Merge tag 'arc-5.11-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc

Pull ARC fixes from Vineet Gupta:

 - Address the 2nd boot failure due to snafu in signal handling code
   (first was generic console ttynull issue)

 - misc other fixes

* tag 'arc-5.11-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc:
  ARC: [hsdk]: Enable FPU_SAVE_RESTORE
  ARC: unbork 5.11 bootup: fix snafu in _TIF_NOTIFY_SIGNAL handling
  include/soc: remove headers for EZChip NPS
  arch/arc: add copy_user_page() to <asm/page.h> to fix build error on ARC
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/regulator/nxp,pf8x00-regulator.yaml b/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml
index a6c259c..956156f 100644
--- a/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml
@@ -19,7 +19,9 @@
 properties:
   compatible:
     enum:
-      - nxp,pf8x00
+      - nxp,pf8100
+      - nxp,pf8121a
+      - nxp,pf8200
 
   reg:
     maxItems: 1
@@ -118,7 +120,7 @@
         #size-cells = <0>;
 
         pmic@8 {
-            compatible = "nxp,pf8x00";
+            compatible = "nxp,pf8100";
             reg = <0x08>;
 
             regulators {
diff --git a/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt
index b8f0b78..7d462b8 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt
@@ -44,6 +44,7 @@
 	Definition: Must be one of below:
 		    "qcom,pm8005-rpmh-regulators"
 		    "qcom,pm8009-rpmh-regulators"
+		    "qcom,pm8009-1-rpmh-regulators"
 		    "qcom,pm8150-rpmh-regulators"
 		    "qcom,pm8150l-rpmh-regulators"
 		    "qcom,pm8350-rpmh-regulators"
diff --git a/Documentation/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/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/networking/device_drivers/ethernet/marvell/octeontx2.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
index d3fcf53..61e8504 100644
--- a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
+++ b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
@@ -164,46 +164,56 @@
 
 NPA Reporters
 -------------
-The NPA reporters are responsible for reporting and recovering the following group of errors
+The NPA reporters are responsible for reporting and recovering the following group of errors:
+
 1. GENERAL events
+
    - Error due to operation of unmapped PF.
    - Error due to disabled alloc/free for other HW blocks (NIX, SSO, TIM, DPI and AURA).
+
 2. ERROR events
+
    - Fault due to NPA_AQ_INST_S read or NPA_AQ_RES_S write.
    - AQ Doorbell Error.
+
 3. RAS events
+
    - RAS Error Reporting for NPA_AQ_INST_S/NPA_AQ_RES_S.
+
 4. RVU events
+
    - Error due to unmapped slot.
 
-Sample Output
--------------
-~# devlink health
-pci/0002:01:00.0:
-  reporter hw_npa_intr
-      state healthy error 2872 recover 2872 last_dump_date 2020-12-10 last_dump_time 09:39:09 grace_period 0 auto_recover true auto_dump true
-  reporter hw_npa_gen
-      state healthy error 2872 recover 2872 last_dump_date 2020-12-11 last_dump_time 04:43:04 grace_period 0 auto_recover true auto_dump true
-  reporter hw_npa_err
-      state healthy error 2871 recover 2871 last_dump_date 2020-12-10 last_dump_time 09:39:17 grace_period 0 auto_recover true auto_dump true
-   reporter hw_npa_ras
-      state healthy error 0 recover 0 last_dump_date 2020-12-10 last_dump_time 09:32:40 grace_period 0 auto_recover true auto_dump true
+Sample Output::
+
+	~# devlink health
+	pci/0002:01:00.0:
+	  reporter hw_npa_intr
+	      state healthy error 2872 recover 2872 last_dump_date 2020-12-10 last_dump_time 09:39:09 grace_period 0 auto_recover true auto_dump true
+	  reporter hw_npa_gen
+	      state healthy error 2872 recover 2872 last_dump_date 2020-12-11 last_dump_time 04:43:04 grace_period 0 auto_recover true auto_dump true
+	  reporter hw_npa_err
+	      state healthy error 2871 recover 2871 last_dump_date 2020-12-10 last_dump_time 09:39:17 grace_period 0 auto_recover true auto_dump true
+	   reporter hw_npa_ras
+	      state healthy error 0 recover 0 last_dump_date 2020-12-10 last_dump_time 09:32:40 grace_period 0 auto_recover true auto_dump true
 
 Each reporter dumps the
+
  - Error Type
  - Error Register value
  - Reason in words
 
-For eg:
-~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_gen
- NPA_AF_GENERAL:
-         NPA General Interrupt Reg : 1
-         NIX0: free disabled RX
-~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_intr
- NPA_AF_RVU:
-         NPA RVU Interrupt Reg : 1
-         Unmap Slot Error
-~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_err
- NPA_AF_ERR:
-        NPA Error Interrupt Reg : 4096
-        AQ Doorbell Error
+For example::
+
+	~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_gen
+	 NPA_AF_GENERAL:
+	         NPA General Interrupt Reg : 1
+	         NIX0: free disabled RX
+	~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_intr
+	 NPA_AF_RVU:
+	         NPA RVU Interrupt Reg : 1
+	         Unmap Slot Error
+	~# devlink health dump show  pci/0002:01:00.0 reporter hw_npa_err
+	 NPA_AF_ERR:
+	        NPA Error Interrupt Reg : 4096
+	        AQ Doorbell Error
diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst
index 5a85fcc..e65665c 100644
--- a/Documentation/networking/netdevices.rst
+++ b/Documentation/networking/netdevices.rst
@@ -64,8 +64,8 @@
 	Context: process
 
 ndo_get_stats:
-	Synchronization: dev_base_lock rwlock.
-	Context: nominally process, but don't sleep inside an rwlock
+	Synchronization: rtnl_lock() semaphore, dev_base_lock rwlock, or RCU.
+	Context: atomic (can't sleep under rwlock or RCU)
 
 ndo_start_xmit:
 	Synchronization: __netif_tx_lock spinlock.
diff --git a/Documentation/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/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 7c1e45c..6390491 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9273,7 +9273,7 @@
 
 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
@@ -9776,7 +9776,7 @@
 
 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>
@@ -10260,7 +10260,6 @@
 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
@@ -10847,7 +10846,7 @@
 
 MCAN MMIO DEVICE DRIVER
 M:	Dan Murphy <dmurphy@ti.com>
-M:	Sriram Dash <sriram.dash@samsung.com>
+M:	Pankaj Sharma <pankj.sharma@samsung.com>
 L:	linux-can@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/can/bosch,m_can.yaml
@@ -17553,6 +17552,19 @@
 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>
@@ -19505,7 +19517,7 @@
 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/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/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/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c
index 7b5cf84..cdde8fd 100644
--- a/arch/arm/crypto/chacha-glue.c
+++ b/arch/arm/crypto/chacha-glue.c
@@ -60,6 +60,7 @@
 		chacha_block_xor_neon(state, d, s, nrounds);
 		if (d != dst)
 			memcpy(dst, buf, bytes);
+		state[12]++;
 	}
 }
 
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/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/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/crypto/ecdh.c b/crypto/ecdh.c
index d56b860..96f80c8 100644
--- a/crypto/ecdh.c
+++ b/crypto/ecdh.c
@@ -39,7 +39,8 @@
 	struct ecdh params;
 	unsigned int ndigits;
 
-	if (crypto_ecdh_decode_key(buf, len, &params) < 0)
+	if (crypto_ecdh_decode_key(buf, len, &params) < 0 ||
+	    params.key_size > sizeof(ctx->private_key))
 		return -EINVAL;
 
 	ndigits = ecdh_supported_curve(params.curve_id);
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 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/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 8dfac7f..ff2ee87 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -582,8 +582,12 @@
 		devname = dev_name(map->dev);
 
 	if (name) {
-		map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s",
+		if (!map->debugfs_name) {
+			map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s",
 					      devname, name);
+			if (!map->debugfs_name)
+				return;
+		}
 		name = map->debugfs_name;
 	} else {
 		name = devname;
@@ -591,9 +595,10 @@
 
 	if (!strcmp(name, "dummy")) {
 		kfree(map->debugfs_name);
-
 		map->debugfs_name = kasprintf(GFP_KERNEL, "dummy%d",
 						dummy_index);
+		if (!map->debugfs_name)
+				return;
 		name = map->debugfs_name;
 		dummy_index++;
 	}
diff --git a/drivers/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/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/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/isdn/mISDN/Kconfig b/drivers/isdn/mISDN/Kconfig
index 26cf0ac..c9a53c2 100644
--- a/drivers/isdn/mISDN/Kconfig
+++ b/drivers/isdn/mISDN/Kconfig
@@ -13,6 +13,7 @@
 config MISDN_DSP
 	tristate "Digital Audio Processing of transparent data"
 	depends on MISDN
+	select BITREVERSE
 	help
 	  Enable support for digital audio processing capability.
 
diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index 708171c..85de5f9 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -645,11 +645,20 @@
 	return 0;
 }
 
+static void bareudp_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct bareudp_dev *bareudp = netdev_priv(dev);
+
+	list_del(&bareudp->next);
+	unregister_netdevice_queue(dev, head);
+}
+
 static int bareudp_newlink(struct net *net, struct net_device *dev,
 			   struct nlattr *tb[], struct nlattr *data[],
 			   struct netlink_ext_ack *extack)
 {
 	struct bareudp_conf conf;
+	LIST_HEAD(list_kill);
 	int err;
 
 	err = bareudp2info(data, &conf, extack);
@@ -662,17 +671,14 @@
 
 	err = bareudp_link_config(dev, tb);
 	if (err)
-		return err;
+		goto err_unconfig;
 
 	return 0;
-}
 
-static void bareudp_dellink(struct net_device *dev, struct list_head *head)
-{
-	struct bareudp_dev *bareudp = netdev_priv(dev);
-
-	list_del(&bareudp->next);
-	unregister_netdevice_queue(dev, head);
+err_unconfig:
+	bareudp_dellink(dev, &list_kill);
+	unregister_netdevice_many(&list_kill);
+	return err;
 }
 
 static size_t bareudp_get_size(const struct net_device *dev)
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 4249709..1c28ead 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -123,6 +123,7 @@
 config CAN_KVASER_PCIEFD
 	depends on PCI
 	tristate "Kvaser PCIe FD cards"
+	select CRC32
 	  help
 	  This is a driver for the Kvaser PCI Express CAN FD family.
 
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 2c9f124..da551fd 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1852,8 +1852,6 @@
 void m_can_class_unregister(struct m_can_classdev *cdev)
 {
 	unregister_candev(cdev->net);
-
-	m_can_clk_stop(cdev);
 }
 EXPORT_SYMBOL_GPL(m_can_class_unregister);
 
diff --git a/drivers/net/can/m_can/tcan4x5x.c b/drivers/net/can/m_can/tcan4x5x.c
index 24c737c..970f0e9 100644
--- a/drivers/net/can/m_can/tcan4x5x.c
+++ b/drivers/net/can/m_can/tcan4x5x.c
@@ -131,30 +131,6 @@
 
 }
 
-static struct can_bittiming_const tcan4x5x_bittiming_const = {
-	.name = DEVICE_NAME,
-	.tseg1_min = 2,
-	.tseg1_max = 31,
-	.tseg2_min = 2,
-	.tseg2_max = 16,
-	.sjw_max = 16,
-	.brp_min = 1,
-	.brp_max = 32,
-	.brp_inc = 1,
-};
-
-static struct can_bittiming_const tcan4x5x_data_bittiming_const = {
-	.name = DEVICE_NAME,
-	.tseg1_min = 1,
-	.tseg1_max = 32,
-	.tseg2_min = 1,
-	.tseg2_max = 16,
-	.sjw_max = 16,
-	.brp_min = 1,
-	.brp_max = 32,
-	.brp_inc = 1,
-};
-
 static void tcan4x5x_check_wake(struct tcan4x5x_priv *priv)
 {
 	int wake_state = 0;
@@ -469,8 +445,6 @@
 	mcan_class->dev = &spi->dev;
 	mcan_class->ops = &tcan4x5x_ops;
 	mcan_class->is_peripheral = true;
-	mcan_class->bit_timing = &tcan4x5x_bittiming_const;
-	mcan_class->data_timing = &tcan4x5x_data_bittiming_const;
 	mcan_class->net->irq = spi->irq;
 
 	spi_set_drvdata(spi, priv);
diff --git a/drivers/net/can/rcar/Kconfig b/drivers/net/can/rcar/Kconfig
index 8d36101..29cabc2 100644
--- a/drivers/net/can/rcar/Kconfig
+++ b/drivers/net/can/rcar/Kconfig
@@ -1,10 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 config CAN_RCAR
-	tristate "Renesas R-Car CAN controller"
+	tristate "Renesas R-Car and RZ/G CAN controller"
 	depends on ARCH_RENESAS || ARM
 	help
 	  Say Y here if you want to use CAN controller found on Renesas R-Car
-	  SoCs.
+	  or RZ/G SoCs.
 
 	  To compile this driver as a module, choose M here: the module will
 	  be called rcar_can.
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 77129d5..36235af 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -1368,13 +1368,10 @@
 		struct mcp251xfd_tx_ring *tx_ring = priv->tx;
 		struct spi_transfer *last_xfer;
 
-		tx_ring->tail += len;
-
 		/* Increment the TEF FIFO tail pointer 'len' times in
 		 * a single SPI message.
-		 */
-
-		/* Note:
+		 *
+		 * Note:
 		 *
 		 * "cs_change == 1" on the last transfer results in an
 		 * active chip select after the complete SPI
@@ -1391,6 +1388,8 @@
 		if (err)
 			return err;
 
+		tx_ring->tail += len;
+
 		err = mcp251xfd_check_tef_tail(priv);
 		if (err)
 			return err;
@@ -1553,10 +1552,8 @@
 
 		/* Increment the RX FIFO tail pointer 'len' times in a
 		 * single SPI message.
-		 */
-		ring->tail += len;
-
-		/* Note:
+		 *
+		 * Note:
 		 *
 		 * "cs_change == 1" on the last transfer results in an
 		 * active chip select after the complete SPI
@@ -1572,6 +1569,8 @@
 		last_xfer->cs_change = 1;
 		if (err)
 			return err;
+
+		ring->tail += len;
 	}
 
 	return 0;
diff --git a/drivers/net/dsa/hirschmann/Kconfig b/drivers/net/dsa/hirschmann/Kconfig
index 222dd35..e011911 100644
--- a/drivers/net/dsa/hirschmann/Kconfig
+++ b/drivers/net/dsa/hirschmann/Kconfig
@@ -4,6 +4,7 @@
 	depends on HAS_IOMEM
 	depends on NET_DSA
 	depends on PTP_1588_CLOCK
+	depends on LEDS_CLASS
 	select NET_DSA_TAG_HELLCREEK
 	help
 	  This driver adds support for Hirschmann Hellcreek TSN switches.
diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
index 4b36d89..662e68a0 100644
--- a/drivers/net/dsa/lantiq_gswip.c
+++ b/drivers/net/dsa/lantiq_gswip.c
@@ -1436,11 +1436,12 @@
 	phylink_set(mask, Pause);
 	phylink_set(mask, Asym_Pause);
 
-	/* With the exclusion of MII and Reverse MII, we support Gigabit,
-	 * including Half duplex
+	/* With the exclusion of MII, Reverse MII and Reduced MII, we
+	 * support Gigabit, including Half duplex
 	 */
 	if (state->interface != PHY_INTERFACE_MODE_MII &&
-	    state->interface != PHY_INTERFACE_MODE_REVMII) {
+	    state->interface != PHY_INTERFACE_MODE_REVMII &&
+	    state->interface != PHY_INTERFACE_MODE_RMII) {
 		phylink_set(mask, 1000baseT_Full);
 		phylink_set(mask, 1000baseT_Half);
 	}
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
index a0e0d8a..51dd030 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
@@ -621,7 +621,7 @@
 
 	while (!skb_queue_empty(&listen_ctx->synq)) {
 		struct chtls_sock *csk =
-			container_of((struct synq *)__skb_dequeue
+			container_of((struct synq *)skb_peek
 				(&listen_ctx->synq), struct chtls_sock, synq);
 		struct sock *child = csk->sk;
 
@@ -1109,6 +1109,7 @@
 				    const struct cpl_pass_accept_req *req,
 				    struct chtls_dev *cdev)
 {
+	struct adapter *adap = pci_get_drvdata(cdev->pdev);
 	struct neighbour *n = NULL;
 	struct inet_sock *newinet;
 	const struct iphdr *iph;
@@ -1118,9 +1119,10 @@
 	struct dst_entry *dst;
 	struct tcp_sock *tp;
 	struct sock *newsk;
+	bool found = false;
 	u16 port_id;
 	int rxq_idx;
-	int step;
+	int step, i;
 
 	iph = (const struct iphdr *)network_hdr;
 	newsk = tcp_create_openreq_child(lsk, oreq, cdev->askb);
@@ -1152,7 +1154,7 @@
 		n = dst_neigh_lookup(dst, &ip6h->saddr);
 #endif
 	}
-	if (!n)
+	if (!n || !n->dev)
 		goto free_sk;
 
 	ndev = n->dev;
@@ -1161,6 +1163,13 @@
 	if (is_vlan_dev(ndev))
 		ndev = vlan_dev_real_dev(ndev);
 
+	for_each_port(adap, i)
+		if (cdev->ports[i] == ndev)
+			found = true;
+
+	if (!found)
+		goto free_dst;
+
 	port_id = cxgb4_port_idx(ndev);
 
 	csk = chtls_sock_create(cdev);
@@ -1238,6 +1247,7 @@
 free_csk:
 	chtls_sock_release(&csk->kref);
 free_dst:
+	neigh_release(n);
 	dst_release(dst);
 free_sk:
 	inet_csk_prepare_forced_close(newsk);
@@ -1387,7 +1397,7 @@
 
 	newsk = chtls_recv_sock(sk, oreq, network_hdr, req, cdev);
 	if (!newsk)
-		goto free_oreq;
+		goto reject;
 
 	if (chtls_get_module(newsk))
 		goto reject;
@@ -1403,8 +1413,6 @@
 	kfree_skb(skb);
 	return;
 
-free_oreq:
-	chtls_reqsk_free(oreq);
 reject:
 	mk_tid_release(reply_skb, 0, tid);
 	cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb);
@@ -1589,6 +1597,11 @@
 			sk_wake_async(sk, 0, POLL_OUT);
 
 		data = lookup_stid(cdev->tids, stid);
+		if (!data) {
+			/* listening server close */
+			kfree_skb(skb);
+			goto unlock;
+		}
 		lsk = ((struct listen_ctx *)data)->lsk;
 
 		bh_lock_sock(lsk);
@@ -1997,39 +2010,6 @@
 	spin_unlock_bh(&cdev->deferq.lock);
 }
 
-static void send_abort_rpl(struct sock *sk, struct sk_buff *skb,
-			   struct chtls_dev *cdev, int status, int queue)
-{
-	struct cpl_abort_req_rss *req = cplhdr(skb);
-	struct sk_buff *reply_skb;
-	struct chtls_sock *csk;
-
-	csk = rcu_dereference_sk_user_data(sk);
-
-	reply_skb = alloc_skb(sizeof(struct cpl_abort_rpl),
-			      GFP_KERNEL);
-
-	if (!reply_skb) {
-		req->status = (queue << 1);
-		t4_defer_reply(skb, cdev, send_defer_abort_rpl);
-		return;
-	}
-
-	set_abort_rpl_wr(reply_skb, GET_TID(req), status);
-	kfree_skb(skb);
-
-	set_wr_txq(reply_skb, CPL_PRIORITY_DATA, queue);
-	if (csk_conn_inline(csk)) {
-		struct l2t_entry *e = csk->l2t_entry;
-
-		if (e && sk->sk_state != TCP_SYN_RECV) {
-			cxgb4_l2t_send(csk->egress_dev, reply_skb, e);
-			return;
-		}
-	}
-	cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb);
-}
-
 static void chtls_send_abort_rpl(struct sock *sk, struct sk_buff *skb,
 				 struct chtls_dev *cdev,
 				 int status, int queue)
@@ -2078,9 +2058,9 @@
 	queue = csk->txq_idx;
 
 	skb->sk	= NULL;
+	chtls_send_abort_rpl(child, skb, BLOG_SKB_CB(skb)->cdev,
+			     CPL_ABORT_NO_RST, queue);
 	do_abort_syn_rcv(child, lsk);
-	send_abort_rpl(child, skb, BLOG_SKB_CB(skb)->cdev,
-		       CPL_ABORT_NO_RST, queue);
 }
 
 static int abort_syn_rcv(struct sock *sk, struct sk_buff *skb)
@@ -2110,8 +2090,8 @@
 	if (!sock_owned_by_user(psk)) {
 		int queue = csk->txq_idx;
 
+		chtls_send_abort_rpl(sk, skb, cdev, CPL_ABORT_NO_RST, queue);
 		do_abort_syn_rcv(sk, psk);
-		send_abort_rpl(sk, skb, cdev, CPL_ABORT_NO_RST, queue);
 	} else {
 		skb->sk = sk;
 		BLOG_SKB_CB(skb)->backlog_rcv = bl_abort_syn_rcv;
@@ -2129,9 +2109,6 @@
 	int queue = csk->txq_idx;
 
 	if (is_neg_adv(req->status)) {
-		if (sk->sk_state == TCP_SYN_RECV)
-			chtls_set_tcb_tflag(sk, 0, 0);
-
 		kfree_skb(skb);
 		return;
 	}
@@ -2158,12 +2135,12 @@
 		if (sk->sk_state == TCP_SYN_RECV && !abort_syn_rcv(sk, skb))
 			return;
 
-		chtls_release_resources(sk);
-		chtls_conn_done(sk);
 	}
 
 	chtls_send_abort_rpl(sk, skb, BLOG_SKB_CB(skb)->cdev,
 			     rst_status, queue);
+	chtls_release_resources(sk);
+	chtls_conn_done(sk);
 }
 
 static void chtls_abort_rpl_rss(struct sock *sk, struct sk_buff *skb)
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
index c8e5d88..21de563 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
@@ -223,3 +223,4 @@
 };
 
 module_platform_driver(fs_enet_bb_mdio_driver);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
index 8b51ee1..152f4d8 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
@@ -224,3 +224,4 @@
 };
 
 module_platform_driver(fs_enet_fec_mdio_driver);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index fb5e884..33defa4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -169,7 +169,7 @@
 #define hclge_mbx_ring_ptr_move_crq(crq) \
 	(crq->next_to_use = (crq->next_to_use + 1) % crq->desc_num)
 #define hclge_mbx_tail_ptr_move_arq(arq) \
-	(arq.tail = (arq.tail + 1) % HCLGE_MBX_MAX_ARQ_MSG_SIZE)
+		(arq.tail = (arq.tail + 1) % HCLGE_MBX_MAX_ARQ_MSG_NUM)
 #define hclge_mbx_head_ptr_move_arq(arq) \
-		(arq.head = (arq.head + 1) % HCLGE_MBX_MAX_ARQ_MSG_SIZE)
+		(arq.head = (arq.head + 1) % HCLGE_MBX_MAX_ARQ_MSG_NUM)
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index e6f37f9..c242883 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -752,7 +752,8 @@
 		handle->flags |= HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK;
 		handle->flags |= HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK;
 
-		if (hdev->hw.mac.phydev) {
+		if (hdev->hw.mac.phydev && hdev->hw.mac.phydev->drv &&
+		    hdev->hw.mac.phydev->drv->set_loopback) {
 			count += 1;
 			handle->flags |= HNAE3_SUPPORT_PHY_LOOPBACK;
 		}
@@ -4537,8 +4538,8 @@
 		req->ipv4_sctp_en = tuple_sets;
 		break;
 	case SCTP_V6_FLOW:
-		if ((nfc->data & RXH_L4_B_0_1) ||
-		    (nfc->data & RXH_L4_B_2_3))
+		if (hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 &&
+		    (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)))
 			return -EINVAL;
 
 		req->ipv6_sctp_en = tuple_sets;
@@ -4730,6 +4731,8 @@
 		vport[i].rss_tuple_sets.ipv6_udp_en =
 			HCLGE_RSS_INPUT_TUPLE_OTHER;
 		vport[i].rss_tuple_sets.ipv6_sctp_en =
+			hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 ?
+			HCLGE_RSS_INPUT_TUPLE_SCTP_NO_PORT :
 			HCLGE_RSS_INPUT_TUPLE_SCTP;
 		vport[i].rss_tuple_sets.ipv6_fragment_en =
 			HCLGE_RSS_INPUT_TUPLE_OTHER;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 50a294d..ca46bc9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -107,6 +107,8 @@
 #define HCLGE_D_IP_BIT			BIT(2)
 #define HCLGE_S_IP_BIT			BIT(3)
 #define HCLGE_V_TAG_BIT			BIT(4)
+#define HCLGE_RSS_INPUT_TUPLE_SCTP_NO_PORT	\
+		(HCLGE_D_IP_BIT | HCLGE_S_IP_BIT | HCLGE_V_TAG_BIT)
 
 #define HCLGE_RSS_TC_SIZE_0		1
 #define HCLGE_RSS_TC_SIZE_1		2
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 145757c..674b3a2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -917,8 +917,8 @@
 		req->ipv4_sctp_en = tuple_sets;
 		break;
 	case SCTP_V6_FLOW:
-		if ((nfc->data & RXH_L4_B_0_1) ||
-		    (nfc->data & RXH_L4_B_2_3))
+		if (hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 &&
+		    (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)))
 			return -EINVAL;
 
 		req->ipv6_sctp_en = tuple_sets;
@@ -2502,7 +2502,10 @@
 		tuple_sets->ipv4_fragment_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
 		tuple_sets->ipv6_tcp_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
 		tuple_sets->ipv6_udp_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
-		tuple_sets->ipv6_sctp_en = HCLGEVF_RSS_INPUT_TUPLE_SCTP;
+		tuple_sets->ipv6_sctp_en =
+			hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 ?
+					HCLGEVF_RSS_INPUT_TUPLE_SCTP_NO_PORT :
+					HCLGEVF_RSS_INPUT_TUPLE_SCTP;
 		tuple_sets->ipv6_fragment_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 1b183bc..f6d817a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -122,6 +122,8 @@
 #define HCLGEVF_D_IP_BIT		BIT(2)
 #define HCLGEVF_S_IP_BIT		BIT(3)
 #define HCLGEVF_V_TAG_BIT		BIT(4)
+#define HCLGEVF_RSS_INPUT_TUPLE_SCTP_NO_PORT	\
+	(HCLGEVF_D_IP_BIT | HCLGEVF_S_IP_BIT | HCLGEVF_V_TAG_BIT)
 
 #define HCLGEVF_STATS_TIMER_INTERVAL	36U
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 3369ec7..bc4d8d1 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4432,7 +4432,7 @@
 	struct bpf_prog *old_prog;
 
 	if (prog && dev->mtu > MVNETA_MAX_RX_BUF_SIZE) {
-		NL_SET_ERR_MSG_MOD(extack, "Jumbo frames not supported on XDP");
+		NL_SET_ERR_MSG_MOD(extack, "MTU too large for XDP");
 		return -EOPNOTSUPP;
 	}
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 7d0f962..1a8f5a0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -871,8 +871,10 @@
 		if (!lmac)
 			return -ENOMEM;
 		lmac->name = kcalloc(1, sizeof("cgx_fwi_xxx_yyy"), GFP_KERNEL);
-		if (!lmac->name)
-			return -ENOMEM;
+		if (!lmac->name) {
+			err = -ENOMEM;
+			goto err_lmac_free;
+		}
 		sprintf(lmac->name, "cgx_fwi_%d_%d", cgx->cgx_id, i);
 		lmac->lmac_id = i;
 		lmac->cgx = cgx;
@@ -883,7 +885,7 @@
 						 CGX_LMAC_FWI + i * 9),
 				   cgx_fwi_event_handler, 0, lmac->name, lmac);
 		if (err)
-			return err;
+			goto err_irq;
 
 		/* Enable interrupt */
 		cgx_write(cgx, lmac->lmac_id, CGXX_CMRX_INT_ENA_W1S,
@@ -895,6 +897,12 @@
 	}
 
 	return cgx_lmac_verify_fwi_version(cgx);
+
+err_irq:
+	kfree(lmac->name);
+err_lmac_free:
+	kfree(lmac);
+	return err;
 }
 
 static int cgx_lmac_exit(struct cgx *cgx)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index d29af7b..76177f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -626,6 +626,11 @@
 	if (!reg_c0)
 		return true;
 
+	/* If reg_c0 is not equal to the default flow tag then skb->mark
+	 * is not supported and must be reset back to 0.
+	 */
+	skb->mark = 0;
+
 	priv = netdev_priv(skb->dev);
 	esw = priv->mdev->priv.eswitch;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index e521254..072363e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -118,16 +118,17 @@
 	u16 zone;
 };
 
-struct mlx5_ct_shared_counter {
+struct mlx5_ct_counter {
 	struct mlx5_fc *counter;
 	refcount_t refcount;
+	bool is_shared;
 };
 
 struct mlx5_ct_entry {
 	struct rhash_head node;
 	struct rhash_head tuple_node;
 	struct rhash_head tuple_nat_node;
-	struct mlx5_ct_shared_counter *shared_counter;
+	struct mlx5_ct_counter *counter;
 	unsigned long cookie;
 	unsigned long restore_cookie;
 	struct mlx5_ct_tuple tuple;
@@ -394,13 +395,14 @@
 }
 
 static void
-mlx5_tc_ct_shared_counter_put(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_entry *entry)
+mlx5_tc_ct_counter_put(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_entry *entry)
 {
-	if (!refcount_dec_and_test(&entry->shared_counter->refcount))
+	if (entry->counter->is_shared &&
+	    !refcount_dec_and_test(&entry->counter->refcount))
 		return;
 
-	mlx5_fc_destroy(ct_priv->dev, entry->shared_counter->counter);
-	kfree(entry->shared_counter);
+	mlx5_fc_destroy(ct_priv->dev, entry->counter->counter);
+	kfree(entry->counter);
 }
 
 static void
@@ -699,7 +701,7 @@
 	attr->dest_ft = ct_priv->post_ct;
 	attr->ft = nat ? ct_priv->ct_nat : ct_priv->ct;
 	attr->outer_match_level = MLX5_MATCH_L4;
-	attr->counter = entry->shared_counter->counter;
+	attr->counter = entry->counter->counter;
 	attr->flags |= MLX5_ESW_ATTR_FLAG_NO_IN_PORT;
 
 	mlx5_tc_ct_set_tuple_match(netdev_priv(ct_priv->netdev), spec, flow_rule);
@@ -732,13 +734,34 @@
 	return err;
 }
 
-static struct mlx5_ct_shared_counter *
+static struct mlx5_ct_counter *
+mlx5_tc_ct_counter_create(struct mlx5_tc_ct_priv *ct_priv)
+{
+	struct mlx5_ct_counter *counter;
+	int ret;
+
+	counter = kzalloc(sizeof(*counter), GFP_KERNEL);
+	if (!counter)
+		return ERR_PTR(-ENOMEM);
+
+	counter->is_shared = false;
+	counter->counter = mlx5_fc_create(ct_priv->dev, true);
+	if (IS_ERR(counter->counter)) {
+		ct_dbg("Failed to create counter for ct entry");
+		ret = PTR_ERR(counter->counter);
+		kfree(counter);
+		return ERR_PTR(ret);
+	}
+
+	return counter;
+}
+
+static struct mlx5_ct_counter *
 mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv,
 			      struct mlx5_ct_entry *entry)
 {
 	struct mlx5_ct_tuple rev_tuple = entry->tuple;
-	struct mlx5_ct_shared_counter *shared_counter;
-	struct mlx5_core_dev *dev = ct_priv->dev;
+	struct mlx5_ct_counter *shared_counter;
 	struct mlx5_ct_entry *rev_entry;
 	__be16 tmp_port;
 	int ret;
@@ -767,25 +790,20 @@
 	rev_entry = rhashtable_lookup_fast(&ct_priv->ct_tuples_ht, &rev_tuple,
 					   tuples_ht_params);
 	if (rev_entry) {
-		if (refcount_inc_not_zero(&rev_entry->shared_counter->refcount)) {
+		if (refcount_inc_not_zero(&rev_entry->counter->refcount)) {
 			mutex_unlock(&ct_priv->shared_counter_lock);
-			return rev_entry->shared_counter;
+			return rev_entry->counter;
 		}
 	}
 	mutex_unlock(&ct_priv->shared_counter_lock);
 
-	shared_counter = kzalloc(sizeof(*shared_counter), GFP_KERNEL);
-	if (!shared_counter)
-		return ERR_PTR(-ENOMEM);
-
-	shared_counter->counter = mlx5_fc_create(dev, true);
-	if (IS_ERR(shared_counter->counter)) {
-		ct_dbg("Failed to create counter for ct entry");
-		ret = PTR_ERR(shared_counter->counter);
-		kfree(shared_counter);
+	shared_counter = mlx5_tc_ct_counter_create(ct_priv);
+	if (IS_ERR(shared_counter)) {
+		ret = PTR_ERR(shared_counter);
 		return ERR_PTR(ret);
 	}
 
+	shared_counter->is_shared = true;
 	refcount_set(&shared_counter->refcount, 1);
 	return shared_counter;
 }
@@ -798,10 +816,13 @@
 {
 	int err;
 
-	entry->shared_counter = mlx5_tc_ct_shared_counter_get(ct_priv, entry);
-	if (IS_ERR(entry->shared_counter)) {
-		err = PTR_ERR(entry->shared_counter);
-		ct_dbg("Failed to create counter for ct entry");
+	if (nf_ct_acct_enabled(dev_net(ct_priv->netdev)))
+		entry->counter = mlx5_tc_ct_counter_create(ct_priv);
+	else
+		entry->counter = mlx5_tc_ct_shared_counter_get(ct_priv, entry);
+
+	if (IS_ERR(entry->counter)) {
+		err = PTR_ERR(entry->counter);
 		return err;
 	}
 
@@ -820,7 +841,7 @@
 err_nat:
 	mlx5_tc_ct_entry_del_rule(ct_priv, entry, false);
 err_orig:
-	mlx5_tc_ct_shared_counter_put(ct_priv, entry);
+	mlx5_tc_ct_counter_put(ct_priv, entry);
 	return err;
 }
 
@@ -918,7 +939,7 @@
 	rhashtable_remove_fast(&ct_priv->ct_tuples_ht, &entry->tuple_node,
 			       tuples_ht_params);
 	mutex_unlock(&ct_priv->shared_counter_lock);
-	mlx5_tc_ct_shared_counter_put(ct_priv, entry);
+	mlx5_tc_ct_counter_put(ct_priv, entry);
 
 }
 
@@ -956,7 +977,7 @@
 	if (!entry)
 		return -ENOENT;
 
-	mlx5_fc_query_cached(entry->shared_counter->counter, &bytes, &packets, &lastuse);
+	mlx5_fc_query_cached(entry->counter->counter, &bytes, &packets, &lastuse);
 	flow_stats_update(&f->stats, bytes, packets, 0, lastuse,
 			  FLOW_ACTION_HW_STATS_DELAYED);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 7943eb3..4880f21 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -371,6 +371,15 @@
 	u8 tun_l4_proto;
 };
 
+static inline void mlx5e_eseg_swp_offsets_add_vlan(struct mlx5_wqe_eth_seg *eseg)
+{
+	/* SWP offsets are in 2-bytes words */
+	eseg->swp_outer_l3_offset += VLAN_HLEN / 2;
+	eseg->swp_outer_l4_offset += VLAN_HLEN / 2;
+	eseg->swp_inner_l3_offset += VLAN_HLEN / 2;
+	eseg->swp_inner_l4_offset += VLAN_HLEN / 2;
+}
+
 static inline void
 mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg,
 		   struct mlx5e_swp_spec *swp_spec)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index 899b98a..1fae7fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -51,7 +51,7 @@
 }
 
 static inline void
-mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
+mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
 	struct mlx5e_swp_spec swp_spec = {};
 	unsigned int offset = 0;
@@ -85,6 +85,8 @@
 	}
 
 	mlx5e_set_eseg_swp(skb, eseg, &swp_spec);
+	if (skb_vlan_tag_present(skb) &&  ihs)
+		mlx5e_eseg_swp_offsets_add_vlan(eseg);
 }
 
 #else
@@ -163,7 +165,7 @@
 
 static inline bool mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
 				       struct sk_buff *skb,
-				       struct mlx5_wqe_eth_seg *eseg)
+				       struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
 #ifdef CONFIG_MLX5_EN_IPSEC
 	if (xfrm_offload(skb))
@@ -172,7 +174,7 @@
 
 #if IS_ENABLED(CONFIG_GENEVE)
 	if (skb->encapsulation)
-		mlx5e_tx_tunnel_accel(skb, eseg);
+		mlx5e_tx_tunnel_accel(skb, eseg, ihs);
 #endif
 
 	return true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index d9076d5..2d37742 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1010,6 +1010,22 @@
 	return mlx5e_ethtool_get_link_ksettings(priv, link_ksettings);
 }
 
+static int mlx5e_speed_validate(struct net_device *netdev, bool ext,
+				const unsigned long link_modes, u8 autoneg)
+{
+	/* Extended link-mode has no speed limitations. */
+	if (ext)
+		return 0;
+
+	if ((link_modes & MLX5E_PROT_MASK(MLX5E_56GBASE_R4)) &&
+	    autoneg != AUTONEG_ENABLE) {
+		netdev_err(netdev, "%s: 56G link speed requires autoneg enabled\n",
+			   __func__);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 {
 	u32 i, ptys_modes = 0;
@@ -1103,13 +1119,9 @@
 	link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) :
 		mlx5e_port_speed2linkmodes(mdev, speed, !ext);
 
-	if ((link_modes & MLX5E_PROT_MASK(MLX5E_56GBASE_R4)) &&
-	    autoneg != AUTONEG_ENABLE) {
-		netdev_err(priv->netdev, "%s: 56G link speed requires autoneg enabled\n",
-			   __func__);
-		err = -EINVAL;
+	err = mlx5e_speed_validate(priv->netdev, ext, link_modes, autoneg);
+	if (err)
 		goto out;
-	}
 
 	link_modes = link_modes & eproto.cap;
 	if (!link_modes) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index fa8149f..e02e589 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -942,6 +942,7 @@
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		kfree(ft->g);
+		ft->g = NULL;
 		return -ENOMEM;
 	}
 
@@ -1087,6 +1088,7 @@
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in) {
 		kfree(ft->g);
+		ft->g = NULL;
 		return -ENOMEM;
 	}
 
@@ -1390,6 +1392,7 @@
 	ft->g[ft->num_groups] = NULL;
 	mlx5e_destroy_groups(ft);
 	kvfree(in);
+	kfree(ft->g);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7a79d33..6a852b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3161,7 +3161,8 @@
 
 	mlx5_set_port_admin_status(mdev, state);
 
-	if (mlx5_eswitch_mode(mdev) != MLX5_ESWITCH_LEGACY)
+	if (mlx5_eswitch_mode(mdev) == MLX5_ESWITCH_OFFLOADS ||
+	    !MLX5_CAP_GEN(mdev, uplink_follow))
 		return;
 
 	if (state == MLX5_PORT_UP)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index e47e2a0..61ed671 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -682,9 +682,9 @@
 
 static bool mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq,
 				   struct sk_buff *skb, struct mlx5e_accel_tx_state *accel,
-				   struct mlx5_wqe_eth_seg *eseg)
+				   struct mlx5_wqe_eth_seg *eseg, u16 ihs)
 {
-	if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg)))
+	if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg, ihs)))
 		return false;
 
 	mlx5e_txwqe_build_eseg_csum(sq, skb, accel, eseg);
@@ -714,7 +714,8 @@
 		if (mlx5e_tx_skb_supports_mpwqe(skb, &attr)) {
 			struct mlx5_wqe_eth_seg eseg = {};
 
-			if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg)))
+			if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg,
+							     attr.ihs)))
 				return NETDEV_TX_OK;
 
 			mlx5e_sq_xmit_mpwqe(sq, skb, &eseg, netdev_xmit_more());
@@ -731,7 +732,7 @@
 	/* May update the WQE, but may not post other WQEs. */
 	mlx5e_accel_tx_finish(sq, wqe, &accel,
 			      (struct mlx5_wqe_inline_seg *)(wqe->data + wqe_attr.ds_cnt_inl));
-	if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth)))
+	if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth, attr.ihs)))
 		return NETDEV_TX_OK;
 
 	mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, netdev_xmit_more());
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
index 2b85d47..3e19b17 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
@@ -95,22 +95,21 @@
 		return 0;
 	}
 
-	if (!IS_ERR_OR_NULL(vport->egress.acl))
-		return 0;
+	if (!vport->egress.acl) {
+		vport->egress.acl = esw_acl_table_create(esw, vport->vport,
+							 MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+							 table_size);
+		if (IS_ERR(vport->egress.acl)) {
+			err = PTR_ERR(vport->egress.acl);
+			vport->egress.acl = NULL;
+			goto out;
+		}
 
-	vport->egress.acl = esw_acl_table_create(esw, vport->vport,
-						 MLX5_FLOW_NAMESPACE_ESW_EGRESS,
-						 table_size);
-	if (IS_ERR(vport->egress.acl)) {
-		err = PTR_ERR(vport->egress.acl);
-		vport->egress.acl = NULL;
-		goto out;
+		err = esw_acl_egress_lgcy_groups_create(esw, vport);
+		if (err)
+			goto out;
 	}
 
-	err = esw_acl_egress_lgcy_groups_create(esw, vport);
-	if (err)
-		goto out;
-
 	esw_debug(esw->dev,
 		  "vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
 		  vport->vport, vport->info.vlan, vport->info.qos);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index f3d45ef..83a0537 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -564,7 +564,9 @@
 	struct mlx5_core_dev *tmp_dev;
 	int i, err;
 
-	if (!MLX5_CAP_GEN(dev, vport_group_manager))
+	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
+	    !MLX5_CAP_GEN(dev, lag_master) ||
+	    MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_MAX_PORTS)
 		return;
 
 	tmp_dev = mlx5_get_next_phys_dev(dev);
@@ -582,12 +584,9 @@
 	if (mlx5_lag_dev_add_pf(ldev, dev, netdev) < 0)
 		return;
 
-	for (i = 0; i < MLX5_MAX_PORTS; i++) {
-		tmp_dev = ldev->pf[i].dev;
-		if (!tmp_dev || !MLX5_CAP_GEN(tmp_dev, lag_master) ||
-		    MLX5_CAP_GEN(tmp_dev, num_lag_ports) != MLX5_MAX_PORTS)
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (!ldev->pf[i].dev)
 			break;
-	}
 
 	if (i >= MLX5_MAX_PORTS)
 		ldev->flags |= MLX5_LAG_FLAG_READY;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c08315b..ca6f2fc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1368,8 +1368,10 @@
 			 MLX5_COREDEV_VF : MLX5_COREDEV_PF;
 
 	dev->priv.adev_idx = mlx5_adev_idx_alloc();
-	if (dev->priv.adev_idx < 0)
-		return dev->priv.adev_idx;
+	if (dev->priv.adev_idx < 0) {
+		err = dev->priv.adev_idx;
+		goto adev_init_err;
+	}
 
 	err = mlx5_mdev_init(dev, prof_sel);
 	if (err)
@@ -1403,6 +1405,7 @@
 	mlx5_mdev_uninit(dev);
 mdev_init_err:
 	mlx5_adev_idx_free(dev->priv.adev_idx);
+adev_init_err:
 	mlx5_devlink_free(devlink);
 
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index 0fc7de4a..8e0dddc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -116,7 +116,7 @@
 static void mlx5_rdma_del_roce_addr(struct mlx5_core_dev *dev)
 {
 	mlx5_core_roce_gid_set(dev, 0, 0, 0,
-			       NULL, NULL, false, 0, 0);
+			       NULL, NULL, false, 0, 1);
 }
 
 static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *gid)
diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c
index 776b7d2..2289e1f 100644
--- a/drivers/net/ethernet/natsemi/macsonic.c
+++ b/drivers/net/ethernet/natsemi/macsonic.c
@@ -506,10 +506,14 @@
 
 	err = register_netdev(dev);
 	if (err)
-		goto out;
+		goto undo_probe;
 
 	return 0;
 
+undo_probe:
+	dma_free_coherent(lp->device,
+			  SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+			  lp->descriptors, lp->descriptors_laddr);
 out:
 	free_netdev(dev);
 
@@ -584,12 +588,16 @@
 
 	err = register_netdev(ndev);
 	if (err)
-		goto out;
+		goto undo_probe;
 
 	nubus_set_drvdata(board, ndev);
 
 	return 0;
 
+undo_probe:
+	dma_free_coherent(lp->device,
+			  SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+			  lp->descriptors, lp->descriptors_laddr);
 out:
 	free_netdev(ndev);
 	return err;
diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c
index afa166f..28d9e98 100644
--- a/drivers/net/ethernet/natsemi/xtsonic.c
+++ b/drivers/net/ethernet/natsemi/xtsonic.c
@@ -229,11 +229,14 @@
 	sonic_msg_init(dev);
 
 	if ((err = register_netdev(dev)))
-		goto out1;
+		goto undo_probe1;
 
 	return 0;
 
-out1:
+undo_probe1:
+	dma_free_coherent(lp->device,
+			  SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+			  lp->descriptors, lp->descriptors_laddr);
 	release_region(dev->base_addr, SONIC_MEM_SIZE);
 out:
 	free_netdev(dev);
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index 4366c7a..6b5ddb0 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -78,6 +78,7 @@
 	depends on PCI
 	select ZLIB_INFLATE
 	select CRC8
+	select CRC32
 	select NET_DEVLINK
 	help
 	  This enables the support for Marvell FastLinQ adapters family.
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 58e0511..a5e0eff 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -64,6 +64,7 @@
  * @variant:	reference to the current board variant
  * @regmap:	regmap for using the syscon
  * @internal_phy_powered: Does the internal PHY is enabled
+ * @use_internal_phy: Is the internal PHY selected for use
  * @mux_handle:	Internal pointer used by mdio-mux lib
  */
 struct sunxi_priv_data {
@@ -74,6 +75,7 @@
 	const struct emac_variant *variant;
 	struct regmap_field *regmap_field;
 	bool internal_phy_powered;
+	bool use_internal_phy;
 	void *mux_handle;
 };
 
@@ -539,8 +541,11 @@
 	.dma_interrupt = sun8i_dwmac_dma_interrupt,
 };
 
+static int sun8i_dwmac_power_internal_phy(struct stmmac_priv *priv);
+
 static int sun8i_dwmac_init(struct platform_device *pdev, void *priv)
 {
+	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct sunxi_priv_data *gmac = priv;
 	int ret;
 
@@ -554,13 +559,25 @@
 
 	ret = clk_prepare_enable(gmac->tx_clk);
 	if (ret) {
-		if (gmac->regulator)
-			regulator_disable(gmac->regulator);
 		dev_err(&pdev->dev, "Could not enable AHB clock\n");
-		return ret;
+		goto err_disable_regulator;
+	}
+
+	if (gmac->use_internal_phy) {
+		ret = sun8i_dwmac_power_internal_phy(netdev_priv(ndev));
+		if (ret)
+			goto err_disable_clk;
 	}
 
 	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(gmac->tx_clk);
+err_disable_regulator:
+	if (gmac->regulator)
+		regulator_disable(gmac->regulator);
+
+	return ret;
 }
 
 static void sun8i_dwmac_core_init(struct mac_device_info *hw,
@@ -831,7 +848,6 @@
 	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
 	u32 reg, val;
 	int ret = 0;
-	bool need_power_ephy = false;
 
 	if (current_child ^ desired_child) {
 		regmap_field_read(gmac->regmap_field, &reg);
@@ -839,13 +855,12 @@
 		case DWMAC_SUN8I_MDIO_MUX_INTERNAL_ID:
 			dev_info(priv->device, "Switch mux to internal PHY");
 			val = (reg & ~H3_EPHY_MUX_MASK) | H3_EPHY_SELECT;
-
-			need_power_ephy = true;
+			gmac->use_internal_phy = true;
 			break;
 		case DWMAC_SUN8I_MDIO_MUX_EXTERNAL_ID:
 			dev_info(priv->device, "Switch mux to external PHY");
 			val = (reg & ~H3_EPHY_MUX_MASK) | H3_EPHY_SHUTDOWN;
-			need_power_ephy = false;
+			gmac->use_internal_phy = false;
 			break;
 		default:
 			dev_err(priv->device, "Invalid child ID %x\n",
@@ -853,7 +868,7 @@
 			return -EINVAL;
 		}
 		regmap_field_write(gmac->regmap_field, val);
-		if (need_power_ephy) {
+		if (gmac->use_internal_phy) {
 			ret = sun8i_dwmac_power_internal_phy(priv);
 			if (ret)
 				return ret;
@@ -883,22 +898,23 @@
 	return ret;
 }
 
-static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
+static int sun8i_dwmac_set_syscon(struct device *dev,
+				  struct plat_stmmacenet_data *plat)
 {
-	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
-	struct device_node *node = priv->device->of_node;
+	struct sunxi_priv_data *gmac = plat->bsp_priv;
+	struct device_node *node = dev->of_node;
 	int ret;
 	u32 reg, val;
 
 	ret = regmap_field_read(gmac->regmap_field, &val);
 	if (ret) {
-		dev_err(priv->device, "Fail to read from regmap field.\n");
+		dev_err(dev, "Fail to read from regmap field.\n");
 		return ret;
 	}
 
 	reg = gmac->variant->default_syscon_value;
 	if (reg != val)
-		dev_warn(priv->device,
+		dev_warn(dev,
 			 "Current syscon value is not the default %x (expect %x)\n",
 			 val, reg);
 
@@ -911,9 +927,9 @@
 		/* Force EPHY xtal frequency to 24MHz. */
 		reg |= H3_EPHY_CLK_SEL;
 
-		ret = of_mdio_parse_addr(priv->device, priv->plat->phy_node);
+		ret = of_mdio_parse_addr(dev, plat->phy_node);
 		if (ret < 0) {
-			dev_err(priv->device, "Could not parse MDIO addr\n");
+			dev_err(dev, "Could not parse MDIO addr\n");
 			return ret;
 		}
 		/* of_mdio_parse_addr returns a valid (0 ~ 31) PHY
@@ -929,17 +945,17 @@
 
 	if (!of_property_read_u32(node, "allwinner,tx-delay-ps", &val)) {
 		if (val % 100) {
-			dev_err(priv->device, "tx-delay must be a multiple of 100\n");
+			dev_err(dev, "tx-delay must be a multiple of 100\n");
 			return -EINVAL;
 		}
 		val /= 100;
-		dev_dbg(priv->device, "set tx-delay to %x\n", val);
+		dev_dbg(dev, "set tx-delay to %x\n", val);
 		if (val <= gmac->variant->tx_delay_max) {
 			reg &= ~(gmac->variant->tx_delay_max <<
 				 SYSCON_ETXDC_SHIFT);
 			reg |= (val << SYSCON_ETXDC_SHIFT);
 		} else {
-			dev_err(priv->device, "Invalid TX clock delay: %d\n",
+			dev_err(dev, "Invalid TX clock delay: %d\n",
 				val);
 			return -EINVAL;
 		}
@@ -947,17 +963,17 @@
 
 	if (!of_property_read_u32(node, "allwinner,rx-delay-ps", &val)) {
 		if (val % 100) {
-			dev_err(priv->device, "rx-delay must be a multiple of 100\n");
+			dev_err(dev, "rx-delay must be a multiple of 100\n");
 			return -EINVAL;
 		}
 		val /= 100;
-		dev_dbg(priv->device, "set rx-delay to %x\n", val);
+		dev_dbg(dev, "set rx-delay to %x\n", val);
 		if (val <= gmac->variant->rx_delay_max) {
 			reg &= ~(gmac->variant->rx_delay_max <<
 				 SYSCON_ERXDC_SHIFT);
 			reg |= (val << SYSCON_ERXDC_SHIFT);
 		} else {
-			dev_err(priv->device, "Invalid RX clock delay: %d\n",
+			dev_err(dev, "Invalid RX clock delay: %d\n",
 				val);
 			return -EINVAL;
 		}
@@ -968,7 +984,7 @@
 	if (gmac->variant->support_rmii)
 		reg &= ~SYSCON_RMII_EN;
 
-	switch (priv->plat->interface) {
+	switch (plat->interface) {
 	case PHY_INTERFACE_MODE_MII:
 		/* default */
 		break;
@@ -982,8 +998,8 @@
 		reg |= SYSCON_RMII_EN | SYSCON_ETCS_EXT_GMII;
 		break;
 	default:
-		dev_err(priv->device, "Unsupported interface mode: %s",
-			phy_modes(priv->plat->interface));
+		dev_err(dev, "Unsupported interface mode: %s",
+			phy_modes(plat->interface));
 		return -EINVAL;
 	}
 
@@ -1004,17 +1020,10 @@
 	struct sunxi_priv_data *gmac = priv;
 
 	if (gmac->variant->soc_has_internal_phy) {
-		/* sun8i_dwmac_exit could be called with mdiomux uninit */
-		if (gmac->mux_handle)
-			mdio_mux_uninit(gmac->mux_handle);
 		if (gmac->internal_phy_powered)
 			sun8i_dwmac_unpower_internal_phy(gmac);
 	}
 
-	sun8i_dwmac_unset_syscon(gmac);
-
-	reset_control_put(gmac->rst_ephy);
-
 	clk_disable_unprepare(gmac->tx_clk);
 
 	if (gmac->regulator)
@@ -1049,16 +1058,11 @@
 {
 	struct mac_device_info *mac;
 	struct stmmac_priv *priv = ppriv;
-	int ret;
 
 	mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL);
 	if (!mac)
 		return NULL;
 
-	ret = sun8i_dwmac_set_syscon(priv);
-	if (ret)
-		return NULL;
-
 	mac->pcsr = priv->ioaddr;
 	mac->mac = &sun8i_dwmac_ops;
 	mac->dma = &sun8i_dwmac_dma_ops;
@@ -1134,10 +1138,6 @@
 	if (ret)
 		return ret;
 
-	plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
-	if (IS_ERR(plat_dat))
-		return PTR_ERR(plat_dat);
-
 	gmac = devm_kzalloc(dev, sizeof(*gmac), GFP_KERNEL);
 	if (!gmac)
 		return -ENOMEM;
@@ -1201,11 +1201,15 @@
 	ret = of_get_phy_mode(dev->of_node, &interface);
 	if (ret)
 		return -EINVAL;
-	plat_dat->interface = interface;
+
+	plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
+	if (IS_ERR(plat_dat))
+		return PTR_ERR(plat_dat);
 
 	/* platform data specifying hardware features and callbacks.
 	 * hardware features were copied from Allwinner drivers.
 	 */
+	plat_dat->interface = interface;
 	plat_dat->rx_coe = STMMAC_RX_COE_TYPE2;
 	plat_dat->tx_coe = 1;
 	plat_dat->has_sun8i = true;
@@ -1214,9 +1218,13 @@
 	plat_dat->exit = sun8i_dwmac_exit;
 	plat_dat->setup = sun8i_dwmac_setup;
 
+	ret = sun8i_dwmac_set_syscon(&pdev->dev, plat_dat);
+	if (ret)
+		goto dwmac_deconfig;
+
 	ret = sun8i_dwmac_init(pdev, plat_dat->bsp_priv);
 	if (ret)
-		return ret;
+		goto dwmac_syscon;
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
@@ -1230,7 +1238,7 @@
 	if (gmac->variant->soc_has_internal_phy) {
 		ret = get_ephy_nodes(priv);
 		if (ret)
-			goto dwmac_exit;
+			goto dwmac_remove;
 		ret = sun8i_dwmac_register_mdio_mux(priv);
 		if (ret) {
 			dev_err(&pdev->dev, "Failed to register mux\n");
@@ -1239,15 +1247,42 @@
 	} else {
 		ret = sun8i_dwmac_reset(priv);
 		if (ret)
-			goto dwmac_exit;
+			goto dwmac_remove;
 	}
 
 	return ret;
 dwmac_mux:
-	sun8i_dwmac_unset_syscon(gmac);
+	reset_control_put(gmac->rst_ephy);
+	clk_put(gmac->ephy_clk);
+dwmac_remove:
+	stmmac_dvr_remove(&pdev->dev);
 dwmac_exit:
+	sun8i_dwmac_exit(pdev, gmac);
+dwmac_syscon:
+	sun8i_dwmac_unset_syscon(gmac);
+dwmac_deconfig:
+	stmmac_remove_config_dt(pdev, plat_dat);
+
+	return ret;
+}
+
+static int sun8i_dwmac_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
+
+	if (gmac->variant->soc_has_internal_phy) {
+		mdio_mux_uninit(gmac->mux_handle);
+		sun8i_dwmac_unpower_internal_phy(gmac);
+		reset_control_put(gmac->rst_ephy);
+		clk_put(gmac->ephy_clk);
+	}
+
 	stmmac_pltfr_remove(pdev);
-return ret;
+	sun8i_dwmac_unset_syscon(gmac);
+
+	return 0;
 }
 
 static const struct of_device_id sun8i_dwmac_match[] = {
@@ -1269,7 +1304,7 @@
 
 static struct platform_driver sun8i_dwmac_driver = {
 	.probe  = sun8i_dwmac_probe,
-	.remove = stmmac_pltfr_remove,
+	.remove = sun8i_dwmac_remove,
 	.driver = {
 		.name           = "dwmac-sun8i",
 		.pm		= &stmmac_pltfr_pm_ops,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 3b816a4..5a78848 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1199,7 +1199,10 @@
 	 * accordingly. Otherwise, we should check here.
 	 */
 	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)
-		delayed_ndp_size = ALIGN(ctx->max_ndp_size, ctx->tx_ndp_modulus);
+		delayed_ndp_size = ctx->max_ndp_size +
+			max_t(u32,
+			      ctx->tx_ndp_modulus,
+			      ctx->tx_modulus + ctx->tx_remainder) - 1;
 	else
 		delayed_ndp_size = 0;
 
@@ -1410,7 +1413,8 @@
 	if (!(dev->driver_info->flags & FLAG_SEND_ZLP) &&
 	    skb_out->len > ctx->min_tx_pkt) {
 		padding_count = ctx->tx_curr_size - skb_out->len;
-		skb_put_zero(skb_out, padding_count);
+		if (!WARN_ON(padding_count > ctx->tx_curr_size))
+			skb_put_zero(skb_out, padding_count);
 	} else if (skb_out->len < ctx->tx_curr_size &&
 		   (skb_out->len % dev->maxpacket) == 0) {
 		skb_put_u8(skb_out, 0);	/* force short packet */
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index 4029fde..83c9481 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -282,6 +282,7 @@
 	tristate "Slic Maxim ds26522 card support"
 	depends on SPI
 	depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE || COMPILE_TEST
+	select BITREVERSE
 	help
 	  This module initializes and configures the slic maxim card
 	  in T1 or E1 mode.
diff --git a/drivers/net/wireless/ath/wil6210/Kconfig b/drivers/net/wireless/ath/wil6210/Kconfig
index 6a95b19..f074e9c 100644
--- a/drivers/net/wireless/ath/wil6210/Kconfig
+++ b/drivers/net/wireless/ath/wil6210/Kconfig
@@ -2,6 +2,7 @@
 config WIL6210
 	tristate "Wilocity 60g WiFi card wil6210 support"
 	select WANT_DEV_COREDUMP
+	select CRC32
 	depends on CFG80211
 	depends on PCI
 	default n
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 476d7c7..f2edef0 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -64,6 +64,7 @@
 	depends on NETWORK_PHY_TIMESTAMPING
 	depends on PHYLIB
 	depends on PTP_1588_CLOCK
+	select CRC32
 	help
 	  Supports the DP83640 PHYTER with IEEE 1588 features.
 
@@ -78,6 +79,7 @@
 config PTP_1588_CLOCK_INES
 	tristate "ZHAW InES PTP time stamping IP core"
 	depends on NETWORK_PHY_TIMESTAMPING
+	depends on HAS_IOMEM
 	depends on PHYLIB
 	depends on PTP_1588_CLOCK
 	help
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 53fa84f..5abdd29 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -881,6 +881,7 @@
 config REGULATOR_QCOM_RPMH
 	tristate "Qualcomm Technologies, Inc. RPMh regulator driver"
 	depends on QCOM_RPMH || (QCOM_RPMH=n && COMPILE_TEST)
+	depends on QCOM_COMMAND_DB || (QCOM_COMMAND_DB=n && COMPILE_TEST)
 	help
 	  This driver supports control of PMIC regulators via the RPMh hardware
 	  block found on Qualcomm Technologies Inc. SoCs.  RPMh regulator
diff --git a/drivers/regulator/bd718x7-regulator.c b/drivers/regulator/bd718x7-regulator.c
index e6d5d98..9309765 100644
--- a/drivers/regulator/bd718x7-regulator.c
+++ b/drivers/regulator/bd718x7-regulator.c
@@ -15,6 +15,36 @@
 #include <linux/regulator/of_regulator.h>
 #include <linux/slab.h>
 
+/* Typical regulator startup times as per data sheet in uS */
+#define BD71847_BUCK1_STARTUP_TIME 144
+#define BD71847_BUCK2_STARTUP_TIME 162
+#define BD71847_BUCK3_STARTUP_TIME 162
+#define BD71847_BUCK4_STARTUP_TIME 240
+#define BD71847_BUCK5_STARTUP_TIME 270
+#define BD71847_BUCK6_STARTUP_TIME 200
+#define BD71847_LDO1_STARTUP_TIME  440
+#define BD71847_LDO2_STARTUP_TIME  370
+#define BD71847_LDO3_STARTUP_TIME  310
+#define BD71847_LDO4_STARTUP_TIME  400
+#define BD71847_LDO5_STARTUP_TIME  530
+#define BD71847_LDO6_STARTUP_TIME  400
+
+#define BD71837_BUCK1_STARTUP_TIME 160
+#define BD71837_BUCK2_STARTUP_TIME 180
+#define BD71837_BUCK3_STARTUP_TIME 180
+#define BD71837_BUCK4_STARTUP_TIME 180
+#define BD71837_BUCK5_STARTUP_TIME 160
+#define BD71837_BUCK6_STARTUP_TIME 240
+#define BD71837_BUCK7_STARTUP_TIME 220
+#define BD71837_BUCK8_STARTUP_TIME 200
+#define BD71837_LDO1_STARTUP_TIME  440
+#define BD71837_LDO2_STARTUP_TIME  370
+#define BD71837_LDO3_STARTUP_TIME  310
+#define BD71837_LDO4_STARTUP_TIME  400
+#define BD71837_LDO5_STARTUP_TIME  310
+#define BD71837_LDO6_STARTUP_TIME  400
+#define BD71837_LDO7_STARTUP_TIME  530
+
 /*
  * BD718(37/47/50) have two "enable control modes". ON/OFF can either be
  * controlled by software - or by PMIC internal HW state machine. Whether
@@ -613,6 +643,7 @@
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD718XX_REG_BUCK1_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK1_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -646,6 +677,7 @@
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD718XX_REG_BUCK2_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK2_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -680,6 +712,7 @@
 			.linear_range_selectors = bd71847_buck3_volt_range_sel,
 			.enable_reg = BD718XX_REG_1ST_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK3_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -706,6 +739,7 @@
 			.vsel_range_mask = BD71847_BUCK4_RANGE_MASK,
 			.linear_range_selectors = bd71847_buck4_volt_range_sel,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK4_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -727,6 +761,7 @@
 			.vsel_mask = BD718XX_3RD_NODVS_BUCK_MASK,
 			.enable_reg = BD718XX_REG_3RD_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK5_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -750,6 +785,7 @@
 			.vsel_mask = BD718XX_4TH_NODVS_BUCK_MASK,
 			.enable_reg = BD718XX_REG_4TH_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71847_BUCK6_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -775,6 +811,7 @@
 			.linear_range_selectors = bd718xx_ldo1_volt_range_sel,
 			.enable_reg = BD718XX_REG_LDO1_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO1_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -796,6 +833,7 @@
 			.n_voltages = ARRAY_SIZE(ldo_2_volts),
 			.enable_reg = BD718XX_REG_LDO2_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO2_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -818,6 +856,7 @@
 			.vsel_mask = BD718XX_LDO3_MASK,
 			.enable_reg = BD718XX_REG_LDO3_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO3_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -840,6 +879,7 @@
 			.vsel_mask = BD718XX_LDO4_MASK,
 			.enable_reg = BD718XX_REG_LDO4_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO4_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -865,6 +905,7 @@
 			.linear_range_selectors = bd71847_ldo5_volt_range_sel,
 			.enable_reg = BD718XX_REG_LDO5_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO5_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -889,6 +930,7 @@
 			.vsel_mask = BD718XX_LDO6_MASK,
 			.enable_reg = BD718XX_REG_LDO6_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71847_LDO6_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -942,6 +984,7 @@
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD718XX_REG_BUCK1_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK1_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -975,6 +1018,7 @@
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD718XX_REG_BUCK2_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK2_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -1005,6 +1049,7 @@
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD71837_REG_BUCK3_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK3_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -1033,6 +1078,7 @@
 			.vsel_mask = DVS_BUCK_RUN_MASK,
 			.enable_reg = BD71837_REG_BUCK4_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK4_STARTUP_TIME,
 			.owner = THIS_MODULE,
 			.of_parse_cb = buck_set_hw_dvs_levels,
 		},
@@ -1065,6 +1111,7 @@
 			.linear_range_selectors = bd71837_buck5_volt_range_sel,
 			.enable_reg = BD718XX_REG_1ST_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK5_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1088,6 +1135,7 @@
 			.vsel_mask = BD71837_BUCK6_MASK,
 			.enable_reg = BD718XX_REG_2ND_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK6_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1109,6 +1157,7 @@
 			.vsel_mask = BD718XX_3RD_NODVS_BUCK_MASK,
 			.enable_reg = BD718XX_REG_3RD_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK7_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1132,6 +1181,7 @@
 			.vsel_mask = BD718XX_4TH_NODVS_BUCK_MASK,
 			.enable_reg = BD718XX_REG_4TH_NODVS_BUCK_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
+			.enable_time = BD71837_BUCK8_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1157,6 +1207,7 @@
 			.linear_range_selectors = bd718xx_ldo1_volt_range_sel,
 			.enable_reg = BD718XX_REG_LDO1_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO1_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1178,6 +1229,7 @@
 			.n_voltages = ARRAY_SIZE(ldo_2_volts),
 			.enable_reg = BD718XX_REG_LDO2_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO2_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1200,6 +1252,7 @@
 			.vsel_mask = BD718XX_LDO3_MASK,
 			.enable_reg = BD718XX_REG_LDO3_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO3_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1222,6 +1275,7 @@
 			.vsel_mask = BD718XX_LDO4_MASK,
 			.enable_reg = BD718XX_REG_LDO4_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO4_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1246,6 +1300,7 @@
 			.vsel_mask = BD71837_LDO5_MASK,
 			.enable_reg = BD718XX_REG_LDO5_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO5_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1272,6 +1327,7 @@
 			.vsel_mask = BD718XX_LDO6_MASK,
 			.enable_reg = BD718XX_REG_LDO6_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO6_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
@@ -1296,6 +1352,7 @@
 			.vsel_mask = BD71837_LDO7_MASK,
 			.enable_reg = BD71837_REG_LDO7_VOLT,
 			.enable_mask = BD718XX_LDO_EN,
+			.enable_time = BD71837_LDO7_STARTUP_TIME,
 			.owner = THIS_MODULE,
 		},
 		.init = {
diff --git a/drivers/regulator/pf8x00-regulator.c b/drivers/regulator/pf8x00-regulator.c
index 308c27f..af9918c 100644
--- a/drivers/regulator/pf8x00-regulator.c
+++ b/drivers/regulator/pf8x00-regulator.c
@@ -469,13 +469,17 @@
 }
 
 static const struct of_device_id pf8x00_dt_ids[] = {
-	{ .compatible = "nxp,pf8x00",},
+	{ .compatible = "nxp,pf8100",},
+	{ .compatible = "nxp,pf8121a",},
+	{ .compatible = "nxp,pf8200",},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, pf8x00_dt_ids);
 
 static const struct i2c_device_id pf8x00_i2c_id[] = {
-	{ "pf8x00", 0 },
+	{ "pf8100", 0 },
+	{ "pf8121a", 0 },
+	{ "pf8200", 0 },
 	{},
 };
 MODULE_DEVICE_TABLE(i2c, pf8x00_i2c_id);
diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
index fe030ec..c395a8d 100644
--- a/drivers/regulator/qcom-rpmh-regulator.c
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -726,7 +726,7 @@
 static const struct rpmh_vreg_hw_data pmic5_hfsmps515 = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(2800000, 0, 4, 1600),
+	.voltage_range = REGULATOR_LINEAR_RANGE(2800000, 0, 4, 16000),
 	.n_voltages = 5,
 	.pmic_mode_map = pmic_mode_map_pmic5_smps,
 	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 6f5ddc3..28f6370 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -1079,7 +1079,8 @@
 void qeth_set_allowed_threads(struct qeth_card *card, unsigned long threads,
 			      int clear_start_mask);
 int qeth_threads_running(struct qeth_card *, unsigned long);
-int qeth_set_offline(struct qeth_card *card, bool resetting);
+int qeth_set_offline(struct qeth_card *card, const struct qeth_discipline *disc,
+		     bool resetting);
 
 int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *,
 		  int (*reply_cb)
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index f4b6029..cf18d87 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5507,12 +5507,12 @@
 	return rc;
 }
 
-static int qeth_set_online(struct qeth_card *card)
+static int qeth_set_online(struct qeth_card *card,
+			   const struct qeth_discipline *disc)
 {
 	bool carrier_ok;
 	int rc;
 
-	mutex_lock(&card->discipline_mutex);
 	mutex_lock(&card->conf_mutex);
 	QETH_CARD_TEXT(card, 2, "setonlin");
 
@@ -5529,7 +5529,7 @@
 		/* no need for locking / error handling at this early stage: */
 		qeth_set_real_num_tx_queues(card, qeth_tx_actual_queues(card));
 
-	rc = card->discipline->set_online(card, carrier_ok);
+	rc = disc->set_online(card, carrier_ok);
 	if (rc)
 		goto err_online;
 
@@ -5537,7 +5537,6 @@
 	kobject_uevent(&card->gdev->dev.kobj, KOBJ_CHANGE);
 
 	mutex_unlock(&card->conf_mutex);
-	mutex_unlock(&card->discipline_mutex);
 	return 0;
 
 err_online:
@@ -5552,15 +5551,14 @@
 	qdio_free(CARD_DDEV(card));
 
 	mutex_unlock(&card->conf_mutex);
-	mutex_unlock(&card->discipline_mutex);
 	return rc;
 }
 
-int qeth_set_offline(struct qeth_card *card, bool resetting)
+int qeth_set_offline(struct qeth_card *card, const struct qeth_discipline *disc,
+		     bool resetting)
 {
 	int rc, rc2, rc3;
 
-	mutex_lock(&card->discipline_mutex);
 	mutex_lock(&card->conf_mutex);
 	QETH_CARD_TEXT(card, 3, "setoffl");
 
@@ -5581,7 +5579,7 @@
 
 	cancel_work_sync(&card->rx_mode_work);
 
-	card->discipline->set_offline(card);
+	disc->set_offline(card);
 
 	qeth_qdio_clear_card(card, 0);
 	qeth_drain_output_queues(card);
@@ -5602,16 +5600,19 @@
 	kobject_uevent(&card->gdev->dev.kobj, KOBJ_CHANGE);
 
 	mutex_unlock(&card->conf_mutex);
-	mutex_unlock(&card->discipline_mutex);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(qeth_set_offline);
 
 static int qeth_do_reset(void *data)
 {
+	const struct qeth_discipline *disc;
 	struct qeth_card *card = data;
 	int rc;
 
+	/* Lock-free, other users will block until we are done. */
+	disc = card->discipline;
+
 	QETH_CARD_TEXT(card, 2, "recover1");
 	if (!qeth_do_run_thread(card, QETH_RECOVER_THREAD))
 		return 0;
@@ -5619,8 +5620,8 @@
 	dev_warn(&card->gdev->dev,
 		 "A recovery process has been started for the device\n");
 
-	qeth_set_offline(card, true);
-	rc = qeth_set_online(card);
+	qeth_set_offline(card, disc, true);
+	rc = qeth_set_online(card, disc);
 	if (!rc) {
 		dev_info(&card->gdev->dev,
 			 "Device successfully recovered!\n");
@@ -6584,6 +6585,7 @@
 		break;
 	default:
 		card->info.layer_enforced = true;
+		/* It's so early that we don't need the discipline_mutex yet. */
 		rc = qeth_core_load_discipline(card, enforced_disc);
 		if (rc)
 			goto err_load;
@@ -6616,10 +6618,12 @@
 
 	QETH_CARD_TEXT(card, 2, "removedv");
 
+	mutex_lock(&card->discipline_mutex);
 	if (card->discipline) {
 		card->discipline->remove(gdev);
 		qeth_core_free_discipline(card);
 	}
+	mutex_unlock(&card->discipline_mutex);
 
 	qeth_free_qdio_queues(card);
 
@@ -6634,6 +6638,7 @@
 	int rc = 0;
 	enum qeth_discipline_id def_discipline;
 
+	mutex_lock(&card->discipline_mutex);
 	if (!card->discipline) {
 		def_discipline = IS_IQD(card) ? QETH_DISCIPLINE_LAYER3 :
 						QETH_DISCIPLINE_LAYER2;
@@ -6647,16 +6652,23 @@
 		}
 	}
 
-	rc = qeth_set_online(card);
+	rc = qeth_set_online(card, card->discipline);
+
 err:
+	mutex_unlock(&card->discipline_mutex);
 	return rc;
 }
 
 static int qeth_core_set_offline(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+	int rc;
 
-	return qeth_set_offline(card, false);
+	mutex_lock(&card->discipline_mutex);
+	rc = qeth_set_offline(card, card->discipline, false);
+	mutex_unlock(&card->discipline_mutex);
+
+	return rc;
 }
 
 static void qeth_core_shutdown(struct ccwgroup_device *gdev)
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 4ed0fb0..4254caf 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -2208,7 +2208,7 @@
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 
 	if (gdev->state == CCWGROUP_ONLINE)
-		qeth_set_offline(card, false);
+		qeth_set_offline(card, card->discipline, false);
 
 	cancel_work_sync(&card->close_dev_work);
 	if (card->dev->reg_state == NETREG_REGISTERED)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index d138ac4..4c2cae7 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1813,7 +1813,7 @@
 						    struct net_device *dev,
 						    netdev_features_t features)
 {
-	if (qeth_get_ip_version(skb) != 4)
+	if (vlan_get_protocol(skb) != htons(ETH_P_IP))
 		features &= ~NETIF_F_HW_VLAN_CTAG_TX;
 	return qeth_features_check(skb, dev, features);
 }
@@ -1971,7 +1971,7 @@
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 
 	if (cgdev->state == CCWGROUP_ONLINE)
-		qeth_set_offline(card, false);
+		qeth_set_offline(card, card->discipline, false);
 
 	cancel_work_sync(&card->close_dev_work);
 	if (card->dev->reg_state == NETREG_REGISTERED)
diff --git a/drivers/spi/spi-altera.c b/drivers/spi/spi-altera.c
index 809bfff..cbc4c28 100644
--- a/drivers/spi/spi-altera.c
+++ b/drivers/spi/spi-altera.c
@@ -189,24 +189,26 @@
 
 		/* send the first byte */
 		altera_spi_tx_word(hw);
-	} else {
-		while (hw->count < hw->len) {
-			altera_spi_tx_word(hw);
 
-			for (;;) {
-				altr_spi_readl(hw, ALTERA_SPI_STATUS, &val);
-				if (val & ALTERA_SPI_STATUS_RRDY_MSK)
-					break;
-
-				cpu_relax();
-			}
-
-			altera_spi_rx_word(hw);
-		}
-		spi_finalize_current_transfer(master);
+		return 1;
 	}
 
-	return t->len;
+	while (hw->count < hw->len) {
+		altera_spi_tx_word(hw);
+
+		for (;;) {
+			altr_spi_readl(hw, ALTERA_SPI_STATUS, &val);
+			if (val & ALTERA_SPI_STATUS_RRDY_MSK)
+				break;
+
+			cpu_relax();
+		}
+
+		altera_spi_rx_word(hw);
+	}
+	spi_finalize_current_transfer(master);
+
+	return 0;
 }
 
 static irqreturn_t altera_spi_irq(int irq, void *dev)
diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index 512e925..881f645 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -83,6 +83,7 @@
 	spinlock_t lock;
 	int irq;
 	bool cs_flag;
+	bool abort_failed;
 };
 
 static int get_spi_clk_cfg(unsigned int speed_hz,
@@ -141,8 +142,49 @@
 	spin_unlock_irq(&mas->lock);
 
 	time_left = wait_for_completion_timeout(&mas->abort_done, HZ);
-	if (!time_left)
+	if (!time_left) {
 		dev_err(mas->dev, "Failed to cancel/abort m_cmd\n");
+
+		/*
+		 * No need for a lock since SPI core has a lock and we never
+		 * access this from an interrupt.
+		 */
+		mas->abort_failed = true;
+	}
+}
+
+static bool spi_geni_is_abort_still_pending(struct spi_geni_master *mas)
+{
+	struct geni_se *se = &mas->se;
+	u32 m_irq, m_irq_en;
+
+	if (!mas->abort_failed)
+		return false;
+
+	/*
+	 * The only known case where a transfer times out and then a cancel
+	 * times out then an abort times out is if something is blocking our
+	 * interrupt handler from running.  Avoid starting any new transfers
+	 * until that sorts itself out.
+	 */
+	spin_lock_irq(&mas->lock);
+	m_irq = readl(se->base + SE_GENI_M_IRQ_STATUS);
+	m_irq_en = readl(se->base + SE_GENI_M_IRQ_EN);
+	spin_unlock_irq(&mas->lock);
+
+	if (m_irq & m_irq_en) {
+		dev_err(mas->dev, "Interrupts pending after abort: %#010x\n",
+			m_irq & m_irq_en);
+		return true;
+	}
+
+	/*
+	 * If we're here the problem resolved itself so no need to check more
+	 * on future transfers.
+	 */
+	mas->abort_failed = false;
+
+	return false;
 }
 
 static void spi_geni_set_cs(struct spi_device *slv, bool set_flag)
@@ -158,10 +200,21 @@
 	if (set_flag == mas->cs_flag)
 		return;
 
-	mas->cs_flag = set_flag;
-
 	pm_runtime_get_sync(mas->dev);
+
+	if (spi_geni_is_abort_still_pending(mas)) {
+		dev_err(mas->dev, "Can't set chip select\n");
+		goto exit;
+	}
+
 	spin_lock_irq(&mas->lock);
+	if (mas->cur_xfer) {
+		dev_err(mas->dev, "Can't set CS when prev xfer running\n");
+		spin_unlock_irq(&mas->lock);
+		goto exit;
+	}
+
+	mas->cs_flag = set_flag;
 	reinit_completion(&mas->cs_done);
 	if (set_flag)
 		geni_se_setup_m_cmd(se, SPI_CS_ASSERT, 0);
@@ -170,9 +223,12 @@
 	spin_unlock_irq(&mas->lock);
 
 	time_left = wait_for_completion_timeout(&mas->cs_done, HZ);
-	if (!time_left)
+	if (!time_left) {
+		dev_warn(mas->dev, "Timeout setting chip select\n");
 		handle_fifo_timeout(spi, NULL);
+	}
 
+exit:
 	pm_runtime_put(mas->dev);
 }
 
@@ -280,6 +336,9 @@
 	int ret;
 	struct spi_geni_master *mas = spi_master_get_devdata(spi);
 
+	if (spi_geni_is_abort_still_pending(mas))
+		return -EBUSY;
+
 	ret = setup_fifo_params(spi_msg->spi, spi);
 	if (ret)
 		dev_err(mas->dev, "Couldn't select mode %d\n", ret);
@@ -354,6 +413,12 @@
 	unsigned int bytes_per_fifo_word = geni_byte_per_fifo_word(mas);
 	unsigned int i = 0;
 
+	/* Stop the watermark IRQ if nothing to send */
+	if (!mas->cur_xfer) {
+		writel(0, se->base + SE_GENI_TX_WATERMARK_REG);
+		return false;
+	}
+
 	max_bytes = (mas->tx_fifo_depth - mas->tx_wm) * bytes_per_fifo_word;
 	if (mas->tx_rem_bytes < max_bytes)
 		max_bytes = mas->tx_rem_bytes;
@@ -396,6 +461,14 @@
 		if (rx_last_byte_valid && rx_last_byte_valid < 4)
 			rx_bytes -= bytes_per_fifo_word - rx_last_byte_valid;
 	}
+
+	/* Clear out the FIFO and bail if nowhere to put it */
+	if (!mas->cur_xfer) {
+		for (i = 0; i < DIV_ROUND_UP(rx_bytes, bytes_per_fifo_word); i++)
+			readl(se->base + SE_GENI_RX_FIFOn);
+		return;
+	}
+
 	if (mas->rx_rem_bytes < rx_bytes)
 		rx_bytes = mas->rx_rem_bytes;
 
@@ -495,6 +568,9 @@
 {
 	struct spi_geni_master *mas = spi_master_get_devdata(spi);
 
+	if (spi_geni_is_abort_still_pending(mas))
+		return -EBUSY;
+
 	/* Terminate and return success for 0 byte length transfer */
 	if (!xfer->len)
 		return 0;
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index 471dedf..6017209 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -493,9 +493,9 @@
 
 	/* align packet size with data registers access */
 	if (spi->cur_bpw > 8)
-		fthlv -= (fthlv % 2); /* multiple of 2 */
+		fthlv += (fthlv % 2) ? 1 : 0;
 	else
-		fthlv -= (fthlv % 4); /* multiple of 4 */
+		fthlv += (fthlv % 4) ? (4 - (fthlv % 4)) : 0;
 
 	if (!fthlv)
 		fthlv = 1;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 51d7c00..720ab34 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1108,6 +1108,7 @@
 {
 	struct spi_statistics *statm = &ctlr->statistics;
 	struct spi_statistics *stats = &msg->spi->statistics;
+	u32 speed_hz = xfer->speed_hz;
 	unsigned long long ms;
 
 	if (spi_controller_is_slave(ctlr)) {
@@ -1116,8 +1117,11 @@
 			return -EINTR;
 		}
 	} else {
+		if (!speed_hz)
+			speed_hz = 100000;
+
 		ms = 8LL * 1000LL * xfer->len;
-		do_div(ms, xfer->speed_hz);
+		do_div(ms, speed_hz);
 		ms += ms + 200; /* some tolerance */
 
 		if (ms > UINT_MAX)
@@ -3378,8 +3382,9 @@
 	if (status)
 		return status;
 
-	if (!spi->max_speed_hz ||
-	    spi->max_speed_hz > spi->controller->max_speed_hz)
+	if (spi->controller->max_speed_hz &&
+	    (!spi->max_speed_hz ||
+	     spi->max_speed_hz > spi->controller->max_speed_hz))
 		spi->max_speed_hz = spi->controller->max_speed_hz;
 
 	mutex_lock(&spi->controller->io_mutex);
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index 47a6e42..e15cd6b 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -401,6 +401,20 @@
 	help
 	  FDC channel number to use for KGDB.
 
+config NULL_TTY
+	tristate "NULL TTY driver"
+	help
+	  Say Y here if you want a NULL TTY which simply discards messages.
+
+	  This is useful to allow userspace applications which expect a console
+	  device to work without modifications even when no console is
+	  available or desired.
+
+	  In order to use this driver, you should redirect the console to this
+	  TTY, or boot the kernel with console=ttynull.
+
+	  If unsure, say N.
+
 config TRACE_ROUTER
 	tristate "Trace data router for MIPI P1149.7 cJTAG standard"
 	depends on TRACE_SINK
diff --git a/drivers/tty/Makefile b/drivers/tty/Makefile
index 3c1c5a9..b3ccae9 100644
--- a/drivers/tty/Makefile
+++ b/drivers/tty/Makefile
@@ -2,7 +2,7 @@
 obj-$(CONFIG_TTY)		+= tty_io.o n_tty.o tty_ioctl.o tty_ldisc.o \
 				   tty_buffer.o tty_port.o tty_mutex.o \
 				   tty_ldsem.o tty_baudrate.o tty_jobctrl.o \
-				   n_null.o ttynull.o
+				   n_null.o
 obj-$(CONFIG_LEGACY_PTYS)	+= pty.o
 obj-$(CONFIG_UNIX98_PTYS)	+= pty.o
 obj-$(CONFIG_AUDIT)		+= tty_audit.o
@@ -25,6 +25,7 @@
 obj-$(CONFIG_MOXA_INTELLIO)	+= moxa.o
 obj-$(CONFIG_MOXA_SMARTIO)	+= mxser.o
 obj-$(CONFIG_NOZOMI)		+= nozomi.o
+obj-$(CONFIG_NULL_TTY)	        += ttynull.o
 obj-$(CONFIG_ROCKETPORT)	+= rocket.o
 obj-$(CONFIG_SYNCLINK_GT)	+= synclink_gt.o
 obj-$(CONFIG_PPC_EPAPR_HV_BYTECHAN) += ehv_bytechan.o
diff --git a/drivers/tty/ttynull.c b/drivers/tty/ttynull.c
index eced70e..17f05b7 100644
--- a/drivers/tty/ttynull.c
+++ b/drivers/tty/ttynull.c
@@ -2,13 +2,6 @@
 /*
  * Copyright (C) 2019 Axis Communications AB
  *
- * The console is useful for userspace applications which expect a console
- * device to work without modifications even when no console is available
- * or desired.
- *
- * In order to use this driver, you should redirect the console to this
- * TTY, or boot the kernel with console=ttynull.
- *
  * Based on ttyprintk.c:
  *  Copyright (C) 2010 Samo Pogacnik
  */
@@ -66,17 +59,6 @@
 	.device = ttynull_device,
 };
 
-void __init register_ttynull_console(void)
-{
-	if (!ttynull_driver)
-		return;
-
-	if (add_preferred_console(ttynull_console.name, 0, NULL))
-		return;
-
-	register_console(&ttynull_console);
-}
-
 static int __init ttynull_init(void)
 {
 	struct tty_driver *driver;
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index a483cec..5e78fb7 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -30,7 +30,12 @@
 #define VHOST_VSOCK_PKT_WEIGHT 256
 
 enum {
-	VHOST_VSOCK_FEATURES = VHOST_FEATURES,
+	VHOST_VSOCK_FEATURES = VHOST_FEATURES |
+			       (1ULL << VIRTIO_F_ACCESS_PLATFORM)
+};
+
+enum {
+	VHOST_VSOCK_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2)
 };
 
 /* Used to track all the vhost_vsock instances on the system. */
@@ -94,6 +99,9 @@
 	if (!vhost_vq_get_backend(vq))
 		goto out;
 
+	if (!vq_meta_prefetch(vq))
+		goto out;
+
 	/* Avoid further vmexits, we're already processing the virtqueue */
 	vhost_disable_notify(&vsock->dev, vq);
 
@@ -449,6 +457,9 @@
 	if (!vhost_vq_get_backend(vq))
 		goto out;
 
+	if (!vq_meta_prefetch(vq))
+		goto out;
+
 	vhost_disable_notify(&vsock->dev, vq);
 	do {
 		u32 len;
@@ -766,8 +777,12 @@
 	mutex_lock(&vsock->dev.mutex);
 	if ((features & (1 << VHOST_F_LOG_ALL)) &&
 	    !vhost_log_access_ok(&vsock->dev)) {
-		mutex_unlock(&vsock->dev.mutex);
-		return -EFAULT;
+		goto err;
+	}
+
+	if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) {
+		if (vhost_init_device_iotlb(&vsock->dev, true))
+			goto err;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
@@ -778,6 +793,10 @@
 	}
 	mutex_unlock(&vsock->dev.mutex);
 	return 0;
+
+err:
+	mutex_unlock(&vsock->dev.mutex);
+	return -EFAULT;
 }
 
 static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
@@ -811,6 +830,18 @@
 		if (copy_from_user(&features, argp, sizeof(features)))
 			return -EFAULT;
 		return vhost_vsock_set_features(vsock, features);
+	case VHOST_GET_BACKEND_FEATURES:
+		features = VHOST_VSOCK_BACKEND_FEATURES;
+		if (copy_to_user(argp, &features, sizeof(features)))
+			return -EFAULT;
+		return 0;
+	case VHOST_SET_BACKEND_FEATURES:
+		if (copy_from_user(&features, argp, sizeof(features)))
+			return -EFAULT;
+		if (features & ~VHOST_VSOCK_BACKEND_FEATURES)
+			return -EOPNOTSUPP;
+		vhost_set_backend_features(&vsock->dev, features);
+		return 0;
 	default:
 		mutex_lock(&vsock->dev.mutex);
 		r = vhost_dev_ioctl(&vsock->dev, ioctl, argp);
@@ -823,6 +854,34 @@
 	}
 }
 
+static ssize_t vhost_vsock_chr_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct vhost_vsock *vsock = file->private_data;
+	struct vhost_dev *dev = &vsock->dev;
+	int noblock = file->f_flags & O_NONBLOCK;
+
+	return vhost_chr_read_iter(dev, to, noblock);
+}
+
+static ssize_t vhost_vsock_chr_write_iter(struct kiocb *iocb,
+					struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct vhost_vsock *vsock = file->private_data;
+	struct vhost_dev *dev = &vsock->dev;
+
+	return vhost_chr_write_iter(dev, from);
+}
+
+static __poll_t vhost_vsock_chr_poll(struct file *file, poll_table *wait)
+{
+	struct vhost_vsock *vsock = file->private_data;
+	struct vhost_dev *dev = &vsock->dev;
+
+	return vhost_chr_poll(file, dev, wait);
+}
+
 static const struct file_operations vhost_vsock_fops = {
 	.owner          = THIS_MODULE,
 	.open           = vhost_vsock_dev_open,
@@ -830,6 +889,9 @@
 	.llseek		= noop_llseek,
 	.unlocked_ioctl = vhost_vsock_dev_ioctl,
 	.compat_ioctl   = compat_ptr_ioctl,
+	.read_iter      = vhost_vsock_chr_read_iter,
+	.write_iter     = vhost_vsock_chr_write_iter,
+	.poll           = vhost_vsock_chr_poll,
 };
 
 static struct miscdevice vhost_vsock_misc = {
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 555cbce..d9bf53d 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -42,6 +42,15 @@
 	 * to an inode.
 	 */
 	BTRFS_INODE_NO_XATTRS,
+	/*
+	 * Set when we are in a context where we need to start a transaction and
+	 * have dirty pages with the respective file range locked. This is to
+	 * ensure that when reserving space for the transaction, if we are low
+	 * on available space and need to flush delalloc, we will not flush
+	 * delalloc for this inode, because that could result in a deadlock (on
+	 * the file range, inode's io_tree).
+	 */
+	BTRFS_INODE_NO_DELALLOC_FLUSH,
 };
 
 /* in memory btrfs inode */
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 0781089..cc89b63 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2555,8 +2555,14 @@
  * @p:		Holds all btree nodes along the search path
  * @root:	The root node of the tree
  * @key:	The key we are looking for
- * @ins_len:	Indicates purpose of search, for inserts it is 1, for
- *		deletions it's -1. 0 for plain searches
+ * @ins_len:	Indicates purpose of search:
+ *              >0  for inserts it's size of item inserted (*)
+ *              <0  for deletions
+ *               0  for plain searches, not modifying the tree
+ *
+ *              (*) If size of item inserted doesn't include
+ *              sizeof(struct btrfs_item), then p->search_for_extension must
+ *              be set.
  * @cow:	boolean should CoW operations be performed. Must always be 1
  *		when modifying the tree.
  *
@@ -2717,6 +2723,20 @@
 
 		if (level == 0) {
 			p->slots[level] = slot;
+			/*
+			 * Item key already exists. In this case, if we are
+			 * allowed to insert the item (for example, in dir_item
+			 * case, item key collision is allowed), it will be
+			 * merged with the original item. Only the item size
+			 * grows, no new btrfs item will be added. If
+			 * search_for_extension is not set, ins_len already
+			 * accounts the size btrfs_item, deduct it here so leaf
+			 * space check will be correct.
+			 */
+			if (ret == 0 && ins_len > 0 && !p->search_for_extension) {
+				ASSERT(ins_len >= sizeof(struct btrfs_item));
+				ins_len -= sizeof(struct btrfs_item);
+			}
 			if (ins_len > 0 &&
 			    btrfs_leaf_free_space(b) < ins_len) {
 				if (write_lock_level < 1) {
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 1d3c1e4..e6e3759 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -131,6 +131,8 @@
 	 * defrag
 	 */
 	BTRFS_FS_STATE_REMOUNTING,
+	/* Filesystem in RO mode */
+	BTRFS_FS_STATE_RO,
 	/* Track if a transaction abort has been reported on this filesystem */
 	BTRFS_FS_STATE_TRANS_ABORTED,
 	/*
@@ -367,6 +369,12 @@
 	unsigned int search_commit_root:1;
 	unsigned int need_commit_sem:1;
 	unsigned int skip_release_on_error:1;
+	/*
+	 * Indicate that new item (btrfs_search_slot) is extending already
+	 * existing item and ins_len contains only the data size and not item
+	 * header (ie. sizeof(struct btrfs_item) is not included).
+	 */
+	unsigned int search_for_extension:1;
 };
 #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \
 					sizeof(struct btrfs_item))
@@ -2885,10 +2893,26 @@
  * If we remount the fs to be R/O or umount the fs, the cleaner needn't do
  * anything except sleeping. This function is used to check the status of
  * the fs.
+ * We check for BTRFS_FS_STATE_RO to avoid races with a concurrent remount,
+ * since setting and checking for SB_RDONLY in the superblock's flags is not
+ * atomic.
  */
 static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info)
 {
-	return fs_info->sb->s_flags & SB_RDONLY || btrfs_fs_closing(fs_info);
+	return test_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state) ||
+		btrfs_fs_closing(fs_info);
+}
+
+static inline void btrfs_set_sb_rdonly(struct super_block *sb)
+{
+	sb->s_flags |= SB_RDONLY;
+	set_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state);
+}
+
+static inline void btrfs_clear_sb_rdonly(struct super_block *sb)
+{
+	sb->s_flags &= ~SB_RDONLY;
+	clear_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state);
 }
 
 /* tree mod log functions from ctree.c */
@@ -3073,7 +3097,8 @@
 			       u32 min_type);
 
 int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr);
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
+			       bool in_reclaim_context);
 int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 			      unsigned int extra_bits,
 			      struct extent_state **cached_state);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index a98e33f..324f646 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -715,7 +715,7 @@
 	 * flush all outstanding I/O and inode extent mappings before the
 	 * copy operation is declared as being finished
 	 */
-	ret = btrfs_start_delalloc_roots(fs_info, U64_MAX);
+	ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false);
 	if (ret) {
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return ret;
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 1db966b..2b8383d 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -199,16 +199,15 @@
 static struct btrfs_block_group *peek_discard_list(
 					struct btrfs_discard_ctl *discard_ctl,
 					enum btrfs_discard_state *discard_state,
-					int *discard_index)
+					int *discard_index, u64 now)
 {
 	struct btrfs_block_group *block_group;
-	const u64 now = ktime_get_ns();
 
 	spin_lock(&discard_ctl->lock);
 again:
 	block_group = find_next_block_group(discard_ctl, now);
 
-	if (block_group && now > block_group->discard_eligible_time) {
+	if (block_group && now >= block_group->discard_eligible_time) {
 		if (block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED &&
 		    block_group->used != 0) {
 			if (btrfs_is_block_group_data_only(block_group))
@@ -222,12 +221,11 @@
 			block_group->discard_state = BTRFS_DISCARD_EXTENTS;
 		}
 		discard_ctl->block_group = block_group;
+	}
+	if (block_group) {
 		*discard_state = block_group->discard_state;
 		*discard_index = block_group->discard_index;
-	} else {
-		block_group = NULL;
 	}
-
 	spin_unlock(&discard_ctl->lock);
 
 	return block_group;
@@ -330,28 +328,15 @@
 		btrfs_discard_schedule_work(discard_ctl, false);
 }
 
-/**
- * btrfs_discard_schedule_work - responsible for scheduling the discard work
- * @discard_ctl: discard control
- * @override: override the current timer
- *
- * Discards are issued by a delayed workqueue item.  @override is used to
- * update the current delay as the baseline delay interval is reevaluated on
- * transaction commit.  This is also maxed with any other rate limit.
- */
-void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
-				 bool override)
+static void __btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
+					  u64 now, bool override)
 {
 	struct btrfs_block_group *block_group;
-	const u64 now = ktime_get_ns();
-
-	spin_lock(&discard_ctl->lock);
 
 	if (!btrfs_run_discard_work(discard_ctl))
-		goto out;
-
+		return;
 	if (!override && delayed_work_pending(&discard_ctl->work))
-		goto out;
+		return;
 
 	block_group = find_next_block_group(discard_ctl, now);
 	if (block_group) {
@@ -393,7 +378,24 @@
 		mod_delayed_work(discard_ctl->discard_workers,
 				 &discard_ctl->work, nsecs_to_jiffies(delay));
 	}
-out:
+}
+
+/*
+ * btrfs_discard_schedule_work - responsible for scheduling the discard work
+ * @discard_ctl:  discard control
+ * @override:     override the current timer
+ *
+ * Discards are issued by a delayed workqueue item.  @override is used to
+ * update the current delay as the baseline delay interval is reevaluated on
+ * transaction commit.  This is also maxed with any other rate limit.
+ */
+void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
+				 bool override)
+{
+	const u64 now = ktime_get_ns();
+
+	spin_lock(&discard_ctl->lock);
+	__btrfs_discard_schedule_work(discard_ctl, now, override);
 	spin_unlock(&discard_ctl->lock);
 }
 
@@ -438,13 +440,18 @@
 	int discard_index = 0;
 	u64 trimmed = 0;
 	u64 minlen = 0;
+	u64 now = ktime_get_ns();
 
 	discard_ctl = container_of(work, struct btrfs_discard_ctl, work.work);
 
 	block_group = peek_discard_list(discard_ctl, &discard_state,
-					&discard_index);
+					&discard_index, now);
 	if (!block_group || !btrfs_run_discard_work(discard_ctl))
 		return;
+	if (now < block_group->discard_eligible_time) {
+		btrfs_discard_schedule_work(discard_ctl, false);
+		return;
+	}
 
 	/* Perform discarding */
 	minlen = discard_minlen[discard_index];
@@ -474,13 +481,6 @@
 		discard_ctl->discard_extent_bytes += trimmed;
 	}
 
-	/*
-	 * Updated without locks as this is inside the workfn and nothing else
-	 * is reading the values
-	 */
-	discard_ctl->prev_discard = trimmed;
-	discard_ctl->prev_discard_time = ktime_get_ns();
-
 	/* Determine next steps for a block_group */
 	if (block_group->discard_cursor >= btrfs_block_group_end(block_group)) {
 		if (discard_state == BTRFS_DISCARD_BITMAPS) {
@@ -496,11 +496,13 @@
 		}
 	}
 
+	now = ktime_get_ns();
 	spin_lock(&discard_ctl->lock);
+	discard_ctl->prev_discard = trimmed;
+	discard_ctl->prev_discard_time = now;
 	discard_ctl->block_group = NULL;
+	__btrfs_discard_schedule_work(discard_ctl, now, false);
 	spin_unlock(&discard_ctl->lock);
-
-	btrfs_discard_schedule_work(discard_ctl, false);
 }
 
 /**
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 765deef..1dfd4b2 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1729,7 +1729,7 @@
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 sleep:
-		clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
+		clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
 		if (kthread_should_park())
 			kthread_parkme();
 		if (kthread_should_stop())
@@ -2830,6 +2830,9 @@
 		return -ENOMEM;
 	btrfs_init_delayed_root(fs_info->delayed_root);
 
+	if (sb_rdonly(sb))
+		set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);
+
 	return btrfs_alloc_stripe_hash_table(fs_info);
 }
 
@@ -2969,6 +2972,7 @@
 		}
 	}
 
+	ret = btrfs_find_orphan_roots(fs_info);
 out:
 	return ret;
 }
@@ -3383,10 +3387,6 @@
 		}
 	}
 
-	ret = btrfs_find_orphan_roots(fs_info);
-	if (ret)
-		goto fail_qgroup;
-
 	fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true);
 	if (IS_ERR(fs_info->fs_root)) {
 		err = PTR_ERR(fs_info->fs_root);
@@ -4181,6 +4181,9 @@
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
+	/* We shouldn't have any transaction open at this point */
+	ASSERT(list_empty(&fs_info->trans_list));
+
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
 	free_root_pointers(fs_info, true);
 	btrfs_free_fs_roots(fs_info);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 56ea380..d79b836 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -844,6 +844,7 @@
 	want = extent_ref_type(parent, owner);
 	if (insert) {
 		extra_size = btrfs_extent_inline_ref_size(want);
+		path->search_for_extension = 1;
 		path->keep_locks = 1;
 	} else
 		extra_size = -1;
@@ -996,6 +997,7 @@
 out:
 	if (insert) {
 		path->keep_locks = 0;
+		path->search_for_extension = 0;
 		btrfs_unlock_up_safe(path, 1);
 	}
 	return err;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 1545c22..6ccfc01 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -1016,8 +1016,10 @@
 	}
 
 	btrfs_release_path(path);
+	path->search_for_extension = 1;
 	ret = btrfs_search_slot(trans, root, &file_key, path,
 				csum_size, 1);
+	path->search_for_extension = 0;
 	if (ret < 0)
 		goto out;
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8e23780..0707166 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, u64 *nr, bool snapshot,
+				 bool in_reclaim_context)
 {
 	struct btrfs_inode *binode;
 	struct inode *inode;
@@ -9411,6 +9412,11 @@
 
 		list_move_tail(&binode->delalloc_inodes,
 			       &root->delalloc_inodes);
+
+		if (in_reclaim_context &&
+		    test_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &binode->runtime_flags))
+			continue;
+
 		inode = igrab(&binode->vfs_inode);
 		if (!inode) {
 			cond_resched_lock(&root->delalloc_lock);
@@ -9464,10 +9470,11 @@
 	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
 		return -EROFS;
 
-	return start_delalloc_inodes(root, &nr, true);
+	return start_delalloc_inodes(root, &nr, true, false);
 }
 
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr)
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
+			       bool in_reclaim_context)
 {
 	struct btrfs_root *root;
 	struct list_head splice;
@@ -9490,7 +9497,7 @@
 			       &fs_info->delalloc_roots);
 		spin_unlock(&fs_info->delalloc_root_lock);
 
-		ret = start_delalloc_inodes(root, &nr, false);
+		ret = start_delalloc_inodes(root, &nr, false, in_reclaim_context);
 		btrfs_put_root(root);
 		if (ret < 0)
 			goto out;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 703212f..dde49a7 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4951,7 +4951,7 @@
 	case BTRFS_IOC_SYNC: {
 		int ret;
 
-		ret = btrfs_start_delalloc_roots(fs_info, U64_MAX);
+		ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false);
 		if (ret)
 			return ret;
 		ret = btrfs_sync_fs(inode->i_sb, 1);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index fe30460..808370a 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -3190,6 +3190,12 @@
 	return ret;
 }
 
+static bool rescan_should_stop(struct btrfs_fs_info *fs_info)
+{
+	return btrfs_fs_closing(fs_info) ||
+		test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
+}
+
 static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 {
 	struct btrfs_fs_info *fs_info = container_of(work, struct btrfs_fs_info,
@@ -3198,6 +3204,7 @@
 	struct btrfs_trans_handle *trans = NULL;
 	int err = -ENOMEM;
 	int ret = 0;
+	bool stopped = false;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -3210,7 +3217,7 @@
 	path->skip_locking = 1;
 
 	err = 0;
-	while (!err && !btrfs_fs_closing(fs_info)) {
+	while (!err && !(stopped = rescan_should_stop(fs_info))) {
 		trans = btrfs_start_transaction(fs_info->fs_root, 0);
 		if (IS_ERR(trans)) {
 			err = PTR_ERR(trans);
@@ -3253,7 +3260,7 @@
 	}
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
-	if (!btrfs_fs_closing(fs_info))
+	if (!stopped)
 		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
 	if (trans) {
 		ret = update_qgroup_status_item(trans);
@@ -3272,7 +3279,7 @@
 
 	btrfs_end_transaction(trans);
 
-	if (btrfs_fs_closing(fs_info)) {
+	if (stopped) {
 		btrfs_info(fs_info, "qgroup scan paused");
 	} else if (err >= 0) {
 		btrfs_info(fs_info, "qgroup scan completed%s",
@@ -3531,16 +3538,6 @@
 	bool can_commit = true;
 
 	/*
-	 * We don't want to run flush again and again, so if there is a running
-	 * one, we won't try to start a new flush, but exit directly.
-	 */
-	if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) {
-		wait_event(root->qgroup_flush_wait,
-			!test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state));
-		return 0;
-	}
-
-	/*
 	 * If current process holds a transaction, we shouldn't flush, as we
 	 * assume all space reservation happens before a transaction handle is
 	 * held.
@@ -3554,6 +3551,26 @@
 	    current->journal_info != BTRFS_SEND_TRANS_STUB)
 		can_commit = false;
 
+	/*
+	 * We don't want to run flush again and again, so if there is a running
+	 * one, we won't try to start a new flush, but exit directly.
+	 */
+	if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) {
+		/*
+		 * We are already holding a transaction, thus we can block other
+		 * threads from flushing.  So exit right now. This increases
+		 * the chance of EDQUOT for heavy load and near limit cases.
+		 * But we can argue that if we're already near limit, EDQUOT is
+		 * unavoidable anyway.
+		 */
+		if (!can_commit)
+			return 0;
+
+		wait_event(root->qgroup_flush_wait,
+			!test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state));
+		return 0;
+	}
+
 	ret = btrfs_start_delalloc_snapshot(root);
 	if (ret < 0)
 		goto out;
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index ab80896..b03e789 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -89,6 +89,19 @@
 	if (ret)
 		goto out_unlock;
 
+	/*
+	 * After dirtying the page our caller will need to start a transaction,
+	 * and if we are low on metadata free space, that can cause flushing of
+	 * delalloc for all inodes in order to get metadata space released.
+	 * However we are holding the range locked for the whole duration of
+	 * the clone/dedupe operation, so we may deadlock if that happens and no
+	 * other task releases enough space. So mark this inode as not being
+	 * possible to flush to avoid such deadlock. We will clear that flag
+	 * when we finish cloning all extents, since a transaction is started
+	 * after finding each extent to clone.
+	 */
+	set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags);
+
 	if (comp_type == BTRFS_COMPRESS_NONE) {
 		char *map;
 
@@ -549,6 +562,8 @@
 out:
 	btrfs_free_path(path);
 	kvfree(buf);
+	clear_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &BTRFS_I(inode)->runtime_flags);
+
 	return ret;
 }
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index d719a275..ae97f4d 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -236,6 +236,7 @@
 	 * after this directory is moved, we can try to rmdir the ino rmdir_ino.
 	 */
 	u64 rmdir_ino;
+	u64 rmdir_gen;
 	bool orphanized;
 };
 
@@ -316,7 +317,7 @@
 static struct waiting_dir_move *
 get_waiting_dir_move(struct send_ctx *sctx, u64 ino);
 
-static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino);
+static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen);
 
 static int need_send_hole(struct send_ctx *sctx)
 {
@@ -2299,7 +2300,7 @@
 
 		fs_path_reset(name);
 
-		if (is_waiting_for_rm(sctx, ino)) {
+		if (is_waiting_for_rm(sctx, ino, gen)) {
 			ret = gen_unique_name(sctx, ino, gen, name);
 			if (ret < 0)
 				goto out;
@@ -2858,8 +2859,8 @@
 	return ret;
 }
 
-static struct orphan_dir_info *
-add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
+static struct orphan_dir_info *add_orphan_dir_info(struct send_ctx *sctx,
+						   u64 dir_ino, u64 dir_gen)
 {
 	struct rb_node **p = &sctx->orphan_dirs.rb_node;
 	struct rb_node *parent = NULL;
@@ -2868,20 +2869,23 @@
 	while (*p) {
 		parent = *p;
 		entry = rb_entry(parent, struct orphan_dir_info, node);
-		if (dir_ino < entry->ino) {
+		if (dir_ino < entry->ino)
 			p = &(*p)->rb_left;
-		} else if (dir_ino > entry->ino) {
+		else if (dir_ino > entry->ino)
 			p = &(*p)->rb_right;
-		} else {
+		else if (dir_gen < entry->gen)
+			p = &(*p)->rb_left;
+		else if (dir_gen > entry->gen)
+			p = &(*p)->rb_right;
+		else
 			return entry;
-		}
 	}
 
 	odi = kmalloc(sizeof(*odi), GFP_KERNEL);
 	if (!odi)
 		return ERR_PTR(-ENOMEM);
 	odi->ino = dir_ino;
-	odi->gen = 0;
+	odi->gen = dir_gen;
 	odi->last_dir_index_offset = 0;
 
 	rb_link_node(&odi->node, parent, p);
@@ -2889,8 +2893,8 @@
 	return odi;
 }
 
-static struct orphan_dir_info *
-get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
+static struct orphan_dir_info *get_orphan_dir_info(struct send_ctx *sctx,
+						   u64 dir_ino, u64 gen)
 {
 	struct rb_node *n = sctx->orphan_dirs.rb_node;
 	struct orphan_dir_info *entry;
@@ -2901,15 +2905,19 @@
 			n = n->rb_left;
 		else if (dir_ino > entry->ino)
 			n = n->rb_right;
+		else if (gen < entry->gen)
+			n = n->rb_left;
+		else if (gen > entry->gen)
+			n = n->rb_right;
 		else
 			return entry;
 	}
 	return NULL;
 }
 
-static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino)
+static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen)
 {
-	struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino);
+	struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino, gen);
 
 	return odi != NULL;
 }
@@ -2954,7 +2962,7 @@
 	key.type = BTRFS_DIR_INDEX_KEY;
 	key.offset = 0;
 
-	odi = get_orphan_dir_info(sctx, dir);
+	odi = get_orphan_dir_info(sctx, dir, dir_gen);
 	if (odi)
 		key.offset = odi->last_dir_index_offset;
 
@@ -2985,7 +2993,7 @@
 
 		dm = get_waiting_dir_move(sctx, loc.objectid);
 		if (dm) {
-			odi = add_orphan_dir_info(sctx, dir);
+			odi = add_orphan_dir_info(sctx, dir, dir_gen);
 			if (IS_ERR(odi)) {
 				ret = PTR_ERR(odi);
 				goto out;
@@ -2993,12 +3001,13 @@
 			odi->gen = dir_gen;
 			odi->last_dir_index_offset = found_key.offset;
 			dm->rmdir_ino = dir;
+			dm->rmdir_gen = dir_gen;
 			ret = 0;
 			goto out;
 		}
 
 		if (loc.objectid > send_progress) {
-			odi = add_orphan_dir_info(sctx, dir);
+			odi = add_orphan_dir_info(sctx, dir, dir_gen);
 			if (IS_ERR(odi)) {
 				ret = PTR_ERR(odi);
 				goto out;
@@ -3038,6 +3047,7 @@
 		return -ENOMEM;
 	dm->ino = ino;
 	dm->rmdir_ino = 0;
+	dm->rmdir_gen = 0;
 	dm->orphanized = orphanized;
 
 	while (*p) {
@@ -3183,7 +3193,7 @@
 	while (ino != BTRFS_FIRST_FREE_OBJECTID) {
 		fs_path_reset(name);
 
-		if (is_waiting_for_rm(sctx, ino))
+		if (is_waiting_for_rm(sctx, ino, gen))
 			break;
 		if (is_waiting_for_move(sctx, ino)) {
 			if (*ancestor_ino == 0)
@@ -3223,6 +3233,7 @@
 	u64 parent_ino, parent_gen;
 	struct waiting_dir_move *dm = NULL;
 	u64 rmdir_ino = 0;
+	u64 rmdir_gen;
 	u64 ancestor;
 	bool is_orphan;
 	int ret;
@@ -3237,6 +3248,7 @@
 	dm = get_waiting_dir_move(sctx, pm->ino);
 	ASSERT(dm);
 	rmdir_ino = dm->rmdir_ino;
+	rmdir_gen = dm->rmdir_gen;
 	is_orphan = dm->orphanized;
 	free_waiting_dir_move(sctx, dm);
 
@@ -3273,6 +3285,7 @@
 			dm = get_waiting_dir_move(sctx, pm->ino);
 			ASSERT(dm);
 			dm->rmdir_ino = rmdir_ino;
+			dm->rmdir_gen = rmdir_gen;
 		}
 		goto out;
 	}
@@ -3291,7 +3304,7 @@
 		struct orphan_dir_info *odi;
 		u64 gen;
 
-		odi = get_orphan_dir_info(sctx, rmdir_ino);
+		odi = get_orphan_dir_info(sctx, rmdir_ino, rmdir_gen);
 		if (!odi) {
 			/* already deleted */
 			goto finish;
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 6409956..67e55c5 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -532,7 +532,7 @@
 
 	loops = 0;
 	while ((delalloc_bytes || dio_bytes) && loops < 3) {
-		btrfs_start_delalloc_roots(fs_info, items);
+		btrfs_start_delalloc_roots(fs_info, items, true);
 
 		loops++;
 		if (wait_ordered && !trans) {
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 022f208..12d7d3b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -175,7 +175,7 @@
 	btrfs_discard_stop(fs_info);
 
 	/* btrfs handle error by forcing the filesystem readonly */
-	sb->s_flags |= SB_RDONLY;
+	btrfs_set_sb_rdonly(sb);
 	btrfs_info(fs_info, "forced readonly");
 	/*
 	 * Note that a running device replace operation is not canceled here
@@ -1953,7 +1953,7 @@
 		/* avoid complains from lockdep et al. */
 		up(&fs_info->uuid_tree_rescan_sem);
 
-		sb->s_flags |= SB_RDONLY;
+		btrfs_set_sb_rdonly(sb);
 
 		/*
 		 * Setting SB_RDONLY will put the cleaner thread to
@@ -1964,10 +1964,42 @@
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 
+		/*
+		 * The cleaner task could be already running before we set the
+		 * flag BTRFS_FS_STATE_RO (and SB_RDONLY in the superblock).
+		 * We must make sure that after we finish the remount, i.e. after
+		 * we call btrfs_commit_super(), the cleaner can no longer start
+		 * a transaction - either because it was dropping a dead root,
+		 * running delayed iputs or deleting an unused block group (the
+		 * cleaner picked a block group from the list of unused block
+		 * groups before we were able to in the previous call to
+		 * btrfs_delete_unused_bgs()).
+		 */
+		wait_on_bit(&fs_info->flags, BTRFS_FS_CLEANER_RUNNING,
+			    TASK_UNINTERRUPTIBLE);
+
+		/*
+		 * We've set the superblock to RO mode, so we might have made
+		 * the cleaner task sleep without running all pending delayed
+		 * iputs. Go through all the delayed iputs here, so that if an
+		 * unmount happens without remounting RW we don't end up at
+		 * finishing close_ctree() with a non-empty list of delayed
+		 * iputs.
+		 */
+		btrfs_run_delayed_iputs(fs_info);
+
 		btrfs_dev_replace_suspend_for_unmount(fs_info);
 		btrfs_scrub_cancel(fs_info);
 		btrfs_pause_balance(fs_info);
 
+		/*
+		 * Pause the qgroup rescan worker if it is running. We don't want
+		 * it to be still running after we are in RO mode, as after that,
+		 * by the time we unmount, it might have left a transaction open,
+		 * so we would leak the transaction and/or crash.
+		 */
+		btrfs_qgroup_wait_for_completion(fs_info, false);
+
 		ret = btrfs_commit_super(fs_info);
 		if (ret)
 			goto restore;
@@ -2006,7 +2038,7 @@
 		if (ret)
 			goto restore;
 
-		sb->s_flags &= ~SB_RDONLY;
+		btrfs_clear_sb_rdonly(sb);
 
 		set_bit(BTRFS_FS_OPEN, &fs_info->flags);
 	}
@@ -2028,6 +2060,8 @@
 	/* We've hit an error - don't reset SB_RDONLY */
 	if (sb_rdonly(sb))
 		old_flags |= SB_RDONLY;
+	if (!(old_flags & SB_RDONLY))
+		clear_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);
 	sb->s_flags = old_flags;
 	fs_info->mount_opt = old_opts;
 	fs_info->compress_type = old_compress_type;
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 8ca334d..6bd97bd 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -55,8 +55,14 @@
 	struct inode *inode;
 
 	inode = new_inode(test_mnt->mnt_sb);
-	if (inode)
-		inode_init_owner(inode, NULL, S_IFREG);
+	if (!inode)
+		return NULL;
+
+	inode->i_mode = S_IFREG;
+	BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
+	BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
+	BTRFS_I(inode)->location.offset = 0;
+	inode_init_owner(inode, NULL, S_IFREG);
 
 	return inode;
 }
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 0402206..c9874b1 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -232,11 +232,6 @@
 		return ret;
 	}
 
-	inode->i_mode = S_IFREG;
-	BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
-	BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
-	BTRFS_I(inode)->location.offset = 0;
-
 	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
 	if (!fs_info) {
 		test_std_err(TEST_ALLOC_FS_INFO);
@@ -835,10 +830,6 @@
 		return ret;
 	}
 
-	BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
-	BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
-	BTRFS_I(inode)->location.offset = 0;
-
 	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
 	if (!fs_info) {
 		test_std_err(TEST_ALLOC_FS_INFO);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ee086fc..b62be84 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2592,7 +2592,7 @@
 	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
 
 	if (seeding_dev) {
-		sb->s_flags &= ~SB_RDONLY;
+		btrfs_clear_sb_rdonly(sb);
 		ret = btrfs_prepare_sprout(fs_info);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -2728,7 +2728,7 @@
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 error_trans:
 	if (seeding_dev)
-		sb->s_flags |= SB_RDONLY;
+		btrfs_set_sb_rdonly(sb);
 	if (trans)
 		btrfs_end_transaction(trans);
 error_free_zone:
diff --git a/fs/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/select.c b/fs/select.c
index ebfebdf..37aaa83 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -1011,14 +1011,17 @@
 	fdcount = do_poll(head, &table, end_time);
 	poll_freewait(&table);
 
+	if (!user_write_access_begin(ufds, nfds * sizeof(*ufds)))
+		goto out_fds;
+
 	for (walk = head; walk; walk = walk->next) {
 		struct pollfd *fds = walk->entries;
 		int j;
 
-		for (j = 0; j < walk->len; j++, ufds++)
-			if (__put_user(fds[j].revents, &ufds->revents))
-				goto out_fds;
+		for (j = walk->len; j; fds++, ufds++, j--)
+			unsafe_put_user(fds->revents, &ufds->revents, Efault);
   	}
+	user_write_access_end();
 
 	err = fdcount;
 out_fds:
@@ -1030,6 +1033,11 @@
 	}
 
 	return err;
+
+Efault:
+	user_write_access_end();
+	err = -EFAULT;
+	goto out_fds;
 }
 
 static long do_restart_poll(struct restart_block *restart_block)
diff --git a/fs/zonefs/Kconfig b/fs/zonefs/Kconfig
index 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/console.h b/include/linux/console.h
index dbe78e8..20874db 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -186,12 +186,9 @@
 extern int braille_unregister_console(struct console *);
 #ifdef CONFIG_TTY
 extern void console_sysfs_notify(void);
-extern void register_ttynull_console(void);
 #else
 static inline void console_sysfs_notify(void)
 { }
-static inline void register_ttynull_console(void)
-{ }
 #endif
 extern bool console_suspend_enabled;
 
diff --git a/include/linux/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/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 8fbddec..442c016 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1280,7 +1280,8 @@
 	u8	   ece_support[0x1];
 	u8	   reserved_at_a4[0x7];
 	u8         log_max_srq[0x5];
-	u8         reserved_at_b0[0x2];
+	u8         reserved_at_b0[0x1];
+	u8         uplink_follow[0x1];
 	u8         ts_cqe_to_dest_cqn[0x1];
 	u8         reserved_at_b3[0xd];
 
diff --git a/include/linux/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/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 874cc12..82708c6 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -75,8 +75,9 @@
  *
  * @rx_dropped: Number of packets received but not processed,
  *   e.g. due to lack of resources or unsupported protocol.
- *   For hardware interfaces this counter should not include packets
- *   dropped by the device which are counted separately in
+ *   For hardware interfaces this counter may include packets discarded
+ *   due to L2 address filtering but should not include packets dropped
+ *   by the device due to buffer exhaustion which are counted separately in
  *   @rx_missed_errors (since procfs folds those two counters together).
  *
  * @tx_dropped: Number of packets dropped on their way to transmission,
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 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/init/main.c b/init/main.c
index 421640f..c68d784 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1480,14 +1480,8 @@
 	struct file *file = filp_open("/dev/console", O_RDWR, 0);
 
 	if (IS_ERR(file)) {
-		pr_err("Warning: unable to open an initial console. Fallback to ttynull.\n");
-		register_ttynull_console();
-
-		file = filp_open("/dev/console", O_RDWR, 0);
-		if (IS_ERR(file)) {
-			pr_err("Warning: Failed to add ttynull console. No stdin, stdout, and stderr for the init process!\n");
-			return;
-		}
+		pr_err("Warning: unable to open an initial console.\n");
+		return;
 	}
 	init_dup(file);
 	init_dup(file);
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 3efe381..175b7b4 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -159,6 +159,7 @@
                 }
 
                 /* set info->task and info->tid */
+		info->task = curr_task;
 		if (curr_tid == info->tid) {
 			curr_fd = info->fd;
 		} else {
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index f292e02..15bbfaf 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -284,7 +284,8 @@
 	return 0;
 
 out_free_newdev:
-	if (new_dev->reg_state == NETREG_UNINITIALIZED)
+	if (new_dev->reg_state == NETREG_UNINITIALIZED ||
+	    new_dev->reg_state == NETREG_UNREGISTERED)
 		free_netdev(new_dev);
 	return err;
 }
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 89fff5f..2ed0b01 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -302,7 +302,7 @@
 	if (skb_is_gso(skb))
 		return ip_finish_output_gso(net, sk, skb, mtu);
 
-	if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU))
+	if (skb->len > mtu || IPCB(skb)->frag_max_size)
 		return ip_fragment(net, sk, skb, mtu, ip_finish_output2);
 
 	return ip_finish_output2(net, sk, skb);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index ee65c92..64594aa 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -759,8 +759,11 @@
 		goto tx_error;
 	}
 
-	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph,
-			    0, 0, false)) {
+	df = tnl_params->frag_off;
+	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
+		df |= (inner_iph->frag_off & htons(IP_DF));
+
+	if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
@@ -788,10 +791,6 @@
 			ttl = ip4_dst_hoplimit(&rt->dst);
 	}
 
-	df = tnl_params->frag_off;
-	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
-		df |= (inner_iph->frag_off&htons(IP_DF));
-
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
 	if (max_headroom > dev->needed_headroom)
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 5e1b22d..e53e43a 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -627,7 +627,7 @@
 	for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) {
 		if (!tb[i])
 			continue;
-		if (tb[NHA_FDB])
+		if (i == NHA_FDB)
 			continue;
 		NL_SET_ERR_MSG(extack,
 			       "No other attributes can be set in nexthop groups");
@@ -1459,8 +1459,10 @@
 	return nh;
 
 out_no_nh:
-	for (; i >= 0; --i)
+	for (i--; i >= 0; --i) {
+		list_del(&nhg->nh_entries[i].nh_list);
 		nexthop_put(nhg->nh_entries[i].nh);
+	}
 
 	kfree(nhg->spare);
 	kfree(nhg);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 605cdd3..f43e275 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1025,6 +1025,8 @@
 {
 	struct fib6_table *table = rt->fib6_table;
 
+	/* Flush all cached dst in exception table */
+	rt6_flush_exceptions(rt);
 	fib6_drop_pcpu_from(rt, table);
 
 	if (rt->nh && !list_empty(&rt->nh_list))
@@ -1927,9 +1929,6 @@
 	net->ipv6.rt6_stats->fib_rt_entries--;
 	net->ipv6.rt6_stats->fib_discarded_routes++;
 
-	/* Flush all cached dst in exception table */
-	rt6_flush_exceptions(rt);
-
 	/* Reset round-robin state, if necessary */
 	if (rcu_access_pointer(fn->rr_ptr) == rt)
 		fn->rr_ptr = NULL;
diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c
index 56aaf8c..8d00dfe 100644
--- a/net/qrtr/ns.c
+++ b/net/qrtr/ns.c
@@ -755,7 +755,7 @@
 	queue_work(qrtr_ns.workqueue, &qrtr_ns.work);
 }
 
-void qrtr_ns_init(void)
+int qrtr_ns_init(void)
 {
 	struct sockaddr_qrtr sq;
 	int ret;
@@ -766,7 +766,7 @@
 	ret = sock_create_kern(&init_net, AF_QIPCRTR, SOCK_DGRAM,
 			       PF_QIPCRTR, &qrtr_ns.sock);
 	if (ret < 0)
-		return;
+		return ret;
 
 	ret = kernel_getsockname(qrtr_ns.sock, (struct sockaddr *)&sq);
 	if (ret < 0) {
@@ -797,12 +797,13 @@
 	if (ret < 0)
 		goto err_wq;
 
-	return;
+	return 0;
 
 err_wq:
 	destroy_workqueue(qrtr_ns.workqueue);
 err_sock:
 	sock_release(qrtr_ns.sock);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(qrtr_ns_init);
 
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index f4ab3ca6..b343582 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -1287,13 +1287,19 @@
 		return rc;
 
 	rc = sock_register(&qrtr_family);
-	if (rc) {
-		proto_unregister(&qrtr_proto);
-		return rc;
-	}
+	if (rc)
+		goto err_proto;
 
-	qrtr_ns_init();
+	rc = qrtr_ns_init();
+	if (rc)
+		goto err_sock;
 
+	return 0;
+
+err_sock:
+	sock_unregister(qrtr_family.family);
+err_proto:
+	proto_unregister(&qrtr_proto);
 	return rc;
 }
 postcore_initcall(qrtr_proto_init);
diff --git a/net/qrtr/qrtr.h b/net/qrtr/qrtr.h
index dc2b67f..3f2d286 100644
--- a/net/qrtr/qrtr.h
+++ b/net/qrtr/qrtr.h
@@ -29,7 +29,7 @@
 
 int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len);
 
-void qrtr_ns_init(void);
+int qrtr_ns_init(void);
 
 void qrtr_ns_remove(void);
 
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index 27026f5..f620acd 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -21,6 +21,7 @@
 	tristate "cfg80211 - wireless configuration API"
 	depends on RFKILL || !RFKILL
 	select FW_LOADER
+	select CRC32
 	# may need to update this when certificates are changed and are
 	# using a different algorithm, though right now they shouldn't
 	# (this is here rather than below to allow it to be a module)
diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile
index d66949b..b5487cc 100644
--- a/scripts/gcc-plugins/Makefile
+++ b/scripts/gcc-plugins/Makefile
@@ -22,9 +22,9 @@
 GCC_PLUGINS_DIR = $(shell $(CC) -print-file-name=plugin)
 
 plugin_cxxflags	= -Wp,-MMD,$(depfile) $(KBUILD_HOSTCXXFLAGS) -fPIC \
-		   -I $(GCC_PLUGINS_DIR)/include -I $(obj) -std=gnu++98 \
+		   -I $(GCC_PLUGINS_DIR)/include -I $(obj) -std=gnu++11 \
 		   -fno-rtti -fno-exceptions -fasynchronous-unwind-tables \
-		   -ggdb -Wno-narrowing -Wno-unused-variable -Wno-c++11-compat \
+		   -ggdb -Wno-narrowing -Wno-unused-variable \
 		   -Wno-format-diag
 
 plugin_ldflags	= -shared
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 6852668..770ad25 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2220,8 +2220,6 @@
 	SND_PCI_QUIRK(0x1849, 0x7662, "Asrock H81M-HDS", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
 	SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0),
-	/* https://bugzilla.redhat.com/show_bug.cgi?id=1581607 */
-	SND_PCI_QUIRK(0x1558, 0x3501, "Clevo W35xSS_370SS", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
 	SND_PCI_QUIRK(0x1558, 0x6504, "Clevo W65_67SB", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index be5000d..d49cc44 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -1070,6 +1070,7 @@
 static const struct hda_device_id snd_hda_id_conexant[] = {
 	HDA_CODEC_ENTRY(0x14f11f86, "CX8070", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto),
+	HDA_CODEC_ENTRY(0x14f120d0, "CX11970", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f15051, "CX20561 (Hermosa)", patch_conexant_auto),
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 1e4a4b8..74d246a 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1733,7 +1733,7 @@
 	per_pin->silent_stream = false;
 
  unlock_out:
-	mutex_unlock(&spec->pcm_lock);
+	mutex_unlock(&per_pin->lock);
 }
 
 /* update ELD and jack state via audio component */
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index dde5ba2..3c1d2a3 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6289,6 +6289,7 @@
 	ALC221_FIXUP_HP_FRONT_MIC,
 	ALC292_FIXUP_TPT460,
 	ALC298_FIXUP_SPK_VOLUME,
+	ALC298_FIXUP_LENOVO_SPK_VOLUME,
 	ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER,
 	ALC269_FIXUP_ATIV_BOOK_8,
 	ALC221_FIXUP_HP_MIC_NO_PRESENCE,
@@ -7119,6 +7120,10 @@
 		.chained = true,
 		.chain_id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
 	},
+	[ALC298_FIXUP_LENOVO_SPK_VOLUME] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc298_fixup_speaker_volume,
+	},
 	[ALC295_FIXUP_DISABLE_DAC3] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc295_fixup_disable_dac3,
@@ -7885,7 +7890,7 @@
 	SND_PCI_QUIRK(0x1028, 0x09bf, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0a2e, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1028, 0x0a30, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC),
-	SND_PCI_QUIRK(0x1028, 0x0a58, "Dell Precision 3650 Tower", ALC255_FIXUP_DELL_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1028, 0x0a58, "Dell", ALC255_FIXUP_DELL_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
@@ -7959,11 +7964,13 @@
 	SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED),
+	SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
@@ -8021,6 +8028,8 @@
 	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE),
 	SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
+	SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
+	SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
 	SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
@@ -8126,6 +8135,7 @@
 	SND_PCI_QUIRK(0x17aa, 0x3151, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index 7ef8f31..0ab40a8 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -1002,6 +1002,7 @@
 enum {
 	VIA_FIXUP_INTMIC_BOOST,
 	VIA_FIXUP_ASUS_G75,
+	VIA_FIXUP_POWER_SAVE,
 };
 
 static void via_fixup_intmic_boost(struct hda_codec *codec,
@@ -1011,6 +1012,13 @@
 		override_mic_boost(codec, 0x30, 0, 2, 40);
 }
 
+static void via_fixup_power_save(struct hda_codec *codec,
+				 const struct hda_fixup *fix, int action)
+{
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		codec->power_save_node = 0;
+}
+
 static const struct hda_fixup via_fixups[] = {
 	[VIA_FIXUP_INTMIC_BOOST] = {
 		.type = HDA_FIXUP_FUNC,
@@ -1025,11 +1033,16 @@
 			{ }
 		}
 	},
+	[VIA_FIXUP_POWER_SAVE] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = via_fixup_power_save,
+	},
 };
 
 static const struct snd_pci_quirk vt2002p_fixups[] = {
 	SND_PCI_QUIRK(0x1043, 0x1487, "Asus G75", VIA_FIXUP_ASUS_G75),
 	SND_PCI_QUIRK(0x1043, 0x8532, "Asus X202E", VIA_FIXUP_INTMIC_BOOST),
+	SND_PCI_QUIRK(0x1558, 0x3501, "Clevo W35xSS_370SS", VIA_FIXUP_POWER_SAVE),
 	{}
 };
 
diff --git a/sound/usb/implicit.c b/sound/usb/implicit.c
index eb3a4c4..931042a 100644
--- a/sound/usb/implicit.c
+++ b/sound/usb/implicit.c
@@ -74,10 +74,12 @@
 
 	/* No quirk for playback but with capture quirk (see below) */
 	IMPLICIT_FB_SKIP_DEV(0x0582, 0x0130),	/* BOSS BR-80 */
+	IMPLICIT_FB_SKIP_DEV(0x0582, 0x0171),   /* BOSS RC-505 */
 	IMPLICIT_FB_SKIP_DEV(0x0582, 0x0189),	/* BOSS GT-100v2 */
 	IMPLICIT_FB_SKIP_DEV(0x0582, 0x01d6),	/* BOSS GT-1 */
 	IMPLICIT_FB_SKIP_DEV(0x0582, 0x01d8),	/* BOSS Katana */
 	IMPLICIT_FB_SKIP_DEV(0x0582, 0x01e5),	/* BOSS GT-001 */
+	IMPLICIT_FB_SKIP_DEV(0x0582, 0x0203),   /* BOSS AD-10 */
 
 	{} /* terminator */
 };
@@ -85,10 +87,12 @@
 /* Implicit feedback quirk table for capture: only FIXED type */
 static const struct snd_usb_implicit_fb_match capture_implicit_fb_quirks[] = {
 	IMPLICIT_FB_FIXED_DEV(0x0582, 0x0130, 0x0d, 0x01), /* BOSS BR-80 */
+	IMPLICIT_FB_FIXED_DEV(0x0582, 0x0171, 0x0d, 0x01), /* BOSS RC-505 */
 	IMPLICIT_FB_FIXED_DEV(0x0582, 0x0189, 0x0d, 0x01), /* BOSS GT-100v2 */
 	IMPLICIT_FB_FIXED_DEV(0x0582, 0x01d6, 0x0d, 0x01), /* BOSS GT-1 */
 	IMPLICIT_FB_FIXED_DEV(0x0582, 0x01d8, 0x0d, 0x01), /* BOSS Katana */
 	IMPLICIT_FB_FIXED_DEV(0x0582, 0x01e5, 0x0d, 0x01), /* BOSS GT-001 */
+	IMPLICIT_FB_FIXED_DEV(0x0582, 0x0203, 0x0d, 0x01), /* BOSS AD-10 */
 
 	{} /* terminator */
 };
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index c821365..0c23fa6 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1889,6 +1889,8 @@
 		ms_ep = find_usb_ms_endpoint_descriptor(hostep);
 		if (!ms_ep)
 			continue;
+		if (ms_ep->bNumEmbMIDIJack > 0x10)
+			continue;
 		if (usb_endpoint_dir_out(ep)) {
 			if (endpoints[epidx].out_ep) {
 				if (++epidx >= MIDI_MAX_ENDPOINTS) {
@@ -2141,6 +2143,8 @@
 		    cs_desc[1] == USB_DT_CS_INTERFACE &&
 		    cs_desc[2] == 0xf1 &&
 		    cs_desc[3] == 0x02) {
+			if (cs_desc[4] > 0x10 || cs_desc[5] > 0x10)
+				continue;
 			endpoint->in_cables  = (1 << cs_desc[4]) - 1;
 			endpoint->out_cables = (1 << cs_desc[5]) - 1;
 			return snd_usbmidi_detect_endpoints(umidi, endpoint, 1);
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 3fae61e..ff3aa0c 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -11,7 +11,6 @@
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
 #include <net/if.h>
-#include <linux/if.h>
 #include <linux/rtnetlink.h>
 #include <linux/socket.h>
 #include <linux/tc_act/tc_bpf.h>
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index e3ea569..7409d78 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -139,6 +139,8 @@
 #define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_err(fmt, ...) \
 	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
 
 static bool is_btf_id(const char *name)
 {
@@ -472,7 +474,7 @@
 	int nr_funcs    = obj->nr_funcs;
 	int err, type_id;
 	struct btf *btf;
-	__u32 nr;
+	__u32 nr_types;
 
 	btf = btf__parse(obj->btf ?: obj->path, NULL);
 	err = libbpf_get_error(btf);
@@ -483,12 +485,12 @@
 	}
 
 	err = -1;
-	nr  = btf__get_nr_types(btf);
+	nr_types = btf__get_nr_types(btf);
 
 	/*
 	 * Iterate all the BTF types and search for collected symbol IDs.
 	 */
-	for (type_id = 1; type_id <= nr; type_id++) {
+	for (type_id = 1; type_id <= nr_types; type_id++) {
 		const struct btf_type *type;
 		struct rb_root *root;
 		struct btf_id *id;
@@ -526,8 +528,13 @@
 
 		id = btf_id__find(root, str);
 		if (id) {
-			id->id = type_id;
-			(*nr)--;
+			if (id->id) {
+				pr_info("WARN: multiple IDs found for '%s': %d, %d - using %d\n",
+					str, id->id, type_id, id->id);
+			} else {
+				id->id = type_id;
+				(*nr)--;
+			}
 		}
 	}
 
diff --git a/tools/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/bpf/progs/bprm_opts.c b/tools/testing/selftests/bpf/progs/bprm_opts.c
index 5bfef28..418d9c6 100644
--- a/tools/testing/selftests/bpf/progs/bprm_opts.c
+++ b/tools/testing/selftests/bpf/progs/bprm_opts.c
@@ -4,7 +4,7 @@
  * Copyright 2020 Google LLC.
  */
 
-#include "vmlinux.h"
+#include <linux/bpf.h>
 #include <errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/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/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index eb693a3..4c7d3361 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -869,7 +869,7 @@
 	pid3=$!
 	ip netns exec me ping -f 2001:db8:101::2 >/dev/null 2>&1 &
 	pid4=$!
-	ip netns exec me mausezahn veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+	ip netns exec me mausezahn -6 veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
 	pid5=$!
 
 	sleep 300
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 464e31e..64cd2e2 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -162,7 +162,15 @@
 # - list_flush_ipv6_exception
 #	Using the same topology as in pmtu_ipv6, create exceptions, and check
 #	they are shown when listing exception caches, gone after flushing them
-
+#
+# - pmtu_ipv4_route_change
+#	Use the same topology as in pmtu_ipv4, but issue a route replacement
+#	command and delete the corresponding device afterward. This tests for
+#	proper cleanup of the PMTU exceptions by the route replacement path.
+#	Device unregistration should complete successfully
+#
+# - pmtu_ipv6_route_change
+#	Same as above but with IPv6
 
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
@@ -224,7 +232,9 @@
 	cleanup_ipv4_exception		ipv4: cleanup of cached exceptions	1
 	cleanup_ipv6_exception		ipv6: cleanup of cached exceptions	1
 	list_flush_ipv4_exception	ipv4: list and flush cached exceptions	1
-	list_flush_ipv6_exception	ipv6: list and flush cached exceptions	1"
+	list_flush_ipv6_exception	ipv6: list and flush cached exceptions	1
+	pmtu_ipv4_route_change		ipv4: PMTU exception w/route replace	1
+	pmtu_ipv6_route_change		ipv6: PMTU exception w/route replace	1"
 
 NS_A="ns-A"
 NS_B="ns-B"
@@ -1782,6 +1792,63 @@
 	return ${fail}
 }
 
+test_pmtu_ipvX_route_change() {
+	family=${1}
+
+	setup namespaces routing || return 2
+	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
+	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
+	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2
+
+	if [ ${family} -eq 4 ]; then
+		ping=ping
+		dst1="${prefix4}.${b_r1}.1"
+		dst2="${prefix4}.${b_r2}.1"
+		gw="${prefix4}.${a_r1}.2"
+	else
+		ping=${ping6}
+		dst1="${prefix6}:${b_r1}::1"
+		dst2="${prefix6}:${b_r2}::1"
+		gw="${prefix6}:${a_r1}::2"
+	fi
+
+	# Set up initial MTU values
+	mtu "${ns_a}"  veth_A-R1 2000
+	mtu "${ns_r1}" veth_R1-A 2000
+	mtu "${ns_r1}" veth_R1-B 1400
+	mtu "${ns_b}"  veth_B-R1 1400
+
+	mtu "${ns_a}"  veth_A-R2 2000
+	mtu "${ns_r2}" veth_R2-A 2000
+	mtu "${ns_r2}" veth_R2-B 1500
+	mtu "${ns_b}"  veth_B-R2 1500
+
+	# Create route exceptions
+	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1}
+	run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2}
+
+	# Check that exceptions have been created with the correct PMTU
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
+
+	# Replace the route from A to R1
+	run_cmd ${ns_a} ip route change default via ${gw}
+
+	# Delete the device in A
+	run_cmd ${ns_a} ip link del "veth_A-R1"
+}
+
+test_pmtu_ipv4_route_change() {
+	test_pmtu_ipvX_route_change 4
+}
+
+test_pmtu_ipv6_route_change() {
+	test_pmtu_ipvX_route_change 6
+}
+
 usage() {
 	echo
 	echo "$0 [OPTIONS] [TEST]..."
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index ac2a30b..f8a19f5 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -5,6 +5,14 @@
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
+# set global exit status, but never reset nonzero one.
+check_err()
+{
+	if [ $ret -eq 0 ]; then
+		ret=$1
+	fi
+}
+
 cleanup() {
 	local -r jobs="$(jobs -p)"
 	local -r ns="$(ip netns list|grep $PEER_NS)"
@@ -44,7 +52,9 @@
 	# Hack: let bg programs complete the startup
 	sleep 0.1
 	./udpgso_bench_tx ${tx_args}
+	ret=$?
 	wait $(jobs -p)
+	return $ret
 }
 
 run_test() {
@@ -87,8 +97,10 @@
 
 	sleep 0.1
 	./udpgso_bench_tx ${tx_args}
+	ret=$?
 	kill -INT $pid
 	wait $(jobs -p)
+	return $ret
 }
 
 run_one_2sock() {
@@ -110,7 +122,9 @@
 	sleep 0.1
 	# first UDP GSO socket should be closed at this point
 	./udpgso_bench_tx ${tx_args}
+	ret=$?
 	wait $(jobs -p)
+	return $ret
 }
 
 run_nat_test() {
@@ -131,36 +145,54 @@
 	local -r core_args="-l 4"
 	local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
 	local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+	ret=0
 
 	echo "ipv4"
 	run_test "no GRO" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400"
+	check_err $?
 
 	# explicitly check we are not receiving UDP_SEGMENT cmsg (-S -1)
 	# when GRO does not take place
 	run_test "no GRO chk cmsg" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400 -S -1"
+	check_err $?
 
 	# the GSO packets are aggregated because:
 	# * veth schedule napi after each xmit
 	# * segmentation happens in BH context, veth napi poll is delayed after
 	#   the transmission of the last segment
 	run_test "GRO" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720"
+	check_err $?
 	run_test "GRO chk cmsg" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+	check_err $?
 	run_test "GRO with custom segment size" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720"
+	check_err $?
 	run_test "GRO with custom segment size cmsg" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720 -S 500"
+	check_err $?
 
 	run_nat_test "bad GRO lookup" "${ipv4_args} -M 1 -s 14720 -S 0" "-n 10 -l 1472"
+	check_err $?
 	run_2sock_test "multiple GRO socks" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+	check_err $?
 
 	echo "ipv6"
 	run_test "no GRO" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400"
+	check_err $?
 	run_test "no GRO chk cmsg" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400 -S -1"
+	check_err $?
 	run_test "GRO" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520"
+	check_err $?
 	run_test "GRO chk cmsg" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520 -S 1452"
+	check_err $?
 	run_test "GRO with custom segment size" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520"
+	check_err $?
 	run_test "GRO with custom segment size cmsg" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520 -S 500"
+	check_err $?
 
 	run_nat_test "bad GRO lookup" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 10 -l 1452"
+	check_err $?
 	run_2sock_test "multiple GRO socks" "${ipv6_args} -M 1 -s 14520 -S 0 " "-n 1 -l 14520 -S 1452"
+	check_err $?
+	return $ret
 }
 
 if [ ! -f ../bpf/xdp_dummy.o ]; then
@@ -180,3 +212,5 @@
 	shift
 	run_one_2sock $@
 fi
+
+exit $?
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index a374e10..3006a8e 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -4,7 +4,8 @@
 TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
 	conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
 	nft_concat_range.sh nft_conntrack_helper.sh \
-	nft_queue.sh nft_meta.sh
+	nft_queue.sh nft_meta.sh \
+	ipip-conntrack-mtu.sh
 
 LDLIBS = -lmnl
 TEST_GEN_FILES =  nf-queue
diff --git a/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh b/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh
new file mode 100755
index 0000000..4a6f5c3
--- /dev/null
+++ b/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh
@@ -0,0 +1,206 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# Conntrack needs to reassemble fragments in order to have complete
+# packets for rule matching.  Reassembly can lead to packet loss.
+
+# Consider the following setup:
+#            +--------+       +---------+       +--------+
+#            |Router A|-------|Wanrouter|-------|Router B|
+#            |        |.IPIP..|         |..IPIP.|        |
+#            +--------+       +---------+       +--------+
+#           /                  mtu 1400                   \
+#          /                                               \
+#+--------+                                                 +--------+
+#|Client A|                                                 |Client B|
+#|        |                                                 |        |
+#+--------+                                                 +--------+
+
+# Router A and Router B use IPIP tunnel interfaces to tunnel traffic
+# between Client A and Client B over WAN. Wanrouter has MTU 1400 set
+# on its interfaces.
+
+rnd=$(mktemp -u XXXXXXXX)
+rx=$(mktemp)
+
+r_a="ns-ra-$rnd"
+r_b="ns-rb-$rnd"
+r_w="ns-rw-$rnd"
+c_a="ns-ca-$rnd"
+c_b="ns-cb-$rnd"
+
+checktool (){
+	if ! $1 > /dev/null 2>&1; then
+		echo "SKIP: Could not $2"
+		exit $ksft_skip
+	fi
+}
+
+checktool "iptables --version" "run test without iptables"
+checktool "ip -Version" "run test without ip tool"
+checktool "which nc" "run test without nc (netcat)"
+checktool "ip netns add ${r_a}" "create net namespace"
+
+for n in ${r_b} ${r_w} ${c_a} ${c_b};do
+	ip netns add ${n}
+done
+
+cleanup() {
+	for n in ${r_a} ${r_b} ${r_w} ${c_a} ${c_b};do
+		ip netns del ${n}
+	done
+	rm -f ${rx}
+}
+
+trap cleanup EXIT
+
+test_path() {
+	msg="$1"
+
+	ip netns exec ${c_b} nc -n -w 3 -q 3 -u -l -p 5000 > ${rx} < /dev/null &
+
+	sleep 1
+	for i in 1 2 3; do
+		head -c1400 /dev/zero | tr "\000" "a" | ip netns exec ${c_a} nc -n -w 1 -u 192.168.20.2 5000
+	done
+
+	wait
+
+	bytes=$(wc -c < ${rx})
+
+	if [ $bytes -eq 1400 ];then
+		echo "OK: PMTU $msg connection tracking"
+	else
+		echo "FAIL: PMTU $msg connection tracking: got $bytes, expected 1400"
+		exit 1
+	fi
+}
+
+# Detailed setup for Router A
+# ---------------------------
+# Interfaces:
+# eth0: 10.2.2.1/24
+# eth1: 192.168.10.1/24
+# ipip0: No IP address, local 10.2.2.1 remote 10.4.4.1
+# Routes:
+# 192.168.20.0/24 dev ipip0    (192.168.20.0/24 is subnet of Client B)
+# 10.4.4.1 via 10.2.2.254      (Router B via Wanrouter)
+# No iptables rules at all.
+
+ip link add veth0 netns ${r_a} type veth peer name veth0 netns ${r_w}
+ip link add veth1 netns ${r_a} type veth peer name veth0 netns ${c_a}
+
+l_addr="10.2.2.1"
+r_addr="10.4.4.1"
+ip netns exec ${r_a} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip
+
+for dev in lo veth0 veth1 ipip0; do
+    ip -net ${r_a} link set $dev up
+done
+
+ip -net ${r_a} addr add 10.2.2.1/24 dev veth0
+ip -net ${r_a} addr add 192.168.10.1/24 dev veth1
+
+ip -net ${r_a} route add 192.168.20.0/24 dev ipip0
+ip -net ${r_a} route add 10.4.4.0/24 via 10.2.2.254
+
+ip netns exec ${r_a} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Detailed setup for Router B
+# ---------------------------
+# Interfaces:
+# eth0: 10.4.4.1/24
+# eth1: 192.168.20.1/24
+# ipip0: No IP address, local 10.4.4.1 remote 10.2.2.1
+# Routes:
+# 192.168.10.0/24 dev ipip0    (192.168.10.0/24 is subnet of Client A)
+# 10.2.2.1 via 10.4.4.254      (Router A via Wanrouter)
+# No iptables rules at all.
+
+ip link add veth0 netns ${r_b} type veth peer name veth1 netns ${r_w}
+ip link add veth1 netns ${r_b} type veth peer name veth0 netns ${c_b}
+
+l_addr="10.4.4.1"
+r_addr="10.2.2.1"
+
+ip netns exec ${r_b} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip
+
+for dev in lo veth0 veth1 ipip0; do
+	ip -net ${r_b} link set $dev up
+done
+
+ip -net ${r_b} addr add 10.4.4.1/24 dev veth0
+ip -net ${r_b} addr add 192.168.20.1/24 dev veth1
+
+ip -net ${r_b} route add 192.168.10.0/24 dev ipip0
+ip -net ${r_b} route add 10.2.2.0/24 via 10.4.4.254
+ip netns exec ${r_b} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Client A
+ip -net ${c_a} addr add 192.168.10.2/24 dev veth0
+ip -net ${c_a} link set dev lo up
+ip -net ${c_a} link set dev veth0 up
+ip -net ${c_a} route add default via 192.168.10.1
+
+# Client A
+ip -net ${c_b} addr add 192.168.20.2/24 dev veth0
+ip -net ${c_b} link set dev veth0 up
+ip -net ${c_b} link set dev lo up
+ip -net ${c_b} route add default via 192.168.20.1
+
+# Wan
+ip -net ${r_w} addr add 10.2.2.254/24 dev veth0
+ip -net ${r_w} addr add 10.4.4.254/24 dev veth1
+
+ip -net ${r_w} link set dev lo up
+ip -net ${r_w} link set dev veth0 up mtu 1400
+ip -net ${r_w} link set dev veth1 up mtu 1400
+
+ip -net ${r_a} link set dev veth0 mtu 1400
+ip -net ${r_b} link set dev veth0 mtu 1400
+
+ip netns exec ${r_w} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Path MTU discovery
+# ------------------
+# Running tracepath from Client A to Client B shows PMTU discovery is working
+# as expected:
+#
+# clienta:~# tracepath 192.168.20.2
+# 1?: [LOCALHOST]                      pmtu 1500
+# 1:  192.168.10.1                                          0.867ms
+# 1:  192.168.10.1                                          0.302ms
+# 2:  192.168.10.1                                          0.312ms pmtu 1480
+# 2:  no reply
+# 3:  192.168.10.1                                          0.510ms pmtu 1380
+# 3:  192.168.20.2                                          2.320ms reached
+# Resume: pmtu 1380 hops 3 back 3
+
+# ip netns exec ${c_a} traceroute --mtu 192.168.20.2
+
+# Router A has learned PMTU (1400) to Router B from Wanrouter.
+# Client A has learned PMTU (1400 - IPIP overhead = 1380) to Client B
+# from Router A.
+
+#Send large UDP packet
+#---------------------
+#Now we send a 1400 bytes UDP packet from Client A to Client B:
+
+# clienta:~# head -c1400 /dev/zero | tr "\000" "a" | nc -u 192.168.20.2 5000
+test_path "without"
+
+# The IPv4 stack on Client A already knows the PMTU to Client B, so the
+# UDP packet is sent as two fragments (1380 + 20). Router A forwards the
+# fragments between eth1 and ipip0. The fragments fit into the tunnel and
+# reach their destination.
+
+#When sending the large UDP packet again, Router A now reassembles the
+#fragments before routing the packet over ipip0. The resulting IPIP
+#packet is too big (1400) for the tunnel PMTU (1380) to Router B, it is
+#dropped on Router A before sending.
+
+ip netns exec ${r_a} iptables -A FORWARD -m conntrack --ctstate NEW
+test_path "with"
diff --git a/tools/testing/selftests/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);