Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

CREDITS

@@ -710,6 +710,10 @@ S: Las Cuevas 2385 - Bo Guemes
 S: Las Heras, Mendoza CP 5539
 S: Argentina
 
+N: Jay Cliburn
+E: jcliburn@gmail.com
+D: ATLX Ethernet drivers
+
 N: Steven P. Cole
 E: scole@lanl.gov
 E: elenstev@mesatop.com
@@ -1284,6 +1288,10 @@ D: Major kbuild rework during the 2.5 cycle
 D: ISDN Maintainer
 S: USA
 
+N: Gerrit Renker
+E: gerrit@erg.abdn.ac.uk
+D: DCCP protocol support.
+
 N: Philip Gladstone
 E: philip@gladstonefamily.net
 D: Kernel / timekeeping stuff
@@ -2138,6 +2146,10 @@ E: seasons@falcon.sch.bme.hu
 E: seasons@makosteszta.sote.hu
 D: Original author of software suspend
 
+N: Alexey Kuznetsov
+E: kuznet@ms2.inr.ac.ru
+D: Author and maintainer of large parts of the networking stack
+
 N: Jaroslav Kysela
 E: perex@perex.cz
 W: https://www.perex.cz
@@ -2696,6 +2708,10 @@ N: Wolfgang Muees
 E: wolfgang@iksw-muees.de
 D: Auerswald USB driver
 
+N: Shrijeet Mukherjee
+E: shrijeet@gmail.com
+D: Network routing domains (VRF).
+
 N: Paul Mundt
 E: paul.mundt@gmail.com
 D: SuperH maintainer
@@ -4110,6 +4126,10 @@ S: B-1206 Jingmao Guojigongyu
 S: 16 Baliqiao Nanjie, Beijing 101100
 S: People's Repulic of China
 
+N: Aviad Yehezkel
+E: aviadye@nvidia.com
+D: Kernel TLS implementation and offload support.
+
 N: Victor Yodaiken
 E: yodaiken@fsmlabs.com
 D: RTLinux (RealTime Linux)
@@ -4167,6 +4187,10 @@ S: 1507 145th Place SE #B5
 S: Bellevue, Washington 98007
 S: USA
 
+N: Wensong Zhang
+E: wensong@linux-vs.org
+D: IP virtual server (IPVS).
+
 N: Haojian Zhuang
 E: haojian.zhuang@gmail.com
 D: MMP support

Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst

@@ -473,7 +473,7 @@ read-side critical sections that follow the idle period (the oval near
 the bottom of the diagram above).
 
 Plumbing this into the full grace-period execution is described
-`below <#Forcing%20Quiescent%20States>`__.
+`below <Forcing Quiescent States_>`__.
 
 CPU-Hotplug Interface
 ^^^^^^^^^^^^^^^^^^^^^
@@ -494,7 +494,7 @@ mask to detect CPUs having gone offline since the beginning of this
 grace period.
 
 Plumbing this into the full grace-period execution is described
-`below <#Forcing%20Quiescent%20States>`__.
+`below <Forcing Quiescent States_>`__.
 
 Forcing Quiescent States
 ^^^^^^^^^^^^^^^^^^^^^^^^
@@ -532,7 +532,7 @@ from other CPUs.
 | RCU. But this diagram is complex enough as it is, so simplicity       |
 | overrode accuracy. You can think of it as poetic license, or you can  |
 | think of it as misdirection that is resolved in the                   |
-| `stitched-together diagram <#Putting%20It%20All%20Together>`__.       |
+| `stitched-together diagram <Putting It All Together_>`__.             |
 +-----------------------------------------------------------------------+
 
 Grace-Period Cleanup
@@ -596,7 +596,7 @@ maintain ordering. For example, if the callback function wakes up a task
 that runs on some other CPU, proper ordering must in place in both the
 callback function and the task being awakened. To see why this is
 important, consider the top half of the `grace-period
-cleanup <#Grace-Period%20Cleanup>`__ diagram. The callback might be
+cleanup`_ diagram. The callback might be
 running on a CPU corresponding to the leftmost leaf ``rcu_node``
 structure, and awaken a task that is to run on a CPU corresponding to
 the rightmost leaf ``rcu_node`` structure, and the grace-period kernel

Documentation/RCU/Design/Requirements/Requirements.rst

@@ -45,7 +45,7 @@ requirements:
 #. `Other RCU Flavors`_
 #. `Possible Future Changes`_
 
-This is followed by a `summary <#Summary>`__, however, the answers to
+This is followed by a summary_, however, the answers to
 each quick quiz immediately follows the quiz. Select the big white space
 with your mouse to see the answer.
 
@@ -1096,7 +1096,7 @@ memory barriers.
 | case, voluntary context switch) within an RCU read-side critical      |
 | section. However, sleeping locks may be used within userspace RCU     |
 | read-side critical sections, and also within Linux-kernel sleepable   |
-| RCU `(SRCU) <#Sleepable%20RCU>`__ read-side critical sections. In     |
+| RCU `(SRCU) <Sleepable RCU_>`__ read-side critical sections. In       |
 | addition, the -rt patchset turns spinlocks into a sleeping locks so   |
 | that the corresponding critical sections can be preempted, which also |
 | means that these sleeplockified spinlocks (but not other sleeping     |
@@ -1186,7 +1186,7 @@ non-preemptible (``CONFIG_PREEMPT=n``) kernels, and thus `tiny
 RCU <https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com>`__
 was born. Josh Triplett has since taken over the small-memory banner
 with his `Linux kernel tinification <https://tiny.wiki.kernel.org/>`__
-project, which resulted in `SRCU <#Sleepable%20RCU>`__ becoming optional
+project, which resulted in `SRCU <Sleepable RCU_>`__ becoming optional
 for those kernels not needing it.
 
 The remaining performance requirements are, for the most part,
@@ -1457,8 +1457,8 @@ will vary as the value of ``HZ`` varies, and can also be changed using
 the relevant Kconfig options and kernel boot parameters. RCU currently
 does not do much sanity checking of these parameters, so please use
 caution when changing them. Note that these forward-progress measures
-are provided only for RCU, not for `SRCU <#Sleepable%20RCU>`__ or `Tasks
+are provided only for RCU, not for `SRCU <Sleepable RCU_>`__ or `Tasks
-RCU <#Tasks%20RCU>`__.
+RCU`_.
 
 RCU takes the following steps in ``call_rcu()`` to encourage timely
 invocation of callbacks when any given non-\ ``rcu_nocbs`` CPU has
@@ -1477,8 +1477,8 @@ encouragement was provided:
 
 Again, these are default values when running at ``HZ=1000``, and can be
 overridden. Again, these forward-progress measures are provided only for
-RCU, not for `SRCU <#Sleepable%20RCU>`__ or `Tasks
+RCU, not for `SRCU <Sleepable RCU_>`__ or `Tasks
-RCU <#Tasks%20RCU>`__. Even for RCU, callback-invocation forward
+RCU`_. Even for RCU, callback-invocation forward
 progress for ``rcu_nocbs`` CPUs is much less well-developed, in part
 because workloads benefiting from ``rcu_nocbs`` CPUs tend to invoke
 ``call_rcu()`` relatively infrequently. If workloads emerge that need
@@ -1920,7 +1920,7 @@ Hotplug CPU
 
 The Linux kernel supports CPU hotplug, which means that CPUs can come
 and go. It is of course illegal to use any RCU API member from an
-offline CPU, with the exception of `SRCU <#Sleepable%20RCU>`__ read-side
+offline CPU, with the exception of `SRCU <Sleepable RCU_>`__ read-side
 critical sections. This requirement was present from day one in
 DYNIX/ptx, but on the other hand, the Linux kernel's CPU-hotplug
 implementation is “interesting.”
@@ -2177,7 +2177,7 @@ handles these states differently:
 However, RCU must be reliably informed as to whether any given CPU is
 currently in the idle loop, and, for ``NO_HZ_FULL``, also whether that
 CPU is executing in usermode, as discussed
-`earlier <#Energy%20Efficiency>`__. It also requires that the
+`earlier <Energy Efficiency_>`__. It also requires that the
 scheduling-clock interrupt be enabled when RCU needs it to be:
 
 #. If a CPU is either idle or executing in usermode, and RCU believes it
@@ -2294,7 +2294,7 @@ Performance, Scalability, Response Time, and Reliability
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Expanding on the `earlier
-discussion <#Performance%20and%20Scalability>`__, RCU is used heavily by
+discussion <Performance and Scalability_>`__, RCU is used heavily by
 hot code paths in performance-critical portions of the Linux kernel's
 networking, security, virtualization, and scheduling code paths. RCU
 must therefore use efficient implementations, especially in its

Documentation/admin-guide/binfmt-misc.rst

@@ -23,7 +23,7 @@ Here is what the fields mean:
 
 - ``name``
    is an identifier string. A new /proc file will be created with this
-   ``name below /proc/sys/fs/binfmt_misc``; cannot contain slashes ``/`` for
+   name below ``/proc/sys/fs/binfmt_misc``; cannot contain slashes ``/`` for
    obvious reasons.
 - ``type``
    is the type of recognition. Give ``M`` for magic and ``E`` for extension.
@@ -83,7 +83,7 @@ Here is what the fields mean:
       ``F`` - fix binary
             The usual behaviour of binfmt_misc is to spawn the
 	    binary lazily when the misc format file is invoked.  However,
-	    this doesn``t work very well in the face of mount namespaces and
+	    this doesn't work very well in the face of mount namespaces and
 	    changeroots, so the ``F`` mode opens the binary as soon as the
 	    emulation is installed and uses the opened image to spawn the
 	    emulator, meaning it is always available once installed,

Documentation/admin-guide/bootconfig.rst

@@ -154,7 +154,7 @@ get the boot configuration data.
 Because of this "piggyback" method, there is no need to change or
 update the boot loader and the kernel image itself as long as the boot
 loader passes the correct initrd file size. If by any chance, the boot
-loader passes a longer size, the kernel feils to find the bootconfig data.
+loader passes a longer size, the kernel fails to find the bootconfig data.
 
 To do this operation, Linux kernel provides "bootconfig" command under
 tools/bootconfig, which allows admin to apply or delete the config file

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
+The following is a consolidated list of the kernel parameters as implemented
-implemented by the __setup(), core_param() and module_param() macros
+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.

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]

Documentation/admin-guide/mm/concepts.rst

@@ -184,7 +184,7 @@ pages either asynchronously or synchronously, depending on the state
 of the system. When the system is not loaded, most of the memory is free
 and allocation requests will be satisfied immediately from the free
 pages supply. As the load increases, the amount of the free pages goes
-down and when it reaches a certain threshold (high watermark), an
+down and when it reaches a certain threshold (low watermark), an
 allocation request will awaken the ``kswapd`` daemon. It will
 asynchronously scan memory pages and either just free them if the data
 they contain is available elsewhere, or evict to the backing storage

Documentation/core-api/index.rst

@@ -53,7 +53,6 @@ How Linux keeps everything from happening at the same time.  See
 .. toctree::
    :maxdepth: 1
 
-   atomic_ops
    refcount-vs-atomic
    irq/index
    local_ops

Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml

@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
 %YAML 1.2
 ---
 $id: http://devicetree.org/schemas/dma/ti/k3-bcdma.yaml#
@@ -7,7 +9,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Texas Instruments K3 DMSS BCDMA Device Tree Bindings
 
 maintainers:
-  - Peter Ujfalusi <peter.ujfalusi@ti.com>
+  - Peter Ujfalusi <peter.ujfalusi@gmail.com>
 
 description: |
   The Block Copy DMA (BCDMA) is intended to perform similar functions as the TR

Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml

@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
 %YAML 1.2
 ---
 $id: http://devicetree.org/schemas/dma/ti/k3-pktdma.yaml#
@@ -7,7 +9,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Texas Instruments K3 DMSS PKTDMA Device Tree Bindings
 
 maintainers:
-  - Peter Ujfalusi <peter.ujfalusi@ti.com>
+  - Peter Ujfalusi <peter.ujfalusi@gmail.com>
 
 description: |
   The Packet DMA (PKTDMA) is intended to perform similar functions as the packet

Documentation/devicetree/bindings/dma/ti/k3-udma.yaml

@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2019 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
 %YAML 1.2
 ---
 $id: http://devicetree.org/schemas/dma/ti/k3-udma.yaml#
@@ -7,7 +9,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Texas Instruments K3 NAVSS Unified DMA Device Tree Bindings
 
 maintainers:
-  - Peter Ujfalusi <peter.ujfalusi@ti.com>
+  - Peter Ujfalusi <peter.ujfalusi@gmail.com>
 
 description: |
   The UDMA-P is intended to perform similar (but significantly upgraded)

Documentation/devicetree/bindings/net/renesas,etheravb.yaml

@@ -163,6 +163,7 @@ allOf:
             enum:
               - renesas,etheravb-r8a774a1
               - renesas,etheravb-r8a774b1
+              - renesas,etheravb-r8a774e1
               - renesas,etheravb-r8a7795
               - renesas,etheravb-r8a7796
               - renesas,etheravb-r8a77961

Documentation/devicetree/bindings/net/snps,dwmac.yaml

@@ -161,7 +161,8 @@ properties:
             * snps,route-dcbcp, DCB Control Packets
             * snps,route-up, Untagged Packets
             * snps,route-multi-broad, Multicast & Broadcast Packets
-          * snps,priority, RX queue priority (Range 0x0 to 0xF)
+          * snps,priority, bitmask of the tagged frames priorities assigned to
+            the queue
 
   snps,mtl-tx-config:
     $ref: /schemas/types.yaml#/definitions/phandle
@@ -188,7 +189,10 @@ properties:
             * snps,idle_slope, unlock on WoL
             * snps,high_credit, max write outstanding req. limit
             * snps,low_credit, max read outstanding req. limit
-          * snps,priority, TX queue priority (Range 0x0 to 0xF)
+          * snps,priority, bitmask of the priorities assigned to the queue.
+            When a PFC frame is received with priorities matching the bitmask,
+            the queue is blocked from transmitting for the pause time specified
+            in the PFC frame.
 
   snps,reset-gpio:
     deprecated: true

Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml

@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
 %YAML 1.2
 ---
 $id: http://devicetree.org/schemas/sound/ti,j721e-cpb-audio.yaml#
@@ -7,7 +9,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Texas Instruments J721e Common Processor Board Audio Support
 
 maintainers:
-  - Peter Ujfalusi <peter.ujfalusi@ti.com>
+  - Peter Ujfalusi <peter.ujfalusi@gmail.com>
 
 description: |
   The audio support on the board is using pcm3168a codec connected to McASP10

Documentation/devicetree/bindings/sound/ti,j721e-cpb-ivi-audio.yaml

@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
 %YAML 1.2
 ---
 $id: http://devicetree.org/schemas/sound/ti,j721e-cpb-ivi-audio.yaml#
@@ -7,7 +9,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Texas Instruments J721e Common Processor Board Audio Support
 
 maintainers:
-  - Peter Ujfalusi <peter.ujfalusi@ti.com>
+  - Peter Ujfalusi <peter.ujfalusi@gmail.com>
 
 description: |
   The Infotainment board plugs into the Common Processor Board, the support of the

Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml

@@ -11,8 +11,12 @@ maintainers:
 
 properties:
   compatible:
-    items:
+    oneOf:
       - const: ti,j721e-usb
+      - const: ti,am64-usb
+      - items:
+          - const: ti,j721e-usb
+          - const: ti,am64-usb
 
   reg:
     description: module registers

Documentation/doc-guide/sphinx.rst

@@ -48,12 +48,12 @@ or ``virtualenv``, depending on how your distribution packaged Python 3.
       those versions, you should run ``pip install 'docutils==0.12'``.
 
    #) It is recommended to use the RTD theme for html output. Depending
-      on the Sphinx version, it should be installed  in separate,
+      on the Sphinx version, it should be installed separately,
       with ``pip install sphinx_rtd_theme``.
 
-   #) Some ReST pages contain math expressions. Due to the way Sphinx work,
+   #) Some ReST pages contain math expressions. Due to the way Sphinx works,
       those expressions are written using LaTeX notation. It needs texlive
-      installed with amdfonts and amsmath in order to evaluate them.
+      installed with amsfonts and amsmath in order to evaluate them.
 
 In summary, if you want to install Sphinx version 1.7.9, you should do::
 
@@ -128,7 +128,7 @@ Sphinx Build
 ============
 
 The usual way to generate the documentation is to run ``make htmldocs`` or
-``make pdfdocs``. There are also other formats available, see the documentation
+``make pdfdocs``. There are also other formats available: see the documentation
 section of ``make help``. The generated documentation is placed in
 format-specific subdirectories under ``Documentation/output``.
 
@@ -303,17 +303,17 @@ and *targets* (e.g. a ref to ``:ref:`last row <last row>``` / :ref:`last row
         - head col 3
         - head col 4
 
-      * - column 1
+      * - row 1
         - field 1.1
         - field 1.2 with autospan
 
-      * - column 2
+      * - row 2
         - field 2.1
         - :rspan:`1` :cspan:`1` field 2.2 - 3.3
 
       * .. _`last row`:
 
-        - column 3
+        - row 3
 
 Rendered as:
 
@@ -325,17 +325,17 @@ Rendered as:
         - head col 3
         - head col 4
 
-      * - column 1
+      * - row 1
         - field 1.1
         - field 1.2 with autospan
 
-      * - column 2
+      * - row 2
         - field 2.1
         - :rspan:`1` :cspan:`1` field 2.2 - 3.3
 
       * .. _`last row`:
 
-        - column 3
+        - row 3
 
 Cross-referencing
 -----------------
@@ -361,7 +361,7 @@ Figures & Images
 
 If you want to add an image, you should use the ``kernel-figure`` and
 ``kernel-image`` directives. E.g. to insert a figure with a scalable
-image format use SVG (:ref:`svg_image_example`)::
+image format, use SVG (:ref:`svg_image_example`)::
 
     .. kernel-figure::  svg_image.svg
        :alt:    simple SVG image
@@ -375,7 +375,7 @@ image format use SVG (:ref:`svg_image_example`)::
 
    SVG image example
 
-The kernel figure (and image) directive support **DOT** formatted files, see
+The kernel figure (and image) directive supports **DOT** formatted files, see
 
 * DOT: http://graphviz.org/pdf/dotguide.pdf
 * Graphviz: http://www.graphviz.org/content/dot-language
@@ -394,7 +394,7 @@ A simple example (:ref:`hello_dot_file`)::
 
    DOT's hello world example
 
-Embed *render* markups (or languages) like Graphviz's **DOT** is provided by the
+Embedded *render* markups (or languages) like Graphviz's **DOT** are provided by the
 ``kernel-render`` directives.::
 
   .. kernel-render:: DOT
@@ -406,7 +406,7 @@ Embed *render* markups (or languages) like Graphviz's **DOT** is provided by the
      }
 
 How this will be rendered depends on the installed tools. If Graphviz is
-installed, you will see an vector image. If not the raw markup is inserted as
+installed, you will see a vector image. If not, the raw markup is inserted as
 *literal-block* (:ref:`hello_dot_render`).
 
 .. _hello_dot_render:
@@ -421,8 +421,8 @@ installed, you will see an vector image. If not the raw markup is inserted as
 
 The *render* directive has all the options known from the *figure* directive,
 plus option ``caption``.  If ``caption`` has a value, a *figure* node is
-inserted. If not, a *image* node is inserted. A ``caption`` is also needed, if
+inserted. If not, an *image* node is inserted. A ``caption`` is also needed, if
-you want to refer it (:ref:`hello_svg_render`).
+you want to refer to it (:ref:`hello_svg_render`).
 
 Embedded **SVG**::
 

Documentation/hwmon/sbtsi_temp.rst

@@ -1,7 +1,7 @@
 .. SPDX-License-Identifier: GPL-2.0-or-later
 
 Kernel driver sbtsi_temp
-==================
+========================
 
 Supported hardware:
 

Documentation/kbuild/makefiles.rst

@@ -598,7 +598,7 @@ more details, with real examples.
 	explicitly added to $(targets).
 
 	Assignments to $(targets) are without $(obj)/ prefix. if_changed may be
-	used in conjunction with custom rules as defined in "3.9 Custom Rules".
+	used in conjunction with custom rules as defined in "3.11 Custom Rules".
 
 	Note: It is a typical mistake to forget the FORCE prerequisite.
 	Another common pitfall is that whitespace is sometimes significant; for

Documentation/kernel-hacking/locking.rst

@@ -118,11 +118,11 @@ spinlock, but you may block holding a mutex. If you can't lock a mutex,
 your task will suspend itself, and be woken up when the mutex is
 released. This means the CPU can do something else while you are
 waiting. There are many cases when you simply can't sleep (see
-`What Functions Are Safe To Call From Interrupts? <#sleeping-things>`__),
+`What Functions Are Safe To Call From Interrupts?`_),
 and so have to use a spinlock instead.
 
 Neither type of lock is recursive: see
-`Deadlock: Simple and Advanced <#deadlock>`__.
+`Deadlock: Simple and Advanced`_.
 
 Locks and Uniprocessor Kernels
 ------------------------------
@@ -179,7 +179,7 @@ perfect world).
 
 Note that you can also use spin_lock_irq() or
 spin_lock_irqsave() here, which stop hardware interrupts
-as well: see `Hard IRQ Context <#hard-irq-context>`__.
+as well: see `Hard IRQ Context`_.
 
 This works perfectly for UP as well: the spin lock vanishes, and this
 macro simply becomes local_bh_disable()
@@ -230,7 +230,7 @@ The Same Softirq
 ~~~~~~~~~~~~~~~~
 
 The same softirq can run on the other CPUs: you can use a per-CPU array
-(see `Per-CPU Data <#per-cpu-data>`__) for better performance. If you're
+(see `Per-CPU Data`_) for better performance. If you're
 going so far as to use a softirq, you probably care about scalable
 performance enough to justify the extra complexity.
 

Documentation/networking/netdevices.rst

@@ -10,18 +10,177 @@ Introduction
 The following is a random collection of documentation regarding
 network devices.
 
-struct net_device allocation rules
+struct net_device lifetime rules
-==================================
+================================
 Network device structures need to persist even after module is unloaded and
 must be allocated with alloc_netdev_mqs() and friends.
 If device has registered successfully, it will be freed on last use
-by free_netdev(). This is required to handle the pathologic case cleanly
+by free_netdev(). This is required to handle the pathological case cleanly
-(example: rmmod mydriver </sys/class/net/myeth/mtu )
+(example: ``rmmod mydriver </sys/class/net/myeth/mtu``)
 
-alloc_netdev_mqs()/alloc_netdev() reserve extra space for driver
+alloc_netdev_mqs() / alloc_netdev() reserve extra space for driver
 private data which gets freed when the network device is freed. If
 separately allocated data is attached to the network device
-(netdev_priv(dev)) then it is up to the module exit handler to free that.
+(netdev_priv()) then it is up to the module exit handler to free that.
+
+There are two groups of APIs for registering struct net_device.
+First group can be used in normal contexts where ``rtnl_lock`` is not already
+held: register_netdev(), unregister_netdev().
+Second group can be used when ``rtnl_lock`` is already held:
+register_netdevice(), unregister_netdevice(), free_netdevice().
+
+Simple drivers
+--------------
+
+Most drivers (especially device drivers) handle lifetime of struct net_device
+in context where ``rtnl_lock`` is not held (e.g. driver probe and remove paths).
+
+In that case the struct net_device registration is done using
+the register_netdev(), and unregister_netdev() functions:
+
+.. code-block:: c
+
+  int probe()
+  {
+    struct my_device_priv *priv;
+    int err;
+
+    dev = alloc_netdev_mqs(...);
+    if (!dev)
+      return -ENOMEM;
+    priv = netdev_priv(dev);
+
+    /* ... do all device setup before calling register_netdev() ...
+     */
+
+    err = register_netdev(dev);
+    if (err)
+      goto err_undo;
+
+    /* net_device is visible to the user! */
+
+  err_undo:
+    /* ... undo the device setup ... */
+    free_netdev(dev);
+    return err;
+  }
+
+  void remove()
+  {
+    unregister_netdev(dev);
+    free_netdev(dev);
+  }
+
+Note that after calling register_netdev() the device is visible in the system.
+Users can open it and start sending / receiving traffic immediately,
+or run any other callback, so all initialization must be done prior to
+registration.
+
+unregister_netdev() closes the device and waits for all users to be done
+with it. The memory of struct net_device itself may still be referenced
+by sysfs but all operations on that device will fail.
+
+free_netdev() can be called after unregister_netdev() returns on when
+register_netdev() failed.
+
+Device management under RTNL
+----------------------------
+
+Registering struct net_device while in context which already holds
+the ``rtnl_lock`` requires extra care. In those scenarios most drivers
+will want to make use of struct net_device's ``needs_free_netdev``
+and ``priv_destructor`` members for freeing of state.
+
+Example flow of netdev handling under ``rtnl_lock``:
+
+.. code-block:: c
+
+  static void my_setup(struct net_device *dev)
+  {
+    dev->needs_free_netdev = true;
+  }
+
+  static void my_destructor(struct net_device *dev)
+  {
+    some_obj_destroy(priv->obj);
+    some_uninit(priv);
+  }
+
+  int create_link()
+  {
+    struct my_device_priv *priv;
+    int err;
+
+    ASSERT_RTNL();
+
+    dev = alloc_netdev(sizeof(*priv), "net%d", NET_NAME_UNKNOWN, my_setup);
+    if (!dev)
+      return -ENOMEM;
+    priv = netdev_priv(dev);
+
+    /* Implicit constructor */
+    err = some_init(priv);
+    if (err)
+      goto err_free_dev;
+
+    priv->obj = some_obj_create();
+    if (!priv->obj) {
+      err = -ENOMEM;
+      goto err_some_uninit;
+    }
+    /* End of constructor, set the destructor: */
+    dev->priv_destructor = my_destructor;
+
+    err = register_netdevice(dev);
+    if (err)
+      /* register_netdevice() calls destructor on failure */
+      goto err_free_dev;
+
+    /* If anything fails now unregister_netdevice() (or unregister_netdev())
+     * will take care of calling my_destructor and free_netdev().
+     */
+
+    return 0;
+
+  err_some_uninit:
+    some_uninit(priv);
+  err_free_dev:
+    free_netdev(dev);
+    return err;
+  }
+
+If struct net_device.priv_destructor is set it will be called by the core
+some time after unregister_netdevice(), it will also be called if
+register_netdevice() fails. The callback may be invoked with or without
+``rtnl_lock`` held.
+
+There is no explicit constructor callback, driver "constructs" the private
+netdev state after allocating it and before registration.
+
+Setting struct net_device.needs_free_netdev makes core call free_netdevice()
+automatically after unregister_netdevice() when all references to the device
+are gone. It only takes effect after a successful call to register_netdevice()
+so if register_netdevice() fails driver is responsible for calling
+free_netdev().
+
+free_netdev() is safe to call on error paths right after unregister_netdevice()
+or when register_netdevice() fails. Parts of netdev (de)registration process
+happen after ``rtnl_lock`` is released, therefore in those cases free_netdev()
+will defer some of the processing until ``rtnl_lock`` is released.
+
+Devices spawned from struct rtnl_link_ops should never free the
+struct net_device directly.
+
+.ndo_init and .ndo_uninit
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+``.ndo_init`` and ``.ndo_uninit`` callbacks are called during net_device
+registration and de-registration, under ``rtnl_lock``. Drivers can use
+those e.g. when parts of their init process need to run under ``rtnl_lock``.
+
+``.ndo_init`` runs before device is visible in the system, ``.ndo_uninit``
+runs during de-registering after device is closed but other subsystems
+may still have outstanding references to the netdevice.
 
 MTU
 ===

Documentation/networking/tls-offload.rst

@@ -530,7 +530,7 @@ TLS device feature flags only control adding of new TLS connection
 offloads, old connections will remain active after flags are cleared.
 
 TLS encryption cannot be offloaded to devices without checksum calculation
-offload. Hence, TLS TX device feature flag requires NETIF_F_HW_CSUM being set.
+offload. Hence, TLS TX device feature flag requires TX csum offload being set.
 Disabling the latter implies clearing the former. Disabling TX checksum offload
 should not affect old connections, and drivers should make sure checksum
 calculation does not break for them.

Documentation/process/4.Coding.rst

@@ -249,10 +249,8 @@ features; most of these are found in the "kernel hacking" submenu.  Several
 of these options should be turned on for any kernel used for development or
 testing purposes.  In particular, you should turn on:
 
- - ENABLE_MUST_CHECK and FRAME_WARN to get an
+ - FRAME_WARN to get warnings for stack frames larger than a given amount.
-   extra set of warnings for problems like the use of deprecated interfaces
+   The output generated can be verbose, but one need not worry about
-   or ignoring an important return value from a function.  The output
-   generated by these warnings 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

Documentation/sound/alsa-configuration.rst

@@ -1501,7 +1501,7 @@ Module for Digigram miXart8 sound cards.
 
 This module supports multiple cards.
 Note: One miXart8 board will be represented as 4 alsa cards.
-See MIXART.txt for details.
+See Documentation/sound/cards/mixart.rst for details.
 
 When the driver is compiled as a module and the hotplug firmware
 is supported, the firmware data is loaded via hotplug automatically.

Documentation/sound/kernel-api/writing-an-alsa-driver.rst

@@ -71,7 +71,7 @@ core/oss
 The codes for PCM and mixer OSS emulation modules are stored in this
 directory. The rawmidi OSS emulation is included in the ALSA rawmidi
 code since it's quite small. The sequencer code is stored in
-``core/seq/oss`` directory (see `below <#core-seq-oss>`__).
+``core/seq/oss`` directory (see `below <core/seq/oss_>`__).
 
 core/seq
 ~~~~~~~~
@@ -382,7 +382,7 @@ where ``enable[dev]`` is the module option.
 Each time the ``probe`` callback is called, check the availability of
 the device. If not available, simply increment the device index and
 returns. dev will be incremented also later (`step 7
-<#set-the-pci-driver-data-and-return-zero>`__).
+<7) Set the PCI driver data and return zero._>`__).
 
 2) Create a card instance
 ~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -450,10 +450,10 @@ field contains the information shown in ``/proc/asound/cards``.
 5) Create other components, such as mixer, MIDI, etc.
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Here you define the basic components such as `PCM <#PCM-Interface>`__,
+Here you define the basic components such as `PCM <PCM Interface_>`__,
-mixer (e.g. `AC97 <#API-for-AC97-Codec>`__), MIDI (e.g.
+mixer (e.g. `AC97 <API for AC97 Codec_>`__), MIDI (e.g.
-`MPU-401 <#MIDI-MPU401-UART-Interface>`__), and other interfaces.
+`MPU-401 <MIDI (MPU401-UART) Interface_>`__), and other interfaces.
-Also, if you want a `proc file <#Proc-Interface>`__, define it here,
+Also, if you want a `proc file <Proc Interface_>`__, define it here,
 too.
 
 6) Register the card instance.
@@ -941,7 +941,7 @@ The allocation of an interrupt source is done like this:
   chip->irq = pci->irq;
 
 where :c:func:`snd_mychip_interrupt()` is the interrupt handler
-defined `later <#pcm-interface-interrupt-handler>`__. Note that
+defined `later <PCM Interrupt Handler_>`__. Note that
 ``chip->irq`` should be defined only when :c:func:`request_irq()`
 succeeded.
 
@@ -3104,7 +3104,7 @@ processing the output stream in the irq handler.
 
 If the MPU-401 interface shares its interrupt with the other logical
 devices on the card, set ``MPU401_INFO_IRQ_HOOK`` (see
-`below <#MIDI-Interrupt-Handler>`__).
+`below <MIDI Interrupt Handler_>`__).
 
 Usually, the port address corresponds to the command port and port + 1
 corresponds to the data port. If not, you may change the ``cport``

Documentation/virt/kvm/api.rst

@@ -392,9 +392,14 @@ This ioctl is obsolete and has been removed.
 
 Errors:
 
-  =====      =============================
+  =======    ==============================================================
   EINTR      an unmasked signal is pending
-  =====      =============================
+  ENOEXEC    the vcpu hasn't been initialized or the guest tried to execute
+             instructions from device memory (arm64)
+  ENOSYS     data abort outside memslots with no syndrome info and
+             KVM_CAP_ARM_NISV_TO_USER not enabled (arm64)
+  EPERM      SVE feature set but not finalized (arm64)
+  =======    ==============================================================
 
 This ioctl is used to run a guest virtual cpu.  While there are no
 explicit parameters, there is an implicit parameter block that can be

MAINTAINERS

@@ -820,7 +820,6 @@ M:	Netanel Belgazal <netanel@amazon.com>
 M:	Arthur Kiyanovski <akiyano@amazon.com>
 R:	Guy Tzalik <gtzalik@amazon.com>
 R:	Saeed Bishara <saeedb@amazon.com>
-R:	Zorik Machulsky <zorik@amazon.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/device_drivers/ethernet/amazon/ena.rst
@@ -2942,7 +2941,6 @@ S:	Maintained
 F:	drivers/hwmon/asus_atk0110.c
 
 ATLX ETHERNET DRIVERS
-M:	Jay Cliburn <jcliburn@gmail.com>
 M:	Chris Snook <chris.snook@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -3895,7 +3893,7 @@ F:	drivers/mtd/nand/raw/cadence-nand-controller.c
 CADENCE USB3 DRD IP DRIVER
 M:	Peter Chen <peter.chen@nxp.com>
 M:	Pawel Laszczak <pawell@cadence.com>
-M:	Roger Quadros <rogerq@ti.com>
+R:	Roger Quadros <rogerq@kernel.org>
 R:	Aswath Govindraju <a-govindraju@ti.com>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
@@ -4937,9 +4935,8 @@ F:	Documentation/scsi/dc395x.rst
 F:	drivers/scsi/dc395x.*
 
 DCCP PROTOCOL
-M:	Gerrit Renker <gerrit@erg.abdn.ac.uk>
 L:	dccp@vger.kernel.org
-S:	Maintained
+S:	Orphan
 W:	http://www.linuxfoundation.org/collaborate/workgroups/networking/dccp
 F:	include/linux/dccp.h
 F:	include/linux/tfrc.h
@@ -7378,7 +7375,6 @@ L:	linux-hardening@vger.kernel.org
 S:	Maintained
 F:	Documentation/kbuild/gcc-plugins.rst
 F:	scripts/Makefile.gcc-plugins
-F:	scripts/gcc-plugin.sh
 F:	scripts/gcc-plugins/
 
 GCOV BASED KERNEL PROFILING
@@ -9255,7 +9251,7 @@ F:	tools/testing/selftests/sgx/*
 K:	\bSGX_
 
 INTERCONNECT API
-M:	Georgi Djakov <georgi.djakov@linaro.org>
+M:	Georgi Djakov <djakov@kernel.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/interconnect/
@@ -9288,7 +9284,7 @@ F:	drivers/net/ethernet/sgi/ioc3-eth.c
 
 IOMAP FILESYSTEM LIBRARY
 M:	Christoph Hellwig <hch@infradead.org>
-M:	Darrick J. Wong <darrick.wong@oracle.com>
+M:	Darrick J. Wong <djwong@kernel.org>
 M:	linux-xfs@vger.kernel.org
 M:	linux-fsdevel@vger.kernel.org
 L:	linux-xfs@vger.kernel.org
@@ -9342,7 +9338,6 @@ W:	http://www.adaptec.com/
 F:	drivers/scsi/ips*
 
 IPVS
-M:	Wensong Zhang <wensong@linux-vs.org>
 M:	Simon Horman <horms@verge.net.au>
 M:	Julian Anastasov <ja@ssi.bg>
 L:	netdev@vger.kernel.org
@@ -9791,7 +9786,7 @@ F:	tools/testing/selftests/kvm/s390x/
 
 KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86)
 M:	Paolo Bonzini <pbonzini@redhat.com>
-R:	Sean Christopherson <sean.j.christopherson@intel.com>
+R:	Sean Christopherson <seanjc@google.com>
 R:	Vitaly Kuznetsov <vkuznets@redhat.com>
 R:	Wanpeng Li <wanpengli@tencent.com>
 R:	Jim Mattson <jmattson@google.com>
@@ -10275,7 +10270,6 @@ S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	Documentation/atomic_bitops.txt
 F:	Documentation/atomic_t.txt
-F:	Documentation/core-api/atomic_ops.rst
 F:	Documentation/core-api/refcount-vs-atomic.rst
 F:	Documentation/litmus-tests/
 F:	Documentation/memory-barriers.txt
@@ -12433,7 +12427,6 @@ F:	tools/testing/selftests/net/ipsec.c
 
 NETWORKING [IPv4/IPv6]
 M:	"David S. Miller" <davem@davemloft.net>
-M:	Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
 M:	Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -12490,7 +12483,6 @@ F:	net/ipv6/tcp*.c
 
 NETWORKING [TLS]
 M:	Boris Pismenny <borisp@nvidia.com>
-M:	Aviad Yehezkel <aviadye@nvidia.com>
 M:	John Fastabend <john.fastabend@gmail.com>
 M:	Daniel Borkmann <daniel@iogearbox.net>
 M:	Jakub Kicinski <kuba@kernel.org>
@@ -12865,7 +12857,7 @@ F:	include/misc/ocxl*
 F:	include/uapi/misc/ocxl.h
 
 OMAP AUDIO SUPPORT
-M:	Peter Ujfalusi <peter.ujfalusi@ti.com>
+M:	Peter Ujfalusi <peter.ujfalusi@gmail.com>
 M:	Jarkko Nikula <jarkko.nikula@bitmer.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 L:	linux-omap@vger.kernel.org
@@ -16725,6 +16717,8 @@ M:	Samuel Thibault <samuel.thibault@ens-lyon.org>
 L:	speakup@linux-speakup.org
 S:	Odd Fixes
 W:	http://www.linux-speakup.org/
+W:	https://github.com/linux-speakup/speakup
+B:	https://github.com/linux-speakup/speakup/issues
 F:	drivers/accessibility/speakup/
 
 SPEAR CLOCK FRAMEWORK SUPPORT
@@ -17556,7 +17550,7 @@ F:	arch/xtensa/
 F:	drivers/irqchip/irq-xtensa-*
 
 TEXAS INSTRUMENTS ASoC DRIVERS
-M:	Peter Ujfalusi <peter.ujfalusi@ti.com>
+M:	Peter Ujfalusi <peter.ujfalusi@gmail.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Maintained
 F:	sound/soc/ti/
@@ -17568,6 +17562,19 @@ S:	Supported
 F:	Documentation/devicetree/bindings/iio/dac/ti,dac7612.txt
 F:	drivers/iio/dac/ti-dac7612.c
 
+TEXAS INSTRUMENTS DMA DRIVERS
+M:	Peter Ujfalusi <peter.ujfalusi@gmail.com>
+L:	dmaengine@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt
+F:	Documentation/devicetree/bindings/dma/ti-edma.txt
+F:	Documentation/devicetree/bindings/dma/ti/
+F:	drivers/dma/ti/
+X:	drivers/dma/ti/cppi41.c
+F:	include/linux/dma/k3-udma-glue.h
+F:	include/linux/dma/ti-cppi5.h
+F:	include/linux/dma/k3-psil.h
+
 TEXAS INSTRUMENTS' SYSTEM CONTROL INTERFACE (TISCI) PROTOCOL DRIVER
 M:	Nishanth Menon <nm@ti.com>
 M:	Tero Kristo <t-kristo@ti.com>
@@ -17853,7 +17860,7 @@ F:	Documentation/devicetree/bindings/net/nfc/trf7970a.txt
 F:	drivers/nfc/trf7970a.c
 
 TI TWL4030 SERIES SOC CODEC DRIVER
-M:	Peter Ujfalusi <peter.ujfalusi@ti.com>
+M:	Peter Ujfalusi <peter.ujfalusi@gmail.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Maintained
 F:	sound/soc/codecs/twl4030*
@@ -19073,7 +19080,6 @@ K:	regulator_get_optional
 
 VRF
 M:	David Ahern <dsahern@kernel.org>
-M:	Shrijeet Mukherjee <shrijeet@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/vrf.rst
@@ -19520,7 +19526,7 @@ F:	arch/x86/xen/*swiotlb*
 F:	drivers/xen/*swiotlb*
 
 XFS FILESYSTEM
-M:	Darrick J. Wong <darrick.wong@oracle.com>
+M:	Darrick J. Wong <djwong@kernel.org>
 M:	linux-xfs@vger.kernel.org
 L:	linux-xfs@vger.kernel.org
 S:	Supported

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 11
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*

arch/Kconfig

@@ -1105,6 +1105,12 @@ config HAVE_ARCH_PFN_VALID
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	bool
 
+config ARCH_SPLIT_ARG64
+	bool
+	help
+	   If a 32-bit architecture requires 64-bit arguments to be split into
+	   pairs of 32-bit arguments, select this option.
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"

arch/arc/include/asm/page.h

@@ -10,6 +10,7 @@
 #ifndef __ASSEMBLY__
 
 #define clear_page(paddr)		memset((paddr), 0, PAGE_SIZE)
+#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
 #define copy_page(to, from)		memcpy((to), (from), PAGE_SIZE)
 
 struct vm_area_struct;

arch/arc/kernel/entry.S

@@ -307,7 +307,7 @@ resume_user_mode_begin:
 	mov r0, sp	; pt_regs for arg to do_signal()/do_notify_resume()
 
 	GET_CURR_THR_INFO_FLAGS   r9
-	and.f  0,  r9, TIF_SIGPENDING|TIF_NOTIFY_SIGNAL
+	and.f  0,  r9, _TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL
 	bz .Lchk_notify_resume
 
 	; Normal Trap/IRQ entry only saves Scratch (caller-saved) regs

arch/arc/plat-hsdk/Kconfig

@@ -7,6 +7,7 @@ menuconfig ARC_SOC_HSDK
 	depends on ISA_ARCV2
 	select ARC_HAS_ACCL_REGS
 	select ARC_IRQ_NO_AUTOSAVE
+	select ARC_FPU_SAVE_RESTORE
 	select CLK_HSDK
 	select RESET_CONTROLLER
 	select RESET_HSDK

arch/arm/boot/dts/omap3-n950-n9.dtsi

@@ -494,3 +494,11 @@
 		clock-names = "sysclk";
 	};
 };
+
+&aes1_target {
+	status = "disabled";
+};
+
+&aes2_target {
+	status = "disabled";
+};

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>;
 		};
 	};

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>;

arch/arm/configs/omap2plus_defconfig

@@ -279,6 +279,7 @@ CONFIG_SERIAL_OMAP_CONSOLE=y
 CONFIG_SERIAL_DEV_BUS=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_SPI=y
+CONFIG_SPI_GPIO=m
 CONFIG_SPI_OMAP24XX=y
 CONFIG_SPI_TI_QSPI=m
 CONFIG_HSI=m
@@ -296,7 +297,6 @@ CONFIG_GPIO_TWL4030=y
 CONFIG_W1=m
 CONFIG_HDQ_MASTER_OMAP=m
 CONFIG_W1_SLAVE_DS250X=m
-CONFIG_POWER_AVS=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_GPIO=y
 CONFIG_BATTERY_BQ27XXX=m

arch/arm/mach-omap2/omap_device.c

@@ -230,11 +230,13 @@ static int _omap_device_notifier_call(struct notifier_block *nb,
 		break;
 	case BUS_NOTIFY_BIND_DRIVER:
 		od = to_omap_device(pdev);
-		if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) &&
+		if (od) {
-		    pm_runtime_status_suspended(dev)) {
 			od->_driver_status = BUS_NOTIFY_BIND_DRIVER;
+			if (od->_state == OMAP_DEVICE_STATE_ENABLED &&
+			    pm_runtime_status_suspended(dev)) {
 				pm_runtime_set_active(dev);
 			}
+		}
 		break;
 	case BUS_NOTIFY_ADD_DEVICE:
 		if (pdev->dev.of_node)

arch/arm/mach-omap2/pmic-cpcap.c

@@ -71,7 +71,7 @@ static struct omap_voltdm_pmic omap_cpcap_iva = {
 	.vp_vstepmin = OMAP4_VP_VSTEPMIN_VSTEPMIN,
 	.vp_vstepmax = OMAP4_VP_VSTEPMAX_VSTEPMAX,
 	.vddmin = 900000,
-	.vddmax = 1350000,
+	.vddmax = 1375000,
 	.vp_timeout_us = OMAP4_VP_VLIMITTO_TIMEOUT_US,
 	.i2c_slave_addr = 0x44,
 	.volt_reg_addr = 0x0,

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 @@ KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__AARCH64EB__
 # Prefer the baremetal ELF build target, but not all toolchains include
 # it so fall back to the standard linux version if needed.
-KBUILD_LDFLAGS	+= -EB $(call ld-option, -maarch64elfb, -maarch64linuxb)
+KBUILD_LDFLAGS	+= -EB $(call ld-option, -maarch64elfb, -maarch64linuxb -z norelro)
 UTS_MACHINE	:= aarch64_be
 else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 CHECKFLAGS	+= -D__AARCH64EL__
 # Same as above, prefer ELF but fall back to linux target if needed.
-KBUILD_LDFLAGS	+= -EL $(call ld-option, -maarch64elf, -maarch64linux)
+KBUILD_LDFLAGS	+= -EL $(call ld-option, -maarch64elf, -maarch64linux -z norelro)
 UTS_MACHINE	:= aarch64
 endif
 
+ifeq ($(CONFIG_LD_IS_LLD), y)
+KBUILD_LDFLAGS	+= -z norelro
+endif
+
 CHECKFLAGS	+= -D__aarch64__
 
 ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y)

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>;

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_host_data {
 	struct kvm_pmu_events pmu_events;
 };
 
+struct kvm_host_psci_config {
+	/* PSCI version used by host. */
+	u32 version;
+
+	/* Function IDs used by host if version is v0.1. */
+	struct psci_0_1_function_ids function_ids_0_1;
+
+	bool psci_0_1_cpu_suspend_implemented;
+	bool psci_0_1_cpu_on_implemented;
+	bool psci_0_1_cpu_off_implemented;
+	bool psci_0_1_migrate_implemented;
+};
+
+extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config);
+#define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config)
+
+extern s64 kvm_nvhe_sym(hyp_physvirt_offset);
+#define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset)
+
+extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS];
+#define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map)
+
 struct vcpu_reset_state {
 	unsigned long	pc;
 	unsigned long	r0;

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

arch/arm64/include/asm/uaccess.h

@@ -176,10 +176,21 @@ static inline void __uaccess_enable_hw_pan(void)
  * 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_disable_privileged(void)
 
 static inline void uaccess_enable_privileged(void)
 {
-	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1),
+	__uaccess_enable_tco();
-				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
 
 	if (uaccess_ttbr0_enable())
 		return;

arch/arm64/kernel/cpufeature.c

@@ -2568,7 +2568,7 @@ static void verify_hyp_capabilities(void)
 	int parange, ipa_max;
 	unsigned int safe_vmid_bits, vmid_bits;
 
-	if (!IS_ENABLED(CONFIG_KVM) || !IS_ENABLED(CONFIG_KVM_ARM_HOST))
+	if (!IS_ENABLED(CONFIG_KVM))
 		return;
 
 	safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);

arch/arm64/kernel/entry.S

@@ -182,7 +182,6 @@ alternative_else_nop_endif
 	mrs_s	\tmp2, SYS_GCR_EL1
 	bfi	\tmp2, \tmp, #0, #16
 	msr_s	SYS_GCR_EL1, \tmp2
-	isb
 #endif
 	.endm
 
@@ -194,6 +193,7 @@ alternative_else_nop_endif
 	ldr_l	\tmp, gcr_kernel_excl
 
 	mte_set_gcr \tmp, \tmp2
+	isb
 1:
 #endif
 	.endm

arch/arm64/kernel/smp.c

@@ -434,7 +434,7 @@ static void __init hyp_mode_check(void)
 			   "CPU: CPUs started in inconsistent modes");
 	else
 		pr_info("CPU: All CPU(s) started at EL1\n");
-	if (IS_ENABLED(CONFIG_KVM))
+	if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode())
 		kvm_compute_layout();
 }
 
@@ -807,7 +807,6 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	unsigned int cpu, i;
 
 	for (i = 0; i < NR_IPI; i++) {
-		unsigned int irq = irq_desc_get_irq(ipi_desc[i]);
 		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
 			   prec >= 4 ? " " : "");
 		for_each_online_cpu(cpu)

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>
 

arch/arm64/kernel/vdso/Makefile

@@ -24,8 +24,7 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti
 # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so
 # preparation in build-time C")).
 ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv	\
-	     -Bsymbolic $(call ld-option, --no-eh-frame-hdr) --build-id=sha1 -n	\
+	     -Bsymbolic --build-id=sha1 -n $(btildflags-y) -T
-	     $(btildflags-y) -T
 
 ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
 ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO

arch/arm64/kernel/vdso/vdso.lds.S

@@ -40,9 +40,6 @@ SECTIONS
 	PROVIDE (_etext = .);
 	PROVIDE (etext = .);
 
-	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
-	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
-
 	.dynamic	: { *(.dynamic) }		:text	:dynamic
 
 	.rodata		: { *(.rodata*) }		:text
@@ -54,6 +51,7 @@ SECTIONS
 		*(.note.GNU-stack)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
+		*(.eh_frame .eh_frame_hdr)
 	}
 }
 
@@ -66,7 +64,6 @@ PHDRS
 	text		PT_LOAD		FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
 	dynamic		PT_DYNAMIC	FLAGS(4);		/* PF_R */
 	note		PT_NOTE		FLAGS(4);		/* PF_R */
-	eh_frame_hdr	PT_GNU_EH_FRAME;
 }
 
 /*

arch/arm64/kvm/Kconfig

@@ -49,14 +49,6 @@ if KVM
 
 source "virt/kvm/Kconfig"
 
-config KVM_ARM_PMU
-	bool "Virtual Performance Monitoring Unit (PMU) support"
-	depends on HW_PERF_EVENTS
-	default y
-	help
-	  Adds support for a virtual Performance Monitoring Unit (PMU) in
-	  virtual machines.
-
 endif # KVM
 
 endif # VIRTUALIZATION

arch/arm64/kvm/Makefile

@@ -24,4 +24,4 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \
 	 vgic/vgic-its.o vgic/vgic-debug.o
 
-kvm-$(CONFIG_KVM_ARM_PMU)  += pmu-emul.o
+kvm-$(CONFIG_HW_PERF_EVENTS)  += pmu-emul.o

arch/arm64/kvm/arch_timer.c

@@ -1129,9 +1129,10 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 	if (!irqchip_in_kernel(vcpu->kvm))
 		goto no_vgic;
 
-	if (!vgic_initialized(vcpu->kvm))
+	/*
-		return -ENODEV;
+	 * At this stage, we have the guarantee that the vgic is both
-
+	 * available and initialized.
+	 */
 	if (!timer_irqs_are_valid(vcpu)) {
 		kvm_debug("incorrectly configured timer irqs\n");
 		return -EINVAL;

arch/arm64/kvm/arm.c

@@ -65,10 +65,6 @@ static bool vgic_present;
 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 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 		 * Map the VGIC hardware resources before running a vcpu the
 		 * first time on this VM.
 		 */
-		if (unlikely(!vgic_ready(kvm))) {
 		ret = kvm_vgic_map_resources(kvm);
 		if (ret)
 			return ret;
-		}
 	} else {
 		/*
 		 * Tell the rest of the code that there are userspace irqchip
@@ -1574,12 +1568,12 @@ static struct notifier_block hyp_init_cpu_pm_nb = {
 	.notifier_call = hyp_init_cpu_pm_notifier,
 };
 
-static void __init hyp_cpu_pm_init(void)
+static void hyp_cpu_pm_init(void)
 {
 	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 @@ static void init_cpu_logical_map(void)
 	 * 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 @@ static bool init_psci_relay(void)
 		return false;
 	}
 
-	kvm_nvhe_sym(kvm_host_psci_version) = psci_ops.get_version();
+	kvm_host_psci_config.version = psci_ops.get_version();
-	kvm_nvhe_sym(kvm_host_psci_0_1_function_ids) = get_psci_0_1_function_ids();
+
+	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;
 }
 

arch/arm64/kvm/hyp/include/hyp/adjust_pc.h

@@ -59,4 +59,13 @@ static inline void __adjust_pc(struct kvm_vcpu *vcpu)
 	}
 }
 
+/*
+ * 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

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -157,11 +157,6 @@ static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt)
 	__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 @@ static void handle_host_smc(struct kvm_cpu_context *host_ctxt)
 	if (!handled)
 		default_host_smc_handler(host_ctxt);
 
-	/*
+	/* SMC was trapped, move ELR past the current PC. */
-	 * Unlike HVC, the return address of an SMC is the instruction's PC.
+	kvm_skip_host_instr();
-	 * Move the return address past the instruction.
-	 */
-	skip_host_instruction();
 }
 
 void handle_trap(struct kvm_cpu_context *host_ctxt)

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)

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 kvm_hyp_cpu_resume(unsigned long r0);
 void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt);
 
 /* Config options set by the host. */
-__ro_after_init u32 kvm_host_psci_version;
+struct kvm_host_psci_config __ro_after_init kvm_host_psci_config;
-__ro_after_init struct psci_0_1_function_ids kvm_host_psci_0_1_function_ids;
+s64 __ro_after_init hyp_physvirt_offset;
-__ro_after_init s64 hyp_physvirt_offset;
 
 #define __hyp_pa(x) ((phys_addr_t)((x)) + hyp_physvirt_offset)
 
@@ -47,19 +43,16 @@ struct psci_boot_args {
 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)
+#define	is_psci_0_1(what, func_id)					\
-{
+	(kvm_host_psci_config.psci_0_1_ ## what ## _implemented &&	\
-	DECLARE_REG(u64, func_id, host_ctxt, 0);
+	 (func_id) == kvm_host_psci_config.function_ids_0_1.what)
-
-	return func_id;
-}
 
 static bool is_psci_0_1_call(u64 func_id)
 {
-	return (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend) ||
+	return (is_psci_0_1(cpu_suspend, func_id) ||
-	       (func_id == kvm_host_psci_0_1_function_ids.cpu_on) ||
+		is_psci_0_1(cpu_on, func_id) ||
-	       (func_id == kvm_host_psci_0_1_function_ids.cpu_off) ||
+		is_psci_0_1(cpu_off, func_id) ||
-	       (func_id == kvm_host_psci_0_1_function_ids.migrate);
+		is_psci_0_1(migrate, func_id));
 }
 
 static bool is_psci_0_2_call(u64 func_id)
@@ -69,16 +62,6 @@ static bool is_psci_0_2_call(u64 func_id)
 	       (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)
 {
@@ -248,14 +231,13 @@ asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on)
 
 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) ||
+	if (is_psci_0_1(cpu_off, func_id) || is_psci_0_1(migrate, func_id))
-	    (func_id == kvm_host_psci_0_1_function_ids.migrate))
 		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;
 }
 
@@ -298,20 +280,23 @@ static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_
 
 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))
+	switch (kvm_host_psci_config.version) {
-		return false;
-
-	switch (kvm_host_psci_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;
 	}

arch/arm64/kvm/pmu-emul.c

@@ -850,8 +850,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 		   return -EINVAL;
 	}
 
-	kvm_pmu_vcpu_reset(vcpu);
-
 	return 0;
 }
 

arch/arm64/kvm/sys_regs.c

@@ -594,6 +594,10 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 pmcr, val;
 
+	/* No PMU available, PMCR_EL0 may UNDEF... */
+	if (!kvm_arm_support_pmu_v3())
+		return;
+
 	pmcr = read_sysreg(pmcr_el0);
 	/*
 	 * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN
@@ -919,7 +923,7 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 #define reg_to_encoding(x)						\
 	sys_reg((u32)(x)->Op0, (u32)(x)->Op1,				\
-		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2);
+		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2)
 
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\

arch/arm64/kvm/va_layout.c

@@ -34,17 +34,16 @@ static u64 __early_kern_hyp_va(u64 addr)
 }
 
 /*
- * 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;
 }
 
 /*

arch/arm64/kvm/vgic/vgic-init.c

@@ -419,7 +419,8 @@ int vgic_lazy_init(struct kvm *kvm)
  * Map the MMIO regions depending on the VGIC model exposed to the guest
  * called on the first VCPU run.
  * Also map the virtual CPU interface into the VM.
- * v2/v3 derivatives call vgic_init if not already done.
+ * v2 calls vgic_init() if not already done.
+ * v3 and derivatives return an error if the VGIC is not initialized.
  * vgic_ready() returns true if this function has succeeded.
  * @kvm: kvm struct pointer
  */
@@ -428,7 +429,13 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	int ret = 0;
 
+	if (likely(vgic_ready(kvm)))
+		return 0;
+
 	mutex_lock(&kvm->lock);
+	if (vgic_ready(kvm))
+		goto out;
+
 	if (!irqchip_in_kernel(kvm))
 		goto out;
 
@@ -439,6 +446,8 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 
 	if (ret)
 		__kvm_vgic_destroy(kvm);
+	else
+		dist->ready = true;
 
 out:
 	mutex_unlock(&kvm->lock);

arch/arm64/kvm/vgic/vgic-v2.c

@@ -306,20 +306,15 @@ int vgic_v2_map_resources(struct kvm *kvm)
 	struct vgic_dist *dist = &kvm->arch.vgic;
 	int ret = 0;
 
-	if (vgic_ready(kvm))
-		goto out;
-
 	if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
 	    IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) {
 		kvm_err("Need to set vgic cpu and dist addresses first\n");
-		ret = -ENXIO;
+		return -ENXIO;
-		goto out;
 	}
 
 	if (!vgic_v2_check_base(dist->vgic_dist_base, dist->vgic_cpu_base)) {
 		kvm_err("VGIC CPU and dist frames overlap\n");
-		ret = -EINVAL;
+		return -EINVAL;
-		goto out;
 	}
 
 	/*
@@ -329,13 +324,13 @@ int vgic_v2_map_resources(struct kvm *kvm)
 	ret = vgic_init(kvm);
 	if (ret) {
 		kvm_err("Unable to initialize VGIC dynamic data structures\n");
-		goto out;
+		return ret;
 	}
 
 	ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V2);
 	if (ret) {
 		kvm_err("Unable to register VGIC MMIO regions\n");
-		goto out;
+		return ret;
 	}
 
 	if (!static_branch_unlikely(&vgic_v2_cpuif_trap)) {
@@ -344,14 +339,11 @@ int vgic_v2_map_resources(struct kvm *kvm)
 					    KVM_VGIC_V2_CPU_SIZE, true);
 		if (ret) {
 			kvm_err("Unable to remap VGIC CPU to VCPU\n");
-			goto out;
-		}
-	}
-
-	dist->ready = true;
-
-out:
 			return ret;
+		}
+	}
+
+	return 0;
 }
 
 DEFINE_STATIC_KEY_FALSE(vgic_v2_cpuif_trap);

arch/arm64/kvm/vgic/vgic-v3.c

@@ -500,29 +500,23 @@ int vgic_v3_map_resources(struct kvm *kvm)
 	int ret = 0;
 	int c;
 
-	if (vgic_ready(kvm))
-		goto out;
-
 	kvm_for_each_vcpu(c, vcpu, kvm) {
 		struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
 		if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) {
 			kvm_debug("vcpu %d redistributor base not set\n", c);
-			ret = -ENXIO;
+			return -ENXIO;
-			goto out;
 		}
 	}
 
 	if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) {
 		kvm_err("Need to set vgic distributor addresses first\n");
-		ret = -ENXIO;
+		return -ENXIO;
-		goto out;
 	}
 
 	if (!vgic_v3_check_base(kvm)) {
 		kvm_err("VGIC redist and dist frames overlap\n");
-		ret = -EINVAL;
+		return -EINVAL;
-		goto out;
 	}
 
 	/*
@@ -530,22 +524,19 @@ int vgic_v3_map_resources(struct kvm *kvm)
 	 * the VGIC before we need to use it.
 	 */
 	if (!vgic_initialized(kvm)) {
-		ret = -EBUSY;
+		return -EBUSY;
-		goto out;
 	}
 
 	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 0;
-	return ret;
 }
 
 DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap);

arch/arm64/mm/init.c

@@ -59,7 +59,7 @@ EXPORT_SYMBOL(memstart_addr);
  * 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
 /*

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

arch/powerpc/kernel/head_book3s_32.S

@@ -260,10 +260,19 @@ __secondary_hold_acknowledge:
 MachineCheck:
 	EXCEPTION_PROLOG_0
 #ifdef CONFIG_PPC_CHRP
+#ifdef CONFIG_VMAP_STACK
+	mtspr	SPRN_SPRG_SCRATCH2,r1
+	mfspr	r1, SPRN_SPRG_THREAD
+	lwz	r1, RTAS_SP(r1)
+	cmpwi	cr1, r1, 0
+	bne	cr1, 7f
+	mfspr	r1, SPRN_SPRG_SCRATCH2
+#else
 	mfspr	r11, SPRN_SPRG_THREAD
 	lwz	r11, RTAS_SP(r11)
 	cmpwi	cr1, r11, 0
 	bne	cr1, 7f
+#endif
 #endif /* CONFIG_PPC_CHRP */
 	EXCEPTION_PROLOG_1 for_rtas=1
 7:	EXCEPTION_PROLOG_2

arch/powerpc/kernel/vmlinux.lds.S

@@ -85,7 +85,7 @@ SECTIONS
 		ALIGN_FUNCTION();
 #endif
 		/* careful! __ftr_alt_* sections need to be close to .text */
-		*(.text.hot TEXT_MAIN .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text);
+		*(.text.hot .text.hot.* TEXT_MAIN .text.fixup .text.unlikely .text.unlikely.* .fixup __ftr_alt_* .ref.text);
 #ifdef CONFIG_PPC64
 		*(.tramp.ftrace.text);
 #endif

arch/x86/Kconfig

@@ -19,6 +19,7 @@ config X86_32
 	select KMAP_LOCAL
 	select MODULES_USE_ELF_REL
 	select OLD_SIGACTION
+	select ARCH_SPLIT_ARG64
 
 config X86_64
 	def_bool y

arch/x86/hyperv/hv_init.c

@@ -16,6 +16,7 @@
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 #include <asm/idtentry.h>
+#include <linux/kexec.h>
 #include <linux/version.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
@@ -26,6 +27,8 @@
 #include <linux/syscore_ops.h>
 #include <clocksource/hyperv_timer.h>
 
+int hyperv_init_cpuhp;
+
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 
@@ -401,6 +404,7 @@ void __init hyperv_init(void)
 
 	register_syscore_ops(&hv_syscore_ops);
 
+	hyperv_init_cpuhp = cpuhp;
 	return;
 
 remove_cpuhp_state:

arch/x86/hyperv/mmu.c

@@ -66,11 +66,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	if (!hv_hypercall_pg)
 		goto do_native;
 
-	if (cpumask_empty(cpus))
-		return;
-
 	local_irq_save(flags);
 
+	/*
+	 * Only check the mask _after_ interrupt has been disabled to avoid the
+	 * mask changing under our feet.
+	 */
+	if (cpumask_empty(cpus)) {
+		local_irq_restore(flags);
+		return;
+	}
+
 	flush_pcpu = (struct hv_tlb_flush **)
 		     this_cpu_ptr(hyperv_pcpu_input_arg);
 

arch/x86/include/asm/kvm_host.h

@@ -1010,9 +1010,21 @@ struct kvm_arch {
 	 */
 	bool tdp_mmu_enabled;
 
-	/* List of struct tdp_mmu_pages being used as roots */
+	/*
+	 * List of struct kvmp_mmu_pages being used as roots.
+	 * All struct kvm_mmu_pages in the list should have
+	 * tdp_mmu_page set.
+	 * All struct kvm_mmu_pages in the list should have a positive
+	 * root_count except when a thread holds the MMU lock and is removing
+	 * an entry from the list.
+	 */
 	struct list_head tdp_mmu_roots;
-	/* List of struct tdp_mmu_pages not being used as roots */
+
+	/*
+	 * List of struct kvmp_mmu_pages not being used as roots.
+	 * All struct kvm_mmu_pages in the list should have
+	 * tdp_mmu_page set and a root_count of 0.
+	 */
 	struct list_head tdp_mmu_pages;
 };
 
@@ -1287,6 +1299,8 @@ struct kvm_x86_ops {
 	void (*migrate_timers)(struct kvm_vcpu *vcpu);
 	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
 	int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
+
+	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
 };
 
 struct kvm_x86_nested_ops {
@@ -1468,6 +1482,7 @@ int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in);
 int kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
 int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int kvm_vcpu_halt(struct kvm_vcpu *vcpu);
+int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu);
 int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
 
 void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);

arch/x86/include/asm/mshyperv.h

@@ -74,6 +74,8 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {}
 
 
 #if IS_ENABLED(CONFIG_HYPERV)
+extern int hyperv_init_cpuhp;
+
 extern void *hv_hypercall_pg;
 extern void  __percpu  **hyperv_pcpu_input_arg;
 

arch/x86/kernel/cpu/mshyperv.c

@@ -135,14 +135,32 @@ static void hv_machine_shutdown(void)
 {
 	if (kexec_in_progress && hv_kexec_handler)
 		hv_kexec_handler();
+
+	/*
+	 * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor
+	 * corrupts the old VP Assist Pages and can crash the kexec kernel.
+	 */
+	if (kexec_in_progress && hyperv_init_cpuhp > 0)
+		cpuhp_remove_state(hyperv_init_cpuhp);
+
+	/* The function calls stop_other_cpus(). */
 	native_machine_shutdown();
+
+	/* Disable the hypercall page when there is only 1 active CPU. */
+	if (kexec_in_progress)
+		hyperv_cleanup();
 }
 
 static void hv_machine_crash_shutdown(struct pt_regs *regs)
 {
 	if (hv_crash_handler)
 		hv_crash_handler(regs);
+
+	/* The function calls crash_smp_send_stop(). */
 	native_machine_crash_shutdown(regs);
+
+	/* Disable the hypercall page when there is only 1 active CPU. */
+	hyperv_cleanup();
 }
 #endif /* CONFIG_KEXEC_CORE */
 #endif /* CONFIG_HYPERV */

arch/x86/kernel/cpu/mtrr/generic.c

@@ -167,9 +167,6 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
 	*repeat = 0;
 	*uniform = 1;
 
-	/* Make end inclusive instead of exclusive */
-	end--;
-
 	prev_match = MTRR_TYPE_INVALID;
 	for (i = 0; i < num_var_ranges; ++i) {
 		unsigned short start_state, end_state, inclusive;
@@ -261,6 +258,9 @@ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform)
 	int repeat;
 	u64 partial_end;
 
+	/* Make end inclusive instead of exclusive */
+	end--;
+
 	if (!mtrr_state_set)
 		return MTRR_TYPE_INVALID;
 

arch/x86/kernel/cpu/resctrl/rdtgroup.c

@@ -525,76 +525,43 @@ static void rdtgroup_remove(struct rdtgroup *rdtgrp)
 	kfree(rdtgrp);
 }
 
-struct task_move_callback {
+static void _update_task_closid_rmid(void *task)
-	struct callback_head	work;
-	struct rdtgroup		*rdtgrp;
-};
-
-static void move_myself(struct callback_head *head)
 {
-	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
+	 * If the task is still current on this CPU, update PQR_ASSOC MSR.
-	 * was invoked, then assign the task to root group and free the
+	 * Otherwise, the MSR is updated when the task is scheduled in.
-	 * resource group.
 	 */
-	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
+	if (task == current)
-	    (rdtgrp->flags & RDT_DELETED)) {
-		current->closid = 0;
-		current->rmid = 0;
-		rdtgroup_remove(rdtgrp);
-	}
-
-	if (unlikely(current->flags & PF_EXITING))
-		goto out;
-
-	preempt_disable();
-	/* update PQR_ASSOC MSR to make resource group go into effect */
 		resctrl_sched_in();
-	preempt_enable();
+}
 
-out:
+static void update_task_closid_rmid(struct task_struct *t)
-	kfree(callback);
+{
+	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;
+	/* If the task is already in rdtgrp, no need to move the task. */
-	int ret;
+	if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid &&
-
+	     tsk->rmid == rdtgrp->mon.rmid) ||
-	callback = kzalloc(sizeof(*callback), GFP_KERNEL);
+	    (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid &&
-	if (!callback)
+	     tsk->closid == rdtgrp->mon.parent->closid))
-		return -ENOMEM;
+		return 0;
-	callback->work.func = move_myself;
-	callback->rdtgrp = rdtgrp;
 
 	/*
-	 * Take a refcount, so rdtgrp cannot be freed before the
+	 * Set the task's closid/rmid before the PQR_ASSOC MSR can be
-	 * callback has been invoked.
+	 * updated by them.
-	 */
+	 *
-	atomic_inc(&rdtgrp->waitcount);
+	 * For ctrl_mon groups, move both closid and rmid.
-	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;
 		tsk->rmid = rdtgrp->mon.rmid;
@@ -603,11 +570,25 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 			tsk->rmid = rdtgrp->mon.rmid;
 		} else {
 			rdt_last_cmd_puts("Can't move task to different control group\n");
-				ret = -EINVAL;
+			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)

arch/x86/kernel/sev-es-shared.c

@@ -305,14 +305,14 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 	case 0xe4:
 	case 0xe5:
 		*exitinfo |= IOIO_TYPE_IN;
-		*exitinfo |= (u64)insn->immediate.value << 16;
+		*exitinfo |= (u8)insn->immediate.value << 16;
 		break;
 
 	/* OUT immediate opcodes */
 	case 0xe6:
 	case 0xe7:
 		*exitinfo |= IOIO_TYPE_OUT;
-		*exitinfo |= (u64)insn->immediate.value << 16;
+		*exitinfo |= (u8)insn->immediate.value << 16;
 		break;
 
 	/* IN register opcodes */

arch/x86/kvm/lapic.c

@@ -674,7 +674,7 @@ static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu)
 			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
 		return false;
 	}
-	return val & 0x1;
+	return val & KVM_PV_EOI_ENABLED;
 }
 
 static void pv_eoi_set_pending(struct kvm_vcpu *vcpu)
@@ -2898,7 +2898,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 			/* 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;
 		}
 	}

arch/x86/kvm/mmu.h

@@ -49,7 +49,7 @@ static inline u64 rsvd_bits(int s, int e)
 	if (e < s)
 		return 0;
 
-	return ((1ULL << (e - s + 1)) - 1) << s;
+	return ((2ULL << (e - s)) - 1) << s;
 }
 
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask);

arch/x86/kvm/mmu/mmu.c

@@ -3493,26 +3493,25 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
  * Return the level of the lowest level SPTE added to sptes.
  * That SPTE may be non-present.
  */
-static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
+static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level)
 {
 	struct kvm_shadow_walk_iterator iterator;
-	int leaf = vcpu->arch.mmu->root_level;
+	int leaf = -1;
 	u64 spte;
 
-
 	walk_shadow_page_lockless_begin(vcpu);
 
-	for (shadow_walk_init(&iterator, vcpu, addr);
+	for (shadow_walk_init(&iterator, vcpu, addr),
+	     *root_level = iterator.level;
 	     shadow_walk_okay(&iterator);
 	     __shadow_walk_next(&iterator, spte)) {
 		leaf = iterator.level;
 		spte = mmu_spte_get_lockless(iterator.sptep);
 
-		sptes[leaf - 1] = spte;
+		sptes[leaf] = spte;
 
 		if (!is_shadow_present_pte(spte))
 			break;
-
 	}
 
 	walk_shadow_page_lockless_end(vcpu);
@@ -3520,14 +3519,12 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
 	return leaf;
 }
 
-/* return true if reserved bit is detected on spte. */
+/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
 static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
-	u64 sptes[PT64_ROOT_MAX_LEVEL];
+	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
 	struct rsvd_bits_validate *rsvd_check;
-	int root = vcpu->arch.mmu->shadow_root_level;
+	int root, leaf, level;
-	int leaf;
-	int level;
 	bool reserved = false;
 
 	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) {
@@ -3536,35 +3533,45 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 	}
 
 	if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa))
-		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes);
+		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
 	else
-		leaf = get_walk(vcpu, addr, sptes);
+		leaf = get_walk(vcpu, addr, sptes, &root);
+
+	if (unlikely(leaf < 0)) {
+		*sptep = 0ull;
+		return reserved;
+	}
+
+	*sptep = sptes[leaf];
+
+	/*
+	 * Skip reserved bits checks on the terminal leaf if it's not a valid
+	 * SPTE.  Note, this also (intentionally) skips MMIO SPTEs, which, by
+	 * design, always have reserved bits set.  The purpose of the checks is
+	 * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs.
+	 */
+	if (!is_shadow_present_pte(sptes[leaf]))
+		leaf++;
 
 	rsvd_check = &vcpu->arch.mmu->shadow_zero_check;
 
-	for (level = root; level >= leaf; level--) {
+	for (level = root; level >= leaf; level--)
-		if (!is_shadow_present_pte(sptes[level - 1]))
-			break;
 		/*
 		 * 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]) |
+		reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) |
-			    __is_rsvd_bits_set(rsvd_check, sptes[level - 1],
+			    __is_rsvd_bits_set(rsvd_check, sptes[level], 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;
 }
 

arch/x86/kvm/mmu/tdp_mmu.c

@@ -44,6 +44,47 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
 }
 
+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)
 
@@ -447,18 +488,9 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
 	struct kvm_mmu_page *root;
 	bool flush = false;
 
-	for_each_tdp_mmu_root(kvm, root) {
+	for_each_tdp_mmu_root_yield_safe(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);
-
 		flush |= zap_gfn_range(kvm, root, start, end, true);
 
-		kvm_mmu_put_root(kvm, root);
-	}
-
 	return flush;
 }
 
@@ -619,13 +651,7 @@ static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start,
 	int ret = 0;
 	int as_id;
 
-	for_each_tdp_mmu_root(kvm, root) {
+	for_each_tdp_mmu_root_yield_safe(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);
-
 		as_id = kvm_mmu_page_as_id(root);
 		slots = __kvm_memslots(kvm, as_id);
 		kvm_for_each_memslot(memslot, slots) {
@@ -647,8 +673,6 @@ static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start,
 			ret |= handler(kvm, memslot, root, gfn_start,
 				       gfn_end, data);
 		}
-
-		kvm_mmu_put_root(kvm, root);
 	}
 
 	return ret;
@@ -838,21 +862,13 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot,
 	int root_as_id;
 	bool spte_set = false;
 
-	for_each_tdp_mmu_root(kvm, root) {
+	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
 			continue;
 
-		/*
-		 * Take a reference on the root so that it cannot be freed if
-		 * this thread releases the MMU lock and yields in this loop.
-		 */
-		kvm_mmu_get_root(kvm, root);
-
 		spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn,
 			     slot->base_gfn + slot->npages, min_level);
-
-		kvm_mmu_put_root(kvm, root);
 	}
 
 	return spte_set;
@@ -906,21 +922,13 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
 	int root_as_id;
 	bool spte_set = false;
 
-	for_each_tdp_mmu_root(kvm, root) {
+	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
 			continue;
 
-		/*
-		 * Take a reference on the root so that it cannot be freed if
-		 * this thread releases the MMU lock and yields in this loop.
-		 */
-		kvm_mmu_get_root(kvm, root);
-
 		spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn,
 				slot->base_gfn + slot->npages);
-
-		kvm_mmu_put_root(kvm, root);
 	}
 
 	return spte_set;
@@ -1029,21 +1037,13 @@ bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot)
 	int root_as_id;
 	bool spte_set = false;
 
-	for_each_tdp_mmu_root(kvm, root) {
+	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
 			continue;
 
-		/*
-		 * Take a reference on the root so that it cannot be freed if
-		 * this thread releases the MMU lock and yields in this loop.
-		 */
-		kvm_mmu_get_root(kvm, root);
-
 		spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn,
 				slot->base_gfn + slot->npages);
-
-		kvm_mmu_put_root(kvm, root);
 	}
 	return spte_set;
 }
@@ -1089,21 +1089,13 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
 	struct kvm_mmu_page *root;
 	int root_as_id;
 
-	for_each_tdp_mmu_root(kvm, root) {
+	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
 			continue;
 
-		/*
-		 * Take a reference on the root so that it cannot be freed if
-		 * this thread releases the MMU lock and yields in this loop.
-		 */
-		kvm_mmu_get_root(kvm, root);
-
 		zap_collapsible_spte_range(kvm, root, slot->base_gfn,
 					   slot->base_gfn + slot->npages);
-
-		kvm_mmu_put_root(kvm, root);
 	}
 }
 
@@ -1160,16 +1152,19 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
  * Return the level of the lowest level SPTE added to sptes.
  * That SPTE may be non-present.
  */
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			 int *root_level)
 {
 	struct tdp_iter iter;
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
-	int leaf = vcpu->arch.mmu->shadow_root_level;
 	gfn_t gfn = addr >> PAGE_SHIFT;
+	int leaf = -1;
+
+	*root_level = vcpu->arch.mmu->shadow_root_level;
 
 	tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
 		leaf = iter.level;
-		sptes[leaf - 1] = iter.old_spte;
+		sptes[leaf] = iter.old_spte;
 	}
 
 	return leaf;

arch/x86/kvm/mmu/tdp_mmu.h

@@ -44,5 +44,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
 bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn);
 
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes);
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			 int *root_level);
+
 #endif /* __KVM_X86_MMU_TDP_MMU_H */

arch/x86/kvm/svm/nested.c

@@ -199,6 +199,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+
 	if (!nested_svm_vmrun_msrpm(svm)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror =
@@ -595,6 +596,8 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	svm->nested.vmcb12_gpa = 0;
 	WARN_ON_ONCE(svm->nested.nested_run_pending);
 
+	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu);
+
 	/* in case we halted in L2 */
 	svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
@@ -754,6 +757,7 @@ void svm_leave_nested(struct vcpu_svm *svm)
 		leave_guest_mode(&svm->vcpu);
 		copy_vmcb_control_area(&vmcb->control, &hsave->control);
 		nested_svm_uninit_mmu_context(&svm->vcpu);
+		vmcb_mark_all_dirty(svm->vmcb);
 	}
 
 	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu);
@@ -1194,6 +1198,10 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	 * in the registers, the save area of the nested state instead
 	 * contains saved L1 state.
 	 */
+
+	svm->nested.nested_run_pending =
+		!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
+
 	copy_vmcb_control_area(&hsave->control, &svm->vmcb->control);
 	hsave->save = *save;
 

arch/x86/kvm/svm/sev.c

@@ -1563,6 +1563,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 			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 @@ int sev_handle_vmgexit(struct vcpu_svm *svm)
 	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 @@ void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu)
 	 * 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 @@ void sev_es_vcpu_put(struct vcpu_svm *svm)
 		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);
+}

arch/x86/kvm/svm/svm.c

@@ -3677,8 +3677,6 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 	return EXIT_FASTPATH_NONE;
 }
 
-void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
-
 static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 					struct vcpu_svm *svm)
 {
@@ -4384,6 +4382,14 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
 		   (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT));
 }
 
+static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
+{
+	if (!sev_es_guest(vcpu->kvm))
+		return kvm_vcpu_deliver_sipi_vector(vcpu, vector);
+
+	sev_vcpu_deliver_sipi_vector(vcpu, vector);
+}
+
 static void svm_vm_destroy(struct kvm *kvm)
 {
 	avic_vm_destroy(kvm);
@@ -4526,6 +4532,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.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 = {

arch/x86/kvm/svm/svm.h

@@ -185,6 +185,7 @@ struct vcpu_svm {
 	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_init_vmcb(struct vcpu_svm *svm);
 void sev_es_create_vcpu(struct vcpu_svm *svm);
 void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu);
 void sev_es_vcpu_put(struct vcpu_svm *svm);
+void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
 
 /* vmenter.S */
 

arch/x86/kvm/vmx/nested.c

@@ -4442,6 +4442,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	/* trying to cancel vmlaunch/vmresume is a bug */
 	WARN_ON_ONCE(vmx->nested.nested_run_pending);
 
+	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+
 	/* Service the TLB flush request for L2 before switching to L1. */
 	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
 		kvm_vcpu_flush_tlb_current(vcpu);

arch/x86/kvm/vmx/vmx.c

@@ -7707,6 +7707,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.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)

arch/x86/kvm/x86.c

@@ -7976,17 +7976,22 @@ void kvm_arch_exit(void)
 	kmem_cache_destroy(x86_fpu_cache);
 }
 
-int kvm_vcpu_halt(struct kvm_vcpu *vcpu)
+static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason)
 {
 	++vcpu->stat.halt_exits;
 	if (lapic_in_kernel(vcpu)) {
-		vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+		vcpu->arch.mp_state = state;
 		return 1;
 	} else {
-		vcpu->run->exit_reason = KVM_EXIT_HLT;
+		vcpu->run->exit_reason = reason;
 		return 0;
 	}
 }
+
+int kvm_vcpu_halt(struct kvm_vcpu *vcpu)
+{
+	return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT);
+}
 EXPORT_SYMBOL_GPL(kvm_vcpu_halt);
 
 int kvm_emulate_halt(struct kvm_vcpu *vcpu)
@@ -8000,6 +8005,14 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
+int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu)
+{
+	int ret = kvm_skip_emulated_instruction(vcpu);
+
+	return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret;
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold);
+
 #ifdef CONFIG_X86_64
 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,
 			        unsigned long clock_type)
@@ -8789,7 +8802,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	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 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 	kvm_apic_accept_events(vcpu);
 	switch(vcpu->arch.mp_state) {
 	case KVM_MP_STATE_HALTED:
+	case KVM_MP_STATE_AP_RESET_HOLD:
 		vcpu->arch.pv.pv_unhalted = false;
 		vcpu->arch.mp_state =
 			KVM_MP_STATE_RUNNABLE;
@@ -9520,7 +9536,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 		kvm_load_guest_fpu(vcpu);
 
 	kvm_apic_accept_events(vcpu);
-	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
+	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
@@ -10152,6 +10169,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 	kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
 	kvm_rip_write(vcpu, 0);
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector);
 
 int kvm_arch_hardware_enable(void)
 {

arch/x86/mm/pgtable.c

@@ -829,6 +829,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 	}
 
 	free_page((unsigned long)pmd_sv);
+
+	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	free_page((unsigned long)pmd);
 
 	return 1;

block/bfq-iosched.c

@@ -6332,13 +6332,13 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd,
 	 * limit 'something'.
 	 */
 	/* no more than 50% of tags for async I/O */
-	bfqd->word_depths[0][0] = max((1U << bt->sb.shift) >> 1, 1U);
+	bfqd->word_depths[0][0] = max(bt->sb.depth >> 1, 1U);
 	/*
 	 * no more than 75% of tags for sync writes (25% extra tags
 	 * w.r.t. async I/O, to prevent async I/O from starving sync
 	 * writes)
 	 */
-	bfqd->word_depths[0][1] = max(((1U << bt->sb.shift) * 3) >> 2, 1U);
+	bfqd->word_depths[0][1] = max((bt->sb.depth * 3) >> 2, 1U);
 
 	/*
 	 * In-word depths in case some bfq_queue is being weight-
@@ -6348,9 +6348,9 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd,
 	 * shortage.
 	 */
 	/* no more than ~18% of tags for async I/O */
-	bfqd->word_depths[1][0] = max(((1U << bt->sb.shift) * 3) >> 4, 1U);
+	bfqd->word_depths[1][0] = max((bt->sb.depth * 3) >> 4, 1U);
 	/* no more than ~37% of tags for sync writes (~20% extra tags) */
-	bfqd->word_depths[1][1] = max(((1U << bt->sb.shift) * 6) >> 4, 1U);
+	bfqd->word_depths[1][1] = max((bt->sb.depth * 6) >> 4, 1U);
 
 	for (i = 0; i < 2; i++)
 		for (j = 0; j < 2; j++)

block/blk-iocost.c

@@ -2551,8 +2551,8 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio)
 	bool use_debt, ioc_locked;
 	unsigned long flags;
 
-	/* bypass IOs if disabled or for root cgroup */
+	/* bypass IOs if disabled, still initializing, or for root cgroup */
-	if (!ioc->enabled || !iocg->level)
+	if (!ioc->enabled || !iocg || !iocg->level)
 		return;
 
 	/* calculate the absolute vtime cost */
@@ -2679,14 +2679,14 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq,
 			   struct bio *bio)
 {
 	struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg);
-	struct ioc *ioc = iocg->ioc;
+	struct ioc *ioc = rqos_to_ioc(rqos);
 	sector_t bio_end = bio_end_sector(bio);
 	struct ioc_now now;
 	u64 vtime, abs_cost, cost;
 	unsigned long flags;
 
-	/* bypass if disabled or for root cgroup */
+	/* bypass if disabled, still initializing, or for root cgroup */
-	if (!ioc->enabled || !iocg->level)
+	if (!ioc->enabled || !iocg || !iocg->level)
 		return;
 
 	abs_cost = calc_vtime_cost(bio, iocg, true);
@@ -2863,6 +2863,12 @@ static int blk_iocost_init(struct request_queue *q)
 	ioc_refresh_params(ioc, true);
 	spin_unlock_irq(&ioc->lock);
 
+	/*
+	 * rqos must be added before activation to allow iocg_pd_init() to
+	 * lookup the ioc from q. This means that the rqos methods may get
+	 * called before policy activation completion, can't assume that the
+	 * target bio has an iocg associated and need to test for NULL iocg.
+	 */
 	rq_qos_add(q, rqos);
 	ret = blkcg_activate_policy(q, &blkcg_policy_iocost);
 	if (ret) {

block/blk-mq-debugfs.c

@@ -246,6 +246,7 @@ static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(BLOCKING),
 	HCTX_FLAG_NAME(NO_SCHED),
 	HCTX_FLAG_NAME(STACKING),
+	HCTX_FLAG_NAME(TAG_HCTX_SHARED),
 };
 #undef HCTX_FLAG_NAME
 

block/genhd.c

@@ -246,15 +246,18 @@ struct block_device *disk_part_iter_next(struct disk_part_iter *piter)
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
-		if (!bdev_nr_sectors(part) &&
-		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
-		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
-		      piter->idx == 0))
-			continue;
-
 		piter->part = bdgrab(part);
 		if (!piter->part)
 			continue;
+		if (!bdev_nr_sectors(part) &&
+		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
+		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
+		      piter->idx == 0)) {
+			bdput(piter->part);
+			piter->part = NULL;
+			continue;
+		}
+
 		piter->idx += inc;
 		break;
 	}

crypto/asymmetric_keys/asym_tpm.c

@@ -354,7 +354,7 @@ static uint32_t derive_pub_key(const void *pub_key, uint32_t len, uint8_t *buf)
 	memcpy(cur, e, sizeof(e));
 	cur += sizeof(e);
 	/* Zero parameters to satisfy set_pub_key ABI. */
-	memset(cur, 0, SETKEY_PARAMS_SIZE);
+	memzero_explicit(cur, SETKEY_PARAMS_SIZE);
 
 	return cur - buf;
 }

drivers/acpi/Kconfig

@@ -395,9 +395,6 @@ config ACPI_CONTAINER
 
 	  This helps support hotplug of nodes, CPUs, and memory.
 
-	  To compile this driver as a module, choose M here:
-	  the module will be called container.
-
 config ACPI_HOTPLUG_MEMORY
 	bool "Memory Hotplug"
 	depends on MEMORY_HOTPLUG
@@ -411,9 +408,6 @@ config ACPI_HOTPLUG_MEMORY
 	  removing memory devices at runtime, you need not enable
 	  this driver.
 
-	  To compile this driver as a module, choose M here:
-	  the module will be called acpi_memhotplug.
-
 config ACPI_HOTPLUG_IOAPIC
 	bool
 	depends on PCI

drivers/acpi/x86/s2idle.c

@@ -105,18 +105,8 @@ static void lpi_device_get_constraints_amd(void)
 
 	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) {
+		if (package->type == ACPI_TYPE_PACKAGE) {
-			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) {
 			lpi_constraints_table = kcalloc(package->package.count,
 							sizeof(*lpi_constraints_table),
 							GFP_KERNEL);
@@ -135,12 +125,10 @@ static void lpi_device_get_constraints_amd(void)
 
 				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;

drivers/base/core.c

@@ -4414,6 +4414,12 @@ static inline bool fwnode_is_primary(struct fwnode_handle *fwnode)
  *
  * Set the device's firmware node pointer to @fwnode, but if a secondary
  * firmware node of the device is present, preserve it.
+ *
+ * Valid fwnode cases are:
+ *  - primary --> secondary --> -ENODEV
+ *  - primary --> NULL
+ *  - secondary --> -ENODEV
+ *  - NULL
  */
 void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
 {
@@ -4432,8 +4438,9 @@ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
 	} else {
 		if (fwnode_is_primary(fn)) {
 			dev->fwnode = fn->secondary;
+			/* Set fn->secondary = NULL, so fn remains the primary fwnode */
 			if (!(parent && fn == parent->fwnode))
-				fn->secondary = ERR_PTR(-ENODEV);
+				fn->secondary = NULL;
 		} else {
 			dev->fwnode = NULL;
 		}

drivers/block/Kconfig

@@ -445,6 +445,7 @@ config BLK_DEV_RBD
 config BLK_DEV_RSXX
 	tristate "IBM Flash Adapter 900GB Full Height PCIe Device Driver"
 	depends on PCI
+	select CRC32
 	help
 	  Device driver for IBM's high speed PCIe SSD
 	  storage device: Flash Adapter 900GB Full Height.

drivers/block/rnbd/Kconfig

@@ -7,6 +7,7 @@ config BLK_DEV_RNBD_CLIENT
 	tristate "RDMA Network Block Device driver client"
 	depends on INFINIBAND_RTRS_CLIENT
 	select BLK_DEV_RNBD
+	select SG_POOL
 	help
 	  RNBD client is a network block device driver using rdma transport.