offline big blocks first. */
+	virtio_mem_bbm_for_each_bb_rev(vm, bb_id, VIRTIO_MEM_BBM_BB_ADDED) {
+		cond_resched();
+		/*
+		 * As we're holding no locks, this check is racy as memory
+		 * can get onlined in the meantime - but we'll fail gracefully.
+		 */
+		if (!virtio_mem_bbm_bb_is_offline(vm, bb_id))
+			continue;
+		rc = virtio_mem_bbm_remove_and_unplug_bb(vm, bb_id);
+		if (rc == -EBUSY)
+			continue;
+		if (!rc)
+			nb_bb--;
+		if (rc || !nb_bb)
+			return rc;
+	}
+
+	if (!unplug_online)
+		return 0;
+
+	/* Try to unplug any big blocks. */
+	virtio_mem_bbm_for_each_bb_rev(vm, bb_id, VIRTIO_MEM_BBM_BB_ADDED) {
+		cond_resched();
+		rc = virtio_mem_bbm_offline_remove_and_unplug_bb(vm, bb_id);
+		if (rc == -EBUSY)
+			continue;
+		if (!rc)
+			nb_bb--;
+		if (rc || !nb_bb)
+			return rc;
+	}
+
+	return nb_bb ? -EBUSY : 0;
+}
+
+/*
+ * Try to unplug the requested amount of memory.
+ */
+static int virtio_mem_unplug_request(struct virtio_mem *vm, uint64_t diff)
+{
+	if (vm->in_sbm)
+		return virtio_mem_sbm_unplug_request(vm, diff);
+	return virtio_mem_bbm_unplug_request(vm, diff);
+}
+
+/*
  * Try to unplug all blocks that couldn't be unplugged before, for example,
  * because the hypervisor was busy.
  */
 static int virtio_mem_unplug_pending_mb(struct virtio_mem *vm)
 {
-	unsigned long mb_id;
+	unsigned long id;
 	int rc;
 
-	virtio_mem_for_each_mb_state(vm, mb_id, VIRTIO_MEM_MB_STATE_PLUGGED) {
-		rc = virtio_mem_mb_unplug(vm, mb_id);
+	if (!vm->in_sbm) {
+		virtio_mem_bbm_for_each_bb(vm, id,
+					   VIRTIO_MEM_BBM_BB_PLUGGED) {
+			rc = virtio_mem_bbm_unplug_bb(vm, id);
+			if (rc)
+				return rc;
+			virtio_mem_bbm_set_bb_state(vm, id,
+						    VIRTIO_MEM_BBM_BB_UNUSED);
+		}
+		return 0;
+	}
+
+	virtio_mem_sbm_for_each_mb(vm, id, VIRTIO_MEM_SBM_MB_PLUGGED) {
+		rc = virtio_mem_sbm_unplug_mb(vm, id);
 		if (rc)
 			return rc;
-		virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED);
+		virtio_mem_sbm_set_mb_state(vm, id,
+					    VIRTIO_MEM_SBM_MB_UNUSED);
 	}
 
 	return 0;
@@ -1511,7 +2236,13 @@ static void virtio_mem_refresh_config(struct virtio_mem *vm)
 			usable_region_size, &usable_region_size);
 	end_addr = vm->addr + usable_region_size;
 	end_addr = min(end_addr, phys_limit);
-	vm->last_usable_mb_id = virtio_mem_phys_to_mb_id(end_addr) - 1;
+
+	if (vm->in_sbm)
+		vm->sbm.last_usable_mb_id =
+					 virtio_mem_phys_to_mb_id(end_addr) - 1;
+	else
+		vm->bbm.last_usable_bb_id =
+				     virtio_mem_phys_to_bb_id(vm, end_addr) - 1;
 
 	/* see if there is a request to change the size */
 	virtio_cread_le(vm->vdev, struct virtio_mem_config, requested_size,
@@ -1535,6 +2266,7 @@ static void virtio_mem_run_wq(struct work_struct *work)
 	if (vm->broken)
 		return;
 
+	atomic_set(&vm->wq_active, 1);
 retry:
 	rc = 0;
 
@@ -1595,6 +2327,8 @@ retry:
 			"unknown error, marking device broken: %d\n", rc);
 		vm->broken = true;
 	}
+
+	atomic_set(&vm->wq_active, 0);
 }
 
 static enum hrtimer_restart virtio_mem_timer_expired(struct hrtimer *timer)
@@ -1631,6 +2365,7 @@ static int virtio_mem_init_vq(struct virtio_mem *vm)
 static int virtio_mem_init(struct virtio_mem *vm)
 {
 	const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS;
+	uint64_t sb_size, addr;
 	uint16_t node_id;
 
 	if (!vm->vdev->config->get) {
@@ -1659,15 +2394,9 @@ static int virtio_mem_init(struct virtio_mem *vm)
 	virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size,
 			&vm->region_size);
 
-	/*
-	 * We always hotplug memory in memory block granularity. This way,
-	 * we have to wait for exactly one memory block to online.
-	 */
-	if (vm->device_block_size > memory_block_size_bytes()) {
-		dev_err(&vm->vdev->dev,
-			"The block size is not supported (too big).\n");
-		return -EINVAL;
-	}
+	/* Determine the nid for the device based on the lowest address. */
+	if (vm->nid == NUMA_NO_NODE)
+		vm->nid = memory_add_physaddr_to_nid(vm->addr);
 
 	/* bad device setup - warn only */
 	if (!IS_ALIGNED(vm->addr, memory_block_size_bytes()))
@@ -1681,23 +2410,57 @@ static int virtio_mem_init(struct virtio_mem *vm)
 			 "Some memory is not addressable. This can make some memory unusable.\n");
 
 	/*
-	 * Calculate the subblock size:
-	 * - At least MAX_ORDER - 1 / pageblock_order.
-	 * - At least the device block size.
-	 * In the worst case, a single subblock per memory block.
+	 * We want subblocks to span at least MAX_ORDER_NR_PAGES and
+	 * pageblock_nr_pages pages. This:
+	 * - Simplifies our page onlining code (virtio_mem_online_page_cb)
+	 *   and fake page onlining code (virtio_mem_fake_online).
+	 * - Is required for now for alloc_contig_range() to work reliably -
+	 *   it doesn't properly handle smaller granularity on ZONE_NORMAL.
 	 */
-	vm->subblock_size = PAGE_SIZE * 1ul << max_t(uint32_t, MAX_ORDER - 1,
-						     pageblock_order);
-	vm->subblock_size = max_t(uint64_t, vm->device_block_size,
-				  vm->subblock_size);
-	vm->nb_sb_per_mb = memory_block_size_bytes() / vm->subblock_size;
-
-	/* Round up to the next full memory block */
-	vm->first_mb_id = virtio_mem_phys_to_mb_id(vm->addr - 1 +
-						   memory_block_size_bytes());
-	vm->next_mb_id = vm->first_mb_id;
-	vm->last_mb_id = virtio_mem_phys_to_mb_id(vm->addr +
-			 vm->region_size) - 1;
+	sb_size = max_t(uint64_t, MAX_ORDER_NR_PAGES,
+			pageblock_nr_pages) * PAGE_SIZE;
+	sb_size = max_t(uint64_t, vm->device_block_size, sb_size);
+
+	if (sb_size < memory_block_size_bytes() && !force_bbm) {
+		/* SBM: At least two subblocks per Linux memory block. */
+		vm->in_sbm = true;
+		vm->sbm.sb_size = sb_size;
+		vm->sbm.sbs_per_mb = memory_block_size_bytes() /
+				     vm->sbm.sb_size;
+
+		/* Round up to the next full memory block */
+		addr = vm->addr + memory_block_size_bytes() - 1;
+		vm->sbm.first_mb_id = virtio_mem_phys_to_mb_id(addr);
+		vm->sbm.next_mb_id = vm->sbm.first_mb_id;
+	} else {
+		/* BBM: At least one Linux memory block. */
+		vm->bbm.bb_size = max_t(uint64_t, vm->device_block_size,
+					memory_block_size_bytes());
+
+		if (bbm_block_size) {
+			if (!is_power_of_2(bbm_block_size)) {
+				dev_warn(&vm->vdev->dev,
+					 "bbm_block_size is not a power of 2");
+			} else if (bbm_block_size < vm->bbm.bb_size) {
+				dev_warn(&vm->vdev->dev,
+					 "bbm_block_size is too small");
+			} else {
+				vm->bbm.bb_size = bbm_block_size;
+			}
+		}
+
+		/* Round up to the next aligned big block */
+		addr = vm->addr + vm->bbm.bb_size - 1;
+		vm->bbm.first_bb_id = virtio_mem_phys_to_bb_id(vm, addr);
+		vm->bbm.next_bb_id = vm->bbm.first_bb_id;
+	}
+
+	/* Prepare the offline threshold - make sure we can add two blocks. */
+	vm->offline_threshold = max_t(uint64_t, 2 * memory_block_size_bytes(),
+				      VIRTIO_MEM_DEFAULT_OFFLINE_THRESHOLD);
+	/* In BBM, we also want at least two big blocks. */
+	vm->offline_threshold = max_t(uint64_t, 2 * vm->bbm.bb_size,
+				      vm->offline_threshold);
 
 	dev_info(&vm->vdev->dev, "start address: 0x%llx", vm->addr);
 	dev_info(&vm->vdev->dev, "region size: 0x%llx", vm->region_size);
@@ -1705,9 +2468,13 @@ static int virtio_mem_init(struct virtio_mem *vm)
 		 (unsigned long long)vm->device_block_size);
 	dev_info(&vm->vdev->dev, "memory block size: 0x%lx",
 		 memory_block_size_bytes());
-	dev_info(&vm->vdev->dev, "subblock size: 0x%llx",
-		 (unsigned long long)vm->subblock_size);
-	if (vm->nid != NUMA_NO_NODE)
+	if (vm->in_sbm)
+		dev_info(&vm->vdev->dev, "subblock size: 0x%llx",
+			 (unsigned long long)vm->sbm.sb_size);
+	else
+		dev_info(&vm->vdev->dev, "big block size: 0x%llx",
+			 (unsigned long long)vm->bbm.bb_size);
+	if (vm->nid != NUMA_NO_NODE && IS_ENABLED(CONFIG_NUMA))
 		dev_info(&vm->vdev->dev, "nid: %d", vm->nid);
 
 	return 0;
@@ -1753,6 +2520,20 @@ static void virtio_mem_delete_resource(struct virtio_mem *vm)
 	vm->parent_resource = NULL;
 }
 
+static int virtio_mem_range_has_system_ram(struct resource *res, void *arg)
+{
+	return 1;
+}
+
+static bool virtio_mem_has_memory_added(struct virtio_mem *vm)
+{
+	const unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+
+	return walk_iomem_res_desc(IORES_DESC_NONE, flags, vm->addr,
+				   vm->addr + vm->region_size, NULL,
+				   virtio_mem_range_has_system_ram) == 1;
+}
+
 static int virtio_mem_probe(struct virtio_device *vdev)
 {
 	struct virtio_mem *vm;
@@ -1849,21 +2630,24 @@ static void virtio_mem_remove(struct virtio_device *vdev)
 	cancel_work_sync(&vm->wq);
 	hrtimer_cancel(&vm->retry_timer);
 
-	/*
-	 * After we unregistered our callbacks, user space can online partially
-	 * plugged offline blocks. Make sure to remove them.
-	 */
-	virtio_mem_for_each_mb_state(vm, mb_id,
-				     VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) {
-		rc = virtio_mem_mb_remove(vm, mb_id);
-		BUG_ON(rc);
-		virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED);
+	if (vm->in_sbm) {
+		/*
+		 * After we unregistered our callbacks, user space can online
+		 * partially plugged offline blocks. Make sure to remove them.
+		 */
+		virtio_mem_sbm_for_each_mb(vm, mb_id,
+					   VIRTIO_MEM_SBM_MB_OFFLINE_PARTIAL) {
+			rc = virtio_mem_sbm_remove_mb(vm, mb_id);
+			BUG_ON(rc);
+			virtio_mem_sbm_set_mb_state(vm, mb_id,
+						    VIRTIO_MEM_SBM_MB_UNUSED);
+		}
+		/*
+		 * After we unregistered our callbacks, user space can no longer
+		 * offline partially plugged online memory blocks. No need to
+		 * worry about them.
+		 */
 	}
-	/*
-	 * After we unregistered our callbacks, user space can no longer
-	 * offline partially plugged online memory blocks. No need to worry
-	 * about them.
-	 */
 
 	/* unregister callbacks */
 	unregister_virtio_mem_device(vm);
@@ -1874,10 +2658,7 @@ static void virtio_mem_remove(struct virtio_device *vdev)
 	 * the system. And there is no way to stop the driver/device from going
 	 * away. Warn at least.
 	 */
-	if (vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] ||
-	    vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL] ||
-	    vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE] ||
-	    vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL]) {
+	if (virtio_mem_has_memory_added(vm)) {
 		dev_warn(&vdev->dev, "device still has system memory added\n");
 	} else {
 		virtio_mem_delete_resource(vm);
@@ -1885,8 +2666,12 @@ static void virtio_mem_remove(struct virtio_device *vdev)
 	}
 
 	/* remove all tracking data - no locking needed */
-	vfree(vm->mb_state);
-	vfree(vm->sb_bitmap);
+	if (vm->in_sbm) {
+		vfree(vm->sbm.mb_states);
+		vfree(vm->sbm.sb_states);
+	} else {
+		vfree(vm->bbm.bb_states);
+	}
 
 	/* reset the device and cleanup the queues */
 	vdev->config->reset(vdev);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index becc77697960..71e16b53e9c1 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -1608,7 +1608,6 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	vq->num_added = 0;
 	vq->packed_ring = true;
 	vq->use_dma_api = vring_use_dma_api(vdev);
-	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;
 	vq->last_add_time_valid = false;
@@ -1669,6 +1668,7 @@ static struct virtqueue *vring_create_virtqueue_packed(
 			cpu_to_le16(vq->packed.event_flags_shadow);
 	}
 
+	list_add_tail(&vq->vq.list, &vdev->vqs);
 	return &vq->vq;
 
 err_desc_extra:
@@ -1676,9 +1676,9 @@ err_desc_extra:
 err_desc_state:
 	kfree(vq);
 err_vq:
-	vring_free_queue(vdev, event_size_in_bytes, device, ring_dma_addr);
+	vring_free_queue(vdev, event_size_in_bytes, device, device_event_dma_addr);
 err_device:
-	vring_free_queue(vdev, event_size_in_bytes, driver, ring_dma_addr);
+	vring_free_queue(vdev, event_size_in_bytes, driver, driver_event_dma_addr);
 err_driver:
 	vring_free_queue(vdev, ring_size_in_bytes, ring, ring_dma_addr);
 err_ring:
@@ -2085,7 +2085,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	vq->last_used_idx = 0;
 	vq->num_added = 0;
 	vq->use_dma_api = vring_use_dma_api(vdev);
-	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;
 	vq->last_add_time_valid = false;
@@ -2127,6 +2126,7 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	memset(vq->split.desc_state, 0, vring.num *
 			sizeof(struct vring_desc_state_split));
 
+	list_add_tail(&vq->vq.list, &vdev->vqs);
 	return &vq->vq;
 }
 EXPORT_SYMBOL_GPL(__vring_new_virtqueue);
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index f22e37337030..7ff941e71b79 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -386,6 +386,7 @@ config ARM_SBSA_WATCHDOG
 config ARMADA_37XX_WATCHDOG
 	tristate "Armada 37xx watchdog"
 	depends on ARCH_MVEBU || COMPILE_TEST
+	depends on HAS_IOMEM
 	select MFD_SYSCON
 	select WATCHDOG_CORE
 	help
@@ -631,7 +632,7 @@ config SUNXI_WATCHDOG
 
 config COH901327_WATCHDOG
 	bool "ST-Ericsson COH 901 327 watchdog"
-	depends on ARCH_U300 || (ARM && COMPILE_TEST)
+	depends on ARCH_U300 || (ARM && COMMON_CLK && COMPILE_TEST)
 	default y if MACH_U300
 	select WATCHDOG_CORE
 	help
@@ -789,6 +790,7 @@ config MOXART_WDT
 
 config SIRFSOC_WATCHDOG
 	tristate "SiRFSOC watchdog"
+	depends on HAS_IOMEM
 	depends on ARCH_SIRF || COMPILE_TEST
 	select WATCHDOG_CORE
 	default y
@@ -1696,16 +1698,6 @@ config WDT_MTX1
 	  Hardware driver for the MTX-1 boards. This is a watchdog timer that
 	  will reboot the machine after a 100 seconds timer expired.
 
-config PNX833X_WDT
-	tristate "PNX833x Hardware Watchdog"
-	depends on SOC_PNX8335
-	depends on BROKEN
-	help
-	  Hardware driver for the PNX833x's watchdog. This is a
-	  watchdog timer that will reboot the machine after a programmable
-	  timer has expired and no process has written to /dev/watchdog during
-	  that time.
-
 config SIBYTE_WDOG
 	tristate "Sibyte SoC hardware watchdog"
 	depends on CPU_SB1 || (MIPS && COMPILE_TEST)
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index 071a2e50be98..5c74ee19d441 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -161,7 +161,6 @@ obj-$(CONFIG_RC32434_WDT) += rc32434_wdt.o
 obj-$(CONFIG_INDYDOG) += indydog.o
 obj-$(CONFIG_JZ4740_WDT) += jz4740_wdt.o
 obj-$(CONFIG_WDT_MTX1) += mtx-1_wdt.o
-obj-$(CONFIG_PNX833X_WDT) += pnx833x_wdt.o
 obj-$(CONFIG_SIBYTE_WDOG) += sb_wdog.o
 obj-$(CONFIG_AR7_WDT) += ar7_wdt.o
 obj-$(CONFIG_TXX9_WDT) += txx9wdt.o
diff --git a/drivers/watchdog/geodewdt.c b/drivers/watchdog/geodewdt.c
index 83418924e30a..0b699c783d57 100644
--- a/drivers/watchdog/geodewdt.c
+++ b/drivers/watchdog/geodewdt.c
@@ -150,8 +150,6 @@ static long geodewdt_ioctl(struct file *file, unsigned int cmd,
 	case WDIOC_GETSUPPORT:
 		return copy_to_user(argp, &ident,
 				    sizeof(ident)) ? -EFAULT : 0;
-		break;
-
 	case WDIOC_GETSTATUS:
 	case WDIOC_GETBOOTSTATUS:
 		return put_user(0, p);
diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c
index 7d34bcf1c45b..cbd1498ff015 100644
--- a/drivers/watchdog/hpwdt.c
+++ b/drivers/watchdog/hpwdt.c
@@ -21,8 +21,9 @@
 #include <linux/types.h>
 #include <linux/watchdog.h>
 #include <asm/nmi.h>
+#include <linux/crash_dump.h>
 
-#define HPWDT_VERSION			"2.0.3"
+#define HPWDT_VERSION			"2.0.4"
 #define SECS_TO_TICKS(secs)		((secs) * 1000 / 128)
 #define TICKS_TO_SECS(ticks)		((ticks) * 128 / 1000)
 #define HPWDT_MAX_TICKS			65535
@@ -334,6 +335,11 @@ static int hpwdt_init_one(struct pci_dev *dev,
 	watchdog_set_nowayout(&hpwdt_dev, nowayout);
 	watchdog_init_timeout(&hpwdt_dev, soft_margin, NULL);
 
+	if (is_kdump_kernel()) {
+		pretimeout = 0;
+		kdumptimeout = 0;
+	}
+
 	if (pretimeout && hpwdt_dev.timeout <= PRETIMEOUT_SEC) {
 		dev_warn(&dev->dev, "timeout <= pretimeout. Setting pretimeout to zero\n");
 		pretimeout = 0;
diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
index a370a185a41c..bf31d7b67a69 100644
--- a/drivers/watchdog/iTCO_wdt.c
+++ b/drivers/watchdog/iTCO_wdt.c
@@ -40,8 +40,6 @@
  *	Includes, defines, variables, module parameters, ...
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 /* Module and version information */
 #define DRV_NAME	"iTCO_wdt"
 #define DRV_VERSION	"1.11"
@@ -279,7 +277,7 @@ static int iTCO_wdt_start(struct watchdog_device *wd_dev)
 	/* disable chipset's NO_REBOOT bit */
 	if (p->update_no_reboot_bit(p->no_reboot_priv, false)) {
 		spin_unlock(&p->io_lock);
-		pr_err("failed to reset NO_REBOOT flag, reboot disabled by hardware/BIOS\n");
+		dev_err(wd_dev->parent, "failed to reset NO_REBOOT flag, reboot disabled by hardware/BIOS\n");
 		return -EIO;
 	}
 
@@ -510,7 +508,7 @@ static int iTCO_wdt_probe(struct platform_device *pdev)
 	/* Check chipset's NO_REBOOT bit */
 	if (p->update_no_reboot_bit(p->no_reboot_priv, false) &&
 	    iTCO_vendor_check_noreboot_on()) {
-		pr_info("unable to reset NO_REBOOT flag, device disabled by hardware/BIOS\n");
+		dev_info(dev, "unable to reset NO_REBOOT flag, device disabled by hardware/BIOS\n");
 		return -ENODEV;	/* Cannot reset NO_REBOOT bit */
 	}
 
@@ -530,12 +528,12 @@ static int iTCO_wdt_probe(struct platform_device *pdev)
 	if (!devm_request_region(dev, p->tco_res->start,
 				 resource_size(p->tco_res),
 				 pdev->name)) {
-		pr_err("I/O address 0x%04llx already in use, device disabled\n",
+		dev_err(dev, "I/O address 0x%04llx already in use, device disabled\n",
 		       (u64)TCOBASE(p));
 		return -EBUSY;
 	}
 
-	pr_info("Found a %s TCO device (Version=%d, TCOBASE=0x%04llx)\n",
+	dev_info(dev, "Found a %s TCO device (Version=%d, TCOBASE=0x%04llx)\n",
 		pdata->name, pdata->version, (u64)TCOBASE(p));
 
 	/* Clear out the (probably old) status */
@@ -558,7 +556,7 @@ static int iTCO_wdt_probe(struct platform_device *pdev)
 		break;
 	}
 
-	p->wddev.info =	&ident,
+	p->wddev.info = &ident,
 	p->wddev.ops = &iTCO_wdt_ops,
 	p->wddev.bootstatus = 0;
 	p->wddev.timeout = WATCHDOG_TIMEOUT;
@@ -575,7 +573,7 @@ static int iTCO_wdt_probe(struct platform_device *pdev)
 	   if not reset to the default */
 	if (iTCO_wdt_set_timeout(&p->wddev, heartbeat)) {
 		iTCO_wdt_set_timeout(&p->wddev, WATCHDOG_TIMEOUT);
-		pr_info("timeout value out of range, using %d\n",
+		dev_info(dev, "timeout value out of range, using %d\n",
 			WATCHDOG_TIMEOUT);
 	}
 
@@ -583,11 +581,11 @@ static int iTCO_wdt_probe(struct platform_device *pdev)
 	watchdog_stop_on_unregister(&p->wddev);
 	ret = devm_watchdog_register_device(dev, &p->wddev);
 	if (ret != 0) {
-		pr_err("cannot register watchdog device (err=%d)\n", ret);
+		dev_err(dev, "cannot register watchdog device (err=%d)\n", ret);
 		return ret;
 	}
 
-	pr_info("initialized. heartbeat=%d sec (nowayout=%d)\n",
+	dev_info(dev, "initialized. heartbeat=%d sec (nowayout=%d)\n",
 		heartbeat, nowayout);
 
 	return 0;
@@ -651,21 +649,7 @@ static struct platform_driver iTCO_wdt_driver = {
 	},
 };
 
-static int __init iTCO_wdt_init_module(void)
-{
-	pr_info("Intel TCO WatchDog Timer Driver v%s\n", DRV_VERSION);
-
-	return platform_driver_register(&iTCO_wdt_driver);
-}
-
-static void __exit iTCO_wdt_cleanup_module(void)
-{
-	platform_driver_unregister(&iTCO_wdt_driver);
-	pr_info("Watchdog Module Unloaded\n");
-}
-
-module_init(iTCO_wdt_init_module);
-module_exit(iTCO_wdt_cleanup_module);
+module_platform_driver(iTCO_wdt_driver);
 
 MODULE_AUTHOR("Wim Van Sebroeck <wim@iguana.be>");
 MODULE_DESCRIPTION("Intel TCO WatchDog Timer Driver");
diff --git a/drivers/watchdog/mpc8xxx_wdt.c b/drivers/watchdog/mpc8xxx_wdt.c
index 3fc457bc16db..2f7ded32e878 100644
--- a/drivers/watchdog/mpc8xxx_wdt.c
+++ b/drivers/watchdog/mpc8xxx_wdt.c
@@ -175,8 +175,8 @@ static int mpc8xxx_wdt_probe(struct platform_device *ofdev)
 
 	spin_lock_init(&ddata->lock);
 
-	ddata->wdd.info = &mpc8xxx_wdt_info,
-	ddata->wdd.ops = &mpc8xxx_wdt_ops,
+	ddata->wdd.info = &mpc8xxx_wdt_info;
+	ddata->wdd.ops = &mpc8xxx_wdt_ops;
 
 	ddata->wdd.timeout = WATCHDOG_TIMEOUT;
 	watchdog_init_timeout(&ddata->wdd, timeout, dev);
diff --git a/drivers/watchdog/pnx833x_wdt.c b/drivers/watchdog/pnx833x_wdt.c
deleted file mode 100644
index 4097d076aab8..000000000000
--- a/drivers/watchdog/pnx833x_wdt.c
+++ /dev/null
@@ -1,277 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- *  PNX833x Hardware Watchdog Driver
- *  Copyright 2008 NXP Semiconductors
- *  Daniel Laird <daniel.j.laird@nxp.com>
- *  Andre McCurdy <andre.mccurdy@nxp.com>
- *
- *  Heavily based upon - IndyDog	0.3
- *  A Hardware Watchdog Device for SGI IP22
- *
- * (c) Copyright 2002 Guido Guenther <agx@sigxcpu.org>, All Rights Reserved.
- *
- * based on softdog.c by Alan Cox <alan@redhat.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/miscdevice.h>
-#include <linux/watchdog.h>
-#include <linux/notifier.h>
-#include <linux/reboot.h>
-#include <linux/init.h>
-#include <asm/mach-pnx833x/pnx833x.h>
-
-#define WATCHDOG_TIMEOUT 30		/* 30 sec Maximum timeout */
-#define WATCHDOG_COUNT_FREQUENCY 68000000U /* Watchdog counts at 68MHZ. */
-#define	PNX_WATCHDOG_TIMEOUT	(WATCHDOG_TIMEOUT * WATCHDOG_COUNT_FREQUENCY)
-#define PNX_TIMEOUT_VALUE	2040000000U
-
-/** CONFIG block */
-#define PNX833X_CONFIG                      (0x07000U)
-#define PNX833X_CONFIG_CPU_WATCHDOG         (0x54)
-#define PNX833X_CONFIG_CPU_WATCHDOG_COMPARE (0x58)
-#define PNX833X_CONFIG_CPU_COUNTERS_CONTROL (0x1c)
-
-/** RESET block */
-#define PNX833X_RESET                       (0x08000U)
-#define PNX833X_RESET_CONFIG                (0x08)
-
-static int pnx833x_wdt_alive;
-
-/* Set default timeout in MHZ.*/
-static int pnx833x_wdt_timeout = PNX_WATCHDOG_TIMEOUT;
-module_param(pnx833x_wdt_timeout, int, 0);
-MODULE_PARM_DESC(timeout, "Watchdog timeout in Mhz. (68Mhz clock), default="
-			__MODULE_STRING(PNX_TIMEOUT_VALUE) "(30 seconds).");
-
-static bool nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, bool, 0);
-MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
-					__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
-
-#define START_DEFAULT	1
-static int start_enabled = START_DEFAULT;
-module_param(start_enabled, int, 0);
-MODULE_PARM_DESC(start_enabled, "Watchdog is started on module insertion "
-				"(default=" __MODULE_STRING(START_DEFAULT) ")");
-
-static void pnx833x_wdt_start(void)
-{
-	/* Enable watchdog causing reset. */
-	PNX833X_REG(PNX833X_RESET + PNX833X_RESET_CONFIG) |= 0x1;
-	/* Set timeout.*/
-	PNX833X_REG(PNX833X_CONFIG +
-		PNX833X_CONFIG_CPU_WATCHDOG_COMPARE) = pnx833x_wdt_timeout;
-	/* Enable watchdog. */
-	PNX833X_REG(PNX833X_CONFIG +
-				PNX833X_CONFIG_CPU_COUNTERS_CONTROL) |= 0x1;
-
-	pr_info("Started watchdog timer\n");
-}
-
-static void pnx833x_wdt_stop(void)
-{
-	/* Disable watchdog causing reset. */
-	PNX833X_REG(PNX833X_RESET + PNX833X_CONFIG) &= 0xFFFFFFFE;
-	/* Disable watchdog.*/
-	PNX833X_REG(PNX833X_CONFIG +
-			PNX833X_CONFIG_CPU_COUNTERS_CONTROL) &= 0xFFFFFFFE;
-
-	pr_info("Stopped watchdog timer\n");
-}
-
-static void pnx833x_wdt_ping(void)
-{
-	PNX833X_REG(PNX833X_CONFIG +
-		PNX833X_CONFIG_CPU_WATCHDOG_COMPARE) = pnx833x_wdt_timeout;
-}
-
-/*
- *	Allow only one person to hold it open
- */
-static int pnx833x_wdt_open(struct inode *inode, struct file *file)
-{
-	if (test_and_set_bit(0, &pnx833x_wdt_alive))
-		return -EBUSY;
-
-	if (nowayout)
-		__module_get(THIS_MODULE);
-
-	/* Activate timer */
-	if (!start_enabled)
-		pnx833x_wdt_start();
-
-	pnx833x_wdt_ping();
-
-	pr_info("Started watchdog timer\n");
-
-	return stream_open(inode, file);
-}
-
-static int pnx833x_wdt_release(struct inode *inode, struct file *file)
-{
-	/* Shut off the timer.
-	 * Lock it in if it's a module and we defined ...NOWAYOUT */
-	if (!nowayout)
-		pnx833x_wdt_stop(); /* Turn the WDT off */
-
-	clear_bit(0, &pnx833x_wdt_alive);
-	return 0;
-}
-
-static ssize_t pnx833x_wdt_write(struct file *file, const char *data, size_t len, loff_t *ppos)
-{
-	/* Refresh the timer. */
-	if (len)
-		pnx833x_wdt_ping();
-
-	return len;
-}
-
-static long pnx833x_wdt_ioctl(struct file *file, unsigned int cmd,
-							unsigned long arg)
-{
-	int options, new_timeout = 0;
-	uint32_t timeout, timeout_left = 0;
-
-	static const struct watchdog_info ident = {
-		.options = WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT,
-		.firmware_version = 0,
-		.identity = "Hardware Watchdog for PNX833x",
-	};
-
-	switch (cmd) {
-	default:
-		return -ENOTTY;
-
-	case WDIOC_GETSUPPORT:
-		if (copy_to_user((struct watchdog_info *)arg,
-				 &ident, sizeof(ident)))
-			return -EFAULT;
-		return 0;
-
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		return put_user(0, (int *)arg);
-
-	case WDIOC_SETOPTIONS:
-		if (get_user(options, (int *)arg))
-			return -EFAULT;
-
-		if (options & WDIOS_DISABLECARD)
-			pnx833x_wdt_stop();
-
-		if (options & WDIOS_ENABLECARD)
-			pnx833x_wdt_start();
-
-		return 0;
-
-	case WDIOC_KEEPALIVE:
-		pnx833x_wdt_ping();
-		return 0;
-
-	case WDIOC_SETTIMEOUT:
-	{
-		if (get_user(new_timeout, (int *)arg))
-			return -EFAULT;
-
-		pnx833x_wdt_timeout = new_timeout;
-		PNX833X_REG(PNX833X_CONFIG +
-			PNX833X_CONFIG_CPU_WATCHDOG_COMPARE) = new_timeout;
-		return put_user(new_timeout, (int *)arg);
-	}
-
-	case WDIOC_GETTIMEOUT:
-		timeout = PNX833X_REG(PNX833X_CONFIG +
-					PNX833X_CONFIG_CPU_WATCHDOG_COMPARE);
-		return put_user(timeout, (int *)arg);
-
-	case WDIOC_GETTIMELEFT:
-		timeout_left = PNX833X_REG(PNX833X_CONFIG +
-						PNX833X_CONFIG_CPU_WATCHDOG);
-		return put_user(timeout_left, (int *)arg);
-
-	}
-}
-
-static int pnx833x_wdt_notify_sys(struct notifier_block *this,
-					unsigned long code, void *unused)
-{
-	if (code == SYS_DOWN || code == SYS_HALT)
-		pnx833x_wdt_stop(); /* Turn the WDT off */
-
-	return NOTIFY_DONE;
-}
-
-static const struct file_operations pnx833x_wdt_fops = {
-	.owner		= THIS_MODULE,
-	.llseek		= no_llseek,
-	.write		= pnx833x_wdt_write,
-	.unlocked_ioctl	= pnx833x_wdt_ioctl,
-	.compat_ioctl	= compat_ptr_ioctl,
-	.open		= pnx833x_wdt_open,
-	.release	= pnx833x_wdt_release,
-};
-
-static struct miscdevice pnx833x_wdt_miscdev = {
-	.minor		= WATCHDOG_MINOR,
-	.name		= "watchdog",
-	.fops		= &pnx833x_wdt_fops,
-};
-
-static struct notifier_block pnx833x_wdt_notifier = {
-	.notifier_call = pnx833x_wdt_notify_sys,
-};
-
-static int __init watchdog_init(void)
-{
-	int ret, cause;
-
-	/* Lets check the reason for the reset.*/
-	cause = PNX833X_REG(PNX833X_RESET);
-	/*If bit 31 is set then watchdog was cause of reset.*/
-	if (cause & 0x80000000) {
-		pr_info("The system was previously reset due to the watchdog firing - please investigate...\n");
-	}
-
-	ret = register_reboot_notifier(&pnx833x_wdt_notifier);
-	if (ret) {
-		pr_err("cannot register reboot notifier (err=%d)\n", ret);
-		return ret;
-	}
-
-	ret = misc_register(&pnx833x_wdt_miscdev);
-	if (ret) {
-		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
-		       WATCHDOG_MINOR, ret);
-		unregister_reboot_notifier(&pnx833x_wdt_notifier);
-		return ret;
-	}
-
-	pr_info("Hardware Watchdog Timer for PNX833x: Version 0.1\n");
-
-	if (start_enabled)
-		pnx833x_wdt_start();
-
-	return 0;
-}
-
-static void __exit watchdog_exit(void)
-{
-	misc_deregister(&pnx833x_wdt_miscdev);
-	unregister_reboot_notifier(&pnx833x_wdt_notifier);
-}
-
-module_init(watchdog_init);
-module_exit(watchdog_exit);
-
-MODULE_AUTHOR("Daniel Laird/Andre McCurdy");
-MODULE_DESCRIPTION("Hardware Watchdog Device for PNX833x");
-MODULE_LICENSE("GPL");
diff --git a/drivers/watchdog/qcom-wdt.c b/drivers/watchdog/qcom-wdt.c
index ab7465d186fd..7cf0f2ec649b 100644
--- a/drivers/watchdog/qcom-wdt.c
+++ b/drivers/watchdog/qcom-wdt.c
@@ -148,10 +148,17 @@ static int qcom_wdt_restart(struct watchdog_device *wdd, unsigned long action,
 	 */
 	wmb();
 
-	msleep(150);
+	mdelay(150);
 	return 0;
 }
 
+static int qcom_wdt_is_running(struct watchdog_device *wdd)
+{
+	struct qcom_wdt *wdt = to_qcom_wdt(wdd);
+
+	return (readl(wdt_addr(wdt, WDT_EN)) & QCOM_WDT_ENABLE);
+}
+
 static const struct watchdog_ops qcom_wdt_ops = {
 	.start		= qcom_wdt_start,
 	.stop		= qcom_wdt_stop,
@@ -294,6 +301,17 @@ static int qcom_wdt_probe(struct platform_device *pdev)
 	wdt->wdd.timeout = min(wdt->wdd.max_timeout, 30U);
 	watchdog_init_timeout(&wdt->wdd, 0, dev);
 
+	/*
+	 * If WDT is already running, call WDT start which
+	 * will stop the WDT, set timeouts as bootloader
+	 * might use different ones and set running bit
+	 * to inform the WDT subsystem to ping the WDT
+	 */
+	if (qcom_wdt_is_running(&wdt->wdd)) {
+		qcom_wdt_start(&wdt->wdd);
+		set_bit(WDOG_HW_RUNNING, &wdt->wdd.status);
+	}
+
 	ret = devm_watchdog_register_device(dev, &wdt->wdd);
 	if (ret)
 		return ret;
diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c
index 836319cbaca9..359302f71f7e 100644
--- a/drivers/watchdog/rti_wdt.c
+++ b/drivers/watchdog/rti_wdt.c
@@ -227,8 +227,10 @@ static int rti_wdt_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(dev);
 	ret = pm_runtime_get_sync(dev);
-	if (ret)
+	if (ret) {
+		pm_runtime_put_noidle(dev);
 		return dev_err_probe(dev, ret, "runtime pm failed\n");
+	}
 
 	platform_set_drvdata(pdev, wdt);
 
diff --git a/drivers/watchdog/sbc_fitpc2_wdt.c b/drivers/watchdog/sbc_fitpc2_wdt.c
index 04483d6453d6..13db71e16583 100644
--- a/drivers/watchdog/sbc_fitpc2_wdt.c
+++ b/drivers/watchdog/sbc_fitpc2_wdt.c
@@ -78,7 +78,7 @@ static int fitpc2_wdt_open(struct inode *inode, struct file *file)
 	return stream_open(inode, file);
 }
 
-static ssize_t fitpc2_wdt_write(struct file *file, const char *data,
+static ssize_t fitpc2_wdt_write(struct file *file, const char __user *data,
 						size_t len, loff_t *ppos)
 {
 	size_t i;
@@ -125,16 +125,16 @@ static long fitpc2_wdt_ioctl(struct file *file, unsigned int cmd,
 
 	switch (cmd) {
 	case WDIOC_GETSUPPORT:
-		ret = copy_to_user((struct watchdog_info *)arg, &ident,
+		ret = copy_to_user((struct watchdog_info __user *)arg, &ident,
 				   sizeof(ident)) ? -EFAULT : 0;
 		break;
 
 	case WDIOC_GETSTATUS:
-		ret = put_user(0, (int *)arg);
+		ret = put_user(0, (int __user *)arg);
 		break;
 
 	case WDIOC_GETBOOTSTATUS:
-		ret = put_user(0, (int *)arg);
+		ret = put_user(0, (int __user *)arg);
 		break;
 
 	case WDIOC_KEEPALIVE:
@@ -143,7 +143,7 @@ static long fitpc2_wdt_ioctl(struct file *file, unsigned int cmd,
 		break;
 
 	case WDIOC_SETTIMEOUT:
-		ret = get_user(time, (int *)arg);
+		ret = get_user(time, (int __user *)arg);
 		if (ret)
 			break;
 
@@ -157,7 +157,7 @@ static long fitpc2_wdt_ioctl(struct file *file, unsigned int cmd,
 		fallthrough;
 
 	case WDIOC_GETTIMEOUT:
-		ret = put_user(margin, (int *)arg);
+		ret = put_user(margin, (int __user *)arg);
 		break;
 	}
 
diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c
index 190d26e2e75f..958dc32a708f 100644
--- a/drivers/watchdog/sp805_wdt.c
+++ b/drivers/watchdog/sp805_wdt.c
@@ -291,6 +291,7 @@ sp805_wdt_probe(struct amba_device *adev, const struct amba_id *id)
 		set_bit(WDOG_HW_RUNNING, &wdt->wdd.status);
 	}
 
+	watchdog_stop_on_reboot(&wdt->wdd);
 	ret = watchdog_register_device(&wdt->wdd);
 	if (ret)
 		goto err;
diff --git a/drivers/watchdog/sprd_wdt.c b/drivers/watchdog/sprd_wdt.c
index 65cb55f3916f..4e689b6ff141 100644
--- a/drivers/watchdog/sprd_wdt.c
+++ b/drivers/watchdog/sprd_wdt.c
@@ -6,6 +6,7 @@
 
 #include <linux/bitops.h>
 #include <linux/clk.h>
+#include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
@@ -53,7 +54,7 @@
 
 #define SPRD_WDT_CNT_HIGH_SHIFT		16
 #define SPRD_WDT_LOW_VALUE_MASK		GENMASK(15, 0)
-#define SPRD_WDT_LOAD_TIMEOUT		1000
+#define SPRD_WDT_LOAD_TIMEOUT		11
 
 struct sprd_wdt {
 	void __iomem *base;
@@ -108,6 +109,23 @@ static int sprd_wdt_load_value(struct sprd_wdt *wdt, u32 timeout,
 	u32 tmr_step = timeout * SPRD_WDT_CNT_STEP;
 	u32 prtmr_step = pretimeout * SPRD_WDT_CNT_STEP;
 
+	/*
+	 * Checking busy bit to make sure the previous loading operation is
+	 * done. According to the specification, the busy bit would be set
+	 * after a new loading operation and last 2 or 3 RTC clock
+	 * cycles (about 60us~92us).
+	 */
+	do {
+		val = readl_relaxed(wdt->base + SPRD_WDT_INT_RAW);
+		if (!(val & SPRD_WDT_LD_BUSY_BIT))
+			break;
+
+		usleep_range(10, 100);
+	} while (delay_cnt++ < SPRD_WDT_LOAD_TIMEOUT);
+
+	if (delay_cnt >= SPRD_WDT_LOAD_TIMEOUT)
+		return -EBUSY;
+
 	sprd_wdt_unlock(wdt->base);
 	writel_relaxed((tmr_step >> SPRD_WDT_CNT_HIGH_SHIFT) &
 		      SPRD_WDT_LOW_VALUE_MASK, wdt->base + SPRD_WDT_LOAD_HIGH);
@@ -120,20 +138,6 @@ static int sprd_wdt_load_value(struct sprd_wdt *wdt, u32 timeout,
 		       wdt->base + SPRD_WDT_IRQ_LOAD_LOW);
 	sprd_wdt_lock(wdt->base);
 
-	/*
-	 * Waiting the load value operation done,
-	 * it needs two or three RTC clock cycles.
-	 */
-	do {
-		val = readl_relaxed(wdt->base + SPRD_WDT_INT_RAW);
-		if (!(val & SPRD_WDT_LD_BUSY_BIT))
-			break;
-
-		cpu_relax();
-	} while (delay_cnt++ < SPRD_WDT_LOAD_TIMEOUT);
-
-	if (delay_cnt >= SPRD_WDT_LOAD_TIMEOUT)
-		return -EBUSY;
 	return 0;
 }
 
@@ -345,15 +349,10 @@ static int __maybe_unused sprd_wdt_pm_resume(struct device *dev)
 	if (ret)
 		return ret;
 
-	if (watchdog_active(&wdt->wdd)) {
+	if (watchdog_active(&wdt->wdd))
 		ret = sprd_wdt_start(&wdt->wdd);
-		if (ret) {
-			sprd_wdt_disable(wdt);
-			return ret;
-		}
-	}
 
-	return 0;
+	return ret;
 }
 
 static const struct dev_pm_ops sprd_wdt_pm_ops = {
diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c
index 25188d6bbe15..a3436c296c97 100644
--- a/drivers/watchdog/stm32_iwdg.c
+++ b/drivers/watchdog/stm32_iwdg.c
@@ -162,18 +162,15 @@ static int stm32_iwdg_clk_init(struct platform_device *pdev,
 	u32 ret;
 
 	wdt->clk_lsi = devm_clk_get(dev, "lsi");
-	if (IS_ERR(wdt->clk_lsi)) {
-		dev_err(dev, "Unable to get lsi clock\n");
-		return PTR_ERR(wdt->clk_lsi);
-	}
+	if (IS_ERR(wdt->clk_lsi))
+		return dev_err_probe(dev, PTR_ERR(wdt->clk_lsi), "Unable to get lsi clock\n");
 
 	/* optional peripheral clock */
 	if (wdt->data->has_pclk) {
 		wdt->clk_pclk = devm_clk_get(dev, "pclk");
-		if (IS_ERR(wdt->clk_pclk)) {
-			dev_err(dev, "Unable to get pclk clock\n");
-			return PTR_ERR(wdt->clk_pclk);
-		}
+		if (IS_ERR(wdt->clk_pclk))
+			return dev_err_probe(dev, PTR_ERR(wdt->clk_pclk),
+					     "Unable to get pclk clock\n");
 
 		ret = clk_prepare_enable(wdt->clk_pclk);
 		if (ret) {
diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c
index 423844757812..0e9a99559609 100644
--- a/drivers/watchdog/watchdog_core.c
+++ b/drivers/watchdog/watchdog_core.c
@@ -267,15 +267,19 @@ static int __watchdog_register_device(struct watchdog_device *wdd)
 	}
 
 	if (test_bit(WDOG_STOP_ON_REBOOT, &wdd->status)) {
-		wdd->reboot_nb.notifier_call = watchdog_reboot_notifier;
-
-		ret = register_reboot_notifier(&wdd->reboot_nb);
-		if (ret) {
-			pr_err("watchdog%d: Cannot register reboot notifier (%d)\n",
-			       wdd->id, ret);
-			watchdog_dev_unregister(wdd);
-			ida_simple_remove(&watchdog_ida, id);
-			return ret;
+		if (!wdd->ops->stop)
+			pr_warn("watchdog%d: stop_on_reboot not supported\n", wdd->id);
+		else {
+			wdd->reboot_nb.notifier_call = watchdog_reboot_notifier;
+
+			ret = register_reboot_notifier(&wdd->reboot_nb);
+			if (ret) {
+				pr_err("watchdog%d: Cannot register reboot notifier (%d)\n",
+					wdd->id, ret);
+				watchdog_dev_unregister(wdd);
+				ida_simple_remove(&watchdog_ida, id);
+				return ret;
+			}
 		}
 	}
 
diff --git a/drivers/watchdog/wdat_wdt.c b/drivers/watchdog/wdat_wdt.c
index 3065dd670a18..cec7917790e5 100644
--- a/drivers/watchdog/wdat_wdt.c
+++ b/drivers/watchdog/wdat_wdt.c
@@ -34,9 +34,9 @@ struct wdat_instruction {
  * @period: How long is one watchdog period in ms
  * @stopped_in_sleep: Is this watchdog stopped by the firmware in S1-S5
  * @stopped: Was the watchdog stopped by the driver in suspend
- * @actions: An array of instruction lists indexed by an action number from
- *           the WDAT table. There can be %NULL entries for not implemented
- *           actions.
+ * @instructions: An array of instruction lists indexed by an action number from
+ *                the WDAT table. There can be %NULL entries for not implemented
+ *                actions.
  */
 struct wdat_wdt {
 	struct platform_device *pdev;
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 6038c4c35db5..e850f79351cb 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -95,7 +95,8 @@ struct irq_info {
 	struct list_head list;
 	struct list_head eoi_list;
 	short refcnt;
-	short spurious_cnt;
+	u8 spurious_cnt;
+	u8 is_accounted;
 	enum xen_irq_type type; /* type */
 	unsigned irq;
 	evtchn_port_t evtchn;   /* event channel */
@@ -161,6 +162,9 @@ static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1};
 /* IRQ <-> IPI mapping */
 static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
 
+/* Event channel distribution data */
+static atomic_t channels_on_cpu[NR_CPUS];
+
 static int **evtchn_to_irq;
 #ifdef CONFIG_X86
 static unsigned long *pirq_eoi_map;
@@ -257,6 +261,32 @@ static void set_info_for_irq(unsigned int irq, struct irq_info *info)
 		irq_set_chip_data(irq, info);
 }
 
+/* Per CPU channel accounting */
+static void channels_on_cpu_dec(struct irq_info *info)
+{
+	if (!info->is_accounted)
+		return;
+
+	info->is_accounted = 0;
+
+	if (WARN_ON_ONCE(info->cpu >= nr_cpu_ids))
+		return;
+
+	WARN_ON_ONCE(!atomic_add_unless(&channels_on_cpu[info->cpu], -1 , 0));
+}
+
+static void channels_on_cpu_inc(struct irq_info *info)
+{
+	if (WARN_ON_ONCE(info->cpu >= nr_cpu_ids))
+		return;
+
+	if (WARN_ON_ONCE(!atomic_add_unless(&channels_on_cpu[info->cpu], 1,
+					    INT_MAX)))
+		return;
+
+	info->is_accounted = 1;
+}
+
 /* Constructors for packed IRQ information. */
 static int xen_irq_info_common_setup(struct irq_info *info,
 				     unsigned irq,
@@ -339,6 +369,7 @@ static void xen_irq_info_cleanup(struct irq_info *info)
 {
 	set_evtchn_to_irq(info->evtchn, -1);
 	info->evtchn = 0;
+	channels_on_cpu_dec(info);
 }
 
 /*
@@ -433,18 +464,25 @@ static bool pirq_needs_eoi_flag(unsigned irq)
 	return info->u.pirq.flags & PIRQ_NEEDS_EOI;
 }
 
-static void bind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int cpu)
+static void bind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int cpu,
+			       bool force_affinity)
 {
 	int irq = get_evtchn_to_irq(evtchn);
 	struct irq_info *info = info_for_irq(irq);
 
 	BUG_ON(irq == -1);
-#ifdef CONFIG_SMP
-	cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(cpu));
-#endif
+
+	if (IS_ENABLED(CONFIG_SMP) && force_affinity) {
+		cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(cpu));
+		cpumask_copy(irq_get_effective_affinity_mask(irq),
+			     cpumask_of(cpu));
+	}
+
 	xen_evtchn_port_bind_to_cpu(evtchn, cpu, info->cpu);
 
+	channels_on_cpu_dec(info);
 	info->cpu = cpu;
+	channels_on_cpu_inc(info);
 }
 
 /**
@@ -523,8 +561,10 @@ static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious)
 		return;
 
 	if (spurious) {
-		if ((1 << info->spurious_cnt) < (HZ << 2))
-			info->spurious_cnt++;
+		if ((1 << info->spurious_cnt) < (HZ << 2)) {
+			if (info->spurious_cnt != 0xFF)
+				info->spurious_cnt++;
+		}
 		if (info->spurious_cnt > 1) {
 			delay = 1 << (info->spurious_cnt - 2);
 			if (delay > HZ)
@@ -615,11 +655,6 @@ static void xen_irq_init(unsigned irq)
 {
 	struct irq_info *info;
 
-#ifdef CONFIG_SMP
-	/* By default all event channels notify CPU#0. */
-	cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(0));
-#endif
-
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (info == NULL)
 		panic("Unable to allocate metadata for IRQ%d\n", irq);
@@ -628,6 +663,11 @@ static void xen_irq_init(unsigned irq)
 	info->refcnt = -1;
 
 	set_info_for_irq(irq, info);
+	/*
+	 * Interrupt affinity setting can be immediate. No point
+	 * in delaying it until an interrupt is handled.
+	 */
+	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 
 	INIT_LIST_HEAD(&info->eoi_list);
 	list_add_tail(&info->list, &xen_irq_list_head);
@@ -739,18 +779,7 @@ static void eoi_pirq(struct irq_data *data)
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
-	if (unlikely(irqd_is_setaffinity_pending(data)) &&
-	    likely(!irqd_irq_disabled(data))) {
-		int masked = test_and_set_mask(evtchn);
-
-		clear_evtchn(evtchn);
-
-		irq_move_masked_irq(data);
-
-		if (!masked)
-			unmask_evtchn(evtchn);
-	} else
-		clear_evtchn(evtchn);
+	clear_evtchn(evtchn);
 
 	if (pirq_needs_eoi(data->irq)) {
 		rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
@@ -794,7 +823,7 @@ static unsigned int __startup_pirq(unsigned int irq)
 		goto err;
 
 	info->evtchn = evtchn;
-	bind_evtchn_to_cpu(evtchn, 0);
+	bind_evtchn_to_cpu(evtchn, 0, false);
 
 	rc = xen_evtchn_port_setup(evtchn);
 	if (rc)
@@ -1113,8 +1142,14 @@ static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip)
 			irq = ret;
 			goto out;
 		}
-		/* New interdomain events are bound to VCPU 0. */
-		bind_evtchn_to_cpu(evtchn, 0);
+		/*
+		 * New interdomain events are initially bound to vCPU0 This
+		 * is required to setup the event channel in the first
+		 * place and also important for UP guests because the
+		 * affinity setting is not invoked on them so nothing would
+		 * bind the channel.
+		 */
+		bind_evtchn_to_cpu(evtchn, 0, false);
 	} else {
 		struct irq_info *info = info_for_irq(irq);
 		WARN_ON(info == NULL || info->type != IRQT_EVTCHN);
@@ -1132,12 +1167,6 @@ int bind_evtchn_to_irq(evtchn_port_t evtchn)
 }
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);
 
-int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn)
-{
-	return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip);
-}
-EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi);
-
 static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 {
 	struct evtchn_bind_ipi bind_ipi;
@@ -1168,7 +1197,11 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 			irq = ret;
 			goto out;
 		}
-		bind_evtchn_to_cpu(evtchn, cpu);
+		/*
+		 * Force the affinity mask to the target CPU so proc shows
+		 * the correct target.
+		 */
+		bind_evtchn_to_cpu(evtchn, cpu, true);
 	} else {
 		struct irq_info *info = info_for_irq(irq);
 		WARN_ON(info == NULL || info->type != IRQT_IPI);
@@ -1281,7 +1314,11 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu)
 			goto out;
 		}
 
-		bind_evtchn_to_cpu(evtchn, cpu);
+		/*
+		 * Force the affinity mask for percpu interrupts so proc
+		 * shows the correct target.
+		 */
+		bind_evtchn_to_cpu(evtchn, cpu, percpu);
 	} else {
 		struct irq_info *info = info_for_irq(irq);
 		WARN_ON(info == NULL || info->type != IRQT_VIRQ);
@@ -1646,9 +1683,7 @@ void rebind_evtchn_irq(evtchn_port_t evtchn, int irq)
 
 	mutex_unlock(&irq_mapping_update_lock);
 
-        bind_evtchn_to_cpu(evtchn, info->cpu);
-	/* This will be deferred until interrupt is processed */
-	irq_set_affinity(irq, cpumask_of(info->cpu));
+	bind_evtchn_to_cpu(evtchn, info->cpu, false);
 
 	/* Unmask the event channel. */
 	enable_irq(irq);
@@ -1682,7 +1717,7 @@ static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu)
 	 * it, but don't do the xenlinux-level rebind in that case.
 	 */
 	if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
-		bind_evtchn_to_cpu(evtchn, tcpu);
+		bind_evtchn_to_cpu(evtchn, tcpu, false);
 
 	if (!masked)
 		unmask_evtchn(evtchn);
@@ -1690,27 +1725,47 @@ static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu)
 	return 0;
 }
 
+/*
+ * Find the CPU within @dest mask which has the least number of channels
+ * assigned. This is not precise as the per cpu counts can be modified
+ * concurrently.
+ */
+static unsigned int select_target_cpu(const struct cpumask *dest)
+{
+	unsigned int cpu, best_cpu = UINT_MAX, minch = UINT_MAX;
+
+	for_each_cpu_and(cpu, dest, cpu_online_mask) {
+		unsigned int curch = atomic_read(&channels_on_cpu[cpu]);
+
+		if (curch < minch) {
+			minch = curch;
+			best_cpu = cpu;
+		}
+	}
+
+	/*
+	 * Catch the unlikely case that dest contains no online CPUs. Can't
+	 * recurse.
+	 */
+	if (best_cpu == UINT_MAX)
+		return select_target_cpu(cpu_online_mask);
+
+	return best_cpu;
+}
+
 static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 			    bool force)
 {
-	unsigned tcpu = cpumask_first_and(dest, cpu_online_mask);
-	int ret = xen_rebind_evtchn_to_cpu(evtchn_from_irq(data->irq), tcpu);
+	unsigned int tcpu = select_target_cpu(dest);
+	int ret;
 
+	ret = xen_rebind_evtchn_to_cpu(evtchn_from_irq(data->irq), tcpu);
 	if (!ret)
 		irq_data_update_effective_affinity(data, cpumask_of(tcpu));
 
 	return ret;
 }
 
-/* To be called with desc->lock held. */
-int xen_set_affinity_evtchn(struct irq_desc *desc, unsigned int tcpu)
-{
-	struct irq_data *d = irq_desc_get_irq_data(desc);
-
-	return set_affinity_irq(d, cpumask_of(tcpu), false);
-}
-EXPORT_SYMBOL_GPL(xen_set_affinity_evtchn);
-
 static void enable_dynirq(struct irq_data *data)
 {
 	evtchn_port_t evtchn = evtchn_from_irq(data->irq);
@@ -1734,18 +1789,7 @@ static void ack_dynirq(struct irq_data *data)
 	if (!VALID_EVTCHN(evtchn))
 		return;
 
-	if (unlikely(irqd_is_setaffinity_pending(data)) &&
-	    likely(!irqd_irq_disabled(data))) {
-		int masked = test_and_set_mask(evtchn);
-
-		clear_evtchn(evtchn);
-
-		irq_move_masked_irq(data);
-
-		if (!masked)
-			unmask_evtchn(evtchn);
-	} else
-		clear_evtchn(evtchn);
+	clear_evtchn(evtchn);
 }
 
 static void mask_ack_dynirq(struct irq_data *data)
@@ -1830,7 +1874,8 @@ static void restore_cpu_virqs(unsigned int cpu)
 
 		/* Record the new mapping. */
 		(void)xen_irq_info_virq_setup(cpu, irq, evtchn, virq);
-		bind_evtchn_to_cpu(evtchn, cpu);
+		/* The affinity mask is still valid */
+		bind_evtchn_to_cpu(evtchn, cpu, false);
 	}
 }
 
@@ -1855,7 +1900,8 @@ static void restore_cpu_ipis(unsigned int cpu)
 
 		/* Record the new mapping. */
 		(void)xen_irq_info_ipi_setup(cpu, irq, evtchn, ipi);
-		bind_evtchn_to_cpu(evtchn, cpu);
+		/* The affinity mask is still valid */
+		bind_evtchn_to_cpu(evtchn, cpu, false);
 	}
 }
 
@@ -1938,8 +1984,12 @@ void xen_irq_resume(void)
 	xen_evtchn_resume();
 
 	/* No IRQ <-> event-channel mappings. */
-	list_for_each_entry(info, &xen_irq_list_head, list)
-		info->evtchn = 0; /* zap event-channel binding */
+	list_for_each_entry(info, &xen_irq_list_head, list) {
+		/* Zap event-channel binding */
+		info->evtchn = 0;
+		/* Adjust accounting */
+		channels_on_cpu_dec(info);
+	}
 
 	clear_evtchn_to_irq_all();
 
@@ -2010,16 +2060,6 @@ static struct irq_chip xen_percpu_chip __read_mostly = {
 	.irq_ack		= ack_dynirq,
 };
 
-int xen_set_callback_via(uint64_t via)
-{
-	struct xen_hvm_param a;
-	a.domid = DOMID_SELF;
-	a.index = HVM_PARAM_CALLBACK_IRQ;
-	a.value = via;
-	return HYPERVISOR_hvm_op(HVMOP_set_param, &a);
-}
-EXPORT_SYMBOL_GPL(xen_set_callback_via);
-
 #ifdef CONFIG_XEN_PVHVM
 /* Vector callbacks are better than PCI interrupts to receive event
  * channel notifications because we can receive vector callbacks on any
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index 5dc016d68f83..a7a85719a8c8 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -421,36 +421,6 @@ static void evtchn_unbind_from_user(struct per_user_data *u,
 	del_evtchn(u, evtchn);
 }
 
-static DEFINE_PER_CPU(int, bind_last_selected_cpu);
-
-static void evtchn_bind_interdom_next_vcpu(evtchn_port_t evtchn)
-{
-	unsigned int selected_cpu, irq;
-	struct irq_desc *desc;
-	unsigned long flags;
-
-	irq = irq_from_evtchn(evtchn);
-	desc = irq_to_desc(irq);
-
-	if (!desc)
-		return;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	selected_cpu = this_cpu_read(bind_last_selected_cpu);
-	selected_cpu = cpumask_next_and(selected_cpu,
-			desc->irq_common_data.affinity, cpu_online_mask);
-
-	if (unlikely(selected_cpu >= nr_cpu_ids))
-		selected_cpu = cpumask_first_and(desc->irq_common_data.affinity,
-				cpu_online_mask);
-
-	this_cpu_write(bind_last_selected_cpu, selected_cpu);
-
-	/* unmask expects irqs to be disabled */
-	xen_set_affinity_evtchn(desc, selected_cpu);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
 static long evtchn_ioctl(struct file *file,
 			 unsigned int cmd, unsigned long arg)
 {
@@ -508,10 +478,8 @@ static long evtchn_ioctl(struct file *file,
 			break;
 
 		rc = evtchn_bind_to_user(u, bind_interdomain.local_port);
-		if (rc == 0) {
+		if (rc == 0)
 			rc = bind_interdomain.local_port;
-			evtchn_bind_interdom_next_vcpu(rc);
-		}
 		break;
 	}
 
diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c
index dd911e1ff782..18f0ed8b1f93 100644
--- a/drivers/xen/platform-pci.c
+++ b/drivers/xen/platform-pci.c
@@ -132,6 +132,13 @@ static int platform_pci_probe(struct pci_dev *pdev,
 			dev_warn(&pdev->dev, "request_irq failed err=%d\n", ret);
 			goto out;
 		}
+		/*
+		 * It doesn't strictly *have* to run on CPU0 but it sure
+		 * as hell better process the event channel ports delivered
+		 * to CPU0.
+		 */
+		irq_set_affinity(pdev->irq, cpumask_of(0));
+
 		callback_via = get_callback_via(pdev);
 		ret = xen_set_callback_via(callback_via);
 		if (ret) {
@@ -149,7 +156,6 @@ static int platform_pci_probe(struct pci_dev *pdev,
 	ret = gnttab_init();
 	if (ret)
 		goto grant_out;
-	xenbus_probe(NULL);
 	return 0;
 grant_out:
 	gnttab_free_auto_xlat_frames();
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index b0c73c58f987..720a7b7abd46 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -717,14 +717,15 @@ static long privcmd_ioctl_restrict(struct file *file, void __user *udata)
 	return 0;
 }
 
-static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
+static long privcmd_ioctl_mmap_resource(struct file *file,
+				struct privcmd_mmap_resource __user *udata)
 {
 	struct privcmd_data *data = file->private_data;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	struct privcmd_mmap_resource kdata;
 	xen_pfn_t *pfns = NULL;
-	struct xen_mem_acquire_resource xdata;
+	struct xen_mem_acquire_resource xdata = { };
 	int rc;
 
 	if (copy_from_user(&kdata, udata, sizeof(kdata)))
@@ -734,6 +735,22 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
 	if (data->domid != DOMID_INVALID && data->domid != kdata.dom)
 		return -EPERM;
 
+	/* Both fields must be set or unset */
+	if (!!kdata.addr != !!kdata.num)
+		return -EINVAL;
+
+	xdata.domid = kdata.dom;
+	xdata.type = kdata.type;
+	xdata.id = kdata.id;
+
+	if (!kdata.addr && !kdata.num) {
+		/* Query the size of the resource. */
+		rc = HYPERVISOR_memory_op(XENMEM_acquire_resource, &xdata);
+		if (rc)
+			return rc;
+		return __put_user(xdata.nr_frames, &udata->num);
+	}
+
 	mmap_write_lock(mm);
 
 	vma = find_vma(mm, kdata.addr);
@@ -768,10 +785,6 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
 	} else
 		vma->vm_private_data = PRIV_VMA_LOCKED;
 
-	memset(&xdata, 0, sizeof(xdata));
-	xdata.domid = kdata.dom;
-	xdata.type = kdata.type;
-	xdata.id = kdata.id;
 	xdata.frame = kdata.idx;
 	xdata.nr_frames = kdata.num;
 	set_xen_guest_handle(xdata.frame_list, pfns);
diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h
index 2a93b7c9c159..dc1537335414 100644
--- a/drivers/xen/xenbus/xenbus.h
+++ b/drivers/xen/xenbus/xenbus.h
@@ -115,6 +115,7 @@ int xenbus_probe_node(struct xen_bus_type *bus,
 		      const char *type,
 		      const char *nodename);
 int xenbus_probe_devices(struct xen_bus_type *bus);
+void xenbus_probe(void);
 
 void xenbus_dev_changed(const char *node, struct xen_bus_type *bus);
 
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
index eb5151fc8efa..e5fda0256feb 100644
--- a/drivers/xen/xenbus/xenbus_comms.c
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -57,16 +57,8 @@ DEFINE_MUTEX(xs_response_mutex);
 static int xenbus_irq;
 static struct task_struct *xenbus_task;
 
-static DECLARE_WORK(probe_work, xenbus_probe);
-
-
 static irqreturn_t wake_waiting(int irq, void *unused)
 {
-	if (unlikely(xenstored_ready == 0)) {
-		xenstored_ready = 1;
-		schedule_work(&probe_work);
-	}
-
 	wake_up(&xb_waitq);
 	return IRQ_HANDLED;
 }
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 44634d970a5c..c8f0282bb649 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -683,29 +683,76 @@ void unregister_xenstore_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(unregister_xenstore_notifier);
 
-void xenbus_probe(struct work_struct *unused)
+void xenbus_probe(void)
 {
 	xenstored_ready = 1;
 
+	/*
+	 * In the HVM case, xenbus_init() deferred its call to
+	 * xs_init() in case callbacks were not operational yet.
+	 * So do it now.
+	 */
+	if (xen_store_domain_type == XS_HVM)
+		xs_init();
+
 	/* Notify others that xenstore is up */
 	blocking_notifier_call_chain(&xenstore_chain, 0, NULL);
 }
-EXPORT_SYMBOL_GPL(xenbus_probe);
 
-static int __init xenbus_probe_initcall(void)
+/*
+ * Returns true when XenStore init must be deferred in order to
+ * allow the PCI platform device to be initialised, before we
+ * can actually have event channel interrupts working.
+ */
+static bool xs_hvm_defer_init_for_callback(void)
 {
-	if (!xen_domain())
-		return -ENODEV;
+#ifdef CONFIG_XEN_PVHVM
+	return xen_store_domain_type == XS_HVM &&
+		!xen_have_vector_callback;
+#else
+	return false;
+#endif
+}
 
-	if (xen_initial_domain() || xen_hvm_domain())
-		return 0;
+static int __init xenbus_probe_initcall(void)
+{
+	/*
+	 * Probe XenBus here in the XS_PV case, and also XS_HVM unless we
+	 * need to wait for the platform PCI device to come up.
+	 */
+	if (xen_store_domain_type == XS_PV ||
+	    (xen_store_domain_type == XS_HVM &&
+	     !xs_hvm_defer_init_for_callback()))
+		xenbus_probe();
 
-	xenbus_probe(NULL);
 	return 0;
 }
-
 device_initcall(xenbus_probe_initcall);
 
+int xen_set_callback_via(uint64_t via)
+{
+	struct xen_hvm_param a;
+	int ret;
+
+	a.domid = DOMID_SELF;
+	a.index = HVM_PARAM_CALLBACK_IRQ;
+	a.value = via;
+
+	ret = HYPERVISOR_hvm_op(HVMOP_set_param, &a);
+	if (ret)
+		return ret;
+
+	/*
+	 * If xenbus_probe_initcall() deferred the xenbus_probe()
+	 * due to the callback not functioning yet, we can do it now.
+	 */
+	if (!xenstored_ready && xs_hvm_defer_init_for_callback())
+		xenbus_probe();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xen_set_callback_via);
+
 /* Set up event channel for xenstored which is run as a local process
  * (this is normally used only in dom0)
  */
@@ -818,11 +865,17 @@ static int __init xenbus_init(void)
 		break;
 	}
 
-	/* Initialize the interface to xenstore. */
-	err = xs_init();
-	if (err) {
-		pr_warn("Error initializing xenstore comms: %i\n", err);
-		goto out_error;
+	/*
+	 * HVM domains may not have a functional callback yet. In that
+	 * case let xs_init() be called from xenbus_probe(), which will
+	 * get invoked at an appropriate time.
+	 */
+	if (xen_store_domain_type != XS_HVM) {
+		err = xs_init();
+		if (err) {
+			pr_warn("Error initializing xenstore comms: %i\n", err);
+			goto out_error;
+		}
 	}
 
 	if ((xen_store_domain_type != XS_LOCAL) &&
diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index 3d681a2c2731..9d9de62592be 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -39,6 +39,48 @@ void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid)
 }
 
 /**
+ * v9fs_fid_find_inode - search for an open fid off of the inode list
+ * @inode: return a fid pointing to a specific inode
+ * @uid: return a fid belonging to the specified user
+ *
+ */
+
+static struct p9_fid *v9fs_fid_find_inode(struct inode *inode, kuid_t uid)
+{
+	struct hlist_head *h;
+	struct p9_fid *fid, *ret = NULL;
+
+	p9_debug(P9_DEBUG_VFS, " inode: %p\n", inode);
+
+	spin_lock(&inode->i_lock);
+	h = (struct hlist_head *)&inode->i_private;
+	hlist_for_each_entry(fid, h, ilist) {
+		if (uid_eq(fid->uid, uid)) {
+			refcount_inc(&fid->count);
+			ret = fid;
+			break;
+		}
+	}
+	spin_unlock(&inode->i_lock);
+	return ret;
+}
+
+/**
+ * v9fs_open_fid_add - add an open fid to an inode
+ * @dentry: inode that the fid is being added to
+ * @fid: fid to add
+ *
+ */
+
+void v9fs_open_fid_add(struct inode *inode, struct p9_fid *fid)
+{
+	spin_lock(&inode->i_lock);
+	hlist_add_head(&fid->ilist, (struct hlist_head *)&inode->i_private);
+	spin_unlock(&inode->i_lock);
+}
+
+
+/**
  * v9fs_fid_find - retrieve a fid that belongs to the specified uid
  * @dentry: dentry to look for fid in
  * @uid: return fid that belongs to the specified user
@@ -54,13 +96,18 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
 		 dentry, dentry, from_kuid(&init_user_ns, uid),
 		 any);
 	ret = NULL;
+
+	if (d_inode(dentry))
+		ret = v9fs_fid_find_inode(d_inode(dentry), uid);
+
 	/* we'll recheck under lock if there's anything to look in */
-	if (dentry->d_fsdata) {
+	if (!ret && dentry->d_fsdata) {
 		struct hlist_head *h = (struct hlist_head *)&dentry->d_fsdata;
 		spin_lock(&dentry->d_lock);
 		hlist_for_each_entry(fid, h, dlist) {
 			if (any || uid_eq(fid->uid, uid)) {
 				ret = fid;
+				refcount_inc(&ret->count);
 				break;
 			}
 		}
@@ -122,7 +169,10 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
 	fid = v9fs_fid_find(ds, uid, any);
 	if (fid) {
 		/* Found the parent fid do a lookup with that */
-		fid = p9_client_walk(fid, 1, &dentry->d_name.name, 1);
+		struct p9_fid *ofid = fid;
+
+		fid = p9_client_walk(ofid, 1, &dentry->d_name.name, 1);
+		p9_client_clunk(ofid);
 		goto fid_out;
 	}
 	up_read(&v9ses->rename_sem);
@@ -147,8 +197,10 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
 		v9fs_fid_add(dentry->d_sb->s_root, fid);
 	}
 	/* If we are root ourself just return that */
-	if (dentry->d_sb->s_root == dentry)
+	if (dentry->d_sb->s_root == dentry) {
+		refcount_inc(&fid->count);
 		return fid;
+	}
 	/*
 	 * Do a multipath walk with attached root.
 	 * When walking parent we need to make sure we
@@ -195,6 +247,7 @@ fid_out:
 			fid = ERR_PTR(-ENOENT);
 		} else {
 			__add_fid(dentry, fid);
+			refcount_inc(&fid->count);
 			spin_unlock(&dentry->d_lock);
 		}
 	}
@@ -245,11 +298,13 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
 struct p9_fid *v9fs_writeback_fid(struct dentry *dentry)
 {
 	int err;
-	struct p9_fid *fid;
+	struct p9_fid *fid, *ofid;
 
-	fid = clone_fid(v9fs_fid_lookup_with_uid(dentry, GLOBAL_ROOT_UID, 0));
+	ofid = v9fs_fid_lookup_with_uid(dentry, GLOBAL_ROOT_UID, 0);
+	fid = clone_fid(ofid);
 	if (IS_ERR(fid))
 		goto error_out;
+	p9_client_clunk(ofid);
 	/*
 	 * writeback fid will only be used to write back the
 	 * dirty pages. We always request for the open fid in read-write
diff --git a/fs/9p/fid.h b/fs/9p/fid.h
index 928b1093f511..f7f33509e169 100644
--- a/fs/9p/fid.h
+++ b/fs/9p/fid.h
@@ -15,12 +15,21 @@ static inline struct p9_fid *v9fs_parent_fid(struct dentry *dentry)
 }
 void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid);
 struct p9_fid *v9fs_writeback_fid(struct dentry *dentry);
+void v9fs_open_fid_add(struct inode *inode, struct p9_fid *fid);
 static inline struct p9_fid *clone_fid(struct p9_fid *fid)
 {
 	return IS_ERR(fid) ? fid :  p9_client_walk(fid, 0, NULL, 1);
 }
 static inline struct p9_fid *v9fs_fid_clone(struct dentry *dentry)
 {
-	return clone_fid(v9fs_fid_lookup(dentry));
+	struct p9_fid *fid, *nfid;
+
+	fid = v9fs_fid_lookup(dentry);
+	if (!fid || IS_ERR(fid))
+		return fid;
+
+	nfid = clone_fid(fid);
+	p9_client_clunk(fid);
+	return nfid;
 }
 #endif
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index 7d6f69aefd45..4b4292123b3d 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -85,6 +85,8 @@ static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 			retval = v9fs_refresh_inode_dotl(fid, inode);
 		else
 			retval = v9fs_refresh_inode(fid, inode);
+		p9_client_clunk(fid);
+
 		if (retval == -ENOENT)
 			return 0;
 		if (retval < 0)
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index 674d22bf4f6f..b6a5a0be444d 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -210,8 +210,12 @@ int v9fs_dir_release(struct inode *inode, struct file *filp)
 	fid = filp->private_data;
 	p9_debug(P9_DEBUG_VFS, "inode: %p filp: %p fid: %d\n",
 		 inode, filp, fid ? fid->fid : -1);
-	if (fid)
+	if (fid) {
+		spin_lock(&inode->i_lock);
+		hlist_del(&fid->ilist);
+		spin_unlock(&inode->i_lock);
 		p9_client_clunk(fid);
+	}
 	return 0;
 }
 
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index be5768949cb1..649f04f112dc 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -46,7 +46,7 @@ int v9fs_file_open(struct inode *inode, struct file *file)
 	int err;
 	struct v9fs_inode *v9inode;
 	struct v9fs_session_info *v9ses;
-	struct p9_fid *fid;
+	struct p9_fid *fid, *writeback_fid;
 	int omode;
 
 	p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, file);
@@ -85,17 +85,18 @@ int v9fs_file_open(struct inode *inode, struct file *file)
 		 * because we want write after unlink usecase
 		 * to work.
 		 */
-		fid = v9fs_writeback_fid(file_dentry(file));
+		writeback_fid = v9fs_writeback_fid(file_dentry(file));
 		if (IS_ERR(fid)) {
 			err = PTR_ERR(fid);
 			mutex_unlock(&v9inode->v_mutex);
 			goto out_error;
 		}
-		v9inode->writeback_fid = (void *) fid;
+		v9inode->writeback_fid = (void *) writeback_fid;
 	}
 	mutex_unlock(&v9inode->v_mutex);
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		v9fs_cache_inode_set_cookie(inode, file);
+	v9fs_open_fid_add(inode, fid);
 	return 0;
 out_error:
 	p9_client_clunk(file->private_data);
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index ae0c38ad1fcb..4a937fac1acb 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -256,6 +256,7 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses,
 	inode->i_rdev = rdev;
 	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 	inode->i_mapping->a_ops = &v9fs_addr_operations;
+	inode->i_private = NULL;
 
 	switch (mode & S_IFMT) {
 	case S_IFIFO:
@@ -550,6 +551,7 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags)
 	if (v9fs_proto_dotl(v9ses))
 		retval = p9_client_unlinkat(dfid, dentry->d_name.name,
 					    v9fs_at_to_dotl_flags(flags));
+	p9_client_clunk(dfid);
 	if (retval == -EOPNOTSUPP) {
 		/* Try the one based on path */
 		v9fid = v9fs_fid_clone(dentry);
@@ -570,6 +572,10 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags)
 
 		v9fs_invalidate_inode_attr(inode);
 		v9fs_invalidate_inode_attr(dir);
+
+		/* invalidate all fids associated with dentry */
+		/* NOTE: This will not include open fids */
+		dentry->d_op->d_release(dentry);
 	}
 	return retval;
 }
@@ -590,14 +596,12 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 {
 	int err;
 	const unsigned char *name;
-	struct p9_fid *dfid, *ofid, *fid;
+	struct p9_fid *dfid, *ofid = NULL, *fid = NULL;
 	struct inode *inode;
 
 	p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
 
 	err = 0;
-	ofid = NULL;
-	fid = NULL;
 	name = dentry->d_name.name;
 	dfid = v9fs_parent_fid(dentry);
 	if (IS_ERR(dfid)) {
@@ -611,12 +615,14 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 	if (IS_ERR(ofid)) {
 		err = PTR_ERR(ofid);
 		p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
+		p9_client_clunk(dfid);
 		return ERR_PTR(err);
 	}
 
 	err = p9_client_fcreate(ofid, name, perm, mode, extension);
 	if (err < 0) {
 		p9_debug(P9_DEBUG_VFS, "p9_client_fcreate failed %d\n", err);
+		p9_client_clunk(dfid);
 		goto error;
 	}
 
@@ -628,6 +634,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 			p9_debug(P9_DEBUG_VFS,
 				   "p9_client_walk failed %d\n", err);
 			fid = NULL;
+			p9_client_clunk(dfid);
 			goto error;
 		}
 		/*
@@ -638,11 +645,13 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 			err = PTR_ERR(inode);
 			p9_debug(P9_DEBUG_VFS,
 				   "inode creation failed %d\n", err);
+			p9_client_clunk(dfid);
 			goto error;
 		}
 		v9fs_fid_add(dentry, fid);
 		d_instantiate(dentry, inode);
 	}
+	p9_client_clunk(dfid);
 	return ofid;
 error:
 	if (ofid)
@@ -755,6 +764,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	 */
 	name = dentry->d_name.name;
 	fid = p9_client_walk(dfid, 1, &name, 1);
+	p9_client_clunk(dfid);
 	if (fid == ERR_PTR(-ENOENT))
 		inode = NULL;
 	else if (IS_ERR(fid))
@@ -792,6 +802,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid, *inode_fid;
 	struct dentry *res = NULL;
+	struct inode *inode;
 
 	if (d_in_lookup(dentry)) {
 		res = v9fs_vfs_lookup(dir, dentry, 0);
@@ -820,7 +831,8 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	}
 
 	v9fs_invalidate_inode_attr(dir);
-	v9inode = V9FS_I(d_inode(dentry));
+	inode = d_inode(dentry);
+	v9inode = V9FS_I(inode);
 	mutex_lock(&v9inode->v_mutex);
 	if ((v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) &&
 	    !v9inode->writeback_fid &&
@@ -848,6 +860,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	file->private_data = fid;
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		v9fs_cache_inode_set_cookie(d_inode(dentry), file);
+	v9fs_open_fid_add(inode, fid);
 
 	file->f_mode |= FMODE_CREATED;
 out:
@@ -902,7 +915,7 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct inode *old_inode;
 	struct inode *new_inode;
 	struct v9fs_session_info *v9ses;
-	struct p9_fid *oldfid;
+	struct p9_fid *oldfid, *dfid;
 	struct p9_fid *olddirfid;
 	struct p9_fid *newdirfid;
 	struct p9_wstat wstat;
@@ -919,13 +932,20 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (IS_ERR(oldfid))
 		return PTR_ERR(oldfid);
 
-	olddirfid = clone_fid(v9fs_parent_fid(old_dentry));
+	dfid = v9fs_parent_fid(old_dentry);
+	olddirfid = clone_fid(dfid);
+	if (dfid && !IS_ERR(dfid))
+		p9_client_clunk(dfid);
+
 	if (IS_ERR(olddirfid)) {
 		retval = PTR_ERR(olddirfid);
 		goto done;
 	}
 
-	newdirfid = clone_fid(v9fs_parent_fid(new_dentry));
+	dfid = v9fs_parent_fid(new_dentry);
+	newdirfid = clone_fid(dfid);
+	p9_client_clunk(dfid);
+
 	if (IS_ERR(newdirfid)) {
 		retval = PTR_ERR(newdirfid);
 		goto clunk_olddir;
@@ -982,6 +1002,7 @@ clunk_olddir:
 	p9_client_clunk(olddirfid);
 
 done:
+	p9_client_clunk(oldfid);
 	return retval;
 }
 
@@ -1014,6 +1035,7 @@ v9fs_vfs_getattr(const struct path *path, struct kstat *stat,
 		return PTR_ERR(fid);
 
 	st = p9_client_stat(fid);
+	p9_client_clunk(fid);
 	if (IS_ERR(st))
 		return PTR_ERR(st);
 
@@ -1034,7 +1056,7 @@ v9fs_vfs_getattr(const struct path *path, struct kstat *stat,
 
 static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
 {
-	int retval;
+	int retval, use_dentry = 0;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid = NULL;
 	struct p9_wstat wstat;
@@ -1050,8 +1072,10 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
 		fid = iattr->ia_file->private_data;
 		WARN_ON(!fid);
 	}
-	if (!fid)
+	if (!fid) {
 		fid = v9fs_fid_lookup(dentry);
+		use_dentry = 1;
+	}
 	if(IS_ERR(fid))
 		return PTR_ERR(fid);
 
@@ -1081,6 +1105,10 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
 		filemap_write_and_wait(d_inode(dentry)->i_mapping);
 
 	retval = p9_client_wstat(fid, &wstat);
+
+	if (use_dentry)
+		p9_client_clunk(fid);
+
 	if (retval < 0)
 		return retval;
 
@@ -1205,6 +1233,7 @@ static const char *v9fs_vfs_get_link(struct dentry *dentry,
 		return ERR_PTR(-EBADF);
 
 	st = p9_client_stat(fid);
+	p9_client_clunk(fid);
 	if (IS_ERR(st))
 		return ERR_CAST(st);
 
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 0028eccb665a..823c2eb5f1bf 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -296,6 +296,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 
 	/* instantiate inode and assign the unopened fid to the dentry */
 	fid = p9_client_walk(dfid, 1, &name, 1);
+	p9_client_clunk(dfid);
 	if (IS_ERR(fid)) {
 		err = PTR_ERR(fid);
 		p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
@@ -342,6 +343,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 	file->private_data = ofid;
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		v9fs_cache_inode_set_cookie(inode, file);
+	v9fs_open_fid_add(inode, ofid);
 	file->f_mode |= FMODE_CREATED;
 out:
 	v9fs_put_acl(dacl, pacl);
@@ -407,7 +409,6 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
 	err = p9_client_mkdir_dotl(dfid, name, mode, gid, &qid);
 	if (err < 0)
 		goto error;
-
 	fid = p9_client_walk(dfid, 1, &name, 1);
 	if (IS_ERR(fid)) {
 		err = PTR_ERR(fid);
@@ -451,6 +452,7 @@ error:
 	if (fid)
 		p9_client_clunk(fid);
 	v9fs_put_acl(dacl, pacl);
+	p9_client_clunk(dfid);
 	return err;
 }
 
@@ -478,6 +480,7 @@ v9fs_vfs_getattr_dotl(const struct path *path, struct kstat *stat,
 	 */
 
 	st = p9_client_getattr_dotl(fid, P9_STATS_ALL);
+	p9_client_clunk(fid);
 	if (IS_ERR(st))
 		return PTR_ERR(st);
 
@@ -539,7 +542,7 @@ static int v9fs_mapped_iattr_valid(int iattr_valid)
 
 int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
 {
-	int retval;
+	int retval, use_dentry = 0;
 	struct p9_fid *fid = NULL;
 	struct p9_iattr_dotl p9attr;
 	struct inode *inode = d_inode(dentry);
@@ -564,8 +567,10 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
 		fid = iattr->ia_file->private_data;
 		WARN_ON(!fid);
 	}
-	if (!fid)
+	if (!fid) {
 		fid = v9fs_fid_lookup(dentry);
+		use_dentry = 1;
+	}
 	if (IS_ERR(fid))
 		return PTR_ERR(fid);
 
@@ -574,8 +579,11 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
 		filemap_write_and_wait(inode->i_mapping);
 
 	retval = p9_client_setattr(fid, &p9attr);
-	if (retval < 0)
+	if (retval < 0) {
+		if (use_dentry)
+			p9_client_clunk(fid);
 		return retval;
+	}
 
 	if ((iattr->ia_valid & ATTR_SIZE) &&
 	    iattr->ia_size != i_size_read(inode))
@@ -587,9 +595,15 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
 	if (iattr->ia_valid & ATTR_MODE) {
 		/* We also want to update ACL when we update mode bits */
 		retval = v9fs_acl_chmod(inode, fid);
-		if (retval < 0)
+		if (retval < 0) {
+			if (use_dentry)
+				p9_client_clunk(fid);
 			return retval;
+		}
 	}
+	if (use_dentry)
+		p9_client_clunk(fid);
+
 	return 0;
 }
 
@@ -741,6 +755,7 @@ error:
 	if (fid)
 		p9_client_clunk(fid);
 
+	p9_client_clunk(dfid);
 	return err;
 }
 
@@ -769,11 +784,15 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
 		return PTR_ERR(dfid);
 
 	oldfid = v9fs_fid_lookup(old_dentry);
-	if (IS_ERR(oldfid))
+	if (IS_ERR(oldfid)) {
+		p9_client_clunk(dfid);
 		return PTR_ERR(oldfid);
+	}
 
 	err = p9_client_link(dfid, oldfid, dentry->d_name.name);
 
+	p9_client_clunk(dfid);
+	p9_client_clunk(oldfid);
 	if (err < 0) {
 		p9_debug(P9_DEBUG_VFS, "p9_client_link failed %d\n", err);
 		return err;
@@ -788,6 +807,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
 			return PTR_ERR(fid);
 
 		v9fs_refresh_inode_dotl(fid, d_inode(old_dentry));
+		p9_client_clunk(fid);
 	}
 	ihold(d_inode(old_dentry));
 	d_instantiate(dentry, d_inode(old_dentry));
@@ -886,6 +906,8 @@ error:
 	if (fid)
 		p9_client_clunk(fid);
 	v9fs_put_acl(dacl, pacl);
+	p9_client_clunk(dfid);
+
 	return err;
 }
 
@@ -914,6 +936,7 @@ v9fs_vfs_get_link_dotl(struct dentry *dentry,
 	if (IS_ERR(fid))
 		return ERR_CAST(fid);
 	retval = p9_client_readlink(fid, &target);
+	p9_client_clunk(fid);
 	if (retval)
 		return ERR_PTR(retval);
 	set_delayed_call(done, kfree_link, target);
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 9a21269b7234..5fce6e30bc5a 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -268,6 +268,7 @@ static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	}
 	res = simple_statfs(dentry, buf);
 done:
+	p9_client_clunk(fid);
 	return res;
 }
 
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index ac8ff8ca4c11..87217dd0433e 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -71,14 +71,17 @@ ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name,
 		       void *buffer, size_t buffer_size)
 {
 	struct p9_fid *fid;
+	int ret;
 
 	p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu\n",
 		 name, buffer_size);
 	fid = v9fs_fid_lookup(dentry);
 	if (IS_ERR(fid))
 		return PTR_ERR(fid);
+	ret = v9fs_fid_xattr_get(fid, name, buffer, buffer_size);
+	p9_client_clunk(fid);
 
-	return v9fs_fid_xattr_get(fid, name, buffer, buffer_size);
+	return ret;
 }
 
 /*
@@ -96,8 +99,15 @@ ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name,
 int v9fs_xattr_set(struct dentry *dentry, const char *name,
 		   const void *value, size_t value_len, int flags)
 {
-	struct p9_fid *fid = v9fs_fid_lookup(dentry);
-	return v9fs_fid_xattr_set(fid, name, value, value_len, flags);
+	int ret;
+	struct p9_fid *fid;
+
+	fid  = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid))
+		return PTR_ERR(fid);
+	ret = v9fs_fid_xattr_set(fid, name, value, value_len, flags);
+	p9_client_clunk(fid);
+	return ret;
 }
 
 int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 9068d5578a26..7bd659ad959e 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -350,7 +350,7 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode,
 				 unsigned blkoff)
 {
 	union afs_xdr_dirent *dire;
-	unsigned offset, next, curr;
+	unsigned offset, next, curr, nr_slots;
 	size_t nlen;
 	int tmp;
 
@@ -363,13 +363,12 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode,
 	     offset < AFS_DIR_SLOTS_PER_BLOCK;
 	     offset = next
 	     ) {
-		next = offset + 1;
-
 		/* skip entries marked unused in the bitmap */
 		if (!(block->hdr.bitmap[offset / 8] &
 		      (1 << (offset % 8)))) {
 			_debug("ENT[%zu.%u]: unused",
 			       blkoff / sizeof(union afs_xdr_dir_block), offset);
+			next = offset + 1;
 			if (offset >= curr)
 				ctx->pos = blkoff +
 					next * sizeof(union afs_xdr_dirent);
@@ -381,35 +380,39 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode,
 		nlen = strnlen(dire->u.name,
 			       sizeof(*block) -
 			       offset * sizeof(union afs_xdr_dirent));
+		if (nlen > AFSNAMEMAX - 1) {
+			_debug("ENT[%zu]: name too long (len %u/%zu)",
+			       blkoff / sizeof(union afs_xdr_dir_block),
+			       offset, nlen);
+			return afs_bad(dvnode, afs_file_error_dir_name_too_long);
+		}
 
 		_debug("ENT[%zu.%u]: %s %zu \"%s\"",
 		       blkoff / sizeof(union afs_xdr_dir_block), offset,
 		       (offset < curr ? "skip" : "fill"),
 		       nlen, dire->u.name);
 
-		/* work out where the next possible entry is */
-		for (tmp = nlen; tmp > 15; tmp -= sizeof(union afs_xdr_dirent)) {
-			if (next >= AFS_DIR_SLOTS_PER_BLOCK) {
-				_debug("ENT[%zu.%u]:"
-				       " %u travelled beyond end dir block"
-				       " (len %u/%zu)",
-				       blkoff / sizeof(union afs_xdr_dir_block),
-				       offset, next, tmp, nlen);
-				return afs_bad(dvnode, afs_file_error_dir_over_end);
-			}
-			if (!(block->hdr.bitmap[next / 8] &
-			      (1 << (next % 8)))) {
-				_debug("ENT[%zu.%u]:"
-				       " %u unmarked extension (len %u/%zu)",
+		nr_slots = afs_dir_calc_slots(nlen);
+		next = offset + nr_slots;
+		if (next > AFS_DIR_SLOTS_PER_BLOCK) {
+			_debug("ENT[%zu.%u]:"
+			       " %u extends beyond end dir block"
+			       " (len %zu)",
+			       blkoff / sizeof(union afs_xdr_dir_block),
+			       offset, next, nlen);
+			return afs_bad(dvnode, afs_file_error_dir_over_end);
+		}
+
+		/* Check that the name-extension dirents are all allocated */
+		for (tmp = 1; tmp < nr_slots; tmp++) {
+			unsigned int ix = offset + tmp;
+			if (!(block->hdr.bitmap[ix / 8] & (1 << (ix % 8)))) {
+				_debug("ENT[%zu.u]:"
+				       " %u unmarked extension (%u/%u)",
 				       blkoff / sizeof(union afs_xdr_dir_block),
-				       offset, next, tmp, nlen);
+				       offset, tmp, nr_slots);
 				return afs_bad(dvnode, afs_file_error_dir_unmarked_ext);
 			}
-
-			_debug("ENT[%zu.%u]: ext %u/%zu",
-			       blkoff / sizeof(union afs_xdr_dir_block),
-			       next, tmp, nlen);
-			next++;
 		}
 
 		/* skip if starts before the current position */
diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c
index 2ffe09abae7f..f4600c1353ad 100644
--- a/fs/afs/dir_edit.c
+++ b/fs/afs/dir_edit.c
@@ -215,8 +215,7 @@ void afs_edit_dir_add(struct afs_vnode *vnode,
 	}
 
 	/* Work out how many slots we're going to need. */
-	need_slots = round_up(12 + name->len + 1 + 4, AFS_DIR_DIRENT_SIZE);
-	need_slots /= AFS_DIR_DIRENT_SIZE;
+	need_slots = afs_dir_calc_slots(name->len);
 
 	meta_page = kmap(page0);
 	meta = &meta_page->blocks[0];
@@ -393,8 +392,7 @@ void afs_edit_dir_remove(struct afs_vnode *vnode,
 	}
 
 	/* Work out how many slots we're going to discard. */
-	need_slots = round_up(12 + name->len + 1 + 4, AFS_DIR_DIRENT_SIZE);
-	need_slots /= AFS_DIR_DIRENT_SIZE;
+	need_slots = afs_dir_calc_slots(name->len);
 
 	meta_page = kmap(page0);
 	meta = &meta_page->blocks[0];
diff --git a/fs/afs/xdr_fs.h b/fs/afs/xdr_fs.h
index 94f1f398eefa..8ca868164507 100644
--- a/fs/afs/xdr_fs.h
+++ b/fs/afs/xdr_fs.h
@@ -54,10 +54,16 @@ union afs_xdr_dirent {
 		__be16		hash_next;
 		__be32		vnode;
 		__be32		unique;
-		u8		name[16];
-		u8		overflow[4];	/* if any char of the name (inc
-						 * NUL) reaches here, consume
-						 * the next dirent too */
+		u8		name[];
+		/* When determining the number of dirent slots needed to
+		 * represent a directory entry, name should be assumed to be 16
+		 * bytes, due to a now-standardised (mis)calculation, but it is
+		 * in fact 20 bytes in size.  afs_dir_calc_slots() should be
+		 * used for this.
+		 *
+		 * For names longer than (16 or) 20 bytes, extra slots should
+		 * be annexed to this one using the extended_name format.
+		 */
 	} u;
 	u8			extended_name[32];
 } __packed;
@@ -96,4 +102,15 @@ struct afs_xdr_dir_page {
 	union afs_xdr_dir_block	blocks[AFS_DIR_BLOCKS_PER_PAGE];
 };
 
+/*
+ * Calculate the number of dirent slots required for any given name length.
+ * The calculation is made assuming the part of the name in the first slot is
+ * 16 bytes, rather than 20, but this miscalculation is now standardised.
+ */
+static inline unsigned int afs_dir_calc_slots(size_t name_len)
+{
+	name_len++; /* NUL-terminated */
+	return 1 + ((name_len + 15) / AFS_DIR_DIRENT_SIZE);
+}
+
 #endif /* XDR_FS_H */
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9e56ee1f2652..3b8963e228a1 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1,9 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- *  linux/fs/block_dev.c
- *
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *  Copyright (C) 2001  Andrea Arcangeli <andrea@suse.de> SuSE
+ *  Copyright (C) 2016 - 2020 Christoph Hellwig
  */
 
 #include <linux/init.h>
@@ -606,6 +605,8 @@ int thaw_bdev(struct block_device *bdev)
 		error = thaw_super(sb);
 	if (error)
 		bdev->bd_fsfreeze_count++;
+	else
+		bdev->bd_fsfreeze_sb = NULL;
 out:
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 	return error;
@@ -775,8 +776,11 @@ static struct kmem_cache * bdev_cachep __read_mostly;
 static struct inode *bdev_alloc_inode(struct super_block *sb)
 {
 	struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
+
 	if (!ei)
 		return NULL;
+	memset(&ei->bdev, 0, sizeof(ei->bdev));
+	ei->bdev.bd_bdi = &noop_backing_dev_info;
 	return &ei->vfs_inode;
 }
 
@@ -870,14 +874,12 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	mapping_set_gfp_mask(&inode->i_data, GFP_USER);
 
 	bdev = I_BDEV(inode);
-	memset(bdev, 0, sizeof(*bdev));
 	mutex_init(&bdev->bd_mutex);
 	mutex_init(&bdev->bd_fsfreeze_mutex);
 	spin_lock_init(&bdev->bd_size_lock);
 	bdev->bd_disk = disk;
 	bdev->bd_partno = partno;
 	bdev->bd_inode = inode;
-	bdev->bd_bdi = &noop_backing_dev_info;
 #ifdef CONFIG_SYSFS
 	INIT_LIST_HEAD(&bdev->bd_holder_disks);
 #endif
@@ -1056,7 +1058,6 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder)
 /**
  * bd_abort_claiming - abort claiming of a block device
  * @bdev: block device of interest
- * @whole: whole block device
  * @holder: holder that has claimed @bdev
  *
  * Abort claiming of a block device when the exclusive open failed. This can be
@@ -1829,6 +1830,7 @@ const struct file_operations def_blk_fops = {
 /**
  * lookup_bdev  - lookup a struct block_device by name
  * @pathname:	special file representing the block device
+ * @dev:	return value of the block device's dev_t
  *
  * Get a reference to the blockdevice at @pathname in the current
  * namespace if possible and return it.  Return ERR_PTR(error)
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 555cbcef6585..d9bf53d9ff90 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -42,6 +42,15 @@ enum {
 	 * to an inode.
 	 */
 	BTRFS_INODE_NO_XATTRS,
+	/*
+	 * Set when we are in a context where we need to start a transaction and
+	 * have dirty pages with the respective file range locked. This is to
+	 * ensure that when reserving space for the transaction, if we are low
+	 * on available space and need to flush delalloc, we will not flush
+	 * delalloc for this inode, because that could result in a deadlock (on
+	 * the file range, inode's io_tree).
+	 */
+	BTRFS_INODE_NO_DELALLOC_FLUSH,
 };
 
 /* in memory btrfs inode */
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 07810891e204..cc89b63d65a4 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2555,8 +2555,14 @@ out:
  * @p:		Holds all btree nodes along the search path
  * @root:	The root node of the tree
  * @key:	The key we are looking for
- * @ins_len:	Indicates purpose of search, for inserts it is 1, for
- *		deletions it's -1. 0 for plain searches
+ * @ins_len:	Indicates purpose of search:
+ *              >0  for inserts it's size of item inserted (*)
+ *              <0  for deletions
+ *               0  for plain searches, not modifying the tree
+ *
+ *              (*) If size of item inserted doesn't include
+ *              sizeof(struct btrfs_item), then p->search_for_extension must
+ *              be set.
  * @cow:	boolean should CoW operations be performed. Must always be 1
  *		when modifying the tree.
  *
@@ -2717,6 +2723,20 @@ cow_done:
 
 		if (level == 0) {
 			p->slots[level] = slot;
+			/*
+			 * Item key already exists. In this case, if we are
+			 * allowed to insert the item (for example, in dir_item
+			 * case, item key collision is allowed), it will be
+			 * merged with the original item. Only the item size
+			 * grows, no new btrfs item will be added. If
+			 * search_for_extension is not set, ins_len already
+			 * accounts the size btrfs_item, deduct it here so leaf
+			 * space check will be correct.
+			 */
+			if (ret == 0 && ins_len > 0 && !p->search_for_extension) {
+				ASSERT(ins_len >= sizeof(struct btrfs_item));
+				ins_len -= sizeof(struct btrfs_item);
+			}
 			if (ins_len > 0 &&
 			    btrfs_leaf_free_space(b) < ins_len) {
 				if (write_lock_level < 1) {
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 1d3c1e479f3d..e6e37591f1de 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -131,6 +131,8 @@ enum {
 	 * defrag
 	 */
 	BTRFS_FS_STATE_REMOUNTING,
+	/* Filesystem in RO mode */
+	BTRFS_FS_STATE_RO,
 	/* Track if a transaction abort has been reported on this filesystem */
 	BTRFS_FS_STATE_TRANS_ABORTED,
 	/*
@@ -367,6 +369,12 @@ struct btrfs_path {
 	unsigned int search_commit_root:1;
 	unsigned int need_commit_sem:1;
 	unsigned int skip_release_on_error:1;
+	/*
+	 * Indicate that new item (btrfs_search_slot) is extending already
+	 * existing item and ins_len contains only the data size and not item
+	 * header (ie. sizeof(struct btrfs_item) is not included).
+	 */
+	unsigned int search_for_extension:1;
 };
 #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \
 					sizeof(struct btrfs_item))
@@ -2885,10 +2893,26 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
  * If we remount the fs to be R/O or umount the fs, the cleaner needn't do
  * anything except sleeping. This function is used to check the status of
  * the fs.
+ * We check for BTRFS_FS_STATE_RO to avoid races with a concurrent remount,
+ * since setting and checking for SB_RDONLY in the superblock's flags is not
+ * atomic.
  */
 static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info)
 {
-	return fs_info->sb->s_flags & SB_RDONLY || btrfs_fs_closing(fs_info);
+	return test_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state) ||
+		btrfs_fs_closing(fs_info);
+}
+
+static inline void btrfs_set_sb_rdonly(struct super_block *sb)
+{
+	sb->s_flags |= SB_RDONLY;
+	set_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state);
+}
+
+static inline void btrfs_clear_sb_rdonly(struct super_block *sb)
+{
+	sb->s_flags &= ~SB_RDONLY;
+	clear_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state);
 }
 
 /* tree mod log functions from ctree.c */
@@ -3073,7 +3097,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       u32 min_type);
 
 int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr);
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
+			       bool in_reclaim_context);
 int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 			      unsigned int extra_bits,
 			      struct extent_state **cached_state);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index a98e33f232d5..324f646d6e5e 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -715,7 +715,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	 * flush all outstanding I/O and inode extent mappings before the
 	 * copy operation is declared as being finished
 	 */
-	ret = btrfs_start_delalloc_roots(fs_info, U64_MAX);
+	ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false);
 	if (ret) {
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return ret;
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 1db966bf85b2..2b8383d41144 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -199,16 +199,15 @@ static struct btrfs_block_group *find_next_block_group(
 static struct btrfs_block_group *peek_discard_list(
 					struct btrfs_discard_ctl *discard_ctl,
 					enum btrfs_discard_state *discard_state,
-					int *discard_index)
+					int *discard_index, u64 now)
 {
 	struct btrfs_block_group *block_group;
-	const u64 now = ktime_get_ns();
 
 	spin_lock(&discard_ctl->lock);
 again:
 	block_group = find_next_block_group(discard_ctl, now);
 
-	if (block_group && now > block_group->discard_eligible_time) {
+	if (block_group && now >= block_group->discard_eligible_time) {
 		if (block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED &&
 		    block_group->used != 0) {
 			if (btrfs_is_block_group_data_only(block_group))
@@ -222,12 +221,11 @@ again:
 			block_group->discard_state = BTRFS_DISCARD_EXTENTS;
 		}
 		discard_ctl->block_group = block_group;
+	}
+	if (block_group) {
 		*discard_state = block_group->discard_state;
 		*discard_index = block_group->discard_index;
-	} else {
-		block_group = NULL;
 	}
-
 	spin_unlock(&discard_ctl->lock);
 
 	return block_group;
@@ -330,28 +328,15 @@ void btrfs_discard_queue_work(struct btrfs_discard_ctl *discard_ctl,
 		btrfs_discard_schedule_work(discard_ctl, false);
 }
 
-/**
- * btrfs_discard_schedule_work - responsible for scheduling the discard work
- * @discard_ctl: discard control
- * @override: override the current timer
- *
- * Discards are issued by a delayed workqueue item.  @override is used to
- * update the current delay as the baseline delay interval is reevaluated on
- * transaction commit.  This is also maxed with any other rate limit.
- */
-void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
-				 bool override)
+static void __btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
+					  u64 now, bool override)
 {
 	struct btrfs_block_group *block_group;
-	const u64 now = ktime_get_ns();
-
-	spin_lock(&discard_ctl->lock);
 
 	if (!btrfs_run_discard_work(discard_ctl))
-		goto out;
-
+		return;
 	if (!override && delayed_work_pending(&discard_ctl->work))
-		goto out;
+		return;
 
 	block_group = find_next_block_group(discard_ctl, now);
 	if (block_group) {
@@ -393,7 +378,24 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
 		mod_delayed_work(discard_ctl->discard_workers,
 				 &discard_ctl->work, nsecs_to_jiffies(delay));
 	}
-out:
+}
+
+/*
+ * btrfs_discard_schedule_work - responsible for scheduling the discard work
+ * @discard_ctl:  discard control
+ * @override:     override the current timer
+ *
+ * Discards are issued by a delayed workqueue item.  @override is used to
+ * update the current delay as the baseline delay interval is reevaluated on
+ * transaction commit.  This is also maxed with any other rate limit.
+ */
+void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
+				 bool override)
+{
+	const u64 now = ktime_get_ns();
+
+	spin_lock(&discard_ctl->lock);
+	__btrfs_discard_schedule_work(discard_ctl, now, override);
 	spin_unlock(&discard_ctl->lock);
 }
 
@@ -438,13 +440,18 @@ static void btrfs_discard_workfn(struct work_struct *work)
 	int discard_index = 0;
 	u64 trimmed = 0;
 	u64 minlen = 0;
+	u64 now = ktime_get_ns();
 
 	discard_ctl = container_of(work, struct btrfs_discard_ctl, work.work);
 
 	block_group = peek_discard_list(discard_ctl, &discard_state,
-					&discard_index);
+					&discard_index, now);
 	if (!block_group || !btrfs_run_discard_work(discard_ctl))
 		return;
+	if (now < block_group->discard_eligible_time) {
+		btrfs_discard_schedule_work(discard_ctl, false);
+		return;
+	}
 
 	/* Perform discarding */
 	minlen = discard_minlen[discard_index];
@@ -474,13 +481,6 @@ static void btrfs_discard_workfn(struct work_struct *work)
 		discard_ctl->discard_extent_bytes += trimmed;
 	}
 
-	/*
-	 * Updated without locks as this is inside the workfn and nothing else
-	 * is reading the values
-	 */
-	discard_ctl->prev_discard = trimmed;
-	discard_ctl->prev_discard_time = ktime_get_ns();
-
 	/* Determine next steps for a block_group */
 	if (block_group->discard_cursor >= btrfs_block_group_end(block_group)) {
 		if (discard_state == BTRFS_DISCARD_BITMAPS) {
@@ -496,11 +496,13 @@ static void btrfs_discard_workfn(struct work_struct *work)
 		}
 	}
 
+	now = ktime_get_ns();
 	spin_lock(&discard_ctl->lock);
+	discard_ctl->prev_discard = trimmed;
+	discard_ctl->prev_discard_time = now;
 	discard_ctl->block_group = NULL;
+	__btrfs_discard_schedule_work(discard_ctl, now, false);
 	spin_unlock(&discard_ctl->lock);
-
-	btrfs_discard_schedule_work(discard_ctl, false);
 }
 
 /**
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 765deefda92b..6b35b7e88136 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1457,7 +1457,7 @@ void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info)
 		root = list_first_entry(&fs_info->allocated_roots,
 					struct btrfs_root, leak_list);
 		btrfs_err(fs_info, "leaked root %s refcount %d",
-			  btrfs_root_name(root->root_key.objectid, buf),
+			  btrfs_root_name(&root->root_key, buf),
 			  refcount_read(&root->refs));
 		while (refcount_read(&root->refs) > 1)
 			btrfs_put_root(root);
@@ -1729,7 +1729,7 @@ static int cleaner_kthread(void *arg)
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 sleep:
-		clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
+		clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
 		if (kthread_should_park())
 			kthread_parkme();
 		if (kthread_should_stop())
@@ -2830,6 +2830,9 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block
 		return -ENOMEM;
 	btrfs_init_delayed_root(fs_info->delayed_root);
 
+	if (sb_rdonly(sb))
+		set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);
+
 	return btrfs_alloc_stripe_hash_table(fs_info);
 }
 
@@ -2969,6 +2972,7 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 		}
 	}
 
+	ret = btrfs_find_orphan_roots(fs_info);
 out:
 	return ret;
 }
@@ -3383,10 +3387,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		}
 	}
 
-	ret = btrfs_find_orphan_roots(fs_info);
-	if (ret)
-		goto fail_qgroup;
-
 	fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true);
 	if (IS_ERR(fs_info->fs_root)) {
 		err = PTR_ERR(fs_info->fs_root);
@@ -4181,6 +4181,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
+	/* We shouldn't have any transaction open at this point */
+	ASSERT(list_empty(&fs_info->trans_list));
+
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
 	free_root_pointers(fs_info, true);
 	btrfs_free_fs_roots(fs_info);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 56ea380f5a17..d79b8369e6aa 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -844,6 +844,7 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
 	want = extent_ref_type(parent, owner);
 	if (insert) {
 		extra_size = btrfs_extent_inline_ref_size(want);
+		path->search_for_extension = 1;
 		path->keep_locks = 1;
 	} else
 		extra_size = -1;
@@ -996,6 +997,7 @@ again:
 out:
 	if (insert) {
 		path->keep_locks = 0;
+		path->search_for_extension = 0;
 		btrfs_unlock_up_safe(path, 1);
 	}
 	return err;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6e3b72e63e42..c9cee458e001 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -676,9 +676,7 @@ alloc_extent_state_atomic(struct extent_state *prealloc)
 
 static void extent_io_tree_panic(struct extent_io_tree *tree, int err)
 {
-	struct inode *inode = tree->private_data;
-
-	btrfs_panic(btrfs_sb(inode->i_sb), err,
+	btrfs_panic(tree->fs_info, err,
 	"locking error: extent tree was modified by another thread while locked");
 }
 
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 1545c22ef280..6ccfc019ad90 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -1016,8 +1016,10 @@ again:
 	}
 
 	btrfs_release_path(path);
+	path->search_for_extension = 1;
 	ret = btrfs_search_slot(trans, root, &file_key, path,
 				csum_size, 1);
+	path->search_for_extension = 0;
 	if (ret < 0)
 		goto out;
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8e23780acfae..a8e0a6b038d3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9390,7 +9390,9 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode
  * some fairly slow code that needs optimization. This walks the list
  * of all the inodes with pending delalloc and forces them to disk.
  */
-static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot)
+static int start_delalloc_inodes(struct btrfs_root *root,
+				 struct writeback_control *wbc, bool snapshot,
+				 bool in_reclaim_context)
 {
 	struct btrfs_inode *binode;
 	struct inode *inode;
@@ -9398,6 +9400,7 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot
 	struct list_head works;
 	struct list_head splice;
 	int ret = 0;
+	bool full_flush = wbc->nr_to_write == LONG_MAX;
 
 	INIT_LIST_HEAD(&works);
 	INIT_LIST_HEAD(&splice);
@@ -9411,6 +9414,11 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot
 
 		list_move_tail(&binode->delalloc_inodes,
 			       &root->delalloc_inodes);
+
+		if (in_reclaim_context &&
+		    test_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &binode->runtime_flags))
+			continue;
+
 		inode = igrab(&binode->vfs_inode);
 		if (!inode) {
 			cond_resched_lock(&root->delalloc_lock);
@@ -9421,18 +9429,24 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot
 		if (snapshot)
 			set_bit(BTRFS_INODE_SNAPSHOT_FLUSH,
 				&binode->runtime_flags);
-		work = btrfs_alloc_delalloc_work(inode);
-		if (!work) {
-			iput(inode);
-			ret = -ENOMEM;
-			goto out;
-		}
-		list_add_tail(&work->list, &works);
-		btrfs_queue_work(root->fs_info->flush_workers,
-				 &work->work);
-		if (*nr != U64_MAX) {
-			(*nr)--;
-			if (*nr == 0)
+		if (full_flush) {
+			work = btrfs_alloc_delalloc_work(inode);
+			if (!work) {
+				iput(inode);
+				ret = -ENOMEM;
+				goto out;
+			}
+			list_add_tail(&work->list, &works);
+			btrfs_queue_work(root->fs_info->flush_workers,
+					 &work->work);
+		} else {
+			ret = sync_inode(inode, wbc);
+			if (!ret &&
+			    test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+				     &BTRFS_I(inode)->runtime_flags))
+				ret = sync_inode(inode, wbc);
+			btrfs_add_delayed_iput(inode);
+			if (ret || wbc->nr_to_write <= 0)
 				goto out;
 		}
 		cond_resched();
@@ -9458,17 +9472,29 @@ out:
 
 int btrfs_start_delalloc_snapshot(struct btrfs_root *root)
 {
+	struct writeback_control wbc = {
+		.nr_to_write = LONG_MAX,
+		.sync_mode = WB_SYNC_NONE,
+		.range_start = 0,
+		.range_end = LLONG_MAX,
+	};
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	u64 nr = U64_MAX;
 
 	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
 		return -EROFS;
 
-	return start_delalloc_inodes(root, &nr, true);
+	return start_delalloc_inodes(root, &wbc, true, false);
 }
 
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr)
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
+			       bool in_reclaim_context)
 {
+	struct writeback_control wbc = {
+		.nr_to_write = (nr == U64_MAX) ? LONG_MAX : (unsigned long)nr,
+		.sync_mode = WB_SYNC_NONE,
+		.range_start = 0,
+		.range_end = LLONG_MAX,
+	};
 	struct btrfs_root *root;
 	struct list_head splice;
 	int ret;
@@ -9482,6 +9508,13 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr)
 	spin_lock(&fs_info->delalloc_root_lock);
 	list_splice_init(&fs_info->delalloc_roots, &splice);
 	while (!list_empty(&splice) && nr) {
+		/*
+		 * Reset nr_to_write here so we know that we're doing a full
+		 * flush.
+		 */
+		if (nr == U64_MAX)
+			wbc.nr_to_write = LONG_MAX;
+
 		root = list_first_entry(&splice, struct btrfs_root,
 					delalloc_root);
 		root = btrfs_grab_root(root);
@@ -9490,9 +9523,9 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr)
 			       &fs_info->delalloc_roots);
 		spin_unlock(&fs_info->delalloc_root_lock);
 
-		ret = start_delalloc_inodes(root, &nr, false);
+		ret = start_delalloc_inodes(root, &wbc, false, in_reclaim_context);
 		btrfs_put_root(root);
-		if (ret < 0)
+		if (ret < 0 || wbc.nr_to_write <= 0)
 			goto out;
 		spin_lock(&fs_info->delalloc_root_lock);
 	}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 703212ff50a5..dde49a791f3e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4951,7 +4951,7 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case BTRFS_IOC_SYNC: {
 		int ret;
 
-		ret = btrfs_start_delalloc_roots(fs_info, U64_MAX);
+		ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false);
 		if (ret)
 			return ret;
 		ret = btrfs_sync_fs(inode->i_sb, 1);
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index fe5e0026129d..aae1027bd76a 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -26,22 +26,22 @@ static const struct root_name_map root_map[] = {
 	{ BTRFS_DATA_RELOC_TREE_OBJECTID,	"DATA_RELOC_TREE"	},
 };
 
-const char *btrfs_root_name(u64 objectid, char *buf)
+const char *btrfs_root_name(const struct btrfs_key *key, char *buf)
 {
 	int i;
 
-	if (objectid == BTRFS_TREE_RELOC_OBJECTID) {
+	if (key->objectid == BTRFS_TREE_RELOC_OBJECTID) {
 		snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN,
-			 "TREE_RELOC offset=%llu", objectid);
+			 "TREE_RELOC offset=%llu", key->offset);
 		return buf;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(root_map); i++) {
-		if (root_map[i].id == objectid)
+		if (root_map[i].id == key->objectid)
 			return root_map[i].name;
 	}
 
-	snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", objectid);
+	snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", key->objectid);
 	return buf;
 }
 
diff --git a/fs/btrfs/print-tree.h b/fs/btrfs/print-tree.h
index 78b99385a503..8c3e9319ec4e 100644
--- a/fs/btrfs/print-tree.h
+++ b/fs/btrfs/print-tree.h
@@ -11,6 +11,6 @@
 
 void btrfs_print_leaf(struct extent_buffer *l);
 void btrfs_print_tree(struct extent_buffer *c, bool follow);
-const char *btrfs_root_name(u64 objectid, char *buf);
+const char *btrfs_root_name(const struct btrfs_key *key, char *buf);
 
 #endif
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index fe3046007f52..808370ada888 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -3190,6 +3190,12 @@ out:
 	return ret;
 }
 
+static bool rescan_should_stop(struct btrfs_fs_info *fs_info)
+{
+	return btrfs_fs_closing(fs_info) ||
+		test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
+}
+
 static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 {
 	struct btrfs_fs_info *fs_info = container_of(work, struct btrfs_fs_info,
@@ -3198,6 +3204,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 	struct btrfs_trans_handle *trans = NULL;
 	int err = -ENOMEM;
 	int ret = 0;
+	bool stopped = false;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -3210,7 +3217,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 	path->skip_locking = 1;
 
 	err = 0;
-	while (!err && !btrfs_fs_closing(fs_info)) {
+	while (!err && !(stopped = rescan_should_stop(fs_info))) {
 		trans = btrfs_start_transaction(fs_info->fs_root, 0);
 		if (IS_ERR(trans)) {
 			err = PTR_ERR(trans);
@@ -3253,7 +3260,7 @@ out:
 	}
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
-	if (!btrfs_fs_closing(fs_info))
+	if (!stopped)
 		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
 	if (trans) {
 		ret = update_qgroup_status_item(trans);
@@ -3272,7 +3279,7 @@ out:
 
 	btrfs_end_transaction(trans);
 
-	if (btrfs_fs_closing(fs_info)) {
+	if (stopped) {
 		btrfs_info(fs_info, "qgroup scan paused");
 	} else if (err >= 0) {
 		btrfs_info(fs_info, "qgroup scan completed%s",
@@ -3531,16 +3538,6 @@ static int try_flush_qgroup(struct btrfs_root *root)
 	bool can_commit = true;
 
 	/*
-	 * We don't want to run flush again and again, so if there is a running
-	 * one, we won't try to start a new flush, but exit directly.
-	 */
-	if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) {
-		wait_event(root->qgroup_flush_wait,
-			!test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state));
-		return 0;
-	}
-
-	/*
 	 * If current process holds a transaction, we shouldn't flush, as we
 	 * assume all space reservation happens before a transaction handle is
 	 * held.
@@ -3554,6 +3551,26 @@ static int try_flush_qgroup(struct btrfs_root *root)
 	    current->journal_info != BTRFS_SEND_TRANS_STUB)
 		can_commit = false;
 
+	/*
+	 * We don't want to run flush again and again, so if there is a running
+	 * one, we won't try to start a new flush, but exit directly.
+	 */
+	if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) {
+		/*
+		 * We are already holding a transaction, thus we can block other
+		 * threads from flushing.  So exit right now. This increases
+		 * the chance of EDQUOT for heavy load and near limit cases.
+		 * But we can argue that if we're already near limit, EDQUOT is
+		 * unavoidable anyway.
+		 */
+		if (!can_commit)
+			return 0;
+
+		wait_event(root->qgroup_flush_wait,
+			!test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state));
+		return 0;
+	}
+
 	ret = btrfs_start_delalloc_snapshot(root);
 	if (ret < 0)
 		goto out;
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index ab80896315be..b03e7891394e 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -89,6 +89,19 @@ static int copy_inline_to_page(struct btrfs_inode *inode,
 	if (ret)
 		goto out_unlock;
 
+	/*
+	 * After dirtying the page our caller will need to start a transaction,
+	 * and if we are low on metadata free space, that can cause flushing of
+	 * delalloc for all inodes in order to get metadata space released.
+	 * However we are holding the range locked for the whole duration of
+	 * the clone/dedupe operation, so we may deadlock if that happens and no
+	 * other task releases enough space. So mark this inode as not being
+	 * possible to flush to avoid such deadlock. We will clear that flag
+	 * when we finish cloning all extents, since a transaction is started
+	 * after finding each extent to clone.
+	 */
+	set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags);
+
 	if (comp_type == BTRFS_COMPRESS_NONE) {
 		char *map;
 
@@ -549,6 +562,8 @@ process_slot:
 out:
 	btrfs_free_path(path);
 	kvfree(buf);
+	clear_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &BTRFS_I(inode)->runtime_flags);
+
 	return ret;
 }
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 19b7db8b2117..df63ef64c5c0 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2975,11 +2975,16 @@ static int delete_v1_space_cache(struct extent_buffer *leaf,
 		return 0;
 
 	for (i = 0; i < btrfs_header_nritems(leaf); i++) {
+		u8 type;
+
 		btrfs_item_key_to_cpu(leaf, &key, i);
 		if (key.type != BTRFS_EXTENT_DATA_KEY)
 			continue;
 		ei = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_REG &&
+		type = btrfs_file_extent_type(leaf, ei);
+
+		if ((type == BTRFS_FILE_EXTENT_REG ||
+		     type == BTRFS_FILE_EXTENT_PREALLOC) &&
 		    btrfs_file_extent_disk_bytenr(leaf, ei) == data_bytenr) {
 			found = true;
 			space_cache_ino = key.objectid;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index d719a2755a40..ae97f4dbaff3 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -236,6 +236,7 @@ struct waiting_dir_move {
 	 * after this directory is moved, we can try to rmdir the ino rmdir_ino.
 	 */
 	u64 rmdir_ino;
+	u64 rmdir_gen;
 	bool orphanized;
 };
 
@@ -316,7 +317,7 @@ static int is_waiting_for_move(struct send_ctx *sctx, u64 ino);
 static struct waiting_dir_move *
 get_waiting_dir_move(struct send_ctx *sctx, u64 ino);
 
-static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino);
+static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen);
 
 static int need_send_hole(struct send_ctx *sctx)
 {
@@ -2299,7 +2300,7 @@ static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen,
 
 		fs_path_reset(name);
 
-		if (is_waiting_for_rm(sctx, ino)) {
+		if (is_waiting_for_rm(sctx, ino, gen)) {
 			ret = gen_unique_name(sctx, ino, gen, name);
 			if (ret < 0)
 				goto out;
@@ -2858,8 +2859,8 @@ out:
 	return ret;
 }
 
-static struct orphan_dir_info *
-add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
+static struct orphan_dir_info *add_orphan_dir_info(struct send_ctx *sctx,
+						   u64 dir_ino, u64 dir_gen)
 {
 	struct rb_node **p = &sctx->orphan_dirs.rb_node;
 	struct rb_node *parent = NULL;
@@ -2868,20 +2869,23 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
 	while (*p) {
 		parent = *p;
 		entry = rb_entry(parent, struct orphan_dir_info, node);
-		if (dir_ino < entry->ino) {
+		if (dir_ino < entry->ino)
 			p = &(*p)->rb_left;
-		} else if (dir_ino > entry->ino) {
+		else if (dir_ino > entry->ino)
 			p = &(*p)->rb_right;
-		} else {
+		else if (dir_gen < entry->gen)
+			p = &(*p)->rb_left;
+		else if (dir_gen > entry->gen)
+			p = &(*p)->rb_right;
+		else
 			return entry;
-		}
 	}
 
 	odi = kmalloc(sizeof(*odi), GFP_KERNEL);
 	if (!odi)
 		return ERR_PTR(-ENOMEM);
 	odi->ino = dir_ino;
-	odi->gen = 0;
+	odi->gen = dir_gen;
 	odi->last_dir_index_offset = 0;
 
 	rb_link_node(&odi->node, parent, p);
@@ -2889,8 +2893,8 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
 	return odi;
 }
 
-static struct orphan_dir_info *
-get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
+static struct orphan_dir_info *get_orphan_dir_info(struct send_ctx *sctx,
+						   u64 dir_ino, u64 gen)
 {
 	struct rb_node *n = sctx->orphan_dirs.rb_node;
 	struct orphan_dir_info *entry;
@@ -2901,15 +2905,19 @@ get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
 			n = n->rb_left;
 		else if (dir_ino > entry->ino)
 			n = n->rb_right;
+		else if (gen < entry->gen)
+			n = n->rb_left;
+		else if (gen > entry->gen)
+			n = n->rb_right;
 		else
 			return entry;
 	}
 	return NULL;
 }
 
-static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino)
+static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen)
 {
-	struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino);
+	struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino, gen);
 
 	return odi != NULL;
 }
@@ -2954,7 +2962,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	key.type = BTRFS_DIR_INDEX_KEY;
 	key.offset = 0;
 
-	odi = get_orphan_dir_info(sctx, dir);
+	odi = get_orphan_dir_info(sctx, dir, dir_gen);
 	if (odi)
 		key.offset = odi->last_dir_index_offset;
 
@@ -2985,7 +2993,7 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 
 		dm = get_waiting_dir_move(sctx, loc.objectid);
 		if (dm) {
-			odi = add_orphan_dir_info(sctx, dir);
+			odi = add_orphan_dir_info(sctx, dir, dir_gen);
 			if (IS_ERR(odi)) {
 				ret = PTR_ERR(odi);
 				goto out;
@@ -2993,12 +3001,13 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 			odi->gen = dir_gen;
 			odi->last_dir_index_offset = found_key.offset;
 			dm->rmdir_ino = dir;
+			dm->rmdir_gen = dir_gen;
 			ret = 0;
 			goto out;
 		}
 
 		if (loc.objectid > send_progress) {
-			odi = add_orphan_dir_info(sctx, dir);
+			odi = add_orphan_dir_info(sctx, dir, dir_gen);
 			if (IS_ERR(odi)) {
 				ret = PTR_ERR(odi);
 				goto out;
@@ -3038,6 +3047,7 @@ static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino, bool orphanized)
 		return -ENOMEM;
 	dm->ino = ino;
 	dm->rmdir_ino = 0;
+	dm->rmdir_gen = 0;
 	dm->orphanized = orphanized;
 
 	while (*p) {
@@ -3183,7 +3193,7 @@ static int path_loop(struct send_ctx *sctx, struct fs_path *name,
 	while (ino != BTRFS_FIRST_FREE_OBJECTID) {
 		fs_path_reset(name);
 
-		if (is_waiting_for_rm(sctx, ino))
+		if (is_waiting_for_rm(sctx, ino, gen))
 			break;
 		if (is_waiting_for_move(sctx, ino)) {
 			if (*ancestor_ino == 0)
@@ -3223,6 +3233,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 	u64 parent_ino, parent_gen;
 	struct waiting_dir_move *dm = NULL;
 	u64 rmdir_ino = 0;
+	u64 rmdir_gen;
 	u64 ancestor;
 	bool is_orphan;
 	int ret;
@@ -3237,6 +3248,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 	dm = get_waiting_dir_move(sctx, pm->ino);
 	ASSERT(dm);
 	rmdir_ino = dm->rmdir_ino;
+	rmdir_gen = dm->rmdir_gen;
 	is_orphan = dm->orphanized;
 	free_waiting_dir_move(sctx, dm);
 
@@ -3273,6 +3285,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 			dm = get_waiting_dir_move(sctx, pm->ino);
 			ASSERT(dm);
 			dm->rmdir_ino = rmdir_ino;
+			dm->rmdir_gen = rmdir_gen;
 		}
 		goto out;
 	}
@@ -3291,7 +3304,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 		struct orphan_dir_info *odi;
 		u64 gen;
 
-		odi = get_orphan_dir_info(sctx, rmdir_ino);
+		odi = get_orphan_dir_info(sctx, rmdir_ino, rmdir_gen);
 		if (!odi) {
 			/* already deleted */
 			goto finish;
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 64099565ab8f..e8347461c8dd 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -532,7 +532,9 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
 
 	loops = 0;
 	while ((delalloc_bytes || dio_bytes) && loops < 3) {
-		btrfs_start_delalloc_roots(fs_info, items);
+		u64 nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;
+
+		btrfs_start_delalloc_roots(fs_info, nr_pages, true);
 
 		loops++;
 		if (wait_ordered && !trans) {
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 022f20810089..12d7d3be7cd4 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -175,7 +175,7 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function
 	btrfs_discard_stop(fs_info);
 
 	/* btrfs handle error by forcing the filesystem readonly */
-	sb->s_flags |= SB_RDONLY;
+	btrfs_set_sb_rdonly(sb);
 	btrfs_info(fs_info, "forced readonly");
 	/*
 	 * Note that a running device replace operation is not canceled here
@@ -1953,7 +1953,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		/* avoid complains from lockdep et al. */
 		up(&fs_info->uuid_tree_rescan_sem);
 
-		sb->s_flags |= SB_RDONLY;
+		btrfs_set_sb_rdonly(sb);
 
 		/*
 		 * Setting SB_RDONLY will put the cleaner thread to
@@ -1964,10 +1964,42 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 
+		/*
+		 * The cleaner task could be already running before we set the
+		 * flag BTRFS_FS_STATE_RO (and SB_RDONLY in the superblock).
+		 * We must make sure that after we finish the remount, i.e. after
+		 * we call btrfs_commit_super(), the cleaner can no longer start
+		 * a transaction - either because it was dropping a dead root,
+		 * running delayed iputs or deleting an unused block group (the
+		 * cleaner picked a block group from the list of unused block
+		 * groups before we were able to in the previous call to
+		 * btrfs_delete_unused_bgs()).
+		 */
+		wait_on_bit(&fs_info->flags, BTRFS_FS_CLEANER_RUNNING,
+			    TASK_UNINTERRUPTIBLE);
+
+		/*
+		 * We've set the superblock to RO mode, so we might have made
+		 * the cleaner task sleep without running all pending delayed
+		 * iputs. Go through all the delayed iputs here, so that if an
+		 * unmount happens without remounting RW we don't end up at
+		 * finishing close_ctree() with a non-empty list of delayed
+		 * iputs.
+		 */
+		btrfs_run_delayed_iputs(fs_info);
+
 		btrfs_dev_replace_suspend_for_unmount(fs_info);
 		btrfs_scrub_cancel(fs_info);
 		btrfs_pause_balance(fs_info);
 
+		/*
+		 * Pause the qgroup rescan worker if it is running. We don't want
+		 * it to be still running after we are in RO mode, as after that,
+		 * by the time we unmount, it might have left a transaction open,
+		 * so we would leak the transaction and/or crash.
+		 */
+		btrfs_qgroup_wait_for_completion(fs_info, false);
+
 		ret = btrfs_commit_super(fs_info);
 		if (ret)
 			goto restore;
@@ -2006,7 +2038,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		if (ret)
 			goto restore;
 
-		sb->s_flags &= ~SB_RDONLY;
+		btrfs_clear_sb_rdonly(sb);
 
 		set_bit(BTRFS_FS_OPEN, &fs_info->flags);
 	}
@@ -2028,6 +2060,8 @@ restore:
 	/* We've hit an error - don't reset SB_RDONLY */
 	if (sb_rdonly(sb))
 		old_flags |= SB_RDONLY;
+	if (!(old_flags & SB_RDONLY))
+		clear_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);
 	sb->s_flags = old_flags;
 	fs_info->mount_opt = old_opts;
 	fs_info->compress_type = old_compress_type;
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 8ca334d554af..6bd97bd4cb37 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -55,8 +55,14 @@ struct inode *btrfs_new_test_inode(void)
 	struct inode *inode;
 
 	inode = new_inode(test_mnt->mnt_sb);
-	if (inode)
-		inode_init_owner(inode, NULL, S_IFREG);
+	if (!inode)
+		return NULL;
+
+	inode->i_mode = S_IFREG;
+	BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
+	BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
+	BTRFS_I(inode)->location.offset = 0;
+	inode_init_owner(inode, NULL, S_IFREG);
 
 	return inode;
 }
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 04022069761d..c9874b12d337 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -232,11 +232,6 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		return ret;
 	}
 
-	inode->i_mode = S_IFREG;
-	BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
-	BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
-	BTRFS_I(inode)->location.offset = 0;
-
 	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
 	if (!fs_info) {
 		test_std_err(TEST_ALLOC_FS_INFO);
@@ -835,10 +830,6 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 		return ret;
 	}
 
-	BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
-	BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
-	BTRFS_I(inode)->location.offset = 0;
-
 	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
 	if (!fs_info) {
 		test_std_err(TEST_ALLOC_FS_INFO);
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 028e733e42f3..582061c7b547 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -760,6 +760,7 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf,
 {
 	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	u64 length;
+	u64 chunk_end;
 	u64 stripe_len;
 	u16 num_stripes;
 	u16 sub_stripes;
@@ -814,6 +815,12 @@ int btrfs_check_chunk_valid(struct extent_buffer *leaf,
 			  "invalid chunk length, have %llu", length);
 		return -EUCLEAN;
 	}
+	if (unlikely(check_add_overflow(logical, length, &chunk_end))) {
+		chunk_err(leaf, chunk, logical,
+"invalid chunk logical start and length, have logical start %llu length %llu",
+			  logical, length);
+		return -EUCLEAN;
+	}
 	if (unlikely(!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN)) {
 		chunk_err(leaf, chunk, logical,
 			  "invalid chunk stripe length: %llu",
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ee086fc56c30..b62be84833e9 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2592,7 +2592,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
 
 	if (seeding_dev) {
-		sb->s_flags &= ~SB_RDONLY;
+		btrfs_clear_sb_rdonly(sb);
 		ret = btrfs_prepare_sprout(fs_info);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -2728,7 +2728,7 @@ error_sysfs:
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 error_trans:
 	if (seeding_dev)
-		sb->s_flags |= SB_RDONLY;
+		btrfs_set_sb_rdonly(sb);
 	if (trans)
 		btrfs_end_transaction(trans);
 error_free_zone:
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 98c15ff2e599..840587037b59 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2475,6 +2475,22 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
 	return r;
 }
 
+static void encode_timestamp_and_gids(void **p,
+				      const struct ceph_mds_request *req)
+{
+	struct ceph_timespec ts;
+	int i;
+
+	ceph_encode_timespec64(&ts, &req->r_stamp);
+	ceph_encode_copy(p, &ts, sizeof(ts));
+
+	/* gid_list */
+	ceph_encode_32(p, req->r_cred->group_info->ngroups);
+	for (i = 0; i < req->r_cred->group_info->ngroups; i++)
+		ceph_encode_64(p, from_kgid(&init_user_ns,
+					    req->r_cred->group_info->gid[i]));
+}
+
 /*
  * called under mdsc->mutex
  */
@@ -2491,7 +2507,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	u64 ino1 = 0, ino2 = 0;
 	int pathlen1 = 0, pathlen2 = 0;
 	bool freepath1 = false, freepath2 = false;
-	int len, i;
+	int len;
 	u16 releases;
 	void *p, *end;
 	int ret;
@@ -2517,17 +2533,10 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		goto out_free1;
 	}
 
-	if (legacy) {
-		/* Old style */
-		len = sizeof(*head);
-	} else {
-		/* New style: add gid_list and any later fields */
-		len = sizeof(struct ceph_mds_request_head) + sizeof(u32) +
-		      (sizeof(u64) * req->r_cred->group_info->ngroups);
-	}
-
+	len = legacy ? sizeof(*head) : sizeof(struct ceph_mds_request_head);
 	len += pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
 		sizeof(struct ceph_timespec);
+	len += sizeof(u32) + (sizeof(u64) * req->r_cred->group_info->ngroups);
 
 	/* calculate (max) length for cap releases */
 	len += sizeof(struct ceph_mds_request_release) *
@@ -2548,7 +2557,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	msg->hdr.tid = cpu_to_le64(req->r_tid);
 
 	/*
-	 * The old ceph_mds_request_header didn't contain a version field, and
+	 * The old ceph_mds_request_head didn't contain a version field, and
 	 * one was added when we moved the message version from 3->4.
 	 */
 	if (legacy) {
@@ -2609,20 +2618,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 
 	head->num_releases = cpu_to_le16(releases);
 
-	/* time stamp */
-	{
-		struct ceph_timespec ts;
-		ceph_encode_timespec64(&ts, &req->r_stamp);
-		ceph_encode_copy(&p, &ts, sizeof(ts));
-	}
-
-	/* gid list */
-	if (!legacy) {
-		ceph_encode_32(&p, req->r_cred->group_info->ngroups);
-		for (i = 0; i < req->r_cred->group_info->ngroups; i++)
-			ceph_encode_64(&p, from_kgid(&init_user_ns,
-				       req->r_cred->group_info->gid[i]));
-	}
+	encode_timestamp_and_gids(&p, req);
 
 	if (WARN_ON_ONCE(p > end)) {
 		ceph_msg_put(msg);
@@ -2730,13 +2726,8 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 		/* remove cap/dentry releases from message */
 		rhead->num_releases = 0;
 
-		/* time stamp */
 		p = msg->front.iov_base + req->r_request_release_offset;
-		{
-			struct ceph_timespec ts;
-			ceph_encode_timespec64(&ts, &req->r_stamp);
-			ceph_encode_copy(&p, &ts, sizeof(ts));
-		}
+		encode_timestamp_and_gids(&p, req);
 
 		msg->front.iov_len = p - msg->front.iov_base;
 		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c
index c594e588a8b5..d35f599aa00e 100644
--- a/fs/cifs/cifs_swn.c
+++ b/fs/cifs/cifs_swn.c
@@ -285,8 +285,6 @@ static struct cifs_swn_reg *cifs_find_swn_reg(struct cifs_tcon *tcon)
 			continue;
 		}
 
-		mutex_unlock(&cifs_swnreg_idr_mutex);
-
 		cifs_dbg(FYI, "Existing swn registration for %s:%s found\n", swnreg->net_name,
 				swnreg->share_name);
 
@@ -482,48 +480,51 @@ static int cifs_swn_store_swn_addr(const struct sockaddr_storage *new,
 
 static int cifs_swn_reconnect(struct cifs_tcon *tcon, struct sockaddr_storage *addr)
 {
+	int ret = 0;
+
 	/* Store the reconnect address */
 	mutex_lock(&tcon->ses->server->srv_mutex);
-	if (!cifs_sockaddr_equal(&tcon->ses->server->dstaddr, addr)) {
-		int ret;
-
-		ret = cifs_swn_store_swn_addr(addr, &tcon->ses->server->dstaddr,
-				&tcon->ses->server->swn_dstaddr);
-		if (ret < 0) {
-			cifs_dbg(VFS, "%s: failed to store address: %d\n", __func__, ret);
-			return ret;
-		}
-		tcon->ses->server->use_swn_dstaddr = true;
+	if (cifs_sockaddr_equal(&tcon->ses->server->dstaddr, addr))
+		goto unlock;
 
-		/*
-		 * Unregister to stop receiving notifications for the old IP address.
-		 */
-		ret = cifs_swn_unregister(tcon);
-		if (ret < 0) {
-			cifs_dbg(VFS, "%s: Failed to unregister for witness notifications: %d\n",
-					__func__, ret);
-			return ret;
-		}
+	ret = cifs_swn_store_swn_addr(addr, &tcon->ses->server->dstaddr,
+				      &tcon->ses->server->swn_dstaddr);
+	if (ret < 0) {
+		cifs_dbg(VFS, "%s: failed to store address: %d\n", __func__, ret);
+		goto unlock;
+	}
+	tcon->ses->server->use_swn_dstaddr = true;
 
-		/*
-		 * And register to receive notifications for the new IP address now that we have
-		 * stored the new address.
-		 */
-		ret = cifs_swn_register(tcon);
-		if (ret < 0) {
-			cifs_dbg(VFS, "%s: Failed to register for witness notifications: %d\n",
-					__func__, ret);
-			return ret;
-		}
+	/*
+	 * Unregister to stop receiving notifications for the old IP address.
+	 */
+	ret = cifs_swn_unregister(tcon);
+	if (ret < 0) {
+		cifs_dbg(VFS, "%s: Failed to unregister for witness notifications: %d\n",
+			 __func__, ret);
+		goto unlock;
+	}
 
-		spin_lock(&GlobalMid_Lock);
-		if (tcon->ses->server->tcpStatus != CifsExiting)
-			tcon->ses->server->tcpStatus = CifsNeedReconnect;
-		spin_unlock(&GlobalMid_Lock);
+	/*
+	 * And register to receive notifications for the new IP address now that we have
+	 * stored the new address.
+	 */
+	ret = cifs_swn_register(tcon);
+	if (ret < 0) {
+		cifs_dbg(VFS, "%s: Failed to register for witness notifications: %d\n",
+			 __func__, ret);
+		goto unlock;
 	}
+
+	spin_lock(&GlobalMid_Lock);
+	if (tcon->ses->server->tcpStatus != CifsExiting)
+		tcon->ses->server->tcpStatus = CifsNeedReconnect;
+	spin_unlock(&GlobalMid_Lock);
+
+unlock:
 	mutex_unlock(&tcon->ses->server->srv_mutex);
 
-	return 0;
+	return ret;
 }
 
 static int cifs_swn_client_move(struct cifs_swn_reg *swnreg, struct sockaddr_storage *addr)
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 2f21f89871cc..562913e2b3f2 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1195,7 +1195,8 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
 }
 
 struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
-		const struct cifs_fid *cifsfid, u32 *pacllen)
+				      const struct cifs_fid *cifsfid, u32 *pacllen,
+				      u32 __maybe_unused unused)
 {
 	struct cifs_ntsd *pntsd = NULL;
 	unsigned int xid;
@@ -1263,7 +1264,7 @@ static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb,
 /* Retrieve an ACL from the server */
 struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb,
 				      struct inode *inode, const char *path,
-				      u32 *pacllen)
+			       u32 *pacllen, u32 info)
 {
 	struct cifs_ntsd *pntsd = NULL;
 	struct cifsFileInfo *open_file = NULL;
@@ -1273,7 +1274,7 @@ struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb,
 	if (!open_file)
 		return get_cifs_acl_by_path(cifs_sb, path, pacllen);
 
-	pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen);
+	pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen, info);
 	cifsFileInfo_put(open_file);
 	return pntsd;
 }
@@ -1338,6 +1339,7 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
 	int rc = 0;
 	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
 	struct smb_version_operations *ops;
+	const u32 info = 0;
 
 	cifs_dbg(NOISY, "converting ACL to mode for %s\n", path);
 
@@ -1347,9 +1349,9 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
 	ops = tlink_tcon(tlink)->ses->server->ops;
 
 	if (pfid && (ops->get_acl_by_fid))
-		pntsd = ops->get_acl_by_fid(cifs_sb, pfid, &acllen);
+		pntsd = ops->get_acl_by_fid(cifs_sb, pfid, &acllen, info);
 	else if (ops->get_acl)
-		pntsd = ops->get_acl(cifs_sb, inode, path, &acllen);
+		pntsd = ops->get_acl(cifs_sb, inode, path, &acllen, info);
 	else {
 		cifs_put_tlink(tlink);
 		return -EOPNOTSUPP;
@@ -1388,6 +1390,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
 	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
 	struct smb_version_operations *ops;
 	bool mode_from_sid, id_from_sid;
+	const u32 info = 0;
 
 	if (IS_ERR(tlink))
 		return PTR_ERR(tlink);
@@ -1403,7 +1406,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
 		return -EOPNOTSUPP;
 	}
 
-	pntsd = ops->get_acl(cifs_sb, inode, path, &secdesclen);
+	pntsd = ops->get_acl(cifs_sb, inode, path, &secdesclen, info);
 	if (IS_ERR(pntsd)) {
 		rc = PTR_ERR(pntsd);
 		cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 720d0f6a982d..50fcb65920e8 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -456,9 +456,9 @@ struct smb_version_operations {
 			const char *, const void *, const __u16,
 			const struct nls_table *, struct cifs_sb_info *);
 	struct cifs_ntsd * (*get_acl)(struct cifs_sb_info *, struct inode *,
-			const char *, u32 *);
+			const char *, u32 *, u32);
 	struct cifs_ntsd * (*get_acl_by_fid)(struct cifs_sb_info *,
-			const struct cifs_fid *, u32 *);
+			const struct cifs_fid *, u32 *, u32);
 	int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *,
 			int);
 	/* writepages retry size */
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index ce51183ecaf4..64fe5a47b5e8 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -240,6 +240,8 @@
 #define SYNCHRONIZE           0x00100000  /* The file handle can waited on to */
 					  /* synchronize with the completion  */
 					  /* of an input/output request       */
+#define SYSTEM_SECURITY       0x01000000  /* The system access control list   */
+					  /* can be read and changed          */
 #define GENERIC_ALL           0x10000000
 #define GENERIC_EXECUTE       0x20000000
 #define GENERIC_WRITE         0x40000000
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index bd1c9b038568..340ff81ee87b 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -218,9 +218,9 @@ extern int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb,
 extern int id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
 					kuid_t uid, kgid_t gid);
 extern struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *, struct inode *,
-					const char *, u32 *);
+				      const char *, u32 *, u32);
 extern struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *,
-						const struct cifs_fid *, u32 *);
+				const struct cifs_fid *, u32 *, u32);
 extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *,
 				const char *, int);
 extern unsigned int setup_authusers_ACE(struct cifs_ace *pace);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 509a41ff56b8..5d39129406ea 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -155,6 +155,7 @@ static void reconn_set_next_dfs_target(struct TCP_Server_Info *server,
 		cifs_dbg(FYI,
 			 "%s: failed to extract hostname from target: %ld\n",
 			 __func__, PTR_ERR(server->hostname));
+		return;
 	}
 
 	rc = reconn_set_ipaddr_from_hostname(server);
@@ -3739,7 +3740,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses,
 
 	if (!ses->binding) {
 		ses->capabilities = server->capabilities;
-		if (linuxExtEnabled == 0)
+		if (!linuxExtEnabled)
 			ses->capabilities &= (~server->vals->cap_unix);
 
 		if (ses->auth_key.response) {
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 6ad6ba5f6ebe..0fdb0de7ff86 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1260,7 +1260,8 @@ void dfs_cache_del_vol(const char *fullpath)
 	vi = find_vol(fullpath);
 	spin_unlock(&vol_list_lock);
 
-	kref_put(&vi->refcnt, vol_release);
+	if (!IS_ERR(vi))
+		kref_put(&vi->refcnt, vol_release);
 }
 
 /**
diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c
index 0afccbbed2e6..076bcadc756a 100644
--- a/fs/cifs/fs_context.c
+++ b/fs/cifs/fs_context.c
@@ -303,8 +303,6 @@ do {									\
 int
 smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx)
 {
-	int rc = 0;
-
 	memcpy(new_ctx, ctx, sizeof(*ctx));
 	new_ctx->prepath = NULL;
 	new_ctx->mount_options = NULL;
@@ -327,7 +325,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx
 	DUP_CTX_STR(nodename);
 	DUP_CTX_STR(iocharset);
 
-	return rc;
+	return 0;
 }
 
 static int
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 949cd1177147..f19274857292 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -3214,7 +3214,7 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon,
 
 static struct cifs_ntsd *
 get_smb2_acl_by_fid(struct cifs_sb_info *cifs_sb,
-		const struct cifs_fid *cifsfid, u32 *pacllen)
+		    const struct cifs_fid *cifsfid, u32 *pacllen, u32 info)
 {
 	struct cifs_ntsd *pntsd = NULL;
 	unsigned int xid;
@@ -3228,7 +3228,8 @@ get_smb2_acl_by_fid(struct cifs_sb_info *cifs_sb,
 	cifs_dbg(FYI, "trying to get acl\n");
 
 	rc = SMB2_query_acl(xid, tlink_tcon(tlink), cifsfid->persistent_fid,
-			    cifsfid->volatile_fid, (void **)&pntsd, pacllen);
+			    cifsfid->volatile_fid, (void **)&pntsd, pacllen,
+			    info);
 	free_xid(xid);
 
 	cifs_put_tlink(tlink);
@@ -3242,7 +3243,7 @@ get_smb2_acl_by_fid(struct cifs_sb_info *cifs_sb,
 
 static struct cifs_ntsd *
 get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb,
-		const char *path, u32 *pacllen)
+		     const char *path, u32 *pacllen, u32 info)
 {
 	struct cifs_ntsd *pntsd = NULL;
 	u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
@@ -3280,12 +3281,16 @@ get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb,
 	oparms.fid = &fid;
 	oparms.reconnect = false;
 
+	if (info & SACL_SECINFO)
+		oparms.desired_access |= SYSTEM_SECURITY;
+
 	rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL,
 		       NULL);
 	kfree(utf16_path);
 	if (!rc) {
 		rc = SMB2_query_acl(xid, tlink_tcon(tlink), fid.persistent_fid,
-			    fid.volatile_fid, (void **)&pntsd, pacllen);
+				    fid.volatile_fid, (void **)&pntsd, pacllen,
+				    info);
 		SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 	}
 
@@ -3319,10 +3324,12 @@ set_smb2_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
 	tcon = tlink_tcon(tlink);
 	xid = get_xid();
 
-	if (aclflag == CIFS_ACL_OWNER || aclflag == CIFS_ACL_GROUP)
-		access_flags = WRITE_OWNER;
-	else
-		access_flags = WRITE_DAC;
+	if (aclflag & CIFS_ACL_OWNER || aclflag & CIFS_ACL_GROUP)
+		access_flags |= WRITE_OWNER;
+	if (aclflag & CIFS_ACL_SACL)
+		access_flags |= SYSTEM_SECURITY;
+	if (aclflag & CIFS_ACL_DACL)
+		access_flags |= WRITE_DAC;
 
 	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
 	if (!utf16_path) {
@@ -3356,18 +3363,18 @@ set_smb2_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
 /* Retrieve an ACL from the server */
 static struct cifs_ntsd *
 get_smb2_acl(struct cifs_sb_info *cifs_sb,
-				      struct inode *inode, const char *path,
-				      u32 *pacllen)
+	     struct inode *inode, const char *path,
+	     u32 *pacllen, u32 info)
 {
 	struct cifs_ntsd *pntsd = NULL;
 	struct cifsFileInfo *open_file = NULL;
 
-	if (inode)
+	if (inode && !(info & SACL_SECINFO))
 		open_file = find_readable_file(CIFS_I(inode), true);
-	if (!open_file)
-		return get_smb2_acl_by_path(cifs_sb, path, pacllen);
+	if (!open_file || (info & SACL_SECINFO))
+		return get_smb2_acl_by_path(cifs_sb, path, pacllen, info);
 
-	pntsd = get_smb2_acl_by_fid(cifs_sb, &open_file->fid, pacllen);
+	pntsd = get_smb2_acl_by_fid(cifs_sb, &open_file->fid, pacllen, info);
 	cifsFileInfo_put(open_file);
 	return pntsd;
 }
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index fc06c762fbbf..794fc3b68b4f 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -3248,7 +3248,7 @@ close_exit:
 	free_rsp_buf(resp_buftype, rsp);
 
 	/* retry close in a worker thread if this one is interrupted */
-	if (rc == -EINTR) {
+	if (is_interrupt_error(rc)) {
 		int tmp_rc;
 
 		tmp_rc = smb2_handle_cancelled_close(tcon, persistent_fid,
@@ -3479,10 +3479,11 @@ SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 int
 SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon,
-		u64 persistent_fid, u64 volatile_fid,
-		void **data, u32 *plen)
+	       u64 persistent_fid, u64 volatile_fid,
+	       void **data, u32 *plen, u32 extra_info)
 {
-	__u32 additional_info = OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO;
+	__u32 additional_info = OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO |
+				extra_info;
 	*plen = 0;
 
 	return query_info(xid, tcon, persistent_fid, volatile_fid,
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 204a622b89ed..d85edf5d1429 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -424,7 +424,7 @@ struct smb2_rdma_transform_capabilities_context {
 	__le16	TransformCount;
 	__u16	Reserved1;
 	__u32	Reserved2;
-	__le16	RDMATransformIds[1];
+	__le16	RDMATransformIds[];
 } __packed;
 
 /* Signing algorithms */
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index d4110447ee3a..9565e27681a5 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -200,8 +200,8 @@ extern int SMB2_query_info_init(struct cifs_tcon *tcon,
 				size_t input_len, void *input);
 extern void SMB2_query_info_free(struct smb_rqst *rqst);
 extern int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon,
-			   u64 persistent_file_id, u64 volatile_file_id,
-			   void **data, unsigned int *plen);
+			  u64 persistent_file_id, u64 volatile_file_id,
+			  void **data, unsigned int *plen, u32 info);
 extern int SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon,
 			    u64 persistent_fid, u64 volatile_fid,
 			    __le64 *uniqueid);
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index b8299173ea7e..6b658a1172ef 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -34,6 +34,7 @@
 #define MAX_EA_VALUE_SIZE CIFSMaxBufSize
 #define CIFS_XATTR_CIFS_ACL "system.cifs_acl" /* DACL only */
 #define CIFS_XATTR_CIFS_NTSD "system.cifs_ntsd" /* owner plus DACL */
+#define CIFS_XATTR_CIFS_NTSD_FULL "system.cifs_ntsd_full" /* owner/DACL/SACL */
 #define CIFS_XATTR_ATTRIB "cifs.dosattrib"  /* full name: user.cifs.dosattrib */
 #define CIFS_XATTR_CREATETIME "cifs.creationtime"  /* user.cifs.creationtime */
 /*
@@ -43,12 +44,13 @@
  */
 #define SMB3_XATTR_CIFS_ACL "system.smb3_acl" /* DACL only */
 #define SMB3_XATTR_CIFS_NTSD "system.smb3_ntsd" /* owner plus DACL */
+#define SMB3_XATTR_CIFS_NTSD_FULL "system.smb3_ntsd_full" /* owner/DACL/SACL */
 #define SMB3_XATTR_ATTRIB "smb3.dosattrib"  /* full name: user.smb3.dosattrib */
 #define SMB3_XATTR_CREATETIME "smb3.creationtime"  /* user.smb3.creationtime */
 /* BB need to add server (Samba e.g) support for security and trusted prefix */
 
 enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT,
-	XATTR_CIFS_NTSD };
+	XATTR_CIFS_NTSD, XATTR_CIFS_NTSD_FULL };
 
 static int cifs_attrib_set(unsigned int xid, struct cifs_tcon *pTcon,
 			   struct inode *inode, char *full_path,
@@ -164,7 +166,8 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
 		break;
 
 	case XATTR_CIFS_ACL:
-	case XATTR_CIFS_NTSD: {
+	case XATTR_CIFS_NTSD:
+	case XATTR_CIFS_NTSD_FULL: {
 		struct cifs_ntsd *pacl;
 
 		if (!value)
@@ -174,23 +177,27 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
 			rc = -ENOMEM;
 		} else {
 			memcpy(pacl, value, size);
-			if (value &&
-			    pTcon->ses->server->ops->set_acl) {
+			if (pTcon->ses->server->ops->set_acl) {
+				int aclflags = 0;
 				rc = 0;
-				if (handler->flags == XATTR_CIFS_NTSD) {
-					/* set owner and DACL */
-					rc = pTcon->ses->server->ops->set_acl(
-							pacl, size, inode,
-							full_path,
-							CIFS_ACL_OWNER);
-				}
-				if (rc == 0) {
-					/* set DACL */
-					rc = pTcon->ses->server->ops->set_acl(
-							pacl, size, inode,
-							full_path,
-							CIFS_ACL_DACL);
+
+				switch (handler->flags) {
+				case XATTR_CIFS_NTSD_FULL:
+					aclflags = (CIFS_ACL_OWNER |
+						    CIFS_ACL_DACL |
+						    CIFS_ACL_SACL);
+					break;
+				case XATTR_CIFS_NTSD:
+					aclflags = (CIFS_ACL_OWNER |
+						    CIFS_ACL_DACL);
+					break;
+				case XATTR_CIFS_ACL:
+				default:
+					aclflags = CIFS_ACL_DACL;
 				}
+
+				rc = pTcon->ses->server->ops->set_acl(pacl,
+					size, inode, full_path, aclflags);
 			} else {
 				rc = -EOPNOTSUPP;
 			}
@@ -327,16 +334,25 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
 		break;
 
 	case XATTR_CIFS_ACL:
-	case XATTR_CIFS_NTSD: {
-		/* the whole ntsd is fetched regardless */
-		u32 acllen;
+	case XATTR_CIFS_NTSD:
+	case XATTR_CIFS_NTSD_FULL: {
+		/*
+		 * fetch owner, DACL, and SACL if asked for full descriptor,
+		 * fetch owner and DACL otherwise
+		 */
+		u32 acllen, extra_info;
 		struct cifs_ntsd *pacl;
 
 		if (pTcon->ses->server->ops->get_acl == NULL)
 			goto out; /* rc already EOPNOTSUPP */
 
+		if (handler->flags == XATTR_CIFS_NTSD_FULL) {
+			extra_info = SACL_SECINFO;
+		} else {
+			extra_info = 0;
+		}
 		pacl = pTcon->ses->server->ops->get_acl(cifs_sb,
-				inode, full_path, &acllen);
+				inode, full_path, &acllen, extra_info);
 		if (IS_ERR(pacl)) {
 			rc = PTR_ERR(pacl);
 			cifs_dbg(VFS, "%s: error %zd getting sec desc\n",
@@ -486,6 +502,27 @@ static const struct xattr_handler smb3_ntsd_xattr_handler = {
 	.set = cifs_xattr_set,
 };
 
+static const struct xattr_handler cifs_cifs_ntsd_full_xattr_handler = {
+	.name = CIFS_XATTR_CIFS_NTSD_FULL,
+	.flags = XATTR_CIFS_NTSD_FULL,
+	.get = cifs_xattr_get,
+	.set = cifs_xattr_set,
+};
+
+/*
+ * Although this is just an alias for the above, need to move away from
+ * confusing users and using the 20 year old term 'cifs' when it is no
+ * longer secure and was replaced by SMB2/SMB3 a long time ago, and
+ * SMB3 and later are highly secure.
+ */
+static const struct xattr_handler smb3_ntsd_full_xattr_handler = {
+	.name = SMB3_XATTR_CIFS_NTSD_FULL,
+	.flags = XATTR_CIFS_NTSD_FULL,
+	.get = cifs_xattr_get,
+	.set = cifs_xattr_set,
+};
+
+
 static const struct xattr_handler cifs_posix_acl_access_xattr_handler = {
 	.name = XATTR_NAME_POSIX_ACL_ACCESS,
 	.flags = XATTR_ACL_ACCESS,
@@ -507,6 +544,8 @@ const struct xattr_handler *cifs_xattr_handlers[] = {
 	&smb3_acl_xattr_handler, /* alias for above since avoiding "cifs" */
 	&cifs_cifs_ntsd_xattr_handler,
 	&smb3_ntsd_xattr_handler, /* alias for above since avoiding "cifs" */
+	&cifs_cifs_ntsd_full_xattr_handler,
+	&smb3_ntsd_full_xattr_handler, /* alias for above since avoiding "cifs" */
 	&cifs_posix_acl_access_xattr_handler,
 	&cifs_posix_acl_default_xattr_handler,
 	NULL
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index b0983e2a4e2c..b839dd1b459f 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -267,6 +267,7 @@ static void configfs_remove_dirent(struct dentry *dentry)
  *	configfs_create_dir - create a directory for an config_item.
  *	@item:		config_itemwe're creating directory for.
  *	@dentry:	config_item's dentry.
+ *	@frag:		config_item's fragment.
  *
  *	Note: user-created entries won't be allowed under this new directory
  *	until it is validated by configfs_dir_set_ready()
diff --git a/fs/dcache.c b/fs/dcache.c
index ea0485861d93..97e81a844a96 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -793,10 +793,17 @@ static inline bool fast_dput(struct dentry *dentry)
 	 * a reference to the dentry and change that, but
 	 * our work is done - we can leave the dentry
 	 * around with a zero refcount.
+	 *
+	 * Nevertheless, there are two cases that we should kill
+	 * the dentry anyway.
+	 * 1. free disconnected dentries as soon as their refcount
+	 *    reached zero.
+	 * 2. free dentries if they should not be cached.
 	 */
 	smp_rmb();
 	d_flags = READ_ONCE(dentry->d_flags);
-	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED;
+	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST |
+			DCACHE_DISCONNECTED | DCACHE_DONTCACHE;
 
 	/* Nothing to do? Dropping the reference was all we needed? */
 	if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
diff --git a/fs/eventfd.c b/fs/eventfd.c
index df466ef81ddd..e265b6dd4f34 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -182,11 +182,14 @@ static __poll_t eventfd_poll(struct file *file, poll_table *wait)
 	return events;
 }
 
-static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
+void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
 {
+	lockdep_assert_held(&ctx->wqh.lock);
+
 	*cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count;
 	ctx->count -= *cnt;
 }
+EXPORT_SYMBOL_GPL(eventfd_ctx_do_read);
 
 /**
  * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue.
diff --git a/fs/exfat/nls.c b/fs/exfat/nls.c
index 675d0e7058c5..314d5407a1be 100644
--- a/fs/exfat/nls.c
+++ b/fs/exfat/nls.c
@@ -659,7 +659,7 @@ static int exfat_load_upcase_table(struct super_block *sb,
 	unsigned char skip = false;
 	unsigned short *upcase_table;
 
-	upcase_table = kcalloc(UTBL_COUNT, sizeof(unsigned short), GFP_KERNEL);
+	upcase_table = kvcalloc(UTBL_COUNT, sizeof(unsigned short), GFP_KERNEL);
 	if (!upcase_table)
 		return -ENOMEM;
 
@@ -715,7 +715,7 @@ static int exfat_load_default_upcase_table(struct super_block *sb)
 	unsigned short uni = 0, *upcase_table;
 	unsigned int index = 0;
 
-	upcase_table = kcalloc(UTBL_COUNT, sizeof(unsigned short), GFP_KERNEL);
+	upcase_table = kvcalloc(UTBL_COUNT, sizeof(unsigned short), GFP_KERNEL);
 	if (!upcase_table)
 		return -ENOMEM;
 
@@ -803,5 +803,5 @@ load_default:
 
 void exfat_free_upcase_table(struct exfat_sb_info *sbi)
 {
-	kfree(sbi->vol_utbl);
+	kvfree(sbi->vol_utbl);
 }
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 1d640b145637..f45f9feebe59 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -185,7 +185,7 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_fsblk_t start, tmp;
 
-	J_ASSERT_BH(bh, buffer_locked(bh));
+	ASSERT(buffer_locked(bh));
 
 	/* If checksum is bad mark all blocks used to prevent allocation
 	 * essentially implementing a per-group read-only flag. */
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 8e6ca23ed172..4666b55b736e 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -176,12 +176,10 @@ static int ext4_protect_reserved_inode(struct super_block *sb,
 			err = add_system_zone(system_blks, map.m_pblk, n, ino);
 			if (err < 0) {
 				if (err == -EFSCORRUPTED) {
-					__ext4_error(sb, __func__, __LINE__,
-						     -err, map.m_pblk,
-						     "blocks %llu-%llu from inode %u overlap system zone",
-						     map.m_pblk,
-						     map.m_pblk + map.m_len - 1,
-						     ino);
+					EXT4_ERROR_INODE_ERR(inode, -err,
+						"blocks %llu-%llu from inode overlap system zone",
+						map.m_pblk,
+						map.m_pblk + map.m_len - 1);
 				}
 				break;
 			}
@@ -206,7 +204,7 @@ static void ext4_destroy_system_zone(struct rcu_head *rcu)
  *
  * The update of system_blks pointer in this function is protected by
  * sb->s_umount semaphore. However we have to be careful as we can be
- * racing with ext4_data_block_valid() calls reading system_blks rbtree
+ * racing with ext4_inode_block_valid() calls reading system_blks rbtree
  * protected only by RCU. That's why we first build the rbtree and then
  * swap it in place.
  */
@@ -258,7 +256,7 @@ int ext4_setup_system_zone(struct super_block *sb)
 
 	/*
 	 * System blks rbtree complete, announce it once to prevent racing
-	 * with ext4_data_block_valid() accessing the rbtree at the same
+	 * with ext4_inode_block_valid() accessing the rbtree at the same
 	 * time.
 	 */
 	rcu_assign_pointer(sbi->s_system_blks, system_blks);
@@ -278,7 +276,7 @@ err:
  *
  * The update of system_blks pointer in this function is protected by
  * sb->s_umount semaphore. However we have to be careful as we can be
- * racing with ext4_data_block_valid() calls reading system_blks rbtree
+ * racing with ext4_inode_block_valid() calls reading system_blks rbtree
  * protected only by RCU. So we first clear the system_blks pointer and
  * then free the rbtree only after RCU grace period expires.
  */
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index c64ea8f59ea7..2866d249f3d2 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -98,6 +98,16 @@
 #define ext_debug(ino, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
 #endif
 
+#define ASSERT(assert)						\
+do {									\
+	if (unlikely(!(assert))) {					\
+		printk(KERN_EMERG					\
+		       "Assertion failure in %s() at %s:%d: '%s'\n",	\
+		       __func__, __FILE__, __LINE__, #assert);		\
+		BUG();							\
+	}								\
+} while (0)
+
 /* data type for block offset of block group */
 typedef int ext4_grpblk_t;
 
@@ -1619,6 +1629,27 @@ struct ext4_sb_info {
 	errseq_t s_bdev_wb_err;
 	spinlock_t s_bdev_wb_lock;
 
+	/* Information about errors that happened during this mount */
+	spinlock_t s_error_lock;
+	int s_add_error_count;
+	int s_first_error_code;
+	__u32 s_first_error_line;
+	__u32 s_first_error_ino;
+	__u64 s_first_error_block;
+	const char *s_first_error_func;
+	time64_t s_first_error_time;
+	int s_last_error_code;
+	__u32 s_last_error_line;
+	__u32 s_last_error_ino;
+	__u64 s_last_error_block;
+	const char *s_last_error_func;
+	time64_t s_last_error_time;
+	/*
+	 * If we are in a context where we cannot update error information in
+	 * the on-disk superblock, we queue this work to do it.
+	 */
+	struct work_struct s_error_work;
+
 	/* Ext4 fast commit stuff */
 	atomic_t s_fc_subtid;
 	atomic_t s_fc_ineligible_updates;
@@ -1858,7 +1889,6 @@ static inline bool ext4_verity_in_progress(struct inode *inode)
 #define EXT4_GOOD_OLD_REV	0	/* The good old (original) format */
 #define EXT4_DYNAMIC_REV	1	/* V2 format w/ dynamic inode sizes */
 
-#define EXT4_CURRENT_REV	EXT4_GOOD_OLD_REV
 #define EXT4_MAX_SUPP_REV	EXT4_DYNAMIC_REV
 
 #define EXT4_GOOD_OLD_INODE_SIZE 128
@@ -2952,9 +2982,9 @@ extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
 					     ext4_group_t block_group,
 					     unsigned int flags);
 
-extern __printf(6, 7)
-void __ext4_error(struct super_block *, const char *, unsigned int, int, __u64,
-		  const char *, ...);
+extern __printf(7, 8)
+void __ext4_error(struct super_block *, const char *, unsigned int, bool,
+		  int, __u64, const char *, ...);
 extern __printf(6, 7)
 void __ext4_error_inode(struct inode *, const char *, unsigned int,
 			ext4_fsblk_t, int, const char *, ...);
@@ -2963,9 +2993,6 @@ void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
 		     const char *, ...);
 extern void __ext4_std_error(struct super_block *, const char *,
 			     unsigned int, int);
-extern __printf(5, 6)
-void __ext4_abort(struct super_block *, const char *, unsigned int, int,
-		  const char *, ...);
 extern __printf(4, 5)
 void __ext4_warning(struct super_block *, const char *, unsigned int,
 		    const char *, ...);
@@ -2995,6 +3022,9 @@ void __ext4_grp_locked_error(const char *, unsigned int,
 #define EXT4_ERROR_FILE(file, block, fmt, a...)				\
 	ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a)
 
+#define ext4_abort(sb, err, fmt, a...)					\
+	__ext4_error((sb), __func__, __LINE__, true, (err), 0, (fmt), ## a)
+
 #ifdef CONFIG_PRINTK
 
 #define ext4_error_inode(inode, func, line, block, fmt, ...)		\
@@ -3005,11 +3035,11 @@ void __ext4_grp_locked_error(const char *, unsigned int,
 #define ext4_error_file(file, func, line, block, fmt, ...)		\
 	__ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__)
 #define ext4_error(sb, fmt, ...)					\
-	__ext4_error((sb), __func__, __LINE__, 0, 0, (fmt), ##__VA_ARGS__)
+	__ext4_error((sb), __func__, __LINE__, false, 0, 0, (fmt),	\
+		##__VA_ARGS__)
 #define ext4_error_err(sb, err, fmt, ...)				\
-	__ext4_error((sb), __func__, __LINE__, (err), 0, (fmt), ##__VA_ARGS__)
-#define ext4_abort(sb, err, fmt, ...)					\
-	__ext4_abort((sb), __func__, __LINE__, (err), (fmt), ##__VA_ARGS__)
+	__ext4_error((sb), __func__, __LINE__, false, (err), 0, (fmt),	\
+		##__VA_ARGS__)
 #define ext4_warning(sb, fmt, ...)					\
 	__ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
 #define ext4_warning_inode(inode, fmt, ...)				\
@@ -3042,17 +3072,12 @@ do {									\
 #define ext4_error(sb, fmt, ...)					\
 do {									\
 	no_printk(fmt, ##__VA_ARGS__);					\
-	__ext4_error(sb, "", 0, 0, 0, " ");				\
+	__ext4_error(sb, "", 0, false, 0, 0, " ");			\
 } while (0)
 #define ext4_error_err(sb, err, fmt, ...)				\
 do {									\
 	no_printk(fmt, ##__VA_ARGS__);					\
-	__ext4_error(sb, "", 0, err, 0, " ");				\
-} while (0)
-#define ext4_abort(sb, err, fmt, ...)					\
-do {									\
-	no_printk(fmt, ##__VA_ARGS__);					\
-	__ext4_abort(sb, "", 0, err, " ");				\
+	__ext4_error(sb, "", 0, false, err, 0, " ");			\
 } while (0)
 #define ext4_warning(sb, fmt, ...)					\
 do {									\
@@ -3361,6 +3386,21 @@ static inline void ext4_unlock_group(struct super_block *sb,
 	spin_unlock(ext4_group_lock_ptr(sb, group));
 }
 
+#ifdef CONFIG_QUOTA
+static inline bool ext4_quota_capable(struct super_block *sb)
+{
+	return (test_opt(sb, QUOTA) || ext4_has_feature_quota(sb));
+}
+
+static inline bool ext4_is_quota_journalled(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	return (ext4_has_feature_quota(sb) ||
+		sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]);
+}
+#endif
+
 /*
  * Block validity checking
  */
@@ -3609,7 +3649,6 @@ extern void ext4_io_submit(struct ext4_io_submit *io);
 extern int ext4_bio_write_page(struct ext4_io_submit *io,
 			       struct page *page,
 			       int len,
-			       struct writeback_control *wbc,
 			       bool keep_towrite);
 extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end);
 extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 0fd0c42a4f7d..be799040a415 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -296,8 +296,8 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
 	if (err) {
 		ext4_journal_abort_handle(where, line, __func__,
 					  bh, handle, err);
-		__ext4_abort(inode->i_sb, where, line, -err,
-			   "error %d when attempting revoke", err);
+		__ext4_error(inode->i_sb, where, line, true, -err, 0,
+			     "error %d when attempting revoke", err);
 	}
 	BUFFER_TRACE(bh, "exit");
 	return err;
@@ -372,20 +372,3 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 	}
 	return err;
 }
-
-int __ext4_handle_dirty_super(const char *where, unsigned int line,
-			      handle_t *handle, struct super_block *sb)
-{
-	struct buffer_head *bh = EXT4_SB(sb)->s_sbh;
-	int err = 0;
-
-	ext4_superblock_csum_set(sb);
-	if (ext4_handle_valid(handle)) {
-		err = jbd2_journal_dirty_metadata(handle, bh);
-		if (err)
-			ext4_journal_abort_handle(where, line, __func__,
-						  bh, handle, err);
-	} else
-		mark_buffer_dirty(bh);
-	return err;
-}
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 00dc668e052b..0d2fa423b7ad 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -86,17 +86,14 @@
 #ifdef CONFIG_QUOTA
 /* Amount of blocks needed for quota update - we know that the structure was
  * allocated so we need to update only data block */
-#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
-		ext4_has_feature_quota(sb)) ? 1 : 0)
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0)
 /* Amount of blocks needed for quota insert/delete - we do some block writes
  * but inode, sb and group updates are done only once */
-#define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
-		ext4_has_feature_quota(sb)) ?\
+#define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\
 		(DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
 		 +3+DQUOT_INIT_REWRITE) : 0)
 
-#define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
-		ext4_has_feature_quota(sb)) ?\
+#define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\
 		(DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
 		 +3+DQUOT_DEL_REWRITE) : 0)
 #else
@@ -247,9 +244,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 				 handle_t *handle, struct inode *inode,
 				 struct buffer_head *bh);
 
-int __ext4_handle_dirty_super(const char *where, unsigned int line,
-			      handle_t *handle, struct super_block *sb);
-
 #define ext4_journal_get_write_access(handle, bh) \
 	__ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh))
 #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
@@ -260,8 +254,6 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line,
 #define ext4_handle_dirty_metadata(handle, inode, bh) \
 	__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
 				     (bh))
-#define ext4_handle_dirty_super(handle, sb) \
-	__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
 
 handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
 				  int type, int blocks, int rsv_blocks,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 17d7096b3212..3960b7ec3ab7 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5815,8 +5815,8 @@ int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
 	int ret;
 
 	path = ext4_find_extent(inode, start, NULL, 0);
-	if (!path)
-		return -EINVAL;
+	if (IS_ERR(path))
+		return PTR_ERR(path);
 	ex = path[path->p_depth].p_ext;
 	if (!ex) {
 		ret = -EFSCORRUPTED;
@@ -5988,7 +5988,6 @@ int ext4_ext_replay_set_iblocks(struct inode *inode)
 			kfree(path);
 			break;
 		}
-		ex = path2[path2->p_depth].p_ext;
 		for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) {
 			cmp1 = cmp2 = 0;
 			if (i <= path->p_depth)
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index f2033e13a273..0a14a7c87bf8 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -103,8 +103,69 @@
  *
  * Replay code should thus check for all the valid tails in the FC area.
  *
+ * Fast Commit Replay Idempotence
+ * ------------------------------
+ *
+ * Fast commits tags are idempotent in nature provided the recovery code follows
+ * certain rules. The guiding principle that the commit path follows while
+ * committing is that it stores the result of a particular operation instead of
+ * storing the procedure.
+ *
+ * Let's consider this rename operation: 'mv /a /b'. Let's assume dirent '/a'
+ * was associated with inode 10. During fast commit, instead of storing this
+ * operation as a procedure "rename a to b", we store the resulting file system
+ * state as a "series" of outcomes:
+ *
+ * - Link dirent b to inode 10
+ * - Unlink dirent a
+ * - Inode <10> with valid refcount
+ *
+ * Now when recovery code runs, it needs "enforce" this state on the file
+ * system. This is what guarantees idempotence of fast commit replay.
+ *
+ * Let's take an example of a procedure that is not idempotent and see how fast
+ * commits make it idempotent. Consider following sequence of operations:
+ *
+ *     rm A;    mv B A;    read A
+ *  (x)     (y)        (z)
+ *
+ * (x), (y) and (z) are the points at which we can crash. If we store this
+ * sequence of operations as is then the replay is not idempotent. Let's say
+ * while in replay, we crash at (z). During the second replay, file A (which was
+ * actually created as a result of "mv B A" operation) would get deleted. Thus,
+ * file named A would be absent when we try to read A. So, this sequence of
+ * operations is not idempotent. However, as mentioned above, instead of storing
+ * the procedure fast commits store the outcome of each procedure. Thus the fast
+ * commit log for above procedure would be as follows:
+ *
+ * (Let's assume dirent A was linked to inode 10 and dirent B was linked to
+ * inode 11 before the replay)
+ *
+ *    [Unlink A]   [Link A to inode 11]   [Unlink B]   [Inode 11]
+ * (w)          (x)                    (y)          (z)
+ *
+ * If we crash at (z), we will have file A linked to inode 11. During the second
+ * replay, we will remove file A (inode 11). But we will create it back and make
+ * it point to inode 11. We won't find B, so we'll just skip that step. At this
+ * point, the refcount for inode 11 is not reliable, but that gets fixed by the
+ * replay of last inode 11 tag. Crashes at points (w), (x) and (y) get handled
+ * similarly. Thus, by converting a non-idempotent procedure into a series of
+ * idempotent outcomes, fast commits ensured idempotence during the replay.
+ *
  * TODOs
  * -----
+ *
+ * 0) Fast commit replay path hardening: Fast commit replay code should use
+ *    journal handles to make sure all the updates it does during the replay
+ *    path are atomic. With that if we crash during fast commit replay, after
+ *    trying to do recovery again, we will find a file system where fast commit
+ *    area is invalid (because new full commit would be found). In order to deal
+ *    with that, fast commit replay code should ensure that the "FC_REPLAY"
+ *    superblock state is persisted before starting the replay, so that after
+ *    the crash, fast commit recovery code can look at that flag and perform
+ *    fast commit recovery even if that area is invalidated by later full
+ *    commits.
+ *
  * 1) Make fast commit atomic updates more fine grained. Today, a fast commit
  *    eligible update must be protected within ext4_fc_start_update() and
  *    ext4_fc_stop_update(). These routines are called at much higher
@@ -543,13 +604,13 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star
 	trace_ext4_fc_track_range(inode, start, end, ret);
 }
 
-static void ext4_fc_submit_bh(struct super_block *sb)
+static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
 {
 	int write_flags = REQ_SYNC;
 	struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
 
-	/* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */
-	if (test_opt(sb, BARRIER))
+	/* Add REQ_FUA | REQ_PREFLUSH only its tail */
+	if (test_opt(sb, BARRIER) && is_tail)
 		write_flags |= REQ_FUA | REQ_PREFLUSH;
 	lock_buffer(bh);
 	set_buffer_dirty(bh);
@@ -623,7 +684,7 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc)
 		*crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl));
 	if (pad_len > 0)
 		ext4_fc_memzero(sb, tl + 1, pad_len, crc);
-	ext4_fc_submit_bh(sb);
+	ext4_fc_submit_bh(sb, false);
 
 	ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh);
 	if (ret)
@@ -680,7 +741,7 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc)
 	tail.fc_crc = cpu_to_le32(crc);
 	ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL);
 
-	ext4_fc_submit_bh(sb);
+	ext4_fc_submit_bh(sb, true);
 
 	return 0;
 }
@@ -1207,7 +1268,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
 	list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING],
 				&sbi->s_fc_dentry_q[FC_Q_MAIN]);
 	list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
-				&sbi->s_fc_q[FC_Q_STAGING]);
+				&sbi->s_fc_q[FC_Q_MAIN]);
 
 	ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
 	ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
@@ -1220,18 +1281,6 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
 
 /* Ext4 Replay Path Routines */
 
-/* Get length of a particular tlv */
-static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl)
-{
-	return le16_to_cpu(tl->fc_len);
-}
-
-/* Get a pointer to "value" of a tlv */
-static inline u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl)
-{
-	return (u8 *)tl + sizeof(*tl);
-}
-
 /* Helper struct for dentry replay routines */
 struct dentry_info_args {
 	int parent_ino, dname_len, ino, inode_len;
@@ -1269,14 +1318,14 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl)
 	entry.len = darg.dname_len;
 	inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
 
-	if (IS_ERR_OR_NULL(inode)) {
+	if (IS_ERR(inode)) {
 		jbd_debug(1, "Inode %d not found", darg.ino);
 		return 0;
 	}
 
 	old_parent = ext4_iget(sb, darg.parent_ino,
 				EXT4_IGET_NORMAL);
-	if (IS_ERR_OR_NULL(old_parent)) {
+	if (IS_ERR(old_parent)) {
 		jbd_debug(1, "Dir with inode  %d not found", darg.parent_ino);
 		iput(inode);
 		return 0;
@@ -1361,7 +1410,7 @@ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl)
 			darg.parent_ino, darg.dname_len);
 
 	inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
-	if (IS_ERR_OR_NULL(inode)) {
+	if (IS_ERR(inode)) {
 		jbd_debug(1, "Inode not found.");
 		return 0;
 	}
@@ -1417,10 +1466,11 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
 	trace_ext4_fc_replay(sb, tag, ino, 0, 0);
 
 	inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
-	if (!IS_ERR_OR_NULL(inode)) {
+	if (!IS_ERR(inode)) {
 		ext4_ext_clear_bb(inode);
 		iput(inode);
 	}
+	inode = NULL;
 
 	ext4_fc_record_modified_inode(sb, ino);
 
@@ -1463,7 +1513,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
 
 	/* Given that we just wrote the inode on disk, this SHOULD succeed. */
 	inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
-	if (IS_ERR_OR_NULL(inode)) {
+	if (IS_ERR(inode)) {
 		jbd_debug(1, "Inode not found.");
 		return -EFSCORRUPTED;
 	}
@@ -1515,7 +1565,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
 		goto out;
 
 	inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
-	if (IS_ERR_OR_NULL(inode)) {
+	if (IS_ERR(inode)) {
 		jbd_debug(1, "inode %d not found.", darg.ino);
 		inode = NULL;
 		ret = -EINVAL;
@@ -1528,7 +1578,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
 		 * dot and dot dot dirents are setup properly.
 		 */
 		dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL);
-		if (IS_ERR_OR_NULL(dir)) {
+		if (IS_ERR(dir)) {
 			jbd_debug(1, "Dir %d not found.", darg.ino);
 			goto out;
 		}
@@ -1604,7 +1654,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
 
 	inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino),
 				EXT4_IGET_NORMAL);
-	if (IS_ERR_OR_NULL(inode)) {
+	if (IS_ERR(inode)) {
 		jbd_debug(1, "Inode not found.");
 		return 0;
 	}
@@ -1728,7 +1778,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
 		le32_to_cpu(lrange->fc_ino), cur, remaining);
 
 	inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL);
-	if (IS_ERR_OR_NULL(inode)) {
+	if (IS_ERR(inode)) {
 		jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino));
 		return 0;
 	}
@@ -1770,32 +1820,6 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
 	return 0;
 }
 
-static inline const char *tag2str(u16 tag)
-{
-	switch (tag) {
-	case EXT4_FC_TAG_LINK:
-		return "TAG_ADD_ENTRY";
-	case EXT4_FC_TAG_UNLINK:
-		return "TAG_DEL_ENTRY";
-	case EXT4_FC_TAG_ADD_RANGE:
-		return "TAG_ADD_RANGE";
-	case EXT4_FC_TAG_CREAT:
-		return "TAG_CREAT_DENTRY";
-	case EXT4_FC_TAG_DEL_RANGE:
-		return "TAG_DEL_RANGE";
-	case EXT4_FC_TAG_INODE:
-		return "TAG_INODE";
-	case EXT4_FC_TAG_PAD:
-		return "TAG_PAD";
-	case EXT4_FC_TAG_TAIL:
-		return "TAG_TAIL";
-	case EXT4_FC_TAG_HEAD:
-		return "TAG_HEAD";
-	default:
-		return "TAG_ERROR";
-	}
-}
-
 static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
 {
 	struct ext4_fc_replay_state *state;
@@ -1809,7 +1833,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
 	for (i = 0; i < state->fc_modified_inodes_used; i++) {
 		inode = ext4_iget(sb, state->fc_modified_inodes[i],
 			EXT4_IGET_NORMAL);
-		if (IS_ERR_OR_NULL(inode)) {
+		if (IS_ERR(inode)) {
 			jbd_debug(1, "Inode %d not found.",
 				state->fc_modified_inodes[i]);
 			continue;
@@ -1826,7 +1850,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
 
 			if (ret > 0) {
 				path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
-				if (!IS_ERR_OR_NULL(path)) {
+				if (!IS_ERR(path)) {
 					for (j = 0; j < path->p_depth; j++)
 						ext4_mb_mark_bb(inode->i_sb,
 							path[j].p_block, 1, 1);
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index 3a6e5a1fa1b8..b77f70f55a62 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -3,6 +3,11 @@
 #ifndef __FAST_COMMIT_H__
 #define __FAST_COMMIT_H__
 
+/*
+ * Note this file is present in e2fsprogs/lib/ext2fs/fast_commit.h and
+ * linux/fs/ext4/fast_commit.h. These file should always be byte identical.
+ */
+
 /* Fast commit tags */
 #define EXT4_FC_TAG_ADD_RANGE		0x0001
 #define EXT4_FC_TAG_DEL_RANGE		0x0002
@@ -50,7 +55,7 @@ struct ext4_fc_del_range {
 struct ext4_fc_dentry_info {
 	__le32 fc_parent_ino;
 	__le32 fc_ino;
-	u8 fc_dname[0];
+	__u8 fc_dname[0];
 };
 
 /* Value structure for EXT4_FC_TAG_INODE and EXT4_FC_TAG_INODE_PARTIAL. */
@@ -66,19 +71,6 @@ struct ext4_fc_tail {
 };
 
 /*
- * In memory list of dentry updates that are performed on the file
- * system used by fast commit code.
- */
-struct ext4_fc_dentry_update {
-	int fcd_op;		/* Type of update create / unlink / link */
-	int fcd_parent;		/* Parent inode number */
-	int fcd_ino;		/* Inode number */
-	struct qstr fcd_name;	/* Dirent name */
-	unsigned char fcd_iname[DNAME_INLINE_LEN];	/* Dirent name string */
-	struct list_head fcd_list;
-};
-
-/*
  * Fast commit reason codes
  */
 enum {
@@ -107,6 +99,20 @@ enum {
 	EXT4_FC_REASON_MAX
 };
 
+#ifdef __KERNEL__
+/*
+ * In memory list of dentry updates that are performed on the file
+ * system used by fast commit code.
+ */
+struct ext4_fc_dentry_update {
+	int fcd_op;		/* Type of update create / unlink / link */
+	int fcd_parent;		/* Parent inode number */
+	int fcd_ino;		/* Inode number */
+	struct qstr fcd_name;	/* Dirent name */
+	unsigned char fcd_iname[DNAME_INLINE_LEN];	/* Dirent name string */
+	struct list_head fcd_list;
+};
+
 struct ext4_fc_stats {
 	unsigned int fc_ineligible_reason_count[EXT4_FC_REASON_MAX];
 	unsigned long fc_num_commits;
@@ -145,13 +151,51 @@ struct ext4_fc_replay_state {
 };
 
 #define region_last(__region) (((__region)->lblk) + ((__region)->len) - 1)
+#endif
 
 #define fc_for_each_tl(__start, __end, __tl)				\
-	for (tl = (struct ext4_fc_tl *)start;				\
-		(u8 *)tl < (u8 *)end;					\
-		tl = (struct ext4_fc_tl *)((u8 *)tl +			\
+	for (tl = (struct ext4_fc_tl *)(__start);			\
+	     (__u8 *)tl < (__u8 *)(__end);				\
+		tl = (struct ext4_fc_tl *)((__u8 *)tl +			\
 					sizeof(struct ext4_fc_tl) +	\
 					+ le16_to_cpu(tl->fc_len)))
 
+static inline const char *tag2str(__u16 tag)
+{
+	switch (tag) {
+	case EXT4_FC_TAG_LINK:
+		return "ADD_ENTRY";
+	case EXT4_FC_TAG_UNLINK:
+		return "DEL_ENTRY";
+	case EXT4_FC_TAG_ADD_RANGE:
+		return "ADD_RANGE";
+	case EXT4_FC_TAG_CREAT:
+		return "CREAT_DENTRY";
+	case EXT4_FC_TAG_DEL_RANGE:
+		return "DEL_RANGE";
+	case EXT4_FC_TAG_INODE:
+		return "INODE";
+	case EXT4_FC_TAG_PAD:
+		return "PAD";
+	case EXT4_FC_TAG_TAIL:
+		return "TAIL";
+	case EXT4_FC_TAG_HEAD:
+		return "HEAD";
+	default:
+		return "ERROR";
+	}
+}
+
+/* Get length of a particular tlv */
+static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl)
+{
+	return le16_to_cpu(tl->fc_len);
+}
+
+/* Get a pointer to "value" of a tlv */
+static inline __u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl)
+{
+	return (__u8 *)tl + sizeof(*tl);
+}
 
 #endif /* __FAST_COMMIT_H__ */
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 3ed8c048fb12..349b27f0dda0 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -809,9 +809,12 @@ static int ext4_sample_last_mounted(struct super_block *sb,
 	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
 	if (err)
 		goto out_journal;
-	strlcpy(sbi->s_es->s_last_mounted, cp,
+	lock_buffer(sbi->s_sbh);
+	strncpy(sbi->s_es->s_last_mounted, cp,
 		sizeof(sbi->s_es->s_last_mounted));
-	ext4_handle_dirty_super(handle, sb);
+	ext4_superblock_csum_set(sb);
+	unlock_buffer(sbi->s_sbh);
+	ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
 out_journal:
 	ext4_journal_stop(handle);
 out:
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index a42ca95840f2..113bfb023a4a 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -136,7 +136,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	if (unlikely(ext4_forced_shutdown(sbi)))
 		return -EIO;
 
-	J_ASSERT(ext4_journal_current_handle() == NULL);
+	ASSERT(ext4_journal_current_handle() == NULL);
 
 	trace_ext4_sync_file_enter(file, datasync);
 
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 05efa682bc2f..1223a18c3ff9 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -534,8 +534,8 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 	ext4_fsblk_t first_block = 0;
 
 	trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
-	J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
-	J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
+	ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
+	ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
 	depth = ext4_block_to_path(inode, map->m_lblk, offsets,
 				   &blocks_to_boundary);
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0d8385aea898..c173c8405856 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -175,6 +175,7 @@ void ext4_evict_inode(struct inode *inode)
 	 */
 	int extra_credits = 6;
 	struct ext4_xattr_inode_array *ea_inode_array = NULL;
+	bool freeze_protected = false;
 
 	trace_ext4_evict_inode(inode);
 
@@ -232,9 +233,14 @@ void ext4_evict_inode(struct inode *inode)
 
 	/*
 	 * Protect us against freezing - iput() caller didn't have to have any
-	 * protection against it
+	 * protection against it. When we are in a running transaction though,
+	 * we are already protected against freezing and we cannot grab further
+	 * protection due to lock ordering constraints.
 	 */
-	sb_start_intwrite(inode->i_sb);
+	if (!ext4_journal_current_handle()) {
+		sb_start_intwrite(inode->i_sb);
+		freeze_protected = true;
+	}
 
 	if (!IS_NOQUOTA(inode))
 		extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb);
@@ -253,7 +259,8 @@ void ext4_evict_inode(struct inode *inode)
 		 * cleaned up.
 		 */
 		ext4_orphan_del(NULL, inode);
-		sb_end_intwrite(inode->i_sb);
+		if (freeze_protected)
+			sb_end_intwrite(inode->i_sb);
 		goto no_delete;
 	}
 
@@ -294,7 +301,8 @@ void ext4_evict_inode(struct inode *inode)
 stop_handle:
 		ext4_journal_stop(handle);
 		ext4_orphan_del(NULL, inode);
-		sb_end_intwrite(inode->i_sb);
+		if (freeze_protected)
+			sb_end_intwrite(inode->i_sb);
 		ext4_xattr_inode_array_free(ea_inode_array);
 		goto no_delete;
 	}
@@ -323,7 +331,8 @@ stop_handle:
 	else
 		ext4_free_inode(handle, inode);
 	ext4_journal_stop(handle);
-	sb_end_intwrite(inode->i_sb);
+	if (freeze_protected)
+		sb_end_intwrite(inode->i_sb);
 	ext4_xattr_inode_array_free(ea_inode_array);
 	return;
 no_delete:
@@ -830,8 +839,8 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 	int create = map_flags & EXT4_GET_BLOCKS_CREATE;
 	int err;
 
-	J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
-		 || handle != NULL || create == 0);
+	ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		    || handle != NULL || create == 0);
 
 	map.m_lblk = block;
 	map.m_len = 1;
@@ -846,9 +855,9 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 	if (unlikely(!bh))
 		return ERR_PTR(-ENOMEM);
 	if (map.m_flags & EXT4_MAP_NEW) {
-		J_ASSERT(create != 0);
-		J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
-			 || (handle != NULL));
+		ASSERT(create != 0);
+		ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+			    || (handle != NULL));
 
 		/*
 		 * Now that we do not always journal data, we should
@@ -2055,7 +2064,7 @@ static int ext4_writepage(struct page *page,
 		unlock_page(page);
 		return -ENOMEM;
 	}
-	ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite);
+	ret = ext4_bio_write_page(&io_submit, page, len, keep_towrite);
 	ext4_io_submit(&io_submit);
 	/* Drop io_end reference we got from init */
 	ext4_put_io_end_defer(io_submit.io_end);
@@ -2089,7 +2098,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
 		len = size & ~PAGE_MASK;
 	else
 		len = PAGE_SIZE;
-	err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
+	err = ext4_bio_write_page(&mpd->io_submit, page, len, false);
 	if (!err)
 		mpd->wbc->nr_to_write--;
 	mpd->first_page++;
@@ -4610,7 +4619,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	    (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))) {
 		if (flags & EXT4_IGET_HANDLE)
 			return ERR_PTR(-ESTALE);
-		__ext4_error(sb, function, line, EFSCORRUPTED, 0,
+		__ext4_error(sb, function, line, false, EFSCORRUPTED, 0,
 			     "inode #%lu: comm %s: iget: illegal inode #",
 			     ino, current->comm);
 		return ERR_PTR(-EFSCORRUPTED);
@@ -5141,9 +5150,13 @@ static int ext4_do_update_inode(handle_t *handle,
 		err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
 		if (err)
 			goto out_brelse;
+		lock_buffer(EXT4_SB(sb)->s_sbh);
 		ext4_set_feature_large_file(sb);
+		ext4_superblock_csum_set(sb);
+		unlock_buffer(EXT4_SB(sb)->s_sbh);
 		ext4_handle_sync(handle);
-		err = ext4_handle_dirty_super(handle, sb);
+		err = ext4_handle_dirty_metadata(handle, NULL,
+						 EXT4_SB(sb)->s_sbh);
 	}
 	ext4_update_inode_fsync_trans(handle, inode, need_datasync);
 out_brelse:
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 524e13432447..d9665d2f82db 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -1157,7 +1157,10 @@ resizefs_out:
 			err = ext4_journal_get_write_access(handle, sbi->s_sbh);
 			if (err)
 				goto pwsalt_err_journal;
+			lock_buffer(sbi->s_sbh);
 			generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
+			ext4_superblock_csum_set(sb);
+			unlock_buffer(sbi->s_sbh);
 			err = ext4_handle_dirty_metadata(handle, NULL,
 							 sbi->s_sbh);
 		pwsalt_err_journal:
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 24af9ed5c3e5..99bf091fee10 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -822,24 +822,6 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 	spin_unlock(&sbi->s_bal_lock);
 }
 
-static void mb_regenerate_buddy(struct ext4_buddy *e4b)
-{
-	int count;
-	int order = 1;
-	void *buddy;
-
-	while ((buddy = mb_find_buddy(e4b, order++, &count))) {
-		ext4_set_bits(buddy, 0, count);
-	}
-	e4b->bd_info->bb_fragments = 0;
-	memset(e4b->bd_info->bb_counters, 0,
-		sizeof(*e4b->bd_info->bb_counters) *
-		(e4b->bd_sb->s_blocksize_bits + 2));
-
-	ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy,
-		e4b->bd_bitmap, e4b->bd_group);
-}
-
 /* The buddy information is attached the buddy cache inode
  * for convenience. The information regarding each group
  * is loaded via ext4_mb_load_buddy. The information involve
@@ -1307,22 +1289,18 @@ static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
 
 static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
 {
-	int order = 1;
-	int bb_incr = 1 << (e4b->bd_blkbits - 1);
+	int order = 1, max;
 	void *bb;
 
 	BUG_ON(e4b->bd_bitmap == e4b->bd_buddy);
 	BUG_ON(block >= (1 << (e4b->bd_blkbits + 3)));
 
-	bb = e4b->bd_buddy;
 	while (order <= e4b->bd_blkbits + 1) {
-		block = block >> 1;
-		if (!mb_test_bit(block, bb)) {
+		bb = mb_find_buddy(e4b, order, &max);
+		if (!mb_test_bit(block >> order, bb)) {
 			/* this block is part of buddy of order 'order' */
 			return order;
 		}
-		bb += bb_incr;
-		bb_incr >>= 1;
 		order++;
 	}
 	return 0;
@@ -1512,7 +1490,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 				sb, e4b->bd_group,
 				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		}
-		mb_regenerate_buddy(e4b);
 		goto done;
 	}
 
@@ -2395,9 +2372,9 @@ repeat:
 
 				nr = sbi->s_mb_prefetch;
 				if (ext4_has_feature_flex_bg(sb)) {
-					nr = (group / sbi->s_mb_prefetch) *
-						sbi->s_mb_prefetch;
-					nr = nr + sbi->s_mb_prefetch - group;
+					nr = 1 << sbi->s_log_groups_per_flex;
+					nr -= group & (nr - 1);
+					nr = min(nr, sbi->s_mb_prefetch);
 				}
 				prefetch_grp = ext4_mb_prefetch(sb, group,
 							nr, &prefetch_ios);
@@ -2733,7 +2710,8 @@ static int ext4_mb_init_backend(struct super_block *sb)
 
 	if (ext4_has_feature_flex_bg(sb)) {
 		/* a single flex group is supposed to be read by a single IO */
-		sbi->s_mb_prefetch = 1 << sbi->s_es->s_log_groups_per_flex;
+		sbi->s_mb_prefetch = min(1 << sbi->s_es->s_log_groups_per_flex,
+			BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9));
 		sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */
 	} else {
 		sbi->s_mb_prefetch = 32;
@@ -5126,6 +5104,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 				ext4_group_first_block_no(sb, group) +
 				EXT4_C2B(sbi, cluster),
 				"Block already on to-be-freed list");
+			kmem_cache_free(ext4_free_data_cachep, new_entry);
 			return 0;
 		}
 	}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 326fe402e495..cf652ba3e74d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -182,10 +182,6 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
 	return bh;
 }
 
-#ifndef assert
-#define assert(test) J_ASSERT(test)
-#endif
-
 #ifdef DX_DEBUG
 #define dxtrace(command) command
 #else
@@ -843,7 +839,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
 					break;
 				}
 			}
-			assert (at == p - 1);
+			ASSERT(at == p - 1);
 		}
 
 		at = p - 1;
@@ -1259,8 +1255,8 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
 	struct dx_entry *old = frame->at, *new = old + 1;
 	int count = dx_get_count(entries);
 
-	assert(count < dx_get_limit(entries));
-	assert(old < entries + count);
+	ASSERT(count < dx_get_limit(entries));
+	ASSERT(old < entries + count);
 	memmove(new + 1, new, (char *)(entries + count) - (char *)(new));
 	dx_set_hash(new, hash);
 	dx_set_block(new, block);
@@ -2959,7 +2955,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	 * hold i_mutex, or the inode can not be referenced from outside,
 	 * so i_nlink should not be bumped due to race
 	 */
-	J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+	ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 		  S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
 
 	BUFFER_TRACE(sbi->s_sbh, "get_write_access");
@@ -2980,14 +2976,17 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	    (le32_to_cpu(sbi->s_es->s_inodes_count))) {
 		/* Insert this inode at the head of the on-disk orphan list */
 		NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
+		lock_buffer(sbi->s_sbh);
 		sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+		ext4_superblock_csum_set(sb);
+		unlock_buffer(sbi->s_sbh);
 		dirty = true;
 	}
 	list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
 	mutex_unlock(&sbi->s_orphan_lock);
 
 	if (dirty) {
-		err = ext4_handle_dirty_super(handle, sb);
+		err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
 		rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
 		if (!err)
 			err = rc;
@@ -3063,9 +3062,12 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 			mutex_unlock(&sbi->s_orphan_lock);
 			goto out_brelse;
 		}
+		lock_buffer(sbi->s_sbh);
 		sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+		ext4_superblock_csum_set(inode->i_sb);
+		unlock_buffer(sbi->s_sbh);
 		mutex_unlock(&sbi->s_orphan_lock);
-		err = ext4_handle_dirty_super(handle, inode->i_sb);
+		err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
 	} else {
 		struct ext4_iloc iloc2;
 		struct inode *i_prev =
@@ -3597,9 +3599,6 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
 			return retval2;
 		}
 	}
-	brelse(ent->bh);
-	ent->bh = NULL;
-
 	return retval;
 }
 
@@ -3798,6 +3797,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 	}
 
+	old_file_type = old.de->file_type;
 	if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
 		ext4_handle_sync(handle);
 
@@ -3825,7 +3825,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	force_reread = (new.dir->i_ino == old.dir->i_ino &&
 			ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA));
 
-	old_file_type = old.de->file_type;
 	if (whiteout) {
 		/*
 		 * Do this before adding a new entry, so the old entry is sure
@@ -3923,15 +3922,19 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	retval = 0;
 
 end_rename:
-	brelse(old.dir_bh);
-	brelse(old.bh);
-	brelse(new.bh);
 	if (whiteout) {
-		if (retval)
+		if (retval) {
+			ext4_setent(handle, &old,
+				old.inode->i_ino, old_file_type);
 			drop_nlink(whiteout);
+		}
 		unlock_new_inode(whiteout);
 		iput(whiteout);
+
 	}
+	brelse(old.dir_bh);
+	brelse(old.bh);
+	brelse(new.bh);
 	if (handle)
 		ext4_journal_stop(handle);
 	return retval;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index defd2e10dfd1..03a44a0de86a 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -111,9 +111,6 @@ static void ext4_finish_bio(struct bio *bio)
 		unsigned under_io = 0;
 		unsigned long flags;
 
-		if (!page)
-			continue;
-
 		if (fscrypt_is_bounce_page(page)) {
 			bounce_page = page;
 			page = fscrypt_pagecache_page(bounce_page);
@@ -438,7 +435,6 @@ submit_and_retry:
 int ext4_bio_write_page(struct ext4_io_submit *io,
 			struct page *page,
 			int len,
-			struct writeback_control *wbc,
 			bool keep_towrite)
 {
 	struct page *bounce_page = NULL;
@@ -448,6 +444,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	int ret = 0;
 	int nr_submitted = 0;
 	int nr_to_submit = 0;
+	struct writeback_control *wbc = io->io_wbc;
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(PageWriteback(page));
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 928700d57eb6..bd0d185654f3 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -899,8 +899,11 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	EXT4_SB(sb)->s_gdb_count++;
 	ext4_kvfree_array_rcu(o_group_desc);
 
+	lock_buffer(EXT4_SB(sb)->s_sbh);
 	le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
-	err = ext4_handle_dirty_super(handle, sb);
+	ext4_superblock_csum_set(sb);
+	unlock_buffer(EXT4_SB(sb)->s_sbh);
+	err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
 	if (err)
 		ext4_std_error(sb, err);
 	return err;
@@ -1384,6 +1387,7 @@ static void ext4_update_super(struct super_block *sb,
 	reserved_blocks *= blocks_count;
 	do_div(reserved_blocks, 100);
 
+	lock_buffer(sbi->s_sbh);
 	ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count);
 	ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks);
 	le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) *
@@ -1421,6 +1425,8 @@ static void ext4_update_super(struct super_block *sb,
 	 * active. */
 	ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
 				reserved_blocks);
+	ext4_superblock_csum_set(sb);
+	unlock_buffer(sbi->s_sbh);
 
 	/* Update the free space counts */
 	percpu_counter_add(&sbi->s_freeclusters_counter,
@@ -1515,7 +1521,7 @@ static int ext4_flex_group_add(struct super_block *sb,
 
 	ext4_update_super(sb, flex_gd);
 
-	err = ext4_handle_dirty_super(handle, sb);
+	err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
 
 exit_journal:
 	err2 = ext4_journal_stop(handle);
@@ -1717,15 +1723,18 @@ static int ext4_group_extend_no_check(struct super_block *sb,
 		goto errout;
 	}
 
+	lock_buffer(EXT4_SB(sb)->s_sbh);
 	ext4_blocks_count_set(es, o_blocks_count + add);
 	ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add);
+	ext4_superblock_csum_set(sb);
+	unlock_buffer(EXT4_SB(sb)->s_sbh);
 	ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
 		   o_blocks_count + add);
 	/* We add the blocks to the bitmap and set the group need init bit */
 	err = ext4_group_add_blocks(handle, sb, o_blocks_count, add);
 	if (err)
 		goto errout;
-	ext4_handle_dirty_super(handle, sb);
+	ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
 	ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
 		   o_blocks_count + add);
 errout:
@@ -1874,12 +1883,15 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode)
 	if (err)
 		goto errout;
 
+	lock_buffer(sbi->s_sbh);
 	ext4_clear_feature_resize_inode(sb);
 	ext4_set_feature_meta_bg(sb);
 	sbi->s_es->s_first_meta_bg =
 		cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count));
+	ext4_superblock_csum_set(sb);
+	unlock_buffer(sbi->s_sbh);
 
-	err = ext4_handle_dirty_super(handle, sb);
+	err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
 	if (err) {
 		ext4_std_error(sb, err);
 		goto errout;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 830c196ec069..9a6f9875aa34 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -65,7 +65,8 @@ static struct ratelimit_state ext4_mount_msg_ratelimit;
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
 			     unsigned long journal_devnum);
 static int ext4_show_options(struct seq_file *seq, struct dentry *root);
-static int ext4_commit_super(struct super_block *sb, int sync);
+static void ext4_update_super(struct super_block *sb);
+static int ext4_commit_super(struct super_block *sb);
 static int ext4_mark_recovery_complete(struct super_block *sb,
 					struct ext4_super_block *es);
 static int ext4_clear_journal_err(struct super_block *sb,
@@ -404,10 +405,8 @@ void ext4_itable_unused_set(struct super_block *sb,
 		bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
 }
 
-static void __ext4_update_tstamp(__le32 *lo, __u8 *hi)
+static void __ext4_update_tstamp(__le32 *lo, __u8 *hi, time64_t now)
 {
-	time64_t now = ktime_get_real_seconds();
-
 	now = clamp_val(now, 0, (1ull << 40) - 1);
 
 	*lo = cpu_to_le32(lower_32_bits(now));
@@ -419,108 +418,11 @@ static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi)
 	return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo);
 }
 #define ext4_update_tstamp(es, tstamp) \
-	__ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
+	__ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi, \
+			     ktime_get_real_seconds())
 #define ext4_get_tstamp(es, tstamp) \
 	__ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
 
-static void __save_error_info(struct super_block *sb, int error,
-			      __u32 ino, __u64 block,
-			      const char *func, unsigned int line)
-{
-	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
-	int err;
-
-	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
-	if (bdev_read_only(sb->s_bdev))
-		return;
-	es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-	ext4_update_tstamp(es, s_last_error_time);
-	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
-	es->s_last_error_line = cpu_to_le32(line);
-	es->s_last_error_ino = cpu_to_le32(ino);
-	es->s_last_error_block = cpu_to_le64(block);
-	switch (error) {
-	case EIO:
-		err = EXT4_ERR_EIO;
-		break;
-	case ENOMEM:
-		err = EXT4_ERR_ENOMEM;
-		break;
-	case EFSBADCRC:
-		err = EXT4_ERR_EFSBADCRC;
-		break;
-	case 0:
-	case EFSCORRUPTED:
-		err = EXT4_ERR_EFSCORRUPTED;
-		break;
-	case ENOSPC:
-		err = EXT4_ERR_ENOSPC;
-		break;
-	case ENOKEY:
-		err = EXT4_ERR_ENOKEY;
-		break;
-	case EROFS:
-		err = EXT4_ERR_EROFS;
-		break;
-	case EFBIG:
-		err = EXT4_ERR_EFBIG;
-		break;
-	case EEXIST:
-		err = EXT4_ERR_EEXIST;
-		break;
-	case ERANGE:
-		err = EXT4_ERR_ERANGE;
-		break;
-	case EOVERFLOW:
-		err = EXT4_ERR_EOVERFLOW;
-		break;
-	case EBUSY:
-		err = EXT4_ERR_EBUSY;
-		break;
-	case ENOTDIR:
-		err = EXT4_ERR_ENOTDIR;
-		break;
-	case ENOTEMPTY:
-		err = EXT4_ERR_ENOTEMPTY;
-		break;
-	case ESHUTDOWN:
-		err = EXT4_ERR_ESHUTDOWN;
-		break;
-	case EFAULT:
-		err = EXT4_ERR_EFAULT;
-		break;
-	default:
-		err = EXT4_ERR_UNKNOWN;
-	}
-	es->s_last_error_errcode = err;
-	if (!es->s_first_error_time) {
-		es->s_first_error_time = es->s_last_error_time;
-		es->s_first_error_time_hi = es->s_last_error_time_hi;
-		strncpy(es->s_first_error_func, func,
-			sizeof(es->s_first_error_func));
-		es->s_first_error_line = cpu_to_le32(line);
-		es->s_first_error_ino = es->s_last_error_ino;
-		es->s_first_error_block = es->s_last_error_block;
-		es->s_first_error_errcode = es->s_last_error_errcode;
-	}
-	/*
-	 * Start the daily error reporting function if it hasn't been
-	 * started already
-	 */
-	if (!es->s_error_count)
-		mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ);
-	le32_add_cpu(&es->s_error_count, 1);
-}
-
-static void save_error_info(struct super_block *sb, int error,
-			    __u32 ino, __u64 block,
-			    const char *func, unsigned int line)
-{
-	__save_error_info(sb, error, ino, block, func, line);
-	if (!bdev_read_only(sb->s_bdev))
-		ext4_commit_super(sb, 1);
-}
-
 /*
  * The del_gendisk() function uninitializes the disk-specific data
  * structures, including the bdi structure, without telling anyone
@@ -649,6 +551,71 @@ static bool system_going_down(void)
 		|| system_state == SYSTEM_RESTART;
 }
 
+struct ext4_err_translation {
+	int code;
+	int errno;
+};
+
+#define EXT4_ERR_TRANSLATE(err) { .code = EXT4_ERR_##err, .errno = err }
+
+static struct ext4_err_translation err_translation[] = {
+	EXT4_ERR_TRANSLATE(EIO),
+	EXT4_ERR_TRANSLATE(ENOMEM),
+	EXT4_ERR_TRANSLATE(EFSBADCRC),
+	EXT4_ERR_TRANSLATE(EFSCORRUPTED),
+	EXT4_ERR_TRANSLATE(ENOSPC),
+	EXT4_ERR_TRANSLATE(ENOKEY),
+	EXT4_ERR_TRANSLATE(EROFS),
+	EXT4_ERR_TRANSLATE(EFBIG),
+	EXT4_ERR_TRANSLATE(EEXIST),
+	EXT4_ERR_TRANSLATE(ERANGE),
+	EXT4_ERR_TRANSLATE(EOVERFLOW),
+	EXT4_ERR_TRANSLATE(EBUSY),
+	EXT4_ERR_TRANSLATE(ENOTDIR),
+	EXT4_ERR_TRANSLATE(ENOTEMPTY),
+	EXT4_ERR_TRANSLATE(ESHUTDOWN),
+	EXT4_ERR_TRANSLATE(EFAULT),
+};
+
+static int ext4_errno_to_code(int errno)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(err_translation); i++)
+		if (err_translation[i].errno == errno)
+			return err_translation[i].code;
+	return EXT4_ERR_UNKNOWN;
+}
+
+static void save_error_info(struct super_block *sb, int error,
+			    __u32 ino, __u64 block,
+			    const char *func, unsigned int line)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	/* We default to EFSCORRUPTED error... */
+	if (error == 0)
+		error = EFSCORRUPTED;
+
+	spin_lock(&sbi->s_error_lock);
+	sbi->s_add_error_count++;
+	sbi->s_last_error_code = error;
+	sbi->s_last_error_line = line;
+	sbi->s_last_error_ino = ino;
+	sbi->s_last_error_block = block;
+	sbi->s_last_error_func = func;
+	sbi->s_last_error_time = ktime_get_real_seconds();
+	if (!sbi->s_first_error_time) {
+		sbi->s_first_error_code = error;
+		sbi->s_first_error_line = line;
+		sbi->s_first_error_ino = ino;
+		sbi->s_first_error_block = block;
+		sbi->s_first_error_func = func;
+		sbi->s_first_error_time = sbi->s_last_error_time;
+	}
+	spin_unlock(&sbi->s_error_lock);
+}
+
 /* Deal with the reporting of failure conditions on a filesystem such as
  * inconsistencies detected or read IO failures.
  *
@@ -662,40 +629,102 @@ static bool system_going_down(void)
  * We'll just use the jbd2_journal_abort() error code to record an error in
  * the journal instead.  On recovery, the journal will complain about
  * that error until we've noted it down and cleared it.
+ *
+ * If force_ro is set, we unconditionally force the filesystem into an
+ * ABORT|READONLY state, unless the error response on the fs has been set to
+ * panic in which case we take the easy way out and panic immediately. This is
+ * used to deal with unrecoverable failures such as journal IO errors or ENOMEM
+ * at a critical moment in log management.
  */
-
-static void ext4_handle_error(struct super_block *sb)
+static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
+			      __u32 ino, __u64 block,
+			      const char *func, unsigned int line)
 {
+	journal_t *journal = EXT4_SB(sb)->s_journal;
+	bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT);
+
+	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
 	if (test_opt(sb, WARN_ON_ERROR))
 		WARN_ON_ONCE(1);
 
-	if (sb_rdonly(sb))
-		return;
-
-	if (!test_opt(sb, ERRORS_CONT)) {
-		journal_t *journal = EXT4_SB(sb)->s_journal;
-
+	if (!continue_fs && !sb_rdonly(sb)) {
 		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
 		if (journal)
 			jbd2_journal_abort(journal, -EIO);
 	}
+
+	if (!bdev_read_only(sb->s_bdev)) {
+		save_error_info(sb, error, ino, block, func, line);
+		/*
+		 * In case the fs should keep running, we need to writeout
+		 * superblock through the journal. Due to lock ordering
+		 * constraints, it may not be safe to do it right here so we
+		 * defer superblock flushing to a workqueue.
+		 */
+		if (continue_fs)
+			schedule_work(&EXT4_SB(sb)->s_error_work);
+		else
+			ext4_commit_super(sb);
+	}
+
+	if (sb_rdonly(sb) || continue_fs)
+		return;
+
 	/*
 	 * We force ERRORS_RO behavior when system is rebooting. Otherwise we
 	 * could panic during 'reboot -f' as the underlying device got already
 	 * disabled.
 	 */
-	if (test_opt(sb, ERRORS_RO) || system_going_down()) {
-		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
-		/*
-		 * Make sure updated value of ->s_mount_flags will be visible
-		 * before ->s_flags update
-		 */
-		smp_wmb();
-		sb->s_flags |= SB_RDONLY;
-	} else if (test_opt(sb, ERRORS_PANIC)) {
+	if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) {
 		panic("EXT4-fs (device %s): panic forced after error\n",
 			sb->s_id);
 	}
+	ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
+	/*
+	 * Make sure updated value of ->s_mount_flags will be visible before
+	 * ->s_flags update
+	 */
+	smp_wmb();
+	sb->s_flags |= SB_RDONLY;
+}
+
+static void flush_stashed_error_work(struct work_struct *work)
+{
+	struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info,
+						s_error_work);
+	journal_t *journal = sbi->s_journal;
+	handle_t *handle;
+
+	/*
+	 * If the journal is still running, we have to write out superblock
+	 * through the journal to avoid collisions of other journalled sb
+	 * updates.
+	 *
+	 * We use directly jbd2 functions here to avoid recursing back into
+	 * ext4 error handling code during handling of previous errors.
+	 */
+	if (!sb_rdonly(sbi->s_sb) && journal) {
+		handle = jbd2_journal_start(journal, 1);
+		if (IS_ERR(handle))
+			goto write_directly;
+		if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) {
+			jbd2_journal_stop(handle);
+			goto write_directly;
+		}
+		ext4_update_super(sbi->s_sb);
+		if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) {
+			jbd2_journal_stop(handle);
+			goto write_directly;
+		}
+		jbd2_journal_stop(handle);
+		return;
+	}
+write_directly:
+	/*
+	 * Write through journal failed. Write sb directly to get error info
+	 * out and hope for the best.
+	 */
+	ext4_commit_super(sbi->s_sb);
 }
 
 #define ext4_error_ratelimit(sb)					\
@@ -703,7 +732,7 @@ static void ext4_handle_error(struct super_block *sb)
 			     "EXT4-fs error")
 
 void __ext4_error(struct super_block *sb, const char *function,
-		  unsigned int line, int error, __u64 block,
+		  unsigned int line, bool force_ro, int error, __u64 block,
 		  const char *fmt, ...)
 {
 	struct va_format vaf;
@@ -722,8 +751,7 @@ void __ext4_error(struct super_block *sb, const char *function,
 		       sb->s_id, function, line, current->comm, &vaf);
 		va_end(args);
 	}
-	save_error_info(sb, error, 0, block, function, line);
-	ext4_handle_error(sb);
+	ext4_handle_error(sb, force_ro, error, 0, block, function, line);
 }
 
 void __ext4_error_inode(struct inode *inode, const char *function,
@@ -753,9 +781,8 @@ void __ext4_error_inode(struct inode *inode, const char *function,
 			       current->comm, &vaf);
 		va_end(args);
 	}
-	save_error_info(inode->i_sb, error, inode->i_ino, block,
-			function, line);
-	ext4_handle_error(inode->i_sb);
+	ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block,
+			  function, line);
 }
 
 void __ext4_error_file(struct file *file, const char *function,
@@ -792,9 +819,8 @@ void __ext4_error_file(struct file *file, const char *function,
 			       current->comm, path, &vaf);
 		va_end(args);
 	}
-	save_error_info(inode->i_sb, EFSCORRUPTED, inode->i_ino, block,
-			function, line);
-	ext4_handle_error(inode->i_sb);
+	ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block,
+			  function, line);
 }
 
 const char *ext4_decode_error(struct super_block *sb, int errno,
@@ -861,52 +887,7 @@ void __ext4_std_error(struct super_block *sb, const char *function,
 		       sb->s_id, function, line, errstr);
 	}
 
-	save_error_info(sb, -errno, 0, 0, function, line);
-	ext4_handle_error(sb);
-}
-
-/*
- * ext4_abort is a much stronger failure handler than ext4_error.  The
- * abort function may be used to deal with unrecoverable failures such
- * as journal IO errors or ENOMEM at a critical moment in log management.
- *
- * We unconditionally force the filesystem into an ABORT|READONLY state,
- * unless the error response on the fs has been set to panic in which
- * case we take the easy way out and panic immediately.
- */
-
-void __ext4_abort(struct super_block *sb, const char *function,
-		  unsigned int line, int error, const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
-		return;
-
-	save_error_info(sb, error, 0, 0, function, line);
-	va_start(args, fmt);
-	vaf.fmt = fmt;
-	vaf.va = &args;
-	printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: %pV\n",
-	       sb->s_id, function, line, &vaf);
-	va_end(args);
-
-	if (sb_rdonly(sb) == 0) {
-		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
-		if (EXT4_SB(sb)->s_journal)
-			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
-
-		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
-		/*
-		 * Make sure updated value of ->s_mount_flags will be visible
-		 * before ->s_flags update
-		 */
-		smp_wmb();
-		sb->s_flags |= SB_RDONLY;
-	}
-	if (test_opt(sb, ERRORS_PANIC) && !system_going_down())
-		panic("EXT4-fs panic from previous error\n");
+	ext4_handle_error(sb, false, -errno, 0, 0, function, line);
 }
 
 void __ext4_msg(struct super_block *sb,
@@ -982,8 +963,6 @@ __acquires(bitlock)
 		return;
 
 	trace_ext4_error(sb, function, line);
-	__save_error_info(sb, EFSCORRUPTED, ino, block, function, line);
-
 	if (ext4_error_ratelimit(sb)) {
 		va_start(args, fmt);
 		vaf.fmt = fmt;
@@ -999,17 +978,19 @@ __acquires(bitlock)
 		va_end(args);
 	}
 
-	if (test_opt(sb, WARN_ON_ERROR))
-		WARN_ON_ONCE(1);
-
 	if (test_opt(sb, ERRORS_CONT)) {
-		ext4_commit_super(sb, 0);
+		if (test_opt(sb, WARN_ON_ERROR))
+			WARN_ON_ONCE(1);
+		EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+		if (!bdev_read_only(sb->s_bdev)) {
+			save_error_info(sb, EFSCORRUPTED, ino, block, function,
+					line);
+			schedule_work(&EXT4_SB(sb)->s_error_work);
+		}
 		return;
 	}
-
 	ext4_unlock_group(sb, grp);
-	ext4_commit_super(sb, 1);
-	ext4_handle_error(sb);
+	ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line);
 	/*
 	 * We only get here in the ERRORS_RO case; relocking the group
 	 * may be dangerous, but nothing bad will happen since the
@@ -1181,6 +1162,7 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_unregister_li_request(sb);
 	ext4_quota_off_umount(sb);
 
+	flush_work(&sbi->s_error_work);
 	destroy_workqueue(sbi->rsv_conversion_wq);
 
 	/*
@@ -1210,7 +1192,7 @@ static void ext4_put_super(struct super_block *sb)
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
 	}
 	if (!sb_rdonly(sb))
-		ext4_commit_super(sb, 1);
+		ext4_commit_super(sb);
 
 	rcu_read_lock();
 	group_desc = rcu_dereference(sbi->s_group_desc);
@@ -1240,7 +1222,7 @@ static void ext4_put_super(struct super_block *sb)
 	 * in-memory list had better be clean by this point. */
 	if (!list_empty(&sbi->s_orphan))
 		dump_orphan_list(sb, sbi);
-	J_ASSERT(list_empty(&sbi->s_orphan));
+	ASSERT(list_empty(&sbi->s_orphan));
 
 	sync_blockdev(sb->s_bdev);
 	invalidate_bdev(sb->s_bdev);
@@ -2700,7 +2682,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 	if (sbi->s_journal)
 		ext4_set_feature_journal_needs_recovery(sb);
 
-	err = ext4_commit_super(sb, 1);
+	err = ext4_commit_super(sb);
 done:
 	if (test_opt(sb, DEBUG))
 		printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
@@ -4005,6 +3987,21 @@ static void ext4_set_resv_clusters(struct super_block *sb)
 	atomic64_set(&sbi->s_resv_clusters, resv_clusters);
 }
 
+static const char *ext4_quota_mode(struct super_block *sb)
+{
+#ifdef CONFIG_QUOTA
+	if (!ext4_quota_capable(sb))
+		return "none";
+
+	if (EXT4_SB(sb)->s_journal && ext4_is_quota_journalled(sb))
+		return "journalled";
+	else
+		return "writeback";
+#else
+	return "disabled";
+#endif
+}
+
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
@@ -4073,7 +4070,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (IS_ERR(bh)) {
 		ext4_msg(sb, KERN_ERR, "unable to read superblock");
 		ret = PTR_ERR(bh);
-		bh = NULL;
 		goto out_fail;
 	}
 	/*
@@ -4187,19 +4183,26 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 */
 	sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
 
-	blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
-
-	if (blocksize == PAGE_SIZE)
-		set_opt(sb, DIOREAD_NOLOCK);
-
-	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
-	    blocksize > EXT4_MAX_BLOCK_SIZE) {
+	if (le32_to_cpu(es->s_log_block_size) >
+	    (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
 		ext4_msg(sb, KERN_ERR,
-		       "Unsupported filesystem blocksize %d (%d log_block_size)",
-			 blocksize, le32_to_cpu(es->s_log_block_size));
+			 "Invalid log block size: %u",
+			 le32_to_cpu(es->s_log_block_size));
+		goto failed_mount;
+	}
+	if (le32_to_cpu(es->s_log_cluster_size) >
+	    (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Invalid log cluster size: %u",
+			 le32_to_cpu(es->s_log_cluster_size));
 		goto failed_mount;
 	}
 
+	blocksize = EXT4_MIN_BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
+
+	if (blocksize == PAGE_SIZE)
+		set_opt(sb, DIOREAD_NOLOCK);
+
 	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
 		sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
 		sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
@@ -4417,21 +4420,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ext4_feature_set_ok(sb, (sb_rdonly(sb))))
 		goto failed_mount;
 
-	if (le32_to_cpu(es->s_log_block_size) >
-	    (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
-		ext4_msg(sb, KERN_ERR,
-			 "Invalid log block size: %u",
-			 le32_to_cpu(es->s_log_block_size));
-		goto failed_mount;
-	}
-	if (le32_to_cpu(es->s_log_cluster_size) >
-	    (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
-		ext4_msg(sb, KERN_ERR,
-			 "Invalid log cluster size: %u",
-			 le32_to_cpu(es->s_log_cluster_size));
-		goto failed_mount;
-	}
-
 	if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
 		ext4_msg(sb, KERN_ERR,
 			 "Number of reserved GDT blocks insanely large: %d",
@@ -4702,7 +4690,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			       "can't read group descriptor %d", i);
 			db_count = i;
 			ret = PTR_ERR(bh);
-			bh = NULL;
 			goto failed_mount2;
 		}
 		rcu_read_lock();
@@ -4717,6 +4704,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
+	spin_lock_init(&sbi->s_error_lock);
+	INIT_WORK(&sbi->s_error_work, flush_stashed_error_work);
 
 	/* Register extent status tree shrinker */
 	if (ext4_es_register_shrinker(sbi))
@@ -4872,6 +4861,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			       "requested data journaling mode");
 			goto failed_mount_wq;
 		}
+		break;
 	default:
 		break;
 	}
@@ -4918,7 +4908,7 @@ no_journal:
 	if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) &&
 	    !ext4_has_feature_encrypt(sb)) {
 		ext4_set_feature_encrypt(sb);
-		ext4_commit_super(sb, 1);
+		ext4_commit_super(sb);
 	}
 
 	/*
@@ -5000,13 +4990,11 @@ no_journal:
 	block = ext4_count_free_clusters(sb);
 	ext4_free_blocks_count_set(sbi->s_es, 
 				   EXT4_C2B(sbi, block));
-	ext4_superblock_csum_set(sb);
 	err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
 				  GFP_KERNEL);
 	if (!err) {
 		unsigned long freei = ext4_count_free_inodes(sb);
 		sbi->s_es->s_free_inodes_count = cpu_to_le32(freei);
-		ext4_superblock_csum_set(sb);
 		err = percpu_counter_init(&sbi->s_freeinodes_counter, freei,
 					  GFP_KERNEL);
 	}
@@ -5086,10 +5074,11 @@ no_journal:
 
 	if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount"))
 		ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
-			 "Opts: %.*s%s%s", descr,
+			 "Opts: %.*s%s%s. Quota mode: %s.", descr,
 			 (int) sizeof(sbi->s_es->s_mount_opts),
 			 sbi->s_es->s_mount_opts,
-			 *sbi->s_es->s_mount_opts ? "; " : "", orig_data);
+			 *sbi->s_es->s_mount_opts ? "; " : "", orig_data,
+			 ext4_quota_mode(sb));
 
 	if (es->s_error_count)
 		mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
@@ -5154,6 +5143,7 @@ failed_mount3a:
 	ext4_es_unregister_shrinker(sbi);
 failed_mount3:
 	del_timer_sync(&sbi->s_err_report);
+	flush_work(&sbi->s_error_work);
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2:
@@ -5468,7 +5458,7 @@ static int ext4_load_journal(struct super_block *sb,
 		es->s_journal_dev = cpu_to_le32(journal_devnum);
 
 		/* Make sure we flush the recovery flag to disk. */
-		ext4_commit_super(sb, 1);
+		ext4_commit_super(sb);
 	}
 
 	return 0;
@@ -5478,15 +5468,14 @@ err_out:
 	return err;
 }
 
-static int ext4_commit_super(struct super_block *sb, int sync)
+/* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */
+static void ext4_update_super(struct super_block *sb)
 {
-	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
-	struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
-	int error = 0;
-
-	if (!sbh || block_device_ejected(sb))
-		return error;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	struct buffer_head *sbh = sbi->s_sbh;
 
+	lock_buffer(sbh);
 	/*
 	 * If the file system is mounted read-only, don't update the
 	 * superblock write time.  This avoids updating the superblock
@@ -5500,21 +5489,71 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 	if (!(sb->s_flags & SB_RDONLY))
 		ext4_update_tstamp(es, s_wtime);
 	es->s_kbytes_written =
-		cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
+		cpu_to_le64(sbi->s_kbytes_written +
 		    ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
-		      EXT4_SB(sb)->s_sectors_written_start) >> 1));
-	if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter))
+		      sbi->s_sectors_written_start) >> 1));
+	if (percpu_counter_initialized(&sbi->s_freeclusters_counter))
 		ext4_free_blocks_count_set(es,
-			EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
-				&EXT4_SB(sb)->s_freeclusters_counter)));
-	if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter))
+			EXT4_C2B(sbi, percpu_counter_sum_positive(
+				&sbi->s_freeclusters_counter)));
+	if (percpu_counter_initialized(&sbi->s_freeinodes_counter))
 		es->s_free_inodes_count =
 			cpu_to_le32(percpu_counter_sum_positive(
-				&EXT4_SB(sb)->s_freeinodes_counter));
-	BUFFER_TRACE(sbh, "marking dirty");
+				&sbi->s_freeinodes_counter));
+	/* Copy error information to the on-disk superblock */
+	spin_lock(&sbi->s_error_lock);
+	if (sbi->s_add_error_count > 0) {
+		es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+		if (!es->s_first_error_time && !es->s_first_error_time_hi) {
+			__ext4_update_tstamp(&es->s_first_error_time,
+					     &es->s_first_error_time_hi,
+					     sbi->s_first_error_time);
+			strncpy(es->s_first_error_func, sbi->s_first_error_func,
+				sizeof(es->s_first_error_func));
+			es->s_first_error_line =
+				cpu_to_le32(sbi->s_first_error_line);
+			es->s_first_error_ino =
+				cpu_to_le32(sbi->s_first_error_ino);
+			es->s_first_error_block =
+				cpu_to_le64(sbi->s_first_error_block);
+			es->s_first_error_errcode =
+				ext4_errno_to_code(sbi->s_first_error_code);
+		}
+		__ext4_update_tstamp(&es->s_last_error_time,
+				     &es->s_last_error_time_hi,
+				     sbi->s_last_error_time);
+		strncpy(es->s_last_error_func, sbi->s_last_error_func,
+			sizeof(es->s_last_error_func));
+		es->s_last_error_line = cpu_to_le32(sbi->s_last_error_line);
+		es->s_last_error_ino = cpu_to_le32(sbi->s_last_error_ino);
+		es->s_last_error_block = cpu_to_le64(sbi->s_last_error_block);
+		es->s_last_error_errcode =
+				ext4_errno_to_code(sbi->s_last_error_code);
+		/*
+		 * Start the daily error reporting function if it hasn't been
+		 * started already
+		 */
+		if (!es->s_error_count)
+			mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ);
+		le32_add_cpu(&es->s_error_count, sbi->s_add_error_count);
+		sbi->s_add_error_count = 0;
+	}
+	spin_unlock(&sbi->s_error_lock);
+
 	ext4_superblock_csum_set(sb);
-	if (sync)
-		lock_buffer(sbh);
+	unlock_buffer(sbh);
+}
+
+static int ext4_commit_super(struct super_block *sb)
+{
+	struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
+	int error = 0;
+
+	if (!sbh || block_device_ejected(sb))
+		return error;
+
+	ext4_update_super(sb);
+
 	if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) {
 		/*
 		 * Oh, dear.  A previous attempt to write the
@@ -5529,17 +5568,15 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 		clear_buffer_write_io_error(sbh);
 		set_buffer_uptodate(sbh);
 	}
+	BUFFER_TRACE(sbh, "marking dirty");
 	mark_buffer_dirty(sbh);
-	if (sync) {
-		unlock_buffer(sbh);
-		error = __sync_dirty_buffer(sbh,
-			REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
-		if (buffer_write_io_error(sbh)) {
-			ext4_msg(sb, KERN_ERR, "I/O error while writing "
-			       "superblock");
-			clear_buffer_write_io_error(sbh);
-			set_buffer_uptodate(sbh);
-		}
+	error = __sync_dirty_buffer(sbh,
+		REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
+	if (buffer_write_io_error(sbh)) {
+		ext4_msg(sb, KERN_ERR, "I/O error while writing "
+		       "superblock");
+		clear_buffer_write_io_error(sbh);
+		set_buffer_uptodate(sbh);
 	}
 	return error;
 }
@@ -5570,7 +5607,7 @@ static int ext4_mark_recovery_complete(struct super_block *sb,
 
 	if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) {
 		ext4_clear_feature_journal_needs_recovery(sb);
-		ext4_commit_super(sb, 1);
+		ext4_commit_super(sb);
 	}
 out:
 	jbd2_journal_unlock_updates(journal);
@@ -5612,7 +5649,7 @@ static int ext4_clear_journal_err(struct super_block *sb,
 
 		EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
 		es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-		ext4_commit_super(sb, 1);
+		ext4_commit_super(sb);
 
 		jbd2_journal_clear_err(journal);
 		jbd2_journal_update_sb_errno(journal);
@@ -5714,7 +5751,7 @@ static int ext4_freeze(struct super_block *sb)
 		ext4_clear_feature_journal_needs_recovery(sb);
 	}
 
-	error = ext4_commit_super(sb, 1);
+	error = ext4_commit_super(sb);
 out:
 	if (journal)
 		/* we rely on upper layer to stop further updates */
@@ -5736,7 +5773,7 @@ static int ext4_unfreeze(struct super_block *sb)
 		ext4_set_feature_journal_needs_recovery(sb);
 	}
 
-	ext4_commit_super(sb, 1);
+	ext4_commit_super(sb);
 	return 0;
 }
 
@@ -5864,6 +5901,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 	}
 
+	/* Flush outstanding errors before changing fs state */
+	flush_work(&sbi->s_error_work);
+
 	if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
 		if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) {
 			err = -EROFS;
@@ -5993,7 +6033,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	}
 
 	if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) {
-		err = ext4_commit_super(sb, 1);
+		err = ext4_commit_super(sb);
 		if (err)
 			goto restore_opts;
 	}
@@ -6022,7 +6062,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 	 */
 	*flags = (*flags & ~vfs_flags) | (sb->s_flags & vfs_flags);
 
-	ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
+	ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s. Quota mode: %s.",
+		 orig_data, ext4_quota_mode(sb));
 	kfree(orig_data);
 	return 0;
 
@@ -6201,11 +6242,8 @@ static int ext4_release_dquot(struct dquot *dquot)
 static int ext4_mark_dquot_dirty(struct dquot *dquot)
 {
 	struct super_block *sb = dquot->dq_sb;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	/* Are we journaling quotas? */
-	if (ext4_has_feature_quota(sb) ||
-	    sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
+	if (ext4_is_quota_journalled(sb)) {
 		dquot_mark_dquot_dirty(dquot);
 		return ext4_write_dquot(dquot);
 	} else {
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 6127e94ea4f5..372208500f4e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -792,8 +792,11 @@ static void ext4_xattr_update_super_block(handle_t *handle,
 
 	BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
 	if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
+		lock_buffer(EXT4_SB(sb)->s_sbh);
 		ext4_set_feature_xattr(sb);
-		ext4_handle_dirty_super(handle, sb);
+		ext4_superblock_csum_set(sb);
+		unlock_buffer(EXT4_SB(sb)->s_sbh);
+		ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
 	}
 }
 
@@ -1927,7 +1930,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 	} else {
 		/* Allocate a buffer where we construct the new block. */
 		s->base = kzalloc(sb->s_blocksize, GFP_NOFS);
-		/* assert(header == s->base) */
 		error = -ENOMEM;
 		if (s->base == NULL)
 			goto cleanup;
diff --git a/fs/file.c b/fs/file.c
index c0b60961c672..dab120b71e44 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -21,7 +21,6 @@
 #include <linux/rcupdate.h>
 #include <linux/close_range.h>
 #include <net/sock.h>
-#include <linux/io_uring.h>
 
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;
@@ -428,7 +427,6 @@ void exit_files(struct task_struct *tsk)
 	struct files_struct * files = tsk->files;
 
 	if (files) {
-		io_uring_files_cancel(files);
 		task_lock(tsk);
 		tsk->files = NULL;
 		task_unlock(tsk);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index a1f9dde33058..7a358ae05185 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1538,13 +1538,13 @@ more_rgrps:
 				goto out;
 			}
 			ret = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
-						 0, rd_gh);
+						 LM_FLAG_NODE_SCOPE, rd_gh);
 			if (ret)
 				goto out;
 
 			/* Must be done with the rgrp glock held: */
 			if (gfs2_rs_active(&ip->i_res) &&
-			    rgd == ip->i_res.rs_rbm.rgd)
+			    rgd == ip->i_res.rs_rgd)
 				gfs2_rs_deltree(&ip->i_res);
 		}
 
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index b39b339feddc..294087516ce0 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -716,10 +716,10 @@ static int gfs2_release(struct inode *inode, struct file *file)
 	kfree(file->private_data);
 	file->private_data = NULL;
 
-	if (file->f_mode & FMODE_WRITE) {
+	if (gfs2_rs_active(&ip->i_res))
 		gfs2_rs_delete(ip, &inode->i_writecount);
+	if (file->f_mode & FMODE_WRITE)
 		gfs2_qa_put(ip);
-	}
 	return 0;
 }
 
@@ -1115,8 +1115,8 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t
 			goto out_qunlock;
 
 		/* check if the selected rgrp limits our max_blks further */
-		if (ap.allowed && ap.allowed < max_blks)
-			max_blks = ap.allowed;
+		if (ip->i_res.rs_reserved < max_blks)
+			max_blks = ip->i_res.rs_reserved;
 
 		/* Almost done. Calculate bytes that can be written using
 		 * max_blks. We also recompute max_bytes, data_blocks and
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index d87a5bc3607b..9567520d79f7 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -313,9 +313,23 @@ void gfs2_glock_put(struct gfs2_glock *gl)
 static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holder *gh)
 {
 	const struct gfs2_holder *gh_head = list_first_entry(&gl->gl_holders, const struct gfs2_holder, gh_list);
-	if ((gh->gh_state == LM_ST_EXCLUSIVE ||
-	     gh_head->gh_state == LM_ST_EXCLUSIVE) && gh != gh_head)
-		return 0;
+
+	if (gh != gh_head) {
+		/**
+		 * Here we make a special exception to grant holders who agree
+		 * to share the EX lock with other holders who also have the
+		 * bit set. If the original holder has the LM_FLAG_NODE_SCOPE bit
+		 * is set, we grant more holders with the bit set.
+		 */
+		if (gh_head->gh_state == LM_ST_EXCLUSIVE &&
+		    (gh_head->gh_flags & LM_FLAG_NODE_SCOPE) &&
+		    gh->gh_state == LM_ST_EXCLUSIVE &&
+		    (gh->gh_flags & LM_FLAG_NODE_SCOPE))
+			return 1;
+		if ((gh->gh_state == LM_ST_EXCLUSIVE ||
+		     gh_head->gh_state == LM_ST_EXCLUSIVE))
+			return 0;
+	}
 	if (gl->gl_state == gh->gh_state)
 		return 1;
 	if (gh->gh_flags & GL_EXACT)
@@ -2030,6 +2044,8 @@ static const char *hflags2str(char *buf, u16 flags, unsigned long iflags)
 		*p++ = 'A';
 	if (flags & LM_FLAG_PRIORITY)
 		*p++ = 'p';
+	if (flags & LM_FLAG_NODE_SCOPE)
+		*p++ = 'n';
 	if (flags & GL_ASYNC)
 		*p++ = 'a';
 	if (flags & GL_EXACT)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 53813364517b..31a8f2f649b5 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -75,6 +75,11 @@ enum {
  * request and directly join the other shared lock.  A shared lock request
  * without the priority flag might be forced to wait until the deferred
  * requested had acquired and released the lock.
+ *
+ * LM_FLAG_NODE_SCOPE
+ * This holder agrees to share the lock within this node. In other words,
+ * the glock is held in EX mode according to DLM, but local holders on the
+ * same node can share it.
  */
 
 #define LM_FLAG_TRY		0x0001
@@ -82,6 +87,7 @@ enum {
 #define LM_FLAG_NOEXP		0x0004
 #define LM_FLAG_ANY		0x0008
 #define LM_FLAG_PRIORITY	0x0010
+#define LM_FLAG_NODE_SCOPE	0x0020
 #define GL_ASYNC		0x0040
 #define GL_EXACT		0x0080
 #define GL_SKIP			0x0100
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 3faa421568b0..8e32d569c8bf 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -86,16 +86,12 @@ static int gfs2_ail_empty_gl(struct gfs2_glock *gl)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_trans tr;
+	unsigned int revokes;
 	int ret;
 
-	memset(&tr, 0, sizeof(tr));
-	INIT_LIST_HEAD(&tr.tr_buf);
-	INIT_LIST_HEAD(&tr.tr_databuf);
-	INIT_LIST_HEAD(&tr.tr_ail1_list);
-	INIT_LIST_HEAD(&tr.tr_ail2_list);
-	tr.tr_revokes = atomic_read(&gl->gl_ail_count);
+	revokes = atomic_read(&gl->gl_ail_count);
 
-	if (!tr.tr_revokes) {
+	if (!revokes) {
 		bool have_revokes;
 		bool log_in_flight;
 
@@ -122,20 +118,14 @@ static int gfs2_ail_empty_gl(struct gfs2_glock *gl)
 		return 0;
 	}
 
-	/* A shortened, inline version of gfs2_trans_begin()
-         * tr->alloced is not set since the transaction structure is
-         * on the stack */
-	tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes);
-	tr.tr_ip = _RET_IP_;
-	ret = gfs2_log_reserve(sdp, tr.tr_reserved);
-	if (ret < 0)
-		return ret;
-	WARN_ON_ONCE(current->journal_info);
-	current->journal_info = &tr;
-
-	__gfs2_ail_flush(gl, 0, tr.tr_revokes);
-
+	memset(&tr, 0, sizeof(tr));
+	set_bit(TR_ONSTACK, &tr.tr_flags);
+	ret = __gfs2_trans_begin(&tr, sdp, 0, revokes, _RET_IP_);
+	if (ret)
+		goto flush;
+	__gfs2_ail_flush(gl, 0, revokes);
 	gfs2_trans_end(sdp);
+
 flush:
 	gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
 		       GFS2_LFC_AIL_EMPTY_GL);
@@ -146,19 +136,15 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	unsigned int revokes = atomic_read(&gl->gl_ail_count);
-	unsigned int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
 	int ret;
 
 	if (!revokes)
 		return;
 
-	while (revokes > max_revokes)
-		max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64);
-
-	ret = gfs2_trans_begin(sdp, 0, max_revokes);
+	ret = gfs2_trans_begin(sdp, 0, revokes);
 	if (ret)
 		return;
-	__gfs2_ail_flush(gl, fsync, max_revokes);
+	__gfs2_ail_flush(gl, fsync, revokes);
 	gfs2_trans_end(sdp);
 	gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
 		       GFS2_LFC_AIL_FLUSH);
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index ade0b85eac64..0957119f7744 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -20,6 +20,7 @@
 #include <linux/percpu.h>
 #include <linux/lockref.h>
 #include <linux/rhashtable.h>
+#include <linux/mutex.h>
 
 #define DIO_WAIT	0x00000010
 #define DIO_METADATA	0x00000020
@@ -106,7 +107,8 @@ struct gfs2_rgrpd {
 	u32 rd_data;			/* num of data blocks in rgrp */
 	u32 rd_bitbytes;		/* number of bytes in data bitmaps */
 	u32 rd_free;
-	u32 rd_reserved;                /* number of blocks reserved */
+	u32 rd_requested;		/* number of blocks in rd_rstree */
+	u32 rd_reserved;		/* number of reserved blocks */
 	u32 rd_free_clone;
 	u32 rd_dinodes;
 	u64 rd_igeneration;
@@ -122,34 +124,10 @@ struct gfs2_rgrpd {
 #define GFS2_RDF_PREFERRED	0x80000000 /* This rgrp is preferred */
 #define GFS2_RDF_MASK		0xf0000000 /* mask for internal flags */
 	spinlock_t rd_rsspin;           /* protects reservation related vars */
+	struct mutex rd_mutex;
 	struct rb_root rd_rstree;       /* multi-block reservation tree */
 };
 
-struct gfs2_rbm {
-	struct gfs2_rgrpd *rgd;
-	u32 offset;		/* The offset is bitmap relative */
-	int bii;		/* Bitmap index */
-};
-
-static inline struct gfs2_bitmap *rbm_bi(const struct gfs2_rbm *rbm)
-{
-	return rbm->rgd->rd_bits + rbm->bii;
-}
-
-static inline u64 gfs2_rbm_to_block(const struct gfs2_rbm *rbm)
-{
-	BUG_ON(rbm->offset >= rbm->rgd->rd_data);
-	return rbm->rgd->rd_data0 + (rbm_bi(rbm)->bi_start * GFS2_NBBY) +
-		rbm->offset;
-}
-
-static inline bool gfs2_rbm_eq(const struct gfs2_rbm *rbm1,
-			       const struct gfs2_rbm *rbm2)
-{
-	return (rbm1->rgd == rbm2->rgd) && (rbm1->bii == rbm2->bii) &&
-	       (rbm1->offset == rbm2->offset);
-}
-
 enum gfs2_state_bits {
 	BH_Pinned = BH_PrivateStart,
 	BH_Escaped = BH_PrivateStart + 1,
@@ -313,9 +291,11 @@ struct gfs2_qadata { /* quota allocation data */
 */
 
 struct gfs2_blkreserv {
-	struct rb_node rs_node;       /* link to other block reservations */
-	struct gfs2_rbm rs_rbm;       /* Start of reservation */
-	u32 rs_free;                  /* how many blocks are still free */
+	struct rb_node rs_node;       /* node within rd_rstree */
+	struct gfs2_rgrpd *rs_rgd;
+	u64 rs_start;
+	u32 rs_requested;
+	u32 rs_reserved;              /* number of reserved blocks */
 };
 
 /*
@@ -490,7 +470,7 @@ struct gfs2_quota_data {
 enum {
 	TR_TOUCHED = 1,
 	TR_ATTACHED = 2,
-	TR_ALLOCED = 3,
+	TR_ONSTACK = 3,
 };
 
 struct gfs2_trans {
@@ -506,7 +486,6 @@ struct gfs2_trans {
 	unsigned int tr_num_buf_rm;
 	unsigned int tr_num_databuf_rm;
 	unsigned int tr_num_revoke;
-	unsigned int tr_num_revoke_rm;
 
 	struct list_head tr_list;
 	struct list_head tr_databuf;
@@ -823,7 +802,6 @@ struct gfs2_sbd {
 
 	struct gfs2_trans *sd_log_tr;
 	unsigned int sd_log_blks_reserved;
-	int sd_log_committed_revoke;
 
 	atomic_t sd_log_pinned;
 	unsigned int sd_log_num_revoke;
@@ -836,12 +814,11 @@ struct gfs2_sbd {
 	atomic_t sd_log_thresh2;
 	atomic_t sd_log_blks_free;
 	atomic_t sd_log_blks_needed;
+	atomic_t sd_log_revokes_available;
 	wait_queue_head_t sd_log_waitq;
 	wait_queue_head_t sd_logd_waitq;
 
 	u64 sd_log_sequence;
-	unsigned int sd_log_head;
-	unsigned int sd_log_tail;
 	int sd_log_idle;
 
 	struct rw_semaphore sd_log_flush_lock;
@@ -850,9 +827,9 @@ struct gfs2_sbd {
 	int sd_log_error; /* First log error */
 	wait_queue_head_t sd_withdraw_wait;
 
-	atomic_t sd_reserving_log;
-	wait_queue_head_t sd_reserving_log_wait;
-
+	unsigned int sd_log_tail;
+	unsigned int sd_log_flush_tail;
+	unsigned int sd_log_head;
 	unsigned int sd_log_flush_head;
 
 	spinlock_t sd_ail_lock;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index c1b77e8d6b1c..4d3d8624a95b 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1145,7 +1145,7 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 	if (!rgd)
 		goto out_inodes;
 
-	gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
+	gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, LM_FLAG_NODE_SCOPE, ghs + 2);
 
 
 	error = gfs2_glock_nq(ghs); /* parent */
@@ -1450,8 +1450,8 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 			error = -ENOENT;
 			goto out_gunlock;
 		}
-		error = gfs2_glock_nq_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0,
-					   &rd_gh);
+		error = gfs2_glock_nq_init(nrgd->rd_gl, LM_ST_EXCLUSIVE,
+					   LM_FLAG_NODE_SCOPE, &rd_gh);
 		if (error)
 			goto out_gunlock;
 	}
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index d3fa14ec2c44..a6fbde9f609f 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -50,10 +50,12 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct)
 	unsigned int blks;
 	unsigned int first, second;
 
+	/* The initial struct gfs2_log_descriptor block */
 	blks = 1;
 	first = sdp->sd_ldptrs;
 
 	if (nstruct > first) {
+		/* Subsequent struct gfs2_meta_header blocks */
 		second = sdp->sd_inptrs;
 		blks += DIV_ROUND_UP(nstruct - first, second);
 	}
@@ -240,6 +242,45 @@ static void gfs2_ail1_start(struct gfs2_sbd *sdp)
 	return gfs2_ail1_flush(sdp, &wbc);
 }
 
+static void gfs2_log_update_flush_tail(struct gfs2_sbd *sdp)
+{
+	unsigned int new_flush_tail = sdp->sd_log_head;
+	struct gfs2_trans *tr;
+
+	if (!list_empty(&sdp->sd_ail1_list)) {
+		tr = list_last_entry(&sdp->sd_ail1_list,
+				     struct gfs2_trans, tr_list);
+		new_flush_tail = tr->tr_first;
+	}
+	sdp->sd_log_flush_tail = new_flush_tail;
+}
+
+static void gfs2_log_update_head(struct gfs2_sbd *sdp)
+{
+	unsigned int new_head = sdp->sd_log_flush_head;
+
+	if (sdp->sd_log_flush_tail == sdp->sd_log_head)
+		sdp->sd_log_flush_tail = new_head;
+	sdp->sd_log_head = new_head;
+}
+
+/**
+ * gfs2_ail_empty_tr - empty one of the ail lists of a transaction
+ */
+
+static void gfs2_ail_empty_tr(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
+			      struct list_head *head)
+{
+	struct gfs2_bufdata *bd;
+
+	while (!list_empty(head)) {
+		bd = list_first_entry(head, struct gfs2_bufdata,
+				      bd_ail_st_list);
+		gfs2_assert(sdp, bd->bd_tr == tr);
+		gfs2_remove_from_ail(bd);
+	}
+}
+
 /**
  * gfs2_ail1_empty_one - Check whether or not a trans in the AIL has been synced
  * @sdp: the filesystem
@@ -315,6 +356,7 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp, int max_revokes)
 		else
 			oldest_tr = 0;
 	}
+	gfs2_log_update_flush_tail(sdp);
 	ret = list_empty(&sdp->sd_ail1_list);
 	spin_unlock(&sdp->sd_ail_lock);
 
@@ -348,47 +390,69 @@ static void gfs2_ail1_wait(struct gfs2_sbd *sdp)
 	spin_unlock(&sdp->sd_ail_lock);
 }
 
-/**
- * gfs2_ail_empty_tr - empty one of the ail lists for a transaction
- */
-
-static void gfs2_ail_empty_tr(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
-			      struct list_head *head)
+static void __ail2_empty(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
-	struct gfs2_bufdata *bd;
-
-	while (!list_empty(head)) {
-		bd = list_first_entry(head, struct gfs2_bufdata,
-				      bd_ail_st_list);
-		gfs2_assert(sdp, bd->bd_tr == tr);
-		gfs2_remove_from_ail(bd);
-	}
+	gfs2_ail_empty_tr(sdp, tr, &tr->tr_ail2_list);
+	list_del(&tr->tr_list);
+	gfs2_assert_warn(sdp, list_empty(&tr->tr_ail1_list));
+	gfs2_assert_warn(sdp, list_empty(&tr->tr_ail2_list));
+	gfs2_trans_free(sdp, tr);
 }
 
 static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
 {
-	struct gfs2_trans *tr, *safe;
+	struct list_head *ail2_list = &sdp->sd_ail2_list;
 	unsigned int old_tail = sdp->sd_log_tail;
-	int wrap = (new_tail < old_tail);
-	int a, b, rm;
+	struct gfs2_trans *tr, *safe;
 
 	spin_lock(&sdp->sd_ail_lock);
+	if (old_tail <= new_tail) {
+		list_for_each_entry_safe(tr, safe, ail2_list, tr_list) {
+			if (old_tail <= tr->tr_first && tr->tr_first < new_tail)
+				__ail2_empty(sdp, tr);
+		}
+	} else {
+		list_for_each_entry_safe(tr, safe, ail2_list, tr_list) {
+			if (old_tail <= tr->tr_first || tr->tr_first < new_tail)
+				__ail2_empty(sdp, tr);
+		}
+	}
+	spin_unlock(&sdp->sd_ail_lock);
+}
 
-	list_for_each_entry_safe(tr, safe, &sdp->sd_ail2_list, tr_list) {
-		a = (old_tail <= tr->tr_first);
-		b = (tr->tr_first < new_tail);
-		rm = (wrap) ? (a || b) : (a && b);
-		if (!rm)
-			continue;
+/**
+ * gfs2_log_is_empty - Check if the log is empty
+ * @sdp: The GFS2 superblock
+ */
 
-		gfs2_ail_empty_tr(sdp, tr, &tr->tr_ail2_list);
-		list_del(&tr->tr_list);
-		gfs2_assert_warn(sdp, list_empty(&tr->tr_ail1_list));
-		gfs2_assert_warn(sdp, list_empty(&tr->tr_ail2_list));
-		gfs2_trans_free(sdp, tr);
+bool gfs2_log_is_empty(struct gfs2_sbd *sdp) {
+	return atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks;
+}
+
+static bool __gfs2_log_try_reserve_revokes(struct gfs2_sbd *sdp, unsigned int revokes)
+{
+	unsigned int available;
+
+	available = atomic_read(&sdp->sd_log_revokes_available);
+	while (available >= revokes) {
+		if (atomic_try_cmpxchg(&sdp->sd_log_revokes_available,
+				       &available, available - revokes))
+			return true;
 	}
+	return false;
+}
 
-	spin_unlock(&sdp->sd_ail_lock);
+/**
+ * gfs2_log_release_revokes - Release a given number of revokes
+ * @sdp: The GFS2 superblock
+ * @revokes: The number of revokes to release
+ *
+ * sdp->sd_log_flush_lock must be held.
+ */
+void gfs2_log_release_revokes(struct gfs2_sbd *sdp, unsigned int revokes)
+{
+	if (revokes)
+		atomic_add(revokes, &sdp->sd_log_revokes_available);
 }
 
 /**
@@ -400,86 +464,141 @@ static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
 
 void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
 {
-
 	atomic_add(blks, &sdp->sd_log_blks_free);
 	trace_gfs2_log_blocks(sdp, blks);
 	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
 				  sdp->sd_jdesc->jd_blocks);
-	up_read(&sdp->sd_log_flush_lock);
+	if (atomic_read(&sdp->sd_log_blks_needed))
+		wake_up(&sdp->sd_log_waitq);
 }
 
 /**
- * gfs2_log_reserve - Make a log reservation
+ * __gfs2_log_try_reserve - Try to make a log reservation
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks to reserve
+ * @taboo_blks: The number of blocks to leave free
+ *
+ * Try to do the same as __gfs2_log_reserve(), but fail if no more log
+ * space is immediately available.
+ */
+static bool __gfs2_log_try_reserve(struct gfs2_sbd *sdp, unsigned int blks,
+				   unsigned int taboo_blks)
+{
+	unsigned wanted = blks + taboo_blks;
+	unsigned int free_blocks;
+
+	free_blocks = atomic_read(&sdp->sd_log_blks_free);
+	while (free_blocks >= wanted) {
+		if (atomic_try_cmpxchg(&sdp->sd_log_blks_free, &free_blocks,
+				       free_blocks - blks)) {
+			trace_gfs2_log_blocks(sdp, -blks);
+			return true;
+		}
+	}
+	return false;
+}
+
+/**
+ * __gfs2_log_reserve - Make a log reservation
  * @sdp: The GFS2 superblock
  * @blks: The number of blocks to reserve
+ * @taboo_blks: The number of blocks to leave free
  *
- * Note that we never give out the last few blocks of the journal. Thats
- * due to the fact that there is a small number of header blocks
- * associated with each log flush. The exact number can't be known until
- * flush time, so we ensure that we have just enough free blocks at all
- * times to avoid running out during a log flush.
+ * @taboo_blks is set to 0 for logd, and to GFS2_LOG_FLUSH_MIN_BLOCKS
+ * for all other processes.  This ensures that when the log is almost full,
+ * logd will still be able to call gfs2_log_flush one more time  without
+ * blocking, which will advance the tail and make some more log space
+ * available.
  *
  * We no longer flush the log here, instead we wake up logd to do that
  * for us. To avoid the thundering herd and to ensure that we deal fairly
  * with queued waiters, we use an exclusive wait. This means that when we
  * get woken with enough journal space to get our reservation, we need to
  * wake the next waiter on the list.
- *
- * Returns: errno
  */
 
-int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
+static void __gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks,
+			       unsigned int taboo_blks)
 {
-	int ret = 0;
-	unsigned reserved_blks = 7 * (4096 / sdp->sd_vfs->s_blocksize);
-	unsigned wanted = blks + reserved_blks;
-	DEFINE_WAIT(wait);
-	int did_wait = 0;
+	unsigned wanted = blks + taboo_blks;
 	unsigned int free_blocks;
 
-	if (gfs2_assert_warn(sdp, blks) ||
-	    gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
-		return -EINVAL;
 	atomic_add(blks, &sdp->sd_log_blks_needed);
-retry:
-	free_blocks = atomic_read(&sdp->sd_log_blks_free);
-	if (unlikely(free_blocks <= wanted)) {
-		do {
-			prepare_to_wait_exclusive(&sdp->sd_log_waitq, &wait,
-					TASK_UNINTERRUPTIBLE);
+	for (;;) {
+		if (current != sdp->sd_logd_process)
 			wake_up(&sdp->sd_logd_waitq);
-			did_wait = 1;
-			if (atomic_read(&sdp->sd_log_blks_free) <= wanted)
-				io_schedule();
-			free_blocks = atomic_read(&sdp->sd_log_blks_free);
-		} while(free_blocks <= wanted);
-		finish_wait(&sdp->sd_log_waitq, &wait);
-	}
-	atomic_inc(&sdp->sd_reserving_log);
-	if (atomic_cmpxchg(&sdp->sd_log_blks_free, free_blocks,
-				free_blocks - blks) != free_blocks) {
-		if (atomic_dec_and_test(&sdp->sd_reserving_log))
-			wake_up(&sdp->sd_reserving_log_wait);
-		goto retry;
+		io_wait_event(sdp->sd_log_waitq,
+			(free_blocks = atomic_read(&sdp->sd_log_blks_free),
+			 free_blocks >= wanted));
+		do {
+			if (atomic_try_cmpxchg(&sdp->sd_log_blks_free,
+					       &free_blocks,
+					       free_blocks - blks))
+				goto reserved;
+		} while (free_blocks >= wanted);
 	}
-	atomic_sub(blks, &sdp->sd_log_blks_needed);
-	trace_gfs2_log_blocks(sdp, -blks);
 
-	/*
-	 * If we waited, then so might others, wake them up _after_ we get
-	 * our share of the log.
-	 */
-	if (unlikely(did_wait))
+reserved:
+	trace_gfs2_log_blocks(sdp, -blks);
+	if (atomic_sub_return(blks, &sdp->sd_log_blks_needed))
 		wake_up(&sdp->sd_log_waitq);
+}
+
+/**
+ * gfs2_log_try_reserve - Try to make a log reservation
+ * @sdp: The GFS2 superblock
+ * @tr: The transaction
+ * @extra_revokes: The number of additional revokes reserved (output)
+ *
+ * This is similar to gfs2_log_reserve, but sdp->sd_log_flush_lock must be
+ * held for correct revoke accounting.
+ */
 
-	down_read(&sdp->sd_log_flush_lock);
-	if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) {
-		gfs2_log_release(sdp, blks);
-		ret = -EROFS;
+bool gfs2_log_try_reserve(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
+			  unsigned int *extra_revokes)
+{
+	unsigned int blks = tr->tr_reserved;
+	unsigned int revokes = tr->tr_revokes;
+	unsigned int revoke_blks = 0;
+
+	*extra_revokes = 0;
+	if (revokes && !__gfs2_log_try_reserve_revokes(sdp, revokes)) {
+		revoke_blks = DIV_ROUND_UP(revokes, sdp->sd_inptrs);
+		*extra_revokes = revoke_blks * sdp->sd_inptrs - revokes;
+		blks += revoke_blks;
 	}
-	if (atomic_dec_and_test(&sdp->sd_reserving_log))
-		wake_up(&sdp->sd_reserving_log_wait);
-	return ret;
+	if (!blks)
+		return true;
+	if (__gfs2_log_try_reserve(sdp, blks, GFS2_LOG_FLUSH_MIN_BLOCKS))
+		return true;
+	if (!revoke_blks)
+		gfs2_log_release_revokes(sdp, revokes);
+	return false;
+}
+
+/**
+ * gfs2_log_reserve - Make a log reservation
+ * @sdp: The GFS2 superblock
+ * @tr: The transaction
+ * @extra_revokes: The number of additional revokes reserved (output)
+ *
+ * sdp->sd_log_flush_lock must not be held.
+ */
+
+void gfs2_log_reserve(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
+		      unsigned int *extra_revokes)
+{
+	unsigned int blks = tr->tr_reserved;
+	unsigned int revokes = tr->tr_revokes;
+	unsigned int revoke_blks = 0;
+
+	*extra_revokes = 0;
+	if (revokes) {
+		revoke_blks = DIV_ROUND_UP(revokes, sdp->sd_inptrs);
+		*extra_revokes = revoke_blks * sdp->sd_inptrs - revokes;
+		blks += revoke_blks;
+	}
+	__gfs2_log_reserve(sdp, blks, GFS2_LOG_FLUSH_MIN_BLOCKS);
 }
 
 /**
@@ -507,24 +626,20 @@ static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer
 }
 
 /**
- * calc_reserved - Calculate the number of blocks to reserve when
- *                 refunding a transaction's unused buffers.
+ * calc_reserved - Calculate the number of blocks to keep reserved
  * @sdp: The GFS2 superblock
  *
  * This is complex.  We need to reserve room for all our currently used
- * metadata buffers (e.g. normal file I/O rewriting file time stamps) and 
- * all our journaled data buffers for journaled files (e.g. files in the 
+ * metadata blocks (e.g. normal file I/O rewriting file time stamps) and
+ * all our journaled data blocks for journaled files (e.g. files in the
  * meta_fs like rindex, or files for which chattr +j was done.)
- * If we don't reserve enough space, gfs2_log_refund and gfs2_log_flush
- * will count it as free space (sd_log_blks_free) and corruption will follow.
+ * If we don't reserve enough space, corruption will follow.
  *
- * We can have metadata bufs and jdata bufs in the same journal.  So each
- * type gets its own log header, for which we need to reserve a block.
- * In fact, each type has the potential for needing more than one header 
- * in cases where we have more buffers than will fit on a journal page.
+ * We can have metadata blocks and jdata blocks in the same journal.  Each
+ * type gets its own log descriptor, for which we need to reserve a block.
+ * In fact, each type has the potential for needing more than one log descriptor
+ * in cases where we have more blocks than will fit in a log descriptor.
  * Metadata journal entries take up half the space of journaled buffer entries.
- * Thus, metadata entries have buf_limit (502) and journaled buffers have
- * databuf_limit (251) before they cause a wrap around.
  *
  * Also, we need to reserve blocks for revoke journal entries and one for an
  * overall header for the lot.
@@ -533,59 +648,29 @@ static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer
  */
 static unsigned int calc_reserved(struct gfs2_sbd *sdp)
 {
-	unsigned int reserved = 0;
-	unsigned int mbuf;
-	unsigned int dbuf;
+	unsigned int reserved = GFS2_LOG_FLUSH_MIN_BLOCKS;
+	unsigned int blocks;
 	struct gfs2_trans *tr = sdp->sd_log_tr;
 
 	if (tr) {
-		mbuf = tr->tr_num_buf_new - tr->tr_num_buf_rm;
-		dbuf = tr->tr_num_databuf_new - tr->tr_num_databuf_rm;
-		reserved = mbuf + dbuf;
-		/* Account for header blocks */
-		reserved += DIV_ROUND_UP(mbuf, buf_limit(sdp));
-		reserved += DIV_ROUND_UP(dbuf, databuf_limit(sdp));
+		blocks = tr->tr_num_buf_new - tr->tr_num_buf_rm;
+		reserved += blocks + DIV_ROUND_UP(blocks, buf_limit(sdp));
+		blocks = tr->tr_num_databuf_new - tr->tr_num_databuf_rm;
+		reserved += blocks + DIV_ROUND_UP(blocks, databuf_limit(sdp));
 	}
-
-	if (sdp->sd_log_committed_revoke > 0)
-		reserved += gfs2_struct2blk(sdp, sdp->sd_log_committed_revoke);
-	/* One for the overall header */
-	if (reserved)
-		reserved++;
 	return reserved;
 }
 
-static unsigned int current_tail(struct gfs2_sbd *sdp)
+static void log_pull_tail(struct gfs2_sbd *sdp)
 {
-	struct gfs2_trans *tr;
-	unsigned int tail;
-
-	spin_lock(&sdp->sd_ail_lock);
-
-	if (list_empty(&sdp->sd_ail1_list)) {
-		tail = sdp->sd_log_head;
-	} else {
-		tr = list_last_entry(&sdp->sd_ail1_list, struct gfs2_trans,
-				tr_list);
-		tail = tr->tr_first;
-	}
-
-	spin_unlock(&sdp->sd_ail_lock);
-
-	return tail;
-}
-
-static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
-{
-	unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
+	unsigned int new_tail = sdp->sd_log_flush_tail;
+	unsigned int dist;
 
+	if (new_tail == sdp->sd_log_tail)
+		return;
+	dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
 	ail2_empty(sdp, new_tail);
-
-	atomic_add(dist, &sdp->sd_log_blks_free);
-	trace_gfs2_log_blocks(sdp, dist);
-	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
-			     sdp->sd_jdesc->jd_blocks);
-
+	gfs2_log_release(sdp, dist);
 	sdp->sd_log_tail = new_tail;
 }
 
@@ -698,7 +783,7 @@ void gfs2_glock_remove_revoke(struct gfs2_glock *gl)
 }
 
 /**
- * gfs2_write_revokes - Add as many revokes to the system transaction as we can
+ * gfs2_flush_revokes - Add as many revokes to the system transaction as we can
  * @sdp: The GFS2 superblock
  *
  * Our usual strategy is to defer writing revokes as much as we can in the hope
@@ -709,38 +794,14 @@ void gfs2_glock_remove_revoke(struct gfs2_glock *gl)
  * been written back.  This will basically come at no cost now, and will save
  * us from having to keep track of those blocks on the AIL2 list later.
  */
-void gfs2_write_revokes(struct gfs2_sbd *sdp)
+void gfs2_flush_revokes(struct gfs2_sbd *sdp)
 {
 	/* number of revokes we still have room for */
-	int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
+	unsigned int max_revokes = atomic_read(&sdp->sd_log_revokes_available);
 
 	gfs2_log_lock(sdp);
-	while (sdp->sd_log_num_revoke > max_revokes)
-		max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64);
-	max_revokes -= sdp->sd_log_num_revoke;
-	if (!sdp->sd_log_num_revoke) {
-		atomic_dec(&sdp->sd_log_blks_free);
-		/* If no blocks have been reserved, we need to also
-		 * reserve a block for the header */
-		if (!sdp->sd_log_blks_reserved) {
-			atomic_dec(&sdp->sd_log_blks_free);
-			trace_gfs2_log_blocks(sdp, -2);
-		} else {
-			trace_gfs2_log_blocks(sdp, -1);
-		}
-	}
 	gfs2_ail1_empty(sdp, max_revokes);
 	gfs2_log_unlock(sdp);
-
-	if (!sdp->sd_log_num_revoke) {
-		atomic_inc(&sdp->sd_log_blks_free);
-		if (!sdp->sd_log_blks_reserved) {
-			atomic_inc(&sdp->sd_log_blks_free);
-			trace_gfs2_log_blocks(sdp, 2);
-		} else {
-			trace_gfs2_log_blocks(sdp, 1);
-		}
-	}
 }
 
 /**
@@ -769,7 +830,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 	u64 dblock;
 
 	if (gfs2_withdrawn(sdp))
-		goto out;
+		return;
 
 	page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
 	lh = page_address(page);
@@ -824,8 +885,6 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 
 	gfs2_log_write(sdp, jd, page, sb->s_blocksize, 0, dblock);
 	gfs2_log_submit_bio(&jd->jd_log_bio, REQ_OP_WRITE | op_flags);
-out:
-	log_flush_wait(sdp);
 }
 
 /**
@@ -838,25 +897,24 @@ out:
 
 static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
 {
-	unsigned int tail;
 	int op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC;
 	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
 
 	gfs2_assert_withdraw(sdp, (state != SFS_FROZEN));
-	tail = current_tail(sdp);
 
 	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) {
 		gfs2_ordered_wait(sdp);
 		log_flush_wait(sdp);
 		op_flags = REQ_SYNC | REQ_META | REQ_PRIO;
 	}
-	sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
-	gfs2_write_log_header(sdp, sdp->sd_jdesc, sdp->sd_log_sequence++, tail,
-			      sdp->sd_log_flush_head, flags, op_flags);
+	sdp->sd_log_idle = (sdp->sd_log_flush_tail == sdp->sd_log_flush_head);
+	gfs2_write_log_header(sdp, sdp->sd_jdesc, sdp->sd_log_sequence++,
+			      sdp->sd_log_flush_tail, sdp->sd_log_flush_head,
+			      flags, op_flags);
 	gfs2_log_incr_head(sdp);
-
-	if (sdp->sd_log_tail != tail)
-		log_pull_tail(sdp, tail);
+	log_flush_wait(sdp);
+	log_pull_tail(sdp);
+	gfs2_log_update_head(sdp);
 }
 
 /**
@@ -956,10 +1014,15 @@ static void trans_drain(struct gfs2_trans *tr)
 void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 {
 	struct gfs2_trans *tr = NULL;
+	unsigned int reserved_blocks = 0, used_blocks = 0;
 	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
+	unsigned int first_log_head;
+	unsigned int reserved_revokes = 0;
 
 	down_write(&sdp->sd_log_flush_lock);
+	trace_gfs2_log_flush(sdp, 1, flags);
 
+repeat:
 	/*
 	 * Do this check while holding the log_flush_lock to prevent new
 	 * buffers from being added to the ail via gfs2_pin()
@@ -970,28 +1033,47 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 	/* Log might have been flushed while we waited for the flush lock */
 	if (gl && !test_bit(GLF_LFLUSH, &gl->gl_flags))
 		goto out;
-	trace_gfs2_log_flush(sdp, 1, flags);
 
-	if (flags & GFS2_LOG_HEAD_FLUSH_SHUTDOWN)
-		clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+	first_log_head = sdp->sd_log_head;
+	sdp->sd_log_flush_head = first_log_head;
 
-	sdp->sd_log_flush_head = sdp->sd_log_head;
 	tr = sdp->sd_log_tr;
-	if (tr) {
-		sdp->sd_log_tr = NULL;
-		tr->tr_first = sdp->sd_log_flush_head;
-		if (unlikely (state == SFS_FROZEN))
-			if (gfs2_assert_withdraw_delayed(sdp,
-			       !tr->tr_num_buf_new && !tr->tr_num_databuf_new))
-				goto out_withdraw;
+	if (tr || sdp->sd_log_num_revoke) {
+		if (reserved_blocks)
+			gfs2_log_release(sdp, reserved_blocks);
+		reserved_blocks = sdp->sd_log_blks_reserved;
+		reserved_revokes = sdp->sd_log_num_revoke;
+		if (tr) {
+			sdp->sd_log_tr = NULL;
+			tr->tr_first = first_log_head;
+			if (unlikely (state == SFS_FROZEN)) {
+				if (gfs2_assert_withdraw_delayed(sdp,
+				       !tr->tr_num_buf_new && !tr->tr_num_databuf_new))
+					goto out_withdraw;
+			}
+		}
+	} else if (!reserved_blocks) {
+		unsigned int taboo_blocks = GFS2_LOG_FLUSH_MIN_BLOCKS;
+
+		reserved_blocks = GFS2_LOG_FLUSH_MIN_BLOCKS;
+		if (current == sdp->sd_logd_process)
+			taboo_blocks = 0;
+
+		if (!__gfs2_log_try_reserve(sdp, reserved_blocks, taboo_blocks)) {
+			up_write(&sdp->sd_log_flush_lock);
+			__gfs2_log_reserve(sdp, reserved_blocks, taboo_blocks);
+			down_write(&sdp->sd_log_flush_lock);
+			goto repeat;
+		}
+		BUG_ON(sdp->sd_log_num_revoke);
 	}
 
+	if (flags & GFS2_LOG_HEAD_FLUSH_SHUTDOWN)
+		clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
 	if (unlikely(state == SFS_FROZEN))
-		if (gfs2_assert_withdraw_delayed(sdp, !sdp->sd_log_num_revoke))
+		if (gfs2_assert_withdraw_delayed(sdp, !reserved_revokes))
 			goto out_withdraw;
-	if (gfs2_assert_withdraw_delayed(sdp,
-			sdp->sd_log_num_revoke == sdp->sd_log_committed_revoke))
-		goto out_withdraw;
 
 	gfs2_ordered_write(sdp);
 	if (gfs2_withdrawn(sdp))
@@ -1005,9 +1087,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 
 	if (sdp->sd_log_head != sdp->sd_log_flush_head) {
 		log_write_header(sdp, flags);
-	} else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
-		atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
-		trace_gfs2_log_blocks(sdp, -1);
+	} else if (sdp->sd_log_tail != sdp->sd_log_flush_tail && !sdp->sd_log_idle) {
 		log_write_header(sdp, flags);
 	}
 	if (gfs2_withdrawn(sdp))
@@ -1015,9 +1095,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 	lops_after_commit(sdp, tr);
 
 	gfs2_log_lock(sdp);
-	sdp->sd_log_head = sdp->sd_log_flush_head;
 	sdp->sd_log_blks_reserved = 0;
-	sdp->sd_log_committed_revoke = 0;
 
 	spin_lock(&sdp->sd_ail_lock);
 	if (tr && !list_empty(&tr->tr_ail1_list)) {
@@ -1032,10 +1110,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 			empty_ail1_list(sdp);
 			if (gfs2_withdrawn(sdp))
 				goto out_withdraw;
-			atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
-			trace_gfs2_log_blocks(sdp, -1);
 			log_write_header(sdp, flags);
-			sdp->sd_log_head = sdp->sd_log_flush_head;
 		}
 		if (flags & (GFS2_LOG_HEAD_FLUSH_SHUTDOWN |
 			     GFS2_LOG_HEAD_FLUSH_FREEZE))
@@ -1045,12 +1120,22 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 	}
 
 out_end:
-	trace_gfs2_log_flush(sdp, 0, flags);
+	used_blocks = log_distance(sdp, sdp->sd_log_flush_head, first_log_head);
+	reserved_revokes += atomic_read(&sdp->sd_log_revokes_available);
+	atomic_set(&sdp->sd_log_revokes_available, sdp->sd_ldptrs);
+	gfs2_assert_withdraw(sdp, reserved_revokes % sdp->sd_inptrs == sdp->sd_ldptrs);
+	if (reserved_revokes > sdp->sd_ldptrs)
+		reserved_blocks += (reserved_revokes - sdp->sd_ldptrs) / sdp->sd_inptrs;
 out:
+	if (used_blocks != reserved_blocks) {
+		gfs2_assert_withdraw_delayed(sdp, used_blocks < reserved_blocks);
+		gfs2_log_release(sdp, reserved_blocks - used_blocks);
+	}
 	up_write(&sdp->sd_log_flush_lock);
 	gfs2_trans_free(sdp, tr);
 	if (gfs2_withdrawing(sdp))
 		gfs2_withdraw(sdp);
+	trace_gfs2_log_flush(sdp, 0, flags);
 	return;
 
 out_withdraw:
@@ -1086,8 +1171,8 @@ static void gfs2_merge_trans(struct gfs2_sbd *sdp, struct gfs2_trans *new)
 	old->tr_num_databuf_new	+= new->tr_num_databuf_new;
 	old->tr_num_buf_rm	+= new->tr_num_buf_rm;
 	old->tr_num_databuf_rm	+= new->tr_num_databuf_rm;
+	old->tr_revokes		+= new->tr_revokes;
 	old->tr_num_revoke	+= new->tr_num_revoke;
-	old->tr_num_revoke_rm	+= new->tr_num_revoke_rm;
 
 	list_splice_tail_init(&new->tr_databuf, &old->tr_databuf);
 	list_splice_tail_init(&new->tr_buf, &old->tr_buf);
@@ -1109,20 +1194,17 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	if (sdp->sd_log_tr) {
 		gfs2_merge_trans(sdp, tr);
 	} else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
-		gfs2_assert_withdraw(sdp, test_bit(TR_ALLOCED, &tr->tr_flags));
+		gfs2_assert_withdraw(sdp, !test_bit(TR_ONSTACK, &tr->tr_flags));
 		sdp->sd_log_tr = tr;
 		set_bit(TR_ATTACHED, &tr->tr_flags);
 	}
 
-	sdp->sd_log_committed_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
 	reserved = calc_reserved(sdp);
 	maxres = sdp->sd_log_blks_reserved + tr->tr_reserved;
 	gfs2_assert_withdraw(sdp, maxres >= reserved);
 	unused = maxres - reserved;
-	atomic_add(unused, &sdp->sd_log_blks_free);
-	trace_gfs2_log_blocks(sdp, unused);
-	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
-			     sdp->sd_jdesc->jd_blocks);
+	if (unused)
+		gfs2_log_release(sdp, unused);
 	sdp->sd_log_blks_reserved = reserved;
 
 	gfs2_log_unlock(sdp);
@@ -1165,15 +1247,11 @@ static void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
 	gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
 
-	sdp->sd_log_flush_head = sdp->sd_log_head;
-
 	log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT | GFS2_LFC_SHUTDOWN);
+	log_pull_tail(sdp);
 
 	gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
 	gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
-
-	sdp->sd_log_head = sdp->sd_log_flush_head;
-	sdp->sd_log_tail = sdp->sd_log_head;
 }
 
 static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
@@ -1207,7 +1285,6 @@ int gfs2_logd(void *data)
 	struct gfs2_sbd *sdp = data;
 	unsigned long t = 1;
 	DEFINE_WAIT(wait);
-	bool did_flush;
 
 	while (!kthread_should_stop()) {
 
@@ -1226,12 +1303,10 @@ int gfs2_logd(void *data)
 			continue;
 		}
 
-		did_flush = false;
 		if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
 			gfs2_ail1_empty(sdp, 0);
 			gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
-				       GFS2_LFC_LOGD_JFLUSH_REQD);
-			did_flush = true;
+						  GFS2_LFC_LOGD_JFLUSH_REQD);
 		}
 
 		if (gfs2_ail_flush_reqd(sdp)) {
@@ -1239,13 +1314,9 @@ int gfs2_logd(void *data)
 			gfs2_ail1_wait(sdp);
 			gfs2_ail1_empty(sdp, 0);
 			gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
-				       GFS2_LFC_LOGD_AIL_FLUSH_REQD);
-			did_flush = true;
+						  GFS2_LFC_LOGD_AIL_FLUSH_REQD);
 		}
 
-		if (!gfs2_ail_flush_reqd(sdp) || did_flush)
-			wake_up(&sdp->sd_log_waitq);
-
 		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
 
 		try_to_freeze();
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 79f97290146e..eea58015710e 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -13,6 +13,13 @@
 #include "incore.h"
 #include "inode.h"
 
+/*
+ * The minimum amount of log space required for a log flush is one block for
+ * revokes and one block for the log header.  Log flushes other than
+ * GFS2_LOG_HEAD_FLUSH_NORMAL may write one or two more log headers.
+ */
+#define GFS2_LOG_FLUSH_MIN_BLOCKS 4
+
 /**
  * gfs2_log_lock - acquire the right to mess with the log manager
  * @sdp: the filesystem
@@ -43,7 +50,9 @@ static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp,
 	if (++value == sdp->sd_jdesc->jd_blocks) {
 		value = 0;
 	}
-	sdp->sd_log_head = sdp->sd_log_tail = value;
+	sdp->sd_log_tail = value;
+	sdp->sd_log_flush_tail = value;
+	sdp->sd_log_head = value;
 }
 
 static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
@@ -64,8 +73,13 @@ static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
 extern void gfs2_ordered_del_inode(struct gfs2_inode *ip);
 extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct);
 extern void gfs2_remove_from_ail(struct gfs2_bufdata *bd);
+extern bool gfs2_log_is_empty(struct gfs2_sbd *sdp);
+extern void gfs2_log_release_revokes(struct gfs2_sbd *sdp, unsigned int revokes);
 extern void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
-extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
+extern bool gfs2_log_try_reserve(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
+				 unsigned int *extra_revokes);
+extern void gfs2_log_reserve(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
+			     unsigned int *extra_revokes);
 extern void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 				  u64 seq, u32 tail, u32 lblock, u32 flags,
 				  int op_flags);
@@ -78,6 +92,6 @@ extern void log_flush_wait(struct gfs2_sbd *sdp);
 extern int gfs2_logd(void *data);
 extern void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
 extern void gfs2_glock_remove_revoke(struct gfs2_glock *gl);
-extern void gfs2_write_revokes(struct gfs2_sbd *sdp);
+extern void gfs2_flush_revokes(struct gfs2_sbd *sdp);
 
 #endif /* __LOG_DOT_H__ */
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 921e156d3181..dc1b93a877c6 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -76,15 +76,20 @@ static void maybe_release_space(struct gfs2_bufdata *bd)
 	unsigned int index = bd->bd_bh->b_blocknr - gl->gl_name.ln_number;
 	struct gfs2_bitmap *bi = rgd->rd_bits + index;
 
+	rgrp_lock_local(rgd);
 	if (bi->bi_clone == NULL)
-		return;
+		goto out;
 	if (sdp->sd_args.ar_discard)
 		gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bd->bd_bh, bi, 1, NULL);
 	memcpy(bi->bi_clone + bi->bi_offset,
 	       bd->bd_bh->b_data + bi->bi_offset, bi->bi_bytes);
 	clear_bit(GBF_FULL, &bi->bi_flags);
 	rgd->rd_free_clone = rgd->rd_free;
+	BUG_ON(rgd->rd_free_clone < rgd->rd_reserved);
 	rgd->rd_extfail_pt = rgd->rd_free;
+
+out:
+	rgrp_unlock_local(rgd);
 }
 
 /**
@@ -847,7 +852,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	struct page *page;
 	unsigned int length;
 
-	gfs2_write_revokes(sdp);
+	gfs2_flush_revokes(sdp);
 	if (!sdp->sd_log_num_revoke)
 		return;
 
@@ -859,7 +864,6 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 		sdp->sd_log_num_revoke--;
 
 		if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
-
 			gfs2_log_write_page(sdp, page);
 			page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
 			mh = page_address(page);
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index 9a85b9d7ad60..31b6dd0d2e5d 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -10,13 +10,6 @@
 #include <linux/list.h>
 #include "incore.h"
 
-#define BUF_OFFSET \
-	((sizeof(struct gfs2_log_descriptor) + sizeof(__be64) - 1) & \
-	 ~(sizeof(__be64) - 1))
-#define DATABUF_OFFSET \
-	((sizeof(struct gfs2_log_descriptor) + (2 * sizeof(__be64) - 1)) & \
-	 ~(2 * sizeof(__be64) - 1))
-
 extern const struct gfs2_log_operations *gfs2_log_ops[];
 extern void gfs2_log_incr_head(struct gfs2_sbd *sdp);
 extern u64 gfs2_log_bmap(struct gfs2_jdesc *jd, unsigned int lbn);
@@ -29,18 +22,12 @@ extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
 			   struct gfs2_log_header_host *head, bool keep_cache);
 static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
 {
-	unsigned int limit;
-
-	limit = (sdp->sd_sb.sb_bsize - BUF_OFFSET) / sizeof(__be64);
-	return limit;
+	return sdp->sd_ldptrs;
 }
 
 static inline unsigned int databuf_limit(struct gfs2_sbd *sdp)
 {
-	unsigned int limit;
-
-	limit = (sdp->sd_sb.sb_bsize - DATABUF_OFFSET) / (2 * sizeof(__be64));
-	return limit;
+	return sdp->sd_ldptrs / 2;
 }
 
 static inline void lops_before_commit(struct gfs2_sbd *sdp,
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index d89764856f21..74c7d01723b9 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -136,8 +136,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 
 	init_rwsem(&sdp->sd_log_flush_lock);
 	atomic_set(&sdp->sd_log_in_flight, 0);
-	atomic_set(&sdp->sd_reserving_log, 0);
-	init_waitqueue_head(&sdp->sd_reserving_log_wait);
 	init_waitqueue_head(&sdp->sd_log_flush_wait);
 	atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN);
 	mutex_init(&sdp->sd_freeze_mutex);
@@ -318,6 +316,13 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
 				     sizeof(struct gfs2_meta_header))
 		* GFS2_NBBY; /* not the rgrp bitmap, subsequent bitmaps only */
 
+	/*
+	 * We always keep at least one block reserved for revokes in
+	 * transactions.  This greatly simplifies allocating additional
+	 * revoke blocks.
+	 */
+	atomic_set(&sdp->sd_log_revokes_available, sdp->sd_ldptrs);
+
 	/* Compute maximum reservation required to add a entry to a directory */
 
 	hash_blocks = DIV_ROUND_UP(sizeof(u64) * BIT(GFS2_DIR_MAX_DEPTH),
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 5e8eef9990e3..89c37a845e64 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -36,6 +36,24 @@
 #define BFITNOENT ((u32)~0)
 #define NO_BLOCK ((u64)~0)
 
+struct gfs2_rbm {
+	struct gfs2_rgrpd *rgd;
+	u32 offset;		/* The offset is bitmap relative */
+	int bii;		/* Bitmap index */
+};
+
+static inline struct gfs2_bitmap *rbm_bi(const struct gfs2_rbm *rbm)
+{
+	return rbm->rgd->rd_bits + rbm->bii;
+}
+
+static inline u64 gfs2_rbm_to_block(const struct gfs2_rbm *rbm)
+{
+	BUG_ON(rbm->offset >= rbm->rgd->rd_data);
+	return rbm->rgd->rd_data0 + (rbm_bi(rbm)->bi_start * GFS2_NBBY) +
+		rbm->offset;
+}
+
 /*
  * These routines are used by the resource group routines (rgrp.c)
  * to keep track of block allocation.  Each block is represented by two
@@ -61,7 +79,7 @@ static const char valid_change[16] = {
 };
 
 static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
-			 const struct gfs2_inode *ip, bool nowrap);
+			 struct gfs2_blkreserv *rs, bool nowrap);
 
 
 /**
@@ -175,7 +193,7 @@ static inline u64 gfs2_bit_search(const __le64 *ptr, u64 mask, u8 state)
 
 /**
  * rs_cmp - multi-block reservation range compare
- * @blk: absolute file system block number of the new reservation
+ * @start: start of the new reservation
  * @len: number of blocks in the new reservation
  * @rs: existing reservation to compare against
  *
@@ -183,13 +201,11 @@ static inline u64 gfs2_bit_search(const __le64 *ptr, u64 mask, u8 state)
  *         -1 if the block range is before the start of the reservation
  *          0 if the block range overlaps with the reservation
  */
-static inline int rs_cmp(u64 blk, u32 len, struct gfs2_blkreserv *rs)
+static inline int rs_cmp(u64 start, u32 len, struct gfs2_blkreserv *rs)
 {
-	u64 startblk = gfs2_rbm_to_block(&rs->rs_rbm);
-
-	if (blk >= startblk + rs->rs_free)
+	if (start >= rs->rs_start + rs->rs_requested)
 		return 1;
-	if (blk + len - 1 < startblk)
+	if (rs->rs_start >= start + len)
 		return -1;
 	return 0;
 }
@@ -277,29 +293,38 @@ static int gfs2_rbm_from_block(struct gfs2_rbm *rbm, u64 block)
 }
 
 /**
- * gfs2_rbm_incr - increment an rbm structure
+ * gfs2_rbm_add - add a number of blocks to an rbm
  * @rbm: The rbm with rgd already set correctly
+ * @blocks: The number of blocks to add to rpm
  *
- * This function takes an existing rbm structure and increments it to the next
- * viable block offset.
- *
- * Returns: If incrementing the offset would cause the rbm to go past the
- *          end of the rgrp, true is returned, otherwise false.
+ * This function takes an existing rbm structure and adds a number of blocks to
+ * it.
  *
+ * Returns: True if the new rbm would point past the end of the rgrp.
  */
 
-static bool gfs2_rbm_incr(struct gfs2_rbm *rbm)
+static bool gfs2_rbm_add(struct gfs2_rbm *rbm, u32 blocks)
 {
-	if (rbm->offset + 1 < rbm_bi(rbm)->bi_blocks) { /* in the same bitmap */
-		rbm->offset++;
+	struct gfs2_rgrpd *rgd = rbm->rgd;
+	struct gfs2_bitmap *bi = rgd->rd_bits + rbm->bii;
+
+	if (rbm->offset + blocks < bi->bi_blocks) {
+		rbm->offset += blocks;
 		return false;
 	}
-	if (rbm->bii == rbm->rgd->rd_length - 1) /* at the last bitmap */
-		return true;
+	blocks -= bi->bi_blocks - rbm->offset;
 
-	rbm->offset = 0;
-	rbm->bii++;
-	return false;
+	for(;;) {
+		bi++;
+		if (bi == rgd->rd_bits + rgd->rd_length)
+			return true;
+		if (blocks < bi->bi_blocks) {
+			rbm->offset = blocks;
+			rbm->bii = bi - rgd->rd_bits;
+			return false;
+		}
+		blocks -= bi->bi_blocks;
+	}
 }
 
 /**
@@ -308,7 +333,8 @@ static bool gfs2_rbm_incr(struct gfs2_rbm *rbm)
  * @n_unaligned: Number of unaligned blocks to check
  * @len: Decremented for each block found (terminate on zero)
  *
- * Returns: true if a non-free block is encountered
+ * Returns: true if a non-free block is encountered or the end of the resource
+ *	    group is reached.
  */
 
 static bool gfs2_unaligned_extlen(struct gfs2_rbm *rbm, u32 n_unaligned, u32 *len)
@@ -323,7 +349,7 @@ static bool gfs2_unaligned_extlen(struct gfs2_rbm *rbm, u32 n_unaligned, u32 *le
 		(*len)--;
 		if (*len == 0)
 			return true;
-		if (gfs2_rbm_incr(rbm))
+		if (gfs2_rbm_add(rbm, 1))
 			return true;
 	}
 
@@ -595,10 +621,11 @@ static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs,
 {
 	struct gfs2_inode *ip = container_of(rs, struct gfs2_inode, i_res);
 
-	gfs2_print_dbg(seq, "%s  B: n:%llu s:%llu b:%u f:%u\n", fs_id_buf,
+	gfs2_print_dbg(seq, "%s  B: n:%llu s:%llu f:%u\n",
+		       fs_id_buf,
 		       (unsigned long long)ip->i_no_addr,
-		       (unsigned long long)gfs2_rbm_to_block(&rs->rs_rbm),
-		       rs->rs_rbm.offset, rs->rs_free);
+		       (unsigned long long)rs->rs_start,
+		       rs->rs_requested);
 }
 
 /**
@@ -613,33 +640,22 @@ static void __rs_deltree(struct gfs2_blkreserv *rs)
 	if (!gfs2_rs_active(rs))
 		return;
 
-	rgd = rs->rs_rbm.rgd;
+	rgd = rs->rs_rgd;
 	trace_gfs2_rs(rs, TRACE_RS_TREEDEL);
 	rb_erase(&rs->rs_node, &rgd->rd_rstree);
 	RB_CLEAR_NODE(&rs->rs_node);
 
-	if (rs->rs_free) {
-		u64 last_block = gfs2_rbm_to_block(&rs->rs_rbm) +
-				 rs->rs_free - 1;
-		struct gfs2_rbm last_rbm = { .rgd = rs->rs_rbm.rgd, };
-		struct gfs2_bitmap *start, *last;
+	if (rs->rs_requested) {
+		/* return requested blocks to the rgrp */
+		BUG_ON(rs->rs_rgd->rd_requested < rs->rs_requested);
+		rs->rs_rgd->rd_requested -= rs->rs_requested;
 
-		/* return reserved blocks to the rgrp */
-		BUG_ON(rs->rs_rbm.rgd->rd_reserved < rs->rs_free);
-		rs->rs_rbm.rgd->rd_reserved -= rs->rs_free;
 		/* The rgrp extent failure point is likely not to increase;
 		   it will only do so if the freed blocks are somehow
 		   contiguous with a span of free blocks that follows. Still,
 		   it will force the number to be recalculated later. */
-		rgd->rd_extfail_pt += rs->rs_free;
-		rs->rs_free = 0;
-		if (gfs2_rbm_from_block(&last_rbm, last_block))
-			return;
-		start = rbm_bi(&rs->rs_rbm);
-		last = rbm_bi(&last_rbm);
-		do
-			clear_bit(GBF_FULL, &start->bi_flags);
-		while (start++ != last);
+		rgd->rd_extfail_pt += rs->rs_requested;
+		rs->rs_requested = 0;
 	}
 }
 
@@ -652,11 +668,11 @@ void gfs2_rs_deltree(struct gfs2_blkreserv *rs)
 {
 	struct gfs2_rgrpd *rgd;
 
-	rgd = rs->rs_rbm.rgd;
+	rgd = rs->rs_rgd;
 	if (rgd) {
 		spin_lock(&rgd->rd_rsspin);
 		__rs_deltree(rs);
-		BUG_ON(rs->rs_free);
+		BUG_ON(rs->rs_requested);
 		spin_unlock(&rgd->rd_rsspin);
 	}
 }
@@ -904,6 +920,7 @@ static int read_rindex_entry(struct gfs2_inode *ip)
 	rgd->rd_data = be32_to_cpu(buf.ri_data);
 	rgd->rd_bitbytes = be32_to_cpu(buf.ri_bitbytes);
 	spin_lock_init(&rgd->rd_rsspin);
+	mutex_init(&rgd->rd_mutex);
 
 	error = compute_bitstructs(rgd);
 	if (error)
@@ -1149,6 +1166,23 @@ static u32 count_unlinked(struct gfs2_rgrpd *rgd)
 	return count;
 }
 
+static void rgrp_set_bitmap_flags(struct gfs2_rgrpd *rgd)
+{
+	struct gfs2_bitmap *bi;
+	int x;
+
+	if (rgd->rd_free) {
+		for (x = 0; x < rgd->rd_length; x++) {
+			bi = rgd->rd_bits + x;
+			clear_bit(GBF_FULL, &bi->bi_flags);
+		}
+	} else {
+		for (x = 0; x < rgd->rd_length; x++) {
+			bi = rgd->rd_bits + x;
+			set_bit(GBF_FULL, &bi->bi_flags);
+		}
+	}
+}
 
 /**
  * gfs2_rgrp_bh_get - Read in a RG's header and bitmaps
@@ -1192,11 +1226,11 @@ static int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 	}
 
 	if (!(rgd->rd_flags & GFS2_RDF_UPTODATE)) {
-		for (x = 0; x < length; x++)
-			clear_bit(GBF_FULL, &rgd->rd_bits[x].bi_flags);
 		gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data);
+		rgrp_set_bitmap_flags(rgd);
 		rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
 		rgd->rd_free_clone = rgd->rd_free;
+		BUG_ON(rgd->rd_reserved);
 		/* max out the rgrp allocation failure point */
 		rgd->rd_extfail_pt = rgd->rd_free;
 	}
@@ -1244,7 +1278,11 @@ static int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
 	if (rgd->rd_rgl->rl_unlinked == 0)
 		rgd->rd_flags &= ~GFS2_RDF_CHECK;
 	rgd->rd_free = be32_to_cpu(rgd->rd_rgl->rl_free);
+	rgrp_set_bitmap_flags(rgd);
 	rgd->rd_free_clone = rgd->rd_free;
+	BUG_ON(rgd->rd_reserved);
+	/* max out the rgrp allocation failure point */
+	rgd->rd_extfail_pt = rgd->rd_free;
 	rgd->rd_dinodes = be32_to_cpu(rgd->rd_rgl->rl_dinodes);
 	rgd->rd_igeneration = be64_to_cpu(rgd->rd_rgl->rl_igeneration);
 	return 0;
@@ -1404,7 +1442,8 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
 
 	while (1) {
 
-		ret = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, &gh);
+		ret = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
+					 LM_FLAG_NODE_SCOPE, &gh);
 		if (ret)
 			goto out;
 
@@ -1412,9 +1451,11 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
 			/* Trim each bitmap in the rgrp */
 			for (x = 0; x < rgd->rd_length; x++) {
 				struct gfs2_bitmap *bi = rgd->rd_bits + x;
+				rgrp_lock_local(rgd);
 				ret = gfs2_rgrp_send_discards(sdp,
 						rgd->rd_data0, NULL, bi, minlen,
 						&amt);
+				rgrp_unlock_local(rgd);
 				if (ret) {
 					gfs2_glock_dq_uninit(&gh);
 					goto out;
@@ -1426,9 +1467,11 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
 			ret = gfs2_trans_begin(sdp, RES_RG_HDR, 0);
 			if (ret == 0) {
 				bh = rgd->rd_bits[0].bi_bh;
+				rgrp_lock_local(rgd);
 				rgd->rd_flags |= GFS2_RGF_TRIMMED;
 				gfs2_trans_add_meta(rgd->rd_gl, bh);
 				gfs2_rgrp_out(rgd, bh->b_data);
+				rgrp_unlock_local(rgd);
 				gfs2_trans_end(sdp);
 			}
 		}
@@ -1458,8 +1501,7 @@ static void rs_insert(struct gfs2_inode *ip)
 	struct rb_node **newn, *parent = NULL;
 	int rc;
 	struct gfs2_blkreserv *rs = &ip->i_res;
-	struct gfs2_rgrpd *rgd = rs->rs_rbm.rgd;
-	u64 fsblock = gfs2_rbm_to_block(&rs->rs_rbm);
+	struct gfs2_rgrpd *rgd = rs->rs_rgd;
 
 	BUG_ON(gfs2_rs_active(rs));
 
@@ -1470,7 +1512,7 @@ static void rs_insert(struct gfs2_inode *ip)
 			rb_entry(*newn, struct gfs2_blkreserv, rs_node);
 
 		parent = *newn;
-		rc = rs_cmp(fsblock, rs->rs_free, cur);
+		rc = rs_cmp(rs->rs_start, rs->rs_requested, cur);
 		if (rc > 0)
 			newn = &((*newn)->rb_right);
 		else if (rc < 0)
@@ -1486,7 +1528,7 @@ static void rs_insert(struct gfs2_inode *ip)
 	rb_insert_color(&rs->rs_node, &rgd->rd_rstree);
 
 	/* Do our rgrp accounting for the reservation */
-	rgd->rd_reserved += rs->rs_free; /* blocks reserved */
+	rgd->rd_requested += rs->rs_requested; /* blocks requested */
 	spin_unlock(&rgd->rd_rsspin);
 	trace_gfs2_rs(rs, TRACE_RS_INSERT);
 }
@@ -1507,9 +1549,9 @@ static inline u32 rgd_free(struct gfs2_rgrpd *rgd, struct gfs2_blkreserv *rs)
 {
 	u32 tot_reserved, tot_free;
 
-	if (WARN_ON_ONCE(rgd->rd_reserved < rs->rs_free))
+	if (WARN_ON_ONCE(rgd->rd_requested < rs->rs_requested))
 		return 0;
-	tot_reserved = rgd->rd_reserved - rs->rs_free;
+	tot_reserved = rgd->rd_requested - rs->rs_requested;
 
 	if (rgd->rd_free_clone < tot_reserved)
 		tot_reserved = 0;
@@ -1534,17 +1576,26 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip,
 	u64 goal;
 	struct gfs2_blkreserv *rs = &ip->i_res;
 	u32 extlen;
-	u32 free_blocks = rgd_free(rgd, rs);
+	u32 free_blocks, blocks_available;
 	int ret;
 	struct inode *inode = &ip->i_inode;
 
+	spin_lock(&rgd->rd_rsspin);
+	free_blocks = rgd_free(rgd, rs);
+	if (rgd->rd_free_clone < rgd->rd_requested)
+		free_blocks = 0;
+	blocks_available = rgd->rd_free_clone - rgd->rd_reserved;
+	if (rgd == rs->rs_rgd)
+		blocks_available += rs->rs_reserved;
+	spin_unlock(&rgd->rd_rsspin);
+
 	if (S_ISDIR(inode->i_mode))
 		extlen = 1;
 	else {
 		extlen = max_t(u32, atomic_read(&ip->i_sizehint), ap->target);
 		extlen = clamp(extlen, (u32)RGRP_RSRV_MINBLKS, free_blocks);
 	}
-	if ((rgd->rd_free_clone < rgd->rd_reserved) || (free_blocks < extlen))
+	if (free_blocks < extlen || blocks_available < extlen)
 		return;
 
 	/* Find bitmap block that contains bits for goal block */
@@ -1556,10 +1607,10 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip,
 	if (WARN_ON(gfs2_rbm_from_block(&rbm, goal)))
 		return;
 
-	ret = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, &extlen, ip, true);
+	ret = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, &extlen, &ip->i_res, true);
 	if (ret == 0) {
-		rs->rs_rbm = rbm;
-		rs->rs_free = extlen;
+		rs->rs_start = gfs2_rbm_to_block(&rbm);
+		rs->rs_requested = extlen;
 		rs_insert(ip);
 	} else {
 		if (goal == rgd->rd_last_alloc + rgd->rd_data0)
@@ -1572,7 +1623,7 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip,
  * @rgd: The resource group
  * @block: The starting block
  * @length: The required length
- * @ip: Ignore any reservations for this inode
+ * @ignore_rs: Reservation to ignore
  *
  * If the block does not appear in any reservation, then return the
  * block number unchanged. If it does appear in the reservation, then
@@ -1582,7 +1633,7 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip,
 
 static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block,
 				      u32 length,
-				      const struct gfs2_inode *ip)
+				      struct gfs2_blkreserv *ignore_rs)
 {
 	struct gfs2_blkreserv *rs;
 	struct rb_node *n;
@@ -1602,8 +1653,8 @@ static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block,
 	}
 
 	if (n) {
-		while ((rs_cmp(block, length, rs) == 0) && (&ip->i_res != rs)) {
-			block = gfs2_rbm_to_block(&rs->rs_rbm) + rs->rs_free;
+		while (rs_cmp(block, length, rs) == 0 && rs != ignore_rs) {
+			block = rs->rs_start + rs->rs_requested;
 			n = n->rb_right;
 			if (n == NULL)
 				break;
@@ -1618,7 +1669,7 @@ static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block,
 /**
  * gfs2_reservation_check_and_update - Check for reservations during block alloc
  * @rbm: The current position in the resource group
- * @ip: The inode for which we are searching for blocks
+ * @rs: Our own reservation
  * @minext: The minimum extent length
  * @maxext: A pointer to the maximum extent structure
  *
@@ -1632,20 +1683,19 @@ static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block,
  */
 
 static int gfs2_reservation_check_and_update(struct gfs2_rbm *rbm,
-					     const struct gfs2_inode *ip,
+					     struct gfs2_blkreserv *rs,
 					     u32 minext,
 					     struct gfs2_extent *maxext)
 {
 	u64 block = gfs2_rbm_to_block(rbm);
 	u32 extlen = 1;
 	u64 nblock;
-	int ret;
 
 	/*
 	 * If we have a minimum extent length, then skip over any extent
 	 * which is less than the min extent length in size.
 	 */
-	if (minext) {
+	if (minext > 1) {
 		extlen = gfs2_free_extlen(rbm, minext);
 		if (extlen <= maxext->len)
 			goto fail;
@@ -1655,7 +1705,7 @@ static int gfs2_reservation_check_and_update(struct gfs2_rbm *rbm,
 	 * Check the extent which has been found against the reservations
 	 * and skip if parts of it are already reserved
 	 */
-	nblock = gfs2_next_unreserved_block(rbm->rgd, block, extlen, ip);
+	nblock = gfs2_next_unreserved_block(rbm->rgd, block, extlen, rs);
 	if (nblock == block) {
 		if (!minext || extlen >= minext)
 			return 0;
@@ -1664,12 +1714,15 @@ static int gfs2_reservation_check_and_update(struct gfs2_rbm *rbm,
 			maxext->len = extlen;
 			maxext->rbm = *rbm;
 		}
-fail:
-		nblock = block + extlen;
+	} else {
+		u64 len = nblock - block;
+		if (len >= (u64)1 << 32)
+			return -E2BIG;
+		extlen = len;
 	}
-	ret = gfs2_rbm_from_block(rbm, nblock);
-	if (ret < 0)
-		return ret;
+fail:
+	if (gfs2_rbm_add(rbm, extlen))
+		return -E2BIG;
 	return 1;
 }
 
@@ -1677,9 +1730,9 @@ fail:
  * gfs2_rbm_find - Look for blocks of a particular state
  * @rbm: Value/result starting position and final position
  * @state: The state which we want to find
- * @minext: Pointer to the requested extent length (NULL for a single block)
+ * @minext: Pointer to the requested extent length
  *          This is updated to be the actual reservation size.
- * @ip: If set, check for reservations
+ * @rs: Our own reservation (NULL to skip checking for reservations)
  * @nowrap: Stop looking at the end of the rgrp, rather than wrapping
  *          around until we've reached the starting point.
  *
@@ -1693,7 +1746,7 @@ fail:
  */
 
 static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
-			 const struct gfs2_inode *ip, bool nowrap)
+			 struct gfs2_blkreserv *rs, bool nowrap)
 {
 	bool scan_from_start = rbm->bii == 0 && rbm->offset == 0;
 	struct buffer_head *bh;
@@ -1714,8 +1767,7 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
 
 	while(1) {
 		bi = rbm_bi(rbm);
-		if ((ip == NULL || !gfs2_rs_active(&ip->i_res)) &&
-		    test_bit(GBF_FULL, &bi->bi_flags) &&
+		if (test_bit(GBF_FULL, &bi->bi_flags) &&
 		    (state == GFS2_BLKST_FREE))
 			goto next_bitmap;
 
@@ -1731,11 +1783,10 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
 			goto next_bitmap;
 		}
 		rbm->offset = offset;
-		if (ip == NULL)
+		if (!rs)
 			return 0;
 
-		ret = gfs2_reservation_check_and_update(rbm, ip,
-							minext ? *minext : 0,
+		ret = gfs2_reservation_check_and_update(rbm, rs, *minext,
 							&maxext);
 		if (ret == 0)
 			return 0;
@@ -1767,7 +1818,7 @@ next_iter:
 			break;
 	}
 
-	if (minext == NULL || state != GFS2_BLKST_FREE)
+	if (state != GFS2_BLKST_FREE)
 		return -ENOSPC;
 
 	/* If the extent was too small, and it's smaller than the smallest
@@ -1775,7 +1826,7 @@ next_iter:
 	   useless to search this rgrp again for this amount or more. */
 	if (wrapped && (scan_from_start || rbm->bii > last_bii) &&
 	    *minext < rbm->rgd->rd_extfail_pt)
-		rbm->rgd->rd_extfail_pt = *minext;
+		rbm->rgd->rd_extfail_pt = *minext - 1;
 
 	/* If the maximum extent we found is big enough to fulfill the
 	   minimum requirements, use it anyway. */
@@ -1938,7 +1989,7 @@ static bool gfs2_rgrp_used_recently(const struct gfs2_blkreserv *rs,
 	u64 tdiff;
 
 	tdiff = ktime_to_ns(ktime_sub(ktime_get_real(),
-                            rs->rs_rbm.rgd->rd_gl->gl_dstamp));
+                            rs->rs_rgd->rd_gl->gl_dstamp));
 
 	return tdiff > (msecs * 1000 * 1000);
 }
@@ -1993,8 +2044,7 @@ static inline int fast_to_acquire(struct gfs2_rgrpd *rgd)
  * We try our best to find an rgrp that has at least ap->target blocks
  * available. After a couple of passes (loops == 2), the prospects of finding
  * such an rgrp diminish. At this stage, we return the first rgrp that has
- * at least ap->min_target blocks available. Either way, we set ap->allowed to
- * the number of blocks available in the chosen rgrp.
+ * at least ap->min_target blocks available.
  *
  * Returns: 0 on success,
  *          -ENOMEM if a suitable rgrp can't be found
@@ -2006,56 +2056,64 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrpd *begin = NULL;
 	struct gfs2_blkreserv *rs = &ip->i_res;
-	int error = 0, rg_locked, flags = 0;
+	int error = 0, flags = LM_FLAG_NODE_SCOPE;
+	bool rg_locked;
 	u64 last_unlinked = NO_BLOCK;
+	u32 target = ap->target;
 	int loops = 0;
-	u32 free_blocks, skip = 0;
+	u32 free_blocks, blocks_available, skip = 0;
+
+	BUG_ON(rs->rs_reserved);
 
 	if (sdp->sd_args.ar_rgrplvb)
 		flags |= GL_SKIP;
-	if (gfs2_assert_warn(sdp, ap->target))
+	if (gfs2_assert_warn(sdp, target))
 		return -EINVAL;
 	if (gfs2_rs_active(rs)) {
-		begin = rs->rs_rbm.rgd;
-	} else if (rs->rs_rbm.rgd &&
-		   rgrp_contains_block(rs->rs_rbm.rgd, ip->i_goal)) {
-		begin = rs->rs_rbm.rgd;
+		begin = rs->rs_rgd;
+	} else if (rs->rs_rgd &&
+		   rgrp_contains_block(rs->rs_rgd, ip->i_goal)) {
+		begin = rs->rs_rgd;
 	} else {
 		check_and_update_goal(ip);
-		rs->rs_rbm.rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal, 1);
+		rs->rs_rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal, 1);
 	}
 	if (S_ISDIR(ip->i_inode.i_mode) && (ap->aflags & GFS2_AF_ORLOV))
 		skip = gfs2_orlov_skip(ip);
-	if (rs->rs_rbm.rgd == NULL)
+	if (rs->rs_rgd == NULL)
 		return -EBADSLT;
 
 	while (loops < 3) {
-		rg_locked = 1;
+		struct gfs2_rgrpd *rgd;
 
-		if (!gfs2_glock_is_locked_by_me(rs->rs_rbm.rgd->rd_gl)) {
-			rg_locked = 0;
+		rg_locked = gfs2_glock_is_locked_by_me(rs->rs_rgd->rd_gl);
+		if (rg_locked) {
+			rgrp_lock_local(rs->rs_rgd);
+		} else {
 			if (skip && skip--)
 				goto next_rgrp;
 			if (!gfs2_rs_active(rs)) {
 				if (loops == 0 &&
-				    !fast_to_acquire(rs->rs_rbm.rgd))
+				    !fast_to_acquire(rs->rs_rgd))
 					goto next_rgrp;
 				if ((loops < 2) &&
 				    gfs2_rgrp_used_recently(rs, 1000) &&
-				    gfs2_rgrp_congested(rs->rs_rbm.rgd, loops))
+				    gfs2_rgrp_congested(rs->rs_rgd, loops))
 					goto next_rgrp;
 			}
-			error = gfs2_glock_nq_init(rs->rs_rbm.rgd->rd_gl,
+			error = gfs2_glock_nq_init(rs->rs_rgd->rd_gl,
 						   LM_ST_EXCLUSIVE, flags,
 						   &ip->i_rgd_gh);
 			if (unlikely(error))
 				return error;
+			rgrp_lock_local(rs->rs_rgd);
 			if (!gfs2_rs_active(rs) && (loops < 2) &&
-			    gfs2_rgrp_congested(rs->rs_rbm.rgd, loops))
+			    gfs2_rgrp_congested(rs->rs_rgd, loops))
 				goto skip_rgrp;
 			if (sdp->sd_args.ar_rgrplvb) {
-				error = update_rgrp_lvb(rs->rs_rbm.rgd);
+				error = update_rgrp_lvb(rs->rs_rgd);
 				if (unlikely(error)) {
+					rgrp_unlock_local(rs->rs_rgd);
 					gfs2_glock_dq_uninit(&ip->i_rgd_gh);
 					return error;
 				}
@@ -2063,36 +2121,46 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
 		}
 
 		/* Skip unusable resource groups */
-		if ((rs->rs_rbm.rgd->rd_flags & (GFS2_RGF_NOALLOC |
+		if ((rs->rs_rgd->rd_flags & (GFS2_RGF_NOALLOC |
 						 GFS2_RDF_ERROR)) ||
-		    (loops == 0 && ap->target > rs->rs_rbm.rgd->rd_extfail_pt))
+		    (loops == 0 && target > rs->rs_rgd->rd_extfail_pt))
 			goto skip_rgrp;
 
 		if (sdp->sd_args.ar_rgrplvb)
-			gfs2_rgrp_bh_get(rs->rs_rbm.rgd);
+			gfs2_rgrp_bh_get(rs->rs_rgd);
 
 		/* Get a reservation if we don't already have one */
 		if (!gfs2_rs_active(rs))
-			rg_mblk_search(rs->rs_rbm.rgd, ip, ap);
+			rg_mblk_search(rs->rs_rgd, ip, ap);
 
 		/* Skip rgrps when we can't get a reservation on first pass */
 		if (!gfs2_rs_active(rs) && (loops < 1))
 			goto check_rgrp;
 
 		/* If rgrp has enough free space, use it */
-		free_blocks = rgd_free(rs->rs_rbm.rgd, rs);
-		if (free_blocks >= ap->target ||
-		    (loops == 2 && ap->min_target &&
-		     free_blocks >= ap->min_target)) {
-			ap->allowed = free_blocks;
-			return 0;
+		rgd = rs->rs_rgd;
+		spin_lock(&rgd->rd_rsspin);
+		free_blocks = rgd_free(rgd, rs);
+		blocks_available = rgd->rd_free_clone - rgd->rd_reserved;
+		if (free_blocks < target || blocks_available < target) {
+			spin_unlock(&rgd->rd_rsspin);
+			goto check_rgrp;
 		}
+		rs->rs_reserved = ap->target;
+		if (rs->rs_reserved > blocks_available)
+			rs->rs_reserved = blocks_available;
+		rgd->rd_reserved += rs->rs_reserved;
+		spin_unlock(&rgd->rd_rsspin);
+		rgrp_unlock_local(rs->rs_rgd);
+		return 0;
 check_rgrp:
 		/* Check for unlinked inodes which can be reclaimed */
-		if (rs->rs_rbm.rgd->rd_flags & GFS2_RDF_CHECK)
-			try_rgrp_unlink(rs->rs_rbm.rgd, &last_unlinked,
+		if (rs->rs_rgd->rd_flags & GFS2_RDF_CHECK)
+			try_rgrp_unlink(rs->rs_rgd, &last_unlinked,
 					ip->i_no_addr);
 skip_rgrp:
+		rgrp_unlock_local(rs->rs_rgd);
+
 		/* Drop reservation, if we couldn't use reserved rgrp */
 		if (gfs2_rs_active(rs))
 			gfs2_rs_deltree(rs);
@@ -2102,7 +2170,7 @@ skip_rgrp:
 			gfs2_glock_dq_uninit(&ip->i_rgd_gh);
 next_rgrp:
 		/* Find the next rgrp, and continue looking */
-		if (gfs2_select_rgrp(&rs->rs_rbm.rgd, begin))
+		if (gfs2_select_rgrp(&rs->rs_rgd, begin))
 			continue;
 		if (skip)
 			continue;
@@ -2119,9 +2187,12 @@ next_rgrp:
 				return error;
 		}
 		/* Flushing the log may release space */
-		if (loops == 2)
+		if (loops == 2) {
+			if (ap->min_target)
+				target = ap->min_target;
 			gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
 				       GFS2_LFC_INPLACE_RESERVE);
+		}
 	}
 
 	return -ENOSPC;
@@ -2136,6 +2207,17 @@ next_rgrp:
 
 void gfs2_inplace_release(struct gfs2_inode *ip)
 {
+	struct gfs2_blkreserv *rs = &ip->i_res;
+
+	if (rs->rs_reserved) {
+		struct gfs2_rgrpd *rgd = rs->rs_rgd;
+
+		spin_lock(&rgd->rd_rsspin);
+		BUG_ON(rgd->rd_reserved < rs->rs_reserved);
+		rgd->rd_reserved -= rs->rs_reserved;
+		spin_unlock(&rgd->rd_rsspin);
+		rs->rs_reserved = 0;
+	}
 	if (gfs2_holder_initialized(&ip->i_rgd_gh))
 		gfs2_glock_dq_uninit(&ip->i_rgd_gh);
 }
@@ -2205,7 +2287,7 @@ static void rgblk_free(struct gfs2_sbd *sdp, struct gfs2_rgrpd *rgd,
 			bi_prev = bi;
 		}
 		gfs2_setbit(&rbm, false, new_state);
-		gfs2_rbm_incr(&rbm);
+		gfs2_rbm_add(&rbm, 1);
 	}
 }
 
@@ -2223,11 +2305,12 @@ void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_rgrpd *rgd,
 	struct gfs2_blkreserv *trs;
 	const struct rb_node *n;
 
-	gfs2_print_dbg(seq, "%s R: n:%llu f:%02x b:%u/%u i:%u r:%u e:%u\n",
+	spin_lock(&rgd->rd_rsspin);
+	gfs2_print_dbg(seq, "%s R: n:%llu f:%02x b:%u/%u i:%u q:%u r:%u e:%u\n",
 		       fs_id_buf,
 		       (unsigned long long)rgd->rd_addr, rgd->rd_flags,
 		       rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes,
-		       rgd->rd_reserved, rgd->rd_extfail_pt);
+		       rgd->rd_requested, rgd->rd_reserved, rgd->rd_extfail_pt);
 	if (rgd->rd_sbd->sd_args.ar_rgrplvb) {
 		struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;
 
@@ -2236,7 +2319,6 @@ void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_rgrpd *rgd,
 			       be32_to_cpu(rgl->rl_free),
 			       be32_to_cpu(rgl->rl_dinodes));
 	}
-	spin_lock(&rgd->rd_rsspin);
 	for (n = rb_first(&rgd->rd_rstree); n; n = rb_next(&trs->rs_node)) {
 		trs = rb_entry(n, struct gfs2_blkreserv, rs_node);
 		dump_rs(seq, trs, fs_id_buf);
@@ -2273,29 +2355,29 @@ static void gfs2_adjust_reservation(struct gfs2_inode *ip,
 {
 	struct gfs2_blkreserv *rs = &ip->i_res;
 	struct gfs2_rgrpd *rgd = rbm->rgd;
-	unsigned rlen;
-	u64 block;
-	int ret;
 
-	spin_lock(&rgd->rd_rsspin);
+	BUG_ON(rs->rs_reserved < len);
+	rs->rs_reserved -= len;
 	if (gfs2_rs_active(rs)) {
-		if (gfs2_rbm_eq(&rs->rs_rbm, rbm)) {
-			block = gfs2_rbm_to_block(rbm);
-			ret = gfs2_rbm_from_block(&rs->rs_rbm, block + len);
-			rlen = min(rs->rs_free, len);
-			rs->rs_free -= rlen;
-			rgd->rd_reserved -= rlen;
+		u64 start = gfs2_rbm_to_block(rbm);
+
+		if (rs->rs_start == start) {
+			unsigned int rlen;
+
+			rs->rs_start += len;
+			rlen = min(rs->rs_requested, len);
+			rs->rs_requested -= rlen;
+			rgd->rd_requested -= rlen;
 			trace_gfs2_rs(rs, TRACE_RS_CLAIM);
-			if (rs->rs_free && !ret)
-				goto out;
+			if (rs->rs_start < rgd->rd_data0 + rgd->rd_data &&
+			    rs->rs_requested)
+				return;
 			/* We used up our block reservation, so we should
 			   reserve more blocks next time. */
 			atomic_add(RGRP_RSRV_ADDBLKS, &ip->i_sizehint);
 		}
 		__rs_deltree(rs);
 	}
-out:
-	spin_unlock(&rgd->rd_rsspin);
 }
 
 /**
@@ -2315,15 +2397,13 @@ static void gfs2_set_alloc_start(struct gfs2_rbm *rbm,
 	u64 goal;
 
 	if (gfs2_rs_active(&ip->i_res)) {
-		*rbm = ip->i_res.rs_rbm;
-		return;
+		goal = ip->i_res.rs_start;
+	} else {
+		if (!dinode && rgrp_contains_block(rbm->rgd, ip->i_goal))
+			goal = ip->i_goal;
+		else
+			goal = rbm->rgd->rd_last_alloc + rbm->rgd->rd_data0;
 	}
-
-	if (!dinode && rgrp_contains_block(rbm->rgd, ip->i_goal))
-		goal = ip->i_goal;
-	else
-		goal = rbm->rgd->rd_last_alloc + rbm->rgd->rd_data0;
-
 	if (WARN_ON_ONCE(gfs2_rbm_from_block(rbm, goal))) {
 		rbm->bii = 0;
 		rbm->offset = 0;
@@ -2346,17 +2426,21 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct buffer_head *dibh;
-	struct gfs2_rbm rbm = { .rgd = ip->i_res.rs_rbm.rgd, };
-	unsigned int ndata;
+	struct gfs2_rbm rbm = { .rgd = ip->i_res.rs_rgd, };
 	u64 block; /* block, within the file system scope */
-	int error;
+	u32 minext = 1;
+	int error = -ENOSPC;
 
-	gfs2_set_alloc_start(&rbm, ip, dinode);
-	error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, NULL, ip, false);
+	BUG_ON(ip->i_res.rs_reserved < *nblocks);
 
+	rgrp_lock_local(rbm.rgd);
+	if (gfs2_rs_active(&ip->i_res)) {
+		gfs2_set_alloc_start(&rbm, ip, dinode);
+		error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, &minext, &ip->i_res, false);
+	}
 	if (error == -ENOSPC) {
 		gfs2_set_alloc_start(&rbm, ip, dinode);
-		error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, NULL, NULL, false);
+		error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, &minext, NULL, false);
 	}
 
 	/* Since all blocks are reserved in advance, this shouldn't happen */
@@ -2371,14 +2455,8 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 	gfs2_alloc_extent(&rbm, dinode, nblocks);
 	block = gfs2_rbm_to_block(&rbm);
 	rbm.rgd->rd_last_alloc = block - rbm.rgd->rd_data0;
-	if (gfs2_rs_active(&ip->i_res))
-		gfs2_adjust_reservation(ip, &rbm, *nblocks);
-	ndata = *nblocks;
-	if (dinode)
-		ndata--;
-
 	if (!dinode) {
-		ip->i_goal = block + ndata - 1;
+		ip->i_goal = block + *nblocks - 1;
 		error = gfs2_meta_inode_buffer(ip, &dibh);
 		if (error == 0) {
 			struct gfs2_dinode *di =
@@ -2389,12 +2467,20 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 			brelse(dibh);
 		}
 	}
-	if (rbm.rgd->rd_free < *nblocks) {
+	spin_lock(&rbm.rgd->rd_rsspin);
+	gfs2_adjust_reservation(ip, &rbm, *nblocks);
+	if (rbm.rgd->rd_free < *nblocks || rbm.rgd->rd_reserved < *nblocks) {
 		fs_warn(sdp, "nblocks=%u\n", *nblocks);
+		spin_unlock(&rbm.rgd->rd_rsspin);
 		goto rgrp_error;
 	}
-
+	BUG_ON(rbm.rgd->rd_reserved < *nblocks);
+	BUG_ON(rbm.rgd->rd_free_clone < *nblocks);
+	BUG_ON(rbm.rgd->rd_free < *nblocks);
+	rbm.rgd->rd_reserved -= *nblocks;
+	rbm.rgd->rd_free_clone -= *nblocks;
 	rbm.rgd->rd_free -= *nblocks;
+	spin_unlock(&rbm.rgd->rd_rsspin);
 	if (dinode) {
 		rbm.rgd->rd_dinodes++;
 		*generation = rbm.rgd->rd_igeneration++;
@@ -2404,6 +2490,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 
 	gfs2_trans_add_meta(rbm.rgd->rd_gl, rbm.rgd->rd_bits[0].bi_bh);
 	gfs2_rgrp_out(rbm.rgd, rbm.rgd->rd_bits[0].bi_bh->b_data);
+	rgrp_unlock_local(rbm.rgd);
 
 	gfs2_statfs_change(sdp, 0, -(s64)*nblocks, dinode ? 1 : 0);
 	if (dinode)
@@ -2411,13 +2498,13 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 
 	gfs2_quota_change(ip, *nblocks, ip->i_inode.i_uid, ip->i_inode.i_gid);
 
-	rbm.rgd->rd_free_clone -= *nblocks;
 	trace_gfs2_block_alloc(ip, rbm.rgd, block, *nblocks,
 			       dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED);
 	*bn = block;
 	return 0;
 
 rgrp_error:
+	rgrp_unlock_local(rbm.rgd);
 	gfs2_rgrp_error(rbm.rgd);
 	return -EIO;
 }
@@ -2437,12 +2524,14 @@ void __gfs2_free_blocks(struct gfs2_inode *ip, struct gfs2_rgrpd *rgd,
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 
+	rgrp_lock_local(rgd);
 	rgblk_free(sdp, rgd, bstart, blen, GFS2_BLKST_FREE);
 	trace_gfs2_block_alloc(ip, rgd, bstart, blen, GFS2_BLKST_FREE);
 	rgd->rd_free += blen;
 	rgd->rd_flags &= ~GFS2_RGF_TRIMMED;
 	gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+	rgrp_unlock_local(rgd);
 
 	/* Directories keep their data in the metadata address space */
 	if (meta || ip->i_depth || gfs2_is_jdata(ip))
@@ -2478,17 +2567,20 @@ void gfs2_unlink_di(struct inode *inode)
 	rgd = gfs2_blk2rgrpd(sdp, blkno, true);
 	if (!rgd)
 		return;
+	rgrp_lock_local(rgd);
 	rgblk_free(sdp, rgd, blkno, 1, GFS2_BLKST_UNLINKED);
 	trace_gfs2_block_alloc(ip, rgd, blkno, 1, GFS2_BLKST_UNLINKED);
 	gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
 	be32_add_cpu(&rgd->rd_rgl->rl_unlinked, 1);
+	rgrp_unlock_local(rgd);
 }
 
 void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = rgd->rd_sbd;
 
+	rgrp_lock_local(rgd);
 	rgblk_free(sdp, rgd, ip->i_no_addr, 1, GFS2_BLKST_FREE);
 	if (!rgd->rd_dinodes)
 		gfs2_consist_rgrpd(rgd);
@@ -2497,6 +2589,7 @@ void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
 
 	gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+	rgrp_unlock_local(rgd);
 	be32_add_cpu(&rgd->rd_rgl->rl_unlinked, -1);
 
 	gfs2_statfs_change(sdp, 0, +1, -1);
@@ -2511,6 +2604,10 @@ void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
  * @no_addr: The block number to check
  * @type: The block type we are looking for
  *
+ * The inode glock of @no_addr must be held.  The @type to check for is either
+ * GFS2_BLKST_DINODE or GFS2_BLKST_UNLINKED; checking for type GFS2_BLKST_FREE
+ * or GFS2_BLKST_USED would make no sense.
+ *
  * Returns: 0 if the block type matches the expected type
  *          -ESTALE if it doesn't match
  *          or -ve errno if something went wrong while checking
@@ -2534,6 +2631,13 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type)
 	rbm.rgd = rgd;
 	error = gfs2_rbm_from_block(&rbm, no_addr);
 	if (!WARN_ON_ONCE(error)) {
+		/*
+		 * No need to take the local resource group lock here; the
+		 * inode glock of @no_addr provides the necessary
+		 * synchronization in case the block is an inode.  (In case
+		 * the block is not an inode, the block type will not match
+		 * the @type we are looking for.)
+		 */
 		if (gfs2_testbit(&rbm, false) != type)
 			error = -ESTALE;
 	}
@@ -2578,7 +2682,7 @@ void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist,
 			return;
 		rgd = gfs2_blk2rgrpd(sdp, block, 1);
 	} else {
-		rgd = ip->i_res.rs_rbm.rgd;
+		rgd = ip->i_res.rs_rgd;
 		if (!rgd || !rgrp_contains_block(rgd, block))
 			rgd = gfs2_blk2rgrpd(sdp, block, 1);
 	}
@@ -2633,9 +2737,8 @@ void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist)
 				      sizeof(struct gfs2_holder),
 				      GFP_NOFS | __GFP_NOFAIL);
 	for (x = 0; x < rlist->rl_rgrps; x++)
-		gfs2_holder_init(rlist->rl_rgd[x]->rd_gl,
-				LM_ST_EXCLUSIVE, 0,
-				&rlist->rl_ghs[x]);
+		gfs2_holder_init(rlist->rl_rgd[x]->rd_gl, LM_ST_EXCLUSIVE,
+				 LM_FLAG_NODE_SCOPE, &rlist->rl_ghs[x]);
 }
 
 /**
@@ -2658,3 +2761,14 @@ void gfs2_rlist_free(struct gfs2_rgrp_list *rlist)
 	}
 }
 
+void rgrp_lock_local(struct gfs2_rgrpd *rgd)
+{
+	BUG_ON(!gfs2_glock_is_held_excl(rgd->rd_gl) &&
+	       !test_bit(SDF_NORECOVERY, &rgd->rd_sbd->sd_flags));
+	mutex_lock(&rgd->rd_mutex);
+}
+
+void rgrp_unlock_local(struct gfs2_rgrpd *rgd)
+{
+	mutex_unlock(&rgd->rd_mutex);
+}
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index 9a587ada51ed..a6855fd796e0 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -77,7 +77,7 @@ extern int gfs2_fitrim(struct file *filp, void __user *argp);
 /* This is how to tell if a reservation is in the rgrp tree: */
 static inline bool gfs2_rs_active(const struct gfs2_blkreserv *rs)
 {
-	return rs && !RB_EMPTY_NODE(&rs->rs_node);
+	return !RB_EMPTY_NODE(&rs->rs_node);
 }
 
 static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
@@ -88,4 +88,8 @@ static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
 }
 
 extern void check_and_update_goal(struct gfs2_inode *ip);
+
+extern void rgrp_lock_local(struct gfs2_rgrpd *rgd);
+extern void rgrp_unlock_local(struct gfs2_rgrpd *rgd);
+
 #endif /* __RGRP_DOT_H__ */
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 754ea2a137b4..7aa602a0ef1b 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -81,19 +81,12 @@ void gfs2_jindex_free(struct gfs2_sbd *sdp)
 static struct gfs2_jdesc *jdesc_find_i(struct list_head *head, unsigned int jid)
 {
 	struct gfs2_jdesc *jd;
-	int found = 0;
 
 	list_for_each_entry(jd, head, jd_list) {
-		if (jd->jd_jid == jid) {
-			found = 1;
-			break;
-		}
+		if (jd->jd_jid == jid)
+			return jd;
 	}
-
-	if (!found)
-		jd = NULL;
-
-	return jd;
+	return NULL;
 }
 
 struct gfs2_jdesc *gfs2_jdesc_find(struct gfs2_sbd *sdp, unsigned int jid)
@@ -620,13 +613,13 @@ int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 
 		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_SHUTDOWN |
 			       GFS2_LFC_MAKE_FS_RO);
-		wait_event(sdp->sd_reserving_log_wait,
-			   atomic_read(&sdp->sd_reserving_log) == 0);
-		gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) ==
-				 sdp->sd_jdesc->jd_blocks);
+		wait_event_timeout(sdp->sd_log_waitq,
+				   gfs2_log_is_empty(sdp),
+				   HZ * 5);
+		gfs2_assert_warn(sdp, gfs2_log_is_empty(sdp));
 	} else {
-		wait_event_timeout(sdp->sd_reserving_log_wait,
-				   atomic_read(&sdp->sd_reserving_log) == 0,
+		wait_event_timeout(sdp->sd_log_waitq,
+				   gfs2_log_is_empty(sdp),
 				   HZ * 5);
 	}
 	gfs2_quota_cleanup(sdp);
@@ -1192,7 +1185,8 @@ static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
 		goto out_qs;
 	}
 
-	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
+				   LM_FLAG_NODE_SCOPE, &gh);
 	if (error)
 		goto out_qs;
 
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
index 0b2f858d9a8c..bd6c8e9e49db 100644
--- a/fs/gfs2/trace_gfs2.h
+++ b/fs/gfs2/trace_gfs2.h
@@ -560,6 +560,7 @@ TRACE_EVENT(gfs2_block_alloc,
 		__field(	u8,	block_state		)
 		__field(        u64,	rd_addr			)
 		__field(        u32,	rd_free_clone		)
+		__field(	u32,	rd_requested		)
 		__field(	u32,	rd_reserved		)
 	),
 
@@ -571,17 +572,20 @@ TRACE_EVENT(gfs2_block_alloc,
 		__entry->block_state	= block_state;
 		__entry->rd_addr	= rgd->rd_addr;
 		__entry->rd_free_clone	= rgd->rd_free_clone;
+		__entry->rd_requested	= rgd->rd_requested;
 		__entry->rd_reserved	= rgd->rd_reserved;
 	),
 
-	TP_printk("%u,%u bmap %llu alloc %llu/%lu %s rg:%llu rf:%u rr:%lu",
+	TP_printk("%u,%u bmap %llu alloc %llu/%lu %s rg:%llu rf:%u rq:%u rr:%u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long long)__entry->inum,
 		  (unsigned long long)__entry->start,
 		  (unsigned long)__entry->len,
 		  block_state_name(__entry->block_state),
 		  (unsigned long long)__entry->rd_addr,
-		  __entry->rd_free_clone, (unsigned long)__entry->rd_reserved)
+		  __entry->rd_free_clone,
+		  __entry->rd_requested,
+		  __entry->rd_reserved)
 );
 
 /* Keep track of multi-block reservations as they are allocated/freed */
@@ -595,33 +599,40 @@ TRACE_EVENT(gfs2_rs,
 		__field(        dev_t,  dev                     )
 		__field(	u64,	rd_addr			)
 		__field(	u32,	rd_free_clone		)
+		__field(	u32,	rd_requested		)
 		__field(	u32,	rd_reserved		)
 		__field(	u64,	inum			)
 		__field(	u64,	start			)
-		__field(	u32,	free			)
+		__field(	u32,	requested		)
+		__field(	u32,	reserved		)
 		__field(	u8,	func			)
 	),
 
 	TP_fast_assign(
-		__entry->dev		= rs->rs_rbm.rgd->rd_sbd->sd_vfs->s_dev;
-		__entry->rd_addr	= rs->rs_rbm.rgd->rd_addr;
-		__entry->rd_free_clone	= rs->rs_rbm.rgd->rd_free_clone;
-		__entry->rd_reserved	= rs->rs_rbm.rgd->rd_reserved;
+		__entry->dev		= rs->rs_rgd->rd_sbd->sd_vfs->s_dev;
+		__entry->rd_addr	= rs->rs_rgd->rd_addr;
+		__entry->rd_free_clone	= rs->rs_rgd->rd_free_clone;
+		__entry->rd_requested	= rs->rs_rgd->rd_requested;
+		__entry->rd_reserved	= rs->rs_rgd->rd_reserved;
 		__entry->inum		= container_of(rs, struct gfs2_inode,
 						       i_res)->i_no_addr;
-		__entry->start		= gfs2_rbm_to_block(&rs->rs_rbm);
-		__entry->free		= rs->rs_free;
+		__entry->start		= rs->rs_start;
+		__entry->requested	= rs->rs_requested;
+		__entry->reserved	= rs->rs_reserved;
 		__entry->func		= func;
 	),
 
-	TP_printk("%u,%u bmap %llu resrv %llu rg:%llu rf:%lu rr:%lu %s f:%lu",
+	TP_printk("%u,%u bmap %llu resrv %llu rg:%llu rf:%u rq:%u rr:%u %s q:%u r:%u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  (unsigned long long)__entry->inum,
 		  (unsigned long long)__entry->start,
 		  (unsigned long long)__entry->rd_addr,
-		  (unsigned long)__entry->rd_free_clone,
-		  (unsigned long)__entry->rd_reserved,
-		  rs_func_name(__entry->func), (unsigned long)__entry->free)
+		  __entry->rd_free_clone,
+		  __entry->rd_requested,
+		  __entry->rd_reserved,
+		  rs_func_name(__entry->func),
+		  __entry->requested,
+		  __entry->reserved)
 );
 
 #endif /* _TRACE_GFS2_H */
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 6d4bf7ea7b3b..ab96cf0bf26b 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -31,17 +31,17 @@ static void gfs2_print_trans(struct gfs2_sbd *sdp, const struct gfs2_trans *tr)
 	fs_warn(sdp, "blocks=%u revokes=%u reserved=%u touched=%u\n",
 		tr->tr_blocks, tr->tr_revokes, tr->tr_reserved,
 		test_bit(TR_TOUCHED, &tr->tr_flags));
-	fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
+	fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u\n",
 		tr->tr_num_buf_new, tr->tr_num_buf_rm,
 		tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
-		tr->tr_num_revoke, tr->tr_num_revoke_rm);
+		tr->tr_num_revoke);
 }
 
-int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
-		     unsigned int revokes)
+int __gfs2_trans_begin(struct gfs2_trans *tr, struct gfs2_sbd *sdp,
+		       unsigned int blocks, unsigned int revokes,
+		       unsigned long ip)
 {
-	struct gfs2_trans *tr;
-	int error;
+	unsigned int extra_revokes;
 
 	if (current->journal_info) {
 		gfs2_print_trans(sdp, current->journal_info);
@@ -52,39 +52,72 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
 		return -EROFS;
 
-	tr = kmem_cache_zalloc(gfs2_trans_cachep, GFP_NOFS);
-	if (!tr)
-		return -ENOMEM;
-
-	tr->tr_ip = _RET_IP_;
+	tr->tr_ip = ip;
 	tr->tr_blocks = blocks;
 	tr->tr_revokes = revokes;
-	tr->tr_reserved = 1;
-	set_bit(TR_ALLOCED, &tr->tr_flags);
-	if (blocks)
-		tr->tr_reserved += 6 + blocks;
-	if (revokes)
-		tr->tr_reserved += gfs2_struct2blk(sdp, revokes);
+	tr->tr_reserved = GFS2_LOG_FLUSH_MIN_BLOCKS;
+	if (blocks) {
+		/*
+		 * The reserved blocks are either used for data or metadata.
+		 * We can have mixed data and metadata, each with its own log
+		 * descriptor block; see calc_reserved().
+		 */
+		tr->tr_reserved += blocks + 1 + DIV_ROUND_UP(blocks - 1, databuf_limit(sdp));
+	}
 	INIT_LIST_HEAD(&tr->tr_databuf);
 	INIT_LIST_HEAD(&tr->tr_buf);
 	INIT_LIST_HEAD(&tr->tr_list);
 	INIT_LIST_HEAD(&tr->tr_ail1_list);
 	INIT_LIST_HEAD(&tr->tr_ail2_list);
 
+	if (gfs2_assert_warn(sdp, tr->tr_reserved <= sdp->sd_jdesc->jd_blocks))
+		return -EINVAL;
+
 	sb_start_intwrite(sdp->sd_vfs);
 
-	error = gfs2_log_reserve(sdp, tr->tr_reserved);
-	if (error)
-		goto fail;
+	/*
+	 * Try the reservations under sd_log_flush_lock to prevent log flushes
+	 * from creating inconsistencies between the number of allocated and
+	 * reserved revokes.  If that fails, do a full-block allocation outside
+	 * of the lock to avoid stalling log flushes.  Then, allot the
+	 * appropriate number of blocks to revokes, use as many revokes locally
+	 * as needed, and "release" the surplus into the revokes pool.
+	 */
+
+	down_read(&sdp->sd_log_flush_lock);
+	if (gfs2_log_try_reserve(sdp, tr, &extra_revokes))
+		goto reserved;
+	up_read(&sdp->sd_log_flush_lock);
+	gfs2_log_reserve(sdp, tr, &extra_revokes);
+	down_read(&sdp->sd_log_flush_lock);
+
+reserved:
+	gfs2_log_release_revokes(sdp, extra_revokes);
+	if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) {
+		gfs2_log_release_revokes(sdp, tr->tr_revokes);
+		up_read(&sdp->sd_log_flush_lock);
+		gfs2_log_release(sdp, tr->tr_reserved);
+		sb_end_intwrite(sdp->sd_vfs);
+		return -EROFS;
+	}
 
 	current->journal_info = tr;
 
 	return 0;
+}
 
-fail:
-	sb_end_intwrite(sdp->sd_vfs);
-	kmem_cache_free(gfs2_trans_cachep, tr);
+int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
+		     unsigned int revokes)
+{
+	struct gfs2_trans *tr;
+	int error;
 
+	tr = kmem_cache_zalloc(gfs2_trans_cachep, GFP_NOFS);
+	if (!tr)
+		return -ENOMEM;
+	error = __gfs2_trans_begin(tr, sdp, blocks, revokes, _RET_IP_);
+	if (error)
+		kmem_cache_free(gfs2_trans_cachep, tr);
 	return error;
 }
 
@@ -92,37 +125,39 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
 {
 	struct gfs2_trans *tr = current->journal_info;
 	s64 nbuf;
-	int alloced = test_bit(TR_ALLOCED, &tr->tr_flags);
 
 	current->journal_info = NULL;
 
 	if (!test_bit(TR_TOUCHED, &tr->tr_flags)) {
+		gfs2_log_release_revokes(sdp, tr->tr_revokes);
+		up_read(&sdp->sd_log_flush_lock);
 		gfs2_log_release(sdp, tr->tr_reserved);
-		if (alloced) {
+		if (!test_bit(TR_ONSTACK, &tr->tr_flags))
 			gfs2_trans_free(sdp, tr);
-			sb_end_intwrite(sdp->sd_vfs);
-		}
+		sb_end_intwrite(sdp->sd_vfs);
 		return;
 	}
 
+	gfs2_log_release_revokes(sdp, tr->tr_revokes - tr->tr_num_revoke);
+
 	nbuf = tr->tr_num_buf_new + tr->tr_num_databuf_new;
 	nbuf -= tr->tr_num_buf_rm;
 	nbuf -= tr->tr_num_databuf_rm;
 
-	if (gfs2_assert_withdraw(sdp, (nbuf <= tr->tr_blocks) &&
-				       (tr->tr_num_revoke <= tr->tr_revokes)))
+	if (gfs2_assert_withdraw(sdp, nbuf <= tr->tr_blocks) ||
+	    gfs2_assert_withdraw(sdp, tr->tr_num_revoke <= tr->tr_revokes))
 		gfs2_print_trans(sdp, tr);
 
 	gfs2_log_commit(sdp, tr);
-	if (alloced && !test_bit(TR_ATTACHED, &tr->tr_flags))
+	if (!test_bit(TR_ONSTACK, &tr->tr_flags) &&
+	    !test_bit(TR_ATTACHED, &tr->tr_flags))
 		gfs2_trans_free(sdp, tr);
 	up_read(&sdp->sd_log_flush_lock);
 
 	if (sdp->sd_vfs->s_flags & SB_SYNCHRONOUS)
 		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
 			       GFS2_LFC_TRANS_END);
-	if (alloced)
-		sb_end_intwrite(sdp->sd_vfs);
+	sb_end_intwrite(sdp->sd_vfs);
 }
 
 static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl,
@@ -262,7 +297,6 @@ void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
 {
 	struct gfs2_bufdata *bd, *tmp;
-	struct gfs2_trans *tr = current->journal_info;
 	unsigned int n = len;
 
 	gfs2_log_lock(sdp);
@@ -274,7 +308,7 @@ void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
 			if (bd->bd_gl)
 				gfs2_glock_remove_revoke(bd->bd_gl);
 			kmem_cache_free(gfs2_bufdata_cachep, bd);
-			tr->tr_num_revoke_rm++;
+			gfs2_log_release_revokes(sdp, 1);
 			if (--n == 0)
 				break;
 		}
diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h
index 83199ce5a5c5..c76ad9a4c75a 100644
--- a/fs/gfs2/trans.h
+++ b/fs/gfs2/trans.h
@@ -27,13 +27,16 @@ struct gfs2_glock;
  * block, or all of the blocks in the rg, whichever is smaller */
 static inline unsigned int gfs2_rg_blocks(const struct gfs2_inode *ip, unsigned requested)
 {
-	struct gfs2_rgrpd *rgd = ip->i_res.rs_rbm.rgd;
+	struct gfs2_rgrpd *rgd = ip->i_res.rs_rgd;
 
 	if (requested < rgd->rd_length)
 		return requested + 1;
 	return rgd->rd_length;
 }
 
+extern int __gfs2_trans_begin(struct gfs2_trans *tr, struct gfs2_sbd *sdp,
+			      unsigned int blocks, unsigned int revokes,
+			      unsigned long ip);
 extern int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 			    unsigned int revokes);
 
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 2b520ac49d5f..a1b9c96cb8ef 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -273,7 +273,8 @@ static int ea_dealloc_unstuffed(struct gfs2_inode *ip, struct buffer_head *bh,
 		return -EIO;
 	}
 
-	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, &rg_gh);
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
+				   LM_FLAG_NODE_SCOPE, &rg_gh);
 	if (error)
 		return error;
 
@@ -1406,7 +1407,8 @@ static int ea_dealloc_block(struct gfs2_inode *ip)
 		return -EIO;
 	}
 
-	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
+				   LM_FLAG_NODE_SCOPE, &gh);
 	if (error)
 		return error;
 
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index c070c0d8e3e9..aea35459d390 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -315,7 +315,7 @@ retry:
 	if (mode & FMODE_WRITE)
 		r = w = 1;
 
-	name = dentry_name(file->f_path.dentry);
+	name = dentry_name(d_real(file->f_path.dentry, file->f_inode));
 	if (name == NULL)
 		return -ENOMEM;
 
diff --git a/fs/inode.c b/fs/inode.c
index cb008acf0efd..6442d97d9a4a 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1624,7 +1624,9 @@ static void iput_final(struct inode *inode)
 	else
 		drop = generic_drop_inode(inode);
 
-	if (!drop && (sb->s_flags & SB_ACTIVE)) {
+	if (!drop &&
+	    !(inode->i_state & I_DONTCACHE) &&
+	    (sb->s_flags & SB_ACTIVE)) {
 		inode_add_lru(inode);
 		spin_unlock(&inode->i_lock);
 		return;
diff --git a/fs/io-wq.c b/fs/io-wq.c
index f72d53848dcb..a564f36e260c 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -36,8 +36,7 @@ enum {
 
 enum {
 	IO_WQ_BIT_EXIT		= 0,	/* wq exiting */
-	IO_WQ_BIT_CANCEL	= 1,	/* cancel work on list */
-	IO_WQ_BIT_ERROR		= 2,	/* error on setup */
+	IO_WQ_BIT_ERROR		= 1,	/* error on setup */
 };
 
 enum {
@@ -561,12 +560,6 @@ get_next:
 
 			next_hashed = wq_next_work(work);
 			io_impersonate_work(worker, work);
-			/*
-			 * OK to set IO_WQ_WORK_CANCEL even for uncancellable
-			 * work, the worker function will do the right thing.
-			 */
-			if (test_bit(IO_WQ_BIT_CANCEL, &wq->state))
-				work->flags |= IO_WQ_WORK_CANCEL;
 
 			old_work = work;
 			linked = wq->do_work(work);
@@ -732,12 +725,6 @@ static inline bool io_wqe_need_worker(struct io_wqe *wqe, int index)
 	return acct->nr_workers < acct->max_workers;
 }
 
-static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data)
-{
-	send_sig(SIGINT, worker->task, 1);
-	return false;
-}
-
 /*
  * Iterate the passed in list and call the specific function for each
  * worker that isn't exiting
@@ -938,21 +925,6 @@ void io_wq_hash_work(struct io_wq_work *work, void *val)
 	work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT));
 }
 
-void io_wq_cancel_all(struct io_wq *wq)
-{
-	int node;
-
-	set_bit(IO_WQ_BIT_CANCEL, &wq->state);
-
-	rcu_read_lock();
-	for_each_node(node) {
-		struct io_wqe *wqe = wq->wqes[node];
-
-		io_wq_for_each_worker(wqe, io_wqe_worker_send_sig, NULL);
-	}
-	rcu_read_unlock();
-}
-
 struct io_cb_cancel_data {
 	work_cancel_fn *fn;
 	void *data;
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 069496c6d4f9..b158f8addcf3 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -59,6 +59,7 @@ static inline void wq_list_add_tail(struct io_wq_work_node *node,
 		list->last->next = node;
 		list->last = node;
 	}
+	node->next = NULL;
 }
 
 static inline void wq_list_cut(struct io_wq_work_list *list,
@@ -128,8 +129,6 @@ static inline bool io_wq_is_hashed(struct io_wq_work *work)
 	return work->flags & IO_WQ_WORK_HASHED;
 }
 
-void io_wq_cancel_all(struct io_wq *wq);
-
 typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
 
 enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 6f9392c35eef..985a9e3f976d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -262,6 +262,7 @@ struct io_ring_ctx {
 		unsigned int		drain_next: 1;
 		unsigned int		eventfd_async: 1;
 		unsigned int		restricted: 1;
+		unsigned int		sqo_dead: 1;
 
 		/*
 		 * Ring buffer of indices into array of io_uring_sqe, which is
@@ -353,6 +354,7 @@ struct io_ring_ctx {
 		unsigned		cq_entries;
 		unsigned		cq_mask;
 		atomic_t		cq_timeouts;
+		unsigned		cq_last_tm_flush;
 		unsigned long		cq_check_overflow;
 		struct wait_queue_head	cq_wait;
 		struct fasync_struct	*cq_fasync;
@@ -992,6 +994,13 @@ enum io_mem_account {
 	ACCT_PINNED,
 };
 
+static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
+					    struct task_struct *task);
+
+static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node);
+static struct fixed_file_ref_node *alloc_fixed_file_ref_node(
+			struct io_ring_ctx *ctx);
+
 static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
 			     struct io_comp_state *cs);
 static void io_cqring_fill_event(struct io_kiocb *req, long res);
@@ -1098,6 +1107,9 @@ static void io_sq_thread_drop_mm_files(void)
 
 static int __io_sq_thread_acquire_files(struct io_ring_ctx *ctx)
 {
+	if (current->flags & PF_EXITING)
+		return -EFAULT;
+
 	if (!current->files) {
 		struct files_struct *files;
 		struct nsproxy *nsproxy;
@@ -1125,6 +1137,8 @@ static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx)
 {
 	struct mm_struct *mm;
 
+	if (current->flags & PF_EXITING)
+		return -EFAULT;
 	if (current->mm)
 		return 0;
 
@@ -1338,11 +1352,6 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
 
 	/* order cqe stores with ring update */
 	smp_store_release(&rings->cq.tail, ctx->cached_cq_tail);
-
-	if (wq_has_sleeper(&ctx->cq_wait)) {
-		wake_up_interruptible(&ctx->cq_wait);
-		kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
-	}
 }
 
 static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req)
@@ -1501,6 +1510,13 @@ static bool io_grab_identity(struct io_kiocb *req)
 		spin_unlock_irq(&ctx->inflight_lock);
 		req->work.flags |= IO_WQ_WORK_FILES;
 	}
+	if (!(req->work.flags & IO_WQ_WORK_MM) &&
+	    (def->work_flags & IO_WQ_WORK_MM)) {
+		if (id->mm != current->mm)
+			return false;
+		mmgrab(id->mm);
+		req->work.flags |= IO_WQ_WORK_MM;
+	}
 
 	return true;
 }
@@ -1509,10 +1525,8 @@ static void io_prep_async_work(struct io_kiocb *req)
 {
 	const struct io_op_def *def = &io_op_defs[req->opcode];
 	struct io_ring_ctx *ctx = req->ctx;
-	struct io_identity *id;
 
 	io_req_init_async(req);
-	id = req->work.identity;
 
 	if (req->flags & REQ_F_FORCE_ASYNC)
 		req->work.flags |= IO_WQ_WORK_CONCURRENT;
@@ -1525,13 +1539,6 @@ static void io_prep_async_work(struct io_kiocb *req)
 			req->work.flags |= IO_WQ_WORK_UNBOUND;
 	}
 
-	/* ->mm can never change on us */
-	if (!(req->work.flags & IO_WQ_WORK_MM) &&
-	    (def->work_flags & IO_WQ_WORK_MM)) {
-		mmgrab(id->mm);
-		req->work.flags |= IO_WQ_WORK_MM;
-	}
-
 	/* if we fail grabbing identity, we must COW, regrab, and retry */
 	if (io_grab_identity(req))
 		return;
@@ -1633,19 +1640,38 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx)
 
 static void io_flush_timeouts(struct io_ring_ctx *ctx)
 {
-	while (!list_empty(&ctx->timeout_list)) {
+	u32 seq;
+
+	if (list_empty(&ctx->timeout_list))
+		return;
+
+	seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
+
+	do {
+		u32 events_needed, events_got;
 		struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
 						struct io_kiocb, timeout.list);
 
 		if (io_is_timeout_noseq(req))
 			break;
-		if (req->timeout.target_seq != ctx->cached_cq_tail
-					- atomic_read(&ctx->cq_timeouts))
+
+		/*
+		 * Since seq can easily wrap around over time, subtract
+		 * the last seq at which timeouts were flushed before comparing.
+		 * Assuming not more than 2^31-1 events have happened since,
+		 * these subtractions won't have wrapped, so we can check if
+		 * target is in [last_seq, current_seq] by comparing the two.
+		 */
+		events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush;
+		events_got = seq - ctx->cq_last_tm_flush;
+		if (events_got < events_needed)
 			break;
 
 		list_del_init(&req->timeout.list);
 		io_kill_timeout(req);
-	}
+	} while (!list_empty(&ctx->timeout_list));
+
+	ctx->cq_last_tm_flush = seq;
 }
 
 static void io_commit_cqring(struct io_ring_ctx *ctx)
@@ -1693,51 +1719,61 @@ static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx)
 	return io_wq_current_is_worker();
 }
 
+static inline unsigned __io_cqring_events(struct io_ring_ctx *ctx)
+{
+	return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head);
+}
+
 static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
 {
+	/* see waitqueue_active() comment */
+	smp_mb();
+
 	if (waitqueue_active(&ctx->wait))
 		wake_up(&ctx->wait);
 	if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait))
 		wake_up(&ctx->sq_data->wait);
 	if (io_should_trigger_evfd(ctx))
 		eventfd_signal(ctx->cq_ev_fd, 1);
+	if (waitqueue_active(&ctx->cq_wait)) {
+		wake_up_interruptible(&ctx->cq_wait);
+		kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
+	}
 }
 
-static void io_cqring_mark_overflow(struct io_ring_ctx *ctx)
+static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
 {
-	if (list_empty(&ctx->cq_overflow_list)) {
-		clear_bit(0, &ctx->sq_check_overflow);
-		clear_bit(0, &ctx->cq_check_overflow);
-		ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
+	/* see waitqueue_active() comment */
+	smp_mb();
+
+	if (ctx->flags & IORING_SETUP_SQPOLL) {
+		if (waitqueue_active(&ctx->wait))
+			wake_up(&ctx->wait);
+	}
+	if (io_should_trigger_evfd(ctx))
+		eventfd_signal(ctx->cq_ev_fd, 1);
+	if (waitqueue_active(&ctx->cq_wait)) {
+		wake_up_interruptible(&ctx->cq_wait);
+		kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
 	}
 }
 
 /* Returns true if there are no backlogged entries after the flush */
-static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
-				     struct task_struct *tsk,
-				     struct files_struct *files)
+static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
+				       struct task_struct *tsk,
+				       struct files_struct *files)
 {
 	struct io_rings *rings = ctx->rings;
 	struct io_kiocb *req, *tmp;
 	struct io_uring_cqe *cqe;
 	unsigned long flags;
+	bool all_flushed;
 	LIST_HEAD(list);
 
-	if (!force) {
-		if (list_empty_careful(&ctx->cq_overflow_list))
-			return true;
-		if ((ctx->cached_cq_tail - READ_ONCE(rings->cq.head) ==
-		    rings->cq_ring_entries))
-			return false;
-	}
+	if (!force && __io_cqring_events(ctx) == rings->cq_ring_entries)
+		return false;
 
 	spin_lock_irqsave(&ctx->completion_lock, flags);
-
-	/* if force is set, the ring is going away. always drop after that */
-	if (force)
-		ctx->cq_overflow_flushed = 1;
-
-	cqe = NULL;
 	list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) {
 		if (!io_match_task(req, tsk, files))
 			continue;
@@ -1758,9 +1794,14 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
 		}
 	}
 
-	io_commit_cqring(ctx);
-	io_cqring_mark_overflow(ctx);
+	all_flushed = list_empty(&ctx->cq_overflow_list);
+	if (all_flushed) {
+		clear_bit(0, &ctx->sq_check_overflow);
+		clear_bit(0, &ctx->cq_check_overflow);
+		ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
+	}
 
+	io_commit_cqring(ctx);
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 	io_cqring_ev_posted(ctx);
 
@@ -1770,7 +1811,21 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
 		io_put_req(req);
 	}
 
-	return cqe != NULL;
+	return all_flushed;
+}
+
+static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
+				     struct task_struct *tsk,
+				     struct files_struct *files)
+{
+	if (test_bit(0, &ctx->cq_check_overflow)) {
+		/* iopoll syncs against uring_lock, not completion_lock */
+		if (ctx->flags & IORING_SETUP_IOPOLL)
+			mutex_lock(&ctx->uring_lock);
+		__io_cqring_overflow_flush(ctx, force, tsk, files);
+		if (ctx->flags & IORING_SETUP_IOPOLL)
+			mutex_unlock(&ctx->uring_lock);
+	}
 }
 
 static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
@@ -2132,14 +2187,14 @@ static void __io_req_task_submit(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 
-	if (!__io_sq_thread_acquire_mm(ctx) &&
-	    !__io_sq_thread_acquire_files(ctx)) {
-		mutex_lock(&ctx->uring_lock);
+	mutex_lock(&ctx->uring_lock);
+	if (!ctx->sqo_dead &&
+	    !__io_sq_thread_acquire_mm(ctx) &&
+	    !__io_sq_thread_acquire_files(ctx))
 		__io_queue_sqe(req, NULL);
-		mutex_unlock(&ctx->uring_lock);
-	} else {
+	else
 		__io_req_task_cancel(req, -EFAULT);
-	}
+	mutex_unlock(&ctx->uring_lock);
 }
 
 static void io_req_task_submit(struct callback_head *cb)
@@ -2318,25 +2373,11 @@ static void io_double_put_req(struct io_kiocb *req)
 		io_free_req(req);
 }
 
-static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush)
+static unsigned io_cqring_events(struct io_ring_ctx *ctx)
 {
-	struct io_rings *rings = ctx->rings;
-
-	if (test_bit(0, &ctx->cq_check_overflow)) {
-		/*
-		 * noflush == true is from the waitqueue handler, just ensure
-		 * we wake up the task, and the next invocation will flush the
-		 * entries. We cannot safely to it from here.
-		 */
-		if (noflush)
-			return -1U;
-
-		io_cqring_overflow_flush(ctx, false, NULL, NULL);
-	}
-
 	/* See comment at the top of this file */
 	smp_rmb();
-	return ctx->cached_cq_tail - READ_ONCE(rings->cq.head);
+	return __io_cqring_events(ctx);
 }
 
 static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
@@ -2431,8 +2472,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 	}
 
 	io_commit_cqring(ctx);
-	if (ctx->flags & IORING_SETUP_SQPOLL)
-		io_cqring_ev_posted(ctx);
+	io_cqring_ev_posted_iopoll(ctx);
 	io_req_free_batch_finish(ctx, &rb);
 
 	if (!list_empty(&again))
@@ -2558,7 +2598,9 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
 		 * If we do, we can potentially be spinning for commands that
 		 * already triggered a CQE (eg in error).
 		 */
-		if (io_cqring_events(ctx, false))
+		if (test_bit(0, &ctx->cq_check_overflow))
+			__io_cqring_overflow_flush(ctx, false, NULL, NULL);
+		if (io_cqring_events(ctx))
 			break;
 
 		/*
@@ -2675,6 +2717,8 @@ static bool io_rw_reissue(struct io_kiocb *req, long res)
 	if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker())
 		return false;
 
+	lockdep_assert_held(&req->ctx->uring_lock);
+
 	ret = io_sq_thread_acquire_mm_files(req->ctx, req);
 
 	if (io_resubmit_prep(req, ret)) {
@@ -3136,9 +3180,7 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
 		iov[0].iov_len = kbuf->len;
 		return 0;
 	}
-	if (!req->rw.len)
-		return 0;
-	else if (req->rw.len > 1)
+	if (req->rw.len != 1)
 		return -EINVAL;
 
 #ifdef CONFIG_COMPAT
@@ -3784,6 +3826,8 @@ static int io_shutdown(struct io_kiocb *req, bool force_nonblock)
 		return -ENOTSOCK;
 
 	ret = __sys_shutdown_sock(sock, req->shutdown.how);
+	if (ret < 0)
+		req_set_fail_links(req);
 	io_req_complete(req, ret);
 	return 0;
 #else
@@ -5813,6 +5857,12 @@ static int io_timeout(struct io_kiocb *req)
 	tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
 	req->timeout.target_seq = tail + off;
 
+	/* Update the last seq here in case io_flush_timeouts() hasn't.
+	 * This is safe because ->completion_lock is held, and submissions
+	 * and completions are never mixed in the same ->completion_lock section.
+	 */
+	ctx->cq_last_tm_flush = tail;
+
 	/*
 	 * Insertion sort, ensuring the first entry in the list is always
 	 * the one we need first.
@@ -6107,15 +6157,15 @@ static void io_req_drop_files(struct io_kiocb *req)
 	struct io_uring_task *tctx = req->task->io_uring;
 	unsigned long flags;
 
+	put_files_struct(req->work.identity->files);
+	put_nsproxy(req->work.identity->nsproxy);
 	spin_lock_irqsave(&ctx->inflight_lock, flags);
 	list_del(&req->inflight_entry);
-	if (atomic_read(&tctx->in_idle))
-		wake_up(&tctx->wait);
 	spin_unlock_irqrestore(&ctx->inflight_lock, flags);
 	req->flags &= ~REQ_F_INFLIGHT;
-	put_files_struct(req->work.identity->files);
-	put_nsproxy(req->work.identity->nsproxy);
 	req->work.flags &= ~IO_WQ_WORK_FILES;
+	if (atomic_read(&tctx->in_idle))
+		wake_up(&tctx->wait);
 }
 
 static void __io_clean_op(struct io_kiocb *req)
@@ -6343,19 +6393,28 @@ static struct io_wq_work *io_wq_submit_work(struct io_wq_work *work)
 	}
 
 	if (ret) {
+		struct io_ring_ctx *lock_ctx = NULL;
+
+		if (req->ctx->flags & IORING_SETUP_IOPOLL)
+			lock_ctx = req->ctx;
+
 		/*
-		 * io_iopoll_complete() does not hold completion_lock to complete
-		 * polled io, so here for polled io, just mark it done and still let
-		 * io_iopoll_complete() complete it.
+		 * io_iopoll_complete() does not hold completion_lock to
+		 * complete polled io, so here for polled io, we can not call
+		 * io_req_complete() directly, otherwise there maybe concurrent
+		 * access to cqring, defer_list, etc, which is not safe. Given
+		 * that io_iopoll_complete() is always called under uring_lock,
+		 * so here for polled io, we also get uring_lock to complete
+		 * it.
 		 */
-		if (req->ctx->flags & IORING_SETUP_IOPOLL) {
-			struct kiocb *kiocb = &req->rw.kiocb;
+		if (lock_ctx)
+			mutex_lock(&lock_ctx->uring_lock);
 
-			kiocb_done(kiocb, ret, NULL);
-		} else {
-			req_set_fail_links(req);
-			io_req_complete(req, ret);
-		}
+		req_set_fail_links(req);
+		io_req_complete(req, ret);
+
+		if (lock_ctx)
+			mutex_unlock(&lock_ctx->uring_lock);
 	}
 
 	return io_steal_work(req);
@@ -6824,8 +6883,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
 
 	/* if we have a backlog and couldn't flush it all, return BUSY */
 	if (test_bit(0, &ctx->sq_check_overflow)) {
-		if (!list_empty(&ctx->cq_overflow_list) &&
-		    !io_cqring_overflow_flush(ctx, false, NULL, NULL))
+		if (!__io_cqring_overflow_flush(ctx, false, NULL, NULL))
 			return -EBUSY;
 	}
 
@@ -6927,7 +6985,8 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
 		if (!list_empty(&ctx->iopoll_list))
 			io_do_iopoll(ctx, &nr_events, 0);
 
-		if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)))
+		if (to_submit && !ctx->sqo_dead &&
+		    likely(!percpu_ref_is_dying(&ctx->refs)))
 			ret = io_submit_sqes(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
 	}
@@ -7028,6 +7087,7 @@ static int io_sq_thread(void *data)
 
 		if (sqt_spin || !time_after(jiffies, timeout)) {
 			io_run_task_work();
+			io_sq_thread_drop_mm_files();
 			cond_resched();
 			if (sqt_spin)
 				timeout = jiffies + sqd->sq_thread_idle;
@@ -7065,6 +7125,7 @@ static int io_sq_thread(void *data)
 	}
 
 	io_run_task_work();
+	io_sq_thread_drop_mm_files();
 
 	if (cur_css)
 		io_sq_thread_unassociate_blkcg();
@@ -7088,7 +7149,7 @@ struct io_wait_queue {
 	unsigned nr_timeouts;
 };
 
-static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush)
+static inline bool io_should_wake(struct io_wait_queue *iowq)
 {
 	struct io_ring_ctx *ctx = iowq->ctx;
 
@@ -7097,7 +7158,7 @@ static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush)
 	 * started waiting. For timeouts, we always want to return to userspace,
 	 * regardless of event count.
 	 */
-	return io_cqring_events(ctx, noflush) >= iowq->to_wait ||
+	return io_cqring_events(ctx) >= iowq->to_wait ||
 			atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
 }
 
@@ -7107,11 +7168,13 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
 	struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue,
 							wq);
 
-	/* use noflush == true, as we can't safely rely on locking context */
-	if (!io_should_wake(iowq, true))
-		return -1;
-
-	return autoremove_wake_function(curr, mode, wake_flags, key);
+	/*
+	 * Cannot safely flush overflowed CQEs from here, ensure we wake up
+	 * the task, and the next invocation will do it.
+	 */
+	if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->cq_check_overflow))
+		return autoremove_wake_function(curr, mode, wake_flags, key);
+	return -1;
 }
 
 static int io_run_task_work_sig(void)
@@ -7148,7 +7211,8 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	int ret = 0;
 
 	do {
-		if (io_cqring_events(ctx, false) >= min_events)
+		io_cqring_overflow_flush(ctx, false, NULL, NULL);
+		if (io_cqring_events(ctx) >= min_events)
 			return 0;
 		if (!io_run_task_work())
 			break;
@@ -7176,6 +7240,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
+		io_cqring_overflow_flush(ctx, false, NULL, NULL);
 		prepare_to_wait_exclusive(&ctx->wait, &iowq.wq,
 						TASK_INTERRUPTIBLE);
 		/* make sure we run task_work before checking for signals */
@@ -7184,8 +7249,10 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 			continue;
 		else if (ret < 0)
 			break;
-		if (io_should_wake(&iowq, false))
+		if (io_should_wake(&iowq))
 			break;
+		if (test_bit(0, &ctx->cq_check_overflow))
+			continue;
 		if (uts) {
 			timeout = schedule_timeout(timeout);
 			if (timeout == 0) {
@@ -7234,14 +7301,28 @@ static void io_file_ref_kill(struct percpu_ref *ref)
 	complete(&data->done);
 }
 
+static void io_sqe_files_set_node(struct fixed_file_data *file_data,
+				  struct fixed_file_ref_node *ref_node)
+{
+	spin_lock_bh(&file_data->lock);
+	file_data->node = ref_node;
+	list_add_tail(&ref_node->node, &file_data->ref_list);
+	spin_unlock_bh(&file_data->lock);
+	percpu_ref_get(&file_data->refs);
+}
+
 static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 {
 	struct fixed_file_data *data = ctx->file_data;
-	struct fixed_file_ref_node *ref_node = NULL;
+	struct fixed_file_ref_node *backup_node, *ref_node = NULL;
 	unsigned nr_tables, i;
+	int ret;
 
 	if (!data)
 		return -ENXIO;
+	backup_node = alloc_fixed_file_ref_node(ctx);
+	if (!backup_node)
+		return -ENOMEM;
 
 	spin_lock_bh(&data->lock);
 	ref_node = data->node;
@@ -7253,7 +7334,18 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 
 	/* wait for all refs nodes to complete */
 	flush_delayed_work(&ctx->file_put_work);
-	wait_for_completion(&data->done);
+	do {
+		ret = wait_for_completion_interruptible(&data->done);
+		if (!ret)
+			break;
+		ret = io_run_task_work_sig();
+		if (ret < 0) {
+			percpu_ref_resurrect(&data->refs);
+			reinit_completion(&data->done);
+			io_sqe_files_set_node(data, backup_node);
+			return ret;
+		}
+	} while (1);
 
 	__io_sqe_files_unregister(ctx);
 	nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE);
@@ -7264,6 +7356,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 	kfree(data);
 	ctx->file_data = NULL;
 	ctx->nr_user_files = 0;
+	destroy_fixed_file_ref_node(backup_node);
 	return 0;
 }
 
@@ -7657,12 +7750,12 @@ static struct fixed_file_ref_node *alloc_fixed_file_ref_node(
 
 	ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL);
 	if (!ref_node)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	if (percpu_ref_init(&ref_node->refs, io_file_data_ref_zero,
 			    0, GFP_KERNEL)) {
 		kfree(ref_node);
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 	}
 	INIT_LIST_HEAD(&ref_node->node);
 	INIT_LIST_HEAD(&ref_node->file_list);
@@ -7756,16 +7849,12 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 	}
 
 	ref_node = alloc_fixed_file_ref_node(ctx);
-	if (IS_ERR(ref_node)) {
+	if (!ref_node) {
 		io_sqe_files_unregister(ctx);
-		return PTR_ERR(ref_node);
+		return -ENOMEM;
 	}
 
-	file_data->node = ref_node;
-	spin_lock_bh(&file_data->lock);
-	list_add_tail(&ref_node->node, &file_data->ref_list);
-	spin_unlock_bh(&file_data->lock);
-	percpu_ref_get(&file_data->refs);
+	io_sqe_files_set_node(file_data, ref_node);
 	return ret;
 out_fput:
 	for (i = 0; i < ctx->nr_user_files; i++) {
@@ -7862,8 +7951,8 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 		return -EINVAL;
 
 	ref_node = alloc_fixed_file_ref_node(ctx);
-	if (IS_ERR(ref_node))
-		return PTR_ERR(ref_node);
+	if (!ref_node)
+		return -ENOMEM;
 
 	done = 0;
 	fds = u64_to_user_ptr(up->fds);
@@ -7921,11 +8010,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 
 	if (needs_switch) {
 		percpu_ref_kill(&data->node->refs);
-		spin_lock_bh(&data->lock);
-		list_add_tail(&ref_node->node, &data->ref_list);
-		data->node = ref_node;
-		spin_unlock_bh(&data->lock);
-		percpu_ref_get(&ctx->file_data->refs);
+		io_sqe_files_set_node(data, ref_node);
 	} else
 		destroy_fixed_file_ref_node(ref_node);
 
@@ -8155,10 +8240,13 @@ static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages,
 		__io_unaccount_mem(ctx->user, nr_pages);
 
 	if (ctx->mm_account) {
-		if (acct == ACCT_LOCKED)
+		if (acct == ACCT_LOCKED) {
+			mmap_write_lock(ctx->mm_account);
 			ctx->mm_account->locked_vm -= nr_pages;
-		else if (acct == ACCT_PINNED)
+			mmap_write_unlock(ctx->mm_account);
+		}else if (acct == ACCT_PINNED) {
 			atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm);
+		}
 	}
 }
 
@@ -8174,10 +8262,13 @@ static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages,
 	}
 
 	if (ctx->mm_account) {
-		if (acct == ACCT_LOCKED)
+		if (acct == ACCT_LOCKED) {
+			mmap_write_lock(ctx->mm_account);
 			ctx->mm_account->locked_vm += nr_pages;
-		else if (acct == ACCT_PINNED)
+			mmap_write_unlock(ctx->mm_account);
+		} else if (acct == ACCT_PINNED) {
 			atomic64_add(nr_pages, &ctx->mm_account->pinned_vm);
+		}
 	}
 
 	return 0;
@@ -8599,7 +8690,8 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
 	smp_rmb();
 	if (!io_sqring_full(ctx))
 		mask |= EPOLLOUT | EPOLLWRNORM;
-	if (io_cqring_events(ctx, false))
+	io_cqring_overflow_flush(ctx, false, NULL, NULL);
+	if (io_cqring_events(ctx))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	return mask;
@@ -8638,24 +8730,37 @@ static void io_ring_exit_work(struct work_struct *work)
 	 * as nobody else will be looking for them.
 	 */
 	do {
-		io_iopoll_try_reap_events(ctx);
+		__io_uring_cancel_task_requests(ctx, NULL);
 	} while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20));
 	io_ring_ctx_free(ctx);
 }
 
+static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
+{
+	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+	return req->ctx == data;
+}
+
 static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 {
 	mutex_lock(&ctx->uring_lock);
 	percpu_ref_kill(&ctx->refs);
+
+	if (WARN_ON_ONCE((ctx->flags & IORING_SETUP_SQPOLL) && !ctx->sqo_dead))
+		ctx->sqo_dead = 1;
+
+	/* if force is set, the ring is going away. always drop after that */
+	ctx->cq_overflow_flushed = 1;
 	if (ctx->rings)
-		io_cqring_overflow_flush(ctx, true, NULL, NULL);
+		__io_cqring_overflow_flush(ctx, true, NULL, NULL);
 	mutex_unlock(&ctx->uring_lock);
 
 	io_kill_timeouts(ctx, NULL, NULL);
 	io_poll_remove_all(ctx, NULL, NULL);
 
 	if (ctx->io_wq)
-		io_wq_cancel_all(ctx->io_wq);
+		io_wq_cancel_cb(ctx->io_wq, io_cancel_ctx_cb, ctx, true);
 
 	/* if we failed setting up the ctx, we might not have any rings */
 	io_iopoll_try_reap_events(ctx);
@@ -8784,9 +8889,11 @@ static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
 		enum io_wq_cancel cret;
 		bool ret = false;
 
-		cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true);
-		if (cret != IO_WQ_CANCEL_NOTFOUND)
-			ret = true;
+		if (ctx->io_wq) {
+			cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb,
+					       &cancel, true);
+			ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
+		}
 
 		/* SQPOLL thread does its own polling */
 		if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
@@ -8798,13 +8905,26 @@ static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
 
 		ret |= io_poll_remove_all(ctx, task, NULL);
 		ret |= io_kill_timeouts(ctx, task, NULL);
+		ret |= io_run_task_work();
 		if (!ret)
 			break;
-		io_run_task_work();
 		cond_resched();
 	}
 }
 
+static void io_disable_sqo_submit(struct io_ring_ctx *ctx)
+{
+	WARN_ON_ONCE(ctx->sqo_task != current);
+
+	mutex_lock(&ctx->uring_lock);
+	ctx->sqo_dead = 1;
+	mutex_unlock(&ctx->uring_lock);
+
+	/* make sure callers enter the ring to get error */
+	if (ctx->rings)
+		io_ring_set_wakeup_flag(ctx);
+}
+
 /*
  * We need to iteratively cancel requests, in case a request has dependent
  * hard links. These persist even for failure of cancelations, hence keep
@@ -8816,15 +8936,15 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
 	struct task_struct *task = current;
 
 	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
+		/* for SQPOLL only sqo_task has task notes */
+		io_disable_sqo_submit(ctx);
 		task = ctx->sq_data->thread;
 		atomic_inc(&task->io_uring->in_idle);
 		io_sq_thread_park(ctx->sq_data);
 	}
 
 	io_cancel_defer_files(ctx, task, files);
-	io_ring_submit_lock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
 	io_cqring_overflow_flush(ctx, true, task, files);
-	io_ring_submit_unlock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
 
 	if (!files)
 		__io_uring_cancel_task_requests(ctx, task);
@@ -8849,10 +8969,9 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
 static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
 {
 	struct io_uring_task *tctx = current->io_uring;
+	int ret;
 
 	if (unlikely(!tctx)) {
-		int ret;
-
 		ret = io_uring_alloc_task_context(current);
 		if (unlikely(ret))
 			return ret;
@@ -8863,7 +8982,12 @@ static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
 
 		if (!old) {
 			get_file(file);
-			xa_store(&tctx->xa, (unsigned long)file, file, GFP_KERNEL);
+			ret = xa_err(xa_store(&tctx->xa, (unsigned long)file,
+						file, GFP_KERNEL));
+			if (ret) {
+				fput(file);
+				return ret;
+			}
 		}
 		tctx->last = file;
 	}
@@ -8893,20 +9017,12 @@ static void io_uring_del_task_file(struct file *file)
 		fput(file);
 }
 
-/*
- * Drop task note for this file if we're the only ones that hold it after
- * pending fput()
- */
-static void io_uring_attempt_task_drop(struct file *file)
+static void io_uring_remove_task_files(struct io_uring_task *tctx)
 {
-	if (!current->io_uring)
-		return;
-	/*
-	 * fput() is pending, will be 2 if the only other ref is our potential
-	 * task file note. If the task is exiting, drop regardless of count.
-	 */
-	if (fatal_signal_pending(current) || (current->flags & PF_EXITING) ||
-	    atomic_long_read(&file->f_count) == 2)
+	struct file *file;
+	unsigned long index;
+
+	xa_for_each(&tctx->xa, index, file)
 		io_uring_del_task_file(file);
 }
 
@@ -8918,16 +9034,12 @@ void __io_uring_files_cancel(struct files_struct *files)
 
 	/* make sure overflow events are dropped */
 	atomic_inc(&tctx->in_idle);
-
-	xa_for_each(&tctx->xa, index, file) {
-		struct io_ring_ctx *ctx = file->private_data;
-
-		io_uring_cancel_task_requests(ctx, files);
-		if (files)
-			io_uring_del_task_file(file);
-	}
-
+	xa_for_each(&tctx->xa, index, file)
+		io_uring_cancel_task_requests(file->private_data, files);
 	atomic_dec(&tctx->in_idle);
+
+	if (files)
+		io_uring_remove_task_files(tctx);
 }
 
 static s64 tctx_inflight(struct io_uring_task *tctx)
@@ -8986,15 +9098,44 @@ void __io_uring_task_cancel(void)
 		if (inflight != tctx_inflight(tctx))
 			continue;
 		schedule();
+		finish_wait(&tctx->wait, &wait);
 	} while (1);
 
 	finish_wait(&tctx->wait, &wait);
 	atomic_dec(&tctx->in_idle);
+
+	io_uring_remove_task_files(tctx);
 }
 
 static int io_uring_flush(struct file *file, void *data)
 {
-	io_uring_attempt_task_drop(file);
+	struct io_uring_task *tctx = current->io_uring;
+	struct io_ring_ctx *ctx = file->private_data;
+
+	if (!tctx)
+		return 0;
+
+	/* we should have cancelled and erased it before PF_EXITING */
+	WARN_ON_ONCE((current->flags & PF_EXITING) &&
+		     xa_load(&tctx->xa, (unsigned long)file));
+
+	/*
+	 * fput() is pending, will be 2 if the only other ref is our potential
+	 * task file note. If the task is exiting, drop regardless of count.
+	 */
+	if (atomic_long_read(&file->f_count) != 2)
+		return 0;
+
+	if (ctx->flags & IORING_SETUP_SQPOLL) {
+		/* there is only one file note, which is owned by sqo_task */
+		WARN_ON_ONCE((ctx->sqo_task == current) ==
+			     !xa_load(&tctx->xa, (unsigned long)file));
+
+		io_disable_sqo_submit(ctx);
+	}
+
+	if (!(ctx->flags & IORING_SETUP_SQPOLL) || ctx->sqo_task == current)
+		io_uring_del_task_file(file);
 	return 0;
 }
 
@@ -9068,8 +9209,9 @@ static unsigned long io_uring_nommu_get_unmapped_area(struct file *file,
 
 #endif /* !CONFIG_MMU */
 
-static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
+static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
 {
+	int ret = 0;
 	DEFINE_WAIT(wait);
 
 	do {
@@ -9078,6 +9220,11 @@ static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
 
 		prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE);
 
+		if (unlikely(ctx->sqo_dead)) {
+			ret = -EOWNERDEAD;
+			goto out;
+		}
+
 		if (!io_sqring_full(ctx))
 			break;
 
@@ -9085,6 +9232,8 @@ static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
 	} while (!signal_pending(current));
 
 	finish_wait(&ctx->sqo_sq_wait, &wait);
+out:
+	return ret;
 }
 
 static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz,
@@ -9156,14 +9305,18 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	 */
 	ret = 0;
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
-		io_ring_submit_lock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
-		if (!list_empty_careful(&ctx->cq_overflow_list))
-			io_cqring_overflow_flush(ctx, false, NULL, NULL);
-		io_ring_submit_unlock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
+		io_cqring_overflow_flush(ctx, false, NULL, NULL);
+
+		ret = -EOWNERDEAD;
+		if (unlikely(ctx->sqo_dead))
+			goto out;
 		if (flags & IORING_ENTER_SQ_WAKEUP)
 			wake_up(&ctx->sq_data->wait);
-		if (flags & IORING_ENTER_SQ_WAIT)
-			io_sqpoll_wait_sq(ctx);
+		if (flags & IORING_ENTER_SQ_WAIT) {
+			ret = io_sqpoll_wait_sq(ctx);
+			if (ret)
+				goto out;
+		}
 		submitted = to_submit;
 	} else if (to_submit) {
 		ret = io_uring_add_task_file(ctx, f.file);
@@ -9369,55 +9522,52 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
 	return 0;
 }
 
+static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file)
+{
+	int ret, fd;
+
+	fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+	ret = io_uring_add_task_file(ctx, file);
+	if (ret) {
+		put_unused_fd(fd);
+		return ret;
+	}
+	fd_install(fd, file);
+	return fd;
+}
+
 /*
  * Allocate an anonymous fd, this is what constitutes the application
  * visible backing of an io_uring instance. The application mmaps this
  * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled,
  * we have to tie this fd to a socket for file garbage collection purposes.
  */
-static int io_uring_get_fd(struct io_ring_ctx *ctx)
+static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
 {
 	struct file *file;
+#if defined(CONFIG_UNIX)
 	int ret;
-	int fd;
 
-#if defined(CONFIG_UNIX)
 	ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP,
 				&ctx->ring_sock);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 #endif
 
-	ret = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
-	if (ret < 0)
-		goto err;
-	fd = ret;
-
 	file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx,
 					O_RDWR | O_CLOEXEC);
-	if (IS_ERR(file)) {
-		put_unused_fd(fd);
-		ret = PTR_ERR(file);
-		goto err;
-	}
-
 #if defined(CONFIG_UNIX)
-	ctx->ring_sock->file = file;
-#endif
-	ret = io_uring_add_task_file(ctx, file);
-	if (ret) {
-		fput(file);
-		put_unused_fd(fd);
-		goto err;
+	if (IS_ERR(file)) {
+		sock_release(ctx->ring_sock);
+		ctx->ring_sock = NULL;
+	} else {
+		ctx->ring_sock->file = file;
 	}
-	fd_install(fd, file);
-	return fd;
-err:
-#if defined(CONFIG_UNIX)
-	sock_release(ctx->ring_sock);
-	ctx->ring_sock = NULL;
 #endif
-	return ret;
+	return file;
 }
 
 static int io_uring_create(unsigned entries, struct io_uring_params *p,
@@ -9425,6 +9575,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 {
 	struct user_struct *user = NULL;
 	struct io_ring_ctx *ctx;
+	struct file *file;
 	bool limit_mem;
 	int ret;
 
@@ -9572,17 +9723,28 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
 		goto err;
 	}
 
+	file = io_uring_get_file(ctx);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto err;
+	}
+
 	/*
 	 * Install ring fd as the very last thing, so we don't risk someone
 	 * having closed it before we finish setup
 	 */
-	ret = io_uring_get_fd(ctx);
-	if (ret < 0)
-		goto err;
+	ret = io_uring_install_fd(ctx, file);
+	if (ret < 0) {
+		io_disable_sqo_submit(ctx);
+		/* fput will clean it up */
+		fput(file);
+		return ret;
+	}
 
 	trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
 	return ret;
 err:
+	io_disable_sqo_submit(ctx);
 	io_ring_ctx_wait_and_kill(ctx);
 	return ret;
 }
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 188f79d76988..2dc944442802 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1869,9 +1869,7 @@ static int load_superblock(journal_t *journal)
 
 	if (jbd2_has_feature_fast_commit(journal)) {
 		journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
-		num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks);
-		if (!num_fc_blocks)
-			num_fc_blocks = JBD2_MIN_FC_BLOCKS;
+		num_fc_blocks = jbd2_journal_get_num_fc_blks(sb);
 		if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS)
 			journal->j_last = journal->j_fc_last - num_fc_blocks;
 		journal->j_fc_first = journal->j_last + 1;
@@ -2102,9 +2100,7 @@ jbd2_journal_initialize_fast_commit(journal_t *journal)
 	journal_superblock_t *sb = journal->j_superblock;
 	unsigned long long num_fc_blks;
 
-	num_fc_blks = be32_to_cpu(sb->s_num_fc_blks);
-	if (num_fc_blks == 0)
-		num_fc_blks = JBD2_MIN_FC_BLOCKS;
+	num_fc_blks = jbd2_journal_get_num_fc_blks(sb);
 	if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS)
 		return -ENOSPC;
 
diff --git a/fs/namei.c b/fs/namei.c
index 03d0e11e4f36..78443a85480a 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2114,8 +2114,10 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 		return PTR_ERR(name);
 	while (*name=='/')
 		name++;
-	if (!*name)
+	if (!*name) {
+		nd->dir_mode = 0; // short-circuit the 'hardening' idiocy
 		return 0;
+	}
 
 	/* At this point we know we have a real path component. */
 	for(;;) {
diff --git a/fs/namespace.c b/fs/namespace.c
index 2b681f65ca04..9d33909d0f9e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -156,10 +156,10 @@ static inline void mnt_add_count(struct mount *mnt, int n)
 /*
  * vfsmount lock must be held for write
  */
-unsigned int mnt_get_count(struct mount *mnt)
+int mnt_get_count(struct mount *mnt)
 {
 #ifdef CONFIG_SMP
-	unsigned int count = 0;
+	int count = 0;
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
@@ -1139,6 +1139,7 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
 static void mntput_no_expire(struct mount *mnt)
 {
 	LIST_HEAD(list);
+	int count;
 
 	rcu_read_lock();
 	if (likely(READ_ONCE(mnt->mnt_ns))) {
@@ -1162,7 +1163,9 @@ static void mntput_no_expire(struct mount *mnt)
 	 */
 	smp_mb();
 	mnt_add_count(mnt, -1);
-	if (mnt_get_count(mnt)) {
+	count = mnt_get_count(mnt);
+	if (count != 0) {
+		WARN_ON(count < 0);
 		rcu_read_unlock();
 		unlock_mount_hash();
 		return;
@@ -1710,8 +1713,6 @@ static int can_umount(const struct path *path, int flags)
 {
 	struct mount *mnt = real_mount(path->mnt);
 
-	if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
-		return -EINVAL;
 	if (!may_mount())
 		return -EPERM;
 	if (path->dentry != path->mnt->mnt_root)
@@ -1725,6 +1726,7 @@ static int can_umount(const struct path *path, int flags)
 	return 0;
 }
 
+// caller is responsible for flags being sane
 int path_umount(struct path *path, int flags)
 {
 	struct mount *mnt = real_mount(path->mnt);
@@ -1746,6 +1748,10 @@ static int ksys_umount(char __user *name, int flags)
 	struct path path;
 	int ret;
 
+	// basic validity checks done first
+	if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
+		return -EINVAL;
+
 	if (!(flags & UMOUNT_NOFOLLOW))
 		lookup_flags |= LOOKUP_FOLLOW;
 	ret = user_path_at(AT_FDCWD, name, lookup_flags, &path);
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 816e1427f17e..04bf8066980c 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -1011,22 +1011,24 @@ nfs_delegation_find_inode_server(struct nfs_server *server,
 				 const struct nfs_fh *fhandle)
 {
 	struct nfs_delegation *delegation;
-	struct inode *freeme, *res = NULL;
+	struct super_block *freeme = NULL;
+	struct inode *res = NULL;
 
 	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
 		spin_lock(&delegation->lock);
 		if (delegation->inode != NULL &&
 		    !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) &&
 		    nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) {
-			freeme = igrab(delegation->inode);
-			if (freeme && nfs_sb_active(freeme->i_sb))
-				res = freeme;
+			if (nfs_sb_active(server->super)) {
+				freeme = server->super;
+				res = igrab(delegation->inode);
+			}
 			spin_unlock(&delegation->lock);
 			if (res != NULL)
 				return res;
 			if (freeme) {
 				rcu_read_unlock();
-				iput(freeme);
+				nfs_sb_deactive(freeme);
 				rcu_read_lock();
 			}
 			return ERR_PTR(-EAGAIN);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index b840d0a91c9d..62d3189745cd 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -136,9 +136,29 @@ struct nfs_fs_context {
 	} clone_data;
 };
 
-#define nfs_errorf(fc, fmt, ...) errorf(fc, fmt, ## __VA_ARGS__)
-#define nfs_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__)
-#define nfs_warnf(fc, fmt, ...) warnf(fc, fmt, ## __VA_ARGS__)
+#define nfs_errorf(fc, fmt, ...) ((fc)->log.log ?		\
+	errorf(fc, fmt, ## __VA_ARGS__) :			\
+	({ dprintk(fmt "\n", ## __VA_ARGS__); }))
+
+#define nfs_ferrorf(fc, fac, fmt, ...) ((fc)->log.log ?		\
+	errorf(fc, fmt, ## __VA_ARGS__) :			\
+	({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); }))
+
+#define nfs_invalf(fc, fmt, ...) ((fc)->log.log ?		\
+	invalf(fc, fmt, ## __VA_ARGS__) :			\
+	({ dprintk(fmt "\n", ## __VA_ARGS__);  -EINVAL; }))
+
+#define nfs_finvalf(fc, fac, fmt, ...) ((fc)->log.log ?		\
+	invalf(fc, fmt, ## __VA_ARGS__) :			\
+	({ dfprintk(fac, fmt "\n", ## __VA_ARGS__);  -EINVAL; }))
+
+#define nfs_warnf(fc, fmt, ...) ((fc)->log.log ?		\
+	warnf(fc, fmt, ## __VA_ARGS__) :			\
+	({ dprintk(fmt "\n", ## __VA_ARGS__); }))
+
+#define nfs_fwarnf(fc, fac, fmt, ...) ((fc)->log.log ?		\
+	warnf(fc, fmt, ## __VA_ARGS__) :			\
+	({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); }))
 
 static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc)
 {
@@ -579,12 +599,14 @@ extern void nfs4_test_session_trunk(struct rpc_clnt *clnt,
 
 static inline struct inode *nfs_igrab_and_active(struct inode *inode)
 {
-	inode = igrab(inode);
-	if (inode != NULL && !nfs_sb_active(inode->i_sb)) {
-		iput(inode);
-		inode = NULL;
+	struct super_block *sb = inode->i_sb;
+
+	if (sb && nfs_sb_active(sb)) {
+		if (igrab(inode))
+			return inode;
+		nfs_sb_deactive(sb);
 	}
-	return inode;
+	return NULL;
 }
 
 static inline void nfs_iput_and_deactive(struct inode *inode)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0ce04e0e5d82..2f4679a62712 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3536,10 +3536,8 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 	trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status);
 
 	/* Handle Layoutreturn errors */
-	if (pnfs_roc_done(task, calldata->inode,
-				&calldata->arg.lr_args,
-				&calldata->res.lr_res,
-				&calldata->res.lr_ret) == -EAGAIN)
+	if (pnfs_roc_done(task, &calldata->arg.lr_args, &calldata->res.lr_res,
+			  &calldata->res.lr_ret) == -EAGAIN)
 		goto out_restart;
 
 	/* hmm. we are done with the inode, and in the process of freeing
@@ -6384,10 +6382,8 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
 	trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status);
 
 	/* Handle Layoutreturn errors */
-	if (pnfs_roc_done(task, data->inode,
-				&data->args.lr_args,
-				&data->res.lr_res,
-				&data->res.lr_ret) == -EAGAIN)
+	if (pnfs_roc_done(task, &data->args.lr_args, &data->res.lr_res,
+			  &data->res.lr_ret) == -EAGAIN)
 		goto out_restart;
 
 	switch (task->tk_status) {
@@ -6441,10 +6437,10 @@ static void nfs4_delegreturn_release(void *calldata)
 	struct nfs4_delegreturndata *data = calldata;
 	struct inode *inode = data->inode;
 
+	if (data->lr.roc)
+		pnfs_roc_release(&data->lr.arg, &data->lr.res,
+				 data->res.lr_ret);
 	if (inode) {
-		if (data->lr.roc)
-			pnfs_roc_release(&data->lr.arg, &data->lr.res,
-					data->res.lr_ret);
 		nfs_post_op_update_inode_force_wcc(inode, &data->fattr);
 		nfs_iput_and_deactive(inode);
 	}
@@ -6520,16 +6516,14 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
 	nfs_fattr_init(data->res.fattr);
 	data->timestamp = jiffies;
 	data->rpc_status = 0;
-	data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, cred);
 	data->inode = nfs_igrab_and_active(inode);
-	if (data->inode) {
+	if (data->inode || issync) {
+		data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res,
+					cred);
 		if (data->lr.roc) {
 			data->args.lr_args = &data->lr.arg;
 			data->res.lr_res = &data->lr.res;
 		}
-	} else if (data->lr.roc) {
-		pnfs_roc_release(&data->lr.arg, &data->lr.res, 0);
-		data->lr.roc = false;
 	}
 
 	task_setup_data.callback_data = data;
@@ -7111,9 +7105,9 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 					data->arg.new_lock_owner, ret);
 	} else
 		data->cancelled = true;
+	trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
 	rpc_put_task(task);
 	dprintk("%s: done, ret = %d!\n", __func__, ret);
-	trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
 	return ret;
 }
 
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 984cc42ee54d..d09bcfd7db89 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -227,7 +227,7 @@ int nfs4_try_get_tree(struct fs_context *fc)
 			   fc, ctx->nfs_server.hostname,
 			   ctx->nfs_server.export_path);
 	if (err) {
-		nfs_errorf(fc, "NFS4: Couldn't follow remote path");
+		nfs_ferrorf(fc, MOUNT, "NFS4: Couldn't follow remote path");
 		dfprintk(MOUNT, "<-- nfs4_try_get_tree() = %d [error]\n", err);
 	} else {
 		dfprintk(MOUNT, "<-- nfs4_try_get_tree() = 0\n");
@@ -250,7 +250,7 @@ int nfs4_get_referral_tree(struct fs_context *fc)
 			    fc, ctx->nfs_server.hostname,
 			    ctx->nfs_server.export_path);
 	if (err) {
-		nfs_errorf(fc, "NFS4: Couldn't follow remote path");
+		nfs_ferrorf(fc, MOUNT, "NFS4: Couldn't follow remote path");
 		dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = %d [error]\n", err);
 	} else {
 		dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = 0\n");
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 07f59dc8cb2e..4f274f21c4ab 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1152,7 +1152,7 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
 	LIST_HEAD(freeme);
 
 	spin_lock(&inode->i_lock);
-	if (!pnfs_layout_is_valid(lo) || !arg_stateid ||
+	if (!pnfs_layout_is_valid(lo) ||
 	    !nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
 		goto out_unlock;
 	if (stateid) {
@@ -1509,10 +1509,8 @@ out_noroc:
 	return false;
 }
 
-int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
-		struct nfs4_layoutreturn_args **argpp,
-		struct nfs4_layoutreturn_res **respp,
-		int *ret)
+int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
+		  struct nfs4_layoutreturn_res **respp, int *ret)
 {
 	struct nfs4_layoutreturn_args *arg = *argpp;
 	int retval = -EAGAIN;
@@ -1545,7 +1543,7 @@ int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
 		return 0;
 	case -NFS4ERR_OLD_STATEID:
 		if (!nfs4_layout_refresh_old_stateid(&arg->stateid,
-					&arg->range, inode))
+						     &arg->range, arg->inode))
 			break;
 		*ret = -NFS4ERR_NOMATCHING_LAYOUT;
 		return -EAGAIN;
@@ -1560,23 +1558,28 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
 		int ret)
 {
 	struct pnfs_layout_hdr *lo = args->layout;
-	const nfs4_stateid *arg_stateid = NULL;
+	struct inode *inode = args->inode;
 	const nfs4_stateid *res_stateid = NULL;
 	struct nfs4_xdr_opaque_data *ld_private = args->ld_private;
 
 	switch (ret) {
 	case -NFS4ERR_NOMATCHING_LAYOUT:
+		spin_lock(&inode->i_lock);
+		if (pnfs_layout_is_valid(lo) &&
+		    nfs4_stateid_match_other(&args->stateid, &lo->plh_stateid))
+			pnfs_set_plh_return_info(lo, args->range.iomode, 0);
+		pnfs_clear_layoutreturn_waitbit(lo);
+		spin_unlock(&inode->i_lock);
 		break;
 	case 0:
 		if (res->lrs_present)
 			res_stateid = &res->stateid;
 		fallthrough;
 	default:
-		arg_stateid = &args->stateid;
+		pnfs_layoutreturn_free_lsegs(lo, &args->stateid, &args->range,
+					     res_stateid);
 	}
 	trace_nfs4_layoutreturn_on_close(args->inode, &args->stateid, ret);
-	pnfs_layoutreturn_free_lsegs(lo, arg_stateid, &args->range,
-			res_stateid);
 	if (ld_private && ld_private->ops && ld_private->ops->free)
 		ld_private->ops->free(ld_private);
 	pnfs_put_layout_hdr(lo);
@@ -2015,6 +2018,27 @@ lookup_again:
 		goto lookup_again;
 	}
 
+	/*
+	 * Because we free lsegs when sending LAYOUTRETURN, we need to wait
+	 * for LAYOUTRETURN.
+	 */
+	if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
+		spin_unlock(&ino->i_lock);
+		dprintk("%s wait for layoutreturn\n", __func__);
+		lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
+		if (!IS_ERR(lseg)) {
+			pnfs_put_layout_hdr(lo);
+			dprintk("%s retrying\n", __func__);
+			trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+						 lseg,
+						 PNFS_UPDATE_LAYOUT_RETRY);
+			goto lookup_again;
+		}
+		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+					 PNFS_UPDATE_LAYOUT_RETURN);
+		goto out_put_layout_hdr;
+	}
+
 	lseg = pnfs_find_lseg(lo, &arg, strict_iomode);
 	if (lseg) {
 		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
@@ -2067,28 +2091,6 @@ lookup_again:
 		nfs4_stateid_copy(&stateid, &lo->plh_stateid);
 	}
 
-	/*
-	 * Because we free lsegs before sending LAYOUTRETURN, we need to wait
-	 * for LAYOUTRETURN even if first is true.
-	 */
-	if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
-		spin_unlock(&ino->i_lock);
-		dprintk("%s wait for layoutreturn\n", __func__);
-		lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
-		if (!IS_ERR(lseg)) {
-			if (first)
-				pnfs_clear_first_layoutget(lo);
-			pnfs_put_layout_hdr(lo);
-			dprintk("%s retrying\n", __func__);
-			trace_pnfs_update_layout(ino, pos, count, iomode, lo,
-					lseg, PNFS_UPDATE_LAYOUT_RETRY);
-			goto lookup_again;
-		}
-		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
-				PNFS_UPDATE_LAYOUT_RETURN);
-		goto out_put_layout_hdr;
-	}
-
 	if (pnfs_layoutgets_blocked(lo)) {
 		trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
 				PNFS_UPDATE_LAYOUT_BLOCKED);
@@ -2242,6 +2244,7 @@ static void _lgopen_prepare_attached(struct nfs4_opendata *data,
 					     &rng, GFP_KERNEL);
 	if (!lgp) {
 		pnfs_clear_first_layoutget(lo);
+		nfs_layoutget_end(lo);
 		pnfs_put_layout_hdr(lo);
 		return;
 	}
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index bbd3de1025f2..d810ae674f4e 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -297,10 +297,8 @@ bool pnfs_roc(struct inode *ino,
 		struct nfs4_layoutreturn_args *args,
 		struct nfs4_layoutreturn_res *res,
 		const struct cred *cred);
-int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
-		struct nfs4_layoutreturn_args **argpp,
-		struct nfs4_layoutreturn_res **respp,
-		int *ret);
+int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
+		  struct nfs4_layoutreturn_res **respp, int *ret);
 void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
 		struct nfs4_layoutreturn_res *res,
 		int ret);
@@ -772,7 +770,7 @@ pnfs_roc(struct inode *ino,
 }
 
 static inline int
-pnfs_roc_done(struct rpc_task *task, struct inode *inode,
+pnfs_roc_done(struct rpc_task *task,
 		struct nfs4_layoutreturn_args **argpp,
 		struct nfs4_layoutreturn_res **respp,
 		int *ret)
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 2efcfdd348a1..49d3389bd813 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -78,22 +78,18 @@ void
 pnfs_generic_clear_request_commit(struct nfs_page *req,
 				  struct nfs_commit_info *cinfo)
 {
-	struct pnfs_layout_segment *freeme = NULL;
+	struct pnfs_commit_bucket *bucket = NULL;
 
 	if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
 		goto out;
 	cinfo->ds->nwritten--;
-	if (list_is_singular(&req->wb_list)) {
-		struct pnfs_commit_bucket *bucket;
-
+	if (list_is_singular(&req->wb_list))
 		bucket = list_first_entry(&req->wb_list,
-					  struct pnfs_commit_bucket,
-					  written);
-		freeme = pnfs_free_bucket_lseg(bucket);
-	}
+					  struct pnfs_commit_bucket, written);
 out:
 	nfs_request_remove_commit_list(req, cinfo);
-	pnfs_put_lseg(freeme);
+	if (bucket)
+		pnfs_put_lseg(pnfs_free_bucket_lseg(bucket));
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit);
 
@@ -407,12 +403,16 @@ pnfs_bucket_get_committing(struct list_head *head,
 			   struct pnfs_commit_bucket *bucket,
 			   struct nfs_commit_info *cinfo)
 {
+	struct pnfs_layout_segment *lseg;
 	struct list_head *pos;
 
 	list_for_each(pos, &bucket->committing)
 		cinfo->ds->ncommitting--;
 	list_splice_init(&bucket->committing, head);
-	return pnfs_free_bucket_lseg(bucket);
+	lseg = pnfs_free_bucket_lseg(bucket);
+	if (!lseg)
+		lseg = pnfs_get_lseg(bucket->lseg);
+	return lseg;
 }
 
 static struct nfs_commit_data *
@@ -424,8 +424,6 @@ pnfs_bucket_fetch_commitdata(struct pnfs_commit_bucket *bucket,
 	if (!data)
 		return NULL;
 	data->lseg = pnfs_bucket_get_committing(&data->pages, bucket, cinfo);
-	if (!data->lseg)
-		data->lseg = pnfs_get_lseg(bucket->lseg);
 	return data;
 }
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 4727b7f03c5b..8d6d2678abad 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -50,6 +50,11 @@
 #include "pnfs.h"
 #include "trace.h"
 
+static bool inter_copy_offload_enable;
+module_param(inter_copy_offload_enable, bool, 0644);
+MODULE_PARM_DESC(inter_copy_offload_enable,
+		 "Enable inter server to server copy offload. Default: false");
+
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 45ee6b12ce5b..eaaa1605b5b5 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -147,6 +147,25 @@ svcxdr_dupstr(struct nfsd4_compoundargs *argp, void *buf, u32 len)
 	return p;
 }
 
+static void *
+svcxdr_savemem(struct nfsd4_compoundargs *argp, __be32 *p, u32 len)
+{
+	__be32 *tmp;
+
+	/*
+	 * The location of the decoded data item is stable,
+	 * so @p is OK to use. This is the common case.
+	 */
+	if (p != argp->xdr->scratch.iov_base)
+		return p;
+
+	tmp = svcxdr_tmpalloc(argp, len);
+	if (!tmp)
+		return NULL;
+	memcpy(tmp, p, len);
+	return tmp;
+}
+
 /*
  * NFSv4 basic data type decoders
  */
@@ -183,11 +202,10 @@ nfsd4_decode_opaque(struct nfsd4_compoundargs *argp, struct xdr_netobj *o)
 	p = xdr_inline_decode(argp->xdr, len);
 	if (!p)
 		return nfserr_bad_xdr;
-	o->data = svcxdr_tmpalloc(argp, len);
+	o->data = svcxdr_savemem(argp, p, len);
 	if (!o->data)
 		return nfserr_jukebox;
 	o->len = len;
-	memcpy(o->data, p, len);
 
 	return nfs_ok;
 }
@@ -205,10 +223,9 @@ nfsd4_decode_component4(struct nfsd4_compoundargs *argp, char **namp, u32 *lenp)
 	status = check_filename((char *)p, *lenp);
 	if (status)
 		return status;
-	*namp = svcxdr_tmpalloc(argp, *lenp);
+	*namp = svcxdr_savemem(argp, p, *lenp);
 	if (!*namp)
 		return nfserr_jukebox;
-	memcpy(*namp, p, *lenp);
 
 	return nfs_ok;
 }
@@ -1200,10 +1217,9 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh)
 	p = xdr_inline_decode(argp->xdr, putfh->pf_fhlen);
 	if (!p)
 		return nfserr_bad_xdr;
-	putfh->pf_fhval = svcxdr_tmpalloc(argp, putfh->pf_fhlen);
+	putfh->pf_fhval = svcxdr_savemem(argp, p, putfh->pf_fhlen);
 	if (!putfh->pf_fhval)
 		return nfserr_jukebox;
-	memcpy(putfh->pf_fhval, p, putfh->pf_fhlen);
 
 	return nfs_ok;
 }
@@ -1318,24 +1334,20 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient
 	p = xdr_inline_decode(argp->xdr, setclientid->se_callback_netid_len);
 	if (!p)
 		return nfserr_bad_xdr;
-	setclientid->se_callback_netid_val = svcxdr_tmpalloc(argp,
+	setclientid->se_callback_netid_val = svcxdr_savemem(argp, p,
 						setclientid->se_callback_netid_len);
 	if (!setclientid->se_callback_netid_val)
 		return nfserr_jukebox;
-	memcpy(setclientid->se_callback_netid_val, p,
-	       setclientid->se_callback_netid_len);
 
 	if (xdr_stream_decode_u32(argp->xdr, &setclientid->se_callback_addr_len) < 0)
 		return nfserr_bad_xdr;
 	p = xdr_inline_decode(argp->xdr, setclientid->se_callback_addr_len);
 	if (!p)
 		return nfserr_bad_xdr;
-	setclientid->se_callback_addr_val = svcxdr_tmpalloc(argp,
+	setclientid->se_callback_addr_val = svcxdr_savemem(argp, p,
 						setclientid->se_callback_addr_len);
 	if (!setclientid->se_callback_addr_val)
 		return nfserr_jukebox;
-	memcpy(setclientid->se_callback_addr_val, p,
-	       setclientid->se_callback_addr_len);
 	if (xdr_stream_decode_u32(argp->xdr, &setclientid->se_callback_ident) < 0)
 		return nfserr_bad_xdr;
 
@@ -1375,10 +1387,9 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify
 	p = xdr_inline_decode(argp->xdr, verify->ve_attrlen);
 	if (!p)
 		return nfserr_bad_xdr;
-	verify->ve_attrval = svcxdr_tmpalloc(argp, verify->ve_attrlen);
+	verify->ve_attrval = svcxdr_savemem(argp, p, verify->ve_attrlen);
 	if (!verify->ve_attrval)
 		return nfserr_jukebox;
-	memcpy(verify->ve_attrval, p, verify->ve_attrlen);
 
 	return nfs_ok;
 }
@@ -2333,10 +2344,9 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 		p = xdr_inline_decode(argp->xdr, argp->taglen);
 		if (!p)
 			return 0;
-		argp->tag = svcxdr_tmpalloc(argp, argp->taglen);
+		argp->tag = svcxdr_savemem(argp, p, argp->taglen);
 		if (!argp->tag)
 			return 0;
-		memcpy(argp->tag, p, argp->taglen);
 		max_reply += xdr_align_size(argp->taglen);
 	}
 
@@ -4756,6 +4766,7 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
 			    resp->rqstp->rq_vec, read->rd_vlen, maxcount, eof);
 	if (nfserr)
 		return nfserr;
+	xdr_truncate_encode(xdr, starting_len + 16 + xdr_align_size(*maxcount));
 
 	tmp = htonl(NFS4_CONTENT_DATA);
 	write_bytes_to_xdr_buf(xdr->buf, starting_len,      &tmp,   4);
@@ -4763,6 +4774,10 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
 	write_bytes_to_xdr_buf(xdr->buf, starting_len + 4,  &tmp64, 8);
 	tmp = htonl(*maxcount);
 	write_bytes_to_xdr_buf(xdr->buf, starting_len + 12, &tmp,   4);
+
+	tmp = xdr_zero;
+	write_bytes_to_xdr_buf(xdr->buf, starting_len + 16 + *maxcount, &tmp,
+			       xdr_pad_size(*maxcount));
 	return nfs_ok;
 }
 
@@ -4855,14 +4870,15 @@ out:
 	if (nfserr && segments == 0)
 		xdr_truncate_encode(xdr, starting_len);
 	else {
-		tmp = htonl(eof);
-		write_bytes_to_xdr_buf(xdr->buf, starting_len,     &tmp, 4);
-		tmp = htonl(segments);
-		write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4);
 		if (nfserr) {
 			xdr_truncate_encode(xdr, last_segment);
 			nfserr = nfs_ok;
+			eof = 0;
 		}
+		tmp = htonl(eof);
+		write_bytes_to_xdr_buf(xdr->buf, starting_len,     &tmp, 4);
+		tmp = htonl(segments);
+		write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4);
 	}
 
 	return nfserr;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 00384c332f9b..f9c9f4c63cc7 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -33,12 +33,6 @@
 
 #define NFSDDBG_FACILITY	NFSDDBG_SVC
 
-bool inter_copy_offload_enable;
-EXPORT_SYMBOL_GPL(inter_copy_offload_enable);
-module_param(inter_copy_offload_enable, bool, 0644);
-MODULE_PARM_DESC(inter_copy_offload_enable,
-		 "Enable inter server to server copy offload. Default: false");
-
 extern struct svc_program	nfsd_program;
 static int			nfsd(void *vrqstp);
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index a60ff5ce1a37..c300885ae75d 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -568,7 +568,6 @@ struct nfsd4_copy {
 	struct nfs_fh		c_fh;
 	nfs4_stateid		stateid;
 };
-extern bool inter_copy_offload_enable;
 
 struct nfsd4_seek {
 	/* request */
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 3e01d8f2ab90..dcab112e1f00 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1285,26 +1285,23 @@ fput_and_out:
 	return ret;
 }
 
+#ifndef CONFIG_ARCH_SPLIT_ARG64
 SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
 			      __u64, mask, int, dfd,
 			      const char  __user *, pathname)
 {
 	return do_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname);
 }
+#endif
 
-#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE6(fanotify_mark,
+#if defined(CONFIG_ARCH_SPLIT_ARG64) || defined(CONFIG_COMPAT)
+SYSCALL32_DEFINE6(fanotify_mark,
 				int, fanotify_fd, unsigned int, flags,
-				__u32, mask0, __u32, mask1, int, dfd,
+				SC_ARG64(mask), int, dfd,
 				const char  __user *, pathname)
 {
-	return do_fanotify_mark(fanotify_fd, flags,
-#ifdef __BIG_ENDIAN
-				((__u64)mask0 << 32) | mask1,
-#else
-				((__u64)mask1 << 32) | mask0,
-#endif
-				 dfd, pathname);
+	return do_fanotify_mark(fanotify_fd, flags, SC_VAL64(__u64, mask),
+				dfd, pathname);
 }
 #endif
 
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index af375e049aae..ec8ae4257975 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -663,6 +663,8 @@ const struct file_operations orangefs_file_operations = {
 	.unlocked_ioctl	= orangefs_ioctl,
 	.mmap		= orangefs_file_mmap,
 	.open		= generic_file_open,
+	.splice_read    = generic_file_splice_read,
+	.splice_write   = iter_file_splice_write,
 	.flush		= orangefs_flush,
 	.release	= orangefs_file_release,
 	.fsync		= orangefs_fsync,
diff --git a/fs/pnode.h b/fs/pnode.h
index 49a058c73e4c..26f74e092bd9 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -44,7 +44,7 @@ int propagate_mount_busy(struct mount *, int);
 void propagate_mount_unlock(struct mount *);
 void mnt_release_group_id(struct mount *);
 int get_dominating_id(struct mount *mnt, const struct path *root);
-unsigned int mnt_get_count(struct mount *mnt);
+int mnt_get_count(struct mount *mnt);
 void mnt_set_mountpoint(struct mount *, struct mountpoint *,
 			struct mount *);
 void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ee5a235b3056..602e3a52884d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1035,6 +1035,25 @@ struct clear_refs_private {
 };
 
 #ifdef CONFIG_MEM_SOFT_DIRTY
+
+#define is_cow_mapping(flags) (((flags) & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE)
+
+static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
+{
+	struct page *page;
+
+	if (!pte_write(pte))
+		return false;
+	if (!is_cow_mapping(vma->vm_flags))
+		return false;
+	if (likely(!atomic_read(&vma->vm_mm->has_pinned)))
+		return false;
+	page = vm_normal_page(vma, addr, pte);
+	if (!page)
+		return false;
+	return page_maybe_dma_pinned(page);
+}
+
 static inline void clear_soft_dirty(struct vm_area_struct *vma,
 		unsigned long addr, pte_t *pte)
 {
@@ -1049,6 +1068,8 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 	if (pte_present(ptent)) {
 		pte_t old_pte;
 
+		if (pte_is_pinned(vma, addr, ptent))
+			return;
 		old_pte = ptep_modify_prot_start(vma, addr, pte);
 		ptent = pte_wrprotect(old_pte);
 		ptent = pte_clear_soft_dirty(ptent);
@@ -1215,41 +1236,26 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			.type = type,
 		};
 
+		if (mmap_write_lock_killable(mm)) {
+			count = -EINTR;
+			goto out_mm;
+		}
 		if (type == CLEAR_REFS_MM_HIWATER_RSS) {
-			if (mmap_write_lock_killable(mm)) {
-				count = -EINTR;
-				goto out_mm;
-			}
-
 			/*
 			 * Writing 5 to /proc/pid/clear_refs resets the peak
 			 * resident set size to this mm's current rss value.
 			 */
 			reset_mm_hiwater_rss(mm);
-			mmap_write_unlock(mm);
-			goto out_mm;
+			goto out_unlock;
 		}
 
-		if (mmap_read_lock_killable(mm)) {
-			count = -EINTR;
-			goto out_mm;
-		}
 		tlb_gather_mmu(&tlb, mm, 0, -1);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			for (vma = mm->mmap; vma; vma = vma->vm_next) {
 				if (!(vma->vm_flags & VM_SOFTDIRTY))
 					continue;
-				mmap_read_unlock(mm);
-				if (mmap_write_lock_killable(mm)) {
-					count = -EINTR;
-					goto out_mm;
-				}
-				for (vma = mm->mmap; vma; vma = vma->vm_next) {
-					vma->vm_flags &= ~VM_SOFTDIRTY;
-					vma_set_page_prot(vma);
-				}
-				mmap_write_downgrade(mm);
-				break;
+				vma->vm_flags &= ~VM_SOFTDIRTY;
+				vma_set_page_prot(vma);
 			}
 
 			mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY,
@@ -1261,7 +1267,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		if (type == CLEAR_REFS_SOFT_DIRTY)
 			mmu_notifier_invalidate_range_end(&range);
 		tlb_finish_mmu(&tlb, 0, -1);
-		mmap_read_unlock(mm);
+out_unlock:
+		mmap_write_unlock(mm);
 out_mm:
 		mmput(mm);
 	}
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index e59d4bb3a89e..eafb75755fa3 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -320,7 +320,8 @@ static int mountstats_open(struct inode *inode, struct file *file)
 
 const struct file_operations proc_mounts_operations = {
 	.open		= mounts_open,
-	.read		= seq_read,
+	.read_iter	= seq_read_iter,
+	.splice_read	= generic_file_splice_read,
 	.llseek		= seq_lseek,
 	.release	= mounts_release,
 	.poll		= mounts_poll,
@@ -328,7 +329,8 @@ const struct file_operations proc_mounts_operations = {
 
 const struct file_operations proc_mountinfo_operations = {
 	.open		= mountinfo_open,
-	.read		= seq_read,
+	.read_iter	= seq_read_iter,
+	.splice_read	= generic_file_splice_read,
 	.llseek		= seq_lseek,
 	.release	= mounts_release,
 	.poll		= mounts_poll,
@@ -336,7 +338,8 @@ const struct file_operations proc_mountinfo_operations = {
 
 const struct file_operations proc_mountstats_operations = {
 	.open		= mountstats_open,
-	.read		= seq_read,
+	.read_iter	= seq_read_iter,
+	.splice_read	= generic_file_splice_read,
 	.llseek		= seq_lseek,
 	.release	= mounts_release,
 };
diff --git a/fs/select.c b/fs/select.c
index ebfebdfe5c69..37aaa8317f3a 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -1011,14 +1011,17 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 	fdcount = do_poll(head, &table, end_time);
 	poll_freewait(&table);
 
+	if (!user_write_access_begin(ufds, nfds * sizeof(*ufds)))
+		goto out_fds;
+
 	for (walk = head; walk; walk = walk->next) {
 		struct pollfd *fds = walk->entries;
 		int j;
 
-		for (j = 0; j < walk->len; j++, ufds++)
-			if (__put_user(fds[j].revents, &ufds->revents))
-				goto out_fds;
+		for (j = walk->len; j; fds++, ufds++, j--)
+			unsafe_put_user(fds->revents, &ufds->revents, Efault);
   	}
+	user_write_access_end();
 
 	err = fdcount;
 out_fds:
@@ -1030,6 +1033,11 @@ out_fds:
 	}
 
 	return err;
+
+Efault:
+	user_write_access_end();
+	err = -EFAULT;
+	goto out_fds;
 }
 
 static long do_restart_poll(struct restart_block *restart_block)
diff --git a/fs/zonefs/Kconfig b/fs/zonefs/Kconfig
index ef2697b78820..827278f937fe 100644
--- a/fs/zonefs/Kconfig
+++ b/fs/zonefs/Kconfig
@@ -3,6 +3,7 @@ config ZONEFS_FS
 	depends on BLOCK
 	depends on BLK_DEV_ZONED
 	select FS_IOMAP
+	select CRC32
 	help
 	  zonefs is a simple file system which exposes zones of a zoned block
 	  device (e.g. host-managed or host-aware SMR disk drives) as files.
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index a6a9373ab863..232838d28f50 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -124,11 +124,10 @@ struct cppc_perf_fb_ctrs {
 
 /* Per CPU container for runtime CPPC management. */
 struct cppc_cpudata {
-	int cpu;
+	struct list_head node;
 	struct cppc_perf_caps perf_caps;
 	struct cppc_perf_ctrls perf_ctrls;
 	struct cppc_perf_fb_ctrs perf_fb_ctrs;
-	struct cpufreq_policy *cur_policy;
 	unsigned int shared_type;
 	cpumask_var_t shared_cpu_map;
 };
@@ -137,7 +136,8 @@ extern int cppc_get_desired_perf(int cpunum, u64 *desired_perf);
 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_get_perf_caps(int cpu, struct cppc_perf_caps *caps);
-extern int acpi_get_psd_map(struct cppc_cpudata **);
+extern bool acpi_cpc_valid(void);
+extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data);
 extern unsigned int cppc_get_transition_latency(int cpu);
 extern bool cpc_ffh_supported(void);
 extern int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val);
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 4365b9aa3e3f..267f6dfb8960 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -34,6 +34,7 @@ mandatory-y += kmap_size.h
 mandatory-y += kprobes.h
 mandatory-y += linkage.h
 mandatory-y += local.h
+mandatory-y += local64.h
 mandatory-y += mm-arch-hooks.h
 mandatory-y += mmiowb.h
 mandatory-y += mmu.h
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index dd90c9792909..0e7316a86240 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -11,19 +11,19 @@
  * See Documentation/atomic_bitops.txt for details.
  */
 
-static inline void set_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void set_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
 	atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-static inline void clear_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void clear_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
 	atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-static inline void change_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void change_bit(unsigned int nr, volatile unsigned long *p)
 {
 	p += BIT_WORD(nr);
 	atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
diff --git a/include/dt-bindings/clock/at91.h b/include/dt-bindings/clock/at91.h
index eba17106608b..98e1b2ab6403 100644
--- a/include/dt-bindings/clock/at91.h
+++ b/include/dt-bindings/clock/at91.h
@@ -25,6 +25,17 @@
 #define PMC_PLLBCK		8
 #define PMC_AUDIOPLLCK		9
 
+/* SAMA7G5 */
+#define PMC_CPUPLL		(PMC_MAIN + 1)
+#define PMC_SYSPLL		(PMC_MAIN + 2)
+#define PMC_DDRPLL		(PMC_MAIN + 3)
+#define PMC_IMGPLL		(PMC_MAIN + 4)
+#define PMC_BAUDPLL		(PMC_MAIN + 5)
+#define PMC_AUDIOPMCPLL		(PMC_MAIN + 6)
+#define PMC_AUDIOIOPLL		(PMC_MAIN + 7)
+#define PMC_ETHPLL		(PMC_MAIN + 8)
+#define PMC_CPU			(PMC_MAIN + 9)
+
 #ifndef AT91_PMC_MOSCS
 #define AT91_PMC_MOSCS		0		/* MOSCS Flag */
 #define AT91_PMC_LOCKA		1		/* PLLA Lock */
diff --git a/include/dt-bindings/clock/fsl,qoriq-clockgen.h b/include/dt-bindings/clock/fsl,qoriq-clockgen.h
new file mode 100644
index 000000000000..ddec7d0bdc7f
--- /dev/null
+++ b/include/dt-bindings/clock/fsl,qoriq-clockgen.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef DT_CLOCK_FSL_QORIQ_CLOCKGEN_H
+#define DT_CLOCK_FSL_QORIQ_CLOCKGEN_H
+
+#define QORIQ_CLK_SYSCLK	0
+#define QORIQ_CLK_CMUX		1
+#define QORIQ_CLK_HWACCEL	2
+#define QORIQ_CLK_FMAN		3
+#define QORIQ_CLK_PLATFORM_PLL	4
+#define QORIQ_CLK_CORECLK	5
+
+#define QORIQ_CLK_PLL_DIV(x)	((x) - 1)
+
+#endif /* DT_CLOCK_FSL_QORIQ_CLOCKGEN_H */
diff --git a/include/dt-bindings/clock/g12a-clkc.h b/include/dt-bindings/clock/g12a-clkc.h
index 40d49940d8a8..a93b58c5e18e 100644
--- a/include/dt-bindings/clock/g12a-clkc.h
+++ b/include/dt-bindings/clock/g12a-clkc.h
@@ -147,5 +147,7 @@
 #define CLKID_SPICC1_SCLK			261
 #define CLKID_NNA_AXI_CLK			264
 #define CLKID_NNA_CORE_CLK			267
+#define CLKID_MIPI_DSI_PXCLK_SEL		269
+#define CLKID_MIPI_DSI_PXCLK			270
 
 #endif /* __G12A_CLKC_H */
diff --git a/include/dt-bindings/clock/k210-clk.h b/include/dt-bindings/clock/k210-clk.h
index 5a2fd64d1a49..a48176ad3c23 100644
--- a/include/dt-bindings/clock/k210-clk.h
+++ b/include/dt-bindings/clock/k210-clk.h
@@ -3,18 +3,52 @@
  * Copyright (C) 2019-20 Sean Anderson <seanga2@gmail.com>
  * Copyright (c) 2020 Western Digital Corporation or its affiliates.
  */
-#ifndef K210_CLK_H
-#define K210_CLK_H
+#ifndef CLOCK_K210_CLK_H
+#define CLOCK_K210_CLK_H
 
 /*
- * Arbitrary identifiers for clocks.
- * The structure is: in0 -> pll0 -> aclk -> cpu
- *
- * Since we use the hardware defaults for now, set all these to the same clock.
+ * Kendryte K210 SoC clock identifiers (arbitrary values).
  */
-#define K210_CLK_PLL0   0
-#define K210_CLK_PLL1   0
-#define K210_CLK_ACLK   0
-#define K210_CLK_CPU    0
+#define K210_CLK_ACLK	0
+#define K210_CLK_CPU	0
+#define K210_CLK_SRAM0	1
+#define K210_CLK_SRAM1	2
+#define K210_CLK_AI	3
+#define K210_CLK_DMA	4
+#define K210_CLK_FFT	5
+#define K210_CLK_ROM	6
+#define K210_CLK_DVP	7
+#define K210_CLK_APB0	8
+#define K210_CLK_APB1	9
+#define K210_CLK_APB2	10
+#define K210_CLK_I2S0	11
+#define K210_CLK_I2S1	12
+#define K210_CLK_I2S2	13
+#define K210_CLK_I2S0_M	14
+#define K210_CLK_I2S1_M	15
+#define K210_CLK_I2S2_M	16
+#define K210_CLK_WDT0	17
+#define K210_CLK_WDT1	18
+#define K210_CLK_SPI0	19
+#define K210_CLK_SPI1	20
+#define K210_CLK_SPI2	21
+#define K210_CLK_I2C0	22
+#define K210_CLK_I2C1	23
+#define K210_CLK_I2C2	24
+#define K210_CLK_SPI3	25
+#define K210_CLK_TIMER0	26
+#define K210_CLK_TIMER1	27
+#define K210_CLK_TIMER2	28
+#define K210_CLK_GPIO	29
+#define K210_CLK_UART1	30
+#define K210_CLK_UART2	31
+#define K210_CLK_UART3	32
+#define K210_CLK_FPIOA	33
+#define K210_CLK_SHA	34
+#define K210_CLK_AES	35
+#define K210_CLK_OTP	36
+#define K210_CLK_RTC	37
 
-#endif /* K210_CLK_H */
+#define K210_NUM_CLKS	38
+
+#endif /* CLOCK_K210_CLK_H */
diff --git a/include/dt-bindings/clock/qcom,camcc-sc7180.h b/include/dt-bindings/clock/qcom,camcc-sc7180.h
new file mode 100644
index 000000000000..ef7d3a041b88
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,camcc-sc7180.h
@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2020, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_CAM_CC_SC7180_H
+#define _DT_BINDINGS_CLK_QCOM_CAM_CC_SC7180_H
+
+/* CAM_CC clocks */
+#define CAM_CC_PLL2_OUT_EARLY					0
+#define CAM_CC_PLL0						1
+#define CAM_CC_PLL1						2
+#define CAM_CC_PLL2						3
+#define CAM_CC_PLL2_OUT_AUX					4
+#define CAM_CC_PLL3						5
+#define CAM_CC_CAMNOC_AXI_CLK					6
+#define CAM_CC_CCI_0_CLK					7
+#define CAM_CC_CCI_0_CLK_SRC					8
+#define CAM_CC_CCI_1_CLK					9
+#define CAM_CC_CCI_1_CLK_SRC					10
+#define CAM_CC_CORE_AHB_CLK					11
+#define CAM_CC_CPAS_AHB_CLK					12
+#define CAM_CC_CPHY_RX_CLK_SRC					13
+#define CAM_CC_CSI0PHYTIMER_CLK					14
+#define CAM_CC_CSI0PHYTIMER_CLK_SRC				15
+#define CAM_CC_CSI1PHYTIMER_CLK					16
+#define CAM_CC_CSI1PHYTIMER_CLK_SRC				17
+#define CAM_CC_CSI2PHYTIMER_CLK					18
+#define CAM_CC_CSI2PHYTIMER_CLK_SRC				19
+#define CAM_CC_CSI3PHYTIMER_CLK					20
+#define CAM_CC_CSI3PHYTIMER_CLK_SRC				21
+#define CAM_CC_CSIPHY0_CLK					22
+#define CAM_CC_CSIPHY1_CLK					23
+#define CAM_CC_CSIPHY2_CLK					24
+#define CAM_CC_CSIPHY3_CLK					25
+#define CAM_CC_FAST_AHB_CLK_SRC					26
+#define CAM_CC_ICP_APB_CLK					27
+#define CAM_CC_ICP_ATB_CLK					28
+#define CAM_CC_ICP_CLK						29
+#define CAM_CC_ICP_CLK_SRC					30
+#define CAM_CC_ICP_CTI_CLK					31
+#define CAM_CC_ICP_TS_CLK					32
+#define CAM_CC_IFE_0_AXI_CLK					33
+#define CAM_CC_IFE_0_CLK					34
+#define CAM_CC_IFE_0_CLK_SRC					35
+#define CAM_CC_IFE_0_CPHY_RX_CLK				36
+#define CAM_CC_IFE_0_CSID_CLK					37
+#define CAM_CC_IFE_0_CSID_CLK_SRC				38
+#define CAM_CC_IFE_0_DSP_CLK					39
+#define CAM_CC_IFE_1_AXI_CLK					40
+#define CAM_CC_IFE_1_CLK					41
+#define CAM_CC_IFE_1_CLK_SRC					42
+#define CAM_CC_IFE_1_CPHY_RX_CLK				43
+#define CAM_CC_IFE_1_CSID_CLK					44
+#define CAM_CC_IFE_1_CSID_CLK_SRC				45
+#define CAM_CC_IFE_1_DSP_CLK					46
+#define CAM_CC_IFE_LITE_CLK					47
+#define CAM_CC_IFE_LITE_CLK_SRC					48
+#define CAM_CC_IFE_LITE_CPHY_RX_CLK				49
+#define CAM_CC_IFE_LITE_CSID_CLK				50
+#define CAM_CC_IFE_LITE_CSID_CLK_SRC				51
+#define CAM_CC_IPE_0_AHB_CLK					52
+#define CAM_CC_IPE_0_AREG_CLK					53
+#define CAM_CC_IPE_0_AXI_CLK					54
+#define CAM_CC_IPE_0_CLK					55
+#define CAM_CC_IPE_0_CLK_SRC					56
+#define CAM_CC_JPEG_CLK						57
+#define CAM_CC_JPEG_CLK_SRC					58
+#define CAM_CC_LRME_CLK						59
+#define CAM_CC_LRME_CLK_SRC					60
+#define CAM_CC_MCLK0_CLK					61
+#define CAM_CC_MCLK0_CLK_SRC					62
+#define CAM_CC_MCLK1_CLK					63
+#define CAM_CC_MCLK1_CLK_SRC					64
+#define CAM_CC_MCLK2_CLK					65
+#define CAM_CC_MCLK2_CLK_SRC					66
+#define CAM_CC_MCLK3_CLK					67
+#define CAM_CC_MCLK3_CLK_SRC					68
+#define CAM_CC_MCLK4_CLK					69
+#define CAM_CC_MCLK4_CLK_SRC					70
+#define CAM_CC_BPS_AHB_CLK					71
+#define CAM_CC_BPS_AREG_CLK					72
+#define CAM_CC_BPS_AXI_CLK					73
+#define CAM_CC_BPS_CLK						74
+#define CAM_CC_BPS_CLK_SRC					75
+#define CAM_CC_SLOW_AHB_CLK_SRC					76
+#define CAM_CC_SOC_AHB_CLK					77
+#define CAM_CC_SYS_TMR_CLK					78
+
+/* CAM_CC power domains */
+#define BPS_GDSC						0
+#define IFE_0_GDSC						1
+#define IFE_1_GDSC						2
+#define IPE_0_GDSC						3
+#define TITAN_TOP_GDSC						4
+
+/* CAM_CC resets */
+#define CAM_CC_BPS_BCR						0
+#define CAM_CC_CAMNOC_BCR					1
+#define CAM_CC_CCI_0_BCR					2
+#define CAM_CC_CCI_1_BCR					3
+#define CAM_CC_CPAS_BCR						4
+#define CAM_CC_CSI0PHY_BCR					5
+#define CAM_CC_CSI1PHY_BCR					6
+#define CAM_CC_CSI2PHY_BCR					7
+#define CAM_CC_CSI3PHY_BCR					8
+#define CAM_CC_ICP_BCR						9
+#define CAM_CC_IFE_0_BCR					10
+#define CAM_CC_IFE_1_BCR					11
+#define CAM_CC_IFE_LITE_BCR					12
+#define CAM_CC_IPE_0_BCR					13
+#define CAM_CC_JPEG_BCR						14
+#define CAM_CC_LRME_BCR						15
+#define CAM_CC_MCLK0_BCR					16
+#define CAM_CC_MCLK1_BCR					17
+#define CAM_CC_MCLK2_BCR					18
+#define CAM_CC_MCLK3_BCR					19
+#define CAM_CC_MCLK4_BCR					20
+#define CAM_CC_TITAN_TOP_BCR					21
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,gcc-sdx55.h b/include/dt-bindings/clock/qcom,gcc-sdx55.h
new file mode 100644
index 000000000000..fb9a5942f793
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,gcc-sdx55.h
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2020, Linaro Ltd.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_GCC_SDX55_H
+#define _DT_BINDINGS_CLK_QCOM_GCC_SDX55_H
+
+#define GPLL0							3
+#define GPLL0_OUT_EVEN						4
+#define GPLL4							5
+#define GPLL4_OUT_EVEN						6
+#define GPLL5							7
+#define GCC_AHB_PCIE_LINK_CLK					8
+#define GCC_BLSP1_AHB_CLK					9
+#define GCC_BLSP1_QUP1_I2C_APPS_CLK				10
+#define GCC_BLSP1_QUP1_I2C_APPS_CLK_SRC				11
+#define GCC_BLSP1_QUP1_SPI_APPS_CLK				12
+#define GCC_BLSP1_QUP1_SPI_APPS_CLK_SRC				13
+#define GCC_BLSP1_QUP2_I2C_APPS_CLK				14
+#define GCC_BLSP1_QUP2_I2C_APPS_CLK_SRC				15
+#define GCC_BLSP1_QUP2_SPI_APPS_CLK				16
+#define GCC_BLSP1_QUP2_SPI_APPS_CLK_SRC				17
+#define GCC_BLSP1_QUP3_I2C_APPS_CLK				18
+#define GCC_BLSP1_QUP3_I2C_APPS_CLK_SRC				19
+#define GCC_BLSP1_QUP3_SPI_APPS_CLK				20
+#define GCC_BLSP1_QUP3_SPI_APPS_CLK_SRC				21
+#define GCC_BLSP1_QUP4_I2C_APPS_CLK				22
+#define GCC_BLSP1_QUP4_I2C_APPS_CLK_SRC				23
+#define GCC_BLSP1_QUP4_SPI_APPS_CLK				24
+#define GCC_BLSP1_QUP4_SPI_APPS_CLK_SRC				25
+#define GCC_BLSP1_UART1_APPS_CLK				26
+#define GCC_BLSP1_UART1_APPS_CLK_SRC				27
+#define GCC_BLSP1_UART2_APPS_CLK				28
+#define GCC_BLSP1_UART2_APPS_CLK_SRC				29
+#define GCC_BLSP1_UART3_APPS_CLK				30
+#define GCC_BLSP1_UART3_APPS_CLK_SRC				31
+#define GCC_BLSP1_UART4_APPS_CLK				32
+#define GCC_BLSP1_UART4_APPS_CLK_SRC				33
+#define GCC_BOOT_ROM_AHB_CLK					34
+#define GCC_CE1_AHB_CLK						35
+#define GCC_CE1_AXI_CLK						36
+#define GCC_CE1_CLK						37
+#define GCC_CPUSS_AHB_CLK					38
+#define GCC_CPUSS_AHB_CLK_SRC					39
+#define GCC_CPUSS_GNOC_CLK					40
+#define GCC_CPUSS_RBCPR_CLK					41
+#define GCC_CPUSS_RBCPR_CLK_SRC					42
+#define GCC_EMAC_CLK_SRC					43
+#define GCC_EMAC_PTP_CLK_SRC					44
+#define GCC_ETH_AXI_CLK						45
+#define GCC_ETH_PTP_CLK						46
+#define GCC_ETH_RGMII_CLK					47
+#define GCC_ETH_SLAVE_AHB_CLK					48
+#define GCC_GP1_CLK						49
+#define GCC_GP1_CLK_SRC						50
+#define GCC_GP2_CLK						51
+#define GCC_GP2_CLK_SRC						52
+#define GCC_GP3_CLK						53
+#define GCC_GP3_CLK_SRC						54
+#define GCC_PCIE_0_CLKREF_CLK					55
+#define GCC_PCIE_AUX_CLK					56
+#define GCC_PCIE_AUX_PHY_CLK_SRC				57
+#define GCC_PCIE_CFG_AHB_CLK					58
+#define GCC_PCIE_MSTR_AXI_CLK					59
+#define GCC_PCIE_PIPE_CLK					60
+#define GCC_PCIE_RCHNG_PHY_CLK					61
+#define GCC_PCIE_RCHNG_PHY_CLK_SRC				62
+#define GCC_PCIE_SLEEP_CLK					63
+#define GCC_PCIE_SLV_AXI_CLK					64
+#define GCC_PCIE_SLV_Q2A_AXI_CLK				65
+#define GCC_PDM2_CLK						66
+#define GCC_PDM2_CLK_SRC					67
+#define GCC_PDM_AHB_CLK						68
+#define GCC_PDM_XO4_CLK						69
+#define GCC_SDCC1_AHB_CLK					70
+#define GCC_SDCC1_APPS_CLK					71
+#define GCC_SDCC1_APPS_CLK_SRC					72
+#define GCC_SYS_NOC_CPUSS_AHB_CLK				73
+#define GCC_USB30_MASTER_CLK					74
+#define GCC_USB30_MASTER_CLK_SRC				75
+#define GCC_USB30_MOCK_UTMI_CLK					76
+#define GCC_USB30_MOCK_UTMI_CLK_SRC				77
+#define GCC_USB30_MSTR_AXI_CLK					78
+#define GCC_USB30_SLEEP_CLK					79
+#define GCC_USB30_SLV_AHB_CLK					80
+#define GCC_USB3_PHY_AUX_CLK					81
+#define GCC_USB3_PHY_AUX_CLK_SRC				82
+#define GCC_USB3_PHY_PIPE_CLK					83
+#define GCC_USB3_PRIM_CLKREF_CLK				84
+#define GCC_USB_PHY_CFG_AHB2PHY_CLK				85
+#define GCC_XO_DIV4_CLK						86
+#define GCC_XO_PCIE_LINK_CLK					87
+
+#define GCC_EMAC_BCR						0
+#define GCC_PCIE_BCR						1
+#define GCC_PCIE_LINK_DOWN_BCR					2
+#define GCC_PCIE_NOCSR_COM_PHY_BCR				3
+#define GCC_PCIE_PHY_BCR					4
+#define GCC_PCIE_PHY_CFG_AHB_BCR				5
+#define GCC_PCIE_PHY_COM_BCR					6
+#define GCC_PCIE_PHY_NOCSR_COM_PHY_BCR				7
+#define GCC_PDM_BCR						8
+#define GCC_QUSB2PHY_BCR					9
+#define GCC_TCSR_PCIE_BCR					10
+#define GCC_USB30_BCR						11
+#define GCC_USB3_PHY_BCR					12
+#define GCC_USB3PHY_PHY_BCR					13
+#define GCC_USB_PHY_CFG_AHB2PHY_BCR				14
+
+/* GCC power domains */
+#define USB30_GDSC						0
+#define PCIE_GDSC						1
+#define EMAC_GDSC						2
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,rpmh.h b/include/dt-bindings/clock/qcom,rpmh.h
index 2e6c54e65455..583a99161aaa 100644
--- a/include/dt-bindings/clock/qcom,rpmh.h
+++ b/include/dt-bindings/clock/qcom,rpmh.h
@@ -21,5 +21,15 @@
 #define RPMH_IPA_CLK				12
 #define RPMH_LN_BB_CLK1				13
 #define RPMH_LN_BB_CLK1_A			14
+#define RPMH_CE_CLK				15
+#define RPMH_QPIC_CLK				16
+#define RPMH_DIV_CLK1				17
+#define RPMH_DIV_CLK1_A				18
+#define RPMH_RF_CLK4				19
+#define RPMH_RF_CLK4_A				20
+#define RPMH_RF_CLK5				21
+#define RPMH_RF_CLK5_A				22
+#define RPMH_PKA_CLK				23
+#define RPMH_HWKM_CLK				24
 
 #endif
diff --git a/include/dt-bindings/clock/qcom,sm8250-lpass-aoncc.h b/include/dt-bindings/clock/qcom,sm8250-lpass-aoncc.h
new file mode 100644
index 000000000000..f5a1cfac8612
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sm8250-lpass-aoncc.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _DT_BINDINGS_CLK_LPASS_AONCC_SM8250_H
+#define _DT_BINDINGS_CLK_LPASS_AONCC_SM8250_H
+
+/* from AOCC */
+#define LPASS_CDC_VA_MCLK				0
+#define LPASS_CDC_TX_NPL				1
+#define LPASS_CDC_TX_MCLK				2
+
+#endif /* _DT_BINDINGS_CLK_LPASS_AONCC_SM8250_H */
diff --git a/include/dt-bindings/clock/qcom,sm8250-lpass-audiocc.h b/include/dt-bindings/clock/qcom,sm8250-lpass-audiocc.h
new file mode 100644
index 000000000000..a1aa6cb5d840
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,sm8250-lpass-audiocc.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _DT_BINDINGS_CLK_LPASS_AUDIOCC_SM8250_H
+#define _DT_BINDINGS_CLK_LPASS_AUDIOCC_SM8250_H
+
+/* From AudioCC */
+#define LPASS_CDC_WSA_NPL				0
+#define LPASS_CDC_WSA_MCLK				1
+#define LPASS_CDC_RX_MCLK				2
+#define LPASS_CDC_RX_NPL				3
+#define LPASS_CDC_RX_MCLK_MCLK2				4
+
+#endif /* _DT_BINDINGS_CLK_LPASS_AUDIOCC_SM8250_H */
diff --git a/include/dt-bindings/clock/sifive-fu740-prci.h b/include/dt-bindings/clock/sifive-fu740-prci.h
new file mode 100644
index 000000000000..cd7706ea5677
--- /dev/null
+++ b/include/dt-bindings/clock/sifive-fu740-prci.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Copyright (C) 2019 SiFive, Inc.
+ * Wesley Terpstra
+ * Paul Walmsley
+ * Zong Li
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_SIFIVE_FU740_PRCI_H
+#define __DT_BINDINGS_CLOCK_SIFIVE_FU740_PRCI_H
+
+/* Clock indexes for use by Device Tree data and the PRCI driver */
+
+#define PRCI_CLK_COREPLL	       0
+#define PRCI_CLK_DDRPLL		       1
+#define PRCI_CLK_GEMGXLPLL	       2
+#define PRCI_CLK_DVFSCOREPLL	       3
+#define PRCI_CLK_HFPCLKPLL	       4
+#define PRCI_CLK_CLTXPLL	       5
+#define PRCI_CLK_TLCLK		       6
+#define PRCI_CLK_PCLK		       7
+
+#endif	/* __DT_BINDINGS_CLOCK_SIFIVE_FU740_PRCI_H */
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 1d94acd0bc85..8dcb3e1477bc 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -13,7 +13,7 @@
 #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
 #define ARMV8_PMU_MAX_COUNTER_PAIRS	((ARMV8_PMU_MAX_COUNTERS + 1) >> 1)
 
-#ifdef CONFIG_KVM_ARM_PMU
+#ifdef CONFIG_HW_PERF_EVENTS
 
 struct kvm_pmc {
 	u8 idx;	/* index into the pmu->pmc array */
@@ -24,13 +24,11 @@ struct kvm_pmu {
 	int irq_num;
 	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
 	DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
-	bool ready;
 	bool created;
 	bool irq_level;
 	struct irq_work overflow_work;
 };
 
-#define kvm_arm_pmu_v3_ready(v)		((v)->arch.pmu.ready)
 #define kvm_arm_pmu_irq_initialized(v)	((v)->arch.pmu.irq_num >= VGIC_NR_SGIS)
 u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx);
 void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
@@ -61,7 +59,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu);
 struct kvm_pmu {
 };
 
-#define kvm_arm_pmu_v3_ready(v)		(false)
 #define kvm_arm_pmu_irq_initialized(v)	(false)
 static inline u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu,
 					    u64 select_idx)
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index a8d8fdcd3723..3d74f1060bd1 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -402,6 +402,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq,
 				 struct kvm_kernel_irq_routing_entry *irq_entry);
 
 int vgic_v4_load(struct kvm_vcpu *vcpu);
+void vgic_v4_commit(struct kvm_vcpu *vcpu);
 int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db);
 
 #endif /* __KVM_ARM_VGIC_H */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 2630c2e953f7..053bf05fb1f7 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -885,6 +885,13 @@ static inline int acpi_device_modalias(struct device *dev,
 	return -ENODEV;
 }
 
+static inline struct platform_device *
+acpi_create_platform_device(struct acpi_device *adev,
+			    struct property_entry *properties)
+{
+	return NULL;
+}
+
 static inline bool acpi_dma_supported(struct acpi_device *adev)
 {
 	return false;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 47b021952ac7..d705b174d346 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -447,8 +447,8 @@ enum {
 	BLK_MQ_REQ_NOWAIT	= (__force blk_mq_req_flags_t)(1 << 0),
 	/* allocate from reserved pool */
 	BLK_MQ_REQ_RESERVED	= (__force blk_mq_req_flags_t)(1 << 1),
-	/* set RQF_PREEMPT */
-	BLK_MQ_REQ_PREEMPT	= (__force blk_mq_req_flags_t)(1 << 3),
+	/* set RQF_PM */
+	BLK_MQ_REQ_PM		= (__force blk_mq_req_flags_t)(1 << 2),
 };
 
 struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 070de09425ad..f94ee3089e01 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -79,9 +79,6 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_MQ_INFLIGHT		((__force req_flags_t)(1 << 6))
 /* don't call prep for this one */
 #define RQF_DONTPREP		((__force req_flags_t)(1 << 7))
-/* set for "ide_preempt" requests and also for requests for which the SCSI
-   "quiesce" state must be ignored. */
-#define RQF_PREEMPT		((__force req_flags_t)(1 << 8))
 /* vaguely specified driver internal error.  Ignored by the block layer */
 #define RQF_FAILED		((__force req_flags_t)(1 << 10))
 /* don't warn about errors */
@@ -430,8 +427,7 @@ struct request_queue {
 	unsigned long		queue_flags;
 	/*
 	 * Number of contexts that have called blk_set_pm_only(). If this
-	 * counter is above zero then only RQF_PM and RQF_PREEMPT requests are
-	 * processed.
+	 * counter is above zero then only RQF_PM requests are processed.
 	 */
 	atomic_t		pm_only;
 
@@ -696,6 +692,18 @@ static inline bool queue_is_mq(struct request_queue *q)
 	return q->mq_ops;
 }
 
+#ifdef CONFIG_PM
+static inline enum rpm_status queue_rpm_status(struct request_queue *q)
+{
+	return q->rpm_status;
+}
+#else
+static inline enum rpm_status queue_rpm_status(struct request_queue *q)
+{
+	return RPM_ACTIVE;
+}
+#endif
+
 static inline enum blk_zoned_model
 blk_queue_zoned_model(struct request_queue *q)
 {
diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
index 7bb66e15b481..e3a0be2c90ad 100644
--- a/include/linux/build_bug.h
+++ b/include/linux/build_bug.h
@@ -77,9 +77,4 @@
 #define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
 #define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
 
-#ifdef __GENKSYMS__
-/* genksyms gets confused by _Static_assert */
-#define _Static_assert(expr, ...)
-#endif
-
 #endif	/* _LINUX_BUILD_BUG_H */
diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h
index f5e02f6c0655..3989dcb94d3d 100644
--- a/include/linux/ceph/msgr.h
+++ b/include/linux/ceph/msgr.h
@@ -33,8 +33,8 @@
 #define CEPH_MSGR2_INCARNATION_1 (0ull)
 
 #define DEFINE_MSGR2_FEATURE(bit, incarnation, name)               \
-	static const uint64_t CEPH_MSGR2_FEATURE_##name = (1ULL << bit); \
-	static const uint64_t CEPH_MSGR2_FEATUREMASK_##name =            \
+	static const uint64_t __maybe_unused CEPH_MSGR2_FEATURE_##name = (1ULL << bit); \
+	static const uint64_t __maybe_unused CEPH_MSGR2_FEATUREMASK_##name =            \
 			(1ULL << bit | CEPH_MSGR2_INCARNATION_##incarnation);
 
 #define HAVE_MSGR2_FEATURE(x, name) \
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 03a5de5f99f4..e4316890661a 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -639,6 +639,12 @@ struct clk_hw *__clk_hw_register_divider(struct device *dev,
 		const struct clk_parent_data *parent_data, unsigned long flags,
 		void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags,
 		const struct clk_div_table *table, spinlock_t *lock);
+struct clk_hw *__devm_clk_hw_register_divider(struct device *dev,
+		struct device_node *np, const char *name,
+		const char *parent_name, const struct clk_hw *parent_hw,
+		const struct clk_parent_data *parent_data, unsigned long flags,
+		void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags,
+		const struct clk_div_table *table, spinlock_t *lock);
 struct clk *clk_register_divider_table(struct device *dev, const char *name,
 		const char *parent_name, unsigned long flags,
 		void __iomem *reg, u8 shift, u8 width,
@@ -779,6 +785,27 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name,
 				  (parent_data), (flags), (reg), (shift),     \
 				  (width), (clk_divider_flags), (table),      \
 				  (lock))
+/**
+ * devm_clk_hw_register_divider_table - register a table based divider clock
+ * with the clock framework (devres variant)
+ * @dev: device registering this clock
+ * @name: name of this clock
+ * @parent_name: name of clock's parent
+ * @flags: framework-specific flags
+ * @reg: register address to adjust divider
+ * @shift: number of bits to shift the bitfield
+ * @width: width of the bitfield
+ * @clk_divider_flags: divider-specific flags for this clock
+ * @table: array of divider/value pairs ending with a div set to 0
+ * @lock: shared register lock for this clock
+ */
+#define devm_clk_hw_register_divider_table(dev, name, parent_name, flags,     \
+					   reg, shift, width,		      \
+					   clk_divider_flags, table, lock)    \
+	__devm_clk_hw_register_divider((dev), NULL, (name), (parent_name),    \
+				       NULL, NULL, (flags), (reg), (shift),   \
+				       (width), (clk_divider_flags), (table), \
+				       (lock))
 
 void clk_unregister_divider(struct clk *clk);
 void clk_hw_unregister_divider(struct clk_hw *hw);
@@ -1062,6 +1089,13 @@ struct clk_hw *clk_hw_register_composite_pdata(struct device *dev,
 		struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
 		struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
 		unsigned long flags);
+struct clk_hw *devm_clk_hw_register_composite_pdata(struct device *dev,
+		const char *name, const struct clk_parent_data *parent_data,
+		int num_parents,
+		struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+		struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+		struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+		unsigned long flags);
 void clk_hw_unregister_composite(struct clk_hw *hw);
 
 struct clk *clk_register(struct device *dev, struct clk_hw *hw);
@@ -1088,6 +1122,11 @@ static inline struct clk_hw *__clk_get_hw(struct clk *clk)
 	return (struct clk_hw *)clk;
 }
 #endif
+
+struct clk *clk_hw_get_clk(struct clk_hw *hw, const char *con_id);
+struct clk *devm_clk_hw_get_clk(struct device *dev, struct clk_hw *hw,
+				const char *con_id);
+
 unsigned int clk_hw_get_num_parents(const struct clk_hw *hw);
 struct clk_hw *clk_hw_get_parent(const struct clk_hw *hw);
 struct clk_hw *clk_hw_get_parent_by_index(const struct clk_hw *hw,
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 7fd6a1febcf4..31ff1bf1b79f 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -110,6 +110,17 @@ int clk_notifier_register(struct clk *clk, struct notifier_block *nb);
 int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb);
 
 /**
+ * devm_clk_notifier_register - register a managed rate-change notifier callback
+ * @dev: device for clock "consumer"
+ * @clk: clock whose rate we are interested in
+ * @nb: notifier block with callback function pointer
+ *
+ * Returns 0 on success, -EERROR otherwise
+ */
+int devm_clk_notifier_register(struct device *dev, struct clk *clk,
+			       struct notifier_block *nb);
+
+/**
  * clk_get_accuracy - obtain the clock accuracy in ppb (parts per billion)
  *		      for a clock source.
  * @clk: clock source
@@ -150,7 +161,7 @@ int clk_get_phase(struct clk *clk);
 int clk_set_duty_cycle(struct clk *clk, unsigned int num, unsigned int den);
 
 /**
- * clk_get_duty_cycle - return the duty cycle ratio of a clock signal
+ * clk_get_scaled_duty_cycle - return the duty cycle ratio of a clock signal
  * @clk: clock signal source
  * @scale: scaling factor to be applied to represent the ratio as an integer
  *
@@ -186,6 +197,13 @@ static inline int clk_notifier_unregister(struct clk *clk,
 	return -ENOTSUPP;
 }
 
+static inline int devm_clk_notifier_register(struct device *dev,
+					     struct clk *clk,
+					     struct notifier_block *nb)
+{
+	return -ENOTSUPP;
+}
+
 static inline long clk_get_accuracy(struct clk *clk)
 {
 	return -ENOTSUPP;
diff --git a/include/linux/clk/samsung.h b/include/linux/clk/samsung.h
index 79097e365f7f..38b774001712 100644
--- a/include/linux/clk/samsung.h
+++ b/include/linux/clk/samsung.h
@@ -10,7 +10,7 @@
 
 struct device_node;
 
-#ifdef CONFIG_ARCH_S3C64XX
+#ifdef CONFIG_S3C64XX_COMMON_CLK
 void s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f,
 		      unsigned long xusbxti_f, bool s3c6400,
 		      void __iomem *base);
@@ -19,7 +19,7 @@ static inline void s3c64xx_clk_init(struct device_node *np,
 				    unsigned long xtal_f,
 				    unsigned long xusbxti_f,
 				    bool s3c6400, void __iomem *base) { }
-#endif /* CONFIG_ARCH_S3C64XX */
+#endif /* CONFIG_S3C64XX_COMMON_CLK */
 
 #ifdef CONFIG_S3C2410_COMMON_CLK
 void s3c2410_common_clk_init(struct device_node *np, unsigned long xti_f,
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 74c6c0486eed..555ab0fddbef 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -13,6 +13,12 @@
 /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */
 #if GCC_VERSION < 40900
 # error Sorry, your version of GCC is too old - please use 4.9 or newer.
+#elif defined(CONFIG_ARM64) && GCC_VERSION < 50100
+/*
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293
+ * https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk
+ */
+# error Sorry, your version of GCC is too old - please use 5.1 or newer.
 #endif
 
 /*
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index b2a3f4f641a7..ea5e04e75845 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -273,6 +273,12 @@
 #define __used                          __attribute__((__used__))
 
 /*
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-warn_005funused_005fresult-function-attribute
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#nodiscard-warn-unused-result
+ */
+#define __must_check                    __attribute__((__warn_unused_result__))
+
+/*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute
  */
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index bbaa39e98f9f..e5dd5a4ae946 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -121,12 +121,6 @@ struct ftrace_likely_data {
 	unsigned long			constant;
 };
 
-#ifdef CONFIG_ENABLE_MUST_CHECK
-#define __must_check		__attribute__((__warn_unused_result__))
-#else
-#define __must_check
-#endif
-
 #if defined(CC_USING_HOTPATCH)
 #define notrace			__attribute__((hotpatch(0, 0)))
 #elif defined(CC_USING_PATCHABLE_FUNCTION_ENTRY)
diff --git a/include/linux/console.h b/include/linux/console.h
index dbe78e8e2602..20874db50bc8 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -186,12 +186,9 @@ extern int braille_register_console(struct console *, int index,
 extern int braille_unregister_console(struct console *);
 #ifdef CONFIG_TTY
 extern void console_sysfs_notify(void);
-extern void register_ttynull_console(void);
 #else
 static inline void console_sysfs_notify(void)
 { }
-static inline void register_ttynull_console(void)
-{ }
 #endif
 extern bool console_suspend_enabled;
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 584fccd4fcab..9c8b7437b6cd 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -320,6 +320,15 @@ struct cpufreq_driver {
 					unsigned int index);
 	unsigned int	(*fast_switch)(struct cpufreq_policy *policy,
 				       unsigned int target_freq);
+	/*
+	 * ->fast_switch() replacement for drivers that use an internal
+	 * representation of performance levels and can pass hints other than
+	 * the target performance level to the hardware.
+	 */
+	void		(*adjust_perf)(unsigned int cpu,
+				       unsigned long min_perf,
+				       unsigned long target_perf,
+				       unsigned long capacity);
 
 	/*
 	 * Caches and returns the lowest driver-supported frequency greater than
@@ -588,6 +597,11 @@ struct cpufreq_governor {
 /* Pass a target to the cpufreq driver */
 unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 					unsigned int target_freq);
+void cpufreq_driver_adjust_perf(unsigned int cpu,
+				unsigned long min_perf,
+				unsigned long target_perf,
+				unsigned long capacity);
+bool cpufreq_driver_has_adjust_perf(void);
 int cpufreq_driver_target(struct cpufreq_policy *policy,
 				 unsigned int target_freq,
 				 unsigned int relation);
diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h
index 29d255fdd5d6..90bd558a17f5 100644
--- a/include/linux/dm-bufio.h
+++ b/include/linux/dm-bufio.h
@@ -150,6 +150,7 @@ void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned n);
 
 unsigned dm_bufio_get_block_size(struct dm_bufio_client *c);
 sector_t dm_bufio_get_device_size(struct dm_bufio_client *c);
+struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c);
 sector_t dm_bufio_get_block_number(struct dm_buffer *b);
 void *dm_bufio_get_block_data(struct dm_buffer *b);
 void *dm_bufio_get_aux_data(struct dm_buffer *b);
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 03925e438ec3..70fcd0f610ea 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -317,6 +317,20 @@ static inline void arch_dma_mark_clean(phys_addr_t paddr, size_t size)
 void *arch_dma_set_uncached(void *addr, size_t size);
 void arch_dma_clear_uncached(void *addr, size_t size);
 
+#ifdef CONFIG_ARCH_HAS_DMA_MAP_DIRECT
+bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr);
+bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle);
+bool arch_dma_map_sg_direct(struct device *dev, struct scatterlist *sg,
+		int nents);
+bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
+		int nents);
+#else
+#define arch_dma_map_page_direct(d, a)		(false)
+#define arch_dma_unmap_page_direct(d, a)	(false)
+#define arch_dma_map_sg_direct(d, s, n)		(false)
+#define arch_dma_unmap_sg_direct(d, s, n)	(false)
+#endif
+
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		const struct iommu_ops *iommu, bool coherent);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index d7c0e73af2b9..763b816ba19c 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -817,12 +817,6 @@ static inline bool efi_enabled(int feature)
 static inline void
 efi_reboot(enum reboot_mode reboot_mode, const char *__unused) {}
 
-static inline bool
-efi_capsule_pending(int *reset_type)
-{
-	return false;
-}
-
 static inline bool efi_soft_reserve_enabled(void)
 {
 	return false;
@@ -1038,6 +1032,7 @@ bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
 				  size_t len);
 
+#if IS_ENABLED(CONFIG_EFI_CAPSULE_LOADER)
 extern bool efi_capsule_pending(int *reset_type);
 
 extern int efi_capsule_supported(efi_guid_t guid, u32 flags,
@@ -1045,6 +1040,9 @@ extern int efi_capsule_supported(efi_guid_t guid, u32 flags,
 
 extern int efi_capsule_update(efi_capsule_header_t *capsule,
 			      phys_addr_t *pages);
+#else
+static inline bool efi_capsule_pending(int *reset_type) { return false; }
+#endif
 
 #ifdef CONFIG_EFI_RUNTIME_MAP
 int efi_runtime_map_init(struct kobject *);
@@ -1089,7 +1087,28 @@ enum efi_secureboot_mode {
 	efi_secureboot_mode_disabled,
 	efi_secureboot_mode_enabled,
 };
-enum efi_secureboot_mode efi_get_secureboot(void);
+
+static inline
+enum efi_secureboot_mode efi_get_secureboot_mode(efi_get_variable_t *get_var)
+{
+	u8 secboot, setupmode = 0;
+	efi_status_t status;
+	unsigned long size;
+
+	size = sizeof(secboot);
+	status = get_var(L"SecureBoot", &EFI_GLOBAL_VARIABLE_GUID, NULL, &size,
+			 &secboot);
+	if (status == EFI_NOT_FOUND)
+		return efi_secureboot_mode_disabled;
+	if (status != EFI_SUCCESS)
+		return efi_secureboot_mode_unknown;
+
+	size = sizeof(setupmode);
+	get_var(L"SetupMode", &EFI_GLOBAL_VARIABLE_GUID, NULL, &size, &setupmode);
+	if (secboot == 0 || setupmode == 1)
+		return efi_secureboot_mode_disabled;
+	return efi_secureboot_mode_enabled;
+}
 
 #ifdef CONFIG_RESET_ATTACK_MITIGATION
 void efi_enable_reset_attack_mitigation(void);
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index dc4fd8a6644d..fa0a524baed0 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -41,6 +41,7 @@ struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
 __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
+void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
 
 DECLARE_PER_CPU(int, eventfd_wake_count);
 
@@ -82,6 +83,11 @@ static inline bool eventfd_signal_count(void)
 	return false;
 }
 
+static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
+{
+
+}
+
 #endif
 
 #endif /* _LINUX_EVENTFD_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ad4cf1bae586..fd47deea7c17 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2876,8 +2876,7 @@ extern int inode_needs_sync(struct inode *inode);
 extern int generic_delete_inode(struct inode *inode);
 static inline int generic_drop_inode(struct inode *inode)
 {
-	return !inode->i_nlink || inode_unhashed(inode) ||
-		(inode->i_state & I_DONTCACHE);
+	return !inode->i_nlink || inode_unhashed(inode);
 }
 extern void d_mark_dontcache(struct inode *inode);
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index d956987ed032..09c6a0bf3892 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -533,11 +533,10 @@ struct dmar_domain {
 					/* Domain ids per IOMMU. Use u16 since
 					 * domain ids are 16 bit wide according
 					 * to VT-d spec, section 9.3 */
-	unsigned int	auxd_refcnt;	/* Refcount of auxiliary attaching */
 
 	bool has_iotlb_device;
 	struct list_head devices;	/* all devices' list */
-	struct list_head auxd;		/* link to device's auxiliary list */
+	struct list_head subdevices;	/* all subdevices' list */
 	struct iova_domain iovad;	/* iova's that belong to this domain */
 
 	struct dma_pte	*pgd;		/* virtual address */
@@ -610,14 +609,21 @@ struct intel_iommu {
 	struct dmar_drhd_unit *drhd;
 };
 
+/* Per subdevice private data */
+struct subdev_domain_info {
+	struct list_head link_phys;	/* link to phys device siblings */
+	struct list_head link_domain;	/* link to domain siblings */
+	struct device *pdev;		/* physical device derived from */
+	struct dmar_domain *domain;	/* aux-domain */
+	int users;			/* user count */
+};
+
 /* PCI domain-device relationship */
 struct device_domain_info {
 	struct list_head link;	/* link to domain siblings */
 	struct list_head global; /* link to global list */
 	struct list_head table;	/* link to pasid table */
-	struct list_head auxiliary_domains; /* auxiliary domains
-					     * attached to this device
-					     */
+	struct list_head subdevices; /* subdevices sibling */
 	u32 segment;		/* PCI segment number */
 	u8 bus;			/* PCI bus number */
 	u8 devfn;		/* PCI devfn number */
@@ -758,6 +764,7 @@ struct intel_svm_dev {
 	struct list_head list;
 	struct rcu_head rcu;
 	struct device *dev;
+	struct intel_iommu *iommu;
 	struct svm_dev_ops *ops;
 	struct iommu_sva sva;
 	u32 pasid;
@@ -771,7 +778,6 @@ struct intel_svm {
 	struct mmu_notifier notifier;
 	struct mm_struct *mm;
 
-	struct intel_iommu *iommu;
 	unsigned int flags;
 	u32 pasid;
 	int gpasid; /* In case that guest PASID is different from host PASID */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 870b3251e174..bb8ff9083e7d 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -232,6 +232,7 @@ extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
 # define local_irq_enable_in_hardirq()	local_irq_enable()
 #endif
 
+bool irq_has_action(unsigned int irq);
 extern void disable_irq_nosync(unsigned int irq);
 extern bool disable_hardirq(unsigned int irq);
 extern void disable_irq(unsigned int irq);
diff --git a/include/linux/irq.h b/include/linux/irq.h
index c332871d59da..4aeb1c4c7e07 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -906,6 +906,13 @@ struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d)
 }
 #endif
 
+static inline struct cpumask *irq_get_effective_affinity_mask(unsigned int irq)
+{
+	struct irq_data *d = irq_get_irq_data(irq);
+
+	return d ? irq_data_get_effective_affinity_mask(d) : NULL;
+}
+
 unsigned int arch_dynirq_lower_bound(unsigned int from);
 
 int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 6976b8331b60..943c3411ca10 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -39,6 +39,8 @@ struct its_vpe {
 	irq_hw_number_t		vpe_db_lpi;
 	/* VPE resident */
 	bool			resident;
+	/* VPT parse complete */
+	bool			ready;
 	union {
 		/* GICv4.0 implementations */
 		struct {
@@ -104,6 +106,7 @@ enum its_vcpu_info_cmd_type {
 	PROP_UPDATE_AND_INV_VLPI,
 	SCHEDULE_VPE,
 	DESCHEDULE_VPE,
+	COMMIT_VPE,
 	INVALL_VPE,
 	PROP_UPDATE_VSGI,
 };
@@ -129,6 +132,7 @@ int its_alloc_vcpu_irqs(struct its_vm *vm);
 void its_free_vcpu_irqs(struct its_vm *vm);
 int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en);
 int its_make_vpe_non_resident(struct its_vpe *vpe, bool db);
+int its_commit_vpe(struct its_vpe *vpe);
 int its_invall_vpe(struct its_vpe *vpe);
 int its_map_vlpi(int irq, struct its_vlpi_map *map);
 int its_get_vlpi(int irq, struct its_vlpi_map *map);
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 5745491303e0..891b323266df 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -113,6 +113,12 @@ static inline void irq_unlock_sparse(void) { }
 extern struct irq_desc irq_desc[NR_IRQS];
 #endif
 
+static inline unsigned int irq_desc_kstat_cpu(struct irq_desc *desc,
+					      unsigned int cpu)
+{
+	return desc->kstat_irqs ? *per_cpu_ptr(desc->kstat_irqs, cpu) : 0;
+}
+
 static inline struct irq_desc *irq_data_to_desc(struct irq_data *data)
 {
 	return container_of(data->common, struct irq_desc, irq_common_data);
@@ -179,12 +185,7 @@ int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq,
 /* Test to see if a driver has successfully requested an irq */
 static inline int irq_desc_has_action(struct irq_desc *desc)
 {
-	return desc->action != NULL;
-}
-
-static inline int irq_has_action(unsigned int irq)
-{
-	return irq_desc_has_action(irq_to_desc(irq));
+	return desc && desc->action != NULL;
 }
 
 /**
@@ -228,40 +229,31 @@ irq_set_chip_handler_name_locked(struct irq_data *data, struct irq_chip *chip,
 	data->chip = chip;
 }
 
+bool irq_check_status_bit(unsigned int irq, unsigned int bitmask);
+
 static inline bool irq_balancing_disabled(unsigned int irq)
 {
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	return desc->status_use_accessors & IRQ_NO_BALANCING_MASK;
+	return irq_check_status_bit(irq, IRQ_NO_BALANCING_MASK);
 }
 
 static inline bool irq_is_percpu(unsigned int irq)
 {
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	return desc->status_use_accessors & IRQ_PER_CPU;
+	return irq_check_status_bit(irq, IRQ_PER_CPU);
 }
 
 static inline bool irq_is_percpu_devid(unsigned int irq)
 {
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	return desc->status_use_accessors & IRQ_PER_CPU_DEVID;
+	return irq_check_status_bit(irq, IRQ_PER_CPU_DEVID);
 }
 
+void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
+			     struct lock_class_key *request_class);
 static inline void
 irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
 		      struct lock_class_key *request_class)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (desc) {
-		lockdep_set_class(&desc->lock, lock_class);
-		lockdep_set_class(&desc->request_mutex, request_class);
-	}
+	if (IS_ENABLED(CONFIG_LOCKDEP))
+		__irq_set_lockdep_class(irq, lock_class, request_class);
 }
 
 #endif
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 578ff196b3ce..99d3cd051ac3 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -68,7 +68,7 @@ extern void *jbd2_alloc(size_t size, gfp_t flags);
 extern void jbd2_free(void *ptr, size_t size);
 
 #define JBD2_MIN_JOURNAL_BLOCKS 1024
-#define JBD2_MIN_FC_BLOCKS	256
+#define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256
 
 #ifdef __KERNEL__
 
@@ -538,6 +538,7 @@ struct transaction_chp_stats_s {
  * The transaction keeps track of all of the buffers modified by a
  * running transaction, and all of the buffers committed but not yet
  * flushed to home for finished transactions.
+ * (Locking Documentation improved by LockDoc)
  */
 
 /*
@@ -658,12 +659,12 @@ struct transaction_s
 	unsigned long		t_start;
 
 	/*
-	 * When commit was requested
+	 * When commit was requested [j_state_lock]
 	 */
 	unsigned long		t_requested;
 
 	/*
-	 * Checkpointing stats [j_checkpoint_sem]
+	 * Checkpointing stats [j_list_lock]
 	 */
 	struct transaction_chp_stats_s t_chp_stats;
 
@@ -1691,6 +1692,13 @@ static inline int jbd2_journal_has_csum_v2or3(journal_t *journal)
 	return journal->j_chksum_driver != NULL;
 }
 
+static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb)
+{
+	int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks);
+
+	return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS;
+}
+
 /*
  * Return number of free blocks in the log. Must be called under j_state_lock.
  */
diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h
index ac6aba632f2d..ca5e89fb10d3 100644
--- a/include/linux/kasan-checks.h
+++ b/include/linux/kasan-checks.h
@@ -9,7 +9,7 @@
  * even in compilation units that selectively disable KASAN, but must use KASAN
  * to validate access to an address.   Never use these in header files!
  */
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 bool __kasan_check_read(const volatile void *p, unsigned int size);
 bool __kasan_check_write(const volatile void *p, unsigned int size);
 #else
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 30d343b4a40a..fe1ae73ff8b5 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_KASAN_H
 #define _LINUX_KASAN_H
 
+#include <linux/static_key.h>
 #include <linux/types.h>
 
 struct kmem_cache;
@@ -11,7 +12,7 @@ struct task_struct;
 
 #ifdef CONFIG_KASAN
 
-#include <linux/pgtable.h>
+#include <linux/linkage.h>
 #include <asm/kasan.h>
 
 /* kasan_data struct is used in KUnit tests for KASAN expected failures */
@@ -20,8 +21,26 @@ struct kunit_kasan_expectation {
 	bool report_found;
 };
 
+#endif
+
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+
+#include <linux/pgtable.h>
+
+/* Software KASAN implementations use shadow memory. */
+
+#ifdef CONFIG_KASAN_SW_TAGS
+#define KASAN_SHADOW_INIT 0xFF
+#else
+#define KASAN_SHADOW_INIT 0
+#endif
+
+#ifndef PTE_HWTABLE_PTRS
+#define PTE_HWTABLE_PTRS 0
+#endif
+
 extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
-extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE];
+extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS];
 extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD];
 extern pud_t kasan_early_shadow_pud[PTRS_PER_PUD];
 extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D];
@@ -35,88 +54,219 @@ static inline void *kasan_mem_to_shadow(const void *addr)
 		+ KASAN_SHADOW_OFFSET;
 }
 
+int kasan_add_zero_shadow(void *start, unsigned long size);
+void kasan_remove_zero_shadow(void *start, unsigned long size);
+
 /* Enable reporting bugs after kasan_disable_current() */
 extern void kasan_enable_current(void);
 
 /* Disable reporting bugs for current task */
 extern void kasan_disable_current(void);
 
-void kasan_unpoison_shadow(const void *address, size_t size);
-
-void kasan_unpoison_task_stack(struct task_struct *task);
+#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
-void kasan_alloc_pages(struct page *page, unsigned int order);
-void kasan_free_pages(struct page *page, unsigned int order);
-
-void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
-			slab_flags_t *flags);
+static inline int kasan_add_zero_shadow(void *start, unsigned long size)
+{
+	return 0;
+}
+static inline void kasan_remove_zero_shadow(void *start,
+					unsigned long size)
+{}
 
-void kasan_poison_slab(struct page *page);
-void kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
-void kasan_poison_object_data(struct kmem_cache *cache, void *object);
-void * __must_check kasan_init_slab_obj(struct kmem_cache *cache,
-					const void *object);
+static inline void kasan_enable_current(void) {}
+static inline void kasan_disable_current(void) {}
 
-void * __must_check kasan_kmalloc_large(const void *ptr, size_t size,
-						gfp_t flags);
-void kasan_kfree_large(void *ptr, unsigned long ip);
-void kasan_poison_kfree(void *ptr, unsigned long ip);
-void * __must_check kasan_kmalloc(struct kmem_cache *s, const void *object,
-					size_t size, gfp_t flags);
-void * __must_check kasan_krealloc(const void *object, size_t new_size,
-					gfp_t flags);
+#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
-void * __must_check kasan_slab_alloc(struct kmem_cache *s, void *object,
-					gfp_t flags);
-bool kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip);
+#ifdef CONFIG_KASAN
 
 struct kasan_cache {
 	int alloc_meta_offset;
 	int free_meta_offset;
 };
 
-/*
- * These functions provide a special case to support backing module
- * allocations with real shadow memory. With KASAN vmalloc, the special
- * case is unnecessary, as the work is handled in the generic case.
- */
-#ifndef CONFIG_KASAN_VMALLOC
-int kasan_module_alloc(void *addr, size_t size);
-void kasan_free_shadow(const struct vm_struct *vm);
-#else
-static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
-static inline void kasan_free_shadow(const struct vm_struct *vm) {}
-#endif
+#ifdef CONFIG_KASAN_HW_TAGS
 
-int kasan_add_zero_shadow(void *start, unsigned long size);
-void kasan_remove_zero_shadow(void *start, unsigned long size);
+DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled);
 
-size_t __ksize(const void *);
-static inline void kasan_unpoison_slab(const void *ptr)
+static __always_inline bool kasan_enabled(void)
 {
-	kasan_unpoison_shadow(ptr, __ksize(ptr));
+	return static_branch_likely(&kasan_flag_enabled);
 }
-size_t kasan_metadata_size(struct kmem_cache *cache);
 
-bool kasan_save_enable_multi_shot(void);
-void kasan_restore_multi_shot(bool enabled);
+#else /* CONFIG_KASAN_HW_TAGS */
 
-#else /* CONFIG_KASAN */
+static inline bool kasan_enabled(void)
+{
+	return true;
+}
 
-static inline void kasan_unpoison_shadow(const void *address, size_t size) {}
+#endif /* CONFIG_KASAN_HW_TAGS */
 
-static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
+slab_flags_t __kasan_never_merge(void);
+static __always_inline slab_flags_t kasan_never_merge(void)
+{
+	if (kasan_enabled())
+		return __kasan_never_merge();
+	return 0;
+}
 
-static inline void kasan_enable_current(void) {}
-static inline void kasan_disable_current(void) {}
+void __kasan_unpoison_range(const void *addr, size_t size);
+static __always_inline void kasan_unpoison_range(const void *addr, size_t size)
+{
+	if (kasan_enabled())
+		__kasan_unpoison_range(addr, size);
+}
+
+void __kasan_alloc_pages(struct page *page, unsigned int order);
+static __always_inline void kasan_alloc_pages(struct page *page,
+						unsigned int order)
+{
+	if (kasan_enabled())
+		__kasan_alloc_pages(page, order);
+}
+
+void __kasan_free_pages(struct page *page, unsigned int order);
+static __always_inline void kasan_free_pages(struct page *page,
+						unsigned int order)
+{
+	if (kasan_enabled())
+		__kasan_free_pages(page, order);
+}
+
+void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
+				slab_flags_t *flags);
+static __always_inline void kasan_cache_create(struct kmem_cache *cache,
+				unsigned int *size, slab_flags_t *flags)
+{
+	if (kasan_enabled())
+		__kasan_cache_create(cache, size, flags);
+}
+
+size_t __kasan_metadata_size(struct kmem_cache *cache);
+static __always_inline size_t kasan_metadata_size(struct kmem_cache *cache)
+{
+	if (kasan_enabled())
+		return __kasan_metadata_size(cache);
+	return 0;
+}
+
+void __kasan_poison_slab(struct page *page);
+static __always_inline void kasan_poison_slab(struct page *page)
+{
+	if (kasan_enabled())
+		__kasan_poison_slab(page);
+}
+
+void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
+static __always_inline void kasan_unpoison_object_data(struct kmem_cache *cache,
+							void *object)
+{
+	if (kasan_enabled())
+		__kasan_unpoison_object_data(cache, object);
+}
+
+void __kasan_poison_object_data(struct kmem_cache *cache, void *object);
+static __always_inline void kasan_poison_object_data(struct kmem_cache *cache,
+							void *object)
+{
+	if (kasan_enabled())
+		__kasan_poison_object_data(cache, object);
+}
+
+void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
+					  const void *object);
+static __always_inline void * __must_check kasan_init_slab_obj(
+				struct kmem_cache *cache, const void *object)
+{
+	if (kasan_enabled())
+		return __kasan_init_slab_obj(cache, object);
+	return (void *)object;
+}
+
+bool __kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip);
+static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object,
+						unsigned long ip)
+{
+	if (kasan_enabled())
+		return __kasan_slab_free(s, object, ip);
+	return false;
+}
+
+void __kasan_slab_free_mempool(void *ptr, unsigned long ip);
+static __always_inline void kasan_slab_free_mempool(void *ptr, unsigned long ip)
+{
+	if (kasan_enabled())
+		__kasan_slab_free_mempool(ptr, ip);
+}
+
+void * __must_check __kasan_slab_alloc(struct kmem_cache *s,
+				       void *object, gfp_t flags);
+static __always_inline void * __must_check kasan_slab_alloc(
+				struct kmem_cache *s, void *object, gfp_t flags)
+{
+	if (kasan_enabled())
+		return __kasan_slab_alloc(s, object, flags);
+	return object;
+}
+
+void * __must_check __kasan_kmalloc(struct kmem_cache *s, const void *object,
+				    size_t size, gfp_t flags);
+static __always_inline void * __must_check kasan_kmalloc(struct kmem_cache *s,
+				const void *object, size_t size, gfp_t flags)
+{
+	if (kasan_enabled())
+		return __kasan_kmalloc(s, object, size, flags);
+	return (void *)object;
+}
+
+void * __must_check __kasan_kmalloc_large(const void *ptr,
+					  size_t size, gfp_t flags);
+static __always_inline void * __must_check kasan_kmalloc_large(const void *ptr,
+						      size_t size, gfp_t flags)
+{
+	if (kasan_enabled())
+		return __kasan_kmalloc_large(ptr, size, flags);
+	return (void *)ptr;
+}
 
+void * __must_check __kasan_krealloc(const void *object,
+				     size_t new_size, gfp_t flags);
+static __always_inline void * __must_check kasan_krealloc(const void *object,
+						 size_t new_size, gfp_t flags)
+{
+	if (kasan_enabled())
+		return __kasan_krealloc(object, new_size, flags);
+	return (void *)object;
+}
+
+void __kasan_kfree_large(void *ptr, unsigned long ip);
+static __always_inline void kasan_kfree_large(void *ptr, unsigned long ip)
+{
+	if (kasan_enabled())
+		__kasan_kfree_large(ptr, ip);
+}
+
+bool kasan_save_enable_multi_shot(void);
+void kasan_restore_multi_shot(bool enabled);
+
+#else /* CONFIG_KASAN */
+
+static inline bool kasan_enabled(void)
+{
+	return false;
+}
+static inline slab_flags_t kasan_never_merge(void)
+{
+	return 0;
+}
+static inline void kasan_unpoison_range(const void *address, size_t size) {}
 static inline void kasan_alloc_pages(struct page *page, unsigned int order) {}
 static inline void kasan_free_pages(struct page *page, unsigned int order) {}
-
 static inline void kasan_cache_create(struct kmem_cache *cache,
 				      unsigned int *size,
 				      slab_flags_t *flags) {}
-
+static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
 static inline void kasan_poison_slab(struct page *page) {}
 static inline void kasan_unpoison_object_data(struct kmem_cache *cache,
 					void *object) {}
@@ -127,54 +277,42 @@ static inline void *kasan_init_slab_obj(struct kmem_cache *cache,
 {
 	return (void *)object;
 }
-
-static inline void *kasan_kmalloc_large(void *ptr, size_t size, gfp_t flags)
+static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
+				   unsigned long ip)
+{
+	return false;
+}
+static inline void kasan_slab_free_mempool(void *ptr, unsigned long ip) {}
+static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
+				   gfp_t flags)
 {
-	return ptr;
+	return object;
 }
-static inline void kasan_kfree_large(void *ptr, unsigned long ip) {}
-static inline void kasan_poison_kfree(void *ptr, unsigned long ip) {}
 static inline void *kasan_kmalloc(struct kmem_cache *s, const void *object,
 				size_t size, gfp_t flags)
 {
 	return (void *)object;
 }
+static inline void *kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags)
+{
+	return (void *)ptr;
+}
 static inline void *kasan_krealloc(const void *object, size_t new_size,
 				 gfp_t flags)
 {
 	return (void *)object;
 }
-
-static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
-				   gfp_t flags)
-{
-	return object;
-}
-static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
-				   unsigned long ip)
-{
-	return false;
-}
-
-static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
-static inline void kasan_free_shadow(const struct vm_struct *vm) {}
-
-static inline int kasan_add_zero_shadow(void *start, unsigned long size)
-{
-	return 0;
-}
-static inline void kasan_remove_zero_shadow(void *start,
-					unsigned long size)
-{}
-
-static inline void kasan_unpoison_slab(const void *ptr) { }
-static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
+static inline void kasan_kfree_large(void *ptr, unsigned long ip) {}
 
 #endif /* CONFIG_KASAN */
 
-#ifdef CONFIG_KASAN_GENERIC
+#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
+void kasan_unpoison_task_stack(struct task_struct *task);
+#else
+static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
+#endif
 
-#define KASAN_SHADOW_INIT 0
+#ifdef CONFIG_KASAN_GENERIC
 
 void kasan_cache_shrink(struct kmem_cache *cache);
 void kasan_cache_shutdown(struct kmem_cache *cache);
@@ -188,36 +326,50 @@ static inline void kasan_record_aux_stack(void *ptr) {}
 
 #endif /* CONFIG_KASAN_GENERIC */
 
-#ifdef CONFIG_KASAN_SW_TAGS
-
-#define KASAN_SHADOW_INIT 0xFF
-
-void kasan_init_tags(void);
+#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
 
-void *kasan_reset_tag(const void *addr);
+static inline void *kasan_reset_tag(const void *addr)
+{
+	return (void *)arch_kasan_reset_tag(addr);
+}
 
 bool kasan_report(unsigned long addr, size_t size,
 		bool is_write, unsigned long ip);
 
-#else /* CONFIG_KASAN_SW_TAGS */
-
-static inline void kasan_init_tags(void) { }
+#else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
 
 static inline void *kasan_reset_tag(const void *addr)
 {
 	return (void *)addr;
 }
 
-#endif /* CONFIG_KASAN_SW_TAGS */
+#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS*/
+
+#ifdef CONFIG_KASAN_SW_TAGS
+void __init kasan_init_sw_tags(void);
+#else
+static inline void kasan_init_sw_tags(void) { }
+#endif
+
+#ifdef CONFIG_KASAN_HW_TAGS
+void kasan_init_hw_tags_cpu(void);
+void __init kasan_init_hw_tags(void);
+#else
+static inline void kasan_init_hw_tags_cpu(void) { }
+static inline void kasan_init_hw_tags(void) { }
+#endif
 
 #ifdef CONFIG_KASAN_VMALLOC
+
 int kasan_populate_vmalloc(unsigned long addr, unsigned long size);
 void kasan_poison_vmalloc(const void *start, unsigned long size);
 void kasan_unpoison_vmalloc(const void *start, unsigned long size);
 void kasan_release_vmalloc(unsigned long start, unsigned long end,
 			   unsigned long free_region_start,
 			   unsigned long free_region_end);
-#else
+
+#else /* CONFIG_KASAN_VMALLOC */
+
 static inline int kasan_populate_vmalloc(unsigned long start,
 					unsigned long size)
 {
@@ -232,7 +384,26 @@ static inline void kasan_release_vmalloc(unsigned long start,
 					 unsigned long end,
 					 unsigned long free_region_start,
 					 unsigned long free_region_end) {}
-#endif
+
+#endif /* CONFIG_KASAN_VMALLOC */
+
+#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
+		!defined(CONFIG_KASAN_VMALLOC)
+
+/*
+ * These functions provide a special case to support backing module
+ * allocations with real shadow memory. With KASAN vmalloc, the special
+ * case is unnecessary, as the work is handled in the generic case.
+ */
+int kasan_module_alloc(void *addr, size_t size);
+void kasan_free_shadow(const struct vm_struct *vm);
+
+#else /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */
+
+static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
+static inline void kasan_free_shadow(const struct vm_struct *vm) {}
+
+#endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */
 
 #ifdef CONFIG_KASAN_INLINE
 void kasan_non_canonical_hook(unsigned long addr);
diff --git a/include/linux/kcov.h b/include/linux/kcov.h
index a10e84707d82..4e3037dc1204 100644
--- a/include/linux/kcov.h
+++ b/include/linux/kcov.h
@@ -52,6 +52,25 @@ static inline void kcov_remote_start_usb(u64 id)
 	kcov_remote_start(kcov_remote_handle(KCOV_SUBSYSTEM_USB, id));
 }
 
+/*
+ * The softirq flavor of kcov_remote_*() functions is introduced as a temporary
+ * work around for kcov's lack of nested remote coverage sections support in
+ * task context. Adding suport for nested sections is tracked in:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=210337
+ */
+
+static inline void kcov_remote_start_usb_softirq(u64 id)
+{
+	if (in_serving_softirq())
+		kcov_remote_start_usb(id);
+}
+
+static inline void kcov_remote_stop_softirq(void)
+{
+	if (in_serving_softirq())
+		kcov_remote_stop();
+}
+
 #else
 
 static inline void kcov_task_init(struct task_struct *t) {}
@@ -66,6 +85,8 @@ static inline u64 kcov_common_handle(void)
 }
 static inline void kcov_remote_start_common(u64 id) {}
 static inline void kcov_remote_start_usb(u64 id) {}
+static inline void kcov_remote_start_usb_softirq(u64 id) {}
+static inline void kcov_remote_stop_softirq(void) {}
 
 #endif /* CONFIG_KCOV */
 #endif /* _LINUX_KCOV_H */
diff --git a/include/linux/kdev_t.h b/include/linux/kdev_t.h
index 85b5151911cf..4856706fbfeb 100644
--- a/include/linux/kdev_t.h
+++ b/include/linux/kdev_t.h
@@ -21,61 +21,61 @@
 	})
 
 /* acceptable for old filesystems */
-static inline bool old_valid_dev(dev_t dev)
+static __always_inline bool old_valid_dev(dev_t dev)
 {
 	return MAJOR(dev) < 256 && MINOR(dev) < 256;
 }
 
-static inline u16 old_encode_dev(dev_t dev)
+static __always_inline u16 old_encode_dev(dev_t dev)
 {
 	return (MAJOR(dev) << 8) | MINOR(dev);
 }
 
-static inline dev_t old_decode_dev(u16 val)
+static __always_inline dev_t old_decode_dev(u16 val)
 {
 	return MKDEV((val >> 8) & 255, val & 255);
 }
 
-static inline u32 new_encode_dev(dev_t dev)
+static __always_inline u32 new_encode_dev(dev_t dev)
 {
 	unsigned major = MAJOR(dev);
 	unsigned minor = MINOR(dev);
 	return (minor & 0xff) | (major << 8) | ((minor & ~0xff) << 12);
 }
 
-static inline dev_t new_decode_dev(u32 dev)
+static __always_inline dev_t new_decode_dev(u32 dev)
 {
 	unsigned major = (dev & 0xfff00) >> 8;
 	unsigned minor = (dev & 0xff) | ((dev >> 12) & 0xfff00);
 	return MKDEV(major, minor);
 }
 
-static inline u64 huge_encode_dev(dev_t dev)
+static __always_inline u64 huge_encode_dev(dev_t dev)
 {
 	return new_encode_dev(dev);
 }
 
-static inline dev_t huge_decode_dev(u64 dev)
+static __always_inline dev_t huge_decode_dev(u64 dev)
 {
 	return new_decode_dev(dev);
 }
 
-static inline int sysv_valid_dev(dev_t dev)
+static __always_inline int sysv_valid_dev(dev_t dev)
 {
 	return MAJOR(dev) < (1<<14) && MINOR(dev) < (1<<18);
 }
 
-static inline u32 sysv_encode_dev(dev_t dev)
+static __always_inline u32 sysv_encode_dev(dev_t dev)
 {
 	return MINOR(dev) | (MAJOR(dev) << 18);
 }
 
-static inline unsigned sysv_major(u32 dev)
+static __always_inline unsigned sysv_major(u32 dev)
 {
 	return (dev >> 18) & 0x3fff;
 }
 
-static inline unsigned sysv_minor(u32 dev)
+static __always_inline unsigned sysv_minor(u32 dev)
 {
 	return dev & 0x3ffff;
 }
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 89f0745c096d..44ae1a7eb9e3 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -67,7 +67,6 @@ static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu)
 /*
  * Number of interrupts per specific IRQ source, since bootup
  */
-extern unsigned int kstat_irqs(unsigned int irq);
 extern unsigned int kstat_irqs_usr(unsigned int irq);
 
 /*
diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
new file mode 100644
index 000000000000..120e5e90fa1d
--- /dev/null
+++ b/include/linux/kvm_dirty_ring.h
@@ -0,0 +1,103 @@
+#ifndef KVM_DIRTY_RING_H
+#define KVM_DIRTY_RING_H
+
+#include <linux/kvm.h>
+
+/**
+ * kvm_dirty_ring: KVM internal dirty ring structure
+ *
+ * @dirty_index: free running counter that points to the next slot in
+ *               dirty_ring->dirty_gfns, where a new dirty page should go
+ * @reset_index: free running counter that points to the next dirty page
+ *               in dirty_ring->dirty_gfns for which dirty trap needs to
+ *               be reenabled
+ * @size:        size of the compact list, dirty_ring->dirty_gfns
+ * @soft_limit:  when the number of dirty pages in the list reaches this
+ *               limit, vcpu that owns this ring should exit to userspace
+ *               to allow userspace to harvest all the dirty pages
+ * @dirty_gfns:  the array to keep the dirty gfns
+ * @index:       index of this dirty ring
+ */
+struct kvm_dirty_ring {
+	u32 dirty_index;
+	u32 reset_index;
+	u32 size;
+	u32 soft_limit;
+	struct kvm_dirty_gfn *dirty_gfns;
+	int index;
+};
+
+#if (KVM_DIRTY_LOG_PAGE_OFFSET == 0)
+/*
+ * If KVM_DIRTY_LOG_PAGE_OFFSET not defined, kvm_dirty_ring.o should
+ * not be included as well, so define these nop functions for the arch.
+ */
+static inline u32 kvm_dirty_ring_get_rsvd_entries(void)
+{
+	return 0;
+}
+
+static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring,
+				       int index, u32 size)
+{
+	return 0;
+}
+
+static inline struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm)
+{
+	return NULL;
+}
+
+static inline int kvm_dirty_ring_reset(struct kvm *kvm,
+				       struct kvm_dirty_ring *ring)
+{
+	return 0;
+}
+
+static inline void kvm_dirty_ring_push(struct kvm_dirty_ring *ring,
+				       u32 slot, u64 offset)
+{
+}
+
+static inline struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring,
+						   u32 offset)
+{
+	return NULL;
+}
+
+static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
+{
+}
+
+static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
+{
+	return true;
+}
+
+#else /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */
+
+u32 kvm_dirty_ring_get_rsvd_entries(void);
+int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size);
+struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm);
+
+/*
+ * called with kvm->slots_lock held, returns the number of
+ * processed pages.
+ */
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring);
+
+/*
+ * returns =0: successfully pushed
+ *         <0: unable to push, need to wait
+ */
+void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset);
+
+/* for use in vm_operations_struct */
+struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset);
+
+void kvm_dirty_ring_free(struct kvm_dirty_ring *ring);
+bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring);
+
+#endif /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */
+
+#endif	/* KVM_DIRTY_RING_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7f2e2a09ebbd..f3b1013fb22c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -34,6 +34,7 @@
 #include <linux/kvm_types.h>
 
 #include <asm/kvm_host.h>
+#include <linux/kvm_dirty_ring.h>
 
 #ifndef KVM_MAX_VCPU_ID
 #define KVM_MAX_VCPU_ID KVM_MAX_VCPUS
@@ -319,6 +320,7 @@ struct kvm_vcpu {
 	bool preempted;
 	bool ready;
 	struct kvm_vcpu_arch arch;
+	struct kvm_dirty_ring dirty_ring;
 };
 
 static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
@@ -349,6 +351,11 @@ struct kvm_memory_slot {
 	u16 as_id;
 };
 
+static inline bool kvm_slot_dirty_track_enabled(struct kvm_memory_slot *slot)
+{
+	return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
+}
+
 static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)
 {
 	return ALIGN(memslot->npages, BITS_PER_LONG) / 8;
@@ -505,6 +512,7 @@ struct kvm {
 	struct srcu_struct irq_srcu;
 	pid_t userspace_pid;
 	unsigned int max_halt_poll_ns;
+	u32 dirty_ring_size;
 };
 
 #define kvm_err(fmt, ...) \
@@ -792,13 +800,12 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			offset_in_page(__gpa), v);			\
 })
 
-int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
-void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn);
+void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
@@ -1478,4 +1485,14 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
 }
 #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
 
+/*
+ * This defines how many reserved entries we want to keep before we
+ * kick the vcpu to the userspace to avoid dirty ring full.  This
+ * value can be tuned to higher if e.g. PML is enabled on the host.
+ */
+#define  KVM_DIRTY_RING_RSVD_ENTRIES  64
+
+/* Max number of entries allowed for each kvm dirty ring */
+#define  KVM_DIRTY_RING_MAX_ENTRIES  65536
+
 #endif
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d827bd7f3bfe..eeb0b52203e9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -665,7 +665,7 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
 {
 	struct mem_cgroup *memcg = page_memcg(page);
 
-	VM_WARN_ON_ONCE_PAGE(!memcg, page);
+	VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page);
 	return mem_cgroup_lruvec(memcg, pgdat);
 }
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 8fbddec26eb8..442c0160caab 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1280,7 +1280,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   ece_support[0x1];
 	u8	   reserved_at_a4[0x7];
 	u8         log_max_srq[0x5];
-	u8         reserved_at_b0[0x2];
+	u8         reserved_at_b0[0x1];
+	u8         uplink_follow[0x1];
 	u8         ts_cqe_to_dest_cqn[0x1];
 	u8         reserved_at_b3[0xd];
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 362579ad0758..ecdf8a8cd6ae 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -31,6 +31,7 @@
 #include <linux/sizes.h>
 #include <linux/sched.h>
 #include <linux/pgtable.h>
+#include <linux/kasan.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -215,6 +216,13 @@ int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
 		loff_t *);
 int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
 		loff_t *);
+/*
+ * Any attempt to mark this function as static leads to build failure
+ * when CONFIG_DEBUG_INFO_BTF is enabled because __add_to_page_cache_locked()
+ * is referred to by BPF code. This must be visible for error injection.
+ */
+int __add_to_page_cache_locked(struct page *page, struct address_space *mapping,
+		pgoff_t index, gfp_t gfp, void **shadowp);
 
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
 
@@ -1421,23 +1429,31 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid)
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
-#ifdef CONFIG_KASAN_SW_TAGS
+#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
+
 static inline u8 page_kasan_tag(const struct page *page)
 {
-	return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
+	if (kasan_enabled())
+		return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
+	return 0xff;
 }
 
 static inline void page_kasan_tag_set(struct page *page, u8 tag)
 {
-	page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT);
-	page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT;
+	if (kasan_enabled()) {
+		page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT);
+		page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT;
+	}
 }
 
 static inline void page_kasan_tag_reset(struct page *page)
 {
-	page_kasan_tag_set(page, 0xff);
+	if (kasan_enabled())
+		page_kasan_tag_set(page, 0xff);
 }
-#else
+
+#else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
+
 static inline u8 page_kasan_tag(const struct page *page)
 {
 	return 0xff;
@@ -1445,7 +1461,8 @@ static inline u8 page_kasan_tag(const struct page *page)
 
 static inline void page_kasan_tag_set(struct page *page, u8 tag) { }
 static inline void page_kasan_tag_reset(struct page *page) { }
-#endif
+
+#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
 
 static inline struct zone *page_zone(const struct page *page)
 {
@@ -2422,8 +2439,9 @@ extern int __meminit early_pfn_to_nid(unsigned long pfn);
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
-extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
-		enum meminit_context, struct vmem_altmap *, int migratetype);
+extern void memmap_init_zone(unsigned long, int, unsigned long,
+		unsigned long, unsigned long, enum meminit_context,
+		struct vmem_altmap *, int migratetype);
 extern void setup_per_zone_wmarks(void);
 extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index 4fa67a8b2265..9e09d11ffe5b 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -96,7 +96,8 @@ void module_arch_cleanup(struct module *mod);
 /* Any cleanup before freeing mod->module_init */
 void module_arch_freeing_init(struct module *mod);
 
-#if defined(CONFIG_KASAN) && !defined(CONFIG_KASAN_VMALLOC)
+#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
+		!defined(CONFIG_KASAN_VMALLOC)
 #include <linux/kasan.h>
 #define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
 #else
diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h
index e200eef6a7fd..7d4ec26d8a3e 100644
--- a/include/linux/page-flags-layout.h
+++ b/include/linux/page-flags-layout.h
@@ -77,7 +77,7 @@
 #define LAST_CPUPID_SHIFT 0
 #endif
 
-#ifdef CONFIG_KASAN_SW_TAGS
+#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
 #define KASAN_TAG_WIDTH 8
 #else
 #define KASAN_TAG_WIDTH 0
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index bf7966776c55..505480217cf1 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -163,8 +163,6 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn);
 static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; }
 #endif
 
-bool arm_pmu_irq_is_nmi(void);
-
 /* Internal functions only for core arm_pmu code */
 struct arm_pmu *armpmu_alloc(void);
 struct arm_pmu *armpmu_alloc_atomic(void);
diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h
index a3a9a878415f..86376779ab31 100644
--- a/include/linux/platform_data/cros_ec_commands.h
+++ b/include/linux/platform_data/cros_ec_commands.h
@@ -1284,6 +1284,8 @@ enum ec_feature_code {
 	EC_FEATURE_SCP = 39,
 	/* The MCU is an Integrated Sensor Hub */
 	EC_FEATURE_ISH = 40,
+	/* New TCPMv2 TYPEC_ prefaced commands supported */
+	EC_FEATURE_TYPEC_CMD = 41,
 };
 
 #define EC_FEATURE_MASK_0(event_code) BIT(event_code % 32)
@@ -5528,6 +5530,159 @@ struct ec_response_regulator_get_voltage {
 	uint32_t voltage_mv;
 } __ec_align4;
 
+/*
+ * Gather all discovery information for the given port and partner type.
+ *
+ * Note that if discovery has not yet completed, only the currently completed
+ * responses will be filled in.   If the discovery data structures are changed
+ * in the process of the command running, BUSY will be returned.
+ *
+ * VDO field sizes are set to the maximum possible number of VDOs a VDM may
+ * contain, while the number of SVIDs here is selected to fit within the PROTO2
+ * maximum parameter size.
+ */
+#define EC_CMD_TYPEC_DISCOVERY 0x0131
+
+enum typec_partner_type {
+	TYPEC_PARTNER_SOP = 0,
+	TYPEC_PARTNER_SOP_PRIME = 1,
+};
+
+struct ec_params_typec_discovery {
+	uint8_t port;
+	uint8_t partner_type; /* enum typec_partner_type */
+} __ec_align1;
+
+struct svid_mode_info {
+	uint16_t svid;
+	uint16_t mode_count;  /* Number of modes partner sent */
+	uint32_t mode_vdo[6]; /* Max VDOs allowed after VDM header is 6 */
+};
+
+struct ec_response_typec_discovery {
+	uint8_t identity_count;    /* Number of identity VDOs partner sent */
+	uint8_t svid_count;	   /* Number of SVIDs partner sent */
+	uint16_t reserved;
+	uint32_t discovery_vdo[6]; /* Max VDOs allowed after VDM header is 6 */
+	struct svid_mode_info svids[0];
+} __ec_align1;
+
+/*
+ * Gather all status information for a port.
+ *
+ * Note: this covers many of the return fields from the deprecated
+ * EC_CMD_USB_PD_CONTROL command, except those that are redundant with the
+ * discovery data.  The "enum pd_cc_states" is defined with the deprecated
+ * EC_CMD_USB_PD_CONTROL command.
+ *
+ * This also combines in the EC_CMD_USB_PD_MUX_INFO flags.
+ */
+#define EC_CMD_TYPEC_STATUS 0x0133
+
+/*
+ * Power role.
+ *
+ * Note this is also used for PD header creation, and values align to those in
+ * the Power Delivery Specification Revision 3.0 (See
+ * 6.2.1.1.4 Port Power Role).
+ */
+enum pd_power_role {
+	PD_ROLE_SINK = 0,
+	PD_ROLE_SOURCE = 1
+};
+
+/*
+ * Data role.
+ *
+ * Note this is also used for PD header creation, and the first two values
+ * align to those in the Power Delivery Specification Revision 3.0 (See
+ * 6.2.1.1.6 Port Data Role).
+ */
+enum pd_data_role {
+	PD_ROLE_UFP = 0,
+	PD_ROLE_DFP = 1,
+	PD_ROLE_DISCONNECTED = 2,
+};
+
+enum pd_vconn_role {
+	PD_ROLE_VCONN_OFF = 0,
+	PD_ROLE_VCONN_SRC = 1,
+};
+
+/*
+ * Note: BIT(0) may be used to determine whether the polarity is CC1 or CC2,
+ * regardless of whether a debug accessory is connected.
+ */
+enum tcpc_cc_polarity {
+	/*
+	 * _CCx: is used to indicate the polarity while not connected to
+	 * a Debug Accessory.  Only one CC line will assert a resistor and
+	 * the other will be open.
+	 */
+	POLARITY_CC1 = 0,
+	POLARITY_CC2 = 1,
+
+	/*
+	 * _CCx_DTS is used to indicate the polarity while connected to a
+	 * SRC Debug Accessory.  Assert resistors on both lines.
+	 */
+	POLARITY_CC1_DTS = 2,
+	POLARITY_CC2_DTS = 3,
+
+	/*
+	 * The current TCPC code relies on these specific POLARITY values.
+	 * Adding in a check to verify if the list grows for any reason
+	 * that this will give a hint that other places need to be
+	 * adjusted.
+	 */
+	POLARITY_COUNT
+};
+
+#define PD_STATUS_EVENT_SOP_DISC_DONE		BIT(0)
+#define PD_STATUS_EVENT_SOP_PRIME_DISC_DONE	BIT(1)
+
+struct ec_params_typec_status {
+	uint8_t port;
+} __ec_align1;
+
+struct ec_response_typec_status {
+	uint8_t pd_enabled;		/* PD communication enabled - bool */
+	uint8_t dev_connected;		/* Device connected - bool */
+	uint8_t sop_connected;		/* Device is SOP PD capable - bool */
+	uint8_t source_cap_count;	/* Number of Source Cap PDOs */
+
+	uint8_t power_role;		/* enum pd_power_role */
+	uint8_t data_role;		/* enum pd_data_role */
+	uint8_t vconn_role;		/* enum pd_vconn_role */
+	uint8_t sink_cap_count;		/* Number of Sink Cap PDOs */
+
+	uint8_t polarity;		/* enum tcpc_cc_polarity */
+	uint8_t cc_state;		/* enum pd_cc_states */
+	uint8_t dp_pin;			/* DP pin mode (MODE_DP_IN_[A-E]) */
+	uint8_t mux_state;		/* USB_PD_MUX* - encoded mux state */
+
+	char tc_state[32];		/* TC state name */
+
+	uint32_t events;		/* PD_STATUS_EVENT bitmask */
+
+	/*
+	 * BCD PD revisions for partners
+	 *
+	 * The format has the PD major reversion in the upper nibble, and PD
+	 * minor version in the next nibble.  Following two nibbles are
+	 * currently 0.
+	 * ex. PD 3.2 would map to 0x3200
+	 *
+	 * PD major/minor will be 0 if no PD device is connected.
+	 */
+	uint16_t sop_revision;
+	uint16_t sop_prime_revision;
+
+	uint32_t source_cap_pdos[7];	/* Max 7 PDOs can be present */
+
+	uint32_t sink_cap_pdos[7];	/* Max 7 PDOs can be present */
+} __ec_align1;
+
 /*****************************************************************************/
 /* The command range 0x200-0x2FF is reserved for Rotor. */
 
diff --git a/include/linux/psci.h b/include/linux/psci.h
index 2a1bfb890e58..4ca0060a3fc4 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -34,6 +34,15 @@ struct psci_operations {
 
 extern struct psci_operations psci_ops;
 
+struct psci_0_1_function_ids {
+	u32 cpu_suspend;
+	u32 cpu_on;
+	u32 cpu_off;
+	u32 migrate;
+};
+
+struct psci_0_1_function_ids get_psci_0_1_function_ids(void);
+
 #if defined(CONFIG_ARM_PSCI_FW)
 int __init psci_dt_init(void);
 #else
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index de0826411311..fd02c5fa60cb 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -86,6 +86,12 @@ void rcu_sched_clock_irq(int user);
 void rcu_report_dead(unsigned int cpu);
 void rcutree_migrate_callbacks(int cpu);
 
+#ifdef CONFIG_TASKS_RCU_GENERIC
+void rcu_init_tasks_generic(void);
+#else
+static inline void rcu_init_tasks_generic(void) { }
+#endif
+
 #ifdef CONFIG_RCU_STALL_COMMON
 void rcu_sysrq_start(void);
 void rcu_sysrq_end(void);
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index b829382de6c3..568909449c13 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -141,12 +141,6 @@ struct rtc_device {
 	 */
 	unsigned long set_offset_nsec;
 
-	bool registered;
-
-	/* Old ABI support */
-	bool nvram_old_abi;
-	struct bin_attribute *nvram;
-
 	time64_t range_min;
 	timeu64_t range_max;
 	time64_t start_secs;
@@ -184,7 +178,7 @@ extern struct rtc_device *devm_rtc_device_register(struct device *dev,
 					const struct rtc_class_ops *ops,
 					struct module *owner);
 struct rtc_device *devm_rtc_allocate_device(struct device *dev);
-int __rtc_register_device(struct module *owner, struct rtc_device *rtc);
+int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc);
 
 extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm);
 extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm);
@@ -227,8 +221,8 @@ static inline bool is_leap_year(unsigned int year)
 	return (!(year % 4) && (year % 100)) || !(year % 400);
 }
 
-#define rtc_register_device(device) \
-	__rtc_register_device(THIS_MODULE, device)
+#define devm_rtc_register_device(device) \
+	__devm_rtc_register_device(THIS_MODULE, device)
 
 #ifdef CONFIG_RTC_HCTOSYS_DEVICE
 extern int rtc_hctosys_ret;
@@ -237,16 +231,14 @@ extern int rtc_hctosys_ret;
 #endif
 
 #ifdef CONFIG_RTC_NVMEM
-int rtc_nvmem_register(struct rtc_device *rtc,
-		       struct nvmem_config *nvmem_config);
-void rtc_nvmem_unregister(struct rtc_device *rtc);
+int devm_rtc_nvmem_register(struct rtc_device *rtc,
+			    struct nvmem_config *nvmem_config);
 #else
-static inline int rtc_nvmem_register(struct rtc_device *rtc,
-				     struct nvmem_config *nvmem_config)
+static inline int devm_rtc_nvmem_register(struct rtc_device *rtc,
+					  struct nvmem_config *nvmem_config)
 {
 	return 0;
 }
-static inline void rtc_nvmem_unregister(struct rtc_device *rtc) {}
 #endif
 
 #ifdef CONFIG_RTC_INTF_SYSFS
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 51d535b69bd6..6e3a5eeec509 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1234,7 +1234,7 @@ struct task_struct {
 	u64				timer_slack_ns;
 	u64				default_timer_slack_ns;
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	unsigned int			kasan_depth;
 #endif
 
diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index 3ed5aa18593f..6205578ab6ee 100644
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -28,6 +28,11 @@ static inline unsigned long map_util_freq(unsigned long util,
 {
 	return (freq + (freq >> 2)) * util / cap;
 }
+
+static inline unsigned long map_util_perf(unsigned long util)
+{
+	return util + (util >> 2);
+}
 #endif /* CONFIG_CPU_FREQ */
 
 #endif /* _LINUX_SCHED_CPUFREQ_H */
diff --git a/include/linux/sizes.h b/include/linux/sizes.h
index 9874f6f67537..1ac79bcee2bb 100644
--- a/include/linux/sizes.h
+++ b/include/linux/sizes.h
@@ -44,6 +44,9 @@
 #define SZ_2G				0x80000000
 
 #define SZ_4G				_AC(0x100000000, ULL)
+#define SZ_8G				_AC(0x200000000, ULL)
+#define SZ_16G				_AC(0x400000000, ULL)
+#define SZ_32G				_AC(0x800000000, ULL)
 #define SZ_64T				_AC(0x400000000000, ULL)
 
 #endif /* __LINUX_SIZES_H__ */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 333bcdc39635..5f60c9e907c9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -366,7 +366,7 @@ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta)
 static inline bool skb_frag_must_loop(struct page *p)
 {
 #if defined(CONFIG_HIGHMEM)
-	if (PageHighMem(p))
+	if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(p))
 		return true;
 #endif
 	return false;
@@ -1203,6 +1203,7 @@ struct skb_seq_state {
 	struct sk_buff	*root_skb;
 	struct sk_buff	*cur_skb;
 	__u8		*frag_data;
+	__u32		frag_off;
 };
 
 void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
diff --git a/include/linux/string.h b/include/linux/string.h
index 1cd63a8a23ab..4fcfb56abcf5 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -267,7 +267,7 @@ void __write_overflow(void) __compiletime_error("detected write beyond size of o
 
 #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE)
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr);
 extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp);
 extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index f3929aff39cf..7688bc983de5 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -251,6 +251,30 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
 	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 #endif /* __SYSCALL_DEFINEx */
 
+/* For split 64-bit arguments on 32-bit architectures */
+#ifdef __LITTLE_ENDIAN
+#define SC_ARG64(name) u32, name##_lo, u32, name##_hi
+#else
+#define SC_ARG64(name) u32, name##_hi, u32, name##_lo
+#endif
+#define SC_VAL64(type, name) ((type) name##_hi << 32 | name##_lo)
+
+#ifdef CONFIG_COMPAT
+#define SYSCALL32_DEFINE1 COMPAT_SYSCALL_DEFINE1
+#define SYSCALL32_DEFINE2 COMPAT_SYSCALL_DEFINE2
+#define SYSCALL32_DEFINE3 COMPAT_SYSCALL_DEFINE3
+#define SYSCALL32_DEFINE4 COMPAT_SYSCALL_DEFINE4
+#define SYSCALL32_DEFINE5 COMPAT_SYSCALL_DEFINE5
+#define SYSCALL32_DEFINE6 COMPAT_SYSCALL_DEFINE6
+#else
+#define SYSCALL32_DEFINE1 SYSCALL_DEFINE1
+#define SYSCALL32_DEFINE2 SYSCALL_DEFINE2
+#define SYSCALL32_DEFINE3 SYSCALL_DEFINE3
+#define SYSCALL32_DEFINE4 SYSCALL_DEFINE4
+#define SYSCALL32_DEFINE5 SYSCALL_DEFINE5
+#define SYSCALL32_DEFINE6 SYSCALL_DEFINE6
+#endif
+
 /*
  * Called before coming back to user-mode. Returning to user-mode with an
  * address limit different than USER_DS can allow to overwrite kernel memory.
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 30bc7a7223bb..0fefeb976877 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -42,6 +42,7 @@ struct vdpa_vq_state {
  * @config: the configuration ops for this device.
  * @index: device index
  * @features_valid: were features initialized? for legacy guests
+ * @nvqs: maximum number of supported virtqueues
  */
 struct vdpa_device {
 	struct device dev;
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 27fb99cfeb02..fe10e8570a52 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -22,6 +22,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int
 #define WQ_FLAG_BOOKMARK	0x04
 #define WQ_FLAG_CUSTOM		0x08
 #define WQ_FLAG_DONE		0x10
+#define WQ_FLAG_PRIORITY	0x20
 
 /*
  * A single wait-queue entry structure:
@@ -164,11 +165,20 @@ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head)
 
 extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+extern void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 
 static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	list_add(&wq_entry->entry, &wq_head->head);
+	struct list_head *head = &wq_head->head;
+	struct wait_queue_entry *wq;
+
+	list_for_each_entry(wq, &wq_head->head, entry) {
+		if (!(wq->flags & WQ_FLAG_PRIORITY))
+			break;
+		head = &wq->entry;
+	}
+	list_add(&wq_entry->entry, head);
 }
 
 /*
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index dd5b5bd781a4..e1c308d8d288 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -140,10 +140,16 @@ struct p9_client {
  *
  * TODO: This needs lots of explanation.
  */
+enum fid_source {
+	FID_FROM_OTHER,
+	FID_FROM_INODE,
+	FID_FROM_DENTRY,
+};
 
 struct p9_fid {
 	struct p9_client *clnt;
 	u32 fid;
+	refcount_t count;
 	int mode;
 	struct p9_qid qid;
 	u32 iounit;
@@ -152,6 +158,7 @@ struct p9_fid {
 	void *rdir;
 
 	struct hlist_node dlist;	/* list of all fids attached to a dentry */
+	struct hlist_node ilist;
 };
 
 /**
diff --git a/include/net/red.h b/include/net/red.h
index fc455445f4b2..932f0d79d60c 100644
--- a/include/net/red.h
+++ b/include/net/red.h
@@ -168,12 +168,14 @@ static inline void red_set_vars(struct red_vars *v)
 	v->qcount	= -1;
 }
 
-static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog)
+static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_log)
 {
 	if (fls(qth_min) + Wlog > 32)
 		return false;
 	if (fls(qth_max) + Wlog > 32)
 		return false;
+	if (Scell_log >= 32)
+		return false;
 	if (qth_max < qth_min)
 		return false;
 	return true;
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 4f4e93bf814c..cc17bc957548 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -58,10 +58,6 @@ struct xdp_sock {
 
 	struct xsk_queue *tx ____cacheline_aligned_in_smp;
 	struct list_head tx_list;
-	/* Mutual exclusion of NAPI TX thread and sendmsg error paths
-	 * in the SKB destructor callback.
-	 */
-	spinlock_t tx_completion_lock;
 	/* Protects generic receive. */
 	spinlock_t rx_lock;
 
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 01755b838c74..eaa8386dbc63 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -73,6 +73,11 @@ struct xsk_buff_pool {
 	bool dma_need_sync;
 	bool unaligned;
 	void *addrs;
+	/* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect:
+	 * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when
+	 * sockets share a single cq when the same netdev and queue id is shared.
+	 */
+	spinlock_t cq_lock;
 	struct xdp_buff_xsk *free_heads[];
 };
 
diff --git a/include/soc/nps/common.h b/include/soc/nps/common.h
deleted file mode 100644
index 8c18dc6d3fde..000000000000
--- a/include/soc/nps/common.h
+++ /dev/null
@@ -1,172 +0,0 @@
-/*
- * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * 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 AUTHORS OR COPYRIGHT HOLDERS
- * 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.
- */
-
-#ifndef SOC_NPS_COMMON_H
-#define SOC_NPS_COMMON_H
-
-#ifdef CONFIG_SMP
-#define NPS_IPI_IRQ					5
-#endif
-
-#define NPS_HOST_REG_BASE			0xF6000000
-
-#define NPS_MSU_BLKID				0x018
-
-#define CTOP_INST_RSPI_GIC_0_R12		0x3C56117E
-#define CTOP_INST_MOV2B_FLIP_R3_B1_B2_INST	0x5B60
-#define CTOP_INST_MOV2B_FLIP_R3_B1_B2_LIMM	0x00010422
-
-#ifndef AUX_IENABLE
-#define AUX_IENABLE				0x40c
-#endif
-
-#define CTOP_AUX_IACK				(0xFFFFF800 + 0x088)
-
-#ifndef __ASSEMBLY__
-
-/* In order to increase compilation test coverage */
-#ifdef CONFIG_ARC
-static inline void nps_ack_gic(void)
-{
-	__asm__ __volatile__ (
-	"       .word %0\n"
-	:
-	: "i"(CTOP_INST_RSPI_GIC_0_R12)
-	: "memory");
-}
-#else
-static inline void nps_ack_gic(void) { }
-#define write_aux_reg(r, v)
-#define read_aux_reg(r) 0
-#endif
-
-/* CPU global ID */
-struct global_id {
-	union {
-		struct {
-#ifdef CONFIG_EZNPS_MTM_EXT
-			u32 __reserved:20, cluster:4, core:4, thread:4;
-#else
-			u32 __reserved:24, cluster:4, core:4;
-#endif
-		};
-		u32 value;
-	};
-};
-
-/*
- * Convert logical to physical CPU IDs
- *
- * The conversion swap bits 1 and 2 of cluster id (out of 4 bits)
- * Now quad of logical clusters id's are adjacent physically,
- * and not like the id's physically came with each cluster.
- * Below table is 4x4 mesh of core clusters as it layout on chip.
- * Cluster ids are in format: logical (physical)
- *
- *    -----------------   ------------------
- * 3 |  5 (3)   7 (7)  | | 13 (11)   15 (15)|
- *
- * 2 |  4 (2)   6 (6)  | | 12 (10)   14 (14)|
- *    -----------------   ------------------
- * 1 |  1 (1)   3 (5)  | |  9  (9)   11 (13)|
- *
- * 0 |  0 (0)   2 (4)  | |  8  (8)   10 (12)|
- *    -----------------   ------------------
- *       0       1            2        3
- */
-static inline int nps_cluster_logic_to_phys(int cluster)
-{
-#ifdef __arc__
-	 __asm__ __volatile__(
-	"       mov r3,%0\n"
-	"       .short %1\n"
-	"       .word %2\n"
-	"       mov %0,r3\n"
-	: "+r"(cluster)
-	: "i"(CTOP_INST_MOV2B_FLIP_R3_B1_B2_INST),
-	  "i"(CTOP_INST_MOV2B_FLIP_R3_B1_B2_LIMM)
-	: "r3");
-#endif
-
-	return cluster;
-}
-
-#define NPS_CPU_TO_CLUSTER_NUM(cpu) \
-	({ struct global_id gid; gid.value = cpu; \
-		nps_cluster_logic_to_phys(gid.cluster); })
-
-struct nps_host_reg_address {
-	union {
-		struct {
-			u32 base:8, cl_x:4, cl_y:4,
-			blkid:6, reg:8, __reserved:2;
-		};
-		u32 value;
-	};
-};
-
-struct nps_host_reg_address_non_cl {
-	union {
-		struct {
-			u32 base:7, blkid:11, reg:12, __reserved:2;
-		};
-		u32 value;
-	};
-};
-
-static inline void *nps_host_reg_non_cl(u32 blkid, u32 reg)
-{
-	struct nps_host_reg_address_non_cl reg_address;
-
-	reg_address.value = NPS_HOST_REG_BASE;
-	reg_address.blkid = blkid;
-	reg_address.reg = reg;
-
-	return (void *)reg_address.value;
-}
-
-static inline void *nps_host_reg(u32 cpu, u32 blkid, u32 reg)
-{
-	struct nps_host_reg_address reg_address;
-	u32 cl = NPS_CPU_TO_CLUSTER_NUM(cpu);
-
-	reg_address.value = NPS_HOST_REG_BASE;
-	reg_address.cl_x  = (cl >> 2) & 0x3;
-	reg_address.cl_y  = cl & 0x3;
-	reg_address.blkid = blkid;
-	reg_address.reg   = reg;
-
-	return (void *)reg_address.value;
-}
-#endif /* __ASSEMBLY__ */
-
-#endif /* SOC_NPS_COMMON_H */
diff --git a/include/soc/nps/mtm.h b/include/soc/nps/mtm.h
deleted file mode 100644
index d2f5e7e3703e..000000000000
--- a/include/soc/nps/mtm.h
+++ /dev/null
@@ -1,59 +0,0 @@
-/*
- * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * 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 AUTHORS OR COPYRIGHT HOLDERS
- * 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.
- */
-
-#ifndef SOC_NPS_MTM_H
-#define SOC_NPS_MTM_H
-
-#define CTOP_INST_HWSCHD_OFF_R3                 0x3B6F00BF
-#define CTOP_INST_HWSCHD_RESTORE_R3             0x3E6F70C3
-
-static inline void hw_schd_save(unsigned int *flags)
-{
-	__asm__ __volatile__(
-	"       .word %1\n"
-	"       st r3,[%0]\n"
-	:
-	: "r"(flags), "i"(CTOP_INST_HWSCHD_OFF_R3)
-	: "r3", "memory");
-}
-
-static inline void hw_schd_restore(unsigned int flags)
-{
-	__asm__ __volatile__(
-	"       mov r3, %0\n"
-	"       .word %1\n"
-	:
-	: "r"(flags), "i"(CTOP_INST_HWSCHD_RESTORE_R3)
-	: "r3");
-}
-
-#endif /* SOC_NPS_MTM_H */
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 4eef374d4413..4a5cc8c64be3 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -231,6 +231,7 @@ enum afs_file_error {
 	afs_file_error_dir_bad_magic,
 	afs_file_error_dir_big,
 	afs_file_error_dir_missing_page,
+	afs_file_error_dir_name_too_long,
 	afs_file_error_dir_over_end,
 	afs_file_error_dir_small,
 	afs_file_error_dir_unmarked_ext,
@@ -488,6 +489,7 @@ enum afs_cb_break_reason {
 	EM(afs_file_error_dir_bad_magic,	"DIR_BAD_MAGIC")	\
 	EM(afs_file_error_dir_big,		"DIR_BIG")		\
 	EM(afs_file_error_dir_missing_page,	"DIR_MISSING_PAGE")	\
+	EM(afs_file_error_dir_name_too_long,	"DIR_NAME_TOO_LONG")	\
 	EM(afs_file_error_dir_over_end,		"DIR_ENT_OVER_END")	\
 	EM(afs_file_error_dir_small,		"DIR_SMALL")		\
 	EM(afs_file_error_dir_unmarked_ext,	"DIR_UNMARKED_EXT")	\
diff --git a/include/trace/events/clk.h b/include/trace/events/clk.h
index cb1aea25c199..e19edc63ee95 100644
--- a/include/trace/events/clk.h
+++ b/include/trace/events/clk.h
@@ -118,6 +118,50 @@ DEFINE_EVENT(clk_rate, clk_set_rate_complete,
 	TP_ARGS(core, rate)
 );
 
+DEFINE_EVENT(clk_rate, clk_set_min_rate,
+
+	TP_PROTO(struct clk_core *core, unsigned long rate),
+
+	TP_ARGS(core, rate)
+);
+
+DEFINE_EVENT(clk_rate, clk_set_max_rate,
+
+	TP_PROTO(struct clk_core *core, unsigned long rate),
+
+	TP_ARGS(core, rate)
+);
+
+DECLARE_EVENT_CLASS(clk_rate_range,
+
+	TP_PROTO(struct clk_core *core, unsigned long min, unsigned long max),
+
+	TP_ARGS(core, min, max),
+
+	TP_STRUCT__entry(
+		__string(        name,           core->name                )
+		__field(unsigned long,           min                       )
+		__field(unsigned long,           max                       )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, core->name);
+		__entry->min = min;
+		__entry->max = max;
+	),
+
+	TP_printk("%s min %lu max %lu", __get_str(name),
+		  (unsigned long)__entry->min,
+		  (unsigned long)__entry->max)
+);
+
+DEFINE_EVENT(clk_rate_range, clk_set_rate_range,
+
+	TP_PROTO(struct clk_core *core, unsigned long min, unsigned long max),
+
+	TP_ARGS(core, min, max)
+);
+
 DECLARE_EVENT_CLASS(clk_parent,
 
 	TP_PROTO(struct clk_core *core, struct clk_core *parent),
diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h
index 0b6869980ba2..e282ce02fa2d 100644
--- a/include/trace/events/iocost.h
+++ b/include/trace/events/iocost.h
@@ -11,7 +11,7 @@ struct ioc_gq;
 
 #include <linux/tracepoint.h>
 
-TRACE_EVENT(iocost_iocg_activate,
+DECLARE_EVENT_CLASS(iocost_iocg_state,
 
 	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
 		u64 last_period, u64 cur_period, u64 vtime),
@@ -59,6 +59,20 @@ TRACE_EVENT(iocost_iocg_activate,
 	)
 );
 
+DEFINE_EVENT(iocost_iocg_state, iocost_iocg_activate,
+	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+		 u64 last_period, u64 cur_period, u64 vtime),
+
+	TP_ARGS(iocg, path, now, last_period, cur_period, vtime)
+);
+
+DEFINE_EVENT(iocost_iocg_state, iocost_iocg_idle,
+	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+		 u64 last_period, u64 cur_period, u64 vtime),
+
+	TP_ARGS(iocg, path, now, last_period, cur_period, vtime)
+);
+
 DECLARE_EVENT_CLASS(iocg_inuse_update,
 
 	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 26cfb0fa8e7e..49d7d0fe29f6 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -399,6 +399,69 @@ TRACE_EVENT(kvm_halt_poll_ns,
 #define trace_kvm_halt_poll_ns_shrink(vcpu_id, new, old) \
 	trace_kvm_halt_poll_ns(false, vcpu_id, new, old)
 
+TRACE_EVENT(kvm_dirty_ring_push,
+	TP_PROTO(struct kvm_dirty_ring *ring, u32 slot, u64 offset),
+	TP_ARGS(ring, slot, offset),
+
+	TP_STRUCT__entry(
+		__field(int, index)
+		__field(u32, dirty_index)
+		__field(u32, reset_index)
+		__field(u32, slot)
+		__field(u64, offset)
+	),
+
+	TP_fast_assign(
+		__entry->index          = ring->index;
+		__entry->dirty_index    = ring->dirty_index;
+		__entry->reset_index    = ring->reset_index;
+		__entry->slot           = slot;
+		__entry->offset         = offset;
+	),
+
+	TP_printk("ring %d: dirty 0x%x reset 0x%x "
+		  "slot %u offset 0x%llx (used %u)",
+		  __entry->index, __entry->dirty_index,
+		  __entry->reset_index,  __entry->slot, __entry->offset,
+		  __entry->dirty_index - __entry->reset_index)
+);
+
+TRACE_EVENT(kvm_dirty_ring_reset,
+	TP_PROTO(struct kvm_dirty_ring *ring),
+	TP_ARGS(ring),
+
+	TP_STRUCT__entry(
+		__field(int, index)
+		__field(u32, dirty_index)
+		__field(u32, reset_index)
+	),
+
+	TP_fast_assign(
+		__entry->index          = ring->index;
+		__entry->dirty_index    = ring->dirty_index;
+		__entry->reset_index    = ring->reset_index;
+	),
+
+	TP_printk("ring %d: dirty 0x%x reset 0x%x (used %u)",
+		  __entry->index, __entry->dirty_index, __entry->reset_index,
+		  __entry->dirty_index - __entry->reset_index)
+);
+
+TRACE_EVENT(kvm_dirty_ring_exit,
+	TP_PROTO(struct kvm_vcpu *vcpu),
+	TP_ARGS(vcpu),
+
+	TP_STRUCT__entry(
+	    __field(int, vcpu_id)
+	),
+
+	TP_fast_assign(
+	    __entry->vcpu_id = vcpu->vcpu_id;
+	),
+
+	TP_printk("vcpu %d", __entry->vcpu_id)
+);
+
 #endif /* _TRACE_KVM_MAIN_H */
 
 /* This part must be outside protection */
diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h
index 52e8bcb33981..cf7399f03b71 100644
--- a/include/uapi/linux/bcache.h
+++ b/include/uapi/linux/bcache.h
@@ -213,7 +213,7 @@ struct cache_sb_disk {
 		__le16		keys;
 	};
 	__le64			d[SB_JOURNAL_BUCKETS];	/* journal buckets */
-	__le16			bucket_size_hi;
+	__le16			obso_bucket_size_hi;	/* obsoleted */
 };
 
 /*
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 874cc12a34d9..82708c6db432 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -75,8 +75,9 @@ struct rtnl_link_stats {
  *
  * @rx_dropped: Number of packets received but not processed,
  *   e.g. due to lack of resources or unsupported protocol.
- *   For hardware interfaces this counter should not include packets
- *   dropped by the device which are counted separately in
+ *   For hardware interfaces this counter may include packets discarded
+ *   due to L2 address filtering but should not include packets dropped
+ *   by the device due to buffer exhaustion which are counted separately in
  *   @rx_missed_errors (since procfs folds those two counters together).
  *
  * @tx_dropped: Number of packets dropped on their way to transmission,
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index ca41220b40b8..374c67875cdb 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -250,6 +250,8 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_ARM_NISV         28
 #define KVM_EXIT_X86_RDMSR        29
 #define KVM_EXIT_X86_WRMSR        30
+#define KVM_EXIT_DIRTY_RING_FULL  31
+#define KVM_EXIT_AP_RESET_HOLD    32
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -572,6 +574,7 @@ struct kvm_vapic_addr {
 #define KVM_MP_STATE_CHECK_STOP        6
 #define KVM_MP_STATE_OPERATING         7
 #define KVM_MP_STATE_LOAD              8
+#define KVM_MP_STATE_AP_RESET_HOLD     9
 
 struct kvm_mp_state {
 	__u32 mp_state;
@@ -1053,6 +1056,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_X86_USER_SPACE_MSR 188
 #define KVM_CAP_X86_MSR_FILTER 189
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
+#define KVM_CAP_SYS_HYPERV_CPUID 191
+#define KVM_CAP_DIRTY_LOG_RING 192
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1511,7 +1516,7 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */
 #define KVM_CLEAR_DIRTY_LOG          _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
 
-/* Available with KVM_CAP_HYPERV_CPUID */
+/* Available with KVM_CAP_HYPERV_CPUID (vcpu) / KVM_CAP_SYS_HYPERV_CPUID (system) */
 #define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
 
 /* Available with KVM_CAP_ARM_SVE */
@@ -1557,6 +1562,9 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_X86_MSR_FILTER */
 #define KVM_X86_SET_MSR_FILTER	_IOW(KVMIO,  0xc6, struct kvm_msr_filter)
 
+/* Available with KVM_CAP_DIRTY_LOG_RING */
+#define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1710,4 +1718,52 @@ struct kvm_hyperv_eventfd {
 #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
 #define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
 
+/*
+ * Arch needs to define the macro after implementing the dirty ring
+ * feature.  KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the
+ * starting page offset of the dirty ring structures.
+ */
+#ifndef KVM_DIRTY_LOG_PAGE_OFFSET
+#define KVM_DIRTY_LOG_PAGE_OFFSET 0
+#endif
+
+/*
+ * KVM dirty GFN flags, defined as:
+ *
+ * |---------------+---------------+--------------|
+ * | bit 1 (reset) | bit 0 (dirty) | Status       |
+ * |---------------+---------------+--------------|
+ * |             0 |             0 | Invalid GFN  |
+ * |             0 |             1 | Dirty GFN    |
+ * |             1 |             X | GFN to reset |
+ * |---------------+---------------+--------------|
+ *
+ * Lifecycle of a dirty GFN goes like:
+ *
+ *      dirtied         harvested        reset
+ * 00 -----------> 01 -------------> 1X -------+
+ *  ^                                          |
+ *  |                                          |
+ *  +------------------------------------------+
+ *
+ * The userspace program is only responsible for the 01->1X state
+ * conversion after harvesting an entry.  Also, it must not skip any
+ * dirty bits, so that dirty bits are always harvested in sequence.
+ */
+#define KVM_DIRTY_GFN_F_DIRTY           BIT(0)
+#define KVM_DIRTY_GFN_F_RESET           BIT(1)
+#define KVM_DIRTY_GFN_F_MASK            0x3
+
+/*
+ * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of
+ * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn.  The
+ * size of the gfn buffer is decided by the first argument when
+ * enabling KVM_CAP_DIRTY_LOG_RING.
+ */
+struct kvm_dirty_gfn {
+	__u32 flags;
+	__u32 slot;
+	__u64 offset;
+};
+
 #endif /* __LINUX_KVM_H */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 28b6ee53305f..b1633e7ba529 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -293,6 +293,7 @@ enum nft_rule_compat_attributes {
  * @NFT_SET_EVAL: set can be updated from the evaluation path
  * @NFT_SET_OBJECT: set contains stateful objects
  * @NFT_SET_CONCAT: set contains a concatenation
+ * @NFT_SET_EXPR: set contains expressions
  */
 enum nft_set_flags {
 	NFT_SET_ANONYMOUS		= 0x1,
@@ -303,6 +304,7 @@ enum nft_set_flags {
 	NFT_SET_EVAL			= 0x20,
 	NFT_SET_OBJECT			= 0x40,
 	NFT_SET_CONCAT			= 0x80,
+	NFT_SET_EXPR			= 0x100,
 };
 
 /**
@@ -706,6 +708,7 @@ enum nft_dynset_ops {
 
 enum nft_dynset_flags {
 	NFT_DYNSET_F_INV	= (1 << 0),
+	NFT_DYNSET_F_EXPR	= (1 << 1),
 };
 
 /**
diff --git a/include/uapi/linux/ppp-ioctl.h b/include/uapi/linux/ppp-ioctl.h
index 8dbecb3ad036..1cc5ce0ae062 100644
--- a/include/uapi/linux/ppp-ioctl.h
+++ b/include/uapi/linux/ppp-ioctl.h
@@ -116,7 +116,7 @@ struct pppol2tp_ioc_stats {
 #define PPPIOCGCHAN	_IOR('t', 55, int)	/* get ppp channel number */
 #define PPPIOCGL2TPSTATS _IOR('t', 54, struct pppol2tp_ioc_stats)
 #define PPPIOCBRIDGECHAN _IOW('t', 53, int)	/* bridge one channel to another */
-#define PPPIOCUNBRIDGECHAN _IO('t', 54)	/* unbridge channel */
+#define PPPIOCUNBRIDGECHAN _IO('t', 52)	/* unbridge channel */
 
 #define SIOCGPPPSTATS   (SIOCDEVPRIVATE + 0)
 #define SIOCGPPPVER     (SIOCDEVPRIVATE + 1)	/* NEVER change this!! */
diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
index b052355ac7a3..bc1c0621f5ed 100644
--- a/include/uapi/linux/virtio_ids.h
+++ b/include/uapi/linux/virtio_ids.h
@@ -29,24 +29,30 @@
  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  * SUCH DAMAGE. */
 
-#define VIRTIO_ID_NET		1 /* virtio net */
-#define VIRTIO_ID_BLOCK		2 /* virtio block */
-#define VIRTIO_ID_CONSOLE	3 /* virtio console */
-#define VIRTIO_ID_RNG		4 /* virtio rng */
-#define VIRTIO_ID_BALLOON	5 /* virtio balloon */
-#define VIRTIO_ID_RPMSG		7 /* virtio remote processor messaging */
-#define VIRTIO_ID_SCSI		8 /* virtio scsi */
-#define VIRTIO_ID_9P		9 /* 9p virtio console */
-#define VIRTIO_ID_RPROC_SERIAL 11 /* virtio remoteproc serial link */
-#define VIRTIO_ID_CAIF	       12 /* Virtio caif */
-#define VIRTIO_ID_GPU          16 /* virtio GPU */
-#define VIRTIO_ID_INPUT        18 /* virtio input */
-#define VIRTIO_ID_VSOCK        19 /* virtio vsock transport */
-#define VIRTIO_ID_CRYPTO       20 /* virtio crypto */
-#define VIRTIO_ID_IOMMU        23 /* virtio IOMMU */
-#define VIRTIO_ID_MEM          24 /* virtio mem */
-#define VIRTIO_ID_FS           26 /* virtio filesystem */
-#define VIRTIO_ID_PMEM         27 /* virtio pmem */
-#define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */
+#define VIRTIO_ID_NET			1 /* virtio net */
+#define VIRTIO_ID_BLOCK			2 /* virtio block */
+#define VIRTIO_ID_CONSOLE		3 /* virtio console */
+#define VIRTIO_ID_RNG			4 /* virtio rng */
+#define VIRTIO_ID_BALLOON		5 /* virtio balloon */
+#define VIRTIO_ID_IOMEM			6 /* virtio ioMemory */
+#define VIRTIO_ID_RPMSG			7 /* virtio remote processor messaging */
+#define VIRTIO_ID_SCSI			8 /* virtio scsi */
+#define VIRTIO_ID_9P			9 /* 9p virtio console */
+#define VIRTIO_ID_MAC80211_WLAN		10 /* virtio WLAN MAC */
+#define VIRTIO_ID_RPROC_SERIAL		11 /* virtio remoteproc serial link */
+#define VIRTIO_ID_CAIF			12 /* Virtio caif */
+#define VIRTIO_ID_MEMORY_BALLOON	13 /* virtio memory balloon */
+#define VIRTIO_ID_GPU			16 /* virtio GPU */
+#define VIRTIO_ID_CLOCK			17 /* virtio clock/timer */
+#define VIRTIO_ID_INPUT			18 /* virtio input */
+#define VIRTIO_ID_VSOCK			19 /* virtio vsock transport */
+#define VIRTIO_ID_CRYPTO		20 /* virtio crypto */
+#define VIRTIO_ID_SIGNAL_DIST		21 /* virtio signal distribution device */
+#define VIRTIO_ID_PSTORE		22 /* virtio pstore device */
+#define VIRTIO_ID_IOMMU			23 /* virtio IOMMU */
+#define VIRTIO_ID_MEM			24 /* virtio mem */
+#define VIRTIO_ID_FS			26 /* virtio filesystem */
+#define VIRTIO_ID_PMEM			27 /* virtio pmem */
+#define VIRTIO_ID_MAC80211_HWSIM	29 /* virtio mac80211-hwsim */
 
 #endif /* _LINUX_VIRTIO_IDS_H */
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index 8c15a7d336a0..dba3827c43ca 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -279,6 +279,7 @@ enum hl_device_status {
  * HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason
  * HL_INFO_SYNC_MANAGER  - Retrieve sync manager info per dcore
  * HL_INFO_TOTAL_ENERGY  - Retrieve total energy consumption
+ * HL_INFO_PLL_FREQUENCY - Retrieve PLL frequency
  */
 #define HL_INFO_HW_IP_INFO		0
 #define HL_INFO_HW_EVENTS		1
@@ -425,6 +426,8 @@ struct hl_info_sync_manager {
  * @ctx_device_in_reset_drop_cnt: context dropped due to device in reset
  * @total_max_cs_in_flight_drop_cnt: total dropped due to maximum CS in-flight
  * @ctx_max_cs_in_flight_drop_cnt: context dropped due to maximum CS in-flight
+ * @total_validation_drop_cnt: total dropped due to validation error
+ * @ctx_validation_drop_cnt: context dropped due to validation error
  */
 struct hl_info_cs_counters {
 	__u64 total_out_of_mem_drop_cnt;
@@ -437,6 +440,8 @@ struct hl_info_cs_counters {
 	__u64 ctx_device_in_reset_drop_cnt;
 	__u64 total_max_cs_in_flight_drop_cnt;
 	__u64 ctx_max_cs_in_flight_drop_cnt;
+	__u64 total_validation_drop_cnt;
+	__u64 ctx_validation_drop_cnt;
 };
 
 enum gaudi_dcores {
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index 00c7235ae93e..2c43b0ef1e4d 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -192,7 +192,7 @@ void xs_suspend_cancel(void);
 
 struct work_struct;
 
-void xenbus_probe(struct work_struct *);
+void xenbus_probe(void);
 
 #define XENBUS_IS_ERR_READ(str) ({			\
 	if (!IS_ERR(str) && strlen(str) == 0) {		\
diff --git a/init/init_task.c b/init/init_task.c
index 15f6eb93a04f..8a992d73e6fb 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -176,7 +176,7 @@ struct task_struct init_task
 	.numa_group	= NULL,
 	.numa_faults	= NULL,
 #endif
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	.kasan_depth	= 1,
 #endif
 #ifdef CONFIG_KCSAN
diff --git a/init/main.c b/init/main.c
index 6feee7f11eaf..c68d784376ca 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1480,14 +1480,8 @@ void __init console_on_rootfs(void)
 	struct file *file = filp_open("/dev/console", O_RDWR, 0);
 
 	if (IS_ERR(file)) {
-		pr_err("Warning: unable to open an initial console. Fallback to ttynull.\n");
-		register_ttynull_console();
-
-		file = filp_open("/dev/console", O_RDWR, 0);
-		if (IS_ERR(file)) {
-			pr_err("Warning: Failed to add ttynull console. No stdin, stdout, and stderr for the init process!\n");
-			return;
-		}
+		pr_err("Warning: unable to open an initial console.\n");
+		return;
 	}
 	init_dup(file);
 	init_dup(file);
@@ -1518,6 +1512,7 @@ static noinline void __init kernel_init_freeable(void)
 
 	init_mm_internals();
 
+	rcu_init_tasks_generic();
 	do_pre_smp_initcalls();
 	lockup_detector_init();
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 7e848200cd26..c1ac7f964bc9 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -152,6 +152,7 @@ static void htab_init_buckets(struct bpf_htab *htab)
 			lockdep_set_class(&htab->buckets[i].lock,
 					  &htab->lockdep_key);
 		}
+		cond_resched();
 	}
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4caf06fe4152..c3bb03c8371f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -17,7 +17,6 @@
 #include <linux/fs.h>
 #include <linux/license.h>
 #include <linux/filter.h>
-#include <linux/version.h>
 #include <linux/kernel.h>
 #include <linux/idr.h>
 #include <linux/cred.h>
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index e73c07593024..175b7b42bfc4 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -37,7 +37,7 @@ retry:
 		if (!task) {
 			++*tid;
 			goto retry;
-		} else if (skip_if_dup_files && task->tgid != task->pid &&
+		} else if (skip_if_dup_files && !thread_group_leader(task) &&
 			   task->files == task->group_leader->files) {
 			put_task_struct(task);
 			task = NULL;
@@ -151,13 +151,14 @@ again:
 		curr_task = info->task;
 		curr_fd = info->fd;
 	} else {
-		curr_task = task_seq_get_next(ns, &curr_tid, true);
-		if (!curr_task) {
-			info->task = NULL;
-			return NULL;
-		}
-
-		/* set info->task and info->tid */
+                curr_task = task_seq_get_next(ns, &curr_tid, true);
+                if (!curr_task) {
+                        info->task = NULL;
+                        info->tid = curr_tid;
+                        return NULL;
+                }
+
+                /* set info->task and info->tid */
 		info->task = curr_task;
 		if (curr_tid == info->tid) {
 			curr_fd = info->fd;
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 191c329e482a..32596fdbcd5b 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -908,6 +908,8 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	opt = fs_parse(fc, cgroup1_fs_parameters, param, &result);
 	if (opt == -ENOPARAM) {
 		if (strcmp(param->key, "source") == 0) {
+			if (fc->source)
+				return invalf(fc, "Multiple sources not supported");
 			fc->source = param->string;
 			param->string = NULL;
 			return 0;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index fefa21981027..613845769103 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -244,7 +244,7 @@ bool cgroup_ssid_enabled(int ssid)
  *
  * The default hierarchy is the v2 interface of cgroup and this function
  * can be used to test whether a cgroup is on the default hierarchy for
- * cases where a subsystem should behave differnetly depending on the
+ * cases where a subsystem should behave differently depending on the
  * interface version.
  *
  * List of changed behaviors:
@@ -262,7 +262,7 @@ bool cgroup_ssid_enabled(int ssid)
  *   "cgroup.procs" instead.
  *
  * - "cgroup.procs" is not sorted.  pids will be unique unless they got
- *   recycled inbetween reads.
+ *   recycled in-between reads.
  *
  * - "release_agent" and "notify_on_release" are removed.  Replacement
  *   notification mechanism will be implemented.
@@ -342,7 +342,7 @@ static bool cgroup_is_mixable(struct cgroup *cgrp)
 	return !cgroup_parent(cgrp);
 }
 
-/* can @cgrp become a thread root? should always be true for a thread root */
+/* can @cgrp become a thread root? Should always be true for a thread root */
 static bool cgroup_can_be_thread_root(struct cgroup *cgrp)
 {
 	/* mixables don't care */
@@ -527,7 +527,7 @@ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp,
  * the root css is returned, so this function always returns a valid css.
  *
  * The returned css is not guaranteed to be online, and therefore it is the
- * callers responsiblity to tryget a reference for it.
+ * callers responsibility to try get a reference for it.
  */
 struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
 					 struct cgroup_subsys *ss)
@@ -699,7 +699,7 @@ EXPORT_SYMBOL_GPL(of_css);
 			;						\
 		else
 
-/* walk live descendants in preorder */
+/* walk live descendants in pre order */
 #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp)		\
 	css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL))	\
 		if (({ lockdep_assert_held(&cgroup_mutex);		\
@@ -933,7 +933,7 @@ void put_css_set_locked(struct css_set *cset)
 
 	WARN_ON_ONCE(!list_empty(&cset->threaded_csets));
 
-	/* This css_set is dead. unlink it and release cgroup and css refs */
+	/* This css_set is dead. Unlink it and release cgroup and css refs */
 	for_each_subsys(ss, ssid) {
 		list_del(&cset->e_cset_node[ssid]);
 		css_put(cset->subsys[ssid]);
@@ -1058,7 +1058,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
 
 	/*
 	 * Build the set of subsystem state objects that we want to see in the
-	 * new css_set. while subsystems can change globally, the entries here
+	 * new css_set. While subsystems can change globally, the entries here
 	 * won't change, so no need for locking.
 	 */
 	for_each_subsys(ss, i) {
@@ -1148,7 +1148,7 @@ static void link_css_set(struct list_head *tmp_links, struct css_set *cset,
 
 	/*
 	 * Always add links to the tail of the lists so that the lists are
-	 * in choronological order.
+	 * in chronological order.
 	 */
 	list_move_tail(&link->cset_link, &cgrp->cset_links);
 	list_add_tail(&link->cgrp_link, &cset->cgrp_links);
@@ -3654,7 +3654,7 @@ static ssize_t cgroup_freeze_write(struct kernfs_open_file *of,
 
 static int cgroup_file_open(struct kernfs_open_file *of)
 {
-	struct cftype *cft = of->kn->priv;
+	struct cftype *cft = of_cft(of);
 
 	if (cft->open)
 		return cft->open(of);
@@ -3663,7 +3663,7 @@ static int cgroup_file_open(struct kernfs_open_file *of)
 
 static void cgroup_file_release(struct kernfs_open_file *of)
 {
-	struct cftype *cft = of->kn->priv;
+	struct cftype *cft = of_cft(of);
 
 	if (cft->release)
 		cft->release(of);
@@ -3674,7 +3674,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 {
 	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
 	struct cgroup *cgrp = of->kn->parent->priv;
-	struct cftype *cft = of->kn->priv;
+	struct cftype *cft = of_cft(of);
 	struct cgroup_subsys_state *css;
 	int ret;
 
@@ -3724,7 +3724,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 
 static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt)
 {
-	struct cftype *cft = of->kn->priv;
+	struct cftype *cft = of_cft(of);
 
 	if (cft->poll)
 		return cft->poll(of, pt);
@@ -4134,7 +4134,7 @@ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
 	 * implies that if we observe !CSS_RELEASED on @pos in this RCU
 	 * critical section, the one pointed to by its next pointer is
 	 * guaranteed to not have finished its RCU grace period even if we
-	 * have dropped rcu_read_lock() inbetween iterations.
+	 * have dropped rcu_read_lock() in-between iterations.
 	 *
 	 * If @pos has CSS_RELEASED set, its next pointer can't be
 	 * dereferenced; however, as each css is given a monotonically
@@ -4382,7 +4382,7 @@ static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it)
 }
 
 /**
- * css_task_iter_advance_css_set - advance a task itererator to the next css_set
+ * css_task_iter_advance_css_set - advance a task iterator to the next css_set
  * @it: the iterator to advance
  *
  * Advance @it to the next css_set to walk.
@@ -6308,7 +6308,7 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
  *
  * Find the cgroup at @path on the default hierarchy, increment its
  * reference count and return it.  Returns pointer to the found cgroup on
- * success, ERR_PTR(-ENOENT) if @path doens't exist and ERR_PTR(-ENOTDIR)
+ * success, ERR_PTR(-ENOENT) if @path doesn't exist and ERR_PTR(-ENOTDIR)
  * if @path points to a non-directory.
  */
 struct cgroup *cgroup_get_from_path(const char *path)
diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config
index 53d688bdd894..eb0029c9a6a6 100644
--- a/kernel/configs/android-recommended.config
+++ b/kernel/configs/android-recommended.config
@@ -81,7 +81,6 @@ CONFIG_INPUT_JOYSTICK=y
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_TABLET=y
 CONFIG_INPUT_UINPUT=y
-CONFIG_ION=y
 CONFIG_JOYSTICK_XPAD=y
 CONFIG_JOYSTICK_XPAD_FF=y
 CONFIG_JOYSTICK_XPAD_LEDS=y
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index fd2db2665fc6..479fc145acfc 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -20,6 +20,10 @@ config DMA_OPS
 config DMA_OPS_BYPASS
 	bool
 
+# Lets platform IOMMU driver choose between bypass and IOMMU
+config ARCH_HAS_DMA_MAP_DIRECT
+	bool
+
 config NEED_SG_DMA_LENGTH
 	bool
 
@@ -220,3 +224,12 @@ config DMA_API_DEBUG_SG
 	  is technically out-of-spec.
 
 	  If unsure, say N.
+
+config DMA_MAP_BENCHMARK
+	bool "Enable benchmarking of streaming DMA mapping"
+	depends on DEBUG_FS
+	help
+	  Provides /sys/kernel/debug/dma_map_benchmark that helps with testing
+	  performance of dma_(un)map_page.
+
+	  See tools/testing/selftests/dma/dma_map_benchmark.c
diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile
index cd1d86358a7a..0dd65ec1d234 100644
--- a/kernel/dma/Makefile
+++ b/kernel/dma/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_DMA_API_DEBUG)		+= debug.o
 obj-$(CONFIG_SWIOTLB)			+= swiotlb.o
 obj-$(CONFIG_DMA_COHERENT_POOL)		+= pool.o
 obj-$(CONFIG_DMA_REMAP)			+= remap.o
+obj-$(CONFIG_DMA_MAP_BENCHMARK)		+= map_benchmark.o
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 16b95ff12e4d..3d63d91cba5c 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -20,7 +20,7 @@
  *   coders, etc.
  *
  *   Such devices often require big memory buffers (a full HD frame
- *   is, for instance, more then 2 mega pixels large, i.e. more than 6
+ *   is, for instance, more than 2 mega pixels large, i.e. more than 6
  *   MB of memory), which makes mechanisms such as kmalloc() or
  *   alloc_page() ineffective.
  *
diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
new file mode 100644
index 000000000000..b1496e744c68
--- /dev/null
+++ b/kernel/dma/map_benchmark.c
@@ -0,0 +1,361 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Hisilicon Limited.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/math64.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/timekeeping.h>
+
+#define DMA_MAP_BENCHMARK	_IOWR('d', 1, struct map_benchmark)
+#define DMA_MAP_MAX_THREADS	1024
+#define DMA_MAP_MAX_SECONDS	300
+
+#define DMA_MAP_BIDIRECTIONAL	0
+#define DMA_MAP_TO_DEVICE	1
+#define DMA_MAP_FROM_DEVICE	2
+
+struct map_benchmark {
+	__u64 avg_map_100ns; /* average map latency in 100ns */
+	__u64 map_stddev; /* standard deviation of map latency */
+	__u64 avg_unmap_100ns; /* as above */
+	__u64 unmap_stddev;
+	__u32 threads; /* how many threads will do map/unmap in parallel */
+	__u32 seconds; /* how long the test will last */
+	__s32 node; /* which numa node this benchmark will run on */
+	__u32 dma_bits; /* DMA addressing capability */
+	__u32 dma_dir; /* DMA data direction */
+	__u64 expansion[10];	/* For future use */
+};
+
+struct map_benchmark_data {
+	struct map_benchmark bparam;
+	struct device *dev;
+	struct dentry  *debugfs;
+	enum dma_data_direction dir;
+	atomic64_t sum_map_100ns;
+	atomic64_t sum_unmap_100ns;
+	atomic64_t sum_sq_map;
+	atomic64_t sum_sq_unmap;
+	atomic64_t loops;
+};
+
+static int map_benchmark_thread(void *data)
+{
+	void *buf;
+	dma_addr_t dma_addr;
+	struct map_benchmark_data *map = data;
+	int ret = 0;
+
+	buf = (void *)__get_free_page(GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	while (!kthread_should_stop())  {
+		u64 map_100ns, unmap_100ns, map_sq, unmap_sq;
+		ktime_t map_stime, map_etime, unmap_stime, unmap_etime;
+		ktime_t map_delta, unmap_delta;
+
+		/*
+		 * for a non-coherent device, if we don't stain them in the
+		 * cache, this will give an underestimate of the real-world
+		 * overhead of BIDIRECTIONAL or TO_DEVICE mappings;
+		 * 66 means evertything goes well! 66 is lucky.
+		 */
+		if (map->dir != DMA_FROM_DEVICE)
+			memset(buf, 0x66, PAGE_SIZE);
+
+		map_stime = ktime_get();
+		dma_addr = dma_map_single(map->dev, buf, PAGE_SIZE, map->dir);
+		if (unlikely(dma_mapping_error(map->dev, dma_addr))) {
+			pr_err("dma_map_single failed on %s\n",
+				dev_name(map->dev));
+			ret = -ENOMEM;
+			goto out;
+		}
+		map_etime = ktime_get();
+		map_delta = ktime_sub(map_etime, map_stime);
+
+		unmap_stime = ktime_get();
+		dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir);
+		unmap_etime = ktime_get();
+		unmap_delta = ktime_sub(unmap_etime, unmap_stime);
+
+		/* calculate sum and sum of squares */
+
+		map_100ns = div64_ul(map_delta,  100);
+		unmap_100ns = div64_ul(unmap_delta, 100);
+		map_sq = map_100ns * map_100ns;
+		unmap_sq = unmap_100ns * unmap_100ns;
+
+		atomic64_add(map_100ns, &map->sum_map_100ns);
+		atomic64_add(unmap_100ns, &map->sum_unmap_100ns);
+		atomic64_add(map_sq, &map->sum_sq_map);
+		atomic64_add(unmap_sq, &map->sum_sq_unmap);
+		atomic64_inc(&map->loops);
+	}
+
+out:
+	free_page((unsigned long)buf);
+	return ret;
+}
+
+static int do_map_benchmark(struct map_benchmark_data *map)
+{
+	struct task_struct **tsk;
+	int threads = map->bparam.threads;
+	int node = map->bparam.node;
+	const cpumask_t *cpu_mask = cpumask_of_node(node);
+	u64 loops;
+	int ret = 0;
+	int i;
+
+	tsk = kmalloc_array(threads, sizeof(*tsk), GFP_KERNEL);
+	if (!tsk)
+		return -ENOMEM;
+
+	get_device(map->dev);
+
+	for (i = 0; i < threads; i++) {
+		tsk[i] = kthread_create_on_node(map_benchmark_thread, map,
+				map->bparam.node, "dma-map-benchmark/%d", i);
+		if (IS_ERR(tsk[i])) {
+			pr_err("create dma_map thread failed\n");
+			ret = PTR_ERR(tsk[i]);
+			goto out;
+		}
+
+		if (node != NUMA_NO_NODE)
+			kthread_bind_mask(tsk[i], cpu_mask);
+	}
+
+	/* clear the old value in the previous benchmark */
+	atomic64_set(&map->sum_map_100ns, 0);
+	atomic64_set(&map->sum_unmap_100ns, 0);
+	atomic64_set(&map->sum_sq_map, 0);
+	atomic64_set(&map->sum_sq_unmap, 0);
+	atomic64_set(&map->loops, 0);
+
+	for (i = 0; i < threads; i++)
+		wake_up_process(tsk[i]);
+
+	msleep_interruptible(map->bparam.seconds * 1000);
+
+	/* wait for the completion of benchmark threads */
+	for (i = 0; i < threads; i++) {
+		ret = kthread_stop(tsk[i]);
+		if (ret)
+			goto out;
+	}
+
+	loops = atomic64_read(&map->loops);
+	if (likely(loops > 0)) {
+		u64 map_variance, unmap_variance;
+		u64 sum_map = atomic64_read(&map->sum_map_100ns);
+		u64 sum_unmap = atomic64_read(&map->sum_unmap_100ns);
+		u64 sum_sq_map = atomic64_read(&map->sum_sq_map);
+		u64 sum_sq_unmap = atomic64_read(&map->sum_sq_unmap);
+
+		/* average latency */
+		map->bparam.avg_map_100ns = div64_u64(sum_map, loops);
+		map->bparam.avg_unmap_100ns = div64_u64(sum_unmap, loops);
+
+		/* standard deviation of latency */
+		map_variance = div64_u64(sum_sq_map, loops) -
+				map->bparam.avg_map_100ns *
+				map->bparam.avg_map_100ns;
+		unmap_variance = div64_u64(sum_sq_unmap, loops) -
+				map->bparam.avg_unmap_100ns *
+				map->bparam.avg_unmap_100ns;
+		map->bparam.map_stddev = int_sqrt64(map_variance);
+		map->bparam.unmap_stddev = int_sqrt64(unmap_variance);
+	}
+
+out:
+	put_device(map->dev);
+	kfree(tsk);
+	return ret;
+}
+
+static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
+		unsigned long arg)
+{
+	struct map_benchmark_data *map = file->private_data;
+	void __user *argp = (void __user *)arg;
+	u64 old_dma_mask;
+
+	int ret;
+
+	if (copy_from_user(&map->bparam, argp, sizeof(map->bparam)))
+		return -EFAULT;
+
+	switch (cmd) {
+	case DMA_MAP_BENCHMARK:
+		if (map->bparam.threads == 0 ||
+		    map->bparam.threads > DMA_MAP_MAX_THREADS) {
+			pr_err("invalid thread number\n");
+			return -EINVAL;
+		}
+
+		if (map->bparam.seconds == 0 ||
+		    map->bparam.seconds > DMA_MAP_MAX_SECONDS) {
+			pr_err("invalid duration seconds\n");
+			return -EINVAL;
+		}
+
+		if (map->bparam.node != NUMA_NO_NODE &&
+		    !node_possible(map->bparam.node)) {
+			pr_err("invalid numa node\n");
+			return -EINVAL;
+		}
+
+		switch (map->bparam.dma_dir) {
+		case DMA_MAP_BIDIRECTIONAL:
+			map->dir = DMA_BIDIRECTIONAL;
+			break;
+		case DMA_MAP_FROM_DEVICE:
+			map->dir = DMA_FROM_DEVICE;
+			break;
+		case DMA_MAP_TO_DEVICE:
+			map->dir = DMA_TO_DEVICE;
+			break;
+		default:
+			pr_err("invalid DMA direction\n");
+			return -EINVAL;
+		}
+
+		old_dma_mask = dma_get_mask(map->dev);
+
+		ret = dma_set_mask(map->dev,
+				   DMA_BIT_MASK(map->bparam.dma_bits));
+		if (ret) {
+			pr_err("failed to set dma_mask on device %s\n",
+				dev_name(map->dev));
+			return -EINVAL;
+		}
+
+		ret = do_map_benchmark(map);
+
+		/*
+		 * restore the original dma_mask as many devices' dma_mask are
+		 * set by architectures, acpi, busses. When we bind them back
+		 * to their original drivers, those drivers shouldn't see
+		 * dma_mask changed by benchmark
+		 */
+		dma_set_mask(map->dev, old_dma_mask);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (copy_to_user(argp, &map->bparam, sizeof(map->bparam)))
+		return -EFAULT;
+
+	return ret;
+}
+
+static const struct file_operations map_benchmark_fops = {
+	.open			= simple_open,
+	.unlocked_ioctl		= map_benchmark_ioctl,
+};
+
+static void map_benchmark_remove_debugfs(void *data)
+{
+	struct map_benchmark_data *map = (struct map_benchmark_data *)data;
+
+	debugfs_remove(map->debugfs);
+}
+
+static int __map_benchmark_probe(struct device *dev)
+{
+	struct dentry *entry;
+	struct map_benchmark_data *map;
+	int ret;
+
+	map = devm_kzalloc(dev, sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+	map->dev = dev;
+
+	ret = devm_add_action(dev, map_benchmark_remove_debugfs, map);
+	if (ret) {
+		pr_err("Can't add debugfs remove action\n");
+		return ret;
+	}
+
+	/*
+	 * we only permit a device bound with this driver, 2nd probe
+	 * will fail
+	 */
+	entry = debugfs_create_file("dma_map_benchmark", 0600, NULL, map,
+			&map_benchmark_fops);
+	if (IS_ERR(entry))
+		return PTR_ERR(entry);
+	map->debugfs = entry;
+
+	return 0;
+}
+
+static int map_benchmark_platform_probe(struct platform_device *pdev)
+{
+	return __map_benchmark_probe(&pdev->dev);
+}
+
+static struct platform_driver map_benchmark_platform_driver = {
+	.driver		= {
+		.name	= "dma_map_benchmark",
+	},
+	.probe = map_benchmark_platform_probe,
+};
+
+static int
+map_benchmark_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	return __map_benchmark_probe(&pdev->dev);
+}
+
+static struct pci_driver map_benchmark_pci_driver = {
+	.name	= "dma_map_benchmark",
+	.probe	= map_benchmark_pci_probe,
+};
+
+static int __init map_benchmark_init(void)
+{
+	int ret;
+
+	ret = pci_register_driver(&map_benchmark_pci_driver);
+	if (ret)
+		return ret;
+
+	ret = platform_driver_register(&map_benchmark_platform_driver);
+	if (ret) {
+		pci_unregister_driver(&map_benchmark_pci_driver);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void __exit map_benchmark_cleanup(void)
+{
+	platform_driver_unregister(&map_benchmark_platform_driver);
+	pci_unregister_driver(&map_benchmark_pci_driver);
+}
+
+module_init(map_benchmark_init);
+module_exit(map_benchmark_cleanup);
+
+MODULE_AUTHOR("Barry Song <song.bao.hua@hisilicon.com>");
+MODULE_DESCRIPTION("dma_map benchmark driver");
+MODULE_LICENSE("GPL");
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 51bb8fa8eb89..f87a89d08654 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -149,7 +149,8 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 	if (WARN_ON_ONCE(!dev->dma_mask))
 		return DMA_MAPPING_ERROR;
 
-	if (dma_map_direct(dev, ops))
+	if (dma_map_direct(dev, ops) ||
+	    arch_dma_map_page_direct(dev, page_to_phys(page) + offset + size))
 		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
 	else
 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
@@ -165,7 +166,8 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_map_direct(dev, ops))
+	if (dma_map_direct(dev, ops) ||
+	    arch_dma_unmap_page_direct(dev, addr + size))
 		dma_direct_unmap_page(dev, addr, size, dir, attrs);
 	else if (ops->unmap_page)
 		ops->unmap_page(dev, addr, size, dir, attrs);
@@ -188,7 +190,8 @@ int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
 	if (WARN_ON_ONCE(!dev->dma_mask))
 		return 0;
 
-	if (dma_map_direct(dev, ops))
+	if (dma_map_direct(dev, ops) ||
+	    arch_dma_map_sg_direct(dev, sg, nents))
 		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
 	else
 		ents = ops->map_sg(dev, sg, nents, dir, attrs);
@@ -207,7 +210,8 @@ void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
 
 	BUG_ON(!valid_dma_direction(dir));
 	debug_dma_unmap_sg(dev, sg, nents, dir);
-	if (dma_map_direct(dev, ops))
+	if (dma_map_direct(dev, ops) ||
+	    arch_dma_unmap_sg_direct(dev, sg, nents))
 		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
 	else if (ops->unmap_sg)
 		ops->unmap_sg(dev, sg, nents, dir, attrs);
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index d4637f72239b..5f84e6cdb78e 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -38,9 +38,6 @@ static void __init dma_atomic_pool_debugfs_init(void)
 	struct dentry *root;
 
 	root = debugfs_create_dir("dma_pools", NULL);
-	if (IS_ERR_OR_NULL(root))
-		return;
-
 	debugfs_create_ulong("pool_size_dma", 0400, root, &pool_size_dma);
 	debugfs_create_ulong("pool_size_dma32", 0400, root, &pool_size_dma32);
 	debugfs_create_ulong("pool_size_kernel", 0400, root, &pool_size_kernel);
diff --git a/kernel/exit.c b/kernel/exit.c
index 3594291a8542..04029e35e69a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -63,6 +63,7 @@
 #include <linux/random.h>
 #include <linux/rcuwait.h>
 #include <linux/compat.h>
+#include <linux/io_uring.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -776,6 +777,7 @@ void __noreturn do_exit(long code)
 		schedule();
 	}
 
+	io_uring_files_cancel(tsk->files);
 	exit_signals(tsk);  /* sets PF_EXITING */
 
 	/* sync mm's RSS info before statistics gathering */
diff --git a/kernel/fork.c b/kernel/fork.c
index 41906a52a764..37720a6d04ea 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -225,8 +225,8 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 		if (!s)
 			continue;
 
-		/* Clear the KASAN shadow of the stack. */
-		kasan_unpoison_shadow(s->addr, THREAD_SIZE);
+		/* Mark stack accessible for KASAN. */
+		kasan_unpoison_range(s->addr, THREAD_SIZE);
 
 		/* Clear stale pointers from reused stack. */
 		memset(s->addr, 0, THREAD_SIZE);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index e810eb9906ea..cc1a09406c6e 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -147,12 +147,12 @@ static ssize_t per_cpu_count_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
 {
 	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
-	int cpu, irq = desc->irq_data.irq;
 	ssize_t ret = 0;
 	char *p = "";
+	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		unsigned int c = kstat_irqs_cpu(irq, cpu);
+		unsigned int c = irq_desc_kstat_cpu(desc, cpu);
 
 		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%u", p, c);
 		p = ",";
@@ -352,7 +352,9 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	return radix_tree_lookup(&irq_desc_tree, irq);
 }
-EXPORT_SYMBOL(irq_to_desc);
+#ifdef CONFIG_KVM_BOOK3S_64_HV_MODULE
+EXPORT_SYMBOL_GPL(irq_to_desc);
+#endif
 
 static void delete_irq_desc(unsigned int irq)
 {
@@ -924,15 +926,7 @@ static bool irq_is_nmi(struct irq_desc *desc)
 	return desc->istate & IRQS_NMI;
 }
 
-/**
- * kstat_irqs - Get the statistics for an interrupt
- * @irq:	The interrupt number
- *
- * Returns the sum of interrupt counts on all cpus since boot for
- * @irq. The caller must ensure that the interrupt is not removed
- * concurrently.
- */
-unsigned int kstat_irqs(unsigned int irq)
+static unsigned int kstat_irqs(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned int sum = 0;
@@ -943,21 +937,22 @@ unsigned int kstat_irqs(unsigned int irq)
 	if (!irq_settings_is_per_cpu_devid(desc) &&
 	    !irq_settings_is_per_cpu(desc) &&
 	    !irq_is_nmi(desc))
-	    return desc->tot_count;
+		return data_race(desc->tot_count);
 
 	for_each_possible_cpu(cpu)
-		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
+		sum += data_race(*per_cpu_ptr(desc->kstat_irqs, cpu));
 	return sum;
 }
 
 /**
- * kstat_irqs_usr - Get the statistics for an interrupt
+ * kstat_irqs_usr - Get the statistics for an interrupt from thread context
  * @irq:	The interrupt number
  *
  * Returns the sum of interrupt counts on all cpus since boot for @irq.
- * Contrary to kstat_irqs() this can be called from any context.
- * It uses rcu since a concurrent removal of an interrupt descriptor is
- * observing an rcu grace period before delayed_free_desc()/irq_kobj_release().
+ *
+ * It uses rcu to protect the access since a concurrent removal of an
+ * interrupt descriptor is observing an rcu grace period before
+ * delayed_free_desc()/irq_kobj_release().
  */
 unsigned int kstat_irqs_usr(unsigned int irq)
 {
@@ -968,3 +963,17 @@ unsigned int kstat_irqs_usr(unsigned int irq)
 	rcu_read_unlock();
 	return sum;
 }
+
+#ifdef CONFIG_LOCKDEP
+void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
+			     struct lock_class_key *request_class)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc) {
+		lockdep_set_class(&desc->lock, lock_class);
+		lockdep_set_class(&desc->request_mutex, request_class);
+	}
+}
+EXPORT_SYMBOL_GPL(__irq_set_lockdep_class);
+#endif
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index c826ba4141fe..ab8567f32501 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -2822,3 +2822,40 @@ out_unlock:
 	return err;
 }
 EXPORT_SYMBOL_GPL(irq_set_irqchip_state);
+
+/**
+ * irq_has_action - Check whether an interrupt is requested
+ * @irq:	The linux irq number
+ *
+ * Returns: A snapshot of the current state
+ */
+bool irq_has_action(unsigned int irq)
+{
+	bool res;
+
+	rcu_read_lock();
+	res = irq_desc_has_action(irq_to_desc(irq));
+	rcu_read_unlock();
+	return res;
+}
+EXPORT_SYMBOL_GPL(irq_has_action);
+
+/**
+ * irq_check_status_bit - Check whether bits in the irq descriptor status are set
+ * @irq:	The linux irq number
+ * @bitmask:	The bitmask to evaluate
+ *
+ * Returns: True if one of the bits in @bitmask is set
+ */
+bool irq_check_status_bit(unsigned int irq, unsigned int bitmask)
+{
+	struct irq_desc *desc;
+	bool res = false;
+
+	rcu_read_lock();
+	desc = irq_to_desc(irq);
+	if (desc)
+		res = !!(desc->status_use_accessors & bitmask);
+	rcu_read_unlock();
+	return res;
+}
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 72513ed2a5fc..98138788cb04 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -488,9 +488,10 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (!desc || irq_settings_is_hidden(desc))
 		goto outsparse;
 
-	if (desc->kstat_irqs)
+	if (desc->kstat_irqs) {
 		for_each_online_cpu(j)
-			any_count |= *per_cpu_ptr(desc->kstat_irqs, j);
+			any_count |= data_race(*per_cpu_ptr(desc->kstat_irqs, j));
+	}
 
 	if ((!desc->action || irq_desc_is_chained(desc)) && !any_count)
 		goto outsparse;
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 015ef903ce8c..c6a39d662935 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -793,6 +793,7 @@ int jump_label_text_reserved(void *start, void *end)
 static void jump_label_update(struct static_key *key)
 {
 	struct jump_entry *stop = __stop___jump_table;
+	bool init = system_state < SYSTEM_RUNNING;
 	struct jump_entry *entry;
 #ifdef CONFIG_MODULES
 	struct module *mod;
@@ -804,15 +805,16 @@ static void jump_label_update(struct static_key *key)
 
 	preempt_disable();
 	mod = __module_address((unsigned long)key);
-	if (mod)
+	if (mod) {
 		stop = mod->jump_entries + mod->num_jump_entries;
+		init = mod->state == MODULE_STATE_COMING;
+	}
 	preempt_enable();
 #endif
 	entry = static_key_entries(key);
 	/* if there are no users, entry can be NULL */
 	if (entry)
-		__jump_label_update(key, entry, stop,
-				    system_state < SYSTEM_RUNNING);
+		__jump_label_update(key, entry, stop, init);
 }
 
 #ifdef CONFIG_STATIC_KEYS_SELFTEST
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 35bdcfd84d42..36607551f966 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -241,7 +241,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	}
 }
 
-/* Spawn RCU-tasks grace-period kthread, e.g., at core_initcall() time. */
+/* Spawn RCU-tasks grace-period kthread. */
 static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp)
 {
 	struct task_struct *t;
@@ -564,7 +564,6 @@ static int __init rcu_spawn_tasks_kthread(void)
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks);
 	return 0;
 }
-core_initcall(rcu_spawn_tasks_kthread);
 
 #if !defined(CONFIG_TINY_RCU)
 void show_rcu_tasks_classic_gp_kthread(void)
@@ -692,7 +691,6 @@ static int __init rcu_spawn_tasks_rude_kthread(void)
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
 	return 0;
 }
-core_initcall(rcu_spawn_tasks_rude_kthread);
 
 #if !defined(CONFIG_TINY_RCU)
 void show_rcu_tasks_rude_gp_kthread(void)
@@ -968,6 +966,11 @@ static void rcu_tasks_trace_pregp_step(void)
 static void rcu_tasks_trace_pertask(struct task_struct *t,
 				    struct list_head *hop)
 {
+	// During early boot when there is only the one boot CPU, there
+	// is no idle task for the other CPUs. Just return.
+	if (unlikely(t == NULL))
+		return;
+
 	WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
 	WRITE_ONCE(t->trc_reader_checked, false);
 	t->trc_ipi_to_cpu = -1;
@@ -1193,7 +1196,6 @@ static int __init rcu_spawn_tasks_trace_kthread(void)
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks_trace);
 	return 0;
 }
-core_initcall(rcu_spawn_tasks_trace_kthread);
 
 #if !defined(CONFIG_TINY_RCU)
 void show_rcu_tasks_trace_gp_kthread(void)
@@ -1222,6 +1224,21 @@ void show_rcu_tasks_gp_kthreads(void)
 }
 #endif /* #ifndef CONFIG_TINY_RCU */
 
+void __init rcu_init_tasks_generic(void)
+{
+#ifdef CONFIG_TASKS_RCU
+	rcu_spawn_tasks_kthread();
+#endif
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+	rcu_spawn_tasks_rude_kthread();
+#endif
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+	rcu_spawn_tasks_trace_kthread();
+#endif
+}
+
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
 static inline void rcu_tasks_bootup_oddness(void) {}
 void show_rcu_tasks_gp_kthreads(void) {}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 21b548b69455..15d2562118d1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3985,15 +3985,20 @@ static void do_balance_callbacks(struct rq *rq, struct callback_head *head)
 	}
 }
 
+static void balance_push(struct rq *rq);
+
+struct callback_head balance_push_callback = {
+	.next = NULL,
+	.func = (void (*)(struct callback_head *))balance_push,
+};
+
 static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
 {
 	struct callback_head *head = rq->balance_callback;
 
 	lockdep_assert_held(&rq->lock);
-	if (head) {
+	if (head)
 		rq->balance_callback = NULL;
-		rq->balance_flags &= ~BALANCE_WORK;
-	}
 
 	return head;
 }
@@ -4014,21 +4019,6 @@ static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
 	}
 }
 
-static void balance_push(struct rq *rq);
-
-static inline void balance_switch(struct rq *rq)
-{
-	if (likely(!rq->balance_flags))
-		return;
-
-	if (rq->balance_flags & BALANCE_PUSH) {
-		balance_push(rq);
-		return;
-	}
-
-	__balance_callbacks(rq);
-}
-
 #else
 
 static inline void __balance_callbacks(struct rq *rq)
@@ -4044,10 +4034,6 @@ static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
 {
 }
 
-static inline void balance_switch(struct rq *rq)
-{
-}
-
 #endif
 
 static inline void
@@ -4075,7 +4061,7 @@ static inline void finish_lock_switch(struct rq *rq)
 	 * prev into current:
 	 */
 	spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
-	balance_switch(rq);
+	__balance_callbacks(rq);
 	raw_spin_unlock_irq(&rq->lock);
 }
 
@@ -7282,6 +7268,10 @@ static void balance_push(struct rq *rq)
 
 	lockdep_assert_held(&rq->lock);
 	SCHED_WARN_ON(rq->cpu != smp_processor_id());
+	/*
+	 * Ensure the thing is persistent until balance_push_set(.on = false);
+	 */
+	rq->balance_callback = &balance_push_callback;
 
 	/*
 	 * Both the cpu-hotplug and stop task are in this case and are
@@ -7331,9 +7321,9 @@ static void balance_push_set(int cpu, bool on)
 
 	rq_lock_irqsave(rq, &rf);
 	if (on)
-		rq->balance_flags |= BALANCE_PUSH;
+		rq->balance_callback = &balance_push_callback;
 	else
-		rq->balance_flags &= ~BALANCE_PUSH;
+		rq->balance_callback = NULL;
 	rq_unlock_irqrestore(rq, &rf);
 }
 
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index b0ad37bf95ee..6931f0cdeb80 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -53,6 +53,7 @@ struct sugov_cpu {
 	unsigned int		iowait_boost;
 	u64			last_update;
 
+	unsigned long		util;
 	unsigned long		bw_dl;
 	unsigned long		max;
 
@@ -276,16 +277,15 @@ unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
 	return min(max, util);
 }
 
-static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
+static void sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
-	unsigned long util = cpu_util_cfs(rq);
 	unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu);
 
 	sg_cpu->max = max;
 	sg_cpu->bw_dl = cpu_bw_dl(rq);
-
-	return schedutil_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL);
+	sg_cpu->util = schedutil_cpu_util(sg_cpu->cpu, cpu_util_cfs(rq), max,
+					  FREQUENCY_UTIL, NULL);
 }
 
 /**
@@ -362,8 +362,6 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  * sugov_iowait_apply() - Apply the IO boost to a CPU.
  * @sg_cpu: the sugov data for the cpu to boost
  * @time: the update time from the caller
- * @util: the utilization to (eventually) boost
- * @max: the maximum value the utilization can be boosted to
  *
  * A CPU running a task which woken up after an IO operation can have its
  * utilization boosted to speed up the completion of those IO operations.
@@ -377,18 +375,17 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  * This mechanism is designed to boost high frequently IO waiting tasks, while
  * being more conservative on tasks which does sporadic IO operations.
  */
-static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
-					unsigned long util, unsigned long max)
+static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
 {
 	unsigned long boost;
 
 	/* No boost currently required */
 	if (!sg_cpu->iowait_boost)
-		return util;
+		return;
 
 	/* Reset boost if the CPU appears to have been idle enough */
 	if (sugov_iowait_reset(sg_cpu, time, false))
-		return util;
+		return;
 
 	if (!sg_cpu->iowait_boost_pending) {
 		/*
@@ -397,18 +394,19 @@ static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
 		sg_cpu->iowait_boost >>= 1;
 		if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) {
 			sg_cpu->iowait_boost = 0;
-			return util;
+			return;
 		}
 	}
 
 	sg_cpu->iowait_boost_pending = false;
 
 	/*
-	 * @util is already in capacity scale; convert iowait_boost
+	 * sg_cpu->util is already in capacity scale; convert iowait_boost
 	 * into the same scale so we can compare.
 	 */
-	boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT;
-	return max(boost, util);
+	boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT;
+	if (sg_cpu->util < boost)
+		sg_cpu->util = boost;
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -434,14 +432,10 @@ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_p
 		sg_policy->limits_changed = true;
 }
 
-static void sugov_update_single(struct update_util_data *hook, u64 time,
-				unsigned int flags)
+static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
+					      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 util, max;
-	unsigned int next_f;
-	unsigned int cached_freq = sg_policy->cached_raw_freq;
 
 	sugov_iowait_boost(sg_cpu, time, flags);
 	sg_cpu->last_update = time;
@@ -449,12 +443,26 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	ignore_dl_rate_limit(sg_cpu, sg_policy);
 
 	if (!sugov_should_update_freq(sg_policy, time))
+		return false;
+
+	sugov_get_util(sg_cpu);
+	sugov_iowait_apply(sg_cpu, time);
+
+	return true;
+}
+
+static void sugov_update_single_freq(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 int cached_freq = sg_policy->cached_raw_freq;
+	unsigned int next_f;
+
+	if (!sugov_update_single_common(sg_cpu, time, flags))
 		return;
 
-	util = sugov_get_util(sg_cpu);
-	max = sg_cpu->max;
-	util = sugov_iowait_apply(sg_cpu, time, util, max);
-	next_f = get_next_freq(sg_policy, util, max);
+	next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max);
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
@@ -480,6 +488,38 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	}
 }
 
+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);
+	unsigned long prev_util = sg_cpu->util;
+
+	/*
+	 * Fall back to the "frequency" path if frequency invariance is not
+	 * supported, because the direct mapping between the utilization and
+	 * the performance levels depends on the frequency invariance.
+	 */
+	if (!arch_scale_freq_invariant()) {
+		sugov_update_single_freq(hook, time, flags);
+		return;
+	}
+
+	if (!sugov_update_single_common(sg_cpu, time, flags))
+		return;
+
+	/*
+	 * Do not reduce the target performance level if the CPU has not been
+	 * idle recently, as the reduction is likely to be premature then.
+	 */
+	if (sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
+		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);
+
+	sg_cpu->sg_policy->last_freq_update_time = time;
+}
+
 static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 {
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
@@ -491,9 +531,10 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
 		unsigned long j_util, j_max;
 
-		j_util = sugov_get_util(j_sg_cpu);
+		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;
-		j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max);
 
 		if (j_util * max > j_max * util) {
 			util = j_util;
@@ -817,6 +858,7 @@ static void sugov_exit(struct cpufreq_policy *policy)
 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;
 
 	sg_policy->freq_update_delay_ns	= sg_policy->tunables->rate_limit_us * NSEC_PER_USEC;
@@ -836,13 +878,17 @@ static int sugov_start(struct cpufreq_policy *policy)
 		sg_cpu->sg_policy		= sg_policy;
 	}
 
+	if (policy_is_shared(policy))
+		uu = sugov_update_shared;
+	else if (policy->fast_switch_enabled && cpufreq_driver_has_adjust_perf())
+		uu = sugov_update_single_perf;
+	else
+		uu = sugov_update_single_freq;
+
 	for_each_cpu(cpu, policy->cpus) {
 		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
 
-		cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
-					     policy_is_shared(policy) ?
-							sugov_update_shared :
-							sugov_update_single);
+		cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, uu);
 	}
 	return 0;
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f5acb6c5ce49..12ada79d40f3 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -975,7 +975,6 @@ struct rq {
 	unsigned long		cpu_capacity_orig;
 
 	struct callback_head	*balance_callback;
-	unsigned char		balance_flags;
 
 	unsigned char		nohz_idle_balance;
 	unsigned char		idle_balance;
@@ -1226,6 +1225,8 @@ struct rq_flags {
 #endif
 };
 
+extern struct callback_head balance_push_callback;
+
 /*
  * Lockdep annotation that avoids accidental unlocks; it's like a
  * sticky/continuous lockdep_assert_held().
@@ -1243,9 +1244,9 @@ static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
 #ifdef CONFIG_SCHED_DEBUG
 	rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
 	rf->clock_update_flags = 0;
-#endif
 #ifdef CONFIG_SMP
-	SCHED_WARN_ON(rq->balance_callback);
+	SCHED_WARN_ON(rq->balance_callback && rq->balance_callback != &balance_push_callback);
+#endif
 #endif
 }
 
@@ -1408,9 +1409,6 @@ init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
 
 #ifdef CONFIG_SMP
 
-#define BALANCE_WORK	0x01
-#define BALANCE_PUSH	0x02
-
 static inline void
 queue_balance_callback(struct rq *rq,
 		       struct callback_head *head,
@@ -1418,13 +1416,12 @@ queue_balance_callback(struct rq *rq,
 {
 	lockdep_assert_held(&rq->lock);
 
-	if (unlikely(head->next || (rq->balance_flags & BALANCE_PUSH)))
+	if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
 		return;
 
 	head->func = (void (*)(struct callback_head *))func;
 	head->next = rq->balance_callback;
 	rq->balance_callback = head;
-	rq->balance_flags |= BALANCE_WORK;
 }
 
 #define rcu_dereference_check_sched_domain(p) \
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 01f5d3020589..183cc6ae68a6 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -37,6 +37,17 @@ void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue
 }
 EXPORT_SYMBOL(add_wait_queue_exclusive);
 
+void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
+{
+	unsigned long flags;
+
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE | WQ_FLAG_PRIORITY;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__add_wait_queue(wq_head, wq_entry);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
+}
+EXPORT_SYMBOL_GPL(add_wait_queue_priority);
+
 void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
@@ -57,7 +68,11 @@ EXPORT_SYMBOL(remove_wait_queue);
 /*
  * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
  * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
- * number) then we wake all the non-exclusive tasks and one exclusive task.
+ * number) then we wake that number of exclusive tasks, and potentially all
+ * the non-exclusive tasks. Normally, exclusive tasks will be at the end of
+ * the list and any non-exclusive tasks will be woken first. A priority task
+ * may be at the head of the list, and can consume the event without any other
+ * tasks being woken.
  *
  * There are circumstances in which we can try to wake a task which has already
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
diff --git a/kernel/softirq.c b/kernel/softirq.c
index d5bfd5e661fc..9d71046ea247 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -186,7 +186,7 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
 	 * Keep preemption disabled until we are done with
 	 * softirq processing:
 	 */
-	preempt_count_sub(cnt - 1);
+	__preempt_count_sub(cnt - 1);
 
 	if (unlikely(!in_interrupt() && local_softirq_pending())) {
 		/*
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 9a41848b6ebb..83e158d016ba 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -141,7 +141,7 @@ config CONTEXT_TRACKING_FORCE
 	  dynticks working.
 
 	  This option stands for testing when an arch implements the
-	  context tracking backend but doesn't yet fullfill all the
+	  context tracking backend but doesn't yet fulfill all the
 	  requirements to make the full dynticks feature working.
 	  Without the full dynticks, there is no way to test the support
 	  for context tracking and the subsystems that rely on it: RCU
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index a03764df5366..9d3a22510bab 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -407,17 +407,13 @@ EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
 /*
  * Transfer the do_timer job away from a dying cpu.
  *
- * Called with interrupts disabled. Not locking required. If
+ * Called with interrupts disabled. No locking required. If
  * tick_do_timer_cpu is owned by this cpu, nothing can change it.
  */
 void tick_handover_do_timer(void)
 {
-	if (tick_do_timer_cpu == smp_processor_id()) {
-		int cpu = cpumask_first(cpu_online_mask);
-
-		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
-			TICK_DO_TIMER_NONE;
-	}
+	if (tick_do_timer_cpu == smp_processor_id())
+		tick_do_timer_cpu = cpumask_first(cpu_online_mask);
 }
 
 /*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 030282994b3e..e10a4af88737 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -989,13 +989,6 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 		 */
 		if (tick_do_timer_cpu == cpu)
 			return false;
-		/*
-		 * Boot safety: make sure the timekeeping duty has been
-		 * assigned before entering dyntick-idle mode,
-		 * tick_do_timer_cpu is TICK_DO_TIMER_BOOT
-		 */
-		if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_BOOT))
-			return false;
 
 		/* Should not happen for nohz-full */
 		if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d5a19413d4f8..c1a62ae7e812 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -538,7 +538,7 @@ config KPROBE_EVENTS
 config KPROBE_EVENTS_ON_NOTRACE
 	bool "Do NOT protect notrace function from kprobe events"
 	depends on KPROBE_EVENTS
-	depends on KPROBES_ON_FTRACE
+	depends on DYNAMIC_FTRACE
 	default n
 	help
 	  This is only for the developers who want to debug ftrace itself
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 9c31f42245e9..e6fba1798771 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -434,7 +434,7 @@ static int disable_trace_kprobe(struct trace_event_call *call,
 	return 0;
 }
 
-#if defined(CONFIG_KPROBES_ON_FTRACE) && \
+#if defined(CONFIG_DYNAMIC_FTRACE) && \
 	!defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE)
 static bool __within_notrace_func(unsigned long addr)
 {
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index b5295a0b0536..9880b6c0e272 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3731,17 +3731,24 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
 	 * is updated and visible.
 	 */
 	if (!freezable || !workqueue_freezing) {
+		bool kick = false;
+
 		pwq->max_active = wq->saved_max_active;
 
 		while (!list_empty(&pwq->delayed_works) &&
-		       pwq->nr_active < pwq->max_active)
+		       pwq->nr_active < pwq->max_active) {
 			pwq_activate_first_delayed(pwq);
+			kick = true;
+		}
 
 		/*
 		 * Need to kick a worker after thawed or an unbound wq's
-		 * max_active is bumped.  It's a slow path.  Do it always.
+		 * max_active is bumped. In realtime scenarios, always kicking a
+		 * worker will cause interference on the isolated cpu cores, so
+		 * let's kick iff work items were activated.
 		 */
-		wake_up_worker(pwq->pool);
+		if (kick)
+			wake_up_worker(pwq->pool);
 	} else {
 		pwq->max_active = 0;
 	}
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index e6e58b26e888..7937265ef879 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -295,14 +295,6 @@ config GDB_SCRIPTS
 
 endif # DEBUG_INFO
 
-config ENABLE_MUST_CHECK
-	bool "Enable __must_check logic"
-	default y
-	help
-	  Enable the __must_check logic in the kernel build.  Disable this to
-	  suppress the "warning: ignoring return value of 'foo', declared with
-	  attribute warn_unused_result" messages.
-
 config FRAME_WARN
 	int "Warn for stack frames larger than"
 	range 0 8192
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 8fb097057fec..f5fa4ba126bf 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -6,7 +6,10 @@ config HAVE_ARCH_KASAN
 config HAVE_ARCH_KASAN_SW_TAGS
 	bool
 
-config	HAVE_ARCH_KASAN_VMALLOC
+config HAVE_ARCH_KASAN_HW_TAGS
+	bool
+
+config HAVE_ARCH_KASAN_VMALLOC
 	bool
 
 config CC_HAS_KASAN_GENERIC
@@ -15,15 +18,20 @@ config CC_HAS_KASAN_GENERIC
 config CC_HAS_KASAN_SW_TAGS
 	def_bool $(cc-option, -fsanitize=kernel-hwaddress)
 
+# This option is only required for software KASAN modes.
+# Old GCC versions don't have proper support for no_sanitize_address.
+# See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89124 for details.
 config CC_HAS_WORKING_NOSANITIZE_ADDRESS
 	def_bool !CC_IS_GCC || GCC_VERSION >= 80300
 
 menuconfig KASAN
 	bool "KASAN: runtime memory debugger"
-	depends on (HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC) || \
-		   (HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS)
+	depends on (((HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC) || \
+		     (HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS)) && \
+		    CC_HAS_WORKING_NOSANITIZE_ADDRESS) || \
+		   HAVE_ARCH_KASAN_HW_TAGS
 	depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
-	depends on CC_HAS_WORKING_NOSANITIZE_ADDRESS
+	select STACKDEPOT
 	help
 	  Enables KASAN (KernelAddressSANitizer) - runtime memory debugger,
 	  designed to find out-of-bounds accesses and use-after-free bugs.
@@ -35,21 +43,24 @@ choice
 	prompt "KASAN mode"
 	default KASAN_GENERIC
 	help
-	  KASAN has two modes: generic KASAN (similar to userspace ASan,
-	  x86_64/arm64/xtensa, enabled with CONFIG_KASAN_GENERIC) and
-	  software tag-based KASAN (a version based on software memory
-	  tagging, arm64 only, similar to userspace HWASan, enabled with
-	  CONFIG_KASAN_SW_TAGS).
+	  KASAN has three modes:
+	  1. generic KASAN (similar to userspace ASan,
+	     x86_64/arm64/xtensa, enabled with CONFIG_KASAN_GENERIC),
+	  2. software tag-based KASAN (arm64 only, based on software
+	     memory tagging (similar to userspace HWASan), enabled with
+	     CONFIG_KASAN_SW_TAGS), and
+	  3. hardware tag-based KASAN (arm64 only, based on hardware
+	     memory tagging, enabled with CONFIG_KASAN_HW_TAGS).
+
+	  All KASAN modes are strictly debugging features.
 
-	  Both generic and tag-based KASAN are strictly debugging features.
+	  For better error reports enable CONFIG_STACKTRACE.
 
 config KASAN_GENERIC
 	bool "Generic mode"
 	depends on HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC
-	depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
 	select SLUB_DEBUG if SLUB
 	select CONSTRUCTORS
-	select STACKDEPOT
 	help
 	  Enables generic KASAN mode.
 
@@ -62,23 +73,22 @@ config KASAN_GENERIC
 	  and introduces an overhead of ~x1.5 for the rest of the allocations.
 	  The performance slowdown is ~x3.
 
-	  For better error detection enable CONFIG_STACKTRACE.
-
 	  Currently CONFIG_KASAN_GENERIC doesn't work with CONFIG_DEBUG_SLAB
 	  (the resulting kernel does not boot).
 
 config KASAN_SW_TAGS
 	bool "Software tag-based mode"
 	depends on HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS
-	depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
 	select SLUB_DEBUG if SLUB
 	select CONSTRUCTORS
-	select STACKDEPOT
 	help
 	  Enables software tag-based KASAN mode.
 
-	  This mode requires Top Byte Ignore support by the CPU and therefore
-	  is only supported for arm64. This mode requires Clang.
+	  This mode require software memory tagging support in the form of
+	  HWASan-like compiler instrumentation.
+
+	  Currently this mode is only implemented for arm64 CPUs and relies on
+	  Top Byte Ignore. This mode requires Clang.
 
 	  This mode consumes about 1/16th of available memory at kernel start
 	  and introduces an overhead of ~20% for the rest of the allocations.
@@ -86,15 +96,27 @@ config KASAN_SW_TAGS
 	  casting and comparison, as it embeds tags into the top byte of each
 	  pointer.
 
-	  For better error detection enable CONFIG_STACKTRACE.
-
 	  Currently CONFIG_KASAN_SW_TAGS doesn't work with CONFIG_DEBUG_SLAB
 	  (the resulting kernel does not boot).
 
+config KASAN_HW_TAGS
+	bool "Hardware tag-based mode"
+	depends on HAVE_ARCH_KASAN_HW_TAGS
+	depends on SLUB
+	help
+	  Enables hardware tag-based KASAN mode.
+
+	  This mode requires hardware memory tagging support, and can be used
+	  by any architecture that provides it.
+
+	  Currently this mode is only implemented for arm64 CPUs starting from
+	  ARMv8.5 and relies on Memory Tagging Extension and Top Byte Ignore.
+
 endchoice
 
 choice
 	prompt "Instrumentation type"
+	depends on KASAN_GENERIC || KASAN_SW_TAGS
 	default KASAN_OUTLINE
 
 config KASAN_OUTLINE
@@ -118,6 +140,7 @@ endchoice
 
 config KASAN_STACK_ENABLE
 	bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST
+	depends on KASAN_GENERIC || KASAN_SW_TAGS
 	help
 	  The LLVM stack address sanitizer has a know problem that
 	  causes excessive stack usage in a lot of functions, see
@@ -146,7 +169,7 @@ config KASAN_SW_TAGS_IDENTIFY
 
 config KASAN_VMALLOC
 	bool "Back mappings in vmalloc space with real shadow memory"
-	depends on HAVE_ARCH_KASAN_VMALLOC
+	depends on KASAN_GENERIC && HAVE_ARCH_KASAN_VMALLOC
 	help
 	  By default, the shadow region for vmalloc space is the read-only
 	  zero page. This means that KASAN cannot detect errors involving
diff --git a/lib/fonts/font_ter16x32.c b/lib/fonts/font_ter16x32.c
index 1955d624177c..5baedc573dd6 100644
--- a/lib/fonts/font_ter16x32.c
+++ b/lib/fonts/font_ter16x32.c
@@ -774,8 +774,8 @@ static const struct font_data fontdata_ter16x32 = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0xfc,
 	0x7f, 0xfc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,	/* 95 */
-	0x00, 0x00, 0x1c, 0x00, 0x0e, 0x00, 0x07, 0x00,
-	0x03, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x1c, 0x00, 0x0e, 0x00,
+	0x07, 0x00, 0x03, 0x80, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
@@ -1169,7 +1169,7 @@ static const struct font_data fontdata_ter16x32 = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-	0x7f, 0xf8, 0x7f, 0xfc, 0x03, 0x9e, 0x03, 0x8e,
+	0x7e, 0xf8, 0x7f, 0xfc, 0x03, 0x9e, 0x03, 0x8e,
 	0x03, 0x8e, 0x3f, 0x8e, 0x7f, 0xfe, 0xf3, 0xfe,
 	0xe3, 0x80, 0xe3, 0x80, 0xe3, 0x80, 0xf3, 0xce,
 	0x7f, 0xfe, 0x3e, 0xfc, 0x00, 0x00, 0x00, 0x00,
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 7f1244b5294a..dab97bb69df6 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -81,14 +81,14 @@ static int clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear)
  * users set the same bit, one user will return remain bits, otherwise
  * return 0.
  */
-static int bitmap_set_ll(unsigned long *map, int start, int nr)
+static int bitmap_set_ll(unsigned long *map, unsigned long start, unsigned long nr)
 {
 	unsigned long *p = map + BIT_WORD(start);
-	const int size = start + nr;
+	const unsigned long size = start + nr;
 	int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
 	unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
 
-	while (nr - bits_to_set >= 0) {
+	while (nr >= bits_to_set) {
 		if (set_bits_ll(p, mask_to_set))
 			return nr;
 		nr -= bits_to_set;
@@ -116,14 +116,15 @@ static int bitmap_set_ll(unsigned long *map, int start, int nr)
  * users clear the same bit, one user will return remain bits,
  * otherwise return 0.
  */
-static int bitmap_clear_ll(unsigned long *map, int start, int nr)
+static unsigned long
+bitmap_clear_ll(unsigned long *map, unsigned long start, unsigned long nr)
 {
 	unsigned long *p = map + BIT_WORD(start);
-	const int size = start + nr;
+	const unsigned long size = start + nr;
 	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
 	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
 
-	while (nr - bits_to_clear >= 0) {
+	while (nr >= bits_to_clear) {
 		if (clear_bits_ll(p, mask_to_clear))
 			return nr;
 		nr -= bits_to_clear;
@@ -183,8 +184,8 @@ int gen_pool_add_owner(struct gen_pool *pool, unsigned long virt, phys_addr_t ph
 		 size_t size, int nid, void *owner)
 {
 	struct gen_pool_chunk *chunk;
-	int nbits = size >> pool->min_alloc_order;
-	int nbytes = sizeof(struct gen_pool_chunk) +
+	unsigned long nbits = size >> pool->min_alloc_order;
+	unsigned long nbytes = sizeof(struct gen_pool_chunk) +
 				BITS_TO_LONGS(nbits) * sizeof(long);
 
 	chunk = vzalloc_node(nbytes, nid);
@@ -242,7 +243,7 @@ void gen_pool_destroy(struct gen_pool *pool)
 	struct list_head *_chunk, *_next_chunk;
 	struct gen_pool_chunk *chunk;
 	int order = pool->min_alloc_order;
-	int bit, end_bit;
+	unsigned long bit, end_bit;
 
 	list_for_each_safe(_chunk, _next_chunk, &pool->chunks) {
 		chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
@@ -278,7 +279,7 @@ unsigned long gen_pool_alloc_algo_owner(struct gen_pool *pool, size_t size,
 	struct gen_pool_chunk *chunk;
 	unsigned long addr = 0;
 	int order = pool->min_alloc_order;
-	int nbits, start_bit, end_bit, remain;
+	unsigned long nbits, start_bit, end_bit, remain;
 
 #ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
 	BUG_ON(in_nmi());
@@ -487,7 +488,7 @@ void gen_pool_free_owner(struct gen_pool *pool, unsigned long addr, size_t size,
 {
 	struct gen_pool_chunk *chunk;
 	int order = pool->min_alloc_order;
-	int start_bit, nbits, remain;
+	unsigned long start_bit, nbits, remain;
 
 #ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
 	BUG_ON(in_nmi());
@@ -755,7 +756,7 @@ unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
 	index = bitmap_find_next_zero_area(map, size, start, nr, 0);
 
 	while (index < size) {
-		int next_bit = find_next_bit(map, size, index + nr);
+		unsigned long next_bit = find_next_bit(map, size, index + nr);
 		if ((next_bit - index) < len) {
 			len = next_bit - index;
 			start_bit = index;
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 1635111c5bd2..a21e6a5792c5 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1658,7 +1658,7 @@ static int copy_compat_iovec_from_user(struct iovec *iov,
 		(const struct compat_iovec __user *)uvec;
 	int ret = -EFAULT, i;
 
-	if (!user_access_begin(uvec, nr_segs * sizeof(*uvec)))
+	if (!user_access_begin(uiov, nr_segs * sizeof(*uiov)))
 		return -EFAULT;
 
 	for (i = 0; i < nr_segs; i++) {
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index b4c0df6d706d..c770570bfe4f 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -48,7 +48,7 @@ endif
 endif
 
 quiet_cmd_unroll = UNROLL  $@
-      cmd_unroll = $(AWK) -f$(srctree)/$(src)/unroll.awk -vN=$* < $< > $@
+      cmd_unroll = $(AWK) -v N=$* -f $(srctree)/$(src)/unroll.awk < $< > $@
 
 targets += int1.c int2.c int4.c int8.c int16.c int32.c
 $(obj)/int%.c: $(src)/int.uc $(src)/unroll.awk FORCE
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 662f862702fc..2947274cc2d3 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -25,7 +25,7 @@
 
 #include "../mm/kasan/kasan.h"
 
-#define OOB_TAG_OFF (IS_ENABLED(CONFIG_KASAN_GENERIC) ? 0 : KASAN_SHADOW_SCALE_SIZE)
+#define OOB_TAG_OFF (IS_ENABLED(CONFIG_KASAN_GENERIC) ? 0 : KASAN_GRANULE_SIZE)
 
 /*
  * We assign some test results to these globals to make sure the tests
diff --git a/lib/test_kasan_module.c b/lib/test_kasan_module.c
index 62a87854b120..3b4cc77992d2 100644
--- a/lib/test_kasan_module.c
+++ b/lib/test_kasan_module.c
@@ -15,7 +15,7 @@
 
 #include "../mm/kasan/kasan.h"
 
-#define OOB_TAG_OFF (IS_ENABLED(CONFIG_KASAN_GENERIC) ? 0 : KASAN_SHADOW_SCALE_SIZE)
+#define OOB_TAG_OFF (IS_ENABLED(CONFIG_KASAN_GENERIC) ? 0 : KASAN_GRANULE_SIZE)
 
 static noinline void __init copy_user_test(void)
 {
diff --git a/lib/zlib_dfltcc/Makefile b/lib/zlib_dfltcc/Makefile
index 8e4d5afbbb10..66e1c96387c4 100644
--- a/lib/zlib_dfltcc/Makefile
+++ b/lib/zlib_dfltcc/Makefile
@@ -8,4 +8,4 @@
 
 obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc.o
 
-zlib_dfltcc-objs := dfltcc.o dfltcc_deflate.o dfltcc_inflate.o dfltcc_syms.o
+zlib_dfltcc-objs := dfltcc.o dfltcc_deflate.o dfltcc_inflate.o
diff --git a/lib/zlib_dfltcc/dfltcc.c b/lib/zlib_dfltcc/dfltcc.c
index c30de430b30c..782f76e9d4da 100644
--- a/lib/zlib_dfltcc/dfltcc.c
+++ b/lib/zlib_dfltcc/dfltcc.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: Zlib
 /* dfltcc.c - SystemZ DEFLATE CONVERSION CALL support. */
 
-#include <linux/zutil.h>
+#include <linux/export.h>
+#include <linux/module.h>
 #include "dfltcc_util.h"
 #include "dfltcc.h"
 
@@ -53,3 +54,6 @@ void dfltcc_reset(
     dfltcc_state->dht_threshold = DFLTCC_DHT_MIN_SAMPLE_SIZE;
     dfltcc_state->param.ribm = DFLTCC_RIBM;
 }
+EXPORT_SYMBOL(dfltcc_reset);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/zlib_dfltcc/dfltcc_deflate.c b/lib/zlib_dfltcc/dfltcc_deflate.c
index 00c185101c6d..6c946e8532ee 100644
--- a/lib/zlib_dfltcc/dfltcc_deflate.c
+++ b/lib/zlib_dfltcc/dfltcc_deflate.c
@@ -4,6 +4,7 @@
 #include "dfltcc_util.h"
 #include "dfltcc.h"
 #include <asm/setup.h>
+#include <linux/export.h>
 #include <linux/zutil.h>
 
 /*
@@ -34,6 +35,7 @@ int dfltcc_can_deflate(
 
     return 1;
 }
+EXPORT_SYMBOL(dfltcc_can_deflate);
 
 static void dfltcc_gdht(
     z_streamp strm
@@ -277,3 +279,4 @@ again:
         goto again; /* deflate() must use all input or all output */
     return 1;
 }
+EXPORT_SYMBOL(dfltcc_deflate);
diff --git a/lib/zlib_dfltcc/dfltcc_inflate.c b/lib/zlib_dfltcc/dfltcc_inflate.c
index db107016d29b..fb60b5a6a1cb 100644
--- a/lib/zlib_dfltcc/dfltcc_inflate.c
+++ b/lib/zlib_dfltcc/dfltcc_inflate.c
@@ -125,7 +125,7 @@ dfltcc_inflate_action dfltcc_inflate(
     param->ho = (state->write - state->whave) & ((1 << HB_BITS) - 1);
     if (param->hl)
         param->nt = 0; /* Honor history for the first block */
-    param->cv = state->flags ? REVERSE(state->check) : state->check;
+    param->cv = state->check;
 
     /* Inflate */
     do {
@@ -138,7 +138,7 @@ dfltcc_inflate_action dfltcc_inflate(
     state->bits = param->sbb;
     state->whave = param->hl;
     state->write = (param->ho + param->hl) & ((1 << HB_BITS) - 1);
-    state->check = state->flags ? REVERSE(param->cv) : param->cv;
+    state->check = param->cv;
     if (cc == DFLTCC_CC_OP2_CORRUPT && param->oesc != 0) {
         /* Report an error if stream is corrupted */
         state->mode = BAD;
diff --git a/lib/zlib_dfltcc/dfltcc_syms.c b/lib/zlib_dfltcc/dfltcc_syms.c
deleted file mode 100644
index 6f23481804c1..000000000000
--- a/lib/zlib_dfltcc/dfltcc_syms.c
+++ /dev/null
@@ -1,17 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/lib/zlib_dfltcc/dfltcc_syms.c
- *
- * Exported symbols for the s390 zlib dfltcc support.
- *
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/zlib.h>
-#include "dfltcc.h"
-
-EXPORT_SYMBOL(dfltcc_can_deflate);
-EXPORT_SYMBOL(dfltcc_deflate);
-EXPORT_SYMBOL(dfltcc_reset);
-MODULE_LICENSE("GPL");
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index cbf32d2824fd..18f6ee317900 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4105,10 +4105,30 @@ retry_avoidcopy:
 		 * may get SIGKILLed if it later faults.
 		 */
 		if (outside_reserve) {
+			struct address_space *mapping = vma->vm_file->f_mapping;
+			pgoff_t idx;
+			u32 hash;
+
 			put_page(old_page);
 			BUG_ON(huge_pte_none(pte));
+			/*
+			 * Drop hugetlb_fault_mutex and i_mmap_rwsem before
+			 * unmapping.  unmapping needs to hold i_mmap_rwsem
+			 * in write mode.  Dropping i_mmap_rwsem in read mode
+			 * here is OK as COW mappings do not interact with
+			 * PMD sharing.
+			 *
+			 * Reacquire both after unmap operation.
+			 */
+			idx = vma_hugecache_offset(h, vma, haddr);
+			hash = hugetlb_fault_mutex_hash(mapping, idx);
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			i_mmap_unlock_read(mapping);
+
 			unmap_ref_private(mm, vma, old_page, haddr);
-			BUG_ON(huge_pte_none(pte));
+
+			i_mmap_lock_read(mapping);
+			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 			spin_lock(ptl);
 			ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
 			if (likely(ptep &&
@@ -4351,7 +4371,7 @@ retry:
 		 * So we need to block hugepage fault by PG_hwpoison bit check.
 		 */
 		if (unlikely(PageHWPoison(page))) {
-			ret = VM_FAULT_HWPOISON |
+			ret = VM_FAULT_HWPOISON_LARGE |
 				VM_FAULT_SET_HINDEX(hstate_index(h));
 			goto backout_unlocked;
 		}
diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index 370d970e5ab5..9fe39a66388a 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -6,12 +6,15 @@ KCOV_INSTRUMENT := n
 # Disable ftrace to avoid recursion.
 CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_generic.o = $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_generic_report.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_quarantine.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_tags_report.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_report_generic.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_report_hw_tags.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_report_sw_tags.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_shadow.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_hw_tags.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_sw_tags.o = $(CC_FLAGS_FTRACE)
 
 # Function splitter causes unnecessary splits in __asan_load1/__asan_store1
 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533
@@ -22,13 +25,17 @@ CC_FLAGS_KASAN_RUNTIME += -DDISABLE_BRANCH_PROFILING
 
 CFLAGS_common.o := $(CC_FLAGS_KASAN_RUNTIME)
 CFLAGS_generic.o := $(CC_FLAGS_KASAN_RUNTIME)
-CFLAGS_generic_report.o := $(CC_FLAGS_KASAN_RUNTIME)
 CFLAGS_init.o := $(CC_FLAGS_KASAN_RUNTIME)
 CFLAGS_quarantine.o := $(CC_FLAGS_KASAN_RUNTIME)
 CFLAGS_report.o := $(CC_FLAGS_KASAN_RUNTIME)
-CFLAGS_tags.o := $(CC_FLAGS_KASAN_RUNTIME)
-CFLAGS_tags_report.o := $(CC_FLAGS_KASAN_RUNTIME)
+CFLAGS_report_generic.o := $(CC_FLAGS_KASAN_RUNTIME)
+CFLAGS_report_hw_tags.o := $(CC_FLAGS_KASAN_RUNTIME)
+CFLAGS_report_sw_tags.o := $(CC_FLAGS_KASAN_RUNTIME)
+CFLAGS_shadow.o := $(CC_FLAGS_KASAN_RUNTIME)
+CFLAGS_hw_tags.o := $(CC_FLAGS_KASAN_RUNTIME)
+CFLAGS_sw_tags.o := $(CC_FLAGS_KASAN_RUNTIME)
 
-obj-$(CONFIG_KASAN) := common.o init.o report.o
-obj-$(CONFIG_KASAN_GENERIC) += generic.o generic_report.o quarantine.o
-obj-$(CONFIG_KASAN_SW_TAGS) += tags.o tags_report.o
+obj-$(CONFIG_KASAN) := common.o report.o
+obj-$(CONFIG_KASAN_GENERIC) += init.o generic.o report_generic.o shadow.o quarantine.o
+obj-$(CONFIG_KASAN_HW_TAGS) += hw_tags.o report_hw_tags.o
+obj-$(CONFIG_KASAN_SW_TAGS) += init.o report_sw_tags.o shadow.o sw_tags.o
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 950fd372a07e..b25167664ead 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -1,24 +1,18 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * This file contains common generic and tag-based KASAN code.
+ * This file contains common KASAN code.
  *
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
  * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
  *
  * Some code borrowed from https://github.com/xairy/kasan-prototype by
  *        Andrey Konovalov <andreyknvl@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #include <linux/export.h>
 #include <linux/init.h>
 #include <linux/kasan.h>
 #include <linux/kernel.h>
-#include <linux/kmemleak.h>
 #include <linux/linkage.h>
 #include <linux/memblock.h>
 #include <linux/memory.h>
@@ -31,12 +25,8 @@
 #include <linux/stacktrace.h>
 #include <linux/string.h>
 #include <linux/types.h>
-#include <linux/vmalloc.h>
 #include <linux/bug.h>
 
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-
 #include "kasan.h"
 #include "../slab.h"
 
@@ -56,6 +46,7 @@ void kasan_set_track(struct kasan_track *track, gfp_t flags)
 	track->stack = kasan_save_stack(flags);
 }
 
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 void kasan_enable_current(void)
 {
 	current->kasan_depth++;
@@ -65,106 +56,20 @@ void kasan_disable_current(void)
 {
 	current->kasan_depth--;
 }
+#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
-bool __kasan_check_read(const volatile void *p, unsigned int size)
-{
-	return check_memory_region((unsigned long)p, size, false, _RET_IP_);
-}
-EXPORT_SYMBOL(__kasan_check_read);
-
-bool __kasan_check_write(const volatile void *p, unsigned int size)
-{
-	return check_memory_region((unsigned long)p, size, true, _RET_IP_);
-}
-EXPORT_SYMBOL(__kasan_check_write);
-
-#undef memset
-void *memset(void *addr, int c, size_t len)
-{
-	if (!check_memory_region((unsigned long)addr, len, true, _RET_IP_))
-		return NULL;
-
-	return __memset(addr, c, len);
-}
-
-#ifdef __HAVE_ARCH_MEMMOVE
-#undef memmove
-void *memmove(void *dest, const void *src, size_t len)
-{
-	if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) ||
-	    !check_memory_region((unsigned long)dest, len, true, _RET_IP_))
-		return NULL;
-
-	return __memmove(dest, src, len);
-}
-#endif
-
-#undef memcpy
-void *memcpy(void *dest, const void *src, size_t len)
+void __kasan_unpoison_range(const void *address, size_t size)
 {
-	if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) ||
-	    !check_memory_region((unsigned long)dest, len, true, _RET_IP_))
-		return NULL;
-
-	return __memcpy(dest, src, len);
-}
-
-/*
- * Poisons the shadow memory for 'size' bytes starting from 'addr'.
- * Memory addresses should be aligned to KASAN_SHADOW_SCALE_SIZE.
- */
-void kasan_poison_shadow(const void *address, size_t size, u8 value)
-{
-	void *shadow_start, *shadow_end;
-
-	/*
-	 * Perform shadow offset calculation based on untagged address, as
-	 * some of the callers (e.g. kasan_poison_object_data) pass tagged
-	 * addresses to this function.
-	 */
-	address = reset_tag(address);
-
-	shadow_start = kasan_mem_to_shadow(address);
-	shadow_end = kasan_mem_to_shadow(address + size);
-
-	__memset(shadow_start, value, shadow_end - shadow_start);
-}
-
-void kasan_unpoison_shadow(const void *address, size_t size)
-{
-	u8 tag = get_tag(address);
-
-	/*
-	 * Perform shadow offset calculation based on untagged address, as
-	 * some of the callers (e.g. kasan_unpoison_object_data) pass tagged
-	 * addresses to this function.
-	 */
-	address = reset_tag(address);
-
-	kasan_poison_shadow(address, size, tag);
-
-	if (size & KASAN_SHADOW_MASK) {
-		u8 *shadow = (u8 *)kasan_mem_to_shadow(address + size);
-
-		if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
-			*shadow = tag;
-		else
-			*shadow = size & KASAN_SHADOW_MASK;
-	}
-}
-
-static void __kasan_unpoison_stack(struct task_struct *task, const void *sp)
-{
-	void *base = task_stack_page(task);
-	size_t size = sp - base;
-
-	kasan_unpoison_shadow(base, size);
+	unpoison_range(address, size);
 }
 
+#if CONFIG_KASAN_STACK
 /* Unpoison the entire stack for a task. */
 void kasan_unpoison_task_stack(struct task_struct *task)
 {
-	__kasan_unpoison_stack(task, task_stack_page(task) + THREAD_SIZE);
+	void *base = task_stack_page(task);
+
+	unpoison_range(base, THREAD_SIZE);
 }
 
 /* Unpoison the stack for the current task beyond a watermark sp value. */
@@ -177,10 +82,22 @@ asmlinkage void kasan_unpoison_task_stack_below(const void *watermark)
 	 */
 	void *base = (void *)((unsigned long)watermark & ~(THREAD_SIZE - 1));
 
-	kasan_unpoison_shadow(base, watermark - base);
+	unpoison_range(base, watermark - base);
+}
+#endif /* CONFIG_KASAN_STACK */
+
+/*
+ * Only allow cache merging when stack collection is disabled and no metadata
+ * is present.
+ */
+slab_flags_t __kasan_never_merge(void)
+{
+	if (kasan_stack_collection_enabled())
+		return SLAB_KASAN;
+	return 0;
 }
 
-void kasan_alloc_pages(struct page *page, unsigned int order)
+void __kasan_alloc_pages(struct page *page, unsigned int order)
 {
 	u8 tag;
 	unsigned long i;
@@ -191,13 +108,13 @@ void kasan_alloc_pages(struct page *page, unsigned int order)
 	tag = random_tag();
 	for (i = 0; i < (1 << order); i++)
 		page_kasan_tag_set(page + i, tag);
-	kasan_unpoison_shadow(page_address(page), PAGE_SIZE << order);
+	unpoison_range(page_address(page), PAGE_SIZE << order);
 }
 
-void kasan_free_pages(struct page *page, unsigned int order)
+void __kasan_free_pages(struct page *page, unsigned int order)
 {
 	if (likely(!PageHighMem(page)))
-		kasan_poison_shadow(page_address(page),
+		poison_range(page_address(page),
 				PAGE_SIZE << order,
 				KASAN_FREE_PAGE);
 }
@@ -208,9 +125,6 @@ void kasan_free_pages(struct page *page, unsigned int order)
  */
 static inline unsigned int optimal_redzone(unsigned int object_size)
 {
-	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
-		return 0;
-
 	return
 		object_size <= 64        - 16   ? 16 :
 		object_size <= 128       - 32   ? 32 :
@@ -221,88 +135,129 @@ static inline unsigned int optimal_redzone(unsigned int object_size)
 		object_size <= (1 << 16) - 1024 ? 1024 : 2048;
 }
 
-void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
-			slab_flags_t *flags)
+void __kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
+			  slab_flags_t *flags)
 {
-	unsigned int orig_size = *size;
-	unsigned int redzone_size;
-	int redzone_adjust;
+	unsigned int ok_size;
+	unsigned int optimal_size;
 
-	/* Add alloc meta. */
-	cache->kasan_info.alloc_meta_offset = *size;
-	*size += sizeof(struct kasan_alloc_meta);
+	/*
+	 * SLAB_KASAN is used to mark caches as ones that are sanitized by
+	 * KASAN. Currently this flag is used in two places:
+	 * 1. In slab_ksize() when calculating the size of the accessible
+	 *    memory within the object.
+	 * 2. In slab_common.c to prevent merging of sanitized caches.
+	 */
+	*flags |= SLAB_KASAN;
 
-	/* Add free meta. */
-	if (IS_ENABLED(CONFIG_KASAN_GENERIC) &&
-	    (cache->flags & SLAB_TYPESAFE_BY_RCU || cache->ctor ||
-	     cache->object_size < sizeof(struct kasan_free_meta))) {
-		cache->kasan_info.free_meta_offset = *size;
-		*size += sizeof(struct kasan_free_meta);
-	}
+	if (!kasan_stack_collection_enabled())
+		return;
 
-	redzone_size = optimal_redzone(cache->object_size);
-	redzone_adjust = redzone_size -	(*size - cache->object_size);
-	if (redzone_adjust > 0)
-		*size += redzone_adjust;
+	ok_size = *size;
 
-	*size = min_t(unsigned int, KMALLOC_MAX_SIZE,
-			max(*size, cache->object_size + redzone_size));
+	/* Add alloc meta into redzone. */
+	cache->kasan_info.alloc_meta_offset = *size;
+	*size += sizeof(struct kasan_alloc_meta);
 
 	/*
-	 * If the metadata doesn't fit, don't enable KASAN at all.
+	 * If alloc meta doesn't fit, don't add it.
+	 * This can only happen with SLAB, as it has KMALLOC_MAX_SIZE equal
+	 * to KMALLOC_MAX_CACHE_SIZE and doesn't fall back to page_alloc for
+	 * larger sizes.
 	 */
-	if (*size <= cache->kasan_info.alloc_meta_offset ||
-			*size <= cache->kasan_info.free_meta_offset) {
+	if (*size > KMALLOC_MAX_SIZE) {
 		cache->kasan_info.alloc_meta_offset = 0;
-		cache->kasan_info.free_meta_offset = 0;
-		*size = orig_size;
+		*size = ok_size;
+		/* Continue, since free meta might still fit. */
+	}
+
+	/* Only the generic mode uses free meta or flexible redzones. */
+	if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+		cache->kasan_info.free_meta_offset = KASAN_NO_FREE_META;
 		return;
 	}
 
-	*flags |= SLAB_KASAN;
+	/*
+	 * Add free meta into redzone when it's not possible to store
+	 * it in the object. This is the case when:
+	 * 1. Object is SLAB_TYPESAFE_BY_RCU, which means that it can
+	 *    be touched after it was freed, or
+	 * 2. Object has a constructor, which means it's expected to
+	 *    retain its content until the next allocation, or
+	 * 3. Object is too small.
+	 * Otherwise cache->kasan_info.free_meta_offset = 0 is implied.
+	 */
+	if ((cache->flags & SLAB_TYPESAFE_BY_RCU) || cache->ctor ||
+	    cache->object_size < sizeof(struct kasan_free_meta)) {
+		ok_size = *size;
+
+		cache->kasan_info.free_meta_offset = *size;
+		*size += sizeof(struct kasan_free_meta);
+
+		/* If free meta doesn't fit, don't add it. */
+		if (*size > KMALLOC_MAX_SIZE) {
+			cache->kasan_info.free_meta_offset = KASAN_NO_FREE_META;
+			*size = ok_size;
+		}
+	}
+
+	/* Calculate size with optimal redzone. */
+	optimal_size = cache->object_size + optimal_redzone(cache->object_size);
+	/* Limit it with KMALLOC_MAX_SIZE (relevant for SLAB only). */
+	if (optimal_size > KMALLOC_MAX_SIZE)
+		optimal_size = KMALLOC_MAX_SIZE;
+	/* Use optimal size if the size with added metas is not large enough. */
+	if (*size < optimal_size)
+		*size = optimal_size;
 }
 
-size_t kasan_metadata_size(struct kmem_cache *cache)
+size_t __kasan_metadata_size(struct kmem_cache *cache)
 {
+	if (!kasan_stack_collection_enabled())
+		return 0;
 	return (cache->kasan_info.alloc_meta_offset ?
 		sizeof(struct kasan_alloc_meta) : 0) +
 		(cache->kasan_info.free_meta_offset ?
 		sizeof(struct kasan_free_meta) : 0);
 }
 
-struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
-					const void *object)
+struct kasan_alloc_meta *kasan_get_alloc_meta(struct kmem_cache *cache,
+					      const void *object)
 {
-	return (void *)object + cache->kasan_info.alloc_meta_offset;
+	if (!cache->kasan_info.alloc_meta_offset)
+		return NULL;
+	return kasan_reset_tag(object) + cache->kasan_info.alloc_meta_offset;
 }
 
-struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
-				      const void *object)
+#ifdef CONFIG_KASAN_GENERIC
+struct kasan_free_meta *kasan_get_free_meta(struct kmem_cache *cache,
+					    const void *object)
 {
 	BUILD_BUG_ON(sizeof(struct kasan_free_meta) > 32);
-	return (void *)object + cache->kasan_info.free_meta_offset;
+	if (cache->kasan_info.free_meta_offset == KASAN_NO_FREE_META)
+		return NULL;
+	return kasan_reset_tag(object) + cache->kasan_info.free_meta_offset;
 }
+#endif
 
-void kasan_poison_slab(struct page *page)
+void __kasan_poison_slab(struct page *page)
 {
 	unsigned long i;
 
 	for (i = 0; i < compound_nr(page); i++)
 		page_kasan_tag_reset(page + i);
-	kasan_poison_shadow(page_address(page), page_size(page),
-			KASAN_KMALLOC_REDZONE);
+	poison_range(page_address(page), page_size(page),
+		     KASAN_KMALLOC_REDZONE);
 }
 
-void kasan_unpoison_object_data(struct kmem_cache *cache, void *object)
+void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object)
 {
-	kasan_unpoison_shadow(object, cache->object_size);
+	unpoison_range(object, cache->object_size);
 }
 
-void kasan_poison_object_data(struct kmem_cache *cache, void *object)
+void __kasan_poison_object_data(struct kmem_cache *cache, void *object)
 {
-	kasan_poison_shadow(object,
-			round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE),
-			KASAN_KMALLOC_REDZONE);
+	poison_range(object, cache->object_size, KASAN_KMALLOC_REDZONE);
 }
 
 /*
@@ -322,6 +277,9 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object)
 static u8 assign_tag(struct kmem_cache *cache, const void *object,
 			bool init, bool keep_tag)
 {
+	if (IS_ENABLED(CONFIG_KASAN_GENERIC))
+		return 0xff;
+
 	/*
 	 * 1. When an object is kmalloc()'ed, two hooks are called:
 	 *    kasan_slab_alloc() and kasan_kmalloc(). We assign the
@@ -351,50 +309,32 @@ static u8 assign_tag(struct kmem_cache *cache, const void *object,
 #endif
 }
 
-void * __must_check kasan_init_slab_obj(struct kmem_cache *cache,
+void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
 						const void *object)
 {
-	struct kasan_alloc_meta *alloc_info;
+	struct kasan_alloc_meta *alloc_meta;
 
-	if (!(cache->flags & SLAB_KASAN))
-		return (void *)object;
-
-	alloc_info = get_alloc_info(cache, object);
-	__memset(alloc_info, 0, sizeof(*alloc_info));
+	if (kasan_stack_collection_enabled()) {
+		alloc_meta = kasan_get_alloc_meta(cache, object);
+		if (alloc_meta)
+			__memset(alloc_meta, 0, sizeof(*alloc_meta));
+	}
 
-	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
-		object = set_tag(object,
-				assign_tag(cache, object, true, false));
+	/* Tag is ignored in set_tag() without CONFIG_KASAN_SW/HW_TAGS */
+	object = set_tag(object, assign_tag(cache, object, true, false));
 
 	return (void *)object;
 }
 
-static inline bool shadow_invalid(u8 tag, s8 shadow_byte)
-{
-	if (IS_ENABLED(CONFIG_KASAN_GENERIC))
-		return shadow_byte < 0 ||
-			shadow_byte >= KASAN_SHADOW_SCALE_SIZE;
-
-	/* else CONFIG_KASAN_SW_TAGS: */
-	if ((u8)shadow_byte == KASAN_TAG_INVALID)
-		return true;
-	if ((tag != KASAN_TAG_KERNEL) && (tag != (u8)shadow_byte))
-		return true;
-
-	return false;
-}
-
-static bool __kasan_slab_free(struct kmem_cache *cache, void *object,
+static bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
 			      unsigned long ip, bool quarantine)
 {
-	s8 shadow_byte;
 	u8 tag;
 	void *tagged_object;
-	unsigned long rounded_up_size;
 
 	tag = get_tag(object);
 	tagged_object = object;
-	object = reset_tag(object);
+	object = kasan_reset_tag(object);
 
 	if (unlikely(nearest_obj(cache, virt_to_head_page(object), object) !=
 	    object)) {
@@ -406,37 +346,67 @@ static bool __kasan_slab_free(struct kmem_cache *cache, void *object,
 	if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU))
 		return false;
 
-	shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object));
-	if (shadow_invalid(tag, shadow_byte)) {
+	if (check_invalid_free(tagged_object)) {
 		kasan_report_invalid_free(tagged_object, ip);
 		return true;
 	}
 
-	rounded_up_size = round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE);
-	kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE);
+	poison_range(object, cache->object_size, KASAN_KMALLOC_FREE);
 
-	if ((IS_ENABLED(CONFIG_KASAN_GENERIC) && !quarantine) ||
-			unlikely(!(cache->flags & SLAB_KASAN)))
+	if (!kasan_stack_collection_enabled())
+		return false;
+
+	if ((IS_ENABLED(CONFIG_KASAN_GENERIC) && !quarantine))
 		return false;
 
 	kasan_set_free_info(cache, object, tag);
 
-	quarantine_put(get_free_info(cache, object), cache);
+	return quarantine_put(cache, object);
+}
 
-	return IS_ENABLED(CONFIG_KASAN_GENERIC);
+bool __kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip)
+{
+	return ____kasan_slab_free(cache, object, ip, true);
 }
 
-bool kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip)
+void __kasan_slab_free_mempool(void *ptr, unsigned long ip)
 {
-	return __kasan_slab_free(cache, object, ip, true);
+	struct page *page;
+
+	page = virt_to_head_page(ptr);
+
+	/*
+	 * Even though this function is only called for kmem_cache_alloc and
+	 * kmalloc backed mempool allocations, those allocations can still be
+	 * !PageSlab() when the size provided to kmalloc is larger than
+	 * KMALLOC_MAX_SIZE, and kmalloc falls back onto page_alloc.
+	 */
+	if (unlikely(!PageSlab(page))) {
+		if (ptr != page_address(page)) {
+			kasan_report_invalid_free(ptr, ip);
+			return;
+		}
+		poison_range(ptr, page_size(page), KASAN_FREE_PAGE);
+	} else {
+		____kasan_slab_free(page->slab_cache, ptr, ip, false);
+	}
+}
+
+static void set_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
+{
+	struct kasan_alloc_meta *alloc_meta;
+
+	alloc_meta = kasan_get_alloc_meta(cache, object);
+	if (alloc_meta)
+		kasan_set_track(&alloc_meta->alloc_track, flags);
 }
 
-static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object,
+static void *____kasan_kmalloc(struct kmem_cache *cache, const void *object,
 				size_t size, gfp_t flags, bool keep_tag)
 {
 	unsigned long redzone_start;
 	unsigned long redzone_end;
-	u8 tag = 0xff;
+	u8 tag;
 
 	if (gfpflags_allow_blocking(flags))
 		quarantine_reduce();
@@ -445,38 +415,36 @@ static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object,
 		return NULL;
 
 	redzone_start = round_up((unsigned long)(object + size),
-				KASAN_SHADOW_SCALE_SIZE);
+				KASAN_GRANULE_SIZE);
 	redzone_end = round_up((unsigned long)object + cache->object_size,
-				KASAN_SHADOW_SCALE_SIZE);
-
-	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
-		tag = assign_tag(cache, object, false, keep_tag);
+				KASAN_GRANULE_SIZE);
+	tag = assign_tag(cache, object, false, keep_tag);
 
-	/* Tag is ignored in set_tag without CONFIG_KASAN_SW_TAGS */
-	kasan_unpoison_shadow(set_tag(object, tag), size);
-	kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start,
-		KASAN_KMALLOC_REDZONE);
+	/* Tag is ignored in set_tag without CONFIG_KASAN_SW/HW_TAGS */
+	unpoison_range(set_tag(object, tag), size);
+	poison_range((void *)redzone_start, redzone_end - redzone_start,
+		     KASAN_KMALLOC_REDZONE);
 
-	if (cache->flags & SLAB_KASAN)
-		kasan_set_track(&get_alloc_info(cache, object)->alloc_track, flags);
+	if (kasan_stack_collection_enabled())
+		set_alloc_info(cache, (void *)object, flags);
 
 	return set_tag(object, tag);
 }
 
-void * __must_check kasan_slab_alloc(struct kmem_cache *cache, void *object,
-					gfp_t flags)
+void * __must_check __kasan_slab_alloc(struct kmem_cache *cache,
+					void *object, gfp_t flags)
 {
-	return __kasan_kmalloc(cache, object, cache->object_size, flags, false);
+	return ____kasan_kmalloc(cache, object, cache->object_size, flags, false);
 }
 
-void * __must_check kasan_kmalloc(struct kmem_cache *cache, const void *object,
-				size_t size, gfp_t flags)
+void * __must_check __kasan_kmalloc(struct kmem_cache *cache, const void *object,
+					size_t size, gfp_t flags)
 {
-	return __kasan_kmalloc(cache, object, size, flags, true);
+	return ____kasan_kmalloc(cache, object, size, flags, true);
 }
-EXPORT_SYMBOL(kasan_kmalloc);
+EXPORT_SYMBOL(__kasan_kmalloc);
 
-void * __must_check kasan_kmalloc_large(const void *ptr, size_t size,
+void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size,
 						gfp_t flags)
 {
 	struct page *page;
@@ -491,17 +459,17 @@ void * __must_check kasan_kmalloc_large(const void *ptr, size_t size,
 
 	page = virt_to_page(ptr);
 	redzone_start = round_up((unsigned long)(ptr + size),
-				KASAN_SHADOW_SCALE_SIZE);
+				KASAN_GRANULE_SIZE);
 	redzone_end = (unsigned long)ptr + page_size(page);
 
-	kasan_unpoison_shadow(ptr, size);
-	kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start,
-		KASAN_PAGE_REDZONE);
+	unpoison_range(ptr, size);
+	poison_range((void *)redzone_start, redzone_end - redzone_start,
+		     KASAN_PAGE_REDZONE);
 
 	return (void *)ptr;
 }
 
-void * __must_check kasan_krealloc(const void *object, size_t size, gfp_t flags)
+void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flags)
 {
 	struct page *page;
 
@@ -511,421 +479,15 @@ void * __must_check kasan_krealloc(const void *object, size_t size, gfp_t flags)
 	page = virt_to_head_page(object);
 
 	if (unlikely(!PageSlab(page)))
-		return kasan_kmalloc_large(object, size, flags);
+		return __kasan_kmalloc_large(object, size, flags);
 	else
-		return __kasan_kmalloc(page->slab_cache, object, size,
+		return ____kasan_kmalloc(page->slab_cache, object, size,
 						flags, true);
 }
 
-void kasan_poison_kfree(void *ptr, unsigned long ip)
-{
-	struct page *page;
-
-	page = virt_to_head_page(ptr);
-
-	if (unlikely(!PageSlab(page))) {
-		if (ptr != page_address(page)) {
-			kasan_report_invalid_free(ptr, ip);
-			return;
-		}
-		kasan_poison_shadow(ptr, page_size(page), KASAN_FREE_PAGE);
-	} else {
-		__kasan_slab_free(page->slab_cache, ptr, ip, false);
-	}
-}
-
-void kasan_kfree_large(void *ptr, unsigned long ip)
+void __kasan_kfree_large(void *ptr, unsigned long ip)
 {
 	if (ptr != page_address(virt_to_head_page(ptr)))
 		kasan_report_invalid_free(ptr, ip);
-	/* The object will be poisoned by page_alloc. */
-}
-
-#ifndef CONFIG_KASAN_VMALLOC
-int kasan_module_alloc(void *addr, size_t size)
-{
-	void *ret;
-	size_t scaled_size;
-	size_t shadow_size;
-	unsigned long shadow_start;
-
-	shadow_start = (unsigned long)kasan_mem_to_shadow(addr);
-	scaled_size = (size + KASAN_SHADOW_MASK) >> KASAN_SHADOW_SCALE_SHIFT;
-	shadow_size = round_up(scaled_size, PAGE_SIZE);
-
-	if (WARN_ON(!PAGE_ALIGNED(shadow_start)))
-		return -EINVAL;
-
-	ret = __vmalloc_node_range(shadow_size, 1, shadow_start,
-			shadow_start + shadow_size,
-			GFP_KERNEL,
-			PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE,
-			__builtin_return_address(0));
-
-	if (ret) {
-		__memset(ret, KASAN_SHADOW_INIT, shadow_size);
-		find_vm_area(addr)->flags |= VM_KASAN;
-		kmemleak_ignore(ret);
-		return 0;
-	}
-
-	return -ENOMEM;
-}
-
-void kasan_free_shadow(const struct vm_struct *vm)
-{
-	if (vm->flags & VM_KASAN)
-		vfree(kasan_mem_to_shadow(vm->addr));
-}
-#endif
-
-#ifdef CONFIG_MEMORY_HOTPLUG
-static bool shadow_mapped(unsigned long addr)
-{
-	pgd_t *pgd = pgd_offset_k(addr);
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	if (pgd_none(*pgd))
-		return false;
-	p4d = p4d_offset(pgd, addr);
-	if (p4d_none(*p4d))
-		return false;
-	pud = pud_offset(p4d, addr);
-	if (pud_none(*pud))
-		return false;
-
-	/*
-	 * We can't use pud_large() or pud_huge(), the first one is
-	 * arch-specific, the last one depends on HUGETLB_PAGE.  So let's abuse
-	 * pud_bad(), if pud is bad then it's bad because it's huge.
-	 */
-	if (pud_bad(*pud))
-		return true;
-	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
-		return false;
-
-	if (pmd_bad(*pmd))
-		return true;
-	pte = pte_offset_kernel(pmd, addr);
-	return !pte_none(*pte);
-}
-
-static int __meminit kasan_mem_notifier(struct notifier_block *nb,
-			unsigned long action, void *data)
-{
-	struct memory_notify *mem_data = data;
-	unsigned long nr_shadow_pages, start_kaddr, shadow_start;
-	unsigned long shadow_end, shadow_size;
-
-	nr_shadow_pages = mem_data->nr_pages >> KASAN_SHADOW_SCALE_SHIFT;
-	start_kaddr = (unsigned long)pfn_to_kaddr(mem_data->start_pfn);
-	shadow_start = (unsigned long)kasan_mem_to_shadow((void *)start_kaddr);
-	shadow_size = nr_shadow_pages << PAGE_SHIFT;
-	shadow_end = shadow_start + shadow_size;
-
-	if (WARN_ON(mem_data->nr_pages % KASAN_SHADOW_SCALE_SIZE) ||
-		WARN_ON(start_kaddr % (KASAN_SHADOW_SCALE_SIZE << PAGE_SHIFT)))
-		return NOTIFY_BAD;
-
-	switch (action) {
-	case MEM_GOING_ONLINE: {
-		void *ret;
-
-		/*
-		 * If shadow is mapped already than it must have been mapped
-		 * during the boot. This could happen if we onlining previously
-		 * offlined memory.
-		 */
-		if (shadow_mapped(shadow_start))
-			return NOTIFY_OK;
-
-		ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start,
-					shadow_end, GFP_KERNEL,
-					PAGE_KERNEL, VM_NO_GUARD,
-					pfn_to_nid(mem_data->start_pfn),
-					__builtin_return_address(0));
-		if (!ret)
-			return NOTIFY_BAD;
-
-		kmemleak_ignore(ret);
-		return NOTIFY_OK;
-	}
-	case MEM_CANCEL_ONLINE:
-	case MEM_OFFLINE: {
-		struct vm_struct *vm;
-
-		/*
-		 * shadow_start was either mapped during boot by kasan_init()
-		 * or during memory online by __vmalloc_node_range().
-		 * In the latter case we can use vfree() to free shadow.
-		 * Non-NULL result of the find_vm_area() will tell us if
-		 * that was the second case.
-		 *
-		 * Currently it's not possible to free shadow mapped
-		 * during boot by kasan_init(). It's because the code
-		 * to do that hasn't been written yet. So we'll just
-		 * leak the memory.
-		 */
-		vm = find_vm_area((void *)shadow_start);
-		if (vm)
-			vfree((void *)shadow_start);
-	}
-	}
-
-	return NOTIFY_OK;
-}
-
-static int __init kasan_memhotplug_init(void)
-{
-	hotplug_memory_notifier(kasan_mem_notifier, 0);
-
-	return 0;
-}
-
-core_initcall(kasan_memhotplug_init);
-#endif
-
-#ifdef CONFIG_KASAN_VMALLOC
-static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
-				      void *unused)
-{
-	unsigned long page;
-	pte_t pte;
-
-	if (likely(!pte_none(*ptep)))
-		return 0;
-
-	page = __get_free_page(GFP_KERNEL);
-	if (!page)
-		return -ENOMEM;
-
-	memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE);
-	pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL);
-
-	spin_lock(&init_mm.page_table_lock);
-	if (likely(pte_none(*ptep))) {
-		set_pte_at(&init_mm, addr, ptep, pte);
-		page = 0;
-	}
-	spin_unlock(&init_mm.page_table_lock);
-	if (page)
-		free_page(page);
-	return 0;
-}
-
-int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
-{
-	unsigned long shadow_start, shadow_end;
-	int ret;
-
-	if (!is_vmalloc_or_module_addr((void *)addr))
-		return 0;
-
-	shadow_start = (unsigned long)kasan_mem_to_shadow((void *)addr);
-	shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE);
-	shadow_end = (unsigned long)kasan_mem_to_shadow((void *)addr + size);
-	shadow_end = ALIGN(shadow_end, PAGE_SIZE);
-
-	ret = apply_to_page_range(&init_mm, shadow_start,
-				  shadow_end - shadow_start,
-				  kasan_populate_vmalloc_pte, NULL);
-	if (ret)
-		return ret;
-
-	flush_cache_vmap(shadow_start, shadow_end);
-
-	/*
-	 * We need to be careful about inter-cpu effects here. Consider:
-	 *
-	 *   CPU#0				  CPU#1
-	 * WRITE_ONCE(p, vmalloc(100));		while (x = READ_ONCE(p)) ;
-	 *					p[99] = 1;
-	 *
-	 * With compiler instrumentation, that ends up looking like this:
-	 *
-	 *   CPU#0				  CPU#1
-	 * // vmalloc() allocates memory
-	 * // let a = area->addr
-	 * // we reach kasan_populate_vmalloc
-	 * // and call kasan_unpoison_shadow:
-	 * STORE shadow(a), unpoison_val
-	 * ...
-	 * STORE shadow(a+99), unpoison_val	x = LOAD p
-	 * // rest of vmalloc process		<data dependency>
-	 * STORE p, a				LOAD shadow(x+99)
-	 *
-	 * If there is no barrier between the end of unpoisioning the shadow
-	 * and the store of the result to p, the stores could be committed
-	 * in a different order by CPU#0, and CPU#1 could erroneously observe
-	 * poison in the shadow.
-	 *
-	 * We need some sort of barrier between the stores.
-	 *
-	 * In the vmalloc() case, this is provided by a smp_wmb() in
-	 * clear_vm_uninitialized_flag(). In the per-cpu allocator and in
-	 * get_vm_area() and friends, the caller gets shadow allocated but
-	 * doesn't have any pages mapped into the virtual address space that
-	 * has been reserved. Mapping those pages in will involve taking and
-	 * releasing a page-table lock, which will provide the barrier.
-	 */
-
-	return 0;
-}
-
-/*
- * Poison the shadow for a vmalloc region. Called as part of the
- * freeing process at the time the region is freed.
- */
-void kasan_poison_vmalloc(const void *start, unsigned long size)
-{
-	if (!is_vmalloc_or_module_addr(start))
-		return;
-
-	size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
-	kasan_poison_shadow(start, size, KASAN_VMALLOC_INVALID);
-}
-
-void kasan_unpoison_vmalloc(const void *start, unsigned long size)
-{
-	if (!is_vmalloc_or_module_addr(start))
-		return;
-
-	kasan_unpoison_shadow(start, size);
+	/* The object will be poisoned by kasan_free_pages(). */
 }
-
-static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
-					void *unused)
-{
-	unsigned long page;
-
-	page = (unsigned long)__va(pte_pfn(*ptep) << PAGE_SHIFT);
-
-	spin_lock(&init_mm.page_table_lock);
-
-	if (likely(!pte_none(*ptep))) {
-		pte_clear(&init_mm, addr, ptep);
-		free_page(page);
-	}
-	spin_unlock(&init_mm.page_table_lock);
-
-	return 0;
-}
-
-/*
- * Release the backing for the vmalloc region [start, end), which
- * lies within the free region [free_region_start, free_region_end).
- *
- * This can be run lazily, long after the region was freed. It runs
- * under vmap_area_lock, so it's not safe to interact with the vmalloc/vmap
- * infrastructure.
- *
- * How does this work?
- * -------------------
- *
- * We have a region that is page aligned, labelled as A.
- * That might not map onto the shadow in a way that is page-aligned:
- *
- *                    start                     end
- *                    v                         v
- * |????????|????????|AAAAAAAA|AA....AA|AAAAAAAA|????????| < vmalloc
- *  -------- -------- --------          -------- --------
- *      |        |       |                 |        |
- *      |        |       |         /-------/        |
- *      \-------\|/------/         |/---------------/
- *              |||                ||
- *             |??AAAAAA|AAAAAAAA|AA??????|                < shadow
- *                 (1)      (2)      (3)
- *
- * First we align the start upwards and the end downwards, so that the
- * shadow of the region aligns with shadow page boundaries. In the
- * example, this gives us the shadow page (2). This is the shadow entirely
- * covered by this allocation.
- *
- * Then we have the tricky bits. We want to know if we can free the
- * partially covered shadow pages - (1) and (3) in the example. For this,
- * we are given the start and end of the free region that contains this
- * allocation. Extending our previous example, we could have:
- *
- *  free_region_start                                    free_region_end
- *  |                 start                     end      |
- *  v                 v                         v        v
- * |FFFFFFFF|FFFFFFFF|AAAAAAAA|AA....AA|AAAAAAAA|FFFFFFFF| < vmalloc
- *  -------- -------- --------          -------- --------
- *      |        |       |                 |        |
- *      |        |       |         /-------/        |
- *      \-------\|/------/         |/---------------/
- *              |||                ||
- *             |FFAAAAAA|AAAAAAAA|AAF?????|                < shadow
- *                 (1)      (2)      (3)
- *
- * Once again, we align the start of the free region up, and the end of
- * the free region down so that the shadow is page aligned. So we can free
- * page (1) - we know no allocation currently uses anything in that page,
- * because all of it is in the vmalloc free region. But we cannot free
- * page (3), because we can't be sure that the rest of it is unused.
- *
- * We only consider pages that contain part of the original region for
- * freeing: we don't try to free other pages from the free region or we'd
- * end up trying to free huge chunks of virtual address space.
- *
- * Concurrency
- * -----------
- *
- * How do we know that we're not freeing a page that is simultaneously
- * being used for a fresh allocation in kasan_populate_vmalloc(_pte)?
- *
- * We _can_ have kasan_release_vmalloc and kasan_populate_vmalloc running
- * at the same time. While we run under free_vmap_area_lock, the population
- * code does not.
- *
- * free_vmap_area_lock instead operates to ensure that the larger range
- * [free_region_start, free_region_end) is safe: because __alloc_vmap_area and
- * the per-cpu region-finding algorithm both run under free_vmap_area_lock,
- * no space identified as free will become used while we are running. This
- * means that so long as we are careful with alignment and only free shadow
- * pages entirely covered by the free region, we will not run in to any
- * trouble - any simultaneous allocations will be for disjoint regions.
- */
-void kasan_release_vmalloc(unsigned long start, unsigned long end,
-			   unsigned long free_region_start,
-			   unsigned long free_region_end)
-{
-	void *shadow_start, *shadow_end;
-	unsigned long region_start, region_end;
-	unsigned long size;
-
-	region_start = ALIGN(start, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);
-	region_end = ALIGN_DOWN(end, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);
-
-	free_region_start = ALIGN(free_region_start,
-				  PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);
-
-	if (start != region_start &&
-	    free_region_start < region_start)
-		region_start -= PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE;
-
-	free_region_end = ALIGN_DOWN(free_region_end,
-				     PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);
-
-	if (end != region_end &&
-	    free_region_end > region_end)
-		region_end += PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE;
-
-	shadow_start = kasan_mem_to_shadow((void *)region_start);
-	shadow_end = kasan_mem_to_shadow((void *)region_end);
-
-	if (shadow_end > shadow_start) {
-		size = shadow_end - shadow_start;
-		apply_to_existing_page_range(&init_mm,
-					     (unsigned long)shadow_start,
-					     size, kasan_depopulate_vmalloc_pte,
-					     NULL);
-		flush_tlb_kernel_range((unsigned long)shadow_start,
-				       (unsigned long)shadow_end);
-	}
-}
-#endif
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index 30c0a5038b5c..5106b84b07d4 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -7,15 +7,8 @@
  *
  * Some code borrowed from https://github.com/xairy/kasan-prototype by
  *        Andrey Konovalov <andreyknvl@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
 #include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
@@ -51,7 +44,7 @@ static __always_inline bool memory_is_poisoned_1(unsigned long addr)
 	s8 shadow_value = *(s8 *)kasan_mem_to_shadow((void *)addr);
 
 	if (unlikely(shadow_value)) {
-		s8 last_accessible_byte = addr & KASAN_SHADOW_MASK;
+		s8 last_accessible_byte = addr & KASAN_GRANULE_MASK;
 		return unlikely(last_accessible_byte >= shadow_value);
 	}
 
@@ -67,7 +60,7 @@ static __always_inline bool memory_is_poisoned_2_4_8(unsigned long addr,
 	 * Access crosses 8(shadow size)-byte boundary. Such access maps
 	 * into 2 shadow bytes, so we need to check them both.
 	 */
-	if (unlikely(((addr + size - 1) & KASAN_SHADOW_MASK) < size - 1))
+	if (unlikely(((addr + size - 1) & KASAN_GRANULE_MASK) < size - 1))
 		return *shadow_addr || memory_is_poisoned_1(addr + size - 1);
 
 	return memory_is_poisoned_1(addr + size - 1);
@@ -78,7 +71,7 @@ static __always_inline bool memory_is_poisoned_16(unsigned long addr)
 	u16 *shadow_addr = (u16 *)kasan_mem_to_shadow((void *)addr);
 
 	/* Unaligned 16-bytes access maps into 3 shadow bytes. */
-	if (unlikely(!IS_ALIGNED(addr, KASAN_SHADOW_SCALE_SIZE)))
+	if (unlikely(!IS_ALIGNED(addr, KASAN_GRANULE_SIZE)))
 		return *shadow_addr || memory_is_poisoned_1(addr + 15);
 
 	return *shadow_addr;
@@ -139,7 +132,7 @@ static __always_inline bool memory_is_poisoned_n(unsigned long addr,
 		s8 *last_shadow = (s8 *)kasan_mem_to_shadow((void *)last_byte);
 
 		if (unlikely(ret != (unsigned long)last_shadow ||
-			((long)(last_byte & KASAN_SHADOW_MASK) >= *last_shadow)))
+			((long)(last_byte & KASAN_GRANULE_MASK) >= *last_shadow)))
 			return true;
 	}
 	return false;
@@ -192,6 +185,13 @@ bool check_memory_region(unsigned long addr, size_t size, bool write,
 	return check_memory_region_inline(addr, size, write, ret_ip);
 }
 
+bool check_invalid_free(void *addr)
+{
+	s8 shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(addr));
+
+	return shadow_byte < 0 || shadow_byte >= KASAN_GRANULE_SIZE;
+}
+
 void kasan_cache_shrink(struct kmem_cache *cache)
 {
 	quarantine_remove_cache(cache);
@@ -205,13 +205,13 @@ void kasan_cache_shutdown(struct kmem_cache *cache)
 
 static void register_global(struct kasan_global *global)
 {
-	size_t aligned_size = round_up(global->size, KASAN_SHADOW_SCALE_SIZE);
+	size_t aligned_size = round_up(global->size, KASAN_GRANULE_SIZE);
 
-	kasan_unpoison_shadow(global->beg, global->size);
+	unpoison_range(global->beg, global->size);
 
-	kasan_poison_shadow(global->beg + aligned_size,
-		global->size_with_redzone - aligned_size,
-		KASAN_GLOBAL_REDZONE);
+	poison_range(global->beg + aligned_size,
+		     global->size_with_redzone - aligned_size,
+		     KASAN_GLOBAL_REDZONE);
 }
 
 void __asan_register_globals(struct kasan_global *globals, size_t size)
@@ -279,10 +279,10 @@ EXPORT_SYMBOL(__asan_handle_no_return);
 /* Emitted by compiler to poison alloca()ed objects. */
 void __asan_alloca_poison(unsigned long addr, size_t size)
 {
-	size_t rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
+	size_t rounded_up_size = round_up(size, KASAN_GRANULE_SIZE);
 	size_t padding_size = round_up(size, KASAN_ALLOCA_REDZONE_SIZE) -
 			rounded_up_size;
-	size_t rounded_down_size = round_down(size, KASAN_SHADOW_SCALE_SIZE);
+	size_t rounded_down_size = round_down(size, KASAN_GRANULE_SIZE);
 
 	const void *left_redzone = (const void *)(addr -
 			KASAN_ALLOCA_REDZONE_SIZE);
@@ -290,13 +290,12 @@ void __asan_alloca_poison(unsigned long addr, size_t size)
 
 	WARN_ON(!IS_ALIGNED(addr, KASAN_ALLOCA_REDZONE_SIZE));
 
-	kasan_unpoison_shadow((const void *)(addr + rounded_down_size),
-			      size - rounded_down_size);
-	kasan_poison_shadow(left_redzone, KASAN_ALLOCA_REDZONE_SIZE,
-			KASAN_ALLOCA_LEFT);
-	kasan_poison_shadow(right_redzone,
-			padding_size + KASAN_ALLOCA_REDZONE_SIZE,
-			KASAN_ALLOCA_RIGHT);
+	unpoison_range((const void *)(addr + rounded_down_size),
+		       size - rounded_down_size);
+	poison_range(left_redzone, KASAN_ALLOCA_REDZONE_SIZE,
+		     KASAN_ALLOCA_LEFT);
+	poison_range(right_redzone, padding_size + KASAN_ALLOCA_REDZONE_SIZE,
+		     KASAN_ALLOCA_RIGHT);
 }
 EXPORT_SYMBOL(__asan_alloca_poison);
 
@@ -306,7 +305,7 @@ void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom)
 	if (unlikely(!stack_top || stack_top > stack_bottom))
 		return;
 
-	kasan_unpoison_shadow(stack_top, stack_bottom - stack_top);
+	unpoison_range(stack_top, stack_bottom - stack_top);
 }
 EXPORT_SYMBOL(__asan_allocas_unpoison);
 
@@ -329,7 +328,7 @@ void kasan_record_aux_stack(void *addr)
 {
 	struct page *page = kasan_addr_to_page(addr);
 	struct kmem_cache *cache;
-	struct kasan_alloc_meta *alloc_info;
+	struct kasan_alloc_meta *alloc_meta;
 	void *object;
 
 	if (!(page && PageSlab(page)))
@@ -337,10 +336,12 @@ void kasan_record_aux_stack(void *addr)
 
 	cache = page->slab_cache;
 	object = nearest_obj(cache, page, addr);
-	alloc_info = get_alloc_info(cache, object);
+	alloc_meta = kasan_get_alloc_meta(cache, object);
+	if (!alloc_meta)
+		return;
 
-	alloc_info->aux_stack[1] = alloc_info->aux_stack[0];
-	alloc_info->aux_stack[0] = kasan_save_stack(GFP_NOWAIT);
+	alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0];
+	alloc_meta->aux_stack[0] = kasan_save_stack(GFP_NOWAIT);
 }
 
 void kasan_set_free_info(struct kmem_cache *cache,
@@ -348,12 +349,12 @@ void kasan_set_free_info(struct kmem_cache *cache,
 {
 	struct kasan_free_meta *free_meta;
 
-	free_meta = get_free_info(cache, object);
-	kasan_set_track(&free_meta->free_track, GFP_NOWAIT);
+	free_meta = kasan_get_free_meta(cache, object);
+	if (!free_meta)
+		return;
 
-	/*
-	 *  the object was freed and has free track set
-	 */
+	kasan_set_track(&free_meta->free_track, GFP_NOWAIT);
+	/* The object was freed and has free track set. */
 	*(u8 *)kasan_mem_to_shadow(object) = KASAN_KMALLOC_FREETRACK;
 }
 
@@ -362,5 +363,6 @@ struct kasan_track *kasan_get_free_track(struct kmem_cache *cache,
 {
 	if (*(u8 *)kasan_mem_to_shadow(object) != KASAN_KMALLOC_FREETRACK)
 		return NULL;
-	return &get_free_info(cache, object)->free_track;
+	/* Free meta must be present with KASAN_KMALLOC_FREETRACK. */
+	return &kasan_get_free_meta(cache, object)->free_track;
 }
diff --git a/mm/kasan/generic_report.c b/mm/kasan/generic_report.c
deleted file mode 100644
index a38c7a9e192a..000000000000
--- a/mm/kasan/generic_report.c
+++ /dev/null
@@ -1,165 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * This file contains generic KASAN specific error reporting code.
- *
- * Copyright (c) 2014 Samsung Electronics Co., Ltd.
- * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
- *
- * Some code borrowed from https://github.com/xairy/kasan-prototype by
- *        Andrey Konovalov <andreyknvl@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#include <linux/bitops.h>
-#include <linux/ftrace.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/printk.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/stackdepot.h>
-#include <linux/stacktrace.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/kasan.h>
-#include <linux/module.h>
-
-#include <asm/sections.h>
-
-#include "kasan.h"
-#include "../slab.h"
-
-void *find_first_bad_addr(void *addr, size_t size)
-{
-	void *p = addr;
-
-	while (p < addr + size && !(*(u8 *)kasan_mem_to_shadow(p)))
-		p += KASAN_SHADOW_SCALE_SIZE;
-	return p;
-}
-
-static const char *get_shadow_bug_type(struct kasan_access_info *info)
-{
-	const char *bug_type = "unknown-crash";
-	u8 *shadow_addr;
-
-	shadow_addr = (u8 *)kasan_mem_to_shadow(info->first_bad_addr);
-
-	/*
-	 * If shadow byte value is in [0, KASAN_SHADOW_SCALE_SIZE) we can look
-	 * at the next shadow byte to determine the type of the bad access.
-	 */
-	if (*shadow_addr > 0 && *shadow_addr <= KASAN_SHADOW_SCALE_SIZE - 1)
-		shadow_addr++;
-
-	switch (*shadow_addr) {
-	case 0 ... KASAN_SHADOW_SCALE_SIZE - 1:
-		/*
-		 * In theory it's still possible to see these shadow values
-		 * due to a data race in the kernel code.
-		 */
-		bug_type = "out-of-bounds";
-		break;
-	case KASAN_PAGE_REDZONE:
-	case KASAN_KMALLOC_REDZONE:
-		bug_type = "slab-out-of-bounds";
-		break;
-	case KASAN_GLOBAL_REDZONE:
-		bug_type = "global-out-of-bounds";
-		break;
-	case KASAN_STACK_LEFT:
-	case KASAN_STACK_MID:
-	case KASAN_STACK_RIGHT:
-	case KASAN_STACK_PARTIAL:
-		bug_type = "stack-out-of-bounds";
-		break;
-	case KASAN_FREE_PAGE:
-	case KASAN_KMALLOC_FREE:
-	case KASAN_KMALLOC_FREETRACK:
-		bug_type = "use-after-free";
-		break;
-	case KASAN_ALLOCA_LEFT:
-	case KASAN_ALLOCA_RIGHT:
-		bug_type = "alloca-out-of-bounds";
-		break;
-	case KASAN_VMALLOC_INVALID:
-		bug_type = "vmalloc-out-of-bounds";
-		break;
-	}
-
-	return bug_type;
-}
-
-static const char *get_wild_bug_type(struct kasan_access_info *info)
-{
-	const char *bug_type = "unknown-crash";
-
-	if ((unsigned long)info->access_addr < PAGE_SIZE)
-		bug_type = "null-ptr-deref";
-	else if ((unsigned long)info->access_addr < TASK_SIZE)
-		bug_type = "user-memory-access";
-	else
-		bug_type = "wild-memory-access";
-
-	return bug_type;
-}
-
-const char *get_bug_type(struct kasan_access_info *info)
-{
-	/*
-	 * If access_size is a negative number, then it has reason to be
-	 * defined as out-of-bounds bug type.
-	 *
-	 * Casting negative numbers to size_t would indeed turn up as
-	 * a large size_t and its value will be larger than ULONG_MAX/2,
-	 * so that this can qualify as out-of-bounds.
-	 */
-	if (info->access_addr + info->access_size < info->access_addr)
-		return "out-of-bounds";
-
-	if (addr_has_shadow(info->access_addr))
-		return get_shadow_bug_type(info);
-	return get_wild_bug_type(info);
-}
-
-#define DEFINE_ASAN_REPORT_LOAD(size)                     \
-void __asan_report_load##size##_noabort(unsigned long addr) \
-{                                                         \
-	kasan_report(addr, size, false, _RET_IP_);	  \
-}                                                         \
-EXPORT_SYMBOL(__asan_report_load##size##_noabort)
-
-#define DEFINE_ASAN_REPORT_STORE(size)                     \
-void __asan_report_store##size##_noabort(unsigned long addr) \
-{                                                          \
-	kasan_report(addr, size, true, _RET_IP_);	   \
-}                                                          \
-EXPORT_SYMBOL(__asan_report_store##size##_noabort)
-
-DEFINE_ASAN_REPORT_LOAD(1);
-DEFINE_ASAN_REPORT_LOAD(2);
-DEFINE_ASAN_REPORT_LOAD(4);
-DEFINE_ASAN_REPORT_LOAD(8);
-DEFINE_ASAN_REPORT_LOAD(16);
-DEFINE_ASAN_REPORT_STORE(1);
-DEFINE_ASAN_REPORT_STORE(2);
-DEFINE_ASAN_REPORT_STORE(4);
-DEFINE_ASAN_REPORT_STORE(8);
-DEFINE_ASAN_REPORT_STORE(16);
-
-void __asan_report_load_n_noabort(unsigned long addr, size_t size)
-{
-	kasan_report(addr, size, false, _RET_IP_);
-}
-EXPORT_SYMBOL(__asan_report_load_n_noabort);
-
-void __asan_report_store_n_noabort(unsigned long addr, size_t size)
-{
-	kasan_report(addr, size, true, _RET_IP_);
-}
-EXPORT_SYMBOL(__asan_report_store_n_noabort);
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
new file mode 100644
index 000000000000..55bd6f09c70f
--- /dev/null
+++ b/mm/kasan/hw_tags.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains core hardware tag-based KASAN code.
+ *
+ * Copyright (c) 2020 Google, Inc.
+ * Author: Andrey Konovalov <andreyknvl@google.com>
+ */
+
+#define pr_fmt(fmt) "kasan: " fmt
+
+#include <linux/init.h>
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memory.h>
+#include <linux/mm.h>
+#include <linux/static_key.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "kasan.h"
+
+enum kasan_arg_mode {
+	KASAN_ARG_MODE_DEFAULT,
+	KASAN_ARG_MODE_OFF,
+	KASAN_ARG_MODE_PROD,
+	KASAN_ARG_MODE_FULL,
+};
+
+enum kasan_arg_stacktrace {
+	KASAN_ARG_STACKTRACE_DEFAULT,
+	KASAN_ARG_STACKTRACE_OFF,
+	KASAN_ARG_STACKTRACE_ON,
+};
+
+enum kasan_arg_fault {
+	KASAN_ARG_FAULT_DEFAULT,
+	KASAN_ARG_FAULT_REPORT,
+	KASAN_ARG_FAULT_PANIC,
+};
+
+static enum kasan_arg_mode kasan_arg_mode __ro_after_init;
+static enum kasan_arg_stacktrace kasan_arg_stacktrace __ro_after_init;
+static enum kasan_arg_fault kasan_arg_fault __ro_after_init;
+
+/* Whether KASAN is enabled at all. */
+DEFINE_STATIC_KEY_FALSE(kasan_flag_enabled);
+EXPORT_SYMBOL(kasan_flag_enabled);
+
+/* Whether to collect alloc/free stack traces. */
+DEFINE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
+
+/* Whether panic or disable tag checking on fault. */
+bool kasan_flag_panic __ro_after_init;
+
+/* kasan.mode=off/prod/full */
+static int __init early_kasan_mode(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	if (!strcmp(arg, "off"))
+		kasan_arg_mode = KASAN_ARG_MODE_OFF;
+	else if (!strcmp(arg, "prod"))
+		kasan_arg_mode = KASAN_ARG_MODE_PROD;
+	else if (!strcmp(arg, "full"))
+		kasan_arg_mode = KASAN_ARG_MODE_FULL;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+early_param("kasan.mode", early_kasan_mode);
+
+/* kasan.stack=off/on */
+static int __init early_kasan_flag_stacktrace(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	if (!strcmp(arg, "off"))
+		kasan_arg_stacktrace = KASAN_ARG_STACKTRACE_OFF;
+	else if (!strcmp(arg, "on"))
+		kasan_arg_stacktrace = KASAN_ARG_STACKTRACE_ON;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+early_param("kasan.stacktrace", early_kasan_flag_stacktrace);
+
+/* kasan.fault=report/panic */
+static int __init early_kasan_fault(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	if (!strcmp(arg, "report"))
+		kasan_arg_fault = KASAN_ARG_FAULT_REPORT;
+	else if (!strcmp(arg, "panic"))
+		kasan_arg_fault = KASAN_ARG_FAULT_PANIC;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+early_param("kasan.fault", early_kasan_fault);
+
+/* kasan_init_hw_tags_cpu() is called for each CPU. */
+void kasan_init_hw_tags_cpu(void)
+{
+	/*
+	 * There's no need to check that the hardware is MTE-capable here,
+	 * as this function is only called for MTE-capable hardware.
+	 */
+
+	/* If KASAN is disabled, do nothing. */
+	if (kasan_arg_mode == KASAN_ARG_MODE_OFF)
+		return;
+
+	hw_init_tags(KASAN_TAG_MAX);
+	hw_enable_tagging();
+}
+
+/* kasan_init_hw_tags() is called once on boot CPU. */
+void __init kasan_init_hw_tags(void)
+{
+	/* If hardware doesn't support MTE, do nothing. */
+	if (!system_supports_mte())
+		return;
+
+	/* Choose KASAN mode if kasan boot parameter is not provided. */
+	if (kasan_arg_mode == KASAN_ARG_MODE_DEFAULT) {
+		if (IS_ENABLED(CONFIG_DEBUG_KERNEL))
+			kasan_arg_mode = KASAN_ARG_MODE_FULL;
+		else
+			kasan_arg_mode = KASAN_ARG_MODE_PROD;
+	}
+
+	/* Preset parameter values based on the mode. */
+	switch (kasan_arg_mode) {
+	case KASAN_ARG_MODE_DEFAULT:
+		/* Shouldn't happen as per the check above. */
+		WARN_ON(1);
+		return;
+	case KASAN_ARG_MODE_OFF:
+		/* If KASAN is disabled, do nothing. */
+		return;
+	case KASAN_ARG_MODE_PROD:
+		static_branch_enable(&kasan_flag_enabled);
+		break;
+	case KASAN_ARG_MODE_FULL:
+		static_branch_enable(&kasan_flag_enabled);
+		static_branch_enable(&kasan_flag_stacktrace);
+		break;
+	}
+
+	/* Now, optionally override the presets. */
+
+	switch (kasan_arg_stacktrace) {
+	case KASAN_ARG_STACKTRACE_DEFAULT:
+		break;
+	case KASAN_ARG_STACKTRACE_OFF:
+		static_branch_disable(&kasan_flag_stacktrace);
+		break;
+	case KASAN_ARG_STACKTRACE_ON:
+		static_branch_enable(&kasan_flag_stacktrace);
+		break;
+	}
+
+	switch (kasan_arg_fault) {
+	case KASAN_ARG_FAULT_DEFAULT:
+		break;
+	case KASAN_ARG_FAULT_REPORT:
+		kasan_flag_panic = false;
+		break;
+	case KASAN_ARG_FAULT_PANIC:
+		kasan_flag_panic = true;
+		break;
+	}
+
+	pr_info("KernelAddressSanitizer initialized\n");
+}
+
+void kasan_set_free_info(struct kmem_cache *cache,
+				void *object, u8 tag)
+{
+	struct kasan_alloc_meta *alloc_meta;
+
+	alloc_meta = kasan_get_alloc_meta(cache, object);
+	if (alloc_meta)
+		kasan_set_track(&alloc_meta->free_track[0], GFP_NOWAIT);
+}
+
+struct kasan_track *kasan_get_free_track(struct kmem_cache *cache,
+				void *object, u8 tag)
+{
+	struct kasan_alloc_meta *alloc_meta;
+
+	alloc_meta = kasan_get_alloc_meta(cache, object);
+	if (!alloc_meta)
+		return NULL;
+
+	return &alloc_meta->free_track[0];
+}
diff --git a/mm/kasan/init.c b/mm/kasan/init.c
index fe6be0be1f76..7ca0b92d5886 100644
--- a/mm/kasan/init.c
+++ b/mm/kasan/init.c
@@ -1,14 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * This file contains some kasan initialization code.
+ * This file contains KASAN shadow initialization code.
  *
  * Copyright (c) 2015 Samsung Electronics Co., Ltd.
  * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #include <linux/memblock.h>
@@ -69,7 +64,8 @@ static inline bool kasan_pmd_table(pud_t pud)
 	return false;
 }
 #endif
-pte_t kasan_early_shadow_pte[PTRS_PER_PTE] __page_aligned_bss;
+pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS]
+	__page_aligned_bss;
 
 static inline bool kasan_pte_table(pmd_t pmd)
 {
@@ -446,9 +442,8 @@ void kasan_remove_zero_shadow(void *start, unsigned long size)
 	addr = (unsigned long)kasan_mem_to_shadow(start);
 	end = addr + (size >> KASAN_SHADOW_SCALE_SHIFT);
 
-	if (WARN_ON((unsigned long)start %
-			(KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE)) ||
-	    WARN_ON(size % (KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE)))
+	if (WARN_ON((unsigned long)start % KASAN_MEMORY_PER_SHADOW_PAGE) ||
+	    WARN_ON(size % KASAN_MEMORY_PER_SHADOW_PAGE))
 		return;
 
 	for (; addr < end; addr = next) {
@@ -481,9 +476,8 @@ int kasan_add_zero_shadow(void *start, unsigned long size)
 	shadow_start = kasan_mem_to_shadow(start);
 	shadow_end = shadow_start + (size >> KASAN_SHADOW_SCALE_SHIFT);
 
-	if (WARN_ON((unsigned long)start %
-			(KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE)) ||
-	    WARN_ON(size % (KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE)))
+	if (WARN_ON((unsigned long)start % KASAN_MEMORY_PER_SHADOW_PAGE) ||
+	    WARN_ON(size % KASAN_MEMORY_PER_SHADOW_PAGE))
 		return -EINVAL;
 
 	ret = kasan_populate_early_shadow(shadow_start, shadow_end);
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index ac499456740f..cc4d9e1d49b1 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -5,8 +5,32 @@
 #include <linux/kasan.h>
 #include <linux/stackdepot.h>
 
-#define KASAN_SHADOW_SCALE_SIZE (1UL << KASAN_SHADOW_SCALE_SHIFT)
-#define KASAN_SHADOW_MASK       (KASAN_SHADOW_SCALE_SIZE - 1)
+#ifdef CONFIG_KASAN_HW_TAGS
+#include <linux/static_key.h>
+DECLARE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
+static inline bool kasan_stack_collection_enabled(void)
+{
+	return static_branch_unlikely(&kasan_flag_stacktrace);
+}
+#else
+static inline bool kasan_stack_collection_enabled(void)
+{
+	return true;
+}
+#endif
+
+extern bool kasan_flag_panic __ro_after_init;
+
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+#define KASAN_GRANULE_SIZE	(1UL << KASAN_SHADOW_SCALE_SHIFT)
+#else
+#include <asm/mte-kasan.h>
+#define KASAN_GRANULE_SIZE	MTE_GRANULE_SIZE
+#endif
+
+#define KASAN_GRANULE_MASK	(KASAN_GRANULE_SIZE - 1)
+
+#define KASAN_MEMORY_PER_SHADOW_PAGE	(KASAN_GRANULE_SIZE << PAGE_SHIFT)
 
 #define KASAN_TAG_KERNEL	0xFF /* native kernel pointers tag */
 #define KASAN_TAG_INVALID	0xFE /* inaccessible memory tag */
@@ -56,6 +80,13 @@
 #define KASAN_ABI_VERSION 1
 #endif
 
+/* Metadata layout customization. */
+#define META_BYTES_PER_BLOCK 1
+#define META_BLOCKS_PER_ROW 16
+#define META_BYTES_PER_ROW (META_BLOCKS_PER_ROW * META_BYTES_PER_BLOCK)
+#define META_MEM_BYTES_PER_ROW (META_BYTES_PER_ROW * KASAN_GRANULE_SIZE)
+#define META_ROWS_AROUND_ADDR 2
+
 struct kasan_access_info {
 	const void *access_addr;
 	const void *first_bad_addr;
@@ -124,20 +155,33 @@ struct kasan_alloc_meta {
 struct qlist_node {
 	struct qlist_node *next;
 };
+
+/*
+ * Generic mode either stores free meta in the object itself or in the redzone
+ * after the object. In the former case free meta offset is 0, in the latter
+ * case it has some sane value smaller than INT_MAX. Use INT_MAX as free meta
+ * offset when free meta isn't present.
+ */
+#define KASAN_NO_FREE_META INT_MAX
+
 struct kasan_free_meta {
+#ifdef CONFIG_KASAN_GENERIC
 	/* This field is used while the object is in the quarantine.
 	 * Otherwise it might be used for the allocator freelist.
 	 */
 	struct qlist_node quarantine_link;
-#ifdef CONFIG_KASAN_GENERIC
 	struct kasan_track free_track;
 #endif
 };
 
-struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
-					const void *object);
-struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
-					const void *object);
+struct kasan_alloc_meta *kasan_get_alloc_meta(struct kmem_cache *cache,
+						const void *object);
+#ifdef CONFIG_KASAN_GENERIC
+struct kasan_free_meta *kasan_get_free_meta(struct kmem_cache *cache,
+						const void *object);
+#endif
+
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 
 static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
 {
@@ -145,13 +189,11 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
 		<< KASAN_SHADOW_SCALE_SHIFT);
 }
 
-static inline bool addr_has_shadow(const void *addr)
+static inline bool addr_has_metadata(const void *addr)
 {
 	return (addr >= kasan_shadow_to_mem((void *)KASAN_SHADOW_START));
 }
 
-void kasan_poison_shadow(const void *address, size_t size, u8 value);
-
 /**
  * check_memory_region - Check memory region, and report if invalid access.
  * @addr: the accessed address
@@ -163,8 +205,30 @@ void kasan_poison_shadow(const void *address, size_t size, u8 value);
 bool check_memory_region(unsigned long addr, size_t size, bool write,
 				unsigned long ret_ip);
 
+#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
+
+static inline bool addr_has_metadata(const void *addr)
+{
+	return true;
+}
+
+#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
+
+#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
+void print_tags(u8 addr_tag, const void *addr);
+#else
+static inline void print_tags(u8 addr_tag, const void *addr) { }
+#endif
+
 void *find_first_bad_addr(void *addr, size_t size);
 const char *get_bug_type(struct kasan_access_info *info);
+void metadata_fetch_row(char *buffer, void *row);
+
+#if defined(CONFIG_KASAN_GENERIC) && CONFIG_KASAN_STACK
+void print_address_stack_frame(const void *addr);
+#else
+static inline void print_address_stack_frame(const void *addr) { }
+#endif
 
 bool kasan_report(unsigned long addr, size_t size,
 		bool is_write, unsigned long ip);
@@ -180,49 +244,92 @@ struct kasan_track *kasan_get_free_track(struct kmem_cache *cache,
 
 #if defined(CONFIG_KASAN_GENERIC) && \
 	(defined(CONFIG_SLAB) || defined(CONFIG_SLUB))
-void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache);
+bool quarantine_put(struct kmem_cache *cache, void *object);
 void quarantine_reduce(void);
 void quarantine_remove_cache(struct kmem_cache *cache);
 #else
-static inline void quarantine_put(struct kasan_free_meta *info,
-				struct kmem_cache *cache) { }
+static inline bool quarantine_put(struct kmem_cache *cache, void *object) { return false; }
 static inline void quarantine_reduce(void) { }
 static inline void quarantine_remove_cache(struct kmem_cache *cache) { }
 #endif
 
-#ifdef CONFIG_KASAN_SW_TAGS
+#ifndef arch_kasan_set_tag
+static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
+{
+	return addr;
+}
+#endif
+#ifndef arch_kasan_get_tag
+#define arch_kasan_get_tag(addr)	0
+#endif
 
-void print_tags(u8 addr_tag, const void *addr);
+#define set_tag(addr, tag)	((void *)arch_kasan_set_tag((addr), (tag)))
+#define get_tag(addr)		arch_kasan_get_tag(addr)
 
-u8 random_tag(void);
+#ifdef CONFIG_KASAN_HW_TAGS
+
+#ifndef arch_enable_tagging
+#define arch_enable_tagging()
+#endif
+#ifndef arch_init_tags
+#define arch_init_tags(max_tag)
+#endif
+#ifndef arch_get_random_tag
+#define arch_get_random_tag()	(0xFF)
+#endif
+#ifndef arch_get_mem_tag
+#define arch_get_mem_tag(addr)	(0xFF)
+#endif
+#ifndef arch_set_mem_tag_range
+#define arch_set_mem_tag_range(addr, size, tag) ((void *)(addr))
+#endif
+
+#define hw_enable_tagging()			arch_enable_tagging()
+#define hw_init_tags(max_tag)			arch_init_tags(max_tag)
+#define hw_get_random_tag()			arch_get_random_tag()
+#define hw_get_mem_tag(addr)			arch_get_mem_tag(addr)
+#define hw_set_mem_tag_range(addr, size, tag)	arch_set_mem_tag_range((addr), (size), (tag))
 
+#endif /* CONFIG_KASAN_HW_TAGS */
+
+#ifdef CONFIG_KASAN_SW_TAGS
+u8 random_tag(void);
+#elif defined(CONFIG_KASAN_HW_TAGS)
+static inline u8 random_tag(void) { return hw_get_random_tag(); }
 #else
+static inline u8 random_tag(void) { return 0; }
+#endif
 
-static inline void print_tags(u8 addr_tag, const void *addr) { }
+#ifdef CONFIG_KASAN_HW_TAGS
 
-static inline u8 random_tag(void)
+static inline void poison_range(const void *address, size_t size, u8 value)
 {
-	return 0;
+	hw_set_mem_tag_range(kasan_reset_tag(address),
+			round_up(size, KASAN_GRANULE_SIZE), value);
 }
 
-#endif
+static inline void unpoison_range(const void *address, size_t size)
+{
+	hw_set_mem_tag_range(kasan_reset_tag(address),
+			round_up(size, KASAN_GRANULE_SIZE), get_tag(address));
+}
 
-#ifndef arch_kasan_set_tag
-static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
+static inline bool check_invalid_free(void *addr)
 {
-	return addr;
+	u8 ptr_tag = get_tag(addr);
+	u8 mem_tag = hw_get_mem_tag(addr);
+
+	return (mem_tag == KASAN_TAG_INVALID) ||
+		(ptr_tag != KASAN_TAG_KERNEL && ptr_tag != mem_tag);
 }
-#endif
-#ifndef arch_kasan_reset_tag
-#define arch_kasan_reset_tag(addr)	((void *)(addr))
-#endif
-#ifndef arch_kasan_get_tag
-#define arch_kasan_get_tag(addr)	0
-#endif
 
-#define set_tag(addr, tag)	((void *)arch_kasan_set_tag((addr), (tag)))
-#define reset_tag(addr)		((void *)arch_kasan_reset_tag(addr))
-#define get_tag(addr)		arch_kasan_get_tag(addr)
+#else /* CONFIG_KASAN_HW_TAGS */
+
+void poison_range(const void *address, size_t size, u8 value);
+void unpoison_range(const void *address, size_t size);
+bool check_invalid_free(void *addr);
+
+#endif /* CONFIG_KASAN_HW_TAGS */
 
 /*
  * Exported functions for interfaces called from assembly or from generated
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 0e3f8494628f..55783125a767 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -6,16 +6,6 @@
  * Copyright (C) 2016 Google, Inc.
  *
  * Based on code by Dmitry Chernenkov.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
  */
 
 #include <linux/gfp.h>
@@ -147,7 +137,12 @@ static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache)
 	if (IS_ENABLED(CONFIG_SLAB))
 		local_irq_save(flags);
 
+	/*
+	 * As the object now gets freed from the quaratine, assume that its
+	 * free track is no longer valid.
+	 */
 	*(u8 *)kasan_mem_to_shadow(object) = KASAN_KMALLOC_FREE;
+
 	___cache_free(cache, object, _THIS_IP_);
 
 	if (IS_ENABLED(CONFIG_SLAB))
@@ -173,11 +168,19 @@ static void qlist_free_all(struct qlist_head *q, struct kmem_cache *cache)
 	qlist_init(q);
 }
 
-void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
+bool quarantine_put(struct kmem_cache *cache, void *object)
 {
 	unsigned long flags;
 	struct qlist_head *q;
 	struct qlist_head temp = QLIST_INIT;
+	struct kasan_free_meta *meta = kasan_get_free_meta(cache, object);
+
+	/*
+	 * If there's no metadata for this object, don't put it into
+	 * quarantine.
+	 */
+	if (!meta)
+		return false;
 
 	/*
 	 * Note: irq must be disabled until after we move the batch to the
@@ -192,9 +195,9 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
 	q = this_cpu_ptr(&cpu_quarantine);
 	if (q->offline) {
 		local_irq_restore(flags);
-		return;
+		return false;
 	}
-	qlist_put(q, &info->quarantine_link, cache->size);
+	qlist_put(q, &meta->quarantine_link, cache->size);
 	if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) {
 		qlist_move_all(q, &temp);
 
@@ -215,6 +218,8 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
 	}
 
 	local_irq_restore(flags);
+
+	return true;
 }
 
 void quarantine_reduce(void)
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 5a0102f37171..c0fb21797550 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -1,17 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * This file contains common generic and tag-based KASAN error reporting code.
+ * This file contains common KASAN error reporting code.
  *
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
  * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
  *
  * Some code borrowed from https://github.com/xairy/kasan-prototype by
  *        Andrey Konovalov <andreyknvl@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #include <linux/bitops.h>
@@ -38,12 +33,6 @@
 #include "kasan.h"
 #include "../slab.h"
 
-/* Shadow layout customization. */
-#define SHADOW_BYTES_PER_BLOCK 1
-#define SHADOW_BLOCKS_PER_ROW 16
-#define SHADOW_BYTES_PER_ROW (SHADOW_BLOCKS_PER_ROW * SHADOW_BYTES_PER_BLOCK)
-#define SHADOW_ROWS_AROUND_ADDR 2
-
 static unsigned long kasan_flags;
 
 #define KASAN_BIT_REPORTED	0
@@ -73,9 +62,14 @@ static void print_error_description(struct kasan_access_info *info)
 {
 	pr_err("BUG: KASAN: %s in %pS\n",
 		get_bug_type(info), (void *)info->ip);
-	pr_err("%s of size %zu at addr %px by task %s/%d\n",
-		info->is_write ? "Write" : "Read", info->access_size,
-		info->access_addr, current->comm, task_pid_nr(current));
+	if (info->access_size)
+		pr_err("%s of size %zu at addr %px by task %s/%d\n",
+			info->is_write ? "Write" : "Read", info->access_size,
+			info->access_addr, current->comm, task_pid_nr(current));
+	else
+		pr_err("%s at addr %px by task %s/%d\n",
+			info->is_write ? "Write" : "Read",
+			info->access_addr, current->comm, task_pid_nr(current));
 }
 
 static DEFINE_SPINLOCK(report_lock);
@@ -105,6 +99,10 @@ static void end_report(unsigned long *flags)
 		panic_on_warn = 0;
 		panic("panic_on_warn set ...\n");
 	}
+#ifdef CONFIG_KASAN_HW_TAGS
+	if (kasan_flag_panic)
+		panic("kasan.fault=panic set ...\n");
+#endif
 	kasan_enable_current();
 }
 
@@ -167,36 +165,45 @@ static void describe_object_addr(struct kmem_cache *cache, void *object,
 		(void *)(object_addr + cache->object_size));
 }
 
-static void describe_object(struct kmem_cache *cache, void *object,
-				const void *addr, u8 tag)
+static void describe_object_stacks(struct kmem_cache *cache, void *object,
+					const void *addr, u8 tag)
 {
-	struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object);
+	struct kasan_alloc_meta *alloc_meta;
+	struct kasan_track *free_track;
 
-	if (cache->flags & SLAB_KASAN) {
-		struct kasan_track *free_track;
+	alloc_meta = kasan_get_alloc_meta(cache, object);
+	if (alloc_meta) {
+		print_track(&alloc_meta->alloc_track, "Allocated");
+		pr_err("\n");
+	}
 
-		print_track(&alloc_info->alloc_track, "Allocated");
+	free_track = kasan_get_free_track(cache, object, tag);
+	if (free_track) {
+		print_track(free_track, "Freed");
 		pr_err("\n");
-		free_track = kasan_get_free_track(cache, object, tag);
-		if (free_track) {
-			print_track(free_track, "Freed");
-			pr_err("\n");
-		}
+	}
 
 #ifdef CONFIG_KASAN_GENERIC
-		if (alloc_info->aux_stack[0]) {
-			pr_err("Last potentially related work creation:\n");
-			print_stack(alloc_info->aux_stack[0]);
-			pr_err("\n");
-		}
-		if (alloc_info->aux_stack[1]) {
-			pr_err("Second to last potentially related work creation:\n");
-			print_stack(alloc_info->aux_stack[1]);
-			pr_err("\n");
-		}
-#endif
+	if (!alloc_meta)
+		return;
+	if (alloc_meta->aux_stack[0]) {
+		pr_err("Last potentially related work creation:\n");
+		print_stack(alloc_meta->aux_stack[0]);
+		pr_err("\n");
 	}
+	if (alloc_meta->aux_stack[1]) {
+		pr_err("Second to last potentially related work creation:\n");
+		print_stack(alloc_meta->aux_stack[1]);
+		pr_err("\n");
+	}
+#endif
+}
 
+static void describe_object(struct kmem_cache *cache, void *object,
+				const void *addr, u8 tag)
+{
+	if (kasan_stack_collection_enabled())
+		describe_object_stacks(cache, object, addr, tag);
 	describe_object_addr(cache, object, addr);
 }
 
@@ -216,168 +223,6 @@ static inline bool init_task_stack_addr(const void *addr)
 			sizeof(init_thread_union.stack));
 }
 
-static bool __must_check tokenize_frame_descr(const char **frame_descr,
-					      char *token, size_t max_tok_len,
-					      unsigned long *value)
-{
-	const char *sep = strchr(*frame_descr, ' ');
-
-	if (sep == NULL)
-		sep = *frame_descr + strlen(*frame_descr);
-
-	if (token != NULL) {
-		const size_t tok_len = sep - *frame_descr;
-
-		if (tok_len + 1 > max_tok_len) {
-			pr_err("KASAN internal error: frame description too long: %s\n",
-			       *frame_descr);
-			return false;
-		}
-
-		/* Copy token (+ 1 byte for '\0'). */
-		strlcpy(token, *frame_descr, tok_len + 1);
-	}
-
-	/* Advance frame_descr past separator. */
-	*frame_descr = sep + 1;
-
-	if (value != NULL && kstrtoul(token, 10, value)) {
-		pr_err("KASAN internal error: not a valid number: %s\n", token);
-		return false;
-	}
-
-	return true;
-}
-
-static void print_decoded_frame_descr(const char *frame_descr)
-{
-	/*
-	 * We need to parse the following string:
-	 *    "n alloc_1 alloc_2 ... alloc_n"
-	 * where alloc_i looks like
-	 *    "offset size len name"
-	 * or "offset size len name:line".
-	 */
-
-	char token[64];
-	unsigned long num_objects;
-
-	if (!tokenize_frame_descr(&frame_descr, token, sizeof(token),
-				  &num_objects))
-		return;
-
-	pr_err("\n");
-	pr_err("this frame has %lu %s:\n", num_objects,
-	       num_objects == 1 ? "object" : "objects");
-
-	while (num_objects--) {
-		unsigned long offset;
-		unsigned long size;
-
-		/* access offset */
-		if (!tokenize_frame_descr(&frame_descr, token, sizeof(token),
-					  &offset))
-			return;
-		/* access size */
-		if (!tokenize_frame_descr(&frame_descr, token, sizeof(token),
-					  &size))
-			return;
-		/* name length (unused) */
-		if (!tokenize_frame_descr(&frame_descr, NULL, 0, NULL))
-			return;
-		/* object name */
-		if (!tokenize_frame_descr(&frame_descr, token, sizeof(token),
-					  NULL))
-			return;
-
-		/* Strip line number; without filename it's not very helpful. */
-		strreplace(token, ':', '\0');
-
-		/* Finally, print object information. */
-		pr_err(" [%lu, %lu) '%s'", offset, offset + size, token);
-	}
-}
-
-static bool __must_check get_address_stack_frame_info(const void *addr,
-						      unsigned long *offset,
-						      const char **frame_descr,
-						      const void **frame_pc)
-{
-	unsigned long aligned_addr;
-	unsigned long mem_ptr;
-	const u8 *shadow_bottom;
-	const u8 *shadow_ptr;
-	const unsigned long *frame;
-
-	BUILD_BUG_ON(IS_ENABLED(CONFIG_STACK_GROWSUP));
-
-	/*
-	 * NOTE: We currently only support printing frame information for
-	 * accesses to the task's own stack.
-	 */
-	if (!object_is_on_stack(addr))
-		return false;
-
-	aligned_addr = round_down((unsigned long)addr, sizeof(long));
-	mem_ptr = round_down(aligned_addr, KASAN_SHADOW_SCALE_SIZE);
-	shadow_ptr = kasan_mem_to_shadow((void *)aligned_addr);
-	shadow_bottom = kasan_mem_to_shadow(end_of_stack(current));
-
-	while (shadow_ptr >= shadow_bottom && *shadow_ptr != KASAN_STACK_LEFT) {
-		shadow_ptr--;
-		mem_ptr -= KASAN_SHADOW_SCALE_SIZE;
-	}
-
-	while (shadow_ptr >= shadow_bottom && *shadow_ptr == KASAN_STACK_LEFT) {
-		shadow_ptr--;
-		mem_ptr -= KASAN_SHADOW_SCALE_SIZE;
-	}
-
-	if (shadow_ptr < shadow_bottom)
-		return false;
-
-	frame = (const unsigned long *)(mem_ptr + KASAN_SHADOW_SCALE_SIZE);
-	if (frame[0] != KASAN_CURRENT_STACK_FRAME_MAGIC) {
-		pr_err("KASAN internal error: frame info validation failed; invalid marker: %lu\n",
-		       frame[0]);
-		return false;
-	}
-
-	*offset = (unsigned long)addr - (unsigned long)frame;
-	*frame_descr = (const char *)frame[1];
-	*frame_pc = (void *)frame[2];
-
-	return true;
-}
-
-static void print_address_stack_frame(const void *addr)
-{
-	unsigned long offset;
-	const char *frame_descr;
-	const void *frame_pc;
-
-	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
-		return;
-
-	if (!get_address_stack_frame_info(addr, &offset, &frame_descr,
-					  &frame_pc))
-		return;
-
-	/*
-	 * get_address_stack_frame_info only returns true if the given addr is
-	 * on the current task's stack.
-	 */
-	pr_err("\n");
-	pr_err("addr %px is located in stack of task %s/%d at offset %lu in frame:\n",
-	       addr, current->comm, task_pid_nr(current), offset);
-	pr_err(" %pS\n", frame_pc);
-
-	if (!frame_descr)
-		return;
-
-	print_decoded_frame_descr(frame_descr);
-}
-
 static void print_address_description(void *addr, u8 tag)
 {
 	struct page *page = kasan_addr_to_page(addr);
@@ -405,62 +250,68 @@ static void print_address_description(void *addr, u8 tag)
 	print_address_stack_frame(addr);
 }
 
-static bool row_is_guilty(const void *row, const void *guilty)
+static bool meta_row_is_guilty(const void *row, const void *addr)
 {
-	return (row <= guilty) && (guilty < row + SHADOW_BYTES_PER_ROW);
+	return (row <= addr) && (addr < row + META_MEM_BYTES_PER_ROW);
 }
 
-static int shadow_pointer_offset(const void *row, const void *shadow)
+static int meta_pointer_offset(const void *row, const void *addr)
 {
-	/* The length of ">ff00ff00ff00ff00: " is
-	 *    3 + (BITS_PER_LONG/8)*2 chars.
+	/*
+	 * Memory state around the buggy address:
+	 *  ff00ff00ff00ff00: 00 00 00 05 fe fe fe fe fe fe fe fe fe fe fe fe
+	 *  ...
+	 *
+	 * The length of ">ff00ff00ff00ff00: " is
+	 *    3 + (BITS_PER_LONG / 8) * 2 chars.
+	 * The length of each granule metadata is 2 bytes
+	 *    plus 1 byte for space.
 	 */
-	return 3 + (BITS_PER_LONG/8)*2 + (shadow - row)*2 +
-		(shadow - row) / SHADOW_BYTES_PER_BLOCK + 1;
+	return 3 + (BITS_PER_LONG / 8) * 2 +
+		(addr - row) / KASAN_GRANULE_SIZE * 3 + 1;
 }
 
-static void print_shadow_for_address(const void *addr)
+static void print_memory_metadata(const void *addr)
 {
 	int i;
-	const void *shadow = kasan_mem_to_shadow(addr);
-	const void *shadow_row;
+	void *row;
 
-	shadow_row = (void *)round_down((unsigned long)shadow,
-					SHADOW_BYTES_PER_ROW)
-		- SHADOW_ROWS_AROUND_ADDR * SHADOW_BYTES_PER_ROW;
+	row = (void *)round_down((unsigned long)addr, META_MEM_BYTES_PER_ROW)
+			- META_ROWS_AROUND_ADDR * META_MEM_BYTES_PER_ROW;
 
 	pr_err("Memory state around the buggy address:\n");
 
-	for (i = -SHADOW_ROWS_AROUND_ADDR; i <= SHADOW_ROWS_AROUND_ADDR; i++) {
-		const void *kaddr = kasan_shadow_to_mem(shadow_row);
-		char buffer[4 + (BITS_PER_LONG/8)*2];
-		char shadow_buf[SHADOW_BYTES_PER_ROW];
+	for (i = -META_ROWS_AROUND_ADDR; i <= META_ROWS_AROUND_ADDR; i++) {
+		char buffer[4 + (BITS_PER_LONG / 8) * 2];
+		char metadata[META_BYTES_PER_ROW];
 
 		snprintf(buffer, sizeof(buffer),
-			(i == 0) ? ">%px: " : " %px: ", kaddr);
+				(i == 0) ? ">%px: " : " %px: ", row);
+
 		/*
 		 * We should not pass a shadow pointer to generic
 		 * function, because generic functions may try to
 		 * access kasan mapping for the passed address.
 		 */
-		memcpy(shadow_buf, shadow_row, SHADOW_BYTES_PER_ROW);
+		metadata_fetch_row(&metadata[0], row);
+
 		print_hex_dump(KERN_ERR, buffer,
-			DUMP_PREFIX_NONE, SHADOW_BYTES_PER_ROW, 1,
-			shadow_buf, SHADOW_BYTES_PER_ROW, 0);
+			DUMP_PREFIX_NONE, META_BYTES_PER_ROW, 1,
+			metadata, META_BYTES_PER_ROW, 0);
 
-		if (row_is_guilty(shadow_row, shadow))
-			pr_err("%*c\n",
-				shadow_pointer_offset(shadow_row, shadow),
-				'^');
+		if (meta_row_is_guilty(row, addr))
+			pr_err("%*c\n", meta_pointer_offset(row, addr), '^');
 
-		shadow_row += SHADOW_BYTES_PER_ROW;
+		row += META_MEM_BYTES_PER_ROW;
 	}
 }
 
 static bool report_enabled(void)
 {
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	if (current->kasan_depth)
 		return false;
+#endif
 	if (test_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags))
 		return true;
 	return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags);
@@ -490,7 +341,7 @@ void kasan_report_invalid_free(void *object, unsigned long ip)
 	unsigned long flags;
 	u8 tag = get_tag(object);
 
-	object = reset_tag(object);
+	object = kasan_reset_tag(object);
 
 #if IS_ENABLED(CONFIG_KUNIT)
 	if (current->kunit_test)
@@ -503,7 +354,7 @@ void kasan_report_invalid_free(void *object, unsigned long ip)
 	pr_err("\n");
 	print_address_description(object, tag);
 	pr_err("\n");
-	print_shadow_for_address(object);
+	print_memory_metadata(object);
 	end_report(&flags);
 }
 
@@ -523,10 +374,10 @@ static void __kasan_report(unsigned long addr, size_t size, bool is_write,
 	disable_trace_on_warning();
 
 	tagged_addr = (void *)addr;
-	untagged_addr = reset_tag(tagged_addr);
+	untagged_addr = kasan_reset_tag(tagged_addr);
 
 	info.access_addr = tagged_addr;
-	if (addr_has_shadow(untagged_addr))
+	if (addr_has_metadata(untagged_addr))
 		info.first_bad_addr = find_first_bad_addr(tagged_addr, size);
 	else
 		info.first_bad_addr = untagged_addr;
@@ -537,14 +388,14 @@ static void __kasan_report(unsigned long addr, size_t size, bool is_write,
 	start_report(&flags);
 
 	print_error_description(&info);
-	if (addr_has_shadow(untagged_addr))
+	if (addr_has_metadata(untagged_addr))
 		print_tags(get_tag(tagged_addr), info.first_bad_addr);
 	pr_err("\n");
 
-	if (addr_has_shadow(untagged_addr)) {
+	if (addr_has_metadata(untagged_addr)) {
 		print_address_description(untagged_addr, get_tag(tagged_addr));
 		pr_err("\n");
-		print_shadow_for_address(info.first_bad_addr);
+		print_memory_metadata(info.first_bad_addr);
 	} else {
 		dump_stack();
 	}
@@ -604,6 +455,6 @@ void kasan_non_canonical_hook(unsigned long addr)
 	else
 		bug_type = "maybe wild-memory-access";
 	pr_alert("KASAN: %s in range [0x%016lx-0x%016lx]\n", bug_type,
-		 orig_addr, orig_addr + KASAN_SHADOW_MASK);
+		 orig_addr, orig_addr + KASAN_GRANULE_SIZE - 1);
 }
 #endif
diff --git a/mm/kasan/report_generic.c b/mm/kasan/report_generic.c
new file mode 100644
index 000000000000..8a9c889872da
--- /dev/null
+++ b/mm/kasan/report_generic.c
@@ -0,0 +1,327 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains generic KASAN specific error reporting code.
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ *
+ * Some code borrowed from https://github.com/xairy/kasan-prototype by
+ *        Andrey Konovalov <andreyknvl@gmail.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/ftrace.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/printk.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/slab.h>
+#include <linux/stackdepot.h>
+#include <linux/stacktrace.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/kasan.h>
+#include <linux/module.h>
+
+#include <asm/sections.h>
+
+#include "kasan.h"
+#include "../slab.h"
+
+void *find_first_bad_addr(void *addr, size_t size)
+{
+	void *p = addr;
+
+	while (p < addr + size && !(*(u8 *)kasan_mem_to_shadow(p)))
+		p += KASAN_GRANULE_SIZE;
+	return p;
+}
+
+static const char *get_shadow_bug_type(struct kasan_access_info *info)
+{
+	const char *bug_type = "unknown-crash";
+	u8 *shadow_addr;
+
+	shadow_addr = (u8 *)kasan_mem_to_shadow(info->first_bad_addr);
+
+	/*
+	 * If shadow byte value is in [0, KASAN_GRANULE_SIZE) we can look
+	 * at the next shadow byte to determine the type of the bad access.
+	 */
+	if (*shadow_addr > 0 && *shadow_addr <= KASAN_GRANULE_SIZE - 1)
+		shadow_addr++;
+
+	switch (*shadow_addr) {
+	case 0 ... KASAN_GRANULE_SIZE - 1:
+		/*
+		 * In theory it's still possible to see these shadow values
+		 * due to a data race in the kernel code.
+		 */
+		bug_type = "out-of-bounds";
+		break;
+	case KASAN_PAGE_REDZONE:
+	case KASAN_KMALLOC_REDZONE:
+		bug_type = "slab-out-of-bounds";
+		break;
+	case KASAN_GLOBAL_REDZONE:
+		bug_type = "global-out-of-bounds";
+		break;
+	case KASAN_STACK_LEFT:
+	case KASAN_STACK_MID:
+	case KASAN_STACK_RIGHT:
+	case KASAN_STACK_PARTIAL:
+		bug_type = "stack-out-of-bounds";
+		break;
+	case KASAN_FREE_PAGE:
+	case KASAN_KMALLOC_FREE:
+	case KASAN_KMALLOC_FREETRACK:
+		bug_type = "use-after-free";
+		break;
+	case KASAN_ALLOCA_LEFT:
+	case KASAN_ALLOCA_RIGHT:
+		bug_type = "alloca-out-of-bounds";
+		break;
+	case KASAN_VMALLOC_INVALID:
+		bug_type = "vmalloc-out-of-bounds";
+		break;
+	}
+
+	return bug_type;
+}
+
+static const char *get_wild_bug_type(struct kasan_access_info *info)
+{
+	const char *bug_type = "unknown-crash";
+
+	if ((unsigned long)info->access_addr < PAGE_SIZE)
+		bug_type = "null-ptr-deref";
+	else if ((unsigned long)info->access_addr < TASK_SIZE)
+		bug_type = "user-memory-access";
+	else
+		bug_type = "wild-memory-access";
+
+	return bug_type;
+}
+
+const char *get_bug_type(struct kasan_access_info *info)
+{
+	/*
+	 * If access_size is a negative number, then it has reason to be
+	 * defined as out-of-bounds bug type.
+	 *
+	 * Casting negative numbers to size_t would indeed turn up as
+	 * a large size_t and its value will be larger than ULONG_MAX/2,
+	 * so that this can qualify as out-of-bounds.
+	 */
+	if (info->access_addr + info->access_size < info->access_addr)
+		return "out-of-bounds";
+
+	if (addr_has_metadata(info->access_addr))
+		return get_shadow_bug_type(info);
+	return get_wild_bug_type(info);
+}
+
+void metadata_fetch_row(char *buffer, void *row)
+{
+	memcpy(buffer, kasan_mem_to_shadow(row), META_BYTES_PER_ROW);
+}
+
+#if CONFIG_KASAN_STACK
+static bool __must_check tokenize_frame_descr(const char **frame_descr,
+					      char *token, size_t max_tok_len,
+					      unsigned long *value)
+{
+	const char *sep = strchr(*frame_descr, ' ');
+
+	if (sep == NULL)
+		sep = *frame_descr + strlen(*frame_descr);
+
+	if (token != NULL) {
+		const size_t tok_len = sep - *frame_descr;
+
+		if (tok_len + 1 > max_tok_len) {
+			pr_err("KASAN internal error: frame description too long: %s\n",
+			       *frame_descr);
+			return false;
+		}
+
+		/* Copy token (+ 1 byte for '\0'). */
+		strlcpy(token, *frame_descr, tok_len + 1);
+	}
+
+	/* Advance frame_descr past separator. */
+	*frame_descr = sep + 1;
+
+	if (value != NULL && kstrtoul(token, 10, value)) {
+		pr_err("KASAN internal error: not a valid number: %s\n", token);
+		return false;
+	}
+
+	return true;
+}
+
+static void print_decoded_frame_descr(const char *frame_descr)
+{
+	/*
+	 * We need to parse the following string:
+	 *    "n alloc_1 alloc_2 ... alloc_n"
+	 * where alloc_i looks like
+	 *    "offset size len name"
+	 * or "offset size len name:line".
+	 */
+
+	char token[64];
+	unsigned long num_objects;
+
+	if (!tokenize_frame_descr(&frame_descr, token, sizeof(token),
+				  &num_objects))
+		return;
+
+	pr_err("\n");
+	pr_err("this frame has %lu %s:\n", num_objects,
+	       num_objects == 1 ? "object" : "objects");
+
+	while (num_objects--) {
+		unsigned long offset;
+		unsigned long size;
+
+		/* access offset */
+		if (!tokenize_frame_descr(&frame_descr, token, sizeof(token),
+					  &offset))
+			return;
+		/* access size */
+		if (!tokenize_frame_descr(&frame_descr, token, sizeof(token),
+					  &size))
+			return;
+		/* name length (unused) */
+		if (!tokenize_frame_descr(&frame_descr, NULL, 0, NULL))
+			return;
+		/* object name */
+		if (!tokenize_frame_descr(&frame_descr, token, sizeof(token),
+					  NULL))
+			return;
+
+		/* Strip line number; without filename it's not very helpful. */
+		strreplace(token, ':', '\0');
+
+		/* Finally, print object information. */
+		pr_err(" [%lu, %lu) '%s'", offset, offset + size, token);
+	}
+}
+
+static bool __must_check get_address_stack_frame_info(const void *addr,
+						      unsigned long *offset,
+						      const char **frame_descr,
+						      const void **frame_pc)
+{
+	unsigned long aligned_addr;
+	unsigned long mem_ptr;
+	const u8 *shadow_bottom;
+	const u8 *shadow_ptr;
+	const unsigned long *frame;
+
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_STACK_GROWSUP));
+
+	/*
+	 * NOTE: We currently only support printing frame information for
+	 * accesses to the task's own stack.
+	 */
+	if (!object_is_on_stack(addr))
+		return false;
+
+	aligned_addr = round_down((unsigned long)addr, sizeof(long));
+	mem_ptr = round_down(aligned_addr, KASAN_GRANULE_SIZE);
+	shadow_ptr = kasan_mem_to_shadow((void *)aligned_addr);
+	shadow_bottom = kasan_mem_to_shadow(end_of_stack(current));
+
+	while (shadow_ptr >= shadow_bottom && *shadow_ptr != KASAN_STACK_LEFT) {
+		shadow_ptr--;
+		mem_ptr -= KASAN_GRANULE_SIZE;
+	}
+
+	while (shadow_ptr >= shadow_bottom && *shadow_ptr == KASAN_STACK_LEFT) {
+		shadow_ptr--;
+		mem_ptr -= KASAN_GRANULE_SIZE;
+	}
+
+	if (shadow_ptr < shadow_bottom)
+		return false;
+
+	frame = (const unsigned long *)(mem_ptr + KASAN_GRANULE_SIZE);
+	if (frame[0] != KASAN_CURRENT_STACK_FRAME_MAGIC) {
+		pr_err("KASAN internal error: frame info validation failed; invalid marker: %lu\n",
+		       frame[0]);
+		return false;
+	}
+
+	*offset = (unsigned long)addr - (unsigned long)frame;
+	*frame_descr = (const char *)frame[1];
+	*frame_pc = (void *)frame[2];
+
+	return true;
+}
+
+void print_address_stack_frame(const void *addr)
+{
+	unsigned long offset;
+	const char *frame_descr;
+	const void *frame_pc;
+
+	if (!get_address_stack_frame_info(addr, &offset, &frame_descr,
+					  &frame_pc))
+		return;
+
+	/*
+	 * get_address_stack_frame_info only returns true if the given addr is
+	 * on the current task's stack.
+	 */
+	pr_err("\n");
+	pr_err("addr %px is located in stack of task %s/%d at offset %lu in frame:\n",
+	       addr, current->comm, task_pid_nr(current), offset);
+	pr_err(" %pS\n", frame_pc);
+
+	if (!frame_descr)
+		return;
+
+	print_decoded_frame_descr(frame_descr);
+}
+#endif /* CONFIG_KASAN_STACK */
+
+#define DEFINE_ASAN_REPORT_LOAD(size)                     \
+void __asan_report_load##size##_noabort(unsigned long addr) \
+{                                                         \
+	kasan_report(addr, size, false, _RET_IP_);	  \
+}                                                         \
+EXPORT_SYMBOL(__asan_report_load##size##_noabort)
+
+#define DEFINE_ASAN_REPORT_STORE(size)                     \
+void __asan_report_store##size##_noabort(unsigned long addr) \
+{                                                          \
+	kasan_report(addr, size, true, _RET_IP_);	   \
+}                                                          \
+EXPORT_SYMBOL(__asan_report_store##size##_noabort)
+
+DEFINE_ASAN_REPORT_LOAD(1);
+DEFINE_ASAN_REPORT_LOAD(2);
+DEFINE_ASAN_REPORT_LOAD(4);
+DEFINE_ASAN_REPORT_LOAD(8);
+DEFINE_ASAN_REPORT_LOAD(16);
+DEFINE_ASAN_REPORT_STORE(1);
+DEFINE_ASAN_REPORT_STORE(2);
+DEFINE_ASAN_REPORT_STORE(4);
+DEFINE_ASAN_REPORT_STORE(8);
+DEFINE_ASAN_REPORT_STORE(16);
+
+void __asan_report_load_n_noabort(unsigned long addr, size_t size)
+{
+	kasan_report(addr, size, false, _RET_IP_);
+}
+EXPORT_SYMBOL(__asan_report_load_n_noabort);
+
+void __asan_report_store_n_noabort(unsigned long addr, size_t size)
+{
+	kasan_report(addr, size, true, _RET_IP_);
+}
+EXPORT_SYMBOL(__asan_report_store_n_noabort);
diff --git a/mm/kasan/report_hw_tags.c b/mm/kasan/report_hw_tags.c
new file mode 100644
index 000000000000..57114f0e14d1
--- /dev/null
+++ b/mm/kasan/report_hw_tags.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains hardware tag-based KASAN specific error reporting code.
+ *
+ * Copyright (c) 2020 Google, Inc.
+ * Author: Andrey Konovalov <andreyknvl@google.com>
+ */
+
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memory.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "kasan.h"
+
+const char *get_bug_type(struct kasan_access_info *info)
+{
+	return "invalid-access";
+}
+
+void *find_first_bad_addr(void *addr, size_t size)
+{
+	return kasan_reset_tag(addr);
+}
+
+void metadata_fetch_row(char *buffer, void *row)
+{
+	int i;
+
+	for (i = 0; i < META_BYTES_PER_ROW; i++)
+		buffer[i] = hw_get_mem_tag(row + i * KASAN_GRANULE_SIZE);
+}
+
+void print_tags(u8 addr_tag, const void *addr)
+{
+	u8 memory_tag = hw_get_mem_tag((void *)addr);
+
+	pr_err("Pointer tag: [%02x], memory tag: [%02x]\n",
+		addr_tag, memory_tag);
+}
diff --git a/mm/kasan/tags_report.c b/mm/kasan/report_sw_tags.c
index bee43717d6f0..1b026793ad57 100644
--- a/mm/kasan/tags_report.c
+++ b/mm/kasan/report_sw_tags.c
@@ -1,17 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * This file contains tag-based KASAN specific error reporting code.
+ * This file contains software tag-based KASAN specific error reporting code.
  *
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
  * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
  *
  * Some code borrowed from https://github.com/xairy/kasan-prototype by
  *        Andrey Konovalov <andreyknvl@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #include <linux/bitops.h>
@@ -46,16 +41,19 @@ const char *get_bug_type(struct kasan_access_info *info)
 	int i;
 
 	tag = get_tag(info->access_addr);
-	addr = reset_tag(info->access_addr);
+	addr = kasan_reset_tag(info->access_addr);
 	page = kasan_addr_to_page(addr);
 	if (page && PageSlab(page)) {
 		cache = page->slab_cache;
 		object = nearest_obj(cache, page, (void *)addr);
-		alloc_meta = get_alloc_info(cache, object);
+		alloc_meta = kasan_get_alloc_meta(cache, object);
 
-		for (i = 0; i < KASAN_NR_FREE_STACKS; i++)
-			if (alloc_meta->free_pointer_tag[i] == tag)
-				return "use-after-free";
+		if (alloc_meta) {
+			for (i = 0; i < KASAN_NR_FREE_STACKS; i++) {
+				if (alloc_meta->free_pointer_tag[i] == tag)
+					return "use-after-free";
+			}
+		}
 		return "out-of-bounds";
 	}
 
@@ -77,14 +75,19 @@ const char *get_bug_type(struct kasan_access_info *info)
 void *find_first_bad_addr(void *addr, size_t size)
 {
 	u8 tag = get_tag(addr);
-	void *p = reset_tag(addr);
+	void *p = kasan_reset_tag(addr);
 	void *end = p + size;
 
 	while (p < end && tag == *(u8 *)kasan_mem_to_shadow(p))
-		p += KASAN_SHADOW_SCALE_SIZE;
+		p += KASAN_GRANULE_SIZE;
 	return p;
 }
 
+void metadata_fetch_row(char *buffer, void *row)
+{
+	memcpy(buffer, kasan_mem_to_shadow(row), META_BYTES_PER_ROW);
+}
+
 void print_tags(u8 addr_tag, const void *addr)
 {
 	u8 *shadow = (u8 *)kasan_mem_to_shadow(addr);
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
new file mode 100644
index 000000000000..7c2c08c55f32
--- /dev/null
+++ b/mm/kasan/shadow.c
@@ -0,0 +1,504 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains KASAN runtime code that manages shadow memory for
+ * generic and software tag-based KASAN modes.
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
+ *
+ * Some code borrowed from https://github.com/xairy/kasan-prototype by
+ *        Andrey Konovalov <andreyknvl@gmail.com>
+ */
+
+#include <linux/init.h>
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/kmemleak.h>
+#include <linux/memory.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
+#include "kasan.h"
+
+bool __kasan_check_read(const volatile void *p, unsigned int size)
+{
+	return check_memory_region((unsigned long)p, size, false, _RET_IP_);
+}
+EXPORT_SYMBOL(__kasan_check_read);
+
+bool __kasan_check_write(const volatile void *p, unsigned int size)
+{
+	return check_memory_region((unsigned long)p, size, true, _RET_IP_);
+}
+EXPORT_SYMBOL(__kasan_check_write);
+
+#undef memset
+void *memset(void *addr, int c, size_t len)
+{
+	if (!check_memory_region((unsigned long)addr, len, true, _RET_IP_))
+		return NULL;
+
+	return __memset(addr, c, len);
+}
+
+#ifdef __HAVE_ARCH_MEMMOVE
+#undef memmove
+void *memmove(void *dest, const void *src, size_t len)
+{
+	if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) ||
+	    !check_memory_region((unsigned long)dest, len, true, _RET_IP_))
+		return NULL;
+
+	return __memmove(dest, src, len);
+}
+#endif
+
+#undef memcpy
+void *memcpy(void *dest, const void *src, size_t len)
+{
+	if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) ||
+	    !check_memory_region((unsigned long)dest, len, true, _RET_IP_))
+		return NULL;
+
+	return __memcpy(dest, src, len);
+}
+
+/*
+ * Poisons the shadow memory for 'size' bytes starting from 'addr'.
+ * Memory addresses should be aligned to KASAN_GRANULE_SIZE.
+ */
+void poison_range(const void *address, size_t size, u8 value)
+{
+	void *shadow_start, *shadow_end;
+
+	/*
+	 * Perform shadow offset calculation based on untagged address, as
+	 * some of the callers (e.g. kasan_poison_object_data) pass tagged
+	 * addresses to this function.
+	 */
+	address = kasan_reset_tag(address);
+	size = round_up(size, KASAN_GRANULE_SIZE);
+
+	shadow_start = kasan_mem_to_shadow(address);
+	shadow_end = kasan_mem_to_shadow(address + size);
+
+	__memset(shadow_start, value, shadow_end - shadow_start);
+}
+
+void unpoison_range(const void *address, size_t size)
+{
+	u8 tag = get_tag(address);
+
+	/*
+	 * Perform shadow offset calculation based on untagged address, as
+	 * some of the callers (e.g. kasan_unpoison_object_data) pass tagged
+	 * addresses to this function.
+	 */
+	address = kasan_reset_tag(address);
+
+	poison_range(address, size, tag);
+
+	if (size & KASAN_GRANULE_MASK) {
+		u8 *shadow = (u8 *)kasan_mem_to_shadow(address + size);
+
+		if (IS_ENABLED(CONFIG_KASAN_SW_TAGS))
+			*shadow = tag;
+		else /* CONFIG_KASAN_GENERIC */
+			*shadow = size & KASAN_GRANULE_MASK;
+	}
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static bool shadow_mapped(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	if (pgd_none(*pgd))
+		return false;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return false;
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud))
+		return false;
+
+	/*
+	 * We can't use pud_large() or pud_huge(), the first one is
+	 * arch-specific, the last one depends on HUGETLB_PAGE.  So let's abuse
+	 * pud_bad(), if pud is bad then it's bad because it's huge.
+	 */
+	if (pud_bad(*pud))
+		return true;
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return false;
+
+	if (pmd_bad(*pmd))
+		return true;
+	pte = pte_offset_kernel(pmd, addr);
+	return !pte_none(*pte);
+}
+
+static int __meminit kasan_mem_notifier(struct notifier_block *nb,
+			unsigned long action, void *data)
+{
+	struct memory_notify *mem_data = data;
+	unsigned long nr_shadow_pages, start_kaddr, shadow_start;
+	unsigned long shadow_end, shadow_size;
+
+	nr_shadow_pages = mem_data->nr_pages >> KASAN_SHADOW_SCALE_SHIFT;
+	start_kaddr = (unsigned long)pfn_to_kaddr(mem_data->start_pfn);
+	shadow_start = (unsigned long)kasan_mem_to_shadow((void *)start_kaddr);
+	shadow_size = nr_shadow_pages << PAGE_SHIFT;
+	shadow_end = shadow_start + shadow_size;
+
+	if (WARN_ON(mem_data->nr_pages % KASAN_GRANULE_SIZE) ||
+		WARN_ON(start_kaddr % KASAN_MEMORY_PER_SHADOW_PAGE))
+		return NOTIFY_BAD;
+
+	switch (action) {
+	case MEM_GOING_ONLINE: {
+		void *ret;
+
+		/*
+		 * If shadow is mapped already than it must have been mapped
+		 * during the boot. This could happen if we onlining previously
+		 * offlined memory.
+		 */
+		if (shadow_mapped(shadow_start))
+			return NOTIFY_OK;
+
+		ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start,
+					shadow_end, GFP_KERNEL,
+					PAGE_KERNEL, VM_NO_GUARD,
+					pfn_to_nid(mem_data->start_pfn),
+					__builtin_return_address(0));
+		if (!ret)
+			return NOTIFY_BAD;
+
+		kmemleak_ignore(ret);
+		return NOTIFY_OK;
+	}
+	case MEM_CANCEL_ONLINE:
+	case MEM_OFFLINE: {
+		struct vm_struct *vm;
+
+		/*
+		 * shadow_start was either mapped during boot by kasan_init()
+		 * or during memory online by __vmalloc_node_range().
+		 * In the latter case we can use vfree() to free shadow.
+		 * Non-NULL result of the find_vm_area() will tell us if
+		 * that was the second case.
+		 *
+		 * Currently it's not possible to free shadow mapped
+		 * during boot by kasan_init(). It's because the code
+		 * to do that hasn't been written yet. So we'll just
+		 * leak the memory.
+		 */
+		vm = find_vm_area((void *)shadow_start);
+		if (vm)
+			vfree((void *)shadow_start);
+	}
+	}
+
+	return NOTIFY_OK;
+}
+
+static int __init kasan_memhotplug_init(void)
+{
+	hotplug_memory_notifier(kasan_mem_notifier, 0);
+
+	return 0;
+}
+
+core_initcall(kasan_memhotplug_init);
+#endif
+
+#ifdef CONFIG_KASAN_VMALLOC
+
+static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
+				      void *unused)
+{
+	unsigned long page;
+	pte_t pte;
+
+	if (likely(!pte_none(*ptep)))
+		return 0;
+
+	page = __get_free_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE);
+	pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL);
+
+	spin_lock(&init_mm.page_table_lock);
+	if (likely(pte_none(*ptep))) {
+		set_pte_at(&init_mm, addr, ptep, pte);
+		page = 0;
+	}
+	spin_unlock(&init_mm.page_table_lock);
+	if (page)
+		free_page(page);
+	return 0;
+}
+
+int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
+{
+	unsigned long shadow_start, shadow_end;
+	int ret;
+
+	if (!is_vmalloc_or_module_addr((void *)addr))
+		return 0;
+
+	shadow_start = (unsigned long)kasan_mem_to_shadow((void *)addr);
+	shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE);
+	shadow_end = (unsigned long)kasan_mem_to_shadow((void *)addr + size);
+	shadow_end = ALIGN(shadow_end, PAGE_SIZE);
+
+	ret = apply_to_page_range(&init_mm, shadow_start,
+				  shadow_end - shadow_start,
+				  kasan_populate_vmalloc_pte, NULL);
+	if (ret)
+		return ret;
+
+	flush_cache_vmap(shadow_start, shadow_end);
+
+	/*
+	 * We need to be careful about inter-cpu effects here. Consider:
+	 *
+	 *   CPU#0				  CPU#1
+	 * WRITE_ONCE(p, vmalloc(100));		while (x = READ_ONCE(p)) ;
+	 *					p[99] = 1;
+	 *
+	 * With compiler instrumentation, that ends up looking like this:
+	 *
+	 *   CPU#0				  CPU#1
+	 * // vmalloc() allocates memory
+	 * // let a = area->addr
+	 * // we reach kasan_populate_vmalloc
+	 * // and call unpoison_range:
+	 * STORE shadow(a), unpoison_val
+	 * ...
+	 * STORE shadow(a+99), unpoison_val	x = LOAD p
+	 * // rest of vmalloc process		<data dependency>
+	 * STORE p, a				LOAD shadow(x+99)
+	 *
+	 * If there is no barrier between the end of unpoisioning the shadow
+	 * and the store of the result to p, the stores could be committed
+	 * in a different order by CPU#0, and CPU#1 could erroneously observe
+	 * poison in the shadow.
+	 *
+	 * We need some sort of barrier between the stores.
+	 *
+	 * In the vmalloc() case, this is provided by a smp_wmb() in
+	 * clear_vm_uninitialized_flag(). In the per-cpu allocator and in
+	 * get_vm_area() and friends, the caller gets shadow allocated but
+	 * doesn't have any pages mapped into the virtual address space that
+	 * has been reserved. Mapping those pages in will involve taking and
+	 * releasing a page-table lock, which will provide the barrier.
+	 */
+
+	return 0;
+}
+
+/*
+ * Poison the shadow for a vmalloc region. Called as part of the
+ * freeing process at the time the region is freed.
+ */
+void kasan_poison_vmalloc(const void *start, unsigned long size)
+{
+	if (!is_vmalloc_or_module_addr(start))
+		return;
+
+	size = round_up(size, KASAN_GRANULE_SIZE);
+	poison_range(start, size, KASAN_VMALLOC_INVALID);
+}
+
+void kasan_unpoison_vmalloc(const void *start, unsigned long size)
+{
+	if (!is_vmalloc_or_module_addr(start))
+		return;
+
+	unpoison_range(start, size);
+}
+
+static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
+					void *unused)
+{
+	unsigned long page;
+
+	page = (unsigned long)__va(pte_pfn(*ptep) << PAGE_SHIFT);
+
+	spin_lock(&init_mm.page_table_lock);
+
+	if (likely(!pte_none(*ptep))) {
+		pte_clear(&init_mm, addr, ptep);
+		free_page(page);
+	}
+	spin_unlock(&init_mm.page_table_lock);
+
+	return 0;
+}
+
+/*
+ * Release the backing for the vmalloc region [start, end), which
+ * lies within the free region [free_region_start, free_region_end).
+ *
+ * This can be run lazily, long after the region was freed. It runs
+ * under vmap_area_lock, so it's not safe to interact with the vmalloc/vmap
+ * infrastructure.
+ *
+ * How does this work?
+ * -------------------
+ *
+ * We have a region that is page aligned, labelled as A.
+ * That might not map onto the shadow in a way that is page-aligned:
+ *
+ *                    start                     end
+ *                    v                         v
+ * |????????|????????|AAAAAAAA|AA....AA|AAAAAAAA|????????| < vmalloc
+ *  -------- -------- --------          -------- --------
+ *      |        |       |                 |        |
+ *      |        |       |         /-------/        |
+ *      \-------\|/------/         |/---------------/
+ *              |||                ||
+ *             |??AAAAAA|AAAAAAAA|AA??????|                < shadow
+ *                 (1)      (2)      (3)
+ *
+ * First we align the start upwards and the end downwards, so that the
+ * shadow of the region aligns with shadow page boundaries. In the
+ * example, this gives us the shadow page (2). This is the shadow entirely
+ * covered by this allocation.
+ *
+ * Then we have the tricky bits. We want to know if we can free the
+ * partially covered shadow pages - (1) and (3) in the example. For this,
+ * we are given the start and end of the free region that contains this
+ * allocation. Extending our previous example, we could have:
+ *
+ *  free_region_start                                    free_region_end
+ *  |                 start                     end      |
+ *  v                 v                         v        v
+ * |FFFFFFFF|FFFFFFFF|AAAAAAAA|AA....AA|AAAAAAAA|FFFFFFFF| < vmalloc
+ *  -------- -------- --------          -------- --------
+ *      |        |       |                 |        |
+ *      |        |       |         /-------/        |
+ *      \-------\|/------/         |/---------------/
+ *              |||                ||
+ *             |FFAAAAAA|AAAAAAAA|AAF?????|                < shadow
+ *                 (1)      (2)      (3)
+ *
+ * Once again, we align the start of the free region up, and the end of
+ * the free region down so that the shadow is page aligned. So we can free
+ * page (1) - we know no allocation currently uses anything in that page,
+ * because all of it is in the vmalloc free region. But we cannot free
+ * page (3), because we can't be sure that the rest of it is unused.
+ *
+ * We only consider pages that contain part of the original region for
+ * freeing: we don't try to free other pages from the free region or we'd
+ * end up trying to free huge chunks of virtual address space.
+ *
+ * Concurrency
+ * -----------
+ *
+ * How do we know that we're not freeing a page that is simultaneously
+ * being used for a fresh allocation in kasan_populate_vmalloc(_pte)?
+ *
+ * We _can_ have kasan_release_vmalloc and kasan_populate_vmalloc running
+ * at the same time. While we run under free_vmap_area_lock, the population
+ * code does not.
+ *
+ * free_vmap_area_lock instead operates to ensure that the larger range
+ * [free_region_start, free_region_end) is safe: because __alloc_vmap_area and
+ * the per-cpu region-finding algorithm both run under free_vmap_area_lock,
+ * no space identified as free will become used while we are running. This
+ * means that so long as we are careful with alignment and only free shadow
+ * pages entirely covered by the free region, we will not run in to any
+ * trouble - any simultaneous allocations will be for disjoint regions.
+ */
+void kasan_release_vmalloc(unsigned long start, unsigned long end,
+			   unsigned long free_region_start,
+			   unsigned long free_region_end)
+{
+	void *shadow_start, *shadow_end;
+	unsigned long region_start, region_end;
+	unsigned long size;
+
+	region_start = ALIGN(start, KASAN_MEMORY_PER_SHADOW_PAGE);
+	region_end = ALIGN_DOWN(end, KASAN_MEMORY_PER_SHADOW_PAGE);
+
+	free_region_start = ALIGN(free_region_start, KASAN_MEMORY_PER_SHADOW_PAGE);
+
+	if (start != region_start &&
+	    free_region_start < region_start)
+		region_start -= KASAN_MEMORY_PER_SHADOW_PAGE;
+
+	free_region_end = ALIGN_DOWN(free_region_end, KASAN_MEMORY_PER_SHADOW_PAGE);
+
+	if (end != region_end &&
+	    free_region_end > region_end)
+		region_end += KASAN_MEMORY_PER_SHADOW_PAGE;
+
+	shadow_start = kasan_mem_to_shadow((void *)region_start);
+	shadow_end = kasan_mem_to_shadow((void *)region_end);
+
+	if (shadow_end > shadow_start) {
+		size = shadow_end - shadow_start;
+		apply_to_existing_page_range(&init_mm,
+					     (unsigned long)shadow_start,
+					     size, kasan_depopulate_vmalloc_pte,
+					     NULL);
+		flush_tlb_kernel_range((unsigned long)shadow_start,
+				       (unsigned long)shadow_end);
+	}
+}
+
+#else /* CONFIG_KASAN_VMALLOC */
+
+int kasan_module_alloc(void *addr, size_t size)
+{
+	void *ret;
+	size_t scaled_size;
+	size_t shadow_size;
+	unsigned long shadow_start;
+
+	shadow_start = (unsigned long)kasan_mem_to_shadow(addr);
+	scaled_size = (size + KASAN_GRANULE_SIZE - 1) >>
+				KASAN_SHADOW_SCALE_SHIFT;
+	shadow_size = round_up(scaled_size, PAGE_SIZE);
+
+	if (WARN_ON(!PAGE_ALIGNED(shadow_start)))
+		return -EINVAL;
+
+	ret = __vmalloc_node_range(shadow_size, 1, shadow_start,
+			shadow_start + shadow_size,
+			GFP_KERNEL,
+			PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE,
+			__builtin_return_address(0));
+
+	if (ret) {
+		__memset(ret, KASAN_SHADOW_INIT, shadow_size);
+		find_vm_area(addr)->flags |= VM_KASAN;
+		kmemleak_ignore(ret);
+		return 0;
+	}
+
+	return -ENOMEM;
+}
+
+void kasan_free_shadow(const struct vm_struct *vm)
+{
+	if (vm->flags & VM_KASAN)
+		vfree(kasan_mem_to_shadow(vm->addr));
+}
+
+#endif
diff --git a/mm/kasan/tags.c b/mm/kasan/sw_tags.c
index e02a36a51f42..5dcd830805b2 100644
--- a/mm/kasan/tags.c
+++ b/mm/kasan/sw_tags.c
@@ -1,17 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * This file contains core tag-based KASAN code.
+ * This file contains core software tag-based KASAN code.
  *
  * Copyright (c) 2018 Google, Inc.
  * Author: Andrey Konovalov <andreyknvl@google.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#define pr_fmt(fmt) "kasan: " fmt
 
 #include <linux/export.h>
 #include <linux/interrupt.h>
@@ -40,12 +35,14 @@
 
 static DEFINE_PER_CPU(u32, prng_state);
 
-void kasan_init_tags(void)
+void __init kasan_init_sw_tags(void)
 {
 	int cpu;
 
 	for_each_possible_cpu(cpu)
 		per_cpu(prng_state, cpu) = (u32)get_cycles();
+
+	pr_info("KernelAddressSanitizer initialized\n");
 }
 
 /*
@@ -70,11 +67,6 @@ u8 random_tag(void)
 	return (u8)(state % (KASAN_TAG_MAX + 1));
 }
 
-void *kasan_reset_tag(const void *addr)
-{
-	return reset_tag(addr);
-}
-
 bool check_memory_region(unsigned long addr, size_t size, bool write,
 				unsigned long ret_ip)
 {
@@ -110,7 +102,7 @@ bool check_memory_region(unsigned long addr, size_t size, bool write,
 	if (tag == KASAN_TAG_KERNEL)
 		return true;
 
-	untagged_addr = reset_tag((const void *)addr);
+	untagged_addr = kasan_reset_tag((const void *)addr);
 	if (unlikely(untagged_addr <
 			kasan_shadow_to_mem((void *)KASAN_SHADOW_START))) {
 		return !kasan_report(addr, size, write, ret_ip);
@@ -126,6 +118,15 @@ bool check_memory_region(unsigned long addr, size_t size, bool write,
 	return true;
 }
 
+bool check_invalid_free(void *addr)
+{
+	u8 tag = get_tag(addr);
+	u8 shadow_byte = READ_ONCE(*(u8 *)kasan_mem_to_shadow(kasan_reset_tag(addr)));
+
+	return (shadow_byte == KASAN_TAG_INVALID) ||
+		(tag != KASAN_TAG_KERNEL && tag != shadow_byte);
+}
+
 #define DEFINE_HWASAN_LOAD_STORE(size)					\
 	void __hwasan_load##size##_noabort(unsigned long addr)		\
 	{								\
@@ -158,7 +159,7 @@ EXPORT_SYMBOL(__hwasan_storeN_noabort);
 
 void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size)
 {
-	kasan_poison_shadow((void *)addr, size, tag);
+	poison_range((void *)addr, size, tag);
 }
 EXPORT_SYMBOL(__hwasan_tag_memory);
 
@@ -168,7 +169,9 @@ void kasan_set_free_info(struct kmem_cache *cache,
 	struct kasan_alloc_meta *alloc_meta;
 	u8 idx = 0;
 
-	alloc_meta = get_alloc_info(cache, object);
+	alloc_meta = kasan_get_alloc_meta(cache, object);
+	if (!alloc_meta)
+		return;
 
 #ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY
 	idx = alloc_meta->free_track_idx;
@@ -185,7 +188,9 @@ struct kasan_track *kasan_get_free_track(struct kmem_cache *cache,
 	struct kasan_alloc_meta *alloc_meta;
 	int i = 0;
 
-	alloc_meta = get_alloc_info(cache, object);
+	alloc_meta = kasan_get_alloc_meta(cache, object);
+	if (!alloc_meta)
+		return NULL;
 
 #ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY
 	for (i = 0; i < KASAN_NR_FREE_STACKS; i++) {
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5a38e9eade94..04d9f154a130 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1940,7 +1940,7 @@ retry:
 			goto retry;
 		}
 	} else if (ret == -EIO) {
-		pr_info("%s: %#lx: unknown page type: %lx (%pGP)\n",
+		pr_info("%s: %#lx: unknown page type: %lx (%pGp)\n",
 			 __func__, pfn, page->flags, &page->flags);
 	}
 
diff --git a/mm/memory.c b/mm/memory.c
index 7d608765932b..feff48e1465a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2892,11 +2892,13 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		entry = mk_pte(new_page, vma->vm_page_prot);
 		entry = pte_sw_mkyoung(entry);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+
 		/*
 		 * Clear the pte entry and flush it first, before updating the
-		 * pte with the new entry. This will avoid a race condition
-		 * seen in the presence of one thread doing SMC and another
-		 * thread doing COW.
+		 * pte with the new entry, to keep TLBs on different CPUs in
+		 * sync. This code used to set the new PTE then flush TLBs, but
+		 * that left a window where the new PTE could be loaded into
+		 * some TLBs while the old PTE remains in others.
 		 */
 		ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
 		page_add_new_anon_rmap(new_page, vma, vmf->address, false);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c01604224299..f9d57b9be8c7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -713,7 +713,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 	 * expects the zone spans the pfn range. All the pages in the range
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
-	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
+	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, 0,
 			 MEMINIT_HOTPLUG, altmap, migratetype);
 
 	set_zone_contiguous(zone);
@@ -1784,39 +1784,112 @@ int remove_memory(int nid, u64 start, u64 size)
 }
 EXPORT_SYMBOL_GPL(remove_memory);
 
+static int try_offline_memory_block(struct memory_block *mem, void *arg)
+{
+	uint8_t online_type = MMOP_ONLINE_KERNEL;
+	uint8_t **online_types = arg;
+	struct page *page;
+	int rc;
+
+	/*
+	 * Sense the online_type via the zone of the memory block. Offlining
+	 * with multiple zones within one memory block will be rejected
+	 * by offlining code ... so we don't care about that.
+	 */
+	page = pfn_to_online_page(section_nr_to_pfn(mem->start_section_nr));
+	if (page && zone_idx(page_zone(page)) == ZONE_MOVABLE)
+		online_type = MMOP_ONLINE_MOVABLE;
+
+	rc = device_offline(&mem->dev);
+	/*
+	 * Default is MMOP_OFFLINE - change it only if offlining succeeded,
+	 * so try_reonline_memory_block() can do the right thing.
+	 */
+	if (!rc)
+		**online_types = online_type;
+
+	(*online_types)++;
+	/* Ignore if already offline. */
+	return rc < 0 ? rc : 0;
+}
+
+static int try_reonline_memory_block(struct memory_block *mem, void *arg)
+{
+	uint8_t **online_types = arg;
+	int rc;
+
+	if (**online_types != MMOP_OFFLINE) {
+		mem->online_type = **online_types;
+		rc = device_online(&mem->dev);
+		if (rc < 0)
+			pr_warn("%s: Failed to re-online memory: %d",
+				__func__, rc);
+	}
+
+	/* Continue processing all remaining memory blocks. */
+	(*online_types)++;
+	return 0;
+}
+
 /*
- * Try to offline and remove a memory block. Might take a long time to
- * finish in case memory is still in use. Primarily useful for memory devices
- * that logically unplugged all memory (so it's no longer in use) and want to
- * offline + remove the memory block.
+ * Try to offline and remove memory. Might take a long time to finish in case
+ * memory is still in use. Primarily useful for memory devices that logically
+ * unplugged all memory (so it's no longer in use) and want to offline + remove
+ * that memory.
  */
 int offline_and_remove_memory(int nid, u64 start, u64 size)
 {
-	struct memory_block *mem;
-	int rc = -EINVAL;
+	const unsigned long mb_count = size / memory_block_size_bytes();
+	uint8_t *online_types, *tmp;
+	int rc;
 
 	if (!IS_ALIGNED(start, memory_block_size_bytes()) ||
-	    size != memory_block_size_bytes())
-		return rc;
+	    !IS_ALIGNED(size, memory_block_size_bytes()) || !size)
+		return -EINVAL;
+
+	/*
+	 * We'll remember the old online type of each memory block, so we can
+	 * try to revert whatever we did when offlining one memory block fails
+	 * after offlining some others succeeded.
+	 */
+	online_types = kmalloc_array(mb_count, sizeof(*online_types),
+				     GFP_KERNEL);
+	if (!online_types)
+		return -ENOMEM;
+	/*
+	 * Initialize all states to MMOP_OFFLINE, so when we abort processing in
+	 * try_offline_memory_block(), we'll skip all unprocessed blocks in
+	 * try_reonline_memory_block().
+	 */
+	memset(online_types, MMOP_OFFLINE, mb_count);
 
 	lock_device_hotplug();
-	mem = find_memory_block(__pfn_to_section(PFN_DOWN(start)));
-	if (mem)
-		rc = device_offline(&mem->dev);
-	/* Ignore if the device is already offline. */
-	if (rc > 0)
-		rc = 0;
+
+	tmp = online_types;
+	rc = walk_memory_blocks(start, size, &tmp, try_offline_memory_block);
 
 	/*
-	 * In case we succeeded to offline the memory block, remove it.
+	 * In case we succeeded to offline all memory, remove it.
 	 * This cannot fail as it cannot get onlined in the meantime.
 	 */
 	if (!rc) {
 		rc = try_remove_memory(nid, start, size);
-		WARN_ON_ONCE(rc);
+		if (rc)
+			pr_err("%s: Failed to remove memory: %d", __func__, rc);
+	}
+
+	/*
+	 * Rollback what we did. While memory onlining might theoretically fail
+	 * (nacked by a notifier), it barely ever happens.
+	 */
+	if (rc) {
+		tmp = online_types;
+		walk_memory_blocks(start, size, &tmp,
+				   try_reonline_memory_block);
 	}
 	unlock_device_hotplug();
 
+	kfree(online_types);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(offline_and_remove_memory);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 8cf96bd21341..2c3a86502053 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1111,7 +1111,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 		     const nodemask_t *to, int flags)
 {
 	int busy = 0;
-	int err;
+	int err = 0;
 	nodemask_t tmp;
 
 	migrate_prep();
diff --git a/mm/mempool.c b/mm/mempool.c
index f473cdddaff0..624ed51b060f 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -104,7 +104,7 @@ static inline void poison_element(mempool_t *pool, void *element)
 static __always_inline void kasan_poison_element(mempool_t *pool, void *element)
 {
 	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
-		kasan_poison_kfree(element, _RET_IP_);
+		kasan_slab_free_mempool(element, _RET_IP_);
 	else if (pool->alloc == mempool_alloc_pages)
 		kasan_free_pages(element, (unsigned long)pool->pool_data);
 }
@@ -112,7 +112,7 @@ static __always_inline void kasan_poison_element(mempool_t *pool, void *element)
 static void kasan_unpoison_element(mempool_t *pool, void *element)
 {
 	if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc)
-		kasan_unpoison_slab(element);
+		kasan_unpoison_range(element, __ksize(element));
 	else if (pool->alloc == mempool_alloc_pages)
 		kasan_alloc_pages(element, (unsigned long)pool->pool_data);
 }
diff --git a/mm/mremap.c b/mm/mremap.c
index c5590afe7165..f554320281cc 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -358,7 +358,9 @@ static unsigned long get_extent(enum pgt_entry entry, unsigned long old_addr,
 
 	next = (old_addr + size) & mask;
 	/* even if next overflowed, extent below will be ok */
-	extent = (next > old_end) ? old_end - old_addr : next - old_addr;
+	extent = next - old_addr;
+	if (extent > old_end - old_addr)
+		extent = old_end - old_addr;
 	next = (new_addr + size) & mask;
 	if (extent > next - new_addr)
 		extent = next - new_addr;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 586042472ac9..eb34d204d4ee 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2826,7 +2826,7 @@ EXPORT_SYMBOL(__test_set_page_writeback);
  */
 void wait_on_page_writeback(struct page *page)
 {
-	if (PageWriteback(page)) {
+	while (PageWriteback(page)) {
 		trace_wait_on_page_writeback(page, page_mapping(page));
 		wait_on_page_bit(page, PG_writeback);
 	}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3beeb8d722f3..027f6481ba59 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -423,6 +423,8 @@ defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
 	if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
 		return false;
 
+	if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX)
+		return true;
 	/*
 	 * We start only with one section of pages, more pages are added as
 	 * needed until the rest of deferred pages are initialized.
@@ -1204,8 +1206,10 @@ static void kernel_init_free_pages(struct page *page, int numpages)
 
 	/* s390's use of memset() could override KASAN redzones. */
 	kasan_disable_current();
-	for (i = 0; i < numpages; i++)
+	for (i = 0; i < numpages; i++) {
+		page_kasan_tag_reset(page + i);
 		clear_highpage(page + i);
+	}
 	kasan_enable_current();
 }
 
@@ -2858,20 +2862,20 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype,
 {
 	struct page *page;
 
-#ifdef CONFIG_CMA
-	/*
-	 * Balance movable allocations between regular and CMA areas by
-	 * allocating from CMA when over half of the zone's free memory
-	 * is in the CMA area.
-	 */
-	if (alloc_flags & ALLOC_CMA &&
-	    zone_page_state(zone, NR_FREE_CMA_PAGES) >
-	    zone_page_state(zone, NR_FREE_PAGES) / 2) {
-		page = __rmqueue_cma_fallback(zone, order);
-		if (page)
-			return page;
+	if (IS_ENABLED(CONFIG_CMA)) {
+		/*
+		 * Balance movable allocations between regular and CMA areas by
+		 * allocating from CMA when over half of the zone's free memory
+		 * is in the CMA area.
+		 */
+		if (alloc_flags & ALLOC_CMA &&
+		    zone_page_state(zone, NR_FREE_CMA_PAGES) >
+		    zone_page_state(zone, NR_FREE_PAGES) / 2) {
+			page = __rmqueue_cma_fallback(zone, order);
+			if (page)
+				goto out;
+		}
 	}
-#endif
 retry:
 	page = __rmqueue_smallest(zone, order, migratetype);
 	if (unlikely(!page)) {
@@ -2882,8 +2886,9 @@ retry:
 								alloc_flags))
 			goto retry;
 	}
-
-	trace_mm_page_alloc_zone_locked(page, order, migratetype);
+out:
+	if (page)
+		trace_mm_page_alloc_zone_locked(page, order, migratetype);
 	return page;
 }
 
@@ -6114,7 +6119,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
  * zone stats (e.g., nr_isolate_pageblock) are touched.
  */
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
-		unsigned long start_pfn,
+		unsigned long start_pfn, unsigned long zone_end_pfn,
 		enum meminit_context context,
 		struct vmem_altmap *altmap, int migratetype)
 {
@@ -6150,7 +6155,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		if (context == MEMINIT_EARLY) {
 			if (overlap_memmap_init(zone, &pfn))
 				continue;
-			if (defer_init(nid, pfn, end_pfn))
+			if (defer_init(nid, pfn, zone_end_pfn))
 				break;
 		}
 
@@ -6264,7 +6269,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid,
 
 		if (end_pfn > start_pfn) {
 			size = end_pfn - start_pfn;
-			memmap_init_zone(size, nid, zone, start_pfn,
+			memmap_init_zone(size, nid, zone, start_pfn, range_end_pfn,
 					 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 		}
 	}
@@ -7671,6 +7676,11 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
 		 * alias for the memset().
 		 */
 		direct_map_addr = page_address(page);
+		/*
+		 * Perform a kasan-unchecked memset() since this memory
+		 * has not been initialized.
+		 */
+		direct_map_addr = kasan_reset_tag(direct_map_addr);
 		if ((unsigned int)poison <= 0xFF)
 			memset(direct_map_addr, poison, PAGE_SIZE);
 
diff --git a/mm/page_poison.c b/mm/page_poison.c
index 06ec518b2089..65cdf844c8ad 100644
--- a/mm/page_poison.c
+++ b/mm/page_poison.c
@@ -25,7 +25,7 @@ static void poison_page(struct page *page)
 
 	/* KASAN still think the page is in-use, so skip it. */
 	kasan_disable_current();
-	memset(addr, PAGE_POISON, PAGE_SIZE);
+	memset(kasan_reset_tag(addr), PAGE_POISON, PAGE_SIZE);
 	kasan_enable_current();
 	kunmap_atomic(addr);
 }
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 4bcc11958089..f5fee9cf90f8 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/uio.h>
 #include <linux/sched.h>
+#include <linux/compat.h>
 #include <linux/sched/mm.h>
 #include <linux/highmem.h>
 #include <linux/ptrace.h>
diff --git a/mm/ptdump.c b/mm/ptdump.c
index ba88ec43ff21..4354c1422d57 100644
--- a/mm/ptdump.c
+++ b/mm/ptdump.c
@@ -4,7 +4,7 @@
 #include <linux/ptdump.h>
 #include <linux/kasan.h>
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 /*
  * This is an optimization for KASAN=y case. Since all kasan page tables
  * eventually point to the kasan_early_shadow_page we could call note_page()
@@ -31,7 +31,8 @@ static int ptdump_pgd_entry(pgd_t *pgd, unsigned long addr,
 	struct ptdump_state *st = walk->private;
 	pgd_t val = READ_ONCE(*pgd);
 
-#if CONFIG_PGTABLE_LEVELS > 4 && defined(CONFIG_KASAN)
+#if CONFIG_PGTABLE_LEVELS > 4 && \
+		(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS))
 	if (pgd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_p4d)))
 		return note_kasan_page_table(walk, addr);
 #endif
@@ -51,7 +52,8 @@ static int ptdump_p4d_entry(p4d_t *p4d, unsigned long addr,
 	struct ptdump_state *st = walk->private;
 	p4d_t val = READ_ONCE(*p4d);
 
-#if CONFIG_PGTABLE_LEVELS > 3 && defined(CONFIG_KASAN)
+#if CONFIG_PGTABLE_LEVELS > 3 && \
+		(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS))
 	if (p4d_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pud)))
 		return note_kasan_page_table(walk, addr);
 #endif
@@ -71,7 +73,8 @@ static int ptdump_pud_entry(pud_t *pud, unsigned long addr,
 	struct ptdump_state *st = walk->private;
 	pud_t val = READ_ONCE(*pud);
 
-#if CONFIG_PGTABLE_LEVELS > 2 && defined(CONFIG_KASAN)
+#if CONFIG_PGTABLE_LEVELS > 2 && \
+		(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS))
 	if (pud_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pmd)))
 		return note_kasan_page_table(walk, addr);
 #endif
@@ -91,7 +94,7 @@ static int ptdump_pmd_entry(pmd_t *pmd, unsigned long addr,
 	struct ptdump_state *st = walk->private;
 	pmd_t val = READ_ONCE(*pmd);
 
-#if defined(CONFIG_KASAN)
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 	if (pmd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pte)))
 		return note_kasan_page_table(walk, addr);
 #endif
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 2f2b55c2798e..e981c80d216c 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -18,6 +18,7 @@
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
 #include <linux/debugfs.h>
+#include <linux/kasan.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/page.h>
@@ -53,7 +54,7 @@ static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
  */
 #define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
 		SLAB_TRACE | SLAB_TYPESAFE_BY_RCU | SLAB_NOLEAKTRACE | \
-		SLAB_FAILSLAB | SLAB_KASAN)
+		SLAB_FAILSLAB | kasan_never_merge())
 
 #define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \
 			 SLAB_CACHE_DMA32 | SLAB_ACCOUNT)
@@ -1176,7 +1177,7 @@ size_t ksize(const void *objp)
 	 * We assume that ksize callers could use whole allocated area,
 	 * so we need to unpoison this area.
 	 */
-	kasan_unpoison_shadow(objp, size);
+	kasan_unpoison_range(objp, size);
 	return size;
 }
 EXPORT_SYMBOL(ksize);
diff --git a/mm/slub.c b/mm/slub.c
index 4552319148f6..d9e4e10683cc 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -249,7 +249,7 @@ static inline void *freelist_ptr(const struct kmem_cache *s, void *ptr,
 {
 #ifdef CONFIG_SLAB_FREELIST_HARDENED
 	/*
-	 * When CONFIG_KASAN_SW_TAGS is enabled, ptr_addr might be tagged.
+	 * When CONFIG_KASAN_SW/HW_TAGS is enabled, ptr_addr might be tagged.
 	 * Normally, this doesn't cause any issues, as both set_freepointer()
 	 * and get_freepointer() are called with a pointer with the same tag.
 	 * However, there are some issues with CONFIG_SLUB_DEBUG code. For
@@ -275,6 +275,7 @@ static inline void *freelist_dereference(const struct kmem_cache *s,
 
 static inline void *get_freepointer(struct kmem_cache *s, void *object)
 {
+	object = kasan_reset_tag(object);
 	return freelist_dereference(s, object + s->offset);
 }
 
@@ -304,6 +305,7 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
 	BUG_ON(object == fp); /* naive detection of double free or corruption */
 #endif
 
+	freeptr_addr = (unsigned long)kasan_reset_tag((void *)freeptr_addr);
 	*(void **)freeptr_addr = freelist_ptr(s, fp, freeptr_addr);
 }
 
@@ -538,8 +540,8 @@ static void print_section(char *level, char *text, u8 *addr,
 			  unsigned int length)
 {
 	metadata_access_enable();
-	print_hex_dump(level, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
-			length, 1);
+	print_hex_dump(level, kasan_reset_tag(text), DUMP_PREFIX_ADDRESS,
+			16, 1, addr, length, 1);
 	metadata_access_disable();
 }
 
@@ -570,7 +572,7 @@ static struct track *get_track(struct kmem_cache *s, void *object,
 
 	p = object + get_info_end(s);
 
-	return p + alloc;
+	return kasan_reset_tag(p + alloc);
 }
 
 static void set_track(struct kmem_cache *s, void *object,
@@ -583,7 +585,8 @@ static void set_track(struct kmem_cache *s, void *object,
 		unsigned int nr_entries;
 
 		metadata_access_enable();
-		nr_entries = stack_trace_save(p->addrs, TRACK_ADDRS_COUNT, 3);
+		nr_entries = stack_trace_save(kasan_reset_tag(p->addrs),
+					      TRACK_ADDRS_COUNT, 3);
 		metadata_access_disable();
 
 		if (nr_entries < TRACK_ADDRS_COUNT)
@@ -747,7 +750,7 @@ static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page,
 
 static void init_object(struct kmem_cache *s, void *object, u8 val)
 {
-	u8 *p = object;
+	u8 *p = kasan_reset_tag(object);
 
 	if (s->flags & SLAB_RED_ZONE)
 		memset(p - s->red_left_pad, val, s->red_left_pad);
@@ -777,7 +780,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
 	u8 *addr = page_address(page);
 
 	metadata_access_enable();
-	fault = memchr_inv(start, value, bytes);
+	fault = memchr_inv(kasan_reset_tag(start), value, bytes);
 	metadata_access_disable();
 	if (!fault)
 		return 1;
@@ -873,7 +876,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page)
 
 	pad = end - remainder;
 	metadata_access_enable();
-	fault = memchr_inv(pad, POISON_INUSE, remainder);
+	fault = memchr_inv(kasan_reset_tag(pad), POISON_INUSE, remainder);
 	metadata_access_disable();
 	if (!fault)
 		return 1;
@@ -1118,7 +1121,7 @@ void setup_page_debug(struct kmem_cache *s, struct page *page, void *addr)
 		return;
 
 	metadata_access_enable();
-	memset(addr, POISON_INUSE, page_size(page));
+	memset(kasan_reset_tag(addr), POISON_INUSE, page_size(page));
 	metadata_access_disable();
 }
 
@@ -1566,10 +1569,10 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
 			 * Clear the object and the metadata, but don't touch
 			 * the redzone.
 			 */
-			memset(object, 0, s->object_size);
+			memset(kasan_reset_tag(object), 0, s->object_size);
 			rsize = (s->flags & SLAB_RED_ZONE) ? s->red_left_pad
 							   : 0;
-			memset((char *)object + s->inuse, 0,
+			memset((char *)kasan_reset_tag(object) + s->inuse, 0,
 			       s->size - s->inuse - rsize);
 
 		}
@@ -1616,9 +1619,6 @@ static inline struct page *alloc_slab_page(struct kmem_cache *s,
 	else
 		page = __alloc_pages_node(node, flags, order);
 
-	if (page)
-		account_slab_page(page, order, s);
-
 	return page;
 }
 
@@ -1771,6 +1771,8 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 
 	page->objects = oo_objects(oo);
 
+	account_slab_page(page, oo_order(oo), s);
+
 	page->slab_cache = s;
 	__SetPageSlab(page);
 	if (page_is_pfmemalloc(page))
@@ -1971,7 +1973,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 
 		t = acquire_slab(s, n, page, object == NULL, &objects);
 		if (!t)
-			break;
+			continue; /* cmpxchg raced */
 
 		available += objects;
 		if (!object) {
@@ -2881,10 +2883,10 @@ redo:
 		stat(s, ALLOC_FASTPATH);
 	}
 
-	maybe_wipe_obj_freeptr(s, object);
+	maybe_wipe_obj_freeptr(s, kasan_reset_tag(object));
 
 	if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object)
-		memset(object, 0, s->object_size);
+		memset(kasan_reset_tag(object), 0, s->object_size);
 
 	slab_post_alloc_hook(s, objcg, gfpflags, 1, &object);
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 4d88fe5a277a..e6f352bf0498 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2420,8 +2420,10 @@ void *vmap(struct page **pages, unsigned int count,
 		return NULL;
 	}
 
-	if (flags & VM_MAP_PUT_PAGES)
+	if (flags & VM_MAP_PUT_PAGES) {
 		area->pages = pages;
+		area->nr_pages = count;
+	}
 	return area->addr;
 }
 EXPORT_SYMBOL(vmap);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 257cba79a96d..b1b574ad199d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1238,6 +1238,8 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 			if (!PageSwapCache(page)) {
 				if (!(sc->gfp_mask & __GFP_IO))
 					goto keep_locked;
+				if (page_maybe_dma_pinned(page))
+					goto keep_locked;
 				if (PageTransHuge(page)) {
 					/* cannot split THP, skip it */
 					if (!can_split_huge_page(page, NULL))
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index f292e0267bb9..8b644113715e 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -284,8 +284,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 	return 0;
 
 out_free_newdev:
-	if (new_dev->reg_state == NETREG_UNINITIALIZED)
-		free_netdev(new_dev);
+	free_netdev(new_dev);
 	return err;
 }
 
diff --git a/net/9p/client.c b/net/9p/client.c
index 785a7bb6a539..4f62f299da0c 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -903,6 +903,7 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt)
 	fid->clnt = clnt;
 	fid->rdir = NULL;
 	fid->fid = 0;
+	refcount_set(&fid->count, 1);
 
 	idr_preload(GFP_KERNEL);
 	spin_lock_irq(&clnt->lock);
@@ -910,7 +911,6 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt)
 			    GFP_NOWAIT);
 	spin_unlock_irq(&clnt->lock);
 	idr_preload_end();
-
 	if (!ret)
 		return fid;
 
@@ -1189,7 +1189,6 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
 
 	p9_debug(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %ud wname[0] %s\n",
 		 oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL);
-
 	req = p9_client_rpc(clnt, P9_TWALK, "ddT", oldfid->fid, fid->fid,
 								nwname, wnames);
 	if (IS_ERR(req)) {
@@ -1221,7 +1220,7 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
 	if (nwname)
 		memmove(&fid->qid, &wqids[nwqids - 1], sizeof(struct p9_qid));
 	else
-		fid->qid = oldfid->qid;
+		memmove(&fid->qid, &oldfid->qid, sizeof(struct p9_qid));
 
 	kfree(wqids);
 	return fid;
@@ -1274,6 +1273,7 @@ int p9_client_open(struct p9_fid *fid, int mode)
 		p9_is_proto_dotl(clnt) ? "RLOPEN" : "ROPEN",  qid.type,
 		(unsigned long long)qid.path, qid.version, iounit);
 
+	memmove(&fid->qid, &qid, sizeof(struct p9_qid));
 	fid->mode = mode;
 	fid->iounit = iounit;
 
@@ -1319,6 +1319,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32
 			(unsigned long long)qid->path,
 			qid->version, iounit);
 
+	memmove(&ofid->qid, qid, sizeof(struct p9_qid));
 	ofid->mode = mode;
 	ofid->iounit = iounit;
 
@@ -1364,6 +1365,7 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
 				(unsigned long long)qid.path,
 				qid.version, iounit);
 
+	memmove(&fid->qid, &qid, sizeof(struct p9_qid));
 	fid->mode = mode;
 	fid->iounit = iounit;
 
@@ -1460,12 +1462,14 @@ int p9_client_clunk(struct p9_fid *fid)
 	struct p9_req_t *req;
 	int retries = 0;
 
-	if (!fid) {
-		pr_warn("%s (%d): Trying to clunk with NULL fid\n",
+	if (!fid || IS_ERR(fid)) {
+		pr_warn("%s (%d): Trying to clunk with invalid fid\n",
 			__func__, task_pid_nr(current));
 		dump_stack();
 		return 0;
 	}
+	if (!refcount_dec_and_test(&fid->count))
+		return 0;
 
 again:
 	p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d (try %d)\n", fid->fid,
diff --git a/net/can/isotp.c b/net/can/isotp.c
index 7839c3b9e5be..3ef7f78e553b 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1155,6 +1155,7 @@ static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
 	if (peer)
 		return -EOPNOTSUPP;
 
+	memset(addr, 0, sizeof(*addr));
 	addr->can_family = AF_CAN;
 	addr->can_ifindex = so->ifindex;
 	addr->can_addr.tp.rx_id = so->rxid;
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index c1ebb2aa08b5..c38d8de93836 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -1333,7 +1333,8 @@ static int prepare_auth_signature(struct ceph_connection *con)
 	void *buf;
 	int ret;
 
-	buf = alloc_conn_buf(con, head_onwire_len(SHA256_DIGEST_SIZE, false));
+	buf = alloc_conn_buf(con, head_onwire_len(SHA256_DIGEST_SIZE,
+						  con_secure(con)));
 	if (!buf)
 		return -ENOMEM;
 
@@ -2032,10 +2033,18 @@ bad:
 	return -EINVAL;
 }
 
+/*
+ * Align session_key and con_secret to avoid GFP_ATOMIC allocation
+ * inside crypto_shash_setkey() and crypto_aead_setkey() called from
+ * setup_crypto().  __aligned(16) isn't guaranteed to work for stack
+ * objects, so do it by hand.
+ */
 static int process_auth_done(struct ceph_connection *con, void *p, void *end)
 {
-	u8 session_key[CEPH_KEY_LEN];
-	u8 con_secret[CEPH_MAX_CON_SECRET_LEN];
+	u8 session_key_buf[CEPH_KEY_LEN + 16];
+	u8 con_secret_buf[CEPH_MAX_CON_SECRET_LEN + 16];
+	u8 *session_key = PTR_ALIGN(&session_key_buf[0], 16);
+	u8 *con_secret = PTR_ALIGN(&con_secret_buf[0], 16);
 	int session_key_len, con_secret_len;
 	int payload_len;
 	u64 global_id;
diff --git a/net/core/dev.c b/net/core/dev.c
index 8fa739259041..c360bb5367e2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9661,9 +9661,15 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		}
 	}
 
-	if ((features & NETIF_F_HW_TLS_TX) && !(features & NETIF_F_HW_CSUM)) {
-		netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
-		features &= ~NETIF_F_HW_TLS_TX;
+	if (features & NETIF_F_HW_TLS_TX) {
+		bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) ==
+			(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
+		bool hw_csum = features & NETIF_F_HW_CSUM;
+
+		if (!ip_csum && !hw_csum) {
+			netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
+			features &= ~NETIF_F_HW_TLS_TX;
+		}
 	}
 
 	return features;
@@ -10077,17 +10083,11 @@ int register_netdevice(struct net_device *dev)
 	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
 	ret = notifier_to_errno(ret);
 	if (ret) {
+		/* Expect explicit free_netdev() on failure */
+		dev->needs_free_netdev = false;
 		rollback_registered(dev);
-		rcu_barrier();
-
-		dev->reg_state = NETREG_UNREGISTERED;
-		/* We should put the kobject that hold in
-		 * netdev_unregister_kobject(), otherwise
-		 * the net device cannot be freed when
-		 * driver calls free_netdev(), because the
-		 * kobject is being hold.
-		 */
-		kobject_put(&dev->dev.kobj);
+		net_set_todo(dev);
+		goto out;
 	}
 	/*
 	 *	Prevent userspace races by waiting until the network
@@ -10631,6 +10631,17 @@ void free_netdev(struct net_device *dev)
 	struct napi_struct *p, *n;
 
 	might_sleep();
+
+	/* When called immediately after register_netdevice() failed the unwind
+	 * handling may still be dismantling the device. Handle that case by
+	 * deferring the free.
+	 */
+	if (dev->reg_state == NETREG_UNREGISTERING) {
+		ASSERT_RTNL();
+		dev->needs_free_netdev = true;
+		return;
+	}
+
 	netif_free_tx_queues(dev);
 	netif_free_rx_queues(dev);
 
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 9500d28a43b0..277ed854aef1 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1569,10 +1569,8 @@ static void neigh_proxy_process(struct timer_list *t)
 void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
 		    struct sk_buff *skb)
 {
-	unsigned long now = jiffies;
-
-	unsigned long sched_next = now + (prandom_u32() %
-					  NEIGH_VAR(p, PROXY_DELAY));
+	unsigned long sched_next = jiffies +
+			prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY));
 
 	if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
 		kfree_skb(skb);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 999b70c59761..daf502c13d6d 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1317,8 +1317,8 @@ static const struct attribute_group dql_group = {
 static ssize_t xps_cpus_show(struct netdev_queue *queue,
 			     char *buf)
 {
+	int cpu, len, ret, num_tc = 1, tc = 0;
 	struct net_device *dev = queue->dev;
-	int cpu, len, num_tc = 1, tc = 0;
 	struct xps_dev_maps *dev_maps;
 	cpumask_var_t mask;
 	unsigned long index;
@@ -1328,22 +1328,31 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 
 	index = get_netdev_queue_index(queue);
 
+	if (!rtnl_trylock())
+		return restart_syscall();
+
 	if (dev->num_tc) {
 		/* Do not allow XPS on subordinate device directly */
 		num_tc = dev->num_tc;
-		if (num_tc < 0)
-			return -EINVAL;
+		if (num_tc < 0) {
+			ret = -EINVAL;
+			goto err_rtnl_unlock;
+		}
 
 		/* If queue belongs to subordinate dev use its map */
 		dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
 
 		tc = netdev_txq_to_tc(dev, index);
-		if (tc < 0)
-			return -EINVAL;
+		if (tc < 0) {
+			ret = -EINVAL;
+			goto err_rtnl_unlock;
+		}
 	}
 
-	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
-		return -ENOMEM;
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto err_rtnl_unlock;
+	}
 
 	rcu_read_lock();
 	dev_maps = rcu_dereference(dev->xps_cpus_map);
@@ -1366,9 +1375,15 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 	}
 	rcu_read_unlock();
 
+	rtnl_unlock();
+
 	len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask));
 	free_cpumask_var(mask);
 	return len < PAGE_SIZE ? len : -EINVAL;
+
+err_rtnl_unlock:
+	rtnl_unlock();
+	return ret;
 }
 
 static ssize_t xps_cpus_store(struct netdev_queue *queue,
@@ -1396,7 +1411,13 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue,
 		return err;
 	}
 
+	if (!rtnl_trylock()) {
+		free_cpumask_var(mask);
+		return restart_syscall();
+	}
+
 	err = netif_set_xps_queue(dev, mask, index);
+	rtnl_unlock();
 
 	free_cpumask_var(mask);
 
@@ -1408,22 +1429,29 @@ static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init
 
 static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf)
 {
+	int j, len, ret, num_tc = 1, tc = 0;
 	struct net_device *dev = queue->dev;
 	struct xps_dev_maps *dev_maps;
 	unsigned long *mask, index;
-	int j, len, num_tc = 1, tc = 0;
 
 	index = get_netdev_queue_index(queue);
 
+	if (!rtnl_trylock())
+		return restart_syscall();
+
 	if (dev->num_tc) {
 		num_tc = dev->num_tc;
 		tc = netdev_txq_to_tc(dev, index);
-		if (tc < 0)
-			return -EINVAL;
+		if (tc < 0) {
+			ret = -EINVAL;
+			goto err_rtnl_unlock;
+		}
 	}
 	mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL);
-	if (!mask)
-		return -ENOMEM;
+	if (!mask) {
+		ret = -ENOMEM;
+		goto err_rtnl_unlock;
+	}
 
 	rcu_read_lock();
 	dev_maps = rcu_dereference(dev->xps_rxqs_map);
@@ -1449,10 +1477,16 @@ static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf)
 out_no_maps:
 	rcu_read_unlock();
 
+	rtnl_unlock();
+
 	len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues);
 	bitmap_free(mask);
 
 	return len < PAGE_SIZE ? len : -EINVAL;
+
+err_rtnl_unlock:
+	rtnl_unlock();
+	return ret;
 }
 
 static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
@@ -1478,10 +1512,17 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
 		return err;
 	}
 
+	if (!rtnl_trylock()) {
+		bitmap_free(mask);
+		return restart_syscall();
+	}
+
 	cpus_read_lock();
 	err = __netif_set_xps_queue(dev, mask, index, true);
 	cpus_read_unlock();
 
+	rtnl_unlock();
+
 	bitmap_free(mask);
 	return err ? : len;
 }
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index bb0596c41b3e..3d6ab194d0f5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3439,26 +3439,15 @@ replay:
 
 	dev->ifindex = ifm->ifi_index;
 
-	if (ops->newlink) {
+	if (ops->newlink)
 		err = ops->newlink(link_net ? : net, dev, tb, data, extack);
-		/* Drivers should call free_netdev() in ->destructor
-		 * and unregister it on failure after registration
-		 * so that device could be finally freed in rtnl_unlock.
-		 */
-		if (err < 0) {
-			/* If device is not registered at all, free it now */
-			if (dev->reg_state == NETREG_UNINITIALIZED ||
-			    dev->reg_state == NETREG_UNREGISTERED)
-				free_netdev(dev);
-			goto out;
-		}
-	} else {
+	else
 		err = register_netdevice(dev);
-		if (err < 0) {
-			free_netdev(dev);
-			goto out;
-		}
+	if (err < 0) {
+		free_netdev(dev);
+		goto out;
 	}
+
 	err = rtnl_configure_link(dev, ifm);
 	if (err < 0)
 		goto out_unregister;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f62cae3f75d8..c1a6f262636a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -501,13 +501,17 @@ EXPORT_SYMBOL(__netdev_alloc_skb);
 struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 				 gfp_t gfp_mask)
 {
-	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+	struct napi_alloc_cache *nc;
 	struct sk_buff *skb;
 	void *data;
 
 	len += NET_SKB_PAD + NET_IP_ALIGN;
 
-	if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
+	/* If requested length is either too small or too big,
+	 * we use kmalloc() for skb->head allocation.
+	 */
+	if (len <= SKB_WITH_OVERHEAD(1024) ||
+	    len > SKB_WITH_OVERHEAD(PAGE_SIZE) ||
 	    (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
 		skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
 		if (!skb)
@@ -515,6 +519,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 		goto skb_success;
 	}
 
+	nc = this_cpu_ptr(&napi_alloc_cache);
 	len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	len = SKB_DATA_ALIGN(len);
 
@@ -3442,6 +3447,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
 	st->root_skb = st->cur_skb = skb;
 	st->frag_idx = st->stepped_offset = 0;
 	st->frag_data = NULL;
+	st->frag_off = 0;
 }
 EXPORT_SYMBOL(skb_prepare_seq_read);
 
@@ -3496,14 +3502,27 @@ next_skb:
 		st->stepped_offset += skb_headlen(st->cur_skb);
 
 	while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) {
+		unsigned int pg_idx, pg_off, pg_sz;
+
 		frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
-		block_limit = skb_frag_size(frag) + st->stepped_offset;
 
+		pg_idx = 0;
+		pg_off = skb_frag_off(frag);
+		pg_sz = skb_frag_size(frag);
+
+		if (skb_frag_must_loop(skb_frag_page(frag))) {
+			pg_idx = (pg_off + st->frag_off) >> PAGE_SHIFT;
+			pg_off = offset_in_page(pg_off + st->frag_off);
+			pg_sz = min_t(unsigned int, pg_sz - st->frag_off,
+						    PAGE_SIZE - pg_off);
+		}
+
+		block_limit = pg_sz + st->stepped_offset;
 		if (abs_offset < block_limit) {
 			if (!st->frag_data)
-				st->frag_data = kmap_atomic(skb_frag_page(frag));
+				st->frag_data = kmap_atomic(skb_frag_page(frag) + pg_idx);
 
-			*data = (u8 *) st->frag_data + skb_frag_off(frag) +
+			*data = (u8 *)st->frag_data + pg_off +
 				(abs_offset - st->stepped_offset);
 
 			return block_limit - abs_offset;
@@ -3514,8 +3533,12 @@ next_skb:
 			st->frag_data = NULL;
 		}
 
-		st->frag_idx++;
-		st->stepped_offset += skb_frag_size(frag);
+		st->stepped_offset += pg_sz;
+		st->frag_off += pg_sz;
+		if (st->frag_off == skb_frag_size(frag)) {
+			st->frag_off = 0;
+			st->frag_idx++;
+		}
 	}
 
 	if (st->frag_data) {
@@ -3655,7 +3678,8 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
 	unsigned int delta_truesize = 0;
 	unsigned int delta_len = 0;
 	struct sk_buff *tail = NULL;
-	struct sk_buff *nskb;
+	struct sk_buff *nskb, *tmp;
+	int err;
 
 	skb_push(skb, -skb_network_offset(skb) + offset);
 
@@ -3665,11 +3689,28 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
 		nskb = list_skb;
 		list_skb = list_skb->next;
 
+		err = 0;
+		if (skb_shared(nskb)) {
+			tmp = skb_clone(nskb, GFP_ATOMIC);
+			if (tmp) {
+				consume_skb(nskb);
+				nskb = tmp;
+				err = skb_unclone(nskb, GFP_ATOMIC);
+			} else {
+				err = -ENOMEM;
+			}
+		}
+
 		if (!tail)
 			skb->next = nskb;
 		else
 			tail->next = nskb;
 
+		if (unlikely(err)) {
+			nskb->next = list_skb;
+			goto err_linearize;
+		}
+
 		tail = nskb;
 
 		delta_len += nskb->len;
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index bbdd3c7b6cb5..b065f0a103ed 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -293,7 +293,7 @@ select_by_hash:
 			i = j = reciprocal_scale(hash, socks);
 			while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
 				i++;
-				if (i >= reuse->num_socks)
+				if (i >= socks)
 					i = 0;
 				if (i == j)
 					goto out;
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 084e159a12ba..653e3bc9c87b 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1765,6 +1765,8 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	fn = &reply_funcs[dcb->cmd];
 	if (!fn->cb)
 		return -EOPNOTSUPP;
+	if (fn->type == RTM_SETDCB && !netlink_capable(skb, CAP_NET_ADMIN))
+		return -EPERM;
 
 	if (!tb[DCB_ATTR_IFNAME])
 		return -EINVAL;
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 183003e45762..a47e0f9b20d0 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -353,9 +353,13 @@ static int dsa_port_devlink_setup(struct dsa_port *dp)
 
 static void dsa_port_teardown(struct dsa_port *dp)
 {
+	struct devlink_port *dlp = &dp->devlink_port;
+
 	if (!dp->setup)
 		return;
 
+	devlink_port_type_clear(dlp);
+
 	switch (dp->type) {
 	case DSA_PORT_TYPE_UNUSED:
 		break;
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 5a0f6fec4271..cb3a5cf99b25 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -309,8 +309,18 @@ static struct lock_class_key dsa_master_addr_list_lock_key;
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 {
 	int mtu = ETH_DATA_LEN + cpu_dp->tag_ops->overhead;
+	struct dsa_switch *ds = cpu_dp->ds;
+	struct device_link *consumer_link;
 	int ret;
 
+	/* The DSA master must use SET_NETDEV_DEV for this to work. */
+	consumer_link = device_link_add(ds->dev, dev->dev.parent,
+					DL_FLAG_AUTOREMOVE_CONSUMER);
+	if (!consumer_link)
+		netdev_err(dev,
+			   "Failed to create a device link to DSA switch %s\n",
+			   dev_name(ds->dev));
+
 	rtnl_lock();
 	ret = dev_set_mtu(dev, mtu);
 	rtnl_unlock();
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 8b07f3a4f2db..a3271ec3e162 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -443,7 +443,6 @@ static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb,
 int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
 	u8 *tail;
-	u8 *vaddr;
 	int nfrags;
 	int esph_offset;
 	struct page *page;
@@ -485,14 +484,10 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			page = pfrag->page;
 			get_page(page);
 
-			vaddr = kmap_atomic(page);
-
-			tail = vaddr + pfrag->offset;
+			tail = page_address(page) + pfrag->offset;
 
 			esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
 
-			kunmap_atomic(vaddr);
-
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index cdf6ec5aa45d..84bb707bd88d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -292,7 +292,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 			.flowi4_iif = LOOPBACK_IFINDEX,
 			.flowi4_oif = l3mdev_master_ifindex_rcu(dev),
 			.daddr = ip_hdr(skb)->saddr,
-			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
+			.flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK,
 			.flowi4_scope = scope,
 			.flowi4_mark = vmark ? skb->mark : 0,
 		};
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 66fdbfe5447c..5d1e6fe9d838 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -128,7 +128,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	 * to 0 and sets the configured key in the
 	 * inner erspan header field
 	 */
-	if (greh->protocol == htons(ETH_P_ERSPAN) ||
+	if ((greh->protocol == htons(ETH_P_ERSPAN) && hdr_len != 4) ||
 	    greh->protocol == htons(ETH_P_ERSPAN2)) {
 		struct erspan_base_hdr *ershdr;
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 89fff5f59eea..2ed0b01f72f0 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -302,7 +302,7 @@ static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *
 	if (skb_is_gso(skb))
 		return ip_finish_output_gso(net, sk, skb, mtu);
 
-	if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU))
+	if (skb->len > mtu || IPCB(skb)->frag_max_size)
 		return ip_fragment(net, sk, skb, mtu, ip_finish_output2);
 
 	return ip_finish_output2(net, sk, skb);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index ee65c9225178..64594aa755f0 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -759,8 +759,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph,
-			    0, 0, false)) {
+	df = tnl_params->frag_off;
+	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
+		df |= (inner_iph->frag_off & htons(IP_DF));
+
+	if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
@@ -788,10 +791,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			ttl = ip4_dst_hoplimit(&rt->dst);
 	}
 
-	df = tnl_params->frag_off;
-	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
-		df |= (inner_iph->frag_off&htons(IP_DF));
-
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
 	if (max_headroom > dev->needed_headroom)
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 563b62b76a5f..c576a63d09db 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1379,7 +1379,7 @@ static int compat_get_entries(struct net *net,
 	xt_compat_lock(NFPROTO_ARP);
 	t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 		struct xt_table_info info;
 
 		ret = compat_table_info(private, &info);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 6e2851f8d3a3..e8f6f9d86237 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1589,7 +1589,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr,
 	xt_compat_lock(AF_INET);
 	t = xt_find_table_lock(net, AF_INET, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 		struct xt_table_info info;
 		ret = compat_table_info(private, &info);
 		if (!ret && get.size == info.size)
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 5e1b22d4f939..e53e43aef785 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -627,7 +627,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
 	for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) {
 		if (!tb[i])
 			continue;
-		if (tb[NHA_FDB])
+		if (i == NHA_FDB)
 			continue;
 		NL_SET_ERR_MSG(extack,
 			       "No other attributes can be set in nexthop groups");
@@ -1459,8 +1459,10 @@ static struct nexthop *nexthop_create_group(struct net *net,
 	return nh;
 
 out_no_nh:
-	for (; i >= 0; --i)
+	for (i--; i >= 0; --i) {
+		list_del(&nhg->nh_entries[i].nh_list);
 		nexthop_put(nhg->nh_entries[i].nh);
+	}
 
 	kfree(nhg->spare);
 	kfree(nhg);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 52c2f063529f..2b804fcebcc6 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -478,7 +478,6 @@ static int esp6_output_encap(struct xfrm_state *x, struct sk_buff *skb,
 int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
 	u8 *tail;
-	u8 *vaddr;
 	int nfrags;
 	int esph_offset;
 	struct page *page;
@@ -519,14 +518,10 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 			page = pfrag->page;
 			get_page(page);
 
-			vaddr = kmap_atomic(page);
-
-			tail = vaddr + pfrag->offset;
+			tail = page_address(page) + pfrag->offset;
 
 			esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
 
-			kunmap_atomic(vaddr);
-
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 605cdd38a919..f43e27555725 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1025,6 +1025,8 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 {
 	struct fib6_table *table = rt->fib6_table;
 
+	/* Flush all cached dst in exception table */
+	rt6_flush_exceptions(rt);
 	fib6_drop_pcpu_from(rt, table);
 
 	if (rt->nh && !list_empty(&rt->nh_list))
@@ -1927,9 +1929,6 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 	net->ipv6.rt6_stats->fib_rt_entries--;
 	net->ipv6.rt6_stats->fib_discarded_routes++;
 
-	/* Flush all cached dst in exception table */
-	rt6_flush_exceptions(rt);
-
 	/* Reset round-robin state, if necessary */
 	if (rcu_access_pointer(fn->rr_ptr) == rt)
 		fn->rr_ptr = NULL;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 749ad72386b2..077d43af8226 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -125,8 +125,43 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 	return -EINVAL;
 }
 
+static int
+ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
+				    struct sk_buff *skb, unsigned int mtu)
+{
+	struct sk_buff *segs, *nskb;
+	netdev_features_t features;
+	int ret = 0;
+
+	/* Please see corresponding comment in ip_finish_output_gso
+	 * describing the cases where GSO segment length exceeds the
+	 * egress MTU.
+	 */
+	features = netif_skb_features(skb);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR_OR_NULL(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	skb_list_walk_safe(segs, segs, nskb) {
+		int err;
+
+		skb_mark_not_on_list(segs);
+		err = ip6_fragment(net, sk, segs, ip6_finish_output2);
+		if (err && ret == 0)
+			ret = err;
+	}
+
+	return ret;
+}
+
 static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	unsigned int mtu;
+
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
 	if (skb_dst(skb)->xfrm) {
@@ -135,7 +170,11 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 	}
 #endif
 
-	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
+	mtu = ip6_skb_dst_mtu(skb);
+	if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))
+		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
+
+	if ((skb->len > mtu && !skb_is_gso(skb)) ||
 	    dst_allfrag(skb_dst(skb)) ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
 		return ip6_fragment(net, sk, skb, ip6_finish_output2);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index c4f532f4d311..0d453fa9e327 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1598,7 +1598,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr,
 	xt_compat_lock(AF_INET6);
 	t = xt_find_table_lock(net, AF_INET6, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 		struct xt_table_info info;
 		ret = compat_table_info(private, &info);
 		if (!ret && get.size == info.size)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 2da0ee703779..93636867aee2 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1645,8 +1645,11 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 	}
 
 #ifdef CONFIG_IPV6_SIT_6RD
-	if (ipip6_netlink_6rd_parms(data, &ip6rd))
+	if (ipip6_netlink_6rd_parms(data, &ip6rd)) {
 		err = ipip6_tunnel_update_6rd(nt, &ip6rd);
+		if (err < 0)
+			unregister_netdevice_queue(dev, NULL);
+	}
 #endif
 
 	return err;
diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c
index 213ea7abc9ab..40961889e9c0 100644
--- a/net/lapb/lapb_iface.c
+++ b/net/lapb/lapb_iface.c
@@ -489,6 +489,7 @@ static int lapb_device_event(struct notifier_block *this, unsigned long event,
 		break;
 	}
 
+	lapb_put(lapb);
 	return NOTIFY_DONE;
 }
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 09b19aa2f205..f998a077c7dd 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -427,7 +427,7 @@ static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
 static bool tcp_can_send_ack(const struct sock *ssk)
 {
 	return !((1 << inet_sk_state_load(ssk)) &
-	       (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE));
+	       (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
 }
 
 static void mptcp_send_ack(struct mptcp_sock *msk)
@@ -877,6 +877,9 @@ static void __mptcp_wmem_reserve(struct sock *sk, int size)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	WARN_ON_ONCE(msk->wmem_reserved);
+	if (WARN_ON_ONCE(amount < 0))
+		amount = 0;
+
 	if (amount <= sk->sk_forward_alloc)
 		goto reserve;
 
@@ -1587,7 +1590,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
 		return -EOPNOTSUPP;
 
-	mptcp_lock_sock(sk, __mptcp_wmem_reserve(sk, len));
+	mptcp_lock_sock(sk, __mptcp_wmem_reserve(sk, min_t(size_t, 1 << 20, len)));
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
@@ -2639,11 +2642,17 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
 
 static int mptcp_disconnect(struct sock *sk, int flags)
 {
-	/* Should never be called.
-	 * inet_stream_connect() calls ->disconnect, but that
-	 * refers to the subflow socket, not the mptcp one.
-	 */
-	WARN_ON_ONCE(1);
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	__mptcp_flush_join_list(msk);
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		lock_sock(ssk);
+		tcp_disconnect(ssk, flags);
+		release_sock(ssk);
+	}
 	return 0;
 }
 
@@ -3086,6 +3095,14 @@ bool mptcp_finish_join(struct sock *ssk)
 	return true;
 }
 
+static void mptcp_shutdown(struct sock *sk, int how)
+{
+	pr_debug("sk=%p, how=%d", sk, how);
+
+	if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
+		__mptcp_wr_shutdown(sk);
+}
+
 static struct proto mptcp_prot = {
 	.name		= "MPTCP",
 	.owner		= THIS_MODULE,
@@ -3095,7 +3112,7 @@ static struct proto mptcp_prot = {
 	.accept		= mptcp_accept,
 	.setsockopt	= mptcp_setsockopt,
 	.getsockopt	= mptcp_getsockopt,
-	.shutdown	= tcp_shutdown,
+	.shutdown	= mptcp_shutdown,
 	.destroy	= mptcp_destroy,
 	.sendmsg	= mptcp_sendmsg,
 	.recvmsg	= mptcp_recvmsg,
@@ -3341,43 +3358,6 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	return mask;
 }
 
-static int mptcp_shutdown(struct socket *sock, int how)
-{
-	struct mptcp_sock *msk = mptcp_sk(sock->sk);
-	struct sock *sk = sock->sk;
-	int ret = 0;
-
-	pr_debug("sk=%p, how=%d", msk, how);
-
-	lock_sock(sk);
-
-	how++;
-	if ((how & ~SHUTDOWN_MASK) || !how) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
-	if (sock->state == SS_CONNECTING) {
-		if ((1 << sk->sk_state) &
-		    (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
-			sock->state = SS_DISCONNECTING;
-		else
-			sock->state = SS_CONNECTED;
-	}
-
-	sk->sk_shutdown |= how;
-	if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
-		__mptcp_wr_shutdown(sk);
-
-	/* Wake up anyone sleeping in poll. */
-	sk->sk_state_change(sk);
-
-out_unlock:
-	release_sock(sk);
-
-	return ret;
-}
-
 static const struct proto_ops mptcp_stream_ops = {
 	.family		   = PF_INET,
 	.owner		   = THIS_MODULE,
@@ -3391,7 +3371,7 @@ static const struct proto_ops mptcp_stream_ops = {
 	.ioctl		   = inet_ioctl,
 	.gettstamp	   = sock_gettstamp,
 	.listen		   = mptcp_listen,
-	.shutdown	   = mptcp_shutdown,
+	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
 	.getsockopt	   = sock_common_getsockopt,
 	.sendmsg	   = inet_sendmsg,
@@ -3441,7 +3421,7 @@ static const struct proto_ops mptcp_v6_stream_ops = {
 	.ioctl		   = inet6_ioctl,
 	.gettstamp	   = sock_gettstamp,
 	.listen		   = mptcp_listen,
-	.shutdown	   = mptcp_shutdown,
+	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
 	.getsockopt	   = sock_common_getsockopt,
 	.sendmsg	   = inet6_sendmsg,
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 5b1f4ec66dd9..888ccc2d4e34 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -1120,7 +1120,7 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev,
 	int payload, i, ret;
 
 	/* Find the NCSI device */
-	nd = ncsi_find_dev(dev);
+	nd = ncsi_find_dev(orig_dev);
 	ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL;
 	if (!ndp)
 		return -ENODEV;
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 5f1208ad049e..6186358eac7c 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -141,20 +141,6 @@ htable_size(u8 hbits)
 	return hsize * sizeof(struct hbucket *) + sizeof(struct htable);
 }
 
-/* Compute htable_bits from the user input parameter hashsize */
-static u8
-htable_bits(u32 hashsize)
-{
-	/* Assume that hashsize == 2^htable_bits */
-	u8 bits = fls(hashsize - 1);
-
-	if (jhash_size(bits) != hashsize)
-		/* Round up to the first 2^n value */
-		bits = fls(hashsize);
-
-	return bits;
-}
-
 #ifdef IP_SET_HASH_WITH_NETS
 #if IPSET_NET_COUNT > 1
 #define __CIDR(cidr, i)		(cidr[i])
@@ -640,7 +626,7 @@ mtype_resize(struct ip_set *set, bool retried)
 	struct htype *h = set->data;
 	struct htable *t, *orig;
 	u8 htable_bits;
-	size_t dsize = set->dsize;
+	size_t hsize, dsize = set->dsize;
 #ifdef IP_SET_HASH_WITH_NETS
 	u8 flags;
 	struct mtype_elem *tmp;
@@ -664,14 +650,12 @@ mtype_resize(struct ip_set *set, bool retried)
 retry:
 	ret = 0;
 	htable_bits++;
-	if (!htable_bits) {
-		/* In case we have plenty of memory :-) */
-		pr_warn("Cannot increase the hashsize of set %s further\n",
-			set->name);
-		ret = -IPSET_ERR_HASH_FULL;
-		goto out;
-	}
-	t = ip_set_alloc(htable_size(htable_bits));
+	if (!htable_bits)
+		goto hbwarn;
+	hsize = htable_size(htable_bits);
+	if (!hsize)
+		goto hbwarn;
+	t = ip_set_alloc(hsize);
 	if (!t) {
 		ret = -ENOMEM;
 		goto out;
@@ -813,6 +797,12 @@ cleanup:
 	if (ret == -EAGAIN)
 		goto retry;
 	goto out;
+
+hbwarn:
+	/* In case we have plenty of memory :-) */
+	pr_warn("Cannot increase the hashsize of set %s further\n", set->name);
+	ret = -IPSET_ERR_HASH_FULL;
+	goto out;
 }
 
 /* Get the current number of elements and ext_size in the set  */
@@ -1521,7 +1511,11 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 	if (!h)
 		return -ENOMEM;
 
-	hbits = htable_bits(hashsize);
+	/* Compute htable_bits from the user input parameter hashsize.
+	 * Assume that hashsize == 2^htable_bits,
+	 * otherwise round up to the first 2^n value.
+	 */
+	hbits = fls(hashsize - 1);
 	hsize = htable_size(hbits);
 	if (hsize == 0) {
 		kfree(h);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 46c5557c1fec..0ee702d374b0 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -523,6 +523,9 @@ nf_conntrack_hash_sysctl(struct ctl_table *table, int write,
 {
 	int ret;
 
+	/* module_param hashsize could have changed value */
+	nf_conntrack_htable_size_user = nf_conntrack_htable_size;
+
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 	if (ret < 0 || !write)
 		return ret;
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index ea923f8cf9c4..b7c3c902290f 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -1174,6 +1174,7 @@ static int __init nf_nat_init(void)
 	ret = register_pernet_subsys(&nat_net_ops);
 	if (ret < 0) {
 		nf_ct_extend_unregister(&nat_extend);
+		kvfree(nf_nat_bysource);
 		return ret;
 	}
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 8d5aa0ac45f4..15c467f1a9dd 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4162,7 +4162,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 		if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT |
 			      NFT_SET_INTERVAL | NFT_SET_TIMEOUT |
 			      NFT_SET_MAP | NFT_SET_EVAL |
-			      NFT_SET_OBJECT | NFT_SET_CONCAT))
+			      NFT_SET_OBJECT | NFT_SET_CONCAT | NFT_SET_EXPR))
 			return -EOPNOTSUPP;
 		/* Only one of these operations is supported */
 		if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) ==
@@ -4304,6 +4304,10 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 		struct nlattr *tmp;
 		int left;
 
+		if (!(flags & NFT_SET_EXPR)) {
+			err = -EINVAL;
+			goto err_set_alloc_name;
+		}
 		i = 0;
 		nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
 			if (i == NFT_SET_EXPR_MAX) {
@@ -5254,8 +5258,8 @@ static int nft_set_elem_expr_clone(const struct nft_ctx *ctx,
 	return 0;
 
 err_expr:
-	for (k = i - 1; k >= 0; k++)
-		nft_expr_destroy(ctx, expr_array[i]);
+	for (k = i - 1; k >= 0; k--)
+		nft_expr_destroy(ctx, expr_array[k]);
 
 	return -ENOMEM;
 }
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 983a1d5ca3ab..0b053f75cd60 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -19,6 +19,7 @@ struct nft_dynset {
 	enum nft_registers		sreg_key:8;
 	enum nft_registers		sreg_data:8;
 	bool				invert;
+	bool				expr;
 	u8				num_exprs;
 	u64				timeout;
 	struct nft_expr			*expr_array[NFT_SET_EXPR_MAX];
@@ -175,11 +176,12 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 
 	if (tb[NFTA_DYNSET_FLAGS]) {
 		u32 flags = ntohl(nla_get_be32(tb[NFTA_DYNSET_FLAGS]));
-
-		if (flags & ~NFT_DYNSET_F_INV)
-			return -EINVAL;
+		if (flags & ~(NFT_DYNSET_F_INV | NFT_DYNSET_F_EXPR))
+			return -EOPNOTSUPP;
 		if (flags & NFT_DYNSET_F_INV)
 			priv->invert = true;
+		if (flags & NFT_DYNSET_F_EXPR)
+			priv->expr = true;
 	}
 
 	set = nft_set_lookup_global(ctx->net, ctx->table,
@@ -210,7 +212,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 	timeout = 0;
 	if (tb[NFTA_DYNSET_TIMEOUT] != NULL) {
 		if (!(set->flags & NFT_SET_TIMEOUT))
-			return -EINVAL;
+			return -EOPNOTSUPP;
 
 		err = nf_msecs_to_jiffies64(tb[NFTA_DYNSET_TIMEOUT], &timeout);
 		if (err)
@@ -224,7 +226,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 
 	if (tb[NFTA_DYNSET_SREG_DATA] != NULL) {
 		if (!(set->flags & NFT_SET_MAP))
-			return -EINVAL;
+			return -EOPNOTSUPP;
 		if (set->dtype == NFT_DATA_VERDICT)
 			return -EOPNOTSUPP;
 
@@ -261,6 +263,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 		struct nlattr *tmp;
 		int left;
 
+		if (!priv->expr)
+			return -EINVAL;
+
 		i = 0;
 		nla_for_each_nested(tmp, tb[NFTA_DYNSET_EXPRESSIONS], left) {
 			if (i == NFT_SET_EXPR_MAX) {
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 37253d399c6b..0d5c422f8745 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -115,6 +115,9 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
 	} cfg;
 	int ret;
 
+	if (strnlen(info->name, sizeof(est->name)) >= sizeof(est->name))
+		return -ENAMETOOLONG;
+
 	net_get_random_once(&jhash_rnd, sizeof(jhash_rnd));
 
 	mutex_lock(&xn->hash_lock);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index de8e8dbbdeb8..6bbc7a448593 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4595,7 +4595,9 @@ static void packet_seq_stop(struct seq_file *seq, void *v)
 static int packet_seq_show(struct seq_file *seq, void *v)
 {
 	if (v == SEQ_START_TOKEN)
-		seq_puts(seq, "sk       RefCnt Type Proto  Iface R Rmem   User   Inode\n");
+		seq_printf(seq,
+			   "%*sRefCnt Type Proto  Iface R Rmem   User   Inode\n",
+			   IS_ENABLED(CONFIG_64BIT) ? -17 : -9, "sk");
 	else {
 		struct sock *s = sk_entry(v);
 		const struct packet_sock *po = pkt_sk(s);
diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c
index 56aaf8cb6527..8d00dfe8139e 100644
--- a/net/qrtr/ns.c
+++ b/net/qrtr/ns.c
@@ -755,7 +755,7 @@ static void qrtr_ns_data_ready(struct sock *sk)
 	queue_work(qrtr_ns.workqueue, &qrtr_ns.work);
 }
 
-void qrtr_ns_init(void)
+int qrtr_ns_init(void)
 {
 	struct sockaddr_qrtr sq;
 	int ret;
@@ -766,7 +766,7 @@ void qrtr_ns_init(void)
 	ret = sock_create_kern(&init_net, AF_QIPCRTR, SOCK_DGRAM,
 			       PF_QIPCRTR, &qrtr_ns.sock);
 	if (ret < 0)
-		return;
+		return ret;
 
 	ret = kernel_getsockname(qrtr_ns.sock, (struct sockaddr *)&sq);
 	if (ret < 0) {
@@ -797,12 +797,13 @@ void qrtr_ns_init(void)
 	if (ret < 0)
 		goto err_wq;
 
-	return;
+	return 0;
 
 err_wq:
 	destroy_workqueue(qrtr_ns.workqueue);
 err_sock:
 	sock_release(qrtr_ns.sock);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(qrtr_ns_init);
 
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index f4ab3ca6d73b..b34358282f37 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -1287,13 +1287,19 @@ static int __init qrtr_proto_init(void)
 		return rc;
 
 	rc = sock_register(&qrtr_family);
-	if (rc) {
-		proto_unregister(&qrtr_proto);
-		return rc;
-	}
+	if (rc)
+		goto err_proto;
 
-	qrtr_ns_init();
+	rc = qrtr_ns_init();
+	if (rc)
+		goto err_sock;
 
+	return 0;
+
+err_sock:
+	sock_unregister(qrtr_family.family);
+err_proto:
+	proto_unregister(&qrtr_proto);
 	return rc;
 }
 postcore_initcall(qrtr_proto_init);
diff --git a/net/qrtr/qrtr.h b/net/qrtr/qrtr.h
index dc2b67f17927..3f2d28696062 100644
--- a/net/qrtr/qrtr.h
+++ b/net/qrtr/qrtr.h
@@ -29,7 +29,7 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep);
 
 int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len);
 
-void qrtr_ns_init(void);
+int qrtr_ns_init(void);
 
 void qrtr_ns_remove(void);
 
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 667c44aa5a63..dc201363f2c4 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -430,7 +430,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 		return;
 	}
 
-	if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST) {
+	if (state == RXRPC_CALL_SERVER_RECV_REQUEST) {
 		unsigned long timo = READ_ONCE(call->next_req_timo);
 		unsigned long now, expect_req_by;
 
diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 9631aa8543b5..8d2073e0e3da 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -598,7 +598,7 @@ static long rxrpc_read(const struct key *key,
 		default: /* we have a ticket we can't encode */
 			pr_err("Unsupported key token type (%u)\n",
 			       token->security_index);
-			continue;
+			return -ENOPKG;
 		}
 
 		_debug("token[%u]: toksize=%u", ntoks, toksize);
@@ -674,7 +674,9 @@ static long rxrpc_read(const struct key *key,
 			break;
 
 		default:
-			break;
+			pr_err("Unsupported key token type (%u)\n",
+			       token->security_index);
+			return -ENOPKG;
 		}
 
 		ASSERTCMP((unsigned long)xdr - (unsigned long)oldxdr, ==,
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index bd618b00d319..50f680f03a54 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -362,7 +362,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt,
 
 	ctl = nla_data(tb[TCA_CHOKE_PARMS]);
 
-	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog))
+	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log))
 		return -EINVAL;
 
 	if (ctl->limit > CHOKE_MAX_QUEUE)
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 8599c6f31b05..e0bc77533acc 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -480,7 +480,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp,
 	struct gred_sched *table = qdisc_priv(sch);
 	struct gred_sched_data *q = table->tab[dp];
 
-	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) {
+	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) {
 		NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters");
 		return -EINVAL;
 	}
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index e89fab6ccb34..b4ae34d7aa96 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -250,7 +250,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb,
 	max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0;
 
 	ctl = nla_data(tb[TCA_RED_PARMS]);
-	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog))
+	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log))
 		return -EINVAL;
 
 	err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS,
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index bca2be57d9fc..b25e51440623 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -647,7 +647,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	}
 
 	if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max,
-					ctl_v1->Wlog))
+					ctl_v1->Wlog, ctl_v1->Scell_log))
 		return -EINVAL;
 	if (ctl_v1 && ctl_v1->qth_min) {
 		p = kmalloc(sizeof(*p), GFP_KERNEL);
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index c74817ec9964..6f775275826a 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1605,8 +1605,9 @@ static void taprio_reset(struct Qdisc *sch)
 
 	hrtimer_cancel(&q->advance_timer);
 	if (q->qdiscs) {
-		for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++)
-			qdisc_reset(q->qdiscs[i]);
+		for (i = 0; i < dev->num_tx_queues; i++)
+			if (q->qdiscs[i])
+				qdisc_reset(q->qdiscs[i]);
 	}
 	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
@@ -1626,7 +1627,7 @@ static void taprio_destroy(struct Qdisc *sch)
 	taprio_disable_offload(dev, q, NULL);
 
 	if (q->qdiscs) {
-		for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++)
+		for (i = 0; i < dev->num_tx_queues; i++)
 			qdisc_put(q->qdiscs[i]);
 
 		kfree(q->qdiscs);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 59342b519e34..0df85a12651e 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -246,7 +246,8 @@ int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb)
 		goto errattr;
 	smc_clc_get_hostname(&host);
 	if (host) {
-		snprintf(hostname, sizeof(hostname), "%s", host);
+		memcpy(hostname, host, SMC_MAX_HOSTNAME_LEN);
+		hostname[SMC_MAX_HOSTNAME_LEN] = 0;
 		if (nla_put_string(skb, SMC_NLA_SYS_LOCAL_HOST, hostname))
 			goto errattr;
 	}
@@ -257,7 +258,8 @@ int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb)
 		smc_ism_get_system_eid(smcd_dev, &seid);
 	mutex_unlock(&smcd_dev_list.mutex);
 	if (seid && smc_ism_is_v2_capable()) {
-		snprintf(smc_seid, sizeof(smc_seid), "%s", seid);
+		memcpy(smc_seid, seid, SMC_MAX_EID_LEN);
+		smc_seid[SMC_MAX_EID_LEN] = 0;
 		if (nla_put_string(skb, SMC_NLA_SYS_SEID, smc_seid))
 			goto errattr;
 	}
@@ -295,7 +297,8 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr,
 		goto errattr;
 	if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id))
 		goto errattr;
-	snprintf(smc_target, sizeof(smc_target), "%s", lgr->pnet_id);
+	memcpy(smc_target, lgr->pnet_id, SMC_MAX_PNETID_LEN);
+	smc_target[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target))
 		goto errattr;
 
@@ -312,7 +315,7 @@ static int smc_nl_fill_lgr_link(struct smc_link_group *lgr,
 				struct sk_buff *skb,
 				struct netlink_callback *cb)
 {
-	char smc_ibname[IB_DEVICE_NAME_MAX + 1];
+	char smc_ibname[IB_DEVICE_NAME_MAX];
 	u8 smc_gid_target[41];
 	struct nlattr *attrs;
 	u32 link_uid = 0;
@@ -461,7 +464,8 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
 		goto errattr;
 	if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd)))
 		goto errattr;
-	snprintf(smc_pnet, sizeof(smc_pnet), "%s", lgr->smcd->pnetid);
+	memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN);
+	smc_pnet[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet))
 		goto errattr;
 
@@ -474,10 +478,12 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
 		goto errv2attr;
 	if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os))
 		goto errv2attr;
-	snprintf(smc_host, sizeof(smc_host), "%s", lgr->peer_hostname);
+	memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN);
+	smc_host[SMC_MAX_HOSTNAME_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host))
 		goto errv2attr;
-	snprintf(smc_eid, sizeof(smc_eid), "%s", lgr->negotiated_eid);
+	memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN);
+	smc_eid[SMC_MAX_EID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid))
 		goto errv2attr;
 
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index ddd7fac98b1d..7d7ba0320d5a 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -371,8 +371,8 @@ static int smc_nl_handle_dev_port(struct sk_buff *skb,
 	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR,
 		       smcibdev->pnetid_by_user[port]))
 		goto errattr;
-	snprintf(smc_pnet, sizeof(smc_pnet), "%s",
-		 (char *)&smcibdev->pnetid[port]);
+	memcpy(smc_pnet, &smcibdev->pnetid[port], SMC_MAX_PNETID_LEN);
+	smc_pnet[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
 		goto errattr;
 	if (nla_put_u32(skb, SMC_NLA_DEV_PORT_NETDEV,
@@ -414,7 +414,7 @@ static int smc_nl_handle_smcr_dev(struct smc_ib_device *smcibdev,
 				  struct sk_buff *skb,
 				  struct netlink_callback *cb)
 {
-	char smc_ibname[IB_DEVICE_NAME_MAX + 1];
+	char smc_ibname[IB_DEVICE_NAME_MAX];
 	struct smc_pci_dev smc_pci_dev;
 	struct pci_dev *pci_dev;
 	unsigned char is_crit;
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 524ef64a191a..9c6e95882553 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -250,7 +250,8 @@ static int smc_nl_handle_smcd_dev(struct smcd_dev *smcd,
 		goto errattr;
 	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR, smcd->pnetid_by_user))
 		goto errportattr;
-	snprintf(smc_pnet, sizeof(smc_pnet), "%s", smcd->pnetid);
+	memcpy(smc_pnet, smcd->pnetid, SMC_MAX_PNETID_LEN);
+	smc_pnet[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
 		goto errportattr;
 
diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c
index 010dcb876f9d..6e4dbd577a39 100644
--- a/net/sunrpc/addr.c
+++ b/net/sunrpc/addr.c
@@ -185,7 +185,7 @@ static int rpc_parse_scope_id(struct net *net, const char *buf,
 			scope_id = dev->ifindex;
 			dev_put(dev);
 		} else {
-			if (kstrtou32(p, 10, &scope_id) == 0) {
+			if (kstrtou32(p, 10, &scope_id) != 0) {
 				kfree(p);
 				return 0;
 			}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index b248f2349437..c9766d07eb81 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1062,6 +1062,90 @@ err_noclose:
 	return 0;	/* record not complete */
 }
 
+static int svc_tcp_send_kvec(struct socket *sock, const struct kvec *vec,
+			      int flags)
+{
+	return kernel_sendpage(sock, virt_to_page(vec->iov_base),
+			       offset_in_page(vec->iov_base),
+			       vec->iov_len, flags);
+}
+
+/*
+ * kernel_sendpage() is used exclusively to reduce the number of
+ * copy operations in this path. Therefore the caller must ensure
+ * that the pages backing @xdr are unchanging.
+ *
+ * In addition, the logic assumes that * .bv_len is never larger
+ * than PAGE_SIZE.
+ */
+static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg,
+			   struct xdr_buf *xdr, rpc_fraghdr marker,
+			   unsigned int *sentp)
+{
+	const struct kvec *head = xdr->head;
+	const struct kvec *tail = xdr->tail;
+	struct kvec rm = {
+		.iov_base	= &marker,
+		.iov_len	= sizeof(marker),
+	};
+	int flags, ret;
+
+	*sentp = 0;
+	xdr_alloc_bvec(xdr, GFP_KERNEL);
+
+	msg->msg_flags = MSG_MORE;
+	ret = kernel_sendmsg(sock, msg, &rm, 1, rm.iov_len);
+	if (ret < 0)
+		return ret;
+	*sentp += ret;
+	if (ret != rm.iov_len)
+		return -EAGAIN;
+
+	flags = head->iov_len < xdr->len ? MSG_MORE | MSG_SENDPAGE_NOTLAST : 0;
+	ret = svc_tcp_send_kvec(sock, head, flags);
+	if (ret < 0)
+		return ret;
+	*sentp += ret;
+	if (ret != head->iov_len)
+		goto out;
+
+	if (xdr->page_len) {
+		unsigned int offset, len, remaining;
+		struct bio_vec *bvec;
+
+		bvec = xdr->bvec;
+		offset = xdr->page_base;
+		remaining = xdr->page_len;
+		flags = MSG_MORE | MSG_SENDPAGE_NOTLAST;
+		while (remaining > 0) {
+			if (remaining <= PAGE_SIZE && tail->iov_len == 0)
+				flags = 0;
+			len = min(remaining, bvec->bv_len);
+			ret = kernel_sendpage(sock, bvec->bv_page,
+					      bvec->bv_offset + offset,
+					      len, flags);
+			if (ret < 0)
+				return ret;
+			*sentp += ret;
+			if (ret != len)
+				goto out;
+			remaining -= len;
+			offset = 0;
+			bvec++;
+		}
+	}
+
+	if (tail->iov_len) {
+		ret = svc_tcp_send_kvec(sock, tail, 0);
+		if (ret < 0)
+			return ret;
+		*sentp += ret;
+	}
+
+out:
+	return 0;
+}
+
 /**
  * svc_tcp_sendto - Send out a reply on a TCP socket
  * @rqstp: completed svc_rqst
@@ -1089,7 +1173,7 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
 	mutex_lock(&xprt->xpt_mutex);
 	if (svc_xprt_is_dead(xprt))
 		goto out_notconn;
-	err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, marker, &sent);
+	err = svc_tcp_sendmsg(svsk->sk_sock, &msg, xdr, marker, &sent);
 	xdr_free_bvec(xdr);
 	trace_svcsock_tcp_send(xprt, err < 0 ? err : sent);
 	if (err < 0 || sent != (xdr->len + sizeof(marker)))
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 6ae2140eb4f7..115109259430 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1030,7 +1030,6 @@ void tipc_link_reset(struct tipc_link *l)
 int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 		   struct sk_buff_head *xmitq)
 {
-	struct tipc_msg *hdr = buf_msg(skb_peek(list));
 	struct sk_buff_head *backlogq = &l->backlogq;
 	struct sk_buff_head *transmq = &l->transmq;
 	struct sk_buff *skb, *_skb;
@@ -1038,13 +1037,18 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 	u16 ack = l->rcv_nxt - 1;
 	u16 seqno = l->snd_nxt;
 	int pkt_cnt = skb_queue_len(list);
-	int imp = msg_importance(hdr);
 	unsigned int mss = tipc_link_mss(l);
 	unsigned int cwin = l->window;
 	unsigned int mtu = l->mtu;
+	struct tipc_msg *hdr;
 	bool new_bundle;
 	int rc = 0;
+	int imp;
+
+	if (pkt_cnt <= 0)
+		return 0;
 
+	hdr = buf_msg(skb_peek(list));
 	if (unlikely(msg_size(hdr) > mtu)) {
 		pr_warn("Too large msg, purging xmit list %d %d %d %d %d!\n",
 			skb_queue_len(list), msg_user(hdr),
@@ -1053,6 +1057,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 		return -EMSGSIZE;
 	}
 
+	imp = msg_importance(hdr);
 	/* Allow oversubscription of one data msg per source at congestion */
 	if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) {
 		if (imp == TIPC_SYSTEM_IMPORTANCE) {
@@ -2539,7 +2544,7 @@ void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win)
 }
 
 /**
- * link_reset_stats - reset link statistics
+ * tipc_link_reset_stats - reset link statistics
  * @l: pointer to link
  */
 void tipc_link_reset_stats(struct tipc_link *l)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 83d9eb830592..008670d1f43e 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1665,7 +1665,7 @@ static void tipc_lxc_xmit(struct net *peer_net, struct sk_buff_head *list)
 }
 
 /**
- * tipc_node_xmit() is the general link level function for message sending
+ * tipc_node_xmit() - general link level function for message sending
  * @net: the applicable net namespace
  * @list: chain of buffers containing message
  * @dnode: address of destination node
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index 27026f587fa6..f620acd2a0f5 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -21,6 +21,7 @@ config CFG80211
 	tristate "cfg80211 - wireless configuration API"
 	depends on RFKILL || !RFKILL
 	select FW_LOADER
+	select CRC32
 	# may need to update this when certificates are changed and are
 	# using a different algorithm, though right now they shouldn't
 	# (this is here rather than below to allow it to be a module)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index ac4a317038f1..8037b04a9edd 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -423,9 +423,9 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 	struct xdp_sock *xs = xdp_sk(skb->sk);
 	unsigned long flags;
 
-	spin_lock_irqsave(&xs->tx_completion_lock, flags);
+	spin_lock_irqsave(&xs->pool->cq_lock, flags);
 	xskq_prod_submit_addr(xs->pool->cq, addr);
-	spin_unlock_irqrestore(&xs->tx_completion_lock, flags);
+	spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 
 	sock_wfree(skb);
 }
@@ -437,6 +437,7 @@ static int xsk_generic_xmit(struct sock *sk)
 	bool sent_frame = false;
 	struct xdp_desc desc;
 	struct sk_buff *skb;
+	unsigned long flags;
 	int err = 0;
 
 	mutex_lock(&xs->mutex);
@@ -468,10 +469,13 @@ static int xsk_generic_xmit(struct sock *sk)
 		 * if there is space in it. This avoids having to implement
 		 * any buffering in the Tx path.
 		 */
+		spin_lock_irqsave(&xs->pool->cq_lock, flags);
 		if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {
+			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 			kfree_skb(skb);
 			goto out;
 		}
+		spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 
 		skb->dev = xs->dev;
 		skb->priority = sk->sk_priority;
@@ -483,6 +487,9 @@ static int xsk_generic_xmit(struct sock *sk)
 		if  (err == NETDEV_TX_BUSY) {
 			/* Tell user-space to retry the send */
 			skb->destructor = sock_wfree;
+			spin_lock_irqsave(&xs->pool->cq_lock, flags);
+			xskq_prod_cancel(xs->pool->cq);
+			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 			/* Free skb without triggering the perf drop trace */
 			consume_skb(skb);
 			err = -EAGAIN;
@@ -878,6 +885,10 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		}
 	}
 
+	/* FQ and CQ are now owned by the buffer pool and cleaned up with it. */
+	xs->fq_tmp = NULL;
+	xs->cq_tmp = NULL;
+
 	xs->dev = dev;
 	xs->zc = xs->umem->zc;
 	xs->queue_id = qid;
@@ -1299,7 +1310,6 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 	xs->state = XSK_READY;
 	mutex_init(&xs->mutex);
 	spin_lock_init(&xs->rx_lock);
-	spin_lock_init(&xs->tx_completion_lock);
 
 	INIT_LIST_HEAD(&xs->map_list);
 	spin_lock_init(&xs->map_list_lock);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 67a4494d63b6..20598eea658c 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -71,12 +71,11 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	INIT_LIST_HEAD(&pool->free_list);
 	INIT_LIST_HEAD(&pool->xsk_tx_list);
 	spin_lock_init(&pool->xsk_tx_list_lock);
+	spin_lock_init(&pool->cq_lock);
 	refcount_set(&pool->users, 1);
 
 	pool->fq = xs->fq_tmp;
 	pool->cq = xs->cq_tmp;
-	xs->fq_tmp = NULL;
-	xs->cq_tmp = NULL;
 
 	for (i = 0; i < pool->free_heads_cnt; i++) {
 		xskb = &pool->heads[i];
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 4a9663aa7afe..2823b7c3302d 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -334,6 +334,11 @@ static inline bool xskq_prod_is_full(struct xsk_queue *q)
 	return xskq_prod_nb_free(q, 1) ? false : true;
 }
 
+static inline void xskq_prod_cancel(struct xsk_queue *q)
+{
+	q->cached_prod--;
+}
+
 static inline int xskq_prod_reserve(struct xsk_queue *q)
 {
 	if (xskq_prod_is_full(q))
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index 6baee1200615..d53825503874 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -61,7 +61,6 @@ endif
 ifneq ($(findstring 2, $(KBUILD_EXTRA_WARN)),)
 
 KBUILD_CFLAGS += -Wdisabled-optimization
-KBUILD_CFLAGS += -Wnested-externs
 KBUILD_CFLAGS += -Wshadow
 KBUILD_CFLAGS += $(call cc-option, -Wlogical-op)
 KBUILD_CFLAGS += -Wmissing-field-initializers
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 94133708889d..213677a5ed33 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -148,10 +148,12 @@ endif
 # we don't want to check (depends on variables KASAN_SANITIZE_obj.o, KASAN_SANITIZE)
 #
 ifeq ($(CONFIG_KASAN),y)
+ifneq ($(CONFIG_KASAN_HW_TAGS),y)
 _c_flags += $(if $(patsubst n%,, \
 		$(KASAN_SANITIZE_$(basetarget).o)$(KASAN_SANITIZE)y), \
 		$(CFLAGS_KASAN), $(CFLAGS_KASAN_NOSANITIZE))
 endif
+endif
 
 ifeq ($(CONFIG_UBSAN),y)
 _c_flags += $(if $(patsubst n%,, \
diff --git a/scripts/bloat-o-meter b/scripts/bloat-o-meter
index d7ca46c612b3..652e9542043f 100755
--- a/scripts/bloat-o-meter
+++ b/scripts/bloat-o-meter
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 #
 # Copyright 2004 Matt Mackall <mpm@selenic.com>
 #
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 00085308ed9d..92e888ed939f 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -6646,6 +6646,12 @@ sub process {
 #			}
 #		}
 
+# strlcpy uses that should likely be strscpy
+		if ($line =~ /\bstrlcpy\s*\(/) {
+			WARN("STRLCPY",
+			     "Prefer strscpy over strlcpy - see: https://lore.kernel.org/r/CAHk-=wgfRnXz0W3D37d01q3JFkr_i_uTL=V6A6G1oUZcprmknw\@mail.gmail.com/\n" . $herecurr);
+		}
+
 # typecasts on min/max could be min_t/max_t
 		if ($perl_version_ok &&
 		    defined $stat &&
diff --git a/scripts/coccicheck b/scripts/coccicheck
index 209bb0427b43..65fee63aeadb 100755
--- a/scripts/coccicheck
+++ b/scripts/coccicheck
@@ -16,7 +16,6 @@ if [ ! -x "$SPATCH" ]; then
 fi
 
 SPATCH_VERSION=$($SPATCH --version | head -1 | awk '{print $3}')
-SPATCH_VERSION_NUM=$(echo $SPATCH_VERSION | ${DIR}/scripts/ld-version.sh)
 
 USE_JOBS="no"
 $SPATCH --help | grep "\-\-jobs" > /dev/null && USE_JOBS="yes"
@@ -61,6 +60,18 @@ COCCIINCLUDE=${COCCIINCLUDE// -include/ --include}
 if [ "$C" = "1" -o "$C" = "2" ]; then
     ONLINE=1
 
+    if [[ $# -le 0 ]]; then
+	    echo ''
+	    echo 'Specifying both the variable "C" and rule "coccicheck" in the make
+command results in a shift count error.'
+	    echo ''
+	    echo 'Try specifying "scripts/coccicheck" as a value for the CHECK variable instead.'
+	    echo ''
+	    echo 'Example:	make C=2 CHECK=scripts/coccicheck drivers/net/ethernet/ethoc.o'
+	    echo ''
+	    exit 1
+    fi
+
     # Take only the last argument, which is the C file to test
     shift $(( $# - 1 ))
     OPTIONS="$COCCIINCLUDE $1"
@@ -186,14 +197,11 @@ coccinelle () {
 
     OPT=`grep "Options:" $COCCI | cut -d':' -f2`
     REQ=`grep "Requires:" $COCCI | cut -d':' -f2 | sed "s| ||"`
-    REQ_NUM=$(echo $REQ | ${DIR}/scripts/ld-version.sh)
-    if [ "$REQ_NUM" != "0" ] ; then
-	    if [ "$SPATCH_VERSION_NUM" -lt "$REQ_NUM" ] ; then
-		    echo "Skipping coccinelle SmPL patch: $COCCI"
-		    echo "You have coccinelle:           $SPATCH_VERSION"
-		    echo "This SmPL patch requires:      $REQ"
-		    return
-	    fi
+    if [ -n "$REQ" ] && ! { echo "$REQ"; echo "$SPATCH_VERSION"; } | sort -CV ; then
+	    echo "Skipping coccinelle SmPL patch: $COCCI"
+	    echo "You have coccinelle:           $SPATCH_VERSION"
+	    echo "This SmPL patch requires:      $REQ"
+	    return
     fi
 
 #   The option '--parse-cocci' can be used to syntactically check the SmPL files.
diff --git a/scripts/coccinelle/api/ptr_ret.cocci b/scripts/coccinelle/api/ptr_ret.cocci
deleted file mode 100644
index e76cd5d90a8a..000000000000
--- a/scripts/coccinelle/api/ptr_ret.cocci
+++ /dev/null
@@ -1,97 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-///
-/// Use PTR_ERR_OR_ZERO rather than if(IS_ERR(...)) + PTR_ERR
-///
-// Confidence: High
-// Copyright: (C) 2012 Julia Lawall, INRIA/LIP6.
-// Copyright: (C) 2012 Gilles Muller, INRIA/LiP6.
-// URL: http://coccinelle.lip6.fr/
-// Options: --no-includes --include-headers
-//
-// Keywords: ERR_PTR, PTR_ERR, PTR_ERR_OR_ZERO
-// Version min: 2.6.39
-//
-
-virtual context
-virtual patch
-virtual org
-virtual report
-
-@depends on patch@
-expression ptr;
-@@
-
-- if (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0;
-+ return PTR_ERR_OR_ZERO(ptr);
-
-@depends on patch@
-expression ptr;
-@@
-
-- if (IS_ERR(ptr)) return PTR_ERR(ptr); return 0;
-+ return PTR_ERR_OR_ZERO(ptr);
-
-@depends on patch@
-expression ptr;
-@@
-
-- (IS_ERR(ptr) ? PTR_ERR(ptr) : 0)
-+ PTR_ERR_OR_ZERO(ptr)
-
-@r1 depends on !patch@
-expression ptr;
-position p1;
-@@
-
-* if@p1 (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0;
-
-@r2 depends on !patch@
-expression ptr;
-position p2;
-@@
-
-* if@p2 (IS_ERR(ptr)) return PTR_ERR(ptr); return 0;
-
-@r3 depends on !patch@
-expression ptr;
-position p3;
-@@
-
-* IS_ERR@p3(ptr) ? PTR_ERR(ptr) : 0
-
-@script:python depends on org@
-p << r1.p1;
-@@
-
-coccilib.org.print_todo(p[0], "WARNING: PTR_ERR_OR_ZERO can be used")
-
-
-@script:python depends on org@
-p << r2.p2;
-@@
-
-coccilib.org.print_todo(p[0], "WARNING: PTR_ERR_OR_ZERO can be used")
-
-@script:python depends on org@
-p << r3.p3;
-@@
-
-coccilib.org.print_todo(p[0], "WARNING: PTR_ERR_OR_ZERO can be used")
-
-@script:python depends on report@
-p << r1.p1;
-@@
-
-coccilib.report.print_report(p[0], "WARNING: PTR_ERR_OR_ZERO can be used")
-
-@script:python depends on report@
-p << r2.p2;
-@@
-
-coccilib.report.print_report(p[0], "WARNING: PTR_ERR_OR_ZERO can be used")
-
-@script:python depends on report@
-p << r3.p3;
-@@
-
-coccilib.report.print_report(p[0], "WARNING: PTR_ERR_OR_ZERO can be used")
diff --git a/scripts/coccinelle/misc/boolinit.cocci b/scripts/coccinelle/misc/boolinit.cocci
deleted file mode 100644
index fed6126e2b9d..000000000000
--- a/scripts/coccinelle/misc/boolinit.cocci
+++ /dev/null
@@ -1,195 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/// Bool initializations should use true and false.  Bool tests don't need
-/// comparisons.  Based on contributions from Joe Perches, Rusty Russell
-/// and Bruce W Allan.
-///
-// Confidence: High
-// Copyright: (C) 2012 Julia Lawall, INRIA/LIP6.
-// Copyright: (C) 2012 Gilles Muller, INRIA/LiP6.
-// URL: http://coccinelle.lip6.fr/
-// Options: --include-headers
-
-virtual patch
-virtual context
-virtual org
-virtual report
-
-@boolok@
-symbol true,false;
-@@
-(
-true
-|
-false
-)
-
-@depends on patch@
-bool t;
-@@
-
-(
-- t == true
-+ t
-|
-- true == t
-+ t
-|
-- t != true
-+ !t
-|
-- true != t
-+ !t
-|
-- t == false
-+ !t
-|
-- false == t
-+ !t
-|
-- t != false
-+ t
-|
-- false != t
-+ t
-)
-
-@depends on patch disable is_zero, isnt_zero@
-bool t;
-@@
-
-(
-- t == 1
-+ t
-|
-- t != 1
-+ !t
-|
-- t == 0
-+ !t
-|
-- t != 0
-+ t
-)
-
-@depends on patch && boolok@
-bool b;
-@@
-(
- b =
-- 0
-+ false
-|
- b =
-- 1
-+ true
-)
-
-// ---------------------------------------------------------------------
-
-@r1 depends on !patch@
-bool t;
-position p;
-@@
-
-(
-* t@p == true
-|
-* true == t@p
-|
-* t@p != true
-|
-* true != t@p
-|
-* t@p == false
-|
-* false == t@p
-|
-* t@p != false
-|
-* false != t@p
-)
-
-@r2 depends on !patch disable is_zero, isnt_zero@
-bool t;
-position p;
-@@
-
-(
-* t@p == 1
-|
-* t@p != 1
-|
-* t@p == 0
-|
-* t@p != 0
-)
-
-@r3 depends on !patch && boolok@
-bool b;
-position p1;
-@@
-(
-*b@p1 = 0
-|
-*b@p1 = 1
-)
-
-@r4 depends on !patch@
-bool b;
-position p2;
-identifier i;
-constant c != {0,1};
-@@
-(
- b = i
-|
-*b@p2 = c
-)
-
-@script:python depends on org@
-p << r1.p;
-@@
-
-cocci.print_main("WARNING: Comparison to bool",p)
-
-@script:python depends on org@
-p << r2.p;
-@@
-
-cocci.print_main("WARNING: Comparison of 0/1 to bool variable",p)
-
-@script:python depends on org@
-p1 << r3.p1;
-@@
-
-cocci.print_main("WARNING: Assignment of 0/1 to bool variable",p1)
-
-@script:python depends on org@
-p2 << r4.p2;
-@@
-
-cocci.print_main("ERROR: Assignment of non-0/1 constant to bool variable",p2)
-
-@script:python depends on report@
-p << r1.p;
-@@
-
-coccilib.report.print_report(p[0],"WARNING: Comparison to bool")
-
-@script:python depends on report@
-p << r2.p;
-@@
-
-coccilib.report.print_report(p[0],"WARNING: Comparison of 0/1 to bool variable")
-
-@script:python depends on report@
-p1 << r3.p1;
-@@
-
-coccilib.report.print_report(p1[0],"WARNING: Assignment of 0/1 to bool variable")
-
-@script:python depends on report@
-p2 << r4.p2;
-@@
-
-coccilib.report.print_report(p2[0],"ERROR: Assignment of non-0/1 constant to bool variable")
diff --git a/scripts/config b/scripts/config
index eee5b7f3a092..ff88e2faefd3 100755
--- a/scripts/config
+++ b/scripts/config
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/usr/bin/env bash
 # SPDX-License-Identifier: GPL-2.0
 # Manipulate options in a .config file from the command line
 
@@ -223,6 +223,7 @@ while [ "$1" != "" ] ; do
 		;;
 
 	*)
+		echo "bad command: $CMD" >&2
 		usage
 		;;
 	esac
diff --git a/scripts/depmod.sh b/scripts/depmod.sh
index e083bcae343f..3643b4f896ed 100755
--- a/scripts/depmod.sh
+++ b/scripts/depmod.sh
@@ -15,6 +15,8 @@ if ! test -r System.map ; then
 	exit 0
 fi
 
+# legacy behavior: "depmod" in /sbin, no /sbin in PATH
+PATH="$PATH:/sbin"
 if [ -z $(command -v $DEPMOD) ]; then
 	echo "Warning: 'make modules_install' requires $DEPMOD. Please install it." >&2
 	echo "This is probably in the kmod package." >&2
diff --git a/scripts/diffconfig b/scripts/diffconfig
index 89abf777f197..627eba5849b5 100755
--- a/scripts/diffconfig
+++ b/scripts/diffconfig
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 # SPDX-License-Identifier: GPL-2.0
 #
 # diffconfig - a tool to compare .config files.
diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile
index d66949bfeba4..b5487cce69e8 100644
--- a/scripts/gcc-plugins/Makefile
+++ b/scripts/gcc-plugins/Makefile
@@ -22,9 +22,9 @@ always-y += $(GCC_PLUGIN)
 GCC_PLUGINS_DIR = $(shell $(CC) -print-file-name=plugin)
 
 plugin_cxxflags	= -Wp,-MMD,$(depfile) $(KBUILD_HOSTCXXFLAGS) -fPIC \
-		   -I $(GCC_PLUGINS_DIR)/include -I $(obj) -std=gnu++98 \
+		   -I $(GCC_PLUGINS_DIR)/include -I $(obj) -std=gnu++11 \
 		   -fno-rtti -fno-exceptions -fasynchronous-unwind-tables \
-		   -ggdb -Wno-narrowing -Wno-unused-variable -Wno-c++11-compat \
+		   -ggdb -Wno-narrowing -Wno-unused-variable \
 		   -Wno-format-diag
 
 plugin_ldflags	= -shared
diff --git a/scripts/genksyms/keywords.c b/scripts/genksyms/keywords.c
index 057c6cabad1d..b85e0979a00c 100644
--- a/scripts/genksyms/keywords.c
+++ b/scripts/genksyms/keywords.c
@@ -32,6 +32,9 @@ static struct resword {
 	{ "restrict", RESTRICT_KEYW },
 	{ "asm", ASM_KEYW },
 
+	// c11 keywords that can be used at module scope
+	{ "_Static_assert", STATIC_ASSERT_KEYW },
+
 	// attribute commented out in modutils 2.4.2.  People are using 'attribute' as a
 	// field name which breaks the genksyms parser.  It is not a gcc keyword anyway.
 	// KAO. },
diff --git a/scripts/genksyms/lex.l b/scripts/genksyms/lex.l
index e265c5d96861..ae76472efc43 100644
--- a/scripts/genksyms/lex.l
+++ b/scripts/genksyms/lex.l
@@ -118,7 +118,7 @@ yylex(void)
 {
   static enum {
     ST_NOTSTARTED, ST_NORMAL, ST_ATTRIBUTE, ST_ASM, ST_TYPEOF, ST_TYPEOF_1,
-    ST_BRACKET, ST_BRACE, ST_EXPRESSION,
+    ST_BRACKET, ST_BRACE, ST_EXPRESSION, ST_STATIC_ASSERT,
     ST_TABLE_1, ST_TABLE_2, ST_TABLE_3, ST_TABLE_4,
     ST_TABLE_5, ST_TABLE_6
   } lexstate = ST_NOTSTARTED;
@@ -201,6 +201,11 @@ repeat:
 
 		  case EXPORT_SYMBOL_KEYW:
 		      goto fini;
+
+		  case STATIC_ASSERT_KEYW:
+		    lexstate = ST_STATIC_ASSERT;
+		    count = 0;
+		    goto repeat;
 		  }
 	      }
 	    if (!suppress_type_lookup)
@@ -401,6 +406,26 @@ repeat:
 	}
       break;
 
+    case ST_STATIC_ASSERT:
+      APP;
+      switch (token)
+	{
+	case '(':
+	  ++count;
+	  goto repeat;
+	case ')':
+	  if (--count == 0)
+	    {
+	      lexstate = ST_NORMAL;
+	      token = STATIC_ASSERT_PHRASE;
+	      break;
+	    }
+	  goto repeat;
+	default:
+	  goto repeat;
+	}
+      break;
+
     case ST_TABLE_1:
       goto repeat;
 
diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y
index e22b42245bcc..8e9b5e69e8f0 100644
--- a/scripts/genksyms/parse.y
+++ b/scripts/genksyms/parse.y
@@ -80,6 +80,7 @@ static void record_compound(struct string_list **keyw,
 %token SHORT_KEYW
 %token SIGNED_KEYW
 %token STATIC_KEYW
+%token STATIC_ASSERT_KEYW
 %token STRUCT_KEYW
 %token TYPEDEF_KEYW
 %token UNION_KEYW
@@ -97,6 +98,7 @@ static void record_compound(struct string_list **keyw,
 %token BRACE_PHRASE
 %token BRACKET_PHRASE
 %token EXPRESSION_PHRASE
+%token STATIC_ASSERT_PHRASE
 
 %token CHAR
 %token DOTS
@@ -130,6 +132,7 @@ declaration1:
 	| function_definition
 	| asm_definition
 	| export_definition
+	| static_assert
 	| error ';'				{ $$ = $2; }
 	| error '}'				{ $$ = $2; }
 	;
@@ -493,6 +496,10 @@ export_definition:
 		{ export_symbol((*$3)->string); $$ = $5; }
 	;
 
+/* Ignore any module scoped _Static_assert(...) */
+static_assert:
+	STATIC_ASSERT_PHRASE ';'			{ $$ = $2; }
+	;
 
 %%
 
diff --git a/scripts/get_abi.pl b/scripts/get_abi.pl
index 68dab828a722..92d9aa6cc4f5 100755
--- a/scripts/get_abi.pl
+++ b/scripts/get_abi.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
 # SPDX-License-Identifier: GPL-2.0
 
 use strict;
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index e46df0a2d4f9..2c40e68853dd 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -94,16 +94,6 @@ configfiles=$(wildcard $(srctree)/kernel/configs/$@ $(srctree)/arch/$(SRCARCH)/c
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m .config $(configfiles)
 	$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 
-PHONY += kvmconfig
-kvmconfig: kvm_guest.config
-	@echo >&2 "WARNING: 'make $@' will be removed after Linux 5.10"
-	@echo >&2 "         Please use 'make $<' instead."
-
-PHONY += xenconfig
-xenconfig: xen.config
-	@echo >&2 "WARNING: 'make $@' will be removed after Linux 5.10"
-	@echo >&2 "         Please use 'make $<' instead."
-
 PHONY += tinyconfig
 tinyconfig:
 	$(Q)$(MAKE) -f $(srctree)/Makefile allnoconfig tiny.config
diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c
index f6e548b8f795..db03e2f45de4 100644
--- a/scripts/kconfig/conf.c
+++ b/scripts/kconfig/conf.c
@@ -11,7 +11,6 @@
 #include <time.h>
 #include <unistd.h>
 #include <getopt.h>
-#include <sys/stat.h>
 #include <sys/time.h>
 #include <errno.h>
 
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index a39d93e3c6ae..2568dbe16ed6 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -5,6 +5,7 @@
 
 #include <sys/mman.h>
 #include <sys/stat.h>
+#include <sys/types.h>
 #include <ctype.h>
 #include <errno.h>
 #include <fcntl.h>
diff --git a/scripts/kconfig/lexer.l b/scripts/kconfig/lexer.l
index 240109f965ae..9c22cb554673 100644
--- a/scripts/kconfig/lexer.l
+++ b/scripts/kconfig/lexer.l
@@ -12,7 +12,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <unistd.h>
 
 #include "lkc.h"
 #include "parser.tab.h"
diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h
index 8454649b17bd..bee2413bda63 100644
--- a/scripts/kconfig/lkc.h
+++ b/scripts/kconfig/lkc.h
@@ -6,6 +6,10 @@
 #ifndef LKC_H
 #define LKC_H
 
+#include <assert.h>
+#include <stdio.h>
+#include <stdlib.h>
+
 #include "expr.h"
 
 #ifdef __cplusplus
diff --git a/scripts/kconfig/mconf-cfg.sh b/scripts/kconfig/mconf-cfg.sh
index aa68ec95620d..fcd4acd4e9cb 100755
--- a/scripts/kconfig/mconf-cfg.sh
+++ b/scripts/kconfig/mconf-cfg.sh
@@ -33,7 +33,9 @@ if [ -f /usr/include/ncurses/ncurses.h ]; then
 	exit 0
 fi
 
-if [ -f /usr/include/ncurses.h ]; then
+# As a final fallback before giving up, check if $HOSTCC knows of a default
+# ncurses installation (e.g. from a vendor-specific sysroot).
+if echo '#include <ncurses.h>' | "${HOSTCC}" -E - >/dev/null 2>&1; then
 	echo cflags=\"-D_GNU_SOURCE\"
 	echo libs=\"-lncurses\"
 	exit 0
diff --git a/scripts/kconfig/preprocess.c b/scripts/kconfig/preprocess.c
index 0243086fb168..0590f86df6e4 100644
--- a/scripts/kconfig/preprocess.c
+++ b/scripts/kconfig/preprocess.c
@@ -114,7 +114,7 @@ static char *do_error_if(int argc, char *argv[])
 	if (!strcmp(argv[0], "y"))
 		pperror("%s", argv[1]);
 
-	return NULL;
+	return xstrdup("");
 }
 
 static char *do_filename(int argc, char *argv[])
diff --git a/scripts/kconfig/qconf-cfg.sh b/scripts/kconfig/qconf-cfg.sh
index 02ccc0ae1031..fa564cd795b7 100755
--- a/scripts/kconfig/qconf-cfg.sh
+++ b/scripts/kconfig/qconf-cfg.sh
@@ -2,7 +2,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
 PKG="Qt5Core Qt5Gui Qt5Widgets"
-PKG2="QtCore QtGui"
 
 if [ -z "$(command -v pkg-config)" ]; then
 	echo >&2 "*"
@@ -12,21 +11,14 @@ if [ -z "$(command -v pkg-config)" ]; then
 fi
 
 if pkg-config --exists $PKG; then
-	echo cflags=\"-std=c++11 -fPIC $(pkg-config --cflags Qt5Core Qt5Gui Qt5Widgets)\"
+	echo cflags=\"-std=c++11 -fPIC $(pkg-config --cflags $PKG)\"
 	echo libs=\"$(pkg-config --libs $PKG)\"
 	echo moc=\"$(pkg-config --variable=host_bins Qt5Core)/moc\"
 	exit 0
 fi
 
-if pkg-config --exists $PKG2; then
-	echo cflags=\"$(pkg-config --cflags $PKG2)\"
-	echo libs=\"$(pkg-config --libs $PKG2)\"
-	echo moc=\"$(pkg-config --variable=moc_location QtCore)\"
-	exit 0
-fi
-
 echo >&2 "*"
-echo >&2 "* Could not find Qt via pkg-config."
-echo >&2 "* Please install either Qt 4.8 or 5.x. and make sure it's in PKG_CONFIG_PATH"
+echo >&2 "* Could not find Qt5 via pkg-config."
+echo >&2 "* Please install Qt5 and make sure it's in PKG_CONFIG_PATH"
 echo >&2 "*"
 exit 1
diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc
index f7eb093614f2..d000869b787c 100644
--- a/scripts/kconfig/qconf.cc
+++ b/scripts/kconfig/qconf.cc
@@ -310,15 +310,16 @@ ConfigList::ConfigList(QWidget *parent, const char *name)
 
 	setHeaderLabels(QStringList() << "Option" << "Name" << "Value");
 
-	connect(this, SIGNAL(itemSelectionChanged(void)),
-		SLOT(updateSelection(void)));
+	connect(this, &ConfigList::itemSelectionChanged,
+		this, &ConfigList::updateSelection);
 
 	if (name) {
 		configSettings->beginGroup(name);
 		showName = configSettings->value("/showName", false).toBool();
 		optMode = (enum optionMode)configSettings->value("/optionMode", 0).toInt();
 		configSettings->endGroup();
-		connect(configApp, SIGNAL(aboutToQuit()), SLOT(saveSettings()));
+		connect(configApp, &QApplication::aboutToQuit,
+			this, &ConfigList::saveSettings);
 	}
 
 	showColumn(promptColIdx);
@@ -888,10 +889,10 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e)
 		headerPopup = new QMenu(this);
 		action = new QAction("Show Name", this);
 		action->setCheckable(true);
-		connect(action, SIGNAL(toggled(bool)),
-			SLOT(setShowName(bool)));
-		connect(this, SIGNAL(showNameChanged(bool)),
-			action, SLOT(setChecked(bool)));
+		connect(action, &QAction::toggled,
+			this, &ConfigList::setShowName);
+		connect(this, &ConfigList::showNameChanged,
+			action, &QAction::setChecked);
 		action->setChecked(showName);
 		headerPopup->addAction(action);
 	}
@@ -936,15 +937,18 @@ ConfigInfoView::ConfigInfoView(QWidget* parent, const char *name)
 		configSettings->beginGroup(objectName());
 		setShowDebug(configSettings->value("/showDebug", false).toBool());
 		configSettings->endGroup();
-		connect(configApp, SIGNAL(aboutToQuit()), SLOT(saveSettings()));
+		connect(configApp, &QApplication::aboutToQuit,
+			this, &ConfigInfoView::saveSettings);
 	}
 
 	contextMenu = createStandardContextMenu();
 	QAction *action = new QAction("Show Debug Info", contextMenu);
 
 	action->setCheckable(true);
-	connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool)));
-	connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setChecked(bool)));
+	connect(action, &QAction::toggled,
+		this, &ConfigInfoView::setShowDebug);
+	connect(this, &ConfigInfoView::showDebugChanged,
+		action, &QAction::setChecked);
 	action->setChecked(showDebug());
 	contextMenu->addSeparator();
 	contextMenu->addAction(action);
@@ -1231,11 +1235,13 @@ ConfigSearchWindow::ConfigSearchWindow(ConfigMainWindow *parent)
 	layout2->setSpacing(6);
 	layout2->addWidget(new QLabel("Find:", this));
 	editField = new QLineEdit(this);
-	connect(editField, SIGNAL(returnPressed()), SLOT(search()));
+	connect(editField, &QLineEdit::returnPressed,
+		this, &ConfigSearchWindow::search);
 	layout2->addWidget(editField);
 	searchButton = new QPushButton("Search", this);
 	searchButton->setAutoDefault(false);
-	connect(searchButton, SIGNAL(clicked()), SLOT(search()));
+	connect(searchButton, &QPushButton::clicked,
+		this, &ConfigSearchWindow::search);
 	layout2->addWidget(searchButton);
 	layout1->addLayout(layout2);
 
@@ -1244,10 +1250,10 @@ ConfigSearchWindow::ConfigSearchWindow(ConfigMainWindow *parent)
 	list = new ConfigList(split, "search");
 	list->mode = listMode;
 	info = new ConfigInfoView(split, "search");
-	connect(list, SIGNAL(menuChanged(struct menu *)),
-		info, SLOT(setInfo(struct menu *)));
-	connect(list, SIGNAL(menuChanged(struct menu *)),
-		parent, SLOT(setMenuLink(struct menu *)));
+	connect(list, &ConfigList::menuChanged,
+		info, &ConfigInfoView::setInfo);
+	connect(list, &ConfigList::menuChanged,
+		parent, &ConfigMainWindow::setMenuLink);
 
 	layout1->addWidget(split);
 
@@ -1267,7 +1273,8 @@ ConfigSearchWindow::ConfigSearchWindow(ConfigMainWindow *parent)
 	if (ok)
 		split->setSizes(sizes);
 	configSettings->endGroup();
-	connect(configApp, SIGNAL(aboutToQuit()), SLOT(saveSettings()));
+	connect(configApp, &QApplication::aboutToQuit,
+		this, &ConfigSearchWindow::saveSettings);
 }
 
 void ConfigSearchWindow::saveSettings(void)
@@ -1367,19 +1374,23 @@ ConfigMainWindow::ConfigMainWindow(void)
 	configList->setFocus();
 
 	backAction = new QAction(QPixmap(xpm_back), "Back", this);
-	connect(backAction, SIGNAL(triggered(bool)), SLOT(goBack()));
+	connect(backAction, &QAction::triggered,
+		this, &ConfigMainWindow::goBack);
 
 	QAction *quitAction = new QAction("&Quit", this);
 	quitAction->setShortcut(Qt::CTRL + Qt::Key_Q);
-	connect(quitAction, SIGNAL(triggered(bool)), SLOT(close()));
+	connect(quitAction, &QAction::triggered,
+		this, &ConfigMainWindow::close);
 
 	QAction *loadAction = new QAction(QPixmap(xpm_load), "&Load", this);
 	loadAction->setShortcut(Qt::CTRL + Qt::Key_L);
-	connect(loadAction, SIGNAL(triggered(bool)), SLOT(loadConfig()));
+	connect(loadAction, &QAction::triggered,
+		this, &ConfigMainWindow::loadConfig);
 
 	saveAction = new QAction(QPixmap(xpm_save), "&Save", this);
 	saveAction->setShortcut(Qt::CTRL + Qt::Key_S);
-	connect(saveAction, SIGNAL(triggered(bool)), SLOT(saveConfig()));
+	connect(saveAction, &QAction::triggered,
+		this, &ConfigMainWindow::saveConfig);
 
 	conf_set_changed_callback(conf_changed);
 
@@ -1388,31 +1399,37 @@ ConfigMainWindow::ConfigMainWindow(void)
 	configname = xstrdup(conf_get_configname());
 
 	QAction *saveAsAction = new QAction("Save &As...", this);
-	  connect(saveAsAction, SIGNAL(triggered(bool)), SLOT(saveConfigAs()));
+	connect(saveAsAction, &QAction::triggered,
+		this, &ConfigMainWindow::saveConfigAs);
 	QAction *searchAction = new QAction("&Find", this);
 	searchAction->setShortcut(Qt::CTRL + Qt::Key_F);
-	  connect(searchAction, SIGNAL(triggered(bool)), SLOT(searchConfig()));
+	connect(searchAction, &QAction::triggered,
+		this, &ConfigMainWindow::searchConfig);
 	singleViewAction = new QAction(QPixmap(xpm_single_view), "Single View", this);
 	singleViewAction->setCheckable(true);
-	  connect(singleViewAction, SIGNAL(triggered(bool)), SLOT(showSingleView()));
+	connect(singleViewAction, &QAction::triggered,
+		this, &ConfigMainWindow::showSingleView);
 	splitViewAction = new QAction(QPixmap(xpm_split_view), "Split View", this);
 	splitViewAction->setCheckable(true);
-	  connect(splitViewAction, SIGNAL(triggered(bool)), SLOT(showSplitView()));
+	connect(splitViewAction, &QAction::triggered,
+		this, &ConfigMainWindow::showSplitView);
 	fullViewAction = new QAction(QPixmap(xpm_tree_view), "Full View", this);
 	fullViewAction->setCheckable(true);
-	  connect(fullViewAction, SIGNAL(triggered(bool)), SLOT(showFullView()));
+	connect(fullViewAction, &QAction::triggered,
+		this, &ConfigMainWindow::showFullView);
 
 	QAction *showNameAction = new QAction("Show Name", this);
 	  showNameAction->setCheckable(true);
-	connect(showNameAction, SIGNAL(toggled(bool)), configList, SLOT(setShowName(bool)));
+	connect(showNameAction, &QAction::toggled,
+		configList, &ConfigList::setShowName);
 	showNameAction->setChecked(configList->showName);
 
 	QActionGroup *optGroup = new QActionGroup(this);
 	optGroup->setExclusive(true);
-	connect(optGroup, SIGNAL(triggered(QAction*)), configList,
-		SLOT(setOptionMode(QAction *)));
-	connect(optGroup, SIGNAL(triggered(QAction *)), menuList,
-		SLOT(setOptionMode(QAction *)));
+	connect(optGroup, &QActionGroup::triggered,
+		configList, &ConfigList::setOptionMode);
+	connect(optGroup, &QActionGroup::triggered,
+		menuList, &ConfigList::setOptionMode);
 
 	ConfigList::showNormalAction = new QAction("Show Normal Options", optGroup);
 	ConfigList::showNormalAction->setCheckable(true);
@@ -1423,13 +1440,16 @@ ConfigMainWindow::ConfigMainWindow(void)
 
 	QAction *showDebugAction = new QAction("Show Debug Info", this);
 	  showDebugAction->setCheckable(true);
-	  connect(showDebugAction, SIGNAL(toggled(bool)), helpText, SLOT(setShowDebug(bool)));
+	connect(showDebugAction, &QAction::toggled,
+		helpText, &ConfigInfoView::setShowDebug);
 	  showDebugAction->setChecked(helpText->showDebug());
 
 	QAction *showIntroAction = new QAction("Introduction", this);
-	  connect(showIntroAction, SIGNAL(triggered(bool)), SLOT(showIntro()));
+	connect(showIntroAction, &QAction::triggered,
+		this, &ConfigMainWindow::showIntro);
 	QAction *showAboutAction = new QAction("About", this);
-	  connect(showAboutAction, SIGNAL(triggered(bool)), SLOT(showAbout()));
+	connect(showAboutAction, &QAction::triggered,
+		this, &ConfigMainWindow::showAbout);
 
 	// init tool bar
 	QToolBar *toolBar = addToolBar("Tools");
@@ -1467,30 +1487,30 @@ ConfigMainWindow::ConfigMainWindow(void)
 	menu->addAction(showIntroAction);
 	menu->addAction(showAboutAction);
 
-	connect (helpText, SIGNAL (anchorClicked (const QUrl &)),
-		 helpText, SLOT (clicked (const QUrl &)) );
-
-	connect(configList, SIGNAL(menuChanged(struct menu *)),
-		helpText, SLOT(setInfo(struct menu *)));
-	connect(configList, SIGNAL(menuSelected(struct menu *)),
-		SLOT(changeMenu(struct menu *)));
-	connect(configList, SIGNAL(itemSelected(struct menu *)),
-		SLOT(changeItens(struct menu *)));
-	connect(configList, SIGNAL(parentSelected()),
-		SLOT(goBack()));
-	connect(menuList, SIGNAL(menuChanged(struct menu *)),
-		helpText, SLOT(setInfo(struct menu *)));
-	connect(menuList, SIGNAL(menuSelected(struct menu *)),
-		SLOT(changeMenu(struct menu *)));
-
-	connect(configList, SIGNAL(gotFocus(struct menu *)),
-		helpText, SLOT(setInfo(struct menu *)));
-	connect(menuList, SIGNAL(gotFocus(struct menu *)),
-		helpText, SLOT(setInfo(struct menu *)));
-	connect(menuList, SIGNAL(gotFocus(struct menu *)),
-		SLOT(listFocusChanged(void)));
-	connect(helpText, SIGNAL(menuSelected(struct menu *)),
-		SLOT(setMenuLink(struct menu *)));
+	connect(helpText, &ConfigInfoView::anchorClicked,
+		helpText, &ConfigInfoView::clicked);
+
+	connect(configList, &ConfigList::menuChanged,
+		helpText, &ConfigInfoView::setInfo);
+	connect(configList, &ConfigList::menuSelected,
+		this, &ConfigMainWindow::changeMenu);
+	connect(configList, &ConfigList::itemSelected,
+		this, &ConfigMainWindow::changeItens);
+	connect(configList, &ConfigList::parentSelected,
+		this, &ConfigMainWindow::goBack);
+	connect(menuList, &ConfigList::menuChanged,
+		helpText, &ConfigInfoView::setInfo);
+	connect(menuList, &ConfigList::menuSelected,
+		this, &ConfigMainWindow::changeMenu);
+
+	connect(configList, &ConfigList::gotFocus,
+		helpText, &ConfigInfoView::setInfo);
+	connect(menuList, &ConfigList::gotFocus,
+		helpText, &ConfigInfoView::setInfo);
+	connect(menuList, &ConfigList::gotFocus,
+		this, &ConfigMainWindow::listFocusChanged);
+	connect(helpText, &ConfigInfoView::menuSelected,
+		this, &ConfigMainWindow::setMenuLink);
 
 	QString listMode = configSettings->value("/listMode", "symbol").toString();
 	if (listMode == "single")
@@ -1779,10 +1799,13 @@ void ConfigMainWindow::showIntro(void)
 void ConfigMainWindow::showAbout(void)
 {
 	static const QString str = "qconf is Copyright (C) 2002 Roman Zippel <zippel@linux-m68k.org>.\n"
-		"Copyright (C) 2015 Boris Barbulovski <bbarbulovski@gmail.com>.\n\n"
-		"Bug reports and feature request can also be entered at http://bugzilla.kernel.org/\n";
+		"Copyright (C) 2015 Boris Barbulovski <bbarbulovski@gmail.com>.\n"
+		"\n"
+		"Bug reports and feature request can also be entered at http://bugzilla.kernel.org/\n"
+		"\n"
+		"Qt Version: ";
 
-	QMessageBox::information(this, "qconf", str);
+	QMessageBox::information(this, "qconf", str + qVersion());
 }
 
 void ConfigMainWindow::saveSettings(void)
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index ffa3ec65cc90..fe38e6fd2c2a 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -3,11 +3,11 @@
  * Copyright (C) 2002 Roman Zippel <zippel@linux-m68k.org>
  */
 
+#include <sys/types.h>
 #include <ctype.h>
 #include <stdlib.h>
 #include <string.h>
 #include <regex.h>
-#include <sys/utsname.h>
 
 #include "lkc.h"
 
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index f882ce0d9327..d6c81657d695 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -34,12 +34,14 @@ static int external_module = 0;
 static int warn_unresolved = 0;
 /* How a symbol is exported */
 static int sec_mismatch_count = 0;
-static int sec_mismatch_fatal = 0;
+static int sec_mismatch_warn_only = true;
 /* ignore missing files */
 static int ignore_missing_files;
 /* If set to 1, only warn (instead of error) about missing ns imports */
 static int allow_missing_ns_imports;
 
+static bool error_occurred;
+
 enum export {
 	export_plain,      export_unused,     export_gpl,
 	export_unused_gpl, export_gpl_future, export_unknown
@@ -78,6 +80,8 @@ modpost_log(enum loglevel loglevel, const char *fmt, ...)
 
 	if (loglevel == LOG_FATAL)
 		exit(1);
+	if (loglevel == LOG_ERROR)
+		error_occurred = true;
 }
 
 static inline bool strends(const char *str, const char *postfix)
@@ -403,8 +407,8 @@ static void sym_update_namespace(const char *symname, const char *namespace)
 	 * actually an assertion.
 	 */
 	if (!s) {
-		merror("Could not update namespace(%s) for symbol %s\n",
-		       namespace, symname);
+		error("Could not update namespace(%s) for symbol %s\n",
+		      namespace, symname);
 		return;
 	}
 
@@ -2014,7 +2018,7 @@ static void read_symbols(const char *modname)
 	if (!mod->is_vmlinux) {
 		license = get_modinfo(&info, "license");
 		if (!license)
-			warn("missing MODULE_LICENSE() in %s\n", modname);
+			error("missing MODULE_LICENSE() in %s\n", modname);
 		while (license) {
 			if (license_is_gpl_compatible(license))
 				mod->gpl_compatible = 1;
@@ -2141,11 +2145,11 @@ static void check_for_gpl_usage(enum export exp, const char *m, const char *s)
 {
 	switch (exp) {
 	case export_gpl:
-		fatal("GPL-incompatible module %s.ko uses GPL-only symbol '%s'\n",
+		error("GPL-incompatible module %s.ko uses GPL-only symbol '%s'\n",
 		      m, s);
 		break;
 	case export_unused_gpl:
-		fatal("GPL-incompatible module %s.ko uses GPL-only symbol marked UNUSED '%s'\n",
+		error("GPL-incompatible module %s.ko uses GPL-only symbol marked UNUSED '%s'\n",
 		      m, s);
 		break;
 	case export_gpl_future:
@@ -2174,22 +2178,18 @@ static void check_for_unused(enum export exp, const char *m, const char *s)
 	}
 }
 
-static int check_exports(struct module *mod)
+static void check_exports(struct module *mod)
 {
 	struct symbol *s, *exp;
-	int err = 0;
 
 	for (s = mod->unres; s; s = s->next) {
 		const char *basename;
 		exp = find_symbol(s->name);
 		if (!exp || exp->module == mod) {
-			if (have_vmlinux && !s->weak) {
+			if (have_vmlinux && !s->weak)
 				modpost_log(warn_unresolved ? LOG_WARN : LOG_ERROR,
 					    "\"%s\" [%s.ko] undefined!\n",
 					    s->name, mod->name);
-				if (!warn_unresolved)
-					err = 1;
-			}
 			continue;
 		}
 		basename = strrchr(mod->name, '/');
@@ -2203,8 +2203,6 @@ static int check_exports(struct module *mod)
 			modpost_log(allow_missing_ns_imports ? LOG_WARN : LOG_ERROR,
 				    "module %s uses symbol %s from namespace %s, but does not import it.\n",
 				    basename, exp->name, exp->namespace);
-			if (!allow_missing_ns_imports)
-				err = 1;
 			add_namespace(&mod->missing_namespaces, exp->namespace);
 		}
 
@@ -2212,11 +2210,9 @@ static int check_exports(struct module *mod)
 			check_for_gpl_usage(exp->export, basename, exp->name);
 		check_for_unused(exp->export, basename, exp->name);
 	}
-
-	return err;
 }
 
-static int check_modname_len(struct module *mod)
+static void check_modname_len(struct module *mod)
 {
 	const char *mod_name;
 
@@ -2225,12 +2221,8 @@ static int check_modname_len(struct module *mod)
 		mod_name = mod->name;
 	else
 		mod_name++;
-	if (strlen(mod_name) >= MODULE_NAME_LEN) {
-		merror("module name is too long [%s.ko]\n", mod->name);
-		return 1;
-	}
-
-	return 0;
+	if (strlen(mod_name) >= MODULE_NAME_LEN)
+		error("module name is too long [%s.ko]\n", mod->name);
 }
 
 /**
@@ -2289,10 +2281,9 @@ static void add_staging_flag(struct buffer *b, const char *name)
 /**
  * Record CRCs for unresolved symbols
  **/
-static int add_versions(struct buffer *b, struct module *mod)
+static void add_versions(struct buffer *b, struct module *mod)
 {
 	struct symbol *s, *exp;
-	int err = 0;
 
 	for (s = mod->unres; s; s = s->next) {
 		exp = find_symbol(s->name);
@@ -2304,7 +2295,7 @@ static int add_versions(struct buffer *b, struct module *mod)
 	}
 
 	if (!modversions)
-		return err;
+		return;
 
 	buf_printf(b, "\n");
 	buf_printf(b, "static const struct modversion_info ____versions[]\n");
@@ -2319,9 +2310,8 @@ static int add_versions(struct buffer *b, struct module *mod)
 			continue;
 		}
 		if (strlen(s->name) >= MODULE_NAME_LEN) {
-			merror("too long symbol \"%s\" [%s.ko]\n",
-			       s->name, mod->name);
-			err = 1;
+			error("too long symbol \"%s\" [%s.ko]\n",
+			      s->name, mod->name);
 			break;
 		}
 		buf_printf(b, "\t{ %#8x, \"%s\" },\n",
@@ -2329,8 +2319,6 @@ static int add_versions(struct buffer *b, struct module *mod)
 	}
 
 	buf_printf(b, "};\n");
-
-	return err;
 }
 
 static void add_depends(struct buffer *b, struct module *mod)
@@ -2554,7 +2542,6 @@ int main(int argc, char **argv)
 	char *missing_namespace_deps = NULL;
 	char *dump_write = NULL, *files_source = NULL;
 	int opt;
-	int err;
 	int n;
 	struct dump_list *dump_read_start = NULL;
 	struct dump_list **dump_read_iter = &dump_read_start;
@@ -2589,7 +2576,7 @@ int main(int argc, char **argv)
 			warn_unresolved = 1;
 			break;
 		case 'E':
-			sec_mismatch_fatal = 1;
+			sec_mismatch_warn_only = false;
 			break;
 		case 'N':
 			allow_missing_ns_imports = 1;
@@ -2624,8 +2611,6 @@ int main(int argc, char **argv)
 	if (!have_vmlinux)
 		warn("Symbol info of vmlinux is missing. Unresolved symbol check will be entirely skipped.\n");
 
-	err = 0;
-
 	for (mod = modules; mod; mod = mod->next) {
 		char fname[PATH_MAX];
 
@@ -2634,14 +2619,14 @@ int main(int argc, char **argv)
 
 		buf.pos = 0;
 
-		err |= check_modname_len(mod);
-		err |= check_exports(mod);
+		check_modname_len(mod);
+		check_exports(mod);
 
 		add_header(&buf, mod);
 		add_intree_flag(&buf, !external_module);
 		add_retpoline(&buf);
 		add_staging_flag(&buf, mod->name);
-		err |= add_versions(&buf, mod);
+		add_versions(&buf, mod);
 		add_depends(&buf, mod);
 		add_moddevtable(&buf, mod);
 		add_srcversion(&buf, mod);
@@ -2655,21 +2640,21 @@ int main(int argc, char **argv)
 
 	if (dump_write)
 		write_dump(dump_write);
-	if (sec_mismatch_count && sec_mismatch_fatal)
-		fatal("Section mismatches detected.\n"
+	if (sec_mismatch_count && !sec_mismatch_warn_only)
+		error("Section mismatches detected.\n"
 		      "Set CONFIG_SECTION_MISMATCH_WARN_ONLY=y to allow them.\n");
 	for (n = 0; n < SYMBOL_HASH_SIZE; n++) {
 		struct symbol *s;
 
 		for (s = symbolhash[n]; s; s = s->next) {
 			if (s->is_static)
-				warn("\"%s\" [%s] is a static %s\n",
-				     s->name, s->module->name,
-				     export_str(s->export));
+				error("\"%s\" [%s] is a static %s\n",
+				      s->name, s->module->name,
+				      export_str(s->export));
 		}
 	}
 
 	free(buf.p);
 
-	return err;
+	return error_occurred ? 1 : 0;
 }
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index 3aa052722233..e6f46eee0af0 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -201,6 +201,19 @@ enum loglevel {
 
 void modpost_log(enum loglevel loglevel, const char *fmt, ...);
 
+/*
+ * warn - show the given message, then let modpost continue running, still
+ *        allowing modpost to exit successfully. This should be used when
+ *        we still allow to generate vmlinux and modules.
+ *
+ * error - show the given message, then let modpost continue running, but fail
+ *         in the end. This should be used when we should stop building vmlinux
+ *         or modules, but we can continue running modpost to catch as many
+ *         issues as possible.
+ *
+ * fatal - show the given message, and bail out immediately. This should be
+ *         used when there is no point to continue running modpost.
+ */
 #define warn(fmt, args...)	modpost_log(LOG_WARN, fmt, ##args)
-#define merror(fmt, args...)	modpost_log(LOG_ERROR, fmt, ##args)
+#define error(fmt, args...)	modpost_log(LOG_ERROR, fmt, ##args)
 #define fatal(fmt, args...)	modpost_log(LOG_FATAL, fmt, ##args)
diff --git a/scripts/nsdeps b/scripts/nsdeps
index dab4c1a0e27d..e8ce2a4d704a 100644
--- a/scripts/nsdeps
+++ b/scripts/nsdeps
@@ -12,11 +12,9 @@ if [ ! -x "$SPATCH" ]; then
 	exit 1
 fi
 
-SPATCH_REQ_VERSION_NUM=$(echo $SPATCH_REQ_VERSION | ${DIR}/scripts/ld-version.sh)
 SPATCH_VERSION=$($SPATCH --version | head -1 | awk '{print $3}')
-SPATCH_VERSION_NUM=$(echo $SPATCH_VERSION | ${DIR}/scripts/ld-version.sh)
 
-if [ "$SPATCH_VERSION_NUM" -lt "$SPATCH_REQ_VERSION_NUM" ] ; then
+if ! { echo "$SPATCH_REQ_VERSION"; echo "$SPATCH_VERSION"; } | sort -CV ; then
 	echo "spatch needs to be version $SPATCH_REQ_VERSION or higher"
 	exit 1
 fi
diff --git a/scripts/show_delta b/scripts/show_delta
index 264399307c4f..28e67e178194 100755
--- a/scripts/show_delta
+++ b/scripts/show_delta
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 # SPDX-License-Identifier: GPL-2.0-only
 #
 # show_deltas: Read list of printk messages instrumented with
diff --git a/scripts/sphinx-pre-install b/scripts/sphinx-pre-install
index 40fa6923e80a..828a8615a918 100755
--- a/scripts/sphinx-pre-install
+++ b/scripts/sphinx-pre-install
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
 # SPDX-License-Identifier: GPL-2.0-or-later
 use strict;
 
diff --git a/scripts/split-man.pl b/scripts/split-man.pl
index c3db607ee9ec..96bd99dc977a 100755
--- a/scripts/split-man.pl
+++ b/scripts/split-man.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
 # SPDX-License-Identifier: GPL-2.0
 #
 # Author: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
diff --git a/scripts/tracing/draw_functrace.py b/scripts/tracing/draw_functrace.py
index b65735758520..74f8aadfd4cb 100755
--- a/scripts/tracing/draw_functrace.py
+++ b/scripts/tracing/draw_functrace.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 # SPDX-License-Identifier: GPL-2.0-only
 
 """
diff --git a/security/integrity/ima/Makefile b/security/integrity/ima/Makefile
index 67dabca670e2..2499f2485c04 100644
--- a/security/integrity/ima/Makefile
+++ b/security/integrity/ima/Makefile
@@ -14,3 +14,7 @@ ima-$(CONFIG_HAVE_IMA_KEXEC) += ima_kexec.o
 ima-$(CONFIG_IMA_BLACKLIST_KEYRING) += ima_mok.o
 ima-$(CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS) += ima_asymmetric_keys.o
 ima-$(CONFIG_IMA_QUEUE_EARLY_BOOT_KEYS) += ima_queue_keys.o
+
+ifeq ($(CONFIG_EFI),y)
+ima-$(CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT) += ima_efi.o
+endif
diff --git a/arch/x86/kernel/ima_arch.c b/security/integrity/ima/ima_efi.c
index 7dfb1e808928..71786d01946f 100644
--- a/arch/x86/kernel/ima_arch.c
+++ b/security/integrity/ima/ima_efi.c
@@ -5,50 +5,29 @@
 #include <linux/efi.h>
 #include <linux/module.h>
 #include <linux/ima.h>
+#include <asm/efi.h>
 
-extern struct boot_params boot_params;
+#ifndef arch_ima_efi_boot_mode
+#define arch_ima_efi_boot_mode efi_secureboot_mode_unset
+#endif
 
 static enum efi_secureboot_mode get_sb_mode(void)
 {
-	efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
-	efi_status_t status;
-	unsigned long size;
-	u8 secboot, setupmode;
-
-	size = sizeof(secboot);
+	enum efi_secureboot_mode mode;
 
 	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE)) {
 		pr_info("ima: secureboot mode unknown, no efi\n");
 		return efi_secureboot_mode_unknown;
 	}
 
-	/* Get variable contents into buffer */
-	status = efi.get_variable(L"SecureBoot", &efi_variable_guid,
-				  NULL, &size, &secboot);
-	if (status == EFI_NOT_FOUND) {
+	mode = efi_get_secureboot_mode(efi.get_variable);
+	if (mode == efi_secureboot_mode_disabled)
 		pr_info("ima: secureboot mode disabled\n");
-		return efi_secureboot_mode_disabled;
-	}
-
-	if (status != EFI_SUCCESS) {
+	else if (mode == efi_secureboot_mode_unknown)
 		pr_info("ima: secureboot mode unknown\n");
-		return efi_secureboot_mode_unknown;
-	}
-
-	size = sizeof(setupmode);
-	status = efi.get_variable(L"SetupMode", &efi_variable_guid,
-				  NULL, &size, &setupmode);
-
-	if (status != EFI_SUCCESS)	/* ignore unknown SetupMode */
-		setupmode = 0;
-
-	if (secboot == 0 || setupmode == 1) {
-		pr_info("ima: secureboot mode disabled\n");
-		return efi_secureboot_mode_disabled;
-	}
-
-	pr_info("ima: secureboot mode enabled\n");
-	return efi_secureboot_mode_enabled;
+	else
+		pr_info("ima: secureboot mode enabled\n");
+	return mode;
 }
 
 bool arch_ima_get_secureboot(void)
@@ -57,7 +36,7 @@ bool arch_ima_get_secureboot(void)
 	static bool initialized;
 
 	if (!initialized && efi_enabled(EFI_BOOT)) {
-		sb_mode = boot_params.secure_boot;
+		sb_mode = arch_ima_efi_boot_mode;
 
 		if (sb_mode == efi_secureboot_mode_unset)
 			sb_mode = get_sb_mode();
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 7d8026f3f377..a0cd28cd31a8 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -275,7 +275,9 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 		struct inode *inode;
 
 		audit_log_format(ab, " name=");
+		spin_lock(&a->u.dentry->d_lock);
 		audit_log_untrustedstring(ab, a->u.dentry->d_name.name);
+		spin_unlock(&a->u.dentry->d_lock);
 
 		inode = d_backing_inode(a->u.dentry);
 		if (inode) {
@@ -293,8 +295,9 @@ static void dump_common_audit_data(struct audit_buffer *ab,
 		dentry = d_find_alias(inode);
 		if (dentry) {
 			audit_log_format(ab, " name=");
-			audit_log_untrustedstring(ab,
-					 dentry->d_name.name);
+			spin_lock(&dentry->d_lock);
+			audit_log_untrustedstring(ab, dentry->d_name.name);
+			spin_unlock(&dentry->d_lock);
 			dput(dentry);
 		}
 		audit_log_format(ab, " dev=");
diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c
index efe2406a3960..7eabb448acab 100644
--- a/security/smack/smack_access.c
+++ b/security/smack/smack_access.c
@@ -688,9 +688,10 @@ bool smack_privileged_cred(int cap, const struct cred *cred)
 bool smack_privileged(int cap)
 {
 	/*
-	 * All kernel tasks are privileged
+	 * Kernel threads may not have credentials we can use.
+	 * The io_uring kernel threads do have reliable credentials.
 	 */
-	if (unlikely(current->flags & PF_KTHREAD))
+	if ((current->flags & (PF_KTHREAD | PF_IO_WORKER)) == PF_KTHREAD)
 		return true;
 
 	return smack_privileged_cred(cap, current_cred());
diff --git a/sound/core/init.c b/sound/core/init.c
index 764dbe673d48..75aec71c48a8 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -149,8 +149,6 @@ static void release_card_device(struct device *dev)
  *  @extra_size: allocate this extra size after the main soundcard structure
  *  @card_ret: the pointer to store the created card instance
  *
- *  Creates and initializes a soundcard structure.
- *
  *  The function allocates snd_card instance via kzalloc with the given
  *  space for the driver to use freely.  The allocated struct is stored
  *  in the given card_ret pointer.
diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c
index 0aeeb6244ff6..966bef5acc75 100644
--- a/sound/core/memalloc.c
+++ b/sound/core/memalloc.c
@@ -77,7 +77,8 @@ static void snd_malloc_dev_iram(struct snd_dma_buffer *dmab, size_t size)
 	/* Assign the pool into private_data field */
 	dmab->private_data = pool;
 
-	dmab->area = gen_pool_dma_alloc(pool, size, &dmab->addr);
+	dmab->area = gen_pool_dma_alloc_align(pool, size, &dmab->addr,
+					PAGE_SIZE);
 }
 
 /**
@@ -132,6 +133,7 @@ int snd_dma_alloc_pages(int type, struct device *device, size_t size,
 	if (WARN_ON(!dmab))
 		return -ENXIO;
 
+	size = PAGE_ALIGN(size);
 	dmab->dev.type = type;
 	dmab->dev.dev = device;
 	dmab->bytes = 0;
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index de1917484647..142fc751a847 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -693,6 +693,8 @@ static int snd_pcm_oss_period_size(struct snd_pcm_substream *substream,
 
 	oss_buffer_size = snd_pcm_plug_client_size(substream,
 						   snd_pcm_hw_param_value_max(slave_params, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, NULL)) * oss_frame_size;
+	if (!oss_buffer_size)
+		return -EINVAL;
 	oss_buffer_size = rounddown_pow_of_two(oss_buffer_size);
 	if (atomic_read(&substream->mmap_count)) {
 		if (oss_buffer_size > runtime->oss.mmap_bytes)
@@ -728,17 +730,21 @@ static int snd_pcm_oss_period_size(struct snd_pcm_substream *substream,
 
 	min_period_size = snd_pcm_plug_client_size(substream,
 						   snd_pcm_hw_param_value_min(slave_params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, NULL));
-	min_period_size *= oss_frame_size;
-	min_period_size = roundup_pow_of_two(min_period_size);
-	if (oss_period_size < min_period_size)
-		oss_period_size = min_period_size;
+	if (min_period_size) {
+		min_period_size *= oss_frame_size;
+		min_period_size = roundup_pow_of_two(min_period_size);
+		if (oss_period_size < min_period_size)
+			oss_period_size = min_period_size;
+	}
 
 	max_period_size = snd_pcm_plug_client_size(substream,
 						   snd_pcm_hw_param_value_max(slave_params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, NULL));
-	max_period_size *= oss_frame_size;
-	max_period_size = rounddown_pow_of_two(max_period_size);
-	if (oss_period_size > max_period_size)
-		oss_period_size = max_period_size;
+	if (max_period_size) {
+		max_period_size *= oss_frame_size;
+		max_period_size = rounddown_pow_of_two(max_period_size);
+		if (oss_period_size > max_period_size)
+			oss_period_size = max_period_size;
+	}
 
 	oss_periods = oss_buffer_size / oss_period_size;
 
diff --git a/sound/core/pcm_memory.c b/sound/core/pcm_memory.c
index 4f03ba8ed0ae..ee6e9c5eec45 100644
--- a/sound/core/pcm_memory.c
+++ b/sound/core/pcm_memory.c
@@ -89,14 +89,6 @@ static int preallocate_pcm_pages(struct snd_pcm_substream *substream, size_t siz
 	return 0;
 }
 
-/*
- * release the preallocated buffer if not yet done.
- */
-static void snd_pcm_lib_preallocate_dma_free(struct snd_pcm_substream *substream)
-{
-	do_free_pages(substream->pcm->card, &substream->dma_buffer);
-}
-
 /**
  * snd_pcm_lib_preallocate_free - release the preallocated buffer of the specified substream.
  * @substream: the pcm substream instance
@@ -105,7 +97,7 @@ static void snd_pcm_lib_preallocate_dma_free(struct snd_pcm_substream *substream
  */
 void snd_pcm_lib_preallocate_free(struct snd_pcm_substream *substream)
 {
-	snd_pcm_lib_preallocate_dma_free(substream);
+	do_free_pages(substream->pcm->card, &substream->dma_buffer);
 }
 
 /**
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 47b155a49226..9f3f8e953ff0 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -755,8 +755,13 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream,
 		runtime->boundary *= 2;
 
 	/* clear the buffer for avoiding possible kernel info leaks */
-	if (runtime->dma_area && !substream->ops->copy_user)
-		memset(runtime->dma_area, 0, runtime->dma_bytes);
+	if (runtime->dma_area && !substream->ops->copy_user) {
+		size_t size = runtime->dma_bytes;
+
+		if (runtime->info & SNDRV_PCM_INFO_MMAP)
+			size = PAGE_ALIGN(size);
+		memset(runtime->dma_area, 0, size);
+	}
 
 	snd_pcm_timer_resolution_change(substream);
 	snd_pcm_set_state(substream, SNDRV_PCM_STATE_SETUP);
diff --git a/sound/firewire/fireface/ff-transaction.c b/sound/firewire/fireface/ff-transaction.c
index 7f82762ccc8c..ee7122c461d4 100644
--- a/sound/firewire/fireface/ff-transaction.c
+++ b/sound/firewire/fireface/ff-transaction.c
@@ -88,7 +88,7 @@ static void transmit_midi_msg(struct snd_ff *ff, unsigned int port)
 
 	/* Set interval to next transaction. */
 	ff->next_ktime[port] = ktime_add_ns(ktime_get(),
-				ff->rx_bytes[port] * 8 * NSEC_PER_SEC / 31250);
+			ff->rx_bytes[port] * 8 * (NSEC_PER_SEC / 31250));
 
 	if (quad_count == 1)
 		tcode = TCODE_WRITE_QUADLET_REQUEST;
diff --git a/sound/firewire/tascam/tascam-transaction.c b/sound/firewire/tascam/tascam-transaction.c
index 90288b4b4637..a073cece4a7d 100644
--- a/sound/firewire/tascam/tascam-transaction.c
+++ b/sound/firewire/tascam/tascam-transaction.c
@@ -209,7 +209,7 @@ static void midi_port_work(struct work_struct *work)
 
 	/* Set interval to next transaction. */
 	port->next_ktime = ktime_add_ns(ktime_get(),
-				port->consume_bytes * 8 * NSEC_PER_SEC / 31250);
+			port->consume_bytes * 8 * (NSEC_PER_SEC / 31250));
 
 	/* Start this transaction. */
 	port->idling = false;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 6852668f1bcb..e4dd2ff5e473 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2220,8 +2220,6 @@ static const struct snd_pci_quirk power_save_denylist[] = {
 	SND_PCI_QUIRK(0x1849, 0x7662, "Asrock H81M-HDS", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
 	SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0),
-	/* https://bugzilla.redhat.com/show_bug.cgi?id=1581607 */
-	SND_PCI_QUIRK(0x1558, 0x3501, "Clevo W35xSS_370SS", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
 	SND_PCI_QUIRK(0x1558, 0x6504, "Clevo W65_67SB", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
@@ -2600,7 +2598,8 @@ static const struct pci_device_id azx_ids[] = {
 	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_AMD_SB },
 	/* ATI HDMI */
 	{ PCI_DEVICE(0x1002, 0x0002),
-	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS |
+	  AZX_DCAPS_PM_RUNTIME },
 	{ PCI_DEVICE(0x1002, 0x1308),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0x157a),
@@ -2662,9 +2661,11 @@ static const struct pci_device_id azx_ids[] = {
 	{ PCI_DEVICE(0x1002, 0xaab0),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0xaac0),
-	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS |
+	  AZX_DCAPS_PM_RUNTIME },
 	{ PCI_DEVICE(0x1002, 0xaac8),
-	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS |
+	  AZX_DCAPS_PM_RUNTIME },
 	{ PCI_DEVICE(0x1002, 0xaad8),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS |
 	  AZX_DCAPS_PM_RUNTIME },
diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c
index 70164d1428d4..361cf2041911 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -388,7 +388,7 @@ static int hda_tegra_first_init(struct azx *chip, struct platform_device *pdev)
 	 * in powers of 2, next available ratio is 16 which can be
 	 * used as a limiting factor here.
 	 */
-	if (of_device_is_compatible(np, "nvidia,tegra194-hda"))
+	if (of_device_is_compatible(np, "nvidia,tegra30-hda"))
 		chip->bus.core.sdo_limit = 16;
 
 	/* codec detection */
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index be5000dd1585..d49cc4409d59 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -1070,6 +1070,7 @@ static int patch_conexant_auto(struct hda_codec *codec)
 static const struct hda_device_id snd_hda_id_conexant[] = {
 	HDA_CODEC_ENTRY(0x14f11f86, "CX8070", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto),
+	HDA_CODEC_ENTRY(0x14f120d0, "CX11970", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f15051, "CX20561 (Hermosa)", patch_conexant_auto),
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 1e4a4b83fbf6..74d246a0dc6d 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1733,7 +1733,7 @@ static void silent_stream_disable(struct hda_codec *codec,
 	per_pin->silent_stream = false;
 
  unlock_out:
-	mutex_unlock(&spec->pcm_lock);
+	mutex_unlock(&per_pin->lock);
 }
 
 /* update ELD and jack state via audio component */
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 41cc64036f22..dd82ff2bd5d6 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2516,6 +2516,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1458, 0xa0ce, "Gigabyte X570 Aorus Xtreme", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x11f7, "MSI-GE63", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x1228, "MSI-GP63", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1462, 0x1229, "MSI-GP73", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x1275, "MSI-GL63", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950),
@@ -6288,6 +6289,7 @@ enum {
 	ALC221_FIXUP_HP_FRONT_MIC,
 	ALC292_FIXUP_TPT460,
 	ALC298_FIXUP_SPK_VOLUME,
+	ALC298_FIXUP_LENOVO_SPK_VOLUME,
 	ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER,
 	ALC269_FIXUP_ATIV_BOOK_8,
 	ALC221_FIXUP_HP_MIC_NO_PRESENCE,
@@ -6368,6 +6370,7 @@ enum {
 	ALC287_FIXUP_HP_GPIO_LED,
 	ALC256_FIXUP_HP_HEADSET_MIC,
 	ALC236_FIXUP_DELL_AIO_HEADSET_MIC,
+	ALC282_FIXUP_ACER_DISABLE_LINEOUT,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -7117,6 +7120,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
 	},
+	[ALC298_FIXUP_LENOVO_SPK_VOLUME] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc298_fixup_speaker_volume,
+	},
 	[ALC295_FIXUP_DISABLE_DAC3] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc295_fixup_disable_dac3,
@@ -7791,6 +7798,16 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
 	},
+	[ALC282_FIXUP_ACER_DISABLE_LINEOUT] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1b, 0x411111f0 },
+			{ 0x18, 0x01a1913c }, /* use as headset mic, without its own jack detect */
+			{ },
+		},
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MODE
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -7805,11 +7822,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x0762, "Acer Aspire E1-472", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
 	SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
 	SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
+	SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK),
 	SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x1065, "Acer Aspire C20-820", ALC269VC_FIXUP_ACER_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK),
 	SND_PCI_QUIRK(0x1025, 0x1099, "Acer Aspire E5-523G", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x110e, "Acer Aspire ES1-432", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1025, 0x1166, "Acer Veriton N4640G", ALC269_FIXUP_LIFEBOOK),
+	SND_PCI_QUIRK(0x1025, 0x1167, "Acer Veriton N6640G", ALC269_FIXUP_LIFEBOOK),
 	SND_PCI_QUIRK(0x1025, 0x1246, "Acer Predator Helios 500", ALC299_FIXUP_PREDATOR_SPK),
 	SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS),
 	SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE),
@@ -7870,6 +7890,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x09bf, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0a2e, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1028, 0x0a30, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1028, 0x0a58, "Dell", ALC255_FIXUP_DELL_HEADSET_MIC),
 	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),
@@ -7943,11 +7964,17 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x8780, "HP ZBook Fury 17 G7 Mobile Workstation",
+		      ALC285_FIXUP_HP_GPIO_AMP_INIT),
+	SND_PCI_QUIRK(0x103c, 0x8783, "HP ZBook Fury 15 G7 Mobile Workstation",
+		      ALC285_FIXUP_HP_GPIO_AMP_INIT),
+	SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
@@ -8005,6 +8032,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE),
 	SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
+	SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
+	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),
@@ -8017,6 +8046,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	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),
 	SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x152d, 0x1082, "Quanta NL3", ALC269_FIXUP_LIFEBOOK),
 	SND_PCI_QUIRK(0x1558, 0x1323, "Clevo N130ZU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x1325, "System76 Darter Pro (darp5)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x1401, "Clevo L140[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
@@ -8109,6 +8139,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3151, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME),
 	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),
@@ -8564,6 +8595,22 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60140},
 		{0x19, 0x04a11030},
 		{0x21, 0x04211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0282, 0x1025, "Acer", ALC282_FIXUP_ACER_DISABLE_LINEOUT,
+		ALC282_STANDARD_PINS,
+		{0x12, 0x90a609c0},
+		{0x18, 0x03a11830},
+		{0x19, 0x04a19831},
+		{0x1a, 0x0481303f},
+		{0x1b, 0x04211020},
+		{0x21, 0x0321101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0282, 0x1025, "Acer", ALC282_FIXUP_ACER_DISABLE_LINEOUT,
+		ALC282_STANDARD_PINS,
+		{0x12, 0x90a60940},
+		{0x18, 0x03a11830},
+		{0x19, 0x04a19831},
+		{0x1a, 0x0481303f},
+		{0x1b, 0x04211020},
+		{0x21, 0x0321101f}),
 	SND_HDA_PIN_QUIRK(0x10ec0283, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC282_STANDARD_PINS,
 		{0x12, 0x90a60130},
diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index 7ef8f3105cdb..0ab40a8a68fb 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -1002,6 +1002,7 @@ static const struct hda_verb vt1802_init_verbs[] = {
 enum {
 	VIA_FIXUP_INTMIC_BOOST,
 	VIA_FIXUP_ASUS_G75,
+	VIA_FIXUP_POWER_SAVE,
 };
 
 static void via_fixup_intmic_boost(struct hda_codec *codec,
@@ -1011,6 +1012,13 @@ static void via_fixup_intmic_boost(struct hda_codec *codec,
 		override_mic_boost(codec, 0x30, 0, 2, 40);
 }
 
+static void via_fixup_power_save(struct hda_codec *codec,
+				 const struct hda_fixup *fix, int action)
+{
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		codec->power_save_node = 0;
+}
+
 static const struct hda_fixup via_fixups[] = {
 	[VIA_FIXUP_INTMIC_BOOST] = {
 		.type = HDA_FIXUP_FUNC,
@@ -1025,11 +1033,16 @@ static const struct hda_fixup via_fixups[] = {
 			{ }
 		}
 	},
+	[VIA_FIXUP_POWER_SAVE] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = via_fixup_power_save,
+	},
 };
 
 static const struct snd_pci_quirk vt2002p_fixups[] = {
 	SND_PCI_QUIRK(0x1043, 0x1487, "Asus G75", VIA_FIXUP_ASUS_G75),
 	SND_PCI_QUIRK(0x1043, 0x8532, "Asus X202E", VIA_FIXUP_INTMIC_BOOST),
+	SND_PCI_QUIRK(0x1558, 0x3501, "Clevo W35xSS_370SS", VIA_FIXUP_POWER_SAVE),
 	{}
 };
 
diff --git a/sound/soc/amd/raven/pci-acp3x.c b/sound/soc/amd/raven/pci-acp3x.c
index 8c138e490f0c..d3536fd6a124 100644
--- a/sound/soc/amd/raven/pci-acp3x.c
+++ b/sound/soc/amd/raven/pci-acp3x.c
@@ -140,21 +140,14 @@ static int snd_acp3x_probe(struct pci_dev *pci,
 		goto release_regions;
 	}
 
-	/* check for msi interrupt support */
-	ret = pci_enable_msi(pci);
-	if (ret)
-		/* msi is not enabled */
-		irqflags = IRQF_SHARED;
-	else
-		/* msi is enabled */
-		irqflags = 0;
+	irqflags = IRQF_SHARED;
 
 	addr = pci_resource_start(pci, 0);
 	adata->acp3x_base = devm_ioremap(&pci->dev, addr,
 					pci_resource_len(pci, 0));
 	if (!adata->acp3x_base) {
 		ret = -ENOMEM;
-		goto disable_msi;
+		goto release_regions;
 	}
 	pci_set_master(pci);
 	pci_set_drvdata(pci, adata);
@@ -162,7 +155,7 @@ static int snd_acp3x_probe(struct pci_dev *pci,
 	adata->pme_en = rv_readl(adata->acp3x_base + mmACP_PME_EN);
 	ret = acp3x_init(adata);
 	if (ret)
-		goto disable_msi;
+		goto release_regions;
 
 	val = rv_readl(adata->acp3x_base + mmACP_I2S_PIN_CONFIG);
 	switch (val) {
@@ -251,8 +244,6 @@ unregister_devs:
 de_init:
 	if (acp3x_deinit(adata->acp3x_base))
 		dev_err(&pci->dev, "ACP de-init failed\n");
-disable_msi:
-	pci_disable_msi(pci);
 release_regions:
 	pci_release_regions(pci);
 disable_pci:
@@ -311,7 +302,6 @@ static void snd_acp3x_remove(struct pci_dev *pci)
 		dev_err(&pci->dev, "ACP de-init failed\n");
 	pm_runtime_forbid(&pci->dev);
 	pm_runtime_get_noresume(&pci->dev);
-	pci_disable_msi(pci);
 	pci_release_regions(pci);
 	pci_disable_device(pci);
 }
diff --git a/sound/soc/amd/renoir/rn-pci-acp3x.c b/sound/soc/amd/renoir/rn-pci-acp3x.c
index fa169bf09886..deca8c7a0e87 100644
--- a/sound/soc/amd/renoir/rn-pci-acp3x.c
+++ b/sound/soc/amd/renoir/rn-pci-acp3x.c
@@ -171,6 +171,20 @@ static const struct dmi_system_id rn_acp_quirk_table[] = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "LNVNB161216"),
 		}
 	},
+	{
+		/* Lenovo ThinkPad E14 Gen 2 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "20T6CTO1WW"),
+		}
+	},
+	{
+		/* Lenovo ThinkPad X395 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "20NLCTO1WW"),
+		}
+	},
 	{}
 };
 
diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig
index 142373ec411a..9fe9471f4514 100644
--- a/sound/soc/atmel/Kconfig
+++ b/sound/soc/atmel/Kconfig
@@ -143,7 +143,7 @@ config SND_MCHP_SOC_SPDIFTX
 	  - sama7g5
 
 	  This S/PDIF TX driver is compliant with IEC-60958 standard and
-	  includes programable User Data and Channel Status fields.
+	  includes programmable User Data and Channel Status fields.
 
 config SND_MCHP_SOC_SPDIFRX
 	tristate "Microchip ASoC driver for boards using S/PDIF RX"
@@ -157,5 +157,5 @@ config SND_MCHP_SOC_SPDIFRX
 	  - sama7g5
 
 	  This S/PDIF RX driver is compliant with IEC-60958 standard and
-	  includes programable User Data and Channel Status fields.
+	  includes programmable User Data and Channel Status fields.
 endif
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index ba4eb54aafcb..9bf6bfdaf11e 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -457,7 +457,7 @@ config SND_SOC_ADAU7118_HW
 	help
 	  Enable support for the Analog Devices ADAU7118 8 Channel PDM-to-I2S/TDM
 	  Converter. In this mode, the device works in standalone mode which
-	  means that there is no bus to comunicate with it. Stereo mode is not
+	  means that there is no bus to communicate with it. Stereo mode is not
 	  supported in this mode.
 
 	  To compile this driver as a module, choose M here: the module
diff --git a/sound/soc/codecs/max98373-i2c.c b/sound/soc/codecs/max98373-i2c.c
index 92921e34f948..85f6865019d4 100644
--- a/sound/soc/codecs/max98373-i2c.c
+++ b/sound/soc/codecs/max98373-i2c.c
@@ -19,6 +19,12 @@
 #include <sound/tlv.h>
 #include "max98373.h"
 
+static const u32 max98373_i2c_cache_reg[] = {
+	MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK,
+	MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK,
+	MAX98373_R20B6_BDE_CUR_STATE_READBACK,
+};
+
 static struct reg_default max98373_reg[] = {
 	{MAX98373_R2000_SW_RESET, 0x00},
 	{MAX98373_R2001_INT_RAW1, 0x00},
@@ -472,6 +478,11 @@ static struct snd_soc_dai_driver max98373_dai[] = {
 static int max98373_suspend(struct device *dev)
 {
 	struct max98373_priv *max98373 = dev_get_drvdata(dev);
+	int i;
+
+	/* cache feedback register values before suspend */
+	for (i = 0; i < max98373->cache_num; i++)
+		regmap_read(max98373->regmap, max98373->cache[i].reg, &max98373->cache[i].val);
 
 	regcache_cache_only(max98373->regmap, true);
 	regcache_mark_dirty(max98373->regmap);
@@ -509,6 +520,7 @@ static int max98373_i2c_probe(struct i2c_client *i2c,
 {
 	int ret = 0;
 	int reg = 0;
+	int i;
 	struct max98373_priv *max98373 = NULL;
 
 	max98373 = devm_kzalloc(&i2c->dev, sizeof(*max98373), GFP_KERNEL);
@@ -534,6 +546,14 @@ static int max98373_i2c_probe(struct i2c_client *i2c,
 		return ret;
 	}
 
+	max98373->cache_num = ARRAY_SIZE(max98373_i2c_cache_reg);
+	max98373->cache = devm_kcalloc(&i2c->dev, max98373->cache_num,
+				       sizeof(*max98373->cache),
+				       GFP_KERNEL);
+
+	for (i = 0; i < max98373->cache_num; i++)
+		max98373->cache[i].reg = max98373_i2c_cache_reg[i];
+
 	/* voltage/current slot & gpio configuration */
 	max98373_slot_config(&i2c->dev, max98373);
 
diff --git a/sound/soc/codecs/max98373-sdw.c b/sound/soc/codecs/max98373-sdw.c
index ec2e79c57357..b8d471d79e93 100644
--- a/sound/soc/codecs/max98373-sdw.c
+++ b/sound/soc/codecs/max98373-sdw.c
@@ -23,6 +23,12 @@ struct sdw_stream_data {
 	struct sdw_stream_runtime *sdw_stream;
 };
 
+static const u32 max98373_sdw_cache_reg[] = {
+	MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK,
+	MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK,
+	MAX98373_R20B6_BDE_CUR_STATE_READBACK,
+};
+
 static struct reg_default max98373_reg[] = {
 	{MAX98373_R0040_SCP_INIT_STAT_1, 0x00},
 	{MAX98373_R0041_SCP_INIT_MASK_1, 0x00},
@@ -245,6 +251,11 @@ static const struct regmap_config max98373_sdw_regmap = {
 static __maybe_unused int max98373_suspend(struct device *dev)
 {
 	struct max98373_priv *max98373 = dev_get_drvdata(dev);
+	int i;
+
+	/* cache feedback register values before suspend */
+	for (i = 0; i < max98373->cache_num; i++)
+		regmap_read(max98373->regmap, max98373->cache[i].reg, &max98373->cache[i].val);
 
 	regcache_cache_only(max98373->regmap, true);
 
@@ -757,6 +768,7 @@ static int max98373_init(struct sdw_slave *slave, struct regmap *regmap)
 {
 	struct max98373_priv *max98373;
 	int ret;
+	int i;
 	struct device *dev = &slave->dev;
 
 	/*  Allocate and assign private driver data structure  */
@@ -768,6 +780,14 @@ static int max98373_init(struct sdw_slave *slave, struct regmap *regmap)
 	max98373->regmap = regmap;
 	max98373->slave = slave;
 
+	max98373->cache_num = ARRAY_SIZE(max98373_sdw_cache_reg);
+	max98373->cache = devm_kcalloc(dev, max98373->cache_num,
+				       sizeof(*max98373->cache),
+				       GFP_KERNEL);
+
+	for (i = 0; i < max98373->cache_num; i++)
+		max98373->cache[i].reg = max98373_sdw_cache_reg[i];
+
 	/* Read voltage and slot configuration */
 	max98373_slot_config(dev, max98373);
 
diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c
index 929bb1798c43..31d571d4fac1 100644
--- a/sound/soc/codecs/max98373.c
+++ b/sound/soc/codecs/max98373.c
@@ -168,6 +168,31 @@ static SOC_ENUM_SINGLE_DECL(max98373_adc_samplerate_enum,
 			    MAX98373_R2051_MEAS_ADC_SAMPLING_RATE, 0,
 			    max98373_ADC_samplerate_text);
 
+static int max98373_feedback_get(struct snd_kcontrol *kcontrol,
+				 struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+	struct soc_mixer_control *mc =
+		(struct soc_mixer_control *)kcontrol->private_value;
+	struct max98373_priv *max98373 = snd_soc_component_get_drvdata(component);
+	int i;
+
+	if (snd_soc_component_get_bias_level(component) == SND_SOC_BIAS_OFF) {
+		/*
+		 * Register values will be cached before suspend. The cached value
+		 * will be a valid value and userspace will happy with that.
+		 */
+		for (i = 0; i < max98373->cache_num; i++) {
+			if (mc->reg == max98373->cache[i].reg) {
+				ucontrol->value.integer.value[0] = max98373->cache[i].val;
+				return 0;
+			}
+		}
+	}
+
+	return snd_soc_put_volsw(kcontrol, ucontrol);
+}
+
 static const struct snd_kcontrol_new max98373_snd_controls[] = {
 SOC_SINGLE("Digital Vol Sel Switch", MAX98373_R203F_AMP_DSP_CFG,
 	MAX98373_AMP_VOL_SEL_SHIFT, 1, 0),
@@ -209,8 +234,10 @@ SOC_SINGLE("ADC PVDD FLT Switch", MAX98373_R2052_MEAS_ADC_PVDD_FLT_CFG,
 	MAX98373_FLT_EN_SHIFT, 1, 0),
 SOC_SINGLE("ADC TEMP FLT Switch", MAX98373_R2053_MEAS_ADC_THERM_FLT_CFG,
 	MAX98373_FLT_EN_SHIFT, 1, 0),
-SOC_SINGLE("ADC PVDD", MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK, 0, 0xFF, 0),
-SOC_SINGLE("ADC TEMP", MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK, 0, 0xFF, 0),
+SOC_SINGLE_EXT("ADC PVDD", MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK, 0, 0xFF, 0,
+	max98373_feedback_get, NULL),
+SOC_SINGLE_EXT("ADC TEMP", MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK, 0, 0xFF, 0,
+	max98373_feedback_get, NULL),
 SOC_SINGLE("ADC PVDD FLT Coeff", MAX98373_R2052_MEAS_ADC_PVDD_FLT_CFG,
 	0, 0x3, 0),
 SOC_SINGLE("ADC TEMP FLT Coeff", MAX98373_R2053_MEAS_ADC_THERM_FLT_CFG,
@@ -226,7 +253,8 @@ SOC_SINGLE("BDE LVL1 Thresh", MAX98373_R2097_BDE_L1_THRESH, 0, 0xFF, 0),
 SOC_SINGLE("BDE LVL2 Thresh", MAX98373_R2098_BDE_L2_THRESH, 0, 0xFF, 0),
 SOC_SINGLE("BDE LVL3 Thresh", MAX98373_R2099_BDE_L3_THRESH, 0, 0xFF, 0),
 SOC_SINGLE("BDE LVL4 Thresh", MAX98373_R209A_BDE_L4_THRESH, 0, 0xFF, 0),
-SOC_SINGLE("BDE Active Level", MAX98373_R20B6_BDE_CUR_STATE_READBACK, 0, 8, 0),
+SOC_SINGLE_EXT("BDE Active Level", MAX98373_R20B6_BDE_CUR_STATE_READBACK, 0, 8, 0,
+	max98373_feedback_get, NULL),
 SOC_SINGLE("BDE Clip Mode Switch", MAX98373_R2092_BDE_CLIPPER_MODE, 0, 1, 0),
 SOC_SINGLE("BDE Thresh Hysteresis", MAX98373_R209B_BDE_THRESH_HYST, 0, 0xFF, 0),
 SOC_SINGLE("BDE Hold Time", MAX98373_R2090_BDE_LVL_HOLD, 0, 0xFF, 0),
diff --git a/sound/soc/codecs/max98373.h b/sound/soc/codecs/max98373.h
index 4ab29b9d51c7..71f5a5228f34 100644
--- a/sound/soc/codecs/max98373.h
+++ b/sound/soc/codecs/max98373.h
@@ -203,6 +203,11 @@
 /* MAX98373_R2000_SW_RESET */
 #define MAX98373_SOFT_RESET (0x1 << 0)
 
+struct max98373_cache {
+	u32 reg;
+	u32 val;
+};
+
 struct max98373_priv {
 	struct regmap *regmap;
 	int reset_gpio;
@@ -212,6 +217,9 @@ struct max98373_priv {
 	bool interleave_mode;
 	unsigned int ch_size;
 	bool tdm_mode;
+	/* cache for reading a valid fake feedback value */
+	struct max98373_cache *cache;
+	int cache_num;
 	/* variables to support soundwire */
 	struct sdw_slave *slave;
 	bool hw_init;
diff --git a/sound/soc/codecs/rt711.c b/sound/soc/codecs/rt711.c
index 5771c02c3459..85f744184a60 100644
--- a/sound/soc/codecs/rt711.c
+++ b/sound/soc/codecs/rt711.c
@@ -462,6 +462,8 @@ static int rt711_set_amp_gain_put(struct snd_kcontrol *kcontrol,
 	unsigned int read_ll, read_rl;
 	int i;
 
+	mutex_lock(&rt711->calibrate_mutex);
+
 	/* Can't use update bit function, so read the original value first */
 	addr_h = mc->reg;
 	addr_l = mc->rreg;
@@ -547,6 +549,8 @@ static int rt711_set_amp_gain_put(struct snd_kcontrol *kcontrol,
 	if (dapm->bias_level <= SND_SOC_BIAS_STANDBY)
 		regmap_write(rt711->regmap,
 				RT711_SET_AUDIO_POWER_STATE, AC_PWRST_D3);
+
+	mutex_unlock(&rt711->calibrate_mutex);
 	return 0;
 }
 
@@ -859,9 +863,11 @@ static int rt711_set_bias_level(struct snd_soc_component *component,
 		break;
 
 	case SND_SOC_BIAS_STANDBY:
+		mutex_lock(&rt711->calibrate_mutex);
 		regmap_write(rt711->regmap,
 			RT711_SET_AUDIO_POWER_STATE,
 			AC_PWRST_D3);
+		mutex_unlock(&rt711->calibrate_mutex);
 		break;
 
 	default:
diff --git a/sound/soc/fsl/imx-hdmi.c b/sound/soc/fsl/imx-hdmi.c
index 2c2a76a71940..ede4a9ad1054 100644
--- a/sound/soc/fsl/imx-hdmi.c
+++ b/sound/soc/fsl/imx-hdmi.c
@@ -164,6 +164,7 @@ static int imx_hdmi_probe(struct platform_device *pdev)
 
 	if ((hdmi_out && hdmi_in) || (!hdmi_out && !hdmi_in)) {
 		dev_err(&pdev->dev, "Invalid HDMI DAI link\n");
+		ret = -EINVAL;
 		goto fail;
 	}
 
diff --git a/sound/soc/intel/boards/haswell.c b/sound/soc/intel/boards/haswell.c
index c55d1239e705..c763bfeb1f38 100644
--- a/sound/soc/intel/boards/haswell.c
+++ b/sound/soc/intel/boards/haswell.c
@@ -189,6 +189,7 @@ static struct platform_driver haswell_audio = {
 	.probe = haswell_audio_probe,
 	.driver = {
 		.name = "haswell-audio",
+		.pm = &snd_soc_pm_ops,
 	},
 };
 
diff --git a/sound/soc/intel/skylake/cnl-sst.c b/sound/soc/intel/skylake/cnl-sst.c
index fcd8dff27ae8..1275c149acc0 100644
--- a/sound/soc/intel/skylake/cnl-sst.c
+++ b/sound/soc/intel/skylake/cnl-sst.c
@@ -224,6 +224,7 @@ static int cnl_set_dsp_D0(struct sst_dsp *ctx, unsigned int core_id)
 				"dsp boot timeout, status=%#x error=%#x\n",
 				sst_dsp_shim_read(ctx, CNL_ADSP_FW_STATUS),
 				sst_dsp_shim_read(ctx, CNL_ADSP_ERROR_CODE));
+			ret = -ETIMEDOUT;
 			goto err;
 		}
 	} else {
diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c
index c8664ab80d45..87cac440b369 100644
--- a/sound/soc/meson/axg-tdm-interface.c
+++ b/sound/soc/meson/axg-tdm-interface.c
@@ -467,8 +467,20 @@ static int axg_tdm_iface_set_bias_level(struct snd_soc_component *component,
 	return ret;
 }
 
+static const struct snd_soc_dapm_widget axg_tdm_iface_dapm_widgets[] = {
+	SND_SOC_DAPM_SIGGEN("Playback Signal"),
+};
+
+static const struct snd_soc_dapm_route axg_tdm_iface_dapm_routes[] = {
+	{ "Loopback", NULL, "Playback Signal" },
+};
+
 static const struct snd_soc_component_driver axg_tdm_iface_component_drv = {
-	.set_bias_level	= axg_tdm_iface_set_bias_level,
+	.dapm_widgets		= axg_tdm_iface_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(axg_tdm_iface_dapm_widgets),
+	.dapm_routes		= axg_tdm_iface_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(axg_tdm_iface_dapm_routes),
+	.set_bias_level		= axg_tdm_iface_set_bias_level,
 };
 
 static const struct of_device_id axg_tdm_iface_of_match[] = {
diff --git a/sound/soc/meson/axg-tdmin.c b/sound/soc/meson/axg-tdmin.c
index 88ed95ae886b..b4faf9d5c1aa 100644
--- a/sound/soc/meson/axg-tdmin.c
+++ b/sound/soc/meson/axg-tdmin.c
@@ -228,15 +228,6 @@ static const struct axg_tdm_formatter_driver axg_tdmin_drv = {
 	.regmap_cfg	= &axg_tdmin_regmap_cfg,
 	.ops		= &axg_tdmin_ops,
 	.quirks		= &(const struct axg_tdm_formatter_hw) {
-		.skew_offset	= 2,
-	},
-};
-
-static const struct axg_tdm_formatter_driver g12a_tdmin_drv = {
-	.component_drv	= &axg_tdmin_component_drv,
-	.regmap_cfg	= &axg_tdmin_regmap_cfg,
-	.ops		= &axg_tdmin_ops,
-	.quirks		= &(const struct axg_tdm_formatter_hw) {
 		.skew_offset	= 3,
 	},
 };
@@ -247,10 +238,10 @@ static const struct of_device_id axg_tdmin_of_match[] = {
 		.data = &axg_tdmin_drv,
 	}, {
 		.compatible = "amlogic,g12a-tdmin",
-		.data = &g12a_tdmin_drv,
+		.data = &axg_tdmin_drv,
 	}, {
 		.compatible = "amlogic,sm1-tdmin",
-		.data = &g12a_tdmin_drv,
+		.data = &axg_tdmin_drv,
 	}, {}
 };
 MODULE_DEVICE_TABLE(of, axg_tdmin_of_match);
diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c
index af684fd19ab9..c5e99c2d89c7 100644
--- a/sound/soc/qcom/lpass-cpu.c
+++ b/sound/soc/qcom/lpass-cpu.c
@@ -270,18 +270,6 @@ static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream,
 	struct lpaif_i2sctl *i2sctl = drvdata->i2sctl;
 	unsigned int id = dai->driver->id;
 	int ret = -EINVAL;
-	unsigned int val = 0;
-
-	ret = regmap_read(drvdata->lpaif_map,
-				LPAIF_I2SCTL_REG(drvdata->variant, dai->driver->id), &val);
-	if (ret) {
-		dev_err(dai->dev, "error reading from i2sctl reg: %d\n", ret);
-		return ret;
-	}
-	if (val == LPAIF_I2SCTL_RESET_STATE) {
-		dev_err(dai->dev, "error in i2sctl register state\n");
-		return -ENOTRECOVERABLE;
-	}
 
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
@@ -454,20 +442,16 @@ static bool lpass_cpu_regmap_volatile(struct device *dev, unsigned int reg)
 	struct lpass_variant *v = drvdata->variant;
 	int i;
 
-	for (i = 0; i < v->i2s_ports; ++i)
-		if (reg == LPAIF_I2SCTL_REG(v, i))
-			return true;
 	for (i = 0; i < v->irq_ports; ++i)
 		if (reg == LPAIF_IRQSTAT_REG(v, i))
 			return true;
 
 	for (i = 0; i < v->rdma_channels; ++i)
-		if (reg == LPAIF_RDMACURR_REG(v, i) || reg == LPAIF_RDMACTL_REG(v, i))
+		if (reg == LPAIF_RDMACURR_REG(v, i))
 			return true;
 
 	for (i = 0; i < v->wrdma_channels; ++i)
-		if (reg == LPAIF_WRDMACURR_REG(v, i + v->wrdma_channel_start) ||
-			reg == LPAIF_WRDMACTL_REG(v, i + v->wrdma_channel_start))
+		if (reg == LPAIF_WRDMACURR_REG(v, i + v->wrdma_channel_start))
 			return true;
 
 	return false;
diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c
index 80b09dede5f9..d1c248590f3a 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -452,7 +452,6 @@ static int lpass_platform_pcmops_trigger(struct snd_soc_component *component,
 	unsigned int reg_irqclr = 0, val_irqclr = 0;
 	unsigned int  reg_irqen = 0, val_irqen = 0, val_mask = 0;
 	unsigned int dai_id = cpu_dai->driver->id;
-	unsigned int dma_ctrl_reg = 0;
 
 	ch = pcm_data->dma_ch;
 	if (dir ==  SNDRV_PCM_STREAM_PLAYBACK) {
@@ -469,17 +468,7 @@ static int lpass_platform_pcmops_trigger(struct snd_soc_component *component,
 		id = pcm_data->dma_ch - v->wrdma_channel_start;
 		map = drvdata->lpaif_map;
 	}
-	ret = regmap_read(map, LPAIF_DMACTL_REG(v, ch, dir, dai_id), &dma_ctrl_reg);
-	if (ret) {
-		dev_err(soc_runtime->dev, "error reading from rdmactl reg: %d\n", ret);
-		return ret;
-	}
 
-	if (dma_ctrl_reg == LPAIF_DMACTL_RESET_STATE ||
-		dma_ctrl_reg == LPAIF_DMACTL_RESET_STATE + 1) {
-		dev_err(soc_runtime->dev, "error in rdmactl register state\n");
-		return -ENOTRECOVERABLE;
-	}
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_RESUME:
@@ -500,7 +489,6 @@ static int lpass_platform_pcmops_trigger(struct snd_soc_component *component,
 					"error writing to rdmactl reg: %d\n", ret);
 				return ret;
 			}
-			map = drvdata->hdmiif_map;
 			reg_irqclr = LPASS_HDMITX_APP_IRQCLEAR_REG(v);
 			val_irqclr = (LPAIF_IRQ_ALL(ch) |
 					LPAIF_IRQ_HDMI_REQ_ON_PRELOAD(ch) |
@@ -519,7 +507,6 @@ static int lpass_platform_pcmops_trigger(struct snd_soc_component *component,
 			break;
 		case MI2S_PRIMARY:
 		case MI2S_SECONDARY:
-			map = drvdata->lpaif_map;
 			reg_irqclr = LPAIF_IRQCLEAR_REG(v, LPAIF_IRQ_PORT_HOST);
 			val_irqclr = LPAIF_IRQ_ALL(ch);
 
@@ -563,7 +550,6 @@ static int lpass_platform_pcmops_trigger(struct snd_soc_component *component,
 					"error writing to rdmactl reg: %d\n", ret);
 				return ret;
 			}
-			map = drvdata->hdmiif_map;
 			reg_irqen = LPASS_HDMITX_APP_IRQEN_REG(v);
 			val_mask = (LPAIF_IRQ_ALL(ch) |
 					LPAIF_IRQ_HDMI_REQ_ON_PRELOAD(ch) |
@@ -573,7 +559,6 @@ static int lpass_platform_pcmops_trigger(struct snd_soc_component *component,
 			break;
 		case MI2S_PRIMARY:
 		case MI2S_SECONDARY:
-			map = drvdata->lpaif_map;
 			reg_irqen = LPAIF_IRQEN_REG(v, LPAIF_IRQ_PORT_HOST);
 			val_mask = LPAIF_IRQ_ALL(ch);
 			val_irqen = 0;
@@ -838,6 +823,39 @@ static void lpass_platform_pcm_free(struct snd_soc_component *component,
 	}
 }
 
+static int lpass_platform_pcmops_suspend(struct snd_soc_component *component)
+{
+	struct lpass_data *drvdata = snd_soc_component_get_drvdata(component);
+	struct regmap *map;
+	unsigned int dai_id = component->id;
+
+	if (dai_id == LPASS_DP_RX)
+		map = drvdata->hdmiif_map;
+	else
+		map = drvdata->lpaif_map;
+
+	regcache_cache_only(map, true);
+	regcache_mark_dirty(map);
+
+	return 0;
+}
+
+static int lpass_platform_pcmops_resume(struct snd_soc_component *component)
+{
+	struct lpass_data *drvdata = snd_soc_component_get_drvdata(component);
+	struct regmap *map;
+	unsigned int dai_id = component->id;
+
+	if (dai_id == LPASS_DP_RX)
+		map = drvdata->hdmiif_map;
+	else
+		map = drvdata->lpaif_map;
+
+	regcache_cache_only(map, false);
+	return regcache_sync(map);
+}
+
+
 static const struct snd_soc_component_driver lpass_component_driver = {
 	.name		= DRV_NAME,
 	.open		= lpass_platform_pcmops_open,
@@ -850,6 +868,8 @@ static const struct snd_soc_component_driver lpass_component_driver = {
 	.mmap		= lpass_platform_pcmops_mmap,
 	.pcm_construct	= lpass_platform_pcm_new,
 	.pcm_destruct	= lpass_platform_pcm_free,
+	.suspend		= lpass_platform_pcmops_suspend,
+	.resume			= lpass_platform_pcmops_resume,
 
 };
 
diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c
index b9aacf3d3b29..abdfd9cf91e2 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -366,25 +366,27 @@ void rsnd_adg_clk_control(struct rsnd_priv *priv, int enable)
 	struct rsnd_adg *adg = rsnd_priv_to_adg(priv);
 	struct device *dev = rsnd_priv_to_dev(priv);
 	struct clk *clk;
-	int i, ret;
+	int i;
 
 	for_each_rsnd_clk(clk, adg, i) {
-		ret = 0;
 		if (enable) {
-			ret = clk_prepare_enable(clk);
+			int ret = clk_prepare_enable(clk);
 
 			/*
 			 * We shouldn't use clk_get_rate() under
 			 * atomic context. Let's keep it when
 			 * rsnd_adg_clk_enable() was called
 			 */
-			adg->clk_rate[i] = clk_get_rate(adg->clk[i]);
+			adg->clk_rate[i] = 0;
+			if (ret < 0)
+				dev_warn(dev, "can't use clk %d\n", i);
+			else
+				adg->clk_rate[i] = clk_get_rate(clk);
 		} else {
-			clk_disable_unprepare(clk);
+			if (adg->clk_rate[i])
+				clk_disable_unprepare(clk);
+			adg->clk_rate[i] = 0;
 		}
-
-		if (ret < 0)
-			dev_warn(dev, "can't use clk %d\n", i);
 	}
 }
 
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 9f0c86cbdcca..2b75d0139e47 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -2486,6 +2486,7 @@ void snd_soc_dapm_free_widget(struct snd_soc_dapm_widget *w)
 	enum snd_soc_dapm_direction dir;
 
 	list_del(&w->list);
+	list_del(&w->dirty);
 	/*
 	 * remove source and sink paths associated to this widget.
 	 * While removing the path, remove reference to it from both
diff --git a/sound/soc/sof/Kconfig b/sound/soc/sof/Kconfig
index 031dad5fc4c7..3e8b6c035ce3 100644
--- a/sound/soc/sof/Kconfig
+++ b/sound/soc/sof/Kconfig
@@ -122,7 +122,7 @@ config SND_SOC_SOF_DEBUG_XRUN_STOP
 	bool "SOF stop on XRUN"
 	help
 	  This option forces PCMs to stop on any XRUN event. This is useful to
-	  preserve any trace data ond pipeline status prior to the XRUN.
+	  preserve any trace data and pipeline status prior to the XRUN.
 	  Say Y if you are debugging SOF FW pipeline XRUNs.
 	  If unsure select "N".
 
diff --git a/sound/usb/card.c b/sound/usb/card.c
index cb0b6582dfee..e08fbf8e3ee0 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -383,6 +383,9 @@ static const struct usb_audio_device_name usb_audio_names[] = {
 	/* ASUS ROG Strix */
 	PROFILE_NAME(0x0b05, 0x1917,
 		     "Realtek", "ALC1220-VB-DT", "Realtek-ALC1220-VB-Desktop"),
+	/* ASUS PRIME TRX40 PRO-S */
+	PROFILE_NAME(0x0b05, 0x1918,
+		     "Realtek", "ALC1220-VB-DT", "Realtek-ALC1220-VB-Desktop"),
 
 	/* Dell WD15 Dock */
 	PROFILE_NAME(0x0bda, 0x4014, "Dell", "WD15 Dock", "Dell-WD15-Dock"),
@@ -447,10 +450,8 @@ lookup_device_name(u32 id)
 static void snd_usb_audio_free(struct snd_card *card)
 {
 	struct snd_usb_audio *chip = card->private_data;
-	struct snd_usb_endpoint *ep, *n;
 
-	list_for_each_entry_safe(ep, n, &chip->ep_list, list)
-		snd_usb_endpoint_free(ep);
+	snd_usb_endpoint_free_all(chip);
 
 	mutex_destroy(&chip->mutex);
 	if (!atomic_read(&chip->shutdown))
@@ -608,6 +609,7 @@ static int snd_usb_audio_create(struct usb_interface *intf,
 	chip->usb_id = usb_id;
 	INIT_LIST_HEAD(&chip->pcm_list);
 	INIT_LIST_HEAD(&chip->ep_list);
+	INIT_LIST_HEAD(&chip->iface_ref_list);
 	INIT_LIST_HEAD(&chip->midi_list);
 	INIT_LIST_HEAD(&chip->mixer_list);
 
diff --git a/sound/usb/card.h b/sound/usb/card.h
index 6a027c349194..37091b117614 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -18,6 +18,7 @@ struct audioformat {
 	unsigned int frame_size;	/* samples per frame for non-audio */
 	unsigned char iface;		/* interface number */
 	unsigned char altsetting;	/* corresponding alternate setting */
+	unsigned char ep_idx;		/* endpoint array index */
 	unsigned char altset_idx;	/* array index of altenate setting */
 	unsigned char attributes;	/* corresponding attributes of cs endpoint */
 	unsigned char endpoint;		/* endpoint */
@@ -42,6 +43,7 @@ struct audioformat {
 };
 
 struct snd_usb_substream;
+struct snd_usb_iface_ref;
 struct snd_usb_endpoint;
 struct snd_usb_power_domain;
 
@@ -58,6 +60,7 @@ struct snd_urb_ctx {
 
 struct snd_usb_endpoint {
 	struct snd_usb_audio *chip;
+	struct snd_usb_iface_ref *iface_ref;
 
 	int opened;		/* open refcount; protect with chip->mutex */
 	atomic_t running;	/* running status */
diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index e940dcee792b..31051f2be46d 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -534,6 +534,12 @@ static int set_sample_rate_v1(struct snd_usb_audio *chip,
 	}
 
 	crate = data[0] | (data[1] << 8) | (data[2] << 16);
+	if (!crate) {
+		dev_info(&dev->dev, "failed to read current rate; disabling the check\n");
+		chip->sample_rate_read_error = 3; /* three strikes, see above */
+		return 0;
+	}
+
 	if (crate != rate) {
 		dev_warn(&dev->dev, "current rate %d is different from the runtime rate %d\n", crate, rate);
 		// runtime->rate = crate;
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 162da7a50046..fe73fe3ff2bc 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -24,6 +24,14 @@
 #define EP_FLAG_RUNNING		1
 #define EP_FLAG_STOPPING	2
 
+/* interface refcounting */
+struct snd_usb_iface_ref {
+	unsigned char iface;
+	bool need_setup;
+	int opened;
+	struct list_head list;
+};
+
 /*
  * snd_usb_endpoint is a model that abstracts everything related to an
  * USB endpoint and its streaming.
@@ -489,6 +497,28 @@ exit_clear:
 }
 
 /*
+ * Find or create a refcount object for the given interface
+ *
+ * The objects are released altogether in snd_usb_endpoint_free_all()
+ */
+static struct snd_usb_iface_ref *
+iface_ref_find(struct snd_usb_audio *chip, int iface)
+{
+	struct snd_usb_iface_ref *ip;
+
+	list_for_each_entry(ip, &chip->iface_ref_list, list)
+		if (ip->iface == iface)
+			return ip;
+
+	ip = kzalloc(sizeof(*ip), GFP_KERNEL);
+	if (!ip)
+		return NULL;
+	ip->iface = iface;
+	list_add_tail(&ip->list, &chip->iface_ref_list);
+	return ip;
+}
+
+/*
  * Get the existing endpoint object corresponding EP
  * Returns NULL if not present.
  */
@@ -520,8 +550,8 @@ snd_usb_get_endpoint(struct snd_usb_audio *chip, int ep_num)
  *
  * Returns zero on success or a negative error code.
  *
- * New endpoints will be added to chip->ep_list and must be freed by
- * calling snd_usb_endpoint_free().
+ * New endpoints will be added to chip->ep_list and freed by
+ * calling snd_usb_endpoint_free_all().
  *
  * For SND_USB_ENDPOINT_TYPE_SYNC, the caller needs to guarantee that
  * bNumEndpoints > 1 beforehand.
@@ -653,11 +683,17 @@ snd_usb_endpoint_open(struct snd_usb_audio *chip,
 		} else {
 			ep->iface = fp->iface;
 			ep->altsetting = fp->altsetting;
-			ep->ep_idx = 0;
+			ep->ep_idx = fp->ep_idx;
 		}
 		usb_audio_dbg(chip, "Open EP 0x%x, iface=%d:%d, idx=%d\n",
 			      ep_num, ep->iface, ep->altsetting, ep->ep_idx);
 
+		ep->iface_ref = iface_ref_find(chip, ep->iface);
+		if (!ep->iface_ref) {
+			ep = NULL;
+			goto unlock;
+		}
+
 		ep->cur_audiofmt = fp;
 		ep->cur_channels = fp->channels;
 		ep->cur_rate = params_rate(params);
@@ -681,6 +717,11 @@ snd_usb_endpoint_open(struct snd_usb_audio *chip,
 			      ep->implicit_fb_sync);
 
 	} else {
+		if (WARN_ON(!ep->iface_ref)) {
+			ep = NULL;
+			goto unlock;
+		}
+
 		if (!endpoint_compatible(ep, fp, params)) {
 			usb_audio_err(chip, "Incompatible EP setup for 0x%x\n",
 				      ep_num);
@@ -692,6 +733,9 @@ snd_usb_endpoint_open(struct snd_usb_audio *chip,
 			      ep_num, ep->opened);
 	}
 
+	if (!ep->iface_ref->opened++)
+		ep->iface_ref->need_setup = true;
+
 	ep->opened++;
 
  unlock:
@@ -760,12 +804,16 @@ void snd_usb_endpoint_close(struct snd_usb_audio *chip,
 	mutex_lock(&chip->mutex);
 	usb_audio_dbg(chip, "Closing EP 0x%x (count %d)\n",
 		      ep->ep_num, ep->opened);
-	if (!--ep->opened) {
+
+	if (!--ep->iface_ref->opened)
 		endpoint_set_interface(chip, ep, false);
+
+	if (!--ep->opened) {
 		ep->iface = 0;
 		ep->altsetting = 0;
 		ep->cur_audiofmt = NULL;
 		ep->cur_rate = 0;
+		ep->iface_ref = NULL;
 		usb_audio_dbg(chip, "EP 0x%x closed\n", ep->ep_num);
 	}
 	mutex_unlock(&chip->mutex);
@@ -775,6 +823,8 @@ void snd_usb_endpoint_close(struct snd_usb_audio *chip,
 void snd_usb_endpoint_suspend(struct snd_usb_endpoint *ep)
 {
 	ep->need_setup = true;
+	if (ep->iface_ref)
+		ep->iface_ref->need_setup = true;
 }
 
 /*
@@ -1195,11 +1245,13 @@ int snd_usb_endpoint_configure(struct snd_usb_audio *chip,
 	int err = 0;
 
 	mutex_lock(&chip->mutex);
+	if (WARN_ON(!ep->iface_ref))
+		goto unlock;
 	if (!ep->need_setup)
 		goto unlock;
 
-	/* No need to (re-)configure the sync EP belonging to the same altset */
-	if (ep->ep_idx) {
+	/* If the interface has been already set up, just set EP parameters */
+	if (!ep->iface_ref->need_setup) {
 		err = snd_usb_endpoint_set_params(chip, ep);
 		if (err < 0)
 			goto unlock;
@@ -1242,6 +1294,8 @@ int snd_usb_endpoint_configure(struct snd_usb_audio *chip,
 			goto unlock;
 	}
 
+	ep->iface_ref->need_setup = false;
+
  done:
 	ep->need_setup = false;
 	err = 1;
@@ -1387,15 +1441,21 @@ void snd_usb_endpoint_release(struct snd_usb_endpoint *ep)
 }
 
 /**
- * snd_usb_endpoint_free: Free the resources of an snd_usb_endpoint
+ * snd_usb_endpoint_free_all: Free the resources of an snd_usb_endpoint
+ * @card: The chip
  *
- * @ep: the endpoint to free
- *
- * This free all resources of the given ep.
+ * This free all endpoints and those resources
  */
-void snd_usb_endpoint_free(struct snd_usb_endpoint *ep)
+void snd_usb_endpoint_free_all(struct snd_usb_audio *chip)
 {
-	kfree(ep);
+	struct snd_usb_endpoint *ep, *en;
+	struct snd_usb_iface_ref *ip, *in;
+
+	list_for_each_entry_safe(ep, en, &chip->ep_list, list)
+		kfree(ep);
+
+	list_for_each_entry_safe(ip, in, &chip->iface_ref_list, list)
+		kfree(ip);
 }
 
 /*
diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h
index 11e3bb839fd7..eea4ca49876d 100644
--- a/sound/usb/endpoint.h
+++ b/sound/usb/endpoint.h
@@ -42,7 +42,7 @@ void snd_usb_endpoint_sync_pending_stop(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_suspend(struct snd_usb_endpoint *ep);
 int  snd_usb_endpoint_activate(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_release(struct snd_usb_endpoint *ep);
-void snd_usb_endpoint_free(struct snd_usb_endpoint *ep);
+void snd_usb_endpoint_free_all(struct snd_usb_audio *chip);
 
 int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep);
 int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep,
diff --git a/sound/usb/implicit.c b/sound/usb/implicit.c
index 4e911d200562..1ac2cc6c33fb 100644
--- a/sound/usb/implicit.c
+++ b/sound/usb/implicit.c
@@ -58,8 +58,6 @@ static const struct snd_usb_implicit_fb_match playback_implicit_fb_quirks[] = {
 	IMPLICIT_FB_FIXED_DEV(0x0499, 0x172f, 0x81, 2), /* Steinberg UR22C */
 	IMPLICIT_FB_FIXED_DEV(0x0d9a, 0x00df, 0x81, 2), /* RTX6001 */
 	IMPLICIT_FB_FIXED_DEV(0x22f0, 0x0006, 0x81, 3), /* Allen&Heath Qu-16 */
-	IMPLICIT_FB_FIXED_DEV(0x2b73, 0x000a, 0x82, 0), /* Pioneer DJ DJM-900NXS2 */
-	IMPLICIT_FB_FIXED_DEV(0x2b73, 0x0017, 0x82, 0), /* Pioneer DJ DJM-250MK2 */
 	IMPLICIT_FB_FIXED_DEV(0x1686, 0xf029, 0x82, 2), /* Zoom UAC-2 */
 	IMPLICIT_FB_FIXED_DEV(0x2466, 0x8003, 0x86, 2), /* Fractal Audio Axe-Fx II */
 	IMPLICIT_FB_FIXED_DEV(0x0499, 0x172a, 0x86, 2), /* Yamaha MODX */
@@ -74,9 +72,12 @@ static const struct snd_usb_implicit_fb_match playback_implicit_fb_quirks[] = {
 
 	/* No quirk for playback but with capture quirk (see below) */
 	IMPLICIT_FB_SKIP_DEV(0x0582, 0x0130),	/* BOSS BR-80 */
+	IMPLICIT_FB_SKIP_DEV(0x0582, 0x0171),   /* BOSS RC-505 */
 	IMPLICIT_FB_SKIP_DEV(0x0582, 0x0189),	/* BOSS GT-100v2 */
+	IMPLICIT_FB_SKIP_DEV(0x0582, 0x01d6),	/* BOSS GT-1 */
 	IMPLICIT_FB_SKIP_DEV(0x0582, 0x01d8),	/* BOSS Katana */
 	IMPLICIT_FB_SKIP_DEV(0x0582, 0x01e5),	/* BOSS GT-001 */
+	IMPLICIT_FB_SKIP_DEV(0x0582, 0x0203),   /* BOSS AD-10 */
 
 	{} /* terminator */
 };
@@ -84,9 +85,12 @@ static const struct snd_usb_implicit_fb_match playback_implicit_fb_quirks[] = {
 /* Implicit feedback quirk table for capture: only FIXED type */
 static const struct snd_usb_implicit_fb_match capture_implicit_fb_quirks[] = {
 	IMPLICIT_FB_FIXED_DEV(0x0582, 0x0130, 0x0d, 0x01), /* BOSS BR-80 */
+	IMPLICIT_FB_FIXED_DEV(0x0582, 0x0171, 0x0d, 0x01), /* BOSS RC-505 */
 	IMPLICIT_FB_FIXED_DEV(0x0582, 0x0189, 0x0d, 0x01), /* BOSS GT-100v2 */
+	IMPLICIT_FB_FIXED_DEV(0x0582, 0x01d6, 0x0d, 0x01), /* BOSS GT-1 */
 	IMPLICIT_FB_FIXED_DEV(0x0582, 0x01d8, 0x0d, 0x01), /* BOSS Katana */
 	IMPLICIT_FB_FIXED_DEV(0x0582, 0x01e5, 0x0d, 0x01), /* BOSS GT-001 */
+	IMPLICIT_FB_FIXED_DEV(0x0582, 0x0203, 0x0d, 0x01), /* BOSS AD-10 */
 
 	{} /* terminator */
 };
@@ -94,7 +98,7 @@ static const struct snd_usb_implicit_fb_match capture_implicit_fb_quirks[] = {
 /* set up sync EP information on the audioformat */
 static int add_implicit_fb_sync_ep(struct snd_usb_audio *chip,
 				   struct audioformat *fmt,
-				   int ep, int ifnum,
+				   int ep, int ep_idx, int ifnum,
 				   const struct usb_host_interface *alts)
 {
 	struct usb_interface *iface;
@@ -109,7 +113,7 @@ static int add_implicit_fb_sync_ep(struct snd_usb_audio *chip,
 	fmt->sync_ep = ep;
 	fmt->sync_iface = ifnum;
 	fmt->sync_altsetting = alts->desc.bAlternateSetting;
-	fmt->sync_ep_idx = 0;
+	fmt->sync_ep_idx = ep_idx;
 	fmt->implicit_fb = 1;
 	usb_audio_dbg(chip,
 		      "%d:%d: added %s implicit_fb sync_ep %x, iface %d:%d\n",
@@ -141,7 +145,7 @@ static int add_generic_uac2_implicit_fb(struct snd_usb_audio *chip,
 	    (epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) !=
 					USB_ENDPOINT_USAGE_IMPLICIT_FB)
 		return 0;
-	return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress,
+	return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 0,
 				       ifnum, alts);
 }
 
@@ -167,10 +171,32 @@ static int add_roland_implicit_fb(struct snd_usb_audio *chip,
 	    (epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) !=
 					USB_ENDPOINT_USAGE_IMPLICIT_FB)
 		return 0;
-	return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress,
+	return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 0,
 				       ifnum, alts);
 }
 
+/* Pioneer devices: playback and capture streams sharing the same iface/altset
+ */
+static int add_pioneer_implicit_fb(struct snd_usb_audio *chip,
+				   struct audioformat *fmt,
+				   struct usb_host_interface *alts)
+{
+	struct usb_endpoint_descriptor *epd;
+
+	if (alts->desc.bNumEndpoints != 2)
+		return 0;
+
+	epd = get_endpoint(alts, 1);
+	if (!usb_endpoint_is_isoc_in(epd) ||
+	    (epd->bmAttributes & USB_ENDPOINT_SYNCTYPE) != USB_ENDPOINT_SYNC_ASYNC ||
+	    ((epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) !=
+	     USB_ENDPOINT_USAGE_DATA &&
+	     (epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) !=
+	     USB_ENDPOINT_USAGE_IMPLICIT_FB))
+		return 0;
+	return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 1,
+				       alts->desc.bInterfaceNumber, alts);
+}
 
 static int __add_generic_implicit_fb(struct snd_usb_audio *chip,
 				     struct audioformat *fmt,
@@ -191,7 +217,7 @@ static int __add_generic_implicit_fb(struct snd_usb_audio *chip,
 	if (!usb_endpoint_is_isoc_in(epd) ||
 	    (epd->bmAttributes & USB_ENDPOINT_SYNCTYPE) != USB_ENDPOINT_SYNC_ASYNC)
 		return 0;
-	return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress,
+	return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 0,
 				       iface, alts);
 }
 
@@ -244,7 +270,7 @@ static int audioformat_implicit_fb_quirk(struct snd_usb_audio *chip,
 		case IMPLICIT_FB_NONE:
 			return 0; /* No quirk */
 		case IMPLICIT_FB_FIXED:
-			return add_implicit_fb_sync_ep(chip, fmt, p->ep_num,
+			return add_implicit_fb_sync_ep(chip, fmt, p->ep_num, 0,
 						       p->iface, NULL);
 		}
 	}
@@ -272,6 +298,14 @@ static int audioformat_implicit_fb_quirk(struct snd_usb_audio *chip,
 			return 1;
 	}
 
+	/* Pioneer devices implicit feedback with vendor spec class */
+	if (attr == USB_ENDPOINT_SYNC_ASYNC &&
+	    alts->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC &&
+	    USB_ID_VENDOR(chip->usb_id) == 0x2b73 /* Pioneer */) {
+		if (add_pioneer_implicit_fb(chip, fmt, alts))
+			return 1;
+	}
+
 	/* Try the generic implicit fb if available */
 	if (chip->generic_implicit_fb)
 		return add_generic_implicit_fb(chip, fmt, alts);
@@ -289,8 +323,8 @@ static int audioformat_capture_quirk(struct snd_usb_audio *chip,
 
 	p = find_implicit_fb_entry(chip, capture_implicit_fb_quirks, alts);
 	if (p && p->type == IMPLICIT_FB_FIXED)
-		return add_implicit_fb_sync_ep(chip, fmt, p->ep_num, p->iface,
-					       NULL);
+		return add_implicit_fb_sync_ep(chip, fmt, p->ep_num, 0,
+					       p->iface, NULL);
 	return 0;
 }
 
@@ -372,20 +406,19 @@ snd_usb_find_implicit_fb_sync_format(struct snd_usb_audio *chip,
 				     int stream)
 {
 	struct snd_usb_substream *subs;
-	const struct audioformat *fp, *sync_fmt;
+	const struct audioformat *fp, *sync_fmt = NULL;
 	int score, high_score;
 
-	/* When sharing the same altset, use the original audioformat */
+	/* Use the original audioformat as fallback for the shared altset */
 	if (target->iface == target->sync_iface &&
 	    target->altsetting == target->sync_altsetting)
-		return target;
+		sync_fmt = target;
 
 	subs = find_matching_substream(chip, stream, target->sync_ep,
 				       target->fmt_type);
 	if (!subs)
-		return NULL;
+		return sync_fmt;
 
-	sync_fmt = NULL;
 	high_score = 0;
 	list_for_each_entry(fp, &subs->fmt_list, list) {
 		score = match_endpoint_audioformats(subs, fp,
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index c8213652470c..0c23fa6d8525 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1889,6 +1889,8 @@ static int snd_usbmidi_get_ms_info(struct snd_usb_midi *umidi,
 		ms_ep = find_usb_ms_endpoint_descriptor(hostep);
 		if (!ms_ep)
 			continue;
+		if (ms_ep->bNumEmbMIDIJack > 0x10)
+			continue;
 		if (usb_endpoint_dir_out(ep)) {
 			if (endpoints[epidx].out_ep) {
 				if (++epidx >= MIDI_MAX_ENDPOINTS) {
@@ -2141,6 +2143,8 @@ static int snd_usbmidi_detect_roland(struct snd_usb_midi *umidi,
 		    cs_desc[1] == USB_DT_CS_INTERFACE &&
 		    cs_desc[2] == 0xf1 &&
 		    cs_desc[3] == 0x02) {
+			if (cs_desc[4] > 0x10 || cs_desc[5] > 0x10)
+				continue;
 			endpoint->in_cables  = (1 << cs_desc[4]) - 1;
 			endpoint->out_cables = (1 << cs_desc[5]) - 1;
 			return snd_usbmidi_detect_endpoints(umidi, endpoint, 1);
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 0e11cb96fa8c..c8a4bdf18207 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -3362,6 +3362,7 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 					.altsetting = 1,
 					.altset_idx = 1,
 					.endpoint = 0x86,
+					.ep_idx = 1,
 					.ep_attr = USB_ENDPOINT_XFER_ISOC|
 						 USB_ENDPOINT_SYNC_ASYNC|
 						 USB_ENDPOINT_USAGE_IMPLICIT_FB,
@@ -3450,6 +3451,7 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 					.altsetting = 1,
 					.altset_idx = 1,
 					.endpoint = 0x82,
+					.ep_idx = 1,
 					.ep_attr = USB_ENDPOINT_XFER_ISOC|
 						USB_ENDPOINT_SYNC_ASYNC|
 						USB_ENDPOINT_USAGE_IMPLICIT_FB,
@@ -3506,6 +3508,7 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 					.altsetting = 1,
 					.altset_idx = 1,
 					.endpoint = 0x82,
+					.ep_idx = 1,
 					.ep_attr = USB_ENDPOINT_XFER_ISOC|
 						 USB_ENDPOINT_SYNC_ASYNC|
 						 USB_ENDPOINT_USAGE_IMPLICIT_FB,
@@ -3562,6 +3565,7 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 					.altsetting = 1,
 					.altset_idx = 1,
 					.endpoint = 0x82,
+					.ep_idx = 1,
 					.ep_attr = USB_ENDPOINT_XFER_ISOC|
 						 USB_ENDPOINT_SYNC_ASYNC|
 						 USB_ENDPOINT_USAGE_IMPLICIT_FB,
@@ -3619,6 +3623,7 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 					.altsetting = 1,
 					.altset_idx = 1,
 					.endpoint = 0x82,
+					.ep_idx = 1,
 					.ep_attr = USB_ENDPOINT_XFER_ISOC|
 						USB_ENDPOINT_SYNC_ASYNC|
 					USB_ENDPOINT_USAGE_IMPLICIT_FB,
@@ -3679,6 +3684,7 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"),
 					.altsetting = 1,
 					.altset_idx = 1,
 					.endpoint = 0x82,
+					.ep_idx = 1,
 					.ep_attr = USB_ENDPOINT_XFER_ISOC|
 					    USB_ENDPOINT_SYNC_ASYNC|
 					    USB_ENDPOINT_USAGE_IMPLICIT_FB,
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 63cdf3c8c2bc..89e172642d98 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -120,6 +120,40 @@ static int create_standard_audio_quirk(struct snd_usb_audio *chip,
 	return 0;
 }
 
+/* create the audio stream and the corresponding endpoints from the fixed
+ * audioformat object; this is used for quirks with the fixed EPs
+ */
+static int add_audio_stream_from_fixed_fmt(struct snd_usb_audio *chip,
+					   struct audioformat *fp)
+{
+	int stream, err;
+
+	stream = (fp->endpoint & USB_DIR_IN) ?
+		SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
+
+	snd_usb_audioformat_set_sync_ep(chip, fp);
+
+	err = snd_usb_add_audio_stream(chip, stream, fp);
+	if (err < 0)
+		return err;
+
+	err = snd_usb_add_endpoint(chip, fp->endpoint,
+				   SND_USB_ENDPOINT_TYPE_DATA);
+	if (err < 0)
+		return err;
+
+	if (fp->sync_ep) {
+		err = snd_usb_add_endpoint(chip, fp->sync_ep,
+					   fp->implicit_fb ?
+					   SND_USB_ENDPOINT_TYPE_DATA :
+					   SND_USB_ENDPOINT_TYPE_SYNC);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
 /*
  * create a stream for an endpoint/altsetting without proper descriptors
  */
@@ -131,8 +165,8 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
 	struct audioformat *fp;
 	struct usb_host_interface *alts;
 	struct usb_interface_descriptor *altsd;
-	int stream, err;
 	unsigned *rate_table = NULL;
+	int err;
 
 	fp = kmemdup(quirk->data, sizeof(*fp), GFP_KERNEL);
 	if (!fp)
@@ -153,11 +187,6 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
 		fp->rate_table = rate_table;
 	}
 
-	stream = (fp->endpoint & USB_DIR_IN)
-		? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
-	err = snd_usb_add_audio_stream(chip, stream, fp);
-	if (err < 0)
-		goto error;
 	if (fp->iface != get_iface_desc(&iface->altsetting[0])->bInterfaceNumber ||
 	    fp->altset_idx >= iface->num_altsetting) {
 		err = -EINVAL;
@@ -165,7 +194,7 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
 	}
 	alts = &iface->altsetting[fp->altset_idx];
 	altsd = get_iface_desc(alts);
-	if (altsd->bNumEndpoints < 1) {
+	if (altsd->bNumEndpoints <= fp->ep_idx) {
 		err = -EINVAL;
 		goto error;
 	}
@@ -175,7 +204,14 @@ static int create_fixed_stream_quirk(struct snd_usb_audio *chip,
 	if (fp->datainterval == 0)
 		fp->datainterval = snd_usb_parse_datainterval(chip, alts);
 	if (fp->maxpacksize == 0)
-		fp->maxpacksize = le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize);
+		fp->maxpacksize = le16_to_cpu(get_endpoint(alts, fp->ep_idx)->wMaxPacketSize);
+	if (!fp->fmt_type)
+		fp->fmt_type = UAC_FORMAT_TYPE_I;
+
+	err = add_audio_stream_from_fixed_fmt(chip, fp);
+	if (err < 0)
+		goto error;
+
 	usb_set_interface(chip->dev, fp->iface, 0);
 	snd_usb_init_pitch(chip, fp);
 	snd_usb_init_sample_rate(chip, fp, fp->rate_max);
@@ -417,7 +453,7 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip,
 	struct usb_host_interface *alts;
 	struct usb_interface_descriptor *altsd;
 	struct audioformat *fp;
-	int stream, err;
+	int err;
 
 	/* both PCM and MIDI interfaces have 2 or more altsettings */
 	if (iface->num_altsetting < 2)
@@ -482,9 +518,7 @@ static int create_uaxx_quirk(struct snd_usb_audio *chip,
 		return -ENXIO;
 	}
 
-	stream = (fp->endpoint & USB_DIR_IN)
-		? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
-	err = snd_usb_add_audio_stream(chip, stream, fp);
+	err = add_audio_stream_from_fixed_fmt(chip, fp);
 	if (err < 0) {
 		list_del(&fp->list); /* unlink for avoiding double-free */
 		kfree(fp);
@@ -1771,6 +1805,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 	case 0x25ce:  /* Mytek devices */
 	case 0x278b:  /* Rotel? */
 	case 0x292b:  /* Gustard/Ess based devices */
+	case 0x2972:  /* FiiO devices */
 	case 0x2ab6:  /* T+A devices */
 	case 0x3353:  /* Khadas devices */
 	case 0x3842:  /* EVGA */
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index 980287aadd36..215c1771dd57 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -44,6 +44,7 @@ struct snd_usb_audio {
 
 	struct list_head pcm_list;	/* list of pcm streams */
 	struct list_head ep_list;	/* list of audio-related endpoints */
+	struct list_head iface_ref_list; /* list of interface refcounts */
 	int pcm_devs;
 
 	struct list_head midi_list;	/* list of midi interfaces */
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 1c17c3a24411..24223adae150 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -156,9 +156,6 @@ struct kvm_sync_regs {
 	__u64 device_irq_level;
 };
 
-struct kvm_arch_memory_slot {
-};
-
 /*
  * PMU filter structure. Describe a range of events with a particular
  * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index dad350d42ecf..84b887825f12 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -237,10 +237,12 @@
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
 #define X86_FEATURE_SEV_ES		( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_VM_PAGE_FLUSH	( 8*32+21) /* "" VM Page Flush MSR is supported */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
 #define X86_FEATURE_TSC_ADJUST		( 9*32+ 1) /* TSC adjustment MSR 0x3B */
+#define X86_FEATURE_SGX			( 9*32+ 2) /* Software Guard Extensions */
 #define X86_FEATURE_BMI1		( 9*32+ 3) /* 1st group bit manipulation extensions */
 #define X86_FEATURE_HLE			( 9*32+ 4) /* Hardware Lock Elision */
 #define X86_FEATURE_AVX2		( 9*32+ 5) /* AVX2 instructions */
@@ -356,6 +358,7 @@
 #define X86_FEATURE_MOVDIRI		(16*32+27) /* MOVDIRI instruction */
 #define X86_FEATURE_MOVDIR64B		(16*32+28) /* MOVDIR64B instruction */
 #define X86_FEATURE_ENQCMD		(16*32+29) /* ENQCMD and ENQCMDS instructions */
+#define X86_FEATURE_SGX_LC		(16*32+30) /* Software Guard Extensions Launch Control */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
@@ -374,6 +377,7 @@
 #define X86_FEATURE_TSXLDTRK		(18*32+16) /* TSX Suspend Load Address Tracking */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_ARCH_LBR		(18*32+19) /* Intel ARCH LBR */
+#define X86_FEATURE_AVX512_FP16		(18*32+23) /* AVX512 FP16 */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 5861d34f9771..7947cb1782da 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -62,6 +62,12 @@
 # define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
 #endif
 
+#ifdef CONFIG_X86_SGX
+# define DISABLE_SGX	0
+#else
+# define DISABLE_SGX	(1 << (X86_FEATURE_SGX & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -74,7 +80,7 @@
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
-#define DISABLED_MASK9	(DISABLE_SMAP)
+#define DISABLED_MASK9	(DISABLE_SMAP|DISABLE_SGX)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	0
 #define DISABLED_MASK12	0
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 972a34d93505..546d6ecf0a35 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -139,6 +139,7 @@
 #define MSR_IA32_MCG_CAP		0x00000179
 #define MSR_IA32_MCG_STATUS		0x0000017a
 #define MSR_IA32_MCG_CTL		0x0000017b
+#define MSR_ERROR_CONTROL		0x0000017f
 #define MSR_IA32_MCG_EXT_CTL		0x000004d0
 
 #define MSR_OFFCORE_RSP_0		0x000001a6
@@ -326,8 +327,9 @@
 #define MSR_PP1_ENERGY_STATUS		0x00000641
 #define MSR_PP1_POLICY			0x00000642
 
-#define MSR_AMD_PKG_ENERGY_STATUS	0xc001029b
 #define MSR_AMD_RAPL_POWER_UNIT		0xc0010299
+#define MSR_AMD_CORE_ENERGY_STATUS		0xc001029a
+#define MSR_AMD_PKG_ENERGY_STATUS	0xc001029b
 
 /* Config TDP MSRs */
 #define MSR_CONFIG_TDP_NOMINAL		0x00000648
@@ -470,6 +472,7 @@
 #define MSR_AMD64_ICIBSEXTDCTL		0xc001103c
 #define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_VM_PAGE_FLUSH		0xc001011e
 #define MSR_AMD64_SEV_ES_GHCB		0xc0010130
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0
@@ -609,6 +612,8 @@
 #define FEAT_CTL_LOCKED				BIT(0)
 #define FEAT_CTL_VMX_ENABLED_INSIDE_SMX		BIT(1)
 #define FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX	BIT(2)
+#define FEAT_CTL_SGX_LC_ENABLED			BIT(17)
+#define FEAT_CTL_SGX_ENABLED			BIT(18)
 #define FEAT_CTL_LMCE_ENABLED			BIT(20)
 
 #define MSR_IA32_TSC_ADJUST             0x0000003b
@@ -628,6 +633,12 @@
 #define MSR_IA32_UCODE_WRITE		0x00000079
 #define MSR_IA32_UCODE_REV		0x0000008b
 
+/* Intel SGX Launch Enclave Public Key Hash MSRs */
+#define MSR_IA32_SGXLEPUBKEYHASH0	0x0000008C
+#define MSR_IA32_SGXLEPUBKEYHASH1	0x0000008D
+#define MSR_IA32_SGXLEPUBKEYHASH2	0x0000008E
+#define MSR_IA32_SGXLEPUBKEYHASH3	0x0000008F
+
 #define MSR_IA32_SMM_MONITOR_CTL	0x0000009b
 #define MSR_IA32_SMBASE			0x0000009e
 
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 89e5f3d1bba8..8e76d3701db3 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -12,6 +12,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define KVM_DIRTY_LOG_PAGE_OFFSET 64
 
 #define DE_VECTOR 0
 #define DB_VECTOR 1
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index f1d8307454e0..554f75fe013c 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -77,10 +77,28 @@
 #define SVM_EXIT_MWAIT_COND    0x08c
 #define SVM_EXIT_XSETBV        0x08d
 #define SVM_EXIT_RDPRU         0x08e
+#define SVM_EXIT_EFER_WRITE_TRAP		0x08f
+#define SVM_EXIT_CR0_WRITE_TRAP			0x090
+#define SVM_EXIT_CR1_WRITE_TRAP			0x091
+#define SVM_EXIT_CR2_WRITE_TRAP			0x092
+#define SVM_EXIT_CR3_WRITE_TRAP			0x093
+#define SVM_EXIT_CR4_WRITE_TRAP			0x094
+#define SVM_EXIT_CR5_WRITE_TRAP			0x095
+#define SVM_EXIT_CR6_WRITE_TRAP			0x096
+#define SVM_EXIT_CR7_WRITE_TRAP			0x097
+#define SVM_EXIT_CR8_WRITE_TRAP			0x098
+#define SVM_EXIT_CR9_WRITE_TRAP			0x099
+#define SVM_EXIT_CR10_WRITE_TRAP		0x09a
+#define SVM_EXIT_CR11_WRITE_TRAP		0x09b
+#define SVM_EXIT_CR12_WRITE_TRAP		0x09c
+#define SVM_EXIT_CR13_WRITE_TRAP		0x09d
+#define SVM_EXIT_CR14_WRITE_TRAP		0x09e
+#define SVM_EXIT_CR15_WRITE_TRAP		0x09f
 #define SVM_EXIT_INVPCID       0x0a2
 #define SVM_EXIT_NPF           0x400
 #define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS	0x402
+#define SVM_EXIT_VMGEXIT       0x403
 
 /* SEV-ES software-defined VMGEXIT events */
 #define SVM_VMGEXIT_MMIO_READ			0x80000001
@@ -183,10 +201,20 @@
 	{ SVM_EXIT_MONITOR,     "monitor" }, \
 	{ SVM_EXIT_MWAIT,       "mwait" }, \
 	{ SVM_EXIT_XSETBV,      "xsetbv" }, \
+	{ SVM_EXIT_EFER_WRITE_TRAP,	"write_efer_trap" }, \
+	{ SVM_EXIT_CR0_WRITE_TRAP,	"write_cr0_trap" }, \
+	{ SVM_EXIT_CR4_WRITE_TRAP,	"write_cr4_trap" }, \
+	{ SVM_EXIT_CR8_WRITE_TRAP,	"write_cr8_trap" }, \
 	{ SVM_EXIT_INVPCID,     "invpcid" }, \
 	{ SVM_EXIT_NPF,         "npf" }, \
 	{ SVM_EXIT_AVIC_INCOMPLETE_IPI,		"avic_incomplete_ipi" }, \
 	{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS,   "avic_unaccelerated_access" }, \
+	{ SVM_EXIT_VMGEXIT,		"vmgexit" }, \
+	{ SVM_VMGEXIT_MMIO_READ,	"vmgexit_mmio_read" }, \
+	{ SVM_VMGEXIT_MMIO_WRITE,	"vmgexit_mmio_write" }, \
+	{ SVM_VMGEXIT_NMI_COMPLETE,	"vmgexit_nmi_complete" }, \
+	{ SVM_VMGEXIT_AP_HLT_LOOP,	"vmgexit_ap_hlt_loop" }, \
+	{ SVM_VMGEXIT_AP_JUMP_TABLE,	"vmgexit_ap_jump_table" }, \
 	{ SVM_EXIT_ERR,         "invalid_guest_state" }
 
 
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index b8ff9e8ac0d5..ada955c5ebb6 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -32,6 +32,7 @@
 #define EXIT_REASON_EXTERNAL_INTERRUPT  1
 #define EXIT_REASON_TRIPLE_FAULT        2
 #define EXIT_REASON_INIT_SIGNAL			3
+#define EXIT_REASON_SIPI_SIGNAL         4
 
 #define EXIT_REASON_INTERRUPT_WINDOW    7
 #define EXIT_REASON_NMI_WINDOW          8
@@ -94,6 +95,7 @@
 	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
 	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
 	{ EXIT_REASON_INIT_SIGNAL,           "INIT_SIGNAL" }, \
+	{ EXIT_REASON_SIPI_SIGNAL,           "SIPI_SIGNAL" }, \
 	{ EXIT_REASON_INTERRUPT_WINDOW,      "INTERRUPT_WINDOW" }, \
 	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
 	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
diff --git a/tools/bootconfig/scripts/bconf2ftrace.sh b/tools/bootconfig/scripts/bconf2ftrace.sh
index 595e164dc352..feb30c2c7881 100755
--- a/tools/bootconfig/scripts/bconf2ftrace.sh
+++ b/tools/bootconfig/scripts/bconf2ftrace.sh
@@ -152,6 +152,7 @@ setup_instance() { # [instance]
 	set_array_of ${instance}.options ${instancedir}/trace_options
 	set_value_of ${instance}.trace_clock ${instancedir}/trace_clock
 	set_value_of ${instance}.cpumask ${instancedir}/tracing_cpumask
+	set_value_of ${instance}.tracing_on ${instancedir}/tracing_on
 	set_value_of ${instance}.tracer ${instancedir}/current_tracer
 	set_array_of ${instance}.ftrace.filters \
 		${instancedir}/set_ftrace_filter
diff --git a/tools/bootconfig/scripts/ftrace2bconf.sh b/tools/bootconfig/scripts/ftrace2bconf.sh
index 6c0d4b61e0c2..a0c3bcc6da4f 100755
--- a/tools/bootconfig/scripts/ftrace2bconf.sh
+++ b/tools/bootconfig/scripts/ftrace2bconf.sh
@@ -221,6 +221,10 @@ instance_options() { # [instance-name]
 	if [ `echo $val | sed -e s/f//g`x != x ]; then
 		emit_kv $PREFIX.cpumask = $val
 	fi
+	val=`cat $INSTANCE/tracing_on`
+	if [ `echo $val | sed -e s/f//g`x != x ]; then
+		emit_kv $PREFIX.tracing_on = $val
+	fi
 
 	val=
 	for i in `cat $INSTANCE/set_event`; do
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 3fae61ef6339..ff3aa0cf3997 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -11,7 +11,6 @@
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
 #include <net/if.h>
-#include <linux/if.h>
 #include <linux/rtnetlink.h>
 #include <linux/socket.h>
 #include <linux/tc_act/tc_bpf.h>
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index e3ea569ee125..7409d7860aa6 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -139,6 +139,8 @@ int eprintf(int level, int var, const char *fmt, ...)
 #define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_err(fmt, ...) \
 	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
 
 static bool is_btf_id(const char *name)
 {
@@ -472,7 +474,7 @@ static int symbols_resolve(struct object *obj)
 	int nr_funcs    = obj->nr_funcs;
 	int err, type_id;
 	struct btf *btf;
-	__u32 nr;
+	__u32 nr_types;
 
 	btf = btf__parse(obj->btf ?: obj->path, NULL);
 	err = libbpf_get_error(btf);
@@ -483,12 +485,12 @@ static int symbols_resolve(struct object *obj)
 	}
 
 	err = -1;
-	nr  = btf__get_nr_types(btf);
+	nr_types = btf__get_nr_types(btf);
 
 	/*
 	 * Iterate all the BTF types and search for collected symbol IDs.
 	 */
-	for (type_id = 1; type_id <= nr; type_id++) {
+	for (type_id = 1; type_id <= nr_types; type_id++) {
 		const struct btf_type *type;
 		struct rb_root *root;
 		struct btf_id *id;
@@ -526,8 +528,13 @@ static int symbols_resolve(struct object *obj)
 
 		id = btf_id__find(root, str);
 		if (id) {
-			id->id = type_id;
-			(*nr)--;
+			if (id->id) {
+				pr_info("WARN: multiple IDs found for '%s': %d, %d - using %d\n",
+					str, id->id, type_id, id->id);
+			} else {
+				id->id = type_id;
+				(*nr)--;
+			}
 		}
 	}
 
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index cdde783f3018..89ba522e377d 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -90,7 +90,7 @@ __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(
 ###############################
 
 $(OUTPUT)test-all.bin:
-	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd
+	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap
 
 $(OUTPUT)test-hello.bin:
 	$(BUILD)
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index d22a974372c0..ff872dc2637c 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -2,9 +2,7 @@
 #ifndef _TOOLS_LINUX_COMPILER_H_
 #define _TOOLS_LINUX_COMPILER_H_
 
-#ifdef __GNUC__
-#include <linux/compiler-gcc.h>
-#endif
+#include <linux/compiler_types.h>
 
 #ifndef __compiletime_error
 # define __compiletime_error(message)
diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h
new file mode 100644
index 000000000000..feea09029f61
--- /dev/null
+++ b/tools/include/linux/compiler_types.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_COMPILER_TYPES_H
+#define __LINUX_COMPILER_TYPES_H
+
+/* Builtins */
+
+/*
+ * __has_builtin is supported on gcc >= 10, clang >= 3 and icc >= 21.
+ * In the meantime, to support gcc < 10, we implement __has_builtin
+ * by hand.
+ */
+#ifndef __has_builtin
+#define __has_builtin(x) (0)
+#endif
+
+/* Compiler specific macros. */
+#ifdef __GNUC__
+#include <linux/compiler-gcc.h>
+#endif
+
+#endif /* __LINUX_COMPILER_TYPES_H */
diff --git a/tools/include/linux/ctype.h b/tools/include/linux/ctype.h
index 310090b4c474..29ed3fe94404 100644
--- a/tools/include/linux/ctype.h
+++ b/tools/include/linux/ctype.h
@@ -2,6 +2,8 @@
 #ifndef _LINUX_CTYPE_H
 #define _LINUX_CTYPE_H
 
+#include <linux/compiler.h>
+
 /*
  * NOTE! This ctype does not handle EOF like the standard C
  * library is required to.
@@ -23,11 +25,6 @@ extern const unsigned char _ctype[];
 #define isalnum(c)	((__ismask(c)&(_U|_L|_D)) != 0)
 #define isalpha(c)	((__ismask(c)&(_U|_L)) != 0)
 #define iscntrl(c)	((__ismask(c)&(_C)) != 0)
-static inline int __isdigit(int c)
-{
-	return '0' <= c && c <= '9';
-}
-#define isdigit(c)	__isdigit(c)
 #define isgraph(c)	((__ismask(c)&(_P|_U|_L|_D)) != 0)
 #define islower(c)	((__ismask(c)&(_L)) != 0)
 #define isprint(c)	((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0)
@@ -40,6 +37,16 @@ static inline int __isdigit(int c)
 #define isascii(c) (((unsigned char)(c))<=0x7f)
 #define toascii(c) (((unsigned char)(c))&0x7f)
 
+#if __has_builtin(__builtin_isdigit)
+#define  isdigit(c) __builtin_isdigit(c)
+#else
+static inline int __isdigit(int c)
+{
+	return '0' <= c && c <= '9';
+}
+#define  isdigit(c) __isdigit(c)
+#endif
+
 static inline unsigned char __tolower(unsigned char c)
 {
 	if (isupper(c))
diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
index 5e9e781905ed..db5c99318c79 100644
--- a/tools/include/linux/string.h
+++ b/tools/include/linux/string.h
@@ -46,4 +46,5 @@ extern char * __must_check skip_spaces(const char *);
 
 extern char *strim(char *);
 
+extern void *memchr_inv(const void *start, int c, size_t bytes);
 #endif /* _TOOLS_LINUX_STRING_H_ */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 2056318988f7..728752917785 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -517,7 +517,7 @@ __SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
 __SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex)
 #endif
 
-/* kernel/timer.c */
+/* kernel/sys.c */
 #define __NR_getpid 172
 __SYSCALL(__NR_getpid, sys_getpid)
 #define __NR_getppid 173
@@ -859,9 +859,11 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 __SYSCALL(__NR_faccessat2, sys_faccessat2)
 #define __NR_process_madvise 440
 __SYSCALL(__NR_process_madvise, sys_process_madvise)
+#define __NR_epoll_pwait2 441
+__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
 
 #undef __NR_syscalls
-#define __NR_syscalls 441
+#define __NR_syscalls 442
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h
index 5ed721ad5b19..af2a44c08683 100644
--- a/tools/include/uapi/linux/const.h
+++ b/tools/include/uapi/linux/const.h
@@ -28,4 +28,9 @@
 #define _BITUL(x)	(_UL(1) << (x))
 #define _BITULL(x)	(_ULL(1) << (x))
 
+#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+#define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
+
+#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+
 #endif /* _UAPI_LINUX_CONST_H */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index e5de60336938..9f4428be3e36 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -20,7 +20,6 @@
 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY		0x04
 #define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64	0x08
 #define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32	0x10
-#define FSCRYPT_POLICY_FLAGS_VALID		0x1F
 
 /* Encryption algorithms */
 #define FSCRYPT_MODE_AES_256_XTS		1
@@ -28,7 +27,7 @@
 #define FSCRYPT_MODE_AES_128_CBC		5
 #define FSCRYPT_MODE_AES_128_CTS		6
 #define FSCRYPT_MODE_ADIANTUM			9
-#define __FSCRYPT_MODE_MAX			9
+/* If adding a mode number > 9, update FSCRYPT_MODE_MAX in fscrypt_private.h */
 
 /*
  * Legacy policy version; ad-hoc KDF and no key verification.
@@ -177,7 +176,7 @@ struct fscrypt_get_key_status_arg {
 #define FS_POLICY_FLAGS_PAD_32		FSCRYPT_POLICY_FLAGS_PAD_32
 #define FS_POLICY_FLAGS_PAD_MASK	FSCRYPT_POLICY_FLAGS_PAD_MASK
 #define FS_POLICY_FLAG_DIRECT_KEY	FSCRYPT_POLICY_FLAG_DIRECT_KEY
-#define FS_POLICY_FLAGS_VALID		FSCRYPT_POLICY_FLAGS_VALID
+#define FS_POLICY_FLAGS_VALID		0x07	/* contains old flags only */
 #define FS_ENCRYPTION_MODE_INVALID	0	/* never used */
 #define FS_ENCRYPTION_MODE_AES_256_XTS	FSCRYPT_MODE_AES_256_XTS
 #define FS_ENCRYPTION_MODE_AES_256_GCM	2	/* never used */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index ca41220b40b8..374c67875cdb 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -250,6 +250,8 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_ARM_NISV         28
 #define KVM_EXIT_X86_RDMSR        29
 #define KVM_EXIT_X86_WRMSR        30
+#define KVM_EXIT_DIRTY_RING_FULL  31
+#define KVM_EXIT_AP_RESET_HOLD    32
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -572,6 +574,7 @@ struct kvm_vapic_addr {
 #define KVM_MP_STATE_CHECK_STOP        6
 #define KVM_MP_STATE_OPERATING         7
 #define KVM_MP_STATE_LOAD              8
+#define KVM_MP_STATE_AP_RESET_HOLD     9
 
 struct kvm_mp_state {
 	__u32 mp_state;
@@ -1053,6 +1056,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_X86_USER_SPACE_MSR 188
 #define KVM_CAP_X86_MSR_FILTER 189
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
+#define KVM_CAP_SYS_HYPERV_CPUID 191
+#define KVM_CAP_DIRTY_LOG_RING 192
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1511,7 +1516,7 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */
 #define KVM_CLEAR_DIRTY_LOG          _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
 
-/* Available with KVM_CAP_HYPERV_CPUID */
+/* Available with KVM_CAP_HYPERV_CPUID (vcpu) / KVM_CAP_SYS_HYPERV_CPUID (system) */
 #define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
 
 /* Available with KVM_CAP_ARM_SVE */
@@ -1557,6 +1562,9 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_X86_MSR_FILTER */
 #define KVM_X86_SET_MSR_FILTER	_IOW(KVMIO,  0xc6, struct kvm_msr_filter)
 
+/* Available with KVM_CAP_DIRTY_LOG_RING */
+#define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1710,4 +1718,52 @@ struct kvm_hyperv_eventfd {
 #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
 #define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
 
+/*
+ * Arch needs to define the macro after implementing the dirty ring
+ * feature.  KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the
+ * starting page offset of the dirty ring structures.
+ */
+#ifndef KVM_DIRTY_LOG_PAGE_OFFSET
+#define KVM_DIRTY_LOG_PAGE_OFFSET 0
+#endif
+
+/*
+ * KVM dirty GFN flags, defined as:
+ *
+ * |---------------+---------------+--------------|
+ * | bit 1 (reset) | bit 0 (dirty) | Status       |
+ * |---------------+---------------+--------------|
+ * |             0 |             0 | Invalid GFN  |
+ * |             0 |             1 | Dirty GFN    |
+ * |             1 |             X | GFN to reset |
+ * |---------------+---------------+--------------|
+ *
+ * Lifecycle of a dirty GFN goes like:
+ *
+ *      dirtied         harvested        reset
+ * 00 -----------> 01 -------------> 1X -------+
+ *  ^                                          |
+ *  |                                          |
+ *  +------------------------------------------+
+ *
+ * The userspace program is only responsible for the 01->1X state
+ * conversion after harvesting an entry.  Also, it must not skip any
+ * dirty bits, so that dirty bits are always harvested in sequence.
+ */
+#define KVM_DIRTY_GFN_F_DIRTY           BIT(0)
+#define KVM_DIRTY_GFN_F_RESET           BIT(1)
+#define KVM_DIRTY_GFN_F_MASK            0x3
+
+/*
+ * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of
+ * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn.  The
+ * size of the gfn buffer is decided by the first argument when
+ * enabling KVM_CAP_DIRTY_LOG_RING.
+ */
+struct kvm_dirty_gfn {
+	__u32 flags;
+	__u32 slot;
+	__u64 offset;
+};
+
 #endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index b95d3c485d27..b15e3447cd9f 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -143,8 +143,10 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 	PERF_SAMPLE_AUX				= 1U << 20,
 	PERF_SAMPLE_CGROUP			= 1U << 21,
+	PERF_SAMPLE_DATA_PAGE_SIZE		= 1U << 22,
+	PERF_SAMPLE_CODE_PAGE_SIZE		= 1U << 23,
 
-	PERF_SAMPLE_MAX = 1U << 22,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 24,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -896,6 +898,8 @@ enum perf_event_type {
 	 *	{ u64			phys_addr;} && PERF_SAMPLE_PHYS_ADDR
 	 *	{ u64			size;
 	 *	  char			data[size]; } && PERF_SAMPLE_AUX
+	 *	{ u64			data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE
+	 *	{ u64			code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 7f0827705c9a..90deb41c8a34 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -247,4 +247,9 @@ struct prctl_mm_map {
 #define PR_SET_IO_FLUSHER		57
 #define PR_GET_IO_FLUSHER		58
 
+/* Dispatch syscalls to a userspace handler */
+#define PR_SET_SYSCALL_USER_DISPATCH	59
+# define PR_SYS_DISPATCH_OFF		0
+# define PR_SYS_DISPATCH_ON		1
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 82cc58fe9368..1500a0f58041 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -171,9 +171,12 @@ struct statx {
  * be of use to ordinary userspace programs such as GUIs or ls rather than
  * specialised tools.
  *
- * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS
+ * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags
  * semantically.  Where possible, the numerical value is picked to correspond
- * also.
+ * also.  Note that the DAX attribute indicates that the file is in the CPU
+ * direct access state.  It does not correspond to the per-inode flag that
+ * some filesystems support.
+ *
  */
 #define STATX_ATTR_COMPRESSED		0x00000004 /* [I] File is compressed by the fs */
 #define STATX_ATTR_IMMUTABLE		0x00000010 /* [I] File is marked immutable */
@@ -183,7 +186,7 @@ struct statx {
 #define STATX_ATTR_AUTOMOUNT		0x00001000 /* Dir: Automount trigger */
 #define STATX_ATTR_MOUNT_ROOT		0x00002000 /* Root of a mount */
 #define STATX_ATTR_VERITY		0x00100000 /* [I] Verity protected file */
-#define STATX_ATTR_DAX			0x00002000 /* [I] File is DAX */
+#define STATX_ATTR_DAX			0x00200000 /* File is currently in DAX state */
 
 
 #endif /* _UAPI_LINUX_STAT_H */
diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c
index c8d45091e7c2..c70e9e03af3e 100644
--- a/tools/lib/perf/tests/test-cpumap.c
+++ b/tools/lib/perf/tests/test-cpumap.c
@@ -27,5 +27,5 @@ int main(int argc, char **argv)
 	perf_cpu_map__put(cpus);
 
 	__T_END;
-	return 0;
+	return tests_failed == 0 ? 0 : -1;
 }
diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index 6d8ebe0c2504..e2ac0b7f432e 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -208,13 +208,13 @@ static int test_mmap_thread(void)
 	char path[PATH_MAX];
 	int id, err, pid, go_pipe[2];
 	union perf_event *event;
-	char bf;
 	int count = 0;
 
 	snprintf(path, PATH_MAX, "%s/kernel/debug/tracing/events/syscalls/sys_enter_prctl/id",
 		 sysfs__mountpoint());
 
 	if (filename__read_int(path, &id)) {
+		tests_failed++;
 		fprintf(stderr, "error: failed to get tracepoint id: %s\n", path);
 		return -1;
 	}
@@ -229,6 +229,7 @@ static int test_mmap_thread(void)
 	pid = fork();
 	if (!pid) {
 		int i;
+		char bf;
 
 		read(go_pipe[0], &bf, 1);
 
@@ -266,7 +267,7 @@ static int test_mmap_thread(void)
 	perf_evlist__enable(evlist);
 
 	/* kick the child and wait for it to finish */
-	write(go_pipe[1], &bf, 1);
+	write(go_pipe[1], "A", 1);
 	waitpid(pid, NULL, 0);
 
 	/*
@@ -409,5 +410,5 @@ int main(int argc, char **argv)
 	test_mmap_cpus();
 
 	__T_END;
-	return 0;
+	return tests_failed == 0 ? 0 : -1;
 }
diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
index 135722ac965b..0ad82d7a2a51 100644
--- a/tools/lib/perf/tests/test-evsel.c
+++ b/tools/lib/perf/tests/test-evsel.c
@@ -131,5 +131,5 @@ int main(int argc, char **argv)
 	test_stat_thread_enable();
 
 	__T_END;
-	return 0;
+	return tests_failed == 0 ? 0 : -1;
 }
diff --git a/tools/lib/perf/tests/test-threadmap.c b/tools/lib/perf/tests/test-threadmap.c
index 7dc4d6fbedde..384471441b48 100644
--- a/tools/lib/perf/tests/test-threadmap.c
+++ b/tools/lib/perf/tests/test-threadmap.c
@@ -27,5 +27,5 @@ int main(int argc, char **argv)
 	perf_thread_map__put(threads);
 
 	__T_END;
-	return 0;
+	return tests_failed == 0 ? 0 : -1;
 }
diff --git a/tools/lib/string.c b/tools/lib/string.c
index f645343815de..8b6892f959ab 100644
--- a/tools/lib/string.c
+++ b/tools/lib/string.c
@@ -168,3 +168,61 @@ char *strreplace(char *s, char old, char new)
 			*s = new;
 	return s;
 }
+
+static void *check_bytes8(const u8 *start, u8 value, unsigned int bytes)
+{
+	while (bytes) {
+		if (*start != value)
+			return (void *)start;
+		start++;
+		bytes--;
+	}
+	return NULL;
+}
+
+/**
+ * memchr_inv - Find an unmatching character in an area of memory.
+ * @start: The memory area
+ * @c: Find a character other than c
+ * @bytes: The size of the area.
+ *
+ * returns the address of the first character other than @c, or %NULL
+ * if the whole buffer contains just @c.
+ */
+void *memchr_inv(const void *start, int c, size_t bytes)
+{
+	u8 value = c;
+	u64 value64;
+	unsigned int words, prefix;
+
+	if (bytes <= 16)
+		return check_bytes8(start, value, bytes);
+
+	value64 = value;
+	value64 |= value64 << 8;
+	value64 |= value64 << 16;
+	value64 |= value64 << 32;
+
+	prefix = (unsigned long)start % 8;
+	if (prefix) {
+		u8 *r;
+
+		prefix = 8 - prefix;
+		r = check_bytes8(start, value, prefix);
+		if (r)
+			return r;
+		start += prefix;
+		bytes -= prefix;
+	}
+
+	words = bytes / 8;
+
+	while (words) {
+		if (*(u64 *)start != value64)
+			return check_bytes8(start, value, 8);
+		start += 8;
+		words--;
+	}
+
+	return check_bytes8(start, value, bytes % 8);
+}
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index c6ab44543c92..5f8d3eed78a1 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -467,13 +467,20 @@ static int create_static_call_sections(struct objtool_file *file)
 
 		/* populate reloc for 'addr' */
 		reloc = malloc(sizeof(*reloc));
+
 		if (!reloc) {
 			perror("malloc");
 			return -1;
 		}
 		memset(reloc, 0, sizeof(*reloc));
-		reloc->sym = insn->sec->sym;
-		reloc->addend = insn->offset;
+
+		insn_to_reloc_sym_addend(insn->sec, insn->offset, reloc);
+		if (!reloc->sym) {
+			WARN_FUNC("static call tramp: missing containing symbol",
+				  insn->sec, insn->offset);
+			return -1;
+		}
+
 		reloc->type = R_X86_64_PC32;
 		reloc->offset = idx * sizeof(struct static_call_site);
 		reloc->sec = reloc_sec;
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 4e1d7460574b..be89c741ba9a 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -262,6 +262,32 @@ struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, uns
 	return find_reloc_by_dest_range(elf, sec, offset, 1);
 }
 
+void insn_to_reloc_sym_addend(struct section *sec, unsigned long offset,
+			      struct reloc *reloc)
+{
+	if (sec->sym) {
+		reloc->sym = sec->sym;
+		reloc->addend = offset;
+		return;
+	}
+
+	/*
+	 * The Clang assembler strips section symbols, so we have to reference
+	 * the function symbol instead:
+	 */
+	reloc->sym = find_symbol_containing(sec, offset);
+	if (!reloc->sym) {
+		/*
+		 * Hack alert.  This happens when we need to reference the NOP
+		 * pad insn immediately after the function.
+		 */
+		reloc->sym = find_symbol_containing(sec, offset - 1);
+	}
+
+	if (reloc->sym)
+		reloc->addend = offset - reloc->sym->offset;
+}
+
 static int read_sections(struct elf *elf)
 {
 	Elf_Scn *s = NULL;
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index 807f8c670097..e6890cc70a25 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -140,6 +140,8 @@ struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, uns
 struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec,
 				     unsigned long offset, unsigned int len);
 struct symbol *find_func_containing(struct section *sec, unsigned long offset);
+void insn_to_reloc_sym_addend(struct section *sec, unsigned long offset,
+			      struct reloc *reloc);
 int elf_rebuild_reloc_section(struct elf *elf, struct section *sec);
 
 #define for_each_sec(file, sec)						\
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 235663b96adc..9ce68b385a1b 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -105,30 +105,11 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti
 	}
 	memset(reloc, 0, sizeof(*reloc));
 
-	if (insn_sec->sym) {
-		reloc->sym = insn_sec->sym;
-		reloc->addend = insn_off;
-	} else {
-		/*
-		 * The Clang assembler doesn't produce section symbols, so we
-		 * have to reference the function symbol instead:
-		 */
-		reloc->sym = find_symbol_containing(insn_sec, insn_off);
-		if (!reloc->sym) {
-			/*
-			 * Hack alert.  This happens when we need to reference
-			 * the NOP pad insn immediately after the function.
-			 */
-			reloc->sym = find_symbol_containing(insn_sec,
-							   insn_off - 1);
-		}
-		if (!reloc->sym) {
-			WARN("missing symbol for insn at offset 0x%lx\n",
-			     insn_off);
-			return -1;
-		}
-
-		reloc->addend = insn_off - reloc->sym->offset;
+	insn_to_reloc_sym_addend(insn_sec, insn_off, reloc);
+	if (!reloc->sym) {
+		WARN("missing symbol for insn at offset 0x%lx",
+		     insn_off);
+		return -1;
 	}
 
 	reloc->type = R_X86_64_PC32;
diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index d3740c8f399b..079cdfabb352 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -11,6 +11,7 @@
 		d	create a debug log
 		f	synthesize first level cache events
 		m	synthesize last level cache events
+		M	synthesize memory events
 		t	synthesize TLB events
 		a	synthesize remote access events
 		g	synthesize a call chain (use with i or x)
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 31069d8a5304..5c379adf8304 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -138,7 +138,7 @@ If you want to add or modify several config items, you can do like
 
 To modify the sort order of report functionality in user config file(i.e. `~/.perfconfig`), do
 
-	% perf config --user report sort-order=srcline
+	% perf config --user report.sort-order=srcline
 
 To change colors of selected line to other foreground and background colors
 in system config file (i.e. `$(sysconf)/perfconfig`), do
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 768888b9326a..34cf651ee237 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -293,6 +293,9 @@ OPTIONS
 --phys-data::
 	Record the sample physical addresses.
 
+--data-page-size::
+	Record the sampled data address data page size.
+
 -T::
 --timestamp::
 	Record the sample timestamps. Use it with 'perf report -D' to see the
@@ -634,11 +637,17 @@ endif::HAVE_LIBPFM[]
 --control=fifo:ctl-fifo[,ack-fifo]::
 --control=fd:ctl-fd[,ack-fd]::
 ctl-fifo / ack-fifo are opened and used as ctl-fd / ack-fd as follows.
-Listen on ctl-fd descriptor for command to control measurement ('enable': enable events,
-'disable': disable events, 'snapshot': AUX area tracing snapshot). Measurements can be
-started with events disabled using --delay=-1 option. Optionally send control command
-completion ('ack\n') to ack-fd descriptor to synchronize with the controlling process.
-Example of bash shell script to enable and disable events during measurements:
+Listen on ctl-fd descriptor for command to control measurement.
+
+Available commands:
+  'enable'  : enable events
+  'disable' : disable events
+  'snapshot': AUX area tracing snapshot).
+
+Measurements can be started with events disabled using --delay=-1 option. Optionally
+send control command completion ('ack\n') to ack-fd descriptor to synchronize with the
+controlling process.  Example of bash shell script to enable and disable events during
+measurements:
 
  #!/bin/bash
 
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index d068103690cc..8f7f4e9605d8 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -150,6 +150,7 @@ OPTIONS
 	- snoop: type of snoop (if any) for the data at the time of the sample
 	- dcacheline: the cacheline the data address is on at the time of the sample
 	- phys_daddr: physical address of data being executed on at the time of sample
+	- data_page_size: the data page size of data being executed on at the time of sample
 
 	And the default sort keys are changed to local_weight, mem, sym, dso,
 	symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 4f712fb8f175..44d37210fc8f 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,8 +116,9 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
-        brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode, ipc.
+        srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output,
+        brstackinsn, brstackoff, callindent, insn, insnlen, synth, phys_addr,
+        metric, misc, srccode, ipc, data_page_size.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 9f9f29025e49..5d4a673d7621 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -168,8 +168,9 @@ command line can be used: 'perf stat -e cycles -G cgroup_name -a -e cycles'.
 
 --for-each-cgroup name::
 Expand event list for each cgroup in "name" (allow multiple cgroups separated
-by comma).  This has same effect that repeating -e option and -G option for
-each event x name.  This option cannot be used with -G/--cgroup option.
+by comma).  It also support regex patterns to match multiple groups.  This has same
+effect that repeating -e option and -G option for each event x name.  This option
+cannot be used with -G/--cgroup option.
 
 -o file::
 --output file::
@@ -316,6 +317,10 @@ small group that need not have multiplexing is lowered. This option
 forbids the event merging logic from sharing events between groups and
 may be used to increase accuracy in this case.
 
+--quiet::
+Don't print output. This is useful with perf stat record below to only
+write data to the perf.data file.
+
 STAT RECORD
 -----------
 Stores stat data into perf data file.
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index cad7bf783413..bd446aba64f7 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -395,7 +395,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	 * To obtain the auxtrace buffer file descriptor, the auxtrace
 	 * event must come first.
 	 */
-	perf_evlist__to_front(evlist, cs_etm_evsel);
+	evlist__to_front(evlist, cs_etm_evsel);
 
 	/*
 	 * In the case of per-cpu mmaps, we need the CPU on the
@@ -420,7 +420,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 			goto out;
 
 		tracking_evsel = evlist__last(evlist);
-		perf_evlist__set_tracking_event(evlist, tracking_evsel);
+		evlist__set_tracking_event(evlist, tracking_evsel);
 
 		tracking_evsel->core.attr.freq = 0;
 		tracking_evsel->core.attr.sample_period = 1;
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index dbef716a1913..fab3095fb5d0 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -4,6 +4,7 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+HAVE_KVM_STAT_SUPPORT := 1
 
 #
 # Syscall table generation for perf
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index b53294d74b01..ead2f2275eee 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -2,6 +2,7 @@ perf-y += header.o
 perf-y += machine.o
 perf-y += perf_regs.o
 perf-y += tsc.o
+perf-y += kvm-stat.o
 perf-$(CONFIG_DWARF)     += dwarf-regs.o
 perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
@@ -9,4 +10,4 @@ perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
 			      ../../arm/util/auxtrace.o \
 			      ../../arm/util/cs-etm.o \
-			      arm-spe.o
+			      arm-spe.o mem-events.o
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index e3593063b3d1..414c8a5584b1 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -118,7 +118,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 * To obtain the auxtrace buffer file descriptor, the auxtrace event
 	 * must come first.
 	 */
-	perf_evlist__to_front(evlist, arm_spe_evsel);
+	evlist__to_front(evlist, arm_spe_evsel);
 
 	evsel__set_sample_bit(arm_spe_evsel, CPU);
 	evsel__set_sample_bit(arm_spe_evsel, TIME);
@@ -130,7 +130,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 		return err;
 
 	tracking_evsel = evlist__last(evlist);
-	perf_evlist__set_tracking_event(evlist, tracking_evsel);
+	evlist__set_tracking_event(evlist, tracking_evsel);
 
 	tracking_evsel->core.attr.freq = 0;
 	tracking_evsel->core.attr.sample_period = 1;
diff --git a/tools/perf/arch/arm64/util/arm64_exception_types.h b/tools/perf/arch/arm64/util/arm64_exception_types.h
new file mode 100644
index 000000000000..27c981ebe401
--- /dev/null
+++ b/tools/perf/arch/arm64/util/arm64_exception_types.h
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef ARCH_PERF_ARM64_EXCEPTION_TYPES_H
+#define ARCH_PERF_ARM64_EXCEPTION_TYPES_H
+
+/* Per asm/virt.h */
+#define HVC_STUB_ERR		  0xbadca11
+
+/* Per asm/kvm_asm.h */
+#define ARM_EXCEPTION_IRQ		0
+#define ARM_EXCEPTION_EL1_SERROR	1
+#define ARM_EXCEPTION_TRAP		2
+#define ARM_EXCEPTION_IL		3
+/* The hyp-stub will return this for any kvm_call_hyp() call */
+#define ARM_EXCEPTION_HYP_GONE		HVC_STUB_ERR
+
+#define kvm_arm_exception_type					\
+	{ARM_EXCEPTION_IRQ,		"IRQ"		},	\
+	{ARM_EXCEPTION_EL1_SERROR,	"SERROR"	},	\
+	{ARM_EXCEPTION_TRAP,		"TRAP"		},	\
+	{ARM_EXCEPTION_IL,		"ILLEGAL"	},	\
+	{ARM_EXCEPTION_HYP_GONE,	"HYP_GONE"	}
+
+/* Per asm/esr.h */
+#define ESR_ELx_EC_UNKNOWN	(0x00)
+#define ESR_ELx_EC_WFx		(0x01)
+/* Unallocated EC: 0x02 */
+#define ESR_ELx_EC_CP15_32	(0x03)
+#define ESR_ELx_EC_CP15_64	(0x04)
+#define ESR_ELx_EC_CP14_MR	(0x05)
+#define ESR_ELx_EC_CP14_LS	(0x06)
+#define ESR_ELx_EC_FP_ASIMD	(0x07)
+#define ESR_ELx_EC_CP10_ID	(0x08)	/* EL2 only */
+#define ESR_ELx_EC_PAC		(0x09)	/* EL2 and above */
+/* Unallocated EC: 0x0A - 0x0B */
+#define ESR_ELx_EC_CP14_64	(0x0C)
+/* Unallocated EC: 0x0d */
+#define ESR_ELx_EC_ILL		(0x0E)
+/* Unallocated EC: 0x0F - 0x10 */
+#define ESR_ELx_EC_SVC32	(0x11)
+#define ESR_ELx_EC_HVC32	(0x12)	/* EL2 only */
+#define ESR_ELx_EC_SMC32	(0x13)	/* EL2 and above */
+/* Unallocated EC: 0x14 */
+#define ESR_ELx_EC_SVC64	(0x15)
+#define ESR_ELx_EC_HVC64	(0x16)	/* EL2 and above */
+#define ESR_ELx_EC_SMC64	(0x17)	/* EL2 and above */
+#define ESR_ELx_EC_SYS64	(0x18)
+#define ESR_ELx_EC_SVE		(0x19)
+#define ESR_ELx_EC_ERET		(0x1a)	/* EL2 only */
+/* Unallocated EC: 0x1b - 0x1E */
+#define ESR_ELx_EC_IMP_DEF	(0x1f)	/* EL3 only */
+#define ESR_ELx_EC_IABT_LOW	(0x20)
+#define ESR_ELx_EC_IABT_CUR	(0x21)
+#define ESR_ELx_EC_PC_ALIGN	(0x22)
+/* Unallocated EC: 0x23 */
+#define ESR_ELx_EC_DABT_LOW	(0x24)
+#define ESR_ELx_EC_DABT_CUR	(0x25)
+#define ESR_ELx_EC_SP_ALIGN	(0x26)
+/* Unallocated EC: 0x27 */
+#define ESR_ELx_EC_FP_EXC32	(0x28)
+/* Unallocated EC: 0x29 - 0x2B */
+#define ESR_ELx_EC_FP_EXC64	(0x2C)
+/* Unallocated EC: 0x2D - 0x2E */
+#define ESR_ELx_EC_SERROR	(0x2F)
+#define ESR_ELx_EC_BREAKPT_LOW	(0x30)
+#define ESR_ELx_EC_BREAKPT_CUR	(0x31)
+#define ESR_ELx_EC_SOFTSTP_LOW	(0x32)
+#define ESR_ELx_EC_SOFTSTP_CUR	(0x33)
+#define ESR_ELx_EC_WATCHPT_LOW	(0x34)
+#define ESR_ELx_EC_WATCHPT_CUR	(0x35)
+/* Unallocated EC: 0x36 - 0x37 */
+#define ESR_ELx_EC_BKPT32	(0x38)
+/* Unallocated EC: 0x39 */
+#define ESR_ELx_EC_VECTOR32	(0x3A)	/* EL2 only */
+/* Unallocated EC: 0x3B */
+#define ESR_ELx_EC_BRK64	(0x3C)
+/* Unallocated EC: 0x3D - 0x3F */
+#define ESR_ELx_EC_MAX		(0x3F)
+
+#define ECN(x) { ESR_ELx_EC_##x, #x }
+
+#define kvm_arm_exception_class \
+	ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \
+	ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(PAC), ECN(CP14_64), \
+	ECN(SVC64), ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(SVE), \
+	ECN(IMP_DEF), ECN(IABT_LOW), ECN(IABT_CUR), \
+	ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \
+	ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \
+	ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \
+	ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \
+	ECN(BKPT32), ECN(VECTOR32), ECN(BRK64)
+
+#endif /* ARCH_PERF_ARM64_EXCEPTION_TYPES_H */
diff --git a/tools/perf/arch/arm64/util/kvm-stat.c b/tools/perf/arch/arm64/util/kvm-stat.c
new file mode 100644
index 000000000000..50376b9062c1
--- /dev/null
+++ b/tools/perf/arch/arm64/util/kvm-stat.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <memory.h>
+#include "../../util/evsel.h"
+#include "../../util/kvm-stat.h"
+#include "arm64_exception_types.h"
+#include "debug.h"
+
+define_exit_reasons_table(arm64_exit_reasons, kvm_arm_exception_type);
+define_exit_reasons_table(arm64_trap_exit_reasons, kvm_arm_exception_class);
+
+const char *kvm_trap_exit_reason = "esr_ec";
+const char *vcpu_id_str = "id";
+const int decode_str_len = 20;
+const char *kvm_exit_reason = "ret";
+const char *kvm_entry_trace = "kvm:kvm_entry";
+const char *kvm_exit_trace = "kvm:kvm_exit";
+
+const char *kvm_events_tp[] = {
+	"kvm:kvm_entry",
+	"kvm:kvm_exit",
+	NULL,
+};
+
+static void event_get_key(struct evsel *evsel,
+			  struct perf_sample *sample,
+			  struct event_key *key)
+{
+	key->info = 0;
+	key->key = evsel__intval(evsel, sample, kvm_exit_reason);
+	key->exit_reasons = arm64_exit_reasons;
+
+	/*
+	 * TRAP exceptions carry exception class info in esr_ec field
+	 * and, hence, we need to use a different exit_reasons table to
+	 * properly decode event's est_ec.
+	 */
+	if (key->key == ARM_EXCEPTION_TRAP) {
+		key->key = evsel__intval(evsel, sample, kvm_trap_exit_reason);
+		key->exit_reasons = arm64_trap_exit_reasons;
+	}
+}
+
+static bool event_begin(struct evsel *evsel,
+			struct perf_sample *sample __maybe_unused,
+			struct event_key *key __maybe_unused)
+{
+	return !strcmp(evsel->name, kvm_entry_trace);
+}
+
+static bool event_end(struct evsel *evsel,
+		      struct perf_sample *sample,
+		      struct event_key *key)
+{
+	if (!strcmp(evsel->name, kvm_exit_trace)) {
+		event_get_key(evsel, sample, key);
+		return true;
+	}
+	return false;
+}
+
+static struct kvm_events_ops exit_events = {
+	.is_begin_event = event_begin,
+	.is_end_event	= event_end,
+	.decode_key	= exit_event_decode_key,
+	.name		= "VM-EXIT"
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+	{
+		.name	= "vmexit",
+		.ops	= &exit_events,
+	},
+	{ NULL },
+};
+
+const char * const kvm_skip_events[] = {
+	NULL,
+};
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused)
+{
+	kvm->exit_reasons_isa = "arm64";
+	return 0;
+}
diff --git a/tools/perf/arch/arm64/util/mem-events.c b/tools/perf/arch/arm64/util/mem-events.c
new file mode 100644
index 000000000000..2a2497372671
--- /dev/null
+++ b/tools/perf/arch/arm64/util/mem-events.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "map_symbol.h"
+#include "mem-events.h"
+
+#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+
+static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("spe-load",	"arm_spe_0/ts_enable=1,load_filter=1,store_filter=0,min_latency=%u/",	"arm_spe_0"),
+	E("spe-store",	"arm_spe_0/ts_enable=1,load_filter=0,store_filter=1/",			"arm_spe_0"),
+	E("spe-ldst",	"arm_spe_0/ts_enable=1,load_filter=1,store_filter=1,min_latency=%u/",	"arm_spe_0"),
+};
+
+static char mem_ev_name[100];
+
+struct perf_mem_event *perf_mem_events__ptr(int i)
+{
+	if (i >= PERF_MEM_EVENTS__MAX)
+		return NULL;
+
+	return &perf_mem_events[i];
+}
+
+char *perf_mem_events__name(int i)
+{
+	struct perf_mem_event *e = perf_mem_events__ptr(i);
+
+	if (i >= PERF_MEM_EVENTS__MAX)
+		return NULL;
+
+	if (i == PERF_MEM_EVENTS__LOAD || i == PERF_MEM_EVENTS__LOAD_STORE)
+		scnprintf(mem_ev_name, sizeof(mem_ev_name),
+			  e->name, perf_mem_events__loads_ldlat);
+	else /* PERF_MEM_EVENTS__STORE */
+		scnprintf(mem_ev_name, sizeof(mem_ev_name), e->name);
+
+	return mem_ev_name;
+}
diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c
index 2833e101a7c6..54efa12fdbea 100644
--- a/tools/perf/arch/arm64/util/perf_regs.c
+++ b/tools/perf/arch/arm64/util/perf_regs.c
@@ -2,5 +2,38 @@
 #include "../../../util/perf_regs.h"
 
 const struct sample_reg sample_reg_masks[] = {
+	SMPL_REG(x0, PERF_REG_ARM64_X0),
+	SMPL_REG(x1, PERF_REG_ARM64_X1),
+	SMPL_REG(x2, PERF_REG_ARM64_X2),
+	SMPL_REG(x3, PERF_REG_ARM64_X3),
+	SMPL_REG(x4, PERF_REG_ARM64_X4),
+	SMPL_REG(x5, PERF_REG_ARM64_X5),
+	SMPL_REG(x6, PERF_REG_ARM64_X6),
+	SMPL_REG(x7, PERF_REG_ARM64_X7),
+	SMPL_REG(x8, PERF_REG_ARM64_X8),
+	SMPL_REG(x9, PERF_REG_ARM64_X9),
+	SMPL_REG(x10, PERF_REG_ARM64_X10),
+	SMPL_REG(x11, PERF_REG_ARM64_X11),
+	SMPL_REG(x12, PERF_REG_ARM64_X12),
+	SMPL_REG(x13, PERF_REG_ARM64_X13),
+	SMPL_REG(x14, PERF_REG_ARM64_X14),
+	SMPL_REG(x15, PERF_REG_ARM64_X15),
+	SMPL_REG(x16, PERF_REG_ARM64_X16),
+	SMPL_REG(x17, PERF_REG_ARM64_X17),
+	SMPL_REG(x18, PERF_REG_ARM64_X18),
+	SMPL_REG(x19, PERF_REG_ARM64_X19),
+	SMPL_REG(x20, PERF_REG_ARM64_X20),
+	SMPL_REG(x21, PERF_REG_ARM64_X21),
+	SMPL_REG(x22, PERF_REG_ARM64_X22),
+	SMPL_REG(x23, PERF_REG_ARM64_X23),
+	SMPL_REG(x24, PERF_REG_ARM64_X24),
+	SMPL_REG(x25, PERF_REG_ARM64_X25),
+	SMPL_REG(x26, PERF_REG_ARM64_X26),
+	SMPL_REG(x27, PERF_REG_ARM64_X27),
+	SMPL_REG(x28, PERF_REG_ARM64_X28),
+	SMPL_REG(x29, PERF_REG_ARM64_X29),
+	SMPL_REG(lr, PERF_REG_ARM64_LR),
+	SMPL_REG(sp, PERF_REG_ARM64_SP),
+	SMPL_REG(pc, PERF_REG_ARM64_PC),
 	SMPL_REG_END
 };
diff --git a/tools/perf/arch/mips/Build b/tools/perf/arch/mips/Build
index 1bb8bf6d7fd4..e4e5f33c84d8 100644
--- a/tools/perf/arch/mips/Build
+++ b/tools/perf/arch/mips/Build
@@ -1 +1 @@
-# empty
+perf-y += util/
diff --git a/tools/perf/arch/mips/annotate/instructions.c b/tools/perf/arch/mips/annotate/instructions.c
new file mode 100644
index 000000000000..340993f2a897
--- /dev/null
+++ b/tools/perf/arch/mips/annotate/instructions.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+
+static
+struct ins_ops *mips__associate_ins_ops(struct arch *arch, const char *name)
+{
+	struct ins_ops *ops = NULL;
+
+	if (!strncmp(name, "bal", 3) ||
+	    !strncmp(name, "bgezal", 6) ||
+	    !strncmp(name, "bltzal", 6) ||
+	    !strncmp(name, "bgtzal", 6) ||
+	    !strncmp(name, "blezal", 6) ||
+	    !strncmp(name, "beqzal", 6) ||
+	    !strncmp(name, "bnezal", 6) ||
+	    !strncmp(name, "bgtzl", 5) ||
+	    !strncmp(name, "bltzl", 5) ||
+	    !strncmp(name, "bgezl", 5) ||
+	    !strncmp(name, "blezl", 5) ||
+	    !strncmp(name, "jialc", 5) ||
+	    !strncmp(name, "beql", 4) ||
+	    !strncmp(name, "bnel", 4) ||
+	    !strncmp(name, "jal", 3))
+		ops = &call_ops;
+	else if (!strncmp(name, "jr", 2))
+		ops = &ret_ops;
+	else if (name[0] == 'j' || name[0] == 'b')
+		ops = &jump_ops;
+	else
+		return NULL;
+
+	arch__associate_ins_ops(arch, name, ops);
+
+	return ops;
+}
+
+static
+int mips__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
+{
+	if (!arch->initialized) {
+		arch->associate_instruction_ops = mips__associate_ins_ops;
+		arch->initialized = true;
+		arch->objdump.comment_char = '#';
+	}
+
+	return 0;
+}
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index e58d00d62f02..840ea0e59287 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -14,7 +14,6 @@ PERF_HAVE_JITDUMP := 1
 out    := $(OUTPUT)arch/powerpc/include/generated/asm
 header32 := $(out)/syscalls_32.c
 header64 := $(out)/syscalls_64.c
-syskrn := $(srctree)/arch/powerpc/kernel/syscalls/syscall.tbl
 sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls
 sysdef := $(sysprf)/syscall.tbl
 systbl := $(sysprf)/mksyscalltbl
@@ -23,15 +22,9 @@ systbl := $(sysprf)/mksyscalltbl
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header64): $(sysdef) $(systbl)
-	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
-	(diff -B $(sysdef) $(syskrn) >/dev/null) \
-	|| echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
 	$(Q)$(SHELL) '$(systbl)' '64' $(sysdef) > $@
 
 $(header32): $(sysdef) $(systbl)
-	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
-	(diff -B $(sysdef) $(syskrn) >/dev/null) \
-	|| echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
 	$(Q)$(SHELL) '$(systbl)' '32' $(sysdef) > $@
 
 clean::
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index b168364ac050..f744eb5cba88 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -9,7 +9,9 @@
 #
 0	nospu	restart_syscall			sys_restart_syscall
 1	nospu	exit				sys_exit
-2	nospu	fork				ppc_fork
+2	32	fork				ppc_fork			sys_fork
+2	64	fork				sys_fork
+2	spu	fork				sys_ni_syscall
 3	common	read				sys_read
 4	common	write				sys_write
 5	common	open				sys_open			compat_sys_open
@@ -158,7 +160,9 @@
 119	32	sigreturn			sys_sigreturn			compat_sys_sigreturn
 119	64	sigreturn			sys_ni_syscall
 119	spu	sigreturn			sys_ni_syscall
-120	nospu	clone				ppc_clone
+120	32	clone				ppc_clone			sys_clone
+120	64	clone				sys_clone
+120	spu	clone				sys_ni_syscall
 121	common	setdomainname			sys_setdomainname
 122	common	uname				sys_newuname
 123	common	modify_ldt			sys_ni_syscall
@@ -240,7 +244,9 @@
 186	spu	sendfile			sys_sendfile64
 187	common	getpmsg				sys_ni_syscall
 188	common 	putpmsg				sys_ni_syscall
-189	nospu	vfork				ppc_vfork
+189	32	vfork				ppc_vfork			sys_vfork
+189	64	vfork				sys_vfork
+189	spu	vfork				sys_ni_syscall
 190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
 191	common	readahead			sys_readahead			compat_sys_readahead
 192	32	mmap2				sys_mmap2			compat_sys_mmap2
@@ -316,8 +322,8 @@
 248	32	clock_nanosleep			sys_clock_nanosleep_time32
 248	64	clock_nanosleep			sys_clock_nanosleep
 248	spu	clock_nanosleep			sys_clock_nanosleep
-249	32	swapcontext			ppc_swapcontext			ppc32_swapcontext
-249	64	swapcontext			ppc64_swapcontext
+249	32	swapcontext			ppc_swapcontext			compat_sys_swapcontext
+249	64	swapcontext			sys_swapcontext
 249	spu	swapcontext			sys_ni_syscall
 250	common	tgkill				sys_tgkill
 251	32	utimes				sys_utimes_time32
@@ -456,7 +462,7 @@
 361	common	bpf				sys_bpf
 362	nospu	execveat			sys_execveat			compat_sys_execveat
 363	32	switch_endian			sys_ni_syscall
-363	64	switch_endian			ppc_switch_endian
+363	64	switch_endian			sys_switch_endian
 363	spu	switch_endian			sys_ni_syscall
 364	common	userfaultfd			sys_userfaultfd
 365	common	membarrier			sys_membarrier
@@ -516,6 +522,12 @@
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
-435	nospu	clone3				ppc_clone3
+435	32	clone3				ppc_clone3			sys_clone3
+435	64	clone3				sys_clone3
+435	spu	clone3				sys_ni_syscall
+436	common	close_range			sys_close_range
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd
+439	common	faccessat2			sys_faccessat2
+440	common	process_madvise			sys_process_madvise
+441	common	epoll_pwait2			sys_epoll_pwait2		compat_sys_epoll_pwait2
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
index 6ac8887be7c9..74bffbea03e2 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -12,7 +12,6 @@ PERF_HAVE_JITDUMP := 1
 
 out    := $(OUTPUT)arch/s390/include/generated/asm
 header := $(out)/syscalls_64.c
-syskrn := $(srctree)/arch/s390/kernel/syscalls/syscall.tbl
 sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls
 sysdef := $(sysprf)/syscall.tbl
 systbl := $(sysprf)/mksyscalltbl
@@ -21,9 +20,6 @@ systbl := $(sysprf)/mksyscalltbl
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header): $(sysdef) $(systbl)
-	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
-        (diff -B $(sysdef) $(syskrn) >/dev/null) \
-        || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
 	$(Q)$(SHELL) '$(systbl)' $(sysdef) > $@
 
 clean::
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index d2fa9647ce25..d443423495e5 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -15,86 +15,86 @@
 5    common	open			sys_open			compat_sys_open
 6    common	close			sys_close			sys_close
 7    common	restart_syscall		sys_restart_syscall		sys_restart_syscall
-8    common	creat			sys_creat			compat_sys_creat
-9    common	link			sys_link			compat_sys_link
-10   common	unlink			sys_unlink			compat_sys_unlink
+8    common	creat			sys_creat			sys_creat
+9    common	link			sys_link			sys_link
+10   common	unlink			sys_unlink			sys_unlink
 11   common	execve			sys_execve			compat_sys_execve
-12   common	chdir			sys_chdir			compat_sys_chdir
-13   32		time			-				compat_sys_time
-14   common	mknod			sys_mknod			compat_sys_mknod
-15   common	chmod			sys_chmod			compat_sys_chmod
-16   32		lchown			-				compat_sys_s390_lchown16
+12   common	chdir			sys_chdir			sys_chdir
+13   32		time			-				sys_time32
+14   common	mknod			sys_mknod			sys_mknod
+15   common	chmod			sys_chmod			sys_chmod
+16   32		lchown			-				sys_lchown16
 19   common	lseek			sys_lseek			compat_sys_lseek
 20   common	getpid			sys_getpid			sys_getpid
-21   common	mount			sys_mount
-22   common	umount			sys_oldumount			compat_sys_oldumount
-23   32		setuid			-				compat_sys_s390_setuid16
-24   32		getuid			-				compat_sys_s390_getuid16
-25   32		stime			-				compat_sys_stime
+21   common	mount			sys_mount			sys_mount
+22   common	umount			sys_oldumount			sys_oldumount
+23   32		setuid			-				sys_setuid16
+24   32		getuid			-				sys_getuid16
+25   32		stime			-				sys_stime32
 26   common	ptrace			sys_ptrace			compat_sys_ptrace
 27   common	alarm			sys_alarm			sys_alarm
 29   common	pause			sys_pause			sys_pause
-30   common	utime			sys_utime			compat_sys_utime
-33   common	access			sys_access			compat_sys_access
+30   common	utime			sys_utime			sys_utime32
+33   common	access			sys_access			sys_access
 34   common	nice			sys_nice			sys_nice
 36   common	sync			sys_sync			sys_sync
 37   common	kill			sys_kill			sys_kill
-38   common	rename			sys_rename			compat_sys_rename
-39   common	mkdir			sys_mkdir			compat_sys_mkdir
-40   common	rmdir			sys_rmdir			compat_sys_rmdir
+38   common	rename			sys_rename			sys_rename
+39   common	mkdir			sys_mkdir			sys_mkdir
+40   common	rmdir			sys_rmdir			sys_rmdir
 41   common	dup			sys_dup				sys_dup
-42   common	pipe			sys_pipe			compat_sys_pipe
+42   common	pipe			sys_pipe			sys_pipe
 43   common	times			sys_times			compat_sys_times
-45   common	brk			sys_brk				compat_sys_brk
-46   32		setgid			-				compat_sys_s390_setgid16
-47   32		getgid			-				compat_sys_s390_getgid16
-48   common	signal			sys_signal			compat_sys_signal
-49   32		geteuid			-				compat_sys_s390_geteuid16
-50   32		getegid			-				compat_sys_s390_getegid16
-51   common	acct			sys_acct			compat_sys_acct
-52   common	umount2			sys_umount			compat_sys_umount
+45   common	brk			sys_brk				sys_brk
+46   32		setgid			-				sys_setgid16
+47   32		getgid			-				sys_getgid16
+48   common	signal			sys_signal			sys_signal
+49   32		geteuid			-				sys_geteuid16
+50   32		getegid			-				sys_getegid16
+51   common	acct			sys_acct			sys_acct
+52   common	umount2			sys_umount			sys_umount
 54   common	ioctl			sys_ioctl			compat_sys_ioctl
 55   common	fcntl			sys_fcntl			compat_sys_fcntl
 57   common	setpgid			sys_setpgid			sys_setpgid
 60   common	umask			sys_umask			sys_umask
-61   common	chroot			sys_chroot			compat_sys_chroot
+61   common	chroot			sys_chroot			sys_chroot
 62   common	ustat			sys_ustat			compat_sys_ustat
 63   common	dup2			sys_dup2			sys_dup2
 64   common	getppid			sys_getppid			sys_getppid
 65   common	getpgrp			sys_getpgrp			sys_getpgrp
 66   common	setsid			sys_setsid			sys_setsid
 67   common	sigaction		sys_sigaction			compat_sys_sigaction
-70   32		setreuid		-				compat_sys_s390_setreuid16
-71   32		setregid		-				compat_sys_s390_setregid16
-72   common	sigsuspend		sys_sigsuspend			compat_sys_sigsuspend
+70   32		setreuid		-				sys_setreuid16
+71   32		setregid		-				sys_setregid16
+72   common	sigsuspend		sys_sigsuspend			sys_sigsuspend
 73   common	sigpending		sys_sigpending			compat_sys_sigpending
-74   common	sethostname		sys_sethostname			compat_sys_sethostname
+74   common	sethostname		sys_sethostname			sys_sethostname
 75   common	setrlimit		sys_setrlimit			compat_sys_setrlimit
 76   32		getrlimit		-				compat_sys_old_getrlimit
 77   common	getrusage		sys_getrusage			compat_sys_getrusage
 78   common	gettimeofday		sys_gettimeofday		compat_sys_gettimeofday
 79   common	settimeofday		sys_settimeofday		compat_sys_settimeofday
-80   32		getgroups		-				compat_sys_s390_getgroups16
-81   32		setgroups		-				compat_sys_s390_setgroups16
-83   common	symlink			sys_symlink			compat_sys_symlink
-85   common	readlink		sys_readlink			compat_sys_readlink
-86   common	uselib			sys_uselib			compat_sys_uselib
-87   common	swapon			sys_swapon			compat_sys_swapon
-88   common	reboot			sys_reboot			compat_sys_reboot
+80   32		getgroups		-				sys_getgroups16
+81   32		setgroups		-				sys_setgroups16
+83   common	symlink			sys_symlink			sys_symlink
+85   common	readlink		sys_readlink			sys_readlink
+86   common	uselib			sys_uselib			sys_uselib
+87   common	swapon			sys_swapon			sys_swapon
+88   common	reboot			sys_reboot			sys_reboot
 89   common	readdir			-				compat_sys_old_readdir
 90   common	mmap			sys_old_mmap			compat_sys_s390_old_mmap
-91   common	munmap			sys_munmap			compat_sys_munmap
+91   common	munmap			sys_munmap			sys_munmap
 92   common	truncate		sys_truncate			compat_sys_truncate
 93   common	ftruncate		sys_ftruncate			compat_sys_ftruncate
 94   common	fchmod			sys_fchmod			sys_fchmod
-95   32		fchown			-				compat_sys_s390_fchown16
+95   32		fchown			-				sys_fchown16
 96   common	getpriority		sys_getpriority			sys_getpriority
 97   common	setpriority		sys_setpriority			sys_setpriority
 99   common	statfs			sys_statfs			compat_sys_statfs
 100  common	fstatfs			sys_fstatfs			compat_sys_fstatfs
 101  32		ioperm			-				-
 102  common	socketcall		sys_socketcall			compat_sys_socketcall
-103  common	syslog			sys_syslog			compat_sys_syslog
+103  common	syslog			sys_syslog			sys_syslog
 104  common	setitimer		sys_setitimer			compat_sys_setitimer
 105  common	getitimer		sys_getitimer			compat_sys_getitimer
 106  common	stat			sys_newstat			compat_sys_newstat
@@ -104,76 +104,76 @@
 111  common	vhangup			sys_vhangup			sys_vhangup
 112  common	idle			-				-
 114  common	wait4			sys_wait4			compat_sys_wait4
-115  common	swapoff			sys_swapoff			compat_sys_swapoff
+115  common	swapoff			sys_swapoff			sys_swapoff
 116  common	sysinfo			sys_sysinfo			compat_sys_sysinfo
 117  common	ipc			sys_s390_ipc			compat_sys_s390_ipc
 118  common	fsync			sys_fsync			sys_fsync
 119  common	sigreturn		sys_sigreturn			compat_sys_sigreturn
-120  common	clone			sys_clone			compat_sys_clone
-121  common	setdomainname		sys_setdomainname		compat_sys_setdomainname
-122  common	uname			sys_newuname			compat_sys_newuname
-124  common	adjtimex		sys_adjtimex			compat_sys_adjtimex
-125  common	mprotect		sys_mprotect			compat_sys_mprotect
+120  common	clone			sys_clone			sys_clone
+121  common	setdomainname		sys_setdomainname		sys_setdomainname
+122  common	uname			sys_newuname			sys_newuname
+124  common	adjtimex		sys_adjtimex			sys_adjtimex_time32
+125  common	mprotect		sys_mprotect			sys_mprotect
 126  common	sigprocmask		sys_sigprocmask			compat_sys_sigprocmask
 127  common	create_module		-				-
-128  common	init_module		sys_init_module			compat_sys_init_module
-129  common	delete_module		sys_delete_module		compat_sys_delete_module
+128  common	init_module		sys_init_module			sys_init_module
+129  common	delete_module		sys_delete_module		sys_delete_module
 130  common	get_kernel_syms		-				-
-131  common	quotactl		sys_quotactl			compat_sys_quotactl
+131  common	quotactl		sys_quotactl			sys_quotactl
 132  common	getpgid			sys_getpgid			sys_getpgid
 133  common	fchdir			sys_fchdir			sys_fchdir
-134  common	bdflush			sys_bdflush			compat_sys_bdflush
-135  common	sysfs			sys_sysfs			compat_sys_sysfs
+134  common	bdflush			sys_bdflush			sys_bdflush
+135  common	sysfs			sys_sysfs			sys_sysfs
 136  common	personality		sys_s390_personality		sys_s390_personality
 137  common	afs_syscall		-				-
-138  32		setfsuid		-				compat_sys_s390_setfsuid16
-139  32		setfsgid		-				compat_sys_s390_setfsgid16
-140  32		_llseek			-				compat_sys_llseek
+138  32		setfsuid		-				sys_setfsuid16
+139  32		setfsgid		-				sys_setfsgid16
+140  32		_llseek			-				sys_llseek
 141  common	getdents		sys_getdents			compat_sys_getdents
 142  32		_newselect		-				compat_sys_select
 142  64		select			sys_select			-
 143  common	flock			sys_flock			sys_flock
-144  common	msync			sys_msync			compat_sys_msync
-145  common	readv			sys_readv
-146  common	writev			sys_writev
+144  common	msync			sys_msync			sys_msync
+145  common	readv			sys_readv			sys_readv
+146  common	writev			sys_writev			sys_writev
 147  common	getsid			sys_getsid			sys_getsid
 148  common	fdatasync		sys_fdatasync			sys_fdatasync
 149  common	_sysctl			-				-
-150  common	mlock			sys_mlock			compat_sys_mlock
-151  common	munlock			sys_munlock			compat_sys_munlock
+150  common	mlock			sys_mlock			sys_mlock
+151  common	munlock			sys_munlock			sys_munlock
 152  common	mlockall		sys_mlockall			sys_mlockall
 153  common	munlockall		sys_munlockall			sys_munlockall
-154  common	sched_setparam		sys_sched_setparam		compat_sys_sched_setparam
-155  common	sched_getparam		sys_sched_getparam		compat_sys_sched_getparam
-156  common	sched_setscheduler	sys_sched_setscheduler		compat_sys_sched_setscheduler
+154  common	sched_setparam		sys_sched_setparam		sys_sched_setparam
+155  common	sched_getparam		sys_sched_getparam		sys_sched_getparam
+156  common	sched_setscheduler	sys_sched_setscheduler		sys_sched_setscheduler
 157  common	sched_getscheduler	sys_sched_getscheduler		sys_sched_getscheduler
 158  common	sched_yield		sys_sched_yield			sys_sched_yield
 159  common	sched_get_priority_max	sys_sched_get_priority_max	sys_sched_get_priority_max
 160  common	sched_get_priority_min	sys_sched_get_priority_min	sys_sched_get_priority_min
-161  common	sched_rr_get_interval	sys_sched_rr_get_interval	compat_sys_sched_rr_get_interval
-162  common	nanosleep		sys_nanosleep			compat_sys_nanosleep
-163  common	mremap			sys_mremap			compat_sys_mremap
-164  32		setresuid		-				compat_sys_s390_setresuid16
-165  32		getresuid		-				compat_sys_s390_getresuid16
+161  common	sched_rr_get_interval	sys_sched_rr_get_interval	sys_sched_rr_get_interval_time32
+162  common	nanosleep		sys_nanosleep			sys_nanosleep_time32
+163  common	mremap			sys_mremap			sys_mremap
+164  32		setresuid		-				sys_setresuid16
+165  32		getresuid		-				sys_getresuid16
 167  common	query_module		-				-
-168  common	poll			sys_poll			compat_sys_poll
+168  common	poll			sys_poll			sys_poll
 169  common	nfsservctl		-				-
-170  32		setresgid		-				compat_sys_s390_setresgid16
-171  32		getresgid		-				compat_sys_s390_getresgid16
-172  common	prctl			sys_prctl			compat_sys_prctl
+170  32		setresgid		-				sys_setresgid16
+171  32		getresgid		-				sys_getresgid16
+172  common	prctl			sys_prctl			sys_prctl
 173  common	rt_sigreturn		sys_rt_sigreturn		compat_sys_rt_sigreturn
 174  common	rt_sigaction		sys_rt_sigaction		compat_sys_rt_sigaction
 175  common	rt_sigprocmask		sys_rt_sigprocmask		compat_sys_rt_sigprocmask
 176  common	rt_sigpending		sys_rt_sigpending		compat_sys_rt_sigpending
-177  common	rt_sigtimedwait		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait
+177  common	rt_sigtimedwait		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait_time32
 178  common	rt_sigqueueinfo		sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
 179  common	rt_sigsuspend		sys_rt_sigsuspend		compat_sys_rt_sigsuspend
 180  common	pread64			sys_pread64			compat_sys_s390_pread64
 181  common	pwrite64		sys_pwrite64			compat_sys_s390_pwrite64
-182  32		chown			-				compat_sys_s390_chown16
-183  common	getcwd			sys_getcwd			compat_sys_getcwd
-184  common	capget			sys_capget			compat_sys_capget
-185  common	capset			sys_capset			compat_sys_capset
+182  32		chown			-				sys_chown16
+183  common	getcwd			sys_getcwd			sys_getcwd
+184  common	capget			sys_capget			sys_capget
+185  common	capset			sys_capset			sys_capset
 186  common	sigaltstack		sys_sigaltstack			compat_sys_sigaltstack
 187  common	sendfile		sys_sendfile64			compat_sys_sendfile
 188  common	getpmsg			-				-
@@ -187,7 +187,7 @@
 195  32		stat64			-				compat_sys_s390_stat64
 196  32		lstat64			-				compat_sys_s390_lstat64
 197  32		fstat64			-				compat_sys_s390_fstat64
-198  32		lchown32		-				compat_sys_lchown
+198  32		lchown32		-				sys_lchown
 198  64		lchown			sys_lchown			-
 199  32		getuid32		-				sys_getuid
 199  64		getuid			sys_getuid			-
@@ -201,21 +201,21 @@
 203  64		setreuid		sys_setreuid			-
 204  32		setregid32		-				sys_setregid
 204  64		setregid		sys_setregid			-
-205  32		getgroups32		-				compat_sys_getgroups
+205  32		getgroups32		-				sys_getgroups
 205  64		getgroups		sys_getgroups			-
-206  32		setgroups32		-				compat_sys_setgroups
+206  32		setgroups32		-				sys_setgroups
 206  64		setgroups		sys_setgroups			-
 207  32		fchown32		-				sys_fchown
 207  64		fchown			sys_fchown			-
 208  32		setresuid32		-				sys_setresuid
 208  64		setresuid		sys_setresuid			-
-209  32		getresuid32		-				compat_sys_getresuid
+209  32		getresuid32		-				sys_getresuid
 209  64		getresuid		sys_getresuid			-
 210  32		setresgid32		-				sys_setresgid
 210  64		setresgid		sys_setresgid			-
-211  32		getresgid32		-				compat_sys_getresgid
+211  32		getresgid32		-				sys_getresgid
 211  64		getresgid		sys_getresgid			-
-212  32		chown32			-				compat_sys_chown
+212  32		chown32			-				sys_chown
 212  64		chown			sys_chown			-
 213  32		setuid32		-				sys_setuid
 213  64		setuid			sys_setuid			-
@@ -225,166 +225,222 @@
 215  64		setfsuid		sys_setfsuid			-
 216  32		setfsgid32		-				sys_setfsgid
 216  64		setfsgid		sys_setfsgid			-
-217  common	pivot_root		sys_pivot_root			compat_sys_pivot_root
-218  common	mincore			sys_mincore			compat_sys_mincore
-219  common	madvise			sys_madvise			compat_sys_madvise
-220  common	getdents64		sys_getdents64			compat_sys_getdents64
+217  common	pivot_root		sys_pivot_root			sys_pivot_root
+218  common	mincore			sys_mincore			sys_mincore
+219  common	madvise			sys_madvise			sys_madvise
+220  common	getdents64		sys_getdents64			sys_getdents64
 221  32		fcntl64			-				compat_sys_fcntl64
 222  common	readahead		sys_readahead			compat_sys_s390_readahead
 223  32		sendfile64		-				compat_sys_sendfile64
-224  common	setxattr		sys_setxattr			compat_sys_setxattr
-225  common	lsetxattr		sys_lsetxattr			compat_sys_lsetxattr
-226  common	fsetxattr		sys_fsetxattr			compat_sys_fsetxattr
-227  common	getxattr		sys_getxattr			compat_sys_getxattr
-228  common	lgetxattr		sys_lgetxattr			compat_sys_lgetxattr
-229  common	fgetxattr		sys_fgetxattr			compat_sys_fgetxattr
-230  common	listxattr		sys_listxattr			compat_sys_listxattr
-231  common	llistxattr		sys_llistxattr			compat_sys_llistxattr
-232  common	flistxattr		sys_flistxattr			compat_sys_flistxattr
-233  common	removexattr		sys_removexattr			compat_sys_removexattr
-234  common	lremovexattr		sys_lremovexattr		compat_sys_lremovexattr
-235  common	fremovexattr		sys_fremovexattr		compat_sys_fremovexattr
+224  common	setxattr		sys_setxattr			sys_setxattr
+225  common	lsetxattr		sys_lsetxattr			sys_lsetxattr
+226  common	fsetxattr		sys_fsetxattr			sys_fsetxattr
+227  common	getxattr		sys_getxattr			sys_getxattr
+228  common	lgetxattr		sys_lgetxattr			sys_lgetxattr
+229  common	fgetxattr		sys_fgetxattr			sys_fgetxattr
+230  common	listxattr		sys_listxattr			sys_listxattr
+231  common	llistxattr		sys_llistxattr			sys_llistxattr
+232  common	flistxattr		sys_flistxattr			sys_flistxattr
+233  common	removexattr		sys_removexattr			sys_removexattr
+234  common	lremovexattr		sys_lremovexattr		sys_lremovexattr
+235  common	fremovexattr		sys_fremovexattr		sys_fremovexattr
 236  common	gettid			sys_gettid			sys_gettid
 237  common	tkill			sys_tkill			sys_tkill
-238  common	futex			sys_futex			compat_sys_futex
+238  common	futex			sys_futex			sys_futex_time32
 239  common	sched_setaffinity	sys_sched_setaffinity		compat_sys_sched_setaffinity
 240  common	sched_getaffinity	sys_sched_getaffinity		compat_sys_sched_getaffinity
 241  common	tgkill			sys_tgkill			sys_tgkill
 243  common	io_setup		sys_io_setup			compat_sys_io_setup
-244  common	io_destroy		sys_io_destroy			compat_sys_io_destroy
-245  common	io_getevents		sys_io_getevents		compat_sys_io_getevents
+244  common	io_destroy		sys_io_destroy			sys_io_destroy
+245  common	io_getevents		sys_io_getevents		sys_io_getevents_time32
 246  common	io_submit		sys_io_submit			compat_sys_io_submit
-247  common	io_cancel		sys_io_cancel			compat_sys_io_cancel
+247  common	io_cancel		sys_io_cancel			sys_io_cancel
 248  common	exit_group		sys_exit_group			sys_exit_group
 249  common	epoll_create		sys_epoll_create		sys_epoll_create
-250  common	epoll_ctl		sys_epoll_ctl			compat_sys_epoll_ctl
-251  common	epoll_wait		sys_epoll_wait			compat_sys_epoll_wait
-252  common	set_tid_address		sys_set_tid_address		compat_sys_set_tid_address
+250  common	epoll_ctl		sys_epoll_ctl			sys_epoll_ctl
+251  common	epoll_wait		sys_epoll_wait			sys_epoll_wait
+252  common	set_tid_address		sys_set_tid_address		sys_set_tid_address
 253  common	fadvise64		sys_fadvise64_64		compat_sys_s390_fadvise64
 254  common	timer_create		sys_timer_create		compat_sys_timer_create
-255  common	timer_settime		sys_timer_settime		compat_sys_timer_settime
-256  common	timer_gettime		sys_timer_gettime		compat_sys_timer_gettime
+255  common	timer_settime		sys_timer_settime		sys_timer_settime32
+256  common	timer_gettime		sys_timer_gettime		sys_timer_gettime32
 257  common	timer_getoverrun	sys_timer_getoverrun		sys_timer_getoverrun
 258  common	timer_delete		sys_timer_delete		sys_timer_delete
-259  common	clock_settime		sys_clock_settime		compat_sys_clock_settime
-260  common	clock_gettime		sys_clock_gettime		compat_sys_clock_gettime
-261  common	clock_getres		sys_clock_getres		compat_sys_clock_getres
-262  common	clock_nanosleep		sys_clock_nanosleep		compat_sys_clock_nanosleep
+259  common	clock_settime		sys_clock_settime		sys_clock_settime32
+260  common	clock_gettime		sys_clock_gettime		sys_clock_gettime32
+261  common	clock_getres		sys_clock_getres		sys_clock_getres_time32
+262  common	clock_nanosleep		sys_clock_nanosleep		sys_clock_nanosleep_time32
 264  32		fadvise64_64		-				compat_sys_s390_fadvise64_64
 265  common	statfs64		sys_statfs64			compat_sys_statfs64
 266  common	fstatfs64		sys_fstatfs64			compat_sys_fstatfs64
-267  common	remap_file_pages	sys_remap_file_pages		compat_sys_remap_file_pages
+267  common	remap_file_pages	sys_remap_file_pages		sys_remap_file_pages
 268  common	mbind			sys_mbind			compat_sys_mbind
 269  common	get_mempolicy		sys_get_mempolicy		compat_sys_get_mempolicy
 270  common	set_mempolicy		sys_set_mempolicy		compat_sys_set_mempolicy
 271  common	mq_open			sys_mq_open			compat_sys_mq_open
-272  common	mq_unlink		sys_mq_unlink			compat_sys_mq_unlink
-273  common	mq_timedsend		sys_mq_timedsend		compat_sys_mq_timedsend
-274  common	mq_timedreceive		sys_mq_timedreceive		compat_sys_mq_timedreceive
+272  common	mq_unlink		sys_mq_unlink			sys_mq_unlink
+273  common	mq_timedsend		sys_mq_timedsend		sys_mq_timedsend_time32
+274  common	mq_timedreceive		sys_mq_timedreceive		sys_mq_timedreceive_time32
 275  common	mq_notify		sys_mq_notify			compat_sys_mq_notify
 276  common	mq_getsetattr		sys_mq_getsetattr		compat_sys_mq_getsetattr
 277  common	kexec_load		sys_kexec_load			compat_sys_kexec_load
-278  common	add_key			sys_add_key			compat_sys_add_key
-279  common	request_key		sys_request_key			compat_sys_request_key
+278  common	add_key			sys_add_key			sys_add_key
+279  common	request_key		sys_request_key			sys_request_key
 280  common	keyctl			sys_keyctl			compat_sys_keyctl
 281  common	waitid			sys_waitid			compat_sys_waitid
 282  common	ioprio_set		sys_ioprio_set			sys_ioprio_set
 283  common	ioprio_get		sys_ioprio_get			sys_ioprio_get
 284  common	inotify_init		sys_inotify_init		sys_inotify_init
-285  common	inotify_add_watch	sys_inotify_add_watch		compat_sys_inotify_add_watch
+285  common	inotify_add_watch	sys_inotify_add_watch		sys_inotify_add_watch
 286  common	inotify_rm_watch	sys_inotify_rm_watch		sys_inotify_rm_watch
 287  common	migrate_pages		sys_migrate_pages		compat_sys_migrate_pages
 288  common	openat			sys_openat			compat_sys_openat
-289  common	mkdirat			sys_mkdirat			compat_sys_mkdirat
-290  common	mknodat			sys_mknodat			compat_sys_mknodat
-291  common	fchownat		sys_fchownat			compat_sys_fchownat
-292  common	futimesat		sys_futimesat			compat_sys_futimesat
+289  common	mkdirat			sys_mkdirat			sys_mkdirat
+290  common	mknodat			sys_mknodat			sys_mknodat
+291  common	fchownat		sys_fchownat			sys_fchownat
+292  common	futimesat		sys_futimesat			sys_futimesat_time32
 293  32		fstatat64		-				compat_sys_s390_fstatat64
 293  64		newfstatat		sys_newfstatat			-
-294  common	unlinkat		sys_unlinkat			compat_sys_unlinkat
-295  common	renameat		sys_renameat			compat_sys_renameat
-296  common	linkat			sys_linkat			compat_sys_linkat
-297  common	symlinkat		sys_symlinkat			compat_sys_symlinkat
-298  common	readlinkat		sys_readlinkat			compat_sys_readlinkat
-299  common	fchmodat		sys_fchmodat			compat_sys_fchmodat
-300  common	faccessat		sys_faccessat			compat_sys_faccessat
-301  common	pselect6		sys_pselect6			compat_sys_pselect6
-302  common	ppoll			sys_ppoll			compat_sys_ppoll
-303  common	unshare			sys_unshare			compat_sys_unshare
+294  common	unlinkat		sys_unlinkat			sys_unlinkat
+295  common	renameat		sys_renameat			sys_renameat
+296  common	linkat			sys_linkat			sys_linkat
+297  common	symlinkat		sys_symlinkat			sys_symlinkat
+298  common	readlinkat		sys_readlinkat			sys_readlinkat
+299  common	fchmodat		sys_fchmodat			sys_fchmodat
+300  common	faccessat		sys_faccessat			sys_faccessat
+301  common	pselect6		sys_pselect6			compat_sys_pselect6_time32
+302  common	ppoll			sys_ppoll			compat_sys_ppoll_time32
+303  common	unshare			sys_unshare			sys_unshare
 304  common	set_robust_list		sys_set_robust_list		compat_sys_set_robust_list
 305  common	get_robust_list		sys_get_robust_list		compat_sys_get_robust_list
-306  common	splice			sys_splice			compat_sys_splice
+306  common	splice			sys_splice			sys_splice
 307  common	sync_file_range		sys_sync_file_range		compat_sys_s390_sync_file_range
-308  common	tee			sys_tee				compat_sys_tee
+308  common	tee			sys_tee				sys_tee
 309  common	vmsplice		sys_vmsplice			sys_vmsplice
 310  common	move_pages		sys_move_pages			compat_sys_move_pages
-311  common	getcpu			sys_getcpu			compat_sys_getcpu
+311  common	getcpu			sys_getcpu			sys_getcpu
 312  common	epoll_pwait		sys_epoll_pwait			compat_sys_epoll_pwait
-313  common	utimes			sys_utimes			compat_sys_utimes
+313  common	utimes			sys_utimes			sys_utimes_time32
 314  common	fallocate		sys_fallocate			compat_sys_s390_fallocate
-315  common	utimensat		sys_utimensat			compat_sys_utimensat
+315  common	utimensat		sys_utimensat			sys_utimensat_time32
 316  common	signalfd		sys_signalfd			compat_sys_signalfd
 317  common	timerfd			-				-
 318  common	eventfd			sys_eventfd			sys_eventfd
 319  common	timerfd_create		sys_timerfd_create		sys_timerfd_create
-320  common	timerfd_settime		sys_timerfd_settime		compat_sys_timerfd_settime
-321  common	timerfd_gettime		sys_timerfd_gettime		compat_sys_timerfd_gettime
+320  common	timerfd_settime		sys_timerfd_settime		sys_timerfd_settime32
+321  common	timerfd_gettime		sys_timerfd_gettime		sys_timerfd_gettime32
 322  common	signalfd4		sys_signalfd4			compat_sys_signalfd4
 323  common	eventfd2		sys_eventfd2			sys_eventfd2
 324  common	inotify_init1		sys_inotify_init1		sys_inotify_init1
-325  common	pipe2			sys_pipe2			compat_sys_pipe2
+325  common	pipe2			sys_pipe2			sys_pipe2
 326  common	dup3			sys_dup3			sys_dup3
 327  common	epoll_create1		sys_epoll_create1		sys_epoll_create1
 328  common	preadv			sys_preadv			compat_sys_preadv
 329  common	pwritev			sys_pwritev			compat_sys_pwritev
 330  common	rt_tgsigqueueinfo	sys_rt_tgsigqueueinfo		compat_sys_rt_tgsigqueueinfo
-331  common	perf_event_open		sys_perf_event_open		compat_sys_perf_event_open
+331  common	perf_event_open		sys_perf_event_open		sys_perf_event_open
 332  common	fanotify_init		sys_fanotify_init		sys_fanotify_init
 333  common	fanotify_mark		sys_fanotify_mark		compat_sys_fanotify_mark
-334  common	prlimit64		sys_prlimit64			compat_sys_prlimit64
-335  common	name_to_handle_at	sys_name_to_handle_at		compat_sys_name_to_handle_at
+334  common	prlimit64		sys_prlimit64			sys_prlimit64
+335  common	name_to_handle_at	sys_name_to_handle_at		sys_name_to_handle_at
 336  common	open_by_handle_at	sys_open_by_handle_at		compat_sys_open_by_handle_at
-337  common	clock_adjtime		sys_clock_adjtime		compat_sys_clock_adjtime
+337  common	clock_adjtime		sys_clock_adjtime		sys_clock_adjtime32
 338  common	syncfs			sys_syncfs			sys_syncfs
 339  common	setns			sys_setns			sys_setns
 340  common	process_vm_readv	sys_process_vm_readv		sys_process_vm_readv
 341  common	process_vm_writev	sys_process_vm_writev		sys_process_vm_writev
 342  common	s390_runtime_instr	sys_s390_runtime_instr		sys_s390_runtime_instr
-343  common	kcmp			sys_kcmp			compat_sys_kcmp
-344  common	finit_module		sys_finit_module		compat_sys_finit_module
-345  common	sched_setattr		sys_sched_setattr		compat_sys_sched_setattr
-346  common	sched_getattr		sys_sched_getattr		compat_sys_sched_getattr
-347  common	renameat2		sys_renameat2			compat_sys_renameat2
-348  common	seccomp			sys_seccomp			compat_sys_seccomp
-349  common	getrandom		sys_getrandom			compat_sys_getrandom
-350  common	memfd_create		sys_memfd_create		compat_sys_memfd_create
-351  common	bpf			sys_bpf				compat_sys_bpf
-352  common	s390_pci_mmio_write	sys_s390_pci_mmio_write		compat_sys_s390_pci_mmio_write
-353  common	s390_pci_mmio_read	sys_s390_pci_mmio_read		compat_sys_s390_pci_mmio_read
+343  common	kcmp			sys_kcmp			sys_kcmp
+344  common	finit_module		sys_finit_module		sys_finit_module
+345  common	sched_setattr		sys_sched_setattr		sys_sched_setattr
+346  common	sched_getattr		sys_sched_getattr		sys_sched_getattr
+347  common	renameat2		sys_renameat2			sys_renameat2
+348  common	seccomp			sys_seccomp			sys_seccomp
+349  common	getrandom		sys_getrandom			sys_getrandom
+350  common	memfd_create		sys_memfd_create		sys_memfd_create
+351  common	bpf			sys_bpf				sys_bpf
+352  common	s390_pci_mmio_write	sys_s390_pci_mmio_write		sys_s390_pci_mmio_write
+353  common	s390_pci_mmio_read	sys_s390_pci_mmio_read		sys_s390_pci_mmio_read
 354  common	execveat		sys_execveat			compat_sys_execveat
 355  common	userfaultfd		sys_userfaultfd			sys_userfaultfd
 356  common	membarrier		sys_membarrier			sys_membarrier
-357  common	recvmmsg		sys_recvmmsg			compat_sys_recvmmsg
+357  common	recvmmsg		sys_recvmmsg			compat_sys_recvmmsg_time32
 358  common	sendmmsg		sys_sendmmsg			compat_sys_sendmmsg
 359  common	socket			sys_socket			sys_socket
-360  common	socketpair		sys_socketpair			compat_sys_socketpair
-361  common	bind			sys_bind			compat_sys_bind
-362  common	connect			sys_connect			compat_sys_connect
+360  common	socketpair		sys_socketpair			sys_socketpair
+361  common	bind			sys_bind			sys_bind
+362  common	connect			sys_connect			sys_connect
 363  common	listen			sys_listen			sys_listen
-364  common	accept4			sys_accept4			compat_sys_accept4
+364  common	accept4			sys_accept4			sys_accept4
 365  common	getsockopt		sys_getsockopt			sys_getsockopt
 366  common	setsockopt		sys_setsockopt			sys_setsockopt
-367  common	getsockname		sys_getsockname			compat_sys_getsockname
-368  common	getpeername		sys_getpeername			compat_sys_getpeername
-369  common	sendto			sys_sendto			compat_sys_sendto
+367  common	getsockname		sys_getsockname			sys_getsockname
+368  common	getpeername		sys_getpeername			sys_getpeername
+369  common	sendto			sys_sendto			sys_sendto
 370  common	sendmsg			sys_sendmsg			compat_sys_sendmsg
 371  common	recvfrom		sys_recvfrom			compat_sys_recvfrom
 372  common	recvmsg			sys_recvmsg			compat_sys_recvmsg
 373  common	shutdown		sys_shutdown			sys_shutdown
-374  common	mlock2			sys_mlock2			compat_sys_mlock2
-375  common	copy_file_range		sys_copy_file_range		compat_sys_copy_file_range
+374  common	mlock2			sys_mlock2			sys_mlock2
+375  common	copy_file_range		sys_copy_file_range		sys_copy_file_range
 376  common	preadv2			sys_preadv2			compat_sys_preadv2
 377  common	pwritev2		sys_pwritev2			compat_sys_pwritev2
-378  common	s390_guarded_storage	sys_s390_guarded_storage	compat_sys_s390_guarded_storage
-379  common	statx			sys_statx			compat_sys_statx
-380  common	s390_sthyi		sys_s390_sthyi			compat_sys_s390_sthyi
+378  common	s390_guarded_storage	sys_s390_guarded_storage	sys_s390_guarded_storage
+379  common	statx			sys_statx			sys_statx
+380  common	s390_sthyi		sys_s390_sthyi			sys_s390_sthyi
+381  common	kexec_file_load		sys_kexec_file_load		sys_kexec_file_load
+382  common	io_pgetevents		sys_io_pgetevents		compat_sys_io_pgetevents
+383  common	rseq			sys_rseq			sys_rseq
+384  common	pkey_mprotect		sys_pkey_mprotect		sys_pkey_mprotect
+385  common	pkey_alloc		sys_pkey_alloc			sys_pkey_alloc
+386  common	pkey_free		sys_pkey_free			sys_pkey_free
+# room for arch specific syscalls
+392	64	semtimedop		sys_semtimedop			-
+393  common	semget			sys_semget			sys_semget
+394  common	semctl			sys_semctl			compat_sys_semctl
+395  common	shmget			sys_shmget			sys_shmget
+396  common	shmctl			sys_shmctl			compat_sys_shmctl
+397  common	shmat			sys_shmat			compat_sys_shmat
+398  common	shmdt			sys_shmdt 			sys_shmdt
+399  common	msgget			sys_msgget			sys_msgget
+400  common	msgsnd			sys_msgsnd			compat_sys_msgsnd
+401  common	msgrcv			sys_msgrcv			compat_sys_msgrcv
+402  common	msgctl			sys_msgctl			compat_sys_msgctl
+403	32	clock_gettime64		-				sys_clock_gettime
+404	32	clock_settime64		-				sys_clock_settime
+405	32	clock_adjtime64		-				sys_clock_adjtime
+406	32	clock_getres_time64	-				sys_clock_getres
+407	32	clock_nanosleep_time64	-				sys_clock_nanosleep
+408	32	timer_gettime64		-				sys_timer_gettime
+409	32	timer_settime64		-				sys_timer_settime
+410	32	timerfd_gettime64	-				sys_timerfd_gettime
+411	32	timerfd_settime64	-				sys_timerfd_settime
+412	32	utimensat_time64	-				sys_utimensat
+413	32	pselect6_time64		-				compat_sys_pselect6_time64
+414	32	ppoll_time64		-				compat_sys_ppoll_time64
+416	32	io_pgetevents_time64	-				sys_io_pgetevents
+417	32	recvmmsg_time64		-				compat_sys_recvmmsg_time64
+418	32	mq_timedsend_time64	-				sys_mq_timedsend
+419	32	mq_timedreceive_time64	-				sys_mq_timedreceive
+420	32	semtimedop_time64	-				sys_semtimedop
+421	32	rt_sigtimedwait_time64	-				compat_sys_rt_sigtimedwait_time64
+422	32	futex_time64		-				sys_futex
+423	32	sched_rr_get_interval_time64	-			sys_sched_rr_get_interval
+424  common	pidfd_send_signal	sys_pidfd_send_signal		sys_pidfd_send_signal
+425  common	io_uring_setup		sys_io_uring_setup              sys_io_uring_setup
+426  common	io_uring_enter		sys_io_uring_enter              sys_io_uring_enter
+427  common	io_uring_register	sys_io_uring_register           sys_io_uring_register
+428  common	open_tree		sys_open_tree			sys_open_tree
+429  common	move_mount		sys_move_mount			sys_move_mount
+430  common	fsopen			sys_fsopen			sys_fsopen
+431  common	fsconfig		sys_fsconfig			sys_fsconfig
+432  common	fsmount			sys_fsmount			sys_fsmount
+433  common	fspick			sys_fspick			sys_fspick
+434  common	pidfd_open		sys_pidfd_open			sys_pidfd_open
+435  common	clone3			sys_clone3			sys_clone3
+436  common	close_range		sys_close_range			sys_close_range
+437  common	openat2			sys_openat2			sys_openat2
+438  common	pidfd_getfd		sys_pidfd_getfd			sys_pidfd_getfd
+439  common	faccessat2		sys_faccessat2			sys_faccessat2
+440  common	process_madvise		sys_process_madvise		sys_process_madvise
+441  common	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 379819244b91..78672124d28b 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -362,6 +362,7 @@
 438	common	pidfd_getfd		sys_pidfd_getfd
 439	common	faccessat2		sys_faccessat2
 440	common	process_madvise		sys_process_madvise
+441	common	epoll_pwait2		sys_epoll_pwait2
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index c41c5affe4be..6a54b94f1c25 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -7,7 +7,6 @@ struct test;
 
 /* Tests */
 int test__rdpmc(struct test *test __maybe_unused, int subtest);
-int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest);
 int test__insn_x86(struct test *test __maybe_unused, int subtest);
 int test__intel_pt_pkt_decoder(struct test *test, int subtest);
 int test__bp_modify(struct test *test, int subtest);
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index 2997c506550c..36d4f248b51d 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -3,6 +3,5 @@ perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 
 perf-y += arch-tests.o
 perf-y += rdpmc.o
-perf-y += perf-time-to-tsc.o
 perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o
 perf-$(CONFIG_X86_64) += bp-modify.o
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index 6763135aec17..bc25d727b4e9 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -8,10 +8,6 @@ struct test arch_tests[] = {
 		.desc = "x86 rdpmc",
 		.func = test__rdpmc,
 	},
-	{
-		.desc = "Convert perf time to TSC",
-		.func = test__perf_time_to_tsc,
-	},
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 	{
 		.desc = "DWARF unwind",
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index 3ec562a2aaba..27dd8cf9e060 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -52,7 +52,7 @@ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subt
 
 	evlist = evlist__new();
 	if (!evlist) {
-		pr_debug("perf_evlist__new failed\n");
+		pr_debug("evlist__new failed\n");
 		return TEST_FAIL;
 	}
 
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 0dc09b5809c1..4a76d49d25d6 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -218,7 +218,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 		 * To obtain the auxtrace buffer file descriptor, the auxtrace event
 		 * must come first.
 		 */
-		perf_evlist__to_front(evlist, intel_bts_evsel);
+		evlist__to_front(evlist, intel_bts_evsel);
 		/*
 		 * In the case of per-cpu mmaps, we need the CPU on the
 		 * AUX event.
@@ -238,7 +238,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 
 		tracking_evsel = evlist__last(evlist);
 
-		perf_evlist__set_tracking_event(evlist, tracking_evsel);
+		evlist__set_tracking_event(evlist, tracking_evsel);
 
 		tracking_evsel->core.attr.freq = 0;
 		tracking_evsel->core.attr.sample_period = 1;
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 082e5f2a415a..a6420c647959 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -416,7 +416,7 @@ static int intel_pt_track_switches(struct evlist *evlist)
 	struct evsel *evsel;
 	int err;
 
-	if (!perf_evlist__can_select_event(evlist, sched_switch))
+	if (!evlist__can_select_event(evlist, sched_switch))
 		return -EPERM;
 
 	err = parse_events(evlist, sched_switch, NULL);
@@ -846,7 +846,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		 * To obtain the auxtrace buffer file descriptor, the auxtrace
 		 * event must come first.
 		 */
-		perf_evlist__to_front(evlist, intel_pt_evsel);
+		evlist__to_front(evlist, intel_pt_evsel);
 		/*
 		 * In the case of per-cpu mmaps, we need the CPU on the
 		 * AUX event.
@@ -865,7 +865,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 
 		tracking_evsel = evlist__last(evlist);
 
-		perf_evlist__set_tracking_event(evlist, tracking_evsel);
+		evlist__set_tracking_event(evlist, tracking_evsel);
 
 		tracking_evsel->core.attr.freq = 0;
 		tracking_evsel->core.attr.sample_period = 1;
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 4940d10074c3..a23ba6bb99b6 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -412,7 +412,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 
 	if (dump_trace) {
 		perf_session__fprintf_nr_events(session, stdout);
-		perf_evlist__fprintf_nr_events(session->evlist, stdout);
+		evlist__fprintf_nr_events(session->evlist, stdout);
 		goto out;
 	}
 
@@ -598,7 +598,7 @@ int cmd_annotate(int argc, const char **argv)
 						      HEADER_BRANCH_STACK);
 
 	if (annotate.group_set)
-		perf_evlist__force_leader(annotate.session->evlist);
+		evlist__force_leader(annotate.session->evlist);
 
 	ret = symbol__annotation_init();
 	if (ret < 0)
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index d5bea5d3cd51..c5babeaa3b38 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -369,6 +369,10 @@ static struct perf_c2c c2c = {
 		.exit		= perf_event__process_exit,
 		.fork		= perf_event__process_fork,
 		.lost		= perf_event__process_lost,
+		.attr		= perf_event__process_attr,
+		.auxtrace_info  = perf_event__process_auxtrace_info,
+		.auxtrace       = perf_event__process_auxtrace,
+		.auxtrace_error = perf_event__process_auxtrace_error,
 		.ordered_events	= true,
 		.ordering_requires_timestamps = true,
 	},
@@ -2678,6 +2682,12 @@ static int setup_coalesce(const char *coalesce, bool no_source)
 
 static int perf_c2c__report(int argc, const char **argv)
 {
+	struct itrace_synth_opts itrace_synth_opts = {
+		.set = true,
+		.mem = true,	/* Only enable memory event */
+		.default_no_sample = true,
+	};
+
 	struct perf_session *session;
 	struct ui_progress prog;
 	struct perf_data data = {
@@ -2757,6 +2767,8 @@ static int perf_c2c__report(int argc, const char **argv)
 		goto out;
 	}
 
+	session->itrace_synth_opts = &itrace_synth_opts;
+
 	err = setup_nodes(session);
 	if (err) {
 		pr_err("Failed setup nodes\n");
@@ -2867,6 +2879,7 @@ static int perf_c2c__record(int argc, const char **argv)
 	int ret;
 	bool all_user = false, all_kernel = false;
 	bool event_set = false;
+	struct perf_mem_event *e;
 	struct option options[] = {
 	OPT_CALLBACK('e', "event", &event_set, "event",
 		     "event selector. Use 'perf c2c record -e list' to list available events",
@@ -2894,11 +2907,24 @@ static int perf_c2c__record(int argc, const char **argv)
 	rec_argv[i++] = "record";
 
 	if (!event_set) {
-		perf_mem_events[PERF_MEM_EVENTS__LOAD].record  = true;
-		perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
+		e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD_STORE);
+		/*
+		 * The load and store operations are required, use the event
+		 * PERF_MEM_EVENTS__LOAD_STORE if it is supported.
+		 */
+		if (e->tag) {
+			e->record = true;
+		} else {
+			e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD);
+			e->record = true;
+
+			e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE);
+			e->record = true;
+		}
 	}
 
-	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
+	e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD);
+	if (e->record)
 		rec_argv[i++] = "-W";
 
 	rec_argv[i++] = "-d";
@@ -2906,12 +2932,13 @@ static int perf_c2c__record(int argc, const char **argv)
 	rec_argv[i++] = "--sample-cpu";
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-		if (!perf_mem_events[j].record)
+		e = perf_mem_events__ptr(j);
+		if (!e->record)
 			continue;
 
-		if (!perf_mem_events[j].supported) {
+		if (!e->supported) {
 			pr_err("failed: event '%s' not supported\n",
-			       perf_mem_events[j].name);
+			       perf_mem_events__name(j));
 			free(rec_argv);
 			return -1;
 		}
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index cefc71506409..8f6c784ce629 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -494,7 +494,7 @@ static struct evsel *evsel_match(struct evsel *evsel,
 	return NULL;
 }
 
-static void perf_evlist__collapse_resort(struct evlist *evlist)
+static void evlist__collapse_resort(struct evlist *evlist)
 {
 	struct evsel *evsel;
 
@@ -1214,7 +1214,7 @@ static int __cmd_diff(void)
 			goto out_delete;
 		}
 
-		perf_evlist__collapse_resort(d->session->evlist);
+		evlist__collapse_resort(d->session->evlist);
 
 		if (pdiff.ptime_range)
 			zfree(&pdiff.ptime_range);
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 98e992801251..4617b32c9c97 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -17,6 +17,14 @@
 #include "util/data.h"
 #include "util/debug.h"
 #include <linux/err.h>
+#include "util/tool.h"
+
+static int process_header_feature(struct perf_session *session __maybe_unused,
+				  union perf_event *event __maybe_unused)
+{
+	session_done = 1;
+	return 0;
+}
 
 static int __cmd_evlist(const char *file_name, struct perf_attr_details *details)
 {
@@ -27,12 +35,20 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 		.mode      = PERF_DATA_MODE_READ,
 		.force     = details->force,
 	};
+	struct perf_tool tool = {
+		/* only needed for pipe mode */
+		.attr = perf_event__process_attr,
+		.feature = process_header_feature,
+	};
 	bool has_tracepoint = false;
 
-	session = perf_session__new(&data, 0, NULL);
+	session = perf_session__new(&data, 0, &tool);
 	if (IS_ERR(session))
 		return PTR_ERR(session);
 
+	if (data.is_pipe)
+		perf_session__process_events(session);
+
 	evlist__for_each_entry(session->evlist, pos) {
 		evsel__fprintf(pos, details, stdout);
 
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 9366fad591dc..d49448a1060c 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -67,7 +67,7 @@ static void sig_handler(int sig __maybe_unused)
 }
 
 /*
- * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
  * we asked by setting its exec_error to the function below,
  * ftrace__workload_exec_failed_signal.
  *
@@ -600,9 +600,8 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 	if (write_tracing_file("trace", "0") < 0)
 		goto out;
 
-	if (argc && perf_evlist__prepare_workload(ftrace->evlist,
-				&ftrace->target, argv, false,
-				ftrace__workload_exec_failed_signal) < 0) {
+	if (argc && evlist__prepare_workload(ftrace->evlist, &ftrace->target, argv, false,
+					     ftrace__workload_exec_failed_signal) < 0) {
 		goto out;
 	}
 
@@ -644,7 +643,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 		}
 	}
 
-	perf_evlist__start_workload(ftrace->evlist);
+	evlist__start_workload(ftrace->evlist);
 
 	if (ftrace->initial_delay) {
 		usleep(ftrace->initial_delay * 1000);
@@ -958,7 +957,7 @@ int cmd_ftrace(int argc, const char **argv)
 		goto out_delete_filters;
 	}
 
-	ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target);
+	ret = evlist__create_maps(ftrace.evlist, &ftrace.target);
 	if (ret < 0)
 		goto out_delete_evlist;
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 0462dc8db2e3..43937f4b399a 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -843,10 +843,12 @@ int cmd_inject(int argc, const char **argv)
 		.output = {
 			.path = "-",
 			.mode = PERF_DATA_MODE_WRITE,
+			.use_stdio = true,
 		},
 	};
 	struct perf_data data = {
 		.mode = PERF_DATA_MODE_READ,
+		.use_stdio = true,
 	};
 	int ret;
 
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index a50dae2c4ae9..0062445e8ead 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1960,18 +1960,15 @@ int cmd_kmem(int argc, const char **argv)
 	ret = -1;
 
 	if (kmem_slab) {
-		if (!perf_evlist__find_tracepoint_by_name(session->evlist,
-							  "kmem:kmalloc")) {
+		if (!evlist__find_tracepoint_by_name(session->evlist, "kmem:kmalloc")) {
 			pr_err(errmsg, "slab", "slab");
 			goto out_delete;
 		}
 	}
 
 	if (kmem_page) {
-		struct evsel *evsel;
+		struct evsel *evsel = evlist__find_tracepoint_by_name(session->evlist, "kmem:mm_page_alloc");
 
-		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
-							     "kmem:mm_page_alloc");
 		if (evsel == NULL) {
 			pr_err(errmsg, "page", "page");
 			goto out_delete;
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 460945ded6dd..1105c9e40a80 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -764,7 +764,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 		return (err == -EAGAIN) ? 0 : -1;
 
 	while ((event = perf_mmap__read_event(&md->core)) != NULL) {
-		err = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
+		err = evlist__parse_sample_timestamp(evlist, event, &timestamp);
 		if (err) {
 			perf_mmap__consume(&md->core);
 			pr_err("Failed to parse sample\n");
@@ -1022,7 +1022,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 	struct evlist *evlist = kvm->evlist;
 	char sbuf[STRERR_BUFSIZE];
 
-	perf_evlist__config(evlist, &kvm->opts, NULL);
+	evlist__config(evlist, &kvm->opts, NULL);
 
 	/*
 	 * Note: exclude_{guest,host} do not apply here.
@@ -1349,8 +1349,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 		OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid",
 			"record events on existing process id"),
 		OPT_CALLBACK('m', "mmap-pages", &kvm->opts.mmap_pages, "pages",
-			"number of mmap data pages",
-			perf_evlist__parse_mmap_pages),
+			"number of mmap data pages", evlist__parse_mmap_pages),
 		OPT_INCR('v', "verbose", &verbose,
 			"be more verbose (show counter open errors, etc)"),
 		OPT_BOOLEAN('a', "all-cpus", &kvm->opts.target.system_wide,
@@ -1442,7 +1441,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 		goto out;
 	}
 
-	if (perf_evlist__create_maps(kvm->evlist, &kvm->opts.target) < 0)
+	if (evlist__create_maps(kvm->evlist, &kvm->opts.target) < 0)
 		usage_with_options(live_usage, live_options);
 
 	/*
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 3523279af6af..823742036ddb 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -7,6 +7,7 @@
 #include "perf.h"
 
 #include <subcmd/parse-options.h>
+#include "util/auxtrace.h"
 #include "util/trace-event.h"
 #include "util/tool.h"
 #include "util/session.h"
@@ -64,6 +65,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	const char **rec_argv;
 	int ret;
 	bool all_user = false, all_kernel = false;
+	struct perf_mem_event *e;
 	struct option options[] = {
 	OPT_CALLBACK('e', "event", &mem, "event",
 		     "event selector. use 'perf mem record -e list' to list available events",
@@ -76,6 +78,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	OPT_END()
 	};
 
+	if (perf_mem_events__init()) {
+		pr_err("failed: memory events not supported\n");
+		return -1;
+	}
+
 	argc = parse_options(argc, argv, options, record_mem_usage,
 			     PARSE_OPT_KEEP_UNKNOWN);
 
@@ -86,13 +93,30 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
 	rec_argv[i++] = "record";
 
-	if (mem->operation & MEM_OPERATION_LOAD)
-		perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
+	e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD_STORE);
 
-	if (mem->operation & MEM_OPERATION_STORE)
-		perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
+	/*
+	 * The load and store operations are required, use the event
+	 * PERF_MEM_EVENTS__LOAD_STORE if it is supported.
+	 */
+	if (e->tag &&
+	    (mem->operation & MEM_OPERATION_LOAD) &&
+	    (mem->operation & MEM_OPERATION_STORE)) {
+		e->record = true;
+	} else {
+		if (mem->operation & MEM_OPERATION_LOAD) {
+			e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD);
+			e->record = true;
+		}
 
-	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
+		if (mem->operation & MEM_OPERATION_STORE) {
+			e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE);
+			e->record = true;
+		}
+	}
+
+	e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD);
+	if (e->record)
 		rec_argv[i++] = "-W";
 
 	rec_argv[i++] = "-d";
@@ -101,10 +125,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 		rec_argv[i++] = "--phys-data";
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-		if (!perf_mem_events[j].record)
+		e = perf_mem_events__ptr(j);
+		if (!e->record)
 			continue;
 
-		if (!perf_mem_events[j].supported) {
+		if (!e->supported) {
 			pr_err("failed: event '%s' not supported\n",
 			       perf_mem_events__name(j));
 			free(rec_argv);
@@ -231,6 +256,12 @@ static int process_sample_event(struct perf_tool *tool,
 
 static int report_raw_events(struct perf_mem *mem)
 {
+	struct itrace_synth_opts itrace_synth_opts = {
+		.set = true,
+		.mem = true,	/* Only enable memory event */
+		.default_no_sample = true,
+	};
+
 	struct perf_data data = {
 		.path  = input_name,
 		.mode  = PERF_DATA_MODE_READ,
@@ -243,6 +274,8 @@ static int report_raw_events(struct perf_mem *mem)
 	if (IS_ERR(session))
 		return PTR_ERR(session);
 
+	session->itrace_synth_opts = &itrace_synth_opts;
+
 	if (mem->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, mem->cpu_list,
 					       mem->cpu_bitmap);
@@ -265,11 +298,35 @@ out_delete:
 	perf_session__delete(session);
 	return ret;
 }
+static char *get_sort_order(struct perf_mem *mem)
+{
+	bool has_extra_options = mem->phys_addr ? true : false;
+	char sort[128];
+
+	/*
+	 * there is no weight (cost) associated with stores, so don't print
+	 * the column
+	 */
+	if (!(mem->operation & MEM_OPERATION_LOAD)) {
+		strcpy(sort, "--sort=mem,sym,dso,symbol_daddr,"
+			     "dso_daddr,tlb,locked");
+	} else if (has_extra_options) {
+		strcpy(sort, "--sort=local_weight,mem,sym,dso,symbol_daddr,"
+			     "dso_daddr,snoop,tlb,locked");
+	} else
+		return NULL;
+
+	if (mem->phys_addr)
+		strcat(sort, ",phys_daddr");
+
+	return strdup(sort);
+}
 
 static int report_events(int argc, const char **argv, struct perf_mem *mem)
 {
 	const char **rep_argv;
 	int ret, i = 0, j, rep_argc;
+	char *new_sort_order;
 
 	if (mem->dump_raw)
 		return report_raw_events(mem);
@@ -283,20 +340,9 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
 	rep_argv[i++] = "--mem-mode";
 	rep_argv[i++] = "-n"; /* display number of samples */
 
-	/*
-	 * there is no weight (cost) associated with stores, so don't print
-	 * the column
-	 */
-	if (!(mem->operation & MEM_OPERATION_LOAD)) {
-		if (mem->phys_addr)
-			rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
-					"dso_daddr,tlb,locked,phys_daddr";
-		else
-			rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
-					"dso_daddr,tlb,locked";
-	} else if (mem->phys_addr)
-		rep_argv[i++] = "--sort=local_weight,mem,sym,dso,symbol_daddr,"
-				"dso_daddr,snoop,tlb,locked,phys_daddr";
+	new_sort_order = get_sort_order(mem);
+	if (new_sort_order)
+		rep_argv[i++] = new_sort_order;
 
 	for (j = 1; j < argc; j++, i++)
 		rep_argv[i] = argv[j];
@@ -386,8 +432,12 @@ int cmd_mem(int argc, const char **argv)
 			.comm		= perf_event__process_comm,
 			.lost		= perf_event__process_lost,
 			.fork		= perf_event__process_fork,
+			.attr		= perf_event__process_attr,
 			.build_id	= perf_event__process_build_id,
 			.namespaces	= perf_event__process_namespaces,
+			.auxtrace_info  = perf_event__process_auxtrace_info,
+			.auxtrace       = perf_event__process_auxtrace,
+			.auxtrace_error = perf_event__process_auxtrace_error,
 			.ordered_events	= true,
 		},
 		.input_name		 = "perf.data",
@@ -422,11 +472,6 @@ int cmd_mem(int argc, const char **argv)
 		NULL
 	};
 
-	if (perf_mem_events__init()) {
-		pr_err("failed: memory events not supported\n");
-		return -1;
-	}
-
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
 					mem_usage, PARSE_OPT_KEEP_UNKNOWN);
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index adf311d15d3d..fd3911650612 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -891,13 +891,13 @@ static int record__open(struct record *rec)
 	 * event synthesis.
 	 */
 	if (opts->initial_delay || target__has_cpu(&opts->target)) {
-		pos = perf_evlist__get_tracking_event(evlist);
+		pos = evlist__get_tracking_event(evlist);
 		if (!evsel__is_dummy_event(pos)) {
 			/* Set up dummy event. */
 			if (evlist__add_dummy(evlist))
 				return -ENOMEM;
 			pos = evlist__last(evlist);
-			perf_evlist__set_tracking_event(evlist, pos);
+			evlist__set_tracking_event(evlist, pos);
 		}
 
 		/*
@@ -910,7 +910,7 @@ static int record__open(struct record *rec)
 			pos->immediate = 1;
 	}
 
-	perf_evlist__config(evlist, opts, &callchain_param);
+	evlist__config(evlist, opts, &callchain_param);
 
 	evlist__for_each_entry(evlist, pos) {
 try_again:
@@ -923,7 +923,7 @@ try_again:
 			if ((errno == EINVAL || errno == EBADF) &&
 			    pos->leader != pos &&
 			    pos->weak_group) {
-			        pos = perf_evlist__reset_weak_group(evlist, pos, true);
+			        pos = evlist__reset_weak_group(evlist, pos, true);
 				goto try_again;
 			}
 			rc = -errno;
@@ -935,7 +935,7 @@ try_again:
 		pos->supported = true;
 	}
 
-	if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(evlist)) {
+	if (symbol_conf.kptr_restrict && !evlist__exclude_kernel(evlist)) {
 		pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
 "check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n"
@@ -946,7 +946,7 @@ try_again:
 "even with a suitable vmlinux or kallsyms file.\n\n");
 	}
 
-	if (perf_evlist__apply_filters(evlist, &pos)) {
+	if (evlist__apply_filters(evlist, &pos)) {
 		pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n",
 			pos->filter, evsel__name(pos), errno,
 			str_error_r(errno, msg, sizeof(msg)));
@@ -1166,7 +1166,7 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist,
 		rc = record__write(rec, NULL, &finished_round_event, sizeof(finished_round_event));
 
 	if (overwrite)
-		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
+		evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
 out:
 	return rc;
 }
@@ -1333,7 +1333,7 @@ record__switch_output(struct record *rec, bool at_exit)
 static volatile int workload_exec_errno;
 
 /*
- * perf_evlist__prepare_workload will send a SIGUSR1
+ * evlist__prepare_workload will send a SIGUSR1
  * if the fork fails, since we asked by setting its
  * want_signal to true.
  */
@@ -1349,8 +1349,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 static void snapshot_sig_handler(int sig);
 static void alarm_sig_handler(int sig);
 
-static const struct perf_event_mmap_page *
-perf_evlist__pick_pc(struct evlist *evlist)
+static const struct perf_event_mmap_page *evlist__pick_pc(struct evlist *evlist)
 {
 	if (evlist) {
 		if (evlist->mmap && evlist->mmap[0].core.base)
@@ -1363,9 +1362,7 @@ perf_evlist__pick_pc(struct evlist *evlist)
 
 static const struct perf_event_mmap_page *record__pick_pc(struct record *rec)
 {
-	const struct perf_event_mmap_page *pc;
-
-	pc = perf_evlist__pick_pc(rec->evlist);
+	const struct perf_event_mmap_page *pc = evlist__pick_pc(rec->evlist);
 	if (pc)
 		return pc;
 	return NULL;
@@ -1444,7 +1441,7 @@ static int record__synthesize(struct record *rec, bool tail)
 			goto out;
 	}
 
-	if (!perf_evlist__exclude_kernel(rec->evlist)) {
+	if (!evlist__exclude_kernel(rec->evlist)) {
 		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
 							 machine);
 		WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
@@ -1548,7 +1545,7 @@ static int record__setup_sb_evlist(struct record *rec)
 		}
 	}
 #endif
-	if (perf_evlist__start_sb_thread(rec->sb_evlist, &rec->opts.target)) {
+	if (evlist__start_sb_thread(rec->sb_evlist, &rec->opts.target)) {
 		pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
 		opts->no_bpf_event = true;
 	}
@@ -1689,9 +1686,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	record__init_features(rec);
 
 	if (forks) {
-		err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
-						    argv, data->is_pipe,
-						    workload_exec_failed_signal);
+		err = evlist__prepare_workload(rec->evlist, &opts->target, argv, data->is_pipe,
+					       workload_exec_failed_signal);
 		if (err < 0) {
 			pr_err("Couldn't run the workload!\n");
 			status = err;
@@ -1835,7 +1831,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 						  machine);
 		free(event);
 
-		perf_evlist__start_workload(rec->evlist);
+		evlist__start_workload(rec->evlist);
 	}
 
 	if (evlist__initialize_ctlfd(rec->evlist, opts->ctl_fd, opts->ctl_fd_ack))
@@ -1861,11 +1857,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		 * BKW_MMAP_EMPTY here: when done == true and
 		 * hits != rec->samples in previous round.
 		 *
-		 * perf_evlist__toggle_bkw_mmap ensure we never
+		 * evlist__toggle_bkw_mmap ensure we never
 		 * convert BKW_MMAP_EMPTY to BKW_MMAP_DATA_PENDING.
 		 */
 		if (trigger_is_hit(&switch_output_trigger) || done || draining)
-			perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING);
+			evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING);
 
 		if (record__mmap_read_all(rec, false) < 0) {
 			trigger_error(&auxtrace_snapshot_trigger);
@@ -1904,7 +1900,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 			 * record__mmap_read_all(): we should have collected
 			 * data from it.
 			 */
-			perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_RUNNING);
+			evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_RUNNING);
 
 			if (!quiet)
 				fprintf(stderr, "[ perf record: dump data: Woken up %ld times ]\n",
@@ -2066,7 +2062,7 @@ out_delete_session:
 	perf_session__delete(session);
 
 	if (!opts->no_bpf_event)
-		perf_evlist__stop_sb_thread(rec->sb_evlist);
+		evlist__stop_sb_thread(rec->sb_evlist);
 	return status;
 }
 
@@ -2222,7 +2218,7 @@ static int record__parse_mmap_pages(const struct option *opt,
 		*p = '\0';
 
 	if (*s) {
-		ret = __perf_evlist__parse_mmap_pages(&mmap_pages, s);
+		ret = __evlist__parse_mmap_pages(&mmap_pages, s);
 		if (ret)
 			goto out_free;
 		opts->mmap_pages = mmap_pages;
@@ -2233,7 +2229,7 @@ static int record__parse_mmap_pages(const struct option *opt,
 		goto out_free;
 	}
 
-	ret = __perf_evlist__parse_mmap_pages(&mmap_pages, p + 1);
+	ret = __evlist__parse_mmap_pages(&mmap_pages, p + 1);
 	if (ret)
 		goto out_free;
 
@@ -2413,7 +2409,7 @@ static bool dry_run;
  * XXX Will stay a global variable till we fix builtin-script.c to stop messing
  * with it and switch to use the library functions in perf_evlist that came
  * from builtin-record.c, i.e. use record_opts,
- * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
+ * evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
  * using pipes, etc.
  */
 static struct option __record_options[] = {
@@ -2476,6 +2472,8 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
 	OPT_BOOLEAN(0, "phys-data", &record.opts.sample_phys_addr,
 		    "Record the sample physical addresses"),
+	OPT_BOOLEAN(0, "data-page-size", &record.opts.sample_data_page_size,
+		    "Record the sampled data address data page size"),
 	OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
 	OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
 			&record.opts.sample_time_set,
@@ -2793,7 +2791,7 @@ int cmd_record(int argc, const char **argv)
 	rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX || rec->opts.target.pid;
 
 	err = -ENOMEM;
-	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
+	if (evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);
 
 	err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3c74c9c0f3c3..2a845d6cac09 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -211,7 +211,7 @@ static void setup_forced_leader(struct report *report,
 				struct evlist *evlist)
 {
 	if (report->group_set)
-		perf_evlist__force_leader(evlist);
+		evlist__force_leader(evlist);
 }
 
 static int process_feature_event(struct perf_session *session,
@@ -226,6 +226,8 @@ static int process_feature_event(struct perf_session *session,
 		pr_err("failed: wrong feature ID: %" PRI_lu64 "\n",
 		       event->feat.feat_id);
 		return -1;
+	} else if (rep->header_only) {
+		session_done = 1;
 	}
 
 	/*
@@ -493,8 +495,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 	return ret + fprintf(fp, "\n#\n");
 }
 
-static int perf_evlist__tui_block_hists_browse(struct evlist *evlist,
-					       struct report *rep)
+static int evlist__tui_block_hists_browse(struct evlist *evlist, struct report *rep)
 {
 	struct evsel *pos;
 	int i = 0, ret;
@@ -511,9 +512,7 @@ static int perf_evlist__tui_block_hists_browse(struct evlist *evlist,
 	return 0;
 }
 
-static int perf_evlist__tty_browse_hists(struct evlist *evlist,
-					 struct report *rep,
-					 const char *help)
+static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, const char *help)
 {
 	struct evsel *pos;
 	int i = 0;
@@ -566,7 +565,7 @@ static void report__warn_kptr_restrict(const struct report *rep)
 	struct map *kernel_map = machine__kernel_map(&rep->session->machines.host);
 	struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL;
 
-	if (perf_evlist__exclude_kernel(rep->session->evlist))
+	if (evlist__exclude_kernel(rep->session->evlist))
 		return;
 
 	if (kernel_map == NULL ||
@@ -595,7 +594,7 @@ static int report__gtk_browse_hists(struct report *rep, const char *help)
 	int (*hist_browser)(struct evlist *evlist, const char *help,
 			    struct hist_browser_timer *timer, float min_pcnt);
 
-	hist_browser = dlsym(perf_gtk_handle, "perf_evlist__gtk_browse_hists");
+	hist_browser = dlsym(perf_gtk_handle, "evlist__gtk_browse_hists");
 
 	if (hist_browser == NULL) {
 		ui__error("GTK browser not found!\n");
@@ -622,14 +621,12 @@ static int report__browse_hists(struct report *rep)
 	switch (use_browser) {
 	case 1:
 		if (rep->total_cycles_mode) {
-			ret = perf_evlist__tui_block_hists_browse(evlist, rep);
+			ret = evlist__tui_block_hists_browse(evlist, rep);
 			break;
 		}
 
-		ret = perf_evlist__tui_browse_hists(evlist, help, NULL,
-						    rep->min_percent,
-						    &session->header.env,
-						    true, &rep->annotation_opts);
+		ret = evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent,
+					       &session->header.env, true, &rep->annotation_opts);
 		/*
 		 * Usually "ret" is the last pressed key, and we only
 		 * care if the key notifies us to switch data file.
@@ -641,7 +638,7 @@ static int report__browse_hists(struct report *rep)
 		ret = report__gtk_browse_hists(rep, help);
 		break;
 	default:
-		ret = perf_evlist__tty_browse_hists(evlist, rep, help);
+		ret = evlist__tty_browse_hists(evlist, rep, help);
 		break;
 	}
 
@@ -933,7 +930,7 @@ static int __cmd_report(struct report *rep)
 
 		if (dump_trace) {
 			perf_session__fprintf_nr_events(session, stdout);
-			perf_evlist__fprintf_nr_events(session->evlist, stdout);
+			evlist__fprintf_nr_events(session->evlist, stdout);
 			return 0;
 		}
 	}
@@ -1517,6 +1514,13 @@ repeat:
 		perf_session__fprintf_info(session, stdout,
 					   report.show_full_info);
 		if (report.header_only) {
+			if (data.is_pipe) {
+				/*
+				 * we need to process first few records
+				 * which contains PERF_RECORD_HEADER_FEATURE.
+				 */
+				perf_session__process_events(session);
+			}
 			ret = 0;
 			goto error;
 		}
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 0e16f9d5a947..69c769b04a61 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -3036,8 +3036,7 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	setup_pager();
 
 	/* prefer sched_waking if it is captured */
-	if (perf_evlist__find_tracepoint_by_name(session->evlist,
-						  "sched:sched_waking"))
+	if (evlist__find_tracepoint_by_name(session->evlist, "sched:sched_waking"))
 		handlers[1].handler = timehist_sched_wakeup_ignore;
 
 	/* setup per-evsel handlers */
@@ -3045,8 +3044,7 @@ static int perf_sched__timehist(struct perf_sched *sched)
 		goto out;
 
 	/* sched_switch event at a minimum needs to exist */
-	if (!perf_evlist__find_tracepoint_by_name(session->evlist,
-						  "sched:sched_switch")) {
+	if (!evlist__find_tracepoint_by_name(session->evlist, "sched:sched_switch")) {
 		pr_err("No sched_switch events found. Have you run 'perf sched record'?\n");
 		goto out;
 	}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 48588ccf902e..edacfa98d073 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -30,6 +30,7 @@
 #include "util/thread-stack.h"
 #include "util/time-utils.h"
 #include "util/path.h"
+#include "util/event.h"
 #include "ui/ui.h"
 #include "print_binary.h"
 #include "archinsn.h"
@@ -115,6 +116,7 @@ enum perf_output_field {
 	PERF_OUTPUT_SRCCODE	    = 1ULL << 30,
 	PERF_OUTPUT_IPC             = 1ULL << 31,
 	PERF_OUTPUT_TOD             = 1ULL << 32,
+	PERF_OUTPUT_DATA_PAGE_SIZE  = 1ULL << 33,
 };
 
 struct perf_script {
@@ -179,6 +181,7 @@ struct output_option {
 	{.str = "srccode", .field = PERF_OUTPUT_SRCCODE},
 	{.str = "ipc", .field = PERF_OUTPUT_IPC},
 	{.str = "tod", .field = PERF_OUTPUT_TOD},
+	{.str = "data_page_size", .field = PERF_OUTPUT_DATA_PAGE_SIZE},
 };
 
 enum {
@@ -251,7 +254,8 @@ static struct {
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
 			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
 			      PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC |
-			      PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR,
+			      PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR |
+			      PERF_OUTPUT_DATA_PAGE_SIZE,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -499,6 +503,10 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 	    evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR))
 		return -EINVAL;
 
+	if (PRINT_FIELD(DATA_PAGE_SIZE) &&
+	    evsel__check_stype(evsel, PERF_SAMPLE_DATA_PAGE_SIZE, "DATA_PAGE_SIZE", PERF_OUTPUT_DATA_PAGE_SIZE))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -1847,7 +1855,7 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 	u64 val;
 
 	if (!evsel->stats)
-		perf_evlist__alloc_stats(script->session->evlist, false);
+		evlist__alloc_stats(script->session->evlist, false);
 	if (evsel_script(evsel->leader)->gnum++ == 0)
 		perf_stat__reset_shadow_stats();
 	val = sample->period * evsel->scale;
@@ -1920,6 +1928,7 @@ static void process_event(struct perf_script *script,
 	unsigned int type = output_type(attr->type);
 	struct evsel_script *es = evsel->priv;
 	FILE *fp = es->fp;
+	char str[PAGE_SIZE_NAME_LEN];
 
 	if (output[type].fields == 0)
 		return;
@@ -2008,6 +2017,9 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(PHYS_ADDR))
 		fprintf(fp, "%16" PRIx64, sample->phys_addr);
 
+	if (PRINT_FIELD(DATA_PAGE_SIZE))
+		fprintf(fp, " %s", get_page_size_name(sample->data_page_size, str));
+
 	perf_sample__fprintf_ipc(sample, attr, fp);
 
 	fprintf(fp, "\n");
@@ -2224,7 +2236,7 @@ static int print_event_with_time(struct perf_tool *tool,
 {
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
-	struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	struct evsel *evsel = evlist__id2evsel(session->evlist, sample->id);
 	struct thread *thread = NULL;
 
 	if (evsel && !evsel->core.attr.sample_id_all) {
@@ -3308,7 +3320,7 @@ static int set_maps(struct perf_script *script)
 
 	perf_evlist__set_maps(&evlist->core, script->cpus, script->threads);
 
-	if (perf_evlist__alloc_stats(evlist, true))
+	if (evlist__alloc_stats(evlist, true))
 		return -ENOMEM;
 
 	script->allocated = true;
@@ -3506,7 +3518,8 @@ int cmd_script(int argc, const char **argv)
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
 		     "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
-		     "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod",
+		     "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod,"
+		     "data_page_size",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
@@ -3935,7 +3948,7 @@ out_delete:
 		zfree(&script.ptime_range);
 	}
 
-	perf_evlist__free_stats(session->evlist);
+	evlist__free_stats(session->evlist);
 	perf_session__delete(session);
 
 	if (script_started)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b01af171d94f..8cc24967bc27 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -270,7 +270,7 @@ static void perf_stat__reset_stats(void)
 {
 	int i;
 
-	perf_evlist__reset_stats(evsel_list);
+	evlist__reset_stats(evsel_list);
 	perf_stat__reset_shadow_stats();
 
 	for (i = 0; i < stat_config.stats_num; i++)
@@ -534,7 +534,7 @@ static void disable_counters(void)
 static volatile int workload_exec_errno;
 
 /*
- * perf_evlist__prepare_workload will send a SIGUSR1
+ * evlist__prepare_workload will send a SIGUSR1
  * if the fork fails, since we asked by setting its
  * want_signal to true.
  */
@@ -724,8 +724,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	bool second_pass = false;
 
 	if (forks) {
-		if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe,
-						  workload_exec_failed_signal) < 0) {
+		if (evlist__prepare_workload(evsel_list, &target, argv, is_pipe, workload_exec_failed_signal) < 0) {
 			perror("failed to prepare workload");
 			return -1;
 		}
@@ -733,7 +732,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	}
 
 	if (group)
-		perf_evlist__set_leader(evsel_list);
+		evlist__set_leader(evsel_list);
 
 	if (affinity__setup(&affinity) < 0)
 		return -1;
@@ -760,7 +759,7 @@ try_again:
 				if ((errno == EINVAL || errno == EBADF) &&
 				    counter->leader != counter &&
 				    counter->weak_group) {
-					perf_evlist__reset_weak_group(evsel_list, counter, false);
+					evlist__reset_weak_group(evsel_list, counter, false);
 					assert(counter->reset_group);
 					second_pass = true;
 					continue;
@@ -843,7 +842,7 @@ try_again_reset:
 			return -1;
 	}
 
-	if (perf_evlist__apply_filters(evsel_list, &counter)) {
+	if (evlist__apply_filters(evsel_list, &counter)) {
 		pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n",
 			counter->filter, evsel__name(counter), errno,
 			str_error_r(errno, msg, sizeof(msg)));
@@ -876,7 +875,7 @@ try_again_reset:
 	clock_gettime(CLOCK_MONOTONIC, &ref_time);
 
 	if (forks) {
-		perf_evlist__start_workload(evsel_list);
+		evlist__start_workload(evsel_list);
 		enable_counters();
 
 		if (interval || timeout || evlist__ctlfd_initialized(evsel_list))
@@ -914,10 +913,10 @@ try_again_reset:
 		update_stats(&walltime_nsecs_stats, t1 - t0);
 
 		if (stat_config.aggr_mode == AGGR_GLOBAL)
-			perf_evlist__save_aggr_prev_raw_counts(evsel_list);
+			evlist__save_aggr_prev_raw_counts(evsel_list);
 
-		perf_evlist__copy_prev_raw_counts(evsel_list);
-		perf_evlist__reset_prev_raw_counts(evsel_list);
+		evlist__copy_prev_raw_counts(evsel_list);
+		evlist__reset_prev_raw_counts(evsel_list);
 		runtime_stat_reset(&stat_config);
 		perf_stat__reset_shadow_per_stat(&rt_stat);
 	} else
@@ -972,9 +971,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	/* Do not print anything if we record to the pipe. */
 	if (STAT_RECORD && perf_stat.data.is_pipe)
 		return;
+	if (stat_config.quiet)
+		return;
 
-	perf_evlist__print_counters(evsel_list, &stat_config, &target,
-				    ts, argc, argv);
+	evlist__print_counters(evsel_list, &stat_config, &target, ts, argc, argv);
 }
 
 static volatile int signr = -1;
@@ -1171,6 +1171,8 @@ static struct option stat_options[] = {
 		    "threads of same physical core"),
 	OPT_BOOLEAN(0, "summary", &stat_config.summary,
 		       "print summary for interval mode"),
+	OPT_BOOLEAN(0, "quiet", &stat_config.quiet,
+			"don't print output (useful with record)"),
 #ifdef HAVE_LIBPFM
 	OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
 		"libpfm4 event selector. use 'perf list' to list available events",
@@ -1184,65 +1186,67 @@ static struct option stat_options[] = {
 	OPT_END()
 };
 
-static int perf_stat__get_socket(struct perf_stat_config *config __maybe_unused,
+static struct aggr_cpu_id perf_stat__get_socket(struct perf_stat_config *config __maybe_unused,
 				 struct perf_cpu_map *map, int cpu)
 {
 	return cpu_map__get_socket(map, cpu, NULL);
 }
 
-static int perf_stat__get_die(struct perf_stat_config *config __maybe_unused,
+static struct aggr_cpu_id perf_stat__get_die(struct perf_stat_config *config __maybe_unused,
 			      struct perf_cpu_map *map, int cpu)
 {
 	return cpu_map__get_die(map, cpu, NULL);
 }
 
-static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
+static struct aggr_cpu_id perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
 			       struct perf_cpu_map *map, int cpu)
 {
 	return cpu_map__get_core(map, cpu, NULL);
 }
 
-static int perf_stat__get_node(struct perf_stat_config *config __maybe_unused,
+static struct aggr_cpu_id perf_stat__get_node(struct perf_stat_config *config __maybe_unused,
 			       struct perf_cpu_map *map, int cpu)
 {
 	return cpu_map__get_node(map, cpu, NULL);
 }
 
-static int perf_stat__get_aggr(struct perf_stat_config *config,
+static struct aggr_cpu_id perf_stat__get_aggr(struct perf_stat_config *config,
 			       aggr_get_id_t get_id, struct perf_cpu_map *map, int idx)
 {
 	int cpu;
+	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
 
 	if (idx >= map->nr)
-		return -1;
+		return id;
 
 	cpu = map->map[idx];
 
-	if (config->cpus_aggr_map->map[cpu] == -1)
+	if (cpu_map__aggr_cpu_id_is_empty(config->cpus_aggr_map->map[cpu]))
 		config->cpus_aggr_map->map[cpu] = get_id(config, map, idx);
 
-	return config->cpus_aggr_map->map[cpu];
+	id = config->cpus_aggr_map->map[cpu];
+	return id;
 }
 
-static int perf_stat__get_socket_cached(struct perf_stat_config *config,
+static struct aggr_cpu_id perf_stat__get_socket_cached(struct perf_stat_config *config,
 					struct perf_cpu_map *map, int idx)
 {
 	return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);
 }
 
-static int perf_stat__get_die_cached(struct perf_stat_config *config,
+static struct aggr_cpu_id perf_stat__get_die_cached(struct perf_stat_config *config,
 					struct perf_cpu_map *map, int idx)
 {
 	return perf_stat__get_aggr(config, perf_stat__get_die, map, idx);
 }
 
-static int perf_stat__get_core_cached(struct perf_stat_config *config,
+static struct aggr_cpu_id perf_stat__get_core_cached(struct perf_stat_config *config,
 				      struct perf_cpu_map *map, int idx)
 {
 	return perf_stat__get_aggr(config, perf_stat__get_core, map, idx);
 }
 
-static int perf_stat__get_node_cached(struct perf_stat_config *config,
+static struct aggr_cpu_id perf_stat__get_node_cached(struct perf_stat_config *config,
 				      struct perf_cpu_map *map, int idx)
 {
 	return perf_stat__get_aggr(config, perf_stat__get_node, map, idx);
@@ -1316,14 +1320,29 @@ static int perf_stat_init_aggr_mode(void)
 	 * the aggregation translate cpumap.
 	 */
 	nr = perf_cpu_map__max(evsel_list->core.cpus);
-	stat_config.cpus_aggr_map = perf_cpu_map__empty_new(nr + 1);
+	stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1);
 	return stat_config.cpus_aggr_map ? 0 : -ENOMEM;
 }
 
+static void cpu_aggr_map__delete(struct cpu_aggr_map *map)
+{
+	if (map) {
+		WARN_ONCE(refcount_read(&map->refcnt) != 0,
+			  "cpu_aggr_map refcnt unbalanced\n");
+		free(map);
+	}
+}
+
+static void cpu_aggr_map__put(struct cpu_aggr_map *map)
+{
+	if (map && refcount_dec_and_test(&map->refcnt))
+		cpu_aggr_map__delete(map);
+}
+
 static void perf_stat__exit_aggr_mode(void)
 {
-	perf_cpu_map__put(stat_config.aggr_map);
-	perf_cpu_map__put(stat_config.cpus_aggr_map);
+	cpu_aggr_map__put(stat_config.aggr_map);
+	cpu_aggr_map__put(stat_config.cpus_aggr_map);
 	stat_config.aggr_map = NULL;
 	stat_config.cpus_aggr_map = NULL;
 }
@@ -1343,117 +1362,108 @@ static inline int perf_env__get_cpu(struct perf_env *env, struct perf_cpu_map *m
 	return cpu;
 }
 
-static int perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data)
 {
 	struct perf_env *env = data;
 	int cpu = perf_env__get_cpu(env, map, idx);
+	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
 
-	return cpu == -1 ? -1 : env->cpu[cpu].socket_id;
+	if (cpu != -1)
+		id.socket = env->cpu[cpu].socket_id;
+
+	return id;
 }
 
-static int perf_env__get_die(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_die(struct perf_cpu_map *map, int idx, void *data)
 {
 	struct perf_env *env = data;
-	int die_id = -1, cpu = perf_env__get_cpu(env, map, idx);
+	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+	int cpu = perf_env__get_cpu(env, map, idx);
 
 	if (cpu != -1) {
 		/*
-		 * Encode socket in bit range 15:8
-		 * die_id is relative to socket,
-		 * we need a global id. So we combine
-		 * socket + die id
+		 * die_id is relative to socket, so start
+		 * with the socket ID and then add die to
+		 * make a unique ID.
 		 */
-		if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n"))
-			return -1;
-
-		if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
-			return -1;
-
-		die_id = (env->cpu[cpu].socket_id << 8) | (env->cpu[cpu].die_id & 0xff);
+		id.socket = env->cpu[cpu].socket_id;
+		id.die = env->cpu[cpu].die_id;
 	}
 
-	return die_id;
+	return id;
 }
 
-static int perf_env__get_core(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_core(struct perf_cpu_map *map, int idx, void *data)
 {
 	struct perf_env *env = data;
-	int core = -1, cpu = perf_env__get_cpu(env, map, idx);
+	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+	int cpu = perf_env__get_cpu(env, map, idx);
 
 	if (cpu != -1) {
 		/*
-		 * Encode socket in bit range 31:24
-		 * encode die id in bit range 23:16
 		 * core_id is relative to socket and die,
-		 * we need a global id. So we combine
-		 * socket + die id + core id
+		 * we need a global id. So we set
+		 * socket, die id and core id
 		 */
-		if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n"))
-			return -1;
-
-		if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n"))
-			return -1;
-
-		if (WARN_ONCE(env->cpu[cpu].core_id >> 16, "The core id number is too big.\n"))
-			return -1;
-
-		core = (env->cpu[cpu].socket_id << 24) |
-		       (env->cpu[cpu].die_id << 16) |
-		       (env->cpu[cpu].core_id & 0xffff);
+		id.socket = env->cpu[cpu].socket_id;
+		id.die = env->cpu[cpu].die_id;
+		id.core = env->cpu[cpu].core_id;
 	}
 
-	return core;
+	return id;
 }
 
-static int perf_env__get_node(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_node(struct perf_cpu_map *map, int idx, void *data)
 {
 	int cpu = perf_env__get_cpu(data, map, idx);
+	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
 
-	return perf_env__numa_node(data, cpu);
+	id.node = perf_env__numa_node(data, cpu);
+	return id;
 }
 
 static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus,
-				      struct perf_cpu_map **sockp)
+				      struct cpu_aggr_map **sockp)
 {
 	return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
 }
 
 static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus,
-				   struct perf_cpu_map **diep)
+				   struct cpu_aggr_map **diep)
 {
 	return cpu_map__build_map(cpus, diep, perf_env__get_die, env);
 }
 
 static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus,
-				    struct perf_cpu_map **corep)
+				    struct cpu_aggr_map **corep)
 {
 	return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
 }
 
 static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus,
-				    struct perf_cpu_map **nodep)
+				    struct cpu_aggr_map **nodep)
 {
 	return cpu_map__build_map(cpus, nodep, perf_env__get_node, env);
 }
 
-static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,
+static struct aggr_cpu_id perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,
 				      struct perf_cpu_map *map, int idx)
 {
 	return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
 }
-static int perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused,
+static struct aggr_cpu_id perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused,
 				   struct perf_cpu_map *map, int idx)
 {
 	return perf_env__get_die(map, idx, &perf_stat.session->header.env);
 }
 
-static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
+static struct aggr_cpu_id perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
 				    struct perf_cpu_map *map, int idx)
 {
 	return perf_env__get_core(map, idx, &perf_stat.session->header.env);
 }
 
-static int perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused,
+static struct aggr_cpu_id perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused,
 				    struct perf_cpu_map *map, int idx)
 {
 	return perf_env__get_node(map, idx, &perf_stat.session->header.env);
@@ -1904,7 +1914,7 @@ static int set_maps(struct perf_stat *st)
 
 	perf_evlist__set_maps(&evsel_list->core, st->cpus, st->threads);
 
-	if (perf_evlist__alloc_stats(evsel_list, true))
+	if (evlist__alloc_stats(evsel_list, true))
 		return -ENOMEM;
 
 	st->maps_allocated = true;
@@ -2132,7 +2142,7 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 	}
 
-	if (!output) {
+	if (!output && !stat_config.quiet) {
 		struct timespec tm;
 		mode = append_file ? "a" : "w";
 
@@ -2235,8 +2245,11 @@ int cmd_stat(int argc, const char **argv)
 		}
 
 		if (evlist__expand_cgroup(evsel_list, stat_config.cgroup_list,
-					  &stat_config.metric_events, true) < 0)
+					  &stat_config.metric_events, true) < 0) {
+			parse_options_usage(stat_usage, stat_options,
+					    "for-each-cgroup", 0);
 			goto out;
+		}
 	}
 
 	target__validate(&target);
@@ -2244,7 +2257,7 @@ int cmd_stat(int argc, const char **argv)
 	if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide))
 		target.per_thread = true;
 
-	if (perf_evlist__create_maps(evsel_list, &target) < 0) {
+	if (evlist__create_maps(evsel_list, &target) < 0) {
 		if (target__has_task(&target)) {
 			pr_err("Problems finding threads of monitor\n");
 			parse_options_usage(stat_usage, stat_options, "p", 1);
@@ -2303,7 +2316,7 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 	}
 
-	if (perf_evlist__alloc_stats(evsel_list, interval))
+	if (evlist__alloc_stats(evsel_list, interval))
 		goto out;
 
 	if (perf_stat_init_aggr_mode())
@@ -2343,7 +2356,7 @@ int cmd_stat(int argc, const char **argv)
 				run_idx + 1);
 
 		if (run_idx != 0)
-			perf_evlist__reset_prev_raw_counts(evsel_list);
+			evlist__reset_prev_raw_counts(evsel_list);
 
 		status = run_perf_stat(argc, argv, run_idx);
 		if (forever && status != -1 && !interval) {
@@ -2394,7 +2407,7 @@ int cmd_stat(int argc, const char **argv)
 	}
 
 	perf_stat__exit_aggr_mode();
-	perf_evlist__free_stats(evsel_list);
+	evlist__free_stats(evsel_list);
 out:
 	zfree(&stat_config.walltime_run);
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 7c64134472c7..3673c04d16b6 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -641,12 +641,9 @@ repeat:
 		hists->uid_filter_str = top->record_opts.target.uid_str;
 	}
 
-	ret = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
-				      top->min_percent,
-				      &top->session->header.env,
-				      !top->record_opts.overwrite,
-				      &top->annotation_opts);
-
+	ret = evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
+				       &top->session->header.env, !top->record_opts.overwrite,
+				       &top->annotation_opts);
 	if (ret == K_RELOAD) {
 		top->zero = true;
 		goto repeat;
@@ -782,7 +779,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (!machine->kptr_restrict_warned &&
 	    symbol_conf.kptr_restrict &&
 	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
-		if (!perf_evlist__exclude_kernel(top->session->evlist)) {
+		if (!evlist__exclude_kernel(top->session->evlist)) {
 			ui__warning(
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n"
@@ -890,7 +887,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	while ((event = perf_mmap__read_event(&md->core)) != NULL) {
 		int ret;
 
-		ret = perf_evlist__parse_sample_timestamp(evlist, event, &last_timestamp);
+		ret = evlist__parse_sample_timestamp(evlist, event, &last_timestamp);
 		if (ret && ret != -1)
 			break;
 
@@ -918,14 +915,14 @@ static void perf_top__mmap_read(struct perf_top *top)
 	int i;
 
 	if (overwrite)
-		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING);
+		evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING);
 
 	for (i = 0; i < top->evlist->core.nr_mmaps; i++)
 		perf_top__mmap_read_idx(top, i);
 
 	if (overwrite) {
-		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
-		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+		evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
+		evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
 	}
 }
 
@@ -1025,7 +1022,7 @@ static int perf_top__start_counters(struct perf_top *top)
 		goto out_err;
 	}
 
-	perf_evlist__config(evlist, opts, &callchain_param);
+	evlist__config(evlist, opts, &callchain_param);
 
 	evlist__for_each_entry(evlist, counter) {
 try_again:
@@ -1153,13 +1150,13 @@ static int deliver_event(struct ordered_events *qe,
 		return 0;
 	}
 
-	ret = perf_evlist__parse_sample(evlist, event, &sample);
+	ret = evlist__parse_sample(evlist, event, &sample);
 	if (ret) {
 		pr_err("Can't parse sample, err = %d\n", ret);
 		goto next_event;
 	}
 
-	evsel = perf_evlist__id2evsel(session->evlist, sample.id);
+	evsel = evlist__id2evsel(session->evlist, sample.id);
 	assert(evsel != NULL);
 
 	if (event->header.type == PERF_RECORD_SAMPLE) {
@@ -1469,8 +1466,7 @@ int cmd_top(int argc, const char **argv)
 	OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols,
 		    "hide kernel symbols"),
 	OPT_CALLBACK('m', "mmap-pages", &opts->mmap_pages, "pages",
-		     "number of mmap data pages",
-		     perf_evlist__parse_mmap_pages),
+		     "number of mmap data pages", evlist__parse_mmap_pages),
 	OPT_INTEGER('r', "realtime", &top.realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
 	OPT_INTEGER('d', "delay", &top.delay_secs,
@@ -1697,7 +1693,7 @@ int cmd_top(int argc, const char **argv)
 	if (target__none(target))
 		target->system_wide = true;
 
-	if (perf_evlist__create_maps(top.evlist, target) < 0) {
+	if (evlist__create_maps(top.evlist, target) < 0) {
 		ui__error("Couldn't create thread/CPU maps: %s\n",
 			  errno == ENOENT ? "No such process" : str_error_r(errno, errbuf, sizeof(errbuf)));
 		goto out_delete_evlist;
@@ -1762,7 +1758,7 @@ int cmd_top(int argc, const char **argv)
 	}
 #endif
 
-	if (perf_evlist__start_sb_thread(top.sb_evlist, target)) {
+	if (evlist__start_sb_thread(top.sb_evlist, target)) {
 		pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
 		opts->no_bpf_event = true;
 	}
@@ -1770,7 +1766,7 @@ int cmd_top(int argc, const char **argv)
 	status = __cmd_top(&top);
 
 	if (!opts->no_bpf_event)
-		perf_evlist__stop_sb_thread(top.sb_evlist);
+		evlist__stop_sb_thread(top.sb_evlist);
 
 out_delete_evlist:
 	evlist__delete(top.evlist);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index de80534473af..85b6a46e85b6 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3105,7 +3105,7 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st
 		return;
 	}
 
-	evsel = perf_evlist__id2evsel(trace->evlist, sample->id);
+	evsel = evlist__id2evsel(trace->evlist, sample->id);
 	if (evsel == NULL) {
 		fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample->id);
 		return;
@@ -3666,7 +3666,7 @@ static int trace__set_filter_loop_pids(struct trace *trace)
 		thread = parent;
 	}
 
-	err = perf_evlist__append_tp_filter_pids(trace->evlist, nr, pids);
+	err = evlist__append_tp_filter_pids(trace->evlist, nr, pids);
 	if (!err && trace->filter_pids.map)
 		err = bpf_map__set_filter_pids(trace->filter_pids.map, nr, pids);
 
@@ -3680,11 +3680,11 @@ static int trace__set_filter_pids(struct trace *trace)
 	 * Better not use !target__has_task() here because we need to cover the
 	 * case where no threads were specified in the command line, but a
 	 * workload was, and in that case we will fill in the thread_map when
-	 * we fork the workload in perf_evlist__prepare_workload.
+	 * we fork the workload in evlist__prepare_workload.
 	 */
 	if (trace->filter_pids.nr > 0) {
-		err = perf_evlist__append_tp_filter_pids(trace->evlist, trace->filter_pids.nr,
-							 trace->filter_pids.entries);
+		err = evlist__append_tp_filter_pids(trace->evlist, trace->filter_pids.nr,
+						    trace->filter_pids.entries);
 		if (!err && trace->filter_pids.map) {
 			err = bpf_map__set_filter_pids(trace->filter_pids.map, trace->filter_pids.nr,
 						       trace->filter_pids.entries);
@@ -3700,9 +3700,8 @@ static int __trace__deliver_event(struct trace *trace, union perf_event *event)
 {
 	struct evlist *evlist = trace->evlist;
 	struct perf_sample sample;
-	int err;
+	int err = evlist__parse_sample(evlist, event, &sample);
 
-	err = perf_evlist__parse_sample(evlist, event, &sample);
 	if (err)
 		fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
 	else
@@ -3735,7 +3734,7 @@ static int trace__deliver_event(struct trace *trace, union perf_event *event)
 	if (!trace->sort_events)
 		return __trace__deliver_event(trace, event);
 
-	err = perf_evlist__parse_sample_timestamp(trace->evlist, event, &trace->oe.last);
+	err = evlist__parse_sample_timestamp(trace->evlist, event, &trace->oe.last);
 	if (err && err != -1)
 		return err;
 
@@ -3951,7 +3950,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (trace->cgroup)
 		evlist__set_default_cgroup(trace->evlist, trace->cgroup);
 
-	err = perf_evlist__create_maps(evlist, &trace->opts.target);
+	err = evlist__create_maps(evlist, &trace->opts.target);
 	if (err < 0) {
 		fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
 		goto out_delete_evlist;
@@ -3963,14 +3962,13 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
-	perf_evlist__config(evlist, &trace->opts, &callchain_param);
+	evlist__config(evlist, &trace->opts, &callchain_param);
 
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
 
 	if (forks) {
-		err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
-						    argv, false, NULL);
+		err = evlist__prepare_workload(evlist, &trace->opts.target, argv, false, NULL);
 		if (err < 0) {
 			fprintf(trace->output, "Couldn't run the workload!\n");
 			goto out_delete_evlist;
@@ -4028,7 +4026,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	err = trace__expand_filters(trace, &evsel);
 	if (err)
 		goto out_delete_evlist;
-	err = perf_evlist__apply_filters(evlist, &evsel);
+	err = evlist__apply_filters(evlist, &evsel);
 	if (err < 0)
 		goto out_error_apply_filters;
 
@@ -4043,7 +4041,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		evlist__enable(evlist);
 
 	if (forks)
-		perf_evlist__start_workload(evlist);
+		evlist__start_workload(evlist);
 
 	if (trace->opts.initial_delay) {
 		usleep(trace->opts.initial_delay * 1000);
@@ -4229,12 +4227,10 @@ static int trace__replay(struct trace *trace)
 	if (err)
 		goto out;
 
-	evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
-						     "raw_syscalls:sys_enter");
+	evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_enter");
 	/* older kernels have syscalls tp versus raw_syscalls */
 	if (evsel == NULL)
-		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
-							     "syscalls:sys_enter");
+		evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_enter");
 
 	if (evsel &&
 	    (evsel__init_raw_syscall_tp(evsel, trace__sys_enter) < 0 ||
@@ -4243,11 +4239,9 @@ static int trace__replay(struct trace *trace)
 		goto out;
 	}
 
-	evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
-						     "raw_syscalls:sys_exit");
+	evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_exit");
 	if (evsel == NULL)
-		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
-							     "syscalls:sys_exit");
+		evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_exit");
 	if (evsel &&
 	    (evsel__init_raw_syscall_tp(evsel, trace__sys_exit) < 0 ||
 	    perf_evsel__init_sc_tp_uint_field(evsel, ret))) {
@@ -4769,8 +4763,7 @@ int cmd_trace(int argc, const char **argv)
 	OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
 		    "child tasks do not inherit counters"),
 	OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages",
-		     "number of mmap data pages",
-		     perf_evlist__parse_mmap_pages),
+		     "number of mmap data pages", evlist__parse_mmap_pages),
 	OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user",
 		   "user to profile"),
 	OPT_CALLBACK(0, "duration", &trace, "float",
@@ -4907,7 +4900,7 @@ int cmd_trace(int argc, const char **argv)
 	if (evsel) {
 		trace.syscalls.events.augmented = evsel;
 
-		evsel = perf_evlist__find_tracepoint_by_name(trace.evlist, "raw_syscalls:sys_enter");
+		evsel = evlist__find_tracepoint_by_name(trace.evlist, "raw_syscalls:sys_enter");
 		if (evsel == NULL) {
 			pr_err("ERROR: raw_syscalls:sys_enter not found in the augmented BPF object\n");
 			goto out;
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index d09ec2f03071..9cd074a3d825 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -80,6 +80,7 @@ static void library_status(void)
 	STATUS(HAVE_LIBBPF_SUPPORT, bpf);
 	STATUS(HAVE_AIO_SUPPORT, aio);
 	STATUS(HAVE_ZSTD_SUPPORT, zstd);
+	STATUS(HAVE_LIBPFM, libpfm4);
 }
 
 int cmd_version(int argc, const char **argv)
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 15ecb1803fb9..dded93a2bc89 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -144,6 +144,8 @@ check arch/x86/lib/insn.c             '-I "^#include [\"<]\(../include/\)*asm/in
 
 # diff non-symmetric files
 check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
+check_2 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl
+check_2 tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl
 
 for i in $BEAUTY_FILES; do
   beauty_check $i -B
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
index 65c4ff6892d9..e6b6181c6dc6 100644
--- a/tools/perf/examples/bpf/5sec.c
+++ b/tools/perf/examples/bpf/5sec.c
@@ -39,7 +39,7 @@
    Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
 */
 
-#include <bpf/bpf.h>
+#include <bpf.h>
 
 #define NSEC_PER_SEC	1000000000L
 
diff --git a/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/ddrc.json b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/ddrc.json
new file mode 100644
index 000000000000..3b1cd708f568
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/ddrc.json
@@ -0,0 +1,39 @@
+[
+   {
+           "BriefDescription": "ddr cycles event",
+           "EventCode": "0x00",
+           "EventName": "imx8mm_ddr.cycles",
+           "Unit": "imx8_ddr",
+           "Compat": "i.MX8MM"
+   },
+   {
+           "BriefDescription": "ddr read-cycles event",
+           "EventCode": "0x2a",
+           "EventName": "imx8mm_ddr.read_cycles",
+           "Unit": "imx8_ddr",
+           "Compat": "i.MX8MM"
+   },
+   {
+           "BriefDescription": "ddr write-cycles event",
+           "EventCode": "0x2b",
+           "EventName": "imx8mm_ddr.write_cycles",
+           "Unit": "imx8_ddr",
+           "Compat": "i.MX8MM"
+   },
+   {
+           "BriefDescription": "ddr read event",
+           "EventCode": "0x35",
+           "EventName": "imx8mm_ddr.read",
+           "Unit": "imx8_ddr",
+           "Compat": "i.MX8MM"
+   },
+   {
+           "BriefDescription": "ddr write event",
+           "EventCode": "0x38",
+           "EventName": "imx8mm_ddr.write",
+           "Unit": "imx8_ddr",
+           "Compat": "i.MX8MM"
+   }
+]
+
+
diff --git a/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/metrics.json b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/metrics.json
new file mode 100644
index 000000000000..8e553b67cae6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/metrics.json
@@ -0,0 +1,18 @@
+[
+   {
+	    "BriefDescription": "bytes all masters read from ddr based on read-cycles event",
+	    "MetricName": "imx8mm_ddr_read.all",
+	    "MetricExpr": "imx8mm_ddr.read_cycles * 4 * 4",
+	    "ScaleUnit": "9.765625e-4KB",
+	    "Unit": "imx8_ddr",
+	    "Compat": "i.MX8MM"
+    },
+   {
+	    "BriefDescription": "bytes all masters write to ddr based on write-cycles event",
+	    "MetricName": "imx8mm_ddr_write.all",
+	    "MetricExpr": "imx8mm_ddr.write_cycles * 4 * 4",
+	    "ScaleUnit": "9.765625e-4KB",
+	    "Unit": "imx8_ddr",
+	    "Compat": "i.MX8MM"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/test/arch-std-events.json b/tools/perf/pmu-events/arch/test/arch-std-events.json
new file mode 100644
index 000000000000..43f6f729d6ae
--- /dev/null
+++ b/tools/perf/pmu-events/arch/test/arch-std-events.json
@@ -0,0 +1,8 @@
+[
+    {
+        "PublicDescription": "Attributable Level 3 cache access, read",
+        "EventCode": "0x40",
+        "EventName": "L3_CACHE_RD",
+        "BriefDescription": "L3 cache access, read"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/test/test_cpu/cache.json b/tools/perf/pmu-events/arch/test/test_cpu/cache.json
new file mode 100644
index 000000000000..036d0efdb2bb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/test/test_cpu/cache.json
@@ -0,0 +1,5 @@
+[
+    {
+	 "ArchStdEvent": "L3_CACHE_RD"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylake/cache.json b/tools/perf/pmu-events/arch/x86/skylake/cache.json
index 720458139049..27ea2b00ad00 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/cache.json
@@ -1,2928 +1,2926 @@
 [
     {
-        "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.",
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x21",
-        "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read miss L2, no rejects",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
-        "EventCode": "0x24",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x22",
-        "EventName": "L2_RQSTS.RFO_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that miss L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400400002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
-        "EventCode": "0x24",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache misses when fetching instructions",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400108000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Demand requests that miss L2 cache.",
-        "EventCode": "0x24",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x27",
-        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand requests that miss L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100040002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.",
-        "EventCode": "0x24",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x38",
-        "EventName": "L2_RQSTS.PF_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0080001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "All requests that miss L2 cache.",
-        "EventCode": "0x24",
+        "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM",
         "Counter": "0,1,2,3",
-        "UMask": "0x3f",
-        "EventName": "L2_RQSTS.MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "All requests that miss L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB0",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
-        "EventCode": "0x24",
+        "BriefDescription": "Counts all demand code readshave any response type.",
         "Counter": "0,1,2,3",
-        "UMask": "0xc1",
-        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests that hit L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0000010004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code readshave any response type.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
-        "EventCode": "0x24",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0xc2",
-        "EventName": "L2_RQSTS.RFO_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that hit L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100020002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
-        "EventCode": "0x24",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0xc4",
-        "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xd8",
-        "EventName": "L2_RQSTS.PF_HIT",
+        "EventName": "L2_RQSTS.PF_MISS",
+        "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x38"
     },
     {
-        "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.",
-        "EventCode": "0x24",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0xe1",
-        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC01C0004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
-        "EventCode": "0x24",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0xe2",
-        "EventName": "L2_RQSTS.ALL_RFO",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests to L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100040001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the total number of L2 code requests.",
-        "EventCode": "0x24",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0xe4",
-        "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 code requests",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040100001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Demand requests to L2 cache.",
-        "EventCode": "0x24",
+        "BriefDescription": "Demand requests that miss L2 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0xe7",
-        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand requests to L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xf8",
-        "EventName": "L2_RQSTS.ALL_PF",
+        "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
+        "PublicDescription": "Demand requests that miss L2 cache.",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x27"
     },
     {
-        "PublicDescription": "All L2 requests.",
-        "EventCode": "0x24",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0xff",
-        "EventName": "L2_RQSTS.REFERENCES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "All L2 requests",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400100002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.",
-        "EventCode": "0x2E",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "Errata": "SKL057",
-        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080028000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Core-originated cacheable demand requests missed L3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts core-originated cacheable requests to the  L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2.  It does not include all accesses to the L3.",
-        "EventCode": "0x2E",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x4f",
-        "Errata": "SKL057",
-        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040080004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Core-originated cacheable demand requests that refer to L3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
-        "EventCode": "0x48",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "L1D_PEND_MISS.PENDING",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "L1D miss outstandings duration in cycles",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0408000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
-        "EventCode": "0x48",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with L1D load Misses outstanding.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400400004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0x48",
+        "BriefDescription": "Retired load instructions with L3 cache hits as data sources",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD1",
+        "EventName": "MEM_LOAD_RETIRED.L3_HIT",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "SampleAfterValue": "50021",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.",
-        "EventCode": "0x48",
+        "BriefDescription": "L2 writebacks that access L2 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "L1D_PEND_MISS.FB_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xF0",
+        "EventName": "L2_TRANS.L2_WB",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x40"
     },
     {
-        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
-        "EventCode": "0x51",
+        "BriefDescription": "L2 cache lines filling L2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "L1D.REPLACEMENT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "L1D data line replacements",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xF1",
+        "EventName": "L2_LINES_IN.ALL",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1f"
     },
     {
-        "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.",
-        "EventCode": "0x60",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400408000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
-        "EventCode": "0x60",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00401C0002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0x60",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400040004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
+        "BriefDescription": "Demand Data Read requests sent to uncore",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB0",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0400004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000400001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080080002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080100001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
-        "EventCode": "0x60",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100400004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
-        "EventCode": "0xB0",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001C0004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Demand Data Read requests sent to uncore",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts both cacheable and non-cacheable code read requests.",
-        "EventCode": "0xB0",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00801C0002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Cacheable and noncachaeble code read requests",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
-        "EventCode": "0xB0",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080100004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
-        "EventCode": "0xB0",
+        "BriefDescription": "Retired load instructions missed L3 cache as data sources",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand and prefetch data reads",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD1",
+        "EventName": "MEM_LOAD_RETIRED.L3_MISS",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "SampleAfterValue": "100007",
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..",
-        "EventCode": "0xB0",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040020001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Any memory transaction that reached the SQ.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.",
-        "EventCode": "0xB2",
+        "BriefDescription": "All retired store instructions.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD0",
+        "EventName": "MEM_INST_RETIRED.ALL_STORES",
+        "L1_Hit_Indication": "1",
+        "PEBS": "1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x82"
     },
     {
-        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "EventCode": "0xB7, 0xBB",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080020004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions that miss the STLB.",
-        "EventCode": "0xD0",
+        "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
         "Counter": "0,1,2,3",
-        "UMask": "0x11",
-        "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load instructions that miss the STLB. (Precise Event)",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xF2",
+        "EventName": "L2_LINES_OUT.SILENT",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Retired store instructions that miss the STLB.",
-        "EventCode": "0xD0",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x12",
-        "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store instructions that miss the STLB. (Precise Event)",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1",
-        "L1_Hit_Indication": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040048000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD0",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x21",
-        "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load instructions with locked access. (Precise Event)",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000088000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD0",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load instructions that split across a cacheline boundary. (Precise Event)",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040400004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD0",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
-        "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store instructions that split across a cacheline boundary. (Precise Event)",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1",
-        "L1_Hit_Indication": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x02001C0002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD0",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired load instructions. (Precise Event)",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080020001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "All retired store instructions.",
-        "EventCode": "0xD0",
+        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
         "Counter": "0,1,2,3",
-        "UMask": "0x82",
-        "EventName": "MEM_INST_RETIRED.ALL_STORES",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired store instructions. (Precise Event)",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1",
-        "L1_Hit_Indication": "1"
+        "UMask": "0x8"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
-        "EventCode": "0xD1",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Retired load instructions with L1 cache hits as data sources",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x02001C0004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions with L2 cache hits as data sources.",
-        "EventCode": "0xD1",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load instructions with L2 cache hits as data sources",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400040002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions with L3 cache hits as data sources.",
-        "EventCode": "0xD1",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "SampleAfterValue": "50021",
-        "BriefDescription": "Retired load instructions with L3 cache hits as data sources",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000028000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
-        "EventCode": "0xD1",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load instructions missed L1 cache as data sources",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200028000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions missed L2 cache as data sources.",
-        "EventCode": "0xD1",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "SampleAfterValue": "50021",
-        "BriefDescription": "Retired load instructions missed L2 cache as data sources",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x04001C0001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions missed L3 cache as data sources.",
-        "EventCode": "0xD1",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load instructions missed L3 cache as data sources",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100400001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
-        "EventCode": "0xD1",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x04001C8000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD2",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000080001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
-        "EventCode": "0xD2",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200020001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.",
-        "EventCode": "0xD2",
+        "BriefDescription": "Core-originated cacheable demand requests missed L3",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3",
-        "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "Errata": "SKL057",
+        "EventCode": "0x2E",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x41"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.",
-        "EventCode": "0xD2",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.ALL_PF",
+        "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.",
+        "SampleAfterValue": "200003",
+        "UMask": "0xf8"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0080004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD4",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.",
         "CounterHTOff": "0,1,2,3",
-        "Data_LA": "1"
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100400002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
-        "EventCode": "0xF0",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "L2_TRANS.L2_WB",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 writebacks that access L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040040002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
-        "EventCode": "0xF1",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1f",
-        "EventName": "L2_LINES_IN.ALL",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000400002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "SampleAfterValue": "100003",
-        "BriefDescription": "L2 cache lines filling L2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xF2",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "L2_LINES_OUT.SILENT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100028000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xF2",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "L2_LINES_OUT.NON_SILENT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
+        "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
-        "EventCode": "0xF2",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "L2_LINES_OUT.USELESS_PREF",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200080004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xF2",
+        "BriefDescription": "RFO requests that miss L2 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "L2_LINES_OUT.USELESS_HWPF",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.RFO_MISS",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x22"
     },
     {
-        "PublicDescription": "Counts the number of cache line split locks sent to the uncore.",
-        "EventCode": "0xF4",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "SQ_MISC.SPLIT_LOCK",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400040001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of cache line split locks sent to uncore.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0408000",
+        "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xF2",
+        "EventName": "L2_LINES_OUT.NON_SILENT",
+        "SampleAfterValue": "200003",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000408000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
         "BriefDescription": "Counts any other requests",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040028000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400408000",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200040002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200408000",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
         "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200408000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100408000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080408000",
+        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xF2",
+        "EventName": "L2_LINES_OUT.USELESS_HWPF",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040408000",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200040001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC01C8000",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200100001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001C8000",
+        "BriefDescription": "Counts all demand data writes (RFOs)have any response type.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0000010002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)have any response type.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001C8000",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x04001C0002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001C8000",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00401C0004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001C8000",
+        "BriefDescription": "All requests that miss L2 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.MISS",
+        "PublicDescription": "All requests that miss L2 cache.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x3f"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801C8000",
+        "BriefDescription": "L2 code requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.ALL_CODE_RD",
+        "PublicDescription": "Counts the total number of L2 code requests.",
+        "SampleAfterValue": "200003",
+        "UMask": "0xe4"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00401C8000",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0100002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0108000",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400100004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000108000",
+        "BriefDescription": "RFO requests that hit L2 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.RFO_HIT",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+        "SampleAfterValue": "200003",
+        "UMask": "0xc2"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400108000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
         "BriefDescription": "Counts any other requests",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080048000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200108000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100108000",
+        "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD2",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "SampleAfterValue": "20011",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080108000",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001C0001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040108000",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000080002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0088000",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000040002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000088000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
         "BriefDescription": "Counts any other requests",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0028000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400088000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200088000",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400080001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100088000",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000080004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080088000",
+        "BriefDescription": "Retired load instructions missed L1 cache as data sources",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD1",
+        "EventName": "MEM_LOAD_RETIRED.L1_MISS",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x8"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040088000",
+        "BriefDescription": "L2 cache misses when fetching instructions",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.CODE_RD_MISS",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x24"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0048000",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x01001C0001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000048000",
+        "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
+        "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400048000",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040080002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200048000",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC01C0001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100048000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
         "BriefDescription": "Counts any other requests",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400028000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080048000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040048000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
         "BriefDescription": "Counts any other requests",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400088000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0028000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000028000",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400028000",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200028000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
         "BriefDescription": "Counts any other requests",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x02001C8000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100028000",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100020001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080028000",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100080002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040028000",
+        "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts any other requests have any response type.",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000018000",
+        "BriefDescription": "Demand requests to L2 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests have any response type.",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
+        "PublicDescription": "Demand requests to L2 cache.",
+        "SampleAfterValue": "200003",
+        "UMask": "0xe7"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0400004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100048000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000400004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100108000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400400004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000020001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200400004",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040020002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100400004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000108000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080400004",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040100002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040400004",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0040002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC01C0004",
+        "AnyThread": "1",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x48",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001C0004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC01C8000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001C0004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x02001C0001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001C0004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200088000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001C0004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000100001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801C0004",
+        "BriefDescription": "Core-originated cacheable demand requests that refer to L3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "Errata": "SKL057",
+        "EventCode": "0x2E",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "PublicDescription": "Counts core-originated cacheable requests to the  L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2.  It does not include all accesses to the L3.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x4f"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00401C0004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200048000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0100004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000100004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0020004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400100004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080108000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200100004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040080001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100100004",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100100002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080100004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0040004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040100004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040040001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0080004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100020004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000080004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200020004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400080004",
+        "BriefDescription": "Retired load instructions that miss the STLB.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD0",
+        "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
+        "PEBS": "1",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x11"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200080004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200108000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100080004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080080004",
+        "BriefDescription": "Counts demand data readshave any response type.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0000010001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data readshave any response type.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040080004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000400004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0040004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080080004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000040004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001C8000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400040004",
+        "BriefDescription": "L1D data line replacements",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x51",
+        "EventName": "L1D.REPLACEMENT",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200040004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200040004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100040004",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080040004",
+        "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD4",
+        "EventName": "MEM_LOAD_MISC_RETIRED.UC",
+        "PEBS": "1",
+        "SampleAfterValue": "100007",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040040004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000040004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0020004",
+        "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD1",
+        "EventName": "MEM_LOAD_RETIRED.FB_HIT",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "SampleAfterValue": "100007",
+        "UMask": "0x40"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0020001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020004",
+        "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xF2",
+        "EventName": "L2_LINES_OUT.USELESS_PREF",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020004",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000020002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020004",
+        "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.PF_HIT",
+        "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.",
+        "SampleAfterValue": "200003",
+        "UMask": "0xd8"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020004",
+        "BriefDescription": "Demand Data Read miss L2, no rejects",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
+        "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x21"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040020004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040020004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400100001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0400002",
+        "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD2",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x8"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000400002",
+        "BriefDescription": "All retired load instructions.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD0",
+        "EventName": "MEM_INST_RETIRED.ALL_LOADS",
+        "PEBS": "1",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x81"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400400002",
+        "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD2",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
+        "PEBS": "1",
+        "SampleAfterValue": "20011",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200400002",
+        "BriefDescription": "Demand Data Read requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
+        "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.",
+        "SampleAfterValue": "200003",
+        "UMask": "0xe1"
+    },
+    {
         "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080020002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100400002",
+        "BriefDescription": "All L2 requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.REFERENCES",
+        "PublicDescription": "All L2 requests.",
+        "SampleAfterValue": "200003",
+        "UMask": "0xff"
+    },
+    {
         "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000100002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080400002",
+        "BriefDescription": "Cycles with L1D load Misses outstanding.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x48",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040400002",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100088000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC01C0002",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200400004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001C0002",
+        "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001C0002",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0048000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001C0002",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00401C8000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001C0002",
+        "BriefDescription": "Number of cache line split locks sent to uncore.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xF4",
+        "EventName": "SQ_MISC.SPLIT_LOCK",
+        "PublicDescription": "Counts the number of cache line split locks sent to the uncore.",
         "SampleAfterValue": "100003",
+        "UMask": "0x10"
+    },
+    {
         "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC01C0002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801C0002",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040408000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00401C0002",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001C0002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400080002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0100002",
+        "BriefDescription": "Retired load instructions with L2 cache hits as data sources",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD1",
+        "EventName": "MEM_LOAD_RETIRED.L2_HIT",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions with L2 cache hits as data sources.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000100002",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0040001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400100002",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100100001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200100002",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200100002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100100002",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080100002",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080040004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040100002",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000020004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0080002",
+        "BriefDescription": "L1D miss outstandings duration in cycles",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x48",
+        "EventName": "L1D_PEND_MISS.PENDING",
+        "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000080002",
+        "BriefDescription": "Demand Data Read requests that hit L2 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
+        "SampleAfterValue": "200003",
+        "UMask": "0xc1"
+    },
+    {
         "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400080002",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x04001C0004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200080002",
+        "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD2",
+        "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.",
+        "SampleAfterValue": "20011",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100080002",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0100001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
         "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x01001C0002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080080002",
+        "BriefDescription": "Retired store instructions that split across a cacheline boundary.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD0",
+        "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
+        "L1_Hit_Indication": "1",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x42"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040080002",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080400004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0040002",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000100004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000040002",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00801C0004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
         "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0020002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400040002",
+        "BriefDescription": "Any memory transaction that reached the SQ.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB0",
+        "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
+        "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x80"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200040002",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100040002",
+        "BriefDescription": "Counts any other requestshave any response type.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0000018000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requestshave any response type.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080040002",
+        "BriefDescription": "Cacheable and noncachaeble code read requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB0",
+        "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
+        "PublicDescription": "Counts both cacheable and non-cacheable code read requests.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040040002",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040040004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0020002",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100408000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020002",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020002",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0088000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020002",
+        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.CODE_RD_HIT",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+        "SampleAfterValue": "200003",
+        "UMask": "0xc4"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020002",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080040001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020002",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100040004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040020002",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080088000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) have any response type.",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010002",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000040001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0400001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040088000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000400001",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200020002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400400001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100100004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200400001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040100004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100400001",
+        "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x48",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
+        "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080400001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400048000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040400001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0040108000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC01C0001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0108000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001C0001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000048000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001C0001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400080004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001C0001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100080004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001C0001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200100004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801C0001",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00801C0001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00401C0001",
+        "BriefDescription": "Retired load instructions with L1 cache hits as data sources",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD1",
+        "EventName": "MEM_LOAD_RETIRED.L1_HIT",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0100001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000408000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000100001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400020004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400100001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0100004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
         "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200100001",
+        "BriefDescription": "Retired load instructions with locked access.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD0",
+        "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
+        "PEBS": "1",
+        "SampleAfterValue": "100007",
+        "UMask": "0x21"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100100001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00801C8000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080100001",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080040002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040100001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x01001C0004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0080001",
+        "BriefDescription": "Demand and prefetch data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB0",
+        "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x8"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000080001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080408000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400080001",
+        "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE",
+        "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200080001",
+        "BriefDescription": "Retired load instructions that split across a cacheline boundary.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD0",
+        "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x41"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100080001",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0100080001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080080001",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040080001",
+        "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB2",
+        "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL",
+        "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0040001",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "6",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000040001",
+        "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400040001",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200080002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200040001",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
         "BriefDescription": "Counts demand data reads",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400020001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100040001",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080040001",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080100002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040040001",
+        "BriefDescription": "Retired store instructions that miss the STLB.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD0",
+        "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
+        "L1_Hit_Indication": "1",
+        "PEBS": "1",
         "SampleAfterValue": "100003",
+        "UMask": "0x12"
+    },
+    {
         "BriefDescription": "Counts demand data reads",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200080001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC0020001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x01001C8000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020001",
+        "BriefDescription": "RFO requests to L2 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.ALL_RFO",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "SampleAfterValue": "200003",
+        "UMask": "0xe2"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020001",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0200400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020001",
+        "BriefDescription": "Retired load instructions missed L2 cache as data sources",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xD1",
+        "EventName": "MEM_LOAD_RETIRED.L2_MISS",
+        "PEBS": "1",
+        "PublicDescription": "Retired load instructions missed L2 cache as data sources.",
+        "SampleAfterValue": "50021",
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020001",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0400020002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0080080001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020001",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x8"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0040020001",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC0080002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads have any response type.",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010001",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads have any response type.",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00401C0001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json
index 213dd6230cf2..834e1cd841fc 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json
@@ -1,67 +1,67 @@
 [
     {
-        "EventCode": "0xC7",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC7",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired.  Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4"
     },
     {
-        "EventCode": "0xC7",
+        "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired.  Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "EventCode": "0xC7",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC7",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x10"
     },
     {
-        "EventCode": "0xC7",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC7",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x20"
     },
     {
-        "EventCode": "0xC7",
+        "BriefDescription": "Cycles with any input/output SSE or FP assist",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0xCA",
+        "EventName": "FP_ASSIST.ANY",
+        "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1e"
     },
     {
-        "EventCode": "0xC7",
+        "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC7",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
-        "EventCode": "0xCA",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1e",
-        "EventName": "FP_ASSIST.ANY",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles with any input/output SSE or FP assist",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC7",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x8"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylake/frontend.json b/tools/perf/pmu-events/arch/x86/skylake/frontend.json
index 7fa95a35e3ca..e84504d6adea 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/frontend.json
@@ -1,482 +1,516 @@
 [
     {
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
-        "EventCode": "0x79",
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "IDQ.MITE_UOPS",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x80",
+        "EventName": "ICACHE_16B.IFDATA_STALL",
+        "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.",
-        "EventCode": "0x79",
+        "BriefDescription": "Retired Instructions who experienced iTLB true miss.",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "IDQ.MITE_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.ITLB_MISS",
+        "MSRIndex": "0x3F7",
+        "MSRValue": "0x14",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "SampleAfterValue": "100007",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
-        "EventCode": "0x79",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
+        "MSRIndex": "0x3F7",
+        "MSRValue": "0x408006",
+        "PEBS": "1",
+        "SampleAfterValue": "100007",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
-        "EventCode": "0x79",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x8"
     },
     {
-        "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
-        "EventCode": "0x79",
+        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "IDQ.MS_DSB_CYCLES",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "3",
+        "EventCode": "0x9C",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
-        "EventCode": "0x79",
+        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
         "Counter": "0,1,2,3",
-        "UMask": "0x18",
-        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xE6",
+        "EventName": "BACLEARS.ANY",
+        "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
-        "EventCode": "0x79",
+        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.",
         "Counter": "0,1,2,3",
-        "UMask": "0x18",
-        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.DSB_MISS",
+        "MSRIndex": "0x3F7",
+        "MSRValue": "0x11",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "SampleAfterValue": "100007",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
-        "EventCode": "0x79",
+        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "IDQ.MS_MITE_UOPS",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "4",
+        "EventCode": "0x9C",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
-        "EventCode": "0x79",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles MITE is delivering 4 Uops",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
+        "MSRIndex": "0x3F7",
+        "MSRValue": "0x401006",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "SampleAfterValue": "100007",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
-        "EventCode": "0x79",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x79",
+        "EventName": "IDQ.MITE_UOPS",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles MITE is delivering any Uop",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
-        "EventCode": "0x79",
+        "BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_CYCLES",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "2",
+        "EventCode": "0x9C",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
+        "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
-        "EventCode": "0x79",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EdgeDetect": "1",
-        "EventName": "IDQ.MS_SWITCHES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
         "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_UOPS",
+        "EventName": "IDQ.MS_CYCLES",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x30"
     },
     {
-        "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.",
-        "EventCode": "0x80",
+        "BriefDescription": "Cycles MITE is delivering any Uop",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "ICACHE_16B.IFDATA_STALL",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x79",
+        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x24"
     },
     {
-        "EventCode": "0x83",
+        "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x83",
         "EventName": "ICACHE_64B.IFTAG_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0x83",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "ICACHE_64B.IFTAG_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0x79",
+        "EventName": "IDQ.MS_SWITCHES",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x30"
     },
     {
-        "EventCode": "0x83",
+        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "ICACHE_64B.IFTAG_STALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.L2_MISS",
+        "MSRIndex": "0x3F7",
+        "MSRValue": "0x13",
+        "PEBS": "1",
+        "SampleAfterValue": "100007",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
-        "EventCode": "0x9C",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x79",
+        "EventName": "IDQ.MITE_CYCLES",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
-        "EventCode": "0x9C",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
+        "MSRIndex": "0x3F7",
+        "MSRValue": "0x404006",
+        "PEBS": "1",
+        "SampleAfterValue": "100007",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
-        "EventCode": "0x9C",
+        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x9C",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
-        "EventCode": "0x9C",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x79",
+        "EventName": "IDQ.MS_MITE_UOPS",
+        "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
-        "EventCode": "0x9C",
+        "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x83",
+        "EventName": "ICACHE_64B.IFTAG_STALL",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4"
     },
     {
-        "EventCode": "0x9C",
-        "Invert": "1",
+        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xAB",
+        "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
+        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
-        "EventCode": "0xAB",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x79",
+        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x18"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
-        "EventCode": "0xC6",
-        "MSRValue": "0x11",
+        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.DSB_MISS",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x15",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC6",
-        "MSRValue": "0x12",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.L1I_MISS",
-        "MSRIndex": "0x3F7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x79",
+        "EventName": "IDQ.DSB_UOPS",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x8"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC6",
-        "MSRValue": "0x13",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.L2_MISS",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x420006",
+        "PEBS": "1",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
-        "EventCode": "0xC6",
-        "MSRValue": "0x14",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.ITLB_MISS",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x400806",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
-        "EventCode": "0xC6",
-        "MSRValue": "0x15",
+        "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.STLB_MISS",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xc6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x400106",
+        "PEBS": "2",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC6",
-        "MSRValue": "0x400206",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x400206",
+        "PEBS": "1",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC6",
-        "MSRValue": "0x200206",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x400406",
+        "PEBS": "1",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC6",
-        "MSRValue": "0x400406",
+        "BriefDescription": "Cycles MITE is delivering 4 Uops",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
-        "MSRIndex": "0x3F7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "4",
+        "EventCode": "0x79",
+        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x24"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
-        "EventCode": "0xC6",
-        "MSRValue": "0x400806",
+        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
-        "MSRIndex": "0x3F7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x79",
+        "EventName": "IDQ.MS_DSB_CYCLES",
+        "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
-        "EventCode": "0xC6",
-        "MSRValue": "0x401006",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
-        "MSRIndex": "0x3F7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x79",
+        "EventName": "IDQ.MS_UOPS",
+        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x30"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end  after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
-        "EventCode": "0xC6",
-        "MSRValue": "0x402006",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x410006",
+        "PEBS": "1",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC6",
-        "MSRValue": "0x404006",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x200206",
+        "PEBS": "1",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC6",
-        "MSRValue": "0x408006",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x300206",
+        "PEBS": "1",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC6",
-        "MSRValue": "0x410006",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x100206",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC6",
-        "MSRValue": "0x420006",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
-        "MSRIndex": "0x3F7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "4",
+        "EventCode": "0x79",
+        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x18"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
-        "EventCode": "0xC6",
-        "MSRValue": "0x100206",
+        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xAB",
+        "EventName": "DSB2MITE_SWITCHES.COUNT",
+        "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x402006",
+        "PEBS": "1",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC6",
-        "MSRValue": "0x300206",
+        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x9C",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
+        "Invert": "1",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x83",
+        "EventName": "ICACHE_64B.IFTAG_MISS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC6",
+        "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
+        "MSRValue": "0x12",
+        "PEBS": "1",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x9C",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
+        "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylake/memory.json b/tools/perf/pmu-events/arch/x86/skylake/memory.json
index f197b4c7695b..7bd3ae338343 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/memory.json
@@ -1,1604 +1,1611 @@
 [
     {
-        "PublicDescription": "Number of times a TSX line had a cache conflict.",
-        "EventCode": "0x54",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "TX_MEM.ABORT_CONFLICT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000080004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0x54",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "TX_MEM.ABORT_CAPACITY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0104000001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.",
-        "EventCode": "0x54",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000100002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.",
-        "EventCode": "0x54",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0084008000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.",
-        "EventCode": "0x54",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x007C400004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.",
-        "EventCode": "0x54",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x043C408000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times we could not allocate Lock Buffer.",
-        "EventCode": "0x54",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0204000004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0x5d",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "TX_EXEC.MISC1",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000088000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.",
-        "EventCode": "0x5d",
+        "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "TX_EXEC.MISC2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "6",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.",
-        "EventCode": "0x5d",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "TX_EXEC.MISC3",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00BC408000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "RTM region detected inside HLE.",
-        "EventCode": "0x5d",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "TX_EXEC.MISC4",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x103C408000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.",
-        "EventCode": "0x5d",
+        "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "TX_EXEC.MISC5",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC8",
+        "EventName": "HLE_RETIRED.ABORTED_TIMER",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x10"
     },
     {
-        "EventCode": "0x60",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x023C400001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0x60",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0204000002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0x60",
+        "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC9",
+        "EventName": "RTM_RETIRED.ABORTED_MEM",
+        "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x8"
     },
     {
-        "EventCode": "0xA3",
+        "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC9",
+        "EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
+        "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x40"
     },
     {
-        "EventCode": "0xA3",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x6",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000080002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Demand Data Read requests who miss L3 cache.",
-        "EventCode": "0xB0",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1004008000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Demand Data Read requests who miss L3 cache",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.",
-        "EventCode": "0xC3",
+        "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "Errata": "SKL089",
-        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts the number of machine clears due to memory order conflicts.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "2",
+        "EventCode": "0xA3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.",
-        "EventCode": "0xC8",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "HLE_RETIRED.START",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE execution started.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000028000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times HLE commit succeeded.",
-        "EventCode": "0xC8",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "HLE_RETIRED.COMMIT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE execution successfully committed",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FFC408000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Number of times HLE abort was triggered. (PEBS)",
-        "EventCode": "0xC8",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "HLE_RETIRED.ABORTED",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xcd",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x20",
+        "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "SampleAfterValue": "100007",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xC8",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "HLE_RETIRED.ABORTED_MEM",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x043C400002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xC8",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "HLE_RETIRED.ABORTED_TIMER",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000020004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
-        "EventCode": "0xC8",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0044000002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.",
-        "EventCode": "0xC8",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "HLE_RETIRED.ABORTED_MEMTYPE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0204008000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xC8",
+        "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "HLE_RETIRED.ABORTED_EVENTS",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x54",
+        "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.",
-        "EventCode": "0xC9",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "RTM_RETIRED.START",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an RTM execution started.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x103C400001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times RTM commit succeeded.",
-        "EventCode": "0xC9",
+        "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "RTM_RETIRED.COMMIT",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x54",
+        "EventName": "TX_MEM.ABORT_CONFLICT",
+        "PublicDescription": "Number of times a TSX line had a cache conflict.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an RTM execution successfully committed",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Number of times RTM abort was triggered. (PEBS)",
-        "EventCode": "0xC9",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "RTM_RETIRED.ABORTED",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1004000001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
-        "EventCode": "0xC9",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "RTM_RETIRED.ABORTED_MEM",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000080001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xC9",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "RTM_RETIRED.ABORTED_TIMER",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xcd",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x40",
+        "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "SampleAfterValue": "2003",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.",
-        "EventCode": "0xC9",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0204000001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.",
-        "EventCode": "0xC9",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000020002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
-        "EventCode": "0xC9",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "RTM_RETIRED.ABORTED_EVENTS",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x54",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x8"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
-        "EventCode": "0xCD",
-        "MSRValue": "0x4",
+        "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
-        "MSRIndex": "0x3F6",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x5d",
+        "EventName": "TX_EXEC.MISC5",
+        "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
-        "EventCode": "0xCD",
-        "MSRValue": "0x8",
+        "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
-        "MSRIndex": "0x3F6",
-        "SampleAfterValue": "50021",
-        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x5d",
+        "EventName": "TX_EXEC.MISC4",
+        "PublicDescription": "RTM region detected inside HLE.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x8"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
-        "EventCode": "0xCD",
-        "MSRValue": "0x10",
+        "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
-        "MSRIndex": "0x3F6",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x5d",
+        "EventName": "TX_EXEC.MISC3",
+        "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
-        "EventCode": "0xCD",
-        "MSRValue": "0x20",
+        "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
-        "MSRIndex": "0x3F6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x5d",
+        "EventName": "TX_EXEC.MISC2",
+        "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
-        "EventCode": "0xCD",
-        "MSRValue": "0x40",
+        "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
-        "MSRIndex": "0x3F6",
-        "SampleAfterValue": "2003",
-        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x5d",
+        "EventName": "TX_EXEC.MISC1",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
-        "EventCode": "0xCD",
-        "MSRValue": "0x80",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
-        "MSRIndex": "0x3F6",
-        "SampleAfterValue": "1009",
-        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0404000001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
-        "EventCode": "0xCD",
-        "MSRValue": "0x100",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
-        "MSRIndex": "0x3F6",
-        "SampleAfterValue": "503",
-        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0084000004",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
-        "EventCode": "0xCD",
-        "MSRValue": "0x200",
+        "BriefDescription": "Number of times an RTM execution successfully committed",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
-        "MSRIndex": "0x3F6",
-        "SampleAfterValue": "101",
-        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
-        "TakenAlone": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC9",
+        "EventName": "RTM_RETIRED.COMMIT",
+        "PublicDescription": "Number of times RTM commit succeeded.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FFC408000",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000100001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x203C408000",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x103C400004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103C408000",
+        "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043C408000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
         "BriefDescription": "Counts any other requests",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000048000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023C408000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013C408000",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0104000002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00BC408000",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x203C400004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x007C408000",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x007C408000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC4008000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004008000",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0104000004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004008000",
+        "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC9",
+        "EventName": "RTM_RETIRED.ABORTED_TIMER",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404008000",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2004000004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204008000",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1004000004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104008000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
         "BriefDescription": "Counts any other requests",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0044008000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084008000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0044008000",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0044000001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000408000",
+        "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC8",
+        "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20001C8000",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0084000002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000108000",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x043C400004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000088000",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00BC400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000048000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
         "BriefDescription": "Counts any other requests",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000408000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts any other requests",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000028000",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FFC400004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000040004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x203C400004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000400004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103C400004",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043C400004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x20001C0004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023C400004",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x103C400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013C400004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x013C400004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00BC400004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0404008000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x007C400004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0104008000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC4000004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x013C408000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000004",
+        "BriefDescription": "Number of times an HLE execution successfully committed",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC8",
+        "EventName": "HLE_RETIRED.COMMIT",
+        "PublicDescription": "Number of times HLE commit succeeded.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000020001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000004",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x203C408000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000004",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x023C400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000004",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000040002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0044000004",
+        "BriefDescription": "Demand Data Read requests who miss L3 cache",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB0",
+        "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "Demand Data Read requests who miss L3 cache.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000400004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00BC400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20001C0004",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2004000002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000100004",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x023C400004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000080004",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FFC400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000040004",
+        "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC9",
+        "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
+        "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020004",
+        "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC8",
+        "EventName": "HLE_RETIRED.ABORTED_MEM",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x8"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FFC400002",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xcd",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x100",
+        "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "SampleAfterValue": "503",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x203C400002",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x013C400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103C400002",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x203C400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043C400002",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
         "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x007C400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023C400002",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC4008000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013C400002",
+        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC9",
+        "EventName": "RTM_RETIRED.ABORTED",
+        "PEBS": "1",
+        "PublicDescription": "Number of times RTM abort was triggered.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00BC400002",
+        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC8",
+        "EventName": "HLE_RETIRED.ABORTED",
+        "PEBS": "1",
+        "PublicDescription": "Number of times HLE abort was triggered.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x203C400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x007C400002",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0404000004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC4000002",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xcd",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x10",
+        "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "SampleAfterValue": "20011",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000002",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2004008000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000002",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x54",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000002",
+        "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x60",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000002",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC4000004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000002",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xcd",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x200",
+        "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "SampleAfterValue": "101",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000002",
+        "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x54",
+        "EventName": "TX_MEM.ABORT_CAPACITY",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0044000002",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0084000001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000400002",
+        "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC8",
+        "EventName": "HLE_RETIRED.ABORTED_MEMTYPE",
+        "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x40"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20001C0002",
+        "BriefDescription": "Number of times an RTM execution started.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC9",
+        "EventName": "RTM_RETIRED.START",
+        "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000100002",
+        "BriefDescription": "Counts the number of machine clears due to memory order conflicts.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "Errata": "SKL089",
+        "EventCode": "0xC3",
+        "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+        "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000080002",
+        "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x54",
+        "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH",
+        "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000040002",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x20001C0002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1004000002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs)",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020002",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x20001C0001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FFC400001",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC4000002",
+        "Offcore": "1",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x007C400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x203C400001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000100004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103C400001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x00BC400004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043C400001",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x043C400001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
         "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023C400001",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013C400001",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FFC400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00BC400001",
+        "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC9",
+        "EventName": "RTM_RETIRED.ABORTED_EVENTS",
+        "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x80"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x007C400001",
+        "BriefDescription": "Number of times an HLE execution started.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC8",
+        "EventName": "HLE_RETIRED.START",
+        "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3FC4000001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FFC400004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000001",
+        "BriefDescription": "Counts demand data reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2004000001",
+        "Offcore": "1",
+        "PublicDescription": "Counts demand data reads",
         "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FC4000001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000001",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xcd",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x80",
+        "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "SampleAfterValue": "1009",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000001",
+        "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x54",
+        "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL",
+        "PublicDescription": "Number of times we could not allocate Lock Buffer.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x40"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000108000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000001",
+        "BriefDescription": "Counts all demand code reads",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0044000004",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand code reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000001",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x013C400002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0044000001",
+        "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "6",
+        "EventCode": "0xA3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x6"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000400001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x023C408000",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts any other requests",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20001C0001",
+        "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC8",
+        "EventName": "HLE_RETIRED.ABORTED_EVENTS",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x80"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000100001",
+        "BriefDescription": "Counts any other requests",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x20001C8000",
+        "Offcore": "1",
+        "PublicDescription": "Counts any other requests",
         "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000040001",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts demand data reads",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000080001",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xcd",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x4",
+        "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000040001",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
-        "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3",
+        "Data_LA": "1",
+        "EventCode": "0xcd",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x8",
+        "PEBS": "2",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "SampleAfterValue": "50021",
+        "TakenAlone": "1",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data reads",
-        "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020001",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6, 0x1a7",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x0404000002",
         "Offcore": "1",
-        "CounterHTOff": "0,1,2,3"
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylake/other.json b/tools/perf/pmu-events/arch/x86/skylake/other.json
index 84a316d380ac..1a3683f1de91 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/other.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/other.json
@@ -1,48 +1,56 @@
 [
     {
-        "EventCode": "0x32",
+        "BriefDescription": "Number of PREFETCHW instructions executed.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "SW_PREFETCH_ACCESS.NTA",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x32",
+        "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of PREFETCHNTA instructions executed.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x8"
     },
     {
-        "EventCode": "0x32",
+        "BriefDescription": "Number of PREFETCHT0 instructions executed.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x32",
         "EventName": "SW_PREFETCH_ACCESS.T0",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of PREFETCHT0 instructions executed.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "EventCode": "0x32",
+        "BriefDescription": "Number of hardware interrupts received by the processor.",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "SW_PREFETCH_ACCESS.T1_T2",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xCB",
+        "EventName": "HW_INTERRUPTS.RECEIVED",
+        "PublicDescription": "Counts the number of hardware interruptions received by the processor.",
+        "SampleAfterValue": "203",
+        "UMask": "0x1"
     },
     {
+        "BriefDescription": "Number of PREFETCHNTA instructions executed.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "EventCode": "0x32",
+        "EventName": "SW_PREFETCH_ACCESS.NTA",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x32",
+        "EventName": "SW_PREFETCH_ACCESS.T1_T2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of PREFETCHW instructions executed.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts the number of hardware interruptions received by the processor.",
-        "EventCode": "0xCB",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "HW_INTERRUPTS.RECEIVED",
-        "SampleAfterValue": "203",
-        "BriefDescription": "Number of hardware interrupts received by the processor.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x09",
+        "EventName": "MEMORY_DISAMBIGUATION.HISTORY_RESET",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
index 4a891fbbc4bb..f46e93a57fb4 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
@@ -1,967 +1,969 @@
 [
     {
-        "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
-        "Counter": "Fixed counter 0",
-        "UMask": "0x1",
-        "EventName": "INST_RETIRED.ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Instructions retired from execution.",
-        "CounterHTOff": "Fixed counter 0"
-    },
-    {
-        "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
-        "Counter": "Fixed counter 1",
-        "UMask": "0x2",
-        "EventName": "CPU_CLK_UNHALTED.THREAD",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when the thread is not in halt state",
-        "CounterHTOff": "Fixed counter 1"
+        "BriefDescription": "Number of instructions retired. General Counter - architectural event",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "Errata": "SKL091, SKL044",
+        "EventCode": "0xC0",
+        "EventName": "INST_RETIRED.ANY_P",
+        "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
+        "SampleAfterValue": "2000003"
     },
     {
-        "Counter": "Fixed counter 1",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "Invert": "1",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "CounterHTOff": "Fixed counter 1"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
-        "Counter": "Fixed counter 2",
-        "UMask": "0x3",
-        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA6",
+        "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "CounterHTOff": "Fixed counter 2"
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations,c. preceding lock RMW operations are not forwarded,d. store has the no-forward bit set (uncacheable/page-split/masked stores),e. all-blocking stores are used (mostly, fences and port I/O), and others.The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.",
-        "EventCode": "0x03",
+        "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded .",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x14",
+        "EventName": "ARITH.DIVIDER_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
-        "EventCode": "0x03",
+        "BriefDescription": "False dependencies in MOB due to partial compare on address.",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "LD_BLOCKS.NO_SR",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "EventCode": "0x07",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
         "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
+        "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "False dependencies in MOB due to partial compare on address.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
-        "EventCode": "0x0D",
+        "BriefDescription": "Far branch instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "INT_MISC.RECOVERY_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "Errata": "SKL091",
+        "EventCode": "0xC4",
+        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "PEBS": "1",
+        "PublicDescription": "This event counts far branch instructions retired.",
+        "SampleAfterValue": "100007",
+        "UMask": "0x40"
     },
     {
-        "EventCode": "0x0D",
+        "BriefDescription": "Counts the number of x87 uops dispatched.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.X87",
+        "PublicDescription": "Counts the number of x87 uops executed.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x10"
     },
     {
-        "EventCode": "0x0D",
+        "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x4C",
+        "EventName": "LOAD_HIT_PRE.SW_PF",
+        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
-        "EventCode": "0x0E",
+        "BriefDescription": "Mispredicted direct and indirect near call instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_ISSUED.ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC5",
+        "EventName": "BR_MISP_RETIRED.NEAR_CALL",
+        "PEBS": "1",
+        "PublicDescription": "Counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.",
+        "SampleAfterValue": "400009",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
-        "EventCode": "0x0E",
-        "Invert": "1",
+        "BriefDescription": "Total execution stalls.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "4",
+        "EventCode": "0xA3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.",
-        "EventCode": "0x0E",
+        "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "EventCode": "0x0E",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
         "EventName": "UOPS_ISSUED.SLOW_LEA",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x20"
     },
     {
-        "EventCode": "0x14",
+        "BriefDescription": "Cycles with less than 10 actually retired uops.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ARITH.DIVIDER_ACTIVE",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "10",
+        "EventCode": "0xC2",
+        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
+        "Invert": "1",
+        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
-        "EventCode": "0x3C",
+        "BriefDescription": "Thread cycles when thread is not in halt state",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x3C",
         "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Thread cycles when thread is not in halt state",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "SampleAfterValue": "2000003"
     },
     {
-        "EventCode": "0x3C",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "2",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).",
-        "EventCode": "0x3C",
+        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EdgeDetect": "1",
-        "EventName": "CPU_CLK_UNHALTED.RING0_TRANS",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
         "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
-        "SampleAfterValue": "2503",
-        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "SampleAfterValue": "25003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0x3C",
+        "BriefDescription": "Number of machine clears (nukes) of any type.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2503",
-        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xC3",
+        "EventName": "MACHINE_CLEARS.COUNT",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
-        "SampleAfterValue": "2503",
-        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "AnyThread": "1",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "Counter": "Fixed counter 1",
+        "CounterHTOff": "Fixed counter 1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "EventCode": "0x3C",
+        "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2503",
-        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Number of uops to be executed per-thread each cycle.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0x3C",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "3",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0x3C",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "SampleAfterValue": "2503",
-        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "Invert": "1",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
-        "EventCode": "0x4C",
+        "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LOAD_HIT_PRE.SW_PF",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA6",
+        "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x40"
     },
     {
-        "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.",
-        "EventCode": "0x59",
+        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "8",
+        "EventCode": "0xA3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x8"
     },
     {
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
-        "EventCode": "0x5E",
+        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "RS_EVENTS.EMPTY_CYCLES",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0xA8",
+        "EventName": "LSD.CYCLES_ACTIVE",
+        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.",
-        "EventCode": "0x5E",
-        "Invert": "1",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "RS_EVENTS.EMPTY_END",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x0D",
+        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
-        "EventCode": "0x87",
+        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ILD_STALL.LCP",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x3C",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "25003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.",
-        "EventCode": "0xA1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 0",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA1",
         "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 0",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.",
-        "EventCode": "0xA1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 1",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA1",
         "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.",
-        "EventCode": "0xA1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 2",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA1",
         "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.",
-        "EventCode": "0xA1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 3",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA1",
         "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x8"
     },
     {
-        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.",
-        "EventCode": "0xA1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 4",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA1",
         "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.",
-        "EventCode": "0xA1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 5",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA1",
         "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 5",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.",
-        "EventCode": "0xA1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 6",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA1",
         "EventName": "UOPS_DISPATCHED_PORT.PORT_6",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x40"
     },
     {
-        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.",
-        "EventCode": "0xA1",
+        "BriefDescription": "Cycles per thread when uops are executed in port 7",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA1",
         "EventName": "UOPS_DISPATCHED_PORT.PORT_7",
+        "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are executed in port 7",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x80"
     },
     {
-        "PublicDescription": "Counts resource-related stall cycles.",
-        "EventCode": "0xa2",
+        "AnyThread": "1",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "RESOURCE_STALLS.ANY",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x0D",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource-related stall cycles",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
-        "EventCode": "0xA2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "RESOURCE_STALLS.SB",
+        "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution",
+        "Counter": "1",
+        "CounterHTOff": "1",
+        "Errata": "SKL091, SKL044",
+        "EventCode": "0xC0",
+        "EventName": "INST_RETIRED.PREC_DIST",
+        "PEBS": "2",
+        "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xA3",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "4",
+        "EventCode": "0xA8",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xA3",
+        "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA6",
+        "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Total execution stalls.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x8"
     },
     {
-        "EventCode": "0xA3",
+        "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.",
         "Counter": "0,1,2,3",
-        "UMask": "0x5",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
-        "CounterMask": "5",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x03",
+        "EventName": "LD_BLOCKS.STORE_FORWARD",
+        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2"
     },
     {
-        "EventCode": "0xA3",
+        "AnyThread": "1",
+        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
-        "CounterMask": "8",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x3C",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "25003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xA3",
+        "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x59",
+        "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD",
+        "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
-        "CounterMask": "12",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xA3",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x0E",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "Invert": "1",
+        "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
-        "CounterMask": "16",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xA3",
+        "BriefDescription": "Not taken branch instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x14",
-        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
-        "CounterMask": "20",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "Errata": "SKL091",
+        "EventCode": "0xc4",
+        "EventName": "BR_INST_RETIRED.COND_NTAKEN",
+        "PublicDescription": "This event counts not taken branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.",
-        "EventCode": "0xA6",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "3",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
-        "EventCode": "0xA6",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
-        "EventCode": "0xA6",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "4",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
-        "EventCode": "0xA6",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
+        "BriefDescription": "Reference cycles when the core is not in halt state.",
+        "Counter": "Fixed counter 2",
+        "CounterHTOff": "Fixed counter 2",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x3"
     },
     {
-        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
-        "EventCode": "0xA6",
+        "BriefDescription": "All mispredicted macro branch instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC5",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "SampleAfterValue": "400009"
     },
     {
-        "EventCode": "0xA6",
+        "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC1",
+        "EventName": "OTHER_ASSISTS.ANY",
+        "SampleAfterValue": "100003",
+        "UMask": "0x3f"
+    },
+    {
+        "BriefDescription": "Cycles without actually retired uops.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0xC2",
+        "EventName": "UOPS_RETIRED.STALL_CYCLES",
+        "Invert": "1",
+        "PublicDescription": "This event counts cycles without actually retired uops.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
-        "EventCode": "0xA8",
+        "BriefDescription": "Number of Uops delivered by the LSD.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA8",
         "EventName": "LSD.UOPS",
+        "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of Uops delivered by the LSD.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
-        "EventCode": "0xA8",
+        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x3C",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "25003",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
-        "EventCode": "0xA8",
+        "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_4_UOPS",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x87",
+        "EventName": "ILD_STALL.LCP",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Number of uops to be executed per-thread each cycle.",
-        "EventCode": "0xB1",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.THREAD",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0x5E",
+        "EventName": "RS_EVENTS.EMPTY_END",
+        "Invert": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
-        "EventCode": "0xB1",
-        "Invert": "1",
+        "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "16",
+        "EventCode": "0xA3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
-        "EventCode": "0xB1",
+        "BriefDescription": "Taken branch instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "Errata": "SKL091",
+        "EventCode": "0xC4",
+        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "PEBS": "1",
+        "PublicDescription": "This event counts taken branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
-        "EventCode": "0xB1",
+        "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x03",
+        "EventName": "LD_BLOCKS.NO_SR",
+        "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x8"
     },
     {
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
-        "EventCode": "0xB1",
+        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x0E",
+        "EventName": "UOPS_ISSUED.ANY",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
-        "EventCode": "0xB1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "BriefDescription": "Core cycles when the thread is not in halt state",
+        "Counter": "Fixed counter 1",
+        "CounterHTOff": "Fixed counter 1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD",
+        "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Number of uops executed from any thread.",
-        "EventCode": "0xB1",
+        "AnyThread": "1",
+        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of uops executed on the core.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x3C",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "25003",
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xB1",
+        "BriefDescription": "Direct and indirect near call instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "Errata": "SKL091",
+        "EventCode": "0xC4",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL",
+        "PEBS": "1",
+        "PublicDescription": "This event counts both direct and indirect near call instructions retired.",
+        "SampleAfterValue": "100007",
+        "UMask": "0x2"
     },
     {
-        "EventCode": "0xB1",
+        "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xCC",
+        "EventName": "ROB_MISC_EVENTS.PAUSE_INST",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
-        "CounterMask": "2",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x40"
     },
     {
-        "EventCode": "0xB1",
+        "BriefDescription": "Resource-related stall cycles",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa2",
+        "EventName": "RESOURCE_STALLS.ANY",
+        "PublicDescription": "Counts resource-related stall cycles.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xB1",
+        "BriefDescription": "Self-modifying code (SMC) detected.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC3",
+        "EventName": "MACHINE_CLEARS.SMC",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4"
     },
     {
-        "EventCode": "0xB1",
-        "Invert": "1",
+        "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "5",
+        "EventCode": "0xA3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x5"
     },
     {
-        "PublicDescription": "Counts the number of x87 uops executed.",
-        "EventCode": "0xB1",
+        "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "UOPS_EXECUTED.X87",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x3C",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "SampleAfterValue": "25003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "4",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the number of x87 uops dispatched.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).",
-        "EventCode": "0xC0",
+        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "Errata": "SKL091, SKL044",
-        "EventName": "INST_RETIRED.ANY_P",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC5",
+        "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "PEBS": "1",
+        "SampleAfterValue": "400009",
+        "UMask": "0x20"
+    },
+    {
+        "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3",
+        "CounterMask": "20",
+        "EventCode": "0xA3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of instructions retired. General Counter - architectural event",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x14"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.",
-        "EventCode": "0xC0",
-        "Counter": "1",
-        "UMask": "0x1",
-        "Errata": "SKL091, SKL044",
-        "EventName": "INST_RETIRED.PREC_DIST",
+        "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA6",
+        "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
+        "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution",
-        "CounterHTOff": "1"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "Number of cycles using an always true condition applied to  PEBS instructions retired event. (inst_ret< 16)",
-        "EventCode": "0xC0",
-        "Invert": "1",
+        "BriefDescription": "Number of cycles using always true condition applied to  PEBS instructions retired event.",
         "Counter": "0,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,2,3",
+        "CounterMask": "10",
         "Errata": "SKL091, SKL044",
+        "EventCode": "0xC0",
         "EventName": "INST_RETIRED.TOTAL_CYCLES_PS",
+        "Invert": "1",
+        "PEBS": "2",
+        "PublicDescription": "Number of cycles using an always true condition applied to  PEBS instructions retired event. (inst_ret< 16)",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of cycles using always true condition applied to  PEBS instructions retired event.",
-        "CounterMask": "10",
-        "CounterHTOff": "0,2,3"
+        "UMask": "0x1"
     },
     {
-        "EventCode": "0xC1",
+        "BriefDescription": "Retirement slots used.",
         "Counter": "0,1,2,3",
-        "UMask": "0x3f",
-        "EventName": "OTHER_ASSISTS.ANY",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts the retirement slots used.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "EventCode": "0xC2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
         "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "PublicDescription": "Counts the retirement slots used.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Retirement slots used.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "This event counts cycles without actually retired uops.",
-        "EventCode": "0xC2",
-        "Invert": "1",
+        "AnyThread": "1",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_RETIRED.STALL_CYCLES",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x3C",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "SampleAfterValue": "2000003"
+    },
+    {
+        "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x0E",
+        "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
+        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles without actually retired uops.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
-        "EventCode": "0xC2",
-        "Invert": "1",
+        "BriefDescription": "Number of macro-fused uops retired. (non precise)",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc2",
+        "EventName": "UOPS_RETIRED.MACRO_FUSED",
+        "PublicDescription": "Counts the number of macro-fused uops retired. (non precise)",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with less than 10 actually retired uops.",
-        "CounterMask": "10",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Number of machine clears (nukes) of any type.",
-        "EventCode": "0xC3",
+        "BriefDescription": "Increments whenever there is an update to the LBR array.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "MACHINE_CLEARS.COUNT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of machine clears (nukes) of any type.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xCC",
+        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
+        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
-        "EventCode": "0xC3",
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MACHINE_CLEARS.SMC",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Self-modifying code (SMC) detected.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x5E",
+        "EventName": "RS_EVENTS.EMPTY_CYCLES",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts all (macro) branch instructions retired.",
-        "EventCode": "0xC4",
+        "BriefDescription": "Instructions retired from execution.",
+        "Counter": "Fixed counter 0",
+        "CounterHTOff": "Fixed counter 0",
+        "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "2",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.",
-        "EventCode": "0xC4",
+        "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.CONDITIONAL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Conditional branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA2",
+        "EventName": "RESOURCE_STALLS.SB",
+        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x8"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.",
-        "EventCode": "0xC4",
+        "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Direct and indirect near call instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0x3C",
+        "EventName": "CPU_CLK_UNHALTED.RING0_TRANS",
+        "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).",
+        "SampleAfterValue": "100007"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
-        "EventCode": "0xC4",
+        "BriefDescription": "All (macro) branch instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
+        "CounterHTOff": "0,1,2,3",
         "Errata": "SKL091",
+        "EventCode": "0xC4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+        "PEBS": "2",
+        "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.",
         "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x4"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.",
-        "EventCode": "0xC4",
+        "BriefDescription": "Mispredicted macro branch instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
+        "CounterHTOff": "0,1,2,3",
+        "EventCode": "0xC5",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
+        "PEBS": "2",
+        "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.",
+        "SampleAfterValue": "400009",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "Return instructions retired.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "Errata": "SKL091",
+        "EventCode": "0xC4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "PEBS": "1",
+        "PublicDescription": "This event counts return instructions retired.",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Return instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x8"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.",
-        "EventCode": "0xC4",
+        "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.NOT_TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Counts all not taken macro branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA6",
+        "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
+        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.",
-        "EventCode": "0xC4",
+        "BriefDescription": "Not taken branch instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "EventCode": "0xC4",
+        "EventName": "BR_INST_RETIRED.NOT_TAKEN",
+        "PublicDescription": "This event counts not taken branch instructions retired.",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Taken branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x10"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts far branch instructions retired.",
-        "EventCode": "0xC4",
+        "BriefDescription": "Conditional branch instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "Errata": "SKL091",
-        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of far branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
-        "EventCode": "0xC5",
-        "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "EventCode": "0xC4",
+        "EventName": "BR_INST_RETIRED.CONDITIONAL",
+        "PEBS": "1",
+        "PublicDescription": "This event counts conditional branch instructions retired.",
         "SampleAfterValue": "400009",
-        "BriefDescription": "All mispredicted macro branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.",
-        "EventCode": "0xC5",
+        "BriefDescription": "Mispredicted conditional branch instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xC5",
         "EventName": "BR_MISP_RETIRED.CONDITIONAL",
+        "PEBS": "1",
+        "PublicDescription": "This event counts mispredicted conditional branch instructions retired.",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted conditional branch instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.",
-        "EventCode": "0xC5",
+        "BriefDescription": "Number of uops executed on the core.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "BR_MISP_RETIRED.NEAR_CALL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted direct and indirect near call instructions retired.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.CORE",
+        "PublicDescription": "Number of uops executed from any thread.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.",
-        "EventCode": "0xC5",
+        "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted macro branch instructions retired.",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "12",
+        "EventCode": "0xA3",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "SampleAfterValue": "2000003",
+        "UMask": "0xc"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.",
-        "EventCode": "0xC5",
+        "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xA6",
+        "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
+        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
-        "EventCode": "0xCC",
+        "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x0D",
+        "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Increments whenever there is an update to the LBR array.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x80"
     },
     {
-        "EventCode": "0xCC",
+        "BriefDescription": "All (macro) branch instructions retired.",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "ROB_MISC_EVENTS.PAUSE_INST",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "Errata": "SKL091",
+        "EventCode": "0xC4",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "Counts all (macro) branch instructions retired.",
+        "SampleAfterValue": "400009"
+    },
+    {
+        "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0xB1",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC",
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
-        "EventCode": "0xE6",
+        "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "BACLEARS.ANY",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0xA3",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
index 8704efeb8d31..4cd246782dde 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
@@ -1,370 +1,371 @@
 [
     {
-        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
         "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
         "MetricGroup": "TopdownL1",
-        "MetricName": "Frontend_Bound",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound."
+        "MetricName": "Frontend_Bound"
     },
     {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
         "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
-        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
         "MetricGroup": "TopdownL1_SMT",
-        "MetricName": "Frontend_Bound_SMT",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
+        "MetricName": "Frontend_Bound_SMT"
     },
     {
-        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
         "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
         "MetricGroup": "TopdownL1",
-        "MetricName": "Bad_Speculation",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example."
+        "MetricName": "Bad_Speculation"
     },
     {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
         "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
-        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
         "MetricGroup": "TopdownL1_SMT",
-        "MetricName": "Bad_Speculation_SMT",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU."
+        "MetricName": "Bad_Speculation_SMT"
     },
     {
+        "MetricConstraint": "NO_NMI_WATCHDOG",
+        "MetricGroup": "TopdownL1",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
-        "MetricGroup": "TopdownL1",
-        "MetricName": "Backend_Bound",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound."
+        "MetricName": "Backend_Bound"
     },
     {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
-        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
         "MetricGroup": "TopdownL1_SMT",
-        "MetricName": "Backend_Bound_SMT",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU."
+        "MetricName": "Backend_Bound_SMT"
     },
     {
-        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "MetricGroup": "TopdownL1",
-        "MetricName": "Retiring",
-        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. "
+        "MetricName": "Retiring"
     },
     {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
         "MetricGroup": "TopdownL1_SMT",
-        "MetricName": "Retiring_SMT",
-        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU."
+        "MetricName": "Retiring_SMT"
     },
     {
-        "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
-        "MetricGroup": "TopDownL1",
+        "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
+        "MetricGroup": "Summary",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "BriefDescription": "Uops Per Instruction",
         "MetricGroup": "Pipeline;Retire",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Instruction per taken branch",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
         "MetricGroup": "Branches;Fetch_BW;PGO",
         "MetricName": "IpTB"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch. ",
-        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
-        "MetricGroup": "Branches;PGO",
-        "MetricName": "BpTB"
-    },
-    {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )",
-        "MetricGroup": "PGO;IcMiss",
-        "MetricName": "IFetch_Line_Utilization"
-    },
-    {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
-        "MetricGroup": "DSB;Fetch_BW",
-        "MetricName": "DSB_Coverage"
-    },
-    {
-        "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
-        "MetricGroup": "Pipeline;Summary",
+        "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
+        "MetricGroup": "Pipeline",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots (per-Physical Core)",
         "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots (per-Physical Core)",
-        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
+        "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
         "MetricGroup": "TopDownL1_SMT",
         "MetricName": "SLOTS_SMT"
     },
     {
-        "BriefDescription": "Instructions per Load (lower number means higher occurance rate)",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
-        "MetricGroup": "Instruction_Type",
-        "MetricName": "IpL"
-    },
-    {
-        "BriefDescription": "Instructions per Store (lower number means higher occurance rate)",
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
-        "MetricGroup": "Instruction_Type",
-        "MetricName": "IpS"
-    },
-    {
-        "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
-        "MetricGroup": "Branches;Instruction_Type",
-        "MetricName": "IpB"
-    },
-    {
-        "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)",
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
-        "MetricGroup": "Branches",
-        "MetricName": "IpCall"
-    },
-    {
-        "BriefDescription": "Total number of retired Instructions",
-        "MetricExpr": "INST_RETIRED.ANY",
-        "MetricGroup": "Summary",
-        "MetricName": "Instructions"
-    },
-    {
-        "BriefDescription": "Instructions Per Cycle (per physical core)",
         "MetricExpr": "INST_RETIRED.ANY / cycles",
-        "MetricGroup": "SMT",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT;TopDownL1",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
-        "MetricGroup": "SMT",
+        "MetricGroup": "SMT;TopDownL1",
         "MetricName": "CoreIPC_SMT"
     },
     {
+        "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / cycles",
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
         "MetricGroup": "FLOPS",
         "MetricName": "FLOPc"
     },
     {
+        "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
         "MetricGroup": "FLOPS_SMT",
         "MetricName": "FLOPc_SMT"
     },
     {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 )",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
-        "MetricGroup": "Pipeline",
+        "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)",
         "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
         "MetricGroup": "BrMispredicts",
         "MetricName": "Branch_Misprediction_Cost"
     },
     {
-        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)",
-        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) ) * (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
         "MetricGroup": "BrMispredicts_SMT",
         "MetricName": "Branch_Misprediction_Cost_SMT"
     },
     {
-        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
         "MetricGroup": "BrMispredicts",
         "MetricName": "IpMispredict"
     },
     {
-        "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
         "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
+        "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
+        "MetricGroup": "Instruction_Type",
+        "MetricName": "IpLoad"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
+        "MetricGroup": "Instruction_Type",
+        "MetricName": "IpStore"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
+        "MetricGroup": "Branches;Instruction_Type",
+        "MetricName": "IpBranch"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTkBranch"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
+        "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
+        "MetricGroup": "FLOPS;FP_Arith;Instruction_Type",
+        "MetricName": "IpFLOP"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
+        "MetricGroup": "Summary;TopDownL1",
+        "MetricName": "Instructions"
+    },
+    {
+        "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Fetch_BW",
+        "MetricName": "DSB_Coverage"
+    },
+    {
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
         "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
-        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricConstraint": "NO_NMI_WATCHDOG",
         "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricGroup": "TLB",
-        "MetricName": "Page_Walks_Utilization",
-        "MetricConstraint": "NO_NMI_WATCHDOG"
+        "MetricName": "Page_Walks_Utilization"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
         "MetricGroup": "TLB_SMT",
         "MetricName": "Page_Walks_Utilization_SMT"
     },
     {
-        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
         "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
         "MetricGroup": "Memory_BW",
         "MetricName": "L1D_Cache_Fill_BW"
     },
     {
-        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
         "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
         "MetricGroup": "Memory_BW",
         "MetricName": "L2_Cache_Fill_BW"
     },
     {
-        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
         "MetricGroup": "Memory_BW",
         "MetricName": "L3_Cache_Fill_BW"
     },
     {
-        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
-        "MetricGroup": "Memory_BW",
+        "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "L3_Cache_Access_BW"
     },
     {
-        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
         "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
         "MetricGroup": "Cache_Misses",
         "MetricName": "L1MPKI"
     },
     {
-        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
         "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
         "MetricGroup": "Cache_Misses",
         "MetricName": "L2MPKI"
     },
     {
-        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
         "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
-        "MetricGroup": "Cache_Misses",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;Offcore",
         "MetricName": "L2MPKI_All"
     },
     {
-        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
         "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
         "MetricGroup": "Cache_Misses",
         "MetricName": "L2HPKI_All"
     },
     {
-        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
         "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
         "MetricGroup": "Cache_Misses",
         "MetricName": "L3MPKI"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
-        "MetricGroup": "Summary",
+        "BriefDescription": "Average CPU Utilization",
+        "MetricGroup": "HPC;Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
-        "MetricGroup": "FLOPS;Summary",
+        "MetricGroup": "FLOPS;HPC",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
+        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 )",
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
-        "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
-        "MetricGroup": "SMT;Summary",
+        "MetricGroup": "SMT",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
-        "MetricGroup": "Summary",
+        "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
+        "MetricGroup": "OS",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
         "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
-        "MetricGroup": "Memory_BW",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "HPC;Memory_BW;SoC",
         "MetricName": "DRAM_BW_Use"
     },
     {
+        "MetricExpr": "arb@event\\=0x80\\,umask\\=0x2@ / arb@event\\=0x80\\,umask\\=0x2\\,cmask\\=1@",
         "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
-        "MetricExpr": "arb@event\\=0x80\\,umask\\=0x2@ / arb@event\\=0x80\\,umask\\=0x2\\,thresh\\=1@",
-        "MetricGroup": "Memory_BW",
-        "MetricName": "DRAM_Parallel_Reads"
+        "MetricGroup": "Memory_BW;SoC",
+        "MetricName": "MEM_Parallel_Reads"
     },
     {
-        "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions. )",
         "MetricExpr": "INST_RETIRED.ANY / ( BR_INST_RETIRED.FAR_BRANCH / 2 )",
-        "MetricGroup": "",
+        "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
+        "MetricGroup": "Branches;OS",
         "MetricName": "IpFarBranch"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
+        "BriefDescription": "C3 residency percent per core",
         "MetricGroup": "Power",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
+        "BriefDescription": "C6 residency percent per core",
         "MetricGroup": "Power",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
+        "BriefDescription": "C7 residency percent per core",
         "MetricGroup": "Power",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
+        "BriefDescription": "C2 residency percent per package",
         "MetricGroup": "Power",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
+        "BriefDescription": "C3 residency percent per package",
         "MetricGroup": "Power",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
+        "BriefDescription": "C6 residency percent per package",
         "MetricGroup": "Power",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
+        "BriefDescription": "C7 residency percent per package",
         "MetricGroup": "Power",
         "MetricName": "C7_Pkg_Residency"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json
index 2bcba7daca14..432530d15c26 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json
@@ -1,284 +1,284 @@
 [
     {
-        "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
-        "EventCode": "0x08",
+        "BriefDescription": "Store misses in all DTLB levels that cause page walks",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x49",
+        "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Load misses in all DTLB levels that cause page walks",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
-        "EventCode": "0x08",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Page walk completed due to a demand data load to a 4K page",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages.  The page walks can end with or without a page fault.",
-        "EventCode": "0x08",
+        "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x49",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
-        "EventCode": "0x08",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Page walk completed due to a demand data load to a 1G page",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x85",
+        "EventName": "ITLB_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
-        "EventCode": "0x08",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
         "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x85",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.",
-        "EventCode": "0x08",
+        "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xAE",
+        "EventName": "ITLB.ITLB_FLUSH",
+        "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).",
+        "SampleAfterValue": "100007",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.",
-        "EventCode": "0x08",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "EventCode": "0x85",
+        "EventName": "ITLB_MISSES.WALK_ACTIVE",
+        "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
-        "EventCode": "0x08",
+        "BriefDescription": "Loads that miss the DTLB and hit the STLB.",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x08",
         "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Loads that miss the DTLB and hit the STLB.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
+        "Counter": "0,1,2,3",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
         "EventCode": "0x49",
+        "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
+    },
+    {
+        "BriefDescription": "DTLB flush attempts of the thread-specific entries",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Store misses in all DTLB levels that cause page walks",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xBD",
+        "EventName": "TLB_FLUSH.DTLB_THREAD",
+        "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.",
+        "SampleAfterValue": "100007",
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages.  The page walks can end with or without a page fault.",
-        "EventCode": "0x49",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Page walk completed due to a demand data store to a 4K page",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x08",
+        "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
+        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages.  The page walks can end with or without a page fault.",
-        "EventCode": "0x49",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x49",
+        "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages.  The page walks can end with or without a page fault.",
-        "EventCode": "0x49",
+        "BriefDescription": "Misses at all ITLB levels that cause page walks",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x85",
+        "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Page walk completed due to a demand data store to a 1G page",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.",
-        "EventCode": "0x49",
+        "BriefDescription": "Stores that miss the DTLB and hit the STLB.",
         "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x49",
+        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.",
-        "EventCode": "0x49",
+        "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x08",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "UMask": "0xe"
     },
     {
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
-        "EventCode": "0x49",
+        "BriefDescription": "Page walk completed due to a demand data store to a 4K page",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x49",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
-        "EventCode": "0x49",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x85",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts completed page walks (1G page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Stores that miss the DTLB and hit the STLB.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x8"
     },
     {
-        "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.",
-        "EventCode": "0x4F",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "EPT.WALK_PENDING",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x85",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "UMask": "0xe"
     },
     {
-        "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.",
-        "EventCode": "0x85",
+        "BriefDescription": "Page walk completed due to a demand data load to a 4K page",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Misses at all ITLB levels that cause page walks",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x08",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
     },
     {
-        "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
-        "EventCode": "0x85",
+        "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x85",
+        "EventName": "ITLB_MISSES.STLB_HIT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Counts code misses in all ITLB levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.",
-        "EventCode": "0x85",
+        "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x08",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.",
-        "EventCode": "0x85",
+        "BriefDescription": "Load misses in all DTLB levels that cause page walks",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED_1G",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x08",
+        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
+        "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1"
     },
     {
-        "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.",
-        "EventCode": "0x85",
+        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.",
         "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x4f",
+        "EventName": "EPT.WALK_PENDING",
+        "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.",
-        "EventCode": "0x85",
+        "BriefDescription": "STLB flush attempts",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "ITLB_MISSES.WALK_PENDING",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xBD",
+        "EventName": "TLB_FLUSH.STLB_ANY",
+        "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).",
+        "SampleAfterValue": "100007",
+        "UMask": "0x20"
     },
     {
-        "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.",
-        "EventCode": "0x85",
+        "BriefDescription": "Page walk completed due to a demand data load to a 1G page",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "ITLB_MISSES.WALK_ACTIVE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x08",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x8"
     },
     {
-        "EventCode": "0x85",
+        "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "ITLB_MISSES.STLB_HIT",
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EventCode": "0x08",
+        "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x10"
     },
     {
-        "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).",
-        "EventCode": "0xAE",
+        "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ITLB.ITLB_FLUSH",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x85",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
+        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4"
     },
     {
-        "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.",
-        "EventCode": "0xBD",
+        "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "TLB_FLUSH.DTLB_THREAD",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "DTLB flush attempts of the thread-specific entries",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x49",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "UMask": "0xe"
     },
     {
-        "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).",
-        "EventCode": "0xBD",
+        "BriefDescription": "Page walk completed due to a demand data store to a 1G page",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "TLB_FLUSH.STLB_ANY",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "STLB flush attempts",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x49",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x8"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index e47644cab3fa..e1f3f5c8c550 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -55,6 +55,7 @@ char *prog;
 
 struct json_event {
 	char *name;
+	char *compat;
 	char *event;
 	char *desc;
 	char *long_desc;
@@ -82,6 +83,23 @@ enum aggr_mode_class convert(const char *aggr_mode)
 
 typedef int (*func)(void *data, struct json_event *je);
 
+static LIST_HEAD(sys_event_tables);
+
+struct sys_event_table {
+	struct list_head list;
+	char *soc_id;
+};
+
+static void free_sys_event_tables(void)
+{
+	struct sys_event_table *et, *next;
+
+	list_for_each_entry_safe(et, next, &sys_event_tables, list) {
+		free(et->soc_id);
+		free(et);
+	}
+}
+
 int eprintf(int level, int var, const char *fmt, ...)
 {
 
@@ -263,6 +281,8 @@ static struct map {
 	{ "hisi_sccl,ddrc", "hisi_sccl,ddrc" },
 	{ "hisi_sccl,hha", "hisi_sccl,hha" },
 	{ "hisi_sccl,l3c", "hisi_sccl,l3c" },
+	/* it's not realistic to keep adding these, we need something more scalable ... */
+	{ "imx8_ddr", "imx8_ddr" },
 	{ "L3PMC", "amd_l3" },
 	{ "DFPMC", "amd_df" },
 	{}
@@ -360,6 +380,8 @@ static int print_events_table_entry(void *data, struct json_event *je)
 	if (je->event)
 		fprintf(outfp, "\t.event = \"%s\",\n", je->event);
 	fprintf(outfp, "\t.desc = \"%s\",\n", je->desc);
+	if (je->compat)
+		fprintf(outfp, "\t.compat = \"%s\",\n", je->compat);
 	fprintf(outfp, "\t.topic = \"%s\",\n", topic);
 	if (je->long_desc && je->long_desc[0])
 		fprintf(outfp, "\t.long_desc = \"%s\",\n", je->long_desc);
@@ -390,6 +412,7 @@ struct event_struct {
 	struct list_head list;
 	char *name;
 	char *event;
+	char *compat;
 	char *desc;
 	char *long_desc;
 	char *pmu;
@@ -583,6 +606,8 @@ static int json_events(const char *fn,
 				free(code);
 			} else if (json_streq(map, field, "EventName")) {
 				addfield(map, &je.name, "", "", val);
+			} else if (json_streq(map, field, "Compat")) {
+				addfield(map, &je.compat, "", "", val);
 			} else if (json_streq(map, field, "BriefDescription")) {
 				addfield(map, &je.desc, "", "", val);
 				fixdesc(je.desc);
@@ -683,6 +708,7 @@ free_strings:
 		free(event);
 		free(je.desc);
 		free(je.name);
+		free(je.compat);
 		free(je.long_desc);
 		free(extra_desc);
 		free(je.pmu);
@@ -747,6 +773,15 @@ static char *file_name_to_table_name(char *fname)
 	return tblname;
 }
 
+static bool is_sys_dir(char *fname)
+{
+	size_t len = strlen(fname), len2 = strlen("/sys");
+
+	if (len2 > len)
+		return false;
+	return !strcmp(fname+len-len2, "/sys");
+}
+
 static void print_mapping_table_prefix(FILE *outfp)
 {
 	fprintf(outfp, "struct pmu_events_map pmu_events_map[] = {\n");
@@ -781,6 +816,33 @@ static void print_mapping_test_table(FILE *outfp)
 	fprintf(outfp, "},\n");
 }
 
+static void print_system_event_mapping_table_prefix(FILE *outfp)
+{
+	fprintf(outfp, "\nstruct pmu_sys_events pmu_sys_event_tables[] = {");
+}
+
+static void print_system_event_mapping_table_suffix(FILE *outfp)
+{
+	fprintf(outfp, "\n\t{\n\t\t.table = 0\n\t},");
+	fprintf(outfp, "\n};\n");
+}
+
+static int process_system_event_tables(FILE *outfp)
+{
+	struct sys_event_table *sys_event_table;
+
+	print_system_event_mapping_table_prefix(outfp);
+
+	list_for_each_entry(sys_event_table, &sys_event_tables, list) {
+		fprintf(outfp, "\n\t{\n\t\t.table = %s,\n\t},",
+			sys_event_table->soc_id);
+	}
+
+	print_system_event_mapping_table_suffix(outfp);
+
+	return 0;
+}
+
 static int process_mapfile(FILE *outfp, char *fpath)
 {
 	int n = 16384;
@@ -886,6 +948,8 @@ static void create_empty_mapping(const char *output_file)
 	fprintf(outfp, "#include \"pmu-events/pmu-events.h\"\n");
 	print_mapping_table_prefix(outfp);
 	print_mapping_table_suffix(outfp);
+	print_system_event_mapping_table_prefix(outfp);
+	print_system_event_mapping_table_suffix(outfp);
 	fclose(outfp);
 }
 
@@ -978,15 +1042,20 @@ static int process_one_file(const char *fpath, const struct stat *sb,
 	int level   = ftwbuf->level;
 	int err = 0;
 
-	if (level == 2 && is_dir) {
+	if (level >= 2 && is_dir) {
+		int count = 0;
 		/*
 		 * For level 2 directory, bname will include parent name,
 		 * like vendor/platform. So search back from platform dir
 		 * to find this.
+		 * Something similar for level 3 directory, but we're a PMU
+		 * category folder, like vendor/platform/cpu.
 		 */
 		bname = (char *) fpath + ftwbuf->base - 2;
 		for (;;) {
 			if (*bname == '/')
+				count++;
+			if (count == level - 1)
 				break;
 			bname--;
 		}
@@ -999,13 +1068,13 @@ static int process_one_file(const char *fpath, const struct stat *sb,
 		 level, sb->st_size, bname, fpath);
 
 	/* base dir or too deep */
-	if (level == 0 || level > 3)
+	if (level == 0 || level > 4)
 		return 0;
 
 
 	/* model directory, reset topic */
 	if ((level == 1 && is_dir && is_leaf_dir(fpath)) ||
-	    (level == 2 && is_dir)) {
+	    (level >= 2 && is_dir && is_leaf_dir(fpath))) {
 		if (close_table)
 			print_events_table_suffix(eventsfp);
 
@@ -1021,6 +1090,22 @@ static int process_one_file(const char *fpath, const struct stat *sb,
 			return -1;
 		}
 
+		if (is_sys_dir(bname)) {
+			struct sys_event_table *sys_event_table;
+
+			sys_event_table = malloc(sizeof(*sys_event_table));
+			if (!sys_event_table)
+				return -1;
+
+			sys_event_table->soc_id = strdup(tblname);
+			if (!sys_event_table->soc_id) {
+				free(sys_event_table);
+				return -1;
+			}
+			list_add_tail(&sys_event_table->list,
+				      &sys_event_tables);
+		}
+
 		print_events_table_prefix(eventsfp, tblname);
 		return 0;
 	}
@@ -1100,12 +1185,13 @@ static int process_one_file(const char *fpath, const struct stat *sb,
  */
 int main(int argc, char *argv[])
 {
-	int rc, ret = 0;
+	int rc, ret = 0, empty_map = 0;
 	int maxfds;
 	char ldirname[PATH_MAX];
 	const char *arch;
 	const char *output_file;
 	const char *start_dirname;
+	char *err_string_ext = "";
 	struct stat stbuf;
 
 	prog = basename(argv[0]);
@@ -1133,7 +1219,8 @@ int main(int argc, char *argv[])
 	/* If architecture does not have any event lists, bail out */
 	if (stat(ldirname, &stbuf) < 0) {
 		pr_info("%s: Arch %s has no PMU event lists\n", prog, arch);
-		goto empty_map;
+		empty_map = 1;
+		goto err_close_eventsfp;
 	}
 
 	/* Include pmu-events.h first */
@@ -1150,75 +1237,70 @@ int main(int argc, char *argv[])
 	 */
 
 	maxfds = get_maxfds();
-	mapfile = NULL;
 	rc = nftw(ldirname, preprocess_arch_std_files, maxfds, 0);
-	if (rc && verbose) {
-		pr_info("%s: Error preprocessing arch standard files %s\n",
-			prog, ldirname);
-		goto empty_map;
-	} else if (rc < 0) {
-		/* Make build fail */
-		fclose(eventsfp);
-		free_arch_std_events();
-		return 1;
-	} else if (rc) {
-		goto empty_map;
-	}
+	if (rc)
+		goto err_processing_std_arch_event_dir;
 
 	rc = nftw(ldirname, process_one_file, maxfds, 0);
-	if (rc && verbose) {
-		pr_info("%s: Error walking file tree %s\n", prog, ldirname);
-		goto empty_map;
-	} else if (rc < 0) {
-		/* Make build fail */
-		fclose(eventsfp);
-		free_arch_std_events();
-		ret = 1;
-		goto out_free_mapfile;
-	} else if (rc) {
-		goto empty_map;
-	}
+	if (rc)
+		goto err_processing_dir;
 
 	sprintf(ldirname, "%s/test", start_dirname);
 
+	rc = nftw(ldirname, preprocess_arch_std_files, maxfds, 0);
+	if (rc)
+		goto err_processing_std_arch_event_dir;
+
 	rc = nftw(ldirname, process_one_file, maxfds, 0);
-	if (rc && verbose) {
-		pr_info("%s: Error walking file tree %s rc=%d for test\n",
-			prog, ldirname, rc);
-		goto empty_map;
-	} else if (rc < 0) {
-		/* Make build fail */
-		free_arch_std_events();
-		ret = 1;
-		goto out_free_mapfile;
-	} else if (rc) {
-		goto empty_map;
-	}
+	if (rc)
+		goto err_processing_dir;
 
 	if (close_table)
 		print_events_table_suffix(eventsfp);
 
 	if (!mapfile) {
 		pr_info("%s: No CPU->JSON mapping?\n", prog);
-		goto empty_map;
+		empty_map = 1;
+		goto err_close_eventsfp;
 	}
 
-	if (process_mapfile(eventsfp, mapfile)) {
+	rc = process_mapfile(eventsfp, mapfile);
+	if (rc) {
 		pr_info("%s: Error processing mapfile %s\n", prog, mapfile);
 		/* Make build fail */
-		fclose(eventsfp);
-		free_arch_std_events();
 		ret = 1;
+		goto err_close_eventsfp;
 	}
 
+	rc = process_system_event_tables(eventsfp);
+	fclose(eventsfp);
+	if (rc) {
+		ret = 1;
+		goto err_out;
+	}
 
-	goto out_free_mapfile;
+	free_arch_std_events();
+	free(mapfile);
+	return 0;
 
-empty_map:
+err_processing_std_arch_event_dir:
+	err_string_ext = " for std arch event";
+err_processing_dir:
+	if (verbose) {
+		pr_info("%s: Error walking file tree %s%s\n", prog, ldirname,
+			err_string_ext);
+		empty_map = 1;
+	} else if (rc < 0) {
+		ret = 1;
+	} else {
+		empty_map = 1;
+	}
+err_close_eventsfp:
 	fclose(eventsfp);
-	create_empty_mapping(output_file);
+	if (empty_map)
+		create_empty_mapping(output_file);
+err_out:
 	free_arch_std_events();
-out_free_mapfile:
 	free(mapfile);
 	return ret;
 }
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 7da1a3743b77..d1172f6aebf1 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -12,6 +12,7 @@ enum aggr_mode_class {
  */
 struct pmu_event {
 	const char *name;
+	const char *compat;
 	const char *event;
 	const char *desc;
 	const char *topic;
@@ -43,10 +44,15 @@ struct pmu_events_map {
 	struct pmu_event *table;
 };
 
+struct pmu_sys_events {
+	struct pmu_event *table;
+};
+
 /*
  * Global table mapping each known CPU for the architecture to its
  * table of PMU events.
  */
 extern struct pmu_events_map pmu_events_map[];
+extern struct pmu_sys_events pmu_sys_event_tables[];
 
 #endif
diff --git a/tools/perf/python/tracepoint.py b/tools/perf/python/tracepoint.py
index eb76f6516247..461848c7f57d 100755
--- a/tools/perf/python/tracepoint.py
+++ b/tools/perf/python/tracepoint.py
@@ -1,4 +1,4 @@
-#! /usr/bin/python
+#! /usr/bin/env python
 # SPDX-License-Identifier: GPL-2.0
 # -*- python -*-
 # -*- coding: utf-8 -*-
diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py
index ff87ccf5b708..04f3db29b9bc 100755
--- a/tools/perf/python/twatch.py
+++ b/tools/perf/python/twatch.py
@@ -1,4 +1,4 @@
-#! /usr/bin/python
+#! /usr/bin/env python
 # SPDX-License-Identifier: GPL-2.0-only
 # -*- python -*-
 # -*- coding: utf-8 -*-
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 4d15bf6041fb..aa4dc4f5abde 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -62,6 +62,7 @@ perf-y += pfm.o
 perf-y += parse-metric.o
 perf-y += pe-file-parsing.o
 perf-y += expand-cgroup.o
+perf-y += perf-time-to-tsc.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 15cea518f5ad..b4b9a9488d51 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -109,7 +109,7 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m
 		return TEST_FAIL;
 	}
 
-	err = perf_evlist__create_maps(evlist, &opts.target);
+	err = evlist__create_maps(evlist, &opts.target);
 	if (err < 0) {
 		pr_debug("Not enough memory to create thread/cpu maps\n");
 		goto out_delete_evlist;
@@ -127,7 +127,7 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m
 		goto out_delete_evlist;
 	}
 
-	perf_evlist__config(evlist, &opts, NULL);
+	evlist__config(evlist, &opts, NULL);
 
 	err = evlist__open(evlist);
 	if (err < 0) {
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index cd77e334e577..f57e075b0ed2 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -9,12 +9,10 @@
 #include <util/util.h>
 #include <util/bpf-loader.h>
 #include <util/evlist.h>
-#include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <api/fs/fs.h>
-#include <bpf/bpf.h>
 #include <perf/mmap.h>
 #include "tests.h"
 #include "llvm.h"
@@ -25,6 +23,8 @@
 #define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test"
 
 #ifdef HAVE_LIBBPF_SUPPORT
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
 
 static int epoll_pwait_loop(void)
 {
@@ -144,23 +144,23 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 	pid[sizeof(pid) - 1] = '\0';
 	opts.target.tid = opts.target.pid = pid;
 
-	/* Instead of perf_evlist__new_default, don't add default events */
+	/* Instead of evlist__new_default, don't add default events */
 	evlist = evlist__new();
 	if (!evlist) {
 		pr_debug("Not enough memory to create evlist\n");
 		return TEST_FAIL;
 	}
 
-	err = perf_evlist__create_maps(evlist, &opts.target);
+	err = evlist__create_maps(evlist, &opts.target);
 	if (err < 0) {
 		pr_debug("Not enough memory to create thread/cpu maps\n");
 		goto out_delete_evlist;
 	}
 
-	perf_evlist__splice_list_tail(evlist, &parse_state.list);
+	evlist__splice_list_tail(evlist, &parse_state.list);
 	evlist->nr_groups = parse_state.nr_groups;
 
-	perf_evlist__config(evlist, &opts, NULL);
+	evlist__config(evlist, &opts, NULL);
 
 	err = evlist__open(evlist);
 	if (err < 0) {
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 132bdb3e6c31..7273823d0d02 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -142,6 +142,7 @@ static struct test generic_tests[] = {
 			.skip_if_fail	= false,
 			.get_nr		= test__wp_subtest_get_nr,
 			.get_desc	= test__wp_subtest_get_desc,
+			.skip_reason    = test__wp_subtest_skip_reason,
 		},
 	},
 	{
@@ -350,6 +351,11 @@ static struct test generic_tests[] = {
 		.func = test__expand_cgroup_events,
 	},
 	{
+		.desc = "Convert perf time to TSC",
+		.func = test__perf_time_to_tsc,
+		.is_supported = test__tsc_is_supported,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 035c9123549a..7c098d49c77e 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -378,8 +378,8 @@ static int process_sample_event(struct machine *machine,
 	struct thread *thread;
 	int ret;
 
-	if (perf_evlist__parse_sample(evlist, event, &sample)) {
-		pr_debug("perf_evlist__parse_sample failed\n");
+	if (evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("evlist__parse_sample failed\n");
 		return -1;
 	}
 
@@ -637,7 +637,7 @@ static int do_test_code_reading(bool try_kcore)
 
 		evlist = evlist__new();
 		if (!evlist) {
-			pr_debug("perf_evlist__new failed\n");
+			pr_debug("evlist__new failed\n");
 			goto out_put;
 		}
 
@@ -651,7 +651,7 @@ static int do_test_code_reading(bool try_kcore)
 			goto out_put;
 		}
 
-		perf_evlist__config(evlist, &opts, NULL);
+		evlist__config(evlist, &opts, NULL);
 
 		evsel = evlist__first(evlist);
 
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index db68894a6f40..04ce4401f775 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -26,13 +26,13 @@ static int attach__enable_on_exec(struct evlist *evlist)
 
 	pr_debug("attaching to spawned child, enable on exec\n");
 
-	err = perf_evlist__create_maps(evlist, &target);
+	err = evlist__create_maps(evlist, &target);
 	if (err < 0) {
 		pr_debug("Not enough memory to create thread/cpu maps\n");
 		return err;
 	}
 
-	err = perf_evlist__prepare_workload(evlist, &target, argv, false, NULL);
+	err = evlist__prepare_workload(evlist, &target, argv, false, NULL);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
 		return err;
@@ -47,7 +47,7 @@ static int attach__enable_on_exec(struct evlist *evlist)
 		return err;
 	}
 
-	return perf_evlist__start_workload(evlist) == 1 ? TEST_OK : TEST_FAIL;
+	return evlist__start_workload(evlist) == 1 ? TEST_OK : TEST_FAIL;
 }
 
 static int detach__enable_on_exec(struct evlist *evlist)
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index bdcf032f8516..656218179222 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -85,11 +85,10 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 
 int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused)
 {
-	struct evlist *evlist;
 	struct evsel *evsel;
 	struct event_name tmp;
+	struct evlist *evlist = evlist__new_default();
 
-	evlist = perf_evlist__new_default();
 	TEST_ASSERT_VAL("failed to get evlist", evlist);
 
 	evsel = evlist__first(evlist);
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 0e224a0a55d9..f9e34bd26cf3 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -5,8 +5,7 @@
 #include "tests.h"
 #include "debug.h"
 
-static int perf_evsel__test_field(struct evsel *evsel, const char *name,
-				  int size, bool should_be_signed)
+static int evsel__test_field(struct evsel *evsel, const char *name, int size, bool should_be_signed)
 {
 	struct tep_format_field *field = evsel__field(evsel, name);
 	int is_signed;
@@ -43,25 +42,25 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes
 		return -1;
 	}
 
-	if (perf_evsel__test_field(evsel, "prev_comm", 16, false))
+	if (evsel__test_field(evsel, "prev_comm", 16, false))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "prev_pid", 4, true))
+	if (evsel__test_field(evsel, "prev_pid", 4, true))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "prev_prio", 4, true))
+	if (evsel__test_field(evsel, "prev_prio", 4, true))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "prev_state", sizeof(long), true))
+	if (evsel__test_field(evsel, "prev_state", sizeof(long), true))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "next_comm", 16, false))
+	if (evsel__test_field(evsel, "next_comm", 16, false))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "next_pid", 4, true))
+	if (evsel__test_field(evsel, "next_pid", 4, true))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "next_prio", 4, true))
+	if (evsel__test_field(evsel, "next_prio", 4, true))
 		ret = -1;
 
 	evsel__delete(evsel);
@@ -73,16 +72,16 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes
 		return -1;
 	}
 
-	if (perf_evsel__test_field(evsel, "comm", 16, false))
+	if (evsel__test_field(evsel, "comm", 16, false))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "pid", 4, true))
+	if (evsel__test_field(evsel, "pid", 4, true))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "prio", 4, true))
+	if (evsel__test_field(evsel, "prio", 4, true))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "target_cpu", 4, true))
+	if (evsel__test_field(evsel, "target_cpu", 4, true))
 		ret = -1;
 
 	evsel__delete(evsel);
diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c
index d5771e4d094f..0e46aeb843ce 100644
--- a/tools/perf/tests/expand-cgroup.c
+++ b/tools/perf/tests/expand-cgroup.c
@@ -26,7 +26,7 @@ static int test_expand_events(struct evlist *evlist,
 	char **ev_name;
 	struct evsel *evsel;
 
-	TEST_ASSERT_VAL("evlist is empty", !perf_evlist__empty(evlist));
+	TEST_ASSERT_VAL("evlist is empty", !evlist__empty(evlist));
 
 	nr_events = evlist->core.nr_entries;
 	ev_name = calloc(nr_events, sizeof(*ev_name));
@@ -100,10 +100,9 @@ out:	for (i = 0; i < nr_events; i++)
 static int expand_default_events(void)
 {
 	int ret;
-	struct evlist *evlist;
 	struct rblist metric_events;
+	struct evlist *evlist = evlist__new_default();
 
-	evlist = perf_evlist__new_default();
 	TEST_ASSERT_VAL("failed to get evlist", evlist);
 
 	rblist__init(&metric_events);
@@ -145,7 +144,7 @@ static int expand_libpfm_events(void)
 	int ret;
 	struct evlist *evlist;
 	struct rblist metric_events;
-	const char event_str[] = "UNHALTED_CORE_CYCLES";
+	const char event_str[] = "CYCLES";
 	struct option opt = {
 		.value = &evlist,
 	};
@@ -161,7 +160,7 @@ static int expand_libpfm_events(void)
 			 event_str, ret);
 		goto out;
 	}
-	if (perf_evlist__empty(evlist)) {
+	if (evlist__empty(evlist)) {
 		pr_debug("libpfm was not enabled\n");
 		goto out;
 	}
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 50a0c9fcde7d..e6f1b2a38e03 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -92,7 +92,7 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un
 	CHECK__(parse_events(evlist, "dummy:u", NULL));
 	CHECK__(parse_events(evlist, "cycles:u", NULL));
 
-	perf_evlist__config(evlist, &opts, NULL);
+	evlist__config(evlist, &opts, NULL);
 
 	evsel = evlist__first(evlist);
 
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index ae6cda81c209..98da8a8757ab 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -2,13 +2,13 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <bpf/libbpf.h>
-#include <util/llvm-utils.h>
-#include "llvm.h"
 #include "tests.h"
 #include "debug.h"
 
 #ifdef HAVE_LIBBPF_SUPPORT
+#include <bpf/libbpf.h>
+#include <util/llvm-utils.h>
+#include "llvm.h"
 static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 {
 	struct bpf_object *obj;
@@ -19,14 +19,6 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 	bpf_object__close(obj);
 	return TEST_OK;
 }
-#else
-static int test__bpf_parsing(void *obj_buf __maybe_unused,
-			     size_t obj_buf_sz __maybe_unused)
-{
-	pr_debug("Skip bpf parsing\n");
-	return TEST_OK;
-}
-#endif
 
 static struct {
 	const char *source;
@@ -170,3 +162,19 @@ const char *test__llvm_subtest_get_desc(int subtest)
 
 	return bpf_source_table[subtest].desc;
 }
+#else //HAVE_LIBBPF_SUPPORT
+int test__llvm(struct test *test __maybe_unused, int subtest __maybe_unused)
+{
+	return TEST_SKIP;
+}
+
+int test__llvm_subtest_get_nr(void)
+{
+	return 0;
+}
+
+const char *test__llvm_subtest_get_desc(int subtest __maybe_unused)
+{
+	return NULL;
+}
+#endif // HAVE_LIBBPF_SUPPORT
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 7b0dbfc0e17d..57093aeacc6f 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -69,7 +69,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 
 	evlist = evlist__new();
 	if (evlist == NULL) {
-		pr_debug("perf_evlist__new\n");
+		pr_debug("evlist__new\n");
 		goto out_free_cpus;
 	}
 
@@ -126,14 +126,14 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 			goto out_delete_evlist;
 		}
 
-		err = perf_evlist__parse_sample(evlist, event, &sample);
+		err = evlist__parse_sample(evlist, event, &sample);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
 			goto out_delete_evlist;
 		}
 
 		err = -1;
-		evsel = perf_evlist__id2evsel(evlist, sample.id);
+		evsel = evlist__id2evsel(evlist, sample.id);
 		if (evsel == NULL) {
 			pr_debug("event with id %" PRIu64
 				 " doesn't map to an evsel\n", sample.id);
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 1f5f5e79ae25..5e4af2f0f14a 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -42,7 +42,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 	char sbuf[STRERR_BUFSIZE];
 
 	if (evlist == NULL) {
-		pr_debug("%s: perf_evlist__new\n", __func__);
+		pr_debug("%s: evlist__new\n", __func__);
 		goto out;
 	}
 
@@ -54,9 +54,9 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 
 	evlist__add(evlist, evsel);
 
-	err = perf_evlist__create_maps(evlist, &opts.target);
+	err = evlist__create_maps(evlist, &opts.target);
 	if (err < 0) {
-		pr_debug("%s: perf_evlist__create_maps\n", __func__);
+		pr_debug("%s: evlist__create_maps\n", __func__);
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 611512f22b34..a7f6661e6112 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -115,7 +115,7 @@ static int test__checkevent_symbolic_name_config(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong config",
 			PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config);
 	/*
-	 * The period value gets configured within perf_evlist__config,
+	 * The period value gets configured within evlist__config,
 	 * while this test executes only parse events method.
 	 */
 	TEST_ASSERT_VAL("wrong period",
@@ -443,7 +443,7 @@ static int test__checkevent_pmu(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong config1",    1 == evsel->core.attr.config1);
 	TEST_ASSERT_VAL("wrong config2",    3 == evsel->core.attr.config2);
 	/*
-	 * The period value gets configured within perf_evlist__config,
+	 * The period value gets configured within evlist__config,
 	 * while this test executes only parse events method.
 	 */
 	TEST_ASSERT_VAL("wrong period",     0 == evsel->core.attr.sample_period);
@@ -520,8 +520,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",  1 == evsel->core.attr.config);
 	/*
-	 * The period, time and callgraph value gets configured
-	 * within perf_evlist__config,
+	 * The period, time and callgraph value gets configured within evlist__config,
 	 * while this test executes only parse events method.
 	 */
 	TEST_ASSERT_VAL("wrong period",     0 == evsel->core.attr.sample_period);
@@ -533,8 +532,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config",  2 == evsel->core.attr.config);
 	/*
-	 * The period, time and callgraph value gets configured
-	 * within perf_evlist__config,
+	 * The period, time and callgraph value gets configured within evlist__config,
 	 * while this test executes only parse events method.
 	 */
 	TEST_ASSERT_VAL("wrong period",     0 == evsel->core.attr.sample_period);
diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
index 7c1bde01cb50..ce7be37f0d88 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -166,7 +166,7 @@ static int __compute_metric(const char *name, struct value *vals,
 	if (err)
 		goto out;
 
-	err = perf_evlist__alloc_stats(evlist, false);
+	err = evlist__alloc_stats(evlist, false);
 	if (err)
 		goto out;
 
@@ -183,7 +183,7 @@ out:
 	/* ... clenup. */
 	metricgroup__rblist_exit(&metric_events);
 	runtime_stat__exit(&st);
-	perf_evlist__free_stats(evlist);
+	evlist__free_stats(evlist);
 	perf_cpu_map__put(cpus);
 	evlist__delete(evlist);
 	return err;
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index adf3c9c4a416..471273676701 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -27,8 +27,8 @@ static int process_event(struct evlist **pevlist, union perf_event *event)
 	if (!*pevlist)
 		return -1;
 
-	if (perf_evlist__parse_sample(*pevlist, event, &sample)) {
-		pr_debug("perf_evlist__parse_sample failed\n");
+	if (evlist__parse_sample(*pevlist, event, &sample)) {
+		pr_debug("evlist__parse_sample failed\n");
 		return -1;
 	}
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 67d3f5aad016..0df471bf1590 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -53,7 +53,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 	};
 	cpu_set_t cpu_mask;
 	size_t cpu_mask_size = sizeof(cpu_mask);
-	struct evlist *evlist = perf_evlist__new_dummy();
+	struct evlist *evlist = evlist__new_dummy();
 	struct evsel *evsel;
 	struct perf_sample sample;
 	const char *cmd = "sleep";
@@ -71,7 +71,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 	char sbuf[STRERR_BUFSIZE];
 
 	if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */
-		evlist = perf_evlist__new_default();
+		evlist = evlist__new_default();
 
 	if (evlist == NULL) {
 		pr_debug("Not enough memory to create evlist\n");
@@ -81,10 +81,10 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 	/*
 	 * Create maps of threads and cpus to monitor. In this case
 	 * we start with all threads and cpus (-1, -1) but then in
-	 * perf_evlist__prepare_workload we'll fill in the only thread
+	 * evlist__prepare_workload we'll fill in the only thread
 	 * we're monitoring, the one forked there.
 	 */
-	err = perf_evlist__create_maps(evlist, &opts.target);
+	err = evlist__create_maps(evlist, &opts.target);
 	if (err < 0) {
 		pr_debug("Not enough memory to create thread/cpu maps\n");
 		goto out_delete_evlist;
@@ -92,11 +92,11 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 
 	/*
 	 * Prepare the workload in argv[] to run, it'll fork it, and then wait
-	 * for perf_evlist__start_workload() to exec it. This is done this way
+	 * for evlist__start_workload() to exec it. This is done this way
 	 * so that we have time to open the evlist (calling sys_perf_event_open
 	 * on all the fds) and then mmap them.
 	 */
-	err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false, NULL);
+	err = evlist__prepare_workload(evlist, &opts.target, argv, false, NULL);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
 		goto out_delete_evlist;
@@ -109,7 +109,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 	evsel__set_sample_bit(evsel, CPU);
 	evsel__set_sample_bit(evsel, TID);
 	evsel__set_sample_bit(evsel, TIME);
-	perf_evlist__config(evlist, &opts, NULL);
+	evlist__config(evlist, &opts, NULL);
 
 	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
 	if (err < 0) {
@@ -161,7 +161,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 	/*
 	 * Now!
 	 */
-	perf_evlist__start_workload(evlist);
+	evlist__start_workload(evlist);
 
 	while (1) {
 		int before = total_events;
@@ -182,7 +182,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 				if (type < PERF_RECORD_MAX)
 					nr_events[type]++;
 
-				err = perf_evlist__parse_sample(evlist, event, &sample);
+				err = evlist__parse_sample(evlist, event, &sample);
 				if (err < 0) {
 					if (verbose > 0)
 						perf_event__fprintf(event, NULL, stderr);
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 026d32ed078e..7cff02664d0e 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -18,10 +18,8 @@
 #include "thread_map.h"
 #include "record.h"
 #include "tsc.h"
-#include "util/mmap.h"
-#include "tests/tests.h"
-
-#include "arch-tests.h"
+#include "mmap.h"
+#include "tests.h"
 
 #define CHECK__(x) {				\
 	while ((x) < 0) {			\
@@ -82,7 +80,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
 	CHECK__(parse_events(evlist, "cycles:u", NULL));
 
-	perf_evlist__config(evlist, &opts, NULL);
+	evlist__config(evlist, &opts, NULL);
 
 	evsel = evlist__first(evlist);
 
@@ -171,3 +169,16 @@ out_err:
 	evlist__delete(evlist);
 	return err;
 }
+
+bool test__tsc_is_supported(void)
+{
+	/*
+	 * Except x86_64/i386 and Arm64, other archs don't support TSC in perf.
+	 * Just enable the test for x86_64/i386 and Arm64 archs.
+	 */
+#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__)
+	return true;
+#else
+	return false;
+#endif
+}
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index d3517a74d95e..0ca6a5a53523 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -14,8 +14,10 @@
 #include "util/parse-events.h"
 
 struct perf_pmu_test_event {
+	/* used for matching against events from generated pmu-events.c */
 	struct pmu_event event;
 
+	/* used for matching against event aliases */
 	/* extra events for aliases */
 	const char *alias_str;
 
@@ -78,6 +80,17 @@ static struct perf_pmu_test_event test_cpu_events[] = {
 		.alias_str = "umask=0,(null)=0x30d40,event=0x3a",
 		.alias_long_desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions",
 	},
+	{
+		.event = {
+			.name = "l3_cache_rd",
+			.event = "event=0x40",
+			.desc = "L3 cache access, read",
+			.long_desc = "Attributable Level 3 cache access, read",
+			.topic = "cache",
+		},
+		.alias_str = "event=0x40",
+		.alias_long_desc = "Attributable Level 3 cache access, read",
+	},
 	{ /* sentinel */
 		.event = {
 			.name = NULL,
@@ -357,6 +370,7 @@ static int __test__pmu_event_aliases(char *pmu_name, int *count)
 }
 
 
+/* Test that aliases generated are as expected */
 static int test_aliases(void)
 {
 	struct perf_pmu *pmu = NULL;
@@ -561,7 +575,7 @@ static int metric_parse_fake(const char *str)
 		}
 	}
 
-	if (expr__parse(&result, &ctx, str, 1))
+	if (expr__parse(&result, &ctx, str, 0))
 		pr_err("expr__parse failed\n");
 	else
 		ret = 0;
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index a0bdaf390ac8..2393916f6128 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -154,6 +154,9 @@ static bool samples_same(const struct perf_sample *s1,
 	if (type & PERF_SAMPLE_CGROUP)
 		COMP(cgroup);
 
+	if (type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		COMP(data_page_size);
+
 	if (type & PERF_SAMPLE_AUX) {
 		COMP(aux_sample.size);
 		if (memcmp(s1->aux_sample.data, s2->aux_sample.data,
@@ -234,6 +237,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 		},
 		.phys_addr	= 113,
 		.cgroup		= 114,
+		.data_page_size = 115,
 		.aux_sample	= {
 			.size	= sizeof(aux_data),
 			.data	= (void *)aux_data,
@@ -340,7 +344,7 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u
 	 * were added.  Please actually update the test rather than just change
 	 * the condition below.
 	 */
-	if (PERF_SAMPLE_MAX > PERF_SAMPLE_CGROUP << 1) {
+	if (PERF_SAMPLE_MAX > PERF_SAMPLE_CODE_PAGE_SIZE << 1) {
 		pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
 		return -1;
 	}
diff --git a/tools/perf/tests/shell/stat+shadow_stat.sh b/tools/perf/tests/shell/stat+shadow_stat.sh
new file mode 100755
index 000000000000..ebebd3596cf9
--- /dev/null
+++ b/tools/perf/tests/shell/stat+shadow_stat.sh
@@ -0,0 +1,78 @@
+#!/bin/sh
+# perf stat metrics (shadow stat) test
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+# skip if system-wide mode is forbidden
+perf stat -a true > /dev/null 2>&1 || exit 2
+
+test_global_aggr()
+{
+	perf stat -a --no-big-num -e cycles,instructions sleep 1  2>&1 | \
+	grep -e cycles -e instructions | \
+	while read num evt hash ipc rest
+	do
+		# skip not counted events
+		if [ "$num" = "<not" ]; then
+			continue
+		fi
+
+		# save cycles count
+		if [ "$evt" = "cycles" ]; then
+			cyc=$num
+			continue
+		fi
+
+		# skip if no cycles
+		if [ -z "$cyc" ]; then
+			continue
+		fi
+
+		# use printf for rounding and a leading zero
+		res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
+		if [ "$ipc" != "$res" ]; then
+			echo "IPC is different: $res != $ipc  ($num / $cyc)"
+			exit 1
+		fi
+	done
+}
+
+test_no_aggr()
+{
+	perf stat -a -A --no-big-num -e cycles,instructions sleep 1  2>&1 | \
+	grep ^CPU | \
+	while read cpu num evt hash ipc rest
+	do
+		# skip not counted events
+		if [ "$num" = "<not" ]; then
+			continue
+		fi
+
+		# save cycles count
+		if [ "$evt" = "cycles" ]; then
+			results="$results $cpu:$num"
+			continue
+		fi
+
+		cyc=${results##* $cpu:}
+		cyc=${cyc%% *}
+
+		# skip if no cycles
+		if [ -z "$cyc" ]; then
+			continue
+		fi
+
+		# use printf for rounding and a leading zero
+		res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
+		if [ "$ipc" != "$res" ]; then
+			echo "IPC is different for $cpu: $res != $ipc  ($num / $cyc)"
+			exit 1
+		fi
+	done
+}
+
+test_global_aggr
+test_no_aggr
+
+exit 0
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 11cc2af13f2b..3d31c1d560d6 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -20,7 +20,7 @@ skip_if_no_perf_trace || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+	evts=$(echo $(perf list syscalls:sys_enter_open* 2>/dev/null | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
 	perf trace -e $evts touch $file 2>&1 | \
 	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 4b9b731977c8..a49c9e23053b 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -109,7 +109,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		if (event->header.type != PERF_RECORD_SAMPLE)
 			goto next_event;
 
-		err = perf_evlist__parse_sample(evlist, event, &sample);
+		err = evlist__parse_sample(evlist, event, &sample);
 		if (err < 0) {
 			pr_debug("Error during parse sample\n");
 			goto out_delete_evlist;
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index db5e1f70053a..15a2ab765d89 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -128,12 +128,12 @@ static int process_sample_event(struct evlist *evlist,
 	pid_t next_tid, prev_tid;
 	int cpu, err;
 
-	if (perf_evlist__parse_sample(evlist, event, &sample)) {
-		pr_debug("perf_evlist__parse_sample failed\n");
+	if (evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("evlist__parse_sample failed\n");
 		return -1;
 	}
 
-	evsel = perf_evlist__id2evsel(evlist, sample.id);
+	evsel = evlist__id2evsel(evlist, sample.id);
 	if (evsel == switch_tracking->switch_evsel) {
 		next_tid = evsel__intval(evsel, &sample, "next_pid");
 		prev_tid = evsel__intval(evsel, &sample, "prev_pid");
@@ -223,8 +223,8 @@ static int add_event(struct evlist *evlist, struct list_head *events,
 	node->event = event;
 	list_add(&node->list, events);
 
-	if (perf_evlist__parse_sample(evlist, event, &sample)) {
-		pr_debug("perf_evlist__parse_sample failed\n");
+	if (evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("evlist__parse_sample failed\n");
 		return -1;
 	}
 
@@ -380,7 +380,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_
 	cycles_evsel = evlist__last(evlist);
 
 	/* Third event */
-	if (!perf_evlist__can_select_event(evlist, sched_switch)) {
+	if (!evlist__can_select_event(evlist, sched_switch)) {
 		pr_debug("No sched_switch\n");
 		err = 0;
 		goto out;
@@ -406,7 +406,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_
 		pr_debug("cycles event already at front");
 		goto out_err;
 	}
-	perf_evlist__to_front(evlist, cycles_evsel);
+	evlist__to_front(evlist, cycles_evsel);
 	if (cycles_evsel != evlist__first(evlist)) {
 		pr_debug("Failed to move cycles event to front");
 		goto out_err;
@@ -424,7 +424,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_
 
 	tracking_evsel = evlist__last(evlist);
 
-	perf_evlist__set_tracking_event(evlist, tracking_evsel);
+	evlist__set_tracking_event(evlist, tracking_evsel);
 
 	tracking_evsel->core.attr.freq = 0;
 	tracking_evsel->core.attr.sample_period = 1;
@@ -432,7 +432,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_
 	evsel__set_sample_bit(tracking_evsel, TIME);
 
 	/* Config events */
-	perf_evlist__config(evlist, &opts, NULL);
+	evlist__config(evlist, &opts, NULL);
 
 	/* Check moved event is still at the front */
 	if (cycles_evsel != evlist__first(evlist)) {
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index adaff9044331..bbf94e4aa145 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -23,7 +23,7 @@ static void sig_handler(int sig __maybe_unused)
 }
 
 /*
- * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
  * we asked by setting its exec_error to this handler.
  */
 static void workload_exec_failed_signal(int signo __maybe_unused,
@@ -58,16 +58,16 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 
 	signal(SIGCHLD, sig_handler);
 
-	evlist = perf_evlist__new_default();
+	evlist = evlist__new_default();
 	if (evlist == NULL) {
-		pr_debug("perf_evlist__new_default\n");
+		pr_debug("evlist__new_default\n");
 		return -1;
 	}
 
 	/*
 	 * Create maps of threads and cpus to monitor. In this case
 	 * we start with all threads and cpus (-1, -1) but then in
-	 * perf_evlist__prepare_workload we'll fill in the only thread
+	 * evlist__prepare_workload we'll fill in the only thread
 	 * we're monitoring, the one forked there.
 	 */
 	cpus = perf_cpu_map__dummy_new();
@@ -83,8 +83,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	cpus	= NULL;
 	threads = NULL;
 
-	err = perf_evlist__prepare_workload(evlist, &target, argv, false,
-					    workload_exec_failed_signal);
+	err = evlist__prepare_workload(evlist, &target, argv, false, workload_exec_failed_signal);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
 		goto out_delete_evlist;
@@ -116,7 +115,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 		goto out_delete_evlist;
 	}
 
-	perf_evlist__start_workload(evlist);
+	evlist__start_workload(evlist);
 
 retry:
 	md = &evlist->mmap[0];
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index c85a2c08e407..8e24a61fe4c2 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -66,6 +66,7 @@ int test__bp_signal_overflow(struct test *test, int subtest);
 int test__bp_accounting(struct test *test, int subtest);
 int test__wp(struct test *test, int subtest);
 const char *test__wp_subtest_get_desc(int subtest);
+const char *test__wp_subtest_skip_reason(int subtest);
 int test__wp_subtest_get_nr(void);
 int test__task_exit(struct test *test, int subtest);
 int test__mem(struct test *test, int subtest);
@@ -124,10 +125,12 @@ int test__pfm_subtest_get_nr(void);
 int test__parse_metric(struct test *test, int subtest);
 int test__pe_file_parsing(struct test *test, int subtest);
 int test__expand_cgroup_events(struct test *test, int subtest);
+int test__perf_time_to_tsc(struct test *test, int subtest);
 
 bool test__bp_signal_is_supported(void);
 bool test__bp_account_is_supported(void);
 bool test__wp_is_supported(void);
+bool test__tsc_is_supported(void);
 
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 22daf2bdf5fa..74748ed75b2c 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -40,7 +40,7 @@ static int session_write_header(char *path)
 	session = perf_session__new(&data, false, NULL);
 	TEST_ASSERT_VAL("can't get session", !IS_ERR(session));
 
-	session->evlist = perf_evlist__new_default();
+	session->evlist = evlist__new_default();
 	TEST_ASSERT_VAL("can't get evlist", session->evlist);
 
 	perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY);
@@ -65,9 +65,11 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 		.mode = PERF_DATA_MODE_READ,
 	};
 	int i;
+	struct aggr_cpu_id id;
 
 	session = perf_session__new(&data, false, NULL);
 	TEST_ASSERT_VAL("can't get session", !IS_ERR(session));
+	cpu__setup_cpunode_map();
 
 	/* On platforms with large numbers of CPUs process_cpu_topology()
 	 * might issue an error while reading the perf.data file section
@@ -85,11 +87,18 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	 *  "socket_id number is too big. You may need to upgrade the
 	 *  perf tool."
 	 *
-	 *  This is the reason why this test might be skipped.
+	 *  This is the reason why this test might be skipped. aarch64 and
+	 *  s390 always write this part of the header, even when the above
+	 *  condition is true (see do_core_id_test in header.c). So always
+	 *  run this test on those platforms.
 	 */
-	if (!session->header.env.cpu)
+	if (!session->header.env.cpu
+			&& strncmp(session->header.env.arch, "s390", 4)
+			&& strncmp(session->header.env.arch, "aarch64", 7))
 		return TEST_SKIP;
 
+	TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu);
+
 	for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
 		if (!cpu_map__has(map, i))
 			continue;
@@ -98,14 +107,57 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 			 session->header.env.cpu[i].socket_id);
 	}
 
+	// Test that core ID contains socket, die and core
+	for (i = 0; i < map->nr; i++) {
+		id = cpu_map__get_core(map, i, NULL);
+		TEST_ASSERT_VAL("Core map - Core ID doesn't match",
+			session->header.env.cpu[map->map[i]].core_id == id.core);
+
+		TEST_ASSERT_VAL("Core map - Socket ID doesn't match",
+			session->header.env.cpu[map->map[i]].socket_id == id.socket);
+
+		TEST_ASSERT_VAL("Core map - Die ID doesn't match",
+			session->header.env.cpu[map->map[i]].die_id == id.die);
+		TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1);
+		TEST_ASSERT_VAL("Core map - Thread is set", id.thread == -1);
+	}
+
+	// Test that die ID contains socket and die
 	for (i = 0; i < map->nr; i++) {
-		TEST_ASSERT_VAL("Core ID doesn't match",
-			(session->header.env.cpu[map->map[i]].core_id == (cpu_map__get_core(map, i, NULL) & 0xffff)));
+		id = cpu_map__get_die(map, i, NULL);
+		TEST_ASSERT_VAL("Die map - Socket ID doesn't match",
+			session->header.env.cpu[map->map[i]].socket_id == id.socket);
 
-		TEST_ASSERT_VAL("Socket ID doesn't match",
-			(session->header.env.cpu[map->map[i]].socket_id == cpu_map__get_socket(map, i, NULL)));
+		TEST_ASSERT_VAL("Die map - Die ID doesn't match",
+			session->header.env.cpu[map->map[i]].die_id == id.die);
+
+		TEST_ASSERT_VAL("Die map - Node ID is set", id.node == -1);
+		TEST_ASSERT_VAL("Die map - Core is set", id.core == -1);
+		TEST_ASSERT_VAL("Die map - Thread is set", id.thread == -1);
+	}
+
+	// Test that socket ID contains only socket
+	for (i = 0; i < map->nr; i++) {
+		id = cpu_map__get_socket(map, i, NULL);
+		TEST_ASSERT_VAL("Socket map - Socket ID doesn't match",
+			session->header.env.cpu[map->map[i]].socket_id == id.socket);
+
+		TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1);
+		TEST_ASSERT_VAL("Socket map - Die ID is set", id.die == -1);
+		TEST_ASSERT_VAL("Socket map - Core is set", id.core == -1);
+		TEST_ASSERT_VAL("Socket map - Thread is set", id.thread == -1);
 	}
 
+	// Test that node ID contains only node
+	for (i = 0; i < map->nr; i++) {
+		id = cpu_map__get_node(map, i, NULL);
+		TEST_ASSERT_VAL("Node map - Node ID doesn't match",
+			cpu__get_node(map->map[i]) == id.node);
+		TEST_ASSERT_VAL("Node map - Socket is set", id.socket == -1);
+		TEST_ASSERT_VAL("Node map - Die ID is set", id.die == -1);
+		TEST_ASSERT_VAL("Node map - Core is set", id.core == -1);
+		TEST_ASSERT_VAL("Node map - Thread is set", id.thread == -1);
+	}
 	perf_session__delete(session);
 
 	return 0;
diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
index d262d6639829..9387fa76faa5 100644
--- a/tools/perf/tests/wp.c
+++ b/tools/perf/tests/wp.c
@@ -174,10 +174,12 @@ static bool wp_ro_supported(void)
 #endif
 }
 
-static void wp_ro_skip_msg(void)
+static const char *wp_ro_skip_msg(void)
 {
 #if defined (__x86_64__) || defined (__i386__)
-	pr_debug("Hardware does not support read only watchpoints.\n");
+	return "missing hardware support";
+#else
+	return NULL;
 #endif
 }
 
@@ -185,7 +187,7 @@ static struct {
 	const char *desc;
 	int (*target_func)(void);
 	bool (*is_supported)(void);
-	void (*skip_msg)(void);
+	const char *(*skip_msg)(void);
 } wp_testcase_table[] = {
 	{
 		.desc = "Read Only Watchpoint",
@@ -219,16 +221,23 @@ const char *test__wp_subtest_get_desc(int i)
 	return wp_testcase_table[i].desc;
 }
 
+const char *test__wp_subtest_skip_reason(int i)
+{
+	if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table))
+		return NULL;
+	if (!wp_testcase_table[i].skip_msg)
+		return NULL;
+	return wp_testcase_table[i].skip_msg();
+}
+
 int test__wp(struct test *test __maybe_unused, int i)
 {
 	if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table))
 		return TEST_FAIL;
 
 	if (wp_testcase_table[i].is_supported &&
-	    !wp_testcase_table[i].is_supported()) {
-		wp_testcase_table[i].skip_msg();
+	    !wp_testcase_table[i].is_supported())
 		return TEST_SKIP;
-	}
 
 	return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL;
 }
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index e9cb30d8cbfb..385894b4a8bb 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -436,6 +436,7 @@ extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
 			     int __user *usockaddr_len);
 extern int __sys_socketpair(int family, int type, int protocol,
 			    int __user *usockvec);
+extern int __sys_shutdown_sock(struct socket *sock, int how);
 extern int __sys_shutdown(int fd, int how);
 
 extern struct ns_common *get_net_ns(struct ns_common *ns);
diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh
index 39eb2595983b..76825710c725 100755
--- a/tools/perf/trace/beauty/mmap_flags.sh
+++ b/tools/perf/trace/beauty/mmap_flags.sh
@@ -28,12 +28,12 @@ egrep -q $regex ${linux_mman} && \
 	egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
 	sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n")
-([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) &&
+([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) &&
 (egrep $regex ${header_dir}/mman-common.h | \
 	egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
 	sed -r "s/$regex/\2 \1 \1 \1 \2/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n")
-([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.h>.*' ${arch_mman}) &&
+([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.h>.*' ${arch_mman}) &&
 (egrep $regex ${header_dir}/mman.h | \
 	sed -r "s/$regex/\2 \1 \1 \1 \2/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n")
diff --git a/tools/perf/trace/beauty/mmap_prot.sh b/tools/perf/trace/beauty/mmap_prot.sh
index 28f638f8d216..664d8d534a50 100755
--- a/tools/perf/trace/beauty/mmap_prot.sh
+++ b/tools/perf/trace/beauty/mmap_prot.sh
@@ -17,7 +17,7 @@ prefix="PROT"
 
 printf "static const char *mmap_prot[] = {\n"
 regex=`printf '^[[:space:]]*#[[:space:]]*define[[:space:]]+%s_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' ${prefix}`
-([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) &&
+([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) &&
 (egrep $regex ${common_mman} | \
 	egrep -vw PROT_NONE | \
 	sed -r "s/$regex/\2 \1 \1 \1 \2/g"	| \
diff --git a/tools/perf/trace/beauty/tracepoints/x86_msr.sh b/tools/perf/trace/beauty/tracepoints/x86_msr.sh
index 831c02cf0586..27ee1ea1fe94 100755
--- a/tools/perf/trace/beauty/tracepoints/x86_msr.sh
+++ b/tools/perf/trace/beauty/tracepoints/x86_msr.sh
@@ -15,7 +15,7 @@ x86_msr_index=${arch_x86_header_dir}/msr-index.h
 
 printf "static const char *x86_MSRs[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MSR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x00000[[:xdigit:]]+)[[:space:]]*.*'
-egrep $regex ${x86_msr_index} | egrep -v 'MSR_(ATOM|P[46]|AMD64|IA32_TSCDEADLINE|IDT_FCR4)' | \
+egrep $regex ${x86_msr_index} | egrep -v 'MSR_(ATOM|P[46]|IA32_(TSCDEADLINE|UCODE_REV)|IDT_FCR4)' | \
 	sed -r "s/$regex/\2 \1/g" | sort -n | \
 	xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n\n"
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index b0e1880cf992..3b9818ee9546 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2946,14 +2946,10 @@ next:
 	}
 }
 
-static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
-				    const char *helpline,
-				    bool left_exits,
-				    struct hist_browser_timer *hbt,
-				    float min_pcnt,
-				    struct perf_env *env,
-				    bool warn_lost_event,
-				    struct annotation_options *annotation_opts)
+static int evsel__hists_browse(struct evsel *evsel, int nr_events, const char *helpline,
+			       bool left_exits, struct hist_browser_timer *hbt, float min_pcnt,
+			       struct perf_env *env, bool warn_lost_event,
+			       struct annotation_options *annotation_opts)
 {
 	struct hists *hists = evsel__hists(evsel);
 	struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env, annotation_opts);
@@ -3268,7 +3264,7 @@ do_hotkey:		 // key came straight from options ui__popup_menu()
 			if (!is_report_browser(hbt)) {
 				struct perf_top *top = hbt->arg;
 
-				perf_evlist__toggle_enable(top->evlist);
+				evlist__toggle_enable(top->evlist);
 				/*
 				 * No need to refresh, resort/decay histogram
 				 * entries if we are not collecting samples:
@@ -3498,19 +3494,17 @@ static int perf_evsel_menu__run(struct evsel_menu *menu,
 				continue;
 			pos = menu->selection;
 browse_hists:
-			perf_evlist__set_selected(evlist, pos);
+			evlist__set_selected(evlist, pos);
 			/*
 			 * Give the calling tool a chance to populate the non
 			 * default evsel resorted hists tree.
 			 */
 			if (hbt)
 				hbt->timer(hbt->arg);
-			key = perf_evsel__hists_browse(pos, nr_events, help,
-						       true, hbt,
-						       menu->min_pcnt,
-						       menu->env,
-						       warn_lost_event,
-						       menu->annotation_opts);
+			key = evsel__hists_browse(pos, nr_events, help, true, hbt,
+						  menu->min_pcnt, menu->env,
+						  warn_lost_event,
+						  menu->annotation_opts);
 			ui_browser__show_title(&menu->b, title);
 			switch (key) {
 			case K_TAB:
@@ -3565,13 +3559,9 @@ static bool filter_group_entries(struct ui_browser *browser __maybe_unused,
 	return false;
 }
 
-static int __perf_evlist__tui_browse_hists(struct evlist *evlist,
-					   int nr_entries, const char *help,
-					   struct hist_browser_timer *hbt,
-					   float min_pcnt,
-					   struct perf_env *env,
-					   bool warn_lost_event,
-					   struct annotation_options *annotation_opts)
+static int __evlist__tui_browse_hists(struct evlist *evlist, int nr_entries, const char *help,
+				      struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env,
+				      bool warn_lost_event, struct annotation_options *annotation_opts)
 {
 	struct evsel *pos;
 	struct evsel_menu menu = {
@@ -3603,7 +3593,7 @@ static int __perf_evlist__tui_browse_hists(struct evlist *evlist,
 				    hbt, warn_lost_event);
 }
 
-static bool perf_evlist__single_entry(struct evlist *evlist)
+static bool evlist__single_entry(struct evlist *evlist)
 {
 	int nr_entries = evlist->core.nr_entries;
 
@@ -3620,23 +3610,18 @@ static bool perf_evlist__single_entry(struct evlist *evlist)
 	return false;
 }
 
-int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help,
-				  struct hist_browser_timer *hbt,
-				  float min_pcnt,
-				  struct perf_env *env,
-				  bool warn_lost_event,
-				  struct annotation_options *annotation_opts)
+int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt,
+			     float min_pcnt, struct perf_env *env, bool warn_lost_event,
+			     struct annotation_options *annotation_opts)
 {
 	int nr_entries = evlist->core.nr_entries;
 
-	if (perf_evlist__single_entry(evlist)) {
+	if (evlist__single_entry(evlist)) {
 single_entry: {
 		struct evsel *first = evlist__first(evlist);
 
-		return perf_evsel__hists_browse(first, nr_entries, help,
-						false, hbt, min_pcnt,
-						env, warn_lost_event,
-						annotation_opts);
+		return evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt,
+					   env, warn_lost_event, annotation_opts);
 	}
 	}
 
@@ -3653,10 +3638,8 @@ single_entry: {
 			goto single_entry;
 	}
 
-	return __perf_evlist__tui_browse_hists(evlist, nr_entries, help,
-					       hbt, min_pcnt, env,
-					       warn_lost_event,
-					       annotation_opts);
+	return __evlist__tui_browse_hists(evlist, nr_entries, help, hbt, min_pcnt, env,
+					  warn_lost_event, annotation_opts);
 }
 
 static int block_hists_browser__title(struct hist_browser *browser, char *bf,
diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h
index a9563932fa04..a2b497f03fd6 100644
--- a/tools/perf/ui/gtk/gtk.h
+++ b/tools/perf/ui/gtk/gtk.h
@@ -57,9 +57,8 @@ struct evlist;
 struct hist_entry;
 struct hist_browser_timer;
 
-int perf_evlist__gtk_browse_hists(struct evlist *evlist, const char *help,
-				  struct hist_browser_timer *hbt,
-				  float min_pcnt);
+int evlist__gtk_browse_hists(struct evlist *evlist, const char *help,
+			     struct hist_browser_timer *hbt, float min_pcnt);
 int hist_entry__gtk_annotate(struct hist_entry *he,
 			     struct evsel *evsel,
 			     struct hist_browser_timer *hbt);
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 53ef71a1b15d..c83be2d57f7e 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -590,10 +590,8 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
 	gtk_container_add(GTK_CONTAINER(window), view);
 }
 
-int perf_evlist__gtk_browse_hists(struct evlist *evlist,
-				  const char *help,
-				  struct hist_browser_timer *hbt __maybe_unused,
-				  float min_pcnt)
+int evlist__gtk_browse_hists(struct evlist *evlist, const char *help,
+			     struct hist_browser_timer *hbt __maybe_unused, float min_pcnt)
 {
 	struct evsel *pos;
 	GtkWidget *vbox;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 6c8575e182ed..ce8c07bc8c56 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -10,10 +10,6 @@
 #include <inttypes.h>
 #include <libgen.h>
 #include <stdlib.h>
-#include <bpf/bpf.h>
-#include <bpf/btf.h>
-#include <bpf/libbpf.h>
-#include <linux/btf.h>
 #include "util.h" // hex_width()
 #include "ui/ui.h"
 #include "sort.h"
@@ -152,6 +148,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i
 #include "arch/arm/annotate/instructions.c"
 #include "arch/arm64/annotate/instructions.c"
 #include "arch/csky/annotate/instructions.c"
+#include "arch/mips/annotate/instructions.c"
 #include "arch/x86/annotate/instructions.c"
 #include "arch/powerpc/annotate/instructions.c"
 #include "arch/s390/annotate/instructions.c"
@@ -175,6 +172,13 @@ static struct arch architectures[] = {
 		.init = csky__annotate_init,
 	},
 	{
+		.name = "mips",
+		.init = mips__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
+	{
 		.name = "x86",
 		.init = x86__annotate_init,
 		.instructions = x86__instructions,
@@ -1676,6 +1680,10 @@ fallback:
 #define PACKAGE "perf"
 #include <bfd.h>
 #include <dis-asm.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include <linux/btf.h>
 
 static int symbol__disassemble_bpf(struct symbol *sym,
 				   struct annotate_args *args)
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
index 93e063f22be5..90d575cee1b9 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
@@ -12,6 +12,7 @@
 #include <string.h>
 #include <stdint.h>
 #include <stdlib.h>
+#include <linux/bitops.h>
 #include <linux/compiler.h>
 #include <linux/zalloc.h>
 
@@ -21,42 +22,51 @@
 
 #include "arm-spe-decoder.h"
 
-#ifndef BIT
-#define BIT(n)		(1UL << (n))
-#endif
-
 static u64 arm_spe_calc_ip(int index, u64 payload)
 {
-	u8 *addr = (u8 *)&payload;
-	int ns, el;
+	u64 ns, el, val;
 
 	/* Instruction virtual address or Branch target address */
 	if (index == SPE_ADDR_PKT_HDR_INDEX_INS ||
 	    index == SPE_ADDR_PKT_HDR_INDEX_BRANCH) {
-		ns = addr[7] & SPE_ADDR_PKT_NS;
-		el = (addr[7] & SPE_ADDR_PKT_EL_MASK) >> SPE_ADDR_PKT_EL_OFFSET;
+		ns = SPE_ADDR_PKT_GET_NS(payload);
+		el = SPE_ADDR_PKT_GET_EL(payload);
+
+		/* Clean highest byte */
+		payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload);
 
 		/* Fill highest byte for EL1 or EL2 (VHE) mode */
 		if (ns && (el == SPE_ADDR_PKT_EL1 || el == SPE_ADDR_PKT_EL2))
-			addr[7] = 0xff;
-		/* Clean highest byte for other cases */
-		else
-			addr[7] = 0x0;
+			payload |= 0xffULL << SPE_ADDR_PKT_ADDR_BYTE7_SHIFT;
 
 	/* Data access virtual address */
 	} else if (index == SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT) {
 
-		/* Fill highest byte if bits [48..55] is 0xff */
-		if (addr[6] == 0xff)
-			addr[7] = 0xff;
-		/* Otherwise, cleanup tags */
-		else
-			addr[7] = 0x0;
+		/* Clean tags */
+		payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload);
+
+		/*
+		 * Armv8 ARM (ARM DDI 0487F.c), chapter "D10.2.1 Address packet"
+		 * defines the data virtual address payload format, the top byte
+		 * (bits [63:56]) is assigned as top-byte tag; so we only can
+		 * retrieve address value from bits [55:0].
+		 *
+		 * According to Documentation/arm64/memory.rst, if detects the
+		 * specific pattern in bits [55:52] of payload which falls in
+		 * the kernel space, should fixup the top byte and this allows
+		 * perf tool to parse DSO symbol for data address correctly.
+		 *
+		 * For this reason, if detects the bits [55:52] is 0xf, will
+		 * fill 0xff into the top byte.
+		 */
+		val = SPE_ADDR_PKT_ADDR_GET_BYTE_6(payload);
+		if ((val & 0xf0ULL) == 0xf0ULL)
+			payload |= 0xffULL << SPE_ADDR_PKT_ADDR_BYTE7_SHIFT;
 
 	/* Data access physical address */
 	} else if (index == SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS) {
-		/* Cleanup byte 7 */
-		addr[7] = 0x0;
+		/* Clean highest byte */
+		payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload);
 	} else {
 		pr_err("unsupported address packet index: 0x%x\n", index);
 	}
@@ -182,16 +192,13 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
 			if (payload & BIT(EV_TLB_ACCESS))
 				decoder->record.type |= ARM_SPE_TLB_ACCESS;
 
-			if ((idx == 2 || idx == 4 || idx == 8) &&
-			    (payload & BIT(EV_LLC_MISS)))
+			if (payload & BIT(EV_LLC_MISS))
 				decoder->record.type |= ARM_SPE_LLC_MISS;
 
-			if ((idx == 2 || idx == 4 || idx == 8) &&
-			    (payload & BIT(EV_LLC_ACCESS)))
+			if (payload & BIT(EV_LLC_ACCESS))
 				decoder->record.type |= ARM_SPE_LLC_ACCESS;
 
-			if ((idx == 2 || idx == 4 || idx == 8) &&
-			    (payload & BIT(EV_REMOTE_ACCESS)))
+			if (payload & BIT(EV_REMOTE_ACCESS))
 				decoder->record.type |= ARM_SPE_REMOTE_ACCESS;
 
 			if (payload & BIT(EV_MISPRED))
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
index a5111a8d4360..24727b8ca7ff 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -13,23 +13,6 @@
 
 #include "arm-spe-pkt-decoder.h"
 
-enum arm_spe_events {
-	EV_EXCEPTION_GEN	= 0,
-	EV_RETIRED		= 1,
-	EV_L1D_ACCESS		= 2,
-	EV_L1D_REFILL		= 3,
-	EV_TLB_ACCESS		= 4,
-	EV_TLB_WALK		= 5,
-	EV_NOT_TAKEN		= 6,
-	EV_MISPRED		= 7,
-	EV_LLC_ACCESS		= 8,
-	EV_LLC_MISS		= 9,
-	EV_REMOTE_ACCESS	= 10,
-	EV_ALIGNMENT		= 11,
-	EV_PARTIAL_PREDICATE	= 17,
-	EV_EMPTY_PREDICATE	= 18,
-};
-
 enum arm_spe_sample_type {
 	ARM_SPE_L1D_ACCESS	= 1 << 0,
 	ARM_SPE_L1D_MISS	= 1 << 1,
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
index b94001b756c7..f3ac9d40cebf 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c
@@ -8,36 +8,11 @@
 #include <string.h>
 #include <endian.h>
 #include <byteswap.h>
+#include <linux/bitops.h>
+#include <stdarg.h>
 
 #include "arm-spe-pkt-decoder.h"
 
-#define BIT(n)		(1ULL << (n))
-
-#define NS_FLAG		BIT(63)
-#define EL_FLAG		(BIT(62) | BIT(61))
-
-#define SPE_HEADER0_PAD			0x0
-#define SPE_HEADER0_END			0x1
-#define SPE_HEADER0_ADDRESS		0x30 /* address packet (short) */
-#define SPE_HEADER0_ADDRESS_MASK	0x38
-#define SPE_HEADER0_COUNTER		0x18 /* counter packet (short) */
-#define SPE_HEADER0_COUNTER_MASK	0x38
-#define SPE_HEADER0_TIMESTAMP		0x71
-#define SPE_HEADER0_TIMESTAMP		0x71
-#define SPE_HEADER0_EVENTS		0x2
-#define SPE_HEADER0_EVENTS_MASK		0xf
-#define SPE_HEADER0_SOURCE		0x3
-#define SPE_HEADER0_SOURCE_MASK		0xf
-#define SPE_HEADER0_CONTEXT		0x24
-#define SPE_HEADER0_CONTEXT_MASK	0x3c
-#define SPE_HEADER0_OP_TYPE		0x8
-#define SPE_HEADER0_OP_TYPE_MASK	0x3c
-#define SPE_HEADER1_ALIGNMENT		0x0
-#define SPE_HEADER1_ADDRESS		0xb0 /* address packet (extended) */
-#define SPE_HEADER1_ADDRESS_MASK	0xf8
-#define SPE_HEADER1_COUNTER		0x98 /* counter packet (extended) */
-#define SPE_HEADER1_COUNTER_MASK	0xf8
-
 #if __BYTE_ORDER == __BIG_ENDIAN
 #define le16_to_cpu bswap_16
 #define le32_to_cpu bswap_32
@@ -70,27 +45,28 @@ const char *arm_spe_pkt_name(enum arm_spe_pkt_type type)
 	return arm_spe_packet_name[type];
 }
 
-/* return ARM SPE payload size from its encoding,
- * which is in bits 5:4 of the byte.
- * 00 : byte
- * 01 : halfword (2)
- * 10 : word (4)
- * 11 : doubleword (8)
+/*
+ * Extracts the field "sz" from header bits and converts to bytes:
+ *   00 : byte (1)
+ *   01 : halfword (2)
+ *   10 : word (4)
+ *   11 : doubleword (8)
  */
-static int payloadlen(unsigned char byte)
+static unsigned int arm_spe_payload_len(unsigned char hdr)
 {
-	return 1 << ((byte & 0x30) >> 4);
+	return 1U << ((hdr & GENMASK_ULL(5, 4)) >> 4);
 }
 
 static int arm_spe_get_payload(const unsigned char *buf, size_t len,
+			       unsigned char ext_hdr,
 			       struct arm_spe_pkt *packet)
 {
-	size_t payload_len = payloadlen(buf[0]);
+	size_t payload_len = arm_spe_payload_len(buf[ext_hdr]);
 
-	if (len < 1 + payload_len)
+	if (len < 1 + ext_hdr + payload_len)
 		return ARM_SPE_NEED_MORE_BYTES;
 
-	buf++;
+	buf += 1 + ext_hdr;
 
 	switch (payload_len) {
 	case 1: packet->payload = *(uint8_t *)buf; break;
@@ -100,7 +76,7 @@ static int arm_spe_get_payload(const unsigned char *buf, size_t len,
 	default: return ARM_SPE_BAD_PACKET;
 	}
 
-	return 1 + payload_len;
+	return 1 + ext_hdr + payload_len;
 }
 
 static int arm_spe_get_pad(struct arm_spe_pkt *packet)
@@ -131,127 +107,128 @@ static int arm_spe_get_timestamp(const unsigned char *buf, size_t len,
 				 struct arm_spe_pkt *packet)
 {
 	packet->type = ARM_SPE_TIMESTAMP;
-	return arm_spe_get_payload(buf, len, packet);
+	return arm_spe_get_payload(buf, len, 0, packet);
 }
 
 static int arm_spe_get_events(const unsigned char *buf, size_t len,
 			      struct arm_spe_pkt *packet)
 {
-	int ret = arm_spe_get_payload(buf, len, packet);
-
 	packet->type = ARM_SPE_EVENTS;
 
 	/* we use index to identify Events with a less number of
 	 * comparisons in arm_spe_pkt_desc(): E.g., the LLC-ACCESS,
-	 * LLC-REFILL, and REMOTE-ACCESS events are identified iff
+	 * LLC-REFILL, and REMOTE-ACCESS events are identified if
 	 * index > 1.
 	 */
-	packet->index = ret - 1;
+	packet->index = arm_spe_payload_len(buf[0]);
 
-	return ret;
+	return arm_spe_get_payload(buf, len, 0, packet);
 }
 
 static int arm_spe_get_data_source(const unsigned char *buf, size_t len,
 				   struct arm_spe_pkt *packet)
 {
 	packet->type = ARM_SPE_DATA_SOURCE;
-	return arm_spe_get_payload(buf, len, packet);
+	return arm_spe_get_payload(buf, len, 0, packet);
 }
 
 static int arm_spe_get_context(const unsigned char *buf, size_t len,
 			       struct arm_spe_pkt *packet)
 {
 	packet->type = ARM_SPE_CONTEXT;
-	packet->index = buf[0] & 0x3;
-
-	return arm_spe_get_payload(buf, len, packet);
+	packet->index = SPE_CTX_PKT_HDR_INDEX(buf[0]);
+	return arm_spe_get_payload(buf, len, 0, packet);
 }
 
 static int arm_spe_get_op_type(const unsigned char *buf, size_t len,
 			       struct arm_spe_pkt *packet)
 {
 	packet->type = ARM_SPE_OP_TYPE;
-	packet->index = buf[0] & 0x3;
-	return arm_spe_get_payload(buf, len, packet);
+	packet->index = SPE_OP_PKT_HDR_CLASS(buf[0]);
+	return arm_spe_get_payload(buf, len, 0, packet);
 }
 
 static int arm_spe_get_counter(const unsigned char *buf, size_t len,
 			       const unsigned char ext_hdr, struct arm_spe_pkt *packet)
 {
-	if (len < 2)
-		return ARM_SPE_NEED_MORE_BYTES;
-
 	packet->type = ARM_SPE_COUNTER;
+
 	if (ext_hdr)
-		packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7);
+		packet->index = SPE_HDR_EXTENDED_INDEX(buf[0], buf[1]);
 	else
-		packet->index = buf[0] & 0x7;
-
-	packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
+		packet->index = SPE_HDR_SHORT_INDEX(buf[0]);
 
-	return 1 + ext_hdr + 2;
+	return arm_spe_get_payload(buf, len, ext_hdr, packet);
 }
 
 static int arm_spe_get_addr(const unsigned char *buf, size_t len,
 			    const unsigned char ext_hdr, struct arm_spe_pkt *packet)
 {
-	if (len < 8)
-		return ARM_SPE_NEED_MORE_BYTES;
-
 	packet->type = ARM_SPE_ADDRESS;
+
 	if (ext_hdr)
-		packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7);
+		packet->index = SPE_HDR_EXTENDED_INDEX(buf[0], buf[1]);
 	else
-		packet->index = buf[0] & 0x7;
-
-	memcpy_le64(&packet->payload, buf + 1, 8);
+		packet->index = SPE_HDR_SHORT_INDEX(buf[0]);
 
-	return 1 + ext_hdr + 8;
+	return arm_spe_get_payload(buf, len, ext_hdr, packet);
 }
 
 static int arm_spe_do_get_packet(const unsigned char *buf, size_t len,
 				 struct arm_spe_pkt *packet)
 {
-	unsigned int byte;
+	unsigned int hdr;
+	unsigned char ext_hdr = 0;
 
 	memset(packet, 0, sizeof(struct arm_spe_pkt));
 
 	if (!len)
 		return ARM_SPE_NEED_MORE_BYTES;
 
-	byte = buf[0];
-	if (byte == SPE_HEADER0_PAD)
+	hdr = buf[0];
+
+	if (hdr == SPE_HEADER0_PAD)
 		return arm_spe_get_pad(packet);
-	else if (byte == SPE_HEADER0_END) /* no timestamp at end of record */
+
+	if (hdr == SPE_HEADER0_END) /* no timestamp at end of record */
 		return arm_spe_get_end(packet);
-	else if (byte & 0xc0 /* 0y11xxxxxx */) {
-		if (byte & 0x80) {
-			if ((byte & SPE_HEADER0_ADDRESS_MASK) == SPE_HEADER0_ADDRESS)
-				return arm_spe_get_addr(buf, len, 0, packet);
-			if ((byte & SPE_HEADER0_COUNTER_MASK) == SPE_HEADER0_COUNTER)
-				return arm_spe_get_counter(buf, len, 0, packet);
-		} else
-			if (byte == SPE_HEADER0_TIMESTAMP)
-				return arm_spe_get_timestamp(buf, len, packet);
-			else if ((byte & SPE_HEADER0_EVENTS_MASK) == SPE_HEADER0_EVENTS)
-				return arm_spe_get_events(buf, len, packet);
-			else if ((byte & SPE_HEADER0_SOURCE_MASK) == SPE_HEADER0_SOURCE)
-				return arm_spe_get_data_source(buf, len, packet);
-			else if ((byte & SPE_HEADER0_CONTEXT_MASK) == SPE_HEADER0_CONTEXT)
-				return arm_spe_get_context(buf, len, packet);
-			else if ((byte & SPE_HEADER0_OP_TYPE_MASK) == SPE_HEADER0_OP_TYPE)
-				return arm_spe_get_op_type(buf, len, packet);
-	} else if ((byte & 0xe0) == 0x20 /* 0y001xxxxx */) {
-		/* 16-bit header */
-		byte = buf[1];
-		if (byte == SPE_HEADER1_ALIGNMENT)
+
+	if (hdr == SPE_HEADER0_TIMESTAMP)
+		return arm_spe_get_timestamp(buf, len, packet);
+
+	if ((hdr & SPE_HEADER0_MASK1) == SPE_HEADER0_EVENTS)
+		return arm_spe_get_events(buf, len, packet);
+
+	if ((hdr & SPE_HEADER0_MASK1) == SPE_HEADER0_SOURCE)
+		return arm_spe_get_data_source(buf, len, packet);
+
+	if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_CONTEXT)
+		return arm_spe_get_context(buf, len, packet);
+
+	if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_OP_TYPE)
+		return arm_spe_get_op_type(buf, len, packet);
+
+	if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_EXTENDED) {
+		/* 16-bit extended format header */
+		ext_hdr = 1;
+
+		hdr = buf[1];
+		if (hdr == SPE_HEADER1_ALIGNMENT)
 			return arm_spe_get_alignment(buf, len, packet);
-		else if ((byte & SPE_HEADER1_ADDRESS_MASK) == SPE_HEADER1_ADDRESS)
-			return arm_spe_get_addr(buf, len, 1, packet);
-		else if ((byte & SPE_HEADER1_COUNTER_MASK) == SPE_HEADER1_COUNTER)
-			return arm_spe_get_counter(buf, len, 1, packet);
 	}
 
+	/*
+	 * The short format header's byte 0 or the extended format header's
+	 * byte 1 has been assigned to 'hdr', which uses the same encoding for
+	 * address packet and counter packet, so don't need to distinguish if
+	 * it's short format or extended format and handle in once.
+	 */
+	if ((hdr & SPE_HEADER0_MASK3) == SPE_HEADER0_ADDRESS)
+		return arm_spe_get_addr(buf, len, ext_hdr, packet);
+
+	if ((hdr & SPE_HEADER0_MASK3) == SPE_HEADER0_COUNTER)
+		return arm_spe_get_counter(buf, len, ext_hdr, packet);
+
 	return ARM_SPE_BAD_PACKET;
 }
 
@@ -271,192 +248,286 @@ int arm_spe_get_packet(const unsigned char *buf, size_t len,
 	return ret;
 }
 
+static int arm_spe_pkt_out_string(int *err, char **buf_p, size_t *blen,
+				  const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	/* Bail out if any error occurred */
+	if (err && *err)
+		return *err;
+
+	va_start(ap, fmt);
+	ret = vsnprintf(*buf_p, *blen, fmt, ap);
+	va_end(ap);
+
+	if (ret < 0) {
+		if (err && !*err)
+			*err = ret;
+
+	/*
+	 * A return value of *blen or more means that the output was
+	 * truncated and the buffer is overrun.
+	 */
+	} else if ((size_t)ret >= *blen) {
+		(*buf_p)[*blen - 1] = '\0';
+
+		/*
+		 * Set *err to 'ret' to avoid overflow if tries to
+		 * fill this buffer sequentially.
+		 */
+		if (err && !*err)
+			*err = ret;
+	} else {
+		*buf_p += ret;
+		*blen -= ret;
+	}
+
+	return ret;
+}
+
+static int arm_spe_pkt_desc_event(const struct arm_spe_pkt *packet,
+				  char *buf, size_t buf_len)
+{
+	u64 payload = packet->payload;
+	int err = 0;
+
+	arm_spe_pkt_out_string(&err, &buf, &buf_len, "EV");
+
+	if (payload & BIT(EV_EXCEPTION_GEN))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " EXCEPTION-GEN");
+	if (payload & BIT(EV_RETIRED))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " RETIRED");
+	if (payload & BIT(EV_L1D_ACCESS))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " L1D-ACCESS");
+	if (payload & BIT(EV_L1D_REFILL))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " L1D-REFILL");
+	if (payload & BIT(EV_TLB_ACCESS))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " TLB-ACCESS");
+	if (payload & BIT(EV_TLB_WALK))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " TLB-REFILL");
+	if (payload & BIT(EV_NOT_TAKEN))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " NOT-TAKEN");
+	if (payload & BIT(EV_MISPRED))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " MISPRED");
+	if (payload & BIT(EV_LLC_ACCESS))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " LLC-ACCESS");
+	if (payload & BIT(EV_LLC_MISS))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " LLC-REFILL");
+	if (payload & BIT(EV_REMOTE_ACCESS))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " REMOTE-ACCESS");
+	if (payload & BIT(EV_ALIGNMENT))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " ALIGNMENT");
+	if (payload & BIT(EV_PARTIAL_PREDICATE))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-PARTIAL-PRED");
+	if (payload & BIT(EV_EMPTY_PREDICATE))
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-EMPTY-PRED");
+
+	return err;
+}
+
+static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet,
+				    char *buf, size_t buf_len)
+{
+	u64 payload = packet->payload;
+	int err = 0;
+
+	switch (packet->index) {
+	case SPE_OP_PKT_HDR_CLASS_OTHER:
+		if (SPE_OP_PKT_IS_OTHER_SVE_OP(payload)) {
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, "SVE-OTHER");
+
+			/* SVE effective vector length */
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " EVLEN %d",
+					       SPE_OP_PKG_SVE_EVL(payload));
+
+			if (payload & SPE_OP_PKT_SVE_FP)
+				arm_spe_pkt_out_string(&err, &buf, &buf_len, " FP");
+			if (payload & SPE_OP_PKT_SVE_PRED)
+				arm_spe_pkt_out_string(&err, &buf, &buf_len, " PRED");
+		} else {
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, "OTHER");
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " %s",
+					       payload & SPE_OP_PKT_COND ?
+					       "COND-SELECT" : "INSN-OTHER");
+		}
+		break;
+	case SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC:
+		arm_spe_pkt_out_string(&err, &buf, &buf_len,
+				       payload & 0x1 ? "ST" : "LD");
+
+		if (SPE_OP_PKT_IS_LDST_ATOMIC(payload)) {
+			if (payload & SPE_OP_PKT_AT)
+				arm_spe_pkt_out_string(&err, &buf, &buf_len, " AT");
+			if (payload & SPE_OP_PKT_EXCL)
+				arm_spe_pkt_out_string(&err, &buf, &buf_len, " EXCL");
+			if (payload & SPE_OP_PKT_AR)
+				arm_spe_pkt_out_string(&err, &buf, &buf_len, " AR");
+		}
+
+		switch (SPE_OP_PKT_LDST_SUBCLASS_GET(payload)) {
+		case SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP:
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " SIMD-FP");
+			break;
+		case SPE_OP_PKT_LDST_SUBCLASS_GP_REG:
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " GP-REG");
+			break;
+		case SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG:
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " UNSPEC-REG");
+			break;
+		case SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG:
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " NV-SYSREG");
+			break;
+		default:
+			break;
+		}
+
+		if (SPE_OP_PKT_IS_LDST_SVE(payload)) {
+			/* SVE effective vector length */
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " EVLEN %d",
+					       SPE_OP_PKG_SVE_EVL(payload));
+
+			if (payload & SPE_OP_PKT_SVE_PRED)
+				arm_spe_pkt_out_string(&err, &buf, &buf_len, " PRED");
+			if (payload & SPE_OP_PKT_SVE_SG)
+				arm_spe_pkt_out_string(&err, &buf, &buf_len, " SG");
+		}
+		break;
+	case SPE_OP_PKT_HDR_CLASS_BR_ERET:
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, "B");
+
+		if (payload & SPE_OP_PKT_COND)
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " COND");
+
+		if (SPE_OP_PKT_IS_INDIRECT_BRANCH(payload))
+			arm_spe_pkt_out_string(&err, &buf, &buf_len, " IND");
+
+		break;
+	default:
+		/* Unknown index */
+		err = -1;
+		break;
+	}
+
+	return err;
+}
+
+static int arm_spe_pkt_desc_addr(const struct arm_spe_pkt *packet,
+				 char *buf, size_t buf_len)
+{
+	int ns, el, idx = packet->index;
+	int ch, pat;
+	u64 payload = packet->payload;
+	int err = 0;
+
+	switch (idx) {
+	case SPE_ADDR_PKT_HDR_INDEX_INS:
+	case SPE_ADDR_PKT_HDR_INDEX_BRANCH:
+		ns = !!SPE_ADDR_PKT_GET_NS(payload);
+		el = SPE_ADDR_PKT_GET_EL(payload);
+		payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload);
+		arm_spe_pkt_out_string(&err, &buf, &buf_len,
+				"%s 0x%llx el%d ns=%d",
+				(idx == 1) ? "TGT" : "PC", payload, el, ns);
+		break;
+	case SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT:
+		arm_spe_pkt_out_string(&err, &buf, &buf_len,
+				       "VA 0x%llx", payload);
+		break;
+	case SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS:
+		ns = !!SPE_ADDR_PKT_GET_NS(payload);
+		ch = !!SPE_ADDR_PKT_GET_CH(payload);
+		pat = SPE_ADDR_PKT_GET_PAT(payload);
+		payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload);
+		arm_spe_pkt_out_string(&err, &buf, &buf_len,
+				       "PA 0x%llx ns=%d ch=%d pat=%x",
+				       payload, ns, ch, pat);
+		break;
+	default:
+		/* Unknown index */
+		err = -1;
+		break;
+	}
+
+	return err;
+}
+
+static int arm_spe_pkt_desc_counter(const struct arm_spe_pkt *packet,
+				    char *buf, size_t buf_len)
+{
+	u64 payload = packet->payload;
+	const char *name = arm_spe_pkt_name(packet->type);
+	int err = 0;
+
+	arm_spe_pkt_out_string(&err, &buf, &buf_len, "%s %d ", name,
+			       (unsigned short)payload);
+
+	switch (packet->index) {
+	case SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT:
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, "TOT");
+		break;
+	case SPE_CNT_PKT_HDR_INDEX_ISSUE_LAT:
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, "ISSUE");
+		break;
+	case SPE_CNT_PKT_HDR_INDEX_TRANS_LAT:
+		arm_spe_pkt_out_string(&err, &buf, &buf_len, "XLAT");
+		break;
+	default:
+		break;
+	}
+
+	return err;
+}
+
 int arm_spe_pkt_desc(const struct arm_spe_pkt *packet, char *buf,
 		     size_t buf_len)
 {
-	int ret, ns, el, idx = packet->index;
+	int idx = packet->index;
 	unsigned long long payload = packet->payload;
 	const char *name = arm_spe_pkt_name(packet->type);
+	char *buf_orig = buf;
+	size_t blen = buf_len;
+	int err = 0;
 
 	switch (packet->type) {
 	case ARM_SPE_BAD:
 	case ARM_SPE_PAD:
 	case ARM_SPE_END:
-		return snprintf(buf, buf_len, "%s", name);
-	case ARM_SPE_EVENTS: {
-		size_t blen = buf_len;
-
-		ret = 0;
-		ret = snprintf(buf, buf_len, "EV");
-		buf += ret;
-		blen -= ret;
-		if (payload & 0x1) {
-			ret = snprintf(buf, buf_len, " EXCEPTION-GEN");
-			buf += ret;
-			blen -= ret;
-		}
-		if (payload & 0x2) {
-			ret = snprintf(buf, buf_len, " RETIRED");
-			buf += ret;
-			blen -= ret;
-		}
-		if (payload & 0x4) {
-			ret = snprintf(buf, buf_len, " L1D-ACCESS");
-			buf += ret;
-			blen -= ret;
-		}
-		if (payload & 0x8) {
-			ret = snprintf(buf, buf_len, " L1D-REFILL");
-			buf += ret;
-			blen -= ret;
-		}
-		if (payload & 0x10) {
-			ret = snprintf(buf, buf_len, " TLB-ACCESS");
-			buf += ret;
-			blen -= ret;
-		}
-		if (payload & 0x20) {
-			ret = snprintf(buf, buf_len, " TLB-REFILL");
-			buf += ret;
-			blen -= ret;
-		}
-		if (payload & 0x40) {
-			ret = snprintf(buf, buf_len, " NOT-TAKEN");
-			buf += ret;
-			blen -= ret;
-		}
-		if (payload & 0x80) {
-			ret = snprintf(buf, buf_len, " MISPRED");
-			buf += ret;
-			blen -= ret;
-		}
-		if (idx > 1) {
-			if (payload & 0x100) {
-				ret = snprintf(buf, buf_len, " LLC-ACCESS");
-				buf += ret;
-				blen -= ret;
-			}
-			if (payload & 0x200) {
-				ret = snprintf(buf, buf_len, " LLC-REFILL");
-				buf += ret;
-				blen -= ret;
-			}
-			if (payload & 0x400) {
-				ret = snprintf(buf, buf_len, " REMOTE-ACCESS");
-				buf += ret;
-				blen -= ret;
-			}
-		}
-		if (ret < 0)
-			return ret;
-		blen -= ret;
-		return buf_len - blen;
-	}
+		arm_spe_pkt_out_string(&err, &buf, &blen, "%s", name);
+		break;
+	case ARM_SPE_EVENTS:
+		err = arm_spe_pkt_desc_event(packet, buf, buf_len);
+		break;
 	case ARM_SPE_OP_TYPE:
-		switch (idx) {
-		case 0:	return snprintf(buf, buf_len, "%s", payload & 0x1 ?
-					"COND-SELECT" : "INSN-OTHER");
-		case 1:	{
-			size_t blen = buf_len;
-
-			if (payload & 0x1)
-				ret = snprintf(buf, buf_len, "ST");
-			else
-				ret = snprintf(buf, buf_len, "LD");
-			buf += ret;
-			blen -= ret;
-			if (payload & 0x2) {
-				if (payload & 0x4) {
-					ret = snprintf(buf, buf_len, " AT");
-					buf += ret;
-					blen -= ret;
-				}
-				if (payload & 0x8) {
-					ret = snprintf(buf, buf_len, " EXCL");
-					buf += ret;
-					blen -= ret;
-				}
-				if (payload & 0x10) {
-					ret = snprintf(buf, buf_len, " AR");
-					buf += ret;
-					blen -= ret;
-				}
-			} else if (payload & 0x4) {
-				ret = snprintf(buf, buf_len, " SIMD-FP");
-				buf += ret;
-				blen -= ret;
-			}
-			if (ret < 0)
-				return ret;
-			blen -= ret;
-			return buf_len - blen;
-		}
-		case 2:	{
-			size_t blen = buf_len;
-
-			ret = snprintf(buf, buf_len, "B");
-			buf += ret;
-			blen -= ret;
-			if (payload & 0x1) {
-				ret = snprintf(buf, buf_len, " COND");
-				buf += ret;
-				blen -= ret;
-			}
-			if (payload & 0x2) {
-				ret = snprintf(buf, buf_len, " IND");
-				buf += ret;
-				blen -= ret;
-			}
-			if (ret < 0)
-				return ret;
-			blen -= ret;
-			return buf_len - blen;
-			}
-		default: return 0;
-		}
+		err = arm_spe_pkt_desc_op_type(packet, buf, buf_len);
+		break;
 	case ARM_SPE_DATA_SOURCE:
 	case ARM_SPE_TIMESTAMP:
-		return snprintf(buf, buf_len, "%s %lld", name, payload);
+		arm_spe_pkt_out_string(&err, &buf, &blen, "%s %lld", name, payload);
+		break;
 	case ARM_SPE_ADDRESS:
-		switch (idx) {
-		case 0:
-		case 1: ns = !!(packet->payload & NS_FLAG);
-			el = (packet->payload & EL_FLAG) >> 61;
-			payload &= ~(0xffULL << 56);
-			return snprintf(buf, buf_len, "%s 0x%llx el%d ns=%d",
-				        (idx == 1) ? "TGT" : "PC", payload, el, ns);
-		case 2:	return snprintf(buf, buf_len, "VA 0x%llx", payload);
-		case 3:	ns = !!(packet->payload & NS_FLAG);
-			payload &= ~(0xffULL << 56);
-			return snprintf(buf, buf_len, "PA 0x%llx ns=%d",
-					payload, ns);
-		default: return 0;
-		}
+		err = arm_spe_pkt_desc_addr(packet, buf, buf_len);
+		break;
 	case ARM_SPE_CONTEXT:
-		return snprintf(buf, buf_len, "%s 0x%lx el%d", name,
-				(unsigned long)payload, idx + 1);
-	case ARM_SPE_COUNTER: {
-		size_t blen = buf_len;
-
-		ret = snprintf(buf, buf_len, "%s %d ", name,
-			       (unsigned short)payload);
-		buf += ret;
-		blen -= ret;
-		switch (idx) {
-		case 0:	ret = snprintf(buf, buf_len, "TOT"); break;
-		case 1:	ret = snprintf(buf, buf_len, "ISSUE"); break;
-		case 2:	ret = snprintf(buf, buf_len, "XLAT"); break;
-		default: ret = 0;
-		}
-		if (ret < 0)
-			return ret;
-		blen -= ret;
-		return buf_len - blen;
-	}
+		arm_spe_pkt_out_string(&err, &buf, &blen, "%s 0x%lx el%d",
+				       name, (unsigned long)payload, idx + 1);
+		break;
+	case ARM_SPE_COUNTER:
+		err = arm_spe_pkt_desc_counter(packet, buf, buf_len);
+		break;
 	default:
+		/* Unknown packet type */
+		err = -1;
 		break;
 	}
 
-	return snprintf(buf, buf_len, "%s 0x%llx (%d)",
-			name, payload, packet->index);
+	/* Output raw data if detect any error */
+	if (err) {
+		err = 0;
+		arm_spe_pkt_out_string(&err, &buf_orig, &buf_len, "%s 0x%llx (%d)",
+				       name, payload, packet->index);
+	}
+
+	return err;
 }
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h
index 4c870521b8eb..9b970e7bf1e2 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h
@@ -36,19 +36,115 @@ struct arm_spe_pkt {
 	uint64_t		payload;
 };
 
-#define SPE_ADDR_PKT_HDR_INDEX_INS		(0x0)
-#define SPE_ADDR_PKT_HDR_INDEX_BRANCH		(0x1)
-#define SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT	(0x2)
-#define SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS	(0x3)
-
-#define SPE_ADDR_PKT_NS				BIT(7)
-#define SPE_ADDR_PKT_CH				BIT(6)
-#define SPE_ADDR_PKT_EL_OFFSET			(5)
-#define SPE_ADDR_PKT_EL_MASK			(0x3 << SPE_ADDR_PKT_EL_OFFSET)
-#define SPE_ADDR_PKT_EL0			(0)
-#define SPE_ADDR_PKT_EL1			(1)
-#define SPE_ADDR_PKT_EL2			(2)
-#define SPE_ADDR_PKT_EL3			(3)
+/* Short header (HEADER0) and extended header (HEADER1) */
+#define SPE_HEADER0_PAD				0x0
+#define SPE_HEADER0_END				0x1
+#define SPE_HEADER0_TIMESTAMP			0x71
+/* Mask for event & data source */
+#define SPE_HEADER0_MASK1			(GENMASK_ULL(7, 6) | GENMASK_ULL(3, 0))
+#define SPE_HEADER0_EVENTS			0x42
+#define SPE_HEADER0_SOURCE			0x43
+/* Mask for context & operation */
+#define SPE_HEADER0_MASK2			GENMASK_ULL(7, 2)
+#define SPE_HEADER0_CONTEXT			0x64
+#define SPE_HEADER0_OP_TYPE			0x48
+/* Mask for extended format */
+#define SPE_HEADER0_EXTENDED			0x20
+/* Mask for address & counter */
+#define SPE_HEADER0_MASK3			GENMASK_ULL(7, 3)
+#define SPE_HEADER0_ADDRESS			0xb0
+#define SPE_HEADER0_COUNTER			0x98
+#define SPE_HEADER1_ALIGNMENT			0x0
+
+#define SPE_HDR_SHORT_INDEX(h)			((h) & GENMASK_ULL(2, 0))
+#define SPE_HDR_EXTENDED_INDEX(h0, h1)		(((h0) & GENMASK_ULL(1, 0)) << 3 | \
+						 SPE_HDR_SHORT_INDEX(h1))
+
+/* Address packet header */
+#define SPE_ADDR_PKT_HDR_INDEX_INS		0x0
+#define SPE_ADDR_PKT_HDR_INDEX_BRANCH		0x1
+#define SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT	0x2
+#define SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS	0x3
+
+/* Address packet payload */
+#define SPE_ADDR_PKT_ADDR_BYTE7_SHIFT		56
+#define SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(v)	((v) & GENMASK_ULL(55, 0))
+#define SPE_ADDR_PKT_ADDR_GET_BYTE_6(v)		(((v) & GENMASK_ULL(55, 48)) >> 48)
+
+#define SPE_ADDR_PKT_GET_NS(v)			(((v) & BIT_ULL(63)) >> 63)
+#define SPE_ADDR_PKT_GET_EL(v)			(((v) & GENMASK_ULL(62, 61)) >> 61)
+#define SPE_ADDR_PKT_GET_CH(v)			(((v) & BIT_ULL(62)) >> 62)
+#define SPE_ADDR_PKT_GET_PAT(v)			(((v) & GENMASK_ULL(59, 56)) >> 56)
+
+#define SPE_ADDR_PKT_EL0			0
+#define SPE_ADDR_PKT_EL1			1
+#define SPE_ADDR_PKT_EL2			2
+#define SPE_ADDR_PKT_EL3			3
+
+/* Context packet header */
+#define SPE_CTX_PKT_HDR_INDEX(h)		((h) & GENMASK_ULL(1, 0))
+
+/* Counter packet header */
+#define SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT		0x0
+#define SPE_CNT_PKT_HDR_INDEX_ISSUE_LAT		0x1
+#define SPE_CNT_PKT_HDR_INDEX_TRANS_LAT		0x2
+
+/* Event packet payload */
+enum arm_spe_events {
+	EV_EXCEPTION_GEN	= 0,
+	EV_RETIRED		= 1,
+	EV_L1D_ACCESS		= 2,
+	EV_L1D_REFILL		= 3,
+	EV_TLB_ACCESS		= 4,
+	EV_TLB_WALK		= 5,
+	EV_NOT_TAKEN		= 6,
+	EV_MISPRED		= 7,
+	EV_LLC_ACCESS		= 8,
+	EV_LLC_MISS		= 9,
+	EV_REMOTE_ACCESS	= 10,
+	EV_ALIGNMENT		= 11,
+	EV_PARTIAL_PREDICATE	= 17,
+	EV_EMPTY_PREDICATE	= 18,
+};
+
+/* Operation packet header */
+#define SPE_OP_PKT_HDR_CLASS(h)			((h) & GENMASK_ULL(1, 0))
+#define SPE_OP_PKT_HDR_CLASS_OTHER		0x0
+#define SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC	0x1
+#define SPE_OP_PKT_HDR_CLASS_BR_ERET		0x2
+
+#define SPE_OP_PKT_IS_OTHER_SVE_OP(v)		(((v) & (BIT(7) | BIT(3) | BIT(0))) == 0x8)
+
+#define SPE_OP_PKT_COND				BIT(0)
+
+#define SPE_OP_PKT_LDST_SUBCLASS_GET(v)		((v) & GENMASK_ULL(7, 1))
+#define SPE_OP_PKT_LDST_SUBCLASS_GP_REG		0x0
+#define SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP	0x4
+#define SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG	0x10
+#define SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG	0x30
+
+#define SPE_OP_PKT_IS_LDST_ATOMIC(v)		(((v) & (GENMASK_ULL(7, 5) | BIT(1))) == 0x2)
+
+#define SPE_OP_PKT_AR				BIT(4)
+#define SPE_OP_PKT_EXCL				BIT(3)
+#define SPE_OP_PKT_AT				BIT(2)
+#define SPE_OP_PKT_ST				BIT(0)
+
+#define SPE_OP_PKT_IS_LDST_SVE(v)		(((v) & (BIT(3) | BIT(1))) == 0x8)
+
+#define SPE_OP_PKT_SVE_SG			BIT(7)
+/*
+ * SVE effective vector length (EVL) is stored in byte 0 bits [6:4];
+ * the length is rounded up to a power of two and use 32 as one step,
+ * so EVL calculation is:
+ *
+ *   32 * (2 ^ bits [6:4]) = 32 << (bits [6:4])
+ */
+#define SPE_OP_PKG_SVE_EVL(v)			(32 << (((v) & GENMASK_ULL(6, 4)) >> 4))
+#define SPE_OP_PKT_SVE_PRED			BIT(2)
+#define SPE_OP_PKT_SVE_FP			BIT(1)
+
+#define SPE_OP_PKT_IS_INDIRECT_BRANCH(v)	(((v) & GENMASK_ULL(7, 1)) == 0x2)
 
 const char *arm_spe_pkt_name(enum arm_spe_pkt_type);
 
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 3882a5360ada..8901a1656a41 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -113,7 +113,7 @@ static void arm_spe_dump(struct arm_spe *spe __maybe_unused,
 		if (ret > 0) {
 			ret = arm_spe_pkt_desc(&packet, desc,
 					       ARM_SPE_PKT_DESC_MAX);
-			if (ret > 0)
+			if (!ret)
 				color_fprintf(stdout, color, " %s\n", desc);
 		} else {
 			color_fprintf(stdout, color, " Bad packet!\n");
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 42a85c86421d..a60878498139 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -62,9 +62,7 @@
  * Make a group from 'leader' to 'last', requiring that the events were not
  * already grouped to a different leader.
  */
-static int perf_evlist__regroup(struct evlist *evlist,
-				struct evsel *leader,
-				struct evsel *last)
+static int evlist__regroup(struct evlist *evlist, struct evsel *leader, struct evsel *last)
 {
 	struct evsel *evsel;
 	bool grp;
@@ -658,8 +656,7 @@ int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx)
 		if (evsel->core.attr.type == itr->pmu->type) {
 			if (evsel->disabled)
 				return 0;
-			return perf_evlist__enable_event_idx(itr->evlist, evsel,
-							     idx);
+			return evlist__enable_event_idx(itr->evlist, evsel, idx);
 		}
 	}
 	return -EINVAL;
@@ -776,7 +773,7 @@ no_opt:
 			evsel->core.attr.aux_sample_size = term->val.aux_sample_size;
 			/* If possible, group with the AUX event */
 			if (aux_evsel && evsel->core.attr.aux_sample_size)
-				perf_evlist__regroup(evlist, aux_evsel, evsel);
+				evlist__regroup(evlist, aux_evsel, evsel);
 		}
 	}
 
@@ -1017,7 +1014,7 @@ struct auxtrace_queue *auxtrace_queues__sample_queue(struct auxtrace_queues *que
 	if (!id)
 		return NULL;
 
-	sid = perf_evlist__id2sid(session->evlist, id);
+	sid = evlist__id2sid(session->evlist, id);
 	if (!sid)
 		return NULL;
 
@@ -1047,7 +1044,7 @@ int auxtrace_queues__add_sample(struct auxtrace_queues *queues,
 	if (!id)
 		return -EINVAL;
 
-	sid = perf_evlist__id2sid(session->evlist, id);
+	sid = evlist__id2sid(session->evlist, id);
 	if (!sid)
 		return -ENOENT;
 
@@ -1082,7 +1079,7 @@ static int auxtrace_queue_data_cb(struct perf_session *session,
 	if (!qd->samples || event->header.type != PERF_RECORD_SAMPLE)
 		return 0;
 
-	err = perf_evlist__parse_sample(session->evlist, event, &sample);
+	err = evlist__parse_sample(session->evlist, event, &sample);
 	if (err)
 		return err;
 
@@ -1333,6 +1330,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
 	synth_opts->flc = true;
 	synth_opts->llc = true;
 	synth_opts->tlb = true;
+	synth_opts->mem = true;
 	synth_opts->remote_access = true;
 
 	if (no_sample) {
@@ -1554,6 +1552,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 		case 'a':
 			synth_opts->remote_access = true;
 			break;
+		case 'M':
+			synth_opts->mem = true;
+			break;
 		case 'q':
 			synth_opts->quick += 1;
 			break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 951d2d14cf24..7e5c9e1552bd 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -88,6 +88,7 @@ enum itrace_period_type {
  * @llc: whether to synthesize last level cache events
  * @tlb: whether to synthesize TLB events
  * @remote_access: whether to synthesize remote access events
+ * @mem: whether to synthesize memory events
  * @callchain_sz: maximum callchain size
  * @last_branch_sz: branch context size
  * @period: 'instructions' events period
@@ -126,6 +127,7 @@ struct itrace_synth_opts {
 	bool			llc;
 	bool			tlb;
 	bool			remote_access;
+	bool			mem;
 	unsigned int		callchain_sz;
 	unsigned int		last_branch_sz;
 	unsigned long long	period;
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 3742511a08d1..57d58c81a5f8 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -526,7 +526,7 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
 	 */
 	attr.wakeup_watermark = 1;
 
-	return perf_evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
+	return evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
 }
 
 void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 0374adcb223c..9087f1bffd3d 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1058,12 +1058,11 @@ __bpf_map__config_event(struct bpf_map *map,
 			struct parse_events_term *term,
 			struct evlist *evlist)
 {
-	struct evsel *evsel;
 	const struct bpf_map_def *def;
 	struct bpf_map_op *op;
 	const char *map_name = bpf_map__name(map);
+	struct evsel *evsel = evlist__find_evsel_by_str(evlist, term->val.str);
 
-	evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str);
 	if (!evsel) {
 		pr_debug("Event (for '%s') '%s' doesn't exist\n",
 			 map_name, term->val.str);
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 25251d63164c..5d1c725cea29 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -8,6 +8,8 @@
 
 #include <linux/compiler.h>
 #include <linux/err.h>
+
+#ifdef HAVE_LIBBPF_SUPPORT
 #include <bpf/libbpf.h>
 
 enum bpf_loader_errno {
@@ -38,6 +40,7 @@ enum bpf_loader_errno {
 	BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG,	/* Index too large */
 	__BPF_LOADER_ERRNO__END,
 };
+#endif // HAVE_LIBBPF_SUPPORT
 
 struct evsel;
 struct evlist;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 6b410c3d52dc..02df36b30ac5 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -37,6 +37,7 @@
 
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
+#include <linux/string.h>
 #include <asm/bug.h>
 
 static bool no_buildid_cache;
@@ -260,10 +261,9 @@ static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso,
 	    "debug" : "elf"));
 }
 
-char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
-			     bool is_debug)
+char *__dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
+			       bool is_debug, bool is_kallsyms)
 {
-	bool is_kallsyms = dso__is_kallsyms((struct dso *)dso);
 	bool is_vdso = dso__is_vdso((struct dso *)dso);
 	char sbuild_id[SBUILD_ID_SIZE];
 	char *linkname;
@@ -292,6 +292,14 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
 	return bf;
 }
 
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
+			     bool is_debug)
+{
+	bool is_kallsyms = dso__is_kallsyms((struct dso *)dso);
+
+	return __dso__build_id_filename(dso, bf, size, is_debug, is_kallsyms);
+}
+
 #define dsos__for_each_with_build_id(pos, head)	\
 	list_for_each_entry(pos, head, node)	\
 		if (!pos->has_build_id)		\
@@ -663,24 +671,15 @@ out:
 	return realname;
 }
 
-int build_id_cache__add_s(const char *sbuild_id, const char *name,
-			  struct nsinfo *nsi, bool is_kallsyms, bool is_vdso)
+int
+build_id_cache__add(const char *sbuild_id, const char *name, const char *realname,
+		    struct nsinfo *nsi, bool is_kallsyms, bool is_vdso)
 {
 	const size_t size = PATH_MAX;
-	char *realname = NULL, *filename = NULL, *dir_name = NULL,
-	     *linkname = zalloc(size), *tmp;
+	char *filename = NULL, *dir_name = NULL, *linkname = zalloc(size), *tmp;
 	char *debugfile = NULL;
 	int err = -1;
 
-	if (!is_kallsyms) {
-		if (!is_vdso)
-			realname = nsinfo__realpath(name, nsi);
-		else
-			realname = realpath(name, NULL);
-		if (!realname)
-			goto out_free;
-	}
-
 	dir_name = build_id_cache__cachedir(sbuild_id, name, nsi, is_kallsyms,
 					    is_vdso);
 	if (!dir_name)
@@ -754,8 +753,25 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 	tmp = dir_name + strlen(buildid_dir) - 5;
 	memcpy(tmp, "../..", 5);
 
-	if (symlink(tmp, linkname) == 0)
+	if (symlink(tmp, linkname) == 0) {
+		err = 0;
+	} else if (errno == EEXIST) {
+		char path[PATH_MAX];
+		ssize_t len;
+
+		len = readlink(linkname, path, sizeof(path) - 1);
+		if (len <= 0) {
+			pr_err("Cant read link: %s\n", linkname);
+			goto out_free;
+		}
+		path[len] = '\0';
+
+		if (strcmp(tmp, path)) {
+			pr_debug("build <%s> already linked to %s\n",
+				 sbuild_id, linkname);
+		}
 		err = 0;
+	}
 
 	/* Update SDT cache : error is just warned */
 	if (realname &&
@@ -763,8 +779,6 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 		pr_debug4("Failed to update/scan SDT cache for %s\n", realname);
 
 out_free:
-	if (!is_kallsyms)
-		free(realname);
 	free(filename);
 	free(debugfile);
 	free(dir_name);
@@ -772,6 +786,29 @@ out_free:
 	return err;
 }
 
+int build_id_cache__add_s(const char *sbuild_id, const char *name,
+			  struct nsinfo *nsi, bool is_kallsyms, bool is_vdso)
+{
+	char *realname = NULL;
+	int err = -1;
+
+	if (!is_kallsyms) {
+		if (!is_vdso)
+			realname = nsinfo__realpath(name, nsi);
+		else
+			realname = realpath(name, NULL);
+		if (!realname)
+			goto out_free;
+	}
+
+	err = build_id_cache__add(sbuild_id, name, realname, nsi, is_kallsyms, is_vdso);
+
+out_free:
+	if (!is_kallsyms)
+		free(realname);
+	return err;
+}
+
 static int build_id_cache__add_b(const struct build_id *bid,
 				 const char *name, struct nsinfo *nsi,
 				 bool is_kallsyms, bool is_vdso)
@@ -834,12 +871,16 @@ out_free:
 	return err;
 }
 
-static int dso__cache_build_id(struct dso *dso, struct machine *machine)
+static int dso__cache_build_id(struct dso *dso, struct machine *machine,
+			       void *priv __maybe_unused)
 {
 	bool is_kallsyms = dso__is_kallsyms(dso);
 	bool is_vdso = dso__is_vdso(dso);
 	const char *name = dso->long_name;
 
+	if (!dso->has_build_id)
+		return 0;
+
 	if (dso__is_kcore(dso)) {
 		is_kallsyms = true;
 		name = machine->mmap_name;
@@ -848,43 +889,36 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine)
 				     is_kallsyms, is_vdso);
 }
 
-static int __dsos__cache_build_ids(struct list_head *head,
-				   struct machine *machine)
+static int
+machines__for_each_dso(struct machines *machines, machine__dso_t fn, void *priv)
 {
-	struct dso *pos;
-	int err = 0;
-
-	dsos__for_each_with_build_id(pos, head)
-		if (dso__cache_build_id(pos, machine))
-			err = -1;
+	int ret = machine__for_each_dso(&machines->host, fn, priv);
+	struct rb_node *nd;
 
-	return err;
-}
+	for (nd = rb_first_cached(&machines->guests); nd;
+	     nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
 
-static int machine__cache_build_ids(struct machine *machine)
-{
-	return __dsos__cache_build_ids(&machine->dsos.head, machine);
+		ret |= machine__for_each_dso(pos, fn, priv);
+	}
+	return ret ? -1 : 0;
 }
 
-int perf_session__cache_build_ids(struct perf_session *session)
+int __perf_session__cache_build_ids(struct perf_session *session,
+				    machine__dso_t fn, void *priv)
 {
-	struct rb_node *nd;
-	int ret;
-
 	if (no_buildid_cache)
 		return 0;
 
 	if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST)
 		return -1;
 
-	ret = machine__cache_build_ids(&session->machines.host);
+	return machines__for_each_dso(&session->machines, fn, priv) ?  -1 : 0;
+}
 
-	for (nd = rb_first_cached(&session->machines.guests); nd;
-	     nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret |= machine__cache_build_ids(pos);
-	}
-	return ret ? -1 : 0;
+int perf_session__cache_build_ids(struct perf_session *session)
+{
+	return __perf_session__cache_build_ids(session, dso__cache_build_id, NULL);
 }
 
 static bool machine__read_build_ids(struct machine *machine, bool with_hits)
@@ -912,3 +946,8 @@ void build_id__init(struct build_id *bid, const u8 *data, size_t size)
 	memcpy(bid->data, data, size);
 	bid->size = size;
 }
+
+bool build_id__is_defined(const struct build_id *bid)
+{
+	return bid && bid->size ? !!memchr_inv(bid->data, 0, bid->size) : false;
+}
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index f293f99d5dba..02613f4b2c29 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -5,6 +5,7 @@
 #define BUILD_ID_SIZE	20
 #define SBUILD_ID_SIZE	(BUILD_ID_SIZE * 2 + 1)
 
+#include "machine.h"
 #include "tool.h"
 #include <linux/types.h>
 
@@ -21,6 +22,7 @@ struct feat_fd;
 
 void build_id__init(struct build_id *bid, const u8 *data, size_t size);
 int build_id__sprintf(const struct build_id *build_id, char *bf);
+bool build_id__is_defined(const struct build_id *bid);
 int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id);
 int filename__sprintf_build_id(const char *pathname, char *sbuild_id);
 char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
@@ -28,6 +30,8 @@ char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
 			     bool is_debug);
+char *__dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
+			       bool is_debug, bool is_kallsyms);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct evsel *evsel,
@@ -43,6 +47,8 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
 int perf_session__write_buildid_table(struct perf_session *session,
 				      struct feat_fd *fd);
 int perf_session__cache_build_ids(struct perf_session *session);
+int __perf_session__cache_build_ids(struct perf_session *session,
+				    machine__dso_t fn, void *priv);
 
 char *build_id_cache__origname(const char *sbuild_id);
 char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size);
@@ -57,6 +63,8 @@ char *build_id_cache__complement(const char *incomplete_sbuild_id);
 int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi,
 				   struct strlist **result);
 bool build_id_cache__cached(const char *sbuild_id);
+int build_id_cache__add(const char *sbuild_id, const char *name, const char *realname,
+			struct nsinfo *nsi, bool is_kallsyms, bool is_vdso);
 int build_id_cache__add_s(const char *sbuild_id,
 			  const char *name, struct nsinfo *nsi,
 			  bool is_kallsyms, bool is_vdso);
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index b81324a13a2b..5dff7e489921 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -13,9 +13,19 @@
 #include <stdlib.h>
 #include <string.h>
 #include <api/fs/fs.h>
+#include <ftw.h>
+#include <regex.h>
 
 int nr_cgroups;
 
+/* used to match cgroup name with patterns */
+struct cgroup_name {
+	struct list_head list;
+	bool used;
+	char name[];
+};
+static LIST_HEAD(cgroup_list);
+
 static int open_cgroup(const char *name)
 {
 	char path[PATH_MAX + 1];
@@ -149,6 +159,137 @@ void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup)
 		evsel__set_default_cgroup(evsel, cgroup);
 }
 
+/* helper function for ftw() in match_cgroups and list_cgroups */
+static int add_cgroup_name(const char *fpath, const struct stat *sb __maybe_unused,
+			   int typeflag)
+{
+	struct cgroup_name *cn;
+
+	if (typeflag != FTW_D)
+		return 0;
+
+	cn = malloc(sizeof(*cn) + strlen(fpath) + 1);
+	if (cn == NULL)
+		return -1;
+
+	cn->used = false;
+	strcpy(cn->name, fpath);
+
+	list_add_tail(&cn->list, &cgroup_list);
+	return 0;
+}
+
+static void release_cgroup_list(void)
+{
+	struct cgroup_name *cn;
+
+	while (!list_empty(&cgroup_list)) {
+		cn = list_first_entry(&cgroup_list, struct cgroup_name, list);
+		list_del(&cn->list);
+		free(cn);
+	}
+}
+
+/* collect given cgroups only */
+static int list_cgroups(const char *str)
+{
+	const char *p, *e, *eos = str + strlen(str);
+	struct cgroup_name *cn;
+	char *s;
+
+	/* use given name as is - for testing purpose */
+	for (;;) {
+		p = strchr(str, ',');
+		e = p ? p : eos;
+
+		if (e - str) {
+			int ret;
+
+			s = strndup(str, e - str);
+			if (!s)
+				return -1;
+			/* pretend if it's added by ftw() */
+			ret = add_cgroup_name(s, NULL, FTW_D);
+			free(s);
+			if (ret)
+				return -1;
+		} else {
+			if (add_cgroup_name("", NULL, FTW_D) < 0)
+				return -1;
+		}
+
+		if (!p)
+			break;
+		str = p+1;
+	}
+
+	/* these groups will be used */
+	list_for_each_entry(cn, &cgroup_list, list)
+		cn->used = true;
+
+	return 0;
+}
+
+/* collect all cgroups first and then match with the pattern */
+static int match_cgroups(const char *str)
+{
+	char mnt[PATH_MAX];
+	const char *p, *e, *eos = str + strlen(str);
+	struct cgroup_name *cn;
+	regex_t reg;
+	int prefix_len;
+	char *s;
+
+	if (cgroupfs_find_mountpoint(mnt, sizeof(mnt), "perf_event"))
+		return -1;
+
+	/* cgroup_name will have a full path, skip the root directory */
+	prefix_len = strlen(mnt);
+
+	/* collect all cgroups in the cgroup_list */
+	if (ftw(mnt, add_cgroup_name, 20) < 0)
+		return -1;
+
+	for (;;) {
+		p = strchr(str, ',');
+		e = p ? p : eos;
+
+		/* allow empty cgroups, i.e., skip */
+		if (e - str) {
+			/* termination added */
+			s = strndup(str, e - str);
+			if (!s)
+				return -1;
+			if (regcomp(&reg, s, REG_NOSUB)) {
+				free(s);
+				return -1;
+			}
+
+			/* check cgroup name with the pattern */
+			list_for_each_entry(cn, &cgroup_list, list) {
+				char *name = cn->name + prefix_len;
+
+				if (name[0] == '/' && name[1])
+					name++;
+				if (!regexec(&reg, name, 0, NULL, 0))
+					cn->used = true;
+			}
+			regfree(&reg);
+			free(s);
+		} else {
+			/* first entry to root cgroup */
+			cn = list_first_entry(&cgroup_list, struct cgroup_name,
+					      list);
+			cn->used = true;
+		}
+
+		if (!p)
+			break;
+		str = p+1;
+	}
+	return prefix_len;
+}
+
 int parse_cgroups(const struct option *opt, const char *str,
 		  int unset __maybe_unused)
 {
@@ -201,6 +342,11 @@ int parse_cgroups(const struct option *opt, const char *str,
 	return 0;
 }
 
+static bool has_pattern_string(const char *str)
+{
+	return !!strpbrk(str, "{}[]()|*+?^$");
+}
+
 int evlist__expand_cgroup(struct evlist *evlist, const char *str,
 			  struct rblist *metric_events, bool open_cgroup)
 {
@@ -208,8 +354,9 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str,
 	struct evsel *pos, *evsel, *leader;
 	struct rblist orig_metric_events;
 	struct cgroup *cgrp = NULL;
-	const char *p, *e, *eos = str + strlen(str);
+	struct cgroup_name *cn;
 	int ret = -1;
+	int prefix_len;
 
 	if (evlist->core.nr_entries == 0) {
 		fprintf(stderr, "must define events before cgroups\n");
@@ -224,7 +371,7 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str,
 	}
 
 	/* save original events and init evlist */
-	perf_evlist__splice_list_tail(orig_list, &evlist->core.entries);
+	evlist__splice_list_tail(orig_list, &evlist->core.entries);
 	evlist->core.nr_entries = 0;
 
 	if (metric_events) {
@@ -234,24 +381,27 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str,
 		rblist__init(&orig_metric_events);
 	}
 
-	for (;;) {
-		p = strchr(str, ',');
-		e = p ? p : eos;
+	if (has_pattern_string(str))
+		prefix_len = match_cgroups(str);
+	else
+		prefix_len = list_cgroups(str);
 
-		/* allow empty cgroups, i.e., skip */
-		if (e - str) {
-			/* termination added */
-			char *name = strndup(str, e - str);
-			if (!name)
-				goto out_err;
+	if (prefix_len < 0)
+		goto out_err;
 
-			cgrp = cgroup__new(name, open_cgroup);
-			free(name);
-			if (cgrp == NULL)
-				goto out_err;
-		} else {
-			cgrp = NULL;
-		}
+	list_for_each_entry(cn, &cgroup_list, list) {
+		char *name;
+
+		if (!cn->used)
+			continue;
+
+		/* cgroup_name might have a full path, skip the prefix */
+		name = cn->name + prefix_len;
+		if (name[0] == '/' && name[1])
+			name++;
+		cgrp = cgroup__new(name, open_cgroup);
+		if (cgrp == NULL)
+			goto out_err;
 
 		leader = NULL;
 		evlist__for_each_entry(orig_list, pos) {
@@ -277,23 +427,25 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str,
 			if (metricgroup__copy_metric_events(tmp_list, cgrp,
 							    metric_events,
 							    &orig_metric_events) < 0)
-				break;
+				goto out_err;
 		}
 
-		perf_evlist__splice_list_tail(evlist, &tmp_list->core.entries);
+		evlist__splice_list_tail(evlist, &tmp_list->core.entries);
 		tmp_list->core.nr_entries = 0;
+	}
 
-		if (!p) {
-			ret = 0;
-			break;
-		}
-		str = p+1;
+	if (list_empty(&evlist->core.entries)) {
+		fprintf(stderr, "no cgroup matched: %s\n", str);
+		goto out_err;
 	}
 
+	ret = 0;
+
 out_err:
 	evlist__delete(orig_list);
 	evlist__delete(tmp_list);
 	rblist__exit(&orig_metric_events);
+	release_cgroup_list();
 
 	return ret;
 }
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index dc5c5e6fc502..87d3eca9b872 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -95,6 +95,23 @@ struct perf_cpu_map *perf_cpu_map__empty_new(int nr)
 	return cpus;
 }
 
+struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr)
+{
+	struct cpu_aggr_map *cpus = malloc(sizeof(*cpus) + sizeof(struct aggr_cpu_id) * nr);
+
+	if (cpus != NULL) {
+		int i;
+
+		cpus->nr = nr;
+		for (i = 0; i < nr; i++)
+			cpus->map[i] = cpu_map__empty_aggr_cpu_id();
+
+		refcount_set(&cpus->refcnt, 1);
+	}
+
+	return cpus;
+}
+
 static int cpu__get_topology_int(int cpu, const char *name, int *value)
 {
 	char path[PATH_MAX];
@@ -111,40 +128,57 @@ int cpu_map__get_socket_id(int cpu)
 	return ret ?: value;
 }
 
-int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data __maybe_unused)
+struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx,
+					void *data __maybe_unused)
 {
 	int cpu;
+	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
 
 	if (idx > map->nr)
-		return -1;
+		return id;
 
 	cpu = map->map[idx];
 
-	return cpu_map__get_socket_id(cpu);
+	id.socket = cpu_map__get_socket_id(cpu);
+	return id;
 }
 
-static int cmp_ids(const void *a, const void *b)
+static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer)
 {
-	return *(int *)a - *(int *)b;
+	struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer;
+	struct aggr_cpu_id *b = (struct aggr_cpu_id *)b_pointer;
+
+	if (a->node != b->node)
+		return a->node - b->node;
+	else if (a->socket != b->socket)
+		return a->socket - b->socket;
+	else if (a->die != b->die)
+		return a->die - b->die;
+	else if (a->core != b->core)
+		return a->core - b->core;
+	else
+		return a->thread - b->thread;
 }
 
-int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res,
-		       int (*f)(struct perf_cpu_map *map, int cpu, void *data),
+int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res,
+		       struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data),
 		       void *data)
 {
-	struct perf_cpu_map *c;
 	int nr = cpus->nr;
-	int cpu, s1, s2;
+	struct cpu_aggr_map *c = cpu_aggr_map__empty_new(nr);
+	int cpu, s2;
+	struct aggr_cpu_id s1;
 
-	/* allocate as much as possible */
-	c = calloc(1, sizeof(*c) + nr * sizeof(int));
 	if (!c)
 		return -1;
 
+	/* Reset size as it may only be partially filled */
+	c->nr = 0;
+
 	for (cpu = 0; cpu < nr; cpu++) {
 		s1 = f(cpus, cpu, data);
 		for (s2 = 0; s2 < c->nr; s2++) {
-			if (s1 == c->map[s2])
+			if (cpu_map__compare_aggr_cpu_id(s1, c->map[s2]))
 				break;
 		}
 		if (s2 == c->nr) {
@@ -153,9 +187,8 @@ int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res,
 		}
 	}
 	/* ensure we process id in increasing order */
-	qsort(c->map, c->nr, sizeof(int), cmp_ids);
+	qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), cmp_aggr_cpu_id);
 
-	refcount_set(&c->refcnt, 1);
 	*res = c;
 	return 0;
 }
@@ -167,37 +200,32 @@ int cpu_map__get_die_id(int cpu)
 	return ret ?: value;
 }
 
-int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data)
+struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data)
 {
-	int cpu, die_id, s;
+	int cpu, die;
+	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
 
 	if (idx > map->nr)
-		return -1;
+		return id;
 
 	cpu = map->map[idx];
 
-	die_id = cpu_map__get_die_id(cpu);
+	die = cpu_map__get_die_id(cpu);
 	/* There is no die_id on legacy system. */
-	if (die_id == -1)
-		die_id = 0;
-
-	s = cpu_map__get_socket(map, idx, data);
-	if (s == -1)
-		return -1;
+	if (die == -1)
+		die = 0;
 
 	/*
-	 * Encode socket in bit range 15:8
-	 * die_id is relative to socket, and
-	 * we need a global id. So we combine
-	 * socket + die id
+	 * die_id is relative to socket, so start
+	 * with the socket ID and then add die to
+	 * make a unique ID.
 	 */
-	if (WARN_ONCE(die_id >> 8, "The die id number is too big.\n"))
-		return -1;
-
-	if (WARN_ONCE(s >> 8, "The socket id number is too big.\n"))
-		return -1;
+	id = cpu_map__get_socket(map, idx, data);
+	if (cpu_map__aggr_cpu_id_is_empty(id))
+		return id;
 
-	return (s << 8) | (die_id & 0xff);
+	id.die = die;
+	return id;
 }
 
 int cpu_map__get_core_id(int cpu)
@@ -211,59 +239,58 @@ int cpu_map__get_node_id(int cpu)
 	return cpu__get_node(cpu);
 }
 
-int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data)
+struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data)
 {
-	int cpu, s_die;
+	int cpu;
+	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
 
 	if (idx > map->nr)
-		return -1;
+		return id;
 
 	cpu = map->map[idx];
 
 	cpu = cpu_map__get_core_id(cpu);
 
-	/* s_die is the combination of socket + die id */
-	s_die = cpu_map__get_die(map, idx, data);
-	if (s_die == -1)
-		return -1;
+	/* cpu_map__get_die returns a struct with socket and die set*/
+	id = cpu_map__get_die(map, idx, data);
+	if (cpu_map__aggr_cpu_id_is_empty(id))
+		return id;
 
 	/*
-	 * encode socket in bit range 31:24
-	 * encode die id in bit range 23:16
-	 * core_id is relative to socket and die,
-	 * we need a global id. So we combine
-	 * socket + die id + core id
+	 * core_id is relative to socket and die, we need a global id.
+	 * So we combine the result from cpu_map__get_die with the core id
 	 */
-	if (WARN_ONCE(cpu >> 16, "The core id number is too big.\n"))
-		return -1;
-
-	return (s_die << 16) | (cpu & 0xffff);
+	id.core = cpu;
+	return id;
 }
 
-int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused)
+struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused)
 {
+	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+
 	if (idx < 0 || idx >= map->nr)
-		return -1;
+		return id;
 
-	return cpu_map__get_node_id(map->map[idx]);
+	id.node = cpu_map__get_node_id(map->map[idx]);
+	return id;
 }
 
-int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp)
+int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp)
 {
 	return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL);
 }
 
-int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep)
+int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep)
 {
 	return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL);
 }
 
-int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep)
+int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep)
 {
 	return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL);
 }
 
-int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **numap)
+int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **numap)
 {
 	return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL);
 }
@@ -586,3 +613,33 @@ const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */
 
 	return online;
 }
+
+bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b)
+{
+	return a.thread == b.thread &&
+		a.node == b.node &&
+		a.socket == b.socket &&
+		a.die == b.die &&
+		a.core == b.core;
+}
+
+bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a)
+{
+	return a.thread == -1 &&
+		a.node == -1 &&
+		a.socket == -1 &&
+		a.die == -1 &&
+		a.core == -1;
+}
+
+struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void)
+{
+	struct aggr_cpu_id ret = {
+		.thread = -1,
+		.node = -1,
+		.socket = -1,
+		.die = -1,
+		.core = -1
+	};
+	return ret;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 3a442f021468..a27eeaf086e8 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -7,25 +7,41 @@
 #include <internal/cpumap.h>
 #include <perf/cpumap.h>
 
+struct aggr_cpu_id {
+	int thread;
+	int node;
+	int socket;
+	int die;
+	int core;
+};
+
+struct cpu_aggr_map {
+	refcount_t refcnt;
+	int nr;
+	struct aggr_cpu_id map[];
+};
+
 struct perf_record_cpu_map_data;
 
 struct perf_cpu_map *perf_cpu_map__empty_new(int nr);
+struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr);
+
 struct perf_cpu_map *cpu_map__new_data(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);
 int cpu_map__get_socket_id(int cpu);
-int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data);
+struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data);
 int cpu_map__get_die_id(int cpu);
-int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data);
+struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data);
 int cpu_map__get_core_id(int cpu);
-int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data);
+struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data);
 int cpu_map__get_node_id(int cpu);
-int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp);
-int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep);
-int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep);
-int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **nodep);
+struct aggr_cpu_id  cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data);
+int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp);
+int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep);
+int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep);
+int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **nodep);
 const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */
 
 static inline int cpu_map__socket(struct perf_cpu_map *sock, int s)
@@ -35,21 +51,6 @@ static inline int cpu_map__socket(struct perf_cpu_map *sock, int s)
 	return sock->map[s];
 }
 
-static inline int cpu_map__id_to_socket(int id)
-{
-	return id >> 24;
-}
-
-static inline int cpu_map__id_to_die(int id)
-{
-	return (id >> 16) & 0xff;
-}
-
-static inline int cpu_map__id_to_cpu(int id)
-{
-	return id & 0xffff;
-}
-
 int cpu__setup_cpunode_map(void);
 
 int cpu__max_node(void);
@@ -57,11 +58,15 @@ int cpu__max_cpu(void);
 int cpu__max_present_cpu(void);
 int cpu__get_node(int cpu);
 
-int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res,
-		       int (*f)(struct perf_cpu_map *map, int cpu, void *data),
+int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res,
+		       struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data),
 		       void *data);
 
 int cpu_map__cpu(struct perf_cpu_map *cpus, int idx);
 bool cpu_map__has(struct perf_cpu_map *cpus, int cpu);
 
+bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b);
+bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a);
+struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void);
+
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index c47aa34fdc0a..f29af4fc3d09 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -174,8 +174,21 @@ static bool check_pipe(struct perf_data *data)
 			is_pipe = true;
 	}
 
-	if (is_pipe)
-		data->file.fd = fd;
+	if (is_pipe) {
+		if (data->use_stdio) {
+			const char *mode;
+
+			mode = perf_data__is_read(data) ? "r" : "w";
+			data->file.fptr = fdopen(fd, mode);
+
+			if (data->file.fptr == NULL) {
+				data->file.fd = fd;
+				data->use_stdio = false;
+			}
+		} else {
+			data->file.fd = fd;
+		}
+	}
 
 	return data->is_pipe = is_pipe;
 }
@@ -334,6 +347,9 @@ int perf_data__open(struct perf_data *data)
 	if (check_pipe(data))
 		return 0;
 
+	/* currently it allows stdio for pipe only */
+	data->use_stdio = false;
+
 	if (!data->path)
 		data->path = "perf.data";
 
@@ -353,7 +369,21 @@ void perf_data__close(struct perf_data *data)
 		perf_data__close_dir(data);
 
 	zfree(&data->file.path);
-	close(data->file.fd);
+
+	if (data->use_stdio)
+		fclose(data->file.fptr);
+	else
+		close(data->file.fd);
+}
+
+ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size)
+{
+	if (data->use_stdio) {
+		if (fread(buf, size, 1, data->file.fptr) == 1)
+			return size;
+		return feof(data->file.fptr) ? 0 : -1;
+	}
+	return readn(data->file.fd, buf, size);
 }
 
 ssize_t perf_data_file__write(struct perf_data_file *file,
@@ -365,6 +395,11 @@ ssize_t perf_data_file__write(struct perf_data_file *file,
 ssize_t perf_data__write(struct perf_data *data,
 			      void *buf, size_t size)
 {
+	if (data->use_stdio) {
+		if (fwrite(buf, size, 1, data->file.fptr) == 1)
+			return size;
+		return -1;
+	}
 	return perf_data_file__write(&data->file, buf, size);
 }
 
@@ -457,3 +492,22 @@ char *perf_data__kallsyms_name(struct perf_data *data)
 
 	return kallsyms_name;
 }
+
+bool is_perf_data(const char *path)
+{
+	bool ret = false;
+	FILE *file;
+	u64 magic;
+
+	file = fopen(path, "r");
+	if (!file)
+		return false;
+
+	if (fread(&magic, 1, 8, file) < 8)
+		goto out;
+
+	ret = is_perf_magic(magic);
+out:
+	fclose(file);
+	return ret;
+}
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 75947ef6bc17..62a3e66fbee8 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -2,6 +2,7 @@
 #ifndef __PERF_DATA_H
 #define __PERF_DATA_H
 
+#include <stdio.h>
 #include <stdbool.h>
 
 enum perf_data_mode {
@@ -16,7 +17,10 @@ enum perf_dir_version {
 
 struct perf_data_file {
 	char		*path;
-	int		 fd;
+	union {
+		int	 fd;
+		FILE	*fptr;
+	};
 	unsigned long	 size;
 };
 
@@ -26,6 +30,7 @@ struct perf_data {
 	bool			 is_pipe;
 	bool			 is_dir;
 	bool			 force;
+	bool			 use_stdio;
 	enum perf_data_mode	 mode;
 
 	struct {
@@ -62,11 +67,15 @@ static inline bool perf_data__is_single_file(struct perf_data *data)
 
 static inline int perf_data__fd(struct perf_data *data)
 {
+	if (data->use_stdio)
+		return fileno(data->file.fptr);
+
 	return data->file.fd;
 }
 
 int perf_data__open(struct perf_data *data);
 void perf_data__close(struct perf_data *data);
+ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size);
 ssize_t perf_data__write(struct perf_data *data,
 			      void *buf, size_t size);
 ssize_t perf_data_file__write(struct perf_data_file *file,
@@ -89,4 +98,5 @@ int perf_data__update_dir(struct perf_data *data);
 unsigned long perf_data__size(struct perf_data *data);
 int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz);
 char *perf_data__kallsyms_name(struct perf_data *data);
+bool is_perf_data(const char *path);
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 5cda5565777a..50fd6a4be4e0 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -30,6 +30,12 @@ bool dump_trace = false, quiet = false;
 int debug_ordered_events;
 static int redirect_to_stderr;
 int debug_data_convert;
+static FILE *debug_file;
+
+void debug_set_file(FILE *file)
+{
+	debug_file = file;
+}
 
 int veprintf(int level, int var, const char *fmt, va_list args)
 {
@@ -39,7 +45,7 @@ int veprintf(int level, int var, const char *fmt, va_list args)
 		if (use_browser >= 1 && !redirect_to_stderr)
 			ui_helpline__vshow(fmt, args);
 		else
-			ret = vfprintf(stderr, fmt, args);
+			ret = vfprintf(debug_file, fmt, args);
 	}
 
 	return ret;
@@ -227,6 +233,7 @@ DEBUG_WRAPPER(debug, 1);
 
 void perf_debug_setup(void)
 {
+	debug_set_file(stderr);
 	libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper);
 }
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index f1734abd98dd..43f712295645 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -5,6 +5,7 @@
 
 #include <stdarg.h>
 #include <stdbool.h>
+#include <stdio.h>
 #include <linux/compiler.h>
 
 extern int verbose;
@@ -62,6 +63,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5)
 int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
+void debug_set_file(FILE *file);
 void perf_debug_setup(void);
 int perf_quiet_option(void);
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 55c11e854fe4..d786cf6b0cfa 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -11,8 +11,10 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <stdlib.h>
+#ifdef HAVE_LIBBPF_SUPPORT
 #include <bpf/libbpf.h>
 #include "bpf-event.h"
+#endif
 #include "compress.h"
 #include "env.h"
 #include "namespaces.h"
@@ -277,18 +279,12 @@ bool dso__needs_decompress(struct dso *dso)
 		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 }
 
-static int decompress_kmodule(struct dso *dso, const char *name,
-			      char *pathname, size_t len)
+int filename__decompress(const char *name, char *pathname,
+			 size_t len, int comp, int *err)
 {
 	char tmpbuf[] = KMOD_DECOMP_NAME;
 	int fd = -1;
 
-	if (!dso__needs_decompress(dso))
-		return -1;
-
-	if (dso->comp == COMP_ID__NONE)
-		return -1;
-
 	/*
 	 * We have proper compression id for DSO and yet the file
 	 * behind the 'name' can still be plain uncompressed object.
@@ -302,17 +298,17 @@ static int decompress_kmodule(struct dso *dso, const char *name,
 	 * To keep this transparent, we detect this and return the file
 	 * descriptor to the uncompressed file.
 	 */
-	if (!compressions[dso->comp].is_compressed(name))
+	if (!compressions[comp].is_compressed(name))
 		return open(name, O_RDONLY);
 
 	fd = mkstemp(tmpbuf);
 	if (fd < 0) {
-		dso->load_errno = errno;
+		*err = errno;
 		return -1;
 	}
 
-	if (compressions[dso->comp].decompress(name, fd)) {
-		dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
+	if (compressions[comp].decompress(name, fd)) {
+		*err = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
 		close(fd);
 		fd = -1;
 	}
@@ -326,6 +322,19 @@ static int decompress_kmodule(struct dso *dso, const char *name,
 	return fd;
 }
 
+static int decompress_kmodule(struct dso *dso, const char *name,
+			      char *pathname, size_t len)
+{
+	if (!dso__needs_decompress(dso))
+		return -1;
+
+	if (dso->comp == COMP_ID__NONE)
+		return -1;
+
+	return filename__decompress(name, pathname, len, dso->comp,
+				    &dso->load_errno);
+}
+
 int dso__decompress_kmodule_fd(struct dso *dso, const char *name)
 {
 	return decompress_kmodule(dso, name, NULL, 0);
@@ -728,6 +737,7 @@ bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 	return false;
 }
 
+#ifdef HAVE_LIBBPF_SUPPORT
 static ssize_t bpf_read(struct dso *dso, u64 offset, char *data)
 {
 	struct bpf_prog_info_node *node;
@@ -765,6 +775,7 @@ static int bpf_size(struct dso *dso)
 	dso->data.file_size = node->info_linear->info.jited_prog_len;
 	return 0;
 }
+#endif // HAVE_LIBBPF_SUPPORT
 
 static void
 dso_cache__free(struct dso *dso)
@@ -894,10 +905,12 @@ static struct dso_cache *dso_cache__populate(struct dso *dso,
 		*ret = -ENOMEM;
 		return NULL;
 	}
-
+#ifdef HAVE_LIBBPF_SUPPORT
 	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
 		*ret = bpf_read(dso, cache_offset, cache->data);
-	else if (dso->binary_type == DSO_BINARY_TYPE__OOL)
+	else
+#endif
+	if (dso->binary_type == DSO_BINARY_TYPE__OOL)
 		*ret = DSO__DATA_CACHE_SIZE;
 	else
 		*ret = file_read(dso, machine, cache_offset, cache->data);
@@ -1018,10 +1031,10 @@ int dso__data_file_size(struct dso *dso, struct machine *machine)
 
 	if (dso->data.status == DSO_DATA_STATUS_ERROR)
 		return -1;
-
+#ifdef HAVE_LIBBPF_SUPPORT
 	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
 		return bpf_size(dso);
-
+#endif
 	return file_size(dso, machine);
 }
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index d8cb4f5680a4..cd2fe64a3c5d 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -274,6 +274,8 @@ bool dso__needs_decompress(struct dso *dso);
 int dso__decompress_kmodule_fd(struct dso *dso, const char *name);
 int dso__decompress_kmodule_path(struct dso *dso, const char *name,
 				 char *pathname, size_t len);
+int filename__decompress(const char *name, char *pathname,
+			 size_t len, int comp, int *err);
 
 #define KMOD_DECOMP_NAME  "/tmp/perf-kmod-XXXXXX"
 #define KMOD_DECOMP_LEN   sizeof(KMOD_DECOMP_NAME)
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index fadc59708ece..9130f6fad8d5 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -5,16 +5,18 @@
 #include "util/header.h"
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
-#include "bpf-event.h"
 #include "cgroup.h"
 #include <errno.h>
 #include <sys/utsname.h>
-#include <bpf/libbpf.h>
 #include <stdlib.h>
 #include <string.h>
 
 struct perf_env perf_env;
 
+#ifdef HAVE_LIBBPF_SUPPORT
+#include "bpf-event.h"
+#include <bpf/libbpf.h>
+
 void perf_env__insert_bpf_prog_info(struct perf_env *env,
 				    struct bpf_prog_info_node *info_node)
 {
@@ -163,6 +165,11 @@ static void perf_env__purge_bpf(struct perf_env *env)
 
 	up_write(&env->bpf_progs.lock);
 }
+#else // HAVE_LIBBPF_SUPPORT
+static void perf_env__purge_bpf(struct perf_env *env __maybe_unused)
+{
+}
+#endif // HAVE_LIBBPF_SUPPORT
 
 void perf_env__exit(struct perf_env *env)
 {
@@ -197,11 +204,13 @@ void perf_env__exit(struct perf_env *env)
 	zfree(&env->memory_nodes);
 }
 
-void perf_env__init(struct perf_env *env)
+void perf_env__init(struct perf_env *env __maybe_unused)
 {
+#ifdef HAVE_LIBBPF_SUPPORT
 	env->bpf_progs.infos = RB_ROOT;
 	env->bpf_progs.btfs = RB_ROOT;
 	init_rwsem(&env->bpf_progs.lock);
+#endif
 }
 
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index a12972652006..ca249bf5e984 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -77,7 +77,7 @@ struct perf_env {
 	struct numa_node	*numa_nodes;
 	struct memory_node	*memory_nodes;
 	unsigned long long	 memory_bsize;
-
+#ifdef HAVE_LIBBPF_SUPPORT
 	/*
 	 * bpf_info_lock protects bpf rbtrees. This is needed because the
 	 * trees are accessed by different threads in perf-top
@@ -89,7 +89,7 @@ struct perf_env {
 		struct rb_root		btfs;
 		u32			btfs_cnt;
 	} bpf_progs;
-
+#endif // HAVE_LIBBPF_SUPPORT
 	/* same reason as above (for perf-top) */
 	struct {
 		struct rw_semaphore	lock;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index b828b99176f4..ff403ea578e1 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -135,6 +135,7 @@ struct perf_sample {
 	u32 raw_size;
 	u64 data_src;
 	u64 phys_addr;
+	u64 data_page_size;
 	u64 cgroup;
 	u32 flags;
 	u16 insn_len;
@@ -408,4 +409,7 @@ extern int sysctl_perf_event_max_stack;
 extern int sysctl_perf_event_max_contexts_per_stack;
 extern unsigned int proc_map_timeout;
 
+#define PAGE_SIZE_NAME_LEN	32
+char *get_page_size_name(u64 size, char *str);
+
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 8bdf3d2c907c..05363a7247c4 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -78,7 +78,7 @@ struct evlist *evlist__new(void)
 	return evlist;
 }
 
-struct evlist *perf_evlist__new_default(void)
+struct evlist *evlist__new_default(void)
 {
 	struct evlist *evlist = evlist__new();
 
@@ -90,7 +90,7 @@ struct evlist *perf_evlist__new_default(void)
 	return evlist;
 }
 
-struct evlist *perf_evlist__new_dummy(void)
+struct evlist *evlist__new_dummy(void)
 {
 	struct evlist *evlist = evlist__new();
 
@@ -103,13 +103,13 @@ struct evlist *perf_evlist__new_dummy(void)
 }
 
 /**
- * perf_evlist__set_id_pos - set the positions of event ids.
+ * evlist__set_id_pos - set the positions of event ids.
  * @evlist: selected event list
  *
  * Events with compatible sample types all have the same id_pos
  * and is_pos.  For convenience, put a copy on evlist.
  */
-void perf_evlist__set_id_pos(struct evlist *evlist)
+void evlist__set_id_pos(struct evlist *evlist)
 {
 	struct evsel *first = evlist__first(evlist);
 
@@ -117,14 +117,14 @@ void perf_evlist__set_id_pos(struct evlist *evlist)
 	evlist->is_pos = first->is_pos;
 }
 
-static void perf_evlist__update_id_pos(struct evlist *evlist)
+static void evlist__update_id_pos(struct evlist *evlist)
 {
 	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel)
 		evsel__calc_id_pos(evsel);
 
-	perf_evlist__set_id_pos(evlist);
+	evlist__set_id_pos(evlist);
 }
 
 static void evlist__purge(struct evlist *evlist)
@@ -168,7 +168,7 @@ void evlist__add(struct evlist *evlist, struct evsel *entry)
 	perf_evlist__add(&evlist->core, &entry->core);
 
 	if (evlist->core.nr_entries == 1)
-		perf_evlist__set_id_pos(evlist);
+		evlist__set_id_pos(evlist);
 }
 
 void evlist__remove(struct evlist *evlist, struct evsel *evsel)
@@ -177,27 +177,36 @@ void evlist__remove(struct evlist *evlist, struct evsel *evsel)
 	perf_evlist__remove(&evlist->core, &evsel->core);
 }
 
-void perf_evlist__splice_list_tail(struct evlist *evlist,
-				   struct list_head *list)
+void evlist__splice_list_tail(struct evlist *evlist, struct list_head *list)
 {
-	struct evsel *evsel, *temp;
+	while (!list_empty(list)) {
+		struct evsel *evsel, *temp, *leader = NULL;
 
-	__evlist__for_each_entry_safe(list, temp, evsel) {
-		list_del_init(&evsel->core.node);
-		evlist__add(evlist, evsel);
+		__evlist__for_each_entry_safe(list, temp, evsel) {
+			list_del_init(&evsel->core.node);
+			evlist__add(evlist, evsel);
+			leader = evsel;
+			break;
+		}
+
+		__evlist__for_each_entry_safe(list, temp, evsel) {
+			if (evsel->leader == leader) {
+				list_del_init(&evsel->core.node);
+				evlist__add(evlist, evsel);
+			}
+		}
 	}
 }
 
 int __evlist__set_tracepoints_handlers(struct evlist *evlist,
 				       const struct evsel_str_handler *assocs, size_t nr_assocs)
 {
-	struct evsel *evsel;
 	size_t i;
 	int err;
 
 	for (i = 0; i < nr_assocs; i++) {
 		// Adding a handler for an event not in this evlist, just ignore it.
-		evsel = perf_evlist__find_tracepoint_by_name(evlist, assocs[i].name);
+		struct evsel *evsel = evlist__find_tracepoint_by_name(evlist, assocs[i].name);
 		if (evsel == NULL)
 			continue;
 
@@ -212,7 +221,7 @@ out:
 	return err;
 }
 
-void __perf_evlist__set_leader(struct list_head *list)
+void __evlist__set_leader(struct list_head *list)
 {
 	struct evsel *evsel, *leader;
 
@@ -226,11 +235,11 @@ void __perf_evlist__set_leader(struct list_head *list)
 	}
 }
 
-void perf_evlist__set_leader(struct evlist *evlist)
+void evlist__set_leader(struct evlist *evlist)
 {
 	if (evlist->core.nr_entries) {
 		evlist->nr_groups = evlist->core.nr_entries > 1 ? 1 : 0;
-		__perf_evlist__set_leader(&evlist->core.entries);
+		__evlist__set_leader(&evlist->core.entries);
 	}
 }
 
@@ -274,7 +283,7 @@ static int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attr
 		list_add_tail(&evsel->core.node, &head);
 	}
 
-	perf_evlist__splice_list_tail(evlist, &head);
+	evlist__splice_list_tail(evlist, &head);
 
 	return 0;
 
@@ -294,8 +303,7 @@ int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *a
 	return evlist__add_attrs(evlist, attrs, nr_attrs);
 }
 
-struct evsel *
-perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id)
+struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id)
 {
 	struct evsel *evsel;
 
@@ -308,9 +316,7 @@ perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id)
 	return NULL;
 }
 
-struct evsel *
-perf_evlist__find_tracepoint_by_name(struct evlist *evlist,
-				     const char *name)
+struct evsel *evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name)
 {
 	struct evsel *evsel;
 
@@ -335,8 +341,7 @@ int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name,
 	return 0;
 }
 
-static int perf_evlist__nr_threads(struct evlist *evlist,
-				   struct evsel *evsel)
+static int evlist__nr_threads(struct evlist *evlist, struct evsel *evsel)
 {
 	if (evsel->core.system_wide)
 		return 1;
@@ -376,7 +381,30 @@ bool evsel__cpu_iter_skip(struct evsel *ev, int cpu)
 	return true;
 }
 
-void evlist__disable(struct evlist *evlist)
+static int evsel__strcmp(struct evsel *pos, char *evsel_name)
+{
+	if (!evsel_name)
+		return 0;
+	if (evsel__is_dummy_event(pos))
+		return 1;
+	return strcmp(pos->name, evsel_name);
+}
+
+static int evlist__is_enabled(struct evlist *evlist)
+{
+	struct evsel *pos;
+
+	evlist__for_each_entry(evlist, pos) {
+		if (!evsel__is_group_leader(pos) || !pos->core.fd)
+			continue;
+		/* If at least one event is enabled, evlist is enabled. */
+		if (!pos->disabled)
+			return true;
+	}
+	return false;
+}
+
+static void __evlist__disable(struct evlist *evlist, char *evsel_name)
 {
 	struct evsel *pos;
 	struct affinity affinity;
@@ -392,6 +420,8 @@ void evlist__disable(struct evlist *evlist)
 			affinity__set(&affinity, cpu);
 
 			evlist__for_each_entry(evlist, pos) {
+				if (evsel__strcmp(pos, evsel_name))
+					continue;
 				if (evsel__cpu_iter_skip(pos, cpu))
 					continue;
 				if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
@@ -409,15 +439,34 @@ void evlist__disable(struct evlist *evlist)
 
 	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
+		if (evsel__strcmp(pos, evsel_name))
+			continue;
 		if (!evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
 		pos->disabled = true;
 	}
 
-	evlist->enabled = false;
+	/*
+	 * If we disabled only single event, we need to check
+	 * the enabled state of the evlist manually.
+	 */
+	if (evsel_name)
+		evlist->enabled = evlist__is_enabled(evlist);
+	else
+		evlist->enabled = false;
 }
 
-void evlist__enable(struct evlist *evlist)
+void evlist__disable(struct evlist *evlist)
+{
+	__evlist__disable(evlist, NULL);
+}
+
+void evlist__disable_evsel(struct evlist *evlist, char *evsel_name)
+{
+	__evlist__disable(evlist, evsel_name);
+}
+
+static void __evlist__enable(struct evlist *evlist, char *evsel_name)
 {
 	struct evsel *pos;
 	struct affinity affinity;
@@ -430,6 +479,8 @@ void evlist__enable(struct evlist *evlist)
 		affinity__set(&affinity, cpu);
 
 		evlist__for_each_entry(evlist, pos) {
+			if (evsel__strcmp(pos, evsel_name))
+				continue;
 			if (evsel__cpu_iter_skip(pos, cpu))
 				continue;
 			if (!evsel__is_group_leader(pos) || !pos->core.fd)
@@ -439,24 +490,40 @@ void evlist__enable(struct evlist *evlist)
 	}
 	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
+		if (evsel__strcmp(pos, evsel_name))
+			continue;
 		if (!evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
 		pos->disabled = false;
 	}
 
+	/*
+	 * Even single event sets the 'enabled' for evlist,
+	 * so the toggle can work properly and toggle to
+	 * 'disabled' state.
+	 */
 	evlist->enabled = true;
 }
 
-void perf_evlist__toggle_enable(struct evlist *evlist)
+void evlist__enable(struct evlist *evlist)
+{
+	__evlist__enable(evlist, NULL);
+}
+
+void evlist__enable_evsel(struct evlist *evlist, char *evsel_name)
+{
+	__evlist__enable(evlist, evsel_name);
+}
+
+void evlist__toggle_enable(struct evlist *evlist)
 {
 	(evlist->enabled ? evlist__disable : evlist__enable)(evlist);
 }
 
-static int perf_evlist__enable_event_cpu(struct evlist *evlist,
-					 struct evsel *evsel, int cpu)
+static int evlist__enable_event_cpu(struct evlist *evlist, struct evsel *evsel, int cpu)
 {
 	int thread;
-	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
+	int nr_threads = evlist__nr_threads(evlist, evsel);
 
 	if (!evsel->core.fd)
 		return -EINVAL;
@@ -469,9 +536,7 @@ static int perf_evlist__enable_event_cpu(struct evlist *evlist,
 	return 0;
 }
 
-static int perf_evlist__enable_event_thread(struct evlist *evlist,
-					    struct evsel *evsel,
-					    int thread)
+static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evsel, int thread)
 {
 	int cpu;
 	int nr_cpus = perf_cpu_map__nr(evlist->core.cpus);
@@ -487,15 +552,14 @@ static int perf_evlist__enable_event_thread(struct evlist *evlist,
 	return 0;
 }
 
-int perf_evlist__enable_event_idx(struct evlist *evlist,
-				  struct evsel *evsel, int idx)
+int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx)
 {
 	bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.cpus);
 
 	if (per_cpu_mmaps)
-		return perf_evlist__enable_event_cpu(evlist, evsel, idx);
-	else
-		return perf_evlist__enable_event_thread(evlist, evsel, idx);
+		return evlist__enable_event_cpu(evlist, evsel, idx);
+
+	return evlist__enable_event_thread(evlist, evsel, idx);
 }
 
 int evlist__add_pollfd(struct evlist *evlist, int fd)
@@ -513,7 +577,7 @@ int evlist__poll(struct evlist *evlist, int timeout)
 	return perf_evlist__poll(&evlist->core, timeout);
 }
 
-struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id)
+struct perf_sample_id *evlist__id2sid(struct evlist *evlist, u64 id)
 {
 	struct hlist_head *head;
 	struct perf_sample_id *sid;
@@ -529,14 +593,14 @@ struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id)
 	return NULL;
 }
 
-struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id)
+struct evsel *evlist__id2evsel(struct evlist *evlist, u64 id)
 {
 	struct perf_sample_id *sid;
 
 	if (evlist->core.nr_entries == 1 || !id)
 		return evlist__first(evlist);
 
-	sid = perf_evlist__id2sid(evlist, id);
+	sid = evlist__id2sid(evlist, id);
 	if (sid)
 		return container_of(sid->evsel, struct evsel, core);
 
@@ -546,23 +610,21 @@ struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id)
 	return NULL;
 }
 
-struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist,
-						u64 id)
+struct evsel *evlist__id2evsel_strict(struct evlist *evlist, u64 id)
 {
 	struct perf_sample_id *sid;
 
 	if (!id)
 		return NULL;
 
-	sid = perf_evlist__id2sid(evlist, id);
+	sid = evlist__id2sid(evlist, id);
 	if (sid)
 		return container_of(sid->evsel, struct evsel, core);
 
 	return NULL;
 }
 
-static int perf_evlist__event2id(struct evlist *evlist,
-				 union perf_event *event, u64 *id)
+static int evlist__event2id(struct evlist *evlist, union perf_event *event, u64 *id)
 {
 	const __u64 *array = event->sample.array;
 	ssize_t n;
@@ -582,8 +644,7 @@ static int perf_evlist__event2id(struct evlist *evlist,
 	return 0;
 }
 
-struct evsel *perf_evlist__event2evsel(struct evlist *evlist,
-					    union perf_event *event)
+struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event)
 {
 	struct evsel *first = evlist__first(evlist);
 	struct hlist_head *head;
@@ -598,7 +659,7 @@ struct evsel *perf_evlist__event2evsel(struct evlist *evlist,
 	    event->header.type != PERF_RECORD_SAMPLE)
 		return first;
 
-	if (perf_evlist__event2id(evlist, event, &id))
+	if (evlist__event2id(evlist, event, &id))
 		return NULL;
 
 	/* Synthesized events have an id of zero */
@@ -615,7 +676,7 @@ struct evsel *perf_evlist__event2evsel(struct evlist *evlist,
 	return NULL;
 }
 
-static int perf_evlist__set_paused(struct evlist *evlist, bool value)
+static int evlist__set_paused(struct evlist *evlist, bool value)
 {
 	int i;
 
@@ -635,14 +696,14 @@ static int perf_evlist__set_paused(struct evlist *evlist, bool value)
 	return 0;
 }
 
-static int perf_evlist__pause(struct evlist *evlist)
+static int evlist__pause(struct evlist *evlist)
 {
-	return perf_evlist__set_paused(evlist, true);
+	return evlist__set_paused(evlist, true);
 }
 
-static int perf_evlist__resume(struct evlist *evlist)
+static int evlist__resume(struct evlist *evlist)
 {
-	return perf_evlist__set_paused(evlist, false);
+	return evlist__set_paused(evlist, false);
 }
 
 static void evlist__munmap_nofree(struct evlist *evlist)
@@ -727,7 +788,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx)
 		if (overwrite) {
 			evlist->overwrite_mmap = maps;
 			if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY)
-				perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+				evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
 		} else {
 			evlist->mmap = maps;
 		}
@@ -827,7 +888,7 @@ static long parse_pages_arg(const char *str, unsigned long min,
 	return pages;
 }
 
-int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
+int __evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
 {
 	unsigned long max = UINT_MAX;
 	long pages;
@@ -845,10 +906,9 @@ int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
 	return 0;
 }
 
-int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
-				  int unset __maybe_unused)
+int evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset __maybe_unused)
 {
-	return __perf_evlist__parse_mmap_pages(opt->value, str);
+	return __evlist__parse_mmap_pages(opt->value, str);
 }
 
 /**
@@ -904,7 +964,7 @@ int evlist__mmap(struct evlist *evlist, unsigned int pages)
 	return evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1, 0);
 }
 
-int perf_evlist__create_maps(struct evlist *evlist, struct target *target)
+int evlist__create_maps(struct evlist *evlist, struct target *target)
 {
 	bool all_threads = (target->per_thread && target->system_wide);
 	struct perf_cpu_map *cpus;
@@ -957,25 +1017,7 @@ out_delete_threads:
 	return -1;
 }
 
-void __perf_evlist__set_sample_bit(struct evlist *evlist,
-				   enum perf_event_sample_format bit)
-{
-	struct evsel *evsel;
-
-	evlist__for_each_entry(evlist, evsel)
-		__evsel__set_sample_bit(evsel, bit);
-}
-
-void __perf_evlist__reset_sample_bit(struct evlist *evlist,
-				     enum perf_event_sample_format bit)
-{
-	struct evsel *evsel;
-
-	evlist__for_each_entry(evlist, evsel)
-		__evsel__reset_sample_bit(evsel, bit);
-}
-
-int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel)
+int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel)
 {
 	struct evsel *evsel;
 	int err = 0;
@@ -998,7 +1040,7 @@ int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel)
 	return err;
 }
 
-int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter)
+int evlist__set_tp_filter(struct evlist *evlist, const char *filter)
 {
 	struct evsel *evsel;
 	int err = 0;
@@ -1018,7 +1060,7 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter)
 	return err;
 }
 
-int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter)
+int evlist__append_tp_filter(struct evlist *evlist, const char *filter)
 {
 	struct evsel *evsel;
 	int err = 0;
@@ -1064,32 +1106,32 @@ out_free:
 	return NULL;
 }
 
-int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
+int evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
 {
 	char *filter = asprintf__tp_filter_pids(npids, pids);
-	int ret = perf_evlist__set_tp_filter(evlist, filter);
+	int ret = evlist__set_tp_filter(evlist, filter);
 
 	free(filter);
 	return ret;
 }
 
-int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid)
+int evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid)
 {
-	return perf_evlist__set_tp_filter_pids(evlist, 1, &pid);
+	return evlist__set_tp_filter_pids(evlist, 1, &pid);
 }
 
-int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
+int evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids)
 {
 	char *filter = asprintf__tp_filter_pids(npids, pids);
-	int ret = perf_evlist__append_tp_filter(evlist, filter);
+	int ret = evlist__append_tp_filter(evlist, filter);
 
 	free(filter);
 	return ret;
 }
 
-int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid)
+int evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid)
 {
-	return perf_evlist__append_tp_filter_pids(evlist, 1, &pid);
+	return evlist__append_tp_filter_pids(evlist, 1, &pid);
 }
 
 bool evlist__valid_sample_type(struct evlist *evlist)
@@ -1140,7 +1182,7 @@ u64 evlist__combined_branch_type(struct evlist *evlist)
 	return branch_type;
 }
 
-bool perf_evlist__valid_read_format(struct evlist *evlist)
+bool evlist__valid_read_format(struct evlist *evlist)
 {
 	struct evsel *first = evlist__first(evlist), *pos = first;
 	u64 read_format = first->core.attr.read_format;
@@ -1162,7 +1204,7 @@ bool perf_evlist__valid_read_format(struct evlist *evlist)
 	return true;
 }
 
-u16 perf_evlist__id_hdr_size(struct evlist *evlist)
+u16 evlist__id_hdr_size(struct evlist *evlist)
 {
 	struct evsel *first = evlist__first(evlist);
 	struct perf_sample *data;
@@ -1213,8 +1255,7 @@ bool evlist__sample_id_all(struct evlist *evlist)
 	return first->core.attr.sample_id_all;
 }
 
-void perf_evlist__set_selected(struct evlist *evlist,
-			       struct evsel *evsel)
+void evlist__set_selected(struct evlist *evlist, struct evsel *evsel)
 {
 	evlist->selected = evsel;
 }
@@ -1253,7 +1294,7 @@ void evlist__close(struct evlist *evlist)
 	}
 }
 
-static int perf_evlist__create_syswide_maps(struct evlist *evlist)
+static int evlist__create_syswide_maps(struct evlist *evlist)
 {
 	struct perf_cpu_map *cpus;
 	struct perf_thread_map *threads;
@@ -1295,12 +1336,12 @@ int evlist__open(struct evlist *evlist)
 	 * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL
 	 */
 	if (evlist->core.threads == NULL && evlist->core.cpus == NULL) {
-		err = perf_evlist__create_syswide_maps(evlist);
+		err = evlist__create_syswide_maps(evlist);
 		if (err < 0)
 			goto out_err;
 	}
 
-	perf_evlist__update_id_pos(evlist);
+	evlist__update_id_pos(evlist);
 
 	evlist__for_each_entry(evlist, evsel) {
 		err = evsel__open(evsel, evsel->core.cpus, evsel->core.threads);
@@ -1315,9 +1356,8 @@ out_err:
 	return err;
 }
 
-int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target,
-				  const char *argv[], bool pipe_output,
-				  void (*exec_error)(int signo, siginfo_t *info, void *ucontext))
+int evlist__prepare_workload(struct evlist *evlist, struct target *target, const char *argv[],
+			     bool pipe_output, void (*exec_error)(int signo, siginfo_t *info, void *ucontext))
 {
 	int child_ready_pipe[2], go_pipe[2];
 	char bf;
@@ -1362,7 +1402,7 @@ int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target,
 		/*
 		 * The parent will ask for the execvp() to be performed by
 		 * writing exactly one byte, in workload.cork_fd, usually via
-		 * perf_evlist__start_workload().
+		 * evlist__start_workload().
 		 *
 		 * For cancelling the workload without actually running it,
 		 * the parent will just close workload.cork_fd, without writing
@@ -1429,7 +1469,7 @@ out_close_ready_pipe:
 	return -1;
 }
 
-int perf_evlist__start_workload(struct evlist *evlist)
+int evlist__start_workload(struct evlist *evlist)
 {
 	if (evlist->workload.cork_fd > 0) {
 		char bf = 0;
@@ -1448,21 +1488,18 @@ int perf_evlist__start_workload(struct evlist *evlist)
 	return 0;
 }
 
-int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event,
-			      struct perf_sample *sample)
+int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
 {
-	struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
+	struct evsel *evsel = evlist__event2evsel(evlist, event);
 
 	if (!evsel)
 		return -EFAULT;
 	return evsel__parse_sample(evsel, event, sample);
 }
 
-int perf_evlist__parse_sample_timestamp(struct evlist *evlist,
-					union perf_event *event,
-					u64 *timestamp)
+int evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp)
 {
-	struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
+	struct evsel *evsel = evlist__event2evsel(evlist, event);
 
 	if (!evsel)
 		return -EFAULT;
@@ -1553,8 +1590,7 @@ int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size
 	return 0;
 }
 
-void perf_evlist__to_front(struct evlist *evlist,
-			   struct evsel *move_evsel)
+void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel)
 {
 	struct evsel *evsel, *n;
 	LIST_HEAD(move);
@@ -1570,7 +1606,7 @@ void perf_evlist__to_front(struct evlist *evlist,
 	list_splice(&move, &evlist->core.entries);
 }
 
-struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist)
+struct evsel *evlist__get_tracking_event(struct evlist *evlist)
 {
 	struct evsel *evsel;
 
@@ -1582,8 +1618,7 @@ struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist)
 	return evlist__first(evlist);
 }
 
-void perf_evlist__set_tracking_event(struct evlist *evlist,
-				     struct evsel *tracking_evsel)
+void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel)
 {
 	struct evsel *evsel;
 
@@ -1598,9 +1633,7 @@ void perf_evlist__set_tracking_event(struct evlist *evlist,
 	tracking_evsel->tracking = true;
 }
 
-struct evsel *
-perf_evlist__find_evsel_by_str(struct evlist *evlist,
-			       const char *str)
+struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str)
 {
 	struct evsel *evsel;
 
@@ -1614,8 +1647,7 @@ perf_evlist__find_evsel_by_str(struct evlist *evlist,
 	return NULL;
 }
 
-void perf_evlist__toggle_bkw_mmap(struct evlist *evlist,
-				  enum bkw_mmap_state state)
+void evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state)
 {
 	enum bkw_mmap_state old_state = evlist->bkw_mmap_state;
 	enum action {
@@ -1658,10 +1690,10 @@ void perf_evlist__toggle_bkw_mmap(struct evlist *evlist,
 
 	switch (action) {
 	case PAUSE:
-		perf_evlist__pause(evlist);
+		evlist__pause(evlist);
 		break;
 	case RESUME:
-		perf_evlist__resume(evlist);
+		evlist__resume(evlist);
 		break;
 	case NONE:
 	default:
@@ -1672,7 +1704,7 @@ state_err:
 	return;
 }
 
-bool perf_evlist__exclude_kernel(struct evlist *evlist)
+bool evlist__exclude_kernel(struct evlist *evlist)
 {
 	struct evsel *evsel;
 
@@ -1689,19 +1721,17 @@ bool perf_evlist__exclude_kernel(struct evlist *evlist)
  * the group display. Set the artificial group and set the leader's
  * forced_leader flag to notify the display code.
  */
-void perf_evlist__force_leader(struct evlist *evlist)
+void evlist__force_leader(struct evlist *evlist)
 {
 	if (!evlist->nr_groups) {
 		struct evsel *leader = evlist__first(evlist);
 
-		perf_evlist__set_leader(evlist);
+		evlist__set_leader(evlist);
 		leader->forced_leader = true;
 	}
 }
 
-struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
-						 struct evsel *evsel,
-						bool close)
+struct evsel *evlist__reset_weak_group(struct evlist *evsel_list, struct evsel *evsel, bool close)
 {
 	struct evsel *c2, *leader;
 	bool is_open = true;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index e1a450322bc5..1aae75895dea 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -87,8 +87,8 @@ struct evsel_str_handler {
 };
 
 struct evlist *evlist__new(void);
-struct evlist *perf_evlist__new_default(void);
-struct evlist *perf_evlist__new_dummy(void);
+struct evlist *evlist__new_default(void);
+struct evlist *evlist__new_dummy(void);
 void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
 		  struct perf_thread_map *threads);
 void evlist__exit(struct evlist *evlist);
@@ -112,14 +112,11 @@ int __evlist__add_default_attrs(struct evlist *evlist,
 
 int evlist__add_dummy(struct evlist *evlist);
 
-int perf_evlist__add_sb_event(struct evlist *evlist,
-			      struct perf_event_attr *attr,
-			      evsel__sb_cb_t cb,
-			      void *data);
+int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
+			 evsel__sb_cb_t cb, void *data);
 void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data);
-int perf_evlist__start_sb_thread(struct evlist *evlist,
-				 struct target *target);
-void perf_evlist__stop_sb_thread(struct evlist *evlist);
+int evlist__start_sb_thread(struct evlist *evlist, struct target *target);
+void evlist__stop_sb_thread(struct evlist *evlist);
 
 int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, void *handler);
 
@@ -130,45 +127,29 @@ int __evlist__set_tracepoints_handlers(struct evlist *evlist,
 #define evlist__set_tracepoints_handlers(evlist, array) \
 	__evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array))
 
-void __perf_evlist__set_sample_bit(struct evlist *evlist,
-				   enum perf_event_sample_format bit);
-void __perf_evlist__reset_sample_bit(struct evlist *evlist,
-				     enum perf_event_sample_format bit);
+int evlist__set_tp_filter(struct evlist *evlist, const char *filter);
+int evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid);
+int evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
 
-#define perf_evlist__set_sample_bit(evlist, bit) \
-	__perf_evlist__set_sample_bit(evlist, PERF_SAMPLE_##bit)
+int evlist__append_tp_filter(struct evlist *evlist, const char *filter);
 
-#define perf_evlist__reset_sample_bit(evlist, bit) \
-	__perf_evlist__reset_sample_bit(evlist, PERF_SAMPLE_##bit)
+int evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid);
+int evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
 
-int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter);
-int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid);
-int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
-
-int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter);
-
-int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid);
-int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids);
-
-struct evsel *
-perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id);
-
-struct evsel *
-perf_evlist__find_tracepoint_by_name(struct evlist *evlist,
-				     const char *name);
+struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id);
+struct evsel *evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name);
 
 int evlist__add_pollfd(struct evlist *evlist, int fd);
 int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask);
 
 int evlist__poll(struct evlist *evlist, int timeout);
 
-struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id);
-struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist,
-						u64 id);
+struct evsel *evlist__id2evsel(struct evlist *evlist, u64 id);
+struct evsel *evlist__id2evsel_strict(struct evlist *evlist, u64 id);
 
-struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id);
+struct perf_sample_id *evlist__id2sid(struct evlist *evlist, u64 id);
 
-void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state);
+void evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state);
 
 void evlist__mmap_consume(struct evlist *evlist, int idx);
 
@@ -177,24 +158,19 @@ void evlist__close(struct evlist *evlist);
 
 struct callchain_param;
 
-void perf_evlist__set_id_pos(struct evlist *evlist);
-void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
-			 struct callchain_param *callchain);
+void evlist__set_id_pos(struct evlist *evlist);
+void evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain);
 int record_opts__config(struct record_opts *opts);
 
-int perf_evlist__prepare_workload(struct evlist *evlist,
-				  struct target *target,
-				  const char *argv[], bool pipe_output,
-				  void (*exec_error)(int signo, siginfo_t *info,
-						     void *ucontext));
-int perf_evlist__start_workload(struct evlist *evlist);
+int evlist__prepare_workload(struct evlist *evlist, struct target *target,
+			     const char *argv[], bool pipe_output,
+			     void (*exec_error)(int signo, siginfo_t *info, void *ucontext));
+int evlist__start_workload(struct evlist *evlist);
 
 struct option;
 
-int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str);
-int perf_evlist__parse_mmap_pages(const struct option *opt,
-				  const char *str,
-				  int unset);
+int __evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str);
+int evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset);
 
 unsigned long perf_event_mlock_kb_in_pages(void);
 
@@ -209,41 +185,36 @@ size_t evlist__mmap_size(unsigned long pages);
 
 void evlist__disable(struct evlist *evlist);
 void evlist__enable(struct evlist *evlist);
-void perf_evlist__toggle_enable(struct evlist *evlist);
+void evlist__toggle_enable(struct evlist *evlist);
+void evlist__disable_evsel(struct evlist *evlist, char *evsel_name);
+void evlist__enable_evsel(struct evlist *evlist, char *evsel_name);
 
-int perf_evlist__enable_event_idx(struct evlist *evlist,
-				  struct evsel *evsel, int idx);
+int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx);
 
-void perf_evlist__set_selected(struct evlist *evlist,
-			       struct evsel *evsel);
+void evlist__set_selected(struct evlist *evlist, struct evsel *evsel);
 
-int perf_evlist__create_maps(struct evlist *evlist, struct target *target);
-int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel);
+int evlist__create_maps(struct evlist *evlist, struct target *target);
+int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel);
 
-void __perf_evlist__set_leader(struct list_head *list);
-void perf_evlist__set_leader(struct evlist *evlist);
+void __evlist__set_leader(struct list_head *list);
+void evlist__set_leader(struct evlist *evlist);
 
 u64 __evlist__combined_sample_type(struct evlist *evlist);
 u64 evlist__combined_sample_type(struct evlist *evlist);
 u64 evlist__combined_branch_type(struct evlist *evlist);
 bool evlist__sample_id_all(struct evlist *evlist);
-u16 perf_evlist__id_hdr_size(struct evlist *evlist);
-
-int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event,
-			      struct perf_sample *sample);
+u16 evlist__id_hdr_size(struct evlist *evlist);
 
-int perf_evlist__parse_sample_timestamp(struct evlist *evlist,
-					union perf_event *event,
-					u64 *timestamp);
+int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample);
+int evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp);
 
 bool evlist__valid_sample_type(struct evlist *evlist);
 bool evlist__valid_sample_id_all(struct evlist *evlist);
-bool perf_evlist__valid_read_format(struct evlist *evlist);
+bool evlist__valid_read_format(struct evlist *evlist);
 
-void perf_evlist__splice_list_tail(struct evlist *evlist,
-				   struct list_head *list);
+void evlist__splice_list_tail(struct evlist *evlist, struct list_head *list);
 
-static inline bool perf_evlist__empty(struct evlist *evlist)
+static inline bool evlist__empty(struct evlist *evlist)
 {
 	return list_empty(&evlist->core.entries);
 }
@@ -265,9 +236,8 @@ static inline struct evsel *evlist__last(struct evlist *evlist)
 int evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size);
 int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size);
 
-bool perf_evlist__can_select_event(struct evlist *evlist, const char *str);
-void perf_evlist__to_front(struct evlist *evlist,
-			   struct evsel *move_evsel);
+bool evlist__can_select_event(struct evlist *evlist, const char *str);
+void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel);
 
 /**
  * __evlist__for_each_entry - iterate thru all the evsels
@@ -339,27 +309,23 @@ void perf_evlist__to_front(struct evlist *evlist,
 	evlist__cpu_iter_start(evlist);			\
 	perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus)
 
-struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist);
-void perf_evlist__set_tracking_event(struct evlist *evlist,
-				     struct evsel *tracking_evsel);
+struct evsel *evlist__get_tracking_event(struct evlist *evlist);
+void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel);
 
 void evlist__cpu_iter_start(struct evlist *evlist);
 bool evsel__cpu_iter_skip(struct evsel *ev, int cpu);
 bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu);
 
-struct evsel *
-perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str);
+struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str);
+
+struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event);
 
-struct evsel *perf_evlist__event2evsel(struct evlist *evlist,
-					    union perf_event *event);
+bool evlist__exclude_kernel(struct evlist *evlist);
 
-bool perf_evlist__exclude_kernel(struct evlist *evlist);
+void evlist__force_leader(struct evlist *evlist);
 
-void perf_evlist__force_leader(struct evlist *evlist);
+struct evsel *evlist__reset_weak_group(struct evlist *evlist, struct evsel *evsel, bool close);
 
-struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist,
-						 struct evsel *evsel,
-						bool close);
 #define EVLIST_CTL_CMD_ENABLE_TAG  "enable"
 #define EVLIST_CTL_CMD_DISABLE_TAG "disable"
 #define EVLIST_CTL_CMD_ACK_TAG     "ack\n"
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1cad6051d8b0..c26ea82220bd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -497,7 +497,7 @@ static const char *__evsel__hw_name(u64 config)
 	return "unknown-hardware";
 }
 
-static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
+static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
 {
 	int colon = 0, r = 0;
 	struct perf_event_attr *attr = &evsel->core.attr;
@@ -536,7 +536,7 @@ static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
 static int evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
 {
 	int r = scnprintf(bf, size, "%s", __evsel__hw_name(evsel->core.attr.config));
-	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+	return r + evsel__add_modifiers(evsel, bf + r, size - r);
 }
 
 const char *evsel__sw_names[PERF_COUNT_SW_MAX] = {
@@ -562,7 +562,7 @@ static const char *__evsel__sw_name(u64 config)
 static int evsel__sw_name(struct evsel *evsel, char *bf, size_t size)
 {
 	int r = scnprintf(bf, size, "%s", __evsel__sw_name(evsel->core.attr.config));
-	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+	return r + evsel__add_modifiers(evsel, bf + r, size - r);
 }
 
 static int __evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
@@ -587,7 +587,7 @@ static int evsel__bp_name(struct evsel *evsel, char *bf, size_t size)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
 	int r = __evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
-	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
+	return r + evsel__add_modifiers(evsel, bf + r, size - r);
 }
 
 const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES] = {
@@ -682,13 +682,13 @@ out_err:
 static int evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size)
 {
 	int ret = __evsel__hw_cache_name(evsel->core.attr.config, bf, size);
-	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
+	return ret + evsel__add_modifiers(evsel, bf + ret, size - ret);
 }
 
 static int evsel__raw_name(struct evsel *evsel, char *bf, size_t size)
 {
 	int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->core.attr.config);
-	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
+	return ret + evsel__add_modifiers(evsel, bf + ret, size - ret);
 }
 
 static int evsel__tool_name(char *bf, size_t size)
@@ -850,9 +850,7 @@ void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts,
 		return __evsel__config_callchain(evsel, opts, param);
 }
 
-static void
-perf_evsel__reset_callgraph(struct evsel *evsel,
-			    struct callchain_param *param)
+static void evsel__reset_callgraph(struct evsel *evsel, struct callchain_param *param)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
 
@@ -988,7 +986,7 @@ static void evsel__apply_config_terms(struct evsel *evsel,
 
 		/* If global callgraph set, clear it */
 		if (callchain_param.enabled)
-			perf_evsel__reset_callgraph(evsel, &callchain_param);
+			evsel__reset_callgraph(evsel, &callchain_param);
 
 		/* set perf-event callgraph */
 		if (param.enabled) {
@@ -1190,6 +1188,9 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 		evsel__set_sample_bit(evsel, CGROUP);
 	}
 
+	if (opts->sample_data_page_size)
+		evsel__set_sample_bit(evsel, DATA_PAGE_SIZE);
+
 	if (opts->record_switch_events)
 		attr->context_switch = track;
 
@@ -1434,9 +1435,7 @@ static int evsel__read_one(struct evsel *evsel, int cpu, int thread)
 	return perf_evsel__read(&evsel->core, cpu, thread, count);
 }
 
-static void
-perf_evsel__set_count(struct evsel *counter, int cpu, int thread,
-		      u64 val, u64 ena, u64 run)
+static void evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run)
 {
 	struct perf_counts_values *count;
 
@@ -1449,9 +1448,7 @@ perf_evsel__set_count(struct evsel *counter, int cpu, int thread,
 	perf_counts__set_loaded(counter->counts, cpu, thread, true);
 }
 
-static int
-perf_evsel__process_group_data(struct evsel *leader,
-			       int cpu, int thread, u64 *data)
+static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data)
 {
 	u64 read_format = leader->core.attr.read_format;
 	struct sample_read_value *v;
@@ -1470,18 +1467,16 @@ perf_evsel__process_group_data(struct evsel *leader,
 
 	v = (struct sample_read_value *) data;
 
-	perf_evsel__set_count(leader, cpu, thread,
-			      v[0].value, ena, run);
+	evsel__set_count(leader, cpu, thread, v[0].value, ena, run);
 
 	for (i = 1; i < nr; i++) {
 		struct evsel *counter;
 
-		counter = perf_evlist__id2evsel(leader->evlist, v[i].id);
+		counter = evlist__id2evsel(leader->evlist, v[i].id);
 		if (!counter)
 			return -EINVAL;
 
-		perf_evsel__set_count(counter, cpu, thread,
-				      v[i].value, ena, run);
+		evsel__set_count(counter, cpu, thread, v[i].value, ena, run);
 	}
 
 	return 0;
@@ -1514,7 +1509,7 @@ static int evsel__read_group(struct evsel *leader, int cpu, int thread)
 	if (readn(FD(leader, cpu, thread), data, size) <= 0)
 		return -errno;
 
-	return perf_evsel__process_group_data(leader, cpu, thread, data);
+	return evsel__process_group_data(leader, cpu, thread, data);
 }
 
 int evsel__read_counter(struct evsel *evsel, int cpu, int thread)
@@ -1567,9 +1562,7 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread)
 	return fd;
 }
 
-static void perf_evsel__remove_fd(struct evsel *pos,
-				  int nr_cpus, int nr_threads,
-				  int thread_idx)
+static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx)
 {
 	for (int cpu = 0; cpu < nr_cpus; cpu++)
 		for (int thread = thread_idx; thread < nr_threads - 1; thread++)
@@ -1588,7 +1581,7 @@ static int update_fds(struct evsel *evsel,
 	evlist__for_each_entry(evsel->evlist, pos) {
 		nr_cpus = pos != evsel ? nr_cpus : cpu_idx;
 
-		perf_evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
+		evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
 
 		/*
 		 * Since fds for next evsel has not been created,
@@ -1880,7 +1873,12 @@ try_fallback:
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-        if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) {
+        if (!perf_missing_features.data_page_size &&
+	    (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)) {
+		perf_missing_features.data_page_size = true;
+		pr_debug2_peo("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support, bailing out\n");
+		goto out_close;
+	} else if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) {
 		perf_missing_features.cgroup = true;
 		pr_debug2_peo("Kernel has no cgroup sampling support, bailing out\n");
 		goto out_close;
@@ -2365,6 +2363,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 		array++;
 	}
 
+	data->data_page_size = 0;
+	if (type & PERF_SAMPLE_DATA_PAGE_SIZE) {
+		data->data_page_size = *array;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_AUX) {
 		OVERFLOW_CHECK_u64(array);
 		sz = *array++;
@@ -2674,6 +2678,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
 	"We found oprofile daemon running, please stop it and try again.");
 		break;
 	case EINVAL:
+		if (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE && perf_missing_features.data_page_size)
+			return scnprintf(msg, size, "Asking for the data page size isn't supported by this kernel.");
 		if (evsel->core.attr.write_backward && perf_missing_features.write_backward)
 			return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel.");
 		if (perf_missing_features.clockid)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 79a860d8e3ee..cd1d8dd43199 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -144,6 +144,7 @@ struct perf_missing_features {
 	bool aux_output;
 	bool branch_hw_idx;
 	bool cgroup;
+	bool data_page_size;
 };
 
 extern struct perf_missing_features perf_missing_features;
diff --git a/tools/perf/util/evswitch.c b/tools/perf/util/evswitch.c
index 3ba72f743d3c..40cb56a9347d 100644
--- a/tools/perf/util/evswitch.c
+++ b/tools/perf/util/evswitch.c
@@ -41,7 +41,7 @@ static int evswitch__fprintf_enoent(FILE *fp, const char *evtype, const char *ev
 int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp)
 {
 	if (evswitch->on_name) {
-		evswitch->on = perf_evlist__find_evsel_by_str(evlist, evswitch->on_name);
+		evswitch->on = evlist__find_evsel_by_str(evlist, evswitch->on_name);
 		if (evswitch->on == NULL) {
 			evswitch__fprintf_enoent(fp, "on", evswitch->on_name);
 			return -ENOENT;
@@ -50,7 +50,7 @@ int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp)
 	}
 
 	if (evswitch->off_name) {
-		evswitch->off = perf_evlist__find_evsel_by_str(evlist, evswitch->off_name);
+		evswitch->off = evlist__find_evsel_by_str(evlist, evswitch->off_name);
 		if (evswitch->off == NULL) {
 			evswitch__fprintf_enoent(fp, "off", evswitch->off_name);
 			return -ENOENT;
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 53482ef53c41..a850fd0be3ee 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -17,6 +17,29 @@
 extern int expr_debug;
 #endif
 
+struct expr_id_data {
+	union {
+		double val;
+		struct {
+			double val;
+			const char *metric_name;
+			const char *metric_expr;
+		} ref;
+		struct expr_id	*parent;
+	};
+
+	enum {
+		/* Holding a double value. */
+		EXPR_ID_DATA__VALUE,
+		/* Reference to another metric. */
+		EXPR_ID_DATA__REF,
+		/* A reference but the value has been computed. */
+		EXPR_ID_DATA__REF_VALUE,
+		/* A parent is remembered for the recursion check. */
+		EXPR_ID_DATA__PARENT,
+	} kind;
+};
+
 static size_t key_hash(const void *key, void *ctx __maybe_unused)
 {
 	const char *str = (const char *)key;
@@ -48,6 +71,7 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id)
 		return -ENOMEM;
 
 	data_ptr->parent = ctx->parent;
+	data_ptr->kind = EXPR_ID_DATA__PARENT;
 
 	ret = hashmap__set(&ctx->ids, id, data_ptr,
 			   (const void **)&old_key, (void **)&old_data);
@@ -69,7 +93,7 @@ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val)
 	if (!data_ptr)
 		return -ENOMEM;
 	data_ptr->val = val;
-	data_ptr->is_ref = false;
+	data_ptr->kind = EXPR_ID_DATA__VALUE;
 
 	ret = hashmap__set(&ctx->ids, id, data_ptr,
 			   (const void **)&old_key, (void **)&old_data);
@@ -114,8 +138,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref)
 	 */
 	data_ptr->ref.metric_name = ref->metric_name;
 	data_ptr->ref.metric_expr = ref->metric_expr;
-	data_ptr->ref.counted = false;
-	data_ptr->is_ref = true;
+	data_ptr->kind = EXPR_ID_DATA__REF;
 
 	ret = hashmap__set(&ctx->ids, name, data_ptr,
 			   (const void **)&old_key, (void **)&old_data);
@@ -148,17 +171,30 @@ int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id,
 
 	data = *datap;
 
-	pr_debug2("lookup: is_ref %d, counted %d, val %f: %s\n",
-		  data->is_ref, data->ref.counted, data->val, id);
-
-	if (data->is_ref && !data->ref.counted) {
-		data->ref.counted = true;
+	switch (data->kind) {
+	case EXPR_ID_DATA__VALUE:
+		pr_debug2("lookup(%s): val %f\n", id, data->val);
+		break;
+	case EXPR_ID_DATA__PARENT:
+		pr_debug2("lookup(%s): parent %s\n", id, data->parent->id);
+		break;
+	case EXPR_ID_DATA__REF:
+		pr_debug2("lookup(%s): ref metric name %s\n", id,
+			data->ref.metric_name);
 		pr_debug("processing metric: %s ENTRY\n", id);
-		if (expr__parse(&data->val, ctx, data->ref.metric_expr, 1)) {
+		data->kind = EXPR_ID_DATA__REF_VALUE;
+		if (expr__parse(&data->ref.val, ctx, data->ref.metric_expr, 1)) {
 			pr_debug("%s failed to count\n", id);
 			return -1;
 		}
 		pr_debug("processing metric: %s EXIT: %f\n", id, data->val);
+		break;
+	case EXPR_ID_DATA__REF_VALUE:
+		pr_debug2("lookup(%s): ref val %f metric name %s\n", id,
+			data->ref.val, data->ref.metric_name);
+		break;
+	default:
+		assert(0);  /* Unreachable. */
 	}
 
 	return 0;
@@ -241,3 +277,17 @@ int expr__find_other(const char *expr, const char *one,
 
 	return ret;
 }
+
+double expr_id_data__value(const struct expr_id_data *data)
+{
+	if (data->kind == EXPR_ID_DATA__VALUE)
+		return data->val;
+	assert(data->kind == EXPR_ID_DATA__REF_VALUE);
+	return data->ref.val;
+}
+
+struct expr_id *expr_id_data__parent(struct expr_id_data *data)
+{
+	assert(data->kind == EXPR_ID_DATA__PARENT);
+	return data->parent;
+}
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index fc2b5e824a66..dcf8d19b83c8 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -23,19 +23,7 @@ struct expr_parse_ctx {
 	struct expr_id	*parent;
 };
 
-struct expr_id_data {
-	union {
-		double val;
-		struct {
-			const char *metric_name;
-			const char *metric_expr;
-			bool counted;
-		} ref;
-		struct expr_id	*parent;
-	};
-
-	bool is_ref;
-};
+struct expr_id_data;
 
 struct expr_scanner_ctx {
 	int start_token;
@@ -57,4 +45,7 @@ int expr__parse(double *final_val, struct expr_parse_ctx *ctx,
 int expr__find_other(const char *expr, const char *one,
 		struct expr_parse_ctx *ids, int runtime);
 
+double expr_id_data__value(const struct expr_id_data *data);
+struct expr_id *expr_id_data__parent(struct expr_id_data *data);
+
 #endif
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index d34b370391c6..b2ada8f8309a 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -93,7 +93,7 @@ expr:	  NUMBER
 						YYABORT;
 					}
 
-					$$ = data->val;
+					$$ = expr_id_data__value(data);
 					free($1);
 				}
 	| expr '|' expr		{ $$ = (long)$1 | (long)$3; }
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index be850e9f8852..c4ed3dc2c8f4 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -19,7 +19,9 @@
 #include <sys/utsname.h>
 #include <linux/time64.h>
 #include <dirent.h>
+#ifdef HAVE_LIBBPF_SUPPORT
 #include <bpf/libbpf.h>
+#endif
 #include <perf/cpumap.h>
 
 #include "dso.h"
@@ -987,13 +989,6 @@ out:
 	up_read(&env->bpf_progs.lock);
 	return ret;
 }
-#else // HAVE_LIBBPF_SUPPORT
-static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused,
-			       struct evlist *evlist __maybe_unused)
-{
-	return 0;
-}
-#endif // HAVE_LIBBPF_SUPPORT
 
 static int write_bpf_btf(struct feat_fd *ff,
 			 struct evlist *evlist __maybe_unused)
@@ -1027,6 +1022,7 @@ out:
 	up_read(&env->bpf_progs.lock);
 	return ret;
 }
+#endif // HAVE_LIBBPF_SUPPORT
 
 static int cpu_cache_level__sort(const void *a, const void *b)
 {
@@ -1638,6 +1634,7 @@ static void print_dir_format(struct feat_fd *ff, FILE *fp)
 	fprintf(fp, "# directory data version : %"PRIu64"\n", data->dir.version);
 }
 
+#ifdef HAVE_LIBBPF_SUPPORT
 static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp)
 {
 	struct perf_env *env = &ff->ph->env;
@@ -1683,6 +1680,7 @@ static void print_bpf_btf(struct feat_fd *ff, FILE *fp)
 
 	up_read(&env->bpf_progs.lock);
 }
+#endif // HAVE_LIBBPF_SUPPORT
 
 static void free_event_desc(struct evsel *events)
 {
@@ -2265,8 +2263,7 @@ static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused)
 	return 0;
 }
 
-static struct evsel *
-perf_evlist__find_by_index(struct evlist *evlist, int idx)
+static struct evsel *evlist__find_by_index(struct evlist *evlist, int idx)
 {
 	struct evsel *evsel;
 
@@ -2278,16 +2275,14 @@ perf_evlist__find_by_index(struct evlist *evlist, int idx)
 	return NULL;
 }
 
-static void
-perf_evlist__set_event_name(struct evlist *evlist,
-			    struct evsel *event)
+static void evlist__set_event_name(struct evlist *evlist, struct evsel *event)
 {
 	struct evsel *evsel;
 
 	if (!event->name)
 		return;
 
-	evsel = perf_evlist__find_by_index(evlist, event->idx);
+	evsel = evlist__find_by_index(evlist, event->idx);
 	if (!evsel)
 		return;
 
@@ -2315,7 +2310,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
 	}
 
 	for (evsel = events; evsel->core.attr.size; evsel++)
-		perf_evlist__set_event_name(session->evlist, evsel);
+		evlist__set_event_name(session->evlist, evsel);
 
 	if (!session->data->is_pipe)
 		free_event_desc(events);
@@ -2938,12 +2933,6 @@ out:
 	up_write(&env->bpf_progs.lock);
 	return err;
 }
-#else // HAVE_LIBBPF_SUPPORT
-static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data __maybe_unused)
-{
-	return 0;
-}
-#endif // HAVE_LIBBPF_SUPPORT
 
 static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 {
@@ -2990,6 +2979,7 @@ out:
 	free(node);
 	return err;
 }
+#endif // HAVE_LIBBPF_SUPPORT
 
 static int process_compressed(struct feat_fd *ff,
 			      void *data __maybe_unused)
@@ -3120,8 +3110,10 @@ const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPR(MEM_TOPOLOGY,	mem_topology,	true),
 	FEAT_OPR(CLOCKID,	clockid,	false),
 	FEAT_OPN(DIR_FORMAT,	dir_format,	false),
+#ifdef HAVE_LIBBPF_SUPPORT
 	FEAT_OPR(BPF_PROG_INFO, bpf_prog_info,  false),
 	FEAT_OPR(BPF_BTF,       bpf_btf,        false),
+#endif
 	FEAT_OPR(COMPRESSED,	compressed,	false),
 	FEAT_OPR(CPU_PMU_CAPS,	cpu_pmu_caps,	false),
 	FEAT_OPR(CLOCK_DATA,	clock_data,	false),
@@ -3331,6 +3323,14 @@ int perf_session__write_header(struct perf_session *session,
 	attr_offset = lseek(ff.fd, 0, SEEK_CUR);
 
 	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->core.attr.size < sizeof(evsel->core.attr)) {
+			/*
+			 * We are likely in "perf inject" and have read
+			 * from an older file. Update attr size so that
+			 * reader gets the right offset to the ids.
+			 */
+			evsel->core.attr.size = sizeof(evsel->core.attr);
+		}
 		f_attr = (struct perf_file_attr){
 			.attr = evsel->core.attr,
 			.ids  = {
@@ -3652,7 +3652,8 @@ static int perf_file_section__process(struct perf_file_section *section,
 }
 
 static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
-				       struct perf_header *ph, int fd,
+				       struct perf_header *ph,
+				       struct perf_data* data,
 				       bool repipe)
 {
 	struct feat_fd ff = {
@@ -3661,7 +3662,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
 	};
 	ssize_t ret;
 
-	ret = readn(fd, header, sizeof(*header));
+	ret = perf_data__read(data, header, sizeof(*header));
 	if (ret <= 0)
 		return -1;
 
@@ -3684,8 +3685,7 @@ static int perf_header__read_pipe(struct perf_session *session)
 	struct perf_header *header = &session->header;
 	struct perf_pipe_file_header f_header;
 
-	if (perf_file_header__read_pipe(&f_header, header,
-					perf_data__fd(session->data),
+	if (perf_file_header__read_pipe(&f_header, header, session->data,
 					session->repipe) < 0) {
 		pr_debug("incompatible file format\n");
 		return -EINVAL;
@@ -3740,8 +3740,7 @@ static int read_attr(int fd, struct perf_header *ph,
 	return ret <= 0 ? -1 : 0;
 }
 
-static int perf_evsel__prepare_tracepoint_event(struct evsel *evsel,
-						struct tep_handle *pevent)
+static int evsel__prepare_tracepoint_event(struct evsel *evsel, struct tep_handle *pevent)
 {
 	struct tep_event *event;
 	char bf[128];
@@ -3772,14 +3771,13 @@ static int perf_evsel__prepare_tracepoint_event(struct evsel *evsel,
 	return 0;
 }
 
-static int perf_evlist__prepare_tracepoint_events(struct evlist *evlist,
-						  struct tep_handle *pevent)
+static int evlist__prepare_tracepoint_events(struct evlist *evlist, struct tep_handle *pevent)
 {
 	struct evsel *pos;
 
 	evlist__for_each_entry(evlist, pos) {
 		if (pos->core.attr.type == PERF_TYPE_TRACEPOINT &&
-		    perf_evsel__prepare_tracepoint_event(pos, pevent))
+		    evsel__prepare_tracepoint_event(pos, pevent))
 			return -1;
 	}
 
@@ -3888,8 +3886,7 @@ int perf_session__read_header(struct perf_session *session)
 	perf_header__process_sections(header, fd, &session->tevent,
 				      perf_file_section__process);
 
-	if (perf_evlist__prepare_tracepoint_events(session->evlist,
-						   session->tevent.pevent))
+	if (evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent))
 		goto out_delete_evlist;
 
 	return 0;
@@ -4037,7 +4034,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
 
 	evlist = *pevlist;
 
-	evsel = perf_evlist__id2evsel(evlist, ev->id);
+	evsel = evlist__id2evsel(evlist, ev->id);
 	if (evsel == NULL)
 		return -EINVAL;
 
@@ -4110,8 +4107,7 @@ int perf_event__process_tracing_data(struct perf_session *session,
 		return -1;
 	}
 
-	perf_evlist__prepare_tracepoint_events(session->evlist,
-					       session->tevent.pevent);
+	evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent);
 
 	return size_read + padding;
 }
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 8a793e4c9400..a08fb9ea411b 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -188,6 +188,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR,
 				   unresolved_col_width + 4 + 2);
 
+		hists__new_col_len(hists, HISTC_MEM_DATA_PAGE_SIZE,
+				   unresolved_col_width + 4 + 2);
+
 	} else {
 		symlen = unresolved_col_width + 4 + 2;
 		hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
@@ -2654,7 +2657,7 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 	}
 }
 
-size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp)
+size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp)
 {
 	struct evsel *pos;
 	size_t ret = 0;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 96b1c13bbccc..14f66330923d 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -56,6 +56,7 @@ enum hist_column {
 	HISTC_MEM_DADDR_SYMBOL,
 	HISTC_MEM_DADDR_DSO,
 	HISTC_MEM_PHYS_DADDR,
+	HISTC_MEM_DATA_PAGE_SIZE,
 	HISTC_MEM_LOCKED,
 	HISTC_MEM_TLB,
 	HISTC_MEM_LVL,
@@ -196,7 +197,7 @@ void hists__inc_nr_samples(struct hists *hists, bool filtered);
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
 		      bool ignore_callchains);
-size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp);
+size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
@@ -464,12 +465,9 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel,
 			     struct hist_browser_timer *hbt,
 			     struct annotation_options *annotation_opts);
 
-int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help,
-				  struct hist_browser_timer *hbt,
-				  float min_pcnt,
-				  struct perf_env *env,
-				  bool warn_lost_event,
-				  struct annotation_options *annotation_options);
+int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt,
+			     float min_pcnt, struct perf_env *env, bool warn_lost_event,
+			     struct annotation_options *annotation_options);
 
 int script_browse(const char *script_opt, struct evsel *evsel);
 
@@ -483,13 +481,13 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 			   struct annotation_options *annotation_opts);
 #else
 static inline
-int perf_evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
-				  const char *help __maybe_unused,
-				  struct hist_browser_timer *hbt __maybe_unused,
-				  float min_pcnt __maybe_unused,
-				  struct perf_env *env __maybe_unused,
-				  bool warn_lost_event __maybe_unused,
-				  struct annotation_options *annotation_options __maybe_unused)
+int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused,
+			     const char *help __maybe_unused,
+			     struct hist_browser_timer *hbt __maybe_unused,
+			     float min_pcnt __maybe_unused,
+			     struct perf_env *env __maybe_unused,
+			     bool warn_lost_event __maybe_unused,
+			     struct annotation_options *annotation_options __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 3a0348caec7d..60214de42f31 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2520,11 +2520,10 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid,
 static int intel_pt_process_switch(struct intel_pt *pt,
 				   struct perf_sample *sample)
 {
-	struct evsel *evsel;
 	pid_t tid;
 	int cpu, ret;
+	struct evsel *evsel = evlist__id2evsel(pt->session->evlist, sample->id);
 
-	evsel = perf_evlist__id2evsel(pt->session->evlist, sample->id);
 	if (evsel != pt->switch_evsel)
 		return 0;
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 15385ea00190..1e9d3f982b47 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1581,32 +1581,25 @@ static bool machine__uses_kcore(struct machine *machine)
 }
 
 static bool perf_event__is_extra_kernel_mmap(struct machine *machine,
-					     union perf_event *event)
+					     struct extra_kernel_map *xm)
 {
 	return machine__is(machine, "x86_64") &&
-	       is_entry_trampoline(event->mmap.filename);
+	       is_entry_trampoline(xm->name);
 }
 
 static int machine__process_extra_kernel_map(struct machine *machine,
-					     union perf_event *event)
+					     struct extra_kernel_map *xm)
 {
 	struct dso *kernel = machine__kernel_dso(machine);
-	struct extra_kernel_map xm = {
-		.start = event->mmap.start,
-		.end   = event->mmap.start + event->mmap.len,
-		.pgoff = event->mmap.pgoff,
-	};
 
 	if (kernel == NULL)
 		return -1;
 
-	strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN);
-
-	return machine__create_extra_kernel_map(machine, kernel, &xm);
+	return machine__create_extra_kernel_map(machine, kernel, xm);
 }
 
 static int machine__process_kernel_mmap_event(struct machine *machine,
-					      union perf_event *event)
+					      struct extra_kernel_map *xm)
 {
 	struct map *map;
 	enum dso_space_type dso_space;
@@ -1621,20 +1614,18 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 	else
 		dso_space = DSO_SPACE__KERNEL_GUEST;
 
-	is_kernel_mmap = memcmp(event->mmap.filename,
-				machine->mmap_name,
+	is_kernel_mmap = memcmp(xm->name, machine->mmap_name,
 				strlen(machine->mmap_name) - 1) == 0;
-	if (event->mmap.filename[0] == '/' ||
-	    (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
-		map = machine__addnew_module_map(machine, event->mmap.start,
-						 event->mmap.filename);
+	if (xm->name[0] == '/' ||
+	    (!is_kernel_mmap && xm->name[0] == '[')) {
+		map = machine__addnew_module_map(machine, xm->start,
+						 xm->name);
 		if (map == NULL)
 			goto out_problem;
 
-		map->end = map->start + event->mmap.len;
+		map->end = map->start + xm->end - xm->start;
 	} else if (is_kernel_mmap) {
-		const char *symbol_name = (event->mmap.filename +
-				strlen(machine->mmap_name));
+		const char *symbol_name = (xm->name + strlen(machine->mmap_name));
 		/*
 		 * Should be there already, from the build-id table in
 		 * the header.
@@ -1688,18 +1679,17 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
-		machine__update_kernel_mmap(machine, event->mmap.start,
-					 event->mmap.start + event->mmap.len);
+		machine__update_kernel_mmap(machine, xm->start, xm->end);
 
 		/*
 		 * Avoid using a zero address (kptr_restrict) for the ref reloc
 		 * symbol. Effectively having zero here means that at record
 		 * time /proc/sys/kernel/kptr_restrict was non zero.
 		 */
-		if (event->mmap.pgoff != 0) {
+		if (xm->pgoff != 0) {
 			map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map,
 							symbol_name,
-							event->mmap.pgoff);
+							xm->pgoff);
 		}
 
 		if (machine__is_default_guest(machine)) {
@@ -1708,8 +1698,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			 */
 			dso__load(kernel, machine__kernel_map(machine));
 		}
-	} else if (perf_event__is_extra_kernel_mmap(machine, event)) {
-		return machine__process_extra_kernel_map(machine, event);
+	} else if (perf_event__is_extra_kernel_mmap(machine, xm)) {
+		return machine__process_extra_kernel_map(machine, xm);
 	}
 	return 0;
 out_problem:
@@ -1735,7 +1725,14 @@ int machine__process_mmap2_event(struct machine *machine,
 
 	if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
 	    sample->cpumode == PERF_RECORD_MISC_KERNEL) {
-		ret = machine__process_kernel_mmap_event(machine, event);
+		struct extra_kernel_map xm = {
+			.start = event->mmap2.start,
+			.end   = event->mmap2.start + event->mmap2.len,
+			.pgoff = event->mmap2.pgoff,
+		};
+
+		strlcpy(xm.name, event->mmap2.filename, KMAP_NAME_LEN);
+		ret = machine__process_kernel_mmap_event(machine, &xm);
 		if (ret < 0)
 			goto out_problem;
 		return 0;
@@ -1785,7 +1782,14 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 
 	if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
 	    sample->cpumode == PERF_RECORD_MISC_KERNEL) {
-		ret = machine__process_kernel_mmap_event(machine, event);
+		struct extra_kernel_map xm = {
+			.start = event->mmap.start,
+			.end   = event->mmap.start + event->mmap.len,
+			.pgoff = event->mmap.pgoff,
+		};
+
+		strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN);
+		ret = machine__process_kernel_mmap_event(machine, &xm);
 		if (ret < 0)
 			goto out_problem;
 		return 0;
@@ -2019,11 +2023,12 @@ static void ip__resolve_ams(struct thread *thread,
 	ams->ms.sym = al.sym;
 	ams->ms.map = al.map;
 	ams->phys_addr = 0;
+	ams->data_page_size = 0;
 }
 
 static void ip__resolve_data(struct thread *thread,
 			     u8 m, struct addr_map_symbol *ams,
-			     u64 addr, u64 phys_addr)
+			     u64 addr, u64 phys_addr, u64 daddr_page_size)
 {
 	struct addr_location al;
 
@@ -2037,6 +2042,7 @@ static void ip__resolve_data(struct thread *thread,
 	ams->ms.sym = al.sym;
 	ams->ms.map = al.map;
 	ams->phys_addr = phys_addr;
+	ams->data_page_size = daddr_page_size;
 }
 
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
@@ -2049,7 +2055,8 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 
 	ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
 	ip__resolve_data(al->thread, al->cpumode, &mi->daddr,
-			 sample->addr, sample->phys_addr);
+			 sample->addr, sample->phys_addr,
+			 sample->data_page_size);
 	mi->data_src.val = sample->data_src;
 
 	return mi;
@@ -2973,7 +2980,7 @@ int machines__for_each_thread(struct machines *machines,
 
 pid_t machine__get_current_tid(struct machine *machine, int cpu)
 {
-	int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+	int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
 
 	if (cpu < 0 || cpu >= nr_cpus || !machine->current_tid)
 		return -1;
@@ -2985,7 +2992,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 			     pid_t tid)
 {
 	struct thread *thread;
-	int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+	int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
 
 	if (cpu < 0)
 		return -EINVAL;
diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h
index 5b8ca93798e9..7d22ade082c8 100644
--- a/tools/perf/util/map_symbol.h
+++ b/tools/perf/util/map_symbol.h
@@ -19,5 +19,6 @@ struct addr_map_symbol {
 	u64	      addr;
 	u64	      al_addr;
 	u64	      phys_addr;
+	u64	      data_page_size;
 };
 #endif // __PERF_MAP_SYMBOL
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index ea0af0bc4314..19007e463b8a 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -17,9 +17,10 @@ unsigned int perf_mem_events__loads_ldlat = 30;
 
 #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
 
-struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
-	E("ldlat-loads",	"cpu/mem-loads,ldlat=%u/P",	"mem-loads"),
-	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
+static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=%u/P",	"cpu/events/mem-loads"),
+	E("ldlat-stores",	"cpu/mem-stores/P",		"cpu/events/mem-stores"),
+	E(NULL,			NULL,				NULL),
 };
 #undef E
 
@@ -28,19 +29,31 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
 
+struct perf_mem_event * __weak perf_mem_events__ptr(int i)
+{
+	if (i >= PERF_MEM_EVENTS__MAX)
+		return NULL;
+
+	return &perf_mem_events[i];
+}
+
 char * __weak perf_mem_events__name(int i)
 {
+	struct perf_mem_event *e = perf_mem_events__ptr(i);
+
+	if (!e)
+		return NULL;
+
 	if (i == PERF_MEM_EVENTS__LOAD) {
 		if (!mem_loads_name__init) {
 			mem_loads_name__init = true;
 			scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  perf_mem_events[i].name,
-				  perf_mem_events__loads_ldlat);
+				  e->name, perf_mem_events__loads_ldlat);
 		}
 		return mem_loads_name;
 	}
 
-	return (char *)perf_mem_events[i].name;
+	return (char *)e->name;
 }
 
 int perf_mem_events__parse(const char *str)
@@ -61,7 +74,10 @@ int perf_mem_events__parse(const char *str)
 
 	while (tok) {
 		for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-			struct perf_mem_event *e = &perf_mem_events[j];
+			struct perf_mem_event *e = perf_mem_events__ptr(j);
+
+			if (!e->tag)
+				continue;
 
 			if (strstr(e->tag, tok))
 				e->record = found = true;
@@ -90,10 +106,17 @@ int perf_mem_events__init(void)
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
 		char path[PATH_MAX];
-		struct perf_mem_event *e = &perf_mem_events[j];
+		struct perf_mem_event *e = perf_mem_events__ptr(j);
 		struct stat st;
 
-		scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s",
+		/*
+		 * If the event entry isn't valid, skip initialization
+		 * and "e->supported" will keep false.
+		 */
+		if (!e->tag)
+			continue;
+
+		scnprintf(path, PATH_MAX, "%s/devices/%s",
 			  mnt, e->sysfs_name);
 
 		if (!stat(path, &st))
@@ -108,10 +131,10 @@ void perf_mem_events__list(void)
 	int j;
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-		struct perf_mem_event *e = &perf_mem_events[j];
+		struct perf_mem_event *e = perf_mem_events__ptr(j);
 
 		fprintf(stderr, "%-13s%-*s%s\n",
-			e->tag,
+			e->tag ?: "",
 			verbose > 0 ? 25 : 0,
 			verbose > 0 ? perf_mem_events__name(j) : "",
 			e->supported ? ": available" : "");
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 904dad34f7f7..5ef178278909 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -28,16 +28,17 @@ struct mem_info {
 enum {
 	PERF_MEM_EVENTS__LOAD,
 	PERF_MEM_EVENTS__STORE,
+	PERF_MEM_EVENTS__LOAD_STORE,
 	PERF_MEM_EVENTS__MAX,
 };
 
-extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
 extern unsigned int perf_mem_events__loads_ldlat;
 
 int perf_mem_events__parse(const char *str);
 int perf_mem_events__init(void);
 
 char *perf_mem_events__name(int i);
+struct perf_mem_event *perf_mem_events__ptr(int i);
 
 void perf_mem_events__list(void);
 
diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c
index c84f5841c7ab..03a7d7b27737 100644
--- a/tools/perf/util/mem2node.c
+++ b/tools/perf/util/mem2node.c
@@ -96,7 +96,8 @@ int mem2node__init(struct mem2node *map, struct perf_env *env)
 
 	/* Cut unused entries, due to merging. */
 	tmp_entries = realloc(entries, sizeof(*entries) * j);
-	if (tmp_entries || WARN_ON_ONCE(j == 0))
+	if (tmp_entries ||
+	    WARN_ONCE(j == 0, "No memory nodes, is CONFIG_MEMORY_HOTPLUG enabled?\n"))
 		entries = tmp_entries;
 
 	for (i = 0; i < j; i++) {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 060454a17293..ee94d3e8dd65 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -279,7 +279,9 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
 			 * when then group is left.
 			 */
 			if (!has_constraint &&
-			    ev->leader != metric_events[i]->leader)
+			    ev->leader != metric_events[i]->leader &&
+			    !strcmp(ev->leader->pmu_name,
+				    metric_events[i]->leader->pmu_name))
 				break;
 			if (!strcmp(metric_events[i]->name, ev->name)) {
 				set_bit(ev->idx, evlist_used);
@@ -413,6 +415,12 @@ static bool match_metric(const char *n, const char *list)
 	return false;
 }
 
+static bool match_pe_metric(struct pmu_event *pe, const char *metric)
+{
+	return match_metric(pe->metric_group, metric) ||
+	       match_metric(pe->metric_name, metric);
+}
+
 struct mep {
 	struct rb_node nd;
 	const char *name;
@@ -491,6 +499,115 @@ static void metricgroup__print_strlist(struct strlist *metrics, bool raw)
 		putchar('\n');
 }
 
+static int metricgroup__print_pmu_event(struct pmu_event *pe,
+					bool metricgroups, char *filter,
+					bool raw, bool details,
+					struct rblist *groups,
+					struct strlist *metriclist)
+{
+	const char *g;
+	char *omg, *mg;
+
+	g = pe->metric_group;
+	if (!g && pe->metric_name) {
+		if (pe->name)
+			return 0;
+		g = "No_group";
+	}
+
+	if (!g)
+		return 0;
+
+	mg = strdup(g);
+
+	if (!mg)
+		return -ENOMEM;
+	omg = mg;
+	while ((g = strsep(&mg, ";")) != NULL) {
+		struct mep *me;
+		char *s;
+
+		g = skip_spaces(g);
+		if (*g == 0)
+			g = "No_group";
+		if (filter && !strstr(g, filter))
+			continue;
+		if (raw)
+			s = (char *)pe->metric_name;
+		else {
+			if (asprintf(&s, "%s\n%*s%s]",
+				     pe->metric_name, 8, "[", pe->desc) < 0)
+				return -1;
+			if (details) {
+				if (asprintf(&s, "%s\n%*s%s]",
+					     s, 8, "[", pe->metric_expr) < 0)
+					return -1;
+			}
+		}
+
+		if (!s)
+			continue;
+
+		if (!metricgroups) {
+			strlist__add(metriclist, s);
+		} else {
+			me = mep_lookup(groups, g);
+			if (!me)
+				continue;
+			strlist__add(me->metrics, s);
+		}
+
+		if (!raw)
+			free(s);
+	}
+	free(omg);
+
+	return 0;
+}
+
+struct metricgroup_print_sys_idata {
+	struct strlist *metriclist;
+	char *filter;
+	struct rblist *groups;
+	bool metricgroups;
+	bool raw;
+	bool details;
+};
+
+typedef int (*metricgroup_sys_event_iter_fn)(struct pmu_event *pe, void *);
+
+struct metricgroup_iter_data {
+	metricgroup_sys_event_iter_fn fn;
+	void *data;
+};
+
+static int metricgroup__sys_event_iter(struct pmu_event *pe, void *data)
+{
+	struct metricgroup_iter_data *d = data;
+	struct perf_pmu *pmu = NULL;
+
+	if (!pe->metric_expr || !pe->compat)
+		return 0;
+
+	while ((pmu = perf_pmu__scan(pmu))) {
+
+		if (!pmu->id || strcmp(pmu->id, pe->compat))
+			continue;
+
+		return d->fn(pe, d->data);
+	}
+
+	return 0;
+}
+
+static int metricgroup__print_sys_event_iter(struct pmu_event *pe, void *data)
+{
+	struct metricgroup_print_sys_idata *d = data;
+
+	return metricgroup__print_pmu_event(pe, d->metricgroups, d->filter, d->raw,
+				     d->details, d->groups, d->metriclist);
+}
+
 void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 			bool raw, bool details)
 {
@@ -501,9 +618,6 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 	struct rb_node *node, *next;
 	struct strlist *metriclist = NULL;
 
-	if (!map)
-		return;
-
 	if (!metricgroups) {
 		metriclist = strlist__new(NULL, NULL);
 		if (!metriclist)
@@ -514,67 +628,33 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 	groups.node_new = mep_new;
 	groups.node_cmp = mep_cmp;
 	groups.node_delete = mep_delete;
-	for (i = 0; ; i++) {
-		const char *g;
+	for (i = 0; map; i++) {
 		pe = &map->table[i];
 
 		if (!pe->name && !pe->metric_group && !pe->metric_name)
 			break;
 		if (!pe->metric_expr)
 			continue;
-		g = pe->metric_group;
-		if (!g && pe->metric_name) {
-			if (pe->name)
-				continue;
-			g = "No_group";
-		}
-		if (g) {
-			char *omg;
-			char *mg = strdup(g);
-
-			if (!mg)
-				return;
-			omg = mg;
-			while ((g = strsep(&mg, ";")) != NULL) {
-				struct mep *me;
-				char *s;
-
-				g = skip_spaces(g);
-				if (*g == 0)
-					g = "No_group";
-				if (filter && !strstr(g, filter))
-					continue;
-				if (raw)
-					s = (char *)pe->metric_name;
-				else {
-					if (asprintf(&s, "%s\n%*s%s]",
-						     pe->metric_name, 8, "[", pe->desc) < 0)
-						return;
-
-					if (details) {
-						if (asprintf(&s, "%s\n%*s%s]",
-							     s, 8, "[", pe->metric_expr) < 0)
-							return;
-					}
-				}
-
-				if (!s)
-					continue;
+		if (metricgroup__print_pmu_event(pe, metricgroups, filter,
+						 raw, details, &groups,
+						 metriclist) < 0)
+			return;
+	}
 
-				if (!metricgroups) {
-					strlist__add(metriclist, s);
-				} else {
-					me = mep_lookup(&groups, g);
-					if (!me)
-						continue;
-					strlist__add(me->metrics, s);
-				}
+	{
+		struct metricgroup_iter_data data = {
+			.fn = metricgroup__print_sys_event_iter,
+			.data = (void *) &(struct metricgroup_print_sys_idata){
+				.metriclist = metriclist,
+				.metricgroups = metricgroups,
+				.filter = filter,
+				.raw = raw,
+				.details = details,
+				.groups = &groups,
+			},
+		};
 
-				if (!raw)
-					free(s);
-			}
-			free(omg);
-		}
+		pmu_for_each_sys_event(metricgroup__sys_event_iter, &data);
 	}
 
 	if (!filter || !rblist__empty(&groups)) {
@@ -683,6 +763,16 @@ int __weak arch_get_runtimeparam(struct pmu_event *pe __maybe_unused)
 	return 1;
 }
 
+struct metricgroup_add_iter_data {
+	struct list_head *metric_list;
+	const char *metric;
+	struct metric **m;
+	struct expr_ids *ids;
+	int *ret;
+	bool *has_match;
+	bool metric_no_group;
+};
+
 static int __add_metric(struct list_head *metric_list,
 			struct pmu_event *pe,
 			bool metric_no_group,
@@ -792,10 +882,11 @@ static int __add_metric(struct list_head *metric_list,
 	return 0;
 }
 
-#define map_for_each_event(__pe, __idx, __map)				\
-	for (__idx = 0, __pe = &__map->table[__idx];			\
-	     __pe->name || __pe->metric_group || __pe->metric_name;	\
-	     __pe = &__map->table[++__idx])
+#define map_for_each_event(__pe, __idx, __map)					\
+	if (__map)								\
+		for (__idx = 0, __pe = &__map->table[__idx];			\
+		     __pe->name || __pe->metric_group || __pe->metric_name;	\
+		     __pe = &__map->table[++__idx])
 
 #define map_for_each_metric(__pe, __idx, __map, __metric)		\
 	map_for_each_event(__pe, __idx, __map)				\
@@ -833,7 +924,7 @@ static int recursion_check(struct metric *m, const char *id, struct expr_id **pa
 	if (ret)
 		return ret;
 
-	p = data->parent;
+	p = expr_id_data__parent(data);
 
 	while (p->parent) {
 		if (!strcmp(p->id, id)) {
@@ -854,7 +945,7 @@ static int recursion_check(struct metric *m, const char *id, struct expr_id **pa
 	}
 
 	p->id     = strdup(id);
-	p->parent = data->parent;
+	p->parent = expr_id_data__parent(data);
 	*parent   = p;
 
 	return p->id ? 0 : -ENOMEM;
@@ -963,6 +1054,29 @@ static int add_metric(struct list_head *metric_list,
 	return ret;
 }
 
+static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe,
+						  void *data)
+{
+	struct metricgroup_add_iter_data *d = data;
+	int ret;
+
+	if (!match_pe_metric(pe, d->metric))
+		return 0;
+
+	ret = add_metric(d->metric_list, pe, d->metric_no_group, d->m, NULL, d->ids);
+	if (ret)
+		return ret;
+
+	ret = resolve_metric(d->metric_no_group,
+				     d->metric_list, NULL, d->ids);
+	if (ret)
+		return ret;
+
+	*(d->has_match) = true;
+
+	return *d->ret;
+}
+
 static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 				   struct strbuf *events,
 				   struct list_head *metric_list,
@@ -993,6 +1107,22 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 			goto out;
 	}
 
+	{
+		struct metricgroup_iter_data data = {
+			.fn = metricgroup__add_metric_sys_event_iter,
+			.data = (void *) &(struct metricgroup_add_iter_data) {
+				.metric_list = &list,
+				.metric = metric,
+				.metric_no_group = metric_no_group,
+				.m = &m,
+				.ids = &ids,
+				.has_match = &has_match,
+				.ret = &ret,
+			},
+		};
+
+		pmu_for_each_sys_event(metricgroup__sys_event_iter, &data);
+	}
 	/* End of pmu events. */
 	if (!has_match) {
 		ret = -EINVAL;
@@ -1119,8 +1249,6 @@ int metricgroup__parse_groups(const struct option *opt,
 	struct evlist *perf_evlist = *(struct evlist **)opt->value;
 	struct pmu_events_map *map = perf_pmu__find_map(NULL);
 
-	if (!map)
-		return 0;
 
 	return parse_groups(perf_evlist, str, metric_no_group,
 			    metric_no_merge, NULL, metric_events, map);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 3b273580fb84..42c84adeb2fb 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -668,6 +668,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 	return ret;
 }
 
+#ifdef HAVE_LIBBPF_SUPPORT
 struct __add_bpf_event_param {
 	struct parse_events_state *parse_state;
 	struct list_head *list;
@@ -900,6 +901,30 @@ int parse_events_load_bpf(struct parse_events_state *parse_state,
 		list_splice_tail(&obj_head_config, head_config);
 	return err;
 }
+#else // HAVE_LIBBPF_SUPPORT
+int parse_events_load_bpf_obj(struct parse_events_state *parse_state,
+			      struct list_head *list __maybe_unused,
+			      struct bpf_object *obj __maybe_unused,
+			      struct list_head *head_config __maybe_unused)
+{
+	parse_events__handle_error(parse_state->error, 0,
+				   strdup("BPF support is not compiled"),
+				   strdup("Make sure libbpf-devel is available at build time."));
+	return -ENOTSUP;
+}
+
+int parse_events_load_bpf(struct parse_events_state *parse_state,
+			  struct list_head *list __maybe_unused,
+			  char *bpf_file_name __maybe_unused,
+			  bool source __maybe_unused,
+			  struct list_head *head_config __maybe_unused)
+{
+	parse_events__handle_error(parse_state->error, 0,
+				   strdup("BPF support is not compiled"),
+				   strdup("Make sure libbpf-devel is available at build time."));
+	return -ENOTSUP;
+}
+#endif // HAVE_LIBBPF_SUPPORT
 
 static int
 parse_breakpoint_type(const char *type, struct perf_event_attr *attr)
@@ -1744,7 +1769,7 @@ void parse_events__set_leader(char *name, struct list_head *list,
 	if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state))
 		return;
 
-	__perf_evlist__set_leader(list);
+	__evlist__set_leader(list);
 	leader = list_entry(list->next, struct evsel, core.node);
 	leader->group_name = name ? strdup(name) : NULL;
 }
@@ -2158,7 +2183,7 @@ int __parse_events(struct evlist *evlist, const char *str,
 	/*
 	 * Add list to the evlist even with errors to allow callers to clean up.
 	 */
-	perf_evlist__splice_list_tail(evlist, &parse_state.list);
+	evlist__splice_list_tail(evlist, &parse_state.list);
 
 	if (!ret) {
 		struct evsel *last;
diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
index e687497b3aac..a4a100425b3a 100644
--- a/tools/perf/util/parse-regs-options.c
+++ b/tools/perf/util/parse-regs-options.c
@@ -54,7 +54,7 @@ __parse_regs(const struct option *opt, const char *str, int unset, bool intr)
 #endif
 				fputc('\n', stderr);
 				/* just printing available regs */
-				return -1;
+				goto error;
 			}
 #ifdef HAVE_PERF_REGS_SUPPORT
 			for (r = sample_reg_masks; r->name; r++) {
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index e67a227c0ce7..fb0bb6684438 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -35,7 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
 		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
 		bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
 		bit_name(WEIGHT), bit_name(PHYS_ADDR), bit_name(AUX),
-		bit_name(CGROUP),
+		bit_name(CGROUP), bit_name(DATA_PAGE_SIZE),
 		{ .name = NULL, }
 	};
 #undef bit_name
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index d41caeb35cf6..44ef28302fc7 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -597,6 +597,7 @@ static struct perf_cpu_map *__pmu_cpumask(const char *path)
  * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64)
  * may have a "cpus" file.
  */
+#define SYS_TEMPLATE_ID	"./bus/event_source/devices/%s/identifier"
 #define CPUS_TEMPLATE_UNCORE	"%s/bus/event_source/devices/%s/cpumask"
 #define CPUS_TEMPLATE_CPU	"%s/bus/event_source/devices/%s/cpus"
 
@@ -635,6 +636,21 @@ static bool pmu_is_uncore(const char *name)
 	return file_available(path);
 }
 
+static char *pmu_id(const char *name)
+{
+	char path[PATH_MAX], *str;
+	size_t len;
+
+	snprintf(path, PATH_MAX, SYS_TEMPLATE_ID, name);
+
+	if (sysfs__read_str(path, &str, &len) < 0)
+		return NULL;
+
+	str[len - 1] = 0; /* remove line feed */
+
+	return str;
+}
+
 /*
  *  PMU CORE devices have different name other than cpu in sysfs on some
  *  platforms.
@@ -796,6 +812,83 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 	pmu_add_cpu_aliases_map(head, pmu, map);
 }
 
+void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data)
+{
+	int i = 0;
+
+	while (1) {
+		struct pmu_sys_events *event_table;
+		int j = 0;
+
+		event_table = &pmu_sys_event_tables[i++];
+
+		if (!event_table->table)
+			break;
+
+		while (1) {
+			struct pmu_event *pe = &event_table->table[j++];
+			int ret;
+
+			if (!pe->name && !pe->metric_group && !pe->metric_name)
+				break;
+
+			ret = fn(pe, data);
+			if (ret)
+				break;
+		}
+	}
+}
+
+struct pmu_sys_event_iter_data {
+	struct list_head *head;
+	struct perf_pmu *pmu;
+};
+
+static int pmu_add_sys_aliases_iter_fn(struct pmu_event *pe, void *data)
+{
+	struct pmu_sys_event_iter_data *idata = data;
+	struct perf_pmu *pmu = idata->pmu;
+
+	if (!pe->name) {
+		if (pe->metric_group || pe->metric_name)
+			return 0;
+		return -EINVAL;
+	}
+
+	if (!pe->compat || !pe->pmu)
+		return 0;
+
+	if (!strcmp(pmu->id, pe->compat) &&
+	    pmu_uncore_alias_match(pe->pmu, pmu->name)) {
+		__perf_pmu__new_alias(idata->head, NULL,
+				      (char *)pe->name,
+				      (char *)pe->desc,
+				      (char *)pe->event,
+				      (char *)pe->long_desc,
+				      (char *)pe->topic,
+				      (char *)pe->unit,
+				      (char *)pe->perpkg,
+				      (char *)pe->metric_expr,
+				      (char *)pe->metric_name,
+				      (char *)pe->deprecated);
+	}
+
+	return 0;
+}
+
+static void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu)
+{
+	struct pmu_sys_event_iter_data idata = {
+		.head = head,
+		.pmu = pmu,
+	};
+
+	if (!pmu->id)
+		return;
+
+	pmu_for_each_sys_event(pmu_add_sys_aliases_iter_fn, &idata);
+}
+
 struct perf_event_attr * __weak
 perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 {
@@ -847,8 +940,11 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	pmu->name = strdup(name);
 	pmu->type = type;
 	pmu->is_uncore = pmu_is_uncore(name);
+	if (pmu->is_uncore)
+		pmu->id = pmu_id(name);
 	pmu->max_precise = pmu_max_precise(name);
 	pmu_add_cpu_aliases(&aliases, pmu);
+	pmu_add_sys_aliases(&aliases, pmu);
 
 	INIT_LIST_HEAD(&pmu->format);
 	INIT_LIST_HEAD(&pmu->aliases);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index a64e9c9ce731..8164388478c6 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -30,6 +30,7 @@ struct perf_pmu_caps {
 
 struct perf_pmu {
 	char *name;
+	char *id;
 	__u32 type;
 	bool selectable;
 	bool is_uncore;
@@ -116,6 +117,8 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu);
 bool pmu_uncore_alias_match(const char *pmu_name, const char *name);
 void perf_pmu_free_alias(struct perf_pmu_alias *alias);
 
+typedef int (*pmu_sys_event_iter_fn)(struct pmu_event *pe, void *data);
+void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data);
 int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 
 int perf_pmu__caps_parse(struct perf_pmu *pmu);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 064b63a6a3f3..bbecb449ea94 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -791,7 +791,7 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note,
 					const char *sdtgrp)
 {
 	struct strbuf buf;
-	char *ret = NULL, **args;
+	char *ret = NULL;
 	int i, args_count, err;
 	unsigned long long ref_ctr_offset;
 
@@ -813,12 +813,19 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note,
 		goto out;
 
 	if (note->args) {
-		args = argv_split(note->args, &args_count);
+		char **args = argv_split(note->args, &args_count);
+
+		if (args == NULL)
+			goto error;
 
 		for (i = 0; i < args_count; ++i) {
-			if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0)
+			if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0) {
+				argv_free(args);
 				goto error;
+			}
 		}
+
+		argv_free(args);
 	}
 
 out:
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index ae8edde7c50e..cc5ade85a33f 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -1055,7 +1055,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		if (pyevent == NULL)
 			return PyErr_NoMemory();
 
-		evsel = perf_evlist__event2evsel(evlist, event);
+		evsel = evlist__event2evsel(evlist, event);
 		if (!evsel) {
 			Py_INCREF(Py_None);
 			return Py_None;
@@ -1089,7 +1089,7 @@ static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist,
 		return NULL;
 
 	if (group)
-		perf_evlist__set_leader(evlist);
+		evlist__set_leader(evlist);
 
 	if (evlist__open(evlist) < 0) {
 		PyErr_SetFromErrno(PyExc_OSError);
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 07e4b96a6625..e70c9dd04567 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -89,8 +89,7 @@ static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *ev
 			    leader->core.attr.sample_type;
 }
 
-void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
-			 struct callchain_param *callchain)
+void evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain)
 {
 	struct evsel *evsel;
 	bool use_sample_identifier = false;
@@ -102,7 +101,7 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
 	 * since some might depend on this info.
 	 */
 	if (opts->group)
-		perf_evlist__set_leader(evlist);
+		evlist__set_leader(evlist);
 
 	if (evlist->core.cpus->map[0] < 0)
 		opts->no_inherit = true;
@@ -144,7 +143,7 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts,
 			evsel__set_sample_id(evsel, use_sample_identifier);
 	}
 
-	perf_evlist__set_id_pos(evlist);
+	evlist__set_id_pos(evlist);
 }
 
 static int get_max_rate(unsigned int *rate)
@@ -217,7 +216,7 @@ int record_opts__config(struct record_opts *opts)
 	return record_opts__config_freq(opts);
 }
 
-bool perf_evlist__can_select_event(struct evlist *evlist, const char *str)
+bool evlist__can_select_event(struct evlist *evlist, const char *str)
 {
 	struct evlist *temp_evlist;
 	struct evsel *evsel;
diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
index 266760ac9143..694b351dcd27 100644
--- a/tools/perf/util/record.h
+++ b/tools/perf/util/record.h
@@ -22,6 +22,7 @@ struct record_opts {
 	bool	      raw_samples;
 	bool	      sample_address;
 	bool	      sample_phys_addr;
+	bool	      sample_data_page_size;
 	bool	      sample_weight;
 	bool	      sample_time;
 	bool	      sample_time_set;
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index f8861998e5bd..078a71773565 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -96,9 +96,9 @@
  * |    than PERF_RECORD_USER_TYPE_START) are handled by
  * |    perf_session__process_user_event(see below)
  * |  - Those generated by the kernel are handled by
- * |    perf_evlist__parse_sample_timestamp()
+ * |    evlist__parse_sample_timestamp()
  * |
- * perf_evlist__parse_sample_timestamp()
+ * evlist__parse_sample_timestamp()
  * |  Extract time stamp from sample data.
  * |
  * perf_session__queue_event()
@@ -932,7 +932,7 @@ s390_cpumsf_process_event(struct perf_session *session,
 	if (event->header.type == PERF_RECORD_SAMPLE &&
 	    sample->raw_size) {
 		/* Handle event with raw data */
-		ev_bc000 = perf_evlist__event2evsel(session->evlist, event);
+		ev_bc000 = evlist__event2evsel(session->evlist, event);
 		if (ev_bc000 &&
 		    ev_bc000->core.attr.config == PERF_EVENT_CPUM_CF_DIAG)
 			err = s390_cpumcf_dumpctr(sf, sample);
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
index 05b43ab4eeef..cfcf8d534d76 100644
--- a/tools/perf/util/s390-sample-raw.c
+++ b/tools/perf/util/s390-sample-raw.c
@@ -197,15 +197,14 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample)
  * its raw data.
  * The function is only invoked when the dump flag -D is set.
  */
-void perf_evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event,
-				  struct perf_sample *sample)
+void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
 {
 	struct evsel *ev_bc000;
 
 	if (event->header.type != PERF_RECORD_SAMPLE)
 		return;
 
-	ev_bc000 = perf_evlist__event2evsel(evlist, event);
+	ev_bc000 = evlist__event2evsel(evlist, event);
 	if (ev_bc000 == NULL ||
 	    ev_bc000->core.attr.config != PERF_EVENT_CPUM_CF_DIAG)
 		return;
diff --git a/tools/perf/util/sample-raw.c b/tools/perf/util/sample-raw.c
index e84bbe0e441a..cde5cd3ce49b 100644
--- a/tools/perf/util/sample-raw.c
+++ b/tools/perf/util/sample-raw.c
@@ -9,10 +9,10 @@
  * Check platform the perf data file was created on and perform platform
  * specific interpretation.
  */
-void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist)
+void evlist__init_trace_event_sample_raw(struct evlist *evlist)
 {
 	const char *arch_pf = perf_env__arch(evlist->env);
 
 	if (arch_pf && !strcmp("s390", arch_pf))
-		evlist->trace_event_sample_raw = perf_evlist__s390_sample_raw;
+		evlist->trace_event_sample_raw = evlist__s390_sample_raw;
 }
diff --git a/tools/perf/util/sample-raw.h b/tools/perf/util/sample-raw.h
index afe1491a117e..4be84a5510cf 100644
--- a/tools/perf/util/sample-raw.h
+++ b/tools/perf/util/sample-raw.h
@@ -6,9 +6,6 @@ struct evlist;
 union perf_event;
 struct perf_sample;
 
-void perf_evlist__s390_sample_raw(struct evlist *evlist,
-				  union perf_event *event,
-				  struct perf_sample *sample);
-
-void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist);
+void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample);
+void evlist__init_trace_event_sample_raw(struct evlist *evlist);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 098080287c68..25adbcce0281 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -32,6 +32,7 @@
 #include "ui/progress.h"
 #include "../perf.h"
 #include "arch/common.h"
+#include "units.h"
 #include <internal/lib.h>
 
 #ifdef HAVE_ZSTD_SUPPORT
@@ -125,7 +126,7 @@ static int perf_session__open(struct perf_session *session)
 		return -1;
 	}
 
-	if (!perf_evlist__valid_read_format(session->evlist)) {
+	if (!evlist__valid_read_format(session->evlist)) {
 		pr_err("non matching read_format\n");
 		return -1;
 	}
@@ -135,7 +136,7 @@ static int perf_session__open(struct perf_session *session)
 
 void perf_session__set_id_hdr_size(struct perf_session *session)
 {
-	u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist);
+	u16 id_hdr_size = evlist__id_hdr_size(session->evlist);
 
 	machines__set_id_hdr_size(&session->machines, id_hdr_size);
 }
@@ -221,7 +222,7 @@ struct perf_session *perf_session__new(struct perf_data *data,
 				perf_session__set_comm_exec(session);
 			}
 
-			perf_evlist__init_trace_event_sample_raw(session->evlist);
+			evlist__init_trace_event_sample_raw(session->evlist);
 
 			/* Open the directory data. */
 			if (data->is_dir) {
@@ -1191,9 +1192,7 @@ static void stack_user__printf(struct stack_dump *dump)
 	       dump->size, dump->offset);
 }
 
-static void perf_evlist__print_tstamp(struct evlist *evlist,
-				       union perf_event *event,
-				       struct perf_sample *sample)
+static void evlist__print_tstamp(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
 {
 	u64 sample_type = __evlist__combined_sample_type(evlist);
 
@@ -1254,16 +1253,25 @@ static void dump_event(struct evlist *evlist, union perf_event *event,
 		evlist->trace_event_sample_raw(evlist, event, sample);
 
 	if (sample)
-		perf_evlist__print_tstamp(evlist, event, sample);
+		evlist__print_tstamp(evlist, event, sample);
 
 	printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset,
 	       event->header.size, perf_event__name(event->header.type));
 }
 
+char *get_page_size_name(u64 size, char *str)
+{
+	if (!size || !unit_number__scnprintf(str, PAGE_SIZE_NAME_LEN, size))
+		snprintf(str, PAGE_SIZE_NAME_LEN, "%s", "N/A");
+
+	return str;
+}
+
 static void dump_sample(struct evsel *evsel, union perf_event *event,
 			struct perf_sample *sample)
 {
 	u64 sample_type;
+	char str[PAGE_SIZE_NAME_LEN];
 
 	if (!dump_trace)
 		return;
@@ -1298,6 +1306,9 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr);
 
+	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		printf(" .. data page size: %s\n", get_page_size_name(sample->data_page_size, str));
+
 	if (sample_type & PERF_SAMPLE_TRANSACTION)
 		printf("... transaction: %" PRIx64 "\n", sample->transaction);
 
@@ -1364,7 +1375,7 @@ static int deliver_sample_value(struct evlist *evlist,
 				struct sample_read_value *v,
 				struct machine *machine)
 {
-	struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id);
+	struct perf_sample_id *sid = evlist__id2sid(evlist, v->id);
 	struct evsel *evsel;
 
 	if (sid) {
@@ -1409,13 +1420,9 @@ static int deliver_sample_group(struct evlist *evlist,
 	return ret;
 }
 
-static int
- perf_evlist__deliver_sample(struct evlist *evlist,
-			     struct perf_tool *tool,
-			     union  perf_event *event,
-			     struct perf_sample *sample,
-			     struct evsel *evsel,
-			     struct machine *machine)
+static int evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool,
+				  union  perf_event *event, struct perf_sample *sample,
+				  struct evsel *evsel, struct machine *machine)
 {
 	/* We know evsel != NULL. */
 	u64 sample_type = evsel->core.attr.sample_type;
@@ -1445,7 +1452,7 @@ static int machines__deliver_event(struct machines *machines,
 
 	dump_event(evlist, event, file_offset, sample);
 
-	evsel = perf_evlist__id2evsel(evlist, sample->id);
+	evsel = evlist__id2evsel(evlist, sample->id);
 
 	machine = machines__find_for_cpumode(machines, event, sample);
 
@@ -1460,7 +1467,7 @@ static int machines__deliver_event(struct machines *machines,
 			++evlist->stats.nr_unprocessable_samples;
 			return 0;
 		}
-		return perf_evlist__deliver_sample(evlist, tool, event, sample, evsel, machine);
+		return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine);
 	case PERF_RECORD_MMAP:
 		return tool->mmap(tool, event, sample, machine);
 	case PERF_RECORD_MMAP2:
@@ -1523,9 +1530,8 @@ static int perf_session__deliver_event(struct perf_session *session,
 				       u64 file_offset)
 {
 	struct perf_sample sample;
-	int ret;
+	int ret = evlist__parse_sample(session->evlist, event, &sample);
 
-	ret = perf_evlist__parse_sample(session->evlist, event, &sample);
 	if (ret) {
 		pr_err("Can't parse sample, err = %d\n", ret);
 		return ret;
@@ -1697,7 +1703,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 out_parse_sample:
 
 	if (sample && event->header.type < PERF_RECORD_USER_TYPE_START &&
-	    perf_evlist__parse_sample(session->evlist, event, sample))
+	    evlist__parse_sample(session->evlist, event, sample))
 		return -1;
 
 	*event_ptr = event;
@@ -1754,7 +1760,7 @@ static s64 perf_session__process_event(struct perf_session *session,
 	if (tool->ordered_events) {
 		u64 timestamp = -1ULL;
 
-		ret = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
+		ret = evlist__parse_sample_timestamp(evlist, event, &timestamp);
 		if (ret && ret != -1)
 			return ret;
 
@@ -1937,7 +1943,6 @@ static int __perf_session__process_pipe_events(struct perf_session *session)
 {
 	struct ordered_events *oe = &session->ordered_events;
 	struct perf_tool *tool = session->tool;
-	int fd = perf_data__fd(session->data);
 	union perf_event *event;
 	uint32_t size, cur_size = 0;
 	void *buf = NULL;
@@ -1957,7 +1962,8 @@ static int __perf_session__process_pipe_events(struct perf_session *session)
 	ordered_events__set_copy_on_queue(oe, true);
 more:
 	event = buf;
-	err = readn(fd, event, sizeof(struct perf_event_header));
+	err = perf_data__read(session->data, event,
+			      sizeof(struct perf_event_header));
 	if (err <= 0) {
 		if (err == 0)
 			goto done;
@@ -1989,7 +1995,8 @@ more:
 	p += sizeof(struct perf_event_header);
 
 	if (size - sizeof(struct perf_event_header)) {
-		err = readn(fd, p, size - sizeof(struct perf_event_header));
+		err = perf_data__read(session->data, p,
+				      size - sizeof(struct perf_event_header));
 		if (err <= 0) {
 			if (err == 0) {
 				pr_err("unexpected end of event stream\n");
@@ -2397,7 +2404,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 {
 	int i, err = -1;
 	struct perf_cpu_map *map;
-	int nr_cpus = min(session->header.env.nr_cpus_online, MAX_NR_CPUS);
+	int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS);
 
 	for (i = 0; i < PERF_TYPE_MAX; ++i) {
 		struct evsel *evsel;
@@ -2476,7 +2483,7 @@ int perf_event__process_id_index(struct perf_session *session,
 			fprintf(stdout,	"  tid: %"PRI_ld64"\n", e->tid);
 		}
 
-		sid = perf_evlist__id2sid(evlist, e->id);
+		sid = evlist__id2sid(evlist, e->id);
 		if (!sid)
 			return -ENOENT;
 		sid->idx = e->idx;
diff --git a/tools/perf/util/sideband_evlist.c b/tools/perf/util/sideband_evlist.c
index ded9ced02797..748371ac22be 100644
--- a/tools/perf/util/sideband_evlist.c
+++ b/tools/perf/util/sideband_evlist.c
@@ -12,8 +12,8 @@
 #include <sched.h>
 #include <stdbool.h>
 
-int perf_evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
-			      evsel__sb_cb_t cb, void *data)
+int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr,
+			 evsel__sb_cb_t cb, void *data)
 {
 	struct evsel *evsel;
 
@@ -62,7 +62,7 @@ static void *perf_evlist__poll_thread(void *arg)
 			if (perf_mmap__read_init(&map->core))
 				continue;
 			while ((event = perf_mmap__read_event(&map->core)) != NULL) {
-				struct evsel *evsel = perf_evlist__event2evsel(evlist, event);
+				struct evsel *evsel = evlist__event2evsel(evlist, event);
 
 				if (evsel && evsel->side_band.cb)
 					evsel->side_band.cb(event, evsel->side_band.data);
@@ -94,14 +94,14 @@ void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data)
       }
 }
 
-int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target)
+int evlist__start_sb_thread(struct evlist *evlist, struct target *target)
 {
 	struct evsel *counter;
 
 	if (!evlist)
 		return 0;
 
-	if (perf_evlist__create_maps(evlist, target))
+	if (evlist__create_maps(evlist, target))
 		goto out_delete_evlist;
 
 	if (evlist->core.nr_entries > 1) {
@@ -110,7 +110,7 @@ int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target)
 		evlist__for_each_entry(evlist, counter)
 			evsel__set_sample_id(counter, can_sample_identifier);
 
-		perf_evlist__set_id_pos(evlist);
+		evlist__set_id_pos(evlist);
 	}
 
 	evlist__for_each_entry(evlist, counter) {
@@ -138,7 +138,7 @@ out_delete_evlist:
 	return -1;
 }
 
-void perf_evlist__stop_sb_thread(struct evlist *evlist)
+void evlist__stop_sb_thread(struct evlist *evlist)
 {
 	if (!evlist)
 		return;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index d42339df20f8..80907bc32683 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1463,6 +1463,35 @@ struct sort_entry sort_mem_phys_daddr = {
 };
 
 static int64_t
+sort__data_page_size_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	uint64_t l = 0, r = 0;
+
+	if (left->mem_info)
+		l = left->mem_info->daddr.data_page_size;
+	if (right->mem_info)
+		r = right->mem_info->daddr.data_page_size;
+
+	return (int64_t)(r - l);
+}
+
+static int hist_entry__data_page_size_snprintf(struct hist_entry *he, char *bf,
+					  size_t size, unsigned int width)
+{
+	char str[PAGE_SIZE_NAME_LEN];
+
+	return repsep_snprintf(bf, size, "%-*s", width,
+			       get_page_size_name(he->mem_info->daddr.data_page_size, str));
+}
+
+struct sort_entry sort_mem_data_page_size = {
+	.se_header	= "Data Page Size",
+	.se_cmp		= sort__data_page_size_cmp,
+	.se_snprintf	= hist_entry__data_page_size_snprintf,
+	.se_width_idx	= HISTC_MEM_DATA_PAGE_SIZE,
+};
+
+static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	if (!left->branch_info || !right->branch_info)
@@ -1740,6 +1769,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
 	DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
 	DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
 	DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr),
+	DIM(SORT_MEM_DATA_PAGE_SIZE, "data_page_size", sort_mem_data_page_size),
 };
 
 #undef DIM
@@ -2756,7 +2786,7 @@ static const char *get_default_sort_order(struct evlist *evlist)
 
 	BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
 
-	if (evlist == NULL || perf_evlist__empty(evlist))
+	if (evlist == NULL || evlist__empty(evlist))
 		goto out_no_evlist;
 
 	evlist__for_each_entry(evlist, evsel) {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 66d39c4cfe2b..e50f2b695bc4 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -255,6 +255,7 @@ enum sort_type {
 	SORT_MEM_DCACHELINE,
 	SORT_MEM_IADDR_SYMBOL,
 	SORT_MEM_PHYS_DADDR,
+	SORT_MEM_DATA_PAGE_SIZE,
 };
 
 /*
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index a963b5b8eb72..583ae4f09c5d 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -68,15 +68,15 @@ static void print_cgroup(struct perf_stat_config *config, struct evsel *evsel)
 
 
 static void aggr_printout(struct perf_stat_config *config,
-			  struct evsel *evsel, int id, int nr)
+			  struct evsel *evsel, struct aggr_cpu_id id, int nr)
 {
 	switch (config->aggr_mode) {
 	case AGGR_CORE:
 		fprintf(config->output, "S%d-D%d-C%*d%s%*d%s",
-			cpu_map__id_to_socket(id),
-			cpu_map__id_to_die(id),
+			id.socket,
+			id.die,
 			config->csv_output ? 0 : -8,
-			cpu_map__id_to_cpu(id),
+			id.core,
 			config->csv_sep,
 			config->csv_output ? 0 : 4,
 			nr,
@@ -84,9 +84,9 @@ static void aggr_printout(struct perf_stat_config *config,
 		break;
 	case AGGR_DIE:
 		fprintf(config->output, "S%d-D%*d%s%*d%s",
-			cpu_map__id_to_socket(id << 16),
+			id.socket,
 			config->csv_output ? 0 : -8,
-			cpu_map__id_to_die(id << 16),
+			id.die,
 			config->csv_sep,
 			config->csv_output ? 0 : 4,
 			nr,
@@ -95,7 +95,7 @@ static void aggr_printout(struct perf_stat_config *config,
 	case AGGR_SOCKET:
 		fprintf(config->output, "S%*d%s%*d%s",
 			config->csv_output ? 0 : -5,
-			id,
+			id.socket,
 			config->csv_sep,
 			config->csv_output ? 0 : 4,
 			nr,
@@ -104,7 +104,7 @@ static void aggr_printout(struct perf_stat_config *config,
 	case AGGR_NODE:
 		fprintf(config->output, "N%*d%s%*d%s",
 			config->csv_output ? 0 : -5,
-			id,
+			id.node,
 			config->csv_sep,
 			config->csv_output ? 0 : 4,
 			nr,
@@ -113,23 +113,23 @@ static void aggr_printout(struct perf_stat_config *config,
 	case AGGR_NONE:
 		if (evsel->percore && !config->percore_show_thread) {
 			fprintf(config->output, "S%d-D%d-C%*d%s",
-				cpu_map__id_to_socket(id),
-				cpu_map__id_to_die(id),
+				id.socket,
+				id.die,
 				config->csv_output ? 0 : -3,
-				cpu_map__id_to_cpu(id), config->csv_sep);
-		} else if (id > -1) {
+				id.core, config->csv_sep);
+		} else if (id.core > -1) {
 			fprintf(config->output, "CPU%*d%s",
 				config->csv_output ? 0 : -7,
-				evsel__cpus(evsel)->map[id],
+				evsel__cpus(evsel)->map[id.core],
 				config->csv_sep);
 		}
 		break;
 	case AGGR_THREAD:
 		fprintf(config->output, "%*s-%*d%s",
 			config->csv_output ? 0 : 16,
-			perf_thread_map__comm(evsel->core.threads, id),
+			perf_thread_map__comm(evsel->core.threads, id.thread),
 			config->csv_output ? 0 : -8,
-			perf_thread_map__pid(evsel->core.threads, id),
+			perf_thread_map__pid(evsel->core.threads, id.thread),
 			config->csv_sep);
 		break;
 	case AGGR_GLOBAL:
@@ -144,7 +144,8 @@ struct outstate {
 	bool newline;
 	const char *prefix;
 	int  nfields;
-	int  id, nr;
+	int  nr;
+	struct aggr_cpu_id id;
 	struct evsel *evsel;
 };
 
@@ -319,13 +320,13 @@ static void print_metric_header(struct perf_stat_config *config,
 }
 
 static int first_shadow_cpu(struct perf_stat_config *config,
-			    struct evsel *evsel, int id)
+			    struct evsel *evsel, struct aggr_cpu_id id)
 {
 	struct evlist *evlist = evsel->evlist;
 	int i;
 
 	if (config->aggr_mode == AGGR_NONE)
-		return id;
+		return id.core;
 
 	if (!config->aggr_get_id)
 		return 0;
@@ -333,14 +334,17 @@ static int first_shadow_cpu(struct perf_stat_config *config,
 	for (i = 0; i < evsel__nr_cpus(evsel); i++) {
 		int cpu2 = evsel__cpus(evsel)->map[i];
 
-		if (config->aggr_get_id(config, evlist->core.cpus, cpu2) == id)
+		if (cpu_map__compare_aggr_cpu_id(
+					config->aggr_get_id(config, evlist->core.cpus, cpu2),
+					id)) {
 			return cpu2;
+		}
 	}
 	return 0;
 }
 
 static void abs_printout(struct perf_stat_config *config,
-			 int id, int nr, struct evsel *evsel, double avg)
+			 struct aggr_cpu_id id, int nr, struct evsel *evsel, double avg)
 {
 	FILE *output = config->output;
 	double sc =  evsel->scale;
@@ -393,7 +397,7 @@ static bool is_mixed_hw_group(struct evsel *counter)
 	return false;
 }
 
-static void printout(struct perf_stat_config *config, int id, int nr,
+static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int nr,
 		     struct evsel *counter, double uval,
 		     char *prefix, u64 run, u64 ena, double noise,
 		     struct runtime_stat *st)
@@ -496,7 +500,8 @@ static void printout(struct perf_stat_config *config, int id, int nr,
 static void aggr_update_shadow(struct perf_stat_config *config,
 			       struct evlist *evlist)
 {
-	int cpu, s2, id, s;
+	int cpu, s;
+	struct aggr_cpu_id s2, id;
 	u64 val;
 	struct evsel *counter;
 
@@ -506,7 +511,7 @@ static void aggr_update_shadow(struct perf_stat_config *config,
 			val = 0;
 			for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
 				s2 = config->aggr_get_id(config, evlist->core.cpus, cpu);
-				if (s2 != id)
+				if (!cpu_map__compare_aggr_cpu_id(s2, id))
 					continue;
 				val += perf_counts(counter->counts, cpu, 0)->val;
 			}
@@ -584,7 +589,7 @@ static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
 
 struct aggr_data {
 	u64 ena, run, val;
-	int id;
+	struct aggr_cpu_id id;
 	int nr;
 	int cpu;
 };
@@ -593,13 +598,14 @@ static void aggr_cb(struct perf_stat_config *config,
 		    struct evsel *counter, void *data, bool first)
 {
 	struct aggr_data *ad = data;
-	int cpu, s2;
+	int cpu;
+	struct aggr_cpu_id s2;
 
 	for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
 		struct perf_counts_values *counts;
 
 		s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu);
-		if (s2 != ad->id)
+		if (!cpu_map__compare_aggr_cpu_id(s2, ad->id))
 			continue;
 		if (first)
 			ad->nr++;
@@ -628,7 +634,8 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
 	struct aggr_data ad;
 	FILE *output = config->output;
 	u64 ena, run, val;
-	int id, nr;
+	int nr;
+	struct aggr_cpu_id id;
 	double uval;
 
 	ad.id = id = config->aggr_map->map[s];
@@ -649,8 +656,12 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
 		fprintf(output, "%s", prefix);
 
 	uval = val * counter->scale;
-	printout(config, cpu != -1 ? cpu : id, nr, counter, uval, prefix,
-		 run, ena, 1.0, &rt_stat);
+	if (cpu != -1) {
+		id = cpu_map__empty_aggr_cpu_id();
+		id.core = cpu;
+	}
+	printout(config, id, nr, counter, uval,
+		 prefix, run, ena, 1.0, &rt_stat);
 	if (!metric_only)
 		fputc('\n', output);
 }
@@ -728,7 +739,8 @@ static struct perf_aggr_thread_value *sort_aggr_thread(
 			continue;
 
 		buf[i].counter = counter;
-		buf[i].id = thread;
+		buf[i].id = cpu_map__empty_aggr_cpu_id();
+		buf[i].id.thread = thread;
 		buf[i].uval = uval;
 		buf[i].val = val;
 		buf[i].run = run;
@@ -751,7 +763,8 @@ static void print_aggr_thread(struct perf_stat_config *config,
 	FILE *output = config->output;
 	int nthreads = perf_thread_map__nr(counter->core.threads);
 	int ncpus = perf_cpu_map__nr(counter->core.cpus);
-	int thread, sorted_threads, id;
+	int thread, sorted_threads;
+	struct aggr_cpu_id id;
 	struct perf_aggr_thread_value *buf;
 
 	buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target);
@@ -768,7 +781,7 @@ static void print_aggr_thread(struct perf_stat_config *config,
 		if (config->stats)
 			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
 				 prefix, buf[thread].run, buf[thread].ena, 1.0,
-				 &config->stats[id]);
+				 &config->stats[id.thread]);
 		else
 			printout(config, id, 0, buf[thread].counter, buf[thread].uval,
 				 prefix, buf[thread].run, buf[thread].ena, 1.0,
@@ -814,8 +827,8 @@ static void print_counter_aggr(struct perf_stat_config *config,
 		fprintf(output, "%s", prefix);
 
 	uval = cd.avg * counter->scale;
-	printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
-		 cd.avg, &rt_stat);
+	printout(config, cpu_map__empty_aggr_cpu_id(), 0, counter, uval, prefix, cd.avg_running,
+		 cd.avg_enabled, cd.avg, &rt_stat);
 	if (!metric_only)
 		fprintf(output, "\n");
 }
@@ -842,6 +855,7 @@ static void print_counter(struct perf_stat_config *config,
 	u64 ena, run, val;
 	double uval;
 	int cpu;
+	struct aggr_cpu_id id;
 
 	for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
 		struct aggr_data ad = { .cpu = cpu };
@@ -856,8 +870,10 @@ static void print_counter(struct perf_stat_config *config,
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
-			 &rt_stat);
+		id = cpu_map__empty_aggr_cpu_id();
+		id.core = cpu;
+		printout(config, id, 0, counter, uval, prefix,
+			 run, ena, 1.0, &rt_stat);
 
 		fputc('\n', output);
 	}
@@ -872,6 +888,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 	struct evsel *counter;
 	u64 ena, run, val;
 	double uval;
+	struct aggr_cpu_id id;
 
 	nrcpus = evlist->core.cpus->nr;
 	for (cpu = 0; cpu < nrcpus; cpu++) {
@@ -880,8 +897,10 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 		if (prefix)
 			fputs(prefix, config->output);
 		evlist__for_each_entry(evlist, counter) {
+			id = cpu_map__empty_aggr_cpu_id();
+			id.core = cpu;
 			if (first) {
-				aggr_printout(config, counter, cpu, 0);
+				aggr_printout(config, counter, id, 0);
 				first = false;
 			}
 			val = perf_counts(counter->counts, cpu, 0)->val;
@@ -889,8 +908,8 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 			run = perf_counts(counter->counts, cpu, 0)->run;
 
 			uval = val * counter->scale;
-			printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0,
-				 &rt_stat);
+			printout(config, id, 0, counter, uval, prefix,
+				 run, ena, 1.0, &rt_stat);
 		}
 		fputc('\n', config->output);
 	}
@@ -1140,14 +1159,15 @@ static void print_footer(struct perf_stat_config *config)
 static void print_percore_thread(struct perf_stat_config *config,
 				 struct evsel *counter, char *prefix)
 {
-	int s, s2, id;
+	int s;
+	struct aggr_cpu_id s2, id;
 	bool first = true;
 
 	for (int i = 0; i < evsel__nr_cpus(counter); i++) {
 		s2 = config->aggr_get_id(config, evsel__cpus(counter), i);
 		for (s = 0; s < config->aggr_map->nr; s++) {
 			id = config->aggr_map->map[s];
-			if (s2 == id)
+			if (cpu_map__compare_aggr_cpu_id(s2, id))
 				break;
 		}
 
@@ -1184,12 +1204,8 @@ static void print_percore(struct perf_stat_config *config,
 		fputc('\n', output);
 }
 
-void
-perf_evlist__print_counters(struct evlist *evlist,
-			    struct perf_stat_config *config,
-			    struct target *_target,
-			    struct timespec *ts,
-			    int argc, const char **argv)
+void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
+			    struct target *_target, struct timespec *ts, int argc, const char **argv)
 {
 	bool metric_only = config->metric_only;
 	int interval = config->interval;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 901265127e36..12eafd12a693 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -8,6 +8,7 @@
 #include "evlist.h"
 #include "expr.h"
 #include "metricgroup.h"
+#include "cgroup.h"
 #include <linux/zalloc.h>
 
 /*
@@ -28,6 +29,7 @@ struct saved_value {
 	enum stat_type type;
 	int ctx;
 	int cpu;
+	struct cgroup *cgrp;
 	struct runtime_stat *stat;
 	struct stats stats;
 	u64 metric_total;
@@ -57,6 +59,9 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
 	if (a->ctx != b->ctx)
 		return a->ctx - b->ctx;
 
+	if (a->cgrp != b->cgrp)
+		return (char *)a->cgrp < (char *)b->cgrp ? -1 : +1;
+
 	if (a->evsel == NULL && b->evsel == NULL) {
 		if (a->stat == b->stat)
 			return 0;
@@ -100,7 +105,8 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel,
 					      bool create,
 					      enum stat_type type,
 					      int ctx,
-					      struct runtime_stat *st)
+					      struct runtime_stat *st,
+					      struct cgroup *cgrp)
 {
 	struct rblist *rblist;
 	struct rb_node *nd;
@@ -110,10 +116,15 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel,
 		.type = type,
 		.ctx = ctx,
 		.stat = st,
+		.cgrp = cgrp,
 	};
 
 	rblist = &st->value_list;
 
+	/* don't use context info for clock events */
+	if (type == STAT_NSECS)
+		dm.ctx = 0;
+
 	nd = rblist__find(rblist, &dm);
 	if (nd)
 		return container_of(nd, struct saved_value, rb_node);
@@ -191,12 +202,18 @@ void perf_stat__reset_shadow_per_stat(struct runtime_stat *st)
 	reset_stat(st);
 }
 
+struct runtime_stat_data {
+	int ctx;
+	struct cgroup *cgrp;
+};
+
 static void update_runtime_stat(struct runtime_stat *st,
 				enum stat_type type,
-				int ctx, int cpu, u64 count)
+				int cpu, u64 count,
+				struct runtime_stat_data *rsd)
 {
-	struct saved_value *v = saved_value_lookup(NULL, cpu, true,
-						   type, ctx, st);
+	struct saved_value *v = saved_value_lookup(NULL, cpu, true, type,
+						   rsd->ctx, st, rsd->cgrp);
 
 	if (v)
 		update_stats(&v->stats, count);
@@ -210,82 +227,86 @@ static void update_runtime_stat(struct runtime_stat *st,
 void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
 				    int cpu, struct runtime_stat *st)
 {
-	int ctx = evsel_context(counter);
 	u64 count_ns = count;
 	struct saved_value *v;
+	struct runtime_stat_data rsd = {
+		.ctx = evsel_context(counter),
+		.cgrp = counter->cgrp,
+	};
 
 	count *= counter->scale;
 
 	if (evsel__is_clock(counter))
-		update_runtime_stat(st, STAT_NSECS, 0, cpu, count_ns);
+		update_runtime_stat(st, STAT_NSECS, cpu, count_ns, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-		update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count);
+		update_runtime_stat(st, STAT_CYCLES, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
-		update_runtime_stat(st, STAT_CYCLES_IN_TX, ctx, cpu, count);
+		update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TRANSACTION_START))
-		update_runtime_stat(st, STAT_TRANSACTION, ctx, cpu, count);
+		update_runtime_stat(st, STAT_TRANSACTION, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, ELISION_START))
-		update_runtime_stat(st, STAT_ELISION, ctx, cpu, count);
+		update_runtime_stat(st, STAT_ELISION, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
 		update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
 		update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
 		update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
 		update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
 		update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
 		update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
 		update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
 		update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
 		update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
 		update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
 		update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-		update_runtime_stat(st, STAT_BRANCHES, ctx, cpu, count);
+		update_runtime_stat(st, STAT_BRANCHES, cpu, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
-		update_runtime_stat(st, STAT_CACHEREFS, ctx, cpu, count);
+		update_runtime_stat(st, STAT_CACHEREFS, cpu, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
-		update_runtime_stat(st, STAT_L1_DCACHE, ctx, cpu, count);
+		update_runtime_stat(st, STAT_L1_DCACHE, cpu, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
-		update_runtime_stat(st, STAT_L1_ICACHE, ctx, cpu, count);
+		update_runtime_stat(st, STAT_L1_ICACHE, cpu, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL))
-		update_runtime_stat(st, STAT_LL_CACHE, ctx, cpu, count);
+		update_runtime_stat(st, STAT_LL_CACHE, cpu, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
-		update_runtime_stat(st, STAT_DTLB_CACHE, ctx, cpu, count);
+		update_runtime_stat(st, STAT_DTLB_CACHE, cpu, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
-		update_runtime_stat(st, STAT_ITLB_CACHE, ctx, cpu, count);
+		update_runtime_stat(st, STAT_ITLB_CACHE, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, SMI_NUM))
-		update_runtime_stat(st, STAT_SMI_NUM, ctx, cpu, count);
+		update_runtime_stat(st, STAT_SMI_NUM, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, APERF))
-		update_runtime_stat(st, STAT_APERF, ctx, cpu, count);
+		update_runtime_stat(st, STAT_APERF, cpu, count, &rsd);
 
 	if (counter->collect_stat) {
-		v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st);
+		v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st,
+				       rsd.cgrp);
 		update_stats(&v->stats, count);
 		if (counter->metric_leader)
 			v->metric_total += count;
 	} else if (counter->metric_leader) {
 		v = saved_value_lookup(counter->metric_leader,
-				       cpu, true, STAT_NONE, 0, st);
+				       cpu, true, STAT_NONE, 0, st, rsd.cgrp);
 		v->metric_total += count;
 		v->metric_other++;
 	}
@@ -422,11 +443,12 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
 }
 
 static double runtime_stat_avg(struct runtime_stat *st,
-			       enum stat_type type, int ctx, int cpu)
+			       enum stat_type type, int cpu,
+			       struct runtime_stat_data *rsd)
 {
 	struct saved_value *v;
 
-	v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+	v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
 	if (!v)
 		return 0.0;
 
@@ -434,11 +456,12 @@ static double runtime_stat_avg(struct runtime_stat *st,
 }
 
 static double runtime_stat_n(struct runtime_stat *st,
-			     enum stat_type type, int ctx, int cpu)
+			     enum stat_type type, int cpu,
+			     struct runtime_stat_data *rsd)
 {
 	struct saved_value *v;
 
-	v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+	v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
 	if (!v)
 		return 0.0;
 
@@ -446,16 +469,15 @@ static double runtime_stat_n(struct runtime_stat *st,
 }
 
 static void print_stalled_cycles_frontend(struct perf_stat_config *config,
-					  int cpu,
-					  struct evsel *evsel, double avg,
+					  int cpu, double avg,
 					  struct perf_stat_output_ctx *out,
-					  struct runtime_stat *st)
+					  struct runtime_stat *st,
+					  struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -470,16 +492,15 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config,
 }
 
 static void print_stalled_cycles_backend(struct perf_stat_config *config,
-					 int cpu,
-					 struct evsel *evsel, double avg,
+					 int cpu, double avg,
 					 struct perf_stat_output_ctx *out,
-					 struct runtime_stat *st)
+					 struct runtime_stat *st,
+					 struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -490,17 +511,15 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config,
 }
 
 static void print_branch_misses(struct perf_stat_config *config,
-				int cpu,
-				struct evsel *evsel,
-				double avg,
+				int cpu, double avg,
 				struct perf_stat_output_ctx *out,
-				struct runtime_stat *st)
+				struct runtime_stat *st,
+				struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_BRANCHES, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_BRANCHES, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -511,18 +530,15 @@ static void print_branch_misses(struct perf_stat_config *config,
 }
 
 static void print_l1_dcache_misses(struct perf_stat_config *config,
-				   int cpu,
-				   struct evsel *evsel,
-				   double avg,
+				   int cpu, double avg,
 				   struct perf_stat_output_ctx *out,
-				   struct runtime_stat *st)
-
+				   struct runtime_stat *st,
+				   struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_L1_DCACHE, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -533,18 +549,15 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
 }
 
 static void print_l1_icache_misses(struct perf_stat_config *config,
-				   int cpu,
-				   struct evsel *evsel,
-				   double avg,
+				   int cpu, double avg,
 				   struct perf_stat_output_ctx *out,
-				   struct runtime_stat *st)
-
+				   struct runtime_stat *st,
+				   struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_L1_ICACHE, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -554,17 +567,15 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
 }
 
 static void print_dtlb_cache_misses(struct perf_stat_config *config,
-				    int cpu,
-				    struct evsel *evsel,
-				    double avg,
+				    int cpu, double avg,
 				    struct perf_stat_output_ctx *out,
-				    struct runtime_stat *st)
+				    struct runtime_stat *st,
+				    struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_DTLB_CACHE, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -574,17 +585,15 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
 }
 
 static void print_itlb_cache_misses(struct perf_stat_config *config,
-				    int cpu,
-				    struct evsel *evsel,
-				    double avg,
+				    int cpu, double avg,
 				    struct perf_stat_output_ctx *out,
-				    struct runtime_stat *st)
+				    struct runtime_stat *st,
+				    struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_ITLB_CACHE, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -594,17 +603,15 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
 }
 
 static void print_ll_cache_misses(struct perf_stat_config *config,
-				  int cpu,
-				  struct evsel *evsel,
-				  double avg,
+				  int cpu, double avg,
 				  struct perf_stat_output_ctx *out,
-				  struct runtime_stat *st)
+				  struct runtime_stat *st,
+				  struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_LL_CACHE, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_LL_CACHE, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -662,56 +669,61 @@ static double sanitize_val(double x)
 	return x;
 }
 
-static double td_total_slots(int ctx, int cpu, struct runtime_stat *st)
+static double td_total_slots(int cpu, struct runtime_stat *st,
+			     struct runtime_stat_data *rsd)
 {
-	return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, ctx, cpu);
+	return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu, rsd);
 }
 
-static double td_bad_spec(int ctx, int cpu, struct runtime_stat *st)
+static double td_bad_spec(int cpu, struct runtime_stat *st,
+			  struct runtime_stat_data *rsd)
 {
 	double bad_spec = 0;
 	double total_slots;
 	double total;
 
-	total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, ctx, cpu) -
-		runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, ctx, cpu) +
-		runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu, rsd) -
+		runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu, rsd) +
+		runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu, rsd);
 
-	total_slots = td_total_slots(ctx, cpu, st);
+	total_slots = td_total_slots(cpu, st, rsd);
 	if (total_slots)
 		bad_spec = total / total_slots;
 	return sanitize_val(bad_spec);
 }
 
-static double td_retiring(int ctx, int cpu, struct runtime_stat *st)
+static double td_retiring(int cpu, struct runtime_stat *st,
+			  struct runtime_stat_data *rsd)
 {
 	double retiring = 0;
-	double total_slots = td_total_slots(ctx, cpu, st);
+	double total_slots = td_total_slots(cpu, st, rsd);
 	double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED,
-					    ctx, cpu);
+					    cpu, rsd);
 
 	if (total_slots)
 		retiring = ret_slots / total_slots;
 	return retiring;
 }
 
-static double td_fe_bound(int ctx, int cpu, struct runtime_stat *st)
+static double td_fe_bound(int cpu, struct runtime_stat *st,
+			  struct runtime_stat_data *rsd)
 {
 	double fe_bound = 0;
-	double total_slots = td_total_slots(ctx, cpu, st);
+	double total_slots = td_total_slots(cpu, st, rsd);
 	double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES,
-					    ctx, cpu);
+					    cpu, rsd);
 
 	if (total_slots)
 		fe_bound = fetch_bub / total_slots;
 	return fe_bound;
 }
 
-static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
+static double td_be_bound(int cpu, struct runtime_stat *st,
+			  struct runtime_stat_data *rsd)
 {
-	double sum = (td_fe_bound(ctx, cpu, st) +
-		      td_bad_spec(ctx, cpu, st) +
-		      td_retiring(ctx, cpu, st));
+	double sum = (td_fe_bound(cpu, st, rsd) +
+		      td_bad_spec(cpu, st, rsd) +
+		      td_retiring(cpu, st, rsd));
 	if (sum == 0)
 		return 0;
 	return sanitize_val(1.0 - sum);
@@ -722,15 +734,15 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
  * the ratios we need to recreate the sum.
  */
 
-static double td_metric_ratio(int ctx, int cpu,
-			      enum stat_type type,
-			      struct runtime_stat *stat)
+static double td_metric_ratio(int cpu, enum stat_type type,
+			      struct runtime_stat *stat,
+			      struct runtime_stat_data *rsd)
 {
-	double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) +
-		runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) +
-		runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) +
-		runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu);
-	double d = runtime_stat_avg(stat, type, ctx, cpu);
+	double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd);
+	double d = runtime_stat_avg(stat, type, cpu, rsd);
 
 	if (sum)
 		return d / sum;
@@ -742,34 +754,33 @@ static double td_metric_ratio(int ctx, int cpu,
  * We allow two missing.
  */
 
-static bool full_td(int ctx, int cpu,
-		    struct runtime_stat *stat)
+static bool full_td(int cpu, struct runtime_stat *stat,
+		    struct runtime_stat_data *rsd)
 {
 	int c = 0;
 
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) > 0)
 		c++;
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) > 0)
 		c++;
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) > 0)
 		c++;
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd) > 0)
 		c++;
 	return c >= 2;
 }
 
-static void print_smi_cost(struct perf_stat_config *config,
-			   int cpu, struct evsel *evsel,
+static void print_smi_cost(struct perf_stat_config *config, int cpu,
 			   struct perf_stat_output_ctx *out,
-			   struct runtime_stat *st)
+			   struct runtime_stat *st,
+			   struct runtime_stat_data *rsd)
 {
 	double smi_num, aperf, cycles, cost = 0.0;
-	int ctx = evsel_context(evsel);
 	const char *color = NULL;
 
-	smi_num = runtime_stat_avg(st, STAT_SMI_NUM, ctx, cpu);
-	aperf = runtime_stat_avg(st, STAT_APERF, ctx, cpu);
-	cycles = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+	smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu, rsd);
+	aperf = runtime_stat_avg(st, STAT_APERF, cpu, rsd);
+	cycles = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
 
 	if ((cycles == 0) || (aperf == 0))
 		return;
@@ -804,7 +815,8 @@ static int prepare_metric(struct evsel **metric_events,
 			scale = 1e-9;
 		} else {
 			v = saved_value_lookup(metric_events[i], cpu, false,
-					       STAT_NONE, 0, st);
+					       STAT_NONE, 0, st,
+					       metric_events[i]->cgrp);
 			if (!v)
 				break;
 			stats = &v->stats;
@@ -930,12 +942,15 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	const char *color = NULL;
-	int ctx = evsel_context(evsel);
+	struct runtime_stat_data rsd = {
+		.ctx = evsel_context(evsel),
+		.cgrp = evsel->cgrp,
+	};
 	struct metric_event *me;
 	int num = 1;
 
 	if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
-		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+		total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
 
 		if (total) {
 			ratio = avg / total;
@@ -945,12 +960,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 
-		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
-					 ctx, cpu);
+		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu, &rsd);
 
 		total = max(total, runtime_stat_avg(st,
 						    STAT_STALLED_CYCLES_BACK,
-						    ctx, cpu));
+						    cpu, &rsd));
 
 		if (total && avg) {
 			out->new_line(config, ctxp);
@@ -960,8 +974,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					ratio);
 		}
 	} else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
-		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
-			print_branch_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_BRANCHES, cpu, &rsd) != 0)
+			print_branch_misses(config, cpu, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
@@ -970,8 +984,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
-			print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_L1_DCACHE, cpu, &rsd) != 0)
+			print_l1_dcache_misses(config, cpu, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
 	} else if (
@@ -980,8 +994,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
-			print_l1_icache_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_L1_ICACHE, cpu, &rsd) != 0)
+			print_l1_icache_misses(config, cpu, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
 	} else if (
@@ -990,8 +1004,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
-			print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu, &rsd) != 0)
+			print_dtlb_cache_misses(config, cpu, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
 	} else if (
@@ -1000,8 +1014,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
-			print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu, &rsd) != 0)
+			print_itlb_cache_misses(config, cpu, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
 	} else if (
@@ -1010,27 +1024,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
-			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_LL_CACHE, cpu, &rsd) != 0)
+			print_ll_cache_misses(config, cpu, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0);
 	} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
-		total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
+		total = runtime_stat_avg(st, STAT_CACHEREFS, cpu, &rsd);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
+		if (runtime_stat_n(st, STAT_CACHEREFS, cpu, &rsd) != 0)
 			print_metric(config, ctxp, NULL, "%8.3f %%",
 				     "of all cache refs", ratio);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
+		print_stalled_cycles_frontend(config, cpu, avg, out, st, &rsd);
 	} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
+		print_stalled_cycles_backend(config, cpu, avg, out, st, &rsd);
 	} else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
-		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
+		total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
 
 		if (total) {
 			ratio = avg / total;
@@ -1039,7 +1053,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
-		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+		total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
 
 		if (total)
 			print_metric(config, ctxp, NULL,
@@ -1049,8 +1063,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, NULL, "transactional cycles",
 				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
-		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
-		total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, ctx, cpu);
+		total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
+		total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
 
 		if (total2 < avg)
 			total2 = avg;
@@ -1060,21 +1074,19 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		else
 			print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
-		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
-					 ctx, cpu);
+		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
 
 		if (avg)
 			ratio = total / avg;
 
-		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
+		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu, &rsd) != 0)
 			print_metric(config, ctxp, NULL, "%8.0f",
 				     "cycles / transaction", ratio);
 		else
 			print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
 				      0);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
-		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
-					 ctx, cpu);
+		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
 
 		if (avg)
 			ratio = total / avg;
@@ -1087,28 +1099,28 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		else
 			print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
-		double fe_bound = td_fe_bound(ctx, cpu, st);
+		double fe_bound = td_fe_bound(cpu, st, &rsd);
 
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
-		double retiring = td_retiring(ctx, cpu, st);
+		double retiring = td_retiring(cpu, st, &rsd);
 
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
 		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
-		double bad_spec = td_bad_spec(ctx, cpu, st);
+		double bad_spec = td_bad_spec(cpu, st, &rsd);
 
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
 				bad_spec * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
-		double be_bound = td_be_bound(ctx, cpu, st);
+		double be_bound = td_be_bound(cpu, st, &rsd);
 		const char *name = "backend bound";
 		static int have_recovery_bubbles = -1;
 
@@ -1121,43 +1133,43 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
-		if (td_total_slots(ctx, cpu, st) > 0)
+		if (td_total_slots(cpu, st, &rsd) > 0)
 			print_metric(config, ctxp, color, "%8.1f%%", name,
 					be_bound * 100.);
 		else
 			print_metric(config, ctxp, NULL, NULL, name, 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
-			full_td(ctx, cpu, st)) {
-		double retiring = td_metric_ratio(ctx, cpu,
-						  STAT_TOPDOWN_RETIRING, st);
-
+		   full_td(cpu, st, &rsd)) {
+		double retiring = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_RETIRING, st,
+						  &rsd);
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
 		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
-			full_td(ctx, cpu, st)) {
-		double fe_bound = td_metric_ratio(ctx, cpu,
-						  STAT_TOPDOWN_FE_BOUND, st);
-
+		   full_td(cpu, st, &rsd)) {
+		double fe_bound = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_FE_BOUND, st,
+						  &rsd);
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
-			full_td(ctx, cpu, st)) {
-		double be_bound = td_metric_ratio(ctx, cpu,
-						  STAT_TOPDOWN_BE_BOUND, st);
-
+		   full_td(cpu, st, &rsd)) {
+		double be_bound = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_BE_BOUND, st,
+						  &rsd);
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
 				be_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
-			full_td(ctx, cpu, st)) {
-		double bad_spec = td_metric_ratio(ctx, cpu,
-						  STAT_TOPDOWN_BAD_SPEC, st);
-
+		   full_td(cpu, st, &rsd)) {
+		double bad_spec = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_BAD_SPEC, st,
+						  &rsd);
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
@@ -1165,11 +1177,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 	} else if (evsel->metric_expr) {
 		generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
 				evsel->name, evsel->metric_name, NULL, 1, cpu, out, st);
-	} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
+	} else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) {
 		char unit = 'M';
 		char unit_buf[10];
 
-		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
+		total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
 
 		if (total)
 			ratio = 1000.0 * avg / total;
@@ -1180,7 +1192,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
 		print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
-		print_smi_cost(config, cpu, evsel, out, st);
+		print_smi_cost(config, cpu, out, st, &rsd);
 	} else {
 		num = 0;
 	}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index bd0decd6d753..8ce1479c98f0 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -184,7 +184,7 @@ static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
 	return 0;
 }
 
-int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw)
+int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw)
 {
 	struct evsel *evsel;
 
@@ -196,11 +196,11 @@ int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw)
 	return 0;
 
 out_free:
-	perf_evlist__free_stats(evlist);
+	evlist__free_stats(evlist);
 	return -1;
 }
 
-void perf_evlist__free_stats(struct evlist *evlist)
+void evlist__free_stats(struct evlist *evlist)
 {
 	struct evsel *evsel;
 
@@ -211,7 +211,7 @@ void perf_evlist__free_stats(struct evlist *evlist)
 	}
 }
 
-void perf_evlist__reset_stats(struct evlist *evlist)
+void evlist__reset_stats(struct evlist *evlist)
 {
 	struct evsel *evsel;
 
@@ -221,7 +221,7 @@ void perf_evlist__reset_stats(struct evlist *evlist)
 	}
 }
 
-void perf_evlist__reset_prev_raw_counts(struct evlist *evlist)
+void evlist__reset_prev_raw_counts(struct evlist *evlist)
 {
 	struct evsel *evsel;
 
@@ -229,7 +229,7 @@ void perf_evlist__reset_prev_raw_counts(struct evlist *evlist)
 		evsel__reset_prev_raw_counts(evsel);
 }
 
-static void perf_evsel__copy_prev_raw_counts(struct evsel *evsel)
+static void evsel__copy_prev_raw_counts(struct evsel *evsel)
 {
 	int ncpus = evsel__nr_cpus(evsel);
 	int nthreads = perf_thread_map__nr(evsel->core.threads);
@@ -245,15 +245,15 @@ static void perf_evsel__copy_prev_raw_counts(struct evsel *evsel)
 	evsel->counts->aggr = evsel->prev_raw_counts->aggr;
 }
 
-void perf_evlist__copy_prev_raw_counts(struct evlist *evlist)
+void evlist__copy_prev_raw_counts(struct evlist *evlist)
 {
 	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel)
-		perf_evsel__copy_prev_raw_counts(evsel);
+		evsel__copy_prev_raw_counts(evsel);
 }
 
-void perf_evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
+void evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
 {
 	struct evsel *evsel;
 
@@ -313,7 +313,7 @@ static int check_per_pkg(struct evsel *counter,
 	if (!(vals->run && vals->ena))
 		return 0;
 
-	s = cpu_map__get_socket(cpus, cpu, NULL);
+	s = cpu_map__get_socket(cpus, cpu, NULL).socket;
 	if (s < 0)
 		return -1;
 
@@ -458,7 +458,7 @@ int perf_event__process_stat_event(struct perf_session *session,
 	count.ena = st->ena;
 	count.run = st->run;
 
-	counter = perf_evlist__id2evsel(session->evlist, st->id);
+	counter = evlist__id2evsel(session->evlist, st->id);
 	if (!counter) {
 		pr_err("Failed to resolve counter for stat event.\n");
 		return -EINVAL;
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 487010c624be..b5369730b4a2 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -6,6 +6,7 @@
 #include <stdio.h>
 #include <sys/types.h>
 #include <sys/resource.h>
+#include "cpumap.h"
 #include "rblist.h"
 
 struct perf_cpu_map;
@@ -99,7 +100,7 @@ struct runtime_stat {
 	struct rblist value_list;
 };
 
-typedef int (*aggr_get_id_t)(struct perf_stat_config *config,
+typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config,
 			     struct perf_cpu_map *m, int cpu);
 
 struct perf_stat_config {
@@ -122,6 +123,7 @@ struct perf_stat_config {
 	bool			 metric_no_group;
 	bool			 metric_no_merge;
 	bool			 stop_read_counter;
+	bool			 quiet;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
@@ -137,9 +139,9 @@ struct perf_stat_config {
 	const char		*csv_sep;
 	struct stats		*walltime_nsecs_stats;
 	struct rusage		 ru_data;
-	struct perf_cpu_map		*aggr_map;
+	struct cpu_aggr_map	*aggr_map;
 	aggr_get_id_t		 aggr_get_id;
-	struct perf_cpu_map		*cpus_aggr_map;
+	struct cpu_aggr_map	*cpus_aggr_map;
 	u64			*walltime_run;
 	struct rblist		 metric_events;
 	int			 ctl_fd;
@@ -169,7 +171,7 @@ struct evlist;
 
 struct perf_aggr_thread_value {
 	struct evsel *counter;
-	int id;
+	struct aggr_cpu_id id;
 	double uval;
 	u64 val;
 	u64 run;
@@ -212,12 +214,12 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 				   struct runtime_stat *st);
 void perf_stat__collect_metric_expr(struct evlist *);
 
-int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw);
-void perf_evlist__free_stats(struct evlist *evlist);
-void perf_evlist__reset_stats(struct evlist *evlist);
-void perf_evlist__reset_prev_raw_counts(struct evlist *evlist);
-void perf_evlist__copy_prev_raw_counts(struct evlist *evlist);
-void perf_evlist__save_aggr_prev_raw_counts(struct evlist *evlist);
+int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw);
+void evlist__free_stats(struct evlist *evlist);
+void evlist__reset_stats(struct evlist *evlist);
+void evlist__reset_prev_raw_counts(struct evlist *evlist);
+void evlist__copy_prev_raw_counts(struct evlist *evlist);
+void evlist__save_aggr_prev_raw_counts(struct evlist *evlist);
 
 int perf_stat_process_counter(struct perf_stat_config *config,
 			      struct evsel *counter);
@@ -237,12 +239,8 @@ int create_perf_stat_counter(struct evsel *evsel,
 			     struct perf_stat_config *config,
 			     struct target *target,
 			     int cpu);
-void
-perf_evlist__print_counters(struct evlist *evlist,
-			    struct perf_stat_config *config,
-			    struct target *_target,
-			    struct timespec *ts,
-			    int argc, const char **argv);
+void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
+			    struct target *_target, struct timespec *ts, int argc, const char **argv);
 
 struct metric_expr;
 double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 44dd86a4f25f..f3577f7d72fe 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -534,7 +534,7 @@ out:
 
 #ifdef HAVE_LIBBFD_BUILDID_SUPPORT
 
-int filename__read_build_id(const char *filename, struct build_id *bid)
+static int read_build_id(const char *filename, struct build_id *bid)
 {
 	size_t size = sizeof(bid->data);
 	int err = -1;
@@ -563,7 +563,7 @@ out_close:
 
 #else // HAVE_LIBBFD_BUILDID_SUPPORT
 
-int filename__read_build_id(const char *filename, struct build_id *bid)
+static int read_build_id(const char *filename, struct build_id *bid)
 {
 	size_t size = sizeof(bid->data);
 	int fd, err = -1;
@@ -595,6 +595,39 @@ out:
 
 #endif // HAVE_LIBBFD_BUILDID_SUPPORT
 
+int filename__read_build_id(const char *filename, struct build_id *bid)
+{
+	struct kmod_path m = { .name = NULL, };
+	char path[PATH_MAX];
+	int err;
+
+	if (!filename)
+		return -EFAULT;
+
+	err = kmod_path__parse(&m, filename);
+	if (err)
+		return -1;
+
+	if (m.comp) {
+		int error = 0, fd;
+
+		fd = filename__decompress(filename, path, sizeof(path), m.comp, &error);
+		if (fd < 0) {
+			pr_debug("Failed to decompress (error %d) %s\n",
+				 error, filename);
+			return -1;
+		}
+		close(fd);
+		filename = path;
+	}
+
+	err = read_build_id(filename, bid);
+
+	if (m.comp)
+		unlink(filename);
+	return err;
+}
+
 int sysfs__read_build_id(const char *filename, struct build_id *bid)
 {
 	size_t size = sizeof(bid->data);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 0d14abdf3d72..64a039cbba1b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -2189,6 +2189,8 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map)
 	int err;
 	const char *kallsyms_filename = NULL;
 	char *kallsyms_allocated_filename = NULL;
+	char *filename = NULL;
+
 	/*
 	 * Step 1: if the user specified a kallsyms or vmlinux filename, use
 	 * it and only it, reporting errors to the user if it cannot be used.
@@ -2213,6 +2215,20 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map)
 		return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name, false);
 	}
 
+	/*
+	 * Before checking on common vmlinux locations, check if it's
+	 * stored as standard build id binary (not kallsyms) under
+	 * .debug cache.
+	 */
+	if (!symbol_conf.ignore_vmlinux_buildid)
+		filename = __dso__build_id_filename(dso, NULL, 0, false, false);
+	if (filename != NULL) {
+		err = dso__load_vmlinux(dso, map, filename, true);
+		if (err > 0)
+			return err;
+		free(filename);
+	}
+
 	if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
 		err = dso__load_vmlinux_path(dso, map);
 		if (err > 0)
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index d9c624377da7..2947e3f3c6d9 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1409,6 +1409,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_CGROUP)
 		result += sizeof(u64);
 
+	if (type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		result += sizeof(u64);
+
 	if (type & PERF_SAMPLE_AUX) {
 		result += sizeof(u64);
 		result += sample->aux_sample.size;
@@ -1588,6 +1591,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 		array++;
 	}
 
+	if (type & PERF_SAMPLE_DATA_PAGE_SIZE) {
+		*array = sample->data_page_size;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_AUX) {
 		sz = sample->aux_sample.size;
 		*array++ = sz;
@@ -1643,7 +1651,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_
 
 			e->id = evsel->core.id[j];
 
-			sid = perf_evlist__id2sid(evlist, e->id);
+			sid = evlist__id2sid(evlist, e->id);
 			if (!sid) {
 				free(ev);
 				return -ENOENT;
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 7a3dbc259cec..0ada907c60d4 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -20,10 +20,24 @@
 
 static char *debuginfo_path;
 
+static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata,
+			    const char *modname __maybe_unused, Dwarf_Addr base __maybe_unused,
+			    const char *file_name, const char *debuglink_file __maybe_unused,
+			    GElf_Word debuglink_crc __maybe_unused, char **debuginfo_file_name)
+{
+	const struct dso *dso = *userdata;
+
+	assert(dso);
+	if (dso->symsrc_filename && strcmp (file_name, dso->symsrc_filename))
+		*debuginfo_file_name = strdup(dso->symsrc_filename);
+	return -1;
+}
+
 static const Dwfl_Callbacks offline_callbacks = {
-	.find_debuginfo		= dwfl_standard_find_debuginfo,
+	.find_debuginfo		= __find_debuginfo,
 	.debuginfo_path		= &debuginfo_path,
 	.section_address	= dwfl_offline_section_address,
+	// .find_elf is not set as we use dwfl_report_elf() instead.
 };
 
 static int __report_module(struct addr_location *al, u64 ip,
@@ -46,16 +60,24 @@ static int __report_module(struct addr_location *al, u64 ip,
 	mod = dwfl_addrmodule(ui->dwfl, ip);
 	if (mod) {
 		Dwarf_Addr s;
+		void **userdatap;
 
-		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
+		dwfl_module_info(mod, &userdatap, &s, NULL, NULL, NULL, NULL, NULL);
+		*userdatap = dso;
 		if (s != al->map->start - al->map->pgoff)
 			mod = 0;
 	}
 
 	if (!mod)
-		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
-				      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start - al->map->pgoff,
-				      false);
+		mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1,
+				      al->map->start - al->map->pgoff, false);
+	if (!mod) {
+		char filename[PATH_MAX];
+
+		if (dso__build_id_filename(dso, filename, sizeof(filename), false))
+			mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
+					      al->map->start - al->map->pgoff, false);
+	}
 
 	return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
 }
diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
index 3c47865bb247..e15e20696d17 100755
--- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
+++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 # SPDX-License-Identifier: GPL-2.0-only
 # -*- coding: utf-8 -*-
 #
diff --git a/tools/testing/ktest/compare-ktest-sample.pl b/tools/testing/ktest/compare-ktest-sample.pl
index 4118eb4a842d..ebea21d0a1be 100755
--- a/tools/testing/ktest/compare-ktest-sample.pl
+++ b/tools/testing/ktest/compare-ktest-sample.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
 # SPDX-License-Identifier: GPL-2.0
 
 open (IN,"ktest.pl");
diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py
index d4f7846d0745..21516e293d17 100755
--- a/tools/testing/kunit/kunit.py
+++ b/tools/testing/kunit/kunit.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python3
+#!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0
 #
 # A thin wrapper on top of the KUnit Kernel
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index 57c1724b7e5d..698358c9c0d6 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -198,7 +198,7 @@ class LinuxSourceTree(object):
 		return self.validate_config(build_dir)
 
 	def run_kernel(self, args=[], build_dir='', timeout=None):
-		args.extend(['mem=1G'])
+		args.extend(['mem=1G', 'console=tty'])
 		self._ops.linux_bin(args, timeout, build_dir)
 		outfile = get_outfile_path(build_dir)
 		subprocess.call(['stty', 'sane'])
diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py
index 497ab51bc170..b593f4448e83 100755
--- a/tools/testing/kunit/kunit_tool_test.py
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python3
+#!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0
 #
 # A collection of tests for tools/testing/kunit/kunit.py
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index afbab4aeef3c..8a917cb4426a 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -77,8 +77,10 @@ TARGETS += zram
 TARGETS_HOTPLUG = cpu-hotplug
 TARGETS_HOTPLUG += memory-hotplug
 
-# User can optionally provide a TARGETS skiplist.
-SKIP_TARGETS ?=
+# User can optionally provide a TARGETS skiplist.  By default we skip
+# BPF since it has cutting edge build time dependencies which require
+# more effort to install.
+SKIP_TARGETS ?= bpf
 ifneq ($(SKIP_TARGETS),)
 	TMP := $(filter-out $(SKIP_TARGETS), $(TARGETS))
 	override TARGETS := $(TMP)
diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S
index 1c5556bdd11d..0dbd594c2747 100644
--- a/tools/testing/selftests/arm64/fp/fpsimd-test.S
+++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S
@@ -457,7 +457,7 @@ function barf
 	mov	x11, x1	// actual data
 	mov	x12, x2	// data size
 
-	puts	"Mistatch: PID="
+	puts	"Mismatch: PID="
 	mov	x0, x20
 	bl	putdec
 	puts	", iteration="
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index f95074c9b48b..9210691aa998 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -625,7 +625,7 @@ function barf
 	mov	x11, x1	// actual data
 	mov	x12, x2	// data size
 
-	puts	"Mistatch: PID="
+	puts	"Mismatch: PID="
 	mov	x0, x20
 	bl	putdec
 	puts	", iteration="
diff --git a/tools/testing/selftests/arm64/mte/Makefile b/tools/testing/selftests/arm64/mte/Makefile
index 2480226dfe57..0b3af552632a 100644
--- a/tools/testing/selftests/arm64/mte/Makefile
+++ b/tools/testing/selftests/arm64/mte/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (C) 2020 ARM Limited
 
-CFLAGS += -std=gnu99 -I.
+CFLAGS += -std=gnu99 -I. -lpthread
 SRCS := $(filter-out mte_common_util.c,$(wildcard *.c))
 PROGS := $(patsubst %.c,%,$(SRCS))
 
diff --git a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c
new file mode 100644
index 000000000000..a876db1f096a
--- /dev/null
+++ b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2020 ARM Limited
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <pthread.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <unistd.h>
+#include <sys/auxv.h>
+#include <sys/mman.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include "kselftest.h"
+#include "mte_common_util.h"
+
+#define PR_SET_TAGGED_ADDR_CTRL 55
+#define PR_GET_TAGGED_ADDR_CTRL 56
+# define PR_TAGGED_ADDR_ENABLE  (1UL << 0)
+# define PR_MTE_TCF_SHIFT	1
+# define PR_MTE_TCF_NONE	(0UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_SYNC	(1UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_ASYNC	(2UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_MASK	(3UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TAG_SHIFT	3
+# define PR_MTE_TAG_MASK	(0xffffUL << PR_MTE_TAG_SHIFT)
+
+#include "mte_def.h"
+
+#define NUM_ITERATIONS		1024
+#define MAX_THREADS		5
+#define THREAD_ITERATIONS	1000
+
+void *execute_thread(void *x)
+{
+	pid_t pid = *((pid_t *)x);
+	pid_t tid = gettid();
+	uint64_t prctl_tag_mask;
+	uint64_t prctl_set;
+	uint64_t prctl_get;
+	uint64_t prctl_tcf;
+
+	srand(time(NULL) ^ (pid << 16) ^ (tid << 16));
+
+	prctl_tag_mask = rand() & 0xffff;
+
+	if (prctl_tag_mask % 2)
+		prctl_tcf = PR_MTE_TCF_SYNC;
+	else
+		prctl_tcf = PR_MTE_TCF_ASYNC;
+
+	prctl_set = PR_TAGGED_ADDR_ENABLE | prctl_tcf | (prctl_tag_mask << PR_MTE_TAG_SHIFT);
+
+	for (int j = 0; j < THREAD_ITERATIONS; j++) {
+		if (prctl(PR_SET_TAGGED_ADDR_CTRL, prctl_set, 0, 0, 0)) {
+			perror("prctl() failed");
+			goto fail;
+		}
+
+		prctl_get = prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0);
+
+		if (prctl_set != prctl_get) {
+			ksft_print_msg("Error: prctl_set: 0x%lx != prctl_get: 0x%lx\n",
+						prctl_set, prctl_get);
+			goto fail;
+		}
+	}
+
+	return (void *)KSFT_PASS;
+
+fail:
+	return (void *)KSFT_FAIL;
+}
+
+int execute_test(pid_t pid)
+{
+	pthread_t thread_id[MAX_THREADS];
+	int thread_data[MAX_THREADS];
+
+	for (int i = 0; i < MAX_THREADS; i++)
+		pthread_create(&thread_id[i], NULL,
+			       execute_thread, (void *)&pid);
+
+	for (int i = 0; i < MAX_THREADS; i++)
+		pthread_join(thread_id[i], (void *)&thread_data[i]);
+
+	for (int i = 0; i < MAX_THREADS; i++)
+		if (thread_data[i] == KSFT_FAIL)
+			return KSFT_FAIL;
+
+	return KSFT_PASS;
+}
+
+int mte_gcr_fork_test(void)
+{
+	pid_t pid;
+	int results[NUM_ITERATIONS];
+	pid_t cpid;
+	int res;
+
+	for (int i = 0; i < NUM_ITERATIONS; i++) {
+		pid = fork();
+
+		if (pid < 0)
+			return KSFT_FAIL;
+
+		if (pid == 0) {
+			cpid = getpid();
+
+			res = execute_test(cpid);
+
+			exit(res);
+		}
+	}
+
+	for (int i = 0; i < NUM_ITERATIONS; i++) {
+		wait(&res);
+
+		if (WIFEXITED(res))
+			results[i] = WEXITSTATUS(res);
+		else
+			--i;
+	}
+
+	for (int i = 0; i < NUM_ITERATIONS; i++)
+		if (results[i] == KSFT_FAIL)
+			return KSFT_FAIL;
+
+	return KSFT_PASS;
+}
+
+int main(int argc, char *argv[])
+{
+	int err;
+
+	err = mte_default_setup();
+	if (err)
+		return err;
+
+	ksft_set_plan(1);
+
+	evaluate_test(mte_gcr_fork_test(),
+		"Verify that GCR_EL1 is set correctly on context switch\n");
+
+	mte_restore_setup();
+	ksft_print_cnts();
+
+	return ksft_get_fail_cnt() == 0 ? KSFT_PASS : KSFT_FAIL;
+}
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 8c33e999319a..c51df6b91bef 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -121,6 +121,9 @@ VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
 		     /sys/kernel/btf/vmlinux				\
 		     /boot/vmlinux-$(shell uname -r)
 VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+ifeq ($(VMLINUX_BTF),)
+$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
+endif
 
 # Define simple and short `make test_progs`, `make test_sysctl`, etc targets
 # to build individual tests.
diff --git a/tools/testing/selftests/bpf/progs/bprm_opts.c b/tools/testing/selftests/bpf/progs/bprm_opts.c
index 5bfef2887e70..418d9c6d4952 100644
--- a/tools/testing/selftests/bpf/progs/bprm_opts.c
+++ b/tools/testing/selftests/bpf/progs/bprm_opts.c
@@ -4,7 +4,7 @@
  * Copyright 2020 Google LLC.
  */
 
-#include "vmlinux.h"
+#include <linux/bpf.h>
 #include <errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 0ad3e6305ff0..51adc42b2b40 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1312,22 +1312,58 @@ static void test_map_stress(void)
 #define DO_UPDATE 1
 #define DO_DELETE 0
 
+#define MAP_RETRIES 20
+
+static int map_update_retriable(int map_fd, const void *key, const void *value,
+				int flags, int attempts)
+{
+	while (bpf_map_update_elem(map_fd, key, value, flags)) {
+		if (!attempts || (errno != EAGAIN && errno != EBUSY))
+			return -errno;
+
+		usleep(1);
+		attempts--;
+	}
+
+	return 0;
+}
+
+static int map_delete_retriable(int map_fd, const void *key, int attempts)
+{
+	while (bpf_map_delete_elem(map_fd, key)) {
+		if (!attempts || (errno != EAGAIN && errno != EBUSY))
+			return -errno;
+
+		usleep(1);
+		attempts--;
+	}
+
+	return 0;
+}
+
 static void test_update_delete(unsigned int fn, void *data)
 {
 	int do_update = ((int *)data)[1];
 	int fd = ((int *)data)[0];
-	int i, key, value;
+	int i, key, value, err;
 
 	for (i = fn; i < MAP_SIZE; i += TASKS) {
 		key = value = i;
 
 		if (do_update) {
-			assert(bpf_map_update_elem(fd, &key, &value,
-						   BPF_NOEXIST) == 0);
-			assert(bpf_map_update_elem(fd, &key, &value,
-						   BPF_EXIST) == 0);
+			err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES);
+			if (err)
+				printf("error %d %d\n", err, errno);
+			assert(err == 0);
+			err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES);
+			if (err)
+				printf("error %d %d\n", err, errno);
+			assert(err == 0);
 		} else {
-			assert(bpf_map_delete_elem(fd, &key) == 0);
+			err = map_delete_retriable(fd, &key, MAP_RETRIES);
+			if (err)
+				printf("error %d %d\n", err, errno);
+			assert(err == 0);
 		}
 	}
 }
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index b99bb8ed3ed4..edaffd43da83 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python3
+#!/usr/bin/env python3
 
 # Copyright (C) 2017 Netronome Systems, Inc.
 # Copyright (c) 2019 Mellanox Technologies. All rights reserved
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 014dedaa4dd2..1e722ee76b1f 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -715,7 +715,7 @@ static void worker_pkt_dump(void)
 		int payload = *((uint32_t *)(pkt_buf[iter]->payload + PKT_HDR_SIZE));
 
 		if (payload == EOT) {
-			ksft_print_msg("End-of-tranmission frame received\n");
+			ksft_print_msg("End-of-transmission frame received\n");
 			fprintf(stdout, "---------------------------------------\n");
 			break;
 		}
@@ -747,7 +747,7 @@ static void worker_pkt_validate(void)
 			}
 
 			if (payloadseqnum == EOT) {
-				ksft_print_msg("End-of-tranmission frame received: PASS\n");
+				ksft_print_msg("End-of-transmission frame received: PASS\n");
 				sigvar = 1;
 				break;
 			}
diff --git a/tools/testing/selftests/dma/Makefile b/tools/testing/selftests/dma/Makefile
new file mode 100644
index 000000000000..aa8e8b5b3864
--- /dev/null
+++ b/tools/testing/selftests/dma/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -I../../../../usr/include/
+
+TEST_GEN_PROGS := dma_map_benchmark
+
+include ../lib.mk
diff --git a/tools/testing/selftests/dma/config b/tools/testing/selftests/dma/config
new file mode 100644
index 000000000000..6102ee3c43cd
--- /dev/null
+++ b/tools/testing/selftests/dma/config
@@ -0,0 +1 @@
+CONFIG_DMA_MAP_BENCHMARK=y
diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c
new file mode 100644
index 000000000000..7065163a8388
--- /dev/null
+++ b/tools/testing/selftests/dma/dma_map_benchmark.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Hisilicon Limited.
+ */
+
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <linux/types.h>
+
+#define DMA_MAP_BENCHMARK	_IOWR('d', 1, struct map_benchmark)
+#define DMA_MAP_MAX_THREADS	1024
+#define DMA_MAP_MAX_SECONDS     300
+
+#define DMA_MAP_BIDIRECTIONAL	0
+#define DMA_MAP_TO_DEVICE	1
+#define DMA_MAP_FROM_DEVICE	2
+
+static char *directions[] = {
+	"BIDIRECTIONAL",
+	"TO_DEVICE",
+	"FROM_DEVICE",
+};
+
+struct map_benchmark {
+	__u64 avg_map_100ns; /* average map latency in 100ns */
+	__u64 map_stddev; /* standard deviation of map latency */
+	__u64 avg_unmap_100ns; /* as above */
+	__u64 unmap_stddev;
+	__u32 threads; /* how many threads will do map/unmap in parallel */
+	__u32 seconds; /* how long the test will last */
+	__s32 node; /* which numa node this benchmark will run on */
+	__u32 dma_bits; /* DMA addressing capability */
+	__u32 dma_dir; /* DMA data direction */
+	__u64 expansion[10];	/* For future use */
+};
+
+int main(int argc, char **argv)
+{
+	struct map_benchmark map;
+	int fd, opt;
+	/* default single thread, run 20 seconds on NUMA_NO_NODE */
+	int threads = 1, seconds = 20, node = -1;
+	/* default dma mask 32bit, bidirectional DMA */
+	int bits = 32, dir = DMA_MAP_BIDIRECTIONAL;
+
+	int cmd = DMA_MAP_BENCHMARK;
+	char *p;
+
+	while ((opt = getopt(argc, argv, "t:s:n:b:d:")) != -1) {
+		switch (opt) {
+		case 't':
+			threads = atoi(optarg);
+			break;
+		case 's':
+			seconds = atoi(optarg);
+			break;
+		case 'n':
+			node = atoi(optarg);
+			break;
+		case 'b':
+			bits = atoi(optarg);
+			break;
+		case 'd':
+			dir = atoi(optarg);
+			break;
+		default:
+			return -1;
+		}
+	}
+
+	if (threads <= 0 || threads > DMA_MAP_MAX_THREADS) {
+		fprintf(stderr, "invalid number of threads, must be in 1-%d\n",
+			DMA_MAP_MAX_THREADS);
+		exit(1);
+	}
+
+	if (seconds <= 0 || seconds > DMA_MAP_MAX_SECONDS) {
+		fprintf(stderr, "invalid number of seconds, must be in 1-%d\n",
+			DMA_MAP_MAX_SECONDS);
+		exit(1);
+	}
+
+	/* suppose the mininum DMA zone is 1MB in the world */
+	if (bits < 20 || bits > 64) {
+		fprintf(stderr, "invalid dma mask bit, must be in 20-64\n");
+		exit(1);
+	}
+
+	if (dir != DMA_MAP_BIDIRECTIONAL && dir != DMA_MAP_TO_DEVICE &&
+			dir != DMA_MAP_FROM_DEVICE) {
+		fprintf(stderr, "invalid dma direction\n");
+		exit(1);
+	}
+
+	fd = open("/sys/kernel/debug/dma_map_benchmark", O_RDWR);
+	if (fd == -1) {
+		perror("open");
+		exit(1);
+	}
+
+	map.seconds = seconds;
+	map.threads = threads;
+	map.node = node;
+	map.dma_bits = bits;
+	map.dma_dir = dir;
+	if (ioctl(fd, cmd, &map)) {
+		perror("ioctl");
+		exit(1);
+	}
+
+	printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s\n",
+			threads, seconds, node, dir[directions]);
+	printf("average map latency(us):%.1f standard deviation:%.1f\n",
+			map.avg_map_100ns/10.0, map.map_stddev/10.0);
+	printf("average unmap latency(us):%.1f standard deviation:%.1f\n",
+			map.avg_unmap_100ns/10.0, map.unmap_stddev/10.0);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
index 4d900bc1f76c..5c7700212f75 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
@@ -230,7 +230,7 @@ switch_create()
 	__mlnx_qos -i $swp4 --pfc=0,1,0,0,0,0,0,0 >/dev/null
 	# PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which
 	# is (-2*MTU) about 80K of delay provision.
-	__mlnx_qos -i $swp3 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null
+	__mlnx_qos -i $swp4 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null
 
 	# bridges
 	# -------
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py
index 0d4b9327c9b3..2223337eed0c 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py
+++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 # SPDX-License-Identifier: GPL-2.0
 
 import subprocess
diff --git a/tools/testing/selftests/kselftest/prefix.pl b/tools/testing/selftests/kselftest/prefix.pl
index 31f7c2a0a8bd..12a7f4ca2684 100755
--- a/tools/testing/selftests/kselftest/prefix.pl
+++ b/tools/testing/selftests/kselftest/prefix.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
 # SPDX-License-Identifier: GPL-2.0
 # Prefix all lines with "# ", unbuffered. Command being piped in may need
 # to have unbuffering forced with "stdbuf -i0 -o0 -e0 $cmd".
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 7a2c242b7152..ce8f4ad39684 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -14,17 +14,17 @@
 /x86_64/set_sregs_test
 /x86_64/smm_test
 /x86_64/state_test
-/x86_64/user_msr_test
-/x86_64/vmx_preemption_timer_test
 /x86_64/svm_vmcall_test
 /x86_64/sync_regs_test
+/x86_64/tsc_msrs_test
+/x86_64/userspace_msr_exit_test
 /x86_64/vmx_apic_access_test
 /x86_64/vmx_close_while_nested_test
 /x86_64/vmx_dirty_log_test
+/x86_64/vmx_preemption_timer_test
 /x86_64/vmx_set_nested_state_test
 /x86_64/vmx_tsc_adjust_test
 /x86_64/xss_msr_test
-/clear_dirty_log_test
 /demand_paging_test
 /dirty_log_test
 /dirty_log_perf_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 3d14ef77755e..fe41c6a0fa67 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -33,10 +33,10 @@ ifeq ($(ARCH),s390)
 	UNAME_M := s390x
 endif
 
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c
+LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
 LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
 LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
-LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c
+LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
@@ -50,6 +50,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
 TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
+TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
@@ -58,7 +59,6 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
 TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
 TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
-TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
@@ -70,6 +70,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
 TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
+TEST_GEN_PROGS_aarch64 += dirty_log_perf_test
 TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_aarch64 += set_memory_region_test
 TEST_GEN_PROGS_aarch64 += steal_time
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index 33218a395d9f..486932164cf2 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -42,12 +42,16 @@
 #define for_each_reg(i)								\
 	for ((i) = 0; (i) < reg_list->n; ++(i))
 
+#define for_each_reg_filtered(i)						\
+	for_each_reg(i)								\
+		if (!filter_reg(reg_list->reg[i]))
+
 #define for_each_missing_reg(i)							\
 	for ((i) = 0; (i) < blessed_n; ++(i))					\
 		if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i]))
 
 #define for_each_new_reg(i)							\
-	for ((i) = 0; (i) < reg_list->n; ++(i))					\
+	for_each_reg_filtered(i)						\
 		if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i]))
 
 
@@ -57,6 +61,18 @@ static __u64 base_regs[], vregs[], sve_regs[], rejects_set[];
 static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n;
 static __u64 *blessed_reg, blessed_n;
 
+static bool filter_reg(__u64 reg)
+{
+	/*
+	 * DEMUX register presence depends on the host's CLIDR_EL1.
+	 * This means there's no set of them that we can bless.
+	 */
+	if ((reg & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
+		return true;
+
+	return false;
+}
+
 static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg)
 {
 	int i;
@@ -325,7 +341,7 @@ int main(int ac, char **av)
 	struct kvm_vcpu_init init = { .target = -1, };
 	int new_regs = 0, missing_regs = 0, i;
 	int failed_get = 0, failed_set = 0, failed_reject = 0;
-	bool print_list = false, fixup_core_regs = false;
+	bool print_list = false, print_filtered = false, fixup_core_regs = false;
 	struct kvm_vm *vm;
 	__u64 *vec_regs;
 
@@ -336,8 +352,10 @@ int main(int ac, char **av)
 			fixup_core_regs = true;
 		else if (strcmp(av[i], "--list") == 0)
 			print_list = true;
+		else if (strcmp(av[i], "--list-filtered") == 0)
+			print_filtered = true;
 		else
-			fprintf(stderr, "Ignoring unknown option: %s\n", av[i]);
+			TEST_FAIL("Unknown option: %s\n", av[i]);
 	}
 
 	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
@@ -350,10 +368,14 @@ int main(int ac, char **av)
 	if (fixup_core_regs)
 		core_reg_fixup();
 
-	if (print_list) {
+	if (print_list || print_filtered) {
 		putchar('\n');
-		for_each_reg(i)
-			print_reg(reg_list->reg[i]);
+		for_each_reg(i) {
+			__u64 id = reg_list->reg[i];
+			if ((print_list && !filter_reg(id)) ||
+			    (print_filtered && filter_reg(id)))
+				print_reg(id);
+		}
 		putchar('\n');
 		return 0;
 	}
@@ -458,6 +480,8 @@ int main(int ac, char **av)
 /*
  * The current blessed list was primed with the output of kernel version
  * v4.15 with --core-reg-fixup and then later updated with new registers.
+ *
+ * The blessed list is up to date with kernel version v5.10-rc5
  */
 static __u64 base_regs[] = {
 	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]),
@@ -736,9 +760,6 @@ static __u64 base_regs[] = {
 	ARM64_SYS_REG(3, 4, 3, 0, 0),	/* DACR32_EL2 */
 	ARM64_SYS_REG(3, 4, 5, 0, 1),	/* IFSR32_EL2 */
 	ARM64_SYS_REG(3, 4, 5, 3, 0),	/* FPEXC32_EL2 */
-	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 0,
-	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 1,
-	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 2,
 };
 static __u64 base_regs_n = ARRAY_SIZE(base_regs);
 
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 3d96a7bfaff3..cdad1eca72f7 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -7,23 +7,20 @@
  * Copyright (C) 2019, Google, Inc.
  */
 
-#define _GNU_SOURCE /* for program_invocation_name */
+#define _GNU_SOURCE /* for pipe2 */
 
 #include <stdio.h>
 #include <stdlib.h>
-#include <sys/syscall.h>
-#include <unistd.h>
-#include <asm/unistd.h>
 #include <time.h>
 #include <poll.h>
 #include <pthread.h>
-#include <linux/bitmap.h>
-#include <linux/bitops.h>
 #include <linux/userfaultfd.h>
+#include <sys/syscall.h>
 
-#include "perf_test_util.h"
-#include "processor.h"
+#include "kvm_util.h"
 #include "test_util.h"
+#include "perf_test_util.h"
+#include "guest_modes.h"
 
 #ifdef __NR_userfaultfd
 
@@ -39,12 +36,14 @@
 #define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
 #endif
 
+static int nr_vcpus = 1;
+static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 static char *guest_data_prototype;
 
 static void *vcpu_worker(void *data)
 {
 	int ret;
-	struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
@@ -248,9 +247,14 @@ static int setup_demand_paging(struct kvm_vm *vm,
 	return 0;
 }
 
-static void run_test(enum vm_guest_mode mode, bool use_uffd,
-		     useconds_t uffd_delay)
+struct test_params {
+	bool use_uffd;
+	useconds_t uffd_delay;
+};
+
+static void run_test(enum vm_guest_mode mode, void *arg)
 {
+	struct test_params *p = arg;
 	pthread_t *vcpu_threads;
 	pthread_t *uffd_handler_threads = NULL;
 	struct uffd_handler_args *uffd_args = NULL;
@@ -261,7 +265,7 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
 	int vcpu_id;
 	int r;
 
-	vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size);
 
 	perf_test_args.wr_fract = 1;
 
@@ -273,9 +277,9 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
 
-	if (use_uffd) {
+	if (p->use_uffd) {
 		uffd_handler_threads =
 			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
 		TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
@@ -308,7 +312,7 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
 			r = setup_demand_paging(vm,
 						&uffd_handler_threads[vcpu_id],
 						pipefds[vcpu_id * 2],
-						uffd_delay, &uffd_args[vcpu_id],
+						p->uffd_delay, &uffd_args[vcpu_id],
 						vcpu_hva, guest_percpu_mem_size);
 			if (r < 0)
 				exit(-r);
@@ -339,7 +343,7 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
 
 	pr_info("All vCPU threads joined\n");
 
-	if (use_uffd) {
+	if (p->use_uffd) {
 		char c;
 
 		/* Tell the user fault fd handler threads to quit */
@@ -357,43 +361,23 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
 		perf_test_args.vcpu_args[0].pages * nr_vcpus /
 		((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
 
-	ucall_uninit(vm);
-	kvm_vm_free(vm);
+	perf_test_destroy_vm(vm);
 
 	free(guest_data_prototype);
 	free(vcpu_threads);
-	if (use_uffd) {
+	if (p->use_uffd) {
 		free(uffd_handler_threads);
 		free(uffd_args);
 		free(pipefds);
 	}
 }
 
-struct guest_mode {
-	bool supported;
-	bool enabled;
-};
-static struct guest_mode guest_modes[NUM_VM_MODES];
-
-#define guest_mode_init(mode, supported, enabled) ({ \
-	guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
-})
-
 static void help(char *name)
 {
-	int i;
-
 	puts("");
 	printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n"
 	       "          [-b memory] [-v vcpus]\n", name);
-	printf(" -m: specify the guest mode ID to test\n"
-	       "     (default: test all supported modes)\n"
-	       "     This option may be used multiple times.\n"
-	       "     Guest mode IDs:\n");
-	for (i = 0; i < NUM_VM_MODES; ++i) {
-		printf("         %d:    %s%s\n", i, vm_guest_mode_string(i),
-		       guest_modes[i].supported ? " (supported)" : "");
-	}
+	guest_modes_help();
 	printf(" -u: use User Fault FD to handle vCPU page\n"
 	       "     faults.\n");
 	printf(" -d: add a delay in usec to the User Fault\n"
@@ -410,53 +394,22 @@ static void help(char *name)
 int main(int argc, char *argv[])
 {
 	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
-	bool mode_selected = false;
-	unsigned int mode;
-	int opt, i;
-	bool use_uffd = false;
-	useconds_t uffd_delay = 0;
-
-#ifdef __x86_64__
-	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
-#endif
-#ifdef __aarch64__
-	guest_mode_init(VM_MODE_P40V48_4K, true, true);
-	guest_mode_init(VM_MODE_P40V48_64K, true, true);
-	{
-		unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
-
-		if (limit >= 52)
-			guest_mode_init(VM_MODE_P52V48_64K, true, true);
-		if (limit >= 48) {
-			guest_mode_init(VM_MODE_P48V48_4K, true, true);
-			guest_mode_init(VM_MODE_P48V48_64K, true, true);
-		}
-	}
-#endif
-#ifdef __s390x__
-	guest_mode_init(VM_MODE_P40V48_4K, true, true);
-#endif
+	struct test_params p = {};
+	int opt;
+
+	guest_modes_append_default();
 
 	while ((opt = getopt(argc, argv, "hm:ud:b:v:")) != -1) {
 		switch (opt) {
 		case 'm':
-			if (!mode_selected) {
-				for (i = 0; i < NUM_VM_MODES; ++i)
-					guest_modes[i].enabled = false;
-				mode_selected = true;
-			}
-			mode = strtoul(optarg, NULL, 10);
-			TEST_ASSERT(mode < NUM_VM_MODES,
-				    "Guest mode ID %d too big", mode);
-			guest_modes[mode].enabled = true;
+			guest_modes_cmdline(optarg);
 			break;
 		case 'u':
-			use_uffd = true;
+			p.use_uffd = true;
 			break;
 		case 'd':
-			uffd_delay = strtoul(optarg, NULL, 0);
-			TEST_ASSERT(uffd_delay >= 0,
-				    "A negative UFFD delay is not supported.");
+			p.uffd_delay = strtoul(optarg, NULL, 0);
+			TEST_ASSERT(p.uffd_delay >= 0, "A negative UFFD delay is not supported.");
 			break;
 		case 'b':
 			guest_percpu_mem_size = parse_size(optarg);
@@ -473,14 +426,7 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	for (i = 0; i < NUM_VM_MODES; ++i) {
-		if (!guest_modes[i].enabled)
-			continue;
-		TEST_ASSERT(guest_modes[i].supported,
-			    "Guest mode ID %d (%s) not supported.",
-			    i, vm_guest_mode_string(i));
-		run_test(i, use_uffd, uffd_delay);
-	}
+	for_each_guest_mode(run_test, &p);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 85c9b8f73142..2283a0ec74a9 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -8,28 +8,28 @@
  * Copyright (C) 2020, Google, Inc.
  */
 
-#define _GNU_SOURCE /* for program_invocation_name */
-
 #include <stdio.h>
 #include <stdlib.h>
-#include <unistd.h>
 #include <time.h>
 #include <pthread.h>
 #include <linux/bitmap.h>
-#include <linux/bitops.h>
 
 #include "kvm_util.h"
-#include "perf_test_util.h"
-#include "processor.h"
 #include "test_util.h"
+#include "perf_test_util.h"
+#include "guest_modes.h"
 
 /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
 #define TEST_HOST_LOOP_N		2UL
 
+static int nr_vcpus = 1;
+static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+
 /* Host variables */
+static u64 dirty_log_manual_caps;
 static bool host_quit;
 static uint64_t iteration;
-static uint64_t vcpu_last_completed_iteration[MAX_VCPUS];
+static uint64_t vcpu_last_completed_iteration[KVM_MAX_VCPUS];
 
 static void *vcpu_worker(void *data)
 {
@@ -41,7 +41,7 @@ static void *vcpu_worker(void *data)
 	struct timespec ts_diff;
 	struct timespec total = (struct timespec){0};
 	struct timespec avg;
-	struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 
 	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
@@ -88,13 +88,15 @@ static void *vcpu_worker(void *data)
 	return NULL;
 }
 
-#ifdef USE_CLEAR_DIRTY_LOG
-static u64 dirty_log_manual_caps;
-#endif
+struct test_params {
+	unsigned long iterations;
+	uint64_t phys_offset;
+	int wr_fract;
+};
 
-static void run_test(enum vm_guest_mode mode, unsigned long iterations,
-		     uint64_t phys_offset, int wr_fract)
+static void run_test(enum vm_guest_mode mode, void *arg)
 {
+	struct test_params *p = arg;
 	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
 	unsigned long *bmap;
@@ -106,30 +108,28 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	struct timespec get_dirty_log_total = (struct timespec){0};
 	struct timespec vcpu_dirty_total = (struct timespec){0};
 	struct timespec avg;
-#ifdef USE_CLEAR_DIRTY_LOG
 	struct kvm_enable_cap cap = {};
 	struct timespec clear_dirty_log_total = (struct timespec){0};
-#endif
 
-	vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size);
 
-	perf_test_args.wr_fract = wr_fract;
+	perf_test_args.wr_fract = p->wr_fract;
 
 	guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
 	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
 	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
 	bmap = bitmap_alloc(host_num_pages);
 
-#ifdef USE_CLEAR_DIRTY_LOG
-	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
-	cap.args[0] = dirty_log_manual_caps;
-	vm_enable_cap(vm, &cap);
-#endif
+	if (dirty_log_manual_caps) {
+		cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
+		cap.args[0] = dirty_log_manual_caps;
+		vm_enable_cap(vm, &cap);
+	}
 
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
 
 	sync_global_to_guest(vm, perf_test_args);
 
@@ -155,13 +155,13 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	/* Enable dirty logging */
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX,
+	vm_mem_region_set_flags(vm, PERF_TEST_MEM_SLOT_INDEX,
 				KVM_MEM_LOG_DIRTY_PAGES);
 	ts_diff = timespec_diff_now(start);
 	pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
 
-	while (iteration < iterations) {
+	while (iteration < p->iterations) {
 		/*
 		 * Incrementing the iteration number will start the vCPUs
 		 * dirtying memory again.
@@ -182,7 +182,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
 
 		clock_gettime(CLOCK_MONOTONIC, &start);
-		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+		kvm_vm_get_dirty_log(vm, PERF_TEST_MEM_SLOT_INDEX, bmap);
 
 		ts_diff = timespec_diff_now(start);
 		get_dirty_log_total = timespec_add(get_dirty_log_total,
@@ -190,17 +190,17 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n",
 			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
 
-#ifdef USE_CLEAR_DIRTY_LOG
-		clock_gettime(CLOCK_MONOTONIC, &start);
-		kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
-				       host_num_pages);
+		if (dirty_log_manual_caps) {
+			clock_gettime(CLOCK_MONOTONIC, &start);
+			kvm_vm_clear_dirty_log(vm, PERF_TEST_MEM_SLOT_INDEX, bmap, 0,
+					       host_num_pages);
 
-		ts_diff = timespec_diff_now(start);
-		clear_dirty_log_total = timespec_add(clear_dirty_log_total,
-						     ts_diff);
-		pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n",
-			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
-#endif
+			ts_diff = timespec_diff_now(start);
+			clear_dirty_log_total = timespec_add(clear_dirty_log_total,
+							     ts_diff);
+			pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n",
+				iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+		}
 	}
 
 	/* Tell the vcpu thread to quit */
@@ -210,43 +210,30 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	/* Disable dirty logging */
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0);
+	vm_mem_region_set_flags(vm, PERF_TEST_MEM_SLOT_INDEX, 0);
 	ts_diff = timespec_diff_now(start);
 	pr_info("Disabling dirty logging time: %ld.%.9lds\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
 
-	avg = timespec_div(get_dirty_log_total, iterations);
+	avg = timespec_div(get_dirty_log_total, p->iterations);
 	pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
-		iterations, get_dirty_log_total.tv_sec,
+		p->iterations, get_dirty_log_total.tv_sec,
 		get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
 
-#ifdef USE_CLEAR_DIRTY_LOG
-	avg = timespec_div(clear_dirty_log_total, iterations);
-	pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
-		iterations, clear_dirty_log_total.tv_sec,
-		clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
-#endif
+	if (dirty_log_manual_caps) {
+		avg = timespec_div(clear_dirty_log_total, p->iterations);
+		pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+			p->iterations, clear_dirty_log_total.tv_sec,
+			clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+	}
 
 	free(bmap);
 	free(vcpu_threads);
-	ucall_uninit(vm);
-	kvm_vm_free(vm);
+	perf_test_destroy_vm(vm);
 }
 
-struct guest_mode {
-	bool supported;
-	bool enabled;
-};
-static struct guest_mode guest_modes[NUM_VM_MODES];
-
-#define guest_mode_init(mode, supported, enabled) ({ \
-	guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
-})
-
 static void help(char *name)
 {
-	int i;
-
 	puts("");
 	printf("usage: %s [-h] [-i iterations] [-p offset] "
 	       "[-m mode] [-b vcpu bytes] [-v vcpus]\n", name);
@@ -255,14 +242,7 @@ static void help(char *name)
 	       TEST_HOST_LOOP_N);
 	printf(" -p: specify guest physical test memory offset\n"
 	       "     Warning: a low offset can conflict with the loaded test code.\n");
-	printf(" -m: specify the guest mode ID to test "
-	       "(default: test all supported modes)\n"
-	       "     This option may be used multiple times.\n"
-	       "     Guest mode IDs:\n");
-	for (i = 0; i < NUM_VM_MODES; ++i) {
-		printf("         %d:    %s%s\n", i, vm_guest_mode_string(i),
-		       guest_modes[i].supported ? " (supported)" : "");
-	}
+	guest_modes_help();
 	printf(" -b: specify the size of the memory region which should be\n"
 	       "     dirtied by each vCPU. e.g. 10M or 3G.\n"
 	       "     (default: 1G)\n");
@@ -277,80 +257,43 @@ static void help(char *name)
 
 int main(int argc, char *argv[])
 {
-	unsigned long iterations = TEST_HOST_LOOP_N;
-	bool mode_selected = false;
-	uint64_t phys_offset = 0;
-	unsigned int mode;
-	int opt, i;
-	int wr_fract = 1;
-
-#ifdef USE_CLEAR_DIRTY_LOG
+	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
+	struct test_params p = {
+		.iterations = TEST_HOST_LOOP_N,
+		.wr_fract = 1,
+	};
+	int opt;
+
 	dirty_log_manual_caps =
 		kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
-	if (!dirty_log_manual_caps) {
-		print_skip("KVM_CLEAR_DIRTY_LOG not available");
-		exit(KSFT_SKIP);
-	}
 	dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
 				  KVM_DIRTY_LOG_INITIALLY_SET);
-#endif
-
-#ifdef __x86_64__
-	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
-#endif
-#ifdef __aarch64__
-	guest_mode_init(VM_MODE_P40V48_4K, true, true);
-	guest_mode_init(VM_MODE_P40V48_64K, true, true);
-
-	{
-		unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
-
-		if (limit >= 52)
-			guest_mode_init(VM_MODE_P52V48_64K, true, true);
-		if (limit >= 48) {
-			guest_mode_init(VM_MODE_P48V48_4K, true, true);
-			guest_mode_init(VM_MODE_P48V48_64K, true, true);
-		}
-	}
-#endif
-#ifdef __s390x__
-	guest_mode_init(VM_MODE_P40V48_4K, true, true);
-#endif
+
+	guest_modes_append_default();
 
 	while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) {
 		switch (opt) {
 		case 'i':
-			iterations = strtol(optarg, NULL, 10);
+			p.iterations = strtol(optarg, NULL, 10);
 			break;
 		case 'p':
-			phys_offset = strtoull(optarg, NULL, 0);
+			p.phys_offset = strtoull(optarg, NULL, 0);
 			break;
 		case 'm':
-			if (!mode_selected) {
-				for (i = 0; i < NUM_VM_MODES; ++i)
-					guest_modes[i].enabled = false;
-				mode_selected = true;
-			}
-			mode = strtoul(optarg, NULL, 10);
-			TEST_ASSERT(mode < NUM_VM_MODES,
-				    "Guest mode ID %d too big", mode);
-			guest_modes[mode].enabled = true;
+			guest_modes_cmdline(optarg);
 			break;
 		case 'b':
 			guest_percpu_mem_size = parse_size(optarg);
 			break;
 		case 'f':
-			wr_fract = atoi(optarg);
-			TEST_ASSERT(wr_fract >= 1,
+			p.wr_fract = atoi(optarg);
+			TEST_ASSERT(p.wr_fract >= 1,
 				    "Write fraction cannot be less than one");
 			break;
 		case 'v':
 			nr_vcpus = atoi(optarg);
-			TEST_ASSERT(nr_vcpus > 0,
-				    "Must have a positive number of vCPUs");
-			TEST_ASSERT(nr_vcpus <= MAX_VCPUS,
-				    "This test does not currently support\n"
-				    "more than %d vCPUs.", MAX_VCPUS);
+			TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
+				    "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
 			break;
 		case 'h':
 		default:
@@ -359,18 +302,11 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	TEST_ASSERT(iterations >= 2, "The test should have at least two iterations");
+	TEST_ASSERT(p.iterations >= 2, "The test should have at least two iterations");
 
-	pr_info("Test iterations: %"PRIu64"\n",	iterations);
+	pr_info("Test iterations: %"PRIu64"\n",	p.iterations);
 
-	for (i = 0; i < NUM_VM_MODES; ++i) {
-		if (!guest_modes[i].enabled)
-			continue;
-		TEST_ASSERT(guest_modes[i].supported,
-			    "Guest mode ID %d (%s) not supported.",
-			    i, vm_guest_mode_string(i));
-		run_test(i, iterations, phys_offset, wr_fract);
-	}
+	for_each_guest_mode(run_test, &p);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 54da9cc20db4..bb2752d78fe3 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -9,14 +9,18 @@
 
 #include <stdio.h>
 #include <stdlib.h>
-#include <unistd.h>
-#include <time.h>
 #include <pthread.h>
+#include <semaphore.h>
+#include <sys/types.h>
+#include <signal.h>
+#include <errno.h>
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
+#include <asm/barrier.h>
 
-#include "test_util.h"
 #include "kvm_util.h"
+#include "test_util.h"
+#include "guest_modes.h"
 #include "processor.h"
 
 #define VCPU_ID				1
@@ -57,6 +61,10 @@
 # define test_and_clear_bit_le	test_and_clear_bit
 #endif
 
+#define TEST_DIRTY_RING_COUNT		65536
+
+#define SIG_IPI SIGUSR1
+
 /*
  * Guest/Host shared variables. Ensure addr_gva2hva() and/or
  * sync_global_to/from_guest() are used when accessing from
@@ -128,6 +136,31 @@ static uint64_t host_dirty_count;
 static uint64_t host_clear_count;
 static uint64_t host_track_next_count;
 
+/* Whether dirty ring reset is requested, or finished */
+static sem_t dirty_ring_vcpu_stop;
+static sem_t dirty_ring_vcpu_cont;
+/*
+ * This is updated by the vcpu thread to tell the host whether it's a
+ * ring-full event.  It should only be read until a sem_wait() of
+ * dirty_ring_vcpu_stop and before vcpu continues to run.
+ */
+static bool dirty_ring_vcpu_ring_full;
+/*
+ * This is only used for verifying the dirty pages.  Dirty ring has a very
+ * tricky case when the ring just got full, kvm will do userspace exit due to
+ * ring full.  When that happens, the very last PFN is set but actually the
+ * data is not changed (the guest WRITE is not really applied yet), because
+ * we found that the dirty ring is full, refused to continue the vcpu, and
+ * recorded the dirty gfn with the old contents.
+ *
+ * For this specific case, it's safe to skip checking this pfn for this
+ * bit, because it's a redundant bit, and when the write happens later the bit
+ * will be set again.  We use this variable to always keep track of the latest
+ * dirty gfn we've collected, so that if a mismatch of data found later in the
+ * verifying process, we let it pass.
+ */
+static uint64_t dirty_ring_last_page;
+
 enum log_mode_t {
 	/* Only use KVM_GET_DIRTY_LOG for logging */
 	LOG_MODE_DIRTY_LOG = 0,
@@ -135,6 +168,9 @@ enum log_mode_t {
 	/* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */
 	LOG_MODE_CLEAR_LOG = 1,
 
+	/* Use dirty ring for logging */
+	LOG_MODE_DIRTY_RING = 2,
+
 	LOG_MODE_NUM,
 
 	/* Run all supported modes */
@@ -145,6 +181,26 @@ enum log_mode_t {
 static enum log_mode_t host_log_mode_option = LOG_MODE_ALL;
 /* Logging mode for current run */
 static enum log_mode_t host_log_mode;
+static pthread_t vcpu_thread;
+static uint32_t test_dirty_ring_count = TEST_DIRTY_RING_COUNT;
+
+static void vcpu_kick(void)
+{
+	pthread_kill(vcpu_thread, SIG_IPI);
+}
+
+/*
+ * In our test we do signal tricks, let's use a better version of
+ * sem_wait to avoid signal interrupts
+ */
+static void sem_wait_until(sem_t *sem)
+{
+	int ret;
+
+	do
+		ret = sem_wait(sem);
+	while (ret == -1 && errno == EINTR);
+}
 
 static bool clear_log_supported(void)
 {
@@ -178,6 +234,152 @@ static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
 }
 
+static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	TEST_ASSERT(ret == 0 || (ret == -1 && err == EINTR),
+		    "vcpu run failed: errno=%d", err);
+
+	TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC,
+		    "Invalid guest sync status: exit_reason=%s\n",
+		    exit_reason_str(run->exit_reason));
+}
+
+static bool dirty_ring_supported(void)
+{
+	return kvm_check_cap(KVM_CAP_DIRTY_LOG_RING);
+}
+
+static void dirty_ring_create_vm_done(struct kvm_vm *vm)
+{
+	/*
+	 * Switch to dirty ring mode after VM creation but before any
+	 * of the vcpu creation.
+	 */
+	vm_enable_dirty_ring(vm, test_dirty_ring_count *
+			     sizeof(struct kvm_dirty_gfn));
+}
+
+static inline bool dirty_gfn_is_dirtied(struct kvm_dirty_gfn *gfn)
+{
+	return gfn->flags == KVM_DIRTY_GFN_F_DIRTY;
+}
+
+static inline void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn)
+{
+	gfn->flags = KVM_DIRTY_GFN_F_RESET;
+}
+
+static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns,
+				       int slot, void *bitmap,
+				       uint32_t num_pages, uint32_t *fetch_index)
+{
+	struct kvm_dirty_gfn *cur;
+	uint32_t count = 0;
+
+	while (true) {
+		cur = &dirty_gfns[*fetch_index % test_dirty_ring_count];
+		if (!dirty_gfn_is_dirtied(cur))
+			break;
+		TEST_ASSERT(cur->slot == slot, "Slot number didn't match: "
+			    "%u != %u", cur->slot, slot);
+		TEST_ASSERT(cur->offset < num_pages, "Offset overflow: "
+			    "0x%llx >= 0x%x", cur->offset, num_pages);
+		//pr_info("fetch 0x%x page %llu\n", *fetch_index, cur->offset);
+		set_bit_le(cur->offset, bitmap);
+		dirty_ring_last_page = cur->offset;
+		dirty_gfn_set_collected(cur);
+		(*fetch_index)++;
+		count++;
+	}
+
+	return count;
+}
+
+static void dirty_ring_wait_vcpu(void)
+{
+	/* This makes sure that hardware PML cache flushed */
+	vcpu_kick();
+	sem_wait_until(&dirty_ring_vcpu_stop);
+}
+
+static void dirty_ring_continue_vcpu(void)
+{
+	pr_info("Notifying vcpu to continue\n");
+	sem_post(&dirty_ring_vcpu_cont);
+}
+
+static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					   void *bitmap, uint32_t num_pages)
+{
+	/* We only have one vcpu */
+	static uint32_t fetch_index = 0;
+	uint32_t count = 0, cleared;
+	bool continued_vcpu = false;
+
+	dirty_ring_wait_vcpu();
+
+	if (!dirty_ring_vcpu_ring_full) {
+		/*
+		 * This is not a ring-full event, it's safe to allow
+		 * vcpu to continue
+		 */
+		dirty_ring_continue_vcpu();
+		continued_vcpu = true;
+	}
+
+	/* Only have one vcpu */
+	count = dirty_ring_collect_one(vcpu_map_dirty_ring(vm, VCPU_ID),
+				       slot, bitmap, num_pages, &fetch_index);
+
+	cleared = kvm_vm_reset_dirty_ring(vm);
+
+	/* Cleared pages should be the same as collected */
+	TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch "
+		    "with collected (%u)", cleared, count);
+
+	if (!continued_vcpu) {
+		TEST_ASSERT(dirty_ring_vcpu_ring_full,
+			    "Didn't continue vcpu even without ring full");
+		dirty_ring_continue_vcpu();
+	}
+
+	pr_info("Iteration %ld collected %u pages\n", iteration, count);
+}
+
+static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	/* A ucall-sync or ring-full event is allowed */
+	if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) {
+		/* We should allow this to continue */
+		;
+	} else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL ||
+		   (ret == -1 && err == EINTR)) {
+		/* Update the flag first before pause */
+		WRITE_ONCE(dirty_ring_vcpu_ring_full,
+			   run->exit_reason == KVM_EXIT_DIRTY_RING_FULL);
+		sem_post(&dirty_ring_vcpu_stop);
+		pr_info("vcpu stops because %s...\n",
+			dirty_ring_vcpu_ring_full ?
+			"dirty ring is full" : "vcpu is kicked out");
+		sem_wait_until(&dirty_ring_vcpu_cont);
+		pr_info("vcpu continues now.\n");
+	} else {
+		TEST_ASSERT(false, "Invalid guest sync status: "
+			    "exit_reason=%s\n",
+			    exit_reason_str(run->exit_reason));
+	}
+}
+
+static void dirty_ring_before_vcpu_join(void)
+{
+	/* Kick another round of vcpu just to make sure it will quit */
+	sem_post(&dirty_ring_vcpu_cont);
+}
+
 struct log_mode {
 	const char *name;
 	/* Return true if this mode is supported, otherwise false */
@@ -187,16 +389,29 @@ struct log_mode {
 	/* Hook to collect the dirty pages into the bitmap provided */
 	void (*collect_dirty_pages) (struct kvm_vm *vm, int slot,
 				     void *bitmap, uint32_t num_pages);
+	/* Hook to call when after each vcpu run */
+	void (*after_vcpu_run)(struct kvm_vm *vm, int ret, int err);
+	void (*before_vcpu_join) (void);
 } log_modes[LOG_MODE_NUM] = {
 	{
 		.name = "dirty-log",
 		.collect_dirty_pages = dirty_log_collect_dirty_pages,
+		.after_vcpu_run = default_after_vcpu_run,
 	},
 	{
 		.name = "clear-log",
 		.supported = clear_log_supported,
 		.create_vm_done = clear_log_create_vm_done,
 		.collect_dirty_pages = clear_log_collect_dirty_pages,
+		.after_vcpu_run = default_after_vcpu_run,
+	},
+	{
+		.name = "dirty-ring",
+		.supported = dirty_ring_supported,
+		.create_vm_done = dirty_ring_create_vm_done,
+		.collect_dirty_pages = dirty_ring_collect_dirty_pages,
+		.before_vcpu_join = dirty_ring_before_vcpu_join,
+		.after_vcpu_run = dirty_ring_after_vcpu_run,
 	},
 };
 
@@ -247,6 +462,22 @@ static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
 }
 
+static void log_mode_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->after_vcpu_run)
+		mode->after_vcpu_run(vm, ret, err);
+}
+
+static void log_mode_before_vcpu_join(void)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->before_vcpu_join)
+		mode->before_vcpu_join();
+}
+
 static void generate_random_array(uint64_t *guest_array, uint64_t size)
 {
 	uint64_t i;
@@ -257,29 +488,44 @@ static void generate_random_array(uint64_t *guest_array, uint64_t size)
 
 static void *vcpu_worker(void *data)
 {
-	int ret;
+	int ret, vcpu_fd;
 	struct kvm_vm *vm = data;
 	uint64_t *guest_array;
 	uint64_t pages_count = 0;
-	struct kvm_run *run;
+	struct kvm_signal_mask *sigmask = alloca(offsetof(struct kvm_signal_mask, sigset)
+						 + sizeof(sigset_t));
+	sigset_t *sigset = (sigset_t *) &sigmask->sigset;
 
-	run = vcpu_state(vm, VCPU_ID);
+	vcpu_fd = vcpu_get_fd(vm, VCPU_ID);
+
+	/*
+	 * SIG_IPI is unblocked atomically while in KVM_RUN.  It causes the
+	 * ioctl to return with -EINTR, but it is still pending and we need
+	 * to accept it with the sigwait.
+	 */
+	sigmask->len = 8;
+	pthread_sigmask(0, NULL, sigset);
+	vcpu_ioctl(vm, VCPU_ID, KVM_SET_SIGNAL_MASK, sigmask);
+	sigaddset(sigset, SIG_IPI);
+	pthread_sigmask(SIG_BLOCK, sigset, NULL);
+
+	sigemptyset(sigset);
+	sigaddset(sigset, SIG_IPI);
 
 	guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array);
-	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
 
 	while (!READ_ONCE(host_quit)) {
+		/* Clear any existing kick signals */
+		generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+		pages_count += TEST_PAGES_PER_LOOP;
 		/* Let the guest dirty the random pages */
-		ret = _vcpu_run(vm, VCPU_ID);
-		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
-		if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) {
-			pages_count += TEST_PAGES_PER_LOOP;
-			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
-		} else {
-			TEST_FAIL("Invalid guest sync status: "
-				  "exit_reason=%s\n",
-				  exit_reason_str(run->exit_reason));
+		ret = ioctl(vcpu_fd, KVM_RUN, NULL);
+		if (ret == -1 && errno == EINTR) {
+			int sig = -1;
+			sigwait(sigset, &sig);
+			assert(sig == SIG_IPI);
 		}
+		log_mode_after_vcpu_run(vm, ret, errno);
 	}
 
 	pr_info("Dirtied %"PRIu64" pages\n", pages_count);
@@ -292,6 +538,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 	uint64_t step = vm_num_host_pages(mode, 1);
 	uint64_t page;
 	uint64_t *value_ptr;
+	uint64_t min_iter = 0;
 
 	for (page = 0; page < host_num_pages; page += step) {
 		value_ptr = host_test_mem + page * host_page_size;
@@ -306,14 +553,64 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 		}
 
 		if (test_and_clear_bit_le(page, bmap)) {
+			bool matched;
+
 			host_dirty_count++;
+
 			/*
 			 * If the bit is set, the value written onto
 			 * the corresponding page should be either the
 			 * previous iteration number or the current one.
 			 */
-			TEST_ASSERT(*value_ptr == iteration ||
-				    *value_ptr == iteration - 1,
+			matched = (*value_ptr == iteration ||
+				   *value_ptr == iteration - 1);
+
+			if (host_log_mode == LOG_MODE_DIRTY_RING && !matched) {
+				if (*value_ptr == iteration - 2 && min_iter <= iteration - 2) {
+					/*
+					 * Short answer: this case is special
+					 * only for dirty ring test where the
+					 * page is the last page before a kvm
+					 * dirty ring full in iteration N-2.
+					 *
+					 * Long answer: Assuming ring size R,
+					 * one possible condition is:
+					 *
+					 *      main thr       vcpu thr
+					 *      --------       --------
+					 *    iter=1
+					 *                   write 1 to page 0~(R-1)
+					 *                   full, vmexit
+					 *    collect 0~(R-1)
+					 *    kick vcpu
+					 *                   write 1 to (R-1)~(2R-2)
+					 *                   full, vmexit
+					 *    iter=2
+					 *    collect (R-1)~(2R-2)
+					 *    kick vcpu
+					 *                   write 1 to (2R-2)
+					 *                   (NOTE!!! "1" cached in cpu reg)
+					 *                   write 2 to (2R-1)~(3R-3)
+					 *                   full, vmexit
+					 *    iter=3
+					 *    collect (2R-2)~(3R-3)
+					 *    (here if we read value on page
+					 *     "2R-2" is 1, while iter=3!!!)
+					 *
+					 * This however can only happen once per iteration.
+					 */
+					min_iter = iteration - 1;
+					continue;
+				} else if (page == dirty_ring_last_page) {
+					/*
+					 * Please refer to comments in
+					 * dirty_ring_last_page.
+					 */
+					continue;
+				}
+			}
+
+			TEST_ASSERT(matched,
 				    "Set page %"PRIu64" value %"PRIu64
 				    " incorrect (iteration=%"PRIu64")",
 				    page, *value_ptr, iteration);
@@ -375,10 +672,15 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 #define DIRTY_MEM_BITS 30 /* 1G */
 #define PAGE_SHIFT_4K  12
 
-static void run_test(enum vm_guest_mode mode, unsigned long iterations,
-		     unsigned long interval, uint64_t phys_offset)
+struct test_params {
+	unsigned long iterations;
+	unsigned long interval;
+	uint64_t phys_offset;
+};
+
+static void run_test(enum vm_guest_mode mode, void *arg)
 {
-	pthread_t vcpu_thread;
+	struct test_params *p = arg;
 	struct kvm_vm *vm;
 	unsigned long *bmap;
 
@@ -412,12 +714,12 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	host_page_size = getpagesize();
 	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
 
-	if (!phys_offset) {
+	if (!p->phys_offset) {
 		guest_test_phys_mem = (vm_get_max_gfn(vm) -
 				       guest_num_pages) * guest_page_size;
 		guest_test_phys_mem &= ~(host_page_size - 1);
 	} else {
-		guest_test_phys_mem = phys_offset;
+		guest_test_phys_mem = p->phys_offset;
 	}
 
 #ifdef __s390x__
@@ -443,9 +745,6 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	/* Cache the HVA pointer of the region */
 	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem);
 
-#ifdef __x86_64__
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-#endif
 	ucall_init(vm, NULL);
 
 	/* Export the shared variables to the guest */
@@ -464,9 +763,9 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
 
-	while (iteration < iterations) {
+	while (iteration < p->iterations) {
 		/* Give the vcpu thread some time to dirty some pages */
-		usleep(interval * 1000);
+		usleep(p->interval * 1000);
 		log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
 					     bmap, host_num_pages);
 		vm_dirty_log_verify(mode, bmap);
@@ -476,6 +775,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	/* Tell the vcpu thread to quit */
 	host_quit = true;
+	log_mode_before_vcpu_join();
 	pthread_join(vcpu_thread, NULL);
 
 	pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "
@@ -488,24 +788,15 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	kvm_vm_free(vm);
 }
 
-struct guest_mode {
-	bool supported;
-	bool enabled;
-};
-static struct guest_mode guest_modes[NUM_VM_MODES];
-
-#define guest_mode_init(mode, supported, enabled) ({ \
-	guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
-})
-
 static void help(char *name)
 {
-	int i;
-
 	puts("");
 	printf("usage: %s [-h] [-i iterations] [-I interval] "
 	       "[-p offset] [-m mode]\n", name);
 	puts("");
+	printf(" -c: specify dirty ring size, in number of entries\n");
+	printf("     (only useful for dirty-ring test; default: %"PRIu32")\n",
+	       TEST_DIRTY_RING_COUNT);
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
 	       TEST_HOST_LOOP_N);
 	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
@@ -515,70 +806,40 @@ static void help(char *name)
 	printf(" -M: specify the host logging mode "
 	       "(default: run all log modes).  Supported modes: \n\t");
 	log_modes_dump();
-	printf(" -m: specify the guest mode ID to test "
-	       "(default: test all supported modes)\n"
-	       "     This option may be used multiple times.\n"
-	       "     Guest mode IDs:\n");
-	for (i = 0; i < NUM_VM_MODES; ++i) {
-		printf("         %d:    %s%s\n", i, vm_guest_mode_string(i),
-		       guest_modes[i].supported ? " (supported)" : "");
-	}
+	guest_modes_help();
 	puts("");
 	exit(0);
 }
 
 int main(int argc, char *argv[])
 {
-	unsigned long iterations = TEST_HOST_LOOP_N;
-	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
-	bool mode_selected = false;
-	uint64_t phys_offset = 0;
-	unsigned int mode;
-	int opt, i, j;
+	struct test_params p = {
+		.iterations = TEST_HOST_LOOP_N,
+		.interval = TEST_HOST_LOOP_INTERVAL,
+	};
+	int opt, i;
 
-#ifdef __x86_64__
-	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
-#endif
-#ifdef __aarch64__
-	guest_mode_init(VM_MODE_P40V48_4K, true, true);
-	guest_mode_init(VM_MODE_P40V48_64K, true, true);
-
-	{
-		unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+	sem_init(&dirty_ring_vcpu_stop, 0, 0);
+	sem_init(&dirty_ring_vcpu_cont, 0, 0);
 
-		if (limit >= 52)
-			guest_mode_init(VM_MODE_P52V48_64K, true, true);
-		if (limit >= 48) {
-			guest_mode_init(VM_MODE_P48V48_4K, true, true);
-			guest_mode_init(VM_MODE_P48V48_64K, true, true);
-		}
-	}
-#endif
-#ifdef __s390x__
-	guest_mode_init(VM_MODE_P40V48_4K, true, true);
-#endif
+	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) {
+	while ((opt = getopt(argc, argv, "c:hi:I:p:m:M:")) != -1) {
 		switch (opt) {
+		case 'c':
+			test_dirty_ring_count = strtol(optarg, NULL, 10);
+			break;
 		case 'i':
-			iterations = strtol(optarg, NULL, 10);
+			p.iterations = strtol(optarg, NULL, 10);
 			break;
 		case 'I':
-			interval = strtol(optarg, NULL, 10);
+			p.interval = strtol(optarg, NULL, 10);
 			break;
 		case 'p':
-			phys_offset = strtoull(optarg, NULL, 0);
+			p.phys_offset = strtoull(optarg, NULL, 0);
 			break;
 		case 'm':
-			if (!mode_selected) {
-				for (i = 0; i < NUM_VM_MODES; ++i)
-					guest_modes[i].enabled = false;
-				mode_selected = true;
-			}
-			mode = strtoul(optarg, NULL, 10);
-			TEST_ASSERT(mode < NUM_VM_MODES,
-				    "Guest mode ID %d too big", mode);
-			guest_modes[mode].enabled = true;
+			guest_modes_cmdline(optarg);
 			break;
 		case 'M':
 			if (!strcmp(optarg, "all")) {
@@ -607,32 +868,24 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
-	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+	TEST_ASSERT(p.iterations > 2, "Iterations must be greater than two");
+	TEST_ASSERT(p.interval > 0, "Interval must be greater than zero");
 
 	pr_info("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
-		iterations, interval);
+		p.iterations, p.interval);
 
 	srandom(time(0));
 
-	for (i = 0; i < NUM_VM_MODES; ++i) {
-		if (!guest_modes[i].enabled)
-			continue;
-		TEST_ASSERT(guest_modes[i].supported,
-			    "Guest mode ID %d (%s) not supported.",
-			    i, vm_guest_mode_string(i));
-		if (host_log_mode_option == LOG_MODE_ALL) {
-			/* Run each log mode */
-			for (j = 0; j < LOG_MODE_NUM; j++) {
-				pr_info("Testing Log Mode '%s'\n",
-					log_modes[j].name);
-				host_log_mode = j;
-				run_test(i, iterations, interval, phys_offset);
-			}
-		} else {
-			host_log_mode = host_log_mode_option;
-			run_test(i, iterations, interval, phys_offset);
+	if (host_log_mode_option == LOG_MODE_ALL) {
+		/* Run each log mode */
+		for (i = 0; i < LOG_MODE_NUM; i++) {
+			pr_info("Testing Log Mode '%s'\n", log_modes[i].name);
+			host_log_mode = i;
+			for_each_guest_mode(run_test, &p);
 		}
+	} else {
+		host_log_mode = host_log_mode_option;
+		for_each_guest_mode(run_test, &p);
 	}
 
 	return 0;
diff --git a/tools/testing/selftests/kvm/include/guest_modes.h b/tools/testing/selftests/kvm/include/guest_modes.h
new file mode 100644
index 000000000000..b691df33e64e
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/guest_modes.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include "kvm_util.h"
+
+struct guest_mode {
+	bool supported;
+	bool enabled;
+};
+
+extern struct guest_mode guest_modes[NUM_VM_MODES];
+
+#define guest_mode_append(mode, supported, enabled) ({ \
+	guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+})
+
+void guest_modes_append_default(void);
+void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg);
+void guest_modes_help(void);
+void guest_modes_cmdline(const char *arg);
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 7d29aa786959..5cbb861525ed 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -16,6 +16,7 @@
 
 #include "sparsebit.h"
 
+#define KVM_MAX_VCPUS 512
 
 /*
  * Callers of kvm_util only have an incomplete/opaque description of the
@@ -45,16 +46,39 @@ enum vm_guest_mode {
 };
 
 #if defined(__aarch64__)
-#define VM_MODE_DEFAULT VM_MODE_P40V48_4K
+
+#define VM_MODE_DEFAULT			VM_MODE_P40V48_4K
+#define MIN_PAGE_SHIFT			12U
+#define ptes_per_page(page_size)	((page_size) / 8)
+
 #elif defined(__x86_64__)
-#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K
-#else
-#define VM_MODE_DEFAULT VM_MODE_P52V48_4K
+
+#define VM_MODE_DEFAULT			VM_MODE_PXXV48_4K
+#define MIN_PAGE_SHIFT			12U
+#define ptes_per_page(page_size)	((page_size) / 8)
+
+#elif defined(__s390x__)
+
+#define VM_MODE_DEFAULT			VM_MODE_P52V48_4K
+#define MIN_PAGE_SHIFT			12U
+#define ptes_per_page(page_size)	((page_size) / 16)
+
 #endif
 
+#define MIN_PAGE_SIZE		(1U << MIN_PAGE_SHIFT)
+#define PTES_PER_MIN_PAGE	ptes_per_page(MIN_PAGE_SIZE)
+
 #define vm_guest_mode_string(m) vm_guest_mode_string[m]
 extern const char * const vm_guest_mode_string[];
 
+struct vm_guest_mode_params {
+	unsigned int pa_bits;
+	unsigned int va_bits;
+	unsigned int page_size;
+	unsigned int page_shift;
+};
+extern const struct vm_guest_mode_params vm_guest_mode_params[];
+
 enum vm_mem_backing_src_type {
 	VM_MEM_SRC_ANONYMOUS,
 	VM_MEM_SRC_ANONYMOUS_THP,
@@ -74,6 +98,7 @@ void kvm_vm_release(struct kvm_vm *vmp);
 void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
 void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
 			    uint64_t first_page, uint32_t num_pages);
+uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm);
 
 int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
 		       size_t len);
@@ -114,6 +139,8 @@ void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
 int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
 		void *arg);
 void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
 void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
 void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
 void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
@@ -146,6 +173,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
 struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
 			  struct kvm_guest_debug *debug);
@@ -199,6 +227,7 @@ void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
 int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
 			  struct kvm_nested_state *state, bool ignore_error);
 #endif
+void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid);
 
 const char *exit_reason_str(unsigned int exit_reason);
 
@@ -246,6 +275,16 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
 struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
 				 void *guest_code);
 
+/* Same as vm_create_default, but can be used for more than one vcpu */
+struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages,
+					    uint32_t num_percpu_pages, void *guest_code,
+					    uint32_t vcpuids[]);
+
+/* Like vm_create_default_with_vcpus, but accepts mode as a parameter */
+struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+				    uint64_t extra_mem_pages, uint32_t num_percpu_pages,
+				    void *guest_code, uint32_t vcpuids[]);
+
 /*
  * Adds a vCPU with reasonable defaults (e.g. a stack)
  *
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 2618052057b1..b1188823c31b 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -9,38 +9,15 @@
 #define SELFTEST_KVM_PERF_TEST_UTIL_H
 
 #include "kvm_util.h"
-#include "processor.h"
-
-#define MAX_VCPUS 512
-
-#define PAGE_SHIFT_4K  12
-#define PTES_PER_4K_PT 512
-
-#define TEST_MEM_SLOT_INDEX		1
 
 /* Default guest test virtual memory offset */
 #define DEFAULT_GUEST_TEST_MEM		0xc0000000
 
 #define DEFAULT_PER_VCPU_MEM_SIZE	(1 << 30) /* 1G */
 
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-static uint64_t guest_test_phys_mem;
-
-/*
- * Guest virtual memory offset of the testing memory slot.
- * Must not conflict with identity mapped test code.
- */
-static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
-static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
-
-/* Number of VCPUs for the test */
-static int nr_vcpus = 1;
+#define PERF_TEST_MEM_SLOT_INDEX	1
 
-struct vcpu_args {
+struct perf_test_vcpu_args {
 	uint64_t gva;
 	uint64_t pages;
 
@@ -54,145 +31,21 @@ struct perf_test_args {
 	uint64_t guest_page_size;
 	int wr_fract;
 
-	struct vcpu_args vcpu_args[MAX_VCPUS];
+	struct perf_test_vcpu_args vcpu_args[KVM_MAX_VCPUS];
 };
 
-static struct perf_test_args perf_test_args;
+extern struct perf_test_args perf_test_args;
 
 /*
- * Continuously write to the first 8 bytes of each page in the
- * specified region.
+ * Guest physical memory offset of the testing memory slot.
+ * This will be set to the topmost valid physical address minus
+ * the test memory size.
  */
-static void guest_code(uint32_t vcpu_id)
-{
-	struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
-	uint64_t gva;
-	uint64_t pages;
-	int i;
-
-	/* Make sure vCPU args data structure is not corrupt. */
-	GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id);
-
-	gva = vcpu_args->gva;
-	pages = vcpu_args->pages;
-
-	while (true) {
-		for (i = 0; i < pages; i++) {
-			uint64_t addr = gva + (i * perf_test_args.guest_page_size);
-
-			if (i % perf_test_args.wr_fract == 0)
-				*(uint64_t *)addr = 0x0123456789ABCDEF;
-			else
-				READ_ONCE(*(uint64_t *)addr);
-		}
-
-		GUEST_SYNC(1);
-	}
-}
-
-static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
-				uint64_t vcpu_memory_bytes)
-{
-	struct kvm_vm *vm;
-	uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
-	uint64_t guest_num_pages;
-
-	/* Account for a few pages per-vCPU for stacks */
-	pages += DEFAULT_STACK_PGS * vcpus;
-
-	/*
-	 * Reserve twice the ammount of memory needed to map the test region and
-	 * the page table / stacks region, at 4k, for page tables. Do the
-	 * calculation with 4K page size: the smallest of all archs. (e.g., 64K
-	 * page size guest will need even less memory for page tables).
-	 */
-	pages += (2 * pages) / PTES_PER_4K_PT;
-	pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
-		 PTES_PER_4K_PT;
-	pages = vm_adjust_num_guest_pages(mode, pages);
-
-	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
-
-	vm = vm_create(mode, pages, O_RDWR);
-	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-#ifdef __x86_64__
-	vm_create_irqchip(vm);
-#endif
-
-	perf_test_args.vm = vm;
-	perf_test_args.guest_page_size = vm_get_page_size(vm);
-	perf_test_args.host_page_size = getpagesize();
-
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
-		    "Guest memory size is not guest page size aligned.");
-
-	guest_num_pages = (vcpus * vcpu_memory_bytes) /
-			  perf_test_args.guest_page_size;
-	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
-
-	/*
-	 * If there should be more memory in the guest test region than there
-	 * can be pages in the guest, it will definitely cause problems.
-	 */
-	TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
-		    "Requested more guest memory than address space allows.\n"
-		    "    guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
-		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
-		    vcpu_memory_bytes);
-
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
-		    "Guest memory size is not host page size aligned.");
-
-	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
-			      perf_test_args.guest_page_size;
-	guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
-
-#ifdef __s390x__
-	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
-#endif
-
-	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
-
-	/* Add an extra memory slot for testing */
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    guest_test_phys_mem,
-				    TEST_MEM_SLOT_INDEX,
-				    guest_num_pages, 0);
-
-	/* Do mapping for the demand paging memory slot */
-	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
-
-	ucall_init(vm, NULL);
-
-	return vm;
-}
-
-static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes)
-{
-	vm_paddr_t vcpu_gpa;
-	struct vcpu_args *vcpu_args;
-	int vcpu_id;
-
-	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
-		vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
-
-		vm_vcpu_add_default(vm, vcpu_id, guest_code);
-
-#ifdef __x86_64__
-		vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
-#endif
-
-		vcpu_args->vcpu_id = vcpu_id;
-		vcpu_args->gva = guest_test_virt_mem +
-				 (vcpu_id * vcpu_memory_bytes);
-		vcpu_args->pages = vcpu_memory_bytes /
-				   perf_test_args.guest_page_size;
+extern uint64_t guest_test_phys_mem;
 
-		vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
-		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-			 vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
-	}
-}
+struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
+				uint64_t vcpu_memory_bytes);
+void perf_test_destroy_vm(struct kvm_vm *vm);
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes);
 
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h b/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h
new file mode 100644
index 000000000000..b0ed71302722
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * Test handler for the s390x DIAGNOSE 0x0318 instruction.
+ *
+ * Copyright (C) 2020, IBM
+ */
+
+#ifndef SELFTEST_KVM_DIAG318_TEST_HANDLER
+#define SELFTEST_KVM_DIAG318_TEST_HANDLER
+
+uint64_t get_diag318_info(void);
+
+#endif
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 8e61340b3911..90cd5984751b 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -27,6 +27,7 @@
 #define X86_CR4_OSFXSR		(1ul << 9)
 #define X86_CR4_OSXMMEXCPT	(1ul << 10)
 #define X86_CR4_UMIP		(1ul << 11)
+#define X86_CR4_LA57		(1ul << 12)
 #define X86_CR4_VMXE		(1ul << 13)
 #define X86_CR4_SMXE		(1ul << 14)
 #define X86_CR4_FSGSBASE	(1ul << 16)
@@ -36,6 +37,22 @@
 #define X86_CR4_SMAP		(1ul << 21)
 #define X86_CR4_PKE		(1ul << 22)
 
+/* CPUID.1.ECX */
+#define CPUID_VMX		(1ul << 5)
+#define CPUID_SMX		(1ul << 6)
+#define CPUID_PCID		(1ul << 17)
+#define CPUID_XSAVE		(1ul << 26)
+
+/* CPUID.7.EBX */
+#define CPUID_FSGSBASE		(1ul << 0)
+#define CPUID_SMEP		(1ul << 7)
+#define CPUID_SMAP		(1ul << 20)
+
+/* CPUID.7.ECX */
+#define CPUID_UMIP		(1ul << 2)
+#define CPUID_PKU		(1ul << 3)
+#define CPUID_LA57		(1ul << 16)
+
 #define UNEXPECTED_VECTOR_PORT 0xfff0u
 
 /* General Registers in 64-Bit Mode */
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index e78d7e26ba61..65eb1079a161 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -11,10 +11,6 @@
 #include <stdint.h>
 #include "processor.h"
 
-#define CPUID_VMX_BIT				5
-
-#define CPUID_VMX				(1 << 5)
-
 /*
  * Definitions of Primary Processor-Based VM-Execution Controls.
  */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index d6c32c328e9a..cee92d477dc0 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -5,8 +5,6 @@
  * Copyright (C) 2018, Red Hat, Inc.
  */
 
-#define _GNU_SOURCE /* for program_invocation_name */
-
 #include <linux/compiler.h>
 
 #include "kvm_util.h"
@@ -219,21 +217,6 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	}
 }
 
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
-				 void *guest_code)
-{
-	uint64_t ptrs_per_4k_pte = 512;
-	uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2;
-	struct kvm_vm *vm;
-
-	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
-
-	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-	vm_vcpu_add_default(vm, vcpuid, guest_code);
-
-	return vm;
-}
-
 void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *init)
 {
 	struct kvm_vcpu_init default_init = { .target = -1, };
diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
new file mode 100644
index 000000000000..25bff307c71f
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/guest_modes.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include "guest_modes.h"
+
+struct guest_mode guest_modes[NUM_VM_MODES];
+
+void guest_modes_append_default(void)
+{
+	guest_mode_append(VM_MODE_DEFAULT, true, true);
+
+#ifdef __aarch64__
+	guest_mode_append(VM_MODE_P40V48_64K, true, true);
+	{
+		unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+		if (limit >= 52)
+			guest_mode_append(VM_MODE_P52V48_64K, true, true);
+		if (limit >= 48) {
+			guest_mode_append(VM_MODE_P48V48_4K, true, true);
+			guest_mode_append(VM_MODE_P48V48_64K, true, true);
+		}
+	}
+#endif
+}
+
+void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg)
+{
+	int i;
+
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		if (!guest_modes[i].enabled)
+			continue;
+		TEST_ASSERT(guest_modes[i].supported,
+			    "Guest mode ID %d (%s) not supported.",
+			    i, vm_guest_mode_string(i));
+		func(i, arg);
+	}
+}
+
+void guest_modes_help(void)
+{
+	int i;
+
+	printf(" -m: specify the guest mode ID to test\n"
+	       "     (default: test all supported modes)\n"
+	       "     This option may be used multiple times.\n"
+	       "     Guest mode IDs:\n");
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		printf("         %d:    %s%s\n", i, vm_guest_mode_string(i),
+		       guest_modes[i].supported ? " (supported)" : "");
+	}
+}
+
+void guest_modes_cmdline(const char *arg)
+{
+	static bool mode_selected;
+	unsigned int mode;
+	int i;
+
+	if (!mode_selected) {
+		for (i = 0; i < NUM_VM_MODES; ++i)
+			guest_modes[i].enabled = false;
+		mode_selected = true;
+	}
+
+	mode = strtoul(optarg, NULL, 10);
+	TEST_ASSERT(mode < NUM_VM_MODES, "Guest mode ID %d too big", mode);
+	guest_modes[mode].enabled = true;
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 126c6727a6b0..fa5a90e6c6f0 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2018, Google LLC.
  */
 
+#define _GNU_SOURCE /* for program_invocation_name */
 #include "test_util.h"
 #include "kvm_util.h"
 #include "kvm_util_internal.h"
@@ -114,6 +115,16 @@ int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
 	return r;
 }
 
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size)
+{
+	struct kvm_enable_cap cap = { 0 };
+
+	cap.cap = KVM_CAP_DIRTY_LOG_RING;
+	cap.args[0] = ring_size;
+	vm_enable_cap(vm, &cap);
+	vm->dirty_ring_size = ring_size;
+}
+
 static void vm_open(struct kvm_vm *vm, int perm)
 {
 	vm->kvm_fd = open(KVM_DEV_PATH, perm);
@@ -142,14 +153,7 @@ const char * const vm_guest_mode_string[] = {
 _Static_assert(sizeof(vm_guest_mode_string)/sizeof(char *) == NUM_VM_MODES,
 	       "Missing new mode strings?");
 
-struct vm_guest_mode_params {
-	unsigned int pa_bits;
-	unsigned int va_bits;
-	unsigned int page_size;
-	unsigned int page_shift;
-};
-
-static const struct vm_guest_mode_params vm_guest_mode_params[] = {
+const struct vm_guest_mode_params vm_guest_mode_params[] = {
 	{ 52, 48,  0x1000, 12 },
 	{ 52, 48, 0x10000, 16 },
 	{ 48, 48,  0x1000, 12 },
@@ -271,6 +275,63 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	return vm;
 }
 
+struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+				    uint64_t extra_mem_pages, uint32_t num_percpu_pages,
+				    void *guest_code, uint32_t vcpuids[])
+{
+	/* The maximum page table size for a memory region will be when the
+	 * smallest pages are used. Considering each page contains x page
+	 * table descriptors, the total extra size for page tables (for extra
+	 * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller
+	 * than N/x*2.
+	 */
+	uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus;
+	uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2;
+	uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages;
+	struct kvm_vm *vm;
+	int i;
+
+	TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
+		    "nr_vcpus = %d too large for host, max-vcpus = %d",
+		    nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS));
+
+	pages = vm_adjust_num_guest_pages(mode, pages);
+	vm = vm_create(mode, pages, O_RDWR);
+
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+
+	for (i = 0; i < nr_vcpus; ++i) {
+		uint32_t vcpuid = vcpuids ? vcpuids[i] : i;
+
+		vm_vcpu_add_default(vm, vcpuid, guest_code);
+
+#ifdef __x86_64__
+		vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
+#endif
+	}
+
+	return vm;
+}
+
+struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages,
+					    uint32_t num_percpu_pages, void *guest_code,
+					    uint32_t vcpuids[])
+{
+	return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, extra_mem_pages,
+				    num_percpu_pages, guest_code, vcpuids);
+}
+
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+				 void *guest_code)
+{
+	return vm_create_default_with_vcpus(1, extra_mem_pages, 0, guest_code,
+					    (uint32_t []){ vcpuid });
+}
+
 /*
  * VM Restart
  *
@@ -328,6 +389,11 @@ void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
 		    __func__, strerror(-ret));
 }
 
+uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm)
+{
+	return ioctl(vm->fd, KVM_RESET_DIRTY_RINGS);
+}
+
 /*
  * Userspace Memory Region Find
  *
@@ -432,10 +498,17 @@ struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid)
  *
  * Removes a vCPU from a VM and frees its resources.
  */
-static void vm_vcpu_rm(struct vcpu *vcpu)
+static void vm_vcpu_rm(struct kvm_vm *vm, struct vcpu *vcpu)
 {
 	int ret;
 
+	if (vcpu->dirty_gfns) {
+		ret = munmap(vcpu->dirty_gfns, vm->dirty_ring_size);
+		TEST_ASSERT(ret == 0, "munmap of VCPU dirty ring failed, "
+			    "rc: %i errno: %i", ret, errno);
+		vcpu->dirty_gfns = NULL;
+	}
+
 	ret = munmap(vcpu->state, sizeof(*vcpu->state));
 	TEST_ASSERT(ret == 0, "munmap of VCPU fd failed, rc: %i "
 		"errno: %i", ret, errno);
@@ -453,7 +526,7 @@ void kvm_vm_release(struct kvm_vm *vmp)
 	int ret;
 
 	list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list)
-		vm_vcpu_rm(vcpu);
+		vm_vcpu_rm(vmp, vcpu);
 
 	ret = close(vmp->fd);
 	TEST_ASSERT(ret == 0, "Close of vm fd failed,\n"
@@ -1233,6 +1306,15 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	return rc;
 }
 
+int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	return vcpu->fd;
+}
+
 void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
@@ -1561,6 +1643,42 @@ int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
 	return ret;
 }
 
+void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu;
+	uint32_t size = vm->dirty_ring_size;
+
+	TEST_ASSERT(size > 0, "Should enable dirty ring first");
+
+	vcpu = vcpu_find(vm, vcpuid);
+
+	TEST_ASSERT(vcpu, "Cannot find vcpu %u", vcpuid);
+
+	if (!vcpu->dirty_gfns) {
+		void *addr;
+
+		addr = mmap(NULL, size, PROT_READ,
+			    MAP_PRIVATE, vcpu->fd,
+			    vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
+		TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped private");
+
+		addr = mmap(NULL, size, PROT_READ | PROT_EXEC,
+			    MAP_PRIVATE, vcpu->fd,
+			    vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
+		TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped exec");
+
+		addr = mmap(NULL, size, PROT_READ | PROT_WRITE,
+			    MAP_SHARED, vcpu->fd,
+			    vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET);
+		TEST_ASSERT(addr != MAP_FAILED, "Dirty ring map failed");
+
+		vcpu->dirty_gfns = addr;
+		vcpu->dirty_gfns_count = size / sizeof(struct kvm_dirty_gfn);
+	}
+
+	return vcpu->dirty_gfns;
+}
+
 /*
  * VM Ioctl
  *
@@ -1583,6 +1701,32 @@ void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
 }
 
 /*
+ * KVM system ioctl
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   cmd - Ioctl number
+ *   arg - Argument to pass to the ioctl
+ *
+ * Return: None
+ *
+ * Issues an arbitrary ioctl on a KVM fd.
+ */
+void kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
+{
+	int ret;
+
+	ret = ioctl(vm->kvm_fd, cmd, arg);
+	TEST_ASSERT(ret == 0, "KVM ioctl %lu failed, rc: %i errno: %i (%s)",
+		cmd, ret, errno, strerror(errno));
+}
+
+int _kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
+{
+	return ioctl(vm->kvm_fd, cmd, arg);
+}
+
+/*
  * VM Dump
  *
  * Input Args:
@@ -1654,6 +1798,9 @@ static struct exit_reason {
 	{KVM_EXIT_INTERNAL_ERROR, "INTERNAL_ERROR"},
 	{KVM_EXIT_OSI, "OSI"},
 	{KVM_EXIT_PAPR_HCALL, "PAPR_HCALL"},
+	{KVM_EXIT_DIRTY_RING_FULL, "DIRTY_RING_FULL"},
+	{KVM_EXIT_X86_RDMSR, "RDMSR"},
+	{KVM_EXIT_X86_WRMSR, "WRMSR"},
 #ifdef KVM_EXIT_MEMORY_NOT_PRESENT
 	{KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"},
 #endif
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index f07d383d03a1..34465dc562d8 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -28,6 +28,9 @@ struct vcpu {
 	uint32_t id;
 	int fd;
 	struct kvm_run *state;
+	struct kvm_dirty_gfn *dirty_gfns;
+	uint32_t fetch_index;
+	uint32_t dirty_gfns_count;
 };
 
 struct kvm_vm {
@@ -52,6 +55,7 @@ struct kvm_vm {
 	vm_vaddr_t tss;
 	vm_vaddr_t idt;
 	vm_vaddr_t handlers;
+	uint32_t dirty_ring_size;
 };
 
 struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
new file mode 100644
index 000000000000..9be1944c2d1c
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#include "kvm_util.h"
+#include "perf_test_util.h"
+#include "processor.h"
+
+struct perf_test_args perf_test_args;
+
+uint64_t guest_test_phys_mem;
+
+/*
+ * Guest virtual memory offset of the testing memory slot.
+ * Must not conflict with identity mapped test code.
+ */
+static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
+
+/*
+ * Continuously write to the first 8 bytes of each page in the
+ * specified region.
+ */
+static void guest_code(uint32_t vcpu_id)
+{
+	struct perf_test_vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+	uint64_t gva;
+	uint64_t pages;
+	int i;
+
+	/* Make sure vCPU args data structure is not corrupt. */
+	GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id);
+
+	gva = vcpu_args->gva;
+	pages = vcpu_args->pages;
+
+	while (true) {
+		for (i = 0; i < pages; i++) {
+			uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+
+			if (i % perf_test_args.wr_fract == 0)
+				*(uint64_t *)addr = 0x0123456789ABCDEF;
+			else
+				READ_ONCE(*(uint64_t *)addr);
+		}
+
+		GUEST_SYNC(1);
+	}
+}
+
+struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
+				   uint64_t vcpu_memory_bytes)
+{
+	struct kvm_vm *vm;
+	uint64_t guest_num_pages;
+
+	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
+	perf_test_args.host_page_size = getpagesize();
+	perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size;
+
+	guest_num_pages = vm_adjust_num_guest_pages(mode,
+				(vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size);
+
+	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+		    "Guest memory size is not host page size aligned.");
+	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+		    "Guest memory size is not guest page size aligned.");
+
+	vm = vm_create_with_vcpus(mode, vcpus,
+				  (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
+				  0, guest_code, NULL);
+
+	perf_test_args.vm = vm;
+
+	/*
+	 * If there should be more memory in the guest test region than there
+	 * can be pages in the guest, it will definitely cause problems.
+	 */
+	TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
+		    "Requested more guest memory than address space allows.\n"
+		    "    guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
+		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
+		    vcpu_memory_bytes);
+
+	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
+			      perf_test_args.guest_page_size;
+	guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+#ifdef __s390x__
+	/* Align to 1M (segment size) */
+	guest_test_phys_mem &= ~((1 << 20) - 1);
+#endif
+	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+
+	/* Add an extra memory slot for testing */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    guest_test_phys_mem,
+				    PERF_TEST_MEM_SLOT_INDEX,
+				    guest_num_pages, 0);
+
+	/* Do mapping for the demand paging memory slot */
+	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
+
+	ucall_init(vm, NULL);
+
+	return vm;
+}
+
+void perf_test_destroy_vm(struct kvm_vm *vm)
+{
+	ucall_uninit(vm);
+	kvm_vm_free(vm);
+}
+
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes)
+{
+	vm_paddr_t vcpu_gpa;
+	struct perf_test_vcpu_args *vcpu_args;
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+
+		vcpu_args->vcpu_id = vcpu_id;
+		vcpu_args->gva = guest_test_virt_mem +
+				 (vcpu_id * vcpu_memory_bytes);
+		vcpu_args->pages = vcpu_memory_bytes /
+				   perf_test_args.guest_page_size;
+
+		vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
+		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+			 vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+	}
+}
diff --git a/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c b/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c
new file mode 100644
index 000000000000..86b9e611ad87
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Test handler for the s390x DIAGNOSE 0x0318 instruction.
+ *
+ * Copyright (C) 2020, IBM
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+
+#define VCPU_ID	6
+
+#define ICPT_INSTRUCTION	0x04
+#define IPA0_DIAG		0x8300
+
+static void guest_code(void)
+{
+	uint64_t diag318_info = 0x12345678;
+
+	asm volatile ("diag %0,0,0x318\n" : : "d" (diag318_info));
+}
+
+/*
+ * The DIAGNOSE 0x0318 instruction call must be handled via userspace. As such,
+ * we create an ad-hoc VM here to handle the instruction then extract the
+ * necessary data. It is up to the caller to decide what to do with that data.
+ */
+static uint64_t diag318_handler(void)
+{
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	uint64_t reg;
+	uint64_t diag318_info;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	vcpu_run(vm, VCPU_ID);
+	run = vcpu_state(vm, VCPU_ID);
+
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC,
+		    "DIAGNOSE 0x0318 instruction was not intercepted");
+	TEST_ASSERT(run->s390_sieic.icptcode == ICPT_INSTRUCTION,
+		    "Unexpected intercept code: 0x%x", run->s390_sieic.icptcode);
+	TEST_ASSERT((run->s390_sieic.ipa & 0xff00) == IPA0_DIAG,
+		    "Unexpected IPA0 code: 0x%x", (run->s390_sieic.ipa & 0xff00));
+
+	reg = (run->s390_sieic.ipa & 0x00f0) >> 4;
+	diag318_info = run->s.regs.gprs[reg];
+
+	TEST_ASSERT(diag318_info != 0, "DIAGNOSE 0x0318 info not set");
+
+	kvm_vm_free(vm);
+
+	return diag318_info;
+}
+
+uint64_t get_diag318_info(void)
+{
+	static uint64_t diag318_info;
+	static bool printed_skip;
+
+	/*
+	 * If KVM does not support diag318, then return 0 to
+	 * ensure tests do not break.
+	 */
+	if (!kvm_check_cap(KVM_CAP_S390_DIAG318)) {
+		if (!printed_skip) {
+			fprintf(stdout, "KVM_CAP_S390_DIAG318 not supported. "
+				"Skipping diag318 test.\n");
+			printed_skip = true;
+		}
+		return 0;
+	}
+
+	/*
+	 * If a test has previously requested the diag318 info,
+	 * then don't bother spinning up a temporary VM again.
+	 */
+	if (!diag318_info)
+		diag318_info = diag318_handler();
+
+	return diag318_info;
+}
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 7349bb2e1a24..0152f356c099 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -5,8 +5,6 @@
  * Copyright (C) 2019, Red Hat, Inc.
  */
 
-#define _GNU_SOURCE /* for program_invocation_name */
-
 #include "processor.h"
 #include "kvm_util.h"
 #include "../kvm_util_internal.h"
@@ -160,26 +158,6 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	virt_dump_region(stream, vm, indent, vm->pgd);
 }
 
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
-				 void *guest_code)
-{
-	/*
-	 * The additional amount of pages required for the page tables is:
-	 * 1 * n / 256 + 4 * (n / 256) / 2048 + 4 * (n / 256) / 2048^2 + ...
-	 * which is definitely smaller than (n / 256) * 2.
-	 */
-	uint64_t extra_pg_pages = extra_mem_pages / 256 * 2;
-	struct kvm_vm *vm;
-
-	vm = vm_create(VM_MODE_DEFAULT,
-		       DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
-
-	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-	vm_vcpu_add_default(vm, vcpuid, guest_code);
-
-	return vm;
-}
-
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
 {
 	size_t stack_size =  DEFAULT_STACK_PGS * getpagesize();
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index d10c5c05bdf0..95e1a757c629 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -5,8 +5,6 @@
  * Copyright (C) 2018, Google LLC.
  */
 
-#define _GNU_SOURCE /* for program_invocation_name */
-
 #include "test_util.h"
 #include "kvm_util.h"
 #include "../kvm_util_internal.h"
@@ -731,36 +729,6 @@ void vcpu_set_cpuid(struct kvm_vm *vm,
 
 }
 
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
-				 void *guest_code)
-{
-	struct kvm_vm *vm;
-	/*
-	 * For x86 the maximum page table size for a memory region
-	 * will be when only 4K pages are used.  In that case the
-	 * total extra size for page tables (for extra N pages) will
-	 * be: N/512+N/512^2+N/512^3+... which is definitely smaller
-	 * than N/512*2.
-	 */
-	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
-
-	/* Create VM */
-	vm = vm_create(VM_MODE_DEFAULT,
-		       DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
-		       O_RDWR);
-
-	/* Setup guest code */
-	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-
-	/* Setup IRQ Chip */
-	vm_create_irqchip(vm);
-
-	/* Add the first vCPU. */
-	vm_vcpu_add_default(vm, vcpuid, guest_code);
-
-	return vm;
-}
-
 /*
  * VCPU Get MSR
  *
diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
index 5731ccf34917..caf7b8859a94 100644
--- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
@@ -20,6 +20,7 @@
 
 #include "test_util.h"
 #include "kvm_util.h"
+#include "diag318_test_handler.h"
 
 #define VCPU_ID 5
 
@@ -70,7 +71,7 @@ static void compare_sregs(struct kvm_sregs *left, struct kvm_sync_regs *right)
 
 #undef REG_COMPARE
 
-#define TEST_SYNC_FIELDS   (KVM_SYNC_GPRS|KVM_SYNC_ACRS|KVM_SYNC_CRS)
+#define TEST_SYNC_FIELDS   (KVM_SYNC_GPRS|KVM_SYNC_ACRS|KVM_SYNC_CRS|KVM_SYNC_DIAG318)
 #define INVALID_SYNC_FIELD 0x80000000
 
 int main(int argc, char *argv[])
@@ -152,6 +153,12 @@ int main(int argc, char *argv[])
 
 	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	run->kvm_dirty_regs = KVM_SYNC_GPRS | KVM_SYNC_ACRS;
+
+	if (get_diag318_info() > 0) {
+		run->s.regs.diag318 = get_diag318_info();
+		run->kvm_dirty_regs |= KVM_SYNC_DIAG318;
+	}
+
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv);
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC,
@@ -164,6 +171,9 @@ int main(int argc, char *argv[])
 	TEST_ASSERT(run->s.regs.acrs[0]  == 1 << 11,
 		    "acr0 sync regs value incorrect 0x%x.",
 		    run->s.regs.acrs[0]);
+	TEST_ASSERT(run->s.regs.diag318 == get_diag318_info(),
+		    "diag318 sync regs value incorrect 0x%llx.",
+		    run->s.regs.diag318);
 
 	vcpu_regs_get(vm, VCPU_ID, &regs);
 	compare_regs(&regs, &run->s.regs);
@@ -177,6 +187,7 @@ int main(int argc, char *argv[])
 	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	run->kvm_dirty_regs = 0;
 	run->s.regs.gprs[11] = 0xDEADBEEF;
+	run->s.regs.diag318 = 0x4B1D;
 	rv = _vcpu_run(vm, VCPU_ID);
 	TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv);
 	TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC,
@@ -186,6 +197,9 @@ int main(int argc, char *argv[])
 	TEST_ASSERT(run->s.regs.gprs[11] != 0xDEADBEEF,
 		    "r11 sync regs value incorrect 0x%llx.",
 		    run->s.regs.gprs[11]);
+	TEST_ASSERT(run->s.regs.diag318 != 0x4B1D,
+		    "diag318 sync regs value incorrect 0x%llx.",
+		    run->s.regs.diag318);
 
 	kvm_vm_free(vm);
 
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 6f441dd9f33c..f127ed31dba7 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -121,8 +121,6 @@ static struct kvm_vm *spawn_vm(pthread_t *vcpu_thread, void *guest_code)
 
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
 
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_THP,
 				    MEM_REGION_GPA, MEM_REGION_SLOT,
 				    MEM_REGION_SIZE / getpagesize(), 0);
diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
index 140e91901582..f40fd097cb35 100644
--- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
@@ -81,7 +81,6 @@ int main(int argc, char *argv[])
 
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 	run = vcpu_state(vm, VCPU_ID);
 
 	while (1) {
diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c
index 2fc6b3af81a1..6097a8283377 100644
--- a/tools/testing/selftests/kvm/x86_64/debug_regs.c
+++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c
@@ -85,7 +85,6 @@ int main(void)
 	}
 
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 	run = vcpu_state(vm, VCPU_ID);
 
 	/* Test software BPs - int3 */
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index 757928199f19..37b8a78f6b74 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -92,8 +92,6 @@ int main(int argc, char *argv[])
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
 
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-
 	if (!nested_vmx_supported() ||
 	    !kvm_check_cap(KVM_CAP_NESTED_STATE) ||
 	    !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
index 745b708c2d3b..88a595b7fbdd 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -46,19 +46,19 @@ static bool smt_possible(void)
 }
 
 static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
-			  bool evmcs_enabled)
+			  bool evmcs_expected)
 {
 	int i;
 	int nent = 9;
 	u32 test_val;
 
-	if (evmcs_enabled)
+	if (evmcs_expected)
 		nent += 1; /* 0x4000000A */
 
 	TEST_ASSERT(hv_cpuid_entries->nent == nent,
 		    "KVM_GET_SUPPORTED_HV_CPUID should return %d entries"
 		    " with evmcs=%d (returned %d)",
-		    nent, evmcs_enabled, hv_cpuid_entries->nent);
+		    nent, evmcs_expected, hv_cpuid_entries->nent);
 
 	for (i = 0; i < hv_cpuid_entries->nent; i++) {
 		struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i];
@@ -68,7 +68,7 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 			    "function %x is our of supported range",
 			    entry->function);
 
-		TEST_ASSERT(evmcs_enabled || (entry->function != 0x4000000A),
+		TEST_ASSERT(evmcs_expected || (entry->function != 0x4000000A),
 			    "0x4000000A leaf should not be reported");
 
 		TEST_ASSERT(entry->index == 0,
@@ -87,7 +87,7 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 			TEST_ASSERT(entry->eax == test_val,
 				    "Wrong max leaf report in 0x40000000.EAX: %x"
 				    " (evmcs=%d)",
-				    entry->eax, evmcs_enabled
+				    entry->eax, evmcs_expected
 				);
 			break;
 		case 0x40000004:
@@ -110,20 +110,23 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 
 }
 
-void test_hv_cpuid_e2big(struct kvm_vm *vm)
+void test_hv_cpuid_e2big(struct kvm_vm *vm, bool system)
 {
 	static struct kvm_cpuid2 cpuid = {.nent = 0};
 	int ret;
 
-	ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid);
+	if (!system)
+		ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid);
+	else
+		ret = _kvm_ioctl(vm, KVM_GET_SUPPORTED_HV_CPUID, &cpuid);
 
 	TEST_ASSERT(ret == -1 && errno == E2BIG,
-		    "KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when"
-		    " it should have: %d %d", ret, errno);
+		    "%s KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when"
+		    " it should have: %d %d", system ? "KVM" : "vCPU", ret, errno);
 }
 
 
-struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm)
+struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm, bool system)
 {
 	int nent = 20; /* should be enough */
 	static struct kvm_cpuid2 *cpuid;
@@ -137,7 +140,10 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm)
 
 	cpuid->nent = nent;
 
-	vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
+	if (!system)
+		vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
+	else
+		kvm_ioctl(vm, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
 
 	return cpuid;
 }
@@ -146,45 +152,50 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm)
 int main(int argc, char *argv[])
 {
 	struct kvm_vm *vm;
-	int rv, stage;
 	struct kvm_cpuid2 *hv_cpuid_entries;
-	bool evmcs_enabled;
 
 	/* Tell stdout not to buffer its content */
 	setbuf(stdout, NULL);
 
-	rv = kvm_check_cap(KVM_CAP_HYPERV_CPUID);
-	if (!rv) {
+	if (!kvm_check_cap(KVM_CAP_HYPERV_CPUID)) {
 		print_skip("KVM_CAP_HYPERV_CPUID not supported");
 		exit(KSFT_SKIP);
 	}
 
-	for (stage = 0; stage < 3; stage++) {
-		evmcs_enabled = false;
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
 
-		vm = vm_create_default(VCPU_ID, 0, guest_code);
-		switch (stage) {
-		case 0:
-			test_hv_cpuid_e2big(vm);
-			continue;
-		case 1:
-			break;
-		case 2:
-			if (!nested_vmx_supported() ||
-			    !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
-				print_skip("Enlightened VMCS is unsupported");
-				continue;
-			}
-			vcpu_enable_evmcs(vm, VCPU_ID);
-			evmcs_enabled = true;
-			break;
-		}
+	/* Test vCPU ioctl version */
+	test_hv_cpuid_e2big(vm, false);
+
+	hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, false);
+	test_hv_cpuid(hv_cpuid_entries, false);
+	free(hv_cpuid_entries);
 
-		hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
-		test_hv_cpuid(hv_cpuid_entries, evmcs_enabled);
-		free(hv_cpuid_entries);
-		kvm_vm_free(vm);
+	if (!nested_vmx_supported() ||
+	    !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
+		print_skip("Enlightened VMCS is unsupported");
+		goto do_sys;
 	}
+	vcpu_enable_evmcs(vm, VCPU_ID);
+	hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, false);
+	test_hv_cpuid(hv_cpuid_entries, true);
+	free(hv_cpuid_entries);
+
+do_sys:
+	/* Test system ioctl version */
+	if (!kvm_check_cap(KVM_CAP_SYS_HYPERV_CPUID)) {
+		print_skip("KVM_CAP_SYS_HYPERV_CPUID not supported");
+		goto out;
+	}
+
+	test_hv_cpuid_e2big(vm, true);
+
+	hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, true);
+	test_hv_cpuid(hv_cpuid_entries, nested_vmx_supported());
+	free(hv_cpuid_entries);
+
+out:
+	kvm_vm_free(vm);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
index b10a27485bad..732b244d6956 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
+++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
@@ -211,8 +211,8 @@ int main(void)
 	struct kvm_vm *vm;
 
 	if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) {
-		pr_info("will skip kvm paravirt restriction tests.\n");
-		return 0;
+		print_skip("KVM_CAP_ENFORCE_PV_FEATURE_CPUID not supported");
+		exit(KSFT_SKIP);
 	}
 
 	vm = vm_create_default(VCPU_ID, 0, guest_main);
diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
index 9f7656184f31..318be0bf77ab 100644
--- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
@@ -24,16 +24,106 @@
 
 #define VCPU_ID                  5
 
+static void test_cr4_feature_bit(struct kvm_vm *vm, struct kvm_sregs *orig,
+				 uint64_t feature_bit)
+{
+	struct kvm_sregs sregs;
+	int rc;
+
+	/* Skip the sub-test, the feature is supported. */
+	if (orig->cr4 & feature_bit)
+		return;
+
+	memcpy(&sregs, orig, sizeof(sregs));
+	sregs.cr4 |= feature_bit;
+
+	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(rc, "KVM allowed unsupported CR4 bit (0x%lx)", feature_bit);
+
+	/* Sanity check that KVM didn't change anything. */
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(!memcmp(&sregs, orig, sizeof(sregs)), "KVM modified sregs");
+}
+
+static uint64_t calc_cr4_feature_bits(struct kvm_vm *vm)
+{
+	struct kvm_cpuid_entry2 *cpuid_1, *cpuid_7;
+	uint64_t cr4;
+
+	cpuid_1 = kvm_get_supported_cpuid_entry(1);
+	cpuid_7 = kvm_get_supported_cpuid_entry(7);
+
+	cr4 = X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE |
+	      X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE | X86_CR4_PGE |
+	      X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT;
+	if (cpuid_7->ecx & CPUID_UMIP)
+		cr4 |= X86_CR4_UMIP;
+	if (cpuid_7->ecx & CPUID_LA57)
+		cr4 |= X86_CR4_LA57;
+	if (cpuid_1->ecx & CPUID_VMX)
+		cr4 |= X86_CR4_VMXE;
+	if (cpuid_1->ecx & CPUID_SMX)
+		cr4 |= X86_CR4_SMXE;
+	if (cpuid_7->ebx & CPUID_FSGSBASE)
+		cr4 |= X86_CR4_FSGSBASE;
+	if (cpuid_1->ecx & CPUID_PCID)
+		cr4 |= X86_CR4_PCIDE;
+	if (cpuid_1->ecx & CPUID_XSAVE)
+		cr4 |= X86_CR4_OSXSAVE;
+	if (cpuid_7->ebx & CPUID_SMEP)
+		cr4 |= X86_CR4_SMEP;
+	if (cpuid_7->ebx & CPUID_SMAP)
+		cr4 |= X86_CR4_SMAP;
+	if (cpuid_7->ecx & CPUID_PKU)
+		cr4 |= X86_CR4_PKE;
+
+	return cr4;
+}
+
 int main(int argc, char *argv[])
 {
 	struct kvm_sregs sregs;
 	struct kvm_vm *vm;
+	uint64_t cr4;
 	int rc;
 
 	/* Tell stdout not to buffer its content */
 	setbuf(stdout, NULL);
 
-	/* Create VM */
+	/*
+	 * Create a dummy VM, specifically to avoid doing KVM_SET_CPUID2, and
+	 * use it to verify all supported CR4 bits can be set prior to defining
+	 * the vCPU model, i.e. without doing KVM_SET_CPUID2.
+	 */
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	vm_vcpu_add(vm, VCPU_ID);
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+
+	sregs.cr4 |= calc_cr4_feature_bits(vm);
+	cr4 = sregs.cr4;
+
+	rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(!rc, "Failed to set supported CR4 bits (0x%lx)", cr4);
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(sregs.cr4 == cr4, "sregs.CR4 (0x%llx) != CR4 (0x%lx)",
+		    sregs.cr4, cr4);
+
+	/* Verify all unsupported features are rejected by KVM. */
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_UMIP);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_LA57);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_VMXE);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_SMXE);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_FSGSBASE);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_PCIDE);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_OSXSAVE);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_SMEP);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_SMAP);
+	test_cr4_feature_bit(vm, &sregs, X86_CR4_PKE);
+	kvm_vm_free(vm);
+
+	/* Create a "real" VM and verify APIC_BASE can be set. */
 	vm = vm_create_default(VCPU_ID, 0, NULL);
 
 	vcpu_sregs_get(vm, VCPU_ID, &sregs);
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index ae39a220609f..613c42c5a9b8 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -102,8 +102,6 @@ int main(int argc, char *argv[])
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
 
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-
 	run = vcpu_state(vm, VCPU_ID);
 
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA,
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index f6c8b9042f8a..32854c1462ad 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -165,7 +165,6 @@ int main(int argc, char *argv[])
 
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 	run = vcpu_state(vm, VCPU_ID);
 
 	vcpu_regs_get(vm, VCPU_ID, &regs1);
diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
index 0e1adb4e3199..be2ca157485b 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
@@ -44,7 +44,6 @@ int main(int argc, char *argv[])
 	nested_svm_check_supported();
 
 	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 
 	vcpu_alloc_svm(vm, &svm_gva);
 	vcpu_args_set(vm, VCPU_ID, 1, svm_gva);
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
index f8e761149daa..e357d8e222d4 100644
--- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
@@ -107,7 +107,6 @@ int main(void)
 	uint64_t val;
 
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 
 	val = 0;
 	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
diff --git a/tools/testing/selftests/kvm/x86_64/user_msr_test.c b/tools/testing/selftests/kvm/x86_64/user_msr_test.c
deleted file mode 100644
index cbe1b08890ff..000000000000
--- a/tools/testing/selftests/kvm/x86_64/user_msr_test.c
+++ /dev/null
@@ -1,248 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * tests for KVM_CAP_X86_USER_SPACE_MSR and KVM_X86_SET_MSR_FILTER
- *
- * Copyright (C) 2020, Amazon Inc.
- *
- * This is a functional test to verify that we can deflect MSR events
- * into user space.
- */
-#define _GNU_SOURCE /* for program_invocation_short_name */
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/ioctl.h>
-
-#include "test_util.h"
-
-#include "kvm_util.h"
-#include "processor.h"
-
-#define VCPU_ID                  5
-
-static u32 msr_reads, msr_writes;
-
-static u8 bitmap_00000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
-static u8 bitmap_00000000_write[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
-static u8 bitmap_40000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
-static u8 bitmap_c0000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
-static u8 bitmap_c0000000_read[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
-static u8 bitmap_deadbeef[1] = { 0x1 };
-
-static void deny_msr(uint8_t *bitmap, u32 msr)
-{
-	u32 idx = msr & (KVM_MSR_FILTER_MAX_BITMAP_SIZE - 1);
-
-	bitmap[idx / 8] &= ~(1 << (idx % 8));
-}
-
-static void prepare_bitmaps(void)
-{
-	memset(bitmap_00000000, 0xff, sizeof(bitmap_00000000));
-	memset(bitmap_00000000_write, 0xff, sizeof(bitmap_00000000_write));
-	memset(bitmap_40000000, 0xff, sizeof(bitmap_40000000));
-	memset(bitmap_c0000000, 0xff, sizeof(bitmap_c0000000));
-	memset(bitmap_c0000000_read, 0xff, sizeof(bitmap_c0000000_read));
-
-	deny_msr(bitmap_00000000_write, MSR_IA32_POWER_CTL);
-	deny_msr(bitmap_c0000000_read, MSR_SYSCALL_MASK);
-	deny_msr(bitmap_c0000000_read, MSR_GS_BASE);
-}
-
-struct kvm_msr_filter filter = {
-	.flags = KVM_MSR_FILTER_DEFAULT_DENY,
-	.ranges = {
-		{
-			.flags = KVM_MSR_FILTER_READ,
-			.base = 0x00000000,
-			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
-			.bitmap = bitmap_00000000,
-		}, {
-			.flags = KVM_MSR_FILTER_WRITE,
-			.base = 0x00000000,
-			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
-			.bitmap = bitmap_00000000_write,
-		}, {
-			.flags = KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE,
-			.base = 0x40000000,
-			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
-			.bitmap = bitmap_40000000,
-		}, {
-			.flags = KVM_MSR_FILTER_READ,
-			.base = 0xc0000000,
-			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
-			.bitmap = bitmap_c0000000_read,
-		}, {
-			.flags = KVM_MSR_FILTER_WRITE,
-			.base = 0xc0000000,
-			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
-			.bitmap = bitmap_c0000000,
-		}, {
-			.flags = KVM_MSR_FILTER_WRITE | KVM_MSR_FILTER_READ,
-			.base = 0xdeadbeef,
-			.nmsrs = 1,
-			.bitmap = bitmap_deadbeef,
-		},
-	},
-};
-
-struct kvm_msr_filter no_filter = {
-	.flags = KVM_MSR_FILTER_DEFAULT_ALLOW,
-};
-
-static void guest_msr_calls(bool trapped)
-{
-	/* This goes into the in-kernel emulation */
-	wrmsr(MSR_SYSCALL_MASK, 0);
-
-	if (trapped) {
-		/* This goes into user space emulation */
-		GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) == MSR_SYSCALL_MASK);
-		GUEST_ASSERT(rdmsr(MSR_GS_BASE) == MSR_GS_BASE);
-	} else {
-		GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) != MSR_SYSCALL_MASK);
-		GUEST_ASSERT(rdmsr(MSR_GS_BASE) != MSR_GS_BASE);
-	}
-
-	/* If trapped == true, this goes into user space emulation */
-	wrmsr(MSR_IA32_POWER_CTL, 0x1234);
-
-	/* This goes into the in-kernel emulation */
-	rdmsr(MSR_IA32_POWER_CTL);
-
-	/* Invalid MSR, should always be handled by user space exit */
-	GUEST_ASSERT(rdmsr(0xdeadbeef) == 0xdeadbeef);
-	wrmsr(0xdeadbeef, 0x1234);
-}
-
-static void guest_code(void)
-{
-	guest_msr_calls(true);
-
-	/*
-	 * Disable msr filtering, so that the kernel
-	 * handles everything in the next round
-	 */
-	GUEST_SYNC(0);
-
-	guest_msr_calls(false);
-
-	GUEST_DONE();
-}
-
-static int handle_ucall(struct kvm_vm *vm)
-{
-	struct ucall uc;
-
-	switch (get_ucall(vm, VCPU_ID, &uc)) {
-	case UCALL_ABORT:
-		TEST_FAIL("Guest assertion not met");
-		break;
-	case UCALL_SYNC:
-		vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &no_filter);
-		break;
-	case UCALL_DONE:
-		return 1;
-	default:
-		TEST_FAIL("Unknown ucall %lu", uc.cmd);
-	}
-
-	return 0;
-}
-
-static void handle_rdmsr(struct kvm_run *run)
-{
-	run->msr.data = run->msr.index;
-	msr_reads++;
-
-	if (run->msr.index == MSR_SYSCALL_MASK ||
-	    run->msr.index == MSR_GS_BASE) {
-		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER,
-			    "MSR read trap w/o access fault");
-	}
-
-	if (run->msr.index == 0xdeadbeef) {
-		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN,
-			    "MSR deadbeef read trap w/o inval fault");
-	}
-}
-
-static void handle_wrmsr(struct kvm_run *run)
-{
-	/* ignore */
-	msr_writes++;
-
-	if (run->msr.index == MSR_IA32_POWER_CTL) {
-		TEST_ASSERT(run->msr.data == 0x1234,
-			    "MSR data for MSR_IA32_POWER_CTL incorrect");
-		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER,
-			    "MSR_IA32_POWER_CTL trap w/o access fault");
-	}
-
-	if (run->msr.index == 0xdeadbeef) {
-		TEST_ASSERT(run->msr.data == 0x1234,
-			    "MSR data for deadbeef incorrect");
-		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN,
-			    "deadbeef trap w/o inval fault");
-	}
-}
-
-int main(int argc, char *argv[])
-{
-	struct kvm_enable_cap cap = {
-		.cap = KVM_CAP_X86_USER_SPACE_MSR,
-		.args[0] = KVM_MSR_EXIT_REASON_INVAL |
-			   KVM_MSR_EXIT_REASON_UNKNOWN |
-			   KVM_MSR_EXIT_REASON_FILTER,
-	};
-	struct kvm_vm *vm;
-	struct kvm_run *run;
-	int rc;
-
-	/* Tell stdout not to buffer its content */
-	setbuf(stdout, NULL);
-
-	/* Create VM */
-	vm = vm_create_default(VCPU_ID, 0, guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
-	run = vcpu_state(vm, VCPU_ID);
-
-	rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
-	TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
-	vm_enable_cap(vm, &cap);
-
-	rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER);
-	TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available");
-
-	prepare_bitmaps();
-	vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter);
-
-	while (1) {
-		rc = _vcpu_run(vm, VCPU_ID);
-
-		TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc);
-
-		switch (run->exit_reason) {
-		case KVM_EXIT_X86_RDMSR:
-			handle_rdmsr(run);
-			break;
-		case KVM_EXIT_X86_WRMSR:
-			handle_wrmsr(run);
-			break;
-		case KVM_EXIT_IO:
-			if (handle_ucall(vm))
-				goto done;
-			break;
-		}
-
-	}
-
-done:
-	TEST_ASSERT(msr_reads == 4, "Handled 4 rdmsr in user space");
-	TEST_ASSERT(msr_writes == 3, "Handled 3 wrmsr in user space");
-
-	kvm_vm_free(vm);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
new file mode 100644
index 000000000000..72c0d0797522
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
@@ -0,0 +1,770 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020, Google LLC.
+ *
+ * Tests for exiting into userspace on registered MSRs
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "vmx.h"
+
+/* Forced emulation prefix, used to invoke the emulator unconditionally. */
+#define KVM_FEP "ud2; .byte 'k', 'v', 'm';"
+#define KVM_FEP_LENGTH 5
+static int fep_available = 1;
+
+#define VCPU_ID	      1
+#define MSR_NON_EXISTENT 0x474f4f00
+
+static u64 deny_bits = 0;
+struct kvm_msr_filter filter_allow = {
+	.flags = KVM_MSR_FILTER_DEFAULT_ALLOW,
+	.ranges = {
+		{
+			.flags = KVM_MSR_FILTER_READ |
+				 KVM_MSR_FILTER_WRITE,
+			.nmsrs = 1,
+			/* Test an MSR the kernel knows about. */
+			.base = MSR_IA32_XSS,
+			.bitmap = (uint8_t*)&deny_bits,
+		}, {
+			.flags = KVM_MSR_FILTER_READ |
+				 KVM_MSR_FILTER_WRITE,
+			.nmsrs = 1,
+			/* Test an MSR the kernel doesn't know about. */
+			.base = MSR_IA32_FLUSH_CMD,
+			.bitmap = (uint8_t*)&deny_bits,
+		}, {
+			.flags = KVM_MSR_FILTER_READ |
+				 KVM_MSR_FILTER_WRITE,
+			.nmsrs = 1,
+			/* Test a fabricated MSR that no one knows about. */
+			.base = MSR_NON_EXISTENT,
+			.bitmap = (uint8_t*)&deny_bits,
+		},
+	},
+};
+
+struct kvm_msr_filter filter_fs = {
+	.flags = KVM_MSR_FILTER_DEFAULT_ALLOW,
+	.ranges = {
+		{
+			.flags = KVM_MSR_FILTER_READ,
+			.nmsrs = 1,
+			.base = MSR_FS_BASE,
+			.bitmap = (uint8_t*)&deny_bits,
+		},
+	},
+};
+
+struct kvm_msr_filter filter_gs = {
+	.flags = KVM_MSR_FILTER_DEFAULT_ALLOW,
+	.ranges = {
+		{
+			.flags = KVM_MSR_FILTER_READ,
+			.nmsrs = 1,
+			.base = MSR_GS_BASE,
+			.bitmap = (uint8_t*)&deny_bits,
+		},
+	},
+};
+
+static uint64_t msr_non_existent_data;
+static int guest_exception_count;
+static u32 msr_reads, msr_writes;
+
+static u8 bitmap_00000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
+static u8 bitmap_00000000_write[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
+static u8 bitmap_40000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
+static u8 bitmap_c0000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
+static u8 bitmap_c0000000_read[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
+static u8 bitmap_deadbeef[1] = { 0x1 };
+
+static void deny_msr(uint8_t *bitmap, u32 msr)
+{
+	u32 idx = msr & (KVM_MSR_FILTER_MAX_BITMAP_SIZE - 1);
+
+	bitmap[idx / 8] &= ~(1 << (idx % 8));
+}
+
+static void prepare_bitmaps(void)
+{
+	memset(bitmap_00000000, 0xff, sizeof(bitmap_00000000));
+	memset(bitmap_00000000_write, 0xff, sizeof(bitmap_00000000_write));
+	memset(bitmap_40000000, 0xff, sizeof(bitmap_40000000));
+	memset(bitmap_c0000000, 0xff, sizeof(bitmap_c0000000));
+	memset(bitmap_c0000000_read, 0xff, sizeof(bitmap_c0000000_read));
+
+	deny_msr(bitmap_00000000_write, MSR_IA32_POWER_CTL);
+	deny_msr(bitmap_c0000000_read, MSR_SYSCALL_MASK);
+	deny_msr(bitmap_c0000000_read, MSR_GS_BASE);
+}
+
+struct kvm_msr_filter filter_deny = {
+	.flags = KVM_MSR_FILTER_DEFAULT_DENY,
+	.ranges = {
+		{
+			.flags = KVM_MSR_FILTER_READ,
+			.base = 0x00000000,
+			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
+			.bitmap = bitmap_00000000,
+		}, {
+			.flags = KVM_MSR_FILTER_WRITE,
+			.base = 0x00000000,
+			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
+			.bitmap = bitmap_00000000_write,
+		}, {
+			.flags = KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE,
+			.base = 0x40000000,
+			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
+			.bitmap = bitmap_40000000,
+		}, {
+			.flags = KVM_MSR_FILTER_READ,
+			.base = 0xc0000000,
+			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
+			.bitmap = bitmap_c0000000_read,
+		}, {
+			.flags = KVM_MSR_FILTER_WRITE,
+			.base = 0xc0000000,
+			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
+			.bitmap = bitmap_c0000000,
+		}, {
+			.flags = KVM_MSR_FILTER_WRITE | KVM_MSR_FILTER_READ,
+			.base = 0xdeadbeef,
+			.nmsrs = 1,
+			.bitmap = bitmap_deadbeef,
+		},
+	},
+};
+
+struct kvm_msr_filter no_filter_deny = {
+	.flags = KVM_MSR_FILTER_DEFAULT_ALLOW,
+};
+
+/*
+ * Note: Force test_rdmsr() to not be inlined to prevent the labels,
+ * rdmsr_start and rdmsr_end, from being defined multiple times.
+ */
+static noinline uint64_t test_rdmsr(uint32_t msr)
+{
+	uint32_t a, d;
+
+	guest_exception_count = 0;
+
+	__asm__ __volatile__("rdmsr_start: rdmsr; rdmsr_end:" :
+			"=a"(a), "=d"(d) : "c"(msr) : "memory");
+
+	return a | ((uint64_t) d << 32);
+}
+
+/*
+ * Note: Force test_wrmsr() to not be inlined to prevent the labels,
+ * wrmsr_start and wrmsr_end, from being defined multiple times.
+ */
+static noinline void test_wrmsr(uint32_t msr, uint64_t value)
+{
+	uint32_t a = value;
+	uint32_t d = value >> 32;
+
+	guest_exception_count = 0;
+
+	__asm__ __volatile__("wrmsr_start: wrmsr; wrmsr_end:" ::
+			"a"(a), "d"(d), "c"(msr) : "memory");
+}
+
+extern char rdmsr_start, rdmsr_end;
+extern char wrmsr_start, wrmsr_end;
+
+/*
+ * Note: Force test_em_rdmsr() to not be inlined to prevent the labels,
+ * rdmsr_start and rdmsr_end, from being defined multiple times.
+ */
+static noinline uint64_t test_em_rdmsr(uint32_t msr)
+{
+	uint32_t a, d;
+
+	guest_exception_count = 0;
+
+	__asm__ __volatile__(KVM_FEP "em_rdmsr_start: rdmsr; em_rdmsr_end:" :
+			"=a"(a), "=d"(d) : "c"(msr) : "memory");
+
+	return a | ((uint64_t) d << 32);
+}
+
+/*
+ * Note: Force test_em_wrmsr() to not be inlined to prevent the labels,
+ * wrmsr_start and wrmsr_end, from being defined multiple times.
+ */
+static noinline void test_em_wrmsr(uint32_t msr, uint64_t value)
+{
+	uint32_t a = value;
+	uint32_t d = value >> 32;
+
+	guest_exception_count = 0;
+
+	__asm__ __volatile__(KVM_FEP "em_wrmsr_start: wrmsr; em_wrmsr_end:" ::
+			"a"(a), "d"(d), "c"(msr) : "memory");
+}
+
+extern char em_rdmsr_start, em_rdmsr_end;
+extern char em_wrmsr_start, em_wrmsr_end;
+
+static void guest_code_filter_allow(void)
+{
+	uint64_t data;
+
+	/*
+	 * Test userspace intercepting rdmsr / wrmsr for MSR_IA32_XSS.
+	 *
+	 * A GP is thrown if anything other than 0 is written to
+	 * MSR_IA32_XSS.
+	 */
+	data = test_rdmsr(MSR_IA32_XSS);
+	GUEST_ASSERT(data == 0);
+	GUEST_ASSERT(guest_exception_count == 0);
+
+	test_wrmsr(MSR_IA32_XSS, 0);
+	GUEST_ASSERT(guest_exception_count == 0);
+
+	test_wrmsr(MSR_IA32_XSS, 1);
+	GUEST_ASSERT(guest_exception_count == 1);
+
+	/*
+	 * Test userspace intercepting rdmsr / wrmsr for MSR_IA32_FLUSH_CMD.
+	 *
+	 * A GP is thrown if MSR_IA32_FLUSH_CMD is read
+	 * from or if a value other than 1 is written to it.
+	 */
+	test_rdmsr(MSR_IA32_FLUSH_CMD);
+	GUEST_ASSERT(guest_exception_count == 1);
+
+	test_wrmsr(MSR_IA32_FLUSH_CMD, 0);
+	GUEST_ASSERT(guest_exception_count == 1);
+
+	test_wrmsr(MSR_IA32_FLUSH_CMD, 1);
+	GUEST_ASSERT(guest_exception_count == 0);
+
+	/*
+	 * Test userspace intercepting rdmsr / wrmsr for MSR_NON_EXISTENT.
+	 *
+	 * Test that a fabricated MSR can pass through the kernel
+	 * and be handled in userspace.
+	 */
+	test_wrmsr(MSR_NON_EXISTENT, 2);
+	GUEST_ASSERT(guest_exception_count == 0);
+
+	data = test_rdmsr(MSR_NON_EXISTENT);
+	GUEST_ASSERT(data == 2);
+	GUEST_ASSERT(guest_exception_count == 0);
+
+	/*
+	 * Test to see if the instruction emulator is available (ie: the module
+	 * parameter 'kvm.force_emulation_prefix=1' is set).  This instruction
+	 * will #UD if it isn't available.
+	 */
+	__asm__ __volatile__(KVM_FEP "nop");
+
+	if (fep_available) {
+		/* Let userspace know we aren't done. */
+		GUEST_SYNC(0);
+
+		/*
+		 * Now run the same tests with the instruction emulator.
+		 */
+		data = test_em_rdmsr(MSR_IA32_XSS);
+		GUEST_ASSERT(data == 0);
+		GUEST_ASSERT(guest_exception_count == 0);
+		test_em_wrmsr(MSR_IA32_XSS, 0);
+		GUEST_ASSERT(guest_exception_count == 0);
+		test_em_wrmsr(MSR_IA32_XSS, 1);
+		GUEST_ASSERT(guest_exception_count == 1);
+
+		test_em_rdmsr(MSR_IA32_FLUSH_CMD);
+		GUEST_ASSERT(guest_exception_count == 1);
+		test_em_wrmsr(MSR_IA32_FLUSH_CMD, 0);
+		GUEST_ASSERT(guest_exception_count == 1);
+		test_em_wrmsr(MSR_IA32_FLUSH_CMD, 1);
+		GUEST_ASSERT(guest_exception_count == 0);
+
+		test_em_wrmsr(MSR_NON_EXISTENT, 2);
+		GUEST_ASSERT(guest_exception_count == 0);
+		data = test_em_rdmsr(MSR_NON_EXISTENT);
+		GUEST_ASSERT(data == 2);
+		GUEST_ASSERT(guest_exception_count == 0);
+	}
+
+	GUEST_DONE();
+}
+
+static void guest_msr_calls(bool trapped)
+{
+	/* This goes into the in-kernel emulation */
+	wrmsr(MSR_SYSCALL_MASK, 0);
+
+	if (trapped) {
+		/* This goes into user space emulation */
+		GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) == MSR_SYSCALL_MASK);
+		GUEST_ASSERT(rdmsr(MSR_GS_BASE) == MSR_GS_BASE);
+	} else {
+		GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) != MSR_SYSCALL_MASK);
+		GUEST_ASSERT(rdmsr(MSR_GS_BASE) != MSR_GS_BASE);
+	}
+
+	/* If trapped == true, this goes into user space emulation */
+	wrmsr(MSR_IA32_POWER_CTL, 0x1234);
+
+	/* This goes into the in-kernel emulation */
+	rdmsr(MSR_IA32_POWER_CTL);
+
+	/* Invalid MSR, should always be handled by user space exit */
+	GUEST_ASSERT(rdmsr(0xdeadbeef) == 0xdeadbeef);
+	wrmsr(0xdeadbeef, 0x1234);
+}
+
+static void guest_code_filter_deny(void)
+{
+	guest_msr_calls(true);
+
+	/*
+	 * Disable msr filtering, so that the kernel
+	 * handles everything in the next round
+	 */
+	GUEST_SYNC(0);
+
+	guest_msr_calls(false);
+
+	GUEST_DONE();
+}
+
+static void guest_code_permission_bitmap(void)
+{
+	uint64_t data;
+
+	data = test_rdmsr(MSR_FS_BASE);
+	GUEST_ASSERT(data == MSR_FS_BASE);
+	data = test_rdmsr(MSR_GS_BASE);
+	GUEST_ASSERT(data != MSR_GS_BASE);
+
+	/* Let userspace know to switch the filter */
+	GUEST_SYNC(0);
+
+	data = test_rdmsr(MSR_FS_BASE);
+	GUEST_ASSERT(data != MSR_FS_BASE);
+	data = test_rdmsr(MSR_GS_BASE);
+	GUEST_ASSERT(data == MSR_GS_BASE);
+
+	GUEST_DONE();
+}
+
+static void __guest_gp_handler(struct ex_regs *regs,
+			       char *r_start, char *r_end,
+			       char *w_start, char *w_end)
+{
+	if (regs->rip == (uintptr_t)r_start) {
+		regs->rip = (uintptr_t)r_end;
+		regs->rax = 0;
+		regs->rdx = 0;
+	} else if (regs->rip == (uintptr_t)w_start) {
+		regs->rip = (uintptr_t)w_end;
+	} else {
+		GUEST_ASSERT(!"RIP is at an unknown location!");
+	}
+
+	++guest_exception_count;
+}
+
+static void guest_gp_handler(struct ex_regs *regs)
+{
+	__guest_gp_handler(regs, &rdmsr_start, &rdmsr_end,
+			   &wrmsr_start, &wrmsr_end);
+}
+
+static void guest_fep_gp_handler(struct ex_regs *regs)
+{
+	__guest_gp_handler(regs, &em_rdmsr_start, &em_rdmsr_end,
+			   &em_wrmsr_start, &em_wrmsr_end);
+}
+
+static void guest_ud_handler(struct ex_regs *regs)
+{
+	fep_available = 0;
+	regs->rip += KVM_FEP_LENGTH;
+}
+
+static void run_guest(struct kvm_vm *vm)
+{
+	int rc;
+
+	rc = _vcpu_run(vm, VCPU_ID);
+	TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc);
+}
+
+static void check_for_guest_assert(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct ucall uc;
+
+	if (run->exit_reason == KVM_EXIT_IO &&
+		get_ucall(vm, VCPU_ID, &uc) == UCALL_ABORT) {
+			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+				__FILE__, uc.args[1]);
+	}
+}
+
+static void process_rdmsr(struct kvm_vm *vm, uint32_t msr_index)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	check_for_guest_assert(vm);
+
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_RDMSR,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+	TEST_ASSERT(run->msr.index == msr_index,
+			"Unexpected msr (0x%04x), expected 0x%04x",
+			run->msr.index, msr_index);
+
+	switch (run->msr.index) {
+	case MSR_IA32_XSS:
+		run->msr.data = 0;
+		break;
+	case MSR_IA32_FLUSH_CMD:
+		run->msr.error = 1;
+		break;
+	case MSR_NON_EXISTENT:
+		run->msr.data = msr_non_existent_data;
+		break;
+	case MSR_FS_BASE:
+		run->msr.data = MSR_FS_BASE;
+		break;
+	case MSR_GS_BASE:
+		run->msr.data = MSR_GS_BASE;
+		break;
+	default:
+		TEST_ASSERT(false, "Unexpected MSR: 0x%04x", run->msr.index);
+	}
+}
+
+static void process_wrmsr(struct kvm_vm *vm, uint32_t msr_index)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	check_for_guest_assert(vm);
+
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_WRMSR,
+		    "Unexpected exit reason: %u (%s),\n",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+	TEST_ASSERT(run->msr.index == msr_index,
+			"Unexpected msr (0x%04x), expected 0x%04x",
+			run->msr.index, msr_index);
+
+	switch (run->msr.index) {
+	case MSR_IA32_XSS:
+		if (run->msr.data != 0)
+			run->msr.error = 1;
+		break;
+	case MSR_IA32_FLUSH_CMD:
+		if (run->msr.data != 1)
+			run->msr.error = 1;
+		break;
+	case MSR_NON_EXISTENT:
+		msr_non_existent_data = run->msr.data;
+		break;
+	default:
+		TEST_ASSERT(false, "Unexpected MSR: 0x%04x", run->msr.index);
+	}
+}
+
+static void process_ucall_done(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct ucall uc;
+
+	check_for_guest_assert(vm);
+
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s)",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+
+	TEST_ASSERT(get_ucall(vm, VCPU_ID, &uc) == UCALL_DONE,
+		    "Unexpected ucall command: %lu, expected UCALL_DONE (%d)",
+		    uc.cmd, UCALL_DONE);
+}
+
+static uint64_t process_ucall(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct ucall uc = {};
+
+	check_for_guest_assert(vm);
+
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Unexpected exit reason: %u (%s)",
+		    run->exit_reason,
+		    exit_reason_str(run->exit_reason));
+
+	switch (get_ucall(vm, VCPU_ID, &uc)) {
+	case UCALL_SYNC:
+		break;
+	case UCALL_ABORT:
+		check_for_guest_assert(vm);
+		break;
+	case UCALL_DONE:
+		process_ucall_done(vm);
+		break;
+	default:
+		TEST_ASSERT(false, "Unexpected ucall");
+	}
+
+	return uc.cmd;
+}
+
+static void run_guest_then_process_rdmsr(struct kvm_vm *vm, uint32_t msr_index)
+{
+	run_guest(vm);
+	process_rdmsr(vm, msr_index);
+}
+
+static void run_guest_then_process_wrmsr(struct kvm_vm *vm, uint32_t msr_index)
+{
+	run_guest(vm);
+	process_wrmsr(vm, msr_index);
+}
+
+static uint64_t run_guest_then_process_ucall(struct kvm_vm *vm)
+{
+	run_guest(vm);
+	return process_ucall(vm);
+}
+
+static void run_guest_then_process_ucall_done(struct kvm_vm *vm)
+{
+	run_guest(vm);
+	process_ucall_done(vm);
+}
+
+static void test_msr_filter_allow(void) {
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_X86_USER_SPACE_MSR,
+		.args[0] = KVM_MSR_EXIT_REASON_FILTER,
+	};
+	struct kvm_vm *vm;
+	int rc;
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code_filter_allow);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
+	TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
+	vm_enable_cap(vm, &cap);
+
+	rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER);
+	TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available");
+
+	vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_allow);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+	vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+
+	/* Process guest code userspace exits. */
+	run_guest_then_process_rdmsr(vm, MSR_IA32_XSS);
+	run_guest_then_process_wrmsr(vm, MSR_IA32_XSS);
+	run_guest_then_process_wrmsr(vm, MSR_IA32_XSS);
+
+	run_guest_then_process_rdmsr(vm, MSR_IA32_FLUSH_CMD);
+	run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD);
+	run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD);
+
+	run_guest_then_process_wrmsr(vm, MSR_NON_EXISTENT);
+	run_guest_then_process_rdmsr(vm, MSR_NON_EXISTENT);
+
+	vm_handle_exception(vm, UD_VECTOR, guest_ud_handler);
+	run_guest(vm);
+	vm_handle_exception(vm, UD_VECTOR, NULL);
+
+	if (process_ucall(vm) != UCALL_DONE) {
+		vm_handle_exception(vm, GP_VECTOR, guest_fep_gp_handler);
+
+		/* Process emulated rdmsr and wrmsr instructions. */
+		run_guest_then_process_rdmsr(vm, MSR_IA32_XSS);
+		run_guest_then_process_wrmsr(vm, MSR_IA32_XSS);
+		run_guest_then_process_wrmsr(vm, MSR_IA32_XSS);
+
+		run_guest_then_process_rdmsr(vm, MSR_IA32_FLUSH_CMD);
+		run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD);
+		run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD);
+
+		run_guest_then_process_wrmsr(vm, MSR_NON_EXISTENT);
+		run_guest_then_process_rdmsr(vm, MSR_NON_EXISTENT);
+
+		/* Confirm the guest completed without issues. */
+		run_guest_then_process_ucall_done(vm);
+	} else {
+		printf("To run the instruction emulated tests set the module parameter 'kvm.force_emulation_prefix=1'\n");
+	}
+
+	kvm_vm_free(vm);
+}
+
+static int handle_ucall(struct kvm_vm *vm)
+{
+	struct ucall uc;
+
+	switch (get_ucall(vm, VCPU_ID, &uc)) {
+	case UCALL_ABORT:
+		TEST_FAIL("Guest assertion not met");
+		break;
+	case UCALL_SYNC:
+		vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &no_filter_deny);
+		break;
+	case UCALL_DONE:
+		return 1;
+	default:
+		TEST_FAIL("Unknown ucall %lu", uc.cmd);
+	}
+
+	return 0;
+}
+
+static void handle_rdmsr(struct kvm_run *run)
+{
+	run->msr.data = run->msr.index;
+	msr_reads++;
+
+	if (run->msr.index == MSR_SYSCALL_MASK ||
+	    run->msr.index == MSR_GS_BASE) {
+		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER,
+			    "MSR read trap w/o access fault");
+	}
+
+	if (run->msr.index == 0xdeadbeef) {
+		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN,
+			    "MSR deadbeef read trap w/o inval fault");
+	}
+}
+
+static void handle_wrmsr(struct kvm_run *run)
+{
+	/* ignore */
+	msr_writes++;
+
+	if (run->msr.index == MSR_IA32_POWER_CTL) {
+		TEST_ASSERT(run->msr.data == 0x1234,
+			    "MSR data for MSR_IA32_POWER_CTL incorrect");
+		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER,
+			    "MSR_IA32_POWER_CTL trap w/o access fault");
+	}
+
+	if (run->msr.index == 0xdeadbeef) {
+		TEST_ASSERT(run->msr.data == 0x1234,
+			    "MSR data for deadbeef incorrect");
+		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN,
+			    "deadbeef trap w/o inval fault");
+	}
+}
+
+static void test_msr_filter_deny(void) {
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_X86_USER_SPACE_MSR,
+		.args[0] = KVM_MSR_EXIT_REASON_INVAL |
+			   KVM_MSR_EXIT_REASON_UNKNOWN |
+			   KVM_MSR_EXIT_REASON_FILTER,
+	};
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	int rc;
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code_filter_deny);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+	run = vcpu_state(vm, VCPU_ID);
+
+	rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
+	TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
+	vm_enable_cap(vm, &cap);
+
+	rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER);
+	TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available");
+
+	prepare_bitmaps();
+	vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_deny);
+
+	while (1) {
+		rc = _vcpu_run(vm, VCPU_ID);
+
+		TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc);
+
+		switch (run->exit_reason) {
+		case KVM_EXIT_X86_RDMSR:
+			handle_rdmsr(run);
+			break;
+		case KVM_EXIT_X86_WRMSR:
+			handle_wrmsr(run);
+			break;
+		case KVM_EXIT_IO:
+			if (handle_ucall(vm))
+				goto done;
+			break;
+		}
+
+	}
+
+done:
+	TEST_ASSERT(msr_reads == 4, "Handled 4 rdmsr in user space");
+	TEST_ASSERT(msr_writes == 3, "Handled 3 wrmsr in user space");
+
+	kvm_vm_free(vm);
+}
+
+static void test_msr_permission_bitmap(void) {
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_X86_USER_SPACE_MSR,
+		.args[0] = KVM_MSR_EXIT_REASON_FILTER,
+	};
+	struct kvm_vm *vm;
+	int rc;
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code_permission_bitmap);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
+	TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
+	vm_enable_cap(vm, &cap);
+
+	rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER);
+	TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available");
+
+	vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_fs);
+	run_guest_then_process_rdmsr(vm, MSR_FS_BASE);
+	TEST_ASSERT(run_guest_then_process_ucall(vm) == UCALL_SYNC, "Expected ucall state to be UCALL_SYNC.");
+	vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_gs);
+	run_guest_then_process_rdmsr(vm, MSR_GS_BASE);
+	run_guest_then_process_ucall_done(vm);
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	test_msr_filter_allow();
+
+	test_msr_filter_deny();
+
+	test_msr_permission_bitmap();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
index 1f65342d6cb7..d14888b34adb 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
@@ -87,7 +87,6 @@ int main(int argc, char *argv[])
 	nested_vmx_check_supported();
 
 	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 
 	kvm_get_cpu_address_width(&paddr_width, &vaddr_width);
 	high_gpa = (1ul << paddr_width) - getpagesize();
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
index fe40ade06a49..2835a17f1b7a 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
@@ -57,7 +57,6 @@ int main(int argc, char *argv[])
 	nested_vmx_check_supported();
 
 	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 
 	/* Allocate VMX pages and shared descriptors (vmx_pages). */
 	vcpu_alloc_vmx(vm, &vmx_pages_gva);
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index e894a638a155..537de1068554 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -82,7 +82,6 @@ int main(int argc, char *argv[])
 
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, l1_guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 	vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva);
 	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
 	run = vcpu_state(vm, VCPU_ID);
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
index a7737af1224f..a07480aed397 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
@@ -169,20 +169,19 @@ int main(int argc, char *argv[])
 	 */
 	nested_vmx_check_supported();
 
+	if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) {
+		print_skip("KVM_CAP_NESTED_STATE not supported");
+		exit(KSFT_SKIP);
+	}
+
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 	run = vcpu_state(vm, VCPU_ID);
 
 	vcpu_regs_get(vm, VCPU_ID, &regs1);
 
-	if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
-		vcpu_alloc_vmx(vm, &vmx_pages_gva);
-		vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
-	} else {
-		pr_info("will skip vmx preemption timer checks\n");
-		goto done;
-	}
+	vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
 
 	for (stage = 1;; stage++) {
 		_vcpu_run(vm, VCPU_ID);
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
index d59f3eb67c8f..5827b9bae468 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
@@ -244,6 +244,22 @@ void test_vmx_nested_state(struct kvm_vm *vm)
 	free(state);
 }
 
+void disable_vmx(struct kvm_vm *vm)
+{
+	struct kvm_cpuid2 *cpuid = kvm_get_supported_cpuid();
+	int i;
+
+	for (i = 0; i < cpuid->nent; ++i)
+		if (cpuid->entries[i].function == 1 &&
+		    cpuid->entries[i].index == 0)
+			break;
+	TEST_ASSERT(i != cpuid->nent, "CPUID function 1 not found");
+
+	cpuid->entries[i].ecx &= ~CPUID_VMX;
+	vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+	cpuid->entries[i].ecx |= CPUID_VMX;
+}
+
 int main(int argc, char *argv[])
 {
 	struct kvm_vm *vm;
@@ -264,6 +280,11 @@ int main(int argc, char *argv[])
 
 	vm = vm_create_default(VCPU_ID, 0, 0);
 
+	/*
+	 * First run tests with VMX disabled to check error handling.
+	 */
+	disable_vmx(vm);
+
 	/* Passing a NULL kvm_nested_state causes a EFAULT. */
 	test_nested_state_expect_efault(vm, NULL);
 
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index fbe8417cbc2c..7e33a350b053 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -132,7 +132,6 @@ int main(int argc, char *argv[])
 	nested_vmx_check_supported();
 
 	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
-	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
 
 	/* Allocate VMX pages and shared descriptors (vmx_pages). */
 	vcpu_alloc_vmx(vm, &vmx_pages_gva);
diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py
index 58bb7e9b88ce..834066d465fc 100755
--- a/tools/testing/selftests/net/devlink_port_split.py
+++ b/tools/testing/selftests/net/devlink_port_split.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python3
+#!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0
 
 from subprocess import PIPE, Popen
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index eb693a3b7b4a..4c7d33618437 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -869,7 +869,7 @@ ipv6_torture()
 	pid3=$!
 	ip netns exec me ping -f 2001:db8:101::2 >/dev/null 2>&1 &
 	pid4=$!
-	ip netns exec me mausezahn veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+	ip netns exec me mausezahn -6 veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
 	pid5=$!
 
 	sleep 300
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 464e31eabc73..64cd2e23c568 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -162,7 +162,15 @@
 # - list_flush_ipv6_exception
 #	Using the same topology as in pmtu_ipv6, create exceptions, and check
 #	they are shown when listing exception caches, gone after flushing them
-
+#
+# - pmtu_ipv4_route_change
+#	Use the same topology as in pmtu_ipv4, but issue a route replacement
+#	command and delete the corresponding device afterward. This tests for
+#	proper cleanup of the PMTU exceptions by the route replacement path.
+#	Device unregistration should complete successfully
+#
+# - pmtu_ipv6_route_change
+#	Same as above but with IPv6
 
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
@@ -224,7 +232,9 @@ tests="
 	cleanup_ipv4_exception		ipv4: cleanup of cached exceptions	1
 	cleanup_ipv6_exception		ipv6: cleanup of cached exceptions	1
 	list_flush_ipv4_exception	ipv4: list and flush cached exceptions	1
-	list_flush_ipv6_exception	ipv6: list and flush cached exceptions	1"
+	list_flush_ipv6_exception	ipv6: list and flush cached exceptions	1
+	pmtu_ipv4_route_change		ipv4: PMTU exception w/route replace	1
+	pmtu_ipv6_route_change		ipv6: PMTU exception w/route replace	1"
 
 NS_A="ns-A"
 NS_B="ns-B"
@@ -1782,6 +1792,63 @@ test_list_flush_ipv6_exception() {
 	return ${fail}
 }
 
+test_pmtu_ipvX_route_change() {
+	family=${1}
+
+	setup namespaces routing || return 2
+	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
+	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
+	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2
+
+	if [ ${family} -eq 4 ]; then
+		ping=ping
+		dst1="${prefix4}.${b_r1}.1"
+		dst2="${prefix4}.${b_r2}.1"
+		gw="${prefix4}.${a_r1}.2"
+	else
+		ping=${ping6}
+		dst1="${prefix6}:${b_r1}::1"
+		dst2="${prefix6}:${b_r2}::1"
+		gw="${prefix6}:${a_r1}::2"
+	fi
+
+	# Set up initial MTU values
+	mtu "${ns_a}"  veth_A-R1 2000
+	mtu "${ns_r1}" veth_R1-A 2000
+	mtu "${ns_r1}" veth_R1-B 1400
+	mtu "${ns_b}"  veth_B-R1 1400
+
+	mtu "${ns_a}"  veth_A-R2 2000
+	mtu "${ns_r2}" veth_R2-A 2000
+	mtu "${ns_r2}" veth_R2-B 1500
+	mtu "${ns_b}"  veth_B-R2 1500
+
+	# Create route exceptions
+	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1}
+	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2}
+
+	# Check that exceptions have been created with the correct PMTU
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
+
+	# Replace the route from A to R1
+	run_cmd ${ns_a} ip route change default via ${gw}
+
+	# Delete the device in A
+	run_cmd ${ns_a} ip link del "veth_A-R1"
+}
+
+test_pmtu_ipv4_route_change() {
+	test_pmtu_ipvX_route_change 4
+}
+
+test_pmtu_ipv6_route_change() {
+	test_pmtu_ipvX_route_change 6
+}
+
 usage() {
 	echo
 	echo "$0 [OPTIONS] [TEST]..."
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index cb0d1890a860..e0088c2d38a5 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -103,8 +103,8 @@ FIXTURE(tls)
 
 FIXTURE_VARIANT(tls)
 {
-	u16 tls_version;
-	u16 cipher_type;
+	uint16_t tls_version;
+	uint16_t cipher_type;
 };
 
 FIXTURE_VARIANT_ADD(tls, 12_gcm)
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index ac2a30be9b32..f8a19f548ae9 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -5,6 +5,14 @@
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
+# set global exit status, but never reset nonzero one.
+check_err()
+{
+	if [ $ret -eq 0 ]; then
+		ret=$1
+	fi
+}
+
 cleanup() {
 	local -r jobs="$(jobs -p)"
 	local -r ns="$(ip netns list|grep $PEER_NS)"
@@ -44,7 +52,9 @@ run_one() {
 	# Hack: let bg programs complete the startup
 	sleep 0.1
 	./udpgso_bench_tx ${tx_args}
+	ret=$?
 	wait $(jobs -p)
+	return $ret
 }
 
 run_test() {
@@ -87,8 +97,10 @@ run_one_nat() {
 
 	sleep 0.1
 	./udpgso_bench_tx ${tx_args}
+	ret=$?
 	kill -INT $pid
 	wait $(jobs -p)
+	return $ret
 }
 
 run_one_2sock() {
@@ -110,7 +122,9 @@ run_one_2sock() {
 	sleep 0.1
 	# first UDP GSO socket should be closed at this point
 	./udpgso_bench_tx ${tx_args}
+	ret=$?
 	wait $(jobs -p)
+	return $ret
 }
 
 run_nat_test() {
@@ -131,36 +145,54 @@ run_all() {
 	local -r core_args="-l 4"
 	local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
 	local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+	ret=0
 
 	echo "ipv4"
 	run_test "no GRO" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400"
+	check_err $?
 
 	# explicitly check we are not receiving UDP_SEGMENT cmsg (-S -1)
 	# when GRO does not take place
 	run_test "no GRO chk cmsg" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400 -S -1"
+	check_err $?
 
 	# the GSO packets are aggregated because:
 	# * veth schedule napi after each xmit
 	# * segmentation happens in BH context, veth napi poll is delayed after
 	#   the transmission of the last segment
 	run_test "GRO" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720"
+	check_err $?
 	run_test "GRO chk cmsg" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+	check_err $?
 	run_test "GRO with custom segment size" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720"
+	check_err $?
 	run_test "GRO with custom segment size cmsg" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720 -S 500"
+	check_err $?
 
 	run_nat_test "bad GRO lookup" "${ipv4_args} -M 1 -s 14720 -S 0" "-n 10 -l 1472"
+	check_err $?
 	run_2sock_test "multiple GRO socks" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+	check_err $?
 
 	echo "ipv6"
 	run_test "no GRO" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400"
+	check_err $?
 	run_test "no GRO chk cmsg" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400 -S -1"
+	check_err $?
 	run_test "GRO" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520"
+	check_err $?
 	run_test "GRO chk cmsg" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520 -S 1452"
+	check_err $?
 	run_test "GRO with custom segment size" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520"
+	check_err $?
 	run_test "GRO with custom segment size cmsg" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520 -S 500"
+	check_err $?
 
 	run_nat_test "bad GRO lookup" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 10 -l 1452"
+	check_err $?
 	run_2sock_test "multiple GRO socks" "${ipv6_args} -M 1 -s 14520 -S 0 " "-n 1 -l 14520 -S 1452"
+	check_err $?
+	return $ret
 }
 
 if [ ! -f ../bpf/xdp_dummy.o ]; then
@@ -180,3 +212,5 @@ elif [[ $1 == "__subprocess_2sock" ]]; then
 	shift
 	run_one_2sock $@
 fi
+
+exit $?
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index a374e10ef506..3006a8e5b41a 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -4,7 +4,8 @@
 TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
 	conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
 	nft_concat_range.sh nft_conntrack_helper.sh \
-	nft_queue.sh nft_meta.sh
+	nft_queue.sh nft_meta.sh \
+	ipip-conntrack-mtu.sh
 
 LDLIBS = -lmnl
 TEST_GEN_FILES =  nf-queue
diff --git a/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh b/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh
new file mode 100755
index 000000000000..4a6f5c3b3215
--- /dev/null
+++ b/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh
@@ -0,0 +1,206 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# Conntrack needs to reassemble fragments in order to have complete
+# packets for rule matching.  Reassembly can lead to packet loss.
+
+# Consider the following setup:
+#            +--------+       +---------+       +--------+
+#            |Router A|-------|Wanrouter|-------|Router B|
+#            |        |.IPIP..|         |..IPIP.|        |
+#            +--------+       +---------+       +--------+
+#           /                  mtu 1400                   \
+#          /                                               \
+#+--------+                                                 +--------+
+#|Client A|                                                 |Client B|
+#|        |                                                 |        |
+#+--------+                                                 +--------+
+
+# Router A and Router B use IPIP tunnel interfaces to tunnel traffic
+# between Client A and Client B over WAN. Wanrouter has MTU 1400 set
+# on its interfaces.
+
+rnd=$(mktemp -u XXXXXXXX)
+rx=$(mktemp)
+
+r_a="ns-ra-$rnd"
+r_b="ns-rb-$rnd"
+r_w="ns-rw-$rnd"
+c_a="ns-ca-$rnd"
+c_b="ns-cb-$rnd"
+
+checktool (){
+	if ! $1 > /dev/null 2>&1; then
+		echo "SKIP: Could not $2"
+		exit $ksft_skip
+	fi
+}
+
+checktool "iptables --version" "run test without iptables"
+checktool "ip -Version" "run test without ip tool"
+checktool "which nc" "run test without nc (netcat)"
+checktool "ip netns add ${r_a}" "create net namespace"
+
+for n in ${r_b} ${r_w} ${c_a} ${c_b};do
+	ip netns add ${n}
+done
+
+cleanup() {
+	for n in ${r_a} ${r_b} ${r_w} ${c_a} ${c_b};do
+		ip netns del ${n}
+	done
+	rm -f ${rx}
+}
+
+trap cleanup EXIT
+
+test_path() {
+	msg="$1"
+
+	ip netns exec ${c_b} nc -n -w 3 -q 3 -u -l -p 5000 > ${rx} < /dev/null &
+
+	sleep 1
+	for i in 1 2 3; do
+		head -c1400 /dev/zero | tr "\000" "a" | ip netns exec ${c_a} nc -n -w 1 -u 192.168.20.2 5000
+	done
+
+	wait
+
+	bytes=$(wc -c < ${rx})
+
+	if [ $bytes -eq 1400 ];then
+		echo "OK: PMTU $msg connection tracking"
+	else
+		echo "FAIL: PMTU $msg connection tracking: got $bytes, expected 1400"
+		exit 1
+	fi
+}
+
+# Detailed setup for Router A
+# ---------------------------
+# Interfaces:
+# eth0: 10.2.2.1/24
+# eth1: 192.168.10.1/24
+# ipip0: No IP address, local 10.2.2.1 remote 10.4.4.1
+# Routes:
+# 192.168.20.0/24 dev ipip0    (192.168.20.0/24 is subnet of Client B)
+# 10.4.4.1 via 10.2.2.254      (Router B via Wanrouter)
+# No iptables rules at all.
+
+ip link add veth0 netns ${r_a} type veth peer name veth0 netns ${r_w}
+ip link add veth1 netns ${r_a} type veth peer name veth0 netns ${c_a}
+
+l_addr="10.2.2.1"
+r_addr="10.4.4.1"
+ip netns exec ${r_a} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip
+
+for dev in lo veth0 veth1 ipip0; do
+    ip -net ${r_a} link set $dev up
+done
+
+ip -net ${r_a} addr add 10.2.2.1/24 dev veth0
+ip -net ${r_a} addr add 192.168.10.1/24 dev veth1
+
+ip -net ${r_a} route add 192.168.20.0/24 dev ipip0
+ip -net ${r_a} route add 10.4.4.0/24 via 10.2.2.254
+
+ip netns exec ${r_a} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Detailed setup for Router B
+# ---------------------------
+# Interfaces:
+# eth0: 10.4.4.1/24
+# eth1: 192.168.20.1/24
+# ipip0: No IP address, local 10.4.4.1 remote 10.2.2.1
+# Routes:
+# 192.168.10.0/24 dev ipip0    (192.168.10.0/24 is subnet of Client A)
+# 10.2.2.1 via 10.4.4.254      (Router A via Wanrouter)
+# No iptables rules at all.
+
+ip link add veth0 netns ${r_b} type veth peer name veth1 netns ${r_w}
+ip link add veth1 netns ${r_b} type veth peer name veth0 netns ${c_b}
+
+l_addr="10.4.4.1"
+r_addr="10.2.2.1"
+
+ip netns exec ${r_b} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip
+
+for dev in lo veth0 veth1 ipip0; do
+	ip -net ${r_b} link set $dev up
+done
+
+ip -net ${r_b} addr add 10.4.4.1/24 dev veth0
+ip -net ${r_b} addr add 192.168.20.1/24 dev veth1
+
+ip -net ${r_b} route add 192.168.10.0/24 dev ipip0
+ip -net ${r_b} route add 10.2.2.0/24 via 10.4.4.254
+ip netns exec ${r_b} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Client A
+ip -net ${c_a} addr add 192.168.10.2/24 dev veth0
+ip -net ${c_a} link set dev lo up
+ip -net ${c_a} link set dev veth0 up
+ip -net ${c_a} route add default via 192.168.10.1
+
+# Client A
+ip -net ${c_b} addr add 192.168.20.2/24 dev veth0
+ip -net ${c_b} link set dev veth0 up
+ip -net ${c_b} link set dev lo up
+ip -net ${c_b} route add default via 192.168.20.1
+
+# Wan
+ip -net ${r_w} addr add 10.2.2.254/24 dev veth0
+ip -net ${r_w} addr add 10.4.4.254/24 dev veth1
+
+ip -net ${r_w} link set dev lo up
+ip -net ${r_w} link set dev veth0 up mtu 1400
+ip -net ${r_w} link set dev veth1 up mtu 1400
+
+ip -net ${r_a} link set dev veth0 mtu 1400
+ip -net ${r_b} link set dev veth0 mtu 1400
+
+ip netns exec ${r_w} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Path MTU discovery
+# ------------------
+# Running tracepath from Client A to Client B shows PMTU discovery is working
+# as expected:
+#
+# clienta:~# tracepath 192.168.20.2
+# 1?: [LOCALHOST]                      pmtu 1500
+# 1:  192.168.10.1                                          0.867ms
+# 1:  192.168.10.1                                          0.302ms
+# 2:  192.168.10.1                                          0.312ms pmtu 1480
+# 2:  no reply
+# 3:  192.168.10.1                                          0.510ms pmtu 1380
+# 3:  192.168.20.2                                          2.320ms reached
+# Resume: pmtu 1380 hops 3 back 3
+
+# ip netns exec ${c_a} traceroute --mtu 192.168.20.2
+
+# Router A has learned PMTU (1400) to Router B from Wanrouter.
+# Client A has learned PMTU (1400 - IPIP overhead = 1380) to Client B
+# from Router A.
+
+#Send large UDP packet
+#---------------------
+#Now we send a 1400 bytes UDP packet from Client A to Client B:
+
+# clienta:~# head -c1400 /dev/zero | tr "\000" "a" | nc -u 192.168.20.2 5000
+test_path "without"
+
+# The IPv4 stack on Client A already knows the PMTU to Client B, so the
+# UDP packet is sent as two fragments (1380 + 20). Router A forwards the
+# fragments between eth1 and ipip0. The fragments fit into the tunnel and
+# reach their destination.
+
+#When sending the large UDP packet again, Router A now reassembles the
+#fragments before routing the packet over ipip0. The resulting IPIP
+#packet is too big (1400) for the tunnel PMTU (1380) to Router B, it is
+#dropped on Router A before sending.
+
+ip netns exec ${r_a} iptables -A FORWARD -m conntrack --ctstate NEW
+test_path "with"
diff --git a/tools/testing/selftests/netfilter/nft_conntrack_helper.sh b/tools/testing/selftests/netfilter/nft_conntrack_helper.sh
index edf0a48da6bf..bf6b9626c7dd 100755
--- a/tools/testing/selftests/netfilter/nft_conntrack_helper.sh
+++ b/tools/testing/selftests/netfilter/nft_conntrack_helper.sh
@@ -94,7 +94,13 @@ check_for_helper()
 	local message=$2
 	local port=$3
 
-	ip netns exec ${netns} conntrack -L -p tcp --dport $port 2> /dev/null |grep -q 'helper=ftp'
+	if echo $message |grep -q 'ipv6';then
+		local family="ipv6"
+	else
+		local family="ipv4"
+	fi
+
+	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
@@ -111,8 +117,8 @@ test_helper()
 
 	sleep 3 | ip netns exec ${ns2} nc -w 2 -l -p $port > /dev/null &
 
-	sleep 1
 	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
@@ -128,8 +134,8 @@ test_helper()
 
 	sleep 3 | ip netns exec ${ns2} nc -w 2 -6 -l -p $port > /dev/null &
 
-	sleep 1
 	sleep 1 | ip netns exec ${ns1} nc -w 2 -6 dead:1::2 $port > /dev/null &
+	sleep 1
 
 	check_for_helper "$ns1" "ipv6 $msg" $port
 	check_for_helper "$ns2" "ipv6 $msg" $port
diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py
index 995f66ce43eb..35d5d9493784 100755
--- a/tools/testing/selftests/tc-testing/tdc_batch.py
+++ b/tools/testing/selftests/tc-testing/tdc_batch.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python3
+#!/usr/bin/env python3
 
 """
 tdc_batch.py - a script to generate TC batch file
diff --git a/tools/testing/selftests/tc-testing/tdc_multibatch.py b/tools/testing/selftests/tc-testing/tdc_multibatch.py
index 5e7237952e49..48e1f17ff2e8 100755
--- a/tools/testing/selftests/tc-testing/tdc_multibatch.py
+++ b/tools/testing/selftests/tc-testing/tdc_multibatch.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python3
+#!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0
 """
 tdc_multibatch.py - a thin wrapper over tdc_batch.py to generate multiple batch
diff --git a/tools/testing/selftests/vDSO/.gitignore b/tools/testing/selftests/vDSO/.gitignore
index 5eb64d41e541..a8dc51af5a9c 100644
--- a/tools/testing/selftests/vDSO/.gitignore
+++ b/tools/testing/selftests/vDSO/.gitignore
@@ -1,5 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 vdso_test
+vdso_test_abi
+vdso_test_clock_getres
+vdso_test_correctness
 vdso_test_gettimeofday
 vdso_test_getcpu
 vdso_standalone_test_x86
diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c
index 5029ef9b228c..c4aea794725a 100644
--- a/tools/testing/selftests/vDSO/vdso_test_correctness.c
+++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c
@@ -349,7 +349,7 @@ static void test_one_clock_gettime64(int clock, const char *name)
 		return;
 	}
 
-	printf("\t%llu.%09ld %llu.%09ld %llu.%09ld\n",
+	printf("\t%llu.%09lld %llu.%09lld %llu.%09lld\n",
 	       (unsigned long long)start.tv_sec, start.tv_nsec,
 	       (unsigned long long)vdso.tv_sec, vdso.tv_nsec,
 	       (unsigned long long)end.tv_sec, end.tv_nsec);
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 9a25307f6115..d42115e4284d 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -4,7 +4,7 @@
 include local_config.mk
 
 uname_M := $(shell uname -m 2>/dev/null || echo not)
-MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
+MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/')
 
 # Without this, failed build products remain, with up-to-date timestamps,
 # thus tricking Make (and you!) into believing that All Is Well, in subsequent
@@ -43,7 +43,7 @@ TEST_GEN_FILES += thuge-gen
 TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += userfaultfd
 
-ifeq ($(ARCH),x86_64)
+ifeq ($(MACHINE),x86_64)
 CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32)
 CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_64bit_program.c)
 CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_program.c -no-pie)
@@ -65,13 +65,13 @@ TEST_GEN_FILES += $(BINARIES_64)
 endif
 else
 
-ifneq (,$(findstring $(ARCH),powerpc))
+ifneq (,$(findstring $(MACHINE),ppc64))
 TEST_GEN_FILES += protection_keys
 endif
 
 endif
 
-ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64))
+ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64))
 TEST_GEN_FILES += va_128TBswitch
 TEST_GEN_FILES += virtual_address_range
 TEST_GEN_FILES += write_to_hugetlbfs
@@ -84,7 +84,7 @@ TEST_FILES := test_vmalloc.sh
 KSFT_KHDR_INSTALL := 1
 include ../lib.mk
 
-ifeq ($(ARCH),x86_64)
+ifeq ($(MACHINE),x86_64)
 BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
 BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
 
diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config
index b50c2085c1ac..fe07d97df9fa 100644
--- a/tools/testing/selftests/wireguard/qemu/debug.config
+++ b/tools/testing/selftests/wireguard/qemu/debug.config
@@ -1,5 +1,4 @@
 CONFIG_LOCALVERSION="-debug"
-CONFIG_ENABLE_MUST_CHECK=y
 CONFIG_FRAME_POINTER=y
 CONFIG_STACK_VALIDATION=y
 CONFIG_DEBUG_KERNEL=y
diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h
index 04d563fc9b95..468435ed64e6 100644
--- a/tools/virtio/asm/barrier.h
+++ b/tools/virtio/asm/barrier.h
@@ -16,6 +16,16 @@
 # define mb() abort()
 # define dma_rmb() abort()
 # define dma_wmb() abort()
+#elif defined(__aarch64__)
+#define dmb(opt) asm volatile("dmb " #opt : : : "memory")
+#define virt_mb() __sync_synchronize()
+#define virt_rmb() dmb(ishld)
+#define virt_wmb() dmb(ishst)
+#define virt_store_mb(var, value)  do { WRITE_ONCE(var, value); dmb(ish); } while (0)
+/* Weak barriers should be used. If not - it's a bug */
+# define mb() abort()
+# define dma_rmb() abort()
+# define dma_wmb() abort()
 #else
 #error Please fill in barrier macros
 #endif
diff --git a/tools/virtio/linux/bug.h b/tools/virtio/linux/bug.h
index b14c2c3b6b85..813baf13f62a 100644
--- a/tools/virtio/linux/bug.h
+++ b/tools/virtio/linux/bug.h
@@ -2,6 +2,8 @@
 #ifndef BUG_H
 #define BUG_H
 
+#include <asm/bug.h>
+
 #define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond))
 
 #define BUILD_BUG_ON(x)
diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h
index 315e85cabeda..0b493542e61a 100644
--- a/tools/virtio/linux/kernel.h
+++ b/tools/virtio/linux/kernel.h
@@ -11,6 +11,7 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include <linux/overflow.h>
 #include <linux/list.h>
 #include <linux/printk.h>
 #include <linux/bug.h>
@@ -117,6 +118,16 @@ static inline void free_page(unsigned long addr)
 #  define unlikely(x)	(__builtin_expect(!!(x), 0))
 # endif
 
+static inline void *krealloc_array(void *p, size_t new_n, size_t new_size, gfp_t gfp)
+{
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(new_n, new_size, &bytes)))
+		return NULL;
+
+	return krealloc(p, bytes, gfp);
+}
+
 #define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
 #ifdef DEBUG
 #define pr_debug(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
@@ -126,8 +137,6 @@ static inline void free_page(unsigned long addr)
 #define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
 #define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
 
-#define WARN_ON_ONCE(cond) (unlikely(cond) ? fprintf (stderr, "WARNING\n") : 0)
-
 #define min(x, y) ({				\
 	typeof(x) _min1 = (x);			\
 	typeof(y) _min2 = (y);			\
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
new file mode 100644
index 000000000000..9d01299563ee
--- /dev/null
+++ b/virt/kvm/dirty_ring.c
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * KVM dirty ring implementation
+ *
+ * Copyright 2019 Red Hat, Inc.
+ */
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/vmalloc.h>
+#include <linux/kvm_dirty_ring.h>
+#include <trace/events/kvm.h>
+
+int __weak kvm_cpu_dirty_log_size(void)
+{
+	return 0;
+}
+
+u32 kvm_dirty_ring_get_rsvd_entries(void)
+{
+	return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size();
+}
+
+static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring)
+{
+	return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index);
+}
+
+bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
+{
+	return kvm_dirty_ring_used(ring) >= ring->soft_limit;
+}
+
+static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring)
+{
+	return kvm_dirty_ring_used(ring) >= ring->size;
+}
+
+struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+
+	WARN_ON_ONCE(vcpu->kvm != kvm);
+
+	return &vcpu->dirty_ring;
+}
+
+static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
+{
+	struct kvm_memory_slot *memslot;
+	int as_id, id;
+
+	as_id = slot >> 16;
+	id = (u16)slot;
+
+	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
+		return;
+
+	memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id);
+
+	if (!memslot || (offset + __fls(mask)) >= memslot->npages)
+		return;
+
+	spin_lock(&kvm->mmu_lock);
+	kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask);
+	spin_unlock(&kvm->mmu_lock);
+}
+
+int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size)
+{
+	ring->dirty_gfns = vmalloc(size);
+	if (!ring->dirty_gfns)
+		return -ENOMEM;
+	memset(ring->dirty_gfns, 0, size);
+
+	ring->size = size / sizeof(struct kvm_dirty_gfn);
+	ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries();
+	ring->dirty_index = 0;
+	ring->reset_index = 0;
+	ring->index = index;
+
+	return 0;
+}
+
+static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn)
+{
+	gfn->flags = 0;
+}
+
+static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn)
+{
+	gfn->flags = KVM_DIRTY_GFN_F_DIRTY;
+}
+
+static inline bool kvm_dirty_gfn_invalid(struct kvm_dirty_gfn *gfn)
+{
+	return gfn->flags == 0;
+}
+
+static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn)
+{
+	return gfn->flags & KVM_DIRTY_GFN_F_RESET;
+}
+
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
+{
+	u32 cur_slot, next_slot;
+	u64 cur_offset, next_offset;
+	unsigned long mask;
+	int count = 0;
+	struct kvm_dirty_gfn *entry;
+	bool first_round = true;
+
+	/* This is only needed to make compilers happy */
+	cur_slot = cur_offset = mask = 0;
+
+	while (true) {
+		entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)];
+
+		if (!kvm_dirty_gfn_harvested(entry))
+			break;
+
+		next_slot = READ_ONCE(entry->slot);
+		next_offset = READ_ONCE(entry->offset);
+
+		/* Update the flags to reflect that this GFN is reset */
+		kvm_dirty_gfn_set_invalid(entry);
+
+		ring->reset_index++;
+		count++;
+		/*
+		 * Try to coalesce the reset operations when the guest is
+		 * scanning pages in the same slot.
+		 */
+		if (!first_round && next_slot == cur_slot) {
+			s64 delta = next_offset - cur_offset;
+
+			if (delta >= 0 && delta < BITS_PER_LONG) {
+				mask |= 1ull << delta;
+				continue;
+			}
+
+			/* Backwards visit, careful about overflows!  */
+			if (delta > -BITS_PER_LONG && delta < 0 &&
+			    (mask << -delta >> -delta) == mask) {
+				cur_offset = next_offset;
+				mask = (mask << -delta) | 1;
+				continue;
+			}
+		}
+		kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
+		cur_slot = next_slot;
+		cur_offset = next_offset;
+		mask = 1;
+		first_round = false;
+	}
+
+	kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
+
+	trace_kvm_dirty_ring_reset(ring);
+
+	return count;
+}
+
+void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset)
+{
+	struct kvm_dirty_gfn *entry;
+
+	/* It should never get full */
+	WARN_ON_ONCE(kvm_dirty_ring_full(ring));
+
+	entry = &ring->dirty_gfns[ring->dirty_index & (ring->size - 1)];
+
+	entry->slot = slot;
+	entry->offset = offset;
+	/*
+	 * Make sure the data is filled in before we publish this to
+	 * the userspace program.  There's no paired kernel-side reader.
+	 */
+	smp_wmb();
+	kvm_dirty_gfn_set_dirtied(entry);
+	ring->dirty_index++;
+	trace_kvm_dirty_ring_push(ring, slot, offset);
+}
+
+struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset)
+{
+	return vmalloc_to_page((void *)ring->dirty_gfns + offset * PAGE_SIZE);
+}
+
+void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
+{
+	vfree(ring->dirty_gfns);
+	ring->dirty_gfns = NULL;
+}
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index c2323c27a28b..e996989cd580 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -191,8 +191,12 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 	struct kvm *kvm = irqfd->kvm;
 	unsigned seq;
 	int idx;
+	int ret = 0;
 
 	if (flags & EPOLLIN) {
+		u64 cnt;
+		eventfd_ctx_do_read(irqfd->eventfd, &cnt);
+
 		idx = srcu_read_lock(&kvm->irq_srcu);
 		do {
 			seq = read_seqcount_begin(&irqfd->irq_entry_sc);
@@ -204,6 +208,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 					      false) == -EWOULDBLOCK)
 			schedule_work(&irqfd->inject);
 		srcu_read_unlock(&kvm->irq_srcu, idx);
+		ret = 1;
 	}
 
 	if (flags & EPOLLHUP) {
@@ -227,7 +232,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 		spin_unlock_irqrestore(&kvm->irqfds.lock, iflags);
 	}
 
-	return 0;
+	return ret;
 }
 
 static void
@@ -236,7 +241,7 @@ irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(pt, struct kvm_kernel_irqfd, pt);
-	add_wait_queue(wqh, &irqfd->wait);
+	add_wait_queue_priority(wqh, &irqfd->wait);
 }
 
 /* Must be called under irqfds.lock */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f69357a29688..fa9e3614d30e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -63,6 +63,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/kvm.h>
 
+#include <linux/kvm_dirty_ring.h>
+
 /* Worst case buffer size needed for holding an integer. */
 #define ITOA_MAX_LEN 12
 
@@ -415,6 +417,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 
 void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
+	kvm_dirty_ring_free(&vcpu->dirty_ring);
 	kvm_arch_vcpu_destroy(vcpu);
 
 	/*
@@ -482,9 +485,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	kvm->mmu_notifier_count++;
 	need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end,
 					     range->flags);
-	need_tlb_flush |= kvm->tlbs_dirty;
 	/* we've to flush the tlb before the pages can be freed */
-	if (need_tlb_flush)
+	if (need_tlb_flush || kvm->tlbs_dirty)
 		kvm_flush_remote_tlbs(kvm);
 
 	spin_unlock(&kvm->mmu_lock);
@@ -1362,7 +1364,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	/* Allocate/free page dirty bitmap as needed */
 	if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES))
 		new.dirty_bitmap = NULL;
-	else if (!new.dirty_bitmap) {
+	else if (!new.dirty_bitmap && !kvm->dirty_ring_size) {
 		r = kvm_alloc_dirty_bitmap(&new);
 		if (r)
 			return r;
@@ -1423,6 +1425,10 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 	unsigned long n;
 	unsigned long any = 0;
 
+	/* Dirty ring tracking is exclusive to dirty log tracking */
+	if (kvm->dirty_ring_size)
+		return -ENXIO;
+
 	*memslot = NULL;
 	*is_dirty = 0;
 
@@ -1484,6 +1490,10 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
+	/* Dirty ring tracking is exclusive to dirty log tracking */
+	if (kvm->dirty_ring_size)
+		return -ENXIO;
+
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
@@ -1592,6 +1602,10 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
+	/* Dirty ring tracking is exclusive to dirty log tracking */
+	if (kvm->dirty_ring_size)
+		return -ENXIO;
+
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
@@ -2196,7 +2210,8 @@ int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_map);
 
-static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
+static void __kvm_unmap_gfn(struct kvm *kvm,
+			struct kvm_memory_slot *memslot,
 			struct kvm_host_map *map,
 			struct gfn_to_pfn_cache *cache,
 			bool dirty, bool atomic)
@@ -2221,7 +2236,7 @@ static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
 #endif
 
 	if (dirty)
-		mark_page_dirty_in_slot(memslot, map->gfn);
+		mark_page_dirty_in_slot(kvm, memslot, map->gfn);
 
 	if (cache)
 		cache->dirty |= dirty;
@@ -2235,7 +2250,7 @@ static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
 int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, 
 		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
 {
-	__kvm_unmap_gfn(gfn_to_memslot(vcpu->kvm, map->gfn), map,
+	__kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map,
 			cache, dirty, atomic);
 	return 0;
 }
@@ -2243,8 +2258,8 @@ EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
 
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
 {
-	__kvm_unmap_gfn(kvm_vcpu_gfn_to_memslot(vcpu, map->gfn), map, NULL,
-			dirty, false);
+	__kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn),
+			map, NULL, dirty, false);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
 
@@ -2418,7 +2433,8 @@ int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa,
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic);
 
-static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn,
+static int __kvm_write_guest_page(struct kvm *kvm,
+				  struct kvm_memory_slot *memslot, gfn_t gfn,
 			          const void *data, int offset, int len)
 {
 	int r;
@@ -2430,7 +2446,7 @@ static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn,
 	r = __copy_to_user((void __user *)addr + offset, data, len);
 	if (r)
 		return -EFAULT;
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(kvm, memslot, gfn);
 	return 0;
 }
 
@@ -2439,7 +2455,7 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn,
 {
 	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
 
-	return __kvm_write_guest_page(slot, gfn, data, offset, len);
+	return __kvm_write_guest_page(kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_write_guest_page);
 
@@ -2448,7 +2464,7 @@ int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn,
 {
 	struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 
-	return __kvm_write_guest_page(slot, gfn, data, offset, len);
+	return __kvm_write_guest_page(vcpu->kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page);
 
@@ -2567,7 +2583,7 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	r = __copy_to_user((void __user *)ghc->hva + offset, data, len);
 	if (r)
 		return -EFAULT;
-	mark_page_dirty_in_slot(ghc->memslot, gpa >> PAGE_SHIFT);
+	mark_page_dirty_in_slot(kvm, ghc->memslot, gpa >> PAGE_SHIFT);
 
 	return 0;
 }
@@ -2616,23 +2632,16 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 }
 EXPORT_SYMBOL_GPL(kvm_read_guest_cached);
 
-int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
-{
-	const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
-
-	return kvm_write_guest_page(kvm, gfn, zero_page, offset, len);
-}
-EXPORT_SYMBOL_GPL(kvm_clear_guest_page);
-
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 {
+	const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	int seg;
 	int offset = offset_in_page(gpa);
 	int ret;
 
 	while ((seg = next_segment(len, offset)) != 0) {
-		ret = kvm_clear_guest_page(kvm, gfn, offset, seg);
+		ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, len);
 		if (ret < 0)
 			return ret;
 		offset = 0;
@@ -2643,12 +2652,19 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest);
 
-void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn)
+void mark_page_dirty_in_slot(struct kvm *kvm,
+			     struct kvm_memory_slot *memslot,
+		 	     gfn_t gfn)
 {
-	if (memslot && memslot->dirty_bitmap) {
+	if (memslot && kvm_slot_dirty_track_enabled(memslot)) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
+		u32 slot = (memslot->as_id << 16) | memslot->id;
 
-		set_bit_le(rel_gfn, memslot->dirty_bitmap);
+		if (kvm->dirty_ring_size)
+			kvm_dirty_ring_push(kvm_dirty_ring_get(kvm),
+					    slot, rel_gfn);
+		else
+			set_bit_le(rel_gfn, memslot->dirty_bitmap);
 	}
 }
 EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot);
@@ -2658,7 +2674,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 	struct kvm_memory_slot *memslot;
 
 	memslot = gfn_to_memslot(kvm, gfn);
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(kvm, memslot, gfn);
 }
 EXPORT_SYMBOL_GPL(mark_page_dirty);
 
@@ -2667,7 +2683,7 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn)
 	struct kvm_memory_slot *memslot;
 
 	memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(vcpu->kvm, memslot, gfn);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty);
 
@@ -3008,6 +3024,17 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
 
+static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff)
+{
+#if KVM_DIRTY_LOG_PAGE_OFFSET > 0
+	return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) &&
+	    (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET +
+	     kvm->dirty_ring_size / PAGE_SIZE);
+#else
+	return false;
+#endif
+}
+
 static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
 {
 	struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data;
@@ -3023,6 +3050,10 @@ static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
 	else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
 		page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
 #endif
+	else if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff))
+		page = kvm_dirty_ring_get_page(
+		    &vcpu->dirty_ring,
+		    vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET);
 	else
 		return kvm_arch_vcpu_fault(vcpu, vmf);
 	get_page(page);
@@ -3036,6 +3067,14 @@ static const struct vm_operations_struct kvm_vcpu_vm_ops = {
 
 static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	struct kvm_vcpu *vcpu = file->private_data;
+	unsigned long pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+
+	if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) ||
+	     kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) &&
+	    ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED)))
+		return -EINVAL;
+
 	vma->vm_ops = &kvm_vcpu_vm_ops;
 	return 0;
 }
@@ -3129,6 +3168,13 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	if (r)
 		goto vcpu_free_run_page;
 
+	if (kvm->dirty_ring_size) {
+		r = kvm_dirty_ring_alloc(&vcpu->dirty_ring,
+					 id, kvm->dirty_ring_size);
+		if (r)
+			goto arch_vcpu_destroy;
+	}
+
 	mutex_lock(&kvm->lock);
 	if (kvm_get_vcpu_by_id(kvm, id)) {
 		r = -EEXIST;
@@ -3162,6 +3208,8 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 
 unlock_vcpu_destroy:
 	mutex_unlock(&kvm->lock);
+	kvm_dirty_ring_free(&vcpu->dirty_ring);
+arch_vcpu_destroy:
 	kvm_arch_vcpu_destroy(vcpu);
 vcpu_free_run_page:
 	free_page((unsigned long)vcpu->run);
@@ -3634,12 +3682,78 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #endif
 	case KVM_CAP_NR_MEMSLOTS:
 		return KVM_USER_MEM_SLOTS;
+	case KVM_CAP_DIRTY_LOG_RING:
+#if KVM_DIRTY_LOG_PAGE_OFFSET > 0
+		return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
+#else
+		return 0;
+#endif
 	default:
 		break;
 	}
 	return kvm_vm_ioctl_check_extension(kvm, arg);
 }
 
+static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size)
+{
+	int r;
+
+	if (!KVM_DIRTY_LOG_PAGE_OFFSET)
+		return -EINVAL;
+
+	/* the size should be power of 2 */
+	if (!size || (size & (size - 1)))
+		return -EINVAL;
+
+	/* Should be bigger to keep the reserved entries, or a page */
+	if (size < kvm_dirty_ring_get_rsvd_entries() *
+	    sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE)
+		return -EINVAL;
+
+	if (size > KVM_DIRTY_RING_MAX_ENTRIES *
+	    sizeof(struct kvm_dirty_gfn))
+		return -E2BIG;
+
+	/* We only allow it to set once */
+	if (kvm->dirty_ring_size)
+		return -EINVAL;
+
+	mutex_lock(&kvm->lock);
+
+	if (kvm->created_vcpus) {
+		/* We don't allow to change this value after vcpu created */
+		r = -EINVAL;
+	} else {
+		kvm->dirty_ring_size = size;
+		r = 0;
+	}
+
+	mutex_unlock(&kvm->lock);
+	return r;
+}
+
+static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+	int cleared = 0;
+
+	if (!kvm->dirty_ring_size)
+		return -EINVAL;
+
+	mutex_lock(&kvm->slots_lock);
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring);
+
+	mutex_unlock(&kvm->slots_lock);
+
+	if (cleared)
+		kvm_flush_remote_tlbs(kvm);
+
+	return cleared;
+}
+
 int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 						  struct kvm_enable_cap *cap)
 {
@@ -3670,6 +3784,8 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 		kvm->max_halt_poll_ns = cap->args[0];
 		return 0;
 	}
+	case KVM_CAP_DIRTY_LOG_RING:
+		return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);
 	}
@@ -3854,6 +3970,9 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_CHECK_EXTENSION:
 		r = kvm_vm_ioctl_check_extension_generic(kvm, arg);
 		break;
+	case KVM_RESET_DIRTY_RINGS:
+		r = kvm_vm_ioctl_reset_dirty_pages(kvm);
+		break;
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}