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 83ae3b7..a648b42 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 @@
 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 @@
 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 @@
 | 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 @@
 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 e8c84fc..d4c9a01 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.rst
+++ b/Documentation/RCU/Design/Requirements/Requirements.rst
@@ -45,7 +45,7 @@
 #. `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 @@
 | 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 @@
 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 @@
 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 @@
 
 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 @@
 
 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 @@
 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 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 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 7a86413..59cd902 100644
--- a/Documentation/admin-guide/binfmt-misc.rst
+++ b/Documentation/admin-guide/binfmt-misc.rst
@@ -23,7 +23,7 @@
 
 - ``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 @@
       ``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 9b90efc..452b7dc 100644
--- a/Documentation/admin-guide/bootconfig.rst
+++ b/Documentation/admin-guide/bootconfig.rst
@@ -154,7 +154,7 @@
 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/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index 06fb1b4..682ab28 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 c722ec1..9e3cdb2 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.
 
@@ -2421,7 +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
@@ -5145,7 +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
@@ -5348,7 +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]
diff --git a/Documentation/admin-guide/mm/concepts.rst b/Documentation/admin-guide/mm/concepts.rst
index fa0974f..b966fcf 100644
--- a/Documentation/admin-guide/mm/concepts.rst
+++ b/Documentation/admin-guide/mm/concepts.rst
@@ -184,7 +184,7 @@
 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/core-api/index.rst b/Documentation/core-api/index.rst
index 69171b1..f1c9d20 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -53,7 +53,6 @@
 .. toctree::
    :maxdepth: 1
 
-   atomic_ops
    refcount-vs-atomic
    irq/index
    local_ops
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
index b15f68c..df29d59 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 @@
 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 b13ab60..ea19d12 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 @@
 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 9a87fd9..6a09bbf 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 @@
 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/sound/ti,j721e-cpb-audio.yaml b/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml
index 805da4d..ec06789 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 @@
 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 bb780f6..ee9f960 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 @@
 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/ti,j721e-usb.yaml b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml
index 388245b..148b3fb 100644
--- a/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml
+++ b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml
@@ -11,8 +11,12 @@
 
 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/doc-guide/sphinx.rst b/Documentation/doc-guide/sphinx.rst
index 2fb2ff2..36ac216 100644
--- a/Documentation/doc-guide/sphinx.rst
+++ b/Documentation/doc-guide/sphinx.rst
@@ -48,12 +48,12 @@
       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 @@
 ============
 
 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 @@
         - 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 @@
         - 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 @@
 
 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 @@
 
    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 @@
 
    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 @@
      }
 
 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 @@
 
 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/hwmon/sbtsi_temp.rst b/Documentation/hwmon/sbtsi_temp.rst
index 922b3c8..749f518 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/makefiles.rst b/Documentation/kbuild/makefiles.rst
index d36768c..9f6a118 100644
--- a/Documentation/kbuild/makefiles.rst
+++ b/Documentation/kbuild/makefiles.rst
@@ -598,7 +598,7 @@
 	explicitly added to $(targets).
 
 	Assignments to $(targets) are without $(obj)/ prefix. if_changed may be
-	used in conjunction with custom rules as defined in "3.9 Custom Rules".
+	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
diff --git a/Documentation/kernel-hacking/locking.rst b/Documentation/kernel-hacking/locking.rst
index 6ed806e..c344892 100644
--- a/Documentation/kernel-hacking/locking.rst
+++ b/Documentation/kernel-hacking/locking.rst
@@ -118,11 +118,11 @@
 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 @@
 
 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 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/process/4.Coding.rst b/Documentation/process/4.Coding.rst
index c27e59d..0825dc4 100644
--- a/Documentation/process/4.Coding.rst
+++ b/Documentation/process/4.Coding.rst
@@ -249,10 +249,8 @@
 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/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst
index fe52c31..b36af65 100644
--- a/Documentation/sound/alsa-configuration.rst
+++ b/Documentation/sound/alsa-configuration.rst
@@ -1501,7 +1501,7 @@
 
 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 73bbd59..e636583 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 @@
 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 @@
 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 @@
 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 @@
   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 @@
 
 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/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 70254ea..c136e25 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -392,9 +392,14 @@
 
 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
diff --git a/MAINTAINERS b/MAINTAINERS
index 2a6dc5b..462bfb7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3881,7 +3881,7 @@
 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
@@ -7360,7 +7360,6 @@
 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
@@ -9237,7 +9236,7 @@
 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/
@@ -9270,7 +9269,7 @@
 
 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
@@ -9772,7 +9771,7 @@
 
 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>
@@ -10256,7 +10255,6 @@
 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
@@ -12844,7 +12842,7 @@
 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
@@ -16704,6 +16702,8 @@
 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
@@ -17535,7 +17535,7 @@
 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/
@@ -17547,6 +17547,19 @@
 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>
@@ -17832,7 +17845,7 @@
 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*
@@ -19498,7 +19511,7 @@
 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 8b2c3f8..9e73f82 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 11
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
diff --git a/arch/Kconfig b/arch/Kconfig
index 78c6f05..24862d1 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1105,6 +1105,12 @@
 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/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index 23e41e8..ad9b7fe 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 1f5308a..1743506 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -307,7 +307,7 @@
 	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 6b5c545..a2d10c2 100644
--- a/arch/arc/plat-hsdk/Kconfig
+++ b/arch/arc/plat-hsdk/Kconfig
@@ -7,6 +7,7 @@
 	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/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi
index 11d41e8..7dde9fb 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 c4c6c7e..5898879 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 496f9d3..60fe618 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 1c11d15..b515c31 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -279,6 +279,7 @@
 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_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/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index f319170..56d6814 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -230,10 +230,12 @@
 		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 eab281a..09076ad 100644
--- a/arch/arm/mach-omap2/pmic-cpcap.c
+++ b/arch/arm/mach-omap2/pmic-cpcap.c
@@ -71,7 +71,7 @@
 	.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/arm64/Makefile b/arch/arm64/Makefile
index 6be9b37..9030920 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
@@ -115,16 +115,20 @@
 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)
diff --git a/arch/arm64/boot/dts/bitmain/bm1880.dtsi b/arch/arm64/boot/dts/bitmain/bm1880.dtsi
index fa6e690..53a9b76 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/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 11beda8..8fcfab0 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>
@@ -240,6 +241,28 @@
 	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;
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ca2cd75..69ad25f 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -94,7 +94,8 @@
 #endif /* CONFIG_ARM64_FORCE_52BIT */
 
 extern phys_addr_t arm64_dma_phys_limit;
-#define ARCH_LOW_ADDRESS_LIMIT	(arm64_dma_phys_limit - 1)
+extern phys_addr_t arm64_dma32_phys_limit;
+#define ARCH_LOW_ADDRESS_LIMIT	((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1)
 
 struct debug_info {
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 6f986e0..f0fe0cc 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -176,10 +176,21 @@
  * The Tag check override (TCO) bit disables temporarily the tag checking
  * preventing the issue.
  */
-static inline void uaccess_disable_privileged(void)
+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;
@@ -189,8 +200,7 @@
 
 static inline void uaccess_enable_privileged(void)
 {
-	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1),
-				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+	__uaccess_enable_tco();
 
 	if (uaccess_ttbr0_enable())
 		return;
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 7ffb5f1..e99edde 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -2568,7 +2568,7 @@
 	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);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 2a93fa5..a8c3e7a 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -182,7 +182,6 @@
 	mrs_s	\tmp2, SYS_GCR_EL1
 	bfi	\tmp2, \tmp, #0, #16
 	msr_s	SYS_GCR_EL1, \tmp2
-	isb
 #endif
 	.endm
 
@@ -194,6 +193,7 @@
 	ldr_l	\tmp, gcr_kernel_excl
 
 	mte_set_gcr \tmp, \tmp2
+	isb
 1:
 #endif
 	.endm
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 6bc3a36..ad00f99 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -434,7 +434,7 @@
 			   "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();
 }
 
@@ -807,7 +807,6 @@
 	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)
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 08156be..6895ce7 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 a8f8e40..cd9c3fa 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -24,8 +24,7 @@
 # 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 d808ad3..61dbb4c 100644
--- a/arch/arm64/kernel/vdso/vdso.lds.S
+++ b/arch/arm64/kernel/vdso/vdso.lds.S
@@ -40,9 +40,6 @@
 	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 @@
 		*(.note.GNU-stack)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
+		*(.eh_frame .eh_frame_hdr)
 	}
 }
 
@@ -66,7 +64,6 @@
 	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/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 043756d..3964acf 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -49,14 +49,6 @@
 
 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 60fd181..13b0172 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -24,4 +24,4 @@
 	 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/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 32ba6fb..74e06996 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -1129,9 +1129,10 @@
 	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 6e637d2..04c44853 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -65,10 +65,6 @@
 static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);
 DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
-extern u64 kvm_nvhe_sym(__cpu_logical_map)[NR_CPUS];
-extern u32 kvm_nvhe_sym(kvm_host_psci_version);
-extern struct psci_0_1_function_ids kvm_nvhe_sym(kvm_host_psci_0_1_function_ids);
-
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
@@ -584,11 +580,9 @@
 		 * 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
@@ -1574,12 +1568,12 @@
 	.notifier_call = hyp_init_cpu_pm_notifier,
 };
 
-static void __init hyp_cpu_pm_init(void)
+static void hyp_cpu_pm_init(void)
 {
 	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)
 {
 	if (!is_protected_kvm_enabled())
 		cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb);
@@ -1604,9 +1598,12 @@
 	 * allow any other CPUs from the `possible` set to boot.
 	 */
 	for_each_online_cpu(cpu)
-		kvm_nvhe_sym(__cpu_logical_map)[cpu] = cpu_logical_map(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)
 {
 	/*
@@ -1618,8 +1615,15 @@
 		return false;
 	}
 
-	kvm_nvhe_sym(kvm_host_psci_version) = psci_ops.get_version();
-	kvm_nvhe_sym(kvm_host_psci_0_1_function_ids) = get_psci_0_1_function_ids();
+	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;
 }
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
index b1f6092..6171635 100644
--- a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
+++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h
@@ -59,4 +59,13 @@
 	}
 }
 
+/*
+ * 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/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index bde658d..a906f9e 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -157,11 +157,6 @@
 	__kvm_hyp_host_forward_smc(host_ctxt);
 }
 
-static void skip_host_instruction(void)
-{
-	write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR);
-}
-
 static void handle_host_smc(struct kvm_cpu_context *host_ctxt)
 {
 	bool handled;
@@ -170,11 +165,8 @@
 	if (!handled)
 		default_host_smc_handler(host_ctxt);
 
-	/*
-	 * Unlike HVC, the return address of an SMC is the instruction's PC.
-	 * Move the return address past the instruction.
-	 */
-	skip_host_instruction();
+	/* SMC was trapped, move ELR past the current PC. */
+	kvm_skip_host_instr();
 }
 
 void handle_trap(struct kvm_cpu_context *host_ctxt)
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c
index cbab0c6..2997aa1 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c
@@ -14,14 +14,14 @@
  * Other CPUs should not be allowed to boot because their features were
  * not checked against the finalized system capabilities.
  */
-u64 __ro_after_init __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
+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(__cpu_logical_map))
+	if (cpu >= ARRAY_SIZE(hyp_cpu_logical_map))
 		hyp_panic();
 
-	return __cpu_logical_map[cpu];
+	return hyp_cpu_logical_map[cpu];
 }
 
 unsigned long __hyp_per_cpu_offset(unsigned int cpu)
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index 08dc9de..e394784 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -7,11 +7,8 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
-#include <kvm/arm_hypercalls.h>
 #include <linux/arm-smccc.h>
 #include <linux/kvm_host.h>
-#include <linux/psci.h>
-#include <kvm/arm_psci.h>
 #include <uapi/linux/psci.h>
 
 #include <nvhe/trap_handler.h>
@@ -22,9 +19,8 @@
 void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt);
 
 /* Config options set by the host. */
-__ro_after_init u32 kvm_host_psci_version;
-__ro_after_init struct psci_0_1_function_ids kvm_host_psci_0_1_function_ids;
-__ro_after_init s64 hyp_physvirt_offset;
+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)
 
@@ -47,19 +43,16 @@
 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;
 
-static u64 get_psci_func_id(struct kvm_cpu_context *host_ctxt)
-{
-	DECLARE_REG(u64, func_id, host_ctxt, 0);
-
-	return func_id;
-}
+#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 (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend) ||
-	       (func_id == kvm_host_psci_0_1_function_ids.cpu_on) ||
-	       (func_id == kvm_host_psci_0_1_function_ids.cpu_off) ||
-	       (func_id == kvm_host_psci_0_1_function_ids.migrate);
+	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)
@@ -69,16 +62,6 @@
 	       (PSCI_0_2_FN64(0) <= func_id && func_id <= PSCI_0_2_FN64(31));
 }
 
-static bool is_psci_call(u64 func_id)
-{
-	switch (kvm_host_psci_version) {
-	case PSCI_VERSION(0, 1):
-		return is_psci_0_1_call(func_id);
-	default:
-		return is_psci_0_2_call(func_id);
-	}
-}
-
 static unsigned long psci_call(unsigned long fn, unsigned long arg0,
 			       unsigned long arg1, unsigned long arg2)
 {
@@ -248,15 +231,14 @@
 
 static unsigned long psci_0_1_handler(u64 func_id, struct kvm_cpu_context *host_ctxt)
 {
-	if ((func_id == kvm_host_psci_0_1_function_ids.cpu_off) ||
-	    (func_id == kvm_host_psci_0_1_function_ids.migrate))
+	if (is_psci_0_1(cpu_off, func_id) || is_psci_0_1(migrate, func_id))
 		return psci_forward(host_ctxt);
-	else if (func_id == kvm_host_psci_0_1_function_ids.cpu_on)
+	if (is_psci_0_1(cpu_on, func_id))
 		return psci_cpu_on(func_id, host_ctxt);
-	else if (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend)
+	if (is_psci_0_1(cpu_suspend, func_id))
 		return psci_cpu_suspend(func_id, host_ctxt);
-	else
-		return PSCI_RET_NOT_SUPPORTED;
+
+	return PSCI_RET_NOT_SUPPORTED;
 }
 
 static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_ctxt)
@@ -298,20 +280,23 @@
 
 bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt)
 {
-	u64 func_id = get_psci_func_id(host_ctxt);
+	DECLARE_REG(u64, func_id, host_ctxt, 0);
 	unsigned long ret;
 
-	if (!is_psci_call(func_id))
-		return false;
-
-	switch (kvm_host_psci_version) {
+	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;
 	}
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 398f6df..4ad66a5 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -850,8 +850,6 @@
 		   return -EINVAL;
 	}
 
-	kvm_pmu_vcpu_reset(vcpu);
-
 	return 0;
 }
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 3313ded..42ccc27 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -594,6 +594,10 @@
 {
 	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
@@ -919,7 +923,7 @@
 
 #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)					\
diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index d8cc51b..70fcd6a 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -34,17 +34,16 @@
 }
 
 /*
- * Store a hyp VA <-> PA offset into a hyp-owned variable.
+ * Store a hyp VA <-> PA offset into a EL2-owned variable.
  */
 static void init_hyp_physvirt_offset(void)
 {
-	extern s64 kvm_nvhe_sym(hyp_physvirt_offset);
 	u64 kern_va, hyp_va;
 
 	/* Compute the offset from the hyp VA and PA of a random symbol. */
-	kern_va = (u64)kvm_ksym_ref(__hyp_text_start);
+	kern_va = (u64)lm_alias(__hyp_text_start);
 	hyp_va = __early_kern_hyp_va(kern_va);
-	CHOOSE_NVHE_SYM(hyp_physvirt_offset) = (s64)__pa(kern_va) - (s64)hyp_va;
+	hyp_physvirt_offset = (s64)__pa(kern_va) - (s64)hyp_va;
 }
 
 /*
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 32e32d6..052917d 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -419,7 +419,8 @@
  * 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 @@
 	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 @@
 
 	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 ebf53a4..11934c2 100644
--- a/arch/arm64/kvm/vgic/vgic-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-v2.c
@@ -306,20 +306,15 @@
 	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 @@
 	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 @@
 					    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 9cdf39a94..52915b3 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -500,29 +500,23 @@
 	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 @@
 	 * 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/mm/init.c b/arch/arm64/mm/init.c
index 75addb3..7deddf5 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -59,7 +59,7 @@
  * bit addressable memory area.
  */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
-static phys_addr_t arm64_dma32_phys_limit __ro_after_init;
+phys_addr_t arm64_dma32_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
 /*
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 37a54b5..1f7ee8c 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -46,7 +46,7 @@
 #endif
 
 #ifdef CONFIG_KASAN_HW_TAGS
-#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1
+#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1
 #else
 #define TCR_KASAN_HW_FLAGS 0
 #endif
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 349bf3f..858fbc8 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -260,10 +260,19 @@
 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/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 0318ba4..8e0b129 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -85,7 +85,7 @@
 		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
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7b6dd10..21f8511 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -19,6 +19,7 @@
 	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/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index e04d90a..4638a52 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 @@
 
 	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 5208ba4..2c87350 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -66,11 +66,17 @@
 	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/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3ab7b46..3d6616f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1010,9 +1010,21 @@
 	 */
 	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;
 };
 
@@ -1287,6 +1299,8 @@
 	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 {
@@ -1468,6 +1482,7 @@
 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);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index ffc2899..30f76b9 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -74,6 +74,8 @@
 
 
 #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/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index f628e3dc..43b54be 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -135,14 +135,32 @@
 {
 	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 23ad8e9..a29997e 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -167,9 +167,6 @@
 	*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 @@
 	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 29ffb95..460f3e0 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -525,89 +525,70 @@
 	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 (task == current)
+		resctrl_sched_in();
+}
 
-	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();
-
-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/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c
index 7d04b35..cdc04d0 100644
--- a/arch/x86/kernel/sev-es-shared.c
+++ b/arch/x86/kernel/sev-es-shared.c
@@ -305,14 +305,14 @@
 	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/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 3136e05..43ccead 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -674,7 +674,7 @@
 			   (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)
@@ -2898,7 +2898,7 @@
 			/* evaluate pending_events before reading the vector */
 			smp_rmb();
 			sipi_vector = apic->sipi_vector;
-			kvm_vcpu_deliver_sipi_vector(vcpu, 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 9c4a9c8e..581925e 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -49,7 +49,7 @@
 	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 c478904..6d16481 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3493,26 +3493,25 @@
  * 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);
@@ -3520,14 +3519,12 @@
 	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)) {
@@ -3536,35 +3533,45 @@
 	}
 
 	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/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 4bd2f1d..2ef8615 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -44,7 +44,48 @@
 	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)
@@ -447,18 +488,9 @@
 	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;
 }
 
@@ -619,13 +651,7 @@
 	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) {
@@ -647,8 +673,6 @@
 			ret |= handler(kvm, memslot, root, gfn_start,
 				       gfn_end, data);
 		}
-
-		kvm_mmu_put_root(kvm, root);
 	}
 
 	return ret;
@@ -838,21 +862,13 @@
 	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;
@@ -906,21 +922,13 @@
 	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;
@@ -1029,21 +1037,13 @@
 	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;
 }
@@ -1089,21 +1089,13 @@
 	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);
 	}
 }
 
@@ -1160,16 +1152,19 @@
  * 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 556e065..cbbdbad 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -44,5 +44,7 @@
 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/svm/nested.c b/arch/x86/kvm/svm/nested.c
index b0b6674..cb4c6ee 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -199,6 +199,7 @@
 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 =
@@ -595,6 +596,8 @@
 	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;
 
@@ -754,6 +757,7 @@
 		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);
@@ -1194,6 +1198,10 @@
 	 * 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 9858d5a..c8ffdbc 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1563,6 +1563,7 @@
 			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;
@@ -1888,6 +1889,9 @@
 	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;
 
@@ -2001,7 +2005,7 @@
 	 * 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") : : "a" (__sme_page_pa(sd->save_area)) : "memory");
+	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
@@ -2040,3 +2044,21 @@
 		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 cce0143..7ef1717 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3677,8 +3677,6 @@
 	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)
 {
@@ -4384,6 +4382,14 @@
 		   (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);
@@ -4526,6 +4532,8 @@
 
 	.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 5431e63..0fe874a 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -185,6 +185,7 @@
 	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;
@@ -591,6 +592,7 @@
 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 */
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index e2f2656..0fbb469 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4442,6 +4442,8 @@
 	/* 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);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 75c9c6a..2af05d3 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7707,6 +7707,8 @@
 	.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)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3f7c1fc..9a8969a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7976,17 +7976,22 @@
 	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)
@@ -8000,6 +8005,14 @@
 }
 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)
@@ -8789,7 +8802,9 @@
 
 	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;
 			}
@@ -9094,6 +9109,7 @@
 	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;
@@ -9520,8 +9536,9 @@
 		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;
@@ -10152,6 +10169,7 @@
 	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)
 {
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index dfd82f5..f6a9e2e 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -829,6 +829,8 @@
 	}
 
 	free_page((unsigned long)pmd_sv);
+
+	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	free_page((unsigned long)pmd);
 
 	return 1;
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 9e81d10..9e4eb0f 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -6332,13 +6332,13 @@
 	 * 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 @@
 	 * 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-iocost.c b/block/blk-iocost.c
index ac6078a..98d656b 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2551,8 +2551,8 @@
 	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 */
@@ -2679,14 +2679,14 @@
 			   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);
@@ -2863,6 +2863,12 @@
 	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 4d6e83e..4de03da 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -246,6 +246,7 @@
 	HCTX_FLAG_NAME(BLOCKING),
 	HCTX_FLAG_NAME(NO_SCHED),
 	HCTX_FLAG_NAME(STACKING),
+	HCTX_FLAG_NAME(TAG_HCTX_SHARED),
 };
 #undef HCTX_FLAG_NAME
 
diff --git a/block/genhd.c b/block/genhd.c
index 73faec43..419548e 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -246,15 +246,18 @@
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
-		if (!bdev_nr_sectors(part) &&
-		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
-		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
-		      piter->idx == 0))
-			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)) {
+			bdput(piter->part);
+			piter->part = NULL;
+			continue;
+		}
+
 		piter->idx += inc;
 		break;
 	}
diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c
index 511932a..0959613 100644
--- a/crypto/asymmetric_keys/asym_tpm.c
+++ b/crypto/asymmetric_keys/asym_tpm.c
@@ -354,7 +354,7 @@
 	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/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index edf1558..ebcf534 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -395,9 +395,6 @@
 
 	  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 @@
 	  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/x86/s2idle.c b/drivers/acpi/x86/s2idle.c
index 25fea34..2b69536 100644
--- a/drivers/acpi/x86/s2idle.c
+++ b/drivers/acpi/x86/s2idle.c
@@ -105,18 +105,8 @@
 
 	for (i = 0; i < out_obj->package.count; i++) {
 		union acpi_object *package = &out_obj->package.elements[i];
-		struct lpi_device_info_amd info = { };
 
-		if (package->type == ACPI_TYPE_INTEGER) {
-			switch (i) {
-			case 0:
-				info.revision = package->integer.value;
-				break;
-			case 1:
-				info.count = package->integer.value;
-				break;
-			}
-		} else if (package->type == ACPI_TYPE_PACKAGE) {
+		if (package->type == ACPI_TYPE_PACKAGE) {
 			lpi_constraints_table = kcalloc(package->package.count,
 							sizeof(*lpi_constraints_table),
 							GFP_KERNEL);
@@ -135,12 +125,10 @@
 
 				for (k = 0; k < info_obj->package.count; ++k) {
 					union acpi_object *obj = &info_obj->package.elements[k];
-					union acpi_object *obj_new;
 
 					list = &lpi_constraints_table[lpi_constraints_table_size];
 					list->min_dstate = -1;
 
-					obj_new = &obj[k];
 					switch (k) {
 					case 0:
 						dev_info.enabled = obj->integer.value;
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 25e08e5..14f1658 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -4414,6 +4414,12 @@
  *
  * 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 @@
 	} 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/block/Kconfig b/drivers/block/Kconfig
index 2623269..583b671 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -445,6 +445,7 @@
 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/rnbd/Kconfig b/drivers/block/rnbd/Kconfig
index 4b6d3d8..2ff05a0 100644
--- a/drivers/block/rnbd/Kconfig
+++ b/drivers/block/rnbd/Kconfig
@@ -7,6 +7,7 @@
 	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 1773c0a..080f58a 100644
--- a/drivers/block/rnbd/README
+++ b/drivers/block/rnbd/README
@@ -90,3 +90,4 @@
 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.c b/drivers/block/rnbd/rnbd-clt.c
index 96e3f9f..45a4700 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -375,12 +375,19 @@
 	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)) {
+		sg_free_table(&iu->sgt);
 		rnbd_put_permit(sess, iu->permit);
 		kfree(iu);
 	}
@@ -487,8 +494,6 @@
 	iu->buf = NULL;
 	iu->dev = dev;
 
-	sg_alloc_table(&iu->sgt, 1, GFP_KERNEL);
-
 	msg.hdr.type	= cpu_to_le16(RNBD_MSG_CLOSE);
 	msg.device_id	= cpu_to_le32(device_id);
 
@@ -502,7 +507,6 @@
 		err = errno;
 	}
 
-	sg_free_table(&iu->sgt);
 	rnbd_put_iu(sess, iu);
 	return err;
 }
@@ -575,7 +579,6 @@
 	iu->buf = rsp;
 	iu->dev = dev;
 
-	sg_alloc_table(&iu->sgt, 1, GFP_KERNEL);
 	sg_init_one(iu->sgt.sgl, rsp, sizeof(*rsp));
 
 	msg.hdr.type	= cpu_to_le16(RNBD_MSG_OPEN);
@@ -594,7 +597,6 @@
 		err = errno;
 	}
 
-	sg_free_table(&iu->sgt);
 	rnbd_put_iu(sess, iu);
 	return err;
 }
@@ -622,8 +624,6 @@
 
 	iu->buf = rsp;
 	iu->sess = sess;
-
-	sg_alloc_table(&iu->sgt, 1, GFP_KERNEL);
 	sg_init_one(iu->sgt.sgl, rsp, sizeof(*rsp));
 
 	msg.hdr.type = cpu_to_le16(RNBD_MSG_SESS_INFO);
@@ -650,7 +650,6 @@
 	} else {
 		err = errno;
 	}
-	sg_free_table(&iu->sgt);
 	rnbd_put_iu(sess, iu);
 	return err;
 }
@@ -1698,7 +1697,8 @@
 	 */
 
 	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-srv.c b/drivers/block/rnbd/rnbd-srv.c
index b8e4433..a6a68d4 100644
--- a/drivers/block/rnbd/rnbd-srv.c
+++ b/drivers/block/rnbd/rnbd-srv.c
@@ -338,10 +338,12 @@
 
 void rnbd_srv_sess_dev_force_close(struct rnbd_srv_sess_dev *sess_dev)
 {
-	mutex_lock(&sess_dev->sess->lock);
-	rnbd_srv_destroy_dev_session_sysfs(sess_dev);
-	mutex_unlock(&sess_dev->sess->lock);
+	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,
diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c
index 37244a7..9cf249c 100644
--- a/drivers/clk/tegra/clk-tegra30.c
+++ b/drivers/clk/tegra/clk-tegra30.c
@@ -1256,6 +1256,8 @@
 	{ 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/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 1a66046..be05e03 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -76,11 +76,6 @@
 	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 @@
 	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
@@ -2653,12 +2643,13 @@
 				      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 ? cpu->pstate.max_pstate :
-					     cpu->pstate.turbo_pstate;
+	cap_pstate = global.turbo_disabled ? HWP_GUARANTEED_PERF(hwp_cap) :
+					     HWP_HIGHEST_PERF(hwp_cap);
 
 	/* Optimization: Avoid unnecessary divisions. */
 
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index 0acc9e2..b9ccb6a 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -878,9 +878,9 @@
 
 /* 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 @@
 	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 @@
 
 	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/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index e63684d..9ad6397 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -76,10 +76,6 @@
 
 	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 @@
 	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 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/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index b971505..08d71da 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -86,12 +86,12 @@
 
 	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 266423a..4dbb03c 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -434,7 +434,7 @@
 	return 0;
 
 drv_fail:
-	for (; i > 0; i--)
+	while (--i >= 0)
 		driver_unregister(&idxd_drvs[i]->drv);
 	return rc;
 }
@@ -1840,7 +1840,7 @@
 	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 f133ae8..6ad8afbb95 100644
--- a/drivers/dma/mediatek/mtk-hsdma.c
+++ b/drivers/dma/mediatek/mtk-hsdma.c
@@ -1007,6 +1007,7 @@
 	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 584c931..d29d01e 100644
--- a/drivers/dma/milbeaut-xdmac.c
+++ b/drivers/dma/milbeaut-xdmac.c
@@ -350,7 +350,7 @@
 
 	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 @@
 
 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 d5773d4..8857985 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -630,7 +630,7 @@
 			     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 @@
 	}
 
 	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 d2334f5..1a0bf6b0 100644
--- a/drivers/dma/qcom/gpi.c
+++ b/drivers/dma/qcom/gpi.c
@@ -1416,7 +1416,7 @@
 	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 @@
 					       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 @@
 	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 @@
 	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 e4637ec..36ba8b4 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 87157cb..2984604 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -4698,9 +4698,9 @@
 		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 22faea6..7977755 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -2781,7 +2781,7 @@
 		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_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 @@
 	}
 
 	/* 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/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 1cb7d73..b69c340 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2548,11 +2548,11 @@
 	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)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 523d22d..347fec6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -563,7 +563,7 @@
 	 * 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 @@
 	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 @@
 
 	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 @@
 	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 @@
 
 	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 @@
 
 	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 c136bd4..82e9526 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1518,7 +1518,7 @@
 	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 @@
 			.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 1dd0401..19d9aa7 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 @@
 	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/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
index b72c8e4..07104a1 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 @@
 		/* 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/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 797b5d4..e509a17 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -6,7 +6,7 @@
 	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 519080e..1464860 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2386,8 +2386,7 @@
 
 			drm_connector_update_edid_property(connector,
 							   aconnector->edid);
-			aconnector->num_modes = drm_add_edid_modes(connector, aconnector->edid);
-			drm_connector_list_update(connector);
+			drm_add_edid_modes(connector, aconnector->edid);
 
 			if (aconnector->dc_link->aux_mode)
 				drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,
@@ -8379,8 +8378,7 @@
 			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 &&
+		if (IS_ENABLED(CONFIG_DEBUG_FS) && 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
@@ -8401,7 +8399,6 @@
 				amdgpu_dm_crtc_configure_crc_source(
 					crtc, dm_new_crtc_state, dm_new_crtc_state->crc_src);
 		}
-#endif
 	}
 
 	for_each_new_crtc_in_state(state, crtc, new_crtc_state, j)
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 0235bfb..eba2f1d 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
@@ -46,13 +46,13 @@
 }
 
 /* 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);
+#ifdef CONFIG_DEBUG_FS
 int amdgpu_dm_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name);
 int amdgpu_dm_crtc_verify_crc_source(struct drm_crtc *crtc,
 				     const char *src_name,
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 64f515d..f3c00f4 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -33,10 +33,6 @@
 calcs_ccflags := -mhard-float -maltivec
 endif
 
-ifdef CONFIG_ARM64
-calcs_rcflags := -mgeneral-regs-only
-endif
-
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
index d59b380..ff96bee 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
@@ -104,13 +104,6 @@
 CFLAGS_$(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 += $(AMD_DAL_CLK_MGR_DCN21)
@@ -125,13 +118,6 @@
 CFLAGS_$(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 += $(AMD_DAL_CLK_MGR_DCN30)
@@ -146,13 +132,6 @@
 CFLAGS_$(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/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 9e1071b..f4a2088 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 @@
 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/dcn10/Makefile b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
index 733e6e6..62ad1a1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
@@ -31,11 +31,4 @@
 
 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_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index bdc3783..3674519 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1534,15 +1534,8 @@
 	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 624cb13..5fcaf78 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
@@ -17,10 +17,6 @@
 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/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index 1ee5fc0..bb8c951 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -13,10 +13,6 @@
 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 248c271..c20331e 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_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 ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
index 2fd5d34..3ca7d91 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
@@ -21,10 +21,6 @@
 CFLAGS_$(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/dcn302/Makefile b/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
index 36e44e1..8d4924b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
@@ -20,10 +20,6 @@
 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 a02a33d..6bb7f29 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -33,10 +33,6 @@
 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/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
index f2624a1..8d31eb7 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -10,10 +10,6 @@
 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/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index 95cb569..126c2f3 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/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index e57e64b..8832278 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 @@
 		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 @@
 
 	/* 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 @@
 	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 @@
 	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 @@
 						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 @@
 						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 @@
 						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 @@
 						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 @@
 						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 @@
 						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 @@
 	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 @@
 		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 @@
 					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 6c9b5f0..808e0ec 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 @@
 	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 @@
 	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 9608745..12b36eb 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 @@
 {
 	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 8cb4fce..5c1482d 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 @@
 		*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 *
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 dc75db8..f743685 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 @@
 			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 522d550..06abf2a 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 @@
 	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/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index ce82d65..34d78c6 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 @@
 		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 2165398..37f1a10 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1489,7 +1489,7 @@
 	 * 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 @@
 
 	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 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 @@
 					       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/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index bcc80f4..bd3046e 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 @@
 	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 @@
 		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/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 180c23e..602f1a0 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 @@
 	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/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 9326595..b0899b6 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1166,7 +1166,7 @@
 		}
 	}
 	if (IS_ERR(src)) {
-		unsigned long x, n;
+		unsigned long x, n, remain;
 		void *ptr;
 
 		/*
@@ -1177,14 +1177,15 @@
 		 * 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 @@
 			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 @@
 
 #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 @@
 				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 320856b..88ad754 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -578,8 +578,6 @@
 
 	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 @@
 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 @@
 
 	if (pdev->msi_enabled)
 		pci_disable_msi(pdev);
-
-	cpu_latency_qos_remove_request(&dev_priv->pm_qos);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0a3ee4f..632c713 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -891,9 +891,6 @@
 
 	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/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
index 7e82c41..bdc9891 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
@@ -534,8 +534,10 @@
 
 	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 93da668..4534633 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -564,8 +564,10 @@
 		 * 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 c0be3a0..82bebb4 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -692,8 +692,10 @@
 		 * 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 87c8b03..12e75ba 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -18,6 +18,10 @@
 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 6cf9975..f091756 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -191,8 +191,6 @@
 		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 @@
 	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 c3775f7..b3d9a33 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 @@
 	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 6e971d5..3bc7ed2 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -693,6 +693,13 @@
 		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 97dca3e..d1780bc 100644
--- a/drivers/gpu/drm/msm/dp/dp_panel.c
+++ b/drivers/gpu/drm/msm/dp/dp_panel.c
@@ -167,14 +167,20 @@
 	panel = container_of(dp_panel, struct dp_panel_private, dp_panel);
 
 	rc = dp_panel_read_dpcd(dp_panel);
-	bw_code = drm_dp_link_rate_to_bw_code(dp_panel->link_info.rate);
-	if (rc || !is_link_rate_valid(bw_code) ||
-			!is_lane_count_valid(dp_panel->link_info.num_lanes) ||
-			(bw_code > dp_panel->max_bw_code)) {
+	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 (!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("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) {
 		rlen = drm_dp_dpcd_read(panel->aux, DP_SINK_COUNT,
 				&count, 1);
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 535a026..108c405 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -457,15 +457,15 @@
 
 	drm_mode_config_init(ddev);
 
+	ret = msm_init_vram(ddev);
+	if (ret)
+		goto err_destroy_mdss;
+
 	/* Bind all our sub-components: */
 	ret = component_bind_all(dev, ddev);
 	if (ret)
 		goto err_destroy_mdss;
 
-	ret = msm_init_vram(ddev);
-	if (ret)
-		goto err_msm_uninit;
-
 	dma_set_max_seg_size(dev, UINT_MAX);
 
 	msm_gem_shrinker_init(ddev);
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 9a7c49b..9d10739 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -96,6 +96,8 @@
 {
 	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 @@
 		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 @@
 	} 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 @@
 		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 @@
 
 		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/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index d59ef6e..23195d5 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -730,9 +730,6 @@
 	}
 	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 7b2f606..a00b7ab 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -507,7 +507,6 @@
 			ttm_pool_type_init(&pool->caching[i].orders[j],
 					   pool, i, j);
 }
-EXPORT_SYMBOL(ttm_pool_init);
 
 /**
  * ttm_pool_fini - Cleanup a pool
@@ -525,7 +524,6 @@
 		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 */
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 7bdda1b..09fa75a 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -899,6 +899,7 @@
 	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 3d1ccac..2ab38b7 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 @@
 
 	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 @@
 		}
 		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 @@
 		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 @@
 		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 6be0783..d7eac17 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 @@
 	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 a51c7b7..dbac166 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 @@
 	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 e8be94f..8f8d19b 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_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 4c5f236..5ba0aa1 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 dc7f6b4a..f23027d 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -322,6 +322,8 @@
 	{ 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 1ffcfc9..45e7e0b 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -1869,6 +1869,10 @@
 	  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 f857814..7eb9a6d 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -4053,6 +4053,8 @@
 	{ /* 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 d670bcd..0743ef5 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -2054,6 +2054,10 @@
 		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 d26d8cd..56406ce 100644
--- a/drivers/hid/hid-uclogic-params.c
+++ b/drivers/hid/hid-uclogic-params.c
@@ -90,7 +90,7 @@
 		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 4101268..4399d6c 100644
--- a/drivers/hid/hid-wiimote-core.c
+++ b/drivers/hid/hid-wiimote-core.c
@@ -1482,7 +1482,7 @@
 		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 045c464..e8acd23 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -1270,6 +1270,37 @@
 					       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 @@
 	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 @@
 
 	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 502f8cd..d491fdce 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2550,7 +2550,6 @@
 	/* 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 @@
 	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 9b30644..822c2e7 100644
--- a/drivers/hwmon/amd_energy.c
+++ b/drivers/hwmon/amd_energy.c
@@ -222,7 +222,7 @@
 	 */
 	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 @@
 			scnprintf(label_l[i], 10, "Esocket%u", (i - cpus));
 	}
 
+	s_config[i] = 0;
 	return 0;
 }
 
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index 777439f..111a91d 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -334,8 +334,18 @@
 
 	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 ae90713..877fe37 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1449,7 +1449,7 @@
 
 	/* 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 33de99b..0818d3e 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 @@
 {
 	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 19cda67..2917fec 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 @@
 			       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 @@
 
 	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/interconnect/imx/imx.c b/drivers/interconnect/imx/imx.c
index 41dba70..c770951 100644
--- a/drivers/interconnect/imx/imx.c
+++ b/drivers/interconnect/imx/imx.c
@@ -96,9 +96,10 @@
 			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 ba43a15..d7768d3 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 @@
 	.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 a8f93ba..b3fb5b0 100644
--- a/drivers/interconnect/qcom/Kconfig
+++ b/drivers/interconnect/qcom/Kconfig
@@ -42,13 +42,23 @@
 	  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_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_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_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 f54cd79..6a1f704 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -1973,8 +1973,6 @@
 		return r;
 	}
 
-	iommu->int_enabled = true;
-
 	return 0;
 }
 
@@ -2169,6 +2167,7 @@
 	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 7e2c445..f0adbc4 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3854,6 +3854,9 @@
 	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 5dff7ff..1b83d14 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 @@
 
 		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);
 	}
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f0305e6..4078358 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -863,33 +863,6 @@
 	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 b46dbfa6..004feae 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1461,8 +1461,8 @@
 		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 788119c..65cf06d 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -719,6 +719,8 @@
 	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 +746,8 @@
 		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 +1468,22 @@
 
 	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 +1564,37 @@
 #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 +1898,7 @@
 		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 +2569,7 @@
 	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 +4497,61 @@
 			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 device_domain_info *info = get_domain_info(dev);
+	struct subdev_domain_info *sinfo;
 
-	assert_spin_locked(&device_domain_lock);
-	if (WARN_ON(!info))
-		return;
+	if (!list_empty(&domain->subdevices)) {
+		list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+			if (sinfo->pdev == dev)
+				return sinfo;
+		}
+	}
 
-	domain->auxd_refcnt++;
-	list_add(&domain->auxd, &info->auxiliary_domains);
+	return NULL;
 }
 
-static void auxiliary_unlink_device(struct dmar_domain *domain,
-				    struct device *dev)
+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;
 
-	list_del(&domain->auxd);
-	domain->auxd_refcnt--;
+	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);
+	}
 
-	if (!domain->auxd_refcnt && domain->default_pasid > 0)
-		ioasid_put(domain->default_pasid);
+	return ++sinfo->users;
+}
+
+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 || !sinfo || sinfo->users <= 0))
+		return -EINVAL;
+
+	ret = --sinfo->users;
+	if (!ret) {
+		list_del(&sinfo->link_phys);
+		list_del(&sinfo->link_domain);
+		kfree(sinfo);
+	}
+
+	return ret;
 }
 
 static int aux_domain_add_dev(struct dmar_domain *domain,
@@ -4530,6 +4580,19 @@
 	}
 
 	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 +4611,9 @@
 						     domain->default_pasid);
 	if (ret)
 		goto table_failed;
+
 	spin_unlock(&iommu->lock);
-
-	auxiliary_link_device(domain, dev);
-
+out:
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	return 0;
@@ -4560,8 +4622,10 @@
 	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 +4645,18 @@
 	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 aeffda9..685200a 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -1353,6 +1353,8 @@
 		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 4fa248b..790ef34 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -142,7 +142,7 @@
 	}
 	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 +166,7 @@
 		}
 		desc.qw2 = 0;
 		desc.qw3 = 0;
-		qi_submit_sync(svm->iommu, &desc, 1, 0);
+		qi_submit_sync(sdev->iommu, &desc, 1, 0);
 	}
 }
 
@@ -211,7 +211,7 @@
 	 */
 	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 +281,7 @@
 	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 +364,7 @@
 	}
 	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 +383,12 @@
 	 * 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 +488,7 @@
 	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 +549,7 @@
 		goto out;
 	}
 	sdev->dev = dev;
+	sdev->iommu = iommu;
 
 	ret = intel_iommu_enable_pasid(iommu, dev);
 	if (ret) {
@@ -575,7 +579,6 @@
 			kfree(sdev);
 			goto out;
 		}
-		svm->iommu = iommu;
 
 		if (pasid_max > intel_pasid_max_id)
 			pasid_max = intel_pasid_max_id;
@@ -605,14 +608,14 @@
 			}
 		}
 
-		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 +635,14 @@
 		 * 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 4bb3293..d20b8b3 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -358,7 +358,7 @@
  * @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 @@
 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 @@
 
 /**
  * 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/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index 8f39f9b..4c2ce21 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -19,6 +19,7 @@
 
 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/bcache/features.c b/drivers/md/bcache/features.c
index 6469223..d636b7b 100644
--- a/drivers/md/bcache/features.c
+++ b/drivers/md/bcache/features.c
@@ -17,7 +17,7 @@
 };
 
 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 a1653c4..84fc2c0 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 @@
 		~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 a4752ac..2047a9c 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -64,9 +64,25 @@
 {
 	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 @@
 		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 @@
 	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 @@
 
 	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 @@
 	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);
 
@@ -2644,8 +2689,8 @@
 	}
 
 	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/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index beb4823..b2b3d2b 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -472,8 +472,11 @@
 	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 @@
 
 	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 @@
 	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 @@
 	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_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 @@
 
 	*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 @@
 	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 @@
 	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 @@
 		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 @@
 			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 @@
 		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 @@
 
 		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 @@
 	}
 
 	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 @@
 }
 
 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 @@
 
 	/* 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 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 
 	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 @@
 	}
 
 	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 @@
 			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 @@
 	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 5871162..1456eab 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -17,12 +17,12 @@
 {
 	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 @@
 						GFP_KERNEL);
 		if (!hdev->kernel_ctx) {
 			rc = -ENOMEM;
+			hl_mmu_fini(hdev);
 			goto out_err;
 		}
 
@@ -1103,6 +1104,7 @@
 				"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 0e1c629..20f77f58 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -627,25 +627,38 @@
 	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 @@
 			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 @@
 	/* 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 @@
 		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 571eda6..e0d7f5f 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -944,7 +944,7 @@
 	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 @@
  * @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 @@
 	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 6bbb6bc..032d114 100644
--- a/drivers/misc/habanalabs/common/habanalabs_drv.c
+++ b/drivers/misc/habanalabs/common/habanalabs_drv.c
@@ -544,6 +544,7 @@
 	.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 32e6af1..12efbd9 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -335,6 +335,8 @@
 			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 @@
 		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 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 7caf868..76217258 100644
--- a/drivers/misc/habanalabs/common/hw_queue.c
+++ b/drivers/misc/habanalabs/common/hw_queue.c
@@ -418,8 +418,11 @@
 		"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 923b260..b4725e6 100644
--- a/drivers/misc/habanalabs/common/pci.c
+++ b/drivers/misc/habanalabs/common/pci.c
@@ -130,10 +130,8 @@
 	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 @@
 
 	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 @@
 
 	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 @@
 	/* 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 1f19266..8c09e44 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -151,19 +151,6 @@
 	[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 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 @@
 	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 @@
 		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:
@@ -703,73 +690,6 @@
 }
 
 /**
- * gaudi_fetch_pll_frequency - Fetch PLL 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)
-{
-	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);
-
-		if (rc)
-			return rc;
-	} else 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);
-
-			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;
-		}
-	} else {
-		dev_err(hdev->dev, "Failed to fetch PLL frequency values\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
-/**
  * gaudi_fetch_psoc_frequency - Fetch PSOC frequency values
  *
  * @hdev: pointer to hl_device structure
@@ -778,18 +698,52 @@
 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];
+	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;
 
-	rc = gaudi_fetch_pll_frequency(hdev, CPU_PLL, pll_freq);
-	if (rc)
-		return rc;
+	if (hdev->asic_prop.fw_security_disabled) {
+		/* Backward compatibility */
+		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);
 
-	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;
+		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 {
+		rc = hl_fw_cpucp_pll_info_get(hdev, CPU_PLL, pll_freq_arr);
+
+		if (rc)
+			return rc;
+
+		freq = pll_freq_arr[2];
+	}
+
+	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 @@
 	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 @@
 		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 @@
 	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 @@
 	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 @@
 	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 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 @@
 		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 @@
 	}
 
 	/* 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 @@
 	/* 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 @@
 
 		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_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 @@
 	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 f2d91f4f..a7ab2d7 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 2e3612e..88a09d4 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 @@
 	}
 
 	/* 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 3e5eb9e..b8b4aa6 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -613,12 +613,6 @@
 	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 @@
 		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_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);
+	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 (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);
+	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_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 e5801ec..b637dfd6 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 @@
 	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 951b37d..41cab29 100644
--- a/drivers/misc/pvpanic.c
+++ b/drivers/misc/pvpanic.c
@@ -55,12 +55,23 @@
 	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/nvme/host/core.c b/drivers/nvme/host/core.c
index ce1b615..f320273 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -179,7 +179,7 @@
 }
 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 @@
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync);
 
 static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
 {
@@ -331,7 +330,7 @@
 		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 @@
 }
 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 @@
 		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)
 {
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 38373a0..5f36cfa 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -166,6 +166,7 @@
 	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 @@
 }
 
 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 @@
 
 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 @@
 {
 	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 @@
 
 	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 @@
 
 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 7e49f61..88a6b97 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -610,8 +610,6 @@
 #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_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 @@
 		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_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 b4385cb..50d9a20 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -967,6 +967,7 @@
 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 @@
 	 * 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 @@
 	{ 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 1ba6599..979ee31 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -262,6 +262,16 @@
 	}
 }
 
+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)
 {
@@ -279,7 +289,7 @@
 	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 733d9363..68213f0 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -1501,7 +1501,8 @@
 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 @@
 
 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 5c1e7cb..bdfc22e 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1641,6 +1641,16 @@
 	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;
diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 2b28dd4..e821dd3 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 @@
 
 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 @@
 	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 b6d4419..cf0bfac 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2614,6 +2614,13 @@
 	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 @@
 		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 b57177b..9adfdef 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 @@
 	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 @@
 {
 	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 @@
 	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 @@
 	}
 
 	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 @@
 		}
 	}
 
-	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 @@
 	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 @@
 #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 6e4bf05..af19209 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 @@
 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 @@
 	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 @@
 	.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 @@
 	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 b0c01cf..fd60728 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -359,24 +359,29 @@
 {
 	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 @@
 	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 @@
 		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/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index d99231c..80d74cc 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -2987,7 +2987,9 @@
 	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 861aedd..0d42bc6 100644
--- a/drivers/staging/hikey9xx/hisi-spmi-controller.c
+++ b/drivers/staging/hikey9xx/hisi-spmi-controller.c
@@ -278,21 +278,24 @@
 	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 @@
 	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 @@
 	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 52b9fb1..b666cb2 100644
--- a/drivers/staging/media/atomisp/pci/atomisp_subdev.c
+++ b/drivers/staging/media/atomisp/pci/atomisp_subdev.c
@@ -1062,26 +1062,6 @@
 	.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 d241349..bc4bb43 100644
--- a/drivers/staging/mt7621-dma/mtk-hsdma.c
+++ b/drivers/staging/mt7621-dma/mtk-hsdma.c
@@ -712,7 +712,7 @@
 	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 @@
 
 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 44e15d7..66d6f1d 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -46,60 +46,83 @@
 	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)
+	rc = memcmp(&tmp_dev_wwn[0], dev_wwn, XCOPY_NAA_IEEE_REGEX_LEN);
+	if (rc != 0) {
+		pr_debug("XCOPY: skip non-matching: %*ph\n",
+			 XCOPY_NAA_IEEE_REGEX_LEN, tmp_dev_wwn);
 		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);
-	if (rc != 0) {
-		pr_err("configfs_depend_item attempt failed: %d for se_dev: %p\n",
-		       rc, se_dev);
-		return rc;
-	}
-
-	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;
+	struct se_dev_entry *deve;
+	struct se_node_acl *nacl;
+	struct se_lun *this_lun = NULL;
+	struct se_device *found_dev = NULL;
 
-	memset(&info, 0, sizeof(info));
-	info.dev_wwn = dev_wwn;
+	/* cmd with NULL sess indicates no associated $FABRIC_MOD */
+	if (!sess)
+		goto err_out;
 
-	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;
+	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 @@
 
 	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 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("putting src lun_ref for %p\n", 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);
-
-	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 c56a1bd..e5f2000 100644
--- a/drivers/target/target_core_xcopy.h
+++ b/drivers/target/target_core_xcopy.h
@@ -27,6 +27,7 @@
 	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/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 9e12152..8b7bc10b 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -139,9 +139,13 @@
 	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 f52f1bc..7819057 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1895,6 +1895,10 @@
 	{ 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 02d0cfd..508b1c3 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -465,13 +465,23 @@
 	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 @@
 	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 67cbd42..134dc20 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -274,8 +274,25 @@
 #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 60886a7..ad5a0f4 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1649,14 +1649,12 @@
 	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 2f95f08..1b241f9 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 417e053..bdf1f98 100644
--- a/drivers/usb/dwc3/dwc3-meson-g12a.c
+++ b/drivers/usb/dwc3/dwc3-meson-g12a.c
@@ -754,7 +754,7 @@
 
 	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 78cb4db..ee44321 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1763,6 +1763,8 @@
 			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 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 @@
 			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 @@
 	}
 
 	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 @@
 	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 aa213c9..f23f4c9 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 @@
 	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 @@
 	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 7e47e62..2d15257 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -265,6 +265,7 @@
 	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 @@
 	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 c6d455f..1a556a6 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -392,8 +392,11 @@
 
 	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 @@
 		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 56051bb..36ffb43 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -221,9 +221,16 @@
 
 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;
 
-	return sprintf(page, "%s\n", udc_name ?: "");
+	mutex_lock(&gi->lock);
+	udc_name = gi->composite.gadget_driver.udc_name;
+	ret = sprintf(page, "%s\n", udc_name ?: "");
+	mutex_unlock(&gi->lock);
+
+	return ret;
 }
 
 static int unregister_gadget(struct gadget_info *gi)
@@ -1248,9 +1255,9 @@
 
 		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 @@
 	.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 @@
 	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 64a4112..2f1eb2e 100644
--- a/drivers/usb/gadget/function/f_printer.c
+++ b/drivers/usb/gadget/function/f_printer.c
@@ -1162,6 +1162,7 @@
 		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 3633df6..5d960b6 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -271,7 +271,7 @@
 
 	.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 @@
 	.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 @@
 
 	.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 @@
 	.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 @@
 	__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 @@
 		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 @@
 	}
 
 	/* 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 31ea76a..c019f2b 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 @@
 
 	/* 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 @@
 
 	/* 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 59be2d8..e8033e5 100644
--- a/drivers/usb/gadget/legacy/acm_ms.c
+++ b/drivers/usb/gadget/legacy/acm_ms.c
@@ -200,8 +200,10 @@
 		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 1a12aab..8c614bb 100644
--- a/drivers/usb/gadget/udc/Kconfig
+++ b/drivers/usb/gadget/udc/Kconfig
@@ -90,7 +90,7 @@
 
 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 f5a7ce2..a21f222 100644
--- a/drivers/usb/gadget/udc/Makefile
+++ b/drivers/usb/gadget/udc/Makefile
@@ -23,7 +23,6 @@
 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 5b5cfeb..6a62bbd 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -659,8 +659,7 @@
  *
  * 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 ab5e978..1a953f4 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -2118,9 +2118,21 @@
 				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 @@
 			 */
 			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 5a32199..0000000
--- 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 91ab81c..e869405 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4770,19 +4770,19 @@
 {
 	unsigned long long timeout_ns;
 
-	/* 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) {
-			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;
 
+	/* 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) <= timeout_ns) {
+			dev_dbg(&udev->dev, "Disable U1, ESIT shorter than exit latency\n");
+			return USB3_LPM_DISABLED;
+		}
+	}
+
 	/* 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 @@
 {
 	unsigned long long timeout_ns;
 
-	/* 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) {
-			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;
 
+	/* 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) <= timeout_ns) {
+			dev_dbg(&udev->dev, "Disable U2, ESIT shorter than exit latency\n");
+			return USB3_LPM_DISABLED;
+		}
+	}
+
 	/* 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 73ebfa6..c640f98 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -496,6 +496,9 @@
 		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 f1201d4..e8f06b4 100644
--- a/drivers/usb/serial/iuu_phoenix.c
+++ b/drivers/usb/serial/iuu_phoenix.c
@@ -532,23 +532,29 @@
 	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 @@
 			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 2c21e34..3fe9591 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1117,6 +1117,8 @@
 	{ 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 @@
 	{ 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 870e9cf..f9677a5 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -91,6 +91,13 @@
 		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 187690f..60d375e 100644
--- a/drivers/usb/typec/altmodes/Kconfig
+++ b/drivers/usb/typec/altmodes/Kconfig
@@ -20,6 +20,6 @@
 	  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 ebfd311..8f77669 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -766,6 +766,7 @@
 		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 @@
 		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 cf37a59..46a25b8 100644
--- a/drivers/usb/typec/mux/intel_pmc_mux.c
+++ b/drivers/usb/typec/mux/intel_pmc_mux.c
@@ -207,10 +207,21 @@
 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 66cde5e..3209b5d 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -396,6 +396,8 @@
 		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/fs/block_dev.c b/fs/block_dev.c
index 3e5b02f..3b8963e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -605,6 +605,8 @@
 		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;
@@ -774,8 +776,11 @@
 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;
 }
 
@@ -869,14 +874,12 @@
 	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
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1dfd4b2..6b35b7e 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1457,7 +1457,7 @@
 		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);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6e3b72e..c9cee45 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -676,9 +676,7 @@
 
 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/inode.c b/fs/btrfs/inode.c
index 0707166..a8e0a6b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9390,7 +9390,8 @@
  * 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;
@@ -9399,6 +9400,7 @@
 	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);
@@ -9427,18 +9429,24 @@
 		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();
@@ -9464,18 +9472,29 @@
 
 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, false);
+	return start_delalloc_inodes(root, &wbc, true, false);
 }
 
 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;
@@ -9489,6 +9508,13 @@
 	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);
@@ -9497,9 +9523,9 @@
 			       &fs_info->delalloc_roots);
 		spin_unlock(&fs_info->delalloc_root_lock);
 
-		ret = start_delalloc_inodes(root, &nr, false, in_reclaim_context);
+		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/print-tree.c b/fs/btrfs/print-tree.c
index fe5e002..aae1027 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -26,22 +26,22 @@
 	{ 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 78b9938..8c3e931 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/relocation.c b/fs/btrfs/relocation.c
index 19b7db8..df63ef6 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2975,11 +2975,16 @@
 		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/space-info.c b/fs/btrfs/space-info.c
index 67e55c5..e834746 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -532,7 +532,9 @@
 
 	loops = 0;
 	while ((delalloc_bytes || dio_bytes) && loops < 3) {
-		btrfs_start_delalloc_roots(fs_info, items, true);
+		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/tree-checker.c b/fs/btrfs/tree-checker.c
index 028e733..582061c 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -760,6 +760,7 @@
 {
 	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 @@
 			  "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/io_uring.c b/fs/io_uring.c
index ca46f31..2f305c0 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -262,6 +262,7 @@
 		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
@@ -992,6 +993,9 @@
 	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);
@@ -1342,11 +1346,6 @@
 
 	/* 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)
@@ -1520,10 +1519,8 @@
 {
 	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;
@@ -1704,18 +1701,42 @@
 
 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_ev_posted_iopoll(struct io_ring_ctx *ctx)
+{
+	/* 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;
@@ -1768,6 +1789,20 @@
 	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)
 {
 	struct io_ring_ctx *ctx = req->ctx;
@@ -2127,14 +2162,14 @@
 {
 	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)
@@ -2313,20 +2348,8 @@
 		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)
 {
-	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 __io_cqring_events(ctx);
@@ -2424,8 +2447,7 @@
 	}
 
 	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))
@@ -2551,7 +2573,9 @@
 		 * 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;
 
 		/*
@@ -2668,6 +2692,8 @@
 	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)) {
@@ -6826,7 +6852,7 @@
 
 	/* if we have a backlog and couldn't flush it all, return BUSY */
 	if (test_bit(0, &ctx->sq_check_overflow)) {
-		if (!io_cqring_overflow_flush(ctx, false, NULL, NULL))
+		if (!__io_cqring_overflow_flush(ctx, false, NULL, NULL))
 			return -EBUSY;
 	}
 
@@ -6928,7 +6954,8 @@
 		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);
 	}
@@ -7089,7 +7116,7 @@
 	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;
 
@@ -7098,7 +7125,7 @@
 	 * 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;
 }
 
@@ -7108,11 +7135,13 @@
 	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)
@@ -7149,7 +7178,8 @@
 	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;
@@ -7177,6 +7207,7 @@
 	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 */
@@ -7185,8 +7216,10 @@
 			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) {
@@ -7684,12 +7717,12 @@
 
 	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);
@@ -7783,9 +7816,9 @@
 	}
 
 	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;
 	}
 
 	io_sqe_files_set_node(file_data, ref_node);
@@ -7885,8 +7918,8 @@
 		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);
@@ -8624,7 +8657,8 @@
 	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;
@@ -8663,7 +8697,7 @@
 	 * 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);
 }
@@ -8679,10 +8713,14 @@
 {
 	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);
@@ -8818,9 +8856,11 @@
 		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)) {
@@ -8839,6 +8879,18 @@
 	}
 }
 
+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 */
+	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
@@ -8850,15 +8902,15 @@
 	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);
@@ -8931,20 +8983,12 @@
 		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);
 }
 
@@ -8956,16 +9000,12 @@
 
 	/* 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)
@@ -9028,11 +9068,39 @@
 	} while (1);
 
 	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;
 }
 
@@ -9106,8 +9174,9 @@
 
 #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 {
@@ -9116,6 +9185,11 @@
 
 		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;
 
@@ -9123,6 +9197,8 @@
 	} 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,
@@ -9194,17 +9270,18 @@
 	 */
 	ret = 0;
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
-		if (!list_empty_careful(&ctx->cq_overflow_list)) {
-			bool needs_lock = ctx->flags & IORING_SETUP_IOPOLL;
+		io_cqring_overflow_flush(ctx, false, NULL, NULL);
 
-			io_ring_submit_lock(ctx, needs_lock);
-			io_cqring_overflow_flush(ctx, false, NULL, NULL);
-			io_ring_submit_unlock(ctx, needs_lock);
-		}
+		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);
@@ -9631,6 +9708,7 @@
 	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/nfs/delegation.c b/fs/nfs/delegation.c
index 816e142..04bf806 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -1011,22 +1011,24 @@
 				 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 b840d0a..62d3189 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -136,9 +136,29 @@
 	} 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 @@
 
 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 0ce04e0..2f4679a 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3536,10 +3536,8 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 					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 984cc42..d09bcfd 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -227,7 +227,7 @@
 			   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 @@
 			    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 07f59dc..4f274f21 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1152,7 +1152,7 @@
 	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 @@
 	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 @@
 		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 @@
 		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 @@
 		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 @@
 		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 @@
 					     &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 bbd3de1..d810ae67 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -297,10 +297,8 @@
 		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 @@
 }
 
 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 2efcfdd..49d3389 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -78,22 +78,18 @@
 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 @@
 			   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 @@
 	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 4727b7f..8d6d267 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 45ee6b1..eaaa160 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -147,6 +147,25 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 		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 @@
 			    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 @@
 	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 @@
 	if (nfserr && segments == 0)
 		xdr_truncate_encode(xdr, starting_len);
 	else {
+		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);
-		if (nfserr) {
-			xdr_truncate_encode(xdr, last_segment);
-			nfserr = nfs_ok;
-		}
 	}
 
 	return nfserr;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 00384c3..f9c9f4c 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 a60ff5c..c300885 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -568,7 +568,6 @@
 	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 3e01d8f..dcab112 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1285,26 +1285,23 @@
 	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/zonefs/Kconfig b/fs/zonefs/Kconfig
index ef2697b..827278f 100644
--- a/fs/zonefs/Kconfig
+++ b/fs/zonefs/Kconfig
@@ -3,6 +3,7 @@
 	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/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index fc85f50..8dcb3e1 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 */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 2630c2e..053bf05 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -885,6 +885,13 @@
 	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/intel-iommu.h b/include/linux/intel-iommu.h
index d956987..09c6a0b 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -533,11 +533,10 @@
 					/* 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 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 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 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/kcov.h b/include/linux/kcov.h
index a10e847..4e3037d 100644
--- a/include/linux/kcov.h
+++ b/include/linux/kcov.h
@@ -52,6 +52,25 @@
 	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 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/syscalls.h b/include/linux/syscalls.h
index f3929af..7688bc98 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -251,6 +251,30 @@
 	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/soc/nps/common.h b/include/soc/nps/common.h
deleted file mode 100644
index 8c18dc6..0000000
--- 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 d2f5e7e..0000000
--- 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/uapi/linux/bcache.h b/include/uapi/linux/bcache.h
index 52e8bcb3..cf7399f 100644
--- a/include/uapi/linux/bcache.h
+++ b/include/uapi/linux/bcache.h
@@ -213,7 +213,7 @@
 		__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/kvm.h b/include/uapi/linux/kvm.h
index 886802b..374c678 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -251,6 +251,7 @@
 #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. */
@@ -573,6 +574,7 @@
 #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;
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index 8c15a7d..dba3827 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -279,6 +279,7 @@
  * 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 @@
  * @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 @@
 	__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/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config
index 53d688b..eb0029c 100644
--- a/kernel/configs/android-recommended.config
+++ b/kernel/configs/android-recommended.config
@@ -81,7 +81,6 @@
 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/trace/Kconfig b/kernel/trace/Kconfig
index d5a1941..c1a62ae 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -538,7 +538,7 @@
 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 9c31f42..e6fba17 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -434,7 +434,7 @@
 	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/lib/fonts/font_ter16x32.c b/lib/fonts/font_ter16x32.c
index 1955d62..5baedc5 100644
--- a/lib/fonts/font_ter16x32.c
+++ b/lib/fonts/font_ter16x32.c
@@ -774,8 +774,8 @@
 	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 @@
 	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/raid6/Makefile b/lib/raid6/Makefile
index b4c0df6..c770570 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -48,7 +48,7 @@
 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/net/sunrpc/addr.c b/net/sunrpc/addr.c
index 010dcb8..6e4dbd5 100644
--- a/net/sunrpc/addr.c
+++ b/net/sunrpc/addr.c
@@ -185,7 +185,7 @@
 			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 b248f23..c9766d0 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1062,6 +1062,90 @@
 	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 @@
 	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/scripts/config b/scripts/config
index 8c8d7c3..ff88e2f 100755
--- a/scripts/config
+++ b/scripts/config
@@ -223,6 +223,7 @@
 		;;
 
 	*)
+		echo "bad command: $CMD" >&2
 		usage
 		;;
 	esac
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index e46df0a..2c40e68 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -94,16 +94,6 @@
 	$(Q)$(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/mconf-cfg.sh b/scripts/kconfig/mconf-cfg.sh
index aa68ec9..fcd4acd 100755
--- a/scripts/kconfig/mconf-cfg.sh
+++ b/scripts/kconfig/mconf-cfg.sh
@@ -33,7 +33,9 @@
 	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/sound/firewire/fireface/ff-transaction.c b/sound/firewire/fireface/ff-transaction.c
index 7f82762..ee7122c 100644
--- a/sound/firewire/fireface/ff-transaction.c
+++ b/sound/firewire/fireface/ff-transaction.c
@@ -88,7 +88,7 @@
 
 	/* 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 90288b4..a073cec 100644
--- a/sound/firewire/tascam/tascam-transaction.c
+++ b/sound/firewire/tascam/tascam-transaction.c
@@ -209,7 +209,7 @@
 
 	/* 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 770ad25..e4dd2ff 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2598,7 +2598,8 @@
 	  .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),
@@ -2660,9 +2661,11 @@
 	{ 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 70164d142..361cf20 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -388,7 +388,7 @@
 	 * 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_realtek.c b/sound/pci/hda/patch_realtek.c
index 3c1d2a3..dd82ff2b 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -7970,6 +7970,10 @@
 	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),
diff --git a/sound/soc/amd/raven/pci-acp3x.c b/sound/soc/amd/raven/pci-acp3x.c
index 8c138e4..d3536fd 100644
--- a/sound/soc/amd/raven/pci-acp3x.c
+++ b/sound/soc/amd/raven/pci-acp3x.c
@@ -140,21 +140,14 @@
 		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 @@
 	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 @@
 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 @@
 		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 fa169bf..deca8c7 100644
--- a/sound/soc/amd/renoir/rn-pci-acp3x.c
+++ b/sound/soc/amd/renoir/rn-pci-acp3x.c
@@ -171,6 +171,20 @@
 			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 142373e..9fe9471 100644
--- a/sound/soc/atmel/Kconfig
+++ b/sound/soc/atmel/Kconfig
@@ -143,7 +143,7 @@
 	  - 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 @@
 	  - 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 ba4eb54..9bf6bfd 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -457,7 +457,7 @@
 	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 92921e3..85f6865 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 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 @@
 {
 	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 @@
 		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 ec2e79c..b8d471d 100644
--- a/sound/soc/codecs/max98373-sdw.c
+++ b/sound/soc/codecs/max98373-sdw.c
@@ -23,6 +23,12 @@
 	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 __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 @@
 {
 	struct max98373_priv *max98373;
 	int ret;
+	int i;
 	struct device *dev = &slave->dev;
 
 	/*  Allocate and assign private driver data structure  */
@@ -768,6 +780,14 @@
 	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 929bb17..31d571d 100644
--- a/sound/soc/codecs/max98373.c
+++ b/sound/soc/codecs/max98373.c
@@ -168,6 +168,31 @@
 			    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 @@
 	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 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 4ab29b9..71f5a52 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 @@
 	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 5771c02..85f7441 100644
--- a/sound/soc/codecs/rt711.c
+++ b/sound/soc/codecs/rt711.c
@@ -462,6 +462,8 @@
 	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 @@
 	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 @@
 		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 2c2a76a..ede4a9a 100644
--- a/sound/soc/fsl/imx-hdmi.c
+++ b/sound/soc/fsl/imx-hdmi.c
@@ -164,6 +164,7 @@
 
 	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 c55d123..c763bfe 100644
--- a/sound/soc/intel/boards/haswell.c
+++ b/sound/soc/intel/boards/haswell.c
@@ -189,6 +189,7 @@
 	.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 fcd8dff..1275c14 100644
--- a/sound/soc/intel/skylake/cnl-sst.c
+++ b/sound/soc/intel/skylake/cnl-sst.c
@@ -224,6 +224,7 @@
 				"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 c8664ab..87cac44 100644
--- a/sound/soc/meson/axg-tdm-interface.c
+++ b/sound/soc/meson/axg-tdm-interface.c
@@ -467,8 +467,20 @@
 	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 88ed95a..b4faf9d 100644
--- a/sound/soc/meson/axg-tdmin.c
+++ b/sound/soc/meson/axg-tdmin.c
@@ -228,15 +228,6 @@
 	.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 @@
 		.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 af684fd..c5e99c2 100644
--- a/sound/soc/qcom/lpass-cpu.c
+++ b/sound/soc/qcom/lpass-cpu.c
@@ -270,18 +270,6 @@
 	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 @@
 	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 80b09de..d1c2485 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -452,7 +452,6 @@
 	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 @@
 		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 @@
 					"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 @@
 			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 @@
 					"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 @@
 			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 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 @@
 	.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 b9aacf3..abdfd9cf 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -366,25 +366,27 @@
 	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 9f0c86c..2b75d01 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -2486,6 +2486,7 @@
 	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 031dad5..3e8b6c0 100644
--- a/sound/soc/sof/Kconfig
+++ b/sound/soc/sof/Kconfig
@@ -122,7 +122,7 @@
 	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 d731ca6..e08fbf8 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -450,10 +450,8 @@
 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))
@@ -611,6 +609,7 @@
 	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 6a027c3..37091b1 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -18,6 +18,7 @@
 	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 snd_usb_substream;
+struct snd_usb_iface_ref;
 struct snd_usb_endpoint;
 struct snd_usb_power_domain;
 
@@ -58,6 +60,7 @@
 
 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/endpoint.c b/sound/usb/endpoint.c
index 162da7a..fe73fe3 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 @@
 }
 
 /*
+ * 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 @@
  *
  * 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 @@
 		} 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 @@
 			      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 @@
 			      ep_num, ep->opened);
 	}
 
+	if (!ep->iface_ref->opened++)
+		ep->iface_ref->need_setup = true;
+
 	ep->opened++;
 
  unlock:
@@ -760,12 +804,16 @@
 	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_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 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 @@
 			goto unlock;
 	}
 
+	ep->iface_ref->need_setup = false;
+
  done:
 	ep->need_setup = false;
 	err = 1;
@@ -1387,15 +1441,21 @@
 }
 
 /**
- * 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 11e3bb8..eea4ca4 100644
--- a/sound/usb/endpoint.h
+++ b/sound/usb/endpoint.h
@@ -42,7 +42,7 @@
 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 931042a..1ac2cc6 100644
--- a/sound/usb/implicit.c
+++ b/sound/usb/implicit.c
@@ -58,8 +58,6 @@
 	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 */
@@ -100,7 +98,7 @@
 /* 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;
@@ -115,7 +113,7 @@
 	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",
@@ -147,7 +145,7 @@
 	    (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);
 }
 
@@ -173,10 +171,32 @@
 	    (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,
@@ -197,7 +217,7 @@
 	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);
 }
 
@@ -250,7 +270,7 @@
 		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);
 		}
 	}
@@ -278,6 +298,14 @@
 			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);
@@ -295,8 +323,8 @@
 
 	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;
 }
 
@@ -378,20 +406,19 @@
 				     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/quirks-table.h b/sound/usb/quirks-table.h
index 0e11cb9..c8a4bdf 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -3362,6 +3362,7 @@
 					.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 @@
 					.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 @@
 					.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 @@
 					.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 @@
 					.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 @@
 					.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 e4a690b..89e1726 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -120,6 +120,40 @@
 	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 @@
 	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 @@
 		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 @@
 	}
 	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 @@
 	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 @@
 	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 @@
 		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);
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index 980287a..215c177 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -44,6 +44,7 @@
 
 	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/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index 57c1724..698358c 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -198,7 +198,7 @@
 		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/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index c7ca4fa..fe41c6a 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -33,7 +33,7 @@
 	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 lib/s390x/diag318_test_handler.c
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 3d96a7b..cdad1ec 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 @@
 	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 @@
 	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 @@
 	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 @@
 			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 @@
 
 	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 @@
 		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 @@
 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;
+	struct test_params p = {};
+	int opt;
 
-#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, "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 @@
 		}
 	}
 
-	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 9c6a7be..2283a0e 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -8,29 +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)
 {
@@ -42,7 +41,7 @@
 	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);
@@ -89,9 +88,15 @@
 	return NULL;
 }
 
-static void run_test(enum vm_guest_mode mode, unsigned long iterations,
-		     uint64_t phys_offset, int wr_fract)
+struct test_params {
+	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;
@@ -106,9 +111,9 @@
 	struct kvm_enable_cap cap = {};
 	struct timespec clear_dirty_log_total = (struct timespec){0};
 
-	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);
@@ -124,7 +129,7 @@
 	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);
 
@@ -150,13 +155,13 @@
 
 	/* 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.
@@ -177,7 +182,7 @@
 			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,
@@ -187,7 +192,7 @@
 
 		if (dirty_log_manual_caps) {
 			clock_gettime(CLOCK_MONOTONIC, &start);
-			kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
+			kvm_vm_clear_dirty_log(vm, PERF_TEST_MEM_SLOT_INDEX, bmap, 0,
 					       host_num_pages);
 
 			ts_diff = timespec_diff_now(start);
@@ -205,43 +210,30 @@
 
 	/* 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);
 
 	if (dirty_log_manual_caps) {
-		avg = timespec_div(clear_dirty_log_total, iterations);
+		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",
-			iterations, clear_dirty_log_total.tv_sec,
+			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);
@@ -250,14 +242,7 @@
 	       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");
@@ -272,74 +257,43 @@
 
 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;
+	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);
 	dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
 				  KVM_DIRTY_LOG_INITIALLY_SET);
 
-#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:
@@ -348,18 +302,11 @@
 		}
 	}
 
-	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 471baec..bb2752d 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -9,8 +9,6 @@
 
 #include <stdio.h>
 #include <stdlib.h>
-#include <unistd.h>
-#include <time.h>
 #include <pthread.h>
 #include <semaphore.h>
 #include <sys/types.h>
@@ -20,8 +18,9 @@
 #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
@@ -673,9 +672,15 @@
 #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)
 {
+	struct test_params *p = arg;
 	struct kvm_vm *vm;
 	unsigned long *bmap;
 
@@ -709,12 +714,12 @@
 	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__
@@ -758,9 +763,9 @@
 
 	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);
@@ -783,20 +788,8 @@
 	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);
@@ -813,51 +806,23 @@
 	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;
 
 	sem_init(&dirty_ring_vcpu_stop, 0, 0);
 	sem_init(&dirty_ring_vcpu_cont, 0, 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
+	guest_modes_append_default();
 
 	while ((opt = getopt(argc, argv, "c:hi:I:p:m:M:")) != -1) {
 		switch (opt) {
@@ -865,24 +830,16 @@
 			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")) {
@@ -911,32 +868,24 @@
 		}
 	}
 
-	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 0000000..b691df3
--- /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 dfa9d36..5cbb861 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
@@ -70,6 +71,14 @@
 #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,
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 239421e..b118882 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;
+#define PERF_TEST_MEM_SLOT_INDEX	1
 
-/*
- * 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;
-
-struct vcpu_args {
+struct perf_test_vcpu_args {
 	uint64_t gva;
 	uint64_t pages;
 
@@ -54,141 +31,21 @@
 	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;
+extern uint64_t guest_test_phys_mem;
 
-	/* 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);
-
-		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);
-	}
-}
+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/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
new file mode 100644
index 0000000..25bff30
--- /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 88ef706..fa5a90e 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -153,14 +153,7 @@
 _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 },
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 0000000..9be1944
--- /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/vDSO/.gitignore b/tools/testing/selftests/vDSO/.gitignore
index 5eb64d4..a8dc51a 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 5029ef9..c4aea79 100644
--- a/tools/testing/selftests/vDSO/vdso_test_correctness.c
+++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c
@@ -349,7 +349,7 @@
 		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/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5f26048..fa9e361 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -485,9 +485,8 @@
 	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);