diff --git a/.mailmap b/.mailmap
index 1e14566..505b3d7 100644
--- a/.mailmap
+++ b/.mailmap
@@ -82,7 +82,10 @@
 Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com>
 Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com>
 <dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be>
-Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+Dmitry Baryshkov <dbaryshkov@gmail.com>
+Dmitry Baryshkov <dbaryshkov@gmail.com> <[dbaryshkov@gmail.com]>
+Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_baryshkov@mentor.com>
+Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_eremin@mentor.com>
 Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com>
 Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
 Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
diff --git a/CREDITS b/CREDITS
index 8592e45..7483019 100644
--- a/CREDITS
+++ b/CREDITS
@@ -98,7 +98,7 @@
 E: andersen@codepoet.org
 W: https://www.codepoet.org/
 P: 1024D/30D39057 1BC4 2742 E885 E4DE 9301  0C82 5F9B 643E 30D3 9057
-D: Maintainer of ide-cd and Uniform CD-ROM driver, 
+D: Maintainer of ide-cd and Uniform CD-ROM driver,
 D: ATAPI CD-Changer support, Major 2.1.x CD-ROM update.
 S: 352 North 525 East
 S: Springville, Utah 84663
@@ -263,7 +263,7 @@
 E: pbd@op.net
 D: Driver for WaveFront soundcards (Turtle Beach Maui, Tropez, Tropez+)
 D: Various bugfixes and changes to sound drivers
-S: USA 
+S: USA
 
 N: Carlos Henrique Bauer
 E: chbauer@acm.org
@@ -849,6 +849,12 @@
 D: AX25-HOWTO, HAM-HOWTO, IPX-HOWTO, NET-2-HOWTO
 D: ax25-utils maintainer.
 
+N: Kamil Debski
+E: kamil@wypas.org
+D: Samsung S5P 2D graphics acceleration and Multi Format Codec drivers
+D: Samsung USB2 phy drivers
+D: PWM fan driver
+
 N: Helge Deller
 E: deller@gmx.de
 W: http://www.parisc-linux.org/
@@ -1199,7 +1205,7 @@
 E: dfrasnel@alphalinux.org
 W: http://www.alphalinux.org/
 P: 1024/3EF87611 B9 F1 44 50 D3 E8 C2 80  DA E5 55 AA 56 7C 42 DA
-D: DEC Alpha hacker 
+D: DEC Alpha hacker
 D: Miscellaneous bug squisher
 
 N: Jim Freeman
@@ -1299,7 +1305,7 @@
 S: New South Wales, 2121
 S: Australia
 
-N: Carlos E. Gorges 
+N: Carlos E. Gorges
 E: carlos@techlinux.com.br
 D: fix smp support on cmpci driver
 P: 2048G/EA3C4B19 FF31 33A6 0362 4915 B7EB  E541 17D0 0379 EA3C 4B19
@@ -1340,7 +1346,7 @@
 E: wgreathouse@myfavoritei.com
 D: Current Belkin USB Serial Adapter F5U103 hacker
 D: Kernel hacker, embedded systems
-S: 7802 Fitzwater Road   
+S: 7802 Fitzwater Road
 S: Brecksville, OH  44141-1334
 S: USA
 
@@ -1381,7 +1387,7 @@
 E: grant@torque.net
 W: http://www.torque.net/linux-pp.html
 D: original author of ppa driver for parallel port ZIP drive
-D: original architect of the parallel-port sharing scheme 
+D: original architect of the parallel-port sharing scheme
 D: PARIDE subsystem: drivers for parallel port IDE & ATAPI devices
 S: 44 St. Joseph Street, Suite 506
 S: Toronto, Ontario, M4Y 2W4
@@ -1523,7 +1529,7 @@
 E: benh@kernel.crashing.org
 D: Various parts of PPC/PPC64 & PowerMac
 S: 312/107 Canberra Avenue
-S: Griffith, ACT 2603 
+S: Griffith, ACT 2603
 S: Australia
 
 N: Andreas Herrmann
@@ -1825,7 +1831,7 @@
 N: Bernhard Kaindl
 E: bkaindl@netway.at
 E: edv@bartelt.via.at
-D: Author of a menu based configuration tool, kmenu, which 
+D: Author of a menu based configuration tool, kmenu, which
 D: is the predecessor of 'make menuconfig' and 'make xconfig'.
 D: digiboard driver update(modularisation work and 2.1.x upd)
 S: Tallak 95
@@ -2016,7 +2022,7 @@
 D: IP transparent proxy support
 S: X/OS Experts in Open Systems BV
 S: Kruislaan 419
-S: 1098 VA Amsterdam 
+S: 1098 VA Amsterdam
 S: The Netherlands
 
 N: Goran Koruga
@@ -2088,7 +2094,7 @@
 
 N: Andrzej M. Krzysztofowicz
 E: ankry@mif.pg.gda.pl
-D: Some 8-bit XT disk driver and devfs hacking 
+D: Some 8-bit XT disk driver and devfs hacking
 D: Aladdin 1533/1543(C) chipset IDE
 D: PIIX chipset IDE
 S: ul. Matemblewska 1B/10
@@ -2463,7 +2469,7 @@
 D: Logical Volume Manager
 S: Bartningstr. 12
 S: 64289 Darmstadt
-S: Germany 
+S: Germany
 
 N: Mark W. McClelland
 E: mmcclell@bigfoot.com
@@ -2547,7 +2553,7 @@
 P: 1024/04B6E8F5 6C 77 33 CA CC D6 22 03  AB AB 15 A3 AE AD 39 7D
 D: Kernel hacker. PostgreSQL hacker. Software watchdog daemon.
 D: Maintainer of several Debian packages
-S: Th.-Heuss-Str. 61 
+S: Th.-Heuss-Str. 61
 S: D-41812 Erkelenz
 S: Germany
 
@@ -2785,7 +2791,7 @@
 W: http://www.i-Connect.Net/~mike/
 D: Developer and maintainer of the EATA-DMA SCSI driver
 D: Co-developer EATA-PIO SCSI driver
-D: /proc/scsi and assorted other snippets 
+D: /proc/scsi and assorted other snippets
 S: Zum Schiersteiner Grund 2
 S: 55127 Mainz
 S: Germany
@@ -2852,6 +2858,10 @@
 N: Venkatesh Pallipadi (Venki)
 D: x86/HPET
 
+N: Kyungmin Park
+E: kyungmin.park@samsung.com
+D: Samsung S5Pv210 and Exynos4210 mobile platforms
+
 N: David Parsons
 E: orc@pell.chi.il.us
 D: improved memory detection code.
@@ -3019,7 +3029,7 @@
 S: Chandler, Arizona 85249
 S: USA
 
-N: Frederic Potter 
+N: Frederic Potter
 E: fpotter@cirpack.com
 D: Some PCI kernel support
 
@@ -3452,21 +3462,21 @@
 S: 76131 Karlsruhe
 S: Germany
 
-N: James Simmons 
+N: James Simmons
 E: jsimmons@infradead.org
-E: jsimmons@users.sf.net 
+E: jsimmons@users.sf.net
 D: Frame buffer device maintainer
 D: input layer development
 D: tty/console layer
-D: various mipsel devices 
-S: 115 Carmel Avenue 
+D: various mipsel devices
+S: 115 Carmel Avenue
 S: El Cerrito CA 94530
-S: USA 
+S: USA
 
 N: Jaspreet Singh
 E: jaspreet@sangoma.com
 W: www.sangoma.com
-D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards 
+D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards
 S: Sangoma Technologies Inc.,
 S: 1001 Denison Street
 S: Suite 101
@@ -3490,7 +3500,7 @@
 E: csmall@triode.apana.org.au
 E: vk2xlz@gonzo.vk2xlz.ampr.org (packet radio)
 D: Gracilis PackeTwin device driver
-D: RSPF daemon 
+D: RSPF daemon
 S: 10 Stockalls Place
 S: Minto, NSW, 2566
 S: Australia
@@ -3700,7 +3710,7 @@
 E: tsusheng@scf.usc.edu
 D: IGMP(Internet Group Management Protocol) version 2
 S: 2F 14 ALY 31 LN 166 SEC 1 SHIH-PEI RD
-S: Taipei 
+S: Taipei
 S: Taiwan 112
 S: Republic of China
 S: 24335 Delta Drive
@@ -3861,7 +3871,7 @@
 D: patches for ghostscript, worked on color 'ls', etc.
 S: 301 15th Street S.
 S: Moorhead, Minnesota 56560
-S: USA 
+S: USA
 
 N: Jos Vos
 E: jos@xos.nl
@@ -3869,7 +3879,7 @@
 D: Various IP firewall updates, ipfwadm
 S: X/OS Experts in Open Systems BV
 S: Kruislaan 419
-S: 1098 VA Amsterdam 
+S: 1098 VA Amsterdam
 S: The Netherlands
 
 N: Jeroen Vreeken
@@ -4107,7 +4117,7 @@
 N: Victor Yodaiken
 E: yodaiken@fsmlabs.com
 D: RTLinux (RealTime Linux)
-S: POB 1822 
+S: POB 1822
 S: Socorro NM, 87801
 S: USA
 
@@ -4205,7 +4215,7 @@
 S: France
 
 # Don't add your name here, unless you really _are_ after Marc
-# alphabetically. Leonard used to be very proud of being the 
+# alphabetically. Leonard used to be very proud of being the
 # last entry, and he'll get positively pissed if he can't even
 # be second-to-last.  (and this file really _is_ supposed to be
 # in alphabetic order)
diff --git a/Documentation/ABI/stable/sysfs-driver-dma-ioatdma b/Documentation/ABI/stable/sysfs-driver-dma-ioatdma
index 420c1d0..3a4e2cd 100644
--- a/Documentation/ABI/stable/sysfs-driver-dma-ioatdma
+++ b/Documentation/ABI/stable/sysfs-driver-dma-ioatdma
@@ -1,29 +1,29 @@
-What:           sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/cap
+What:           /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/cap
 Date:           December 3, 2009
 KernelVersion:  2.6.32
 Contact:        dmaengine@vger.kernel.org
 Description:	Capabilities the DMA supports.Currently there are DMA_PQ, DMA_PQ_VAL,
 		DMA_XOR,DMA_XOR_VAL,DMA_INTERRUPT.
 
-What:           sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_active
+What:           /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_active
 Date:           December 3, 2009
 KernelVersion:  2.6.32
 Contact:        dmaengine@vger.kernel.org
 Description:	The number of descriptors active in the ring.
 
-What:           sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_size
+What:           /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_size
 Date:           December 3, 2009
 KernelVersion:  2.6.32
 Contact:        dmaengine@vger.kernel.org
 Description:	Descriptor ring size, total number of descriptors available.
 
-What:           sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/version
+What:           /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/version
 Date:           December 3, 2009
 KernelVersion:  2.6.32
 Contact:        dmaengine@vger.kernel.org
 Description:	Version of ioatdma device.
 
-What:           sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/intr_coalesce
+What:           /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/intr_coalesce
 Date:           August 8, 2017
 KernelVersion:  4.14
 Contact:        dmaengine@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net
index 7670012..1f2002d 100644
--- a/Documentation/ABI/testing/sysfs-class-net
+++ b/Documentation/ABI/testing/sysfs-class-net
@@ -152,7 +152,7 @@
 		When an interface is under test, it cannot be expected
 		to pass packets as normal.
 
-What:		/sys/clas/net/<iface>/duplex
+What:		/sys/class/net/<iface>/duplex
 Date:		October 2009
 KernelVersion:	2.6.33
 Contact:	netdev@vger.kernel.org
diff --git a/Documentation/Makefile b/Documentation/Makefile
index 6a59a13..61a7310 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -26,6 +26,10 @@
 PDFLATEX      = xelatex
 LATEXOPTS     = -interaction=batchmode
 
+ifeq ($(KBUILD_VERBOSE),0)
+SPHINXOPTS    += "-q"
+endif
+
 # User-friendly check for sphinx-build
 HAVE_SPHINX := $(shell if which $(SPHINXBUILD) >/dev/null 2>&1; then echo 1; else echo 0; fi)
 
diff --git a/Documentation/admin-guide/LSM/SafeSetID.rst b/Documentation/admin-guide/LSM/SafeSetID.rst
index 17996c9..0ec3486 100644
--- a/Documentation/admin-guide/LSM/SafeSetID.rst
+++ b/Documentation/admin-guide/LSM/SafeSetID.rst
@@ -107,7 +107,7 @@
 privileges, such as allowing a user to set up user namespace UID/GID mappings.
 
 Note on GID policies and setgroups()
-==================
+====================================
 In v5.9 we are adding support for limiting CAP_SETGID privileges as was done
 previously for CAP_SETUID. However, for compatibility with common sandboxing
 related code conventions in userspace, we currently allow arbitrary
diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst
index 37940a0..10fde58 100644
--- a/Documentation/admin-guide/pm/cpuidle.rst
+++ b/Documentation/admin-guide/pm/cpuidle.rst
@@ -478,7 +478,7 @@
 statistics of the given idle state.  That information is exposed by the kernel
 via ``sysfs``.
 
-For each CPU in the system, there is a :file:`/sys/devices/system/cpu<N>/cpuidle/`
+For each CPU in the system, there is a :file:`/sys/devices/system/cpu/cpu<N>/cpuidle/`
 directory in ``sysfs``, where the number ``<N>`` is assigned to the given
 CPU at the initialization time.  That directory contains a set of subdirectories
 called :file:`state0`, :file:`state1` and so on, up to the number of idle state
@@ -494,7 +494,7 @@
 	residency.
 
 ``below``
-	Total number of times this idle state had been asked for, but cerainly
+	Total number of times this idle state had been asked for, but certainly
 	a deeper idle state would have been a better match for the observed idle
 	duration.
 
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index 57fd6ce..f2ab8a5 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -300,6 +300,7 @@
       0:    0     1     2     3     4     5     6     7
   RSS hash key:
   84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89
+
 netdev_tstamp_prequeue
 ----------------------
 
diff --git a/Documentation/arm/sunxi.rst b/Documentation/arm/sunxi.rst
index 62b533d..0c536ae 100644
--- a/Documentation/arm/sunxi.rst
+++ b/Documentation/arm/sunxi.rst
@@ -148,3 +148,13 @@
         * User Manual
 
           http://dl.linux-sunxi.org/A64/Allwinner%20A64%20User%20Manual%20v1.0.pdf
+
+      - Allwinner H6
+
+	* Datasheet
+
+	  https://linux-sunxi.org/images/5/5c/Allwinner_H6_V200_Datasheet_V1.1.pdf
+
+	* User Manual
+
+	  https://linux-sunxi.org/images/4/46/Allwinner_H6_V200_User_Manual_V1.1.pdf
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 1e44983..ed2b43e 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -51,7 +51,7 @@
         support for Sphinx v3.0 and above is brand new. Be prepared for
         possible issues in the generated output.
         ''')
-    if minor > 0 or patch >= 2:
+    if (major > 3) or (minor > 0 or patch >= 2):
         # Sphinx c function parser is more pedantic with regards to type
         # checking. Due to that, having macros at c:function cause problems.
         # Those needed to be scaped by using c_id_attributes[] array
diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index c09c9ca..2b68add 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -295,11 +295,13 @@
 pass::
 
         ok 28 - kmalloc_double_kzfree
+
 or, if kmalloc failed::
 
         # kmalloc_large_oob_right: ASSERTION FAILED at lib/test_kasan.c:163
         Expected ptr is not null, but is
         not ok 4 - kmalloc_large_oob_right
+
 or, if a KASAN report was expected, but not found::
 
         # kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:629
diff --git a/Documentation/dev-tools/kunit/faq.rst b/Documentation/dev-tools/kunit/faq.rst
index 1628862..8d5029a 100644
--- a/Documentation/dev-tools/kunit/faq.rst
+++ b/Documentation/dev-tools/kunit/faq.rst
@@ -90,7 +90,7 @@
    re-run kunit_tool.
 5. Try to run ``make ARCH=um defconfig`` before running ``kunit.py run``. This
    may help clean up any residual config items which could be causing problems.
-6. Finally, try running KUnit outside UML. KUnit and KUnit tests can run be
+6. Finally, try running KUnit outside UML. KUnit and KUnit tests can be
    built into any kernel, or can be built as a module and loaded at runtime.
    Doing so should allow you to determine if UML is causing the issue you're
    seeing. When tests are built-in, they will execute when the kernel boots, and
diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst
index d23385e..454f307 100644
--- a/Documentation/dev-tools/kunit/start.rst
+++ b/Documentation/dev-tools/kunit/start.rst
@@ -197,7 +197,7 @@
 
 	config MISC_EXAMPLE_TEST
 		bool "Test for my example"
-		depends on MISC_EXAMPLE && KUNIT
+		depends on MISC_EXAMPLE && KUNIT=y
 
 and the following to ``drivers/misc/Makefile``:
 
diff --git a/Documentation/dev-tools/kunit/style.rst b/Documentation/dev-tools/kunit/style.rst
index da1d6f0..8dbcdc5 100644
--- a/Documentation/dev-tools/kunit/style.rst
+++ b/Documentation/dev-tools/kunit/style.rst
@@ -175,17 +175,17 @@
 
 .. code-block:: none
 
-        config FOO_KUNIT_TEST
-                tristate "KUnit test for foo" if !KUNIT_ALL_TESTS
-                depends on KUNIT
-                default KUNIT_ALL_TESTS
-                help
-                    This builds unit tests for foo.
+	config FOO_KUNIT_TEST
+		tristate "KUnit test for foo" if !KUNIT_ALL_TESTS
+		depends on KUNIT
+		default KUNIT_ALL_TESTS
+		help
+		  This builds unit tests for foo.
 
-                    For more information on KUnit and unit tests in general, please refer
-                    to the KUnit documentation in Documentation/dev-tools/kunit
+		  For more information on KUnit and unit tests in general, please refer
+		  to the KUnit documentation in Documentation/dev-tools/kunit/.
 
-                    If unsure, say N
+		  If unsure, say N.
 
 
 Test File and Module Names
diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst
index 961d3ea..9c28c51 100644
--- a/Documentation/dev-tools/kunit/usage.rst
+++ b/Documentation/dev-tools/kunit/usage.rst
@@ -92,7 +92,7 @@
 the second parameter, in this case, is what the value is expected to be; the
 last value is what the value actually is. If ``add`` passes all of these
 expectations, the test case, ``add_test_basic`` will pass; if any one of these
-expectations fail, the test case will fail.
+expectations fails, the test case will fail.
 
 It is important to understand that a test case *fails* when any expectation is
 violated; however, the test will continue running, potentially trying other
@@ -202,7 +202,7 @@
 	kunit_test_suite(example_test_suite);
 
 In the above example the test suite, ``example_test_suite``, would run the test
-cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``,
+cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``;
 each would have ``example_test_init`` called immediately before it and would
 have ``example_test_exit`` called immediately after it.
 ``kunit_test_suite(example_test_suite)`` registers the test suite with the
@@ -229,7 +229,7 @@
 such that the definition of that function can be changed without affecting the
 rest of the code base. In the kernel this primarily comes from two constructs,
 classes, structs that contain function pointers that are provided by the
-implementer, and architecture specific functions which have definitions selected
+implementer, and architecture-specific functions which have definitions selected
 at compile time.
 
 Classes
@@ -459,7 +459,7 @@
 By default KUnit uses UML as a way to provide dependencies for code under test.
 Under most circumstances KUnit's usage of UML should be treated as an
 implementation detail of how KUnit works under the hood. Nevertheless, there
-are instances where being able to run architecture specific code or test
+are instances where being able to run architecture-specific code or test
 against real hardware is desirable. For these reasons KUnit supports running on
 other architectures.
 
@@ -561,6 +561,11 @@
 
 ...will run the tests.
 
+.. note::
+   Note that you should make sure your test depends on ``KUNIT=y`` in Kconfig
+   if the test does not support module build.  Otherwise, it will trigger
+   compile errors if ``CONFIG_KUNIT`` is ``m``.
+
 Writing new tests for other architectures
 -----------------------------------------
 
@@ -594,7 +599,7 @@
 hardware state in between test cases; if this is not possible, you may only be
 able to run one test case per invocation.
 
-.. TODO(brendanhiggins@google.com): Add an actual example of an architecture
+.. TODO(brendanhiggins@google.com): Add an actual example of an architecture-
    dependent KUnit test.
 
 KUnit debugfs representation
diff --git a/Documentation/devicetree/bindings/clock/hi6220-clock.txt b/Documentation/devicetree/bindings/clock/hi6220-clock.txt
index ef3deb7..17ac4a3 100644
--- a/Documentation/devicetree/bindings/clock/hi6220-clock.txt
+++ b/Documentation/devicetree/bindings/clock/hi6220-clock.txt
@@ -4,7 +4,7 @@
 please refer the following document to know more about the binding rules
 for these system controllers:
 
-Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt
+Documentation/devicetree/bindings/arm/hisilicon/hisilicon.yaml
 
 Required Properties:
 
diff --git a/Documentation/devicetree/bindings/clock/imx5-clock.yaml b/Documentation/devicetree/bindings/clock/imx5-clock.yaml
index 4d9e7c7..90775c2 100644
--- a/Documentation/devicetree/bindings/clock/imx5-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/imx5-clock.yaml
@@ -57,7 +57,7 @@
     };
 
     can@53fc8000 {
-        compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan";
+        compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan";
         reg = <0x53fc8000 0x4000>;
         interrupts = <82>;
         clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>, <&clks IMX5_CLK_CAN1_SERIAL_GATE>;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
index f6c3fcc..b5af120 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
@@ -32,6 +32,11 @@
                        | | vint  | bit  |  | 0 |.....|63| vintx  |
                        | +--------------+  +------------+        |
                        |                                         |
+                       |      Unmap                              |
+                       | +--------------+                        |
+  Unmapped events ---->| |   umapidx    |-------------------------> Globalevents
+                       | +--------------+                        |
+                       |                                         |
                        +-----------------------------------------+
 
   Configuration of these Intmap registers that maps global events to vint is
@@ -70,6 +75,11 @@
         - description: |
             "limit" specifies the limit for translation
 
+  ti,unmapped-event-sources:
+    $ref: /schemas/types.yaml#definitions/phandle-array
+    description:
+      Array of phandles to DMA controllers where the unmapped events originate.
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/net/can/can-controller.yaml b/Documentation/devicetree/bindings/net/can/can-controller.yaml
new file mode 100644
index 0000000..9cf2ae0
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/can-controller.yaml
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/can/can-controller.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: CAN Controller Generic Binding
+
+maintainers:
+  - Marc Kleine-Budde <mkl@pengutronix.de>
+
+properties:
+  $nodename:
+    pattern: "^can(@.*)?$"
+
+additionalProperties: true
+
+...
diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
new file mode 100644
index 0000000..13875ea
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
@@ -0,0 +1,139 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/can/fsl,flexcan.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title:
+  Flexcan CAN controller on Freescale's ARM and PowerPC system-on-a-chip (SOC).
+
+maintainers:
+  - Marc Kleine-Budde <mkl@pengutronix.de>
+
+allOf:
+  - $ref: can-controller.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - enum:
+          - fsl,imx8qm-flexcan
+          - fsl,imx8mp-flexcan
+          - fsl,imx6q-flexcan
+          - fsl,imx28-flexcan
+          - fsl,imx25-flexcan
+          - fsl,p1010-flexcan
+          - fsl,vf610-flexcan
+          - fsl,ls1021ar2-flexcan
+          - fsl,lx2160ar1-flexcan
+      - items:
+          - enum:
+              - fsl,imx53-flexcan
+              - fsl,imx35-flexcan
+          - const: fsl,imx25-flexcan
+      - items:
+          - enum:
+              - fsl,imx7d-flexcan
+              - fsl,imx6ul-flexcan
+              - fsl,imx6sx-flexcan
+          - const: fsl,imx6q-flexcan
+      - items:
+          - enum:
+              - fsl,ls1028ar1-flexcan
+          - const: fsl,lx2160ar1-flexcan
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 2
+
+  clock-names:
+    items:
+      - const: ipg
+      - const: per
+
+  clock-frequency:
+    description: |
+      The oscillator frequency driving the flexcan device, filled in by the
+      boot loader. This property should only be used the used operating system
+      doesn't support the clocks and clock-names property.
+
+  xceiver-supply:
+    description: Regulator that powers the CAN transceiver.
+
+  big-endian:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: |
+      This means the registers of FlexCAN controller are big endian. This is
+      optional property.i.e. if this property is not present in device tree
+      node then controller is assumed to be little endian. If this property is
+      present then controller is assumed to be big endian.
+
+  fsl,stop-mode:
+    description: |
+      Register bits of stop mode control.
+
+      The format should be as follows:
+      <gpr req_gpr req_bit>
+      gpr is the phandle to general purpose register node.
+      req_gpr is the gpr register offset of CAN stop request.
+      req_bit is the bit offset of CAN stop request.
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      items:
+        - description: The 'gpr' is the phandle to general purpose register node.
+        - description: The 'req_gpr' is the gpr register offset of CAN stop request.
+          maximum: 0xff
+        - description: The 'req_bit' is the bit offset of CAN stop request.
+          maximum: 0x1f
+
+  fsl,clk-source:
+    description: |
+      Select the clock source to the CAN Protocol Engine (PE). It's SoC
+      implementation dependent. Refer to RM for detailed definition. If this
+      property is not set in device tree node then driver selects clock source 1
+      by default.
+      0: clock source 0 (oscillator clock)
+      1: clock source 1 (peripheral clock)
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 1
+    minimum: 0
+    maximum: 1
+
+  wakeup-source:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      Enable CAN remote wakeup.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    can@1c000 {
+        compatible = "fsl,p1010-flexcan";
+        reg = <0x1c000 0x1000>;
+        interrupts = <48 0x2>;
+        interrupt-parent = <&mpic>;
+        clock-frequency = <200000000>;
+        fsl,clk-source = <0>;
+    };
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    can@2090000 {
+        compatible = "fsl,imx6q-flexcan";
+        reg = <0x02090000 0x4000>;
+        interrupts = <0 110 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&clks 1>, <&clks 2>;
+        clock-names = "ipg", "per";
+        fsl,stop-mode = <&gpr 0x34 28>;
+    };
diff --git a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt b/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
deleted file mode 100644
index e10b6eb..0000000
--- a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
+++ /dev/null
@@ -1,57 +0,0 @@
-Flexcan CAN controller on Freescale's ARM and PowerPC system-on-a-chip (SOC).
-
-Required properties:
-
-- compatible : Should be "fsl,<processor>-flexcan"
-
-  where <processor> is imx8qm, imx6q, imx28, imx53, imx35, imx25, p1010,
-  vf610, ls1021ar2, lx2160ar1, ls1028ar1.
-
-  The ls1028ar1 must be followed by lx2160ar1, e.g.
-   - "fsl,ls1028ar1-flexcan", "fsl,lx2160ar1-flexcan"
-
-  An implementation should also claim any of the following compatibles
-  that it is fully backwards compatible with:
-
-  - fsl,p1010-flexcan
-
-- reg : Offset and length of the register set for this device
-- interrupts : Interrupt tuple for this device
-
-Optional properties:
-
-- clock-frequency : The oscillator frequency driving the flexcan device
-
-- xceiver-supply: Regulator that powers the CAN transceiver
-
-- big-endian: This means the registers of FlexCAN controller are big endian.
-              This is optional property.i.e. if this property is not present in
-              device tree node then controller is assumed to be little endian.
-              if this property is present then controller is assumed to be big
-              endian.
-
-- fsl,stop-mode: register bits of stop mode control, the format is
-		 <&gpr req_gpr req_bit>.
-		 gpr is the phandle to general purpose register node.
-		 req_gpr is the gpr register offset of CAN stop request.
-		 req_bit is the bit offset of CAN stop request.
-
-- fsl,clk-source: Select the clock source to the CAN Protocol Engine (PE).
-		  It's SoC Implementation dependent. Refer to RM for detailed
-		  definition. If this property is not set in device tree node
-		  then driver selects clock source 1 by default.
-		  0: clock source 0 (oscillator clock)
-		  1: clock source 1 (peripheral clock)
-
-- wakeup-source: enable CAN remote wakeup
-
-Example:
-
-	can@1c000 {
-		compatible = "fsl,p1010-flexcan";
-		reg = <0x1c000 0x1000>;
-		interrupts = <48 0x2>;
-		interrupt-parent = <&mpic>;
-		clock-frequency = <200000000>; // filled in by bootloader
-		fsl,clk-source = <0>; // select clock source 0 for PE
-	};
diff --git a/Documentation/filesystems/api-summary.rst b/Documentation/filesystems/api-summary.rst
index bbb0c1c..a94f17d 100644
--- a/Documentation/filesystems/api-summary.rst
+++ b/Documentation/filesystems/api-summary.rst
@@ -86,9 +86,6 @@
 .. kernel-doc:: fs/dax.c
    :export:
 
-.. kernel-doc:: fs/direct-io.c
-   :export:
-
 .. kernel-doc:: fs/libfs.c
    :export:
 
diff --git a/Documentation/filesystems/ext4/journal.rst b/Documentation/filesystems/ext4/journal.rst
index 805a1e9..849d5b1 100644
--- a/Documentation/filesystems/ext4/journal.rst
+++ b/Documentation/filesystems/ext4/journal.rst
@@ -256,6 +256,10 @@
      - s\_padding2
      -
    * - 0x54
+     - \_\_be32
+     - s\_num\_fc\_blocks
+     - Number of fast commit blocks in the journal.
+   * - 0x58
      - \_\_u32
      - s\_padding[42]
      -
@@ -310,6 +314,8 @@
      - This journal uses v3 of the checksum on-disk format. This is the same as
        v2, but the journal block tag size is fixed regardless of the size of
        block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3)
+   * - 0x20
+     - Journal has fast commit blocks. (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT)
 
 .. _jbd2_checksum_type:
 
diff --git a/Documentation/filesystems/ext4/super.rst b/Documentation/filesystems/ext4/super.rst
index 93e55d7..2eb1ab2 100644
--- a/Documentation/filesystems/ext4/super.rst
+++ b/Documentation/filesystems/ext4/super.rst
@@ -596,6 +596,13 @@
      - Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs
        points to the two block groups that contain backup superblocks
        (COMPAT\_SPARSE\_SUPER2).
+   * - 0x400
+     - Fast commits supported. Although fast commits blocks are
+       backward incompatible, fast commit blocks are not always
+       present in the journal. If fast commit blocks are present in
+       the journal, JBD2 incompat feature
+       (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) gets
+       set (COMPAT\_FAST\_COMMIT).
 
 .. _super_incompat:
 
diff --git a/Documentation/filesystems/journalling.rst b/Documentation/filesystems/journalling.rst
index 5a5f70b..e18f90f 100644
--- a/Documentation/filesystems/journalling.rst
+++ b/Documentation/filesystems/journalling.rst
@@ -136,10 +136,8 @@
 ~~~~~~~~~~~~
 
 JBD2 to also allows you to perform file-system specific delta commits known as
-fast commits. In order to use fast commits, you first need to call
-:c:func:`jbd2_fc_init` and tell how many blocks at the end of journal
-area should be reserved for fast commits. Along with that, you will also need
-to set following callbacks that perform correspodning work:
+fast commits. In order to use fast commits, you will need to set following
+callbacks that perform correspodning work:
 
 `journal->j_fc_cleanup_cb`: Cleanup function called after every full commit and
 fast commit.
diff --git a/Documentation/firmware-guide/acpi/acpi-lid.rst b/Documentation/firmware-guide/acpi/acpi-lid.rst
index 874ce0e..71b9af1 100644
--- a/Documentation/firmware-guide/acpi/acpi-lid.rst
+++ b/Documentation/firmware-guide/acpi/acpi-lid.rst
@@ -19,9 +19,9 @@
 
 For most platforms, both the _LID method and the lid notifications are
 reliable. However, there are exceptions. In order to work with these
-exceptional buggy platforms, special restrictions and expections should be
+exceptional buggy platforms, special restrictions and exceptions should be
 taken into account. This document describes the restrictions and the
-expections of the Linux ACPI lid device driver.
+exceptions of the Linux ACPI lid device driver.
 
 
 Restrictions of the returning value of the _LID control method
@@ -46,7 +46,7 @@
 trigger some system power saving operations on Windows. Since it is fully
 tested, it is reliable from all AML tables.
 
-Expections for the userspace users of the ACPI lid device driver
+Exceptions for the userspace users of the ACPI lid device driver
 ================================================================
 
 The ACPI button driver exports the lid state to the userspace via the
@@ -100,7 +100,7 @@
 C. button.lid_init_state=ignore:
    When this option is specified, the ACPI button driver never reports the
    initial lid state and there is a compensation mechanism implemented to
-   ensure that the reliable "closed" notifications can always be delievered
+   ensure that the reliable "closed" notifications can always be delivered
    to the userspace by always pairing "closed" input events with complement
    "opened" input events. But there is still no guarantee that the "opened"
    notifications can be delivered to the userspace when the lid is actually
diff --git a/Documentation/firmware-guide/acpi/gpio-properties.rst b/Documentation/firmware-guide/acpi/gpio-properties.rst
index bb6d74f..59aad61 100644
--- a/Documentation/firmware-guide/acpi/gpio-properties.rst
+++ b/Documentation/firmware-guide/acpi/gpio-properties.rst
@@ -20,9 +20,9 @@
 
       Name (_CRS, ResourceTemplate ()
       {
-          GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly,
+          GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly,
                   "\\_SB.GPO0", 0, ResourceConsumer) {15}
-          GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly,
+          GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly,
                   "\\_SB.GPO0", 0, ResourceConsumer) {27, 31}
       })
 
@@ -49,15 +49,41 @@
 pin
   Pin in the GpioIo()/GpioInt() resource. Typically this is zero.
 active_low
-  If 1 the GPIO is marked as active_low.
+  If 1, the GPIO is marked as active_low.
 
 Since ACPI GpioIo() resource does not have a field saying whether it is
 active low or high, the "active_low" argument can be used here.  Setting
 it to 1 marks the GPIO as active low.
 
+Note, active_low in _DSD does not make sense for GpioInt() resource and
+must be 0. GpioInt() resource has its own means of defining it.
+
 In our Bluetooth example the "reset-gpios" refers to the second GpioIo()
 resource, second pin in that resource with the GPIO number of 31.
 
+The GpioIo() resource unfortunately doesn't explicitly provide an initial
+state of the output pin which driver should use during its initialization.
+
+Linux tries to use common sense here and derives the state from the bias
+and polarity settings. The table below shows the expectations:
+
+=========  =============  ==============
+Pull Bias     Polarity     Requested...
+=========  =============  ==============
+Implicit     x            AS IS (assumed firmware configured for us)
+Explicit     x (no _DSD)  as Pull Bias (Up == High, Down == Low),
+                          assuming non-active (Polarity = !Pull Bias)
+Down         Low          as low, assuming active
+Down         High         as low, assuming non-active
+Up           Low          as high, assuming non-active
+Up           High         as high, assuming active
+=========  =============  ==============
+
+That said, for our above example the both GPIOs, since the bias setting
+is explicit and _DSD is present, will be treated as active with a high
+polarity and Linux will configure the pins in this state until a driver
+reprograms them differently.
+
 It is possible to leave holes in the array of GPIOs. This is useful in
 cases like with SPI host controllers where some chip selects may be
 implemented as GPIOs and some as native signals. For example a SPI host
@@ -112,8 +138,8 @@
   Package () {
       "gpio-line-names",
       Package () {
-          "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD", "MUX7_IO",
-          "LVL_C_A1", "MUX0_IO", "SPI1_MISO"
+          "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD",
+          "MUX7_IO", "LVL_C_A1", "MUX0_IO", "SPI1_MISO",
       }
   }
 
@@ -137,7 +163,7 @@
 mapping between those names and the ACPI GPIO resources corresponding to them.
 
 To do that, the driver needs to define a mapping table as a NULL-terminated
-array of struct acpi_gpio_mapping objects that each contain a name, a pointer
+array of struct acpi_gpio_mapping objects that each contains a name, a pointer
 to an array of line data (struct acpi_gpio_params) objects and the size of that
 array.  Each struct acpi_gpio_params object consists of three fields,
 crs_entry_index, line_index, active_low, representing the index of the target
@@ -154,13 +180,14 @@
   static const struct acpi_gpio_mapping bluetooth_acpi_gpios[] = {
     { "reset-gpios", &reset_gpio, 1 },
     { "shutdown-gpios", &shutdown_gpio, 1 },
-    { },
+    { }
   };
 
 Next, the mapping table needs to be passed as the second argument to
-acpi_dev_add_driver_gpios() that will register it with the ACPI device object
-pointed to by its first argument.  That should be done in the driver's .probe()
-routine.  On removal, the driver should unregister its GPIO mapping table by
+acpi_dev_add_driver_gpios() or its managed analogue that will
+register it with the ACPI device object pointed to by its first
+argument. That should be done in the driver's .probe() routine.
+On removal, the driver should unregister its GPIO mapping table by
 calling acpi_dev_remove_driver_gpios() on the ACPI device object where that
 table was previously registered.
 
@@ -191,12 +218,12 @@
 but since there is no way to know the mapping between "reset" and
 the GpioIo() in _CRS desc will hold ERR_PTR(-ENOENT).
 
-The driver author can solve this by passing the mapping explictly
-(the recommended way and documented in the above chapter).
+The driver author can solve this by passing the mapping explicitly
+(this is the recommended way and it's documented in the above chapter).
 
 The ACPI GPIO mapping tables should not contaminate drivers that are not
 knowing about which exact device they are servicing on. It implies that
-the ACPI GPIO mapping tables are hardly linked to ACPI ID and certain
+the ACPI GPIO mapping tables are hardly linked to an ACPI ID and certain
 objects, as listed in the above chapter, of the device in question.
 
 Getting GPIO descriptor
@@ -229,5 +256,5 @@
 Be aware that gpiod_get_index() in cases 1 and 2, assuming that there
 are two versions of ACPI device description provided and no mapping is
 present in the driver, will return different resources. That's why a
-certain driver has to handle them carefully as explained in previous
+certain driver has to handle them carefully as explained in the previous
 chapter.
diff --git a/Documentation/firmware-guide/acpi/method-tracing.rst b/Documentation/firmware-guide/acpi/method-tracing.rst
index 0aa7e2c..6ab6c096 100644
--- a/Documentation/firmware-guide/acpi/method-tracing.rst
+++ b/Documentation/firmware-guide/acpi/method-tracing.rst
@@ -98,7 +98,7 @@
    [    0.188903]   exdebug-0398 ex_trace_point        : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
 
 Developers can utilize these special log entries to track the AML
-interpretion, thus can aid issue debugging and performance tuning. Note
+interpretation, thus can aid issue debugging and performance tuning. Note
 that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT()
 macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling
 "AML tracer" logs.
diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index 1f9ea82..2062a60 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -83,10 +83,6 @@
 ===================
 
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
-   :doc: AMDGPU XGMI Support
-
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
-   :internal:
 
 AMDGPU RAS Support
 ==================
@@ -124,9 +120,6 @@
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
    :doc: AMDGPU RAS sysfs gpu_vram_bad_pages Interface
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
-   :internal:
-
 Sample Code
 -----------
 Sample code for testing error injection can be found here:
diff --git a/Documentation/hwmon/adm1266.rst b/Documentation/hwmon/adm1266.rst
index 9257f8a..2b87701 100644
--- a/Documentation/hwmon/adm1266.rst
+++ b/Documentation/hwmon/adm1266.rst
@@ -20,7 +20,7 @@
 integrated 12 bit SAR ADC, accessed using a PMBus interface.
 
 The driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus for details on PMBus client drivers.
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
 
 
 Sysfs entries
diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst
index e6b91ab..b797db7 100644
--- a/Documentation/hwmon/index.rst
+++ b/Documentation/hwmon/index.rst
@@ -132,6 +132,7 @@
    mcp3021
    menf21bmc
    mlxreg-fan
+   mp2975
    nct6683
    nct6775
    nct7802
diff --git a/Documentation/hwmon/mp2975.rst b/Documentation/hwmon/mp2975.rst
index 5b0609c..81d816b 100644
--- a/Documentation/hwmon/mp2975.rst
+++ b/Documentation/hwmon/mp2975.rst
@@ -20,6 +20,7 @@
 vendor dual-loop, digital, multi-phase controller MP2975.
 
 This device:
+
 - Supports up to two power rail.
 - Provides 8 pulse-width modulations (PWMs), and can be configured up
   to 8-phase operation for rail 1 and up to 4-phase operation for rail
@@ -32,10 +33,12 @@
   10-mV DAC, IMVP9 mode with 5-mV DAC.
 
 Device supports:
+
 - SVID interface.
 - AVSBus interface.
 
 Device complaint with:
+
 - PMBus rev 1.3 interface.
 
 Device supports direct format for reading output current, output voltage,
@@ -45,11 +48,14 @@
 The below VID modes are supported: VR12, VR13, IMVP9.
 
 The driver provides the next attributes for the current:
+
 - for current in: input, maximum alarm;
 - for current out input, maximum alarm and highest values;
 - for phase current: input and label.
-attributes.
+  attributes.
+
 The driver exports the following attributes via the 'sysfs' files, where
+
 - 'n' is number of telemetry pages (from 1 to 2);
 - 'k' is number of configured phases (from 1 to 8);
 - indexes 1, 1*n for "iin";
@@ -65,11 +71,14 @@
 **curr[1-{2n+k}]_label**
 
 The driver provides the next attributes for the voltage:
+
 - for voltage in: input, high critical threshold, high critical alarm, all only
   from page 0;
 - for voltage out: input, low and high critical thresholds, low and high
   critical alarms, from pages 0 and 1;
+
 The driver exports the following attributes via the 'sysfs' files, where
+
 - 'n' is number of telemetry pages (from 1 to 2);
 - indexes 1 for "iin";
 - indexes n+1, n+2 for "vout";
@@ -87,9 +96,12 @@
 **in[2-{n+1}1_lcrit_alarm**
 
 The driver provides the next attributes for the power:
+
 - for power in alarm and input.
 - for power out: highest and input.
+
 The driver exports the following attributes via the 'sysfs' files, where
+
 - 'n' is number of telemetry pages (from 1 to 2);
 - indexes 1 for "pin";
 - indexes n+1, n+2 for "pout";
diff --git a/Documentation/leds/index.rst b/Documentation/leds/index.rst
index 53e6090..e5d63b9 100644
--- a/Documentation/leds/index.rst
+++ b/Documentation/leds/index.rst
@@ -25,3 +25,4 @@
    leds-lp5562
    leds-lp55xx
    leds-mlxcpld
+   leds-sc27xx
diff --git a/Documentation/locking/lockdep-design.rst b/Documentation/locking/lockdep-design.rst
index cec03bd1..9f3cfca 100644
--- a/Documentation/locking/lockdep-design.rst
+++ b/Documentation/locking/lockdep-design.rst
@@ -42,6 +42,7 @@
 (4 usages * n STATEs + 1) categories:
 
 where the 4 usages can be:
+
 - 'ever held in STATE context'
 - 'ever held as readlock in STATE context'
 - 'ever held with STATE enabled'
@@ -49,10 +50,12 @@
 
 where the n STATEs are coded in kernel/locking/lockdep_states.h and as of
 now they include:
+
 - hardirq
 - softirq
 
 where the last 1 category is:
+
 - 'ever used'                                       [ == !unused        ]
 
 When locking rules are violated, these usage bits are presented in the
@@ -96,9 +99,9 @@
   +--------------+-------------+--------------+
   |              | irq enabled | irq disabled |
   +--------------+-------------+--------------+
-  | ever in irq  |      ?      |       -      |
+  | ever in irq  |     '?'     |      '-'     |
   +--------------+-------------+--------------+
-  | never in irq |      +      |       .      |
+  | never in irq |     '+'     |      '.'     |
   +--------------+-------------+--------------+
 
 The character '-' suggests irq is disabled because if otherwise the
@@ -216,7 +219,7 @@
        BD_MUTEX_PARTITION
   };
 
-mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
+  mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
 
 In this case the locking is done on a bdev object that is known to be a
 partition.
@@ -334,7 +337,7 @@
 ----------------
 
 The validator tracks a maximum of MAX_LOCKDEP_KEYS number of lock classes.
-Exceeding this number will trigger the following lockdep warning:
+Exceeding this number will trigger the following lockdep warning::
 
 	(DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
 
@@ -420,7 +423,8 @@
 
 The difference between recursive readers and non-recursive readers is because:
 recursive readers get blocked only by a write lock *holder*, while non-recursive
-readers could get blocked by a write lock *waiter*. Considering the follow example:
+readers could get blocked by a write lock *waiter*. Considering the follow
+example::
 
 	TASK A:			TASK B:
 
@@ -448,20 +452,22 @@
 
 Block condition matrix, Y means the row blocks the column, and N means otherwise.
 
-	    | E | r | R |
 	+---+---+---+---+
-	  E | Y | Y | Y |
+	|   | E | r | R |
 	+---+---+---+---+
-	  r | Y | Y | N |
+	| E | Y | Y | Y |
 	+---+---+---+---+
-	  R | Y | Y | N |
+	| r | Y | Y | N |
+	+---+---+---+---+
+	| R | Y | Y | N |
+	+---+---+---+---+
 
 	(W: writers, r: non-recursive readers, R: recursive readers)
 
 
 acquired recursively. Unlike non-recursive read locks, recursive read locks
 only get blocked by current write lock *holders* other than write lock
-*waiters*, for example:
+*waiters*, for example::
 
 	TASK A:			TASK B:
 
@@ -491,7 +497,7 @@
 even true for two non-recursive read locks). A non-recursive lock can block the
 corresponding recursive lock, and vice versa.
 
-A deadlock case with recursive locks involved is as follow:
+A deadlock case with recursive locks involved is as follow::
 
 	TASK A:			TASK B:
 
@@ -510,7 +516,7 @@
 dependencies, but we can show that 4 types of lock dependencies are enough for
 deadlock detection.
 
-For each lock dependency:
+For each lock dependency::
 
 	L1 -> L2
 
@@ -525,20 +531,25 @@
 With the above combination for simplification, there are 4 types of dependency edges
 in the lockdep graph:
 
-1) -(ER)->: exclusive writer to recursive reader dependency, "X -(ER)-> Y" means
+1) -(ER)->:
+	    exclusive writer to recursive reader dependency, "X -(ER)-> Y" means
 	    X -> Y and X is a writer and Y is a recursive reader.
 
-2) -(EN)->: exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means
+2) -(EN)->:
+	    exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means
 	    X -> Y and X is a writer and Y is either a writer or non-recursive reader.
 
-3) -(SR)->: shared reader to recursive reader dependency, "X -(SR)-> Y" means
+3) -(SR)->:
+	    shared reader to recursive reader dependency, "X -(SR)-> Y" means
 	    X -> Y and X is a reader (recursive or not) and Y is a recursive reader.
 
-4) -(SN)->: shared reader to non-recursive locker dependency, "X -(SN)-> Y" means
+4) -(SN)->:
+	    shared reader to non-recursive locker dependency, "X -(SN)-> Y" means
 	    X -> Y and X is a reader (recursive or not) and Y is either a writer or
 	    non-recursive reader.
 
-Note that given two locks, they may have multiple dependencies between them, for example:
+Note that given two locks, they may have multiple dependencies between them,
+for example::
 
 	TASK A:
 
@@ -592,11 +603,11 @@
 
 Proof for sufficiency (Lemma 1):
 
-Let's say we have a strong circle:
+Let's say we have a strong circle::
 
 	L1 -> L2 ... -> Ln -> L1
 
-, which means we have dependencies:
+, which means we have dependencies::
 
 	L1 -> L2
 	L2 -> L3
@@ -633,7 +644,7 @@
 for a lock held by P1. Let's name the lock Px is waiting as Lx, so since P1 is waiting
 for L1 and holding Ln, so we will have Ln -> L1 in the dependency graph. Similarly,
 we have L1 -> L2, L2 -> L3, ..., Ln-1 -> Ln in the dependency graph, which means we
-have a circle:
+have a circle::
 
 	Ln -> L1 -> L2 -> ... -> Ln
 
diff --git a/Documentation/misc-devices/index.rst b/Documentation/misc-devices/index.rst
index 46072ce..64420b331 100644
--- a/Documentation/misc-devices/index.rst
+++ b/Documentation/misc-devices/index.rst
@@ -24,7 +24,6 @@
    isl29003
    lis3lv02d
    max6875
-   mic/index
    pci-endpoint-test
    spear-pcie-gadget
    uacce
diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst
index b165181..a432dc4 100644
--- a/Documentation/networking/devlink/ice.rst
+++ b/Documentation/networking/devlink/ice.rst
@@ -70,6 +70,7 @@
         that both the name (as reported by ``fw.app.name``) and version are
         required to uniquely identify the package.
     * - ``fw.app.bundle_id``
+      - running
       - 0xc0000001
       - Unique identifier for the DDP package loaded in the device. Also
         referred to as the DDP Track ID. Can be used to uniquely identify
diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst
index f5be243..0a4b73b 100644
--- a/Documentation/networking/j1939.rst
+++ b/Documentation/networking/j1939.rst
@@ -10,9 +10,9 @@
 SAE J1939 defines a higher layer protocol on CAN. It implements a more
 sophisticated addressing scheme and extends the maximum packet size above 8
 bytes. Several derived specifications exist, which differ from the original
-J1939 on the application level, like MilCAN A, NMEA2000 and especially
+J1939 on the application level, like MilCAN A, NMEA2000, and especially
 ISO-11783 (ISOBUS). This last one specifies the so-called ETP (Extended
-Transport Protocol) which is has been included in this implementation. This
+Transport Protocol), which has been included in this implementation. This
 results in a maximum packet size of ((2 ^ 24) - 1) * 7 bytes == 111 MiB.
 
 Specifications used
@@ -32,15 +32,15 @@
 addressing and transport methods used by J1939.
 
 * **Addressing:** when a process on an ECU communicates via J1939, it should
-  not necessarily know its source address. Although at least one process per
+  not necessarily know its source address. Although, at least one process per
   ECU should know the source address. Other processes should be able to reuse
   that address. This way, address parameters for different processes
   cooperating for the same ECU, are not duplicated. This way of working is
-  closely related to the UNIX concept where programs do just one thing, and do
+  closely related to the UNIX concept, where programs do just one thing and do
   it well.
 
 * **Dynamic addressing:** Address Claiming in J1939 is time critical.
-  Furthermore data transport should be handled properly during the address
+  Furthermore, data transport should be handled properly during the address
   negotiation. Putting this functionality in the kernel eliminates it as a
   requirement for _every_ user space process that communicates via J1939. This
   results in a consistent J1939 bus with proper addressing.
@@ -58,7 +58,7 @@
 
 The J1939 sockets operate on CAN network devices (see SocketCAN). Any J1939
 user space library operating on CAN raw sockets will still operate properly.
-Since such library does not communicate with the in-kernel implementation, care
+Since such a library does not communicate with the in-kernel implementation, care
 must be taken that these two do not interfere. In practice, this means they
 cannot share ECU addresses. A single ECU (or virtual ECU) address is used by
 the library exclusively, or by the in-kernel system exclusively.
@@ -77,13 +77,13 @@
 8 bits : PS (PDU Specific)
 
 In J1939-21 distinction is made between PDU1 format (where PF < 240) and PDU2
-format (where PF >= 240). Furthermore, when using PDU2 format, the PS-field
+format (where PF >= 240). Furthermore, when using the PDU2 format, the PS-field
 contains a so-called Group Extension, which is part of the PGN. When using PDU2
 format, the Group Extension is set in the PS-field.
 
 On the other hand, when using PDU1 format, the PS-field contains a so-called
 Destination Address, which is _not_ part of the PGN. When communicating a PGN
-from user space to kernel (or visa versa) and PDU2 format is used, the PS-field
+from user space to kernel (or vice versa) and PDU2 format is used, the PS-field
 of the PGN shall be set to zero. The Destination Address shall be set
 elsewhere.
 
@@ -96,15 +96,15 @@
 
 Both static and dynamic addressing methods can be used.
 
-For static addresses, no extra checks are made by the kernel, and provided
+For static addresses, no extra checks are made by the kernel and provided
 addresses are considered right. This responsibility is for the OEM or system
 integrator.
 
 For dynamic addressing, so-called Address Claiming, extra support is foreseen
-in the kernel. In J1939 any ECU is known by it's 64-bit NAME. At the moment of
+in the kernel. In J1939 any ECU is known by its 64-bit NAME. At the moment of
 a successful address claim, the kernel keeps track of both NAME and source
 address being claimed. This serves as a base for filter schemes. By default,
-packets with a destination that is not locally, will be rejected.
+packets with a destination that is not locally will be rejected.
 
 Mixed mode packets (from a static to a dynamic address or vice versa) are
 allowed. The BSD sockets define separate API calls for getting/setting the
@@ -131,31 +131,31 @@
 ---------
 
 On CAN, you first need to open a socket for communicating over a CAN network.
-To use J1939, #include <linux/can/j1939.h>. From there, <linux/can.h> will be
+To use J1939, ``#include <linux/can/j1939.h>``. From there, ``<linux/can.h>`` will be
 included too. To open a socket, use:
 
 .. code-block:: C
 
     s = socket(PF_CAN, SOCK_DGRAM, CAN_J1939);
 
-J1939 does use SOCK_DGRAM sockets. In the J1939 specification, connections are
+J1939 does use ``SOCK_DGRAM`` sockets. In the J1939 specification, connections are
 mentioned in the context of transport protocol sessions. These still deliver
-packets to the other end (using several CAN packets). SOCK_STREAM is not
+packets to the other end (using several CAN packets). ``SOCK_STREAM`` is not
 supported.
 
-After the successful creation of the socket, you would normally use the bind(2)
-and/or connect(2) system call to bind the socket to a CAN interface.  After
-binding and/or connecting the socket, you can read(2) and write(2) from/to the
-socket or use send(2), sendto(2), sendmsg(2) and the recv*() counterpart
+After the successful creation of the socket, you would normally use the ``bind(2)``
+and/or ``connect(2)`` system call to bind the socket to a CAN interface. After
+binding and/or connecting the socket, you can ``read(2)`` and ``write(2)`` from/to the
+socket or use ``send(2)``, ``sendto(2)``, ``sendmsg(2)`` and the ``recv*()`` counterpart
 operations on the socket as usual. There are also J1939 specific socket options
 described below.
 
-In order to send data, a bind(2) must have been successful. bind(2) assigns a
+In order to send data, a ``bind(2)`` must have been successful. ``bind(2)`` assigns a
 local address to a socket.
 
-Different from CAN is that the payload data is just the data that get send,
-without it's header info. The header info is derived from the sockaddr supplied
-to bind(2), connect(2), sendto(2) and recvfrom(2). A write(2) with size 4 will
+Different from CAN is that the payload data is just the data that get sends,
+without its header info. The header info is derived from the sockaddr supplied
+to ``bind(2)``, ``connect(2)``, ``sendto(2)`` and ``recvfrom(2)``. A ``write(2)`` with size 4 will
 result in a packet with 4 bytes.
 
 The sockaddr structure has extensions for use with J1939 as specified below:
@@ -180,47 +180,47 @@
          } can_addr;
       }
 
-can_family & can_ifindex serve the same purpose as for other SocketCAN sockets.
+``can_family`` & ``can_ifindex`` serve the same purpose as for other SocketCAN sockets.
 
-can_addr.j1939.pgn specifies the PGN (max 0x3ffff). Individual bits are
+``can_addr.j1939.pgn`` specifies the PGN (max 0x3ffff). Individual bits are
 specified above.
 
-can_addr.j1939.name contains the 64-bit J1939 NAME.
+``can_addr.j1939.name`` contains the 64-bit J1939 NAME.
 
-can_addr.j1939.addr contains the address.
+``can_addr.j1939.addr`` contains the address.
 
-The bind(2) system call assigns the local address, i.e. the source address when
-sending packages. If a PGN during bind(2) is set, it's used as a RX filter.
-I.e.  only packets with a matching PGN are received. If an ADDR or NAME is set
+The ``bind(2)`` system call assigns the local address, i.e. the source address when
+sending packages. If a PGN during ``bind(2)`` is set, it's used as a RX filter.
+I.e. only packets with a matching PGN are received. If an ADDR or NAME is set
 it is used as a receive filter, too. It will match the destination NAME or ADDR
 of the incoming packet. The NAME filter will work only if appropriate Address
 Claiming for this name was done on the CAN bus and registered/cached by the
 kernel.
 
-On the other hand connect(2) assigns the remote address, i.e. the destination
-address. The PGN from connect(2) is used as the default PGN when sending
+On the other hand ``connect(2)`` assigns the remote address, i.e. the destination
+address. The PGN from ``connect(2)`` is used as the default PGN when sending
 packets. If ADDR or NAME is set it will be used as the default destination ADDR
-or NAME. Further a set ADDR or NAME during connect(2) is used as a receive
+or NAME. Further a set ADDR or NAME during ``connect(2)`` is used as a receive
 filter. It will match the source NAME or ADDR of the incoming packet.
 
-Both write(2) and send(2) will send a packet with local address from bind(2) and
-the remote address from connect(2). Use sendto(2) to overwrite the destination
+Both ``write(2)`` and ``send(2)`` will send a packet with local address from ``bind(2)`` and the
+remote address from ``connect(2)``. Use ``sendto(2)`` to overwrite the destination
 address.
 
-If can_addr.j1939.name is set (!= 0) the NAME is looked up by the kernel and
-the corresponding ADDR is used. If can_addr.j1939.name is not set (== 0),
-can_addr.j1939.addr is used.
+If ``can_addr.j1939.name`` is set (!= 0) the NAME is looked up by the kernel and
+the corresponding ADDR is used. If ``can_addr.j1939.name`` is not set (== 0),
+``can_addr.j1939.addr`` is used.
 
 When creating a socket, reasonable defaults are set. Some options can be
-modified with setsockopt(2) & getsockopt(2).
+modified with ``setsockopt(2)`` & ``getsockopt(2)``.
 
 RX path related options:
 
-- SO_J1939_FILTER - configure array of filters
-- SO_J1939_PROMISC - disable filters set by bind(2) and connect(2)
+- ``SO_J1939_FILTER`` - configure array of filters
+- ``SO_J1939_PROMISC`` - disable filters set by ``bind(2)`` and ``connect(2)``
 
 By default no broadcast packets can be send or received. To enable sending or
-receiving broadcast packets use the socket option SO_BROADCAST:
+receiving broadcast packets use the socket option ``SO_BROADCAST``:
 
 .. code-block:: C
 
@@ -261,26 +261,26 @@
      +---------------------------+
 
 TX path related options:
-SO_J1939_SEND_PRIO - change default send priority for the socket
+``SO_J1939_SEND_PRIO`` - change default send priority for the socket
 
 Message Flags during send() and Related System Calls
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-send(2), sendto(2) and sendmsg(2) take a 'flags' argument. Currently
+``send(2)``, ``sendto(2)`` and ``sendmsg(2)`` take a 'flags' argument. Currently
 supported flags are:
 
-* MSG_DONTWAIT, i.e. non-blocking operation.
+* ``MSG_DONTWAIT``, i.e. non-blocking operation.
 
 recvmsg(2)
 ^^^^^^^^^^
 
-In most cases recvmsg(2) is needed if you want to extract more information than
-recvfrom(2) can provide. For example package priority and timestamp. The
+In most cases ``recvmsg(2)`` is needed if you want to extract more information than
+``recvfrom(2)`` can provide. For example package priority and timestamp. The
 Destination Address, name and packet priority (if applicable) are attached to
-the msghdr in the recvmsg(2) call. They can be extracted using cmsg(3) macros,
-with cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR,
-SCM_J1939_DEST_NAME or SCM_J1939_PRIO. The returned data is a uint8_t for
-priority and dst_addr, and uint64_t for dst_name.
+the msghdr in the ``recvmsg(2)`` call. They can be extracted using ``cmsg(3)`` macros,
+with ``cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR``,
+``SCM_J1939_DEST_NAME`` or ``SCM_J1939_PRIO``. The returned data is a ``uint8_t`` for
+``priority`` and ``dst_addr``, and ``uint64_t`` for ``dst_name``.
 
 .. code-block:: C
 
@@ -305,12 +305,12 @@
 
 Distinction has to be made between using the claimed address and doing an
 address claim. To use an already claimed address, one has to fill in the
-j1939.name member and provide it to bind(2). If the name had claimed an address
+``j1939.name`` member and provide it to ``bind(2)``. If the name had claimed an address
 earlier, all further messages being sent will use that address. And the
-j1939.addr member will be ignored.
+``j1939.addr`` member will be ignored.
 
 An exception on this is PGN 0x0ee00. This is the "Address Claim/Cannot Claim
-Address" message and the kernel will use the j1939.addr member for that PGN if
+Address" message and the kernel will use the ``j1939.addr`` member for that PGN if
 necessary.
 
 To claim an address following code example can be used:
@@ -371,12 +371,12 @@
 
 If another ECU claims the address, the kernel will mark the NAME-SA expired.
 No socket bound to the NAME can send packets (other than address claims). To
-claim another address, some socket bound to NAME, must bind(2) again, but with
-only j1939.addr changed to the new SA, and must then send a valid address claim
+claim another address, some socket bound to NAME, must ``bind(2)`` again, but with
+only ``j1939.addr`` changed to the new SA, and must then send a valid address claim
 packet. This restarts the state machine in the kernel (and any other
 participant on the bus) for this NAME.
 
-can-utils also include the jacd tool, so it can be used as code example or as
+``can-utils`` also include the ``j1939acd`` tool, so it can be used as code example or as
 default Address Claiming daemon.
 
 Send Examples
@@ -403,8 +403,8 @@
 
 	bind(sock, (struct sockaddr *)&baddr, sizeof(baddr));
 
-Now, the socket 'sock' is bound to the SA 0x20. Since no connect(2) was called,
-at this point we can use only sendto(2) or sendmsg(2).
+Now, the socket 'sock' is bound to the SA 0x20. Since no ``connect(2)`` was called,
+at this point we can use only ``sendto(2)`` or ``sendmsg(2)``.
 
 Send:
 
@@ -414,8 +414,8 @@
 		.can_family = AF_CAN,
 		.can_addr.j1939 = {
 			.name = J1939_NO_NAME;
-			.pgn = 0x30,
-			.addr = 0x12300,
+			.addr = 0x30,
+			.pgn = 0x12300,
 		},
 	};
 
diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst
index d5c9320..2153776 100644
--- a/Documentation/networking/netdev-FAQ.rst
+++ b/Documentation/networking/netdev-FAQ.rst
@@ -110,7 +110,7 @@
 Q: How can I tell whether it got merged?
 A: Start by looking at the main patchworks queue for netdev:
 
-  http://patchwork.ozlabs.org/project/netdev/list/
+  https://patchwork.kernel.org/project/netdevbpf/list/
 
 The "State" field will tell you exactly where things are at with your
 patch.
@@ -152,7 +152,7 @@
 
 There is a patchworks queue that you can see here:
 
-  http://patchwork.ozlabs.org/bundle/davem/stable/?state=*
+  https://patchwork.kernel.org/bundle/netdev/stable/?state=*
 
 It contains the patches which Dave has selected, but not yet handed off
 to Greg.  If Greg already has the patch, then it will be here:
diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst
index 2561060..b2f7ec7 100644
--- a/Documentation/networking/phy.rst
+++ b/Documentation/networking/phy.rst
@@ -247,8 +247,8 @@
     speeds (see below.)
 
 ``PHY_INTERFACE_MODE_2500BASEX``
-    This defines a variant of 1000BASE-X which is clocked 2.5 times faster,
-    than the 802.3 standard giving a fixed bit rate of 3.125Gbaud.
+    This defines a variant of 1000BASE-X which is clocked 2.5 times as fast
+    as the 802.3 standard, giving a fixed bit rate of 3.125Gbaud.
 
 ``PHY_INTERFACE_MODE_SGMII``
     This is used for Cisco SGMII, which is a modification of 1000BASE-X
diff --git a/Documentation/networking/statistics.rst b/Documentation/networking/statistics.rst
index 8e15bc9..234abed 100644
--- a/Documentation/networking/statistics.rst
+++ b/Documentation/networking/statistics.rst
@@ -175,5 +175,4 @@
 translated to netlink attributes when dumped. Drivers must not overwrite
 the statistics they don't report with 0.
 
-.. kernel-doc:: include/linux/ethtool.h
-    :identifiers: ethtool_pause_stats
+- ethtool_pause_stats()
diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst
index 06f743b..3973556 100644
--- a/Documentation/process/stable-kernel-rules.rst
+++ b/Documentation/process/stable-kernel-rules.rst
@@ -39,7 +39,7 @@
    submission guidelines as described in
    :ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>`
    after first checking the stable networking queue at
-   https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive=
+   https://patchwork.kernel.org/bundle/netdev/stable/?state=*
    to ensure the requested patch is not already queued up.
  - Security patches should not be handled (solely) by the -stable review
    process but should follow the procedures in
diff --git a/Documentation/sphinx/automarkup.py b/Documentation/sphinx/automarkup.py
index 409dbc4..3e81eba 100644
--- a/Documentation/sphinx/automarkup.py
+++ b/Documentation/sphinx/automarkup.py
@@ -16,28 +16,36 @@
 from itertools import chain
 
 #
+# Python 2 lacks re.ASCII...
+#
+try:
+    ascii_p3 = re.ASCII
+except AttributeError:
+    ascii_p3 = 0
+
+#
 # Regex nastiness.  Of course.
 # Try to identify "function()" that's not already marked up some
 # other way.  Sphinx doesn't like a lot of stuff right after a
 # :c:func: block (i.e. ":c:func:`mmap()`s" flakes out), so the last
 # bit tries to restrict matches to things that won't create trouble.
 #
-RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=re.ASCII)
+RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=ascii_p3)
 
 #
 # Sphinx 2 uses the same :c:type role for struct, union, enum and typedef
 #
 RE_generic_type = re.compile(r'\b(struct|union|enum|typedef)\s+([a-zA-Z_]\w+)',
-                             flags=re.ASCII)
+                             flags=ascii_p3)
 
 #
 # Sphinx 3 uses a different C role for each one of struct, union, enum and
 # typedef
 #
-RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
+RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
 
 #
 # Detects a reference to a documentation page of the form Documentation/... with
diff --git a/Documentation/translations/it_IT/process/stable-kernel-rules.rst b/Documentation/translations/it_IT/process/stable-kernel-rules.rst
index 4f206ce..283d6254 100644
--- a/Documentation/translations/it_IT/process/stable-kernel-rules.rst
+++ b/Documentation/translations/it_IT/process/stable-kernel-rules.rst
@@ -46,7 +46,7 @@
    :ref:`Documentation/translations/it_IT/networking/netdev-FAQ.rst <it_netdev-FAQ>`;
    ma solo dopo aver verificato al seguente indirizzo che la patch non sia
    già in coda:
-   https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive=
+   https://patchwork.kernel.org/bundle/netdev/stable/?state=*
  - Una patch di sicurezza non dovrebbero essere gestite (solamente) dal processo
    di revisione -stable, ma dovrebbe seguire le procedure descritte in
    :ref:`Documentation/translations/it_IT/admin-guide/security-bugs.rst <it_securitybugs>`.
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 69fc516..acd2cc2 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -22,6 +22,7 @@
    spec_ctrl
    accelerators/ocxl
    ioctl/index
+   iommu
    media/index
 
 .. only::  subproject and html
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 36d5f1f..e00a66d 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6367,7 +6367,7 @@
 instead get bounced to user space through the KVM_EXIT_X86_RDMSR and
 KVM_EXIT_X86_WRMSR exit notifications.
 
-8.25 KVM_X86_SET_MSR_FILTER
+8.27 KVM_X86_SET_MSR_FILTER
 ---------------------------
 
 :Architectures: x86
@@ -6381,8 +6381,7 @@
 trap and emulate MSRs that are outside of the scope of KVM as well as
 limit the attack surface on KVM's MSR emulation code.
 
-
-8.26 KVM_CAP_ENFORCE_PV_CPUID
+8.28 KVM_CAP_ENFORCE_PV_CPUID
 -----------------------------
 
 Architectures: x86
diff --git a/Documentation/xtensa/mmu.rst b/Documentation/xtensa/mmu.rst
index e52a129..450573a 100644
--- a/Documentation/xtensa/mmu.rst
+++ b/Documentation/xtensa/mmu.rst
@@ -82,7 +82,8 @@
   +------------------+
   | VMALLOC area     |  VMALLOC_START            0xc0000000  128MB - 64KB
   +------------------+  VMALLOC_END
-  | Cache aliasing   |  TLBTEMP_BASE_1           0xc7ff0000  DCACHE_WAY_SIZE
+  +------------------+
+  | Cache aliasing   |  TLBTEMP_BASE_1           0xc8000000  DCACHE_WAY_SIZE
   | remap area 1     |
   +------------------+
   | Cache aliasing   |  TLBTEMP_BASE_2                       DCACHE_WAY_SIZE
@@ -124,7 +125,8 @@
   +------------------+
   | VMALLOC area     |  VMALLOC_START            0xa0000000  128MB - 64KB
   +------------------+  VMALLOC_END
-  | Cache aliasing   |  TLBTEMP_BASE_1           0xa7ff0000  DCACHE_WAY_SIZE
+  +------------------+
+  | Cache aliasing   |  TLBTEMP_BASE_1           0xa8000000  DCACHE_WAY_SIZE
   | remap area 1     |
   +------------------+
   | Cache aliasing   |  TLBTEMP_BASE_2                       DCACHE_WAY_SIZE
@@ -167,7 +169,8 @@
   +------------------+
   | VMALLOC area     |  VMALLOC_START            0x90000000  128MB - 64KB
   +------------------+  VMALLOC_END
-  | Cache aliasing   |  TLBTEMP_BASE_1           0x97ff0000  DCACHE_WAY_SIZE
+  +------------------+
+  | Cache aliasing   |  TLBTEMP_BASE_1           0x98000000  DCACHE_WAY_SIZE
   | remap area 1     |
   +------------------+
   | Cache aliasing   |  TLBTEMP_BASE_2                       DCACHE_WAY_SIZE
diff --git a/MAINTAINERS b/MAINTAINERS
index b516bb3..5cc595a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -934,7 +934,7 @@
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
 T:	git git://people.freedesktop.org/~agd5f/linux
-F:	drivers/gpu/drm/amd/powerplay/
+F:	drivers/gpu/drm/amd/pm/powerplay/
 
 AMD SEATTLE DEVICE TREE SUPPORT
 M:	Brijesh Singh <brijeshkumar.singh@amd.com>
@@ -978,7 +978,7 @@
 L:	linux-iio@vger.kernel.org
 S:	Supported
 W:	http://ez.analog.com/community/linux-device-drivers
-F:	Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.txt
+F:	Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml
 F:	drivers/iio/adc/ad7768-1.c
 
 ANALOG DEVICES INC AD7780 DRIVER
@@ -1279,7 +1279,7 @@
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	https://www.marvell.com/
-Q:	http://patchwork.ozlabs.org/project/netdev/list/
+Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst
 F:	drivers/net/ethernet/aquantia/atlantic/
 
@@ -1546,6 +1546,7 @@
 ARM/Allwinner sunXi SoC support
 M:	Maxime Ripard <mripard@kernel.org>
 M:	Chen-Yu Tsai <wens@csie.org>
+R:	Jernej Skrabec <jernej.skrabec@siol.net>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git
@@ -2374,7 +2375,7 @@
 F:	sound/soc/rockchip/
 N:	rockchip
 
-ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
+ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES
 M:	Krzysztof Kozlowski <krzk@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-samsung-soc@vger.kernel.org
@@ -2403,15 +2404,7 @@
 N:	s3c64xx
 N:	s5pv210
 
-ARM/SAMSUNG MOBILE MACHINE SUPPORT
-M:	Kyungmin Park <kyungmin.park@samsung.com>
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Maintained
-F:	arch/arm/mach-s5pv210/
-
 ARM/SAMSUNG S5P SERIES 2D GRAPHICS ACCELERATION (G2D) SUPPORT
-M:	Kyungmin Park <kyungmin.park@samsung.com>
-M:	Kamil Debski <kamil@wypas.org>
 M:	Andrzej Hajda <a.hajda@samsung.com>
 L:	linux-arm-kernel@lists.infradead.org
 L:	linux-media@vger.kernel.org
@@ -2436,9 +2429,6 @@
 F:	drivers/media/platform/s5p-jpeg/
 
 ARM/SAMSUNG S5P SERIES Multi Format Codec (MFC) SUPPORT
-M:	Kyungmin Park <kyungmin.park@samsung.com>
-M:	Kamil Debski <kamil@wypas.org>
-M:	Jeongtae Park <jtp.park@samsung.com>
 M:	Andrzej Hajda <a.hajda@samsung.com>
 L:	linux-arm-kernel@lists.infradead.org
 L:	linux-media@vger.kernel.org
@@ -3857,7 +3847,7 @@
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git
-F:	Documentation/devicetree/bindings/usb/cdns-usb3.txt
+F:	Documentation/devicetree/bindings/usb/cdns,usb3.yaml
 F:	drivers/usb/cdns3/
 
 CADET FM/AM RADIO RECEIVER DRIVER
@@ -6614,6 +6604,7 @@
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git
 F:	Documentation/filesystems/ext4/
 F:	fs/ext4/
+F:	include/trace/events/ext4.h
 
 Extended Verification Module (EVM)
 M:	Mimi Zohar <zohar@linux.ibm.com>
@@ -7916,7 +7907,7 @@
 M:	john.garry@huawei.com
 S:	Maintained
 W:	http://www.hisilicon.com
-F:	Documentation/devicetree/bindings/arm/hisilicon/hisilicon-low-pin-count.txt
+F:	Documentation/devicetree/bindings/arm/hisilicon/low-pin-count.yaml
 F:	drivers/bus/hisi_lpc.c
 
 HISILICON NETWORK SUBSYSTEM 3 DRIVER (HNS3)
@@ -8829,8 +8820,8 @@
 W:	http://www.intel.com/support/feedback.htm
 W:	http://e1000.sourceforge.net/
 Q:	http://patchwork.ozlabs.org/project/intel-wired-lan/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue.git
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue.git
 F:	Documentation/networking/device_drivers/ethernet/intel/
 F:	drivers/net/ethernet/intel/
 F:	drivers/net/ethernet/intel/*/
@@ -11163,7 +11154,7 @@
 F:	drivers/input/touchscreen/melfas_mip4.c
 
 MELLANOX BLUEFIELD I2C DRIVER
-M:	Khalil Blaiech <kblaiech@mellanox.com>
+M:	Khalil Blaiech <kblaiech@nvidia.com>
 L:	linux-i2c@vger.kernel.org
 S:	Supported
 F:	drivers/i2c/busses/i2c-mlxbf.c
@@ -11173,7 +11164,7 @@
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
-Q:	http://patchwork.ozlabs.org/project/netdev/list/
+Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlx4/en_*
 
 MELLANOX ETHERNET DRIVER (mlx5e)
@@ -11181,7 +11172,7 @@
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
-Q:	http://patchwork.ozlabs.org/project/netdev/list/
+Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlx5/core/en_*
 
 MELLANOX ETHERNET INNOVA DRIVERS
@@ -11189,7 +11180,7 @@
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
-Q:	http://patchwork.ozlabs.org/project/netdev/list/
+Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlx5/core/accel/*
 F:	drivers/net/ethernet/mellanox/mlx5/core/en_accel/*
 F:	drivers/net/ethernet/mellanox/mlx5/core/fpga/*
@@ -11201,7 +11192,7 @@
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
-Q:	http://patchwork.ozlabs.org/project/netdev/list/
+Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlxsw/
 F:	tools/testing/selftests/drivers/net/mlxsw/
 
@@ -11210,7 +11201,7 @@
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
-Q:	http://patchwork.ozlabs.org/project/netdev/list/
+Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlxfw/
 
 MELLANOX HARDWARE PLATFORM SUPPORT
@@ -11229,7 +11220,7 @@
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
-Q:	http://patchwork.ozlabs.org/project/netdev/list/
+Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlx4/
 F:	include/linux/mlx4/
 
@@ -11250,7 +11241,7 @@
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
-Q:	http://patchwork.ozlabs.org/project/netdev/list/
+Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	Documentation/networking/device_drivers/ethernet/mellanox/
 F:	drivers/net/ethernet/mellanox/mlx5/core/
 F:	include/linux/mlx5/
@@ -12130,7 +12121,7 @@
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	http://www.linuxfoundation.org/en/Net
-Q:	http://patchwork.ozlabs.org/project/netdev/list/
+Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
 F:	Documentation/devicetree/bindings/net/
@@ -12175,7 +12166,7 @@
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	http://www.linuxfoundation.org/en/Net
-Q:	http://patchwork.ozlabs.org/project/netdev/list/
+Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 B:	mailto:netdev@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
@@ -14210,7 +14201,6 @@
 F:	include/trace/events/pwc.h
 
 PWM FAN DRIVER
-M:	Kamil Debski <kamil@wypas.org>
 M:	Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Supported
@@ -14527,6 +14517,14 @@
 F:	drivers/mailbox/qcom-ipcc.c
 F:	include/dt-bindings/mailbox/qcom-ipcc.h
 
+QUALCOMM IPQ4019 VQMMC REGULATOR DRIVER
+M:	Robert Marko <robert.marko@sartura.hr>
+M:	Luka Perkov <luka.perkov@sartura.hr>
+L:	linux-arm-msm@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/regulator/vqmmc-ipq4019-regulator.yaml
+F:	drivers/regulator/vqmmc-ipq4019-regulator.c
+
 QUALCOMM RMNET DRIVER
 M:	Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
 M:	Sean Tranchetti <stranche@codeaurora.org>
@@ -14882,7 +14880,6 @@
 R:	Sergei Shtylyov <sergei.shtylyov@gmail.com>
 L:	netdev@vger.kernel.org
 L:	linux-renesas-soc@vger.kernel.org
-F:	Documentation/devicetree/bindings/net/renesas,*.txt
 F:	Documentation/devicetree/bindings/net/renesas,*.yaml
 F:	drivers/net/ethernet/renesas/
 F:	include/linux/sh_eth.h
@@ -15239,7 +15236,6 @@
 S390 IUCV NETWORK LAYER
 M:	Julian Wiedmann <jwi@linux.ibm.com>
 M:	Karsten Graul <kgraul@linux.ibm.com>
-M:	Ursula Braun <ubraun@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
 W:	http://www.ibm.com/developerworks/linux/linux390/
@@ -15250,7 +15246,6 @@
 S390 NETWORK DRIVERS
 M:	Julian Wiedmann <jwi@linux.ibm.com>
 M:	Karsten Graul <kgraul@linux.ibm.com>
-M:	Ursula Braun <ubraun@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
 W:	http://www.ibm.com/developerworks/linux/linux390/
@@ -15419,14 +15414,12 @@
 F:	drivers/nfc/s3fwrn5
 
 SAMSUNG S5C73M3 CAMERA DRIVER
-M:	Kyungmin Park <kyungmin.park@samsung.com>
 M:	Andrzej Hajda <a.hajda@samsung.com>
 L:	linux-media@vger.kernel.org
 S:	Supported
 F:	drivers/media/i2c/s5c73m3/*
 
 SAMSUNG S5K5BAF CAMERA DRIVER
-M:	Kyungmin Park <kyungmin.park@samsung.com>
 M:	Andrzej Hajda <a.hajda@samsung.com>
 L:	linux-media@vger.kernel.org
 S:	Supported
@@ -15444,7 +15437,6 @@
 F:	drivers/crypto/s5p-sss.c
 
 SAMSUNG S5P/EXYNOS4 SOC SERIES CAMERA SUBSYSTEM DRIVERS
-M:	Kyungmin Park <kyungmin.park@samsung.com>
 M:	Sylwester Nawrocki <s.nawrocki@samsung.com>
 L:	linux-media@vger.kernel.org
 S:	Supported
@@ -15492,7 +15484,6 @@
 F:	drivers/thermal/samsung/
 
 SAMSUNG USB2 PHY DRIVER
-M:	Kamil Debski <kamil@wypas.org>
 M:	Sylwester Nawrocki <s.nawrocki@samsung.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
@@ -15821,7 +15812,6 @@
 F:	drivers/misc/sgi-xp/
 
 SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
-M:	Ursula Braun <ubraun@linux.ibm.com>
 M:	Karsten Graul <kgraul@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
@@ -18083,7 +18073,7 @@
 M:	Binghui Wang <wangbinghui@hisilicon.com>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
-F:	Documentation/devicetree/bindings/phy/phy-hi3660-usb3.txt
+F:	Documentation/devicetree/bindings/phy/hisilicon,hi3660-usb3.yaml
 F:	drivers/phy/hisilicon/phy-hi3660-usb3.c
 
 USB ISP116X DRIVER
@@ -18168,6 +18158,14 @@
 S:	Supported
 F:	drivers/usb/class/usblp.c
 
+USB RAW GADGET DRIVER
+R:	Andrey Konovalov <andreyknvl@gmail.com>
+L:	linux-usb@vger.kernel.org
+S:	Maintained
+F:	Documentation/usb/raw-gadget.rst
+F:	drivers/usb/gadget/legacy/raw_gadget.c
+F:	include/uapi/linux/usb/raw_gadget.h
+
 USB QMI WWAN NETWORK DRIVER
 M:	Bjørn Mork <bjorn@mork.no>
 L:	netdev@vger.kernel.org
diff --git a/Makefile b/Makefile
index 9e7fd6a..e2c3f65 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 17fd1ed..9152782 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -67,7 +67,22 @@
 	sr	r5, [ARC_REG_LPB_CTRL]
 1:
 #endif /* CONFIG_ARC_LPB_DISABLE */
-#endif
+
+	/* On HSDK, CCMs need to remapped super early */
+#ifdef CONFIG_ARC_SOC_HSDK
+	mov	r6, 0x60000000
+	lr	r5, [ARC_REG_ICCM_BUILD]
+	breq	r5, 0, 1f
+	sr	r6, [ARC_REG_AUX_ICCM]
+1:
+	lr	r5, [ARC_REG_DCCM_BUILD]
+	breq	r5, 0, 2f
+	sr	r6, [ARC_REG_AUX_DCCM]
+2:
+#endif	/* CONFIG_ARC_SOC_HSDK */
+
+#endif	/* CONFIG_ISA_ARCV2 */
+
 	; Config DSP_CTRL properly, so kernel may use integer multiply,
 	; multiply-accumulate, and divide operations
 	DSP_EARLY_INIT
diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c
index feba91c..b23986f 100644
--- a/arch/arc/kernel/stacktrace.c
+++ b/arch/arc/kernel/stacktrace.c
@@ -112,7 +112,7 @@
 		int (*consumer_fn) (unsigned int, void *), void *arg)
 {
 #ifdef CONFIG_ARC_DW2_UNWIND
-	int ret = 0;
+	int ret = 0, cnt = 0;
 	unsigned int address;
 	struct unwind_frame_info frame_info;
 
@@ -132,6 +132,11 @@
 			break;
 
 		frame_info.regs.r63 = frame_info.regs.r31;
+
+		if (cnt++ > 128) {
+			printk("unwinder looping too long, aborting !\n");
+			return 0;
+		}
 	}
 
 	return address;		/* return the last address it saw */
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index 0b63fc0..b3ea1fa 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -17,22 +17,6 @@
 
 #define ARC_CCM_UNUSED_ADDR	0x60000000
 
-static void __init hsdk_init_per_cpu(unsigned int cpu)
-{
-	/*
-	 * By default ICCM is mapped to 0x7z while this area is used for
-	 * kernel virtual mappings, so move it to currently unused area.
-	 */
-	if (cpuinfo_arc700[cpu].iccm.sz)
-		write_aux_reg(ARC_REG_AUX_ICCM, ARC_CCM_UNUSED_ADDR);
-
-	/*
-	 * By default DCCM is mapped to 0x8z while this area is used by kernel,
-	 * so move it to currently unused area.
-	 */
-	if (cpuinfo_arc700[cpu].dccm.sz)
-		write_aux_reg(ARC_REG_AUX_DCCM, ARC_CCM_UNUSED_ADDR);
-}
 
 #define ARC_PERIPHERAL_BASE	0xf0000000
 #define CREG_BASE		(ARC_PERIPHERAL_BASE + 0x1000)
@@ -339,5 +323,4 @@
 MACHINE_START(SIMULATION, "hsdk")
 	.dt_compat	= hsdk_compat,
 	.init_early     = hsdk_init_early,
-	.init_per_cpu	= hsdk_init_per_cpu,
 MACHINE_END
diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
index ab291ce..2983e91 100644
--- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
+++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
@@ -122,7 +122,6 @@
 };
 
 &clock {
-	clocks = <&clock CLK_XUSBXTI>;
 	assigned-clocks = <&clock CLK_FOUT_EPLL>;
 	assigned-clock-rates = <45158401>;
 };
diff --git a/arch/arm/boot/dts/imx50-evk.dts b/arch/arm/boot/dts/imx50-evk.dts
index 878e89c..4ea5c23 100644
--- a/arch/arm/boot/dts/imx50-evk.dts
+++ b/arch/arm/boot/dts/imx50-evk.dts
@@ -59,7 +59,7 @@
 				MX50_PAD_CSPI_MISO__CSPI_MISO		0x00
 				MX50_PAD_CSPI_MOSI__CSPI_MOSI		0x00
 				MX50_PAD_CSPI_SS0__GPIO4_11		0xc4
-				MX50_PAD_ECSPI1_MOSI__CSPI_SS1		0xf4
+				MX50_PAD_ECSPI1_MOSI__GPIO4_13		0x84
 			>;
 		};
 
diff --git a/arch/arm/boot/dts/imx6q-prti6q.dts b/arch/arm/boot/dts/imx6q-prti6q.dts
index d112b50..b4605ed 100644
--- a/arch/arm/boot/dts/imx6q-prti6q.dts
+++ b/arch/arm/boot/dts/imx6q-prti6q.dts
@@ -213,8 +213,8 @@
 		#size-cells = <0>;
 
 		/* Microchip KSZ9031RNX PHY */
-		rgmii_phy: ethernet-phy@4 {
-			reg = <4>;
+		rgmii_phy: ethernet-phy@0 {
+			reg = <0>;
 			interrupts-extended = <&gpio1 28 IRQ_TYPE_LEVEL_LOW>;
 			reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>;
 			reset-assert-us = <10000>;
diff --git a/arch/arm/boot/dts/imx6qdl-udoo.dtsi b/arch/arm/boot/dts/imx6qdl-udoo.dtsi
index 828dd20..d07d8f8 100644
--- a/arch/arm/boot/dts/imx6qdl-udoo.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-udoo.dtsi
@@ -98,7 +98,7 @@
 &fec {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi
index 5dff24e..8456f17 100644
--- a/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi
+++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi
@@ -46,6 +46,16 @@
 			linux,code = <KEY_A>;
 			gpios = <&gpiof 3 GPIO_ACTIVE_LOW>;
 		};
+
+		/*
+		 * The EXTi IRQ line 0 is shared with PMIC,
+		 * so mark this as polled GPIO key.
+		 */
+		button-2 {
+			label = "TA3-GPIO-C";
+			linux,code = <KEY_C>;
+			gpios = <&gpiog 0 GPIO_ACTIVE_LOW>;
+		};
 	};
 
 	gpio-keys {
@@ -59,13 +69,6 @@
 			wakeup-source;
 		};
 
-		button-2 {
-			label = "TA3-GPIO-C";
-			linux,code = <KEY_C>;
-			gpios = <&gpioi 11 GPIO_ACTIVE_LOW>;
-			wakeup-source;
-		};
-
 		button-3 {
 			label = "TA4-GPIO-D";
 			linux,code = <KEY_D>;
@@ -79,7 +82,7 @@
 
 		led-0 {
 			label = "green:led5";
-			gpios = <&gpiog 2 GPIO_ACTIVE_HIGH>;
+			gpios = <&gpioc 6 GPIO_ACTIVE_HIGH>;
 			default-state = "off";
 		};
 
diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi
index b4b52cf..f796a61 100644
--- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi
+++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi
@@ -68,6 +68,7 @@
 		gpio = <&gpiog 3 GPIO_ACTIVE_LOW>;
 		regulator-always-on;
 		regulator-boot-on;
+		vin-supply = <&vdd>;
 	};
 };
 
@@ -202,6 +203,7 @@
 
 			vdda: ldo1 {
 				regulator-name = "vdda";
+				regulator-always-on;
 				regulator-min-microvolt = <2900000>;
 				regulator-max-microvolt = <2900000>;
 				interrupts = <IT_CURLIM_LDO1 0>;
diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi
index 04fbb32..803eb8b 100644
--- a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi
+++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi
@@ -21,6 +21,10 @@
 	};
 };
 
+&dts {
+	status = "okay";
+};
+
 &i2c4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c4_pins_a>;
diff --git a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts
index 049e6ab..73de34a 100644
--- a/arch/arm/boot/dts/sun6i-a31-hummingbird.dts
+++ b/arch/arm/boot/dts/sun6i-a31-hummingbird.dts
@@ -154,7 +154,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&gmac_rgmii_pins>;
 	phy-handle = <&phy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts
index 32d5d45..8945dbb 100644
--- a/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts
+++ b/arch/arm/boot/dts/sun7i-a20-bananapi-m1-plus.dts
@@ -130,7 +130,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&gmac_rgmii_pins>;
 	phy-handle = <&phy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-supply = <&reg_gmac_3v3>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts
index 8c8dee6..9109ca0 100644
--- a/arch/arm/boot/dts/sun7i-a20-cubietruck.dts
+++ b/arch/arm/boot/dts/sun7i-a20-cubietruck.dts
@@ -151,7 +151,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&gmac_rgmii_pins>;
 	phy-handle = <&phy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts
index 9d34eab..431f702 100644
--- a/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts
@@ -131,7 +131,7 @@
 	pinctrl-0 = <&emac_rgmii_pins>;
 	phy-supply = <&reg_sw>;
 	phy-handle = <&rgmii_phy>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	allwinner,rx-delay-ps = <700>;
 	allwinner,tx-delay-ps = <700>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
index d9be511..d8326a5 100644
--- a/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-cubietruck-plus.dts
@@ -183,7 +183,7 @@
 	pinctrl-0 = <&emac_rgmii_pins>;
 	phy-supply = <&reg_dldo4>;
 	phy-handle = <&rgmii_phy>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts
index 71fb732..babf4cf 100644
--- a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts
+++ b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts
@@ -53,11 +53,6 @@
 	};
 };
 
-&emac {
-	/* LEDs changed to active high on the plus */
-	/delete-property/ allwinner,leds-active-low;
-};
-
 &mmc1 {
 	vmmc-supply = <&reg_vcc3v3>;
 	bus-width = <4>;
diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts
index 6dbf7b2..b6ca45d 100644
--- a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts
+++ b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts
@@ -67,7 +67,7 @@
 	pinctrl-0 = <&emac_rgmii_pins>;
 	phy-supply = <&reg_gmac_3v3>;
 	phy-handle = <&ext_rgmii_phy>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts
index 2fc62ef..a6a1087 100644
--- a/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts
+++ b/arch/arm/boot/dts/sun8i-r40-bananapi-m2-ultra.dts
@@ -129,7 +129,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&gmac_rgmii_pins>;
 	phy-handle = <&phy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-supply = <&reg_dc1sw>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts
index d3b337b..484b93d 100644
--- a/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts
+++ b/arch/arm/boot/dts/sun9i-a80-cubieboard4.dts
@@ -129,7 +129,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&gmac_rgmii_pins>;
 	phy-handle = <&phy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-supply = <&reg_cldo1>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sun9i-a80-optimus.dts b/arch/arm/boot/dts/sun9i-a80-optimus.dts
index bbc6335..5c3580d 100644
--- a/arch/arm/boot/dts/sun9i-a80-optimus.dts
+++ b/arch/arm/boot/dts/sun9i-a80-optimus.dts
@@ -124,7 +124,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&gmac_rgmii_pins>;
 	phy-handle = <&phy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-supply = <&reg_cldo1>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi
index 39263e7..8e5cb3b 100644
--- a/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi
+++ b/arch/arm/boot/dts/sunxi-bananapi-m2-plus.dtsi
@@ -126,7 +126,7 @@
 	pinctrl-0 = <&emac_rgmii_pins>;
 	phy-supply = <&reg_gmac_3v3>;
 	phy-handle = <&ext_rgmii_phy>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
index e500911..6f1e0f0 100644
--- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
+++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
@@ -406,6 +406,9 @@
 	};
 };
 
+&mdio1 {
+	clock-frequency = <5000000>;
+};
 
 &iomuxc {
 	pinctrl_gpio_e6185_eeprom_sel: pinctrl-gpio-e6185-eeprom-spi0 {
diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
index 213607a..e26a278 100644
--- a/arch/arm/include/asm/kprobes.h
+++ b/arch/arm/include/asm/kprobes.h
@@ -44,20 +44,20 @@
 			     unsigned long val, void *data);
 
 /* optinsn template addresses */
-extern __visible kprobe_opcode_t optprobe_template_entry;
-extern __visible kprobe_opcode_t optprobe_template_val;
-extern __visible kprobe_opcode_t optprobe_template_call;
-extern __visible kprobe_opcode_t optprobe_template_end;
-extern __visible kprobe_opcode_t optprobe_template_sub_sp;
-extern __visible kprobe_opcode_t optprobe_template_add_sp;
-extern __visible kprobe_opcode_t optprobe_template_restore_begin;
-extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn;
-extern __visible kprobe_opcode_t optprobe_template_restore_end;
+extern __visible kprobe_opcode_t optprobe_template_entry[];
+extern __visible kprobe_opcode_t optprobe_template_val[];
+extern __visible kprobe_opcode_t optprobe_template_call[];
+extern __visible kprobe_opcode_t optprobe_template_end[];
+extern __visible kprobe_opcode_t optprobe_template_sub_sp[];
+extern __visible kprobe_opcode_t optprobe_template_add_sp[];
+extern __visible kprobe_opcode_t optprobe_template_restore_begin[];
+extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn[];
+extern __visible kprobe_opcode_t optprobe_template_restore_end[];
 
 #define MAX_OPTIMIZED_LENGTH	4
 #define MAX_OPTINSN_SIZE				\
-	((unsigned long)&optprobe_template_end -	\
-	 (unsigned long)&optprobe_template_entry)
+	((unsigned long)optprobe_template_end -	\
+	 (unsigned long)optprobe_template_entry)
 #define RELATIVEJUMP_SIZE	4
 
 struct arch_optimized_insn {
diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 05fe92a..0529f90 100644
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -32,8 +32,7 @@
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index d57112a..c23dbf8 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -354,8 +354,8 @@
 	/* set highmem page free */
 	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
 				&range_start, &range_end, NULL) {
-		unsigned long start = PHYS_PFN(range_start);
-		unsigned long end = PHYS_PFN(range_end);
+		unsigned long start = PFN_UP(range_start);
+		unsigned long end = PFN_DOWN(range_end);
 
 		/* Ignore complete lowmem entries */
 		if (end <= max_low)
diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c
index 7a449df..c78180172 100644
--- a/arch/arm/probes/kprobes/opt-arm.c
+++ b/arch/arm/probes/kprobes/opt-arm.c
@@ -85,21 +85,21 @@
 			"optprobe_template_end:\n");
 
 #define TMPL_VAL_IDX \
-	((unsigned long *)&optprobe_template_val - (unsigned long *)&optprobe_template_entry)
+	((unsigned long *)optprobe_template_val - (unsigned long *)optprobe_template_entry)
 #define TMPL_CALL_IDX \
-	((unsigned long *)&optprobe_template_call - (unsigned long *)&optprobe_template_entry)
+	((unsigned long *)optprobe_template_call - (unsigned long *)optprobe_template_entry)
 #define TMPL_END_IDX \
-	((unsigned long *)&optprobe_template_end - (unsigned long *)&optprobe_template_entry)
+	((unsigned long *)optprobe_template_end - (unsigned long *)optprobe_template_entry)
 #define TMPL_ADD_SP \
-	((unsigned long *)&optprobe_template_add_sp - (unsigned long *)&optprobe_template_entry)
+	((unsigned long *)optprobe_template_add_sp - (unsigned long *)optprobe_template_entry)
 #define TMPL_SUB_SP \
-	((unsigned long *)&optprobe_template_sub_sp - (unsigned long *)&optprobe_template_entry)
+	((unsigned long *)optprobe_template_sub_sp - (unsigned long *)optprobe_template_entry)
 #define TMPL_RESTORE_BEGIN \
-	((unsigned long *)&optprobe_template_restore_begin - (unsigned long *)&optprobe_template_entry)
+	((unsigned long *)optprobe_template_restore_begin - (unsigned long *)optprobe_template_entry)
 #define TMPL_RESTORE_ORIGN_INSN \
-	((unsigned long *)&optprobe_template_restore_orig_insn - (unsigned long *)&optprobe_template_entry)
+	((unsigned long *)optprobe_template_restore_orig_insn - (unsigned long *)optprobe_template_entry)
 #define TMPL_RESTORE_END \
-	((unsigned long *)&optprobe_template_restore_end - (unsigned long *)&optprobe_template_entry)
+	((unsigned long *)optprobe_template_restore_end - (unsigned long *)optprobe_template_entry)
 
 /*
  * ARM can always optimize an instruction when using ARM ISA, except
@@ -234,7 +234,7 @@
 	}
 
 	/* Copy arch-dep-instance from template. */
-	memcpy(code, (unsigned long *)&optprobe_template_entry,
+	memcpy(code, (unsigned long *)optprobe_template_entry,
 			TMPL_END_IDX * sizeof(kprobe_opcode_t));
 
 	/* Adjust buffer according to instruction. */
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1d466ad..1515f6f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1002,7 +1002,7 @@
 config NODES_SHIFT
 	int "Maximum NUMA Nodes (as a power of 2)"
 	range 1 10
-	default "2"
+	default "4"
 	depends on NEED_MULTIPLE_NODES
 	help
 	  Specify the maximum number of NUMA Nodes available on the target
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
index 3ea5182..e5e840b 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
@@ -105,7 +105,7 @@
 &emac {
 	pinctrl-names = "default";
 	pinctrl-0 = <&rgmii_pins>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ext_rgmii_phy>;
 	phy-supply = <&reg_dc1sw>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
index d894ec5..70e3174 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts
@@ -120,7 +120,7 @@
 &emac {
 	pinctrl-names = "default";
 	pinctrl-0 = <&rgmii_pins>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ext_rgmii_phy>;
 	phy-supply = <&reg_gmac_3v3>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
index b26181c..b54099b 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
@@ -13,7 +13,7 @@
 &emac {
 	pinctrl-names = "default";
 	pinctrl-0 = <&rgmii_pins>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-txid";
 	phy-handle = <&ext_rgmii_phy>;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts
index 3ab0f03..0494bfa 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts
@@ -122,9 +122,6 @@
 	status = "okay";
 
 	port {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
 		csi_ep: endpoint {
 			remote-endpoint = <&ov5640_ep>;
 			bus-width = <8>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts
index df1b926..6e30a56 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-libretech-all-h5-cc.dts
@@ -36,7 +36,7 @@
 	pinctrl-0 = <&emac_rgmii_pins>;
 	phy-supply = <&reg_gmac_3v3>;
 	phy-handle = <&ext_rgmii_phy>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	/delete-property/ allwinner,leds-active-low;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
index 7d7aad1..8bf2db9 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
@@ -123,7 +123,7 @@
 	pinctrl-0 = <&emac_rgmii_pins>;
 	phy-supply = <&reg_gmac_3v3>;
 	phy-handle = <&ext_rgmii_phy>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
index cb44bfa..33ab440 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
@@ -124,7 +124,7 @@
 	pinctrl-0 = <&emac_rgmii_pins>;
 	phy-supply = <&reg_gmac_3v3>;
 	phy-handle = <&ext_rgmii_phy>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
index 3f7ceeb..7c9dbde 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts
@@ -97,7 +97,7 @@
 &emac {
 	pinctrl-names = "default";
 	pinctrl-0 = <&ext_rgmii_pins>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ext_rgmii_phy>;
 	phy-supply = <&reg_aldo2>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts
index af85b20..961732c 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts
@@ -100,7 +100,7 @@
 &emac {
 	pinctrl-names = "default";
 	pinctrl-0 = <&ext_rgmii_pins>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ext_rgmii_phy>;
 	phy-supply = <&reg_gmac_3v3>;
 	allwinner,rx-delay-ps = <200>;
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
index feadd21..46e558a 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
@@ -159,7 +159,7 @@
 	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "n25q00a";
+		compatible = "micron,mt25qu02g", "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <100000000>;
 
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
index c079667..f9b4a39 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
@@ -192,7 +192,7 @@
 	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "n25q00a";
+		compatible = "micron,mt25qu02g", "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <100000000>;
 
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts
index f46eb47..8161dd2 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts
@@ -75,6 +75,7 @@
 &enetc_port0 {
 	phy-handle = <&phy0>;
 	phy-connection-type = "sgmii";
+	managed = "in-band-status";
 	status = "okay";
 
 	mdio {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
index 73e4f94..7a6fb7e 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
@@ -1012,6 +1012,7 @@
 			compatible = "fsl,ls1028a-rcpm", "fsl,qoriq-rcpm-2.1+";
 			reg = <0x0 0x1e34040 0x0 0x1c>;
 			#fsl,rcpm-wakeup-cells = <7>;
+			little-endian;
 		};
 
 		ftm_alarm0: timer@2800000 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
index ff58052..692d8f4 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
@@ -805,6 +805,7 @@
 			compatible = "fsl,ls1088a-rcpm", "fsl,qoriq-rcpm-2.1+";
 			reg = <0x0 0x1e34040 0x0 0x18>;
 			#fsl,rcpm-wakeup-cells = <6>;
+			little-endian;
 		};
 
 		ftm_alarm0: timer@2800000 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
index bf72918..e7abb74 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
@@ -892,6 +892,7 @@
 			compatible = "fsl,ls208xa-rcpm", "fsl,qoriq-rcpm-2.1+";
 			reg = <0x0 0x1e34040 0x0 0x18>;
 			#fsl,rcpm-wakeup-cells = <6>;
+			little-endian;
 		};
 
 		ftm_alarm0: timer@2800000 {
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
index 6de86a4..b88c3c9 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
@@ -72,6 +72,7 @@
 	pmic@4b {
 		compatible = "rohm,bd71847";
 		reg = <0x4b>;
+		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_pmic>;
 		interrupt-parent = <&gpio1>;
 		interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
@@ -210,6 +211,7 @@
 		host-wakeup-gpios = <&gpio2 8 GPIO_ACTIVE_HIGH>;
 		device-wakeup-gpios = <&gpio2 7 GPIO_ACTIVE_HIGH>;
 		clocks = <&osc_32k>;
+		max-speed = <4000000>;
 		clock-names = "extclk";
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
index f305a53..521eb3a 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
@@ -121,6 +121,7 @@
 	pmic@4b {
 		compatible = "rohm,bd71847";
 		reg = <0x4b>;
+		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_pmic>;
 		interrupt-parent = <&gpio1>;
 		interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi
index 4107fe9..4908252 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi
@@ -135,13 +135,10 @@
 	pmic@4b {
 		compatible = "rohm,bd71847";
 		reg = <0x4b>;
+		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_pmic>;
 		interrupt-parent = <&gpio2>;
-		/*
-		 * The interrupt is not correct. It should be level low,
-		 * however with internal pull up this causes IRQ storm.
-		 */
-		interrupts = <8 IRQ_TYPE_EDGE_RISING>;
+		interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
 		rohm,reset-snvs-powered;
 
 		#clock-cells = <0>;
@@ -398,7 +395,7 @@
 
 	pinctrl_pmic: pmicirqgrp {
 		fsl,pins = <
-			MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8	0x41
+			MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8	0x141
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
index b83f400..05ee062 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
@@ -129,7 +129,7 @@
 
 		opp-1600000000 {
 			opp-hz = /bits/ 64 <1600000000>;
-			opp-microvolt = <900000>;
+			opp-microvolt = <950000>;
 			opp-supported-hw = <0xc>, <0x7>;
 			clock-latency-ns = <150000>;
 			opp-suspend;
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
index 46e76cf..7dfee71 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
@@ -53,6 +53,7 @@
 	pmic@4b {
 		compatible = "rohm,bd71847";
 		reg = <0x4b>;
+		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_pmic>;
 		interrupt-parent = <&gpio1>;
 		interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts
index 707d848..8311b95 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-evk.dts
@@ -18,6 +18,7 @@
 	pmic: pmic@25 {
 		compatible = "nxp,pca9450b";
 		reg = <0x25>;
+		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_pmic>;
 		interrupt-parent = <&gpio1>;
 		interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi
index a2d0190..7f356ed 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi
@@ -116,13 +116,10 @@
 	pmic@4b {
 		compatible = "rohm,bd71847";
 		reg = <0x4b>;
+		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_pmic>;
 		interrupt-parent = <&gpio2>;
-		/*
-		 * The interrupt is not correct. It should be level low,
-		 * however with internal pull up this causes IRQ storm.
-		 */
-		interrupts = <8 IRQ_TYPE_EDGE_RISING>;
+		interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
 		rohm,reset-snvs-powered;
 
 		regulators {
@@ -388,7 +385,7 @@
 
 	pinctrl_pmic: pmicirqgrp {
 		fsl,pins = <
-			MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8	0x101
+			MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8	0x141
 		>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
index 746faf1..16c7202 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
@@ -790,28 +790,6 @@
 				#index-cells = <1>;
 				reg = <0x32e40200 0x200>;
 			};
-
-			usbotg2: usb@32e50000 {
-				compatible = "fsl,imx8mn-usb", "fsl,imx7d-usb";
-				reg = <0x32e50000 0x200>;
-				interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MN_CLK_USB1_CTRL_ROOT>;
-				clock-names = "usb1_ctrl_root_clk";
-				assigned-clocks = <&clk IMX8MN_CLK_USB_BUS>,
-						  <&clk IMX8MN_CLK_USB_CORE_REF>;
-				assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_500M>,
-							 <&clk IMX8MN_SYS_PLL1_100M>;
-				fsl,usbphy = <&usbphynop2>;
-				fsl,usbmisc = <&usbmisc2 0>;
-				status = "disabled";
-			};
-
-			usbmisc2: usbmisc@32e50200 {
-				compatible = "fsl,imx8mn-usbmisc", "fsl,imx7d-usbmisc";
-				#index-cells = <1>;
-				reg = <0x32e50200 0x200>;
-			};
-
 		};
 
 		dma_apbh: dma-controller@33000000 {
@@ -876,12 +854,4 @@
 		assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>;
 		clock-names = "main_clk";
 	};
-
-	usbphynop2: usbphynop2 {
-		compatible = "usb-nop-xceiv";
-		clocks = <&clk IMX8MN_CLK_USB_PHY_REF>;
-		assigned-clocks = <&clk IMX8MN_CLK_USB_PHY_REF>;
-		assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>;
-		clock-names = "main_clk";
-	};
 };
diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
index 8bc6caa..4338db1 100644
--- a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
+++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
@@ -19,6 +19,7 @@
 	clock-names = "fmanclk";
 	fsl,qman-channel-range = <0x800 0x10>;
 	ptimer-handle = <&ptp_timer0>;
+	dma-coherent;
 
 	muram@0 {
 		compatible = "fsl,fman-muram";
diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
index 96c50d4..a7a83f2 100644
--- a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
+++ b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
@@ -110,7 +110,7 @@
 	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "mt25qu02g";
+		compatible = "micron,mt25qu02g", "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <100000000>;
 
diff --git a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
index 9cbf963..c296434 100644
--- a/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774e1.dtsi
@@ -28,6 +28,12 @@
 		clock-frequency = <0>;
 	};
 
+	audio_clk_b: audio_clk_b {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <0>;
+	};
+
 	audio_clk_c: audio_clk_c {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h
index e3d47b52..ec7720d 100644
--- a/arch/arm64/include/asm/brk-imm.h
+++ b/arch/arm64/include/asm/brk-imm.h
@@ -10,6 +10,7 @@
  * #imm16 values used for BRK instruction generation
  * 0x004: for installing kprobes
  * 0x005: for installing uprobes
+ * 0x006: for kprobe software single-step
  * Allowed values for kgdb are 0x400 - 0x7ff
  * 0x100: for triggering a fault on purpose (reserved)
  * 0x400: for dynamic BRK instruction
@@ -19,6 +20,7 @@
  */
 #define KPROBES_BRK_IMM			0x004
 #define UPROBES_BRK_IMM			0x005
+#define KPROBES_BRK_SS_IMM		0x006
 #define FAULT_BRK_IMM			0x100
 #define KGDB_DYN_DBG_BRK_IMM		0x400
 #define KGDB_COMPILED_DBG_BRK_IMM	0x401
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 97244d4..da250e4 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -268,6 +268,8 @@
 /*
  * CPU feature detected at boot time based on feature of one or more CPUs.
  * All possible conflicts for a late CPU are ignored.
+ * NOTE: this means that a late CPU with the feature will *not* cause the
+ * capability to be advertised by cpus_have_*cap()!
  */
 #define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE		\
 	(ARM64_CPUCAP_SCOPE_LOCAL_CPU		|	\
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 9e2e9a6..ef5b040 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -86,6 +86,8 @@
 #define QCOM_CPU_PART_FALKOR_V1		0x800
 #define QCOM_CPU_PART_FALKOR		0xC00
 #define QCOM_CPU_PART_KRYO		0x200
+#define QCOM_CPU_PART_KRYO_2XX_GOLD	0x800
+#define QCOM_CPU_PART_KRYO_2XX_SILVER	0x801
 #define QCOM_CPU_PART_KRYO_3XX_SILVER	0x803
 #define QCOM_CPU_PART_KRYO_4XX_GOLD	0x804
 #define QCOM_CPU_PART_KRYO_4XX_SILVER	0x805
@@ -116,6 +118,8 @@
 #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
 #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
 #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
+#define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD)
+#define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER)
 #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
 #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD)
 #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 0b298f4..657c921 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -53,6 +53,7 @@
 
 /* kprobes BRK opcodes with ESR encoding  */
 #define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5))
+#define BRK64_OPCODE_KPROBES_SS	(AARCH64_BREAK_MON | (KPROBES_BRK_SS_IMM << 5))
 /* uprobes BRK opcodes with ESR encoding  */
 #define BRK64_OPCODE_UPROBES	(AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5))
 
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index 97e511d..8699ce3 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -16,7 +16,7 @@
 #include <linux/percpu.h>
 
 #define __ARCH_WANT_KPROBES_INSN_SLOT
-#define MAX_INSN_SIZE			1
+#define MAX_INSN_SIZE			2
 
 #define flush_insn_slot(p)		do { } while (0)
 #define kretprobe_blacklist_size	0
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 781d029..0cd9f0f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -118,6 +118,8 @@
 	 */
 	unsigned long *pmu_filter;
 	unsigned int pmuver;
+
+	u8 pfr0_csv2;
 };
 
 struct kvm_vcpu_fault_info {
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 174817b..e2ef4c2 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -372,6 +372,8 @@
 #define SYS_CONTEXTIDR_EL1		sys_reg(3, 0, 13, 0, 1)
 #define SYS_TPIDR_EL1			sys_reg(3, 0, 13, 0, 4)
 
+#define SYS_SCXTNUM_EL1			sys_reg(3, 0, 13, 0, 7)
+
 #define SYS_CNTKCTL_EL1			sys_reg(3, 0, 14, 1, 0)
 
 #define SYS_CCSIDR_EL1			sys_reg(3, 1, 0, 0, 0)
@@ -404,6 +406,8 @@
 #define SYS_TPIDR_EL0			sys_reg(3, 3, 13, 0, 2)
 #define SYS_TPIDRRO_EL0			sys_reg(3, 3, 13, 0, 3)
 
+#define SYS_SCXTNUM_EL0			sys_reg(3, 3, 13, 0, 7)
+
 /* Definitions for system register interface to AMU for ARMv8.4 onwards */
 #define SYS_AM_EL0(crm, op2)		sys_reg(3, 3, 13, (crm), (op2))
 #define SYS_AMCR_EL0			SYS_AM_EL0(2, 0)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 61314fd..cafaf0d 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -299,6 +299,8 @@
 	MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
 	/* Brahma-B53 r0p[0] */
 	MIDR_REV(MIDR_BRAHMA_B53, 0, 0),
+	/* Kryo2XX Silver rAp4 */
+	MIDR_REV(MIDR_QCOM_KRYO_2XX_SILVER, 0xa, 0x4),
 	{},
 };
 #endif
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index dcc165b..6f36c4f 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1337,6 +1337,8 @@
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
 		MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_GOLD),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER),
 		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
 		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
 		{ /* sentinel */ }
diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c
index af9987c..9ec3469 100644
--- a/arch/arm64/kernel/kexec_image.c
+++ b/arch/arm64/kernel/kexec_image.c
@@ -43,7 +43,7 @@
 	u64 flags, value;
 	bool be_image, be_kernel;
 	struct kexec_buf kbuf;
-	unsigned long text_offset;
+	unsigned long text_offset, kernel_segment_number;
 	struct kexec_segment *kernel_segment;
 	int ret;
 
@@ -88,11 +88,37 @@
 	/* Adjust kernel segment with TEXT_OFFSET */
 	kbuf.memsz += text_offset;
 
-	ret = kexec_add_buffer(&kbuf);
-	if (ret)
-		return ERR_PTR(ret);
+	kernel_segment_number = image->nr_segments;
 
-	kernel_segment = &image->segment[image->nr_segments - 1];
+	/*
+	 * The location of the kernel segment may make it impossible to satisfy
+	 * the other segment requirements, so we try repeatedly to find a
+	 * location that will work.
+	 */
+	while ((ret = kexec_add_buffer(&kbuf)) == 0) {
+		/* Try to load additional data */
+		kernel_segment = &image->segment[kernel_segment_number];
+		ret = load_other_segments(image, kernel_segment->mem,
+					  kernel_segment->memsz, initrd,
+					  initrd_len, cmdline);
+		if (!ret)
+			break;
+
+		/*
+		 * We couldn't find space for the other segments; erase the
+		 * kernel segment and try the next available hole.
+		 */
+		image->nr_segments -= 1;
+		kbuf.buf_min = kernel_segment->mem + kernel_segment->memsz;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+	}
+
+	if (ret) {
+		pr_err("Could not find any suitable kernel location!");
+		return ERR_PTR(ret);
+	}
+
+	kernel_segment = &image->segment[kernel_segment_number];
 	kernel_segment->mem += text_offset;
 	kernel_segment->memsz -= text_offset;
 	image->start = kernel_segment->mem;
@@ -101,12 +127,7 @@
 				kernel_segment->mem, kbuf.bufsz,
 				kernel_segment->memsz);
 
-	/* Load additional data */
-	ret = load_other_segments(image,
-				kernel_segment->mem, kernel_segment->memsz,
-				initrd, initrd_len, cmdline);
-
-	return ERR_PTR(ret);
+	return NULL;
 }
 
 #ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 5b0e67b..03210f6 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -240,6 +240,11 @@
 	return ret;
 }
 
+/*
+ * Tries to add the initrd and DTB to the image. If it is not possible to find
+ * valid locations, this function will undo changes to the image and return non
+ * zero.
+ */
 int load_other_segments(struct kimage *image,
 			unsigned long kernel_load_addr,
 			unsigned long kernel_size,
@@ -248,7 +253,8 @@
 {
 	struct kexec_buf kbuf;
 	void *headers, *dtb = NULL;
-	unsigned long headers_sz, initrd_load_addr = 0, dtb_len;
+	unsigned long headers_sz, initrd_load_addr = 0, dtb_len,
+		      orig_segments = image->nr_segments;
 	int ret = 0;
 
 	kbuf.image = image;
@@ -334,6 +340,7 @@
 	return 0;
 
 out_err:
+	image->nr_segments = orig_segments;
 	vfree(dtb);
 	return ret;
 }
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 94e8718..f6f58e6 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -73,8 +73,7 @@
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index deba7381..f11a1a1 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -36,25 +36,16 @@
 static void __kprobes
 post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
 
-static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode)
-{
-	void *addrs[1];
-	u32 insns[1];
-
-	addrs[0] = addr;
-	insns[0] = opcode;
-
-	return aarch64_insn_patch_text(addrs, insns, 1);
-}
-
 static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
 {
-	/* prepare insn slot */
-	patch_text(p->ainsn.api.insn, p->opcode);
+	kprobe_opcode_t *addr = p->ainsn.api.insn;
+	void *addrs[] = {addr, addr + 1};
+	u32 insns[] = {p->opcode, BRK64_OPCODE_KPROBES_SS};
 
-	flush_icache_range((uintptr_t) (p->ainsn.api.insn),
-			   (uintptr_t) (p->ainsn.api.insn) +
-			   MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	/* prepare insn slot */
+	aarch64_insn_patch_text(addrs, insns, 2);
+
+	flush_icache_range((uintptr_t)addr, (uintptr_t)(addr + MAX_INSN_SIZE));
 
 	/*
 	 * Needs restoring of return address after stepping xol.
@@ -128,13 +119,18 @@
 /* arm kprobe: install breakpoint in text */
 void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
-	patch_text(p->addr, BRK64_OPCODE_KPROBES);
+	void *addr = p->addr;
+	u32 insn = BRK64_OPCODE_KPROBES;
+
+	aarch64_insn_patch_text(&addr, &insn, 1);
 }
 
 /* disarm kprobe: remove breakpoint from text */
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-	patch_text(p->addr, p->opcode);
+	void *addr = p->addr;
+
+	aarch64_insn_patch_text(&addr, &p->opcode, 1);
 }
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
@@ -163,20 +159,15 @@
 }
 
 /*
- * Interrupts need to be disabled before single-step mode is set, and not
- * reenabled until after single-step mode ends.
- * Without disabling interrupt on local CPU, there is a chance of
- * interrupt occurrence in the period of exception return and  start of
- * out-of-line single-step, that result in wrongly single stepping
- * into the interrupt handler.
+ * Mask all of DAIF while executing the instruction out-of-line, to keep things
+ * simple and avoid nesting exceptions. Interrupts do have to be disabled since
+ * the kprobe state is per-CPU and doesn't get migrated.
  */
 static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
 						struct pt_regs *regs)
 {
 	kcb->saved_irqflag = regs->pstate & DAIF_MASK;
-	regs->pstate |= PSR_I_BIT;
-	/* Unmask PSTATE.D for enabling software step exceptions. */
-	regs->pstate &= ~PSR_D_BIT;
+	regs->pstate |= DAIF_MASK;
 }
 
 static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
@@ -219,10 +210,7 @@
 		slot = (unsigned long)p->ainsn.api.insn;
 
 		set_ss_context(kcb, slot);	/* mark pending ss */
-
-		/* IRQs and single stepping do not mix well. */
 		kprobes_save_local_irqflag(kcb, regs);
-		kernel_enable_single_step(regs);
 		instruction_pointer_set(regs, slot);
 	} else {
 		/* insn simulation */
@@ -273,12 +261,8 @@
 	}
 	/* call post handler */
 	kcb->kprobe_status = KPROBE_HIT_SSDONE;
-	if (cur->post_handler)	{
-		/* post_handler can hit breakpoint and single step
-		 * again, so we enable D-flag for recursive exception.
-		 */
+	if (cur->post_handler)
 		cur->post_handler(cur, regs, 0);
-	}
 
 	reset_current_kprobe();
 }
@@ -302,8 +286,6 @@
 		if (!instruction_pointer(regs))
 			BUG();
 
-		kernel_disable_single_step();
-
 		if (kcb->kprobe_status == KPROBE_REENTER)
 			restore_previous_kprobe(kcb);
 		else
@@ -365,10 +347,6 @@
 			 * pre-handler and it returned non-zero, it will
 			 * modify the execution path and no need to single
 			 * stepping. Let's just reset current kprobe and exit.
-			 *
-			 * pre_handler can hit a breakpoint and can step thru
-			 * before return, keep PSTATE D-flag enabled until
-			 * pre_handler return back.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				setup_singlestep(p, regs, kcb, 0);
@@ -399,7 +377,7 @@
 }
 
 static int __kprobes
-kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
+kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	int retval;
@@ -409,16 +387,15 @@
 
 	if (retval == DBG_HOOK_HANDLED) {
 		kprobes_restore_local_irqflag(kcb, regs);
-		kernel_disable_single_step();
-
 		post_kprobe_handler(kcb, regs);
 	}
 
 	return retval;
 }
 
-static struct step_hook kprobes_step_hook = {
-	.fn = kprobe_single_step_handler,
+static struct break_hook kprobes_break_ss_hook = {
+	.imm = KPROBES_BRK_SS_IMM,
+	.fn = kprobe_breakpoint_ss_handler,
 };
 
 static int __kprobes
@@ -486,7 +463,7 @@
 int __init arch_init_kprobes(void)
 {
 	register_kernel_break_hook(&kprobes_break_hook);
-	register_kernel_step_hook(&kprobes_step_hook);
+	register_kernel_break_hook(&kprobes_break_ss_hook);
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 4784011..a47a40e 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -522,14 +522,13 @@
 	bool prev32, next32;
 	u64 val;
 
-	if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) &&
-	      cpus_have_const_cap(ARM64_WORKAROUND_1418040)))
+	if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040))
 		return;
 
 	prev32 = is_compat_thread(task_thread_info(prev));
 	next32 = is_compat_thread(task_thread_info(next));
 
-	if (prev32 == next32)
+	if (prev32 == next32 || !this_cpu_has_cap(ARM64_WORKAROUND_1418040))
 		return;
 
 	val = read_sysreg(cntkctl_el1);
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index c18eb7d..f6e4e37 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -118,6 +118,7 @@
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
 		MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
 		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER),
 		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
 		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
 		{ /* sentinel */ }
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 43ae4e0..62d2bda 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -66,7 +66,6 @@
 
 static void cpu_psci_cpu_die(unsigned int cpu)
 {
-	int ret;
 	/*
 	 * There are no known implementations of PSCI actually using the
 	 * power state field, pass a sensible default for now.
@@ -74,9 +73,7 @@
 	u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN <<
 		    PSCI_0_2_POWER_STATE_TYPE_SHIFT;
 
-	ret = psci_ops.cpu_off(state);
-
-	pr_crit("unable to power off CPU%u (%d)\n", cpu, ret);
+	psci_ops.cpu_off(state);
 }
 
 static int cpu_psci_cpu_kill(unsigned int cpu)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 09c96f5..18e9727 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -413,6 +413,7 @@
 
 	/* Mark this CPU absent */
 	set_cpu_present(cpu, 0);
+	rcu_report_dead(cpu);
 
 	if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
 		update_cpu_boot_status(CPU_KILL_ME);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 5750ec3..c0ffb01 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -102,6 +102,20 @@
 	return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;
 }
 
+static void set_default_csv2(struct kvm *kvm)
+{
+	/*
+	 * The default is to expose CSV2 == 1 if the HW isn't affected.
+	 * Although this is a per-CPU feature, we make it global because
+	 * asymmetric systems are just a nuisance.
+	 *
+	 * Userspace can override this as long as it doesn't promise
+	 * the impossible.
+	 */
+	if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED)
+		kvm->arch.pfr0_csv2 = 1;
+}
+
 /**
  * kvm_arch_init_vm - initializes a VM data structure
  * @kvm:	pointer to the KVM struct
@@ -127,6 +141,8 @@
 	/* The maximum number of VCPUs is limited by the host's GIC model */
 	kvm->arch.max_vcpus = kvm_arm_default_max_vcpus();
 
+	set_default_csv2(kvm);
+
 	return ret;
 out_free_stage2_pgd:
 	kvm_free_stage2_pgd(&kvm->arch.mmu);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 57972bd..1a01da9 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -788,10 +788,12 @@
 	}
 
 	switch (vma_shift) {
+#ifndef __PAGETABLE_PMD_FOLDED
 	case PUD_SHIFT:
 		if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE))
 			break;
 		fallthrough;
+#endif
 	case CONT_PMD_SHIFT:
 		vma_shift = PMD_SHIFT;
 		fallthrough;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index fb12d3e..c1fac98 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1038,8 +1038,8 @@
 	{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)),					\
 	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
 
-static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
-			     const struct sys_reg_desc *r)
+static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			 const struct sys_reg_desc *r)
 {
 	kvm_inject_undefined(vcpu);
 
@@ -1047,33 +1047,25 @@
 }
 
 /* Macro to expand the AMU counter and type registers*/
-#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu }
-#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), access_amu }
-#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu }
-#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), access_amu }
-
-static bool trap_ptrauth(struct kvm_vcpu *vcpu,
-			 struct sys_reg_params *p,
-			 const struct sys_reg_desc *rd)
-{
-	/*
-	 * If we land here, that is because we didn't fixup the access on exit
-	 * by allowing the PtrAuth sysregs. The only way this happens is when
-	 * the guest does not have PtrAuth support enabled.
-	 */
-	kvm_inject_undefined(vcpu);
-
-	return false;
-}
+#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), undef_access }
+#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), undef_access }
+#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), undef_access }
+#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), undef_access }
 
 static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu,
 			const struct sys_reg_desc *rd)
 {
-	return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN_USER | REG_HIDDEN_GUEST;
+	return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN;
 }
 
+/*
+ * If we land here on a PtrAuth access, that is because we didn't
+ * fixup the access on exit by allowing the PtrAuth sysregs. The only
+ * way this happens is when the guest does not have PtrAuth support
+ * enabled.
+ */
 #define __PTRAUTH_KEY(k)						\
-	{ SYS_DESC(SYS_## k), trap_ptrauth, reset_unknown, k,		\
+	{ SYS_DESC(SYS_## k), undef_access, reset_unknown, k,		\
 	.visibility = ptrauth_visibility}
 
 #define PTRAUTH_KEY(k)							\
@@ -1128,9 +1120,8 @@
 		if (!vcpu_has_sve(vcpu))
 			val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
 		val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT);
-		if (!(val & (0xfUL << ID_AA64PFR0_CSV2_SHIFT)) &&
-		    arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED)
-			val |= (1UL << ID_AA64PFR0_CSV2_SHIFT);
+		val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT);
+		val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT);
 	} else if (id == SYS_ID_AA64PFR1_EL1) {
 		val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT);
 	} else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
@@ -1153,6 +1144,22 @@
 	return val;
 }
 
+static unsigned int id_visibility(const struct kvm_vcpu *vcpu,
+				  const struct sys_reg_desc *r)
+{
+	u32 id = sys_reg((u32)r->Op0, (u32)r->Op1,
+			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+
+	switch (id) {
+	case SYS_ID_AA64ZFR0_EL1:
+		if (!vcpu_has_sve(vcpu))
+			return REG_RAZ;
+		break;
+	}
+
+	return 0;
+}
+
 /* cpufeature ID register access trap handlers */
 
 static bool __access_id_reg(struct kvm_vcpu *vcpu,
@@ -1171,7 +1178,9 @@
 			  struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
-	return __access_id_reg(vcpu, p, r, false);
+	bool raz = sysreg_visible_as_raz(vcpu, r);
+
+	return __access_id_reg(vcpu, p, r, raz);
 }
 
 static bool access_raz_id_reg(struct kvm_vcpu *vcpu,
@@ -1192,71 +1201,40 @@
 	if (vcpu_has_sve(vcpu))
 		return 0;
 
-	return REG_HIDDEN_USER | REG_HIDDEN_GUEST;
+	return REG_HIDDEN;
 }
 
-/* Visibility overrides for SVE-specific ID registers */
-static unsigned int sve_id_visibility(const struct kvm_vcpu *vcpu,
-				      const struct sys_reg_desc *rd)
-{
-	if (vcpu_has_sve(vcpu))
-		return 0;
-
-	return REG_HIDDEN_USER;
-}
-
-/* Generate the emulated ID_AA64ZFR0_EL1 value exposed to the guest */
-static u64 guest_id_aa64zfr0_el1(const struct kvm_vcpu *vcpu)
-{
-	if (!vcpu_has_sve(vcpu))
-		return 0;
-
-	return read_sanitised_ftr_reg(SYS_ID_AA64ZFR0_EL1);
-}
-
-static bool access_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
-				   struct sys_reg_params *p,
-				   const struct sys_reg_desc *rd)
-{
-	if (p->is_write)
-		return write_to_read_only(vcpu, p, rd);
-
-	p->regval = guest_id_aa64zfr0_el1(vcpu);
-	return true;
-}
-
-static int get_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
-		const struct sys_reg_desc *rd,
-		const struct kvm_one_reg *reg, void __user *uaddr)
-{
-	u64 val;
-
-	if (WARN_ON(!vcpu_has_sve(vcpu)))
-		return -ENOENT;
-
-	val = guest_id_aa64zfr0_el1(vcpu);
-	return reg_to_user(uaddr, &val, reg->id);
-}
-
-static int set_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
-		const struct sys_reg_desc *rd,
-		const struct kvm_one_reg *reg, void __user *uaddr)
+static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
+			       const struct sys_reg_desc *rd,
+			       const struct kvm_one_reg *reg, void __user *uaddr)
 {
 	const u64 id = sys_reg_to_index(rd);
 	int err;
 	u64 val;
-
-	if (WARN_ON(!vcpu_has_sve(vcpu)))
-		return -ENOENT;
+	u8 csv2;
 
 	err = reg_from_user(&val, uaddr, id);
 	if (err)
 		return err;
 
-	/* This is what we mean by invariant: you can't change it. */
-	if (val != guest_id_aa64zfr0_el1(vcpu))
+	/*
+	 * Allow AA64PFR0_EL1.CSV2 to be set from userspace as long as
+	 * it doesn't promise more than what is actually provided (the
+	 * guest could otherwise be covered in ectoplasmic residue).
+	 */
+	csv2 = cpuid_feature_extract_unsigned_field(val, ID_AA64PFR0_CSV2_SHIFT);
+	if (csv2 > 1 ||
+	    (csv2 && arm64_get_spectre_v2_state() != SPECTRE_UNAFFECTED))
 		return -EINVAL;
 
+	/* We can only differ with CSV2, and anything else is an error */
+	val ^= read_id_reg(vcpu, rd, false);
+	val &= ~(0xFUL << ID_AA64PFR0_CSV2_SHIFT);
+	if (val)
+		return -EINVAL;
+
+	vcpu->kvm->arch.pfr0_csv2 = csv2;
+
 	return 0;
 }
 
@@ -1299,13 +1277,17 @@
 static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		      const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	return __get_id_reg(vcpu, rd, uaddr, false);
+	bool raz = sysreg_visible_as_raz(vcpu, rd);
+
+	return __get_id_reg(vcpu, rd, uaddr, raz);
 }
 
 static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		      const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	return __set_id_reg(vcpu, rd, uaddr, false);
+	bool raz = sysreg_visible_as_raz(vcpu, rd);
+
+	return __set_id_reg(vcpu, rd, uaddr, raz);
 }
 
 static int get_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
@@ -1384,19 +1366,13 @@
 	return true;
 }
 
-static bool access_mte_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
-			    const struct sys_reg_desc *r)
-{
-	kvm_inject_undefined(vcpu);
-	return false;
-}
-
 /* sys_reg_desc initialiser for known cpufeature ID registers */
 #define ID_SANITISED(name) {			\
 	SYS_DESC(SYS_##name),			\
 	.access	= access_id_reg,		\
 	.get_user = get_id_reg,			\
 	.set_user = set_id_reg,			\
+	.visibility = id_visibility,		\
 }
 
 /*
@@ -1514,11 +1490,12 @@
 
 	/* AArch64 ID registers */
 	/* CRm=4 */
-	ID_SANITISED(ID_AA64PFR0_EL1),
+	{ SYS_DESC(SYS_ID_AA64PFR0_EL1), .access = access_id_reg,
+	  .get_user = get_id_reg, .set_user = set_id_aa64pfr0_el1, },
 	ID_SANITISED(ID_AA64PFR1_EL1),
 	ID_UNALLOCATED(4,2),
 	ID_UNALLOCATED(4,3),
-	{ SYS_DESC(SYS_ID_AA64ZFR0_EL1), access_id_aa64zfr0_el1, .get_user = get_id_aa64zfr0_el1, .set_user = set_id_aa64zfr0_el1, .visibility = sve_id_visibility },
+	ID_SANITISED(ID_AA64ZFR0_EL1),
 	ID_UNALLOCATED(4,5),
 	ID_UNALLOCATED(4,6),
 	ID_UNALLOCATED(4,7),
@@ -1557,8 +1534,8 @@
 	{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
 	{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
 
-	{ SYS_DESC(SYS_RGSR_EL1), access_mte_regs },
-	{ SYS_DESC(SYS_GCR_EL1), access_mte_regs },
+	{ SYS_DESC(SYS_RGSR_EL1), undef_access },
+	{ SYS_DESC(SYS_GCR_EL1), undef_access },
 
 	{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
 	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
@@ -1584,8 +1561,8 @@
 	{ SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi },
 	{ SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi },
 
-	{ SYS_DESC(SYS_TFSR_EL1), access_mte_regs },
-	{ SYS_DESC(SYS_TFSRE0_EL1), access_mte_regs },
+	{ SYS_DESC(SYS_TFSR_EL1), undef_access },
+	{ SYS_DESC(SYS_TFSRE0_EL1), undef_access },
 
 	{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
 	{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
@@ -1621,6 +1598,8 @@
 	{ SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
 	{ SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 },
 
+	{ SYS_DESC(SYS_SCXTNUM_EL1), undef_access },
+
 	{ SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0},
 
 	{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr },
@@ -1649,14 +1628,16 @@
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
 	{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
 
-	{ SYS_DESC(SYS_AMCR_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCFGR_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCGCR_EL0), access_amu },
-	{ SYS_DESC(SYS_AMUSERENR_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu },
-	{ SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu },
+	{ SYS_DESC(SYS_SCXTNUM_EL0), undef_access },
+
+	{ SYS_DESC(SYS_AMCR_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCFGR_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCGCR_EL0), undef_access },
+	{ SYS_DESC(SYS_AMUSERENR_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCNTENCLR0_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCNTENSET0_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCNTENCLR1_EL0), undef_access },
+	{ SYS_DESC(SYS_AMCNTENSET1_EL0), undef_access },
 	AMU_AMEVCNTR0_EL0(0),
 	AMU_AMEVCNTR0_EL0(1),
 	AMU_AMEVCNTR0_EL0(2),
@@ -2185,7 +2166,7 @@
 	trace_kvm_sys_access(*vcpu_pc(vcpu), params, r);
 
 	/* Check for regs disabled by runtime config */
-	if (sysreg_hidden_from_guest(vcpu, r)) {
+	if (sysreg_hidden(vcpu, r)) {
 		kvm_inject_undefined(vcpu);
 		return;
 	}
@@ -2684,7 +2665,7 @@
 		return get_invariant_sys_reg(reg->id, uaddr);
 
 	/* Check for regs disabled by runtime config */
-	if (sysreg_hidden_from_user(vcpu, r))
+	if (sysreg_hidden(vcpu, r))
 		return -ENOENT;
 
 	if (r->get_user)
@@ -2709,7 +2690,7 @@
 		return set_invariant_sys_reg(reg->id, uaddr);
 
 	/* Check for regs disabled by runtime config */
-	if (sysreg_hidden_from_user(vcpu, r))
+	if (sysreg_hidden(vcpu, r))
 		return -ENOENT;
 
 	if (r->set_user)
@@ -2780,7 +2761,7 @@
 	if (!(rd->reg || rd->get_user))
 		return 0;
 
-	if (sysreg_hidden_from_user(vcpu, rd))
+	if (sysreg_hidden(vcpu, rd))
 		return 0;
 
 	if (!copy_reg_to_user(rd, uind))
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 5a6fc30..0f95964 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -59,8 +59,8 @@
 				   const struct sys_reg_desc *rd);
 };
 
-#define REG_HIDDEN_USER		(1 << 0) /* hidden from userspace ioctls */
-#define REG_HIDDEN_GUEST	(1 << 1) /* hidden from guest */
+#define REG_HIDDEN		(1 << 0) /* hidden from userspace and guest */
+#define REG_RAZ			(1 << 1) /* RAZ from userspace and guest */
 
 static __printf(2, 3)
 inline void print_sys_reg_msg(const struct sys_reg_params *p,
@@ -111,22 +111,22 @@
 	__vcpu_sys_reg(vcpu, r->reg) = r->val;
 }
 
-static inline bool sysreg_hidden_from_guest(const struct kvm_vcpu *vcpu,
-					    const struct sys_reg_desc *r)
+static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu,
+				 const struct sys_reg_desc *r)
 {
 	if (likely(!r->visibility))
 		return false;
 
-	return r->visibility(vcpu, r) & REG_HIDDEN_GUEST;
+	return r->visibility(vcpu, r) & REG_HIDDEN;
 }
 
-static inline bool sysreg_hidden_from_user(const struct kvm_vcpu *vcpu,
-					   const struct sys_reg_desc *r)
+static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu,
+					 const struct sys_reg_desc *r)
 {
 	if (likely(!r->visibility))
 		return false;
 
-	return r->visibility(vcpu, r) & REG_HIDDEN_USER;
+	return r->visibility(vcpu, r) & REG_RAZ;
 }
 
 static inline int cmp_sys_reg(const struct sys_reg_desc *i1,
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 1c0f3e0..ca692a8 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1444,11 +1444,28 @@
 	free_empty_tables(start, end, PAGE_OFFSET, PAGE_END);
 }
 
+static bool inside_linear_region(u64 start, u64 size)
+{
+	/*
+	 * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)]
+	 * accommodating both its ends but excluding PAGE_END. Max physical
+	 * range which can be mapped inside this linear mapping range, must
+	 * also be derived from its end points.
+	 */
+	return start >= __pa(_PAGE_OFFSET(vabits_actual)) &&
+	       (start + size - 1) <= __pa(PAGE_END - 1);
+}
+
 int arch_add_memory(int nid, u64 start, u64 size,
 		    struct mhp_params *params)
 {
 	int ret, flags = 0;
 
+	if (!inside_linear_region(start, size)) {
+		pr_err("[%llx %llx] is outside linear mapping region\n", start, start + size);
+		return -EINVAL;
+	}
+
 	if (rodata_full || debug_pagealloc_enabled())
 		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
diff --git a/arch/csky/kernel/perf_regs.c b/arch/csky/kernel/perf_regs.c
index eb32838..09b7f88 100644
--- a/arch/csky/kernel/perf_regs.c
+++ b/arch/csky/kernel/perf_regs.c
@@ -32,8 +32,7 @@
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
diff --git a/arch/mips/alchemy/common/clock.c b/arch/mips/alchemy/common/clock.c
index a95a894..f0c8303 100644
--- a/arch/mips/alchemy/common/clock.c
+++ b/arch/mips/alchemy/common/clock.c
@@ -152,6 +152,7 @@
 {
 	struct clk_init_data id;
 	struct clk_hw *h;
+	struct clk *clk;
 
 	h = kzalloc(sizeof(*h), GFP_KERNEL);
 	if (!h)
@@ -164,7 +165,13 @@
 	id.ops = &alchemy_clkops_cpu;
 	h->init = &id;
 
-	return clk_register(NULL, h);
+	clk = clk_register(NULL, h);
+	if (IS_ERR(clk)) {
+		pr_err("failed to register clock\n");
+		kfree(h);
+	}
+
+	return clk;
 }
 
 /* AUXPLLs ************************************************************/
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 0d42532..ca579de 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -262,8 +262,8 @@
 static void __init bootmem_init(void)
 {
 	phys_addr_t ramstart, ramend;
-	phys_addr_t start, end;
-	u64 i;
+	unsigned long start, end;
+	int i;
 
 	ramstart = memblock_start_of_DRAM();
 	ramend = memblock_end_of_DRAM();
@@ -300,7 +300,7 @@
 
 	min_low_pfn = ARCH_PFN_OFFSET;
 	max_pfn = PFN_DOWN(ramend);
-	for_each_mem_range(i, &start, &end) {
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
 		/*
 		 * Skip highmem here so we get an accurate max_low_pfn if low
 		 * memory stops short of high memory.
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index 38e2894..1b939ab 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -438,6 +438,7 @@
 	}
 	return mask == PM_HUGE_MASK;
 }
+EXPORT_SYMBOL(has_transparent_hugepage);
 
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE  */
 
diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
index 85ed239..567cdc5 100644
--- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
@@ -63,7 +63,7 @@
 static inline bool
 bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
-	return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000),
+	return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xff000000),
 		    "Bug: fault blocked by AP register !");
 }
 
diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
index 1d9ac0f..0bd1b14 100644
--- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
@@ -33,19 +33,18 @@
  * respectively NA for All or X for Supervisor and no access for User.
  * Then we use the APG to say whether accesses are according to Page rules or
  * "all Supervisor" rules (Access to all)
- * Therefore, we define 2 APG groups. lsb is _PMD_USER
- * 0 => Kernel => 01 (all accesses performed according to page definition)
- * 1 => User => 00 (all accesses performed as supervisor iaw page definition)
- * 2-15 => Not Used
+ * _PAGE_ACCESSED is also managed via APG. When _PAGE_ACCESSED is not set, say
+ * "all User" rules, that will lead to NA for all.
+ * Therefore, we define 4 APG groups. lsb is _PAGE_ACCESSED
+ * 0 => Kernel => 11 (all accesses performed according as user iaw page definition)
+ * 1 => Kernel+Accessed => 01 (all accesses performed according to page definition)
+ * 2 => User => 11 (all accesses performed according as user iaw page definition)
+ * 3 => User+Accessed => 00 (all accesses performed as supervisor iaw page definition) for INIT
+ *                    => 10 (all accesses performed according to swaped page definition) for KUEP
+ * 4-15 => Not Used
  */
-#define MI_APG_INIT	0x40000000
-
-/*
- * 0 => Kernel => 01 (all accesses performed according to page definition)
- * 1 => User => 10 (all accesses performed according to swaped page definition)
- * 2-15 => Not Used
- */
-#define MI_APG_KUEP	0x60000000
+#define MI_APG_INIT	0xdc000000
+#define MI_APG_KUEP	0xde000000
 
 /* The effective page number register.  When read, contains the information
  * about the last instruction TLB miss.  When MI_RPN is written, bits in
@@ -106,25 +105,9 @@
 #define MD_Ks		0x80000000	/* Should not be set */
 #define MD_Kp		0x40000000	/* Should always be set */
 
-/*
- * All pages' PP data bits are set to either 000 or 011 or 001, which means
- * respectively RW for Supervisor and no access for User, or RO for
- * Supervisor and no access for user and NA for ALL.
- * Then we use the APG to say whether accesses are according to Page rules or
- * "all Supervisor" rules (Access to all)
- * Therefore, we define 2 APG groups. lsb is _PMD_USER
- * 0 => Kernel => 01 (all accesses performed according to page definition)
- * 1 => User => 00 (all accesses performed as supervisor iaw page definition)
- * 2-15 => Not Used
- */
-#define MD_APG_INIT	0x40000000
-
-/*
- * 0 => No user => 01 (all accesses performed according to page definition)
- * 1 => User => 10 (all accesses performed according to swaped page definition)
- * 2-15 => Not Used
- */
-#define MD_APG_KUAP	0x60000000
+/* See explanation above at the definition of MI_APG_INIT */
+#define MD_APG_INIT	0xdc000000
+#define MD_APG_KUAP	0xde000000
 
 /* The effective page number register.  When read, contains the information
  * about the last instruction TLB miss.  When MD_RPN is written, bits in
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index 66f403a..1581204 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -39,9 +39,9 @@
  * into the TLB.
  */
 #define _PAGE_GUARDED	0x0010	/* Copied to L1 G entry in DTLB */
-#define _PAGE_SPECIAL	0x0020	/* SW entry */
+#define _PAGE_ACCESSED	0x0020	/* Copied to L1 APG 1 entry in I/DTLB */
 #define _PAGE_EXEC	0x0040	/* Copied to PP (bit 21) in ITLB */
-#define _PAGE_ACCESSED	0x0080	/* software: page referenced */
+#define _PAGE_SPECIAL	0x0080	/* SW entry */
 
 #define _PAGE_NA	0x0200	/* Supervisor NA, User no access */
 #define _PAGE_RO	0x0600	/* Supervisor RO, User no access */
@@ -59,11 +59,12 @@
 
 #define _PMD_PRESENT	0x0001
 #define _PMD_PRESENT_MASK	_PMD_PRESENT
-#define _PMD_BAD	0x0fd0
+#define _PMD_BAD	0x0f90
 #define _PMD_PAGE_MASK	0x000c
 #define _PMD_PAGE_8M	0x000c
 #define _PMD_PAGE_512K	0x0004
-#define _PMD_USER	0x0020	/* APG 1 */
+#define _PMD_ACCESSED	0x0020	/* APG 1 */
+#define _PMD_USER	0x0040	/* APG 2 */
 
 #define _PTE_NONE_MASK	0
 
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 8728590..3beeb03 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -6,6 +6,7 @@
 
 struct device;
 struct device_node;
+struct drmem_lmb;
 
 #ifdef CONFIG_NUMA
 
@@ -61,6 +62,9 @@
 	 */
 	return (nid < 0) ? 0 : nid;
 }
+
+int of_drconf_to_nid_single(struct drmem_lmb *lmb);
+
 #else
 
 static inline int early_cpu_to_node(int cpu) { return 0; }
@@ -84,10 +88,12 @@
 	return 0;
 }
 
-#endif /* CONFIG_NUMA */
+static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb)
+{
+	return first_online_node;
+}
 
-struct drmem_lmb;
-int of_drconf_to_nid_single(struct drmem_lmb *lmb);
+#endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
 extern int find_and_online_cpu_nid(int cpu);
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index ef5bbb70..501c9a7 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -178,7 +178,7 @@
  * are no aliasing issues.
  */
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm volatile goto(					\
+	asm_volatile_goto(					\
 		"1:	" op "%U1%X1 %0,%1	# put_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -191,7 +191,7 @@
 	__put_user_asm_goto(x, ptr, label, "std")
 #else /* __powerpc64__ */
 #define __put_user_asm2_goto(x, addr, label)			\
-	asm volatile goto(					\
+	asm_volatile_goto(					\
 		"1:	stw%X1 %0, %1\n"			\
 		"2:	stw%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index 6b50bf1..bf32704 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -264,8 +264,9 @@
 {
 	struct pci_io_addr_range *piar;
 	struct rb_node *n;
+	unsigned long flags;
 
-	spin_lock(&pci_io_addr_cache_root.piar_lock);
+	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
 	for (n = rb_first(&pci_io_addr_cache_root.rb_root); n; n = rb_next(n)) {
 		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
 
@@ -273,7 +274,7 @@
 		       (piar->flags & IORESOURCE_IO) ? "i/o" : "mem",
 		       &piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev));
 	}
-	spin_unlock(&pci_io_addr_cache_root.piar_lock);
+	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 44c9018..a1ae006 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -284,11 +284,7 @@
 
 	rlwimi	r11, r10, 22, 20, 29	/* Compute PTE address */
 	lwz	r11, 0(r11)		/* Get Linux PTE */
-#ifdef CONFIG_SWAP
 	li	r9, _PAGE_PRESENT | _PAGE_ACCESSED
-#else
-	li	r9, _PAGE_PRESENT
-#endif
 	andc.	r9, r9, r11		/* Check permission */
 	bne	5f
 
@@ -369,11 +365,7 @@
 
 	rlwimi	r11, r10, 22, 20, 29	/* Compute PTE address */
 	lwz	r11, 0(r11)		/* Get Linux PTE */
-#ifdef CONFIG_SWAP
 	li	r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#else
-	li	r9, _PAGE_PRESENT | _PAGE_EXEC
-#endif
 	andc.	r9, r9, r11		/* Check permission */
 	bne	5f
 
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 9f359d3..ee0bfeb 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -202,9 +202,7 @@
 
 InstructionTLBMiss:
 	mtspr	SPRN_SPRG_SCRATCH0, r10
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS)
 	mtspr	SPRN_SPRG_SCRATCH1, r11
-#endif
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
@@ -224,25 +222,13 @@
 3:
 	mtcr	r11
 #endif
-#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT)
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10)	/* Get level 1 entry */
 	mtspr	SPRN_MD_TWC, r11
-#else
-	lwz	r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10)	/* Get level 1 entry */
-	mtspr	SPRN_MI_TWC, r10	/* Set segment attributes */
-	mtspr	SPRN_MD_TWC, r10
-#endif
 	mfspr	r10, SPRN_MD_TWC
 	lwz	r10, 0(r10)	/* Get the pte */
-#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT)
+	rlwimi	r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
 	rlwimi	r11, r10, 32 - 9, _PMD_PAGE_512K
 	mtspr	SPRN_MI_TWC, r11
-#endif
-#ifdef CONFIG_SWAP
-	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
-	and	r11, r11, r10
-	rlwimi	r10, r11, 0, _PAGE_PRESENT
-#endif
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 20 and 23 must be clear.
 	 * Software indicator bits 22, 24, 25, 26, and 27 must be
@@ -256,9 +242,7 @@
 
 	/* Restore registers */
 0:	mfspr	r10, SPRN_SPRG_SCRATCH0
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS)
 	mfspr	r11, SPRN_SPRG_SCRATCH1
-#endif
 	rfi
 	patch_site	0b, patch__itlbmiss_exit_1
 
@@ -268,9 +252,7 @@
 	addi	r10, r10, 1
 	stw	r10, (itlb_miss_counter - PAGE_OFFSET)@l(0)
 	mfspr	r10, SPRN_SPRG_SCRATCH0
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
 	mfspr	r11, SPRN_SPRG_SCRATCH1
-#endif
 	rfi
 #endif
 
@@ -297,30 +279,16 @@
 	mfspr	r10, SPRN_MD_TWC
 	lwz	r10, 0(r10)	/* Get the pte */
 
-	/* Insert the Guarded flag into the TWC from the Linux PTE.
+	/* Insert Guarded and Accessed flags into the TWC from the Linux PTE.
 	 * It is bit 27 of both the Linux PTE and the TWC (at least
 	 * I got that right :-).  It will be better when we can put
 	 * this into the Linux pgd/pmd and load it in the operation
 	 * above.
 	 */
-	rlwimi	r11, r10, 0, _PAGE_GUARDED
+	rlwimi	r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
 	rlwimi	r11, r10, 32 - 9, _PMD_PAGE_512K
 	mtspr	SPRN_MD_TWC, r11
 
-	/* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
-	 * We also need to know if the insn is a load/store, so:
-	 * Clear _PAGE_PRESENT and load that which will
-	 * trap into DTLB Error with store bit set accordinly.
-	 */
-	/* PRESENT=0x1, ACCESSED=0x20
-	 * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
-	 * r10 = (r10 & ~PRESENT) | r11;
-	 */
-#ifdef CONFIG_SWAP
-	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
-	and	r11, r11, r10
-	rlwimi	r10, r11, 0, _PAGE_PRESENT
-#endif
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
@@ -711,7 +679,7 @@
 	li	r9, 4				/* up to 4 pages of 8M */
 	mtctr	r9
 	lis	r9, KERNELBASE@h		/* Create vaddr for TLB */
-	li	r10, MI_PS8MEG | MI_SVALID	/* Set 8M byte page */
+	li	r10, MI_PS8MEG | _PMD_ACCESSED | MI_SVALID
 	li	r11, MI_BOOTINIT		/* Create RPN for address 0 */
 1:
 	mtspr	SPRN_MI_CTR, r8	/* Set instruction MMU control */
@@ -775,7 +743,7 @@
 #ifdef CONFIG_PIN_TLB_TEXT
 	LOAD_REG_IMMEDIATE(r5, 28 << 8)
 	LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
-	LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG)
+	LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
 	LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT)
 	LOAD_REG_ADDR(r9, _sinittext)
 	li	r0, 4
@@ -797,7 +765,7 @@
 	LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM)
 #ifdef CONFIG_PIN_TLB_DATA
 	LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
-	LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG)
+	LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
 #ifdef CONFIG_PIN_TLB_IMMR
 	li	r0, 3
 #else
@@ -834,7 +802,7 @@
 #endif
 #ifdef CONFIG_PIN_TLB_IMMR
 	LOAD_REG_IMMEDIATE(r0, VIRT_IMMR_BASE | MD_EVALID)
-	LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED)
+	LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED | _PMD_ACCESSED)
 	mfspr   r8, SPRN_IMMR
 	rlwinm	r8, r8, 0, 0xfff80000
 	ori	r8, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | \
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 5eb9eed..2aa16d5 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -457,11 +457,7 @@
 	cmplw	0,r1,r3
 #endif
 	mfspr	r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
 	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#else
-	li	r1,_PAGE_PRESENT | _PAGE_EXEC
-#endif
 #if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
@@ -523,11 +519,7 @@
 	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 	mfspr	r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
 	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED
-#else
-	li	r1, _PAGE_PRESENT
-#endif
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
@@ -603,11 +595,7 @@
 	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 	mfspr	r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
 	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
-#else
-	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT
-#endif
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 3c6b982..8c2857c 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1393,13 +1393,14 @@
 /* Activate a secondary processor. */
 void start_secondary(void *unused)
 {
-	unsigned int cpu = smp_processor_id();
+	unsigned int cpu = raw_smp_processor_id();
 
 	mmgrab(&init_mm);
 	current->active_mm = &init_mm;
 
 	smp_store_cpu_info(cpu);
 	set_dec(tb_ticks_per_jiffy);
+	rcu_cpu_starting(cpu);
 	preempt_disable();
 	cpu_callin_map[cpu] = 1;
 
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index 9ed4fcc..7b25548 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -1336,7 +1336,7 @@
 			/* If this is a valid record, create the sample */
 			struct perf_output_handle handle;
 
-			if (perf_output_begin(&handle, event, header.size))
+			if (perf_output_begin(&handle, &data, event, header.size))
 				return;
 
 			perf_output_sample(&handle, &header, &data, event);
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index 8e53f2f..6f681b1 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -144,8 +144,7 @@
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) :
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index c47e6b3..824b2c9 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -476,7 +476,7 @@
 do {									\
 	long __kr_err;							\
 									\
-	__put_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err);	\
+	__put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err);	\
 	if (unlikely(__kr_err))						\
 		goto err_label;						\
 } while (0)
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 99e12fa..765b624 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2013 Linaro Limited
  * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 11e2a4f..7e84979 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -35,6 +35,10 @@
 	.word 0
 #endif
 	.balign 8
+#ifdef CONFIG_RISCV_M_MODE
+	/* Image load offset (0MB) from start of RAM for M-mode */
+	.dword 0
+#else
 #if __riscv_xlen == 64
 	/* Image load offset(2MB) from start of RAM */
 	.dword 0x200000
@@ -42,6 +46,7 @@
 	/* Image load offset(4MB) from start of RAM */
 	.dword 0x400000
 #endif
+#endif
 	/* Effective size of kernel image */
 	.dword _end - _start
 	.dword __HEAD_FLAGS
diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c
index 04a38fb..fd304a2 100644
--- a/arch/riscv/kernel/perf_regs.c
+++ b/arch/riscv/kernel/perf_regs.c
@@ -36,8 +36,7 @@
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore
index 11ebee9..3a19def 100644
--- a/arch/riscv/kernel/vdso/.gitignore
+++ b/arch/riscv/kernel/vdso/.gitignore
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 vdso.lds
 *.tmp
+vdso-syms.S
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 7d6a94d..cb8f9e4 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -43,19 +43,14 @@
 SYSCFLAGS_vdso.so.dbg = $(c_flags)
 $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE
 	$(call if_changed,vdsold)
+SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
+	-Wl,--build-id -Wl,--hash-style=both
 
 # We also create a special relocatable object that should mirror the symbol
 # table and layout of the linked DSO. With ld --just-symbols we can then
 # refer to these symbols in the kernel code rather than hand-coded addresses.
-
-SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
-	-Wl,--build-id=sha1 -Wl,--hash-style=both
-$(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE
-	$(call if_changed,vdsold)
-
-LDFLAGS_vdso-syms.o := -r --just-symbols
-$(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE
-	$(call if_changed,ld)
+$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE
+	$(call if_changed,so2s)
 
 # strip rule for the .so file
 $(obj)/%.so: OBJCOPYFLAGS := -S
@@ -73,6 +68,11 @@
                            $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
                    rm $@.tmp
 
+# Extracts symbol offsets from the VDSO, converting them into an assembly file
+# that contains the same symbols at the same offsets.
+quiet_cmd_so2s = SO2S    $@
+      cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@
+
 # install commands for the unstripped file
 quiet_cmd_vdso_install = INSTALL $@
       cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
diff --git a/arch/riscv/kernel/vdso/so2s.sh b/arch/riscv/kernel/vdso/so2s.sh
new file mode 100755
index 0000000..e64cb6d
--- /dev/null
+++ b/arch/riscv/kernel/vdso/so2s.sh
@@ -0,0 +1,6 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+# Copyright 2020 Palmer Dabbelt <palmerdabbelt@google.com>
+
+sed 's!\([0-9a-f]*\) T \([a-z0-9_]*\)\(@@LINUX_4.15\)*!.global \2\n.set \2,0x\1!' \
+| grep '^\.'
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 1359e21..3c8b9e4 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -86,6 +86,7 @@
 	pmd_t *pmd, *pmd_k;
 	pte_t *pte_k;
 	int index;
+	unsigned long pfn;
 
 	/* User mode accesses just cause a SIGSEGV */
 	if (user_mode(regs))
@@ -100,7 +101,8 @@
 	 * of a task switch.
 	 */
 	index = pgd_index(addr);
-	pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index;
+	pfn = csr_read(CSR_SATP) & SATP_PPN;
+	pgd = (pgd_t *)pfn_to_virt(pfn) + index;
 	pgd_k = init_mm.pgd + index;
 
 	if (!pgd_present(*pgd_k)) {
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index ea933b7..8e577f1 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -154,9 +154,8 @@
 
 void __init setup_bootmem(void)
 {
-	phys_addr_t mem_size = 0;
-	phys_addr_t total_mem = 0;
-	phys_addr_t mem_start, start, end = 0;
+	phys_addr_t mem_start = 0;
+	phys_addr_t start, end = 0;
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
 	phys_addr_t vmlinux_start = __pa_symbol(&_start);
 	u64 i;
@@ -164,21 +163,18 @@
 	/* Find the memory region containing the kernel */
 	for_each_mem_range(i, &start, &end) {
 		phys_addr_t size = end - start;
-		if (!total_mem)
+		if (!mem_start)
 			mem_start = start;
 		if (start <= vmlinux_start && vmlinux_end <= end)
 			BUG_ON(size == 0);
-		total_mem = total_mem + size;
 	}
 
 	/*
-	 * Remove memblock from the end of usable area to the
-	 * end of region
+	 * The maximal physical memory size is -PAGE_OFFSET.
+	 * Make sure that any memory beyond mem_start + (-PAGE_OFFSET) is removed
+	 * as it is unusable by kernel.
 	 */
-	mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET);
-	if (mem_start + mem_size < end)
-		memblock_remove(mem_start + mem_size,
-				end - mem_start - mem_size);
+	memblock_enforce_memory_limit(mem_start - PAGE_OFFSET);
 
 	/* Reserve from the start of the kernel to the end of the kernel */
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
@@ -297,6 +293,7 @@
 #define NUM_EARLY_PMDS		(1UL + MAX_EARLY_MAPPING_SIZE / PGDIR_SIZE)
 #endif
 pmd_t early_pmd[PTRS_PER_PMD * NUM_EARLY_PMDS] __initdata __aligned(PAGE_SIZE);
+pmd_t early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
 
 static pmd_t *__init get_pmd_virt_early(phys_addr_t pa)
 {
@@ -494,6 +491,18 @@
 				   load_pa + (va - PAGE_OFFSET),
 				   map_size, PAGE_KERNEL_EXEC);
 
+#ifndef __PAGETABLE_PMD_FOLDED
+	/* Setup early PMD for DTB */
+	create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
+			   (uintptr_t)early_dtb_pmd, PGDIR_SIZE, PAGE_TABLE);
+	/* Create two consecutive PMD mappings for FDT early scan */
+	pa = dtb_pa & ~(PMD_SIZE - 1);
+	create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA,
+			   pa, PMD_SIZE, PAGE_KERNEL);
+	create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE,
+			   pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL);
+	dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1));
+#else
 	/* Create two consecutive PGD mappings for FDT early scan */
 	pa = dtb_pa & ~(PGDIR_SIZE - 1);
 	create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
@@ -501,6 +510,7 @@
 	create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA + PGDIR_SIZE,
 			   pa + PGDIR_SIZE, PGDIR_SIZE, PAGE_KERNEL);
 	dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PGDIR_SIZE - 1));
+#endif
 	dtb_early_pa = dtb_pa;
 
 	/*
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 0784bf3..fe6f529 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -1,3 +1,4 @@
+CONFIG_UAPI_HEADER_TEST=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_WATCH_QUEUE=y
@@ -93,9 +94,10 @@
 CONFIG_FRONTSWAP=y
 CONFIG_CMA_DEBUG=y
 CONFIG_CMA_DEBUGFS=y
+CONFIG_CMA_AREAS=7
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC=y
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
@@ -378,7 +380,6 @@
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
-# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
 # CONFIG_PCIEASPM is not set
 CONFIG_PCI_DEBUG=y
@@ -386,7 +387,7 @@
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_DEVTMPFS=y
 CONFIG_CONNECTOR=y
-CONFIG_ZRAM=m
+CONFIG_ZRAM=y
 CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
@@ -689,6 +690,7 @@
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_SM2=m
 CONFIG_CRYPTO_CURVE25519=m
 CONFIG_CRYPTO_GCM=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
@@ -709,7 +711,6 @@
 CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -753,6 +754,7 @@
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_CORDIC=m
 CONFIG_CRC32_SELFTEST=y
 CONFIG_CRC4=m
@@ -829,6 +831,7 @@
 CONFIG_FAULT_INJECTION=y
 CONFIG_FAILSLAB=y
 CONFIG_FAIL_PAGE_ALLOC=y
+CONFIG_FAULT_INJECTION_USERCOPY=y
 CONFIG_FAIL_MAKE_REQUEST=y
 CONFIG_FAIL_IO_TIMEOUT=y
 CONFIG_FAIL_FUTEX=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 905bc8c..17d5df2c 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -87,9 +87,10 @@
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CLEANCACHE=y
 CONFIG_FRONTSWAP=y
+CONFIG_CMA_AREAS=7
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC=y
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
@@ -371,7 +372,6 @@
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
-# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
 # CONFIG_PCIEASPM is not set
 CONFIG_HOTPLUG_PCI=y
@@ -379,7 +379,7 @@
 CONFIG_UEVENT_HELPER=y
 CONFIG_DEVTMPFS=y
 CONFIG_CONNECTOR=y
-CONFIG_ZRAM=m
+CONFIG_ZRAM=y
 CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
@@ -680,6 +680,7 @@
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_SM2=m
 CONFIG_CRYPTO_CURVE25519=m
 CONFIG_CRYPTO_GCM=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
@@ -701,7 +702,6 @@
 CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -745,6 +745,7 @@
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_CORDIC=m
 CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC4=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 8f67c55..a302630 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -17,11 +17,11 @@
 # CONFIG_CHSC_SCH is not set
 # CONFIG_SCM_BUS is not set
 CONFIG_CRASH_DUMP=y
-# CONFIG_SECCOMP is not set
 # CONFIG_PFAULT is not set
 # CONFIG_S390_HYPFS_FS is not set
 # CONFIG_VIRTUALIZATION is not set
 # CONFIG_S390_GUEST is not set
+# CONFIG_SECCOMP is not set
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 6b8d8c6..b5dbae7 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -692,16 +692,6 @@
 	return !!(pud_val(pud) & _REGION3_ENTRY_LARGE);
 }
 
-static inline unsigned long pud_pfn(pud_t pud)
-{
-	unsigned long origin_mask;
-
-	origin_mask = _REGION_ENTRY_ORIGIN;
-	if (pud_large(pud))
-		origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
-	return (pud_val(pud) & origin_mask) >> PAGE_SHIFT;
-}
-
 #define pmd_leaf	pmd_large
 static inline int pmd_large(pmd_t pmd)
 {
@@ -747,16 +737,6 @@
 	return pmd_val(pmd) == _SEGMENT_ENTRY_EMPTY;
 }
 
-static inline unsigned long pmd_pfn(pmd_t pmd)
-{
-	unsigned long origin_mask;
-
-	origin_mask = _SEGMENT_ENTRY_ORIGIN;
-	if (pmd_large(pmd))
-		origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE;
-	return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
-}
-
 #define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
@@ -1238,11 +1218,39 @@
 #define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
 #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
 
-#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
-#define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN)
 #define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN)
 #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN)
 
+static inline unsigned long pmd_deref(pmd_t pmd)
+{
+	unsigned long origin_mask;
+
+	origin_mask = _SEGMENT_ENTRY_ORIGIN;
+	if (pmd_large(pmd))
+		origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE;
+	return pmd_val(pmd) & origin_mask;
+}
+
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+	return pmd_deref(pmd) >> PAGE_SHIFT;
+}
+
+static inline unsigned long pud_deref(pud_t pud)
+{
+	unsigned long origin_mask;
+
+	origin_mask = _REGION_ENTRY_ORIGIN;
+	if (pud_large(pud))
+		origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
+	return pud_val(pud) & origin_mask;
+}
+
+static inline unsigned long pud_pfn(pud_t pud)
+{
+	return pud_deref(pud) >> PAGE_SHIFT;
+}
+
 /*
  * The pgd_offset function *always* adds the index for the top-level
  * region/segment table. This is done to get a sequence like the
diff --git a/arch/s390/include/asm/vdso/vdso.h b/arch/s390/include/asm/vdso/vdso.h
deleted file mode 100644
index e69de29..0000000
--- a/arch/s390/include/asm/vdso/vdso.h
+++ /dev/null
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index ece58f2..2012c1c 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -61,14 +61,6 @@
 	BLANK();
 	OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val);
 	BLANK();
-	/* constants used by the vdso */
-	DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME);
-	DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC);
-	DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
-	DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
-	DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID);
-	DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC);
-	BLANK();
 	/* idle data offsets */
 	OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter);
 	OFFSET(__CLOCK_IDLE_EXIT, s390_idle_data, clock_idle_exit);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 8623591..5346545 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -422,6 +422,7 @@
 #endif
 	LOCKDEP_SYS_EXIT
 .Lsysc_tif:
+	DISABLE_INTS
 	TSTMSK	__PT_FLAGS(%r11),_PIF_WORK
 	jnz	.Lsysc_work
 	TSTMSK	__TI_flags(%r12),_TIF_WORK
@@ -444,6 +445,7 @@
 # One of the work bits is on. Find out which one.
 #
 .Lsysc_work:
+	ENABLE_INTS
 	TSTMSK	__TI_flags(%r12),_TIF_NEED_RESCHED
 	jo	.Lsysc_reschedule
 	TSTMSK	__PT_FLAGS(%r11),_PIF_SYSCALL_RESTART
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 4f9e462..19cd7b9 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -672,7 +672,7 @@
 	rcu_read_lock();
 
 	perf_prepare_sample(&header, data, event, regs);
-	if (perf_output_begin(&handle, event, header.size))
+	if (perf_output_begin(&handle, data, event, header.size))
 		goto out;
 
 	/* Update the process ID (see also kernel/events/core.c) */
@@ -2228,4 +2228,4 @@
 }
 
 arch_initcall(init_cpum_sampling_pmu);
-core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640);
+core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0644);
diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c
index 4352a504..6e9e5d5 100644
--- a/arch/s390/kernel/perf_regs.c
+++ b/arch/s390/kernel/perf_regs.c
@@ -53,8 +53,7 @@
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	/*
 	 * Use the regs from the first interruption and let
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index ebfe86d..390d97d 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -855,13 +855,14 @@
 
 static void smp_init_secondary(void)
 {
-	int cpu = smp_processor_id();
+	int cpu = raw_smp_processor_id();
 
 	S390_lowcore.last_update_clock = get_tod_clock();
 	restore_access_regs(S390_lowcore.access_regs_save_area);
 	set_cpu_flag(CIF_ASCE_PRIMARY);
 	set_cpu_flag(CIF_ASCE_SECONDARY);
 	cpu_init();
+	rcu_cpu_starting(cpu);
 	preempt_disable();
 	init_cpu_timer();
 	vtime_init();
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index d33f215..9a6bae5 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -101,6 +101,10 @@
 		if (ret)
 			break;
 
+		/* the PCI function will be scanned once function 0 appears */
+		if (!zdev->zbus->bus)
+			break;
+
 		pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn);
 		if (!pdev)
 			break;
diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h
index 5393e13..2bbf28c 100644
--- a/arch/um/include/asm/pgalloc.h
+++ b/arch/um/include/asm/pgalloc.h
@@ -33,7 +33,13 @@
 } while (0)
 
 #ifdef CONFIG_3_LEVEL_PGTABLES
-#define __pmd_free_tlb(tlb,x, address)   tlb_remove_page((tlb),virt_to_page(x))
+
+#define __pmd_free_tlb(tlb, pmd, address)		\
+do {							\
+	pgtable_pmd_page_dtor(virt_to_page(pmd));	\
+	tlb_remove_page((tlb),virt_to_page(pmd));	\
+} while (0)						\
+
 #endif
 
 #endif
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index a5e5db6..39b2ede 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -164,6 +164,7 @@
 	add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE);
 
 	/* Load the new page-table. */
+	sev_verify_cbit(top_level_pgt);
 	write_cr3(top_level_pgt);
 }
 
diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S
index dd07e7b..aa56179 100644
--- a/arch/x86/boot/compressed/mem_encrypt.S
+++ b/arch/x86/boot/compressed/mem_encrypt.S
@@ -68,6 +68,9 @@
 SYM_FUNC_END(get_sev_encryption_bit)
 
 	.code64
+
+#include "../../kernel/sev_verify_cbit.S"
+
 SYM_FUNC_START(set_sev_encryption_mask)
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	push	%rbp
@@ -81,6 +84,19 @@
 
 	bts	%rax, sme_me_mask(%rip)	/* Create the encryption mask */
 
+	/*
+	 * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in
+	 * get_sev_encryption_bit() because this function is 32-bit code and
+	 * shared between 64-bit and 32-bit boot path.
+	 */
+	movl	$MSR_AMD64_SEV, %ecx	/* Read the SEV MSR */
+	rdmsr
+
+	/* Store MSR value in sev_status */
+	shlq	$32, %rdx
+	orq	%rdx, %rax
+	movq	%rax, sev_status(%rip)
+
 .Lno_sev_mask:
 	movq	%rbp, %rsp		/* Restore original stack pointer */
 
@@ -96,5 +112,7 @@
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	.balign	8
-SYM_DATA(sme_me_mask, .quad 0)
+SYM_DATA(sme_me_mask,		.quad 0)
+SYM_DATA(sev_status,		.quad 0)
+SYM_DATA(sev_check_data,	.quad 0)
 #endif
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 6d31f1b..d9a631c 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -159,4 +159,6 @@
 void boot_stage1_vc(void);
 void boot_stage2_vc(void);
 
+unsigned long sev_verify_cbit(unsigned long cr3);
+
 #endif /* BOOT_COMPRESSED_MISC_H */
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index f1926e9..af457f8c 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2630,7 +2630,7 @@
 		u64 pebs_enabled = cpuc->pebs_enabled;
 
 		handled++;
-		x86_pmu.drain_pebs(regs);
+		x86_pmu.drain_pebs(regs, &data);
 		status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
 
 		/*
@@ -4987,6 +4987,12 @@
 
 	x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
 
+	if (version >= 5) {
+		x86_pmu.intel_cap.anythread_deprecated = edx.split.anythread_deprecated;
+		if (x86_pmu.intel_cap.anythread_deprecated)
+			pr_cont(" AnyThread deprecated, ");
+	}
+
 	/*
 	 * Install the hw-cache-events table:
 	 */
@@ -5512,6 +5518,10 @@
 	x86_pmu.intel_ctrl |=
 		((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
 
+	/* AnyThread may be deprecated on arch perfmon v5 or later */
+	if (x86_pmu.intel_cap.anythread_deprecated)
+		x86_pmu.format_attrs = intel_arch_formats_attr;
+
 	if (x86_pmu.event_constraints) {
 		/*
 		 * event on fixed counter2 (REF_CYCLES) only works on this
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 404315d..b47cc42 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -642,8 +642,8 @@
 	rcu_read_lock();
 	perf_prepare_sample(&header, &data, event, &regs);
 
-	if (perf_output_begin(&handle, event, header.size *
-			      (top - base - skip)))
+	if (perf_output_begin(&handle, &data, event,
+			      header.size * (top - base - skip)))
 		goto unlock;
 
 	for (at = base; at < top; at++) {
@@ -670,7 +670,9 @@
 
 static inline void intel_pmu_drain_pebs_buffer(void)
 {
-	x86_pmu.drain_pebs(NULL);
+	struct perf_sample_data data;
+
+	x86_pmu.drain_pebs(NULL, &data);
 }
 
 /*
@@ -1719,23 +1721,24 @@
 	return 0;
 }
 
-static void __intel_pmu_pebs_event(struct perf_event *event,
-				   struct pt_regs *iregs,
-				   void *base, void *top,
-				   int bit, int count,
-				   void (*setup_sample)(struct perf_event *,
-						struct pt_regs *,
-						void *,
-						struct perf_sample_data *,
-						struct pt_regs *))
+static __always_inline void
+__intel_pmu_pebs_event(struct perf_event *event,
+		       struct pt_regs *iregs,
+		       struct perf_sample_data *data,
+		       void *base, void *top,
+		       int bit, int count,
+		       void (*setup_sample)(struct perf_event *,
+					    struct pt_regs *,
+					    void *,
+					    struct perf_sample_data *,
+					    struct pt_regs *))
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	struct perf_sample_data data;
 	struct x86_perf_regs perf_regs;
 	struct pt_regs *regs = &perf_regs.regs;
 	void *at = get_next_pebs_record_by_bit(base, top, bit);
-	struct pt_regs dummy_iregs;
+	static struct pt_regs dummy_iregs;
 
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
 		/*
@@ -1752,14 +1755,14 @@
 		iregs = &dummy_iregs;
 
 	while (count > 1) {
-		setup_sample(event, iregs, at, &data, regs);
-		perf_event_output(event, &data, regs);
+		setup_sample(event, iregs, at, data, regs);
+		perf_event_output(event, data, regs);
 		at += cpuc->pebs_record_size;
 		at = get_next_pebs_record_by_bit(at, top, bit);
 		count--;
 	}
 
-	setup_sample(event, iregs, at, &data, regs);
+	setup_sample(event, iregs, at, data, regs);
 	if (iregs == &dummy_iregs) {
 		/*
 		 * The PEBS records may be drained in the non-overflow context,
@@ -1767,18 +1770,18 @@
 		 * last record the same as other PEBS records, and doesn't
 		 * invoke the generic overflow handler.
 		 */
-		perf_event_output(event, &data, regs);
+		perf_event_output(event, data, regs);
 	} else {
 		/*
 		 * All but the last records are processed.
 		 * The last one is left to be able to call the overflow handler.
 		 */
-		if (perf_event_overflow(event, &data, regs))
+		if (perf_event_overflow(event, data, regs))
 			x86_pmu_stop(event, 0);
 	}
 }
 
-static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
@@ -1812,7 +1815,7 @@
 		return;
 	}
 
-	__intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+	__intel_pmu_pebs_event(event, iregs, data, at, top, 0, n,
 			       setup_pebs_fixed_sample_data);
 }
 
@@ -1835,7 +1838,7 @@
 	}
 }
 
-static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_data *data)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
@@ -1942,14 +1945,14 @@
 		}
 
 		if (counts[bit]) {
-			__intel_pmu_pebs_event(event, iregs, base,
+			__intel_pmu_pebs_event(event, iregs, data, base,
 					       top, bit, counts[bit],
 					       setup_pebs_fixed_sample_data);
 		}
 	}
 }
 
-static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data)
 {
 	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1997,7 +2000,7 @@
 		if (WARN_ON_ONCE(!event->attr.precise_ip))
 			continue;
 
-		__intel_pmu_pebs_event(event, iregs, base,
+		__intel_pmu_pebs_event(event, iregs, data, base,
 				       top, bit, counts[bit],
 				       setup_pebs_adaptive_sample_data);
 	}
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 39e632e..bbd1120 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -475,7 +475,7 @@
 static struct freerunning_counters snb_uncore_imc_freerunning[] = {
 	[SNB_PCI_UNCORE_IMC_DATA_READS]		= { SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
 							0x0, 0x0, 1, 32 },
-	[SNB_PCI_UNCORE_IMC_DATA_READS]		= { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE,
+	[SNB_PCI_UNCORE_IMC_DATA_WRITES]	= { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE,
 							0x0, 0x0, 1, 32 },
 	[SNB_PCI_UNCORE_IMC_GT_REQUESTS]	= { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE,
 							0x0, 0x0, 1, 32 },
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ee2b9b9..6a8edfe 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -585,6 +585,7 @@
 		u64     pebs_baseline:1;
 		u64	perf_metrics:1;
 		u64	pebs_output_pt_available:1;
+		u64	anythread_deprecated:1;
 	};
 	u64	capabilities;
 };
@@ -727,7 +728,7 @@
 	int		pebs_record_size;
 	int		pebs_buffer_size;
 	int		max_pebs_events;
-	void		(*drain_pebs)(struct pt_regs *regs);
+	void		(*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
 	unsigned long	large_pebs_flags;
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 40e0e32..284e736 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -273,11 +273,15 @@
 		pr_info("Hyper-V: Using enlightened APIC (%s mode)",
 			x2apic_enabled() ? "x2apic" : "xapic");
 		/*
-		 * With x2apic, architectural x2apic MSRs are equivalent to the
-		 * respective synthetic MSRs, so there's no need to override
-		 * the apic accessors.  The only exception is
-		 * hv_apic_eoi_write, because it benefits from lazy EOI when
-		 * available, but it works for both xapic and x2apic modes.
+		 * When in x2apic mode, don't use the Hyper-V specific APIC
+		 * accessors since the field layout in the ICR register is
+		 * different in x2apic mode. Furthermore, the architectural
+		 * x2apic MSRs function just as well as the Hyper-V
+		 * synthetic APIC MSRs, so there's no benefit in having
+		 * separate Hyper-V accessors for x2apic mode. The only
+		 * exception is hv_apic_eoi_write, because it benefits from
+		 * lazy EOI when available, but the same accessor works for
+		 * both xapic and x2apic because the field layout is the same.
 		 */
 		apic_set_eoi_write(hv_apic_eoi_write);
 		if (!x2apic_enabled()) {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d44858b..324ddd7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -639,6 +639,7 @@
 	int cpuid_nent;
 	struct kvm_cpuid_entry2 *cpuid_entries;
 
+	unsigned long cr3_lm_rsvd_bits;
 	int maxphyaddr;
 	int max_tdp_level;
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 6960cd6..b9a7fd0 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -137,7 +137,9 @@
 	struct {
 		unsigned int num_counters_fixed:5;
 		unsigned int bit_width_fixed:8;
-		unsigned int reserved:19;
+		unsigned int reserved1:2;
+		unsigned int anythread_deprecated:1;
+		unsigned int reserved2:16;
 	} split;
 	unsigned int full;
 };
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index 172d3e4a..648eb23f 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -2,14 +2,8 @@
 #ifndef _ASM_X86_UV_UV_H
 #define _ASM_X86_UV_UV_H
 
-#include <asm/tlbflush.h>
-
 enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC};
 
-struct cpumask;
-struct mm_struct;
-struct flush_tlb_info;
-
 #ifdef CONFIG_X86_UV
 #include <linux/efi.h>
 
@@ -44,10 +38,6 @@
 static inline int is_uv_hubbed(int uv)	{ return 0; }
 static inline void uv_cpu_init(void)	{ }
 static inline void uv_system_init(void)	{ }
-static inline const struct cpumask *
-uv_flush_tlb_others(const struct cpumask *cpumask,
-		    const struct flush_tlb_info *info)
-{ return cpumask; }
 
 #endif	/* X86_UV */
 
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 714233c..1b98f8c 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -33,7 +33,7 @@
 static int			uv_node_id;
 
 /* Unpack AT/OEM/TABLE ID's to be NULL terminated strings */
-static u8 uv_archtype[UV_AT_SIZE];
+static u8 uv_archtype[UV_AT_SIZE + 1];
 static u8 oem_id[ACPI_OEM_ID_SIZE + 1];
 static u8 oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
 
@@ -290,6 +290,9 @@
 {
 	/* Relies on 'to' being NULL chars so result will be NULL terminated */
 	strncpy(to, from, len-1);
+
+	/* Trim trailing spaces */
+	(void)strim(to);
 }
 
 /* Find UV arch type entry in UVsystab */
@@ -317,7 +320,7 @@
 
 	if (n > 0 && n < sizeof(uv_ate->archtype)) {
 		pr_info("UV: UVarchtype received from BIOS\n");
-		uv_stringify(UV_AT_SIZE, uv_archtype, uv_ate->archtype);
+		uv_stringify(sizeof(uv_archtype), uv_archtype, uv_ate->archtype);
 		return 1;
 	}
 	return 0;
@@ -366,7 +369,7 @@
 	return ret;
 }
 
-static int __init uv_set_system_type(char *_oem_id)
+static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id)
 {
 	/* Save OEM_ID passed from ACPI MADT */
 	uv_stringify(sizeof(oem_id), oem_id, _oem_id);
@@ -375,7 +378,7 @@
 	if (!early_get_arch_type())
 
 		/* If not use OEM ID for UVarchtype */
-		uv_stringify(UV_AT_SIZE, uv_archtype, _oem_id);
+		uv_stringify(sizeof(uv_archtype), uv_archtype, oem_id);
 
 	/* Check if not hubbed */
 	if (strncmp(uv_archtype, "SGI", 3) != 0) {
@@ -386,13 +389,23 @@
 			/* (Not hubless), not a UV */
 			return 0;
 
+		/* Is UV hubless system */
+		uv_hubless_system = 0x01;
+
+		/* UV5 Hubless */
+		if (strncmp(uv_archtype, "NSGI5", 5) == 0)
+			uv_hubless_system |= 0x20;
+
 		/* UV4 Hubless: CH */
-		if (strncmp(uv_archtype, "NSGI4", 5) == 0)
-			uv_hubless_system = 0x11;
+		else if (strncmp(uv_archtype, "NSGI4", 5) == 0)
+			uv_hubless_system |= 0x10;
 
 		/* UV3 Hubless: UV300/MC990X w/o hub */
 		else
-			uv_hubless_system = 0x9;
+			uv_hubless_system |= 0x8;
+
+		/* Copy APIC type */
+		uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id);
 
 		pr_info("UV: OEM IDs %s/%s, SystemType %d, HUBLESS ID %x\n",
 			oem_id, oem_table_id, uv_system_type, uv_hubless_system);
@@ -456,7 +469,7 @@
 	uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
 
 	/* If not UV, return. */
-	if (likely(uv_set_system_type(_oem_id) == 0))
+	if (uv_set_system_type(_oem_id, _oem_table_id) == 0)
 		return 0;
 
 	/* Save and Decode OEM Table ID */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d3f0db46..581fb72 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1254,6 +1254,14 @@
 	return 0;
 }
 
+static bool is_spec_ib_user_controlled(void)
+{
+	return spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
+		spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
+		spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
+		spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP;
+}
+
 static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 {
 	switch (ctrl) {
@@ -1261,16 +1269,26 @@
 		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
 		    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 			return 0;
+
 		/*
-		 * Indirect branch speculation is always disabled in strict
-		 * mode. It can neither be enabled if it was force-disabled
-		 * by a  previous prctl call.
+		 * With strict mode for both IBPB and STIBP, the instruction
+		 * code paths avoid checking this task flag and instead,
+		 * unconditionally run the instruction. However, STIBP and IBPB
+		 * are independent and either can be set to conditionally
+		 * enabled regardless of the mode of the other.
+		 *
+		 * If either is set to conditional, allow the task flag to be
+		 * updated, unless it was force-disabled by a previous prctl
+		 * call. Currently, this is possible on an AMD CPU which has the
+		 * feature X86_FEATURE_AMD_STIBP_ALWAYS_ON. In this case, if the
+		 * kernel is booted with 'spectre_v2_user=seccomp', then
+		 * spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP and
+		 * spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED.
 		 */
-		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ||
+		if (!is_spec_ib_user_controlled() ||
 		    task_spec_ib_force_disable(task))
 			return -EPERM;
+
 		task_clear_spec_ib_disable(task);
 		task_update_spec_tif(task);
 		break;
@@ -1283,10 +1301,10 @@
 		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
 		    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 			return -EPERM;
-		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+
+		if (!is_spec_ib_user_controlled())
 			return 0;
+
 		task_set_spec_ib_disable(task);
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
 			task_set_spec_ib_force_disable(task);
@@ -1351,20 +1369,17 @@
 	if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
 	    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 		return PR_SPEC_ENABLE;
-	else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
-		return PR_SPEC_DISABLE;
-	else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
-	    spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) {
+	else if (is_spec_ib_user_controlled()) {
 		if (task_spec_ib_force_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
 		if (task_spec_ib_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
 		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
-	} else
+	} else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+		return PR_SPEC_DISABLE;
+	else
 		return PR_SPEC_NOT_AFFECTED;
 }
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7eb2a1c..3c41773 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -161,6 +161,21 @@
 
 	/* Setup early boot stage 4-/5-level pagetables. */
 	addq	phys_base(%rip), %rax
+
+	/*
+	 * For SEV guests: Verify that the C-bit is correct. A malicious
+	 * hypervisor could lie about the C-bit position to perform a ROP
+	 * attack on the guest by writing to the unencrypted stack and wait for
+	 * the next RET instruction.
+	 * %rsi carries pointer to realmode data and is callee-clobbered. Save
+	 * and restore it.
+	 */
+	pushq	%rsi
+	movq	%rax, %rdi
+	call	sev_verify_cbit
+	popq	%rsi
+
+	/* Switch to new page-table */
 	movq	%rax, %cr3
 
 	/* Ensure I am executing from virtual addresses */
@@ -279,6 +294,7 @@
 SYM_CODE_END(secondary_startup_64)
 
 #include "verify_cpu.S"
+#include "sev_verify_cbit.S"
 
 #ifdef CONFIG_HOTPLUG_CPU
 /*
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index bb7e113..f9e5352 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -101,8 +101,7 @@
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
@@ -129,12 +128,20 @@
 		return PERF_SAMPLE_REGS_ABI_64;
 }
 
+static DEFINE_PER_CPU(struct pt_regs, nmi_user_regs);
+
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
+	struct pt_regs *regs_user_copy = this_cpu_ptr(&nmi_user_regs);
 	struct pt_regs *user_regs = task_pt_regs(current);
 
+	if (!in_nmi()) {
+		regs_user->regs = user_regs;
+		regs_user->abi = perf_reg_abi(current);
+		return;
+	}
+
 	/*
 	 * If we're in an NMI that interrupted task_pt_regs setup, then
 	 * we can't sample user regs at all.  This check isn't really
diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c
index 5f83cca..7d04b35 100644
--- a/arch/x86/kernel/sev-es-shared.c
+++ b/arch/x86/kernel/sev-es-shared.c
@@ -178,6 +178,32 @@
 		goto fail;
 	regs->dx = val >> 32;
 
+	/*
+	 * This is a VC handler and the #VC is only raised when SEV-ES is
+	 * active, which means SEV must be active too. Do sanity checks on the
+	 * CPUID results to make sure the hypervisor does not trick the kernel
+	 * into the no-sev path. This could map sensitive data unencrypted and
+	 * make it accessible to the hypervisor.
+	 *
+	 * In particular, check for:
+	 *	- Hypervisor CPUID bit
+	 *	- Availability of CPUID leaf 0x8000001f
+	 *	- SEV CPUID bit.
+	 *
+	 * The hypervisor might still report the wrong C-bit position, but this
+	 * can't be checked here.
+	 */
+
+	if ((fn == 1 && !(regs->cx & BIT(31))))
+		/* Hypervisor bit */
+		goto fail;
+	else if (fn == 0x80000000 && (regs->ax < 0x8000001f))
+		/* SEV leaf check */
+		goto fail;
+	else if ((fn == 0x8000001f && !(regs->ax & BIT(1))))
+		/* SEV bit */
+		goto fail;
+
 	/* Skip over the CPUID two-byte opcode */
 	regs->ip += 2;
 
diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c
index 4a96726..0bd1a0f 100644
--- a/arch/x86/kernel/sev-es.c
+++ b/arch/x86/kernel/sev-es.c
@@ -374,8 +374,8 @@
 	return ES_EXCEPTION;
 }
 
-static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
-				 unsigned long vaddr, phys_addr_t *paddr)
+static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+					   unsigned long vaddr, phys_addr_t *paddr)
 {
 	unsigned long va = (unsigned long)vaddr;
 	unsigned int level;
@@ -394,15 +394,19 @@
 		if (user_mode(ctxt->regs))
 			ctxt->fi.error_code |= X86_PF_USER;
 
-		return false;
+		return ES_EXCEPTION;
 	}
 
+	if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
+		/* Emulated MMIO to/from encrypted memory not supported */
+		return ES_UNSUPPORTED;
+
 	pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
 	pa |= va & ~page_level_mask(level);
 
 	*paddr = pa;
 
-	return true;
+	return ES_OK;
 }
 
 /* Include code shared with pre-decompression boot stage */
@@ -731,6 +735,7 @@
 {
 	u64 exit_code, exit_info_1, exit_info_2;
 	unsigned long ghcb_pa = __pa(ghcb);
+	enum es_result res;
 	phys_addr_t paddr;
 	void __user *ref;
 
@@ -740,11 +745,12 @@
 
 	exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
 
-	if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) {
-		if (!read)
+	res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
+	if (res != ES_OK) {
+		if (res == ES_EXCEPTION && !read)
 			ctxt->fi.error_code |= X86_PF_WRITE;
 
-		return ES_EXCEPTION;
+		return res;
 	}
 
 	exit_info_1 = paddr;
diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S
new file mode 100644
index 0000000..ee04941
--- /dev/null
+++ b/arch/x86/kernel/sev_verify_cbit.S
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *	sev_verify_cbit.S - Code for verification of the C-bit position reported
+ *			    by the Hypervisor when running with SEV enabled.
+ *
+ *	Copyright (c) 2020  Joerg Roedel (jroedel@suse.de)
+ *
+ * sev_verify_cbit() is called before switching to a new long-mode page-table
+ * at boot.
+ *
+ * Verify that the C-bit position is correct by writing a random value to
+ * an encrypted memory location while on the current page-table. Then it
+ * switches to the new page-table to verify the memory content is still the
+ * same. After that it switches back to the current page-table and when the
+ * check succeeded it returns. If the check failed the code invalidates the
+ * stack pointer and goes into a hlt loop. The stack-pointer is invalidated to
+ * make sure no interrupt or exception can get the CPU out of the hlt loop.
+ *
+ * New page-table pointer is expected in %rdi (first parameter)
+ *
+ */
+SYM_FUNC_START(sev_verify_cbit)
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	/* First check if a C-bit was detected */
+	movq	sme_me_mask(%rip), %rsi
+	testq	%rsi, %rsi
+	jz	3f
+
+	/* sme_me_mask != 0 could mean SME or SEV - Check also for SEV */
+	movq	sev_status(%rip), %rsi
+	testq	%rsi, %rsi
+	jz	3f
+
+	/* Save CR4 in %rsi */
+	movq	%cr4, %rsi
+
+	/* Disable Global Pages */
+	movq	%rsi, %rdx
+	andq	$(~X86_CR4_PGE), %rdx
+	movq	%rdx, %cr4
+
+	/*
+	 * Verified that running under SEV - now get a random value using
+	 * RDRAND. This instruction is mandatory when running as an SEV guest.
+	 *
+	 * Don't bail out of the loop if RDRAND returns errors. It is better to
+	 * prevent forward progress than to work with a non-random value here.
+	 */
+1:	rdrand	%rdx
+	jnc	1b
+
+	/* Store value to memory and keep it in %rdx */
+	movq	%rdx, sev_check_data(%rip)
+
+	/* Backup current %cr3 value to restore it later */
+	movq	%cr3, %rcx
+
+	/* Switch to new %cr3 - This might unmap the stack */
+	movq	%rdi, %cr3
+
+	/*
+	 * Compare value in %rdx with memory location. If C-bit is incorrect
+	 * this would read the encrypted data and make the check fail.
+	 */
+	cmpq	%rdx, sev_check_data(%rip)
+
+	/* Restore old %cr3 */
+	movq	%rcx, %cr3
+
+	/* Restore previous CR4 */
+	movq	%rsi, %cr4
+
+	/* Check CMPQ result */
+	je	3f
+
+	/*
+	 * The check failed, prevent any forward progress to prevent ROP
+	 * attacks, invalidate the stack and go into a hlt loop.
+	 */
+	xorq	%rsp, %rsp
+	subq	$0x1000, %rsp
+2:	hlt
+	jmp 2b
+3:
+#endif
+	/* Return page-table pointer */
+	movq	%rdi, %rax
+	ret
+SYM_FUNC_END(sev_verify_cbit)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 06a278b..83637a2 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -90,6 +90,20 @@
 	return 0;
 }
 
+void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
+
+	/*
+	 * save the feature bitmap to avoid cpuid lookup for every PV
+	 * operation
+	 */
+	if (best)
+		vcpu->arch.pv_cpuid.features = best->eax;
+}
+
 void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
@@ -124,13 +138,6 @@
 		(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
 		best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
 
-	/*
-	 * save the feature bitmap to avoid cpuid lookup for every PV
-	 * operation
-	 */
-	if (best)
-		vcpu->arch.pv_cpuid.features = best->eax;
-
 	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
 		best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
 		if (best)
@@ -162,6 +169,8 @@
 		vcpu->arch.guest_supported_xcr0 =
 			(best->eax | ((u64)best->edx << 32)) & supported_xcr0;
 
+	kvm_update_pv_runtime(vcpu);
+
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
 	kvm_mmu_reset_context(vcpu);
 
@@ -169,6 +178,8 @@
 	vcpu->arch.cr4_guest_rsvd_bits =
 	    __cr4_reserved_bits(guest_cpuid_has, vcpu);
 
+	vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63);
+
 	/* Invoke the vendor callback only after the above state is updated. */
 	kvm_x86_ops.vcpu_after_set_cpuid(vcpu);
 }
@@ -672,7 +683,9 @@
 
 		edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS);
 		edx.split.bit_width_fixed = cap.bit_width_fixed;
-		edx.split.reserved = 0;
+		edx.split.anythread_deprecated = 1;
+		edx.split.reserved1 = 0;
+		edx.split.reserved2 = 0;
 
 		entry->eax = eax.full;
 		entry->ebx = cap.events_mask;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index bf85779..f7a6e8f 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -11,6 +11,7 @@
 void kvm_set_cpu_caps(void);
 
 void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu);
+void kvm_update_pv_runtime(struct kvm_vcpu *vcpu);
 struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 					      u32 function, u32 index);
 int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 0d917eb..56cae1f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4046,6 +4046,12 @@
 	return X86EMUL_CONTINUE;
 }
 
+static int em_clflushopt(struct x86_emulate_ctxt *ctxt)
+{
+	/* emulating clflushopt regardless of cpuid */
+	return X86EMUL_CONTINUE;
+}
+
 static int em_movsxd(struct x86_emulate_ctxt *ctxt)
 {
 	ctxt->dst.val = (s32) ctxt->src.val;
@@ -4585,7 +4591,7 @@
 };
 
 static const struct gprefix pfx_0f_ae_7 = {
-	I(SrcMem | ByteOp, em_clflush), N, N, N,
+	I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N,
 };
 
 static const struct group_dual group15 = { {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1f96adf..5bb1939 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -856,12 +856,14 @@
 	} else {
 		rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte);
 		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
-		while (desc->sptes[PTE_LIST_EXT-1] && desc->more) {
-			desc = desc->more;
+		while (desc->sptes[PTE_LIST_EXT-1]) {
 			count += PTE_LIST_EXT;
-		}
-		if (desc->sptes[PTE_LIST_EXT-1]) {
-			desc->more = mmu_alloc_pte_list_desc(vcpu);
+
+			if (!desc->more) {
+				desc->more = mmu_alloc_pte_list_desc(vcpu);
+				desc = desc->more;
+				break;
+			}
 			desc = desc->more;
 		}
 		for (i = 0; desc->sptes[i]; ++i)
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 27e381c..ff28a5c 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -49,7 +49,14 @@
 {
 	struct kvm_mmu_page *sp;
 
+	if (!kvm->arch.tdp_mmu_enabled)
+		return false;
+	if (WARN_ON(!VALID_PAGE(hpa)))
+		return false;
+
 	sp = to_shadow_page(hpa);
+	if (WARN_ON(!sp))
+		return false;
 
 	return sp->tdp_mmu_page && sp->root_count;
 }
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 2f32fd0..1e81cfe 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3741,6 +3741,7 @@
 static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_cpuid_entry2 *best;
 
 	vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
 				    boot_cpu_has(X86_FEATURE_XSAVE) &&
@@ -3753,6 +3754,13 @@
 	/* Check again if INVPCID interception if required */
 	svm_check_invpcid(svm);
 
+	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
+	if (sev_guest(vcpu->kvm)) {
+		best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0);
+		if (best)
+			vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f));
+	}
+
 	if (!kvm_vcpu_apicv_active(vcpu))
 		return;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f5ede41..078a39d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -255,11 +255,10 @@
 
 /*
  * When called, it means the previous get/set msr reached an invalid msr.
- * Return 0 if we want to ignore/silent this failed msr access, or 1 if we want
- * to fail the caller.
+ * Return true if we want to ignore/silent this failed msr access.
  */
-static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
-				 u64 data, bool write)
+static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
+				  u64 data, bool write)
 {
 	const char *op = write ? "wrmsr" : "rdmsr";
 
@@ -268,11 +267,11 @@
 			kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n",
 				      op, msr, data);
 		/* Mask the error */
-		return 0;
+		return true;
 	} else {
 		kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n",
 				      op, msr, data);
-		return -ENOENT;
+		return false;
 	}
 }
 
@@ -1042,7 +1041,7 @@
 	}
 
 	if (is_long_mode(vcpu) &&
-	    (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63)))
+	    (cr3 & vcpu->arch.cr3_lm_rsvd_bits))
 		return 1;
 	else if (is_pae_paging(vcpu) &&
 		 !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
@@ -1416,7 +1415,8 @@
 	if (r == KVM_MSR_RET_INVALID) {
 		/* Unconditionally clear the output for simplicity */
 		*data = 0;
-		r = kvm_msr_ignored_check(vcpu, index, 0, false);
+		if (kvm_msr_ignored_check(vcpu, index, 0, false))
+			r = 0;
 	}
 
 	if (r)
@@ -1540,7 +1540,7 @@
 	struct msr_data msr;
 
 	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
-		return -EPERM;
+		return KVM_MSR_RET_FILTERED;
 
 	switch (index) {
 	case MSR_FS_BASE:
@@ -1581,7 +1581,8 @@
 	int ret = __kvm_set_msr(vcpu, index, data, host_initiated);
 
 	if (ret == KVM_MSR_RET_INVALID)
-		ret = kvm_msr_ignored_check(vcpu, index, data, true);
+		if (kvm_msr_ignored_check(vcpu, index, data, true))
+			ret = 0;
 
 	return ret;
 }
@@ -1599,7 +1600,7 @@
 	int ret;
 
 	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
-		return -EPERM;
+		return KVM_MSR_RET_FILTERED;
 
 	msr.index = index;
 	msr.host_initiated = host_initiated;
@@ -1618,7 +1619,8 @@
 	if (ret == KVM_MSR_RET_INVALID) {
 		/* Unconditionally clear *data for simplicity */
 		*data = 0;
-		ret = kvm_msr_ignored_check(vcpu, index, 0, false);
+		if (kvm_msr_ignored_check(vcpu, index, 0, false))
+			ret = 0;
 	}
 
 	return ret;
@@ -1662,9 +1664,9 @@
 static u64 kvm_msr_reason(int r)
 {
 	switch (r) {
-	case -ENOENT:
+	case KVM_MSR_RET_INVALID:
 		return KVM_MSR_EXIT_REASON_UNKNOWN;
-	case -EPERM:
+	case KVM_MSR_RET_FILTERED:
 		return KVM_MSR_EXIT_REASON_FILTER;
 	default:
 		return KVM_MSR_EXIT_REASON_INVAL;
@@ -1965,7 +1967,7 @@
 	struct kvm_arch *ka = &vcpu->kvm->arch;
 
 	if (vcpu->vcpu_id == 0 && !host_initiated) {
-		if (ka->boot_vcpu_runs_old_kvmclock && old_msr)
+		if (ka->boot_vcpu_runs_old_kvmclock != old_msr)
 			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 
 		ka->boot_vcpu_runs_old_kvmclock = old_msr;
@@ -3063,9 +3065,9 @@
 			/* Values other than LBR and BTF are vendor-specific,
 			   thus reserved and should throw a #GP */
 			return 1;
-		}
-		vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
-			    __func__, data);
+		} else if (report_ignored_msrs)
+			vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
+				    __func__, data);
 		break;
 	case 0x200 ... 0x2ff:
 		return kvm_mtrr_set_msr(vcpu, msr, data);
@@ -3463,29 +3465,63 @@
 		msr_info->data = vcpu->arch.efer;
 		break;
 	case MSR_KVM_WALL_CLOCK:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+			return 1;
+
+		msr_info->data = vcpu->kvm->arch.wall_clock;
+		break;
 	case MSR_KVM_WALL_CLOCK_NEW:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+			return 1;
+
 		msr_info->data = vcpu->kvm->arch.wall_clock;
 		break;
 	case MSR_KVM_SYSTEM_TIME:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+			return 1;
+
+		msr_info->data = vcpu->arch.time;
+		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+			return 1;
+
 		msr_info->data = vcpu->arch.time;
 		break;
 	case MSR_KVM_ASYNC_PF_EN:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+			return 1;
+
 		msr_info->data = vcpu->arch.apf.msr_en_val;
 		break;
 	case MSR_KVM_ASYNC_PF_INT:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
+			return 1;
+
 		msr_info->data = vcpu->arch.apf.msr_int_val;
 		break;
 	case MSR_KVM_ASYNC_PF_ACK:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+			return 1;
+
 		msr_info->data = 0;
 		break;
 	case MSR_KVM_STEAL_TIME:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME))
+			return 1;
+
 		msr_info->data = vcpu->arch.st.msr_val;
 		break;
 	case MSR_KVM_PV_EOI_EN:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI))
+			return 1;
+
 		msr_info->data = vcpu->arch.pv_eoi.msr_val;
 		break;
 	case MSR_KVM_POLL_CONTROL:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL))
+			return 1;
+
 		msr_info->data = vcpu->arch.msr_kvm_poll_control;
 		break;
 	case MSR_IA32_P5_MC_ADDR:
@@ -4575,6 +4611,8 @@
 
 	case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
 		vcpu->arch.pv_cpuid.enforce = cap->args[0];
+		if (vcpu->arch.pv_cpuid.enforce)
+			kvm_update_pv_runtime(vcpu);
 
 		return 0;
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 3900ab0..e7ca622 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -376,7 +376,13 @@
 int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva);
 bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type);
 
-#define  KVM_MSR_RET_INVALID  2
+/*
+ * Internal error codes that are used to indicate that MSR emulation encountered
+ * an error that should result in #GP in the guest, unless userspace
+ * handles it.
+ */
+#define  KVM_MSR_RET_INVALID	2	/* in-kernel MSR emulation #GP condition */
+#define  KVM_MSR_RET_FILTERED	3	/* #GP due to userspace MSR filter */
 
 #define __cr4_reserved_bits(__cpu_has, __c)             \
 ({                                                      \
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 037faac..1e299ac 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -16,8 +16,6 @@
  * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
  */
 
-.weak memcpy
-
 /*
  * memcpy - Copy a memory block.
  *
@@ -30,7 +28,7 @@
  * rax original destination
  */
 SYM_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_LOCAL(memcpy)
+SYM_FUNC_START_WEAK(memcpy)
 	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memcpy_erms", X86_FEATURE_ERMS
 
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 7ff00ea..41902fe 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -24,9 +24,7 @@
  * Output:
  * rax: dest
  */
-.weak memmove
-
-SYM_FUNC_START_ALIAS(memmove)
+SYM_FUNC_START_WEAK(memmove)
 SYM_FUNC_START(__memmove)
 
 	mov %rdi, %rax
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 9ff15ee..0bfd26e 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -6,8 +6,6 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
-.weak memset
-
 /*
  * ISO C memset - set a memory block to a byte value. This function uses fast
  * string to get better performance than the original function. The code is
@@ -19,7 +17,7 @@
  *
  * rax   original destination
  */
-SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START_WEAK(memset)
 SYM_FUNC_START(__memset)
 	/*
 	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index efbb3de..bc08337 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -39,6 +39,7 @@
  */
 u64 sme_me_mask __section(".data") = 0;
 u64 sev_status __section(".data") = 0;
+u64 sev_check_data __section(".data") = 0;
 EXPORT_SYMBOL(sme_me_mask);
 DEFINE_STATIC_KEY_FALSE(sev_enable_key);
 EXPORT_SYMBOL_GPL(sev_enable_key);
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index fa054a1..4dc04e6 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -69,7 +69,7 @@
  */
 #define VMALLOC_START		(XCHAL_KSEG_CACHED_VADDR - 0x10000000)
 #define VMALLOC_END		(VMALLOC_START + 0x07FEFFFF)
-#define TLBTEMP_BASE_1		(VMALLOC_END + 1)
+#define TLBTEMP_BASE_1		(VMALLOC_START + 0x08000000)
 #define TLBTEMP_BASE_2		(TLBTEMP_BASE_1 + DCACHE_WAY_SIZE)
 #if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE
 #define TLBTEMP_SIZE		(2 * DCACHE_WAY_SIZE)
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index b975811..5c9fb80 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -302,7 +302,7 @@
 	return -EFAULT;
 }
 #else
-long strncpy_from_user(char *dst, const char *src, long count);
+long strncpy_from_user(char *dst, const char __user *src, long count);
 #endif
 
 /*
diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c
index 5835406..085b8c7 100644
--- a/arch/xtensa/mm/cache.c
+++ b/arch/xtensa/mm/cache.c
@@ -70,8 +70,10 @@
 			kvaddr = TLBTEMP_BASE_1 +
 				(page_to_phys(page) & DCACHE_ALIAS_MASK);
 
+			preempt_disable();
 			__invalidate_dcache_page_alias(kvaddr,
 						       page_to_phys(page));
+			preempt_enable();
 		}
 	}
 }
@@ -156,6 +158,7 @@
 		if (!alias && !mapping)
 			return;
 
+		preempt_disable();
 		virt = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK);
 		__flush_invalidate_dcache_page_alias(virt, phys);
 
@@ -166,6 +169,7 @@
 
 		if (mapping)
 			__invalidate_icache_page_alias(virt, phys);
+		preempt_enable();
 	}
 
 	/* There shouldn't be an entry in the cache for this page anymore. */
@@ -199,8 +203,10 @@
 	unsigned long phys = page_to_phys(pfn_to_page(pfn));
 	unsigned long virt = TLBTEMP_BASE_1 + (address & DCACHE_ALIAS_MASK);
 
+	preempt_disable();
 	__flush_invalidate_dcache_page_alias(virt, phys);
 	__invalidate_icache_page_alias(virt, phys);
+	preempt_enable();
 }
 EXPORT_SYMBOL(local_flush_cache_page);
 
@@ -227,11 +233,13 @@
 		unsigned long phys = page_to_phys(page);
 		unsigned long tmp;
 
+		preempt_disable();
 		tmp = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK);
 		__flush_invalidate_dcache_page_alias(tmp, phys);
 		tmp = TLBTEMP_BASE_1 + (addr & DCACHE_ALIAS_MASK);
 		__flush_invalidate_dcache_page_alias(tmp, phys);
 		__invalidate_icache_page_alias(tmp, phys);
+		preempt_enable();
 
 		clear_bit(PG_arch_1, &page->flags);
 	}
@@ -265,7 +273,9 @@
 
 	if (alias) {
 		unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK);
+		preempt_disable();
 		__flush_invalidate_dcache_page_alias(t, phys);
+		preempt_enable();
 	}
 
 	/* Copy data */
@@ -280,9 +290,11 @@
 	if (alias) {
 		unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK);
 
+		preempt_disable();
 		__flush_invalidate_dcache_range((unsigned long) dst, len);
 		if ((vma->vm_flags & VM_EXEC) != 0)
 			__invalidate_icache_page_alias(t, phys);
+		preempt_enable();
 
 	} else if ((vma->vm_flags & VM_EXEC) != 0) {
 		__flush_dcache_range((unsigned long)dst,len);
@@ -304,7 +316,9 @@
 
 	if (alias) {
 		unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK);
+		preempt_disable();
 		__flush_invalidate_dcache_page_alias(t, phys);
+		preempt_enable();
 	}
 
 	memcpy(dst, src, len);
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index c6fc83e..8731b7a 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -89,8 +89,8 @@
 	/* set highmem page free */
 	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
 				&range_start, &range_end, NULL) {
-		unsigned long start = PHYS_PFN(range_start);
-		unsigned long end = PHYS_PFN(range_end);
+		unsigned long start = PFN_UP(range_start);
+		unsigned long end = PFN_DOWN(range_end);
 
 		/* Ignore complete lowmem entries */
 		if (end <= max_low)
diff --git a/block/genhd.c b/block/genhd.c
index 0a27321..9387f05 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -49,7 +49,7 @@
  * Set disk capacity and notify if the size is not currently
  * zero and will not be set to zero
  */
-void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
 					bool update_bdev)
 {
 	sector_t capacity = get_capacity(disk);
@@ -62,7 +62,10 @@
 		char *envp[] = { "RESIZE=1", NULL };
 
 		kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
+		return true;
 	}
+
+	return false;
 }
 
 EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify);
diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c
index be79b21..4801966 100644
--- a/drivers/accessibility/speakup/main.c
+++ b/drivers/accessibility/speakup/main.c
@@ -357,7 +357,6 @@
 	mark_cut_flag = 0;
 	synth_printf("%s\n", spk_msg_get(MSG_CUT));
 
-	speakup_clear_selection();
 	ret = speakup_set_selection(tty);
 
 	switch (ret) {
diff --git a/drivers/accessibility/speakup/selection.c b/drivers/accessibility/speakup/selection.c
index 032f326..7df7afa 100644
--- a/drivers/accessibility/speakup/selection.c
+++ b/drivers/accessibility/speakup/selection.c
@@ -22,13 +22,6 @@
 	struct tty_struct *tty;
 };
 
-void speakup_clear_selection(void)
-{
-	console_lock();
-	clear_selection();
-	console_unlock();
-}
-
 static void __speakup_set_selection(struct work_struct *work)
 {
 	struct speakup_selection_work *ssw =
@@ -51,6 +44,10 @@
 		goto unref;
 	}
 
+	console_lock();
+	clear_selection();
+	console_unlock();
+
 	set_selection_kernel(&sel, tty);
 
 unref:
diff --git a/drivers/accessibility/speakup/speakup.h b/drivers/accessibility/speakup/speakup.h
index 74fe49c..33594f5 100644
--- a/drivers/accessibility/speakup/speakup.h
+++ b/drivers/accessibility/speakup/speakup.h
@@ -70,7 +70,6 @@
 void speakup_start_ttys(void);
 void synth_buffer_add(u16 ch);
 void synth_buffer_clear(void);
-void speakup_clear_selection(void);
 int speakup_set_selection(struct tty_struct *tty);
 void speakup_cancel_selection(void);
 int speakup_paste_selection(struct tty_struct *tty);
diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c
index a831ff6..ecc3998 100644
--- a/drivers/accessibility/speakup/spk_ttyio.c
+++ b/drivers/accessibility/speakup/spk_ttyio.c
@@ -298,11 +298,13 @@
 	struct spk_ldisc_data *ldisc_data = speakup_tty->disc_data;
 	char rv;
 
-	if (wait_for_completion_timeout(&ldisc_data->completion,
+	if (!timeout) {
+		if (!try_wait_for_completion(&ldisc_data->completion))
+			return 0xff;
+	} else if (wait_for_completion_timeout(&ldisc_data->completion,
 					usecs_to_jiffies(timeout)) == 0) {
-		if (timeout)
-			pr_warn("spk_ttyio: timeout (%d)  while waiting for input\n",
-				timeout);
+		pr_warn("spk_ttyio: timeout (%d)  while waiting for input\n",
+			timeout);
 		return 0xff;
 	}
 
diff --git a/drivers/accessibility/speakup/spk_types.h b/drivers/accessibility/speakup/spk_types.h
index 7398f11..91fca303 100644
--- a/drivers/accessibility/speakup/spk_types.h
+++ b/drivers/accessibility/speakup/spk_types.h
@@ -32,6 +32,10 @@
 	E_NEW_DEFAULT,
 };
 
+/*
+ * Note: add new members at the end, speakupmap.h depends on the values of the
+ * enum starting from SPELL_DELAY (see inc_dec_var)
+ */
 enum var_id_t {
 	VERSION = 0, SYNTH, SILENT, SYNTH_DIRECT,
 	KEYMAP, CHARS,
@@ -42,9 +46,9 @@
 	SAY_CONTROL, SAY_WORD_CTL, NO_INTERRUPT, KEY_ECHO,
 	SPELL_DELAY, PUNC_LEVEL, READING_PUNC,
 	ATTRIB_BLEEP, BLEEPS,
-	RATE, PITCH, INFLECTION, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG,
+	RATE, PITCH, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG,
 	DIRECT, PAUSE,
-	CAPS_START, CAPS_STOP, CHARTAB,
+	CAPS_START, CAPS_STOP, CHARTAB, INFLECTION,
 	MAXVARS
 };
 
diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c
index bc96457..a322a7b 100644
--- a/drivers/acpi/acpi_video.c
+++ b/drivers/acpi/acpi_video.c
@@ -578,7 +578,7 @@
 				ACPI_VIDEO_FIRST_LEVEL - 1 - bqc_value;
 
 		level = device->brightness->levels[bqc_value +
-		                                   ACPI_VIDEO_FIRST_LEVEL];
+						   ACPI_VIDEO_FIRST_LEVEL];
 	} else {
 		level = bqc_value;
 	}
@@ -990,8 +990,8 @@
 		goto out_free_levels;
 
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-	                  "found %d brightness levels\n",
-	                  br->count - ACPI_VIDEO_FIRST_LEVEL));
+			  "found %d brightness levels\n",
+			  br->count - ACPI_VIDEO_FIRST_LEVEL));
 	return 0;
 
 out_free_levels:
diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 552fd9f..3294cc8 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -633,6 +633,10 @@
 	if (rc)
 		return rc;
 
+	/* IO space doesn't need mapping */
+	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO)
+		return 0;
+
 	if (!acpi_os_map_generic_address(reg))
 		return -ENXIO;
 
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index cab4af5..08ee1c7 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -987,7 +987,7 @@
 	 */
 	if ((battery->state & ACPI_BATTERY_STATE_CRITICAL) ||
 	    (test_bit(ACPI_BATTERY_ALARM_PRESENT, &battery->flags) &&
-            (battery->capacity_now <= battery->alarm)))
+	     (battery->capacity_now <= battery->alarm)))
 		acpi_pm_wakeup_event(&battery->device->dev);
 
 	return result;
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 0761529..0d93a5e 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -89,7 +89,18 @@
 		 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "MEDION"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "E2215T MD60198"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "E2215T"),
+		},
+		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
+	},
+	{
+		/*
+		 * Medion Akoya E2228T, notification of the LID device only
+		 * happens on close, not on open and _LID always returns closed.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "MEDION"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "E2228T"),
 		},
 		.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
 	},
diff --git a/drivers/acpi/dptf/dptf_pch_fivr.c b/drivers/acpi/dptf/dptf_pch_fivr.c
index 4c1992f..5fca182 100644
--- a/drivers/acpi/dptf/dptf_pch_fivr.c
+++ b/drivers/acpi/dptf/dptf_pch_fivr.c
@@ -106,6 +106,7 @@
 
 static const struct acpi_device_id pch_fivr_device_ids[] = {
 	{"INTC1045", 0},
+	{"INTC1049", 0},
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, pch_fivr_device_ids);
diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c
index 0674130..a24d5d7 100644
--- a/drivers/acpi/dptf/dptf_power.c
+++ b/drivers/acpi/dptf/dptf_power.c
@@ -229,6 +229,8 @@
 	{"INT3532", 0},
 	{"INTC1047", 0},
 	{"INTC1050", 0},
+	{"INTC1060", 0},
+	{"INTC1061", 0},
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, int3407_device_ids);
diff --git a/drivers/acpi/dptf/int340x_thermal.c b/drivers/acpi/dptf/int340x_thermal.c
index 8d420c7..d14025a 100644
--- a/drivers/acpi/dptf/int340x_thermal.c
+++ b/drivers/acpi/dptf/int340x_thermal.c
@@ -25,10 +25,16 @@
 	{"INT340A"},
 	{"INT340B"},
 	{"INTC1040"},
+	{"INTC1041"},
 	{"INTC1043"},
 	{"INTC1044"},
 	{"INTC1045"},
+	{"INTC1046"},
 	{"INTC1047"},
+	{"INTC1048"},
+	{"INTC1049"},
+	{"INTC1060"},
+	{"INTC1061"},
 	{""},
 };
 
diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c
index 1706439..92e59f4 100644
--- a/drivers/acpi/event.c
+++ b/drivers/acpi/event.c
@@ -31,7 +31,7 @@
 	event.type = type;
 	event.data = data;
 	return (blocking_notifier_call_chain(&acpi_chain_head, 0, (void *)&event)
-                        == NOTIFY_BAD) ? -EINVAL : 0;
+			== NOTIFY_BAD) ? -EINVAL : 0;
 }
 EXPORT_SYMBOL(acpi_notifier_call_chain);
 
diff --git a/drivers/acpi/evged.c b/drivers/acpi/evged.c
index b1a7f8d..fe6b679 100644
--- a/drivers/acpi/evged.c
+++ b/drivers/acpi/evged.c
@@ -101,7 +101,7 @@
 
 	switch (gsi) {
 	case 0 ... 255:
-		sprintf(ev_name, "_%c%02hhX",
+		sprintf(ev_name, "_%c%02X",
 			trigger == ACPI_EDGE_SENSITIVE ? 'E' : 'L', gsi);
 
 		if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle)))
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 6287338..66c3983 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -27,6 +27,7 @@
 	{"PNP0C0B", 0},
 	{"INT3404", 0},
 	{"INTC1044", 0},
+	{"INTC1048", 0},
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, fan_device_ids);
@@ -351,6 +352,7 @@
 		struct acpi_fan_fps *fps = &fan->fps[i];
 
 		snprintf(fps->name, ACPI_FPS_NAME_LEN, "state%d", i);
+		sysfs_attr_init(&fps->dev_attr.attr);
 		fps->dev_attr.show = show_state;
 		fps->dev_attr.store = NULL;
 		fps->dev_attr.attr.name = fps->name;
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 43411a74..e3638ba 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -134,7 +134,7 @@
 void acpi_power_add_remove_device(struct acpi_device *adev, bool add);
 int acpi_power_wakeup_list_init(struct list_head *list, int *system_level);
 int acpi_device_sleep_wake(struct acpi_device *dev,
-                           int enable, int sleep_state, int dev_state);
+			   int enable, int sleep_state, int dev_state);
 int acpi_power_get_inferred_state(struct acpi_device *device, int *state);
 int acpi_power_on_resources(struct acpi_device *device, int state);
 int acpi_power_transition(struct acpi_device *device, int state);
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 3a3c209..4426082 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -2175,10 +2175,10 @@
  * these commands.
  */
 enum nfit_aux_cmds {
-        NFIT_CMD_TRANSLATE_SPA = 5,
-        NFIT_CMD_ARS_INJECT_SET = 7,
-        NFIT_CMD_ARS_INJECT_CLEAR = 8,
-        NFIT_CMD_ARS_INJECT_GET = 9,
+	NFIT_CMD_TRANSLATE_SPA = 5,
+	NFIT_CMD_ARS_INJECT_SET = 7,
+	NFIT_CMD_ARS_INJECT_CLEAR = 8,
+	NFIT_CMD_ARS_INJECT_GET = 9,
 };
 
 static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
@@ -2632,7 +2632,7 @@
 	nfit_blk->bdw_offset = nfit_mem->bdw->offset;
 	mmio = &nfit_blk->mmio[BDW];
 	mmio->addr.base = devm_nvdimm_memremap(dev, nfit_mem->spa_bdw->address,
-                        nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr));
+			nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr));
 	if (!mmio->addr.base) {
 		dev_dbg(dev, "%s failed to map bdw\n",
 				nvdimm_name(nvdimm));
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index dea8a60..14ee631 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -175,7 +175,7 @@
 	 * configure the IRQ assigned to this slot|dev|pin.  The 'source_index'
 	 * indicates which resource descriptor in the resource template (of
 	 * the link device) this interrupt is allocated from.
-	 * 
+	 *
 	 * NOTE: Don't query the Link Device for IRQ information at this time
 	 *       because Link Device enumeration may not have occurred yet
 	 *       (e.g. exists somewhere 'below' this _PRT entry in the ACPI
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index 606da5d..fb4c563 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -6,8 +6,8 @@
  *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
  *  Copyright (C) 2002       Dominik Brodowski <devel@brodo.de>
  *
- * TBD: 
- *      1. Support more than one IRQ resource entry per link device (index).
+ * TBD:
+ *	1. Support more than one IRQ resource entry per link device (index).
  *	2. Implement start/stop mechanism and use ACPI Bus Driver facilities
  *	   for IRQ management (e.g. start()->_SRS).
  */
@@ -249,8 +249,8 @@
 		}
 	}
 
-	/* 
-	 * Query and parse _CRS to get the current IRQ assignment. 
+	/*
+	 * Query and parse _CRS to get the current IRQ assignment.
 	 */
 
 	status = acpi_walk_resources(link->device->handle, METHOD_NAME__CRS,
@@ -396,7 +396,7 @@
 /*
  * "acpi_irq_balance" (default in APIC mode) enables ACPI to use PIC Interrupt
  * Link Devices to move the PIRQs around to minimize sharing.
- * 
+ *
  * "acpi_irq_nobalance" (default in PIC mode) tells ACPI not to move any PIC IRQs
  * that the BIOS has already set to active.  This is necessary because
  * ACPI has no automatic means of knowing what ISA IRQs are used.  Note that
@@ -414,7 +414,7 @@
  *
  * Note that PCI IRQ routers have a list of possible IRQs,
  * which may not include the IRQs this table says are available.
- * 
+ *
  * Since this heuristic can't tell the difference between a link
  * that no device will attach to, vs. a link which may be shared
  * by multiple active devices -- it is not optimal.
diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c
index 7ddd57a..95f23ac 100644
--- a/drivers/acpi/pci_mcfg.c
+++ b/drivers/acpi/pci_mcfg.c
@@ -173,7 +173,7 @@
 {
 	if (!memcmp(f->oem_id, mcfg_oem_id, ACPI_OEM_ID_SIZE) &&
 	    !memcmp(f->oem_table_id, mcfg_oem_table_id,
-	            ACPI_OEM_TABLE_ID_SIZE) &&
+		    ACPI_OEM_TABLE_ID_SIZE) &&
 	    f->oem_revision == mcfg_oem_revision &&
 	    f->segment == segment &&
 	    resource_contains(&f->bus_range, bus_range))
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 837b875..8048da8 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -13,7 +13,7 @@
  * 1. via "Device Specific (D-State) Control"
  * 2. via "Power Resource Control".
  * The code below deals with ACPI Power Resources control.
- * 
+ *
  * An ACPI "power resource object" represents a software controllable power
  * plane, clock plane, or other resource depended on by a device.
  *
@@ -645,7 +645,7 @@
  * -ENODEV if the execution of either _DSW or _PSW has failed
  */
 int acpi_device_sleep_wake(struct acpi_device *dev,
-                           int enable, int sleep_state, int dev_state)
+			   int enable, int sleep_state, int dev_state)
 {
 	union acpi_object in_arg[3];
 	struct acpi_object_list arg_list = { 3, in_arg };
@@ -690,7 +690,7 @@
 
 /*
  * Prepare a wakeup device, two steps (Ref ACPI 2.0:P229):
- * 1. Power on the power resources required for the wakeup device 
+ * 1. Power on the power resources required for the wakeup device
  * 2. Execute _DSW (Device Sleep Wake) or (deprecated in ACPI 3.0) _PSW (Power
  *    State Wake) for the device, if present
  */
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 5909e8f..b04a689 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -354,7 +354,7 @@
 				  (u32) px->control, (u32) px->status));
 
 		/*
- 		 * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq
+		 * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq
 		 */
 		if (!px->core_frequency ||
 		    ((u32)(px->core_frequency * 1000) !=
@@ -627,7 +627,7 @@
 		goto err_ret;
 
 	/*
-	 * Now that we have _PSD data from all CPUs, lets setup P-state 
+	 * Now that we have _PSD data from all CPUs, lets setup P-state
 	 * domain info.
 	 */
 	for_each_possible_cpu(i) {
@@ -693,7 +693,7 @@
 			if (match_pdomain->domain != pdomain->domain)
 				continue;
 
-			match_pr->performance->shared_type = 
+			match_pr->performance->shared_type =
 					pr->performance->shared_type;
 			cpumask_copy(match_pr->performance->shared_cpu_map,
 				     pr->performance->shared_cpu_map);
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index f158b8c..e6d9f4d 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -366,7 +366,7 @@
 					 state_readers[i].mode,
 					 ACPI_SBS_BATTERY,
 					 state_readers[i].command,
-				         (u8 *)battery +
+					 (u8 *)battery +
 						state_readers[i].offset);
 		if (result)
 			goto end;
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index 87b74e9..53c2862 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -176,7 +176,7 @@
 EXPORT_SYMBOL_GPL(acpi_smbus_write);
 
 int acpi_smbus_register_callback(struct acpi_smb_hc *hc,
-			         smbus_alarm_callback callback, void *context)
+				 smbus_alarm_callback callback, void *context)
 {
 	mutex_lock(&hc->lock);
 	hc->callback = callback;
diff --git a/drivers/acpi/sbshc.h b/drivers/acpi/sbshc.h
index c3522bb..695c390 100644
--- a/drivers/acpi/sbshc.h
+++ b/drivers/acpi/sbshc.h
@@ -24,9 +24,9 @@
 typedef void (*smbus_alarm_callback)(void *context);
 
 extern int acpi_smbus_read(struct acpi_smb_hc *hc, u8 protocol, u8 address,
-	       u8 command, u8 * data);
+		u8 command, u8 *data);
 extern int acpi_smbus_write(struct acpi_smb_hc *hc, u8 protocol, u8 slave_address,
-		u8 command, u8 * data, u8 length);
+		u8 command, u8 *data, u8 length);
 extern int acpi_smbus_register_callback(struct acpi_smb_hc *hc,
-			         smbus_alarm_callback callback, void *context);
+		smbus_alarm_callback callback, void *context);
 extern int acpi_smbus_unregister_callback(struct acpi_smb_hc *hc);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index a896e5e..bc6a79e 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1453,7 +1453,7 @@
 }
 
 /**
- * acpi_dma_configure - Set-up DMA configuration for the device.
+ * acpi_dma_configure_id - Set-up DMA configuration for the device.
  * @dev: The pointer to the device
  * @attr: device dma attributes
  * @input_id: input device id const value pointer
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 3a032af..4f5463b 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -178,14 +178,14 @@
 		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201s"),
 		},
 	},
-        {
-         .callback = video_detect_force_video,
-         .ident = "ThinkPad X201T",
-         .matches = {
-                DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-                DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"),
-                },
-        },
+	{
+	 .callback = video_detect_force_video,
+	 .ident = "ThinkPad X201T",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"),
+		},
+	},
 
 	/* The native backlight controls do not work on some older machines */
 	{
diff --git a/drivers/acpi/wakeup.c b/drivers/acpi/wakeup.c
index f89dd9a..b02bf77 100644
--- a/drivers/acpi/wakeup.c
+++ b/drivers/acpi/wakeup.c
@@ -44,7 +44,7 @@
 		if (!dev->wakeup.flags.valid
 		    || sleep_state > (u32) dev->wakeup.sleep_state
 		    || !(device_may_wakeup(&dev->dev)
-		        || dev->wakeup.prepare_count))
+			 || dev->wakeup.prepare_count))
 			continue;
 
 		if (device_may_wakeup(&dev->dev))
@@ -69,7 +69,7 @@
 		if (!dev->wakeup.flags.valid
 		    || sleep_state > (u32) dev->wakeup.sleep_state
 		    || !(device_may_wakeup(&dev->dev)
-		        || dev->wakeup.prepare_count))
+			 || dev->wakeup.prepare_count))
 			continue;
 
 		acpi_set_gpe_wake_mask(dev->wakeup.gpe_device, dev->wakeup.gpe_number,
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 78114dd..d661ada 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -773,8 +773,7 @@
 	dev_dbg(link->consumer, "Dropping the link to %s\n",
 		dev_name(link->supplier));
 
-	if (link->flags & DL_FLAG_PM_RUNTIME)
-		pm_runtime_drop_link(link->consumer);
+	pm_runtime_drop_link(link);
 
 	list_del_rcu(&link->s_node);
 	list_del_rcu(&link->c_node);
@@ -788,8 +787,7 @@
 	dev_info(link->consumer, "Dropping the link to %s\n",
 		 dev_name(link->supplier));
 
-	if (link->flags & DL_FLAG_PM_RUNTIME)
-		pm_runtime_drop_link(link->consumer);
+	pm_runtime_drop_link(link);
 
 	list_del(&link->s_node);
 	list_del(&link->c_node);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index b42229b..148e819 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -1117,6 +1117,8 @@
 
 	drv = dev->driver;
 	if (drv) {
+		pm_runtime_get_sync(dev);
+
 		while (device_links_busy(dev)) {
 			__device_driver_unlock(dev, parent);
 
@@ -1128,13 +1130,12 @@
 			 * have released the driver successfully while this one
 			 * was waiting, so check for that.
 			 */
-			if (dev->driver != drv)
+			if (dev->driver != drv) {
+				pm_runtime_put(dev);
 				return;
+			}
 		}
 
-		pm_runtime_get_sync(dev);
-		pm_runtime_clean_up_links(dev);
-
 		driver_sysfs_remove(dev);
 
 		if (dev->bus)
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 6f605f7..bfda153 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1643,42 +1643,6 @@
 }
 
 /**
- * pm_runtime_clean_up_links - Prepare links to consumers for driver removal.
- * @dev: Device whose driver is going to be removed.
- *
- * Check links from this device to any consumers and if any of them have active
- * runtime PM references to the device, drop the usage counter of the device
- * (as many times as needed).
- *
- * Links with the DL_FLAG_MANAGED flag unset are ignored.
- *
- * Since the device is guaranteed to be runtime-active at the point this is
- * called, nothing else needs to be done here.
- *
- * Moreover, this is called after device_links_busy() has returned 'false', so
- * the status of each link is guaranteed to be DL_STATE_SUPPLIER_UNBIND and
- * therefore rpm_active can't be manipulated concurrently.
- */
-void pm_runtime_clean_up_links(struct device *dev)
-{
-	struct device_link *link;
-	int idx;
-
-	idx = device_links_read_lock();
-
-	list_for_each_entry_rcu(link, &dev->links.consumers, s_node,
-				device_links_read_lock_held()) {
-		if (!(link->flags & DL_FLAG_MANAGED))
-			continue;
-
-		while (refcount_dec_not_one(&link->rpm_active))
-			pm_runtime_put_noidle(dev);
-	}
-
-	device_links_read_unlock(idx);
-}
-
-/**
  * pm_runtime_get_suppliers - Resume and reference-count supplier devices.
  * @dev: Consumer device.
  */
@@ -1729,7 +1693,7 @@
 	spin_unlock_irq(&dev->power.lock);
 }
 
-void pm_runtime_drop_link(struct device *dev)
+static void pm_runtime_drop_link_count(struct device *dev)
 {
 	spin_lock_irq(&dev->power.lock);
 	WARN_ON(dev->power.links_count == 0);
@@ -1737,6 +1701,25 @@
 	spin_unlock_irq(&dev->power.lock);
 }
 
+/**
+ * pm_runtime_drop_link - Prepare for device link removal.
+ * @link: Device link going away.
+ *
+ * Drop the link count of the consumer end of @link and decrement the supplier
+ * device's runtime PM usage counter as many times as needed to drop all of the
+ * PM runtime reference to it from the consumer.
+ */
+void pm_runtime_drop_link(struct device_link *link)
+{
+	if (!(link->flags & DL_FLAG_PM_RUNTIME))
+		return;
+
+	pm_runtime_drop_link_count(link->consumer);
+
+	while (refcount_dec_not_one(&link->rpm_active))
+		pm_runtime_put(link->supplier);
+}
+
 static bool pm_runtime_need_not_resume(struct device *dev)
 {
 	return atomic_read(&dev->power.usage_count) <= 1 &&
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index cb1191d..a58084c 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -255,7 +255,8 @@
 
 	bd_set_nr_sectors(bdev, size);
 
-	set_capacity_revalidate_and_notify(lo->lo_disk, size, false);
+	if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, false))
+		kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
 }
 
 static inline int
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index c4f9ccf..aaae922 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1518,6 +1518,7 @@
 	if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) &&
 			bdev->bd_openers == 0)
 		nbd_disconnect_and_put(nbd);
+	bdput(bdev);
 
 	nbd_config_put(nbd);
 	nbd_put(nbd);
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
index cfd00ad..c24d9b5 100644
--- a/drivers/block/null_blk.h
+++ b/drivers/block/null_blk.h
@@ -47,7 +47,7 @@
 	unsigned int nr_zones_closed;
 	struct blk_zone *zones;
 	sector_t zone_size_sects;
-	spinlock_t zone_dev_lock;
+	spinlock_t zone_lock;
 	unsigned long *zone_locks;
 
 	unsigned long size; /* device size in MB */
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index 8775acb..beb34b4 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -46,11 +46,20 @@
 	if (!dev->zones)
 		return -ENOMEM;
 
-	spin_lock_init(&dev->zone_dev_lock);
-	dev->zone_locks = bitmap_zalloc(dev->nr_zones, GFP_KERNEL);
-	if (!dev->zone_locks) {
-		kvfree(dev->zones);
-		return -ENOMEM;
+	/*
+	 * With memory backing, the zone_lock spinlock needs to be temporarily
+	 * released to avoid scheduling in atomic context. To guarantee zone
+	 * information protection, use a bitmap to lock zones with
+	 * wait_on_bit_lock_io(). Sleeping on the lock is OK as memory backing
+	 * implies that the queue is marked with BLK_MQ_F_BLOCKING.
+	 */
+	spin_lock_init(&dev->zone_lock);
+	if (dev->memory_backed) {
+		dev->zone_locks = bitmap_zalloc(dev->nr_zones, GFP_KERNEL);
+		if (!dev->zone_locks) {
+			kvfree(dev->zones);
+			return -ENOMEM;
+		}
 	}
 
 	if (dev->zone_nr_conv >= dev->nr_zones) {
@@ -137,12 +146,17 @@
 
 static inline void null_lock_zone(struct nullb_device *dev, unsigned int zno)
 {
-	wait_on_bit_lock_io(dev->zone_locks, zno, TASK_UNINTERRUPTIBLE);
+	if (dev->memory_backed)
+		wait_on_bit_lock_io(dev->zone_locks, zno, TASK_UNINTERRUPTIBLE);
+	spin_lock_irq(&dev->zone_lock);
 }
 
 static inline void null_unlock_zone(struct nullb_device *dev, unsigned int zno)
 {
-	clear_and_wake_up_bit(zno, dev->zone_locks);
+	spin_unlock_irq(&dev->zone_lock);
+
+	if (dev->memory_backed)
+		clear_and_wake_up_bit(zno, dev->zone_locks);
 }
 
 int null_report_zones(struct gendisk *disk, sector_t sector,
@@ -322,7 +336,6 @@
 		return null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
 
 	null_lock_zone(dev, zno);
-	spin_lock(&dev->zone_dev_lock);
 
 	switch (zone->cond) {
 	case BLK_ZONE_COND_FULL:
@@ -375,9 +388,17 @@
 	if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
 		zone->cond = BLK_ZONE_COND_IMP_OPEN;
 
-	spin_unlock(&dev->zone_dev_lock);
+	/*
+	 * Memory backing allocation may sleep: release the zone_lock spinlock
+	 * to avoid scheduling in atomic context. Zone operation atomicity is
+	 * still guaranteed through the zone_locks bitmap.
+	 */
+	if (dev->memory_backed)
+		spin_unlock_irq(&dev->zone_lock);
 	ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
-	spin_lock(&dev->zone_dev_lock);
+	if (dev->memory_backed)
+		spin_lock_irq(&dev->zone_lock);
+
 	if (ret != BLK_STS_OK)
 		goto unlock;
 
@@ -392,7 +413,6 @@
 	ret = BLK_STS_OK;
 
 unlock:
-	spin_unlock(&dev->zone_dev_lock);
 	null_unlock_zone(dev, zno);
 
 	return ret;
@@ -516,9 +536,7 @@
 			null_lock_zone(dev, i);
 			zone = &dev->zones[i];
 			if (zone->cond != BLK_ZONE_COND_EMPTY) {
-				spin_lock(&dev->zone_dev_lock);
 				null_reset_zone(dev, zone);
-				spin_unlock(&dev->zone_dev_lock);
 				trace_nullb_zone_op(cmd, i, zone->cond);
 			}
 			null_unlock_zone(dev, i);
@@ -530,7 +548,6 @@
 	zone = &dev->zones[zone_no];
 
 	null_lock_zone(dev, zone_no);
-	spin_lock(&dev->zone_dev_lock);
 
 	switch (op) {
 	case REQ_OP_ZONE_RESET:
@@ -550,8 +567,6 @@
 		break;
 	}
 
-	spin_unlock(&dev->zone_dev_lock);
-
 	if (ret == BLK_STS_OK)
 		trace_nullb_zone_op(cmd, zone_no, zone->cond);
 
diff --git a/drivers/char/tpm/eventlog/efi.c b/drivers/char/tpm/eventlog/efi.c
index 6bb023d..35229e5 100644
--- a/drivers/char/tpm/eventlog/efi.c
+++ b/drivers/char/tpm/eventlog/efi.c
@@ -41,6 +41,11 @@
 	log_size = log_tbl->size;
 	memunmap(log_tbl);
 
+	if (!log_size) {
+		pr_warn("UEFI TPM log area empty\n");
+		return -EIO;
+	}
+
 	log_tbl = memremap(efi.tpm_log, sizeof(*log_tbl) + log_size,
 			   MEMREMAP_WB);
 	if (!log_tbl) {
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 0b21496..4ed6e66 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -27,6 +27,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/kernel.h>
+#include <linux/dmi.h>
 #include "tpm.h"
 #include "tpm_tis_core.h"
 
@@ -49,8 +50,8 @@
 	return container_of(data, struct tpm_tis_tcg_phy, priv);
 }
 
-static bool interrupts = true;
-module_param(interrupts, bool, 0444);
+static int interrupts = -1;
+module_param(interrupts, int, 0444);
 MODULE_PARM_DESC(interrupts, "Enable interrupts");
 
 static bool itpm;
@@ -63,6 +64,28 @@
 MODULE_PARM_DESC(force, "Force device probe rather than using ACPI entry");
 #endif
 
+static int tpm_tis_disable_irq(const struct dmi_system_id *d)
+{
+	if (interrupts == -1) {
+		pr_notice("tpm_tis: %s detected: disabling interrupts.\n", d->ident);
+		interrupts = 0;
+	}
+
+	return 0;
+}
+
+static const struct dmi_system_id tpm_tis_dmi_table[] = {
+	{
+		.callback = tpm_tis_disable_irq,
+		.ident = "ThinkPad T490s",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T490s"),
+		},
+	},
+	{}
+};
+
 #if defined(CONFIG_PNP) && defined(CONFIG_ACPI)
 static int has_hid(struct acpi_device *dev, const char *hid)
 {
@@ -192,6 +215,8 @@
 	int irq = -1;
 	int rc;
 
+	dmi_check_system(tpm_tis_dmi_table);
+
 	rc = check_acpi_tpm2(dev);
 	if (rc)
 		return rc;
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index a2da8f7..1836cc5 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -435,12 +435,12 @@
 		/*
 		 * Allocate DMA memory from ancestor. When a virtio
 		 * device is created by remoteproc, the DMA memory is
-		 * associated with the grandparent device:
-		 * vdev => rproc => platform-dev.
+		 * associated with the parent device:
+		 * virtioY => remoteprocX#vdevYbuffer.
 		 */
-		if (!vdev->dev.parent || !vdev->dev.parent->parent)
+		buf->dev = vdev->dev.parent;
+		if (!buf->dev)
 			goto free_buf;
-		buf->dev = vdev->dev.parent->parent;
 
 		/* Increase device refcnt to avoid freeing it */
 		get_device(buf->dev);
diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c
index 0de0be0..f358ad9 100644
--- a/drivers/clk/imx/clk-imx8mm.c
+++ b/drivers/clk/imx/clk-imx8mm.c
@@ -443,9 +443,9 @@
 	hws[IMX8MM_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mm_a53_core_sels, ARRAY_SIZE(imx8mm_a53_core_sels));
 
 	/* BUS */
-	hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi",  imx8mm_main_axi_sels, base + 0x8800);
+	hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi",  imx8mm_main_axi_sels, base + 0x8800);
 	hws[IMX8MM_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mm_enet_axi_sels, base + 0x8880);
-	hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900);
+	hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900);
 	hws[IMX8MM_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mm_vpu_bus_sels, base + 0x8980);
 	hws[IMX8MM_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mm_disp_axi_sels, base + 0x8a00);
 	hws[IMX8MM_CLK_DISP_APB] = imx8m_clk_hw_composite_bus("disp_apb", imx8mm_disp_apb_sels, base + 0x8a80);
@@ -453,11 +453,11 @@
 	hws[IMX8MM_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mm_usb_bus_sels, base + 0x8b80);
 	hws[IMX8MM_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mm_gpu_axi_sels, base + 0x8c00);
 	hws[IMX8MM_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mm_gpu_ahb_sels, base + 0x8c80);
-	hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mm_noc_sels, base + 0x8d00);
-	hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80);
+	hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mm_noc_sels, base + 0x8d00);
+	hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80);
 
 	/* AHB */
-	hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mm_ahb_sels, base + 0x9000);
+	hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mm_ahb_sels, base + 0x9000);
 	hws[IMX8MM_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mm_audio_ahb_sels, base + 0x9100);
 
 	/* IPG */
diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c
index e984de5..f3c5e6c 100644
--- a/drivers/clk/imx/clk-imx8mn.c
+++ b/drivers/clk/imx/clk-imx8mn.c
@@ -431,7 +431,7 @@
 	hws[IMX8MN_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mn_a53_core_sels, ARRAY_SIZE(imx8mn_a53_core_sels));
 
 	/* BUS */
-	hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800);
+	hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800);
 	hws[IMX8MN_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mn_enet_axi_sels, base + 0x8880);
 	hws[IMX8MN_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mn_nand_usdhc_sels, base + 0x8900);
 	hws[IMX8MN_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mn_disp_axi_sels, base + 0x8a00);
@@ -439,9 +439,9 @@
 	hws[IMX8MN_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mn_usb_bus_sels, base + 0x8b80);
 	hws[IMX8MN_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mn_gpu_axi_sels, base + 0x8c00);
 	hws[IMX8MN_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mn_gpu_ahb_sels, base + 0x8c80);
-	hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mn_noc_sels, base + 0x8d00);
+	hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mn_noc_sels, base + 0x8d00);
 
-	hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mn_ahb_sels, base + 0x9000);
+	hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mn_ahb_sels, base + 0x9000);
 	hws[IMX8MN_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mn_audio_ahb_sels, base + 0x9100);
 	hws[IMX8MN_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb", base + 0x9080, 0, 1);
 	hws[IMX8MN_CLK_IPG_AUDIO_ROOT] = imx_clk_hw_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1);
diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c
index 12ce477..48e2124 100644
--- a/drivers/clk/imx/clk-imx8mp.c
+++ b/drivers/clk/imx/clk-imx8mp.c
@@ -557,9 +557,9 @@
 	/* CORE SEL */
 	hws[IMX8MP_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", ccm_base + 0x9880, 24, 1, imx8mp_a53_core_sels, ARRAY_SIZE(imx8mp_a53_core_sels));
 
-	hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800);
+	hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800);
 	hws[IMX8MP_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mp_enet_axi_sels, ccm_base + 0x8880);
-	hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900);
+	hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900);
 	hws[IMX8MP_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mp_vpu_bus_sels, ccm_base + 0x8980);
 	hws[IMX8MP_CLK_MEDIA_AXI] = imx8m_clk_hw_composite_bus("media_axi", imx8mp_media_axi_sels, ccm_base + 0x8a00);
 	hws[IMX8MP_CLK_MEDIA_APB] = imx8m_clk_hw_composite_bus("media_apb", imx8mp_media_apb_sels, ccm_base + 0x8a80);
@@ -567,12 +567,12 @@
 	hws[IMX8MP_CLK_HDMI_AXI] = imx8m_clk_hw_composite_bus("hdmi_axi", imx8mp_media_axi_sels, ccm_base + 0x8b80);
 	hws[IMX8MP_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mp_gpu_axi_sels, ccm_base + 0x8c00);
 	hws[IMX8MP_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mp_gpu_ahb_sels, ccm_base + 0x8c80);
-	hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00);
-	hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80);
+	hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00);
+	hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_bus_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80);
 	hws[IMX8MP_CLK_ML_AXI] = imx8m_clk_hw_composite_bus("ml_axi", imx8mp_ml_axi_sels, ccm_base + 0x8e00);
 	hws[IMX8MP_CLK_ML_AHB] = imx8m_clk_hw_composite_bus("ml_ahb", imx8mp_ml_ahb_sels, ccm_base + 0x8e80);
 
-	hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000);
+	hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000);
 	hws[IMX8MP_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mp_audio_ahb_sels, ccm_base + 0x9100);
 	hws[IMX8MP_CLK_MIPI_DSI_ESC_RX] = imx8m_clk_hw_composite_bus("mipi_dsi_esc_rx", imx8mp_mipi_dsi_esc_rx_sels, ccm_base + 0x9200);
 
diff --git a/drivers/clk/imx/clk-imx8mq.c b/drivers/clk/imx/clk-imx8mq.c
index 8265d1d..06292d4 100644
--- a/drivers/clk/imx/clk-imx8mq.c
+++ b/drivers/clk/imx/clk-imx8mq.c
@@ -431,7 +431,7 @@
 	hws[IMX8MQ_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mq_a53_core_sels, ARRAY_SIZE(imx8mq_a53_core_sels));
 
 	/* BUS */
-	hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800);
+	hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800);
 	hws[IMX8MQ_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mq_enet_axi_sels, base + 0x8880);
 	hws[IMX8MQ_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mq_nand_usdhc_sels, base + 0x8900);
 	hws[IMX8MQ_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mq_vpu_bus_sels, base + 0x8980);
@@ -441,12 +441,12 @@
 	hws[IMX8MQ_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mq_usb_bus_sels, base + 0x8b80);
 	hws[IMX8MQ_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mq_gpu_axi_sels, base + 0x8c00);
 	hws[IMX8MQ_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mq_gpu_ahb_sels, base + 0x8c80);
-	hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mq_noc_sels, base + 0x8d00);
-	hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80);
+	hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mq_noc_sels, base + 0x8d00);
+	hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80);
 
 	/* AHB */
 	/* AHB clock is used by the AHB bus therefore marked as critical */
-	hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mq_ahb_sels, base + 0x9000);
+	hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mq_ahb_sels, base + 0x9000);
 	hws[IMX8MQ_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mq_audio_ahb_sels, base + 0x9100);
 
 	/* IPG */
diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h
index 3b796b3..1d7be0c 100644
--- a/drivers/clk/imx/clk.h
+++ b/drivers/clk/imx/clk.h
@@ -549,6 +549,11 @@
 			IMX_COMPOSITE_BUS, \
 			CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE)
 
+#define imx8m_clk_hw_composite_bus_critical(name, parent_names, reg)	\
+	imx8m_clk_hw_composite_flags(name, parent_names, ARRAY_SIZE(parent_names), reg, \
+			IMX_COMPOSITE_BUS, \
+			CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE | CLK_IS_CRITICAL)
+
 #define imx8m_clk_hw_composite_core(name, parent_names, reg)	\
 	imx8m_clk_hw_composite_flags(name, parent_names, \
 			ARRAY_SIZE(parent_names), reg, \
diff --git a/drivers/clk/meson/clk-regmap.h b/drivers/clk/meson/clk-regmap.h
index c4a3960..e365312 100644
--- a/drivers/clk/meson/clk-regmap.h
+++ b/drivers/clk/meson/clk-regmap.h
@@ -26,7 +26,10 @@
 	void		*data;
 };
 
-#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw)
+static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw)
+{
+	return container_of(hw, struct clk_regmap, hw);
+}
 
 /**
  * struct clk_regmap_gate_data - regmap backed gate specific data
diff --git a/drivers/clk/qcom/clk-regmap.h b/drivers/clk/qcom/clk-regmap.h
index 6cfc1bc..14ec659 100644
--- a/drivers/clk/qcom/clk-regmap.h
+++ b/drivers/clk/qcom/clk-regmap.h
@@ -24,7 +24,11 @@
 	unsigned int enable_mask;
 	bool enable_is_inverted;
 };
-#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw)
+
+static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw)
+{
+	return container_of(hw, struct clk_regmap, hw);
+}
 
 int clk_is_enabled_regmap(struct clk_hw *hw);
 int clk_enable_regmap(struct clk_hw *hw);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 336b5e94..1e7e3f2 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2254,7 +2254,7 @@
 		return -EINVAL;
 
 	/* Platform doesn't want dynamic frequency switching ? */
-	if (policy->governor->dynamic_switching &&
+	if (policy->governor->flags & CPUFREQ_GOV_DYNAMIC_SWITCHING &&
 	    cpufreq_driver->flags & CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING) {
 		struct cpufreq_governor *gov = cpufreq_fallback_governor();
 
@@ -2280,6 +2280,8 @@
 		}
 	}
 
+	policy->strict_target = !!(policy->governor->flags & CPUFREQ_GOV_STRICT_TARGET);
+
 	return 0;
 }
 
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index c56773c..bab8e61 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -156,7 +156,7 @@
 #define CPUFREQ_DBS_GOVERNOR_INITIALIZER(_name_)			\
 	{								\
 		.name = _name_,						\
-		.dynamic_switching = true,				\
+		.flags = CPUFREQ_GOV_DYNAMIC_SWITCHING,			\
 		.owner = THIS_MODULE,					\
 		.init = cpufreq_dbs_governor_init,			\
 		.exit = cpufreq_dbs_governor_exit,			\
diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index 71c1d9a..addd93f 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -20,6 +20,7 @@
 static struct cpufreq_governor cpufreq_gov_performance = {
 	.name		= "performance",
 	.owner		= THIS_MODULE,
+	.flags		= CPUFREQ_GOV_STRICT_TARGET,
 	.limits		= cpufreq_gov_performance_limits,
 };
 
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index 7749522..8d830d8 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -21,6 +21,7 @@
 	.name		= "powersave",
 	.limits		= cpufreq_gov_powersave_limits,
 	.owner		= THIS_MODULE,
+	.flags		= CPUFREQ_GOV_STRICT_TARGET,
 };
 
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index b7a9779..36a3ccf 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2527,7 +2527,7 @@
 }
 
 static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate,
-				     bool fast_switch)
+				     bool strict, bool fast_switch)
 {
 	u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev;
 
@@ -2539,7 +2539,7 @@
 	 * field in it, so opportunistically update the max too if needed.
 	 */
 	value &= ~HWP_MAX_PERF(~0L);
-	value |= HWP_MAX_PERF(cpu->max_perf_ratio);
+	value |= HWP_MAX_PERF(strict ? target_pstate : cpu->max_perf_ratio);
 
 	if (value == prev)
 		return;
@@ -2562,14 +2562,16 @@
 			      pstate_funcs.get_val(cpu, target_pstate));
 }
 
-static int intel_cpufreq_update_pstate(struct cpudata *cpu, int target_pstate,
-				       bool fast_switch)
+static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy,
+				       int target_pstate, bool fast_switch)
 {
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
 	int old_pstate = cpu->pstate.current_pstate;
 
 	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
 	if (hwp_active) {
-		intel_cpufreq_adjust_hwp(cpu, target_pstate, fast_switch);
+		intel_cpufreq_adjust_hwp(cpu, target_pstate,
+					 policy->strict_target, fast_switch);
 		cpu->pstate.current_pstate = target_pstate;
 	} else if (target_pstate != old_pstate) {
 		intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch);
@@ -2609,7 +2611,7 @@
 		break;
 	}
 
-	target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, false);
+	target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false);
 
 	freqs.new = target_pstate * cpu->pstate.scaling;
 
@@ -2628,7 +2630,7 @@
 
 	target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
 
-	target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, true);
+	target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true);
 
 	return target_pstate * cpu->pstate.scaling;
 }
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index e855e86..7831850 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -8,6 +8,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/clk-provider.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
@@ -228,12 +229,17 @@
 static int scmi_cpufreq_probe(struct scmi_device *sdev)
 {
 	int ret;
+	struct device *dev = &sdev->dev;
 
 	handle = sdev->handle;
 
 	if (!handle || !handle->perf_ops)
 		return -ENODEV;
 
+	/* dummy clock provider as needed by OPP if clocks property is used */
+	if (of_find_property(dev->of_node, "#clock-cells", NULL))
+		devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL);
+
 	ret = cpufreq_register_driver(&scmi_cpufreq_driver);
 	if (ret) {
 		dev_err(&sdev->dev, "%s: registering cpufreq failed, err: %d\n",
diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c
index 4b4079f..7eb2c56 100644
--- a/drivers/cpufreq/tegra186-cpufreq.c
+++ b/drivers/cpufreq/tegra186-cpufreq.c
@@ -42,6 +42,8 @@
 struct tegra186_cpufreq_cluster {
 	const struct tegra186_cpufreq_cluster_info *info;
 	struct cpufreq_frequency_table *table;
+	u32 ref_clk_khz;
+	u32 div;
 };
 
 struct tegra186_cpufreq_data {
@@ -94,7 +96,7 @@
 
 static unsigned int tegra186_cpufreq_get(unsigned int cpu)
 {
-	struct cpufreq_frequency_table *tbl;
+	struct tegra186_cpufreq_data *data = cpufreq_get_driver_data();
 	struct cpufreq_policy *policy;
 	void __iomem *edvd_reg;
 	unsigned int i, freq = 0;
@@ -104,17 +106,23 @@
 	if (!policy)
 		return 0;
 
-	tbl = policy->freq_table;
 	edvd_reg = policy->driver_data;
 	ndiv = readl(edvd_reg) & EDVD_CORE_VOLT_FREQ_F_MASK;
 
-	for (i = 0; tbl[i].frequency != CPUFREQ_TABLE_END; i++) {
-		if ((tbl[i].driver_data & EDVD_CORE_VOLT_FREQ_F_MASK) == ndiv) {
-			freq = tbl[i].frequency;
-			break;
+	for (i = 0; i < data->num_clusters; i++) {
+		struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
+		int core;
+
+		for (core = 0; core < ARRAY_SIZE(cluster->info->cpus); core++) {
+			if (cluster->info->cpus[core] != policy->cpu)
+				continue;
+
+			freq = (cluster->ref_clk_khz * ndiv) / cluster->div;
+			goto out;
 		}
 	}
 
+out:
 	cpufreq_cpu_put(policy);
 
 	return freq;
@@ -133,7 +141,7 @@
 
 static struct cpufreq_frequency_table *init_vhint_table(
 	struct platform_device *pdev, struct tegra_bpmp *bpmp,
-	unsigned int cluster_id)
+	struct tegra186_cpufreq_cluster *cluster)
 {
 	struct cpufreq_frequency_table *table;
 	struct mrq_cpu_vhint_request req;
@@ -152,7 +160,7 @@
 
 	memset(&req, 0, sizeof(req));
 	req.addr = phys;
-	req.cluster_id = cluster_id;
+	req.cluster_id = cluster->info->bpmp_cluster_id;
 
 	memset(&msg, 0, sizeof(msg));
 	msg.mrq = MRQ_CPU_VHINT;
@@ -185,6 +193,9 @@
 		goto free;
 	}
 
+	cluster->ref_clk_khz = data->ref_clk_hz / 1000;
+	cluster->div = data->pdiv * data->mdiv;
+
 	for (i = data->vfloor, j = 0; i <= data->vceil; i++) {
 		struct cpufreq_frequency_table *point;
 		u16 ndiv = data->ndiv[i];
@@ -202,8 +213,7 @@
 
 		point = &table[j++];
 		point->driver_data = edvd_val;
-		point->frequency = data->ref_clk_hz * ndiv / data->pdiv /
-			data->mdiv / 1000;
+		point->frequency = (cluster->ref_clk_khz * ndiv) / cluster->div;
 	}
 
 	table[j].frequency = CPUFREQ_TABLE_END;
@@ -245,8 +255,7 @@
 		struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
 
 		cluster->info = &tegra186_clusters[i];
-		cluster->table = init_vhint_table(
-			pdev, bpmp, cluster->info->bpmp_cluster_id);
+		cluster->table = init_vhint_table(pdev, bpmp, cluster);
 		if (IS_ERR(cluster->table)) {
 			err = PTR_ERR(cluster->table);
 			goto put_bpmp;
diff --git a/drivers/cpuidle/cpuidle-tegra.c b/drivers/cpuidle/cpuidle-tegra.c
index e895670..191966d 100644
--- a/drivers/cpuidle/cpuidle-tegra.c
+++ b/drivers/cpuidle/cpuidle-tegra.c
@@ -189,7 +189,7 @@
 	}
 
 	local_fiq_disable();
-	tegra_pm_set_cpu_in_lp2();
+	RCU_NONIDLE(tegra_pm_set_cpu_in_lp2());
 	cpu_pm_enter();
 
 	switch (index) {
@@ -207,7 +207,7 @@
 	}
 
 	cpu_pm_exit();
-	tegra_pm_clear_cpu_in_lp2();
+	RCU_NONIDLE(tegra_pm_clear_cpu_in_lp2());
 	local_fiq_enable();
 
 	return err ?: index;
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
index fa2f1b4..a94bf28 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c
@@ -7,7 +7,7 @@
  *
  * This file add support for MD5 and SHA1/SHA224/SHA256/SHA384/SHA512.
  *
- * You could find the datasheet in Documentation/arm/sunxi/README
+ * You could find the datasheet in Documentation/arm/sunxi.rst
  */
 #include <linux/dma-mapping.h>
 #include <linux/pm_runtime.h>
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c
index 78503006..cfde9ee 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c
@@ -7,7 +7,7 @@
  *
  * This file handle the PRNG
  *
- * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ * You could find a link for the datasheet in Documentation/arm/sunxi.rst
  */
 #include "sun8i-ce.h"
 #include <linux/dma-mapping.h>
diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c
index 6543281..5b7af44 100644
--- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c
+++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c
@@ -7,7 +7,7 @@
  *
  * This file handle the TRNG
  *
- * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ * You could find a link for the datasheet in Documentation/arm/sunxi.rst
  */
 #include "sun8i-ce.h"
 #include <linux/dma-mapping.h>
diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 8d1ff24..efb8a66 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -147,6 +147,9 @@
 		return 0;
 
 	/* Return value if feature is already checked */
+	if (api_id > ARRAY_SIZE(zynqmp_pm_features))
+		return PM_FEATURE_INVALID;
+
 	if (zynqmp_pm_features[api_id] != PM_FEATURE_UNCHECKED)
 		return zynqmp_pm_features[api_id];
 
diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index e44d5de..b966f5e 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -1114,6 +1114,7 @@
 
 static const struct aspeed_bank_props ast2600_bank_props[] = {
 	/*     input	  output   */
+	{4, 0xffffffff,  0x00ffffff}, /* Q/R/S/T */
 	{5, 0xffffffff,  0xffffff00}, /* U/V/W/X */
 	{6, 0x0000ffff,  0x0000ffff}, /* Y/Z */
 	{ },
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index a5b3267..2a9046c 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -343,8 +343,8 @@
 #ifdef CONFIG_PM_SLEEP
 static int dwapb_irq_set_wake(struct irq_data *d, unsigned int enable)
 {
-	struct irq_chip_generic *igc = irq_data_get_irq_chip_data(d);
-	struct dwapb_gpio *gpio = igc->private;
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct dwapb_gpio *gpio = to_dwapb_gpio(gc);
 	struct dwapb_context *ctx = gpio->ports[0].ctx;
 	irq_hw_number_t bit = irqd_to_hwirq(d);
 
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 6d59e3a..f7ceb2b 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -1114,13 +1114,23 @@
 {
 	struct device *dev = bank->chip.parent;
 	void __iomem *base = bank->base;
-	u32 nowake;
+	u32 mask, nowake;
 
 	bank->saved_datain = readl_relaxed(base + bank->regs->datain);
 
 	if (!bank->enabled_non_wakeup_gpios)
 		goto update_gpio_context_count;
 
+	/* Check for pending EDGE_FALLING, ignore EDGE_BOTH */
+	mask = bank->enabled_non_wakeup_gpios & bank->context.fallingdetect;
+	mask &= ~bank->context.risingdetect;
+	bank->saved_datain |= mask;
+
+	/* Check for pending EDGE_RISING, ignore EDGE_BOTH */
+	mask = bank->enabled_non_wakeup_gpios & bank->context.risingdetect;
+	mask &= ~bank->context.fallingdetect;
+	bank->saved_datain &= ~mask;
+
 	if (!may_lose_context)
 		goto update_gpio_context_count;
 
diff --git a/drivers/gpio/gpio-pcie-idio-24.c b/drivers/gpio/gpio-pcie-idio-24.c
index a68941d..2a07fd9 100644
--- a/drivers/gpio/gpio-pcie-idio-24.c
+++ b/drivers/gpio/gpio-pcie-idio-24.c
@@ -28,6 +28,47 @@
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
+/*
+ * PLX PEX8311 PCI LCS_INTCSR Interrupt Control/Status
+ *
+ * Bit: Description
+ *   0: Enable Interrupt Sources (Bit 0)
+ *   1: Enable Interrupt Sources (Bit 1)
+ *   2: Generate Internal PCI Bus Internal SERR# Interrupt
+ *   3: Mailbox Interrupt Enable
+ *   4: Power Management Interrupt Enable
+ *   5: Power Management Interrupt
+ *   6: Slave Read Local Data Parity Check Error Enable
+ *   7: Slave Read Local Data Parity Check Error Status
+ *   8: Internal PCI Wire Interrupt Enable
+ *   9: PCI Express Doorbell Interrupt Enable
+ *  10: PCI Abort Interrupt Enable
+ *  11: Local Interrupt Input Enable
+ *  12: Retry Abort Enable
+ *  13: PCI Express Doorbell Interrupt Active
+ *  14: PCI Abort Interrupt Active
+ *  15: Local Interrupt Input Active
+ *  16: Local Interrupt Output Enable
+ *  17: Local Doorbell Interrupt Enable
+ *  18: DMA Channel 0 Interrupt Enable
+ *  19: DMA Channel 1 Interrupt Enable
+ *  20: Local Doorbell Interrupt Active
+ *  21: DMA Channel 0 Interrupt Active
+ *  22: DMA Channel 1 Interrupt Active
+ *  23: Built-In Self-Test (BIST) Interrupt Active
+ *  24: Direct Master was the Bus Master during a Master or Target Abort
+ *  25: DMA Channel 0 was the Bus Master during a Master or Target Abort
+ *  26: DMA Channel 1 was the Bus Master during a Master or Target Abort
+ *  27: Target Abort after internal 256 consecutive Master Retrys
+ *  28: PCI Bus wrote data to LCS_MBOX0
+ *  29: PCI Bus wrote data to LCS_MBOX1
+ *  30: PCI Bus wrote data to LCS_MBOX2
+ *  31: PCI Bus wrote data to LCS_MBOX3
+ */
+#define PLX_PEX8311_PCI_LCS_INTCSR  0x68
+#define INTCSR_INTERNAL_PCI_WIRE    BIT(8)
+#define INTCSR_LOCAL_INPUT          BIT(11)
+
 /**
  * struct idio_24_gpio_reg - GPIO device registers structure
  * @out0_7:	Read: FET Outputs 0-7
@@ -92,6 +133,7 @@
 struct idio_24_gpio {
 	struct gpio_chip chip;
 	raw_spinlock_t lock;
+	__u8 __iomem *plx;
 	struct idio_24_gpio_reg __iomem *reg;
 	unsigned long irq_mask;
 };
@@ -334,13 +376,13 @@
 	unsigned long flags;
 	const unsigned long bit_offset = irqd_to_hwirq(data) - 24;
 	unsigned char new_irq_mask;
-	const unsigned long bank_offset = bit_offset/8 * 8;
+	const unsigned long bank_offset = bit_offset / 8;
 	unsigned char cos_enable_state;
 
 	raw_spin_lock_irqsave(&idio24gpio->lock, flags);
 
-	idio24gpio->irq_mask &= BIT(bit_offset);
-	new_irq_mask = idio24gpio->irq_mask >> bank_offset;
+	idio24gpio->irq_mask &= ~BIT(bit_offset);
+	new_irq_mask = idio24gpio->irq_mask >> bank_offset * 8;
 
 	if (!new_irq_mask) {
 		cos_enable_state = ioread8(&idio24gpio->reg->cos_enable);
@@ -363,12 +405,12 @@
 	unsigned long flags;
 	unsigned char prev_irq_mask;
 	const unsigned long bit_offset = irqd_to_hwirq(data) - 24;
-	const unsigned long bank_offset = bit_offset/8 * 8;
+	const unsigned long bank_offset = bit_offset / 8;
 	unsigned char cos_enable_state;
 
 	raw_spin_lock_irqsave(&idio24gpio->lock, flags);
 
-	prev_irq_mask = idio24gpio->irq_mask >> bank_offset;
+	prev_irq_mask = idio24gpio->irq_mask >> bank_offset * 8;
 	idio24gpio->irq_mask |= BIT(bit_offset);
 
 	if (!prev_irq_mask) {
@@ -455,6 +497,7 @@
 	struct device *const dev = &pdev->dev;
 	struct idio_24_gpio *idio24gpio;
 	int err;
+	const size_t pci_plx_bar_index = 1;
 	const size_t pci_bar_index = 2;
 	const char *const name = pci_name(pdev);
 	struct gpio_irq_chip *girq;
@@ -469,12 +512,13 @@
 		return err;
 	}
 
-	err = pcim_iomap_regions(pdev, BIT(pci_bar_index), name);
+	err = pcim_iomap_regions(pdev, BIT(pci_plx_bar_index) | BIT(pci_bar_index), name);
 	if (err) {
 		dev_err(dev, "Unable to map PCI I/O addresses (%d)\n", err);
 		return err;
 	}
 
+	idio24gpio->plx = pcim_iomap_table(pdev)[pci_plx_bar_index];
 	idio24gpio->reg = pcim_iomap_table(pdev)[pci_bar_index];
 
 	idio24gpio->chip.label = name;
@@ -504,6 +548,12 @@
 
 	/* Software board reset */
 	iowrite8(0, &idio24gpio->reg->soft_reset);
+	/*
+	 * enable PLX PEX8311 internal PCI wire interrupt and local interrupt
+	 * input
+	 */
+	iowrite8((INTCSR_INTERNAL_PCI_WIRE | INTCSR_LOCAL_INPUT) >> 8,
+		 idio24gpio->plx + PLX_PEX8311_PCI_LCS_INTCSR + 1);
 
 	err = devm_gpiochip_add_data(dev, &idio24gpio->chip, idio24gpio);
 	if (err) {
diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c
index c54dd08..d5eb9ca 100644
--- a/drivers/gpio/gpio-sifive.c
+++ b/drivers/gpio/gpio-sifive.c
@@ -183,7 +183,7 @@
 		return PTR_ERR(chip->regs);
 
 	ngpio = of_irq_count(node);
-	if (ngpio >= SIFIVE_GPIO_MAX) {
+	if (ngpio > SIFIVE_GPIO_MAX) {
 		dev_err(dev, "Too many GPIO interrupts (max=%d)\n",
 			SIFIVE_GPIO_MAX);
 		return -ENXIO;
diff --git a/drivers/gpio/gpiolib-cdev.h b/drivers/gpio/gpiolib-cdev.h
index cb41dd7..b42644c 100644
--- a/drivers/gpio/gpiolib-cdev.h
+++ b/drivers/gpio/gpiolib-cdev.h
@@ -7,22 +7,7 @@
 
 struct gpio_device;
 
-#ifdef CONFIG_GPIO_CDEV
-
 int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt);
 void gpiolib_cdev_unregister(struct gpio_device *gdev);
 
-#else
-
-static inline int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt)
-{
-	return 0;
-}
-
-static inline void gpiolib_cdev_unregister(struct gpio_device *gdev)
-{
-}
-
-#endif /* CONFIG_GPIO_CDEV */
-
 #endif /* GPIOLIB_CDEV_H */
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 3cdf9ef..089ddca 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -480,11 +480,23 @@
 	kfree(gdev);
 }
 
+#ifdef CONFIG_GPIO_CDEV
+#define gcdev_register(gdev, devt)	gpiolib_cdev_register((gdev), (devt))
+#define gcdev_unregister(gdev)		gpiolib_cdev_unregister((gdev))
+#else
+/*
+ * gpiolib_cdev_register() indirectly calls device_add(), which is still
+ * required even when cdev is not selected.
+ */
+#define gcdev_register(gdev, devt)	device_add(&(gdev)->dev)
+#define gcdev_unregister(gdev)		device_del(&(gdev)->dev)
+#endif
+
 static int gpiochip_setup_dev(struct gpio_device *gdev)
 {
 	int ret;
 
-	ret = gpiolib_cdev_register(gdev, gpio_devt);
+	ret = gcdev_register(gdev, gpio_devt);
 	if (ret)
 		return ret;
 
@@ -500,7 +512,7 @@
 	return 0;
 
 err_remove_device:
-	gpiolib_cdev_unregister(gdev);
+	gcdev_unregister(gdev);
 	return ret;
 }
 
@@ -825,7 +837,7 @@
 	 * be removed, else it will be dangling until the last user is
 	 * gone.
 	 */
-	gpiolib_cdev_unregister(gdev);
+	gcdev_unregister(gdev);
 	put_device(&gdev->dev);
 }
 EXPORT_SYMBOL_GPL(gpiochip_remove);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 37da353..e3783f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -80,6 +80,7 @@
 MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_gpu_info.bin");
 
 #define AMDGPU_RESUME_MS		2000
 
@@ -239,9 +240,11 @@
 	return amdgpu_asic_supports_baco(adev);
 }
 
+/*
+ * VRAM access helper functions
+ */
+
 /**
- * VRAM access helper functions.
- *
  * amdgpu_device_vram_access - read/write a buffer in vram
  *
  * @adev: amdgpu_device pointer
@@ -705,7 +708,7 @@
 /**
  * amdgpu_invalid_rreg - dummy reg read function
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  * @reg: offset of register
  *
  * Dummy register read function.  Used for register blocks
@@ -722,7 +725,7 @@
 /**
  * amdgpu_invalid_wreg - dummy reg write function
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  * @reg: offset of register
  * @v: value to write to the register
  *
@@ -739,7 +742,7 @@
 /**
  * amdgpu_invalid_rreg64 - dummy 64 bit reg read function
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  * @reg: offset of register
  *
  * Dummy register read function.  Used for register blocks
@@ -756,7 +759,7 @@
 /**
  * amdgpu_invalid_wreg64 - dummy reg write function
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  * @reg: offset of register
  * @v: value to write to the register
  *
@@ -773,7 +776,7 @@
 /**
  * amdgpu_block_invalid_rreg - dummy reg read function
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  * @block: offset of instance
  * @reg: offset of register
  *
@@ -793,7 +796,7 @@
 /**
  * amdgpu_block_invalid_wreg - dummy reg write function
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  * @block: offset of instance
  * @reg: offset of register
  * @v: value to write to the register
@@ -813,7 +816,7 @@
 /**
  * amdgpu_device_asic_init - Wrapper for atom asic_init
  *
- * @dev: drm_device pointer
+ * @adev: amdgpu_device pointer
  *
  * Does any asic specific work and then calls atom asic init.
  */
@@ -827,7 +830,7 @@
 /**
  * amdgpu_device_vram_scratch_init - allocate the VRAM scratch page
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  *
  * Allocates a scratch page of VRAM for use by various things in the
  * driver.
@@ -844,7 +847,7 @@
 /**
  * amdgpu_device_vram_scratch_fini - Free the VRAM scratch page
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  *
  * Frees the VRAM scratch page.
  */
@@ -1803,7 +1806,10 @@
 		chip_name = "arcturus";
 		break;
 	case CHIP_RENOIR:
-		chip_name = "renoir";
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
+			chip_name = "renoir";
+		else
+			chip_name = "green_sardine";
 		break;
 	case CHIP_NAVI10:
 		chip_name = "navi10";
@@ -3011,7 +3017,7 @@
 /**
  * amdgpu_device_has_dc_support - check if dc is supported
  *
- * @adev: amdgpu_device_pointer
+ * @adev: amdgpu_device pointer
  *
  * Returns true for supported, false for not supported
  */
@@ -4045,7 +4051,7 @@
 /**
  * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  * @from_hypervisor: request from hypervisor
  *
  * do VF FLR and reinitialize Asic
@@ -4100,7 +4106,7 @@
 /**
  * amdgpu_device_has_job_running - check if there is any job in mirror list
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  *
  * check if there is any job in mirror list
  */
@@ -4128,7 +4134,7 @@
 /**
  * amdgpu_device_should_recover_gpu - check if we should try GPU recovery
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  *
  * Check amdgpu_gpu_recovery and SRIOV status to see if we should try to recover
  * a hung GPU.
@@ -4477,7 +4483,7 @@
 /**
  * amdgpu_device_gpu_recover - reset the asic and recover scheduler
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
  * @job: which job trigger hang
  *
  * Attempt to reset the GPU if it has hung (all asics).
@@ -4497,7 +4503,7 @@
 	bool need_emergency_restart = false;
 	bool audio_suspended = false;
 
-	/**
+	/*
 	 * Special case: RAS triggered and full reset isn't supported
 	 */
 	need_emergency_restart = amdgpu_ras_need_emergency_restart(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index f203e4a..731f3aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -81,8 +81,8 @@
 /**
  * amdgpu_gtt_mgr_init - init GTT manager and DRM MM
  *
- * @man: TTM memory type manager
- * @p_size: maximum size of GTT
+ * @adev: amdgpu_device pointer
+ * @gtt_size: maximum size of GTT
  *
  * Allocate and initialize the GTT manager.
  */
@@ -123,7 +123,7 @@
 /**
  * amdgpu_gtt_mgr_fini - free and destroy GTT manager
  *
- * @man: TTM memory type manager
+ * @adev: amdgpu_device pointer
  *
  * Destroy and free the GTT manager, returns -EBUSY if ranges are still
  * allocated inside it.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 96a9699..a6dbe4b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2524,6 +2524,7 @@
 		psp->asd_feature_version   = le32_to_cpu(desc->fw_version);
 		psp->asd_ucode_size 	   = le32_to_cpu(desc->size_bytes);
 		psp->asd_start_addr 	   = ucode_start_addr;
+		psp->asd_fw                = psp->ta_fw;
 		break;
 	case TA_FW_TYPE_PSP_XGMI:
 		psp->ta_xgmi_ucode_version = le32_to_cpu(desc->fw_version);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index f3b7287..a563328 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -39,6 +39,7 @@
 #define FIRMWARE_RAVEN2		"amdgpu/raven2_vcn.bin"
 #define FIRMWARE_ARCTURUS 	"amdgpu/arcturus_vcn.bin"
 #define FIRMWARE_RENOIR 	"amdgpu/renoir_vcn.bin"
+#define FIRMWARE_GREEN_SARDINE 	"amdgpu/green_sardine_vcn.bin"
 #define FIRMWARE_NAVI10 	"amdgpu/navi10_vcn.bin"
 #define FIRMWARE_NAVI14 	"amdgpu/navi14_vcn.bin"
 #define FIRMWARE_NAVI12 	"amdgpu/navi12_vcn.bin"
@@ -50,6 +51,7 @@
 MODULE_FIRMWARE(FIRMWARE_RAVEN2);
 MODULE_FIRMWARE(FIRMWARE_ARCTURUS);
 MODULE_FIRMWARE(FIRMWARE_RENOIR);
+MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE);
 MODULE_FIRMWARE(FIRMWARE_NAVI10);
 MODULE_FIRMWARE(FIRMWARE_NAVI14);
 MODULE_FIRMWARE(FIRMWARE_NAVI12);
@@ -89,7 +91,11 @@
 			adev->vcn.indirect_sram = true;
 		break;
 	case CHIP_RENOIR:
-		fw_name = FIRMWARE_RENOIR;
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
+			fw_name = FIRMWARE_RENOIR;
+		else
+			fw_name = FIRMWARE_GREEN_SARDINE;
+
 		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
 		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
 			adev->vcn.indirect_sram = true;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 01c1171..0c6b7c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -168,8 +168,7 @@
 /**
  * amdgpu_vram_mgr_init - init VRAM manager and DRM MM
  *
- * @man: TTM memory type manager
- * @p_size: maximum size of VRAM
+ * @adev: amdgpu_device pointer
  *
  * Allocate and initialize the VRAM manager.
  */
@@ -199,7 +198,7 @@
 /**
  * amdgpu_vram_mgr_fini - free and destroy VRAM manager
  *
- * @man: TTM memory type manager
+ * @adev: amdgpu_device pointer
  *
  * Destroy and free the VRAM manager, returns -EBUSY if ranges are still
  * allocated inside it.
@@ -229,7 +228,7 @@
 /**
  * amdgpu_vram_mgr_vis_size - Calculate visible node size
  *
- * @adev: amdgpu device structure
+ * @adev: amdgpu_device pointer
  * @node: MM node structure
  *
  * Calculate how many bytes of the MM node are inside visible VRAM
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 03ff8bd..5442df0 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1336,11 +1336,13 @@
 
 	switch (adev->asic_type) {
 	case CHIP_BONAIRE:
-	case CHIP_HAWAII:
 		/* disable baco reset until it works */
 		/* smu7_asic_get_baco_capability(adev, &baco_reset); */
 		baco_reset = false;
 		break;
+	case CHIP_HAWAII:
+		baco_reset = cik_asic_supports_baco(adev);
+		break;
 	default:
 		baco_reset = false;
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 20f1088..a3c3fe9 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -1071,22 +1071,19 @@
 {
 	u32 srbm_soft_reset = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	u32 tmp = RREG32(mmSRBM_STATUS2);
+	u32 tmp;
 
-	if (tmp & SRBM_STATUS2__SDMA_BUSY_MASK) {
-		/* sdma0 */
-		tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET);
-		tmp |= SDMA0_F32_CNTL__HALT_MASK;
-		WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp);
-		srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK;
-	}
-	if (tmp & SRBM_STATUS2__SDMA1_BUSY_MASK) {
-		/* sdma1 */
-		tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET);
-		tmp |= SDMA0_F32_CNTL__HALT_MASK;
-		WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp);
-		srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK;
-	}
+	/* sdma0 */
+	tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET);
+	tmp |= SDMA0_F32_CNTL__HALT_MASK;
+	WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp);
+	srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK;
+
+	/* sdma1 */
+	tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET);
+	tmp |= SDMA0_F32_CNTL__HALT_MASK;
+	WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp);
+	srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK;
 
 	if (srbm_soft_reset) {
 		tmp = RREG32(mmSRBM_SOFT_RESET);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 56fdbe6..3579565 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -128,6 +128,9 @@
 #define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO__SHIFT 0x3
 #define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO_MASK   0x00000008L
 
+#define mmCGTT_SPI_CS_CLK_CTRL			0x507c
+#define mmCGTT_SPI_CS_CLK_CTRL_BASE_IDX         1
+
 MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
 MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
 MODULE_FIRMWARE("amdgpu/navi10_me.bin");
@@ -3094,6 +3097,7 @@
 
 static const struct soc15_reg_golden golden_settings_gc_10_3[] =
 {
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CS_CLK_CTRL, 0x78000000, 0x78000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_PS_CLK_CTRL, 0xff7f0fff, 0x78000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA0_CLK_CTRL, 0xff7f0fff, 0x30000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA1_CLK_CTRL, 0xff7f0fff, 0x7e000100),
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 6959aeb..0d8e203 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -117,6 +117,13 @@
 MODULE_FIRMWARE("amdgpu/renoir_mec2.bin");
 MODULE_FIRMWARE("amdgpu/renoir_rlc.bin");
 
+MODULE_FIRMWARE("amdgpu/green_sardine_ce.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_pfp.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_me.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_mec.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_mec2.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_rlc.bin");
+
 #define mmTCP_CHAN_STEER_0_ARCT								0x0b03
 #define mmTCP_CHAN_STEER_0_ARCT_BASE_IDX							0
 #define mmTCP_CHAN_STEER_1_ARCT								0x0b04
@@ -1630,7 +1637,10 @@
 		chip_name = "arcturus";
 		break;
 	case CHIP_RENOIR:
-		chip_name = "renoir";
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
+			chip_name = "renoir";
+		else
+			chip_name = "green_sardine";
 		break;
 	default:
 		BUG();
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 03462c8..8eeba80 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -455,10 +455,11 @@
 	adev->virt.ops = &xgpu_nv_virt_ops;
 }
 
-static bool nv_is_blockchain_sku(struct pci_dev *pdev)
+static bool nv_is_headless_sku(struct pci_dev *pdev)
 {
-	if (pdev->device == 0x731E &&
-	    (pdev->revision == 0xC6 || pdev->revision == 0xC7))
+	if ((pdev->device == 0x731E &&
+	    (pdev->revision == 0xC6 || pdev->revision == 0xC7)) ||
+	    (pdev->device == 0x7340 && pdev->revision == 0xC9))
 		return true;
 	return false;
 }
@@ -491,8 +492,7 @@
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
-		else if (amdgpu_device_has_dc_support(adev) &&
-			 !nv_is_blockchain_sku(adev->pdev))
+		else if (amdgpu_device_has_dc_support(adev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
@@ -500,7 +500,7 @@
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
 		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
-		if (!nv_is_blockchain_sku(adev->pdev))
+		if (!nv_is_headless_sku(adev->pdev))
 			amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
 		if (adev->enable_mes)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index 7548931..c4828bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -39,6 +39,8 @@
 
 MODULE_FIRMWARE("amdgpu/renoir_asd.bin");
 MODULE_FIRMWARE("amdgpu/renoir_ta.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_asd.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_ta.bin");
 
 /* address block */
 #define smnMP1_FIRMWARE_FLAGS		0x3010024
@@ -54,7 +56,10 @@
 
 	switch (adev->asic_type) {
 	case CHIP_RENOIR:
-		chip_name = "renoir";
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
+			chip_name = "renoir";
+		else
+			chip_name = "green_sardine";
 		break;
 	default:
 		BUG();
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 86fb1ed..e82f49f 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -69,6 +69,7 @@
 MODULE_FIRMWARE("amdgpu/raven2_sdma.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_sdma.bin");
 MODULE_FIRMWARE("amdgpu/renoir_sdma.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_sdma.bin");
 
 #define SDMA0_POWER_CNTL__ON_OFF_CONDITION_HOLD_TIME_MASK  0x000000F8L
 #define SDMA0_POWER_CNTL__ON_OFF_STATUS_DURATION_TIME_MASK 0xFC000000L
@@ -619,7 +620,10 @@
 		chip_name = "arcturus";
 		break;
 	case CHIP_RENOIR:
-		chip_name = "renoir";
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
+			chip_name = "renoir";
+		else
+			chip_name = "green_sardine";
 		break;
 	default:
 		BUG();
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index afcccc6..f57c5f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1195,8 +1195,7 @@
 
 			adev->pg_flags = AMD_PG_SUPPORT_SDMA |
 				AMD_PG_SUPPORT_MMHUB |
-				AMD_PG_SUPPORT_VCN |
-				AMD_PG_SUPPORT_VCN_DPG;
+				AMD_PG_SUPPORT_VCN;
 		} else {
 			adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 				AMD_CG_SUPPORT_GFX_MGLS |
@@ -1243,7 +1242,15 @@
 		break;
 	case CHIP_RENOIR:
 		adev->asic_funcs = &soc15_asic_funcs;
-		adev->apu_flags |= AMD_APU_IS_RENOIR;
+		if (adev->pdev->device == 0x1636)
+			adev->apu_flags |= AMD_APU_IS_RENOIR;
+		else
+			adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE;
+
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
+			adev->external_rev_id = adev->rev_id + 0x91;
+		else
+			adev->external_rev_id = adev->rev_id + 0xa1;
 		adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 				 AMD_CG_SUPPORT_GFX_MGLS |
 				 AMD_CG_SUPPORT_GFX_3D_CGCG |
@@ -1268,7 +1275,6 @@
 				 AMD_PG_SUPPORT_VCN |
 				 AMD_PG_SUPPORT_JPEG |
 				 AMD_PG_SUPPORT_VCN_DPG;
-		adev->external_rev_id = adev->rev_id + 0x91;
 		break;
 	default:
 		/* FIXME: not supported yet */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 5e2254b..3de5e14 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -798,10 +798,10 @@
 	}
 
 	pcrat_image = kvmalloc(crat_table->length, GFP_KERNEL);
-	memcpy(pcrat_image, crat_table, crat_table->length);
 	if (!pcrat_image)
 		return -ENOMEM;
 
+	memcpy(pcrat_image, crat_table, crat_table->length);
 	*crat_image = pcrat_image;
 	*size = crat_table->length;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index e2b23486..e93e18c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -100,6 +100,8 @@
 #define FIRMWARE_NAVY_FLOUNDER_DMUB "amdgpu/navy_flounder_dmcub.bin"
 MODULE_FIRMWARE(FIRMWARE_NAVY_FLOUNDER_DMUB);
 #endif
+#define FIRMWARE_GREEN_SARDINE_DMUB "amdgpu/green_sardine_dmcub.bin"
+MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE_DMUB);
 
 #define FIRMWARE_RAVEN_DMCU		"amdgpu/raven_dmcu.bin"
 MODULE_FIRMWARE(FIRMWARE_RAVEN_DMCU);
@@ -583,7 +585,7 @@
 {
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
-	struct dm_comressor_info *compressor = &adev->dm.compressor;
+	struct dm_compressor_info *compressor = &adev->dm.compressor;
 	struct amdgpu_dm_connector *aconn = to_amdgpu_dm_connector(connector);
 	struct drm_display_mode *mode;
 	unsigned long max_size = 0;
@@ -973,6 +975,8 @@
 	case CHIP_RAVEN:
 	case CHIP_RENOIR:
 		init_data.flags.gpu_vm_support = true;
+		if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id))
+			init_data.flags.disable_dmcu = true;
 		break;
 	default:
 		break;
@@ -1267,6 +1271,8 @@
 	case CHIP_RENOIR:
 		dmub_asic = DMUB_ASIC_DCN21;
 		fw_name_dmub = FIRMWARE_RENOIR_DMUB;
+		if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id))
+			fw_name_dmub = FIRMWARE_GREEN_SARDINE_DMUB;
 		break;
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 	case CHIP_SIENNA_CICHLID:
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 34f6369..a8a0e8c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -86,7 +86,7 @@
  * @bo_ptr: Pointer to the buffer object
  * @gpu_addr: MMIO gpu addr
  */
-struct dm_comressor_info {
+struct dm_compressor_info {
 	void *cpu_addr;
 	struct amdgpu_bo *bo_ptr;
 	uint64_t gpu_addr;
@@ -148,7 +148,7 @@
  * @soc_bounding_box: SOC bounding box values provided by gpu_info FW
  * @cached_state: Caches device atomic state for suspend/resume
  * @cached_dc_state: Cached state of content streams
- * @compressor: Frame buffer compression buffer. See &struct dm_comressor_info
+ * @compressor: Frame buffer compression buffer. See &struct dm_compressor_info
  * @force_timing_sync: set via debugfs. When set, indicates that all connected
  *		       displays will be forced to synchronize.
  */
@@ -324,7 +324,7 @@
 	struct drm_atomic_state *cached_state;
 	struct dc_state *cached_dc_state;
 
-	struct dm_comressor_info compressor;
+	struct dm_compressor_info compressor;
 
 	const struct firmware *fw_dmcu;
 	uint32_t dmcu_fw_version;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
index efb909e..857f156 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -166,6 +166,11 @@
 			rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
 			break;
 		}
+
+		if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev)) {
+			rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
+			break;
+		}
 		if (ASICREV_IS_RAVEN2(asic_id.hw_internal_rev)) {
 			rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu);
 			break;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index e430148..59d48cf 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -120,6 +120,8 @@
 			dc_version = DCN_VERSION_1_01;
 		if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev))
 			dc_version = DCN_VERSION_2_1;
+		if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev))
+			dc_version = DCN_VERSION_2_1;
 		break;
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c
index 49689f7..0effbb2 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c
@@ -306,8 +306,8 @@
 	pflip_int_entry(1),
 	pflip_int_entry(2),
 	pflip_int_entry(3),
-	[DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(),
-	[DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(),
+	pflip_int_entry(4),
+	pflip_int_entry(5),
 	[DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(),
 	gpio_pad_int_entry(0),
 	gpio_pad_int_entry(1),
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index b267987..ffcb059 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -205,6 +205,10 @@
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 #define ASICREV_IS_SIENNA_CICHLID_P(eChipRev)        ((eChipRev >= NV_SIENNA_CICHLID_P_A0))
 #endif
+#define GREEN_SARDINE_A0 0xA1
+#ifndef ASICREV_IS_GREEN_SARDINE
+#define ASICREV_IS_GREEN_SARDINE(eChipRev) ((eChipRev >= GREEN_SARDINE_A0) && (eChipRev < 0xFF))
+#endif
 
 /*
  * ASIC chip ID
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 10dc481..06c1aab 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -45,6 +45,7 @@
 	AMD_APU_IS_RAVEN2 = 0x00000002UL,
 	AMD_APU_IS_PICASSO = 0x00000004UL,
 	AMD_APU_IS_RENOIR = 0x00000008UL,
+	AMD_APU_IS_GREEN_SARDINE = 0x00000010UL,
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/pm/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/inc/hwmgr.h
index 3898a95..518796a2 100644
--- a/drivers/gpu/drm/amd/pm/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/inc/hwmgr.h
@@ -229,6 +229,7 @@
 	bool (*is_hw_avfs_present)(struct pp_hwmgr  *hwmgr);
 	int (*update_dpm_settings)(struct pp_hwmgr *hwmgr, void *profile_setting);
 	int (*smc_table_manager)(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw); /*rw: true for read, false for write */
+	int (*stop_smc)(struct pp_hwmgr *hwmgr);
 };
 
 struct pp_hwmgr_func {
diff --git a/drivers/gpu/drm/amd/pm/inc/smumgr.h b/drivers/gpu/drm/amd/pm/inc/smumgr.h
index ad100b5..5f46f1a 100644
--- a/drivers/gpu/drm/amd/pm/inc/smumgr.h
+++ b/drivers/gpu/drm/amd/pm/inc/smumgr.h
@@ -113,4 +113,6 @@
 
 extern int smum_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw);
 
+extern int smum_stop_smc(struct pp_hwmgr *hwmgr);
+
 #endif
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c
index 3be4011..45f6088 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c
@@ -142,12 +142,12 @@
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK,           BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x00 },
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK,          BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x00 },
 	{ CMD_DELAY_MS, 0, 0, 0, 20, 0 },
-	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x20 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x200 },
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x01 },
-	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c00 },
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x01 },
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x00 },
-	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x10 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x100 },
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x00 },
 	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x00 }
 };
@@ -155,6 +155,7 @@
 static const struct baco_cmd_entry clean_baco_tbl[] =
 {
 	{ CMD_WRITE, mmBIOS_SCRATCH_6, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_7, 0, 0, 0, 0 },
 	{ CMD_WRITE, mmCP_PFP_UCODE_ADDR, 0, 0, 0, 0 }
 };
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index 1e8919b..3562914 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -1541,6 +1541,10 @@
 	PP_ASSERT_WITH_CODE((tmp_result == 0),
 			"Failed to reset to default!", result = tmp_result);
 
+	tmp_result = smum_stop_smc(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to stop smc!", result = tmp_result);
+
 	tmp_result = smu7_force_switch_to_arbf0(hwmgr);
 	PP_ASSERT_WITH_CODE((tmp_result == 0),
 			"Failed to force to switch arbf0!", result = tmp_result);
@@ -1585,18 +1589,24 @@
 	data->current_profile_setting.sclk_down_hyst = 100;
 	data->current_profile_setting.sclk_activity = SMU7_SCLK_TARGETACTIVITY_DFLT;
 	data->current_profile_setting.bupdate_mclk = 1;
-	if (adev->gmc.vram_width == 256) {
-		data->current_profile_setting.mclk_up_hyst = 10;
-		data->current_profile_setting.mclk_down_hyst = 60;
-		data->current_profile_setting.mclk_activity = 25;
-	} else if (adev->gmc.vram_width == 128) {
-		data->current_profile_setting.mclk_up_hyst = 5;
-		data->current_profile_setting.mclk_down_hyst = 16;
-		data->current_profile_setting.mclk_activity = 20;
-	} else if (adev->gmc.vram_width == 64) {
-		data->current_profile_setting.mclk_up_hyst = 3;
-		data->current_profile_setting.mclk_down_hyst = 16;
-		data->current_profile_setting.mclk_activity = 20;
+	if (hwmgr->chip_id >= CHIP_POLARIS10) {
+		if (adev->gmc.vram_width == 256) {
+			data->current_profile_setting.mclk_up_hyst = 10;
+			data->current_profile_setting.mclk_down_hyst = 60;
+			data->current_profile_setting.mclk_activity = 25;
+		} else if (adev->gmc.vram_width == 128) {
+			data->current_profile_setting.mclk_up_hyst = 5;
+			data->current_profile_setting.mclk_down_hyst = 16;
+			data->current_profile_setting.mclk_activity = 20;
+		} else if (adev->gmc.vram_width == 64) {
+			data->current_profile_setting.mclk_up_hyst = 3;
+			data->current_profile_setting.mclk_down_hyst = 16;
+			data->current_profile_setting.mclk_activity = 20;
+		}
+	} else {
+		data->current_profile_setting.mclk_up_hyst = 0;
+		data->current_profile_setting.mclk_down_hyst = 100;
+		data->current_profile_setting.mclk_activity = SMU7_MCLK_TARGETACTIVITY_DFLT;
 	}
 	hwmgr->workload_mask = 1 << hwmgr->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
 	hwmgr->power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c
index e4d1f3d..329bf4d 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c
@@ -2726,10 +2726,7 @@
 
 static bool ci_is_dpm_running(struct pp_hwmgr *hwmgr)
 {
-	return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device,
-					     CGS_IND_REG__SMC, FEATURE_STATUS,
-					     VOLTAGE_CONTROLLER_ON))
-		? true : false;
+	return ci_is_smc_ram_running(hwmgr);
 }
 
 static int ci_smu_init(struct pp_hwmgr *hwmgr)
@@ -2939,6 +2936,29 @@
 	return 0;
 }
 
+static void ci_reset_smc(struct pp_hwmgr *hwmgr)
+{
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+				  SMC_SYSCON_RESET_CNTL,
+				  rst_reg, 1);
+}
+
+
+static void ci_stop_smc_clock(struct pp_hwmgr *hwmgr)
+{
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+				  SMC_SYSCON_CLOCK_CNTL_0,
+				  ck_disable, 1);
+}
+
+static int ci_stop_smc(struct pp_hwmgr *hwmgr)
+{
+	ci_reset_smc(hwmgr);
+	ci_stop_smc_clock(hwmgr);
+
+	return 0;
+}
+
 const struct pp_smumgr_func ci_smu_funcs = {
 	.name = "ci_smu",
 	.smu_init = ci_smu_init,
@@ -2964,4 +2984,5 @@
 	.is_dpm_running = ci_is_dpm_running,
 	.update_dpm_settings = ci_update_dpm_settings,
 	.update_smc_table = ci_update_smc_table,
+	.stop_smc = ci_stop_smc,
 };
diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c
index b6fb480..b6921db 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c
@@ -245,3 +245,11 @@
 
 	return -EINVAL;
 }
+
+int smum_stop_smc(struct pp_hwmgr *hwmgr)
+{
+	if (hwmgr->smumgr_funcs->stop_smc)
+		return hwmgr->smumgr_funcs->stop_smc(hwmgr);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index fc4f95f..b1e5ec0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1029,17 +1029,6 @@
 		return ret;
 	}
 
-	/*
-	 * Set initialized values (get from vbios) to dpm tables context such as
-	 * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each
-	 * type of clks.
-	 */
-	ret = smu_set_default_dpm_table(smu);
-	if (ret) {
-		dev_err(adev->dev, "Failed to setup default dpm clock tables!\n");
-		return ret;
-	}
-
 	ret = smu_notify_display_change(smu);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/bridge/cadence/Kconfig b/drivers/gpu/drm/bridge/cadence/Kconfig
index 511d67b..ef8c230 100644
--- a/drivers/gpu/drm/bridge/cadence/Kconfig
+++ b/drivers/gpu/drm/bridge/cadence/Kconfig
@@ -13,7 +13,7 @@
 if DRM_CDNS_MHDP8546
 
 config DRM_CDNS_MHDP8546_J721E
-	depends on ARCH_K3_J721E_SOC || COMPILE_TEST
+	depends on ARCH_K3 || COMPILE_TEST
 	bool "J721E Cadence DPI/DP wrapper support"
 	default y
 	help
diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c
index 15eb377..361e3a0c 100644
--- a/drivers/gpu/drm/gma500/psb_irq.c
+++ b/drivers/gpu/drm/gma500/psb_irq.c
@@ -347,6 +347,7 @@
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
+	unsigned int i;
 
 	spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags);
 
@@ -359,20 +360,12 @@
 	PSB_WVDC32(dev_priv->vdc_irq_mask, PSB_INT_ENABLE_R);
 	PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
 
-	if (dev->vblank[0].enabled)
-		psb_enable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-	else
-		psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[1].enabled)
-		psb_enable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-	else
-		psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[2].enabled)
-		psb_enable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
-	else
-		psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
+	for (i = 0; i < dev->num_crtcs; ++i) {
+		if (dev->vblank[i].enabled)
+			psb_enable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+		else
+			psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+	}
 
 	if (dev_priv->ops->hotplug_enable)
 		dev_priv->ops->hotplug_enable(dev, true);
@@ -385,6 +378,7 @@
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
+	unsigned int i;
 
 	spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags);
 
@@ -393,14 +387,10 @@
 
 	PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
 
-	if (dev->vblank[0].enabled)
-		psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[1].enabled)
-		psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-
-	if (dev->vblank[2].enabled)
-		psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
+	for (i = 0; i < dev->num_crtcs; ++i) {
+		if (dev->vblank[i].enabled)
+			psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+	}
 
 	dev_priv->vdc_irq_mask &= _PSB_IRQ_SGX_FLAG |
 				  _PSB_IRQ_MSVDX_FLAG |
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 8a9d0bd..40e9cb2 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1754,7 +1754,7 @@
 		return;
 
 	intel_connector = to_intel_connector(connector);
-	dig_port = enc_to_dig_port(intel_attached_encoder(intel_connector));
+	dig_port = enc_to_dig_port(to_intel_encoder(new_state->best_encoder));
 	if (dev_priv->psr.dp != &dig_port->dp)
 		return;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 7c90a63..fcce690 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -509,21 +509,6 @@
 		return -ENOENT;
 
 	/*
-	 * Already in the desired write domain? Nothing for us to do!
-	 *
-	 * We apply a little bit of cunning here to catch a broader set of
-	 * no-ops. If obj->write_domain is set, we must be in the same
-	 * obj->read_domains, and only that domain. Therefore, if that
-	 * obj->write_domain matches the request read_domains, we are
-	 * already in the same read/write domain and can skip the operation,
-	 * without having to further check the requested write_domain.
-	 */
-	if (READ_ONCE(obj->write_domain) == read_domains) {
-		err = 0;
-		goto out;
-	}
-
-	/*
 	 * Try to flush the object off the GPU without holding the lock.
 	 * We will repeat the flush holding the lock in the normal manner
 	 * to catch cases where we are gazumped.
@@ -560,6 +545,19 @@
 	if (err)
 		goto out;
 
+	/*
+	 * Already in the desired write domain? Nothing for us to do!
+	 *
+	 * We apply a little bit of cunning here to catch a broader set of
+	 * no-ops. If obj->write_domain is set, we must be in the same
+	 * obj->read_domains, and only that domain. Therefore, if that
+	 * obj->write_domain matches the request read_domains, we are
+	 * already in the same read/write domain and can skip the operation,
+	 * without having to further check the requested write_domain.
+	 */
+	if (READ_ONCE(obj->write_domain) == read_domains)
+		goto out_unpin;
+
 	err = i915_gem_object_lock_interruptible(obj, NULL);
 	if (err)
 		goto out_unpin;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index b5c1555..d6711ca 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -56,6 +56,8 @@
 	void (*truncate)(struct drm_i915_gem_object *obj);
 	void (*writeback)(struct drm_i915_gem_object *obj);
 
+	int (*pread)(struct drm_i915_gem_object *obj,
+		     const struct drm_i915_gem_pread *arg);
 	int (*pwrite)(struct drm_i915_gem_object *obj,
 		      const struct drm_i915_gem_pwrite *arg);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index 28147aa..3a4dfe2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -134,6 +134,58 @@
 			  vaddr, dma);
 }
 
+static int
+phys_pwrite(struct drm_i915_gem_object *obj,
+	    const struct drm_i915_gem_pwrite *args)
+{
+	void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
+	char __user *user_data = u64_to_user_ptr(args->data_ptr);
+	int err;
+
+	err = i915_gem_object_wait(obj,
+				   I915_WAIT_INTERRUPTIBLE |
+				   I915_WAIT_ALL,
+				   MAX_SCHEDULE_TIMEOUT);
+	if (err)
+		return err;
+
+	/*
+	 * We manually control the domain here and pretend that it
+	 * remains coherent i.e. in the GTT domain, like shmem_pwrite.
+	 */
+	i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU);
+
+	if (copy_from_user(vaddr, user_data, args->size))
+		return -EFAULT;
+
+	drm_clflush_virt_range(vaddr, args->size);
+	intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
+
+	i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
+	return 0;
+}
+
+static int
+phys_pread(struct drm_i915_gem_object *obj,
+	   const struct drm_i915_gem_pread *args)
+{
+	void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
+	char __user *user_data = u64_to_user_ptr(args->data_ptr);
+	int err;
+
+	err = i915_gem_object_wait(obj,
+				   I915_WAIT_INTERRUPTIBLE,
+				   MAX_SCHEDULE_TIMEOUT);
+	if (err)
+		return err;
+
+	drm_clflush_virt_range(vaddr, args->size);
+	if (copy_to_user(user_data, vaddr, args->size))
+		return -EFAULT;
+
+	return 0;
+}
+
 static void phys_release(struct drm_i915_gem_object *obj)
 {
 	fput(obj->base.filp);
@@ -144,6 +196,9 @@
 	.get_pages = i915_gem_object_get_pages_phys,
 	.put_pages = i915_gem_object_put_pages_phys,
 
+	.pread  = phys_pread,
+	.pwrite = phys_pwrite,
+
 	.release = phys_release,
 };
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 7c3a101..760fefd 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -245,22 +245,14 @@
 }
 
 static inline u32 *
-__gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
+__gen8_emit_write_rcs(u32 *cs, u32 value, u32 offset, u32 flags0, u32 flags1)
 {
-	/* We're using qword write, offset should be aligned to 8 bytes. */
-	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
-
-	/* w/a for post sync ops following a GPGPU operation we
-	 * need a prior CS_STALL, which is emitted by the flush
-	 * following the batch.
-	 */
 	*cs++ = GFX_OP_PIPE_CONTROL(6) | flags0;
-	*cs++ = flags1 | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB;
-	*cs++ = gtt_offset;
+	*cs++ = flags1 | PIPE_CONTROL_QW_WRITE;
+	*cs++ = offset;
 	*cs++ = 0;
 	*cs++ = value;
-	/* We're thrashing one dword of HWS. */
-	*cs++ = 0;
+	*cs++ = 0; /* We're thrashing one extra dword. */
 
 	return cs;
 }
@@ -268,13 +260,38 @@
 static inline u32*
 gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 {
-	return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, 0, flags);
+	/* We're using qword write, offset should be aligned to 8 bytes. */
+	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
+
+	return __gen8_emit_write_rcs(cs,
+				     value,
+				     gtt_offset,
+				     0,
+				     flags | PIPE_CONTROL_GLOBAL_GTT_IVB);
 }
 
 static inline u32*
 gen12_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
 {
-	return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, flags0, flags1);
+	/* We're using qword write, offset should be aligned to 8 bytes. */
+	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
+
+	return __gen8_emit_write_rcs(cs,
+				     value,
+				     gtt_offset,
+				     flags0,
+				     flags1 | PIPE_CONTROL_GLOBAL_GTT_IVB);
+}
+
+static inline u32 *
+__gen8_emit_flush_dw(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
+{
+	*cs++ = (MI_FLUSH_DW + 1) | flags;
+	*cs++ = gtt_offset;
+	*cs++ = 0;
+	*cs++ = value;
+
+	return cs;
 }
 
 static inline u32 *
@@ -285,12 +302,10 @@
 	/* Offset should be aligned to 8 bytes for both (QW/DW) write types */
 	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
 
-	*cs++ = (MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW | flags;
-	*cs++ = gtt_offset | MI_FLUSH_DW_USE_GTT;
-	*cs++ = 0;
-	*cs++ = value;
-
-	return cs;
+	return __gen8_emit_flush_dw(cs,
+				    value,
+				    gtt_offset | MI_FLUSH_DW_USE_GTT,
+				    flags | MI_FLUSH_DW_OP_STOREDW);
 }
 
 static inline void __intel_engine_reset(struct intel_engine_cs *engine,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 5bfb5f7..efdeb7b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -371,7 +371,8 @@
 		 * instances.
 		 */
 		if ((INTEL_GEN(i915) >= 11 &&
-		     engine->gt->info.vdbox_sfc_access & engine->mask) ||
+		     (engine->gt->info.vdbox_sfc_access &
+		      BIT(engine->instance))) ||
 		    (INTEL_GEN(i915) >= 9 && engine->instance == 0))
 			engine->uabi_capabilities |=
 				I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a32aabc..f82c6dd 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3547,6 +3547,19 @@
 	.destroy = execlists_context_destroy,
 };
 
+static u32 hwsp_offset(const struct i915_request *rq)
+{
+	const struct intel_timeline_cacheline *cl;
+
+	/* Before the request is executed, the timeline/cachline is fixed */
+
+	cl = rcu_dereference_protected(rq->hwsp_cacheline, 1);
+	if (cl)
+		return cl->ggtt_offset;
+
+	return rcu_dereference_protected(rq->timeline, 1)->hwsp_offset;
+}
+
 static int gen8_emit_init_breadcrumb(struct i915_request *rq)
 {
 	u32 *cs;
@@ -3569,7 +3582,7 @@
 	*cs++ = MI_NOOP;
 
 	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
-	*cs++ = i915_request_timeline(rq)->hwsp_offset;
+	*cs++ = hwsp_offset(rq);
 	*cs++ = 0;
 	*cs++ = rq->fence.seqno - 1;
 
@@ -4886,11 +4899,9 @@
 	return gen8_emit_wa_tail(request, cs);
 }
 
-static u32 *emit_xcs_breadcrumb(struct i915_request *request, u32 *cs)
+static u32 *emit_xcs_breadcrumb(struct i915_request *rq, u32 *cs)
 {
-	u32 addr = i915_request_active_timeline(request)->hwsp_offset;
-
-	return gen8_emit_ggtt_write(cs, request->fence.seqno, addr, 0);
+	return gen8_emit_ggtt_write(cs, rq->fence.seqno, hwsp_offset(rq), 0);
 }
 
 static u32 *gen8_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs)
@@ -4909,7 +4920,7 @@
 	/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      request->fence.seqno,
-				      i915_request_active_timeline(request)->hwsp_offset,
+				      hwsp_offset(request),
 				      PIPE_CONTROL_FLUSH_ENABLE |
 				      PIPE_CONTROL_CS_STALL);
 
@@ -4921,7 +4932,7 @@
 {
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      request->fence.seqno,
-				      i915_request_active_timeline(request)->hwsp_offset,
+				      hwsp_offset(request),
 				      PIPE_CONTROL_CS_STALL |
 				      PIPE_CONTROL_TILE_CACHE_FLUSH |
 				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
@@ -4983,7 +4994,9 @@
 
 static u32 *gen12_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs)
 {
-	return gen12_emit_fini_breadcrumb_tail(rq, emit_xcs_breadcrumb(rq, cs));
+	/* XXX Stalling flush before seqno write; post-sync not */
+	cs = emit_xcs_breadcrumb(rq, __gen8_emit_flush_dw(cs, 0, 0, 0));
+	return gen12_emit_fini_breadcrumb_tail(rq, cs);
 }
 
 static u32 *
@@ -4991,7 +5004,7 @@
 {
 	cs = gen12_emit_ggtt_write_rcs(cs,
 				       request->fence.seqno,
-				       i915_request_active_timeline(request)->hwsp_offset,
+				       hwsp_offset(request),
 				       PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
 				       PIPE_CONTROL_CS_STALL |
 				       PIPE_CONTROL_TILE_CACHE_FLUSH |
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index a2f74ce..7ea94d2 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -188,10 +188,14 @@
 	return cl;
 }
 
-static void cacheline_acquire(struct intel_timeline_cacheline *cl)
+static void cacheline_acquire(struct intel_timeline_cacheline *cl,
+			      u32 ggtt_offset)
 {
-	if (cl)
-		i915_active_acquire(&cl->active);
+	if (!cl)
+		return;
+
+	cl->ggtt_offset = ggtt_offset;
+	i915_active_acquire(&cl->active);
 }
 
 static void cacheline_release(struct intel_timeline_cacheline *cl)
@@ -340,7 +344,7 @@
 	GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
 		 tl->fence_context, tl->hwsp_offset);
 
-	cacheline_acquire(tl->hwsp_cacheline);
+	cacheline_acquire(tl->hwsp_cacheline, tl->hwsp_offset);
 	if (atomic_fetch_inc(&tl->pin_count)) {
 		cacheline_release(tl->hwsp_cacheline);
 		__i915_vma_unpin(tl->hwsp_ggtt);
@@ -515,7 +519,7 @@
 	GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
 		 tl->fence_context, tl->hwsp_offset);
 
-	cacheline_acquire(cl);
+	cacheline_acquire(cl, tl->hwsp_offset);
 	tl->hwsp_cacheline = cl;
 
 	*seqno = timeline_advance(tl);
@@ -573,9 +577,7 @@
 	if (err)
 		goto out;
 
-	*hwsp = i915_ggtt_offset(cl->hwsp->vma) +
-		ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) * CACHELINE_BYTES;
-
+	*hwsp = cl->ggtt_offset;
 out:
 	i915_active_release(&cl->active);
 	return err;
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index 02181c5..4474f48 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -94,6 +94,8 @@
 	struct intel_timeline_hwsp *hwsp;
 	void *vaddr;
 
+	u32 ggtt_offset;
+
 	struct rcu_head rcu;
 };
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 3be37e6..eb342a7 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1489,7 +1489,8 @@
 	const struct intel_engine_cs *engine =
 		intel_gvt_render_mmio_to_engine(vgpu->gvt, offset);
 
-	if (!intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) {
+	if (value != 0 &&
+	    !intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) {
 		gvt_vgpu_err("write invalid HWSP address, reg:0x%x, value:0x%x\n",
 			      offset, value);
 		return -EINVAL;
@@ -1650,6 +1651,34 @@
 	return 0;
 }
 
+/**
+ * FixMe:
+ * If guest fills non-priv batch buffer on ApolloLake/Broxton as Mesa i965 did:
+ * 717e7539124d (i965: Use a WC map and memcpy for the batch instead of pwrite.)
+ * Due to the missing flush of bb filled by VM vCPU, host GPU hangs on executing
+ * these MI_BATCH_BUFFER.
+ * Temporarily workaround this by setting SNOOP bit for PAT3 used by PPGTT
+ * PML4 PTE: PAT(0) PCD(1) PWT(1).
+ * The performance is still expected to be low, will need further improvement.
+ */
+static int bxt_ppat_low_write(struct intel_vgpu *vgpu, unsigned int offset,
+			      void *p_data, unsigned int bytes)
+{
+	u64 pat =
+		GEN8_PPAT(0, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(1, 0) |
+		GEN8_PPAT(2, 0) |
+		GEN8_PPAT(3, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(4, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(5, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(6, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(7, CHV_PPAT_SNOOP);
+
+	vgpu_vreg(vgpu, offset) = lower_32_bits(pat);
+
+	return 0;
+}
+
 static int guc_status_read(struct intel_vgpu *vgpu,
 			   unsigned int offset, void *p_data,
 			   unsigned int bytes)
@@ -2812,7 +2841,7 @@
 
 	MMIO_DH(GEN6_PCODE_MAILBOX, D_BDW_PLUS, NULL, mailbox_write);
 
-	MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS);
+	MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS & ~D_BXT);
 	MMIO_D(GEN8_PRIVATE_PAT_HI, D_BDW_PLUS);
 
 	MMIO_D(GAMTARBMODE, D_BDW_PLUS);
@@ -3139,7 +3168,7 @@
 		 NULL, NULL);
 
 	MMIO_DFH(GAMT_CHKN_BIT_REG, D_KBL | D_CFL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS);
+	MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS & ~D_BXT);
 
 	return 0;
 }
@@ -3313,9 +3342,21 @@
 	MMIO_D(GEN8_PUSHBUS_SHIFT, D_BXT);
 	MMIO_D(GEN6_GFXPAUSE, D_BXT);
 	MMIO_DFH(GEN8_L3SQCREG1, D_BXT, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(GEN8_L3CNTLREG, D_BXT, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x20D8), D_BXT, F_CMD_ACCESS, NULL, NULL);
+	MMIO_F(GEN8_RING_CS_GPR(RENDER_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+	       0, 0, D_BXT, NULL, NULL);
+	MMIO_F(GEN8_RING_CS_GPR(GEN6_BSD_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+	       0, 0, D_BXT, NULL, NULL);
+	MMIO_F(GEN8_RING_CS_GPR(BLT_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+	       0, 0, D_BXT, NULL, NULL);
+	MMIO_F(GEN8_RING_CS_GPR(VEBOX_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+	       0, 0, D_BXT, NULL, NULL);
 
 	MMIO_DFH(GEN9_CTX_PREEMPT_REG, D_BXT, F_CMD_ACCESS, NULL, NULL);
 
+	MMIO_DH(GEN8_PRIVATE_PAT_LO, D_BXT, NULL, bxt_ppat_low_write);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 1570eb8..aed2ef6 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -1277,7 +1277,7 @@
 
 	i915_context_ppgtt_root_restore(s, i915_vm_to_ppgtt(s->shadow[0]->vm));
 	for_each_engine(engine, vgpu->gvt->gt, id)
-		intel_context_unpin(s->shadow[id]);
+		intel_context_put(s->shadow[id]);
 
 	kmem_cache_destroy(s->workloads);
 }
@@ -1369,11 +1369,6 @@
 			ce->ring = __intel_context_ring_size(ring_size);
 		}
 
-		ret = intel_context_pin(ce);
-		intel_context_put(ce);
-		if (ret)
-			goto out_shadow_ctx;
-
 		s->shadow[i] = ce;
 	}
 
@@ -1405,7 +1400,6 @@
 		if (IS_ERR(s->shadow[i]))
 			break;
 
-		intel_context_unpin(s->shadow[i]);
 		intel_context_put(s->shadow[i]);
 	}
 	i915_vm_put(&ppgtt->vm);
@@ -1479,6 +1473,7 @@
 {
 	struct intel_vgpu_submission *s = &workload->vgpu->submission;
 
+	intel_context_unpin(s->shadow[workload->engine->id]);
 	release_shadow_batch_buffer(workload);
 	release_shadow_wa_ctx(&workload->wa_ctx);
 
@@ -1724,6 +1719,12 @@
 		return ERR_PTR(ret);
 	}
 
+	ret = intel_context_pin(s->shadow[engine->id]);
+	if (ret) {
+		intel_vgpu_destroy_workload(workload);
+		return ERR_PTR(ret);
+	}
+
 	return workload;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index bb0c129..5827669 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -180,30 +180,6 @@
 }
 
 static int
-i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
-		     struct drm_i915_gem_pwrite *args,
-		     struct drm_file *file)
-{
-	void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
-	char __user *user_data = u64_to_user_ptr(args->data_ptr);
-
-	/*
-	 * We manually control the domain here and pretend that it
-	 * remains coherent i.e. in the GTT domain, like shmem_pwrite.
-	 */
-	i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU);
-
-	if (copy_from_user(vaddr, user_data, args->size))
-		return -EFAULT;
-
-	drm_clflush_virt_range(vaddr, args->size);
-	intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
-
-	i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
-	return 0;
-}
-
-static int
 i915_gem_create(struct drm_file *file,
 		struct intel_memory_region *mr,
 		u64 *size_p,
@@ -527,6 +503,12 @@
 
 	trace_i915_gem_object_pread(obj, args->offset, args->size);
 
+	ret = -ENODEV;
+	if (obj->ops->pread)
+		ret = obj->ops->pread(obj, args);
+	if (ret != -ENODEV)
+		goto out;
+
 	ret = i915_gem_object_wait(obj,
 				   I915_WAIT_INTERRUPTIBLE,
 				   MAX_SCHEDULE_TIMEOUT);
@@ -866,8 +848,6 @@
 	if (ret == -EFAULT || ret == -ENOSPC) {
 		if (i915_gem_object_has_struct_page(obj))
 			ret = i915_gem_shmem_pwrite(obj, args);
-		else
-			ret = i915_gem_phys_pwrite(obj, args, file);
 	}
 
 	i915_gem_object_unpin_pages(obj);
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index ffb5287..caa9b04 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -314,8 +314,10 @@
 {
 	struct i915_vma_work *vw = container_of(work, typeof(*vw), base);
 
-	if (vw->pinned)
+	if (vw->pinned) {
 		__i915_gem_object_unpin_pages(vw->pinned);
+		i915_gem_object_put(vw->pinned);
+	}
 
 	i915_vm_free_pt_stash(vw->vm, &vw->stash);
 	i915_vm_put(vw->vm);
@@ -431,7 +433,7 @@
 
 		if (vma->obj) {
 			__i915_gem_object_pin_pages(vma->obj);
-			work->pinned = vma->obj;
+			work->pinned = i915_gem_object_get(vma->obj);
 		}
 	} else {
 		vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags);
diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c
index 71d84c7..d07b39b 100644
--- a/drivers/gpu/drm/imx/dw_hdmi-imx.c
+++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c
@@ -111,10 +111,6 @@
 	return 0;
 }
 
-static void dw_hdmi_imx_encoder_disable(struct drm_encoder *encoder)
-{
-}
-
 static void dw_hdmi_imx_encoder_enable(struct drm_encoder *encoder)
 {
 	struct imx_hdmi *hdmi = enc_to_imx_hdmi(encoder);
@@ -140,7 +136,6 @@
 
 static const struct drm_encoder_helper_funcs dw_hdmi_imx_encoder_helper_funcs = {
 	.enable     = dw_hdmi_imx_encoder_enable,
-	.disable    = dw_hdmi_imx_encoder_disable,
 	.atomic_check = dw_hdmi_imx_atomic_check,
 };
 
@@ -219,15 +214,9 @@
 	hdmi->dev = &pdev->dev;
 	encoder = &hdmi->encoder;
 
-	encoder->possible_crtcs = drm_of_find_possible_crtcs(drm, dev->of_node);
-	/*
-	 * If we failed to find the CRTC(s) which this encoder is
-	 * supposed to be connected to, it's because the CRTC has
-	 * not been registered yet.  Defer probing, and hope that
-	 * the required CRTC is added later.
-	 */
-	if (encoder->possible_crtcs == 0)
-		return -EPROBE_DEFER;
+	ret = imx_drm_encoder_parse_of(drm, encoder, dev->of_node);
+	if (ret)
+		return ret;
 
 	ret = dw_hdmi_imx_parse_dt(hdmi);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 7d00c49..9bf5ad6 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -20,6 +20,7 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_managed.h>
 #include <drm/drm_of.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_probe_helper.h>
@@ -212,7 +213,9 @@
 	drm->mode_config.allow_fb_modifiers = true;
 	drm->mode_config.normalize_zpos = true;
 
-	drm_mode_config_init(drm);
+	ret = drmm_mode_config_init(drm);
+	if (ret)
+		return ret;
 
 	ret = drm_vblank_init(drm, MAX_CRTC);
 	if (ret)
@@ -251,7 +254,6 @@
 	drm_kms_helper_poll_fini(drm);
 	component_unbind_all(drm->dev, drm);
 err_kms:
-	drm_mode_config_cleanup(drm);
 	drm_dev_put(drm);
 
 	return ret;
@@ -267,11 +269,9 @@
 
 	component_unbind_all(drm->dev, drm);
 
-	drm_mode_config_cleanup(drm);
+	drm_dev_put(drm);
 
 	dev_set_drvdata(dev, NULL);
-
-	drm_dev_put(drm);
 }
 
 static const struct component_master_ops imx_drm_ops = {
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index af757d1..41e2978 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -62,7 +62,6 @@
 	struct i2c_adapter *ddc;
 	int chno;
 	void *edid;
-	int edid_len;
 	struct drm_display_mode mode;
 	int mode_valid;
 	u32 bus_format;
@@ -536,15 +535,14 @@
 	}
 
 	if (!channel->ddc) {
+		int edid_len;
+
 		/* if no DDC available, fallback to hardcoded EDID */
 		dev_dbg(dev, "no ddc available\n");
 
-		edidp = of_get_property(child, "edid",
-					&channel->edid_len);
+		edidp = of_get_property(child, "edid", &edid_len);
 		if (edidp) {
-			channel->edid = kmemdup(edidp,
-						channel->edid_len,
-						GFP_KERNEL);
+			channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL);
 		} else if (!channel->panel) {
 			/* fallback to display-timings node */
 			ret = of_get_drm_display_mode(child,
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index 813bb61..2a8d2e3 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -13,7 +13,6 @@
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
-#include <linux/spinlock.h>
 #include <linux/videodev2.h>
 
 #include <video/imx-ipu-v3.h>
@@ -104,8 +103,6 @@
 	struct drm_connector connector;
 	struct drm_encoder encoder;
 	struct device *dev;
-	spinlock_t lock;	/* register lock */
-	bool enabled;
 	int mode;
 	int di_hsync_pin;
 	int di_vsync_pin;
@@ -129,30 +126,10 @@
 	return container_of(e, struct imx_tve, encoder);
 }
 
-static void tve_lock(void *__tve)
-__acquires(&tve->lock)
-{
-	struct imx_tve *tve = __tve;
-
-	spin_lock(&tve->lock);
-}
-
-static void tve_unlock(void *__tve)
-__releases(&tve->lock)
-{
-	struct imx_tve *tve = __tve;
-
-	spin_unlock(&tve->lock);
-}
-
 static void tve_enable(struct imx_tve *tve)
 {
-	if (!tve->enabled) {
-		tve->enabled = true;
-		clk_prepare_enable(tve->clk);
-		regmap_update_bits(tve->regmap, TVE_COM_CONF_REG,
-				   TVE_EN, TVE_EN);
-	}
+	clk_prepare_enable(tve->clk);
+	regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, TVE_EN);
 
 	/* clear interrupt status register */
 	regmap_write(tve->regmap, TVE_STAT_REG, 0xffffffff);
@@ -169,11 +146,8 @@
 
 static void tve_disable(struct imx_tve *tve)
 {
-	if (tve->enabled) {
-		tve->enabled = false;
-		regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, 0);
-		clk_disable_unprepare(tve->clk);
-	}
+	regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, 0);
+	clk_disable_unprepare(tve->clk);
 }
 
 static int tve_setup_tvout(struct imx_tve *tve)
@@ -500,8 +474,7 @@
 
 	.readable_reg = imx_tve_readable_reg,
 
-	.lock = tve_lock,
-	.unlock = tve_unlock,
+	.fast_io = true,
 
 	.max_register = 0xdc,
 };
@@ -511,7 +484,7 @@
 	[TVE_MODE_VGA] = "vga",
 };
 
-static const int of_get_tve_mode(struct device_node *np)
+static int of_get_tve_mode(struct device_node *np)
 {
 	const char *bm;
 	int ret, i;
@@ -544,7 +517,6 @@
 	memset(tve, 0, sizeof(*tve));
 
 	tve->dev = dev;
-	spin_lock_init(&tve->lock);
 
 	ddc_node = of_parse_phandle(np, "ddc-i2c-bus", 0);
 	if (ddc_node) {
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 8232f51..2eb8df46 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -28,7 +28,6 @@
 	struct drm_bridge bridge;
 	struct device *dev;
 	void *edid;
-	int edid_len;
 	u32 bus_format;
 	u32 bus_flags;
 	struct drm_display_mode mode;
@@ -41,11 +40,6 @@
 	return container_of(c, struct imx_parallel_display, connector);
 }
 
-static inline struct imx_parallel_display *enc_to_imxpd(struct drm_encoder *e)
-{
-	return container_of(e, struct imx_parallel_display, encoder);
-}
-
 static inline struct imx_parallel_display *bridge_to_imxpd(struct drm_bridge *b)
 {
 	return container_of(b, struct imx_parallel_display, bridge);
@@ -310,6 +304,7 @@
 	struct device_node *np = dev->of_node;
 	const u8 *edidp;
 	struct imx_parallel_display *imxpd;
+	int edid_len;
 	int ret;
 	u32 bus_format = 0;
 	const char *fmt;
@@ -323,9 +318,9 @@
 	if (ret && ret != -ENODEV)
 		return ret;
 
-	edidp = of_get_property(np, "edid", &imxpd->edid_len);
+	edidp = of_get_property(np, "edid", &edid_len);
 	if (edidp)
-		imxpd->edid = kmemdup(edidp, imxpd->edid_len, GFP_KERNEL);
+		imxpd->edid = devm_kmemdup(dev, edidp, edid_len, GFP_KERNEL);
 
 	ret = of_property_read_string(np, "interface-pix-fmt", &fmt);
 	if (!ret) {
@@ -349,17 +344,8 @@
 	return 0;
 }
 
-static void imx_pd_unbind(struct device *dev, struct device *master,
-	void *data)
-{
-	struct imx_parallel_display *imxpd = dev_get_drvdata(dev);
-
-	kfree(imxpd->edid);
-}
-
 static const struct component_ops imx_pd_ops = {
 	.bind	= imx_pd_bind,
-	.unbind	= imx_pd_unbind,
 };
 
 static int imx_pd_probe(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c
index c592957..92f8bd9 100644
--- a/drivers/gpu/drm/mcde/mcde_drv.c
+++ b/drivers/gpu/drm/mcde/mcde_drv.c
@@ -413,7 +413,13 @@
 					      match);
 	if (ret) {
 		dev_err(dev, "failed to add component master\n");
-		goto clk_disable;
+		/*
+		 * The EPOD regulator is already disabled at this point so some
+		 * special errorpath code is needed
+		 */
+		clk_disable_unprepare(mcde->mcde_clk);
+		regulator_disable(mcde->vana);
+		return ret;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index b111fe2..36d6b60 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -455,7 +455,7 @@
  * DAC
  *****************************************************************************/
 static void
-nv50_dac_disable(struct drm_encoder *encoder)
+nv50_dac_disable(struct drm_encoder *encoder, struct drm_atomic_state *state)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nv50_core *core = nv50_disp(encoder->dev)->core;
@@ -467,7 +467,7 @@
 }
 
 static void
-nv50_dac_enable(struct drm_encoder *encoder)
+nv50_dac_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
@@ -525,8 +525,8 @@
 static const struct drm_encoder_helper_funcs
 nv50_dac_help = {
 	.atomic_check = nv50_outp_atomic_check,
-	.enable = nv50_dac_enable,
-	.disable = nv50_dac_disable,
+	.atomic_enable = nv50_dac_enable,
+	.atomic_disable = nv50_dac_disable,
 	.detect = nv50_dac_detect
 };
 
@@ -1055,7 +1055,7 @@
 }
 
 static void
-nv50_msto_enable(struct drm_encoder *encoder)
+nv50_msto_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
 {
 	struct nv50_head *head = nv50_head(encoder->crtc);
 	struct nv50_head_atom *armh = nv50_head_atom(head->base.base.state);
@@ -1101,7 +1101,7 @@
 }
 
 static void
-nv50_msto_disable(struct drm_encoder *encoder)
+nv50_msto_disable(struct drm_encoder *encoder, struct drm_atomic_state *state)
 {
 	struct nv50_msto *msto = nv50_msto(encoder);
 	struct nv50_mstc *mstc = msto->mstc;
@@ -1118,8 +1118,8 @@
 
 static const struct drm_encoder_helper_funcs
 nv50_msto_help = {
-	.disable = nv50_msto_disable,
-	.enable = nv50_msto_enable,
+	.atomic_disable = nv50_msto_disable,
+	.atomic_enable = nv50_msto_enable,
 	.atomic_check = nv50_msto_atomic_check,
 };
 
@@ -1645,8 +1645,7 @@
 }
 
 static void
-nv50_sor_enable(struct drm_encoder *encoder,
-		struct drm_atomic_state *state)
+nv50_sor_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
@@ -1873,7 +1872,7 @@
 }
 
 static void
-nv50_pior_disable(struct drm_encoder *encoder)
+nv50_pior_disable(struct drm_encoder *encoder, struct drm_atomic_state *state)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nv50_core *core = nv50_disp(encoder->dev)->core;
@@ -1885,7 +1884,7 @@
 }
 
 static void
-nv50_pior_enable(struct drm_encoder *encoder)
+nv50_pior_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
@@ -1921,14 +1920,14 @@
 	}
 
 	core->func->pior->ctrl(core, nv_encoder->or, ctrl, asyh);
-	nv_encoder->crtc = encoder->crtc;
+	nv_encoder->crtc = &nv_crtc->base;
 }
 
 static const struct drm_encoder_helper_funcs
 nv50_pior_help = {
 	.atomic_check = nv50_pior_atomic_check,
-	.enable = nv50_pior_enable,
-	.disable = nv50_pior_disable,
+	.atomic_enable = nv50_pior_enable,
+	.atomic_disable = nv50_pior_disable,
 };
 
 static void
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 2ee7564..56b335a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -350,14 +350,13 @@
 
 	if (domain & NOUVEAU_GEM_DOMAIN_VRAM) {
 		struct nvif_mmu *mmu = &drm->client.mmu;
-		const u8 type = mmu->type[drm->ttm.type_vram].type;
 
 		pl[*n].mem_type = TTM_PL_VRAM;
 		pl[*n].flags = flags & ~TTM_PL_FLAG_CACHED;
 
 		/* Some BARs do not support being ioremapped WC */
 		if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA &&
-		    type & NVIF_MEM_UNCACHED)
+		    mmu->type[drm->ttm.type_vram].type & NVIF_MEM_UNCACHED)
 			pl[*n].flags &= ~TTM_PL_FLAG_WC;
 
 		(*n)++;
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 6f21f36..8b4b3688 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -532,11 +532,13 @@
 nouveau_connector_set_edid(struct nouveau_connector *nv_connector,
 			   struct edid *edid)
 {
-	struct edid *old_edid = nv_connector->edid;
+	if (nv_connector->edid != edid) {
+		struct edid *old_edid = nv_connector->edid;
 
-	drm_connector_update_edid_property(&nv_connector->base, edid);
-	kfree(old_edid);
-	nv_connector->edid = edid;
+		drm_connector_update_edid_property(&nv_connector->base, edid);
+		kfree(old_edid);
+		nv_connector->edid = edid;
+	}
 }
 
 static enum drm_connector_status
@@ -669,8 +671,10 @@
 	/* Try retrieving EDID via DDC */
 	if (!drm->vbios.fp_no_ddc) {
 		status = nouveau_connector_detect(connector, force);
-		if (status == connector_status_connected)
+		if (status == connector_status_connected) {
+			edid = nv_connector->edid;
 			goto out;
+		}
 	}
 
 	/* On some laptops (Sony, i'm looking at you) there appears to
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 37d4cb7..0fc0841 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -626,6 +626,7 @@
 err_out1:
 	pm_runtime_disable(pfdev->dev);
 	panfrost_device_fini(pfdev);
+	pm_runtime_set_suspended(pfdev->dev);
 err_out0:
 	drm_dev_put(ddev);
 	return err;
@@ -640,9 +641,9 @@
 	panfrost_gem_shrinker_cleanup(ddev);
 
 	pm_runtime_get_sync(pfdev->dev);
-	panfrost_device_fini(pfdev);
-	pm_runtime_put_sync_suspend(pfdev->dev);
 	pm_runtime_disable(pfdev->dev);
+	panfrost_device_fini(pfdev);
+	pm_runtime_set_suspended(pfdev->dev);
 
 	drm_dev_put(ddev);
 	return 0;
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index 1a6cea0..62d4d71 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -105,14 +105,12 @@
 	kref_put(&mapping->refcount, panfrost_gem_mapping_release);
 }
 
-void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo)
+void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo)
 {
 	struct panfrost_gem_mapping *mapping;
 
-	mutex_lock(&bo->mappings.lock);
 	list_for_each_entry(mapping, &bo->mappings.list, node)
 		panfrost_gem_teardown_mapping(mapping);
-	mutex_unlock(&bo->mappings.lock);
 }
 
 int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv)
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h
index b3517ff..8088d5f 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.h
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.h
@@ -82,7 +82,7 @@
 panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
 			 struct panfrost_file_priv *priv);
 void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping);
-void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo);
+void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo);
 
 void panfrost_gem_shrinker_init(struct drm_device *dev);
 void panfrost_gem_shrinker_cleanup(struct drm_device *dev);
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
index 288e46c..1b9f68d 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
@@ -40,18 +40,26 @@
 {
 	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
 	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
+	bool ret = false;
 
 	if (atomic_read(&bo->gpu_usecount))
 		return false;
 
-	if (!mutex_trylock(&shmem->pages_lock))
+	if (!mutex_trylock(&bo->mappings.lock))
 		return false;
 
-	panfrost_gem_teardown_mappings(bo);
+	if (!mutex_trylock(&shmem->pages_lock))
+		goto unlock_mappings;
+
+	panfrost_gem_teardown_mappings_locked(bo);
 	drm_gem_shmem_purge_locked(obj);
+	ret = true;
 
 	mutex_unlock(&shmem->pages_lock);
-	return true;
+
+unlock_mappings:
+	mutex_unlock(&bo->mappings.lock);
+	return ret;
 }
 
 static unsigned long
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 74ceebd..cc74a3f 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -449,7 +449,7 @@
 	}
 
 	if (IS_ERR(cma_obj)) {
-		struct drm_printer p = drm_info_printer(vc4->dev->dev);
+		struct drm_printer p = drm_info_printer(vc4->base.dev);
 		DRM_ERROR("Failed to allocate from CMA:\n");
 		vc4_bo_stats_print(&p, vc4);
 		return ERR_PTR(-ENOMEM);
@@ -590,7 +590,7 @@
 {
 	struct vc4_dev *vc4 =
 		container_of(work, struct vc4_dev, bo_cache.time_work);
-	struct drm_device *dev = vc4->dev;
+	struct drm_device *dev = &vc4->base;
 
 	mutex_lock(&vc4->bo_lock);
 	vc4_bo_cache_free_old(dev);
@@ -1005,6 +1005,7 @@
 	return 0;
 }
 
+static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused);
 int vc4_bo_cache_init(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
@@ -1033,10 +1034,10 @@
 	INIT_WORK(&vc4->bo_cache.time_work, vc4_bo_cache_time_work);
 	timer_setup(&vc4->bo_cache.time_timer, vc4_bo_cache_time_timer, 0);
 
-	return 0;
+	return drmm_add_action_or_reset(dev, vc4_bo_cache_destroy, NULL);
 }
 
-void vc4_bo_cache_destroy(struct drm_device *dev)
+static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	int i;
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index a17aa1d..839610f 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -257,37 +257,37 @@
 
 	dev->coherent_dma_mask = DMA_BIT_MASK(32);
 
-	vc4 = devm_kzalloc(dev, sizeof(*vc4), GFP_KERNEL);
-	if (!vc4)
-		return -ENOMEM;
-
 	/* If VC4 V3D is missing, don't advertise render nodes. */
 	node = of_find_matching_node_and_match(NULL, vc4_v3d_dt_match, NULL);
 	if (!node || !of_device_is_available(node))
 		vc4_drm_driver.driver_features &= ~DRIVER_RENDER;
 	of_node_put(node);
 
-	drm = drm_dev_alloc(&vc4_drm_driver, dev);
-	if (IS_ERR(drm))
-		return PTR_ERR(drm);
+	vc4 = devm_drm_dev_alloc(dev, &vc4_drm_driver, struct vc4_dev, base);
+	if (IS_ERR(vc4))
+		return PTR_ERR(vc4);
+
+	drm = &vc4->base;
 	platform_set_drvdata(pdev, drm);
-	vc4->dev = drm;
-	drm->dev_private = vc4;
 	INIT_LIST_HEAD(&vc4->debugfs_list);
 
 	mutex_init(&vc4->bin_bo_lock);
 
 	ret = vc4_bo_cache_init(drm);
 	if (ret)
-		goto dev_put;
+		return ret;
 
-	drm_mode_config_init(drm);
+	ret = drmm_mode_config_init(drm);
+	if (ret)
+		return ret;
 
-	vc4_gem_init(drm);
+	ret = vc4_gem_init(drm);
+	if (ret)
+		return ret;
 
 	ret = component_bind_all(dev, drm);
 	if (ret)
-		goto gem_destroy;
+		return ret;
 
 	ret = vc4_plane_create_additional_planes(drm);
 	if (ret)
@@ -312,30 +312,17 @@
 
 unbind_all:
 	component_unbind_all(dev, drm);
-gem_destroy:
-	vc4_gem_destroy(drm);
-	drm_mode_config_cleanup(drm);
-	vc4_bo_cache_destroy(drm);
-dev_put:
-	drm_dev_put(drm);
+
 	return ret;
 }
 
 static void vc4_drm_unbind(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct vc4_dev *vc4 = to_vc4_dev(drm);
 
 	drm_dev_unregister(drm);
 
 	drm_atomic_helper_shutdown(drm);
-
-	drm_mode_config_cleanup(drm);
-
-	drm_atomic_private_obj_fini(&vc4->load_tracker);
-	drm_atomic_private_obj_fini(&vc4->ctm_manager);
-
-	drm_dev_put(drm);
 }
 
 static const struct component_master_ops vc4_drm_ops = {
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 66d4fb1..19b75be 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -14,6 +14,7 @@
 #include <drm/drm_device.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_managed.h>
 #include <drm/drm_mm.h>
 #include <drm/drm_modeset_lock.h>
 
@@ -71,7 +72,7 @@
 };
 
 struct vc4_dev {
-	struct drm_device *dev;
+	struct drm_device base;
 
 	struct vc4_hvs *hvs;
 	struct vc4_v3d *v3d;
@@ -234,7 +235,7 @@
 static inline struct vc4_dev *
 to_vc4_dev(struct drm_device *dev)
 {
-	return (struct vc4_dev *)dev->dev_private;
+	return container_of(dev, struct vc4_dev, base);
 }
 
 struct vc4_bo {
@@ -809,7 +810,6 @@
 						 struct sg_table *sgt);
 void *vc4_prime_vmap(struct drm_gem_object *obj);
 int vc4_bo_cache_init(struct drm_device *dev);
-void vc4_bo_cache_destroy(struct drm_device *dev);
 int vc4_bo_inc_usecnt(struct vc4_bo *bo);
 void vc4_bo_dec_usecnt(struct vc4_bo *bo);
 void vc4_bo_add_to_purgeable_pool(struct vc4_bo *bo);
@@ -874,8 +874,7 @@
 extern const struct dma_fence_ops vc4_fence_ops;
 
 /* vc4_gem.c */
-void vc4_gem_init(struct drm_device *dev);
-void vc4_gem_destroy(struct drm_device *dev);
+int vc4_gem_init(struct drm_device *dev);
 int vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 int vc4_wait_seqno_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 9f01ddd..b641252 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -314,16 +314,16 @@
 	struct vc4_dev *vc4 =
 		container_of(work, struct vc4_dev, hangcheck.reset_work);
 
-	vc4_save_hang_state(vc4->dev);
+	vc4_save_hang_state(&vc4->base);
 
-	vc4_reset(vc4->dev);
+	vc4_reset(&vc4->base);
 }
 
 static void
 vc4_hangcheck_elapsed(struct timer_list *t)
 {
 	struct vc4_dev *vc4 = from_timer(vc4, t, hangcheck.timer);
-	struct drm_device *dev = vc4->dev;
+	struct drm_device *dev = &vc4->base;
 	uint32_t ct0ca, ct1ca;
 	unsigned long irqflags;
 	struct vc4_exec_info *bin_exec, *render_exec;
@@ -1000,7 +1000,7 @@
 		list_del(&exec->head);
 
 		spin_unlock_irqrestore(&vc4->job_lock, irqflags);
-		vc4_complete_exec(vc4->dev, exec);
+		vc4_complete_exec(&vc4->base, exec);
 		spin_lock_irqsave(&vc4->job_lock, irqflags);
 	}
 
@@ -1258,13 +1258,13 @@
 	return 0;
 
 fail:
-	vc4_complete_exec(vc4->dev, exec);
+	vc4_complete_exec(&vc4->base, exec);
 
 	return ret;
 }
 
-void
-vc4_gem_init(struct drm_device *dev)
+static void vc4_gem_destroy(struct drm_device *dev, void *unused);
+int vc4_gem_init(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
@@ -1285,10 +1285,11 @@
 
 	INIT_LIST_HEAD(&vc4->purgeable.list);
 	mutex_init(&vc4->purgeable.lock);
+
+	return drmm_add_action_or_reset(dev, vc4_gem_destroy, NULL);
 }
 
-void
-vc4_gem_destroy(struct drm_device *dev)
+static void vc4_gem_destroy(struct drm_device *dev, void *unused)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index 4d0a833..b72b2bd 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -560,7 +560,7 @@
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct drm_device *drm = dev_get_drvdata(master);
-	struct vc4_dev *vc4 = drm->dev_private;
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_hvs *hvs = NULL;
 	int ret;
 	u32 dispctrl;
@@ -679,7 +679,7 @@
 			   void *data)
 {
 	struct drm_device *drm = dev_get_drvdata(master);
-	struct vc4_dev *vc4 = drm->dev_private;
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_hvs *hvs = vc4->hvs;
 
 	if (drm_mm_node_allocated(&vc4->hvs->mitchell_netravali_filter))
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index 149825f..2b951ca 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -51,7 +51,7 @@
 					       struct drm_private_obj *manager)
 {
 	struct drm_device *dev = state->dev;
-	struct vc4_dev *vc4 = dev->dev_private;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_private_state *priv_state;
 	int ret;
 
@@ -93,6 +93,29 @@
 	.atomic_destroy_state = vc4_ctm_destroy_state,
 };
 
+static void vc4_ctm_obj_fini(struct drm_device *dev, void *unused)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+	drm_atomic_private_obj_fini(&vc4->ctm_manager);
+}
+
+static int vc4_ctm_obj_init(struct vc4_dev *vc4)
+{
+	struct vc4_ctm_state *ctm_state;
+
+	drm_modeset_lock_init(&vc4->ctm_state_lock);
+
+	ctm_state = kzalloc(sizeof(*ctm_state), GFP_KERNEL);
+	if (!ctm_state)
+		return -ENOMEM;
+
+	drm_atomic_private_obj_init(&vc4->base, &vc4->ctm_manager, &ctm_state->base,
+				    &vc4_ctm_state_funcs);
+
+	return drmm_add_action(&vc4->base, vc4_ctm_obj_fini, NULL);
+}
+
 /* Converts a DRM S31.32 value to the HW S0.9 format. */
 static u16 vc4_ctm_s31_32_to_s0_9(u64 in)
 {
@@ -609,6 +632,34 @@
 	.atomic_destroy_state = vc4_load_tracker_destroy_state,
 };
 
+static void vc4_load_tracker_obj_fini(struct drm_device *dev, void *unused)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+	if (!vc4->load_tracker_available)
+		return;
+
+	drm_atomic_private_obj_fini(&vc4->load_tracker);
+}
+
+static int vc4_load_tracker_obj_init(struct vc4_dev *vc4)
+{
+	struct vc4_load_tracker_state *load_state;
+
+	if (!vc4->load_tracker_available)
+		return 0;
+
+	load_state = kzalloc(sizeof(*load_state), GFP_KERNEL);
+	if (!load_state)
+		return -ENOMEM;
+
+	drm_atomic_private_obj_init(&vc4->base, &vc4->load_tracker,
+				    &load_state->base,
+				    &vc4_load_tracker_state_funcs);
+
+	return drmm_add_action(&vc4->base, vc4_load_tracker_obj_fini, NULL);
+}
+
 #define NUM_OUTPUTS  6
 #define NUM_CHANNELS 3
 
@@ -711,8 +762,6 @@
 int vc4_kms_load(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
-	struct vc4_ctm_state *ctm_state;
-	struct vc4_load_tracker_state *load_state;
 	bool is_vc5 = of_device_is_compatible(dev->dev->of_node,
 					      "brcm,bcm2711-vc5");
 	int ret;
@@ -751,26 +800,13 @@
 	dev->mode_config.async_page_flip = true;
 	dev->mode_config.allow_fb_modifiers = true;
 
-	drm_modeset_lock_init(&vc4->ctm_state_lock);
+	ret = vc4_ctm_obj_init(vc4);
+	if (ret)
+		return ret;
 
-	ctm_state = kzalloc(sizeof(*ctm_state), GFP_KERNEL);
-	if (!ctm_state)
-		return -ENOMEM;
-
-	drm_atomic_private_obj_init(dev, &vc4->ctm_manager, &ctm_state->base,
-				    &vc4_ctm_state_funcs);
-
-	if (vc4->load_tracker_available) {
-		load_state = kzalloc(sizeof(*load_state), GFP_KERNEL);
-		if (!load_state) {
-			drm_atomic_private_obj_fini(&vc4->ctm_manager);
-			return -ENOMEM;
-		}
-
-		drm_atomic_private_obj_init(dev, &vc4->load_tracker,
-					    &load_state->base,
-					    &vc4_load_tracker_state_funcs);
-	}
+	ret = vc4_load_tracker_obj_init(vc4);
+	if (ret)
+		return ret;
 
 	drm_mode_config_reset(dev);
 
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index f7ab979..65d0dac 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -168,7 +168,7 @@
 
 int vc4_v3d_get_bin_slot(struct vc4_dev *vc4)
 {
-	struct drm_device *dev = vc4->dev;
+	struct drm_device *dev = &vc4->base;
 	unsigned long irqflags;
 	int slot;
 	uint64_t seqno = 0;
@@ -246,7 +246,7 @@
 	INIT_LIST_HEAD(&list);
 
 	while (true) {
-		struct vc4_bo *bo = vc4_bo_create(vc4->dev, size, true,
+		struct vc4_bo *bo = vc4_bo_create(&vc4->base, size, true,
 						  VC4_BO_TYPE_BIN);
 
 		if (IS_ERR(bo)) {
@@ -361,7 +361,7 @@
 	struct vc4_v3d *v3d = dev_get_drvdata(dev);
 	struct vc4_dev *vc4 = v3d->vc4;
 
-	vc4_irq_uninstall(vc4->dev);
+	vc4_irq_uninstall(&vc4->base);
 
 	clk_disable_unprepare(v3d->clk);
 
@@ -378,11 +378,11 @@
 	if (ret != 0)
 		return ret;
 
-	vc4_v3d_init_hw(vc4->dev);
+	vc4_v3d_init_hw(&vc4->base);
 
 	/* We disabled the IRQ as part of vc4_irq_uninstall in suspend. */
-	enable_irq(vc4->dev->irq);
-	vc4_irq_postinstall(vc4->dev);
+	enable_irq(vc4->base.irq);
+	vc4_irq_postinstall(&vc4->base);
 
 	return 0;
 }
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index b3dae9e..d166ee2 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -133,73 +133,6 @@
 }
 EXPORT_SYMBOL_GPL(ipu_pixelformat_to_colorspace);
 
-bool ipu_pixelformat_is_planar(u32 pixelformat)
-{
-	switch (pixelformat) {
-	case V4L2_PIX_FMT_YUV420:
-	case V4L2_PIX_FMT_YVU420:
-	case V4L2_PIX_FMT_YUV422P:
-	case V4L2_PIX_FMT_NV12:
-	case V4L2_PIX_FMT_NV21:
-	case V4L2_PIX_FMT_NV16:
-	case V4L2_PIX_FMT_NV61:
-		return true;
-	}
-
-	return false;
-}
-EXPORT_SYMBOL_GPL(ipu_pixelformat_is_planar);
-
-enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code)
-{
-	switch (mbus_code & 0xf000) {
-	case 0x1000:
-		return IPUV3_COLORSPACE_RGB;
-	case 0x2000:
-		return IPUV3_COLORSPACE_YUV;
-	default:
-		return IPUV3_COLORSPACE_UNKNOWN;
-	}
-}
-EXPORT_SYMBOL_GPL(ipu_mbus_code_to_colorspace);
-
-int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat)
-{
-	switch (pixelformat) {
-	case V4L2_PIX_FMT_YUV420:
-	case V4L2_PIX_FMT_YVU420:
-	case V4L2_PIX_FMT_YUV422P:
-	case V4L2_PIX_FMT_NV12:
-	case V4L2_PIX_FMT_NV21:
-	case V4L2_PIX_FMT_NV16:
-	case V4L2_PIX_FMT_NV61:
-		/*
-		 * for the planar YUV formats, the stride passed to
-		 * cpmem must be the stride in bytes of the Y plane.
-		 * And all the planar YUV formats have an 8-bit
-		 * Y component.
-		 */
-		return (8 * pixel_stride) >> 3;
-	case V4L2_PIX_FMT_RGB565:
-	case V4L2_PIX_FMT_YUYV:
-	case V4L2_PIX_FMT_UYVY:
-		return (16 * pixel_stride) >> 3;
-	case V4L2_PIX_FMT_BGR24:
-	case V4L2_PIX_FMT_RGB24:
-		return (24 * pixel_stride) >> 3;
-	case V4L2_PIX_FMT_BGR32:
-	case V4L2_PIX_FMT_RGB32:
-	case V4L2_PIX_FMT_XBGR32:
-	case V4L2_PIX_FMT_XRGB32:
-		return (32 * pixel_stride) >> 3;
-	default:
-		break;
-	}
-
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(ipu_stride_to_bytes);
-
 int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
 			    bool hflip, bool vflip)
 {
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 0cde10f..f202ac7 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -244,9 +244,13 @@
 
 	/*
 	 * Hyper-V does not provide a way to change the connect CPU once
-	 * it is set; we must prevent the connect CPU from going offline.
+	 * it is set; we must prevent the connect CPU from going offline
+	 * while the VM is running normally. But in the panic or kexec()
+	 * path where the vmbus is already disconnected, the CPU must be
+	 * allowed to shut down.
 	 */
-	if (cpu == VMBUS_CONNECT_CPU)
+	if (cpu == VMBUS_CONNECT_CPU &&
+	    vmbus_connection.conn_state == CONNECTED)
 		return -EBUSY;
 
 	/*
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index b64d2ef..eb56e09 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -1275,7 +1275,7 @@
 
 	/* Refuse to balloon below the floor. */
 	if (avail_pages < num_pages || avail_pages - num_pages < floor) {
-		pr_warn("Balloon request will be partially fulfilled. %s\n",
+		pr_info("Balloon request will be partially fulfilled. %s\n",
 			avail_pages < num_pages ? "Not enough memory." :
 			"Balloon floor reached.");
 
diff --git a/drivers/hwmon/amd_energy.c b/drivers/hwmon/amd_energy.c
index d065973..3197cda 100644
--- a/drivers/hwmon/amd_energy.c
+++ b/drivers/hwmon/amd_energy.c
@@ -171,7 +171,7 @@
 				     enum hwmon_sensor_types type,
 				     u32 attr, int channel)
 {
-	return 0444;
+	return 0440;
 }
 
 static int energy_accumulator(void *p)
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index a188879..79b498f 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -32,6 +32,7 @@
 #include <linux/hwmon.h>
 #include <linux/workqueue.h>
 #include <linux/err.h>
+#include <linux/bits.h>
 
 /* data port used by Apple SMC */
 #define APPLESMC_DATA_PORT	0x300
@@ -42,10 +43,13 @@
 
 #define APPLESMC_MAX_DATA_LENGTH 32
 
-/* wait up to 128 ms for a status change. */
-#define APPLESMC_MIN_WAIT	0x0010
-#define APPLESMC_RETRY_WAIT	0x0100
-#define APPLESMC_MAX_WAIT	0x20000
+/* Apple SMC status bits */
+#define SMC_STATUS_AWAITING_DATA  BIT(0) /* SMC has data waiting to be read */
+#define SMC_STATUS_IB_CLOSED      BIT(1) /* Will ignore any input */
+#define SMC_STATUS_BUSY           BIT(2) /* Command in progress */
+
+/* Initial wait is 8us */
+#define APPLESMC_MIN_WAIT      0x0008
 
 #define APPLESMC_READ_CMD	0x10
 #define APPLESMC_WRITE_CMD	0x11
@@ -151,65 +155,84 @@
 static struct workqueue_struct *applesmc_led_wq;
 
 /*
- * wait_read - Wait for a byte to appear on SMC port. Callers must
- * hold applesmc_lock.
+ * Wait for specific status bits with a mask on the SMC.
+ * Used before all transactions.
+ * This does 10 fast loops of 8us then exponentially backs off for a
+ * minimum total wait of 262ms. Depending on usleep_range this could
+ * run out past 500ms.
  */
-static int wait_read(void)
+
+static int wait_status(u8 val, u8 mask)
 {
-	unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC;
 	u8 status;
 	int us;
+	int i;
 
-	for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) {
-		usleep_range(us, us * 16);
+	us = APPLESMC_MIN_WAIT;
+	for (i = 0; i < 24 ; i++) {
 		status = inb(APPLESMC_CMD_PORT);
-		/* read: wait for smc to settle */
-		if (status & 0x01)
+		if ((status & mask) == val)
 			return 0;
-		/* timeout: give up */
-		if (time_after(jiffies, end))
-			break;
+		usleep_range(us, us * 2);
+		if (i > 9)
+			us <<= 1;
 	}
-
-	pr_warn("wait_read() fail: 0x%02x\n", status);
 	return -EIO;
 }
 
-/*
- * send_byte - Write to SMC port, retrying when necessary. Callers
- * must hold applesmc_lock.
- */
+/* send_byte - Write to SMC data port. Callers must hold applesmc_lock. */
+
 static int send_byte(u8 cmd, u16 port)
 {
-	u8 status;
-	int us;
-	unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC;
+	int status;
+
+	status = wait_status(0, SMC_STATUS_IB_CLOSED);
+	if (status)
+		return status;
+	/*
+	 * This needs to be a separate read looking for bit 0x04
+	 * after bit 0x02 falls. If consolidated with the wait above
+	 * this extra read may not happen if status returns both
+	 * simultaneously and this would appear to be required.
+	 */
+	status = wait_status(SMC_STATUS_BUSY, SMC_STATUS_BUSY);
+	if (status)
+		return status;
 
 	outb(cmd, port);
-	for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) {
-		usleep_range(us, us * 16);
-		status = inb(APPLESMC_CMD_PORT);
-		/* write: wait for smc to settle */
-		if (status & 0x02)
-			continue;
-		/* ready: cmd accepted, return */
-		if (status & 0x04)
-			return 0;
-		/* timeout: give up */
-		if (time_after(jiffies, end))
-			break;
-		/* busy: long wait and resend */
-		udelay(APPLESMC_RETRY_WAIT);
-		outb(cmd, port);
-	}
-
-	pr_warn("send_byte(0x%02x, 0x%04x) fail: 0x%02x\n", cmd, port, status);
-	return -EIO;
+	return 0;
 }
 
+/* send_command - Write a command to the SMC. Callers must hold applesmc_lock. */
+
 static int send_command(u8 cmd)
 {
-	return send_byte(cmd, APPLESMC_CMD_PORT);
+	int ret;
+
+	ret = wait_status(0, SMC_STATUS_IB_CLOSED);
+	if (ret)
+		return ret;
+	outb(cmd, APPLESMC_CMD_PORT);
+	return 0;
+}
+
+/*
+ * Based on logic from the Apple driver. This is issued before any interaction
+ * If busy is stuck high, issue a read command to reset the SMC state machine.
+ * If busy is stuck high after the command then the SMC is jammed.
+ */
+
+static int smc_sane(void)
+{
+	int ret;
+
+	ret = wait_status(0, SMC_STATUS_BUSY);
+	if (!ret)
+		return ret;
+	ret = send_command(APPLESMC_READ_CMD);
+	if (ret)
+		return ret;
+	return wait_status(0, SMC_STATUS_BUSY);
 }
 
 static int send_argument(const char *key)
@@ -226,6 +249,11 @@
 {
 	u8 status, data = 0;
 	int i;
+	int ret;
+
+	ret = smc_sane();
+	if (ret)
+		return ret;
 
 	if (send_command(cmd) || send_argument(key)) {
 		pr_warn("%.4s: read arg fail\n", key);
@@ -239,7 +267,8 @@
 	}
 
 	for (i = 0; i < len; i++) {
-		if (wait_read()) {
+		if (wait_status(SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY,
+				SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY)) {
 			pr_warn("%.4s: read data[%d] fail\n", key, i);
 			return -EIO;
 		}
@@ -250,19 +279,24 @@
 	for (i = 0; i < 16; i++) {
 		udelay(APPLESMC_MIN_WAIT);
 		status = inb(APPLESMC_CMD_PORT);
-		if (!(status & 0x01))
+		if (!(status & SMC_STATUS_AWAITING_DATA))
 			break;
 		data = inb(APPLESMC_DATA_PORT);
 	}
 	if (i)
 		pr_warn("flushed %d bytes, last value is: %d\n", i, data);
 
-	return 0;
+	return wait_status(0, SMC_STATUS_BUSY);
 }
 
 static int write_smc(u8 cmd, const char *key, const u8 *buffer, u8 len)
 {
 	int i;
+	int ret;
+
+	ret = smc_sane();
+	if (ret)
+		return ret;
 
 	if (send_command(cmd) || send_argument(key)) {
 		pr_warn("%s: write arg fail\n", key);
@@ -281,7 +315,7 @@
 		}
 	}
 
-	return 0;
+	return wait_status(0, SMC_STATUS_BUSY);
 }
 
 static int read_register_count(unsigned int *count)
diff --git a/drivers/hwmon/pmbus/max20730.c b/drivers/hwmon/pmbus/max20730.c
index 57923d7..be83b98 100644
--- a/drivers/hwmon/pmbus/max20730.c
+++ b/drivers/hwmon/pmbus/max20730.c
@@ -122,8 +122,8 @@
 	switch (idx) {
 	case MAX20730_DEBUGFS_VOUT_MIN:
 		ret = VOLT_FROM_REG(data->mfr_voutmin * 10000);
-		len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n",
-			       ret / 10000, ret % 10000);
+		len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n",
+				ret / 10000, ret % 10000);
 		break;
 	case MAX20730_DEBUGFS_FREQUENCY:
 		val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_FSW_MASK)
@@ -141,7 +141,7 @@
 			ret = 800;
 		else
 			ret = 900;
-		len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+		len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
 		break;
 	case MAX20730_DEBUGFS_PG_DELAY:
 		val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_TSTAT_MASK)
@@ -223,7 +223,7 @@
 	case MAX20730_DEBUGFS_OC_PROTECT_MODE:
 		ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_OCPM_MASK)
 			>> MAX20730_MFR_DEVSET2_OCPM_BIT_POS;
-		len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+		len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
 		break;
 	case MAX20730_DEBUGFS_SS_TIMING:
 		val = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_SS_MASK)
@@ -241,32 +241,32 @@
 	case MAX20730_DEBUGFS_IMAX:
 		ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_IMAX_MASK)
 			>> MAX20730_MFR_DEVSET2_IMAX_BIT_POS;
-		len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+		len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
 		break;
 	case MAX20730_DEBUGFS_OPERATION:
 		ret = i2c_smbus_read_byte_data(psu->client, PMBUS_OPERATION);
 		if (ret < 0)
 			return ret;
-		len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+		len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
 		break;
 	case MAX20730_DEBUGFS_ON_OFF_CONFIG:
 		ret = i2c_smbus_read_byte_data(psu->client, PMBUS_ON_OFF_CONFIG);
 		if (ret < 0)
 			return ret;
-		len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+		len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
 		break;
 	case MAX20730_DEBUGFS_SMBALERT_MASK:
 		ret = i2c_smbus_read_word_data(psu->client,
 					       PMBUS_SMB_ALERT_MASK);
 		if (ret < 0)
 			return ret;
-		len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+		len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
 		break;
 	case MAX20730_DEBUGFS_VOUT_MODE:
 		ret = i2c_smbus_read_byte_data(psu->client, PMBUS_VOUT_MODE);
 		if (ret < 0)
 			return ret;
-		len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+		len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
 		break;
 	case MAX20730_DEBUGFS_VOUT_COMMAND:
 		ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_COMMAND);
@@ -274,8 +274,8 @@
 			return ret;
 
 		ret = VOLT_FROM_REG(ret * 10000);
-		len = snprintf(tbuf, DEBUG_FS_DATA_MAX,
-			       "%d.%d\n", ret / 10000, ret % 10000);
+		len = scnprintf(tbuf, DEBUG_FS_DATA_MAX,
+				"%d.%d\n", ret / 10000, ret % 10000);
 		break;
 	case MAX20730_DEBUGFS_VOUT_MAX:
 		ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_MAX);
@@ -283,8 +283,8 @@
 			return ret;
 
 		ret = VOLT_FROM_REG(ret * 10000);
-		len = snprintf(tbuf, DEBUG_FS_DATA_MAX,
-			       "%d.%d\n", ret / 10000, ret % 10000);
+		len = scnprintf(tbuf, DEBUG_FS_DATA_MAX,
+				"%d.%d\n", ret / 10000, ret % 10000);
 		break;
 	default:
 		len = strlcpy(tbuf, "Invalid\n", DEBUG_FS_DATA_MAX);
diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index 170a9f8..b0e2820 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -941,12 +941,16 @@
 	struct i2c_client *client = to_i2c_client(dev->parent);
 	struct pmbus_sensor *sensor = to_pmbus_sensor(devattr);
 	struct pmbus_data *data = i2c_get_clientdata(client);
+	ssize_t ret;
 
+	mutex_lock(&data->update_lock);
 	pmbus_update_sensor_data(client, sensor);
 	if (sensor->data < 0)
-		return sensor->data;
-
-	return snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor));
+		ret = sensor->data;
+	else
+		ret = snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor));
+	mutex_unlock(&data->update_lock);
+	return ret;
 }
 
 static ssize_t pmbus_set_sensor(struct device *dev,
@@ -2012,8 +2016,11 @@
 	int val;
 	struct i2c_client *client = to_i2c_client(dev->parent);
 	struct pmbus_samples_reg *reg = to_samples_reg(devattr);
+	struct pmbus_data *data = i2c_get_clientdata(client);
 
+	mutex_lock(&data->update_lock);
 	val = _pmbus_read_word_data(client, reg->page, 0xff, reg->attr->reg);
+	mutex_unlock(&data->update_lock);
 	if (val < 0)
 		return val;
 
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index bdba214..1f63807 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -54,16 +54,18 @@
 static void sample_timer(struct timer_list *t)
 {
 	struct pwm_fan_ctx *ctx = from_timer(ctx, t, rpm_timer);
+	unsigned int delta = ktime_ms_delta(ktime_get(), ctx->sample_start);
 	int pulses;
-	u64 tmp;
 
-	pulses = atomic_read(&ctx->pulses);
-	atomic_sub(pulses, &ctx->pulses);
-	tmp = (u64)pulses * ktime_ms_delta(ktime_get(), ctx->sample_start) * 60;
-	do_div(tmp, ctx->pulses_per_revolution * 1000);
-	ctx->rpm = tmp;
+	if (delta) {
+		pulses = atomic_read(&ctx->pulses);
+		atomic_sub(pulses, &ctx->pulses);
+		ctx->rpm = (unsigned int)(pulses * 1000 * 60) /
+			(ctx->pulses_per_revolution * delta);
 
-	ctx->sample_start = ktime_get();
+		ctx->sample_start = ktime_get();
+	}
+
 	mod_timer(&ctx->rpm_timer, jiffies + HZ);
 }
 
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index a4f473e..a97a9d0 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -733,7 +733,7 @@
 
 config I2C_MLXBF
         tristate "Mellanox BlueField I2C controller"
-        depends on ARM64
+        depends on MELLANOX_PLATFORM && ARM64
         help
           Enabling this option will add I2C SMBus support for Mellanox BlueField
           system.
diff --git a/drivers/i2c/busses/i2c-designware-slave.c b/drivers/i2c/busses/i2c-designware-slave.c
index 44974b5..0d15f4c 100644
--- a/drivers/i2c/busses/i2c-designware-slave.c
+++ b/drivers/i2c/busses/i2c-designware-slave.c
@@ -159,7 +159,6 @@
 	u32 raw_stat, stat, enabled, tmp;
 	u8 val = 0, slave_activity;
 
-	regmap_read(dev->map, DW_IC_INTR_STAT, &stat);
 	regmap_read(dev->map, DW_IC_ENABLE, &enabled);
 	regmap_read(dev->map, DW_IC_RAW_INTR_STAT, &raw_stat);
 	regmap_read(dev->map, DW_IC_STATUS, &tmp);
@@ -168,32 +167,30 @@
 	if (!enabled || !(raw_stat & ~DW_IC_INTR_ACTIVITY) || !dev->slave)
 		return 0;
 
+	stat = i2c_dw_read_clear_intrbits_slave(dev);
 	dev_dbg(dev->dev,
 		"%#x STATUS SLAVE_ACTIVITY=%#x : RAW_INTR_STAT=%#x : INTR_STAT=%#x\n",
 		enabled, slave_activity, raw_stat, stat);
 
-	if ((stat & DW_IC_INTR_RX_FULL) && (stat & DW_IC_INTR_STOP_DET))
-		i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_REQUESTED, &val);
+	if (stat & DW_IC_INTR_RX_FULL) {
+		if (dev->status != STATUS_WRITE_IN_PROGRESS) {
+			dev->status = STATUS_WRITE_IN_PROGRESS;
+			i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_REQUESTED,
+					&val);
+		}
+
+		regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
+		val = tmp;
+		if (!i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_RECEIVED,
+				     &val))
+			dev_vdbg(dev->dev, "Byte %X acked!", val);
+	}
 
 	if (stat & DW_IC_INTR_RD_REQ) {
 		if (slave_activity) {
-			if (stat & DW_IC_INTR_RX_FULL) {
-				regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
-				val = tmp;
+			regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp);
 
-				if (!i2c_slave_event(dev->slave,
-						     I2C_SLAVE_WRITE_RECEIVED,
-						     &val)) {
-					dev_vdbg(dev->dev, "Byte %X acked!",
-						 val);
-				}
-				regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp);
-				stat = i2c_dw_read_clear_intrbits_slave(dev);
-			} else {
-				regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp);
-				regmap_read(dev->map, DW_IC_CLR_RX_UNDER, &tmp);
-				stat = i2c_dw_read_clear_intrbits_slave(dev);
-			}
+			dev->status = STATUS_READ_IN_PROGRESS;
 			if (!i2c_slave_event(dev->slave,
 					     I2C_SLAVE_READ_REQUESTED,
 					     &val))
@@ -205,21 +202,11 @@
 		if (!i2c_slave_event(dev->slave, I2C_SLAVE_READ_PROCESSED,
 				     &val))
 			regmap_read(dev->map, DW_IC_CLR_RX_DONE, &tmp);
-
-		i2c_slave_event(dev->slave, I2C_SLAVE_STOP, &val);
-		stat = i2c_dw_read_clear_intrbits_slave(dev);
-		return 1;
 	}
 
-	if (stat & DW_IC_INTR_RX_FULL) {
-		regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
-		val = tmp;
-		if (!i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_RECEIVED,
-				     &val))
-			dev_vdbg(dev->dev, "Byte %X acked!", val);
-	} else {
+	if (stat & DW_IC_INTR_STOP_DET) {
+		dev->status = STATUS_IDLE;
 		i2c_slave_event(dev->slave, I2C_SLAVE_STOP, &val);
-		stat = i2c_dw_read_clear_intrbits_slave(dev);
 	}
 
 	return 1;
@@ -230,7 +217,6 @@
 	struct dw_i2c_dev *dev = dev_id;
 	int ret;
 
-	i2c_dw_read_clear_intrbits_slave(dev);
 	ret = i2c_dw_irq_handler_slave(dev);
 	if (ret > 0)
 		complete(&dev->cmd_complete);
diff --git a/drivers/i2c/busses/i2c-mlxbf.c b/drivers/i2c/busses/i2c-mlxbf.c
index ee59e0d..33574d4 100644
--- a/drivers/i2c/busses/i2c-mlxbf.c
+++ b/drivers/i2c/busses/i2c-mlxbf.c
@@ -62,10 +62,8 @@
  * Master. Default value is set to 400MHz.
  */
 #define MLXBF_I2C_TYU_PLL_OUT_FREQ  (400 * 1000 * 1000)
-/* Reference clock for Bluefield 1 - 156 MHz. */
-#define MLXBF_I2C_TYU_PLL_IN_FREQ   (156 * 1000 * 1000)
-/* Reference clock for BlueField 2 - 200 MHz. */
-#define MLXBF_I2C_YU_PLL_IN_FREQ    (200 * 1000 * 1000)
+/* Reference clock for Bluefield - 156 MHz. */
+#define MLXBF_I2C_PLL_IN_FREQ       (156 * 1000 * 1000)
 
 /* Constant used to determine the PLL frequency. */
 #define MLNXBF_I2C_COREPLL_CONST    16384
@@ -489,44 +487,6 @@
 
 #define MLXBF_I2C_FREQUENCY_1GHZ  1000000000
 
-static void mlxbf_i2c_write(void __iomem *io, int reg, u32 val)
-{
-	writel(val, io + reg);
-}
-
-static u32 mlxbf_i2c_read(void __iomem *io, int reg)
-{
-	return readl(io + reg);
-}
-
-/*
- * This function is used to read data from Master GW Data Descriptor.
- * Data bytes in the Master GW Data Descriptor are shifted left so the
- * data starts at the MSB of the descriptor registers as set by the
- * underlying hardware. TYU_READ_DATA enables byte swapping while
- * reading data bytes, and MUST be called by the SMBus read routines
- * to copy data from the 32 * 32-bit HW Data registers a.k.a Master GW
- * Data Descriptor.
- */
-static u32 mlxbf_i2c_read_data(void __iomem *io, int reg)
-{
-	return (u32)be32_to_cpu(mlxbf_i2c_read(io, reg));
-}
-
-/*
- * This function is used to write data to the Master GW Data Descriptor.
- * Data copied to the Master GW Data Descriptor MUST be shifted left so
- * the data starts at the MSB of the descriptor registers as required by
- * the underlying hardware. TYU_WRITE_DATA enables byte swapping when
- * writing data bytes, and MUST be called by the SMBus write routines to
- * copy data to the 32 * 32-bit HW Data registers a.k.a Master GW Data
- * Descriptor.
- */
-static void mlxbf_i2c_write_data(void __iomem *io, int reg, u32 val)
-{
-	mlxbf_i2c_write(io, reg, (u32)cpu_to_be32(val));
-}
-
 /*
  * Function to poll a set of bits at a specific address; it checks whether
  * the bits are equal to zero when eq_zero is set to 'true', and not equal
@@ -541,7 +501,7 @@
 	timeout = (timeout / MLXBF_I2C_POLL_FREQ_IN_USEC) + 1;
 
 	do {
-		bits = mlxbf_i2c_read(io, addr) & mask;
+		bits = readl(io + addr) & mask;
 		if (eq_zero ? bits == 0 : bits != 0)
 			return eq_zero ? 1 : bits;
 		udelay(MLXBF_I2C_POLL_FREQ_IN_USEC);
@@ -609,16 +569,16 @@
 			 MLXBF_I2C_SMBUS_TIMEOUT);
 
 	/* Read cause status bits. */
-	cause_status_bits = mlxbf_i2c_read(priv->mst_cause->io,
-					   MLXBF_I2C_CAUSE_ARBITER);
+	cause_status_bits = readl(priv->mst_cause->io +
+					MLXBF_I2C_CAUSE_ARBITER);
 	cause_status_bits &= MLXBF_I2C_CAUSE_MASTER_ARBITER_BITS_MASK;
 
 	/*
 	 * Parse both Cause and Master GW bits, then return transaction status.
 	 */
 
-	master_status_bits = mlxbf_i2c_read(priv->smbus->io,
-					    MLXBF_I2C_SMBUS_MASTER_STATUS);
+	master_status_bits = readl(priv->smbus->io +
+					MLXBF_I2C_SMBUS_MASTER_STATUS);
 	master_status_bits &= MLXBF_I2C_SMBUS_MASTER_STATUS_MASK;
 
 	if (mlxbf_i2c_smbus_transaction_success(master_status_bits,
@@ -649,10 +609,17 @@
 
 	aligned_length = round_up(length, 4);
 
-	/* Copy data bytes from 4-byte aligned source buffer. */
+	/*
+	 * Copy data bytes from 4-byte aligned source buffer.
+	 * Data copied to the Master GW Data Descriptor MUST be shifted
+	 * left so the data starts at the MSB of the descriptor registers
+	 * as required by the underlying hardware. Enable byte swapping
+	 * when writing data bytes to the 32 * 32-bit HW Data registers
+	 * a.k.a Master GW Data Descriptor.
+	 */
 	for (offset = 0; offset < aligned_length; offset += sizeof(u32)) {
 		data32 = *((u32 *)(data + offset));
-		mlxbf_i2c_write_data(priv->smbus->io, addr + offset, data32);
+		iowrite32be(data32, priv->smbus->io + addr + offset);
 	}
 }
 
@@ -664,15 +631,23 @@
 
 	mask = sizeof(u32) - 1;
 
+	/*
+	 * Data bytes in the Master GW Data Descriptor are shifted left
+	 * so the data starts at the MSB of the descriptor registers as
+	 * set by the underlying hardware. Enable byte swapping while
+	 * reading data bytes from the 32 * 32-bit HW Data registers
+	 * a.k.a Master GW Data Descriptor.
+	 */
+
 	for (offset = 0; offset < (length & ~mask); offset += sizeof(u32)) {
-		data32 = mlxbf_i2c_read_data(priv->smbus->io, addr + offset);
+		data32 = ioread32be(priv->smbus->io + addr + offset);
 		*((u32 *)(data + offset)) = data32;
 	}
 
 	if (!(length & mask))
 		return;
 
-	data32 = mlxbf_i2c_read_data(priv->smbus->io, addr + offset);
+	data32 = ioread32be(priv->smbus->io + addr + offset);
 
 	for (byte = 0; byte < (length & mask); byte++) {
 		data[offset + byte] = data32 & GENMASK(7, 0);
@@ -698,16 +673,16 @@
 	command |= rol32(pec_en, MLXBF_I2C_MASTER_SEND_PEC_SHIFT);
 
 	/* Clear status bits. */
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_STATUS, 0x0);
+	writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_STATUS);
 	/* Set the cause data. */
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_CAUSE_OR_CLEAR, ~0x0);
+	writel(~0x0, priv->smbus->io + MLXBF_I2C_CAUSE_OR_CLEAR);
 	/* Zero PEC byte. */
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_PEC, 0x0);
+	writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_PEC);
 	/* Zero byte count. */
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_RS_BYTES, 0x0);
+	writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_RS_BYTES);
 
 	/* GW activation. */
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_GW, command);
+	writel(command, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_GW);
 
 	/*
 	 * Poll master status and check status bits. An ACK is sent when
@@ -823,8 +798,8 @@
 		 * needs to be 'manually' reset. This should be removed in
 		 * next tag integration.
 		 */
-		mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_FSM,
-				MLXBF_I2C_SMBUS_MASTER_FSM_PS_STATE_MASK);
+		writel(MLXBF_I2C_SMBUS_MASTER_FSM_PS_STATE_MASK,
+			priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_FSM);
 	}
 
 	return ret;
@@ -1113,8 +1088,8 @@
 	timer |= mlxbf_i2c_set_timer(priv, timings->scl_low,
 				     false, MLXBF_I2C_MASK_16,
 				     MLXBF_I2C_SHIFT_16);
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_SCL_LOW_SCL_HIGH,
-			  timer);
+	writel(timer, priv->smbus->io +
+		MLXBF_I2C_SMBUS_TIMER_SCL_LOW_SCL_HIGH);
 
 	timer = mlxbf_i2c_set_timer(priv, timings->sda_rise, false,
 				    MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_0);
@@ -1124,37 +1099,34 @@
 				     MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_16);
 	timer |= mlxbf_i2c_set_timer(priv, timings->scl_fall, false,
 				     MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_24);
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_FALL_RISE_SPIKE,
-			  timer);
+	writel(timer, priv->smbus->io +
+		MLXBF_I2C_SMBUS_TIMER_FALL_RISE_SPIKE);
 
 	timer = mlxbf_i2c_set_timer(priv, timings->hold_start, true,
 				    MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
 	timer |= mlxbf_i2c_set_timer(priv, timings->hold_data, true,
 				     MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16);
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_THOLD, timer);
+	writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_TIMER_THOLD);
 
 	timer = mlxbf_i2c_set_timer(priv, timings->setup_start, true,
 				    MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
 	timer |= mlxbf_i2c_set_timer(priv, timings->setup_stop, true,
 				     MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16);
-	mlxbf_i2c_write(priv->smbus->io,
-			MLXBF_I2C_SMBUS_TIMER_TSETUP_START_STOP, timer);
+	writel(timer, priv->smbus->io +
+		MLXBF_I2C_SMBUS_TIMER_TSETUP_START_STOP);
 
 	timer = mlxbf_i2c_set_timer(priv, timings->setup_data, true,
 				    MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_TSETUP_DATA,
-			  timer);
+	writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_TIMER_TSETUP_DATA);
 
 	timer = mlxbf_i2c_set_timer(priv, timings->buf, false,
 				    MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
 	timer |= mlxbf_i2c_set_timer(priv, timings->thigh_max, false,
 				     MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16);
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_THIGH_MAX_TBUF,
-			timer);
+	writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_THIGH_MAX_TBUF);
 
 	timer = timings->timeout;
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SCL_LOW_TIMEOUT,
-			timer);
+	writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_SCL_LOW_TIMEOUT);
 }
 
 enum mlxbf_i2c_timings_config {
@@ -1426,19 +1398,15 @@
 	 * platform firmware; disabling the bus might compromise the system
 	 * functionality.
 	 */
-	config_reg = mlxbf_i2c_read(gpio_res->io,
-				    MLXBF_I2C_GPIO_0_FUNC_EN_0);
+	config_reg = readl(gpio_res->io + MLXBF_I2C_GPIO_0_FUNC_EN_0);
 	config_reg = MLXBF_I2C_GPIO_SMBUS_GW_ASSERT_PINS(priv->bus,
 							 config_reg);
-	mlxbf_i2c_write(gpio_res->io, MLXBF_I2C_GPIO_0_FUNC_EN_0,
-			config_reg);
+	writel(config_reg, gpio_res->io + MLXBF_I2C_GPIO_0_FUNC_EN_0);
 
-	config_reg = mlxbf_i2c_read(gpio_res->io,
-				    MLXBF_I2C_GPIO_0_FORCE_OE_EN);
+	config_reg = readl(gpio_res->io + MLXBF_I2C_GPIO_0_FORCE_OE_EN);
 	config_reg = MLXBF_I2C_GPIO_SMBUS_GW_RESET_PINS(priv->bus,
 							config_reg);
-	mlxbf_i2c_write(gpio_res->io, MLXBF_I2C_GPIO_0_FORCE_OE_EN,
-			config_reg);
+	writel(config_reg, gpio_res->io + MLXBF_I2C_GPIO_0_FORCE_OE_EN);
 
 	mutex_unlock(gpio_res->lock);
 
@@ -1452,10 +1420,9 @@
 	u32 corepll_val;
 	u16 core_f;
 
-	pad_frequency = MLXBF_I2C_TYU_PLL_IN_FREQ;
+	pad_frequency = MLXBF_I2C_PLL_IN_FREQ;
 
-	corepll_val = mlxbf_i2c_read(corepll_res->io,
-				     MLXBF_I2C_CORE_PLL_REG1);
+	corepll_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1);
 
 	/* Get Core PLL configuration bits. */
 	core_f = rol32(corepll_val, MLXBF_I2C_COREPLL_CORE_F_TYU_SHIFT) &
@@ -1488,12 +1455,10 @@
 	u8 core_od, core_r;
 	u32 core_f;
 
-	pad_frequency = MLXBF_I2C_YU_PLL_IN_FREQ;
+	pad_frequency = MLXBF_I2C_PLL_IN_FREQ;
 
-	corepll_reg1_val = mlxbf_i2c_read(corepll_res->io,
-					  MLXBF_I2C_CORE_PLL_REG1);
-	corepll_reg2_val = mlxbf_i2c_read(corepll_res->io,
-					  MLXBF_I2C_CORE_PLL_REG2);
+	corepll_reg1_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1);
+	corepll_reg2_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG2);
 
 	/* Get Core PLL configuration bits */
 	core_f = rol32(corepll_reg1_val, MLXBF_I2C_COREPLL_CORE_F_YU_SHIFT) &
@@ -1585,7 +1550,7 @@
 	 * (7-bit address, 1 status bit (1 if enabled, 0 if not)).
 	 */
 	for (reg = 0; reg < reg_cnt; reg++) {
-		slave_reg = mlxbf_i2c_read(priv->smbus->io,
+		slave_reg = readl(priv->smbus->io +
 				MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4);
 		/*
 		 * Each register holds 4 slave addresses. So, we have to keep
@@ -1643,8 +1608,8 @@
 
 	/* Enable the slave address and update the register. */
 	slave_reg |= (1 << MLXBF_I2C_SMBUS_SLAVE_ADDR_EN_BIT) << (byte * 8);
-	mlxbf_i2c_write(priv->smbus->io,
-			MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4, slave_reg);
+	writel(slave_reg, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG +
+		reg * 0x4);
 
 	return 0;
 }
@@ -1668,7 +1633,7 @@
 	 * (7-bit address, 1 status bit (1 if enabled, 0 if not)).
 	 */
 	for (reg = 0; reg < reg_cnt; reg++) {
-		slave_reg = mlxbf_i2c_read(priv->smbus->io,
+		slave_reg = readl(priv->smbus->io +
 				MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4);
 
 		/* Check whether the address slots are empty. */
@@ -1708,8 +1673,8 @@
 
 	/* Cleanup the slave address slot. */
 	slave_reg &= ~(GENMASK(7, 0) << (slave_byte * 8));
-	mlxbf_i2c_write(priv->smbus->io,
-			MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4, slave_reg);
+	writel(slave_reg, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG +
+		reg * 0x4);
 
 	return 0;
 }
@@ -1801,7 +1766,7 @@
 	int ret;
 
 	/* Reset FSM. */
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_FSM, 0);
+	writel(0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_FSM);
 
 	/*
 	 * Enable slave cause interrupt bits. Drive
@@ -1810,15 +1775,13 @@
 	 * masters issue a Read and Write, respectively. But, clear all
 	 * interrupts first.
 	 */
-	mlxbf_i2c_write(priv->slv_cause->io,
-			  MLXBF_I2C_CAUSE_OR_CLEAR, ~0);
+	writel(~0, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_CLEAR);
 	int_reg = MLXBF_I2C_CAUSE_READ_WAIT_FW_RESPONSE;
 	int_reg |= MLXBF_I2C_CAUSE_WRITE_SUCCESS;
-	mlxbf_i2c_write(priv->slv_cause->io,
-			  MLXBF_I2C_CAUSE_OR_EVTEN0, int_reg);
+	writel(int_reg, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_EVTEN0);
 
 	/* Finally, set the 'ready' bit to start handling transactions. */
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1);
+	writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY);
 
 	/* Initialize the cause coalesce resource. */
 	ret = mlxbf_i2c_init_coalesce(pdev, priv);
@@ -1844,23 +1807,21 @@
 				MLXBF_I2C_CAUSE_YU_SLAVE_BIT :
 				priv->bus + MLXBF_I2C_CAUSE_TYU_SLAVE_BIT;
 
-	coalesce0_reg = mlxbf_i2c_read(priv->coalesce->io,
-				       MLXBF_I2C_CAUSE_COALESCE_0);
+	coalesce0_reg = readl(priv->coalesce->io + MLXBF_I2C_CAUSE_COALESCE_0);
 	is_set = coalesce0_reg & (1 << slave_shift);
 
 	if (!is_set)
 		return false;
 
 	/* Check the source of the interrupt, i.e. whether a Read or Write. */
-	cause_reg = mlxbf_i2c_read(priv->slv_cause->io,
-				     MLXBF_I2C_CAUSE_ARBITER);
+	cause_reg = readl(priv->slv_cause->io + MLXBF_I2C_CAUSE_ARBITER);
 	if (cause_reg & MLXBF_I2C_CAUSE_READ_WAIT_FW_RESPONSE)
 		*read = true;
 	else if (cause_reg & MLXBF_I2C_CAUSE_WRITE_SUCCESS)
 		*write = true;
 
 	/* Clear cause bits. */
-	mlxbf_i2c_write(priv->slv_cause->io, MLXBF_I2C_CAUSE_OR_CLEAR, ~0x0);
+	writel(~0x0, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_CLEAR);
 
 	return true;
 }
@@ -1900,8 +1861,8 @@
 	 * address, if supplied.
 	 */
 	if (recv_bytes > 0) {
-		data32 = mlxbf_i2c_read_data(priv->smbus->io,
-					     MLXBF_I2C_SLAVE_DATA_DESC_ADDR);
+		data32 = ioread32be(priv->smbus->io +
+					MLXBF_I2C_SLAVE_DATA_DESC_ADDR);
 
 		/* Parse the received bytes. */
 		switch (recv_bytes) {
@@ -1966,7 +1927,7 @@
 	control32 |= rol32(write_size, MLXBF_I2C_SLAVE_WRITE_BYTES_SHIFT);
 	control32 |= rol32(pec_en, MLXBF_I2C_SLAVE_SEND_PEC_SHIFT);
 
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_GW, control32);
+	writel(control32, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_GW);
 
 	/*
 	 * Wait until the transfer is completed; the driver will wait
@@ -1975,10 +1936,9 @@
 	mlxbf_smbus_slave_wait_for_idle(priv, MLXBF_I2C_SMBUS_TIMEOUT);
 
 	/* Release the Slave GW. */
-	mlxbf_i2c_write(priv->smbus->io,
-			MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES, 0x0);
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_PEC, 0x0);
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1);
+	writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
+	writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_PEC);
+	writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY);
 
 	return 0;
 }
@@ -2023,10 +1983,9 @@
 	i2c_slave_event(slave, I2C_SLAVE_STOP, &value);
 
 	/* Release the Slave GW. */
-	mlxbf_i2c_write(priv->smbus->io,
-			MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES, 0x0);
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_PEC, 0x0);
-	mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1);
+	writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
+	writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_PEC);
+	writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY);
 
 	return ret;
 }
@@ -2061,8 +2020,8 @@
 	 * slave, if the higher 8 bits are sent then the slave expect N bytes
 	 * from the master.
 	 */
-	rw_bytes_reg = mlxbf_i2c_read(priv->smbus->io,
-				      MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
+	rw_bytes_reg = readl(priv->smbus->io +
+				MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
 	recv_bytes = (rw_bytes_reg >> 8) & GENMASK(7, 0);
 
 	/*
@@ -2264,6 +2223,7 @@
 
 MODULE_DEVICE_TABLE(of, mlxbf_i2c_dt_ids);
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id mlxbf_i2c_acpi_ids[] = {
 	{ "MLNXBF03", (kernel_ulong_t)&mlxbf_i2c_chip[MLXBF_I2C_CHIP_TYPE_1] },
 	{ "MLNXBF23", (kernel_ulong_t)&mlxbf_i2c_chip[MLXBF_I2C_CHIP_TYPE_2] },
@@ -2305,6 +2265,12 @@
 
 	return ret;
 }
+#else
+static int mlxbf_i2c_acpi_probe(struct device *dev, struct mlxbf_i2c_priv *priv)
+{
+	return -ENOENT;
+}
+#endif /* CONFIG_ACPI */
 
 static int mlxbf_i2c_of_probe(struct device *dev, struct mlxbf_i2c_priv *priv)
 {
@@ -2473,7 +2439,9 @@
 	.driver = {
 		.name = "i2c-mlxbf",
 		.of_match_table = mlxbf_i2c_dt_ids,
+#ifdef CONFIG_ACPI
 		.acpi_match_table = ACPI_PTR(mlxbf_i2c_acpi_ids),
+#endif /* CONFIG_ACPI  */
 	},
 };
 
@@ -2502,5 +2470,5 @@
 module_exit(mlxbf_i2c_exit);
 
 MODULE_DESCRIPTION("Mellanox BlueField I2C bus driver");
-MODULE_AUTHOR("Khalil Blaiech <kblaiech@mellanox.com>");
+MODULE_AUTHOR("Khalil Blaiech <kblaiech@nvidia.com>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index 0cbdfbe..33de99b 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -475,6 +475,10 @@
 {
 	u16 control_reg;
 
+	writel(I2C_DMA_HARD_RST, i2c->pdmabase + OFFSET_RST);
+	udelay(50);
+	writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
+
 	mtk_i2c_writew(i2c, I2C_SOFT_RST, OFFSET_SOFTRESET);
 
 	/* Set ioconfig */
@@ -529,10 +533,6 @@
 
 	mtk_i2c_writew(i2c, control_reg, OFFSET_CONTROL);
 	mtk_i2c_writew(i2c, I2C_DELAY_LEN, OFFSET_DELAY_LEN);
-
-	writel(I2C_DMA_HARD_RST, i2c->pdmabase + OFFSET_RST);
-	udelay(50);
-	writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
 }
 
 static const struct i2c_spec_values *mtk_i2c_get_spec(unsigned int speed)
diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c
index cab7255..bdd60770 100644
--- a/drivers/i2c/busses/i2c-sh_mobile.c
+++ b/drivers/i2c/busses/i2c-sh_mobile.c
@@ -129,6 +129,7 @@
 	int sr;
 	bool send_stop;
 	bool stop_after_dma;
+	bool atomic_xfer;
 
 	struct resource *res;
 	struct dma_chan *dma_tx;
@@ -330,13 +331,15 @@
 		ret = iic_rd(pd, ICDR);
 		break;
 	case OP_RX_STOP: /* enable DTE interrupt, issue stop */
-		iic_wr(pd, ICIC,
-		       ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
+		if (!pd->atomic_xfer)
+			iic_wr(pd, ICIC,
+			       ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
 		iic_wr(pd, ICCR, ICCR_ICE | ICCR_RACK);
 		break;
 	case OP_RX_STOP_DATA: /* enable DTE interrupt, read data, issue stop */
-		iic_wr(pd, ICIC,
-		       ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
+		if (!pd->atomic_xfer)
+			iic_wr(pd, ICIC,
+			       ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
 		ret = iic_rd(pd, ICDR);
 		iic_wr(pd, ICCR, ICCR_ICE | ICCR_RACK);
 		break;
@@ -429,7 +432,8 @@
 
 	if (wakeup) {
 		pd->sr |= SW_DONE;
-		wake_up(&pd->wait);
+		if (!pd->atomic_xfer)
+			wake_up(&pd->wait);
 	}
 
 	/* defeat write posting to avoid spurious WAIT interrupts */
@@ -581,6 +585,9 @@
 	pd->pos = -1;
 	pd->sr = 0;
 
+	if (pd->atomic_xfer)
+		return;
+
 	pd->dma_buf = i2c_get_dma_safe_msg_buf(pd->msg, 8);
 	if (pd->dma_buf)
 		sh_mobile_i2c_xfer_dma(pd);
@@ -637,15 +644,13 @@
 	return i ? 0 : -ETIMEDOUT;
 }
 
-static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter,
-			      struct i2c_msg *msgs,
-			      int num)
+static int sh_mobile_xfer(struct sh_mobile_i2c_data *pd,
+			 struct i2c_msg *msgs, int num)
 {
-	struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter);
 	struct i2c_msg	*msg;
 	int err = 0;
 	int i;
-	long timeout;
+	long time_left;
 
 	/* Wake up device and enable clock */
 	pm_runtime_get_sync(pd->dev);
@@ -662,15 +667,35 @@
 		if (do_start)
 			i2c_op(pd, OP_START);
 
-		/* The interrupt handler takes care of the rest... */
-		timeout = wait_event_timeout(pd->wait,
-				       pd->sr & (ICSR_TACK | SW_DONE),
-				       adapter->timeout);
+		if (pd->atomic_xfer) {
+			unsigned long j = jiffies + pd->adap.timeout;
 
-		/* 'stop_after_dma' tells if DMA transfer was complete */
-		i2c_put_dma_safe_msg_buf(pd->dma_buf, pd->msg, pd->stop_after_dma);
+			time_left = time_before_eq(jiffies, j);
+			while (time_left &&
+			       !(pd->sr & (ICSR_TACK | SW_DONE))) {
+				unsigned char sr = iic_rd(pd, ICSR);
 
-		if (!timeout) {
+				if (sr & (ICSR_AL   | ICSR_TACK |
+					  ICSR_WAIT | ICSR_DTE)) {
+					sh_mobile_i2c_isr(0, pd);
+					udelay(150);
+				} else {
+					cpu_relax();
+				}
+				time_left = time_before_eq(jiffies, j);
+			}
+		} else {
+			/* The interrupt handler takes care of the rest... */
+			time_left = wait_event_timeout(pd->wait,
+					pd->sr & (ICSR_TACK | SW_DONE),
+					pd->adap.timeout);
+
+			/* 'stop_after_dma' tells if DMA xfer was complete */
+			i2c_put_dma_safe_msg_buf(pd->dma_buf, pd->msg,
+						 pd->stop_after_dma);
+		}
+
+		if (!time_left) {
 			dev_err(pd->dev, "Transfer request timed out\n");
 			if (pd->dma_direction != DMA_NONE)
 				sh_mobile_i2c_cleanup_dma(pd);
@@ -696,14 +721,35 @@
 	return err ?: num;
 }
 
+static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter,
+			      struct i2c_msg *msgs,
+			      int num)
+{
+	struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter);
+
+	pd->atomic_xfer = false;
+	return sh_mobile_xfer(pd, msgs, num);
+}
+
+static int sh_mobile_i2c_xfer_atomic(struct i2c_adapter *adapter,
+				     struct i2c_msg *msgs,
+				     int num)
+{
+	struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter);
+
+	pd->atomic_xfer = true;
+	return sh_mobile_xfer(pd, msgs, num);
+}
+
 static u32 sh_mobile_i2c_func(struct i2c_adapter *adapter)
 {
 	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_PROTOCOL_MANGLING;
 }
 
 static const struct i2c_algorithm sh_mobile_i2c_algorithm = {
-	.functionality	= sh_mobile_i2c_func,
-	.master_xfer	= sh_mobile_i2c_xfer,
+	.functionality = sh_mobile_i2c_func,
+	.master_xfer = sh_mobile_i2c_xfer,
+	.master_xfer_atomic = sh_mobile_i2c_xfer_atomic,
 };
 
 static const struct i2c_adapter_quirks sh_mobile_i2c_quirks = {
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
index f0e5ffb..97ed8f9 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.h
@@ -176,7 +176,7 @@
 	u8			subnet_timeout;
 	u8			init_type_reply;
 	u8			active_width;
-	u16			active_speed;
+	u8			active_speed;
 	u8			phys_state;
 	u8			reserved[2];
 };
diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c
index 5221868..670a9623 100644
--- a/drivers/infiniband/sw/rdmavt/vt.c
+++ b/drivers/infiniband/sw/rdmavt/vt.c
@@ -524,6 +524,7 @@
 int rvt_register_device(struct rvt_dev_info *rdi)
 {
 	int ret = 0, i;
+	u64 dma_mask;
 
 	if (!rdi)
 		return -EINVAL;
@@ -580,8 +581,10 @@
 
 	/* DMA Operations */
 	rdi->ibdev.dev.dma_parms = rdi->ibdev.dev.parent->dma_parms;
-	dma_set_coherent_mask(&rdi->ibdev.dev,
-			      rdi->ibdev.dev.parent->coherent_dma_mask);
+	dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32);
+	ret = dma_coerce_mask_and_coherent(&rdi->ibdev.dev, dma_mask);
+	if (ret)
+		goto bail_wss;
 
 	/* Protection Domain */
 	spin_lock_init(&rdi->n_pds_lock);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 1fc0223..f9c832e 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -1118,6 +1118,7 @@
 	int err;
 	struct ib_device *dev = &rxe->ib_dev;
 	struct crypto_shash *tfm;
+	u64 dma_mask;
 
 	strlcpy(dev->node_desc, "rxe", sizeof(dev->node_desc));
 
@@ -1130,7 +1131,10 @@
 			    rxe->ndev->dev_addr);
 	dev->dev.dma_parms = &rxe->dma_parms;
 	dma_set_max_seg_size(&dev->dev, UINT_MAX);
-	dma_set_coherent_mask(&dev->dev, dma_get_required_mask(&dev->dev));
+	dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32);
+	err = dma_coerce_mask_and_coherent(&dev->dev, dma_mask);
+	if (err)
+		return err;
 
 	dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT)
 	    | BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL)
diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c
index ca8bc72..181e06c 100644
--- a/drivers/infiniband/sw/siw/siw_main.c
+++ b/drivers/infiniband/sw/siw/siw_main.c
@@ -306,6 +306,7 @@
 	struct siw_device *sdev = NULL;
 	struct ib_device *base_dev;
 	struct device *parent = netdev->dev.parent;
+	u64 dma_mask;
 	int rv;
 
 	if (!parent) {
@@ -384,8 +385,10 @@
 	base_dev->dev.parent = parent;
 	base_dev->dev.dma_parms = &sdev->dma_parms;
 	dma_set_max_seg_size(&base_dev->dev, UINT_MAX);
-	dma_set_coherent_mask(&base_dev->dev,
-			      dma_get_required_mask(&base_dev->dev));
+	dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32);
+	if (dma_coerce_mask_and_coherent(&base_dev->dev, dma_mask))
+		goto error;
+
 	base_dev->num_comp_vectors = num_possible_cpus();
 
 	xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 0065eb1..53a8bec 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -622,10 +622,11 @@
 /**
  * srpt_unregister_mad_agent - unregister MAD callback functions
  * @sdev: SRPT HCA pointer.
+ * @port_cnt: number of ports with registered MAD
  *
  * Note: It is safe to call this function more than once for the same device.
  */
-static void srpt_unregister_mad_agent(struct srpt_device *sdev)
+static void srpt_unregister_mad_agent(struct srpt_device *sdev, int port_cnt)
 {
 	struct ib_port_modify port_modify = {
 		.clr_port_cap_mask = IB_PORT_DEVICE_MGMT_SUP,
@@ -633,7 +634,7 @@
 	struct srpt_port *sport;
 	int i;
 
-	for (i = 1; i <= sdev->device->phys_port_cnt; i++) {
+	for (i = 1; i <= port_cnt; i++) {
 		sport = &sdev->port[i - 1];
 		WARN_ON(sport->port != i);
 		if (sport->mad_agent) {
@@ -3185,7 +3186,8 @@
 		if (ret) {
 			pr_err("MAD registration failed for %s-%d.\n",
 			       dev_name(&sdev->device->dev), i);
-			goto err_event;
+			i--;
+			goto err_port;
 		}
 	}
 
@@ -3197,7 +3199,8 @@
 	pr_debug("added %s.\n", dev_name(&device->dev));
 	return 0;
 
-err_event:
+err_port:
+	srpt_unregister_mad_agent(sdev, i);
 	ib_unregister_event_handler(&sdev->event_handler);
 err_cm:
 	if (sdev->cm_id)
@@ -3221,7 +3224,7 @@
 	struct srpt_device *sdev = client_data;
 	int i;
 
-	srpt_unregister_mad_agent(sdev);
+	srpt_unregister_mad_agent(sdev, sdev->device->phys_port_cnt);
 
 	ib_unregister_event_handler(&sdev->event_handler);
 
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index 41435a6..bdeb010 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -256,6 +256,7 @@
  * @rdma_cm:	   See below.
  * @rdma_cm.cm_id: RDMA CM ID associated with the channel.
  * @cq:            IB completion queue for this channel.
+ * @cq_size:	   Number of CQEs in @cq.
  * @zw_cqe:	   Zero-length write CQE.
  * @rcu:           RCU head.
  * @kref:	   kref for this channel.
diff --git a/drivers/input/keyboard/sunkbd.c b/drivers/input/keyboard/sunkbd.c
index 27126e6..d450f11 100644
--- a/drivers/input/keyboard/sunkbd.c
+++ b/drivers/input/keyboard/sunkbd.c
@@ -99,7 +99,8 @@
 	switch (data) {
 
 	case SUNKBD_RET_RESET:
-		schedule_work(&sunkbd->tq);
+		if (sunkbd->enabled)
+			schedule_work(&sunkbd->tq);
 		sunkbd->reset = -1;
 		break;
 
@@ -200,16 +201,12 @@
 }
 
 /*
- * sunkbd_reinit() sets leds and beeps to a state the computer remembers they
- * were in.
+ * sunkbd_set_leds_beeps() sets leds and beeps to a state the computer remembers
+ * they were in.
  */
 
-static void sunkbd_reinit(struct work_struct *work)
+static void sunkbd_set_leds_beeps(struct sunkbd *sunkbd)
 {
-	struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq);
-
-	wait_event_interruptible_timeout(sunkbd->wait, sunkbd->reset >= 0, HZ);
-
 	serio_write(sunkbd->serio, SUNKBD_CMD_SETLED);
 	serio_write(sunkbd->serio,
 		(!!test_bit(LED_CAPSL,   sunkbd->dev->led) << 3) |
@@ -222,11 +219,39 @@
 		SUNKBD_CMD_BELLOFF - !!test_bit(SND_BELL, sunkbd->dev->snd));
 }
 
+
+/*
+ * sunkbd_reinit() wait for the keyboard reset to complete and restores state
+ * of leds and beeps.
+ */
+
+static void sunkbd_reinit(struct work_struct *work)
+{
+	struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq);
+
+	/*
+	 * It is OK that we check sunkbd->enabled without pausing serio,
+	 * as we only want to catch true->false transition that will
+	 * happen once and we will be woken up for it.
+	 */
+	wait_event_interruptible_timeout(sunkbd->wait,
+					 sunkbd->reset >= 0 || !sunkbd->enabled,
+					 HZ);
+
+	if (sunkbd->reset >= 0 && sunkbd->enabled)
+		sunkbd_set_leds_beeps(sunkbd);
+}
+
 static void sunkbd_enable(struct sunkbd *sunkbd, bool enable)
 {
 	serio_pause_rx(sunkbd->serio);
 	sunkbd->enabled = enable;
 	serio_continue_rx(sunkbd->serio);
+
+	if (!enable) {
+		wake_up_interruptible(&sunkbd->wait);
+		cancel_work_sync(&sunkbd->tq);
+	}
 }
 
 /*
diff --git a/drivers/input/misc/adxl34x.c b/drivers/input/misc/adxl34x.c
index 5fe92d4..4cc4e8f 100644
--- a/drivers/input/misc/adxl34x.c
+++ b/drivers/input/misc/adxl34x.c
@@ -696,7 +696,7 @@
 	struct input_dev *input_dev;
 	const struct adxl34x_platform_data *pdata;
 	int err, range, i;
-	unsigned char revid;
+	int revid;
 
 	if (!irq) {
 		dev_err(dev, "no IRQ?\n");
diff --git a/drivers/input/mouse/elan_i2c.h b/drivers/input/mouse/elan_i2c.h
index c75b00c..36e3cd9 100644
--- a/drivers/input/mouse/elan_i2c.h
+++ b/drivers/input/mouse/elan_i2c.h
@@ -78,7 +78,7 @@
 	int (*iap_reset)(struct i2c_client *client);
 
 	int (*prepare_fw_update)(struct i2c_client *client, u16 ic_type,
-				 u8 iap_version);
+				 u8 iap_version, u16 fw_page_size);
 	int (*write_fw_block)(struct i2c_client *client, u16 fw_page_size,
 			      const u8 *page, u16 checksum, int idx);
 	int (*finish_fw_update)(struct i2c_client *client,
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index c599e21..61ed3f5 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -497,7 +497,8 @@
 	u16 sw_checksum = 0, fw_checksum = 0;
 
 	error = data->ops->prepare_fw_update(client, data->ic_type,
-					     data->iap_version);
+					     data->iap_version,
+					     data->fw_page_size);
 	if (error)
 		return error;
 
diff --git a/drivers/input/mouse/elan_i2c_i2c.c b/drivers/input/mouse/elan_i2c_i2c.c
index 5a496d4..13dc097 100644
--- a/drivers/input/mouse/elan_i2c_i2c.c
+++ b/drivers/input/mouse/elan_i2c_i2c.c
@@ -517,7 +517,7 @@
 	return 0;
 }
 
-static int elan_read_write_iap_type(struct i2c_client *client)
+static int elan_read_write_iap_type(struct i2c_client *client, u16 fw_page_size)
 {
 	int error;
 	u16 constant;
@@ -526,7 +526,7 @@
 
 	do {
 		error = elan_i2c_write_cmd(client, ETP_I2C_IAP_TYPE_CMD,
-					   ETP_I2C_IAP_TYPE_REG);
+					   fw_page_size / 2);
 		if (error) {
 			dev_err(&client->dev,
 				"cannot write iap type: %d\n", error);
@@ -543,7 +543,7 @@
 		constant = le16_to_cpup((__le16 *)val);
 		dev_dbg(&client->dev, "iap type reg: 0x%04x\n", constant);
 
-		if (constant == ETP_I2C_IAP_TYPE_REG)
+		if (constant == fw_page_size / 2)
 			return 0;
 
 	} while (--retry > 0);
@@ -553,7 +553,7 @@
 }
 
 static int elan_i2c_prepare_fw_update(struct i2c_client *client, u16 ic_type,
-				      u8 iap_version)
+				      u8 iap_version, u16 fw_page_size)
 {
 	struct device *dev = &client->dev;
 	int error;
@@ -594,7 +594,7 @@
 	}
 
 	if (ic_type >= 0x0D && iap_version >= 1) {
-		error = elan_read_write_iap_type(client);
+		error = elan_read_write_iap_type(client, fw_page_size);
 		if (error)
 			return error;
 	}
diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c
index 8ff8237..1820f1c 100644
--- a/drivers/input/mouse/elan_i2c_smbus.c
+++ b/drivers/input/mouse/elan_i2c_smbus.c
@@ -340,7 +340,7 @@
 }
 
 static int elan_smbus_prepare_fw_update(struct i2c_client *client, u16 ic_type,
-					u8 iap_version)
+					u8 iap_version, u16 fw_page_size)
 {
 	struct device *dev = &client->dev;
 	int len;
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index d3eda48..944cbb5 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -122,6 +122,7 @@
 MODULE_PARM_DESC(unmask_kbd_data, "Unconditional enable (may reveal sensitive data) of normally sanitize-filtered kbd data traffic debug log [pre-condition: i8042.debug=1 enabled]");
 #endif
 
+static bool i8042_present;
 static bool i8042_bypass_aux_irq_test;
 static char i8042_kbd_firmware_id[128];
 static char i8042_aux_firmware_id[128];
@@ -343,6 +344,9 @@
 	unsigned long flags;
 	int retval;
 
+	if (!i8042_present)
+		return -1;
+
 	spin_lock_irqsave(&i8042_lock, flags);
 	retval = __i8042_command(param, command);
 	spin_unlock_irqrestore(&i8042_lock, flags);
@@ -1612,12 +1616,15 @@
 
 	err = i8042_platform_init();
 	if (err)
-		return err;
+		return (err == -ENODEV) ? 0 : err;
 
 	err = i8042_controller_check();
 	if (err)
 		goto err_platform_exit;
 
+	/* Set this before creating the dev to allow i8042_command to work right away */
+	i8042_present = true;
+
 	pdev = platform_create_bundle(&i8042_driver, i8042_probe, NULL, 0, NULL, 0);
 	if (IS_ERR(pdev)) {
 		err = PTR_ERR(pdev);
@@ -1636,6 +1643,9 @@
 
 static void __exit i8042_exit(void)
 {
+	if (!i8042_present)
+		return;
+
 	platform_device_unregister(i8042_platform_device);
 	platform_driver_unregister(&i8042_driver);
 	i8042_platform_exit();
diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index f012fe7..cc18f54 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -96,6 +96,7 @@
 config TOUCHSCREEN_ADC
 	tristate "Generic ADC based resistive touchscreen"
 	depends on IIO
+	select IIO_BUFFER
 	select IIO_BUFFER_CB
 	help
 	  Say Y here if you want to use the generic ADC
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index f696ac7..8964770 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -409,7 +409,11 @@
 /* Only true if all IOMMUs support device IOTLBs */
 extern bool amd_iommu_iotlb_sup;
 
-#define MAX_IRQS_PER_TABLE	256
+/*
+ * AMD IOMMU hardware only support 512 IRTEs despite
+ * the architectural limitation of 2048 entries.
+ */
+#define MAX_IRQS_PER_TABLE	512
 #define IRQ_TABLE_ALIGNMENT	128
 
 struct irq_remap_table {
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 404b40a..b2e8044 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -333,6 +333,11 @@
 	dmar_iommu_notify_scope_dev(info);
 }
 
+static inline void vf_inherit_msi_domain(struct pci_dev *pdev)
+{
+	dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&pdev->physfn->dev));
+}
+
 static int dmar_pci_bus_notifier(struct notifier_block *nb,
 				 unsigned long action, void *data)
 {
@@ -342,8 +347,20 @@
 	/* Only care about add/remove events for physical functions.
 	 * For VFs we actually do the lookup based on the corresponding
 	 * PF in device_to_iommu() anyway. */
-	if (pdev->is_virtfn)
+	if (pdev->is_virtfn) {
+		/*
+		 * Ensure that the VF device inherits the irq domain of the
+		 * PF device. Ideally the device would inherit the domain
+		 * from the bus, but DMAR can have multiple units per bus
+		 * which makes this impossible. The VF 'bus' could inherit
+		 * from the PF device, but that's yet another x86'sism to
+		 * inflict on everybody else.
+		 */
+		if (action == BUS_NOTIFY_ADD_DEVICE)
+			vf_inherit_msi_domain(pdev);
 		return NOTIFY_DONE;
+	}
+
 	if (action != BUS_NOTIFY_ADD_DEVICE &&
 	    action != BUS_NOTIFY_REMOVED_DEVICE)
 		return NOTIFY_DONE;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 8651f6d..c662201 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2525,6 +2525,9 @@
 {
 	struct device_domain_info *info;
 
+	if (unlikely(!dev || !dev->iommu))
+		return NULL;
+
 	if (unlikely(attach_deferred(dev)))
 		return NULL;
 
@@ -3815,9 +3818,8 @@
 	 * page aligned, we don't need to use a bounce page.
 	 */
 	if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) {
-		tlb_addr = swiotlb_tbl_map_single(dev,
-				phys_to_dma_unencrypted(dev, io_tlb_start),
-				paddr, size, aligned_size, dir, attrs);
+		tlb_addr = swiotlb_tbl_map_single(dev, paddr, size,
+				aligned_size, dir, attrs);
 		if (tlb_addr == DMA_MAPPING_ERROR) {
 			goto swiotlb_error;
 		} else {
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index f1861fa..3242ebd 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -279,6 +279,7 @@
 	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
 	struct intel_svm_dev *sdev = NULL;
 	struct dmar_domain *dmar_domain;
+	struct device_domain_info *info;
 	struct intel_svm *svm = NULL;
 	int ret = 0;
 
@@ -310,6 +311,10 @@
 	if (data->hpasid <= 0 || data->hpasid >= PASID_MAX)
 		return -EINVAL;
 
+	info = get_domain_info(dev);
+	if (!info)
+		return -EINVAL;
+
 	dmar_domain = to_dmar_domain(domain);
 
 	mutex_lock(&pasid_mutex);
@@ -357,6 +362,7 @@
 		goto out;
 	}
 	sdev->dev = dev;
+	sdev->sid = PCI_DEVID(info->bus, info->devfn);
 
 	/* Only count users if device has aux domains */
 	if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
@@ -1029,7 +1035,7 @@
 			resp.qw0 = QI_PGRP_PASID(req->pasid) |
 				QI_PGRP_DID(req->rid) |
 				QI_PGRP_PASID_P(req->pasid_present) |
-				QI_PGRP_PDP(req->pasid_present) |
+				QI_PGRP_PDP(req->priv_data_present) |
 				QI_PGRP_RESP_CODE(result) |
 				QI_PGRP_RESP_TYPE;
 			resp.qw1 = QI_PGRP_IDX(req->prg_index) |
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 8c470f4..b53446b 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2071,7 +2071,7 @@
 
 static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
 {
-	u32 mask;
+	u64 mask;
 	int i;
 
 	if (data->version != IOMMU_GPASID_BIND_VERSION_1)
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index c6098ee..2aa79c3 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -180,7 +180,6 @@
 	select GENERIC_IRQ_CHIP
 	select GENERIC_IRQ_IPI if SYS_SUPPORTS_MULTITHREADING
 	select IRQ_DOMAIN
-	select IRQ_DOMAIN_HIERARCHY if GENERIC_IRQ_IPI
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
 
 config CLPS711X_IRQCHIP
@@ -315,7 +314,6 @@
 config MIPS_GIC
 	bool
 	select GENERIC_IRQ_IPI
-	select IRQ_DOMAIN_HIERARCHY
 	select MIPS_CM
 
 config INGENIC_IRQ
@@ -591,6 +589,7 @@
 
 config MST_IRQ
 	bool "MStar Interrupt Controller"
+	depends on ARCH_MEDIATEK || ARCH_MSTARV7 || COMPILE_TEST
 	default ARCH_MEDIATEK
 	select IRQ_DOMAIN
 	select IRQ_DOMAIN_HIERARCHY
diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c
index 97838eb..cbc7c74 100644
--- a/drivers/irqchip/irq-bcm2836.c
+++ b/drivers/irqchip/irq-bcm2836.c
@@ -244,7 +244,7 @@
 
 #define BITS_PER_MBOX	32
 
-static void bcm2836_arm_irqchip_smp_init(void)
+static void __init bcm2836_arm_irqchip_smp_init(void)
 {
 	struct irq_fwspec ipi_fwspec = {
 		.fwnode		= intc.domain->fwnode,
diff --git a/drivers/irqchip/irq-mst-intc.c b/drivers/irqchip/irq-mst-intc.c
index 4be0775..143657b 100644
--- a/drivers/irqchip/irq-mst-intc.c
+++ b/drivers/irqchip/irq-mst-intc.c
@@ -154,8 +154,8 @@
 	.free		= irq_domain_free_irqs_common,
 };
 
-int __init
-mst_intc_of_init(struct device_node *dn, struct device_node *parent)
+static int __init mst_intc_of_init(struct device_node *dn,
+				   struct device_node *parent)
 {
 	struct irq_domain *domain, *domain_parent;
 	struct mst_intc_chip_data *cd;
diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c
index 3819185b..cb7f60b 100644
--- a/drivers/irqchip/irq-renesas-intc-irqpin.c
+++ b/drivers/irqchip/irq-renesas-intc-irqpin.c
@@ -71,8 +71,7 @@
 };
 
 struct intc_irqpin_config {
-	unsigned int irlm_bit;
-	unsigned needs_irlm:1;
+	int irlm_bit;		/* -1 if non-existent */
 };
 
 static unsigned long intc_irqpin_read32(void __iomem *iomem)
@@ -349,11 +348,10 @@
 
 static const struct intc_irqpin_config intc_irqpin_irlm_r8a777x = {
 	.irlm_bit = 23, /* ICR0.IRLM0 */
-	.needs_irlm = 1,
 };
 
 static const struct intc_irqpin_config intc_irqpin_rmobile = {
-	.needs_irlm = 0,
+	.irlm_bit = -1,
 };
 
 static const struct of_device_id intc_irqpin_dt_ids[] = {
@@ -470,7 +468,7 @@
 	}
 
 	/* configure "individual IRQ mode" where needed */
-	if (config && config->needs_irlm) {
+	if (config && config->irlm_bit >= 0) {
 		if (io[INTC_IRQPIN_REG_IRLM])
 			intc_irqpin_read_modify_write(p, INTC_IRQPIN_REG_IRLM,
 						      config->irlm_bit, 1, 1);
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index eaa3e9f..6f432d2 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -99,7 +99,7 @@
 				   struct irq_data *d, int enable)
 {
 	int cpu;
-	struct plic_priv *priv = irq_get_chip_data(d->irq);
+	struct plic_priv *priv = irq_data_get_irq_chip_data(d);
 
 	writel(enable, priv->regs + PRIORITY_BASE + d->hwirq * PRIORITY_PER_ID);
 	for_each_cpu(cpu, mask) {
@@ -115,7 +115,7 @@
 {
 	struct cpumask amask;
 	unsigned int cpu;
-	struct plic_priv *priv = irq_get_chip_data(d->irq);
+	struct plic_priv *priv = irq_data_get_irq_chip_data(d);
 
 	cpumask_and(&amask, &priv->lmask, cpu_online_mask);
 	cpu = cpumask_any_and(irq_data_get_affinity_mask(d),
@@ -127,7 +127,7 @@
 
 static void plic_irq_mask(struct irq_data *d)
 {
-	struct plic_priv *priv = irq_get_chip_data(d->irq);
+	struct plic_priv *priv = irq_data_get_irq_chip_data(d);
 
 	plic_irq_toggle(&priv->lmask, d, 0);
 }
@@ -138,7 +138,7 @@
 {
 	unsigned int cpu;
 	struct cpumask amask;
-	struct plic_priv *priv = irq_get_chip_data(d->irq);
+	struct plic_priv *priv = irq_data_get_irq_chip_data(d);
 
 	cpumask_and(&amask, &priv->lmask, mask_val);
 
@@ -151,7 +151,7 @@
 		return -EINVAL;
 
 	plic_irq_toggle(&priv->lmask, d, 0);
-	plic_irq_toggle(cpumask_of(cpu), d, 1);
+	plic_irq_toggle(cpumask_of(cpu), d, !irqd_irq_masked(d));
 
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 0c2c61d..8662d7b 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -195,6 +195,10 @@
 	{ .exti = 25, .irq_parent = 107, .chip = &stm32_exti_h_chip_direct },
 	{ .exti = 30, .irq_parent = 52, .chip = &stm32_exti_h_chip_direct },
 	{ .exti = 47, .irq_parent = 93, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 48, .irq_parent = 138, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 50, .irq_parent = 139, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 52, .irq_parent = 140, .chip = &stm32_exti_h_chip_direct },
+	{ .exti = 53, .irq_parent = 141, .chip = &stm32_exti_h_chip_direct },
 	{ .exti = 54, .irq_parent = 135, .chip = &stm32_exti_h_chip_direct },
 	{ .exti = 61, .irq_parent = 100, .chip = &stm32_exti_h_chip_direct },
 	{ .exti = 65, .irq_parent = 144, .chip = &stm32_exti_h_chip },
diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c
index e0cceb8..b2ab8db4 100644
--- a/drivers/irqchip/irq-ti-sci-inta.c
+++ b/drivers/irqchip/irq-ti-sci-inta.c
@@ -85,6 +85,17 @@
  * @base:		Base address of the memory mapped IO registers
  * @pdev:		Pointer to platform device.
  * @ti_sci_id:		TI-SCI device identifier
+ * @unmapped_cnt:	Number of @unmapped_dev_ids entries
+ * @unmapped_dev_ids:	Pointer to an array of TI-SCI device identifiers of
+ *			unmapped event sources.
+ *			Unmapped Events are not part of the Global Event Map and
+ *			they are converted to Global event within INTA to be
+ *			received by the same INTA to generate an interrupt.
+ *			In case an interrupt request comes for a device which is
+ *			generating Unmapped Event, we must use the INTA's TI-SCI
+ *			device identifier in place of the source device
+ *			identifier to let sysfw know where it has to program the
+ *			Global Event number.
  */
 struct ti_sci_inta_irq_domain {
 	const struct ti_sci_handle *sci;
@@ -96,11 +107,37 @@
 	void __iomem *base;
 	struct platform_device *pdev;
 	u32 ti_sci_id;
+
+	int unmapped_cnt;
+	u16 *unmapped_dev_ids;
 };
 
 #define to_vint_desc(e, i) container_of(e, struct ti_sci_inta_vint_desc, \
 					events[i])
 
+static u16 ti_sci_inta_get_dev_id(struct ti_sci_inta_irq_domain *inta, u32 hwirq)
+{
+	u16 dev_id = HWIRQ_TO_DEVID(hwirq);
+	int i;
+
+	if (inta->unmapped_cnt == 0)
+		return dev_id;
+
+	/*
+	 * For devices sending Unmapped Events we must use the INTA's TI-SCI
+	 * device identifier number to be able to convert it to a Global Event
+	 * and map it to an interrupt.
+	 */
+	for (i = 0; i < inta->unmapped_cnt; i++) {
+		if (dev_id == inta->unmapped_dev_ids[i]) {
+			dev_id = inta->ti_sci_id;
+			break;
+		}
+	}
+
+	return dev_id;
+}
+
 /**
  * ti_sci_inta_irq_handler() - Chained IRQ handler for the vint irqs
  * @desc:	Pointer to irq_desc corresponding to the irq
@@ -251,7 +288,7 @@
 	u16 dev_id, dev_index;
 	int err;
 
-	dev_id = HWIRQ_TO_DEVID(hwirq);
+	dev_id = ti_sci_inta_get_dev_id(inta, hwirq);
 	dev_index = HWIRQ_TO_IRQID(hwirq);
 
 	event_desc = &vint_desc->events[free_bit];
@@ -352,14 +389,15 @@
 {
 	struct ti_sci_inta_vint_desc *vint_desc;
 	struct ti_sci_inta_irq_domain *inta;
+	u16 dev_id;
 
 	vint_desc = to_vint_desc(event_desc, event_desc->vint_bit);
 	inta = vint_desc->domain->host_data;
+	dev_id = ti_sci_inta_get_dev_id(inta, hwirq);
 	/* free event irq */
 	mutex_lock(&inta->vint_mutex);
 	inta->sci->ops.rm_irq_ops.free_event_map(inta->sci,
-						 HWIRQ_TO_DEVID(hwirq),
-						 HWIRQ_TO_IRQID(hwirq),
+						 dev_id, HWIRQ_TO_IRQID(hwirq),
 						 inta->ti_sci_id,
 						 vint_desc->vint_id,
 						 event_desc->global_event,
@@ -574,6 +612,41 @@
 	.chip	= &ti_sci_inta_msi_irq_chip,
 };
 
+static int ti_sci_inta_get_unmapped_sources(struct ti_sci_inta_irq_domain *inta)
+{
+	struct device *dev = &inta->pdev->dev;
+	struct device_node *node = dev_of_node(dev);
+	struct of_phandle_iterator it;
+	int count, err, ret, i;
+
+	count = of_count_phandle_with_args(node, "ti,unmapped-event-sources", NULL);
+	if (count <= 0)
+		return 0;
+
+	inta->unmapped_dev_ids = devm_kcalloc(dev, count,
+					      sizeof(*inta->unmapped_dev_ids),
+					      GFP_KERNEL);
+	if (!inta->unmapped_dev_ids)
+		return -ENOMEM;
+
+	i = 0;
+	of_for_each_phandle(&it, err, node, "ti,unmapped-event-sources", NULL, 0) {
+		u32 dev_id;
+
+		ret = of_property_read_u32(it.node, "ti,sci-dev-id", &dev_id);
+		if (ret) {
+			dev_err(dev, "ti,sci-dev-id read failure for %pOFf\n", it.node);
+			of_node_put(it.node);
+			return ret;
+		}
+		inta->unmapped_dev_ids[i++] = dev_id;
+	}
+
+	inta->unmapped_cnt = count;
+
+	return 0;
+}
+
 static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev)
 {
 	struct irq_domain *parent_domain, *domain, *msi_domain;
@@ -629,6 +702,10 @@
 	if (IS_ERR(inta->base))
 		return PTR_ERR(inta->base);
 
+	ret = ti_sci_inta_get_unmapped_sources(inta);
+	if (ret)
+		return ret;
+
 	domain = irq_domain_add_linear(dev_of_node(dev),
 				       ti_sci_get_num_resources(inta->vint),
 				       &ti_sci_inta_irq_domain_ops, inta);
diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
index 901e213..ada570f3 100644
--- a/drivers/misc/habanalabs/common/command_buffer.c
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -142,11 +142,10 @@
 {
 	if (cb->is_internal)
 		gen_pool_free(hdev->internal_cb_pool,
-				cb->kernel_address, cb->size);
+				(uintptr_t)cb->kernel_address, cb->size);
 	else
 		hdev->asic_funcs->asic_dma_free_coherent(hdev, cb->size,
-				(void *) (uintptr_t) cb->kernel_address,
-				cb->bus_address);
+				cb->kernel_address, cb->bus_address);
 
 	kfree(cb);
 }
@@ -230,7 +229,7 @@
 		return NULL;
 	}
 
-	cb->kernel_address = (u64) (uintptr_t) p;
+	cb->kernel_address = p;
 	cb->size = cb_size;
 
 	return cb;
@@ -509,7 +508,7 @@
 
 	vma->vm_private_data = cb;
 
-	rc = hdev->asic_funcs->cb_mmap(hdev, vma, (void *) cb->kernel_address,
+	rc = hdev->asic_funcs->cb_mmap(hdev, vma, cb->kernel_address,
 					cb->bus_address, cb->size);
 	if (rc) {
 		spin_lock(&cb->lock);
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 80d4d73..6ed974d 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -452,7 +452,7 @@
 	struct list_head	pool_list;
 	struct list_head	va_block_list;
 	u64			id;
-	u64			kernel_address;
+	void			*kernel_address;
 	dma_addr_t		bus_address;
 	u32			mmap_size;
 	u32			size;
@@ -515,7 +515,7 @@
 	struct hl_hw_sob	hw_sob[HL_RSVD_SOBS];
 	struct hl_cs_job	**shadow_queue;
 	enum hl_queue_type	queue_type;
-	u64			kernel_address;
+	void			*kernel_address;
 	dma_addr_t		bus_address;
 	u32			pi;
 	atomic_t		ci;
@@ -544,7 +544,7 @@
  */
 struct hl_cq {
 	struct hl_device	*hdev;
-	u64			kernel_address;
+	void			*kernel_address;
 	dma_addr_t		bus_address;
 	u32			cq_idx;
 	u32			hw_queue_id;
@@ -562,7 +562,7 @@
  */
 struct hl_eq {
 	struct hl_device	*hdev;
-	u64			kernel_address;
+	void			*kernel_address;
 	dma_addr_t		bus_address;
 	u32			ci;
 };
@@ -757,7 +757,7 @@
 	u32 (*get_dma_desc_list_size)(struct hl_device *hdev,
 					struct sg_table *sgt);
 	void (*add_end_of_cb_packets)(struct hl_device *hdev,
-					u64 kernel_address, u32 len,
+					void *kernel_address, u32 len,
 					u64 cq_addr, u32 cq_val, u32 msix_num,
 					bool eb);
 	void (*update_eq_ci)(struct hl_device *hdev, u32 val);
@@ -1382,13 +1382,13 @@
 	for (;;) { \
 		/* Verify we read updates done by other cores or by device */ \
 		mb(); \
-		(val) = *((u32 *) (uintptr_t) (addr)); \
+		(val) = *((u32 *)(addr)); \
 		if (mem_written_by_device) \
 			(val) = le32_to_cpu(*(__le32 *) &(val)); \
 		if (cond) \
 			break; \
 		if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \
-			(val) = *((u32 *) (uintptr_t) (addr)); \
+			(val) = *((u32 *)(addr)); \
 			if (mem_written_by_device) \
 				(val) = le32_to_cpu(*(__le32 *) &(val)); \
 			break; \
diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c
index 5e66c98..250cf9c 100644
--- a/drivers/misc/habanalabs/common/hw_queue.c
+++ b/drivers/misc/habanalabs/common/hw_queue.c
@@ -75,7 +75,7 @@
 {
 	struct hl_bd *bd;
 
-	bd = (struct hl_bd *) (uintptr_t) q->kernel_address;
+	bd = q->kernel_address;
 	bd += hl_pi_2_offset(q->pi);
 	bd->ctl = cpu_to_le32(ctl);
 	bd->len = cpu_to_le32(len);
@@ -335,8 +335,7 @@
 	bd.len = cpu_to_le32(job->job_cb_size);
 	bd.ptr = cpu_to_le64((u64) (uintptr_t) job->user_cb);
 
-	pi = (__le64 *) (uintptr_t) (q->kernel_address +
-		((q->pi & (q->int_queue_len - 1)) * sizeof(bd)));
+	pi = q->kernel_address + (q->pi & (q->int_queue_len - 1)) * sizeof(bd);
 
 	q->pi++;
 	q->pi &= ((q->int_queue_len << 1) - 1);
@@ -630,7 +629,7 @@
 	if (!p)
 		return -ENOMEM;
 
-	q->kernel_address = (u64) (uintptr_t) p;
+	q->kernel_address = p;
 
 	q->shadow_queue = kmalloc_array(HL_QUEUE_LENGTH,
 					sizeof(*q->shadow_queue),
@@ -653,11 +652,11 @@
 	if (is_cpu_queue)
 		hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
 					HL_QUEUE_SIZE_IN_BYTES,
-					(void *) (uintptr_t) q->kernel_address);
+					q->kernel_address);
 	else
 		hdev->asic_funcs->asic_dma_free_coherent(hdev,
 					HL_QUEUE_SIZE_IN_BYTES,
-					(void *) (uintptr_t) q->kernel_address,
+					q->kernel_address,
 					q->bus_address);
 
 	return rc;
@@ -676,7 +675,7 @@
 		return -EFAULT;
 	}
 
-	q->kernel_address = (u64) (uintptr_t) p;
+	q->kernel_address = p;
 	q->pi = 0;
 	atomic_set(&q->ci, 0);
 
@@ -704,7 +703,7 @@
 	if (!p)
 		return -ENOMEM;
 
-	q->kernel_address = (u64) (uintptr_t) p;
+	q->kernel_address = p;
 
 	/* Make sure read/write pointers are initialized to start of queue */
 	atomic_set(&q->ci, 0);
@@ -839,11 +838,11 @@
 	if (q->queue_type == QUEUE_TYPE_CPU)
 		hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
 					HL_QUEUE_SIZE_IN_BYTES,
-					(void *) (uintptr_t) q->kernel_address);
+					q->kernel_address);
 	else
 		hdev->asic_funcs->asic_dma_free_coherent(hdev,
 					HL_QUEUE_SIZE_IN_BYTES,
-					(void *) (uintptr_t) q->kernel_address,
+					q->kernel_address,
 					q->bus_address);
 }
 
diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c
index d20e40a..de53fb5 100644
--- a/drivers/misc/habanalabs/common/irq.c
+++ b/drivers/misc/habanalabs/common/irq.c
@@ -90,7 +90,7 @@
 		return IRQ_HANDLED;
 	}
 
-	cq_base = (struct hl_cq_entry *) (uintptr_t) cq->kernel_address;
+	cq_base = cq->kernel_address;
 
 	while (1) {
 		bool entry_ready = ((le32_to_cpu(cq_base[cq->ci].data) &
@@ -152,7 +152,7 @@
 	struct hl_eq_entry *eq_base;
 	struct hl_eqe_work *handle_eqe_work;
 
-	eq_base = (struct hl_eq_entry *) (uintptr_t) eq->kernel_address;
+	eq_base = eq->kernel_address;
 
 	while (1) {
 		bool entry_ready =
@@ -221,7 +221,7 @@
 		return -ENOMEM;
 
 	q->hdev = hdev;
-	q->kernel_address = (u64) (uintptr_t) p;
+	q->kernel_address = p;
 	q->hw_queue_id = hw_queue_id;
 	q->ci = 0;
 	q->pi = 0;
@@ -242,7 +242,8 @@
 void hl_cq_fini(struct hl_device *hdev, struct hl_cq *q)
 {
 	hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_CQ_SIZE_IN_BYTES,
-			(void *) (uintptr_t) q->kernel_address, q->bus_address);
+						 q->kernel_address,
+						 q->bus_address);
 }
 
 void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q)
@@ -259,7 +260,7 @@
 	 * when the device is operational again
 	 */
 
-	memset((void *) (uintptr_t) q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES);
+	memset(q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES);
 }
 
 /**
@@ -282,7 +283,7 @@
 		return -ENOMEM;
 
 	q->hdev = hdev;
-	q->kernel_address = (u64) (uintptr_t) p;
+	q->kernel_address = p;
 	q->ci = 0;
 
 	return 0;
@@ -302,7 +303,7 @@
 
 	hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
 					HL_EQ_SIZE_IN_BYTES,
-					(void *) (uintptr_t) q->kernel_address);
+					q->kernel_address);
 }
 
 void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q)
@@ -316,5 +317,5 @@
 	 * when the device is operational again
 	 */
 
-	memset((void *) (uintptr_t) q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES);
+	memset(q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES);
 }
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 5f65a16..2519a34 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -680,8 +680,7 @@
 	if (!cb)
 		return -EFAULT;
 
-	init_tpc_mem_pkt = (struct packet_lin_dma *) (uintptr_t)
-					cb->kernel_address;
+	init_tpc_mem_pkt = cb->kernel_address;
 	cb_size = sizeof(*init_tpc_mem_pkt);
 	memset(init_tpc_mem_pkt, 0, cb_size);
 
@@ -3811,8 +3810,7 @@
 		u16 pkt_size;
 		struct gaudi_packet *user_pkt;
 
-		user_pkt = (struct gaudi_packet *) (uintptr_t)
-			(parser->user_cb->kernel_address + cb_parsed_length);
+		user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
 
 		pkt_id = (enum packet_id) (
 				(le64_to_cpu(user_pkt->header) &
@@ -4035,11 +4033,9 @@
 		u32 new_pkt_size = 0;
 		struct gaudi_packet *user_pkt, *kernel_pkt;
 
-		user_pkt = (struct gaudi_packet *) (uintptr_t)
-			(parser->user_cb->kernel_address + cb_parsed_length);
-		kernel_pkt = (struct gaudi_packet *) (uintptr_t)
-			(parser->patched_cb->kernel_address +
-					cb_patched_cur_length);
+		user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
+		kernel_pkt = parser->patched_cb->kernel_address +
+					cb_patched_cur_length;
 
 		pkt_id = (enum packet_id) (
 				(le64_to_cpu(user_pkt->header) &
@@ -4155,8 +4151,8 @@
 	 * The check that parser->user_cb_size <= parser->user_cb->size was done
 	 * in validate_queue_index().
 	 */
-	memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address,
-		(void *) (uintptr_t) parser->user_cb->kernel_address,
+	memcpy(parser->patched_cb->kernel_address,
+		parser->user_cb->kernel_address,
 		parser->user_cb_size);
 
 	patched_cb_size = parser->patched_cb_size;
@@ -4290,7 +4286,7 @@
 }
 
 static void gaudi_add_end_of_cb_packets(struct hl_device *hdev,
-					u64 kernel_address, u32 len,
+					void *kernel_address, u32 len,
 					u64 cq_addr, u32 cq_val, u32 msi_vec,
 					bool eb)
 {
@@ -4298,8 +4294,7 @@
 	struct packet_msg_prot *cq_pkt;
 	u32 tmp;
 
-	cq_pkt = (struct packet_msg_prot *) (uintptr_t)
-		(kernel_address + len - (sizeof(struct packet_msg_prot) * 2));
+	cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2);
 
 	tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT);
 	tmp |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1);
@@ -4342,7 +4337,7 @@
 	if (!cb)
 		return -EFAULT;
 
-	lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address;
+	lin_dma_pkt = cb->kernel_address;
 	memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt));
 	cb_size = sizeof(*lin_dma_pkt);
 
@@ -4747,7 +4742,7 @@
 			(addr - gaudi->hbm_bar_cur_addr));
 }
 
-static void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid)
+void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid)
 {
 	/* mask to zero the MMBP and ASID bits */
 	WREG32_AND(reg, ~0x7FF);
@@ -4915,9 +4910,6 @@
 	gaudi_mmu_prepare_reg(hdev, mmMME2_ACC_WBC, asid);
 	gaudi_mmu_prepare_reg(hdev, mmMME3_ACC_WBC, asid);
 
-	gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid);
-	gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid);
-
 	hdev->asic_funcs->set_clock_gating(hdev);
 
 	mutex_unlock(&gaudi->clk_gate_mutex);
@@ -4954,8 +4946,8 @@
 
 	cb = job->patched_cb;
 
-	fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address +
-			job->job_cb_size - sizeof(struct packet_msg_prot));
+	fence_pkt = cb->kernel_address +
+			job->job_cb_size - sizeof(struct packet_msg_prot);
 
 	tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT);
 	tmp |= FIELD_PREP(GAUDI_PKT_CTL_EB_MASK, 1);
@@ -6386,7 +6378,7 @@
 	struct packet_msg_short *pkt;
 	u32 value, ctl;
 
-	pkt = (struct packet_msg_short *) (uintptr_t) cb->kernel_address;
+	pkt = cb->kernel_address;
 	memset(pkt, 0, sizeof(*pkt));
 
 	/* Inc by 1, Mode ADD */
@@ -6478,7 +6470,7 @@
 			u16 sob_val, u16 mon_id, u32 q_idx)
 {
 	struct hl_cb *cb = (struct hl_cb *) data;
-	void *buf = (void *) (uintptr_t) cb->kernel_address;
+	void *buf = cb->kernel_address;
 	u64 monitor_base, fence_addr = 0;
 	u32 size = 0;
 	u16 msg_addr_offset;
diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h
index 83ad2b0..8eb598d 100644
--- a/drivers/misc/habanalabs/gaudi/gaudiP.h
+++ b/drivers/misc/habanalabs/gaudi/gaudiP.h
@@ -271,5 +271,6 @@
 int gaudi_debug_coresight(struct hl_device *hdev, void *data);
 void gaudi_halt_coresight(struct hl_device *hdev);
 int gaudi_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk);
+void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid);
 
 #endif /* GAUDIP_H_ */
diff --git a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
index 881531d..3d2b0f0 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
@@ -623,6 +623,11 @@
 			return -EINVAL;
 		}
 
+		gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER,
+						hdev->compute_ctx->asid);
+		gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER,
+						hdev->compute_ctx->asid);
+
 		msb = upper_32_bits(input->buffer_address) >> 8;
 		msb &= PSOC_GLOBAL_CONF_TRACE_ADDR_MSB_MASK;
 		WREG32(mmPSOC_GLOBAL_CONF_TRACE_ADDR, msb);
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 5db5206..235d47b 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -2882,8 +2882,8 @@
 
 	cb = job->patched_cb;
 
-	fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address +
-			job->job_cb_size - sizeof(struct packet_msg_prot));
+	fence_pkt = cb->kernel_address +
+			job->job_cb_size - sizeof(struct packet_msg_prot);
 
 	tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) |
 			(1 << GOYA_PKT_CTL_EB_SHIFT) |
@@ -3475,8 +3475,7 @@
 		u16 pkt_size;
 		struct goya_packet *user_pkt;
 
-		user_pkt = (struct goya_packet *) (uintptr_t)
-			(parser->user_cb->kernel_address + cb_parsed_length);
+		user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
 
 		pkt_id = (enum packet_id) (
 				(le64_to_cpu(user_pkt->header) &
@@ -3713,11 +3712,9 @@
 		u32 new_pkt_size = 0;
 		struct goya_packet *user_pkt, *kernel_pkt;
 
-		user_pkt = (struct goya_packet *) (uintptr_t)
-			(parser->user_cb->kernel_address + cb_parsed_length);
-		kernel_pkt = (struct goya_packet *) (uintptr_t)
-			(parser->patched_cb->kernel_address +
-					cb_patched_cur_length);
+		user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
+		kernel_pkt = parser->patched_cb->kernel_address +
+					cb_patched_cur_length;
 
 		pkt_id = (enum packet_id) (
 				(le64_to_cpu(user_pkt->header) &
@@ -3841,8 +3838,8 @@
 	 * The check that parser->user_cb_size <= parser->user_cb->size was done
 	 * in validate_queue_index().
 	 */
-	memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address,
-		(void *) (uintptr_t) parser->user_cb->kernel_address,
+	memcpy(parser->patched_cb->kernel_address,
+		parser->user_cb->kernel_address,
 		parser->user_cb_size);
 
 	patched_cb_size = parser->patched_cb_size;
@@ -3974,15 +3971,14 @@
 		return goya_parse_cb_no_mmu(hdev, parser);
 }
 
-void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address,
+void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address,
 				u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec,
 				bool eb)
 {
 	struct packet_msg_prot *cq_pkt;
 	u32 tmp;
 
-	cq_pkt = (struct packet_msg_prot *) (uintptr_t)
-		(kernel_address + len - (sizeof(struct packet_msg_prot) * 2));
+	cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2);
 
 	tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) |
 			(1 << GOYA_PKT_CTL_EB_SHIFT) |
@@ -4746,7 +4742,7 @@
 	if (!cb)
 		return -ENOMEM;
 
-	lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address;
+	lin_dma_pkt = cb->kernel_address;
 
 	do {
 		memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt));
diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h
index 09b4006..def86c7 100644
--- a/drivers/misc/habanalabs/goya/goyaP.h
+++ b/drivers/misc/habanalabs/goya/goyaP.h
@@ -217,7 +217,7 @@
 void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry);
 void *goya_get_events_stat(struct hl_device *hdev, bool aggregate, u32 *size);
 
-void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address,
+void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address,
 				u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec,
 				bool eb);
 int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser);
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
index f395721..46aed13 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
@@ -421,7 +421,6 @@
 
 #define QM_ARB_ERR_MSG_EN_MASK		(\
 					QM_ARB_ERR_MSG_EN_CHOISE_OVF_MASK |\
-					QM_ARB_ERR_MSG_EN_CHOISE_WDT_MASK |\
 					QM_ARB_ERR_MSG_EN_AXI_LBW_ERR_MASK)
 
 #define PCIE_AUX_FLR_CTRL_HW_CTRL_MASK                               0x1
diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h
index 64143d4..9e08a98 100644
--- a/drivers/misc/mei/client.h
+++ b/drivers/misc/mei/client.h
@@ -182,11 +182,11 @@
  *
  * @cl: host client
  *
- * Return: mtu
+ * Return: mtu or 0 if client is not connected
  */
 static inline size_t mei_cl_mtu(const struct mei_cl *cl)
 {
-	return cl->me_cl->props.max_msg_length;
+	return cl->me_cl ? cl->me_cl->props.max_msg_length : 0;
 }
 
 /**
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index 4143141..acb9c81 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -572,17 +572,6 @@
 					     TMIO_MASK_INIT_RCAR2);
 }
 
-/*
- * This is a temporary workaround! This driver used 'hw_reset' wrongly and the
- * fix for that showed a regression. So, we mimic the old behaviour until the
- * proper solution is found.
- */
-static void renesas_sdhi_hw_reset(struct mmc_host *mmc)
-{
-	struct tmio_mmc_host *host = mmc_priv(mmc);
-	renesas_sdhi_reset(host);
-}
-
 #define SH_MOBILE_SDHI_MIN_TAP_ROW 3
 
 static int renesas_sdhi_select_tuning(struct tmio_mmc_host *host)
@@ -1020,8 +1009,6 @@
 		if (of_data && of_data->scc_offset) {
 			priv->scc_ctl = host->ctl + of_data->scc_offset;
 			host->reset = renesas_sdhi_reset;
-			host->ops.hw_reset = renesas_sdhi_hw_reset;
-			host->mmc->caps |= MMC_CAP_HW_RESET;
 		}
 	}
 
@@ -1160,6 +1147,7 @@
 
 	tmio_mmc_host_remove(host);
 	renesas_sdhi_clk_disable(host);
+	tmio_mmc_host_free(host);
 
 	return 0;
 }
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index bb09445..ab5ab96 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -1324,6 +1324,8 @@
 
 static struct soc_device_attribute soc_unreliable_pulse_detection[] = {
 	{ .family = "QorIQ LX2160A", .revision = "1.0", },
+	{ .family = "QorIQ LX2160A", .revision = "2.0", },
+	{ .family = "QorIQ LS1028A", .revision = "1.0", },
 	{ },
 };
 
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index 2fce051..cb4149f 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -175,6 +175,8 @@
 	if (host->reset)
 		host->reset(host);
 
+	tmio_mmc_abort_dma(host);
+
 	if (host->pdata->flags & TMIO_MMC_SDIO_IRQ) {
 		sd_ctrl_write16(host, CTL_SDIO_IRQ_MASK, host->sdio_irq_mask);
 		sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0001);
@@ -223,8 +225,6 @@
 
 	/* Ready for new calls */
 	host->mrq = NULL;
-
-	tmio_mmc_abort_dma(host);
 	mmc_request_done(host->mmc, mrq);
 }
 
@@ -927,6 +927,9 @@
 	switch (ios->power_mode) {
 	case MMC_POWER_OFF:
 		tmio_mmc_power_off(host);
+		/* Downgrade ensures a sane state for tuning HW (e.g. SCC) */
+		if (host->mmc->ops->hs400_downgrade)
+			host->mmc->ops->hs400_downgrade(host->mmc);
 		host->set_clock(host, 0);
 		break;
 	case MMC_POWER_UP:
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index 0e7a9b6..e345f9d 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -707,6 +707,30 @@
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
+	struct fsl_ifc_ctrl *ctrl = priv->ctrl;
+	struct fsl_ifc_global __iomem *ifc_global = ctrl->gregs;
+	u32 csor;
+
+	csor = ifc_in32(&ifc_global->csor_cs[priv->bank].csor);
+
+	/* Must also set CSOR_NAND_ECC_ENC_EN if DEC_EN set */
+	if (csor & CSOR_NAND_ECC_DEC_EN) {
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
+		mtd_set_ooblayout(mtd, &fsl_ifc_ooblayout_ops);
+
+		/* Hardware generates ECC per 512 Bytes */
+		chip->ecc.size = 512;
+		if ((csor & CSOR_NAND_ECC_MODE_MASK) == CSOR_NAND_ECC_MODE_4) {
+			chip->ecc.bytes = 8;
+			chip->ecc.strength = 4;
+		} else {
+			chip->ecc.bytes = 16;
+			chip->ecc.strength = 8;
+		}
+	} else {
+		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+	}
 
 	dev_dbg(priv->dev, "%s: nand->numchips = %d\n", __func__,
 		nanddev_ntargets(&chip->base));
@@ -910,25 +934,6 @@
 		return -ENODEV;
 	}
 
-	/* Must also set CSOR_NAND_ECC_ENC_EN if DEC_EN set */
-	if (csor & CSOR_NAND_ECC_DEC_EN) {
-		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
-		mtd_set_ooblayout(mtd, &fsl_ifc_ooblayout_ops);
-
-		/* Hardware generates ECC per 512 Bytes */
-		chip->ecc.size = 512;
-		if ((csor & CSOR_NAND_ECC_MODE_MASK) == CSOR_NAND_ECC_MODE_4) {
-			chip->ecc.bytes = 8;
-			chip->ecc.strength = 4;
-		} else {
-			chip->ecc.bytes = 16;
-			chip->ecc.strength = 8;
-		}
-	} else {
-		chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
-		chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
-	}
-
 	ret = fsl_ifc_sram_init(priv);
 	if (ret)
 		return ret;
diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index d4200eb..684c51e 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -1681,6 +1681,11 @@
 	struct mxc_nand_host *host = nand_get_controller_data(chip);
 	struct device *dev = mtd->dev.parent;
 
+	chip->ecc.bytes = host->devtype_data->eccbytes;
+	host->eccsize = host->devtype_data->eccsize;
+	chip->ecc.size = 512;
+	mtd_set_ooblayout(mtd, host->devtype_data->ooblayout);
+
 	switch (chip->ecc.engine_type) {
 	case NAND_ECC_ENGINE_TYPE_ON_HOST:
 		chip->ecc.read_page = mxc_nand_read_page;
@@ -1836,19 +1841,7 @@
 	if (host->devtype_data->axi_offset)
 		host->regs_axi = host->base + host->devtype_data->axi_offset;
 
-	this->ecc.bytes = host->devtype_data->eccbytes;
-	host->eccsize = host->devtype_data->eccsize;
-
 	this->legacy.select_chip = host->devtype_data->select_chip;
-	this->ecc.size = 512;
-	mtd_set_ooblayout(mtd, host->devtype_data->ooblayout);
-
-	if (host->pdata.hw_ecc) {
-		this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
-	} else {
-		this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
-		this->ecc.algo = NAND_ECC_ALGO_HAMMING;
-	}
 
 	/* NAND bus width determines access functions used by upper layer */
 	if (host->pdata.width == 2)
diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index b31a581..550bda4 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -1708,6 +1708,13 @@
 		return -EINVAL;
 	}
 
+	/* Default ECC settings in case they are not set in the device tree */
+	if (!chip->ecc.size)
+		chip->ecc.size = FMC2_ECC_STEP_SIZE;
+
+	if (!chip->ecc.strength)
+		chip->ecc.strength = FMC2_ECC_BCH8;
+
 	ret = nand_ecc_choose_conf(chip, &stm32_fmc2_nfc_ecc_caps,
 				   mtd->oobsize - FMC2_BBM_LEN);
 	if (ret) {
@@ -1727,8 +1734,7 @@
 
 	mtd_set_ooblayout(mtd, &stm32_fmc2_nfc_ooblayout_ops);
 
-	if (chip->options & NAND_BUSWIDTH_16)
-		stm32_fmc2_nfc_set_buswidth_16(nfc, true);
+	stm32_fmc2_nfc_setup(chip);
 
 	return 0;
 }
@@ -1952,11 +1958,6 @@
 	chip->options |= NAND_BUSWIDTH_AUTO | NAND_NO_SUBPAGE_WRITE |
 			 NAND_USES_DMA;
 
-	/* Default ECC settings */
-	chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
-	chip->ecc.size = FMC2_ECC_STEP_SIZE;
-	chip->ecc.strength = FMC2_ECC_BCH8;
-
 	/* Scan to find existence of the device */
 	ret = nand_scan(chip, nand->ncs);
 	if (ret)
diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index 0369d98..f0ae7a0 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -2701,11 +2701,10 @@
 
 	memcpy(&sfdp_params, nor->params, sizeof(sfdp_params));
 
-	if (spi_nor_parse_sfdp(nor, &sfdp_params)) {
+	if (spi_nor_parse_sfdp(nor, nor->params)) {
+		memcpy(nor->params, &sfdp_params, sizeof(*nor->params));
 		nor->addr_width = 0;
 		nor->flags &= ~SNOR_F_4B_OPCODES;
-	} else {
-		memcpy(nor->params, &sfdp_params, sizeof(*nor->params));
 	}
 }
 
@@ -3009,13 +3008,15 @@
 		/* already configured from SFDP */
 	} else if (nor->info->addr_width) {
 		nor->addr_width = nor->info->addr_width;
-	} else if (nor->mtd.size > 0x1000000) {
-		/* enable 4-byte addressing if the device exceeds 16MiB */
-		nor->addr_width = 4;
 	} else {
 		nor->addr_width = 3;
 	}
 
+	if (nor->addr_width == 3 && nor->mtd.size > 0x1000000) {
+		/* enable 4-byte addressing if the device exceeds 16MiB */
+		nor->addr_width = 4;
+	}
+
 	if (nor->addr_width > SPI_NOR_MAX_ADDR_WIDTH) {
 		dev_dbg(nor->dev, "address width is too large: %u\n",
 			nor->addr_width);
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index b70ded3..6dee4f8 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -512,9 +512,13 @@
 		 */
 		struct sk_buff *skb = priv->echo_skb[idx];
 		struct canfd_frame *cf = (struct canfd_frame *)skb->data;
-		u8 len = cf->len;
 
-		*len_ptr = len;
+		/* get the real payload length for netdev statistics */
+		if (cf->can_id & CAN_RTR_FLAG)
+			*len_ptr = 0;
+		else
+			*len_ptr = cf->len;
+
 		priv->echo_skb[idx] = NULL;
 
 		return skb;
@@ -538,7 +542,11 @@
 	if (!skb)
 		return 0;
 
-	netif_rx(skb);
+	skb_get(skb);
+	if (netif_rx(skb) == NET_RX_SUCCESS)
+		dev_consume_skb_any(skb);
+	else
+		dev_kfree_skb_any(skb);
 
 	return len;
 }
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 4d594e9..881799b 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -217,7 +217,7 @@
  *   MX8MP FlexCAN3  03.00.17.01    yes       yes        no      yes       yes          yes
  *   VF610 FlexCAN3  ?               no       yes        no      yes       yes?          no
  * LS1021A FlexCAN2  03.00.04.00     no       yes        no       no       yes           no
- * LX2160A FlexCAN3  03.00.23.00     no       yes        no       no       yes          yes
+ * LX2160A FlexCAN3  03.00.23.00     no       yes        no      yes       yes          yes
  *
  * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected.
  */
@@ -400,19 +400,19 @@
 static const struct flexcan_devtype_data fsl_vf610_devtype_data = {
 	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
 		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP |
-		FLEXCAN_QUIRK_BROKEN_PERR_STATE,
+		FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_SUPPORT_ECC,
 };
 
 static const struct flexcan_devtype_data fsl_ls1021a_r2_devtype_data = {
 	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
-		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
-		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP,
+		FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP,
 };
 
 static const struct flexcan_devtype_data fsl_lx2160a_r1_devtype_data = {
 	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
 		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
-		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_SUPPORT_FD,
+		FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_SUPPORT_FD |
+		FLEXCAN_QUIRK_SUPPORT_ECC,
 };
 
 static const struct can_bittiming_const flexcan_bittiming_const = {
@@ -2062,6 +2062,8 @@
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
 
+	device_set_wakeup_enable(&pdev->dev, false);
+	device_set_wakeup_capable(&pdev->dev, false);
 	unregister_flexcandev(dev);
 	pm_runtime_disable(&pdev->dev);
 	free_candev(dev);
diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index 10aa3e4..40c33b8 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -262,8 +262,7 @@
 		cf_len = get_can_dlc(pucan_msg_get_dlc(msg));
 
 	/* if this frame is an echo, */
-	if ((rx_msg_flags & PUCAN_MSG_LOOPED_BACK) &&
-	    !(rx_msg_flags & PUCAN_MSG_SELF_RECEIVE)) {
+	if (rx_msg_flags & PUCAN_MSG_LOOPED_BACK) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&priv->echo_lock, flags);
@@ -277,7 +276,13 @@
 		netif_wake_queue(priv->ndev);
 
 		spin_unlock_irqrestore(&priv->echo_lock, flags);
-		return 0;
+
+		/* if this frame is only an echo, stop here. Otherwise,
+		 * continue to push this application self-received frame into
+		 * its own rx queue.
+		 */
+		if (!(rx_msg_flags & PUCAN_MSG_SELF_RECEIVE))
+			return 0;
 	}
 
 	/* otherwise, it should be pushed into rx fifo */
diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c
index 3b18026..6e95193 100644
--- a/drivers/net/can/rx-offload.c
+++ b/drivers/net/can/rx-offload.c
@@ -245,7 +245,7 @@
 
 	if (skb_queue_len(&offload->skb_queue) >
 	    offload->skb_queue_len_max) {
-		kfree_skb(skb);
+		dev_kfree_skb_any(skb);
 		return -ENOBUFS;
 	}
 
@@ -290,7 +290,7 @@
 {
 	if (skb_queue_len(&offload->skb_queue) >
 	    offload->skb_queue_len_max) {
-		kfree_skb(skb);
+		dev_kfree_skb_any(skb);
 		return -ENOBUFS;
 	}
 
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index c3f4954..9c215f7 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -75,11 +75,11 @@
 {
 	switch (model) {
 	case MCP251XFD_MODEL_MCP2517FD:
-		return "MCP2517FD"; break;
+		return "MCP2517FD";
 	case MCP251XFD_MODEL_MCP2518FD:
-		return "MCP2518FD"; break;
+		return "MCP2518FD";
 	case MCP251XFD_MODEL_MCP251XFD:
-		return "MCP251xFD"; break;
+		return "MCP251xFD";
 	}
 
 	return "<unknown>";
@@ -95,21 +95,21 @@
 {
 	switch (mode) {
 	case MCP251XFD_REG_CON_MODE_MIXED:
-		return "Mixed (CAN FD/CAN 2.0)"; break;
+		return "Mixed (CAN FD/CAN 2.0)";
 	case MCP251XFD_REG_CON_MODE_SLEEP:
-		return "Sleep"; break;
+		return "Sleep";
 	case MCP251XFD_REG_CON_MODE_INT_LOOPBACK:
-		return "Internal Loopback"; break;
+		return "Internal Loopback";
 	case MCP251XFD_REG_CON_MODE_LISTENONLY:
-		return "Listen Only"; break;
+		return "Listen Only";
 	case MCP251XFD_REG_CON_MODE_CONFIG:
-		return "Configuration"; break;
+		return "Configuration";
 	case MCP251XFD_REG_CON_MODE_EXT_LOOPBACK:
-		return "External Loopback"; break;
+		return "External Loopback";
 	case MCP251XFD_REG_CON_MODE_CAN2_0:
-		return "CAN 2.0"; break;
+		return "CAN 2.0";
 	case MCP251XFD_REG_CON_MODE_RESTRICTED:
-		return "Restricted Operation"; break;
+		return "Restricted Operation";
 	}
 
 	return "<unknown>";
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
index ba25902..314f868 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
@@ -173,7 +173,7 @@
 		memcpy(&buf_tx->cmd, reg, sizeof(buf_tx->cmd));
 		if (MCP251XFD_SANITIZE_SPI)
 			memset(buf_tx->data, 0x0, val_len);
-	};
+	}
 
 	err = spi_sync(spi, &msg);
 	if (err)
@@ -330,17 +330,17 @@
 			goto out;
 		}
 
-		netdev_dbg(priv->ndev,
-			   "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x) retrying.\n",
-			   reg, val_len, (int)val_len, buf_rx->data,
-			   get_unaligned_be16(buf_rx->data + val_len));
+		netdev_info(priv->ndev,
+			    "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x) retrying.\n",
+			    reg, val_len, (int)val_len, buf_rx->data,
+			    get_unaligned_be16(buf_rx->data + val_len));
 	}
 
 	if (err) {
-		netdev_info(priv->ndev,
-			    "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x).\n",
-			    reg, val_len, (int)val_len, buf_rx->data,
-			    get_unaligned_be16(buf_rx->data + val_len));
+		netdev_err(priv->ndev,
+			   "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x).\n",
+			   reg, val_len, (int)val_len, buf_rx->data,
+			   get_unaligned_be16(buf_rx->data + val_len));
 
 		return err;
 	}
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 1d63006..9913f54 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -933,7 +933,7 @@
 	err = clk_prepare_enable(priv->clk);
 	if (err) {
 		dev_err(&pdev->dev, "clk_prepare_enable() failed\n");
-		goto probe_exit_clk;
+		goto probe_exit_release_clk;
 	}
 
 	priv->offload.mailbox_read = ti_hecc_mailbox_read;
@@ -942,7 +942,7 @@
 	err = can_rx_offload_add_timestamp(ndev, &priv->offload);
 	if (err) {
 		dev_err(&pdev->dev, "can_rx_offload_add_timestamp() failed\n");
-		goto probe_exit_clk;
+		goto probe_exit_disable_clk;
 	}
 
 	err = register_candev(ndev);
@@ -960,7 +960,9 @@
 
 probe_exit_offload:
 	can_rx_offload_del(&priv->offload);
-probe_exit_clk:
+probe_exit_disable_clk:
+	clk_disable_unprepare(priv->clk);
+probe_exit_release_clk:
 	clk_put(priv->clk);
 probe_exit_candev:
 	free_candev(ndev);
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index d91df34..c276479 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -130,14 +130,55 @@
 	/* protect from getting time before setting now */
 	if (ktime_to_ns(time_ref->tv_host)) {
 		u64 delta_us;
+		s64 delta_ts = 0;
 
-		delta_us = ts - time_ref->ts_dev_2;
-		if (ts < time_ref->ts_dev_2)
-			delta_us &= (1 << time_ref->adapter->ts_used_bits) - 1;
+		/* General case: dev_ts_1 < dev_ts_2 < ts, with:
+		 *
+		 * - dev_ts_1 = previous sync timestamp
+		 * - dev_ts_2 = last sync timestamp
+		 * - ts = event timestamp
+		 * - ts_period = known sync period (theoretical)
+		 *             ~ dev_ts2 - dev_ts1
+		 * *but*:
+		 *
+		 * - time counters wrap (see adapter->ts_used_bits)
+		 * - sometimes, dev_ts_1 < ts < dev_ts2
+		 *
+		 * "normal" case (sync time counters increase):
+		 * must take into account case when ts wraps (tsw)
+		 *
+		 *      < ts_period > <          >
+		 *     |             |            |
+		 *  ---+--------+----+-------0-+--+-->
+		 *     ts_dev_1 |    ts_dev_2  |
+		 *              ts             tsw
+		 */
+		if (time_ref->ts_dev_1 < time_ref->ts_dev_2) {
+			/* case when event time (tsw) wraps */
+			if (ts < time_ref->ts_dev_1)
+				delta_ts = 1 << time_ref->adapter->ts_used_bits;
 
-		delta_us += time_ref->ts_total;
+		/* Otherwise, sync time counter (ts_dev_2) has wrapped:
+		 * handle case when event time (tsn) hasn't.
+		 *
+		 *      < ts_period > <          >
+		 *     |             |            |
+		 *  ---+--------+--0-+---------+--+-->
+		 *     ts_dev_1 |    ts_dev_2  |
+		 *              tsn            ts
+		 */
+		} else if (time_ref->ts_dev_1 < ts) {
+			delta_ts = -(1 << time_ref->adapter->ts_used_bits);
+		}
 
-		delta_us *= time_ref->adapter->us_per_ts_scale;
+		/* add delay between last sync and event timestamps */
+		delta_ts += (signed int)(ts - time_ref->ts_dev_2);
+
+		/* add time from beginning to last sync */
+		delta_ts += time_ref->ts_total;
+
+		/* convert ticks number into microseconds */
+		delta_us = delta_ts * time_ref->adapter->us_per_ts_scale;
 		delta_us >>= time_ref->adapter->us_per_ts_shift;
 
 		*time = ktime_add_us(time_ref->tv_host_0, delta_us);
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index ab63fd9..d29d205 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -468,12 +468,18 @@
 				     struct pucan_msg *rx_msg)
 {
 	struct pucan_rx_msg *rm = (struct pucan_rx_msg *)rx_msg;
-	struct peak_usb_device *dev = usb_if->dev[pucan_msg_get_channel(rm)];
-	struct net_device *netdev = dev->netdev;
+	struct peak_usb_device *dev;
+	struct net_device *netdev;
 	struct canfd_frame *cfd;
 	struct sk_buff *skb;
 	const u16 rx_msg_flags = le16_to_cpu(rm->flags);
 
+	if (pucan_msg_get_channel(rm) >= ARRAY_SIZE(usb_if->dev))
+		return -ENOMEM;
+
+	dev = usb_if->dev[pucan_msg_get_channel(rm)];
+	netdev = dev->netdev;
+
 	if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN) {
 		/* CANFD frame case */
 		skb = alloc_canfd_skb(netdev, &cfd);
@@ -519,15 +525,21 @@
 				     struct pucan_msg *rx_msg)
 {
 	struct pucan_status_msg *sm = (struct pucan_status_msg *)rx_msg;
-	struct peak_usb_device *dev = usb_if->dev[pucan_stmsg_get_channel(sm)];
-	struct pcan_usb_fd_device *pdev =
-			container_of(dev, struct pcan_usb_fd_device, dev);
+	struct pcan_usb_fd_device *pdev;
 	enum can_state new_state = CAN_STATE_ERROR_ACTIVE;
 	enum can_state rx_state, tx_state;
-	struct net_device *netdev = dev->netdev;
+	struct peak_usb_device *dev;
+	struct net_device *netdev;
 	struct can_frame *cf;
 	struct sk_buff *skb;
 
+	if (pucan_stmsg_get_channel(sm) >= ARRAY_SIZE(usb_if->dev))
+		return -ENOMEM;
+
+	dev = usb_if->dev[pucan_stmsg_get_channel(sm)];
+	pdev = container_of(dev, struct pcan_usb_fd_device, dev);
+	netdev = dev->netdev;
+
 	/* nothing should be sent while in BUS_OFF state */
 	if (dev->can.state == CAN_STATE_BUS_OFF)
 		return 0;
@@ -579,9 +591,14 @@
 				    struct pucan_msg *rx_msg)
 {
 	struct pucan_error_msg *er = (struct pucan_error_msg *)rx_msg;
-	struct peak_usb_device *dev = usb_if->dev[pucan_ermsg_get_channel(er)];
-	struct pcan_usb_fd_device *pdev =
-			container_of(dev, struct pcan_usb_fd_device, dev);
+	struct pcan_usb_fd_device *pdev;
+	struct peak_usb_device *dev;
+
+	if (pucan_ermsg_get_channel(er) >= ARRAY_SIZE(usb_if->dev))
+		return -EINVAL;
+
+	dev = usb_if->dev[pucan_ermsg_get_channel(er)];
+	pdev = container_of(dev, struct pcan_usb_fd_device, dev);
 
 	/* keep a trace of tx and rx error counters for later use */
 	pdev->bec.txerr = er->tx_err_cnt;
@@ -595,11 +612,17 @@
 				      struct pucan_msg *rx_msg)
 {
 	struct pcan_ufd_ovr_msg *ov = (struct pcan_ufd_ovr_msg *)rx_msg;
-	struct peak_usb_device *dev = usb_if->dev[pufd_omsg_get_channel(ov)];
-	struct net_device *netdev = dev->netdev;
+	struct peak_usb_device *dev;
+	struct net_device *netdev;
 	struct can_frame *cf;
 	struct sk_buff *skb;
 
+	if (pufd_omsg_get_channel(ov) >= ARRAY_SIZE(usb_if->dev))
+		return -EINVAL;
+
+	dev = usb_if->dev[pufd_omsg_get_channel(ov)];
+	netdev = dev->netdev;
+
 	/* allocate an skb to store the error frame */
 	skb = alloc_can_err_skb(netdev, &cf);
 	if (!skb)
@@ -716,6 +739,9 @@
 	u16 tx_msg_size, tx_msg_flags;
 	u8 can_dlc;
 
+	if (cfd->len > CANFD_MAX_DLEN)
+		return -EINVAL;
+
 	tx_msg_size = ALIGN(sizeof(struct pucan_tx_msg) + cfd->len, 4);
 	tx_msg->size = cpu_to_le16(tx_msg_size);
 	tx_msg->type = cpu_to_le16(PUCAN_MSG_CAN_TX);
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 6c4d00d..48d746e 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -1395,7 +1395,7 @@
 	if (ret < 0) {
 		netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n",
 			   __func__, ret);
-		return ret;
+		goto err;
 	}
 
 	ret = request_irq(ndev->irq, xcan_interrupt, priv->irq_flags,
@@ -1479,6 +1479,7 @@
 	if (ret < 0) {
 		netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n",
 			   __func__, ret);
+		pm_runtime_put(priv->dev);
 		return ret;
 	}
 
@@ -1793,7 +1794,7 @@
 	if (ret < 0) {
 		netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n",
 			   __func__, ret);
-		goto err_pmdisable;
+		goto err_disableclks;
 	}
 
 	if (priv->read_reg(priv, XCAN_SR_OFFSET) != XCAN_SR_CONFIG_MASK) {
@@ -1828,7 +1829,6 @@
 
 err_disableclks:
 	pm_runtime_put(priv->dev);
-err_pmdisable:
 	pm_runtime_disable(&pdev->dev);
 err_free:
 	free_candev(ndev);
diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c
index 10cd1bf..ade04c0 100644
--- a/drivers/net/dsa/mv88e6xxx/devlink.c
+++ b/drivers/net/dsa/mv88e6xxx/devlink.c
@@ -393,8 +393,10 @@
 	mv88e6xxx_reg_lock(chip);
 
 	err = mv88e6xxx_fid_map(chip, fid_bitmap);
-	if (err)
+	if (err) {
+		kfree(table);
 		goto out;
+	}
 
 	while (1) {
 		fid = find_next_bit(fid_bitmap, MV88E6XXX_N_FID, fid + 1);
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index 53064e0..5bdac66 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -1219,8 +1219,8 @@
 	priv->port_mtu[port] = new_mtu;
 
 	for (i = 0; i < QCA8K_NUM_PORTS; i++)
-		if (priv->port_mtu[port] > mtu)
-			mtu = priv->port_mtu[port];
+		if (priv->port_mtu[i] > mtu)
+			mtu = priv->port_mtu[i];
 
 	/* Include L2 header / FCS length */
 	qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, mtu + ETH_HLEN + ETH_FCS_LEN);
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 883e47c..286f034 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1929,7 +1929,8 @@
 
 static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
 {
-	bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb);
+	bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) ||
+		      skb_is_nonlinear(*skb);
 	int padlen = ETH_ZLEN - (*skb)->len;
 	int headroom = skb_headroom(*skb);
 	int tailroom = skb_tailroom(*skb);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 3352dad..2730860 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -2124,6 +2124,9 @@
 void cxgb4_write_sgl(const struct sk_buff *skb, struct sge_txq *q,
 		     struct ulptx_sgl *sgl, u64 *end, unsigned int start,
 		     const dma_addr_t *addr);
+void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q,
+			     struct ulptx_sgl *sgl, u64 *end,
+			     const dma_addr_t *addr, u32 start, u32 send_len);
 void cxgb4_ring_tx_db(struct adapter *adap, struct sge_txq *q, int n);
 int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf,
 		    u16 vlan);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 0273f40..17410fe 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -3573,6 +3573,8 @@
 		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_complete_pkts));
 	seq_printf(seq, "TX trim pkts :                    %20llu\n",
 		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_trimmed_pkts));
+	seq_printf(seq, "TX sw fallback :                  %20llu\n",
+		   atomic64_read(&adap->ch_ktls_stats.ktls_tx_fallback));
 	while (i < MAX_NPORTS) {
 		ktls_port = &adap->ch_ktls_stats.ktls_port[i];
 		seq_printf(seq, "Port %d\n", i);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index a952fe1..7fd264a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -1176,6 +1176,7 @@
 		txq = netdev_pick_tx(dev, skb, sb_dev);
 		if (xfrm_offload(skb) || is_ptp_enabled(skb, dev) ||
 		    skb->encapsulation ||
+		    cxgb4_is_ktls_skb(skb) ||
 		    (proto != IPPROTO_TCP && proto != IPPROTO_UDP))
 			txq = txq % pi->nqsets;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index b169776..1b49f2f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -388,6 +388,7 @@
 	atomic64_t ktls_tx_retransmit_pkts;
 	atomic64_t ktls_tx_complete_pkts;
 	atomic64_t ktls_tx_trimmed_pkts;
+	atomic64_t ktls_tx_fallback;
 };
 #endif
 
@@ -493,6 +494,11 @@
 #endif
 };
 
+static inline bool cxgb4_is_ktls_skb(struct sk_buff *skb)
+{
+	return skb->sk && tls_is_sk_tx_device_offloaded(skb->sk);
+}
+
 void cxgb4_uld_enable(struct adapter *adap);
 void cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p);
 int cxgb4_unregister_uld(enum cxgb4_uld type);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index a9e9c7a..196652a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -890,6 +890,114 @@
 }
 EXPORT_SYMBOL(cxgb4_write_sgl);
 
+/*	cxgb4_write_partial_sgl - populate SGL for partial packet
+ *	@skb: the packet
+ *	@q: the Tx queue we are writing into
+ *	@sgl: starting location for writing the SGL
+ *	@end: points right after the end of the SGL
+ *	@addr: the list of bus addresses for the SGL elements
+ *	@start: start offset in the SKB where partial data starts
+ *	@len: length of data from @start to send out
+ *
+ *	This API will handle sending out partial data of a skb if required.
+ *	Unlike cxgb4_write_sgl, @start can be any offset into the skb data,
+ *	and @len will decide how much data after @start offset to send out.
+ */
+void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q,
+			     struct ulptx_sgl *sgl, u64 *end,
+			     const dma_addr_t *addr, u32 start, u32 len)
+{
+	struct ulptx_sge_pair buf[MAX_SKB_FRAGS / 2 + 1] = {0}, *to;
+	u32 frag_size, skb_linear_data_len = skb_headlen(skb);
+	struct skb_shared_info *si = skb_shinfo(skb);
+	u8 i = 0, frag_idx = 0, nfrags = 0;
+	skb_frag_t *frag;
+
+	/* Fill the first SGL either from linear data or from partial
+	 * frag based on @start.
+	 */
+	if (unlikely(start < skb_linear_data_len)) {
+		frag_size = min(len, skb_linear_data_len - start);
+		sgl->len0 = htonl(frag_size);
+		sgl->addr0 = cpu_to_be64(addr[0] + start);
+		len -= frag_size;
+		nfrags++;
+	} else {
+		start -= skb_linear_data_len;
+		frag = &si->frags[frag_idx];
+		frag_size = skb_frag_size(frag);
+		/* find the first frag */
+		while (start >= frag_size) {
+			start -= frag_size;
+			frag_idx++;
+			frag = &si->frags[frag_idx];
+			frag_size = skb_frag_size(frag);
+		}
+
+		frag_size = min(len, skb_frag_size(frag) - start);
+		sgl->len0 = cpu_to_be32(frag_size);
+		sgl->addr0 = cpu_to_be64(addr[frag_idx + 1] + start);
+		len -= frag_size;
+		nfrags++;
+		frag_idx++;
+	}
+
+	/* If the entire partial data fit in one SGL, then send it out
+	 * now.
+	 */
+	if (!len)
+		goto done;
+
+	/* Most of the complexity below deals with the possibility we hit the
+	 * end of the queue in the middle of writing the SGL.  For this case
+	 * only we create the SGL in a temporary buffer and then copy it.
+	 */
+	to = (u8 *)end > (u8 *)q->stat ? buf : sgl->sge;
+
+	/* If the skb couldn't fit in first SGL completely, fill the
+	 * rest of the frags in subsequent SGLs. Note that each SGL
+	 * pair can store 2 frags.
+	 */
+	while (len) {
+		frag_size = min(len, skb_frag_size(&si->frags[frag_idx]));
+		to->len[i & 1] = cpu_to_be32(frag_size);
+		to->addr[i & 1] = cpu_to_be64(addr[frag_idx + 1]);
+		if (i && (i & 1))
+			to++;
+		nfrags++;
+		frag_idx++;
+		i++;
+		len -= frag_size;
+	}
+
+	/* If we ended in an odd boundary, then set the second SGL's
+	 * length in the pair to 0.
+	 */
+	if (i & 1)
+		to->len[1] = cpu_to_be32(0);
+
+	/* Copy from temporary buffer to Tx ring, in case we hit the
+	 * end of the queue in the middle of writing the SGL.
+	 */
+	if (unlikely((u8 *)end > (u8 *)q->stat)) {
+		u32 part0 = (u8 *)q->stat - (u8 *)sgl->sge, part1;
+
+		if (likely(part0))
+			memcpy(sgl->sge, buf, part0);
+		part1 = (u8 *)end - (u8 *)q->stat;
+		memcpy(q->desc, (u8 *)buf + part0, part1);
+		end = (void *)q->desc + part1;
+	}
+
+	/* 0-pad to multiple of 16 */
+	if ((uintptr_t)end & 8)
+		*end = 0;
+done:
+	sgl->cmd_nsge = htonl(ULPTX_CMD_V(ULP_TX_SC_DSGL) |
+			ULPTX_NSGE_V(nfrags));
+}
+EXPORT_SYMBOL(cxgb4_write_partial_sgl);
+
 /* This function copies 64 byte coalesced work request to
  * memory mapped BAR2 space. For coalesced WR SGE fetches
  * data from the FIFO instead of from Host.
@@ -1422,7 +1530,8 @@
 #endif /* CHELSIO_IPSEC_INLINE */
 
 #if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
-	if (skb->decrypted)
+	if (cxgb4_is_ktls_skb(skb) &&
+	    (skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb))))
 		return adap->uld[CXGB4_ULD_KTLS].tx_handler(skb, dev);
 #endif /* CHELSIO_TLS_DEVICE */
 
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
index 5195f69..c24485c 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c
@@ -14,6 +14,50 @@
 static LIST_HEAD(uld_ctx_list);
 static DEFINE_MUTEX(dev_mutex);
 
+/* chcr_get_nfrags_to_send: get the remaining nfrags after start offset
+ * @skb: skb
+ * @start: start offset.
+ * @len: how much data to send after @start
+ */
+static int chcr_get_nfrags_to_send(struct sk_buff *skb, u32 start, u32 len)
+{
+	struct skb_shared_info *si = skb_shinfo(skb);
+	u32 frag_size, skb_linear_data_len = skb_headlen(skb);
+	u8 nfrags = 0, frag_idx = 0;
+	skb_frag_t *frag;
+
+	/* if its a linear skb then return 1 */
+	if (!skb_is_nonlinear(skb))
+		return 1;
+
+	if (unlikely(start < skb_linear_data_len)) {
+		frag_size = min(len, skb_linear_data_len - start);
+		start = 0;
+	} else {
+		start -= skb_linear_data_len;
+
+		frag = &si->frags[frag_idx];
+		frag_size = skb_frag_size(frag);
+		while (start >= frag_size) {
+			start -= frag_size;
+			frag_idx++;
+			frag = &si->frags[frag_idx];
+			frag_size = skb_frag_size(frag);
+		}
+		frag_size = min(len, skb_frag_size(frag) - start);
+	}
+	len -= frag_size;
+	nfrags++;
+
+	while (len) {
+		frag_size = min(len, skb_frag_size(&si->frags[frag_idx]));
+		len -= frag_size;
+		nfrags++;
+		frag_idx++;
+	}
+	return nfrags;
+}
+
 static int chcr_init_tcb_fields(struct chcr_ktls_info *tx_info);
 /*
  * chcr_ktls_save_keys: calculate and save crypto keys.
@@ -689,7 +733,8 @@
 }
 
 static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info,
-					u32 tid, void *pos, u16 word, u64 mask,
+					u32 tid, void *pos, u16 word,
+					struct sge_eth_txq *q, u64 mask,
 					u64 val, u32 reply)
 {
 	struct cpl_set_tcb_field_core *cpl;
@@ -698,7 +743,10 @@
 
 	/* ULP_TXPKT */
 	txpkt = pos;
-	txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0));
+	txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) |
+				ULP_TXPKT_CHANNELID_V(tx_info->port_id) |
+				ULP_TXPKT_FID_V(q->q.cntxt_id) |
+				ULP_TXPKT_RO_F);
 	txpkt->len = htonl(DIV_ROUND_UP(CHCR_SET_TCB_FIELD_LEN, 16));
 
 	/* ULPTX_IDATA sub-command */
@@ -753,7 +801,7 @@
 		} else {
 			u8 buf[48] = {0};
 
-			__chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word,
+			__chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, q,
 						     mask, val, reply);
 
 			return chcr_copy_to_txd(buf, &q->q, pos,
@@ -761,7 +809,7 @@
 		}
 	}
 
-	pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word,
+	pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, q,
 					   mask, val, reply);
 
 	/* check again if we are at the end of the queue */
@@ -783,11 +831,11 @@
  */
 static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info,
 				   struct sge_eth_txq *q, u64 tcp_seq,
-				   u64 tcp_ack, u64 tcp_win)
+				   u64 tcp_ack, u64 tcp_win, bool offset)
 {
 	bool first_wr = ((tx_info->prev_ack == 0) && (tx_info->prev_win == 0));
 	struct ch_ktls_port_stats_debug *port_stats;
-	u32 len, cpl = 0, ndesc, wr_len;
+	u32 len, cpl = 0, ndesc, wr_len, wr_mid = 0;
 	struct fw_ulptx_wr *wr;
 	int credits;
 	void *pos;
@@ -803,6 +851,11 @@
 		return NETDEV_TX_BUSY;
 	}
 
+	if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+		chcr_eth_txq_stop(q);
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+	}
+
 	pos = &q->q.desc[q->q.pidx];
 	/* make space for WR, we'll fill it later when we know all the cpls
 	 * being sent out and have complete length.
@@ -818,7 +871,7 @@
 		cpl++;
 	}
 	/* reset snd una if it's a re-transmit pkt */
-	if (tcp_seq != tx_info->prev_seq) {
+	if (tcp_seq != tx_info->prev_seq || offset) {
 		/* reset snd_una */
 		port_stats =
 			&tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id];
@@ -827,7 +880,8 @@
 						 TCB_SND_UNA_RAW_V
 						 (TCB_SND_UNA_RAW_M),
 						 TCB_SND_UNA_RAW_V(0), 0);
-		atomic64_inc(&port_stats->ktls_tx_ooo);
+		if (tcp_seq != tx_info->prev_seq)
+			atomic64_inc(&port_stats->ktls_tx_ooo);
 		cpl++;
 	}
 	/* update ack */
@@ -856,7 +910,8 @@
 		wr->op_to_compl = htonl(FW_WR_OP_V(FW_ULPTX_WR));
 		wr->cookie = 0;
 		/* fill len in wr field */
-		wr->flowid_len16 = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(len, 16)));
+		wr->flowid_len16 = htonl(wr_mid |
+					 FW_WR_LEN16_V(DIV_ROUND_UP(len, 16)));
 
 		ndesc = DIV_ROUND_UP(len, 64);
 		chcr_txq_advance(&q->q, ndesc);
@@ -866,34 +921,14 @@
 }
 
 /*
- * chcr_ktls_skb_copy
- * @nskb - new skb where the frags to be added.
- * @skb - old skb from which frags will be copied.
- */
-static void chcr_ktls_skb_copy(struct sk_buff *skb, struct sk_buff *nskb)
-{
-	int i;
-
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		skb_shinfo(nskb)->frags[i] = skb_shinfo(skb)->frags[i];
-		__skb_frag_ref(&skb_shinfo(nskb)->frags[i]);
-	}
-
-	skb_shinfo(nskb)->nr_frags = skb_shinfo(skb)->nr_frags;
-	nskb->len += skb->data_len;
-	nskb->data_len = skb->data_len;
-	nskb->truesize += skb->data_len;
-}
-
-/*
  * chcr_ktls_get_tx_flits
  * returns number of flits to be sent out, it includes key context length, WR
  * size and skb fragments.
  */
 static unsigned int
-chcr_ktls_get_tx_flits(const struct sk_buff *skb, unsigned int key_ctx_len)
+chcr_ktls_get_tx_flits(u32 nr_frags, unsigned int key_ctx_len)
 {
-	return chcr_sgl_len(skb_shinfo(skb)->nr_frags) +
+	return chcr_sgl_len(nr_frags) +
 	       DIV_ROUND_UP(key_ctx_len + CHCR_KTLS_WR_SIZE, 8);
 }
 
@@ -957,8 +992,10 @@
 	struct tcphdr *tcp;
 	int len16, pktlen;
 	struct iphdr *ip;
+	u32 wr_mid = 0;
 	int credits;
 	u8 buf[150];
+	u64 cntrl1;
 	void *pos;
 
 	iplen = skb_network_header_len(skb);
@@ -967,7 +1004,7 @@
 	/* packet length = eth hdr len + ip hdr len + tcp hdr len
 	 * (including options).
 	 */
-	pktlen = skb->len - skb->data_len;
+	pktlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
 
 	ctrl = sizeof(*cpl) + pktlen;
 	len16 = DIV_ROUND_UP(sizeof(*wr) + ctrl, 16);
@@ -980,6 +1017,11 @@
 		return NETDEV_TX_BUSY;
 	}
 
+	if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+		chcr_eth_txq_stop(q);
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+	}
+
 	pos = &q->q.desc[q->q.pidx];
 	wr = pos;
 
@@ -987,7 +1029,7 @@
 	wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) |
 			       FW_WR_IMMDLEN_V(ctrl));
 
-	wr->equiq_to_len16 = htonl(FW_WR_LEN16_V(len16));
+	wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16));
 	wr->r3 = 0;
 
 	cpl = (void *)(wr + 1);
@@ -997,22 +1039,28 @@
 			   TXPKT_PF_V(tx_info->adap->pf));
 	cpl->pack = 0;
 	cpl->len = htons(pktlen);
-	/* checksum offload */
-	cpl->ctrl1 = 0;
-
-	pos = cpl + 1;
 
 	memcpy(buf, skb->data, pktlen);
 	if (tx_info->ip_family == AF_INET) {
 		/* we need to correct ip header len */
 		ip = (struct iphdr *)(buf + maclen);
 		ip->tot_len = htons(pktlen - maclen);
+		cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
 		ip6 = (struct ipv6hdr *)(buf + maclen);
 		ip6->payload_len = htons(pktlen - maclen - iplen);
+		cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP6);
 #endif
 	}
+
+	cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) |
+		  TXPKT_IPHDR_LEN_V(iplen);
+	/* checksum offload */
+	cpl->ctrl1 = cpu_to_be64(cntrl1);
+
+	pos = cpl + 1;
+
 	/* now take care of the tcp header, if fin is not set then clear push
 	 * bit as well, and if fin is set, it will be sent at the last so we
 	 * need to update the tcp sequence number as per the last packet.
@@ -1031,71 +1079,6 @@
 	return 0;
 }
 
-/* chcr_ktls_skb_shift - Shifts request length paged data from skb to another.
- * @tgt- buffer into which tail data gets added
- * @skb- buffer from which the paged data comes from
- * @shiftlen- shift up to this many bytes
- */
-static int chcr_ktls_skb_shift(struct sk_buff *tgt, struct sk_buff *skb,
-			       int shiftlen)
-{
-	skb_frag_t *fragfrom, *fragto;
-	int from, to, todo;
-
-	WARN_ON(shiftlen > skb->data_len);
-
-	todo = shiftlen;
-	from = 0;
-	to = 0;
-	fragfrom = &skb_shinfo(skb)->frags[from];
-
-	while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) {
-		fragfrom = &skb_shinfo(skb)->frags[from];
-		fragto = &skb_shinfo(tgt)->frags[to];
-
-		if (todo >= skb_frag_size(fragfrom)) {
-			*fragto = *fragfrom;
-			todo -= skb_frag_size(fragfrom);
-			from++;
-			to++;
-
-		} else {
-			__skb_frag_ref(fragfrom);
-			skb_frag_page_copy(fragto, fragfrom);
-			skb_frag_off_copy(fragto, fragfrom);
-			skb_frag_size_set(fragto, todo);
-
-			skb_frag_off_add(fragfrom, todo);
-			skb_frag_size_sub(fragfrom, todo);
-			todo = 0;
-
-			to++;
-			break;
-		}
-	}
-
-	/* Ready to "commit" this state change to tgt */
-	skb_shinfo(tgt)->nr_frags = to;
-
-	/* Reposition in the original skb */
-	to = 0;
-	while (from < skb_shinfo(skb)->nr_frags)
-		skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++];
-
-	skb_shinfo(skb)->nr_frags = to;
-
-	WARN_ON(todo > 0 && !skb_shinfo(skb)->nr_frags);
-
-	skb->len -= shiftlen;
-	skb->data_len -= shiftlen;
-	skb->truesize -= shiftlen;
-	tgt->len += shiftlen;
-	tgt->data_len += shiftlen;
-	tgt->truesize += shiftlen;
-
-	return shiftlen;
-}
-
 /*
  * chcr_ktls_xmit_wr_complete: This sends out the complete record. If an skb
  * received has partial end part of the record, send out the complete record, so
@@ -1111,6 +1094,8 @@
 static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb,
 				      struct chcr_ktls_info *tx_info,
 				      struct sge_eth_txq *q, u32 tcp_seq,
+				      bool is_last_wr, u32 data_len,
+				      u32 skb_offset, u32 nfrags,
 				      bool tcp_push, u32 mss)
 {
 	u32 len16, wr_mid = 0, flits = 0, ndesc, cipher_start;
@@ -1126,7 +1111,7 @@
 	u64 *end;
 
 	/* get the number of flits required */
-	flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len);
+	flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len);
 	/* number of descriptors */
 	ndesc = chcr_flits_to_desc(flits);
 	/* check if enough credits available */
@@ -1155,6 +1140,9 @@
 		return NETDEV_TX_BUSY;
 	}
 
+	if (!is_last_wr)
+		skb_get(skb);
+
 	pos = &q->q.desc[q->q.pidx];
 	end = (u64 *)pos + flits;
 	/* FW_ULPTX_WR */
@@ -1187,7 +1175,7 @@
 		      CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) |
 		      CPL_TX_SEC_PDU_PLACEHOLDER_V(1) |
 		      CPL_TX_SEC_PDU_IVINSRTOFST_V(TLS_HEADER_SIZE + 1));
-	cpl->pldlen = htonl(skb->data_len);
+	cpl->pldlen = htonl(data_len);
 
 	/* encryption should start after tls header size + iv size */
 	cipher_start = TLS_HEADER_SIZE + tx_info->iv_size + 1;
@@ -1229,7 +1217,7 @@
 	/* CPL_TX_DATA */
 	tx_data = (void *)pos;
 	OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid));
-	tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(skb->data_len));
+	tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(data_len));
 
 	tx_data->rsvd = htonl(tcp_seq);
 
@@ -1249,8 +1237,8 @@
 	}
 
 	/* send the complete packet except the header */
-	cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len,
-			sgl_sdesc->addr);
+	cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr,
+				skb_offset, data_len);
 	sgl_sdesc->skb = skb;
 
 	chcr_txq_advance(&q->q, ndesc);
@@ -1282,10 +1270,11 @@
 				   struct sge_eth_txq *q,
 				   u32 tcp_seq, bool tcp_push, u32 mss,
 				   u32 tls_rec_offset, u8 *prior_data,
-				   u32 prior_data_len)
+				   u32 prior_data_len, u32 data_len,
+				   u32 skb_offset)
 {
+	u32 len16, wr_mid = 0, cipher_start, nfrags;
 	struct adapter *adap = tx_info->adap;
-	u32 len16, wr_mid = 0, cipher_start;
 	unsigned int flits = 0, ndesc;
 	int credits, left, last_desc;
 	struct tx_sw_desc *sgl_sdesc;
@@ -1298,10 +1287,11 @@
 	void *pos;
 	u64 *end;
 
+	nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len);
 	/* get the number of flits required, it's a partial record so 2 flits
 	 * (AES_BLOCK_SIZE) will be added.
 	 */
-	flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len) + 2;
+	flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len) + 2;
 	/* get the correct 8 byte IV of this record */
 	iv_record = cpu_to_be64(tx_info->iv + tx_info->record_no);
 	/* If it's a middle record and not 16 byte aligned to run AES CTR, need
@@ -1373,7 +1363,7 @@
 		htonl(CPL_TX_SEC_PDU_OPCODE_V(CPL_TX_SEC_PDU) |
 		      CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) |
 		      CPL_TX_SEC_PDU_IVINSRTOFST_V(1));
-	cpl->pldlen = htonl(skb->data_len + AES_BLOCK_LEN + prior_data_len);
+	cpl->pldlen = htonl(data_len + AES_BLOCK_LEN + prior_data_len);
 	cpl->aadstart_cipherstop_hi =
 		htonl(CPL_TX_SEC_PDU_CIPHERSTART_V(cipher_start));
 	cpl->cipherstop_lo_authinsert = 0;
@@ -1404,7 +1394,7 @@
 	tx_data = (void *)pos;
 	OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid));
 	tx_data->len = htonl(TX_DATA_MSS_V(mss) |
-			TX_LENGTH_V(skb->data_len + prior_data_len));
+			     TX_LENGTH_V(data_len + prior_data_len));
 	tx_data->rsvd = htonl(tcp_seq);
 	tx_data->flags = htonl(TX_BYPASS_F);
 	if (tcp_push)
@@ -1437,8 +1427,8 @@
 	if (prior_data_len)
 		pos = chcr_copy_to_txd(prior_data, &q->q, pos, 16);
 	/* send the complete packet except the header */
-	cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len,
-			sgl_sdesc->addr);
+	cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr,
+				skb_offset, data_len);
 	sgl_sdesc->skb = skb;
 
 	chcr_txq_advance(&q->q, ndesc);
@@ -1466,6 +1456,7 @@
 				 struct sk_buff *skb, u32 tcp_seq, u32 mss,
 				 bool tcp_push, struct sge_eth_txq *q,
 				 u32 port_id, u8 *prior_data,
+				 u32 data_len, u32 skb_offset,
 				 u32 prior_data_len)
 {
 	int credits, left, len16, last_desc;
@@ -1475,14 +1466,16 @@
 	struct ulptx_idata *idata;
 	struct ulp_txpkt *ulptx;
 	struct fw_ulptx_wr *wr;
-	u32 wr_mid = 0;
+	u32 wr_mid = 0, nfrags;
 	void *pos;
 	u64 *end;
 
 	flits = DIV_ROUND_UP(CHCR_PLAIN_TX_DATA_LEN, 8);
-	flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags);
+	nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len);
+	flits += chcr_sgl_len(nfrags);
 	if (prior_data_len)
 		flits += 2;
+
 	/* WR will need len16 */
 	len16 = DIV_ROUND_UP(flits, 2);
 	/* check how many descriptors needed */
@@ -1535,7 +1528,7 @@
 	tx_data = (struct cpl_tx_data *)(idata + 1);
 	OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid));
 	tx_data->len = htonl(TX_DATA_MSS_V(mss) |
-			TX_LENGTH_V(skb->data_len + prior_data_len));
+			     TX_LENGTH_V(data_len + prior_data_len));
 	/* set tcp seq number */
 	tx_data->rsvd = htonl(tcp_seq);
 	tx_data->flags = htonl(TX_BYPASS_F);
@@ -1559,8 +1552,8 @@
 		end = pos + left;
 	}
 	/* send the complete packet including the header */
-	cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len,
-			sgl_sdesc->addr);
+	cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr,
+				skb_offset, data_len);
 	sgl_sdesc->skb = skb;
 
 	chcr_txq_advance(&q->q, ndesc);
@@ -1568,12 +1561,96 @@
 	return 0;
 }
 
+static int chcr_ktls_tunnel_pkt(struct chcr_ktls_info *tx_info,
+				struct sk_buff *skb,
+				struct sge_eth_txq *q)
+{
+	u32 ctrl, iplen, maclen, wr_mid = 0, len16;
+	struct tx_sw_desc *sgl_sdesc;
+	struct fw_eth_tx_pkt_wr *wr;
+	struct cpl_tx_pkt_core *cpl;
+	unsigned int flits, ndesc;
+	int credits, last_desc;
+	u64 cntrl1, *end;
+	void *pos;
+
+	ctrl = sizeof(*cpl);
+	flits = DIV_ROUND_UP(sizeof(*wr) + ctrl, 8);
+
+	flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags + 1);
+	len16 = DIV_ROUND_UP(flits, 2);
+	/* check how many descriptors needed */
+	ndesc = DIV_ROUND_UP(flits, 8);
+
+	credits = chcr_txq_avail(&q->q) - ndesc;
+	if (unlikely(credits < 0)) {
+		chcr_eth_txq_stop(q);
+		return -ENOMEM;
+	}
+
+	if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+		chcr_eth_txq_stop(q);
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+	}
+
+	last_desc = q->q.pidx + ndesc - 1;
+	if (last_desc >= q->q.size)
+		last_desc -= q->q.size;
+	sgl_sdesc = &q->q.sdesc[last_desc];
+
+	if (unlikely(cxgb4_map_skb(tx_info->adap->pdev_dev, skb,
+				   sgl_sdesc->addr) < 0)) {
+		memset(sgl_sdesc->addr, 0, sizeof(sgl_sdesc->addr));
+		q->mapping_err++;
+		return -ENOMEM;
+	}
+
+	iplen = skb_network_header_len(skb);
+	maclen = skb_mac_header_len(skb);
+
+	pos = &q->q.desc[q->q.pidx];
+	end = (u64 *)pos + flits;
+	wr = pos;
+
+	/* Firmware work request header */
+	wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) |
+			       FW_WR_IMMDLEN_V(ctrl));
+
+	wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16));
+	wr->r3 = 0;
+
+	cpl = (void *)(wr + 1);
+
+	/* CPL header */
+	cpl->ctrl0 = htonl(TXPKT_OPCODE_V(CPL_TX_PKT) |
+			   TXPKT_INTF_V(tx_info->tx_chan) |
+			   TXPKT_PF_V(tx_info->adap->pf));
+	cpl->pack = 0;
+	cntrl1 = TXPKT_CSUM_TYPE_V(tx_info->ip_family == AF_INET ?
+				   TX_CSUM_TCPIP : TX_CSUM_TCPIP6);
+	cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) |
+		  TXPKT_IPHDR_LEN_V(iplen);
+	/* checksum offload */
+	cpl->ctrl1 = cpu_to_be64(cntrl1);
+	cpl->len = htons(skb->len);
+
+	pos = cpl + 1;
+
+	cxgb4_write_sgl(skb, &q->q, pos, end, 0, sgl_sdesc->addr);
+	sgl_sdesc->skb = skb;
+	chcr_txq_advance(&q->q, ndesc);
+	cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc);
+	return 0;
+}
+
 /*
  * chcr_ktls_copy_record_in_skb
  * @nskb - new skb where the frags to be added.
+ * @skb - old skb, to copy socket and destructor details.
  * @record - specific record which has complete 16k record in frags.
  */
 static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb,
+					 struct sk_buff *skb,
 					 struct tls_record_info *record)
 {
 	int i = 0;
@@ -1588,6 +1665,9 @@
 	nskb->data_len = record->len;
 	nskb->len += record->len;
 	nskb->truesize += record->len;
+	nskb->sk = skb->sk;
+	nskb->destructor = skb->destructor;
+	refcount_add(nskb->truesize, &nskb->sk->sk_wmem_alloc);
 }
 
 /*
@@ -1659,7 +1739,7 @@
 				 struct sk_buff *skb,
 				 struct tls_record_info *record,
 				 u32 tcp_seq, int mss, bool tcp_push_no_fin,
-				 struct sge_eth_txq *q,
+				 struct sge_eth_txq *q, u32 skb_offset,
 				 u32 tls_end_offset, bool last_wr)
 {
 	struct sk_buff *nskb = NULL;
@@ -1668,30 +1748,37 @@
 		nskb = skb;
 		atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_complete_pkts);
 	} else {
-		dev_kfree_skb_any(skb);
-
-		nskb = alloc_skb(0, GFP_KERNEL);
-		if (!nskb)
+		nskb = alloc_skb(0, GFP_ATOMIC);
+		if (!nskb) {
+			dev_kfree_skb_any(skb);
 			return NETDEV_TX_BUSY;
+		}
+
 		/* copy complete record in skb */
-		chcr_ktls_copy_record_in_skb(nskb, record);
+		chcr_ktls_copy_record_in_skb(nskb, skb, record);
 		/* packet is being sent from the beginning, update the tcp_seq
 		 * accordingly.
 		 */
 		tcp_seq = tls_record_start_seq(record);
-		/* reset snd una, so the middle record won't send the already
-		 * sent part.
-		 */
-		if (chcr_ktls_update_snd_una(tx_info, q))
-			goto out;
+		/* reset skb offset */
+		skb_offset = 0;
+
+		if (last_wr)
+			dev_kfree_skb_any(skb);
+
+		last_wr = true;
+
 		atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_end_pkts);
 	}
 
 	if (chcr_ktls_xmit_wr_complete(nskb, tx_info, q, tcp_seq,
+				       last_wr, record->len, skb_offset,
+				       record->num_frags,
 				       (last_wr && tcp_push_no_fin),
 				       mss)) {
 		goto out;
 	}
+	tx_info->prev_seq = record->end_seq;
 	return 0;
 out:
 	dev_kfree_skb_any(nskb);
@@ -1723,41 +1810,47 @@
 				     struct sk_buff *skb,
 				     struct tls_record_info *record,
 				     u32 tcp_seq, int mss, bool tcp_push_no_fin,
+				     u32 data_len, u32 skb_offset,
 				     struct sge_eth_txq *q, u32 tls_end_offset)
 {
 	u32 tls_rec_offset = tcp_seq - tls_record_start_seq(record);
 	u8 prior_data[16] = {0};
 	u32 prior_data_len = 0;
-	u32 data_len;
 
 	/* check if the skb is ending in middle of tag/HASH, its a big
 	 * trouble, send the packet before the HASH.
 	 */
-	int remaining_record = tls_end_offset - skb->data_len;
+	int remaining_record = tls_end_offset - data_len;
 
 	if (remaining_record > 0 &&
 	    remaining_record < TLS_CIPHER_AES_GCM_128_TAG_SIZE) {
-		int trimmed_len = skb->data_len -
-			(TLS_CIPHER_AES_GCM_128_TAG_SIZE - remaining_record);
-		struct sk_buff *tmp_skb = NULL;
-		/* don't process the pkt if it is only a partial tag */
-		if (skb->data_len < TLS_CIPHER_AES_GCM_128_TAG_SIZE)
-			goto out;
+		int trimmed_len = 0;
 
-		WARN_ON(trimmed_len > skb->data_len);
+		if (tls_end_offset > TLS_CIPHER_AES_GCM_128_TAG_SIZE)
+			trimmed_len = data_len -
+				      (TLS_CIPHER_AES_GCM_128_TAG_SIZE -
+				       remaining_record);
+		if (!trimmed_len)
+			return FALLBACK;
 
-		/* shift to those many bytes */
-		tmp_skb = alloc_skb(0, GFP_KERNEL);
-		if (unlikely(!tmp_skb))
-			goto out;
+		WARN_ON(trimmed_len > data_len);
 
-		chcr_ktls_skb_shift(tmp_skb, skb, trimmed_len);
-		/* free the last trimmed portion */
-		dev_kfree_skb_any(skb);
-		skb = tmp_skb;
+		data_len = trimmed_len;
 		atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_trimmed_pkts);
 	}
-	data_len = skb->data_len;
+
+	/* check if it is only the header part. */
+	if (tls_rec_offset + data_len <= (TLS_HEADER_SIZE + tx_info->iv_size)) {
+		if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss,
+					  tcp_push_no_fin, q,
+					  tx_info->port_id, prior_data,
+					  data_len, skb_offset, prior_data_len))
+			goto out;
+
+		tx_info->prev_seq = tcp_seq + data_len;
+		return 0;
+	}
+
 	/* check if the middle record's start point is 16 byte aligned. CTR
 	 * needs 16 byte aligned start point to start encryption.
 	 */
@@ -1818,9 +1911,6 @@
 			}
 			/* reset tcp_seq as per the prior_data_required len */
 			tcp_seq -= prior_data_len;
-			/* include prio_data_len for  further calculation.
-			 */
-			data_len += prior_data_len;
 		}
 		/* reset snd una, so the middle record won't send the already
 		 * sent part.
@@ -1829,37 +1919,54 @@
 			goto out;
 		atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_middle_pkts);
 	} else {
-		/* Else means, its a partial first part of the record. Check if
-		 * its only the header, don't need to send for encryption then.
-		 */
-		if (data_len <= TLS_HEADER_SIZE + tx_info->iv_size) {
-			if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss,
-						  tcp_push_no_fin, q,
-						  tx_info->port_id,
-						  prior_data,
-						  prior_data_len)) {
-				goto out;
-			}
-			return 0;
-		}
 		atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_start_pkts);
 	}
 
 	if (chcr_ktls_xmit_wr_short(skb, tx_info, q, tcp_seq, tcp_push_no_fin,
 				    mss, tls_rec_offset, prior_data,
-				    prior_data_len)) {
+				    prior_data_len, data_len, skb_offset)) {
 		goto out;
 	}
 
+	tx_info->prev_seq = tcp_seq + data_len + prior_data_len;
 	return 0;
 out:
 	dev_kfree_skb_any(skb);
 	return NETDEV_TX_BUSY;
 }
 
+static int chcr_ktls_sw_fallback(struct sk_buff *skb,
+				 struct chcr_ktls_info *tx_info,
+				 struct sge_eth_txq *q)
+{
+	u32 data_len, skb_offset;
+	struct sk_buff *nskb;
+	struct tcphdr *th;
+
+	nskb = tls_encrypt_skb(skb);
+
+	if (!nskb)
+		return 0;
+
+	th = tcp_hdr(nskb);
+	skb_offset =  skb_transport_offset(nskb) + tcp_hdrlen(nskb);
+	data_len = nskb->len - skb_offset;
+	skb_tx_timestamp(nskb);
+
+	if (chcr_ktls_tunnel_pkt(tx_info, nskb, q))
+		goto out;
+
+	tx_info->prev_seq = ntohl(th->seq) + data_len;
+	atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_fallback);
+	return 0;
+out:
+	dev_kfree_skb_any(nskb);
+	return 0;
+}
 /* nic tls TX handler */
 static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	u32 tls_end_offset, tcp_seq, skb_data_len, skb_offset;
 	struct ch_ktls_port_stats_debug *port_stats;
 	struct chcr_ktls_ofld_ctx_tx *tx_ctx;
 	struct ch_ktls_stats_debug *stats;
@@ -1867,20 +1974,17 @@
 	int data_len, qidx, ret = 0, mss;
 	struct tls_record_info *record;
 	struct chcr_ktls_info *tx_info;
-	u32 tls_end_offset, tcp_seq;
 	struct tls_context *tls_ctx;
-	struct sk_buff *local_skb;
 	struct sge_eth_txq *q;
 	struct adapter *adap;
 	unsigned long flags;
 
 	tcp_seq = ntohl(th->seq);
+	skb_offset = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	skb_data_len = skb->len - skb_offset;
+	data_len = skb_data_len;
 
-	mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : skb->data_len;
-
-	/* check if we haven't set it for ktls offload */
-	if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk))
-		goto out;
+	mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : data_len;
 
 	tls_ctx = tls_get_ctx(skb->sk);
 	if (unlikely(tls_ctx->netdev != dev))
@@ -1892,14 +1996,6 @@
 	if (unlikely(!tx_info))
 		goto out;
 
-	/* don't touch the original skb, make a new skb to extract each records
-	 * and send them separately.
-	 */
-	local_skb = alloc_skb(0, GFP_KERNEL);
-
-	if (unlikely(!local_skb))
-		return NETDEV_TX_BUSY;
-
 	adap = tx_info->adap;
 	stats = &adap->ch_ktls_stats;
 	port_stats = &stats->ktls_port[tx_info->port_id];
@@ -1914,20 +2010,7 @@
 		if (ret)
 			return NETDEV_TX_BUSY;
 	}
-	/* update tcb */
-	ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, ntohl(th->seq),
-				      ntohl(th->ack_seq),
-				      ntohs(th->window));
-	if (ret) {
-		dev_kfree_skb_any(local_skb);
-		return NETDEV_TX_BUSY;
-	}
 
-	/* copy skb contents into local skb */
-	chcr_ktls_skb_copy(skb, local_skb);
-
-	/* go through the skb and send only one record at a time. */
-	data_len = skb->data_len;
 	/* TCP segments can be in received either complete or partial.
 	 * chcr_end_part_handler will handle cases if complete record or end
 	 * part of the record is received. Incase of partial end part of record,
@@ -1952,10 +2035,64 @@
 			goto out;
 		}
 
+		tls_end_offset = record->end_seq - tcp_seq;
+
+		pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n",
+			 tcp_seq, record->end_seq, tx_info->prev_seq, data_len);
+		/* update tcb for the skb */
+		if (skb_data_len == data_len) {
+			u32 tx_max = tcp_seq;
+
+			if (!tls_record_is_start_marker(record) &&
+			    tls_end_offset < TLS_CIPHER_AES_GCM_128_TAG_SIZE)
+				tx_max = record->end_seq -
+					TLS_CIPHER_AES_GCM_128_TAG_SIZE;
+
+			ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, tx_max,
+						      ntohl(th->ack_seq),
+						      ntohs(th->window),
+						      tls_end_offset !=
+						      record->len);
+			if (ret) {
+				spin_unlock_irqrestore(&tx_ctx->base.lock,
+						       flags);
+				goto out;
+			}
+
+			if (th->fin)
+				skb_get(skb);
+		}
+
 		if (unlikely(tls_record_is_start_marker(record))) {
-			spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
 			atomic64_inc(&port_stats->ktls_tx_skip_no_sync_data);
-			goto out;
+			/* If tls_end_offset < data_len, means there is some
+			 * data after start marker, which needs encryption, send
+			 * plaintext first and take skb refcount. else send out
+			 * complete pkt as plaintext.
+			 */
+			if (tls_end_offset < data_len)
+				skb_get(skb);
+			else
+				tls_end_offset = data_len;
+
+			ret = chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss,
+						    (!th->fin && th->psh), q,
+						    tx_info->port_id, NULL,
+						    tls_end_offset, skb_offset,
+						    0);
+
+			spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
+			if (ret) {
+				/* free the refcount taken earlier */
+				if (tls_end_offset < data_len)
+					dev_kfree_skb_any(skb);
+				goto out;
+			}
+
+			data_len -= tls_end_offset;
+			tcp_seq = record->end_seq;
+			skb_offset += tls_end_offset;
+			continue;
 		}
 
 		/* increase page reference count of the record, so that there
@@ -1967,73 +2104,64 @@
 		/* lock cleared */
 		spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
 
-		tls_end_offset = record->end_seq - tcp_seq;
 
-		pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n",
-			 tcp_seq, record->end_seq, tx_info->prev_seq, data_len);
 		/* if a tls record is finishing in this SKB */
 		if (tls_end_offset <= data_len) {
-			struct sk_buff *nskb = NULL;
-
-			if (tls_end_offset < data_len) {
-				nskb = alloc_skb(0, GFP_KERNEL);
-				if (unlikely(!nskb)) {
-					ret = -ENOMEM;
-					goto clear_ref;
-				}
-
-				chcr_ktls_skb_shift(nskb, local_skb,
-						    tls_end_offset);
-			} else {
-				/* its the only record in this skb, directly
-				 * point it.
-				 */
-				nskb = local_skb;
-			}
-			ret = chcr_end_part_handler(tx_info, nskb, record,
+			ret = chcr_end_part_handler(tx_info, skb, record,
 						    tcp_seq, mss,
 						    (!th->fin && th->psh), q,
+						    skb_offset,
 						    tls_end_offset,
-						    (nskb == local_skb));
-
-			if (ret && nskb != local_skb)
-				dev_kfree_skb_any(local_skb);
+						    skb_offset +
+						    tls_end_offset == skb->len);
 
 			data_len -= tls_end_offset;
 			/* tcp_seq increment is required to handle next record.
 			 */
 			tcp_seq += tls_end_offset;
+			skb_offset += tls_end_offset;
 		} else {
-			ret = chcr_short_record_handler(tx_info, local_skb,
+			ret = chcr_short_record_handler(tx_info, skb,
 							record, tcp_seq, mss,
 							(!th->fin && th->psh),
+							data_len, skb_offset,
 							q, tls_end_offset);
 			data_len = 0;
 		}
-clear_ref:
+
 		/* clear the frag ref count which increased locally before */
 		for (i = 0; i < record->num_frags; i++) {
 			/* clear the frag ref count */
 			__skb_frag_unref(&record->frags[i]);
 		}
 		/* if any failure, come out from the loop. */
-		if (ret)
-			goto out;
+		if (ret) {
+			if (th->fin)
+				dev_kfree_skb_any(skb);
+
+			if (ret == FALLBACK)
+				return chcr_ktls_sw_fallback(skb, tx_info, q);
+
+			return NETDEV_TX_OK;
+		}
+
 		/* length should never be less than 0 */
 		WARN_ON(data_len < 0);
 
 	} while (data_len > 0);
 
-	tx_info->prev_seq = ntohl(th->seq) + skb->data_len;
 	atomic64_inc(&port_stats->ktls_tx_encrypted_packets);
-	atomic64_add(skb->data_len, &port_stats->ktls_tx_encrypted_bytes);
+	atomic64_add(skb_data_len, &port_stats->ktls_tx_encrypted_bytes);
 
 	/* tcp finish is set, send a separate tcp msg including all the options
 	 * as well.
 	 */
-	if (th->fin)
+	if (th->fin) {
 		chcr_ktls_write_tcp_options(tx_info, skb, q, tx_info->tx_chan);
+		dev_kfree_skb_any(skb);
+	}
 
+	return NETDEV_TX_OK;
 out:
 	dev_kfree_skb_any(skb);
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h
index c1651b1..18b3b1f 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h
+++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h
@@ -26,6 +26,7 @@
 
 #define CHCR_KTLS_WR_SIZE	(CHCR_PLAIN_TX_DATA_LEN +\
 				 sizeof(struct cpl_tx_sec_pdu))
+#define FALLBACK		35
 
 enum ch_ktls_open_state {
 	CH_KTLS_OPEN_SUCCESS = 0,
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
index d581c4e..96d5616 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c
@@ -212,7 +212,7 @@
 {
 	if (likely(skb && !skb_shared(skb) && !skb_cloned(skb))) {
 		__skb_trim(skb, 0);
-		refcount_add(2, &skb->users);
+		refcount_inc(&skb->users);
 	} else {
 		skb = alloc_skb(len, GFP_KERNEL | __GFP_NOFAIL);
 	}
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c
index f1820ac..62c8290 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_hw.c
@@ -383,6 +383,9 @@
 	if (ret)
 		goto out_notcb;
 
+	if (unlikely(csk_flag(sk, CSK_ABORT_SHUTDOWN)))
+		goto out_notcb;
+
 	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->tlshws.txqid);
 	csk->wr_credits -= DIV_ROUND_UP(len, 16);
 	csk->wr_unacked += DIV_ROUND_UP(len, 16);
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 06cc863..d9c2859 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -174,12 +174,17 @@
 #define DPAA_PARSE_RESULTS_SIZE sizeof(struct fman_prs_result)
 #define DPAA_TIME_STAMP_SIZE 8
 #define DPAA_HASH_RESULTS_SIZE 8
-#ifdef CONFIG_DPAA_ERRATUM_A050385
-#define DPAA_RX_PRIV_DATA_SIZE (DPAA_A050385_ALIGN - (DPAA_PARSE_RESULTS_SIZE\
-	 + DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE))
-#else
-#define DPAA_RX_PRIV_DATA_SIZE	(u16)(DPAA_TX_PRIV_DATA_SIZE + \
+#define DPAA_HWA_SIZE (DPAA_PARSE_RESULTS_SIZE + DPAA_TIME_STAMP_SIZE \
+		       + DPAA_HASH_RESULTS_SIZE)
+#define DPAA_RX_PRIV_DATA_DEFAULT_SIZE (DPAA_TX_PRIV_DATA_SIZE + \
 					dpaa_rx_extra_headroom)
+#ifdef CONFIG_DPAA_ERRATUM_A050385
+#define DPAA_RX_PRIV_DATA_A050385_SIZE (DPAA_A050385_ALIGN - DPAA_HWA_SIZE)
+#define DPAA_RX_PRIV_DATA_SIZE (fman_has_errata_a050385() ? \
+				DPAA_RX_PRIV_DATA_A050385_SIZE : \
+				DPAA_RX_PRIV_DATA_DEFAULT_SIZE)
+#else
+#define DPAA_RX_PRIV_DATA_SIZE DPAA_RX_PRIV_DATA_DEFAULT_SIZE
 #endif
 
 #define DPAA_ETH_PCD_RXQ_NUM	128
@@ -2840,7 +2845,8 @@
 	return err;
 }
 
-static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl)
+static u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl,
+			     enum port_type port)
 {
 	u16 headroom;
 
@@ -2854,10 +2860,12 @@
 	 *
 	 * Also make sure the headroom is a multiple of data_align bytes
 	 */
-	headroom = (u16)(bl->priv_data_size + DPAA_PARSE_RESULTS_SIZE +
-		DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE);
+	headroom = (u16)(bl[port].priv_data_size + DPAA_HWA_SIZE);
 
-	return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT);
+	if (port == RX)
+		return ALIGN(headroom, DPAA_FD_RX_DATA_ALIGNMENT);
+	else
+		return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT);
 }
 
 static int dpaa_eth_probe(struct platform_device *pdev)
@@ -3025,8 +3033,8 @@
 			goto free_dpaa_fqs;
 	}
 
-	priv->tx_headroom = dpaa_get_headroom(&priv->buf_layout[TX]);
-	priv->rx_headroom = dpaa_get_headroom(&priv->buf_layout[RX]);
+	priv->tx_headroom = dpaa_get_headroom(priv->buf_layout, TX);
+	priv->rx_headroom = dpaa_get_headroom(priv->buf_layout, RX);
 
 	/* All real interfaces need their ports initialized */
 	err = dpaa_eth_init_ports(mac_dev, dpaa_bp, &port_fqs,
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 832a2175..c527f4e 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -456,6 +456,12 @@
  */
 #define FEC_QUIRK_HAS_FRREG		(1 << 16)
 
+/* Some FEC hardware blocks need the MMFR cleared at setup time to avoid
+ * the generation of an MII event. This must be avoided in the older
+ * FEC blocks where it will stop MII events being generated.
+ */
+#define FEC_QUIRK_CLEAR_SETUP_MII	(1 << 17)
+
 struct bufdesc_prop {
 	int qid;
 	/* Address of Rx and Tx buffers */
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8f7eca1..d791955 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -100,14 +100,14 @@
 static const struct fec_devinfo fec_imx28_info = {
 	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
 		  FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC |
-		  FEC_QUIRK_HAS_FRREG,
+		  FEC_QUIRK_HAS_FRREG | FEC_QUIRK_CLEAR_SETUP_MII,
 };
 
 static const struct fec_devinfo fec_imx6q_info = {
 	.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
 		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
 		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
-		  FEC_QUIRK_HAS_RACC,
+		  FEC_QUIRK_HAS_RACC | FEC_QUIRK_CLEAR_SETUP_MII,
 };
 
 static const struct fec_devinfo fec_mvf600_info = {
@@ -119,7 +119,8 @@
 		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
 		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
 		  FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
-		  FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE,
+		  FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE |
+		  FEC_QUIRK_CLEAR_SETUP_MII,
 };
 
 static const struct fec_devinfo fec_imx6ul_info = {
@@ -127,7 +128,7 @@
 		  FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
 		  FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 |
 		  FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC |
-		  FEC_QUIRK_HAS_COALESCE,
+		  FEC_QUIRK_HAS_COALESCE | FEC_QUIRK_CLEAR_SETUP_MII,
 };
 
 static struct platform_device_id fec_devtype[] = {
@@ -2134,15 +2135,17 @@
 	if (suppress_preamble)
 		fep->phy_speed |= BIT(7);
 
-	/* Clear MMFR to avoid to generate MII event by writing MSCR.
-	 * MII event generation condition:
-	 * - writing MSCR:
-	 *	- mmfr[31:0]_not_zero & mscr[7:0]_is_zero &
-	 *	  mscr_reg_data_in[7:0] != 0
-	 * - writing MMFR:
-	 *	- mscr[7:0]_not_zero
-	 */
-	writel(0, fep->hwp + FEC_MII_DATA);
+	if (fep->quirks & FEC_QUIRK_CLEAR_SETUP_MII) {
+		/* Clear MMFR to avoid to generate MII event by writing MSCR.
+		 * MII event generation condition:
+		 * - writing MSCR:
+		 *	- mmfr[31:0]_not_zero & mscr[7:0]_is_zero &
+		 *	  mscr_reg_data_in[7:0] != 0
+		 * - writing MMFR:
+		 *	- mscr[7:0]_not_zero
+		 */
+		writel(0, fep->hwp + FEC_MII_DATA);
+	}
 
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 41dd3d0..d391a45 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1829,20 +1829,12 @@
 		fcb_len = GMAC_FCB_LEN + GMAC_TXPAL_LEN;
 
 	/* make space for additional header when fcb is needed */
-	if (fcb_len && unlikely(skb_headroom(skb) < fcb_len)) {
-		struct sk_buff *skb_new;
-
-		skb_new = skb_realloc_headroom(skb, fcb_len);
-		if (!skb_new) {
+	if (fcb_len) {
+		if (unlikely(skb_cow_head(skb, fcb_len))) {
 			dev->stats.tx_errors++;
 			dev_kfree_skb_any(skb);
 			return NETDEV_TX_OK;
 		}
-
-		if (skb->sk)
-			skb_set_owner_w(skb_new, skb->sk);
-		dev_consume_skb_any(skb);
-		skb = skb_new;
 	}
 
 	/* total number of fragments in the SKB */
@@ -3380,7 +3372,7 @@
 
 	if (dev->features & NETIF_F_IP_CSUM ||
 	    priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)
-		dev->needed_headroom = GMAC_FCB_LEN;
+		dev->needed_headroom = GMAC_FCB_LEN + GMAC_TXPAL_LEN;
 
 	/* Initializing some of the rx/tx queue level parameters */
 	for (i = 0; i < priv->num_tx_queues; i++) {
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index af4dfbe..da15913 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1185,18 +1185,27 @@
 	if (adapter->state != VNIC_CLOSED) {
 		rc = ibmvnic_login(netdev);
 		if (rc)
-			return rc;
+			goto out;
 
 		rc = init_resources(adapter);
 		if (rc) {
 			netdev_err(netdev, "failed to initialize resources\n");
 			release_resources(adapter);
-			return rc;
+			goto out;
 		}
 	}
 
 	rc = __ibmvnic_open(netdev);
 
+out:
+	/*
+	 * If open fails due to a pending failover, set device state and
+	 * return. Device operation will be handled by reset routine.
+	 */
+	if (rc && adapter->failover_pending) {
+		adapter->state = VNIC_OPEN;
+		rc = 0;
+	}
 	return rc;
 }
 
@@ -1922,6 +1931,13 @@
 		   rwi->reset_reason);
 
 	rtnl_lock();
+	/*
+	 * Now that we have the rtnl lock, clear any pending failover.
+	 * This will ensure ibmvnic_open() has either completed or will
+	 * block until failover is complete.
+	 */
+	if (rwi->reset_reason == VNIC_RESET_FAILOVER)
+		adapter->failover_pending = false;
 
 	netif_carrier_off(netdev);
 	adapter->reset_reason = rwi->reset_reason;
@@ -2202,6 +2218,13 @@
 			/* CHANGE_PARAM requestor holds rtnl_lock */
 			rc = do_change_param_reset(adapter, rwi, reset_state);
 		} else if (adapter->force_reset_recovery) {
+			/*
+			 * Since we are doing a hard reset now, clear the
+			 * failover_pending flag so we don't ignore any
+			 * future MOBILITY or other resets.
+			 */
+			adapter->failover_pending = false;
+
 			/* Transport event occurred during previous reset */
 			if (adapter->wait_for_reset) {
 				/* Previous was CHANGE_PARAM; caller locked */
@@ -2266,9 +2289,15 @@
 	unsigned long flags;
 	int ret;
 
+	/*
+	 * If failover is pending don't schedule any other reset.
+	 * Instead let the failover complete. If there is already a
+	 * a failover reset scheduled, we will detect and drop the
+	 * duplicate reset when walking the ->rwi_list below.
+	 */
 	if (adapter->state == VNIC_REMOVING ||
 	    adapter->state == VNIC_REMOVED ||
-	    adapter->failover_pending) {
+	    (adapter->failover_pending && reason != VNIC_RESET_FAILOVER)) {
 		ret = EBUSY;
 		netdev_dbg(netdev, "Adapter removing or pending failover, skipping reset\n");
 		goto err;
@@ -4713,7 +4742,6 @@
 		case IBMVNIC_CRQ_INIT:
 			dev_info(dev, "Partner initialized\n");
 			adapter->from_passive_init = true;
-			adapter->failover_pending = false;
 			if (!completion_done(&adapter->init_done)) {
 				complete(&adapter->init_done);
 				adapter->init_done_rc = -EIO;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index c96e2f2..4919d22d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -2713,6 +2713,10 @@
 				spin_unlock_bh(&vsi->mac_filter_hash_lock);
 				goto error_param;
 			}
+			if (is_valid_ether_addr(al->list[i].addr) &&
+			    is_zero_ether_addr(vf->default_lan_addr.addr))
+				ether_addr_copy(vf->default_lan_addr.addr,
+						al->list[i].addr);
 		}
 	}
 	spin_unlock_bh(&vsi->mac_filter_hash_lock);
@@ -2740,6 +2744,7 @@
 {
 	struct virtchnl_ether_addr_list *al =
 	    (struct virtchnl_ether_addr_list *)msg;
+	bool was_unimac_deleted = false;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = NULL;
 	i40e_status ret = 0;
@@ -2759,6 +2764,8 @@
 			ret = I40E_ERR_INVALID_MAC_ADDR;
 			goto error_param;
 		}
+		if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr))
+			was_unimac_deleted = true;
 	}
 	vsi = pf->vsi[vf->lan_vsi_idx];
 
@@ -2779,10 +2786,25 @@
 		dev_err(&pf->pdev->dev, "Unable to program VF %d MAC filters, error %d\n",
 			vf->vf_id, ret);
 
+	if (vf->trusted && was_unimac_deleted) {
+		struct i40e_mac_filter *f;
+		struct hlist_node *h;
+		u8 *macaddr = NULL;
+		int bkt;
+
+		/* set last unicast mac address as default */
+		spin_lock_bh(&vsi->mac_filter_hash_lock);
+		hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
+			if (is_valid_ether_addr(f->macaddr))
+				macaddr = f->macaddr;
+		}
+		if (macaddr)
+			ether_addr_copy(vf->default_lan_addr.addr, macaddr);
+		spin_unlock_bh(&vsi->mac_filter_hash_lock);
+	}
 error_param:
 	/* send the response to the VF */
-	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR,
-				       ret);
+	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, ret);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 6acede0..567fd67 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -281,8 +281,8 @@
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
 	unsigned int xdp_res, xdp_xmit = 0;
+	bool failure = false;
 	struct sk_buff *skb;
-	bool failure;
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union i40e_rx_desc *rx_desc;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 9112dff..b673ac1 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3891,21 +3891,23 @@
 }
 
 /**
- * igc_get_stats - Get System Network Statistics
+ * igc_get_stats64 - Get System Network Statistics
  * @netdev: network interface device structure
+ * @stats: rtnl_link_stats64 pointer
  *
  * Returns the address of the device statistics structure.
  * The statistics are updated here and also from the timer callback.
  */
-static struct net_device_stats *igc_get_stats(struct net_device *netdev)
+static void igc_get_stats64(struct net_device *netdev,
+			    struct rtnl_link_stats64 *stats)
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
+	spin_lock(&adapter->stats64_lock);
 	if (!test_bit(__IGC_RESETTING, &adapter->state))
 		igc_update_stats(adapter);
-
-	/* only return the current stats */
-	return &netdev->stats;
+	memcpy(stats, &adapter->stats64, sizeof(*stats));
+	spin_unlock(&adapter->stats64_lock);
 }
 
 static netdev_features_t igc_fix_features(struct net_device *netdev,
@@ -4855,7 +4857,7 @@
 	.ndo_set_rx_mode	= igc_set_rx_mode,
 	.ndo_set_mac_address	= igc_set_mac,
 	.ndo_change_mtu		= igc_change_mtu,
-	.ndo_get_stats		= igc_get_stats,
+	.ndo_get_stats64	= igc_get_stats64,
 	.ndo_fix_features	= igc_fix_features,
 	.ndo_set_features	= igc_set_features,
 	.ndo_features_check	= igc_features_check,
diff --git a/drivers/net/ethernet/marvell/prestera/Kconfig b/drivers/net/ethernet/marvell/prestera/Kconfig
index b1fcc44..b6f20e2 100644
--- a/drivers/net/ethernet/marvell/prestera/Kconfig
+++ b/drivers/net/ethernet/marvell/prestera/Kconfig
@@ -6,6 +6,7 @@
 config PRESTERA
 	tristate "Marvell Prestera Switch ASICs support"
 	depends on NET_SWITCHDEV && VLAN_8021Q
+	depends on BRIDGE || BRIDGE=n
 	select NET_DEVLINK
 	help
 	  This driver supports Marvell Prestera Switch ASICs family.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index e36e505..d29af7b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -107,12 +107,16 @@
 		mlx5e_tc_encap_flows_del(priv, e, &flow_list);
 
 	if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) {
+		struct net_device *route_dev;
+
 		ether_addr_copy(e->h_dest, ha);
 		ether_addr_copy(eth->h_dest, ha);
 		/* Update the encap source mac, in case that we delete
 		 * the flows when encap source mac changed.
 		 */
-		ether_addr_copy(eth->h_source, e->route_dev->dev_addr);
+		route_dev = __dev_get_by_index(dev_net(priv->netdev), e->route_dev_ifindex);
+		if (route_dev)
+			ether_addr_copy(eth->h_source, route_dev->dev_addr);
 
 		mlx5e_tc_encap_flows_add(priv, e, &flow_list);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 7cce85f..90930e5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -77,13 +77,13 @@
 	return 0;
 }
 
-static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
-				   struct net_device *mirred_dev,
-				   struct net_device **out_dev,
-				   struct net_device **route_dev,
-				   struct flowi4 *fl4,
-				   struct neighbour **out_n,
-				   u8 *out_ttl)
+static int mlx5e_route_lookup_ipv4_get(struct mlx5e_priv *priv,
+				       struct net_device *mirred_dev,
+				       struct net_device **out_dev,
+				       struct net_device **route_dev,
+				       struct flowi4 *fl4,
+				       struct neighbour **out_n,
+				       u8 *out_ttl)
 {
 	struct neighbour *n;
 	struct rtable *rt;
@@ -117,18 +117,28 @@
 		ip_rt_put(rt);
 		return ret;
 	}
+	dev_hold(*route_dev);
 
 	if (!(*out_ttl))
 		*out_ttl = ip4_dst_hoplimit(&rt->dst);
 	n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
 	ip_rt_put(rt);
-	if (!n)
+	if (!n) {
+		dev_put(*route_dev);
 		return -ENOMEM;
+	}
 
 	*out_n = n;
 	return 0;
 }
 
+static void mlx5e_route_lookup_ipv4_put(struct net_device *route_dev,
+					struct neighbour *n)
+{
+	neigh_release(n);
+	dev_put(route_dev);
+}
+
 static const char *mlx5e_netdev_kind(struct net_device *dev)
 {
 	if (dev->rtnl_link_ops)
@@ -193,8 +203,8 @@
 	fl4.saddr = tun_key->u.ipv4.src;
 	ttl = tun_key->ttl;
 
-	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, &route_dev,
-				      &fl4, &n, &ttl);
+	err = mlx5e_route_lookup_ipv4_get(priv, mirred_dev, &out_dev, &route_dev,
+					  &fl4, &n, &ttl);
 	if (err)
 		return err;
 
@@ -223,7 +233,7 @@
 	e->m_neigh.family = n->ops->family;
 	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
 	e->out_dev = out_dev;
-	e->route_dev = route_dev;
+	e->route_dev_ifindex = route_dev->ifindex;
 
 	/* It's important to add the neigh to the hash table before checking
 	 * the neigh validity state. So if we'll get a notification, in case the
@@ -278,7 +288,7 @@
 
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
 	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
-	neigh_release(n);
+	mlx5e_route_lookup_ipv4_put(route_dev, n);
 	return err;
 
 destroy_neigh_entry:
@@ -286,18 +296,18 @@
 free_encap:
 	kfree(encap_header);
 release_neigh:
-	neigh_release(n);
+	mlx5e_route_lookup_ipv4_put(route_dev, n);
 	return err;
 }
 
 #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
-static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
-				   struct net_device *mirred_dev,
-				   struct net_device **out_dev,
-				   struct net_device **route_dev,
-				   struct flowi6 *fl6,
-				   struct neighbour **out_n,
-				   u8 *out_ttl)
+static int mlx5e_route_lookup_ipv6_get(struct mlx5e_priv *priv,
+				       struct net_device *mirred_dev,
+				       struct net_device **out_dev,
+				       struct net_device **route_dev,
+				       struct flowi6 *fl6,
+				       struct neighbour **out_n,
+				       u8 *out_ttl)
 {
 	struct dst_entry *dst;
 	struct neighbour *n;
@@ -318,15 +328,25 @@
 		return ret;
 	}
 
+	dev_hold(*route_dev);
 	n = dst_neigh_lookup(dst, &fl6->daddr);
 	dst_release(dst);
-	if (!n)
+	if (!n) {
+		dev_put(*route_dev);
 		return -ENOMEM;
+	}
 
 	*out_n = n;
 	return 0;
 }
 
+static void mlx5e_route_lookup_ipv6_put(struct net_device *route_dev,
+					struct neighbour *n)
+{
+	neigh_release(n);
+	dev_put(route_dev);
+}
+
 int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 				    struct net_device *mirred_dev,
 				    struct mlx5e_encap_entry *e)
@@ -348,8 +368,8 @@
 	fl6.daddr = tun_key->u.ipv6.dst;
 	fl6.saddr = tun_key->u.ipv6.src;
 
-	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, &route_dev,
-				      &fl6, &n, &ttl);
+	err = mlx5e_route_lookup_ipv6_get(priv, mirred_dev, &out_dev, &route_dev,
+					  &fl6, &n, &ttl);
 	if (err)
 		return err;
 
@@ -378,7 +398,7 @@
 	e->m_neigh.family = n->ops->family;
 	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
 	e->out_dev = out_dev;
-	e->route_dev = route_dev;
+	e->route_dev_ifindex = route_dev->ifindex;
 
 	/* It's importent to add the neigh to the hash table before checking
 	 * the neigh validity state. So if we'll get a notification, in case the
@@ -433,7 +453,7 @@
 
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
 	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
-	neigh_release(n);
+	mlx5e_route_lookup_ipv6_put(route_dev, n);
 	return err;
 
 destroy_neigh_entry:
@@ -441,7 +461,7 @@
 free_encap:
 	kfree(encap_header);
 release_neigh:
-	neigh_release(n);
+	mlx5e_route_lookup_ipv6_put(route_dev, n);
 	return err;
 }
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 4e574ac..be3465b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -122,9 +122,9 @@
 	set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
 	/* TX queue is created active. */
 
-	spin_lock(&c->async_icosq_lock);
+	spin_lock_bh(&c->async_icosq_lock);
 	mlx5e_trigger_irq(&c->async_icosq);
-	spin_unlock(&c->async_icosq_lock);
+	spin_unlock_bh(&c->async_icosq_lock);
 }
 
 void mlx5e_deactivate_xsk(struct mlx5e_channel *c)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index fb671a4..8e96260 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -36,9 +36,9 @@
 		if (test_and_set_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->async_icosq.state))
 			return 0;
 
-		spin_lock(&c->async_icosq_lock);
+		spin_lock_bh(&c->async_icosq_lock);
 		mlx5e_trigger_irq(&c->async_icosq);
-		spin_unlock(&c->async_icosq_lock);
+		spin_unlock_bh(&c->async_icosq_lock);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index ccaccb9..7f6221b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -188,7 +188,7 @@
 
 	err = 0;
 	sq = &c->async_icosq;
-	spin_lock(&c->async_icosq_lock);
+	spin_lock_bh(&c->async_icosq_lock);
 
 	cseg = post_static_params(sq, priv_rx);
 	if (IS_ERR(cseg))
@@ -199,7 +199,7 @@
 
 	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
 unlock:
-	spin_unlock(&c->async_icosq_lock);
+	spin_unlock_bh(&c->async_icosq_lock);
 
 	return err;
 
@@ -265,10 +265,10 @@
 
 	BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1);
 
-	spin_lock(&sq->channel->async_icosq_lock);
+	spin_lock_bh(&sq->channel->async_icosq_lock);
 
 	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
-		spin_unlock(&sq->channel->async_icosq_lock);
+		spin_unlock_bh(&sq->channel->async_icosq_lock);
 		err = -ENOSPC;
 		goto err_dma_unmap;
 	}
@@ -299,7 +299,7 @@
 	icosq_fill_wi(sq, pi, &wi);
 	sq->pc++;
 	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
-	spin_unlock(&sq->channel->async_icosq_lock);
+	spin_unlock_bh(&sq->channel->async_icosq_lock);
 
 	return 0;
 
@@ -360,7 +360,7 @@
 	err = 0;
 
 	sq = &c->async_icosq;
-	spin_lock(&c->async_icosq_lock);
+	spin_lock_bh(&c->async_icosq_lock);
 
 	cseg = post_static_params(sq, priv_rx);
 	if (IS_ERR(cseg)) {
@@ -372,7 +372,7 @@
 	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
 	priv_rx->stats->tls_resync_res_ok++;
 unlock:
-	spin_unlock(&c->async_icosq_lock);
+	spin_unlock_bh(&c->async_icosq_lock);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b3f02aa..ebce979 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5253,6 +5253,7 @@
 
 	mlx5e_disable_async_events(priv);
 	mlx5_lag_remove(mdev);
+	mlx5_vxlan_reset_to_default(mdev->vxlan);
 }
 
 int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 9020d14..8932c38 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -186,7 +186,7 @@
 	unsigned char h_dest[ETH_ALEN];	/* destination eth addr	*/
 
 	struct net_device *out_dev;
-	struct net_device *route_dev;
+	int route_dev_ifindex;
 	struct mlx5e_tc_tunnel *tunnel;
 	int reformat_type;
 	u8 flags;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 599f5b5..6628a01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1584,7 +1584,7 @@
 	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq)));
 
 out:
-	if (rq->xdp_prog)
+	if (rcu_access_pointer(rq->xdp_prog))
 		mlx5e_xdp_rx_poll_complete(rq);
 
 	mlx5_cqwq_update_db_record(cqwq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e3a968e..2e2fa04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4658,6 +4658,7 @@
 	return flow;
 
 err_free:
+	dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
 	mlx5e_flow_put(priv, flow);
 out:
 	return ERR_PTR(err);
@@ -4802,6 +4803,7 @@
 	return 0;
 
 err_free:
+	dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
 	mlx5e_flow_put(priv, flow);
 out:
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 6e6a9a56..e8e6294 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1902,8 +1902,6 @@
 		ether_addr_copy(hw_addr, vport->info.mac);
 		*hw_addr_len = ETH_ALEN;
 		err = 0;
-	} else {
-		NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled");
 	}
 	mutex_unlock(&esw->state_lock);
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 1609183..325a5b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2010,10 +2010,11 @@
 	down_write_ref_node(&fte->node, false);
 	for (i = handle->num_rules - 1; i >= 0; i--)
 		tree_remove_node(&handle->rule[i]->node, true);
-	if (fte->modify_mask && fte->dests_size) {
-		modify_fte(fte);
+	if (fte->dests_size) {
+		if (fte->modify_mask)
+			modify_fte(fte);
 		up_write_ref_node(&fte->node, false);
-	} else {
+	} else if (list_empty(&fte->node.children)) {
 		del_hw_fte(&fte->node);
 		/* Avoid double call to del_hw_fte */
 		fte->node.del_hw_func = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
index 3315afe..3808440 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
@@ -168,6 +168,17 @@
 
 void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan)
 {
+	if (!mlx5_vxlan_allowed(vxlan))
+		return;
+
+	mlx5_vxlan_del_port(vxlan, IANA_VXLAN_UDP_PORT);
+	WARN_ON(!hash_empty(vxlan->htable));
+
+	kfree(vxlan);
+}
+
+void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan)
+{
 	struct mlx5_vxlan_port *vxlanp;
 	struct hlist_node *tmp;
 	int bkt;
@@ -175,12 +186,12 @@
 	if (!mlx5_vxlan_allowed(vxlan))
 		return;
 
-	/* Lockless since we are the only hash table consumers*/
 	hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) {
-		hash_del(&vxlanp->hlist);
-		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port);
-		kfree(vxlanp);
+		/* Don't delete default UDP port added by the HW.
+		 * Remove only user configured ports
+		 */
+		if (vxlanp->udp_port == IANA_VXLAN_UDP_PORT)
+			continue;
+		mlx5_vxlan_del_port(vxlan, vxlanp->udp_port);
 	}
-
-	kfree(vxlan);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
index ec76652..34ef662 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
@@ -56,6 +56,7 @@
 int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
 int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
 bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
+void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan);
 #else
 static inline struct mlx5_vxlan*
 mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-EOPNOTSUPP); }
@@ -63,6 +64,7 @@
 static inline int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
 static inline int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
 static inline bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) { return false; }
+static inline void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan) { return; }
 #endif
 
 #endif /* __MLX5_VXLAN_H__ */
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index a1938842..e2c99d9 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -674,14 +674,12 @@
 static int lan743x_dp_write(struct lan743x_adapter *adapter,
 			    u32 select, u32 addr, u32 length, u32 *buf)
 {
-	int ret = -EIO;
 	u32 dp_sel;
 	int i;
 
-	mutex_lock(&adapter->dp_lock);
 	if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_,
 				     1, 40, 100, 100))
-		goto unlock;
+		return -EIO;
 	dp_sel = lan743x_csr_read(adapter, DP_SEL);
 	dp_sel &= ~DP_SEL_MASK_;
 	dp_sel |= select;
@@ -693,13 +691,10 @@
 		lan743x_csr_write(adapter, DP_CMD, DP_CMD_WRITE_);
 		if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_,
 					     1, 40, 100, 100))
-			goto unlock;
+			return -EIO;
 	}
-	ret = 0;
 
-unlock:
-	mutex_unlock(&adapter->dp_lock);
-	return ret;
+	return 0;
 }
 
 static u32 lan743x_mac_mii_access(u16 id, u16 index, int read)
@@ -1019,16 +1014,16 @@
 static int lan743x_phy_open(struct lan743x_adapter *adapter)
 {
 	struct lan743x_phy *phy = &adapter->phy;
+	struct phy_device *phydev = NULL;
 	struct device_node *phynode;
-	struct phy_device *phydev;
 	struct net_device *netdev;
 	int ret = -EIO;
 
 	netdev = adapter->netdev;
 	phynode = of_node_get(adapter->pdev->dev.of_node);
-	adapter->phy_mode = PHY_INTERFACE_MODE_GMII;
 
 	if (phynode) {
+		/* try devicetree phy, or fixed link */
 		of_get_phy_mode(phynode, &adapter->phy_mode);
 
 		if (of_phy_is_fixed_link(phynode)) {
@@ -1044,13 +1039,15 @@
 					lan743x_phy_link_status_change, 0,
 					adapter->phy_mode);
 		of_node_put(phynode);
-		if (!phydev)
-			goto return_error;
-	} else {
+	}
+
+	if (!phydev) {
+		/* try internal phy */
 		phydev = phy_find_first(adapter->mdiobus);
 		if (!phydev)
 			goto return_error;
 
+		adapter->phy_mode = PHY_INTERFACE_MODE_GMII;
 		ret = phy_connect_direct(netdev, phydev,
 					 lan743x_phy_link_status_change,
 					 adapter->phy_mode);
@@ -2733,7 +2730,6 @@
 
 	adapter->intr.irq = adapter->pdev->irq;
 	lan743x_csr_write(adapter, INT_EN_CLR, 0xFFFFFFFF);
-	mutex_init(&adapter->dp_lock);
 
 	ret = lan743x_gpio_init(adapter);
 	if (ret)
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index c61a4041..a536f4a 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -712,9 +712,6 @@
 	struct lan743x_csr      csr;
 	struct lan743x_intr     intr;
 
-	/* lock, used to prevent concurrent access to data port */
-	struct mutex		dp_lock;
-
 	struct lan743x_gpio	gpio;
 	struct lan743x_ptp	ptp;
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index ed9808f..35c72d4 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -126,6 +126,11 @@
 
 	ethtool_link_ksettings_zero_link_mode(ks, supported);
 
+	if (!idev->port_info) {
+		netdev_err(netdev, "port_info not initialized\n");
+		return -EOPNOTSUPP;
+	}
+
 	/* The port_info data is found in a DMA space that the NIC keeps
 	 * up-to-date, so there's no need to request the data from the
 	 * NIC, we already have it in our memory space.
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 00f1380..85d9c3e 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4080,9 +4080,17 @@
 	return -EIO;
 }
 
-static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp, struct sk_buff *skb)
+static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp)
 {
-	return skb->len < ETH_ZLEN && tp->mac_version == RTL_GIGA_MAC_VER_34;
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_60:
+	case RTL_GIGA_MAC_VER_61:
+	case RTL_GIGA_MAC_VER_63:
+		return true;
+	default:
+		return false;
+	}
 }
 
 static void rtl8169_tso_csum_v1(struct sk_buff *skb, u32 *opts)
@@ -4154,8 +4162,9 @@
 
 		opts[1] |= transport_offset << TCPHO_SHIFT;
 	} else {
-		if (unlikely(rtl_test_hw_pad_bug(tp, skb)))
-			return !eth_skb_pad(skb);
+		if (unlikely(skb->len < ETH_ZLEN && rtl_test_hw_pad_bug(tp)))
+			/* eth_skb_pad would free the skb on error */
+			return !__skb_put_padto(skb, ETH_ZLEN, false);
 	}
 
 	return true;
@@ -4334,18 +4343,9 @@
 		    rtl_chip_supports_csum_v2(tp))
 			features &= ~NETIF_F_ALL_TSO;
 	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		if (skb->len < ETH_ZLEN) {
-			switch (tp->mac_version) {
-			case RTL_GIGA_MAC_VER_11:
-			case RTL_GIGA_MAC_VER_12:
-			case RTL_GIGA_MAC_VER_17:
-			case RTL_GIGA_MAC_VER_34:
-				features &= ~NETIF_F_CSUM_MASK;
-				break;
-			default:
-				break;
-			}
-		}
+		/* work around hw bug on some chip versions */
+		if (skb->len < ETH_ZLEN)
+			features &= ~NETIF_F_CSUM_MASK;
 
 		if (transport_offset > TCPHO_MAX &&
 		    rtl_chip_supports_csum_v2(tp))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index b6e5e3e..81ee0a0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -625,13 +625,6 @@
 	if (ret)
 		return ret;
 
-	if (plat->eee_usecs_rate > 0) {
-		u32 tx_lpi_usec;
-
-		tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1;
-		writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER);
-	}
-
 	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
 	if (ret < 0)
 		return ret;
@@ -641,6 +634,13 @@
 	res.wol_irq = pci_irq_vector(pdev, 0);
 	res.irq = pci_irq_vector(pdev, 0);
 
+	if (plat->eee_usecs_rate > 0) {
+		u32 tx_lpi_usec;
+
+		tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1;
+		writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER);
+	}
+
 	ret = stmmac_dvr_probe(&pdev->dev, plat, &res);
 	if (ret) {
 		pci_free_irq_vectors(pdev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 220626a..d833908 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4757,6 +4757,7 @@
 
 		ch->priv_data = priv;
 		ch->index = queue;
+		spin_lock_init(&ch->lock);
 
 		if (queue < priv->plat->rx_queues_to_use) {
 			netif_napi_add(dev, &ch->rx_napi, stmmac_napi_poll_rx,
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index 4d02c51..4619c3a 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -728,7 +728,6 @@
 		(1 << HWTSTAMP_TX_ON);
 	info->rx_filters =
 		(1 << HWTSTAMP_FILTER_NONE) |
-		(1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
 		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
 	return 0;
 }
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
index 51cc29f..31c5e36 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.c
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -639,13 +639,10 @@
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_NTP_ALL:
-		return -ERANGE;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-		priv->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
-		break;
+		return -ERANGE;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index fb1db71..575580d 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -551,6 +551,8 @@
 	{
 		PHY_ID_MATCH_EXACT(0x00008201),
 		.name           = "RTL8201CP Ethernet",
+		.read_page	= rtl821x_read_page,
+		.write_page	= rtl821x_write_page,
 	}, {
 		PHY_ID_MATCH_EXACT(0x001cc816),
 		.name		= "RTL8201F Fast Ethernet",
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 1d18c10..34aa196 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -2389,7 +2389,8 @@
 			continue;
 
 		sfp->gpio_irq[i] = gpiod_to_irq(sfp->gpio[i]);
-		if (!sfp->gpio_irq[i]) {
+		if (sfp->gpio_irq[i] < 0) {
+			sfp->gpio_irq[i] = 0;
 			sfp->need_poll = true;
 			continue;
 		}
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index a322f51..581ed51 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1309,6 +1309,7 @@
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)},	/* Telit LE920, LE920A4 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1230, 2)},	/* Telit LE910Cx */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1260, 2)},	/* Telit LE910Cx */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1261, 2)},	/* Telit LE910Cx */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1900, 1)},	/* Telit LN940 series */
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 60c1aad..f2793ff 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -608,8 +608,7 @@
 	return ret;
 }
 
-static int vrf_finish_direct(struct net *net, struct sock *sk,
-			     struct sk_buff *skb)
+static void vrf_finish_direct(struct sk_buff *skb)
 {
 	struct net_device *vrf_dev = skb->dev;
 
@@ -628,7 +627,8 @@
 		skb_pull(skb, ETH_HLEN);
 	}
 
-	return 1;
+	/* reset skb device */
+	nf_reset_ct(skb);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -707,15 +707,41 @@
 	return skb;
 }
 
+static int vrf_output6_direct_finish(struct net *net, struct sock *sk,
+				     struct sk_buff *skb)
+{
+	vrf_finish_direct(skb);
+
+	return vrf_ip6_local_out(net, sk, skb);
+}
+
 static int vrf_output6_direct(struct net *net, struct sock *sk,
 			      struct sk_buff *skb)
 {
+	int err = 1;
+
 	skb->protocol = htons(ETH_P_IPV6);
 
-	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
-			    net, sk, skb, NULL, skb->dev,
-			    vrf_finish_direct,
-			    !(IPCB(skb)->flags & IPSKB_REROUTED));
+	if (!(IPCB(skb)->flags & IPSKB_REROUTED))
+		err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb,
+			      NULL, skb->dev, vrf_output6_direct_finish);
+
+	if (likely(err == 1))
+		vrf_finish_direct(skb);
+
+	return err;
+}
+
+static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk,
+				     struct sk_buff *skb)
+{
+	int err;
+
+	err = vrf_output6_direct(net, sk, skb);
+	if (likely(err == 1))
+		err = vrf_ip6_local_out(net, sk, skb);
+
+	return err;
 }
 
 static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev,
@@ -728,18 +754,15 @@
 	skb->dev = vrf_dev;
 
 	err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk,
-		      skb, NULL, vrf_dev, vrf_output6_direct);
+		      skb, NULL, vrf_dev, vrf_ip6_out_direct_finish);
 
 	if (likely(err == 1))
 		err = vrf_output6_direct(net, sk, skb);
 
-	/* reset skb device */
 	if (likely(err == 1))
-		nf_reset_ct(skb);
-	else
-		skb = NULL;
+		return skb;
 
-	return skb;
+	return NULL;
 }
 
 static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
@@ -919,15 +942,41 @@
 	return skb;
 }
 
+static int vrf_output_direct_finish(struct net *net, struct sock *sk,
+				    struct sk_buff *skb)
+{
+	vrf_finish_direct(skb);
+
+	return vrf_ip_local_out(net, sk, skb);
+}
+
 static int vrf_output_direct(struct net *net, struct sock *sk,
 			     struct sk_buff *skb)
 {
+	int err = 1;
+
 	skb->protocol = htons(ETH_P_IP);
 
-	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
-			    net, sk, skb, NULL, skb->dev,
-			    vrf_finish_direct,
-			    !(IPCB(skb)->flags & IPSKB_REROUTED));
+	if (!(IPCB(skb)->flags & IPSKB_REROUTED))
+		err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb,
+			      NULL, skb->dev, vrf_output_direct_finish);
+
+	if (likely(err == 1))
+		vrf_finish_direct(skb);
+
+	return err;
+}
+
+static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk,
+				    struct sk_buff *skb)
+{
+	int err;
+
+	err = vrf_output_direct(net, sk, skb);
+	if (likely(err == 1))
+		err = vrf_ip_local_out(net, sk, skb);
+
+	return err;
 }
 
 static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev,
@@ -940,18 +989,15 @@
 	skb->dev = vrf_dev;
 
 	err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
-		      skb, NULL, vrf_dev, vrf_output_direct);
+		      skb, NULL, vrf_dev, vrf_ip_out_direct_finish);
 
 	if (likely(err == 1))
 		err = vrf_output_direct(net, sk, skb);
 
-	/* reset skb device */
 	if (likely(err == 1))
-		nf_reset_ct(skb);
-	else
-		skb = NULL;
+		return skb;
 
-	return skb;
+	return NULL;
 }
 
 static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c
index f8aed06..2369ca2 100644
--- a/drivers/net/wan/cosa.c
+++ b/drivers/net/wan/cosa.c
@@ -889,6 +889,7 @@
 			chan->tx_status = 1;
 			spin_unlock_irqrestore(&cosa->lock, flags);
 			up(&chan->wsem);
+			kfree(kbuf);
 			return -ERESTARTSYS;
 		}
 	}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 376096b..9b01afc 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2060,8 +2060,6 @@
 
 	if (id->nsattr & NVME_NS_ATTR_RO)
 		set_disk_ro(disk, true);
-	else
-		set_disk_ro(disk, false);
 }
 
 static inline bool nvme_first_scan(struct gendisk *disk)
@@ -4582,8 +4580,7 @@
 }
 EXPORT_SYMBOL_GPL(nvme_start_queues);
 
-
-void nvme_sync_queues(struct nvme_ctrl *ctrl)
+void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
@@ -4591,7 +4588,12 @@
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		blk_sync_queue(ns->queue);
 	up_read(&ctrl->namespaces_rwsem);
+}
+EXPORT_SYMBOL_GPL(nvme_sync_io_queues);
 
+void nvme_sync_queues(struct nvme_ctrl *ctrl)
+{
+	nvme_sync_io_queues(ctrl);
 	if (ctrl->admin_q)
 		blk_sync_queue(ctrl->admin_q);
 }
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index cc11113..bc330bf 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -602,6 +602,7 @@
 void nvme_start_queues(struct nvme_ctrl *ctrl);
 void nvme_kill_queues(struct nvme_ctrl *ctrl);
 void nvme_sync_queues(struct nvme_ctrl *ctrl);
+void nvme_sync_io_queues(struct nvme_ctrl *ctrl);
 void nvme_unfreeze(struct nvme_ctrl *ctrl);
 void nvme_wait_freeze(struct nvme_ctrl *ctrl);
 int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index df8f361..0578ff2 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -198,6 +198,7 @@
 	u32 q_depth;
 	u16 cq_vector;
 	u16 sq_tail;
+	u16 last_sq_tail;
 	u16 cq_head;
 	u16 qid;
 	u8 cq_phase;
@@ -455,11 +456,24 @@
 	return 0;
 }
 
-static inline void nvme_write_sq_db(struct nvme_queue *nvmeq)
+/*
+ * Write sq tail if we are asked to, or if the next command would wrap.
+ */
+static inline void nvme_write_sq_db(struct nvme_queue *nvmeq, bool write_sq)
 {
+	if (!write_sq) {
+		u16 next_tail = nvmeq->sq_tail + 1;
+
+		if (next_tail == nvmeq->q_depth)
+			next_tail = 0;
+		if (next_tail != nvmeq->last_sq_tail)
+			return;
+	}
+
 	if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail,
 			nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei))
 		writel(nvmeq->sq_tail, nvmeq->q_db);
+	nvmeq->last_sq_tail = nvmeq->sq_tail;
 }
 
 /**
@@ -476,8 +490,7 @@
 	       cmd, sizeof(*cmd));
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
-	if (write_sq)
-		nvme_write_sq_db(nvmeq);
+	nvme_write_sq_db(nvmeq, write_sq);
 	spin_unlock(&nvmeq->sq_lock);
 }
 
@@ -486,7 +499,8 @@
 	struct nvme_queue *nvmeq = hctx->driver_data;
 
 	spin_lock(&nvmeq->sq_lock);
-	nvme_write_sq_db(nvmeq);
+	if (nvmeq->sq_tail != nvmeq->last_sq_tail)
+		nvme_write_sq_db(nvmeq, true);
 	spin_unlock(&nvmeq->sq_lock);
 }
 
@@ -1496,6 +1510,7 @@
 	struct nvme_dev *dev = nvmeq->dev;
 
 	nvmeq->sq_tail = 0;
+	nvmeq->last_sq_tail = 0;
 	nvmeq->cq_head = 0;
 	nvmeq->cq_phase = 1;
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 541b0cb..65e3d0e 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -122,7 +122,6 @@
 	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
-	struct mutex		teardown_lock;
 	bool			use_inline_data;
 	u32			io_queues[HCTX_MAX_TYPES];
 };
@@ -1010,8 +1009,8 @@
 static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&ctrl->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	blk_sync_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	if (ctrl->ctrl.admin_tagset) {
 		blk_mq_tagset_busy_iter(ctrl->ctrl.admin_tagset,
@@ -1021,16 +1020,15 @@
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_destroy_admin_queue(ctrl, remove);
-	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&ctrl->teardown_lock);
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
+		nvme_sync_io_queues(&ctrl->ctrl);
 		nvme_rdma_stop_io_queues(ctrl);
 		if (ctrl->ctrl.tagset) {
 			blk_mq_tagset_busy_iter(ctrl->ctrl.tagset,
@@ -1041,7 +1039,6 @@
 			nvme_start_queues(&ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, remove);
 	}
-	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
@@ -1976,16 +1973,12 @@
 {
 	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_rdma_queue *queue = req->queue;
-	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
 
-	/* fence other contexts that may complete the command */
-	mutex_lock(&ctrl->teardown_lock);
 	nvme_rdma_stop_queue(queue);
-	if (!blk_mq_request_completed(rq)) {
+	if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
 		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
 		blk_mq_complete_request(rq);
 	}
-	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static enum blk_eh_timer_return
@@ -2320,7 +2313,6 @@
 		return ERR_PTR(-ENOMEM);
 	ctrl->ctrl.opts = opts;
 	INIT_LIST_HEAD(&ctrl->list);
-	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index d6a3e14..c0c3332 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -124,7 +124,6 @@
 	struct sockaddr_storage src_addr;
 	struct nvme_ctrl	ctrl;
 
-	struct mutex		teardown_lock;
 	struct work_struct	err_work;
 	struct delayed_work	connect_work;
 	struct nvme_tcp_request async_req;
@@ -1886,8 +1885,8 @@
 static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->admin_q);
+	blk_sync_queue(ctrl->admin_q);
 	nvme_tcp_stop_queue(ctrl, 0);
 	if (ctrl->admin_tagset) {
 		blk_mq_tagset_busy_iter(ctrl->admin_tagset,
@@ -1897,18 +1896,17 @@
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 	nvme_tcp_destroy_admin_queue(ctrl, remove);
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 		bool remove)
 {
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	if (ctrl->queue_count <= 1)
-		goto out;
+		return;
 	blk_mq_quiesce_queue(ctrl->admin_q);
 	nvme_start_freeze(ctrl);
 	nvme_stop_queues(ctrl);
+	nvme_sync_io_queues(ctrl);
 	nvme_tcp_stop_io_queues(ctrl);
 	if (ctrl->tagset) {
 		blk_mq_tagset_busy_iter(ctrl->tagset,
@@ -1918,8 +1916,6 @@
 	if (remove)
 		nvme_start_queues(ctrl);
 	nvme_tcp_destroy_io_queues(ctrl, remove);
-out:
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
@@ -2171,14 +2167,11 @@
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 	struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
 
-	/* fence other contexts that may complete the command */
-	mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
 	nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
-	if (!blk_mq_request_completed(rq)) {
+	if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
 		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
 		blk_mq_complete_request(rq);
 	}
-	mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
 }
 
 static enum blk_eh_timer_return
@@ -2455,7 +2448,6 @@
 			nvme_tcp_reconnect_ctrl_work);
 	INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work);
 	INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work);
-	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =
diff --git a/drivers/of/address.c b/drivers/of/address.c
index eb9ab4f..1c3257a 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -1034,11 +1034,13 @@
  */
 bool of_dma_is_coherent(struct device_node *np)
 {
-	struct device_node *node = of_node_get(np);
+	struct device_node *node;
 
 	if (IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT))
 		return true;
 
+	node = of_node_get(np);
+
 	while (node) {
 		if (of_property_read_bool(node, "dma-coherent")) {
 			of_node_put(node);
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 3a469c7..aedfaaa 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -112,7 +112,7 @@
 		u64 dma_end = 0;
 
 		/* Determine the overall bounds of all DMA regions */
-		for (dma_start = ~0ULL; r->size; r++) {
+		for (dma_start = ~0; r->size; r++) {
 			/* Take lower and upper limits */
 			if (r->dma_start < dma_start)
 				dma_start = r->dma_start;
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 2483e76..0e0a526 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -1181,6 +1181,10 @@
 	struct opp_device *opp_dev, *temp;
 	int i;
 
+	/* Drop the lock as soon as we can */
+	list_del(&opp_table->node);
+	mutex_unlock(&opp_table_lock);
+
 	_of_clear_opp_table(opp_table);
 
 	/* Release clk */
@@ -1208,10 +1212,7 @@
 
 	mutex_destroy(&opp_table->genpd_virt_dev_lock);
 	mutex_destroy(&opp_table->lock);
-	list_del(&opp_table->node);
 	kfree(opp_table);
-
-	mutex_unlock(&opp_table_lock);
 }
 
 void dev_pm_opp_put_opp_table(struct opp_table *opp_table)
@@ -1930,7 +1931,7 @@
 		return ERR_PTR(-EINVAL);
 
 	opp_table = dev_pm_opp_get_opp_table(dev);
-	if (!IS_ERR(opp_table))
+	if (IS_ERR(opp_table))
 		return opp_table;
 
 	/* This should be called before OPPs are initialized */
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 874b587..9faeb83 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -944,6 +944,8 @@
 		nr -= 2;
 	}
 
+	return 0;
+
 remove_static_opp:
 	_opp_remove_all_static(opp_table);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 674f32d..44c2a65 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -586,8 +586,12 @@
 	 * ATU, so we should not program the ATU here.
 	 */
 	if (pp->bridge->child_ops == &dw_child_pcie_ops) {
-		struct resource_entry *entry =
-			resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM);
+		struct resource_entry *tmp, *entry = NULL;
+
+		/* Get last memory resource entry */
+		resource_list_for_each_entry(tmp, &pp->bridge->windows)
+			if (resource_type(tmp->res) == IORESOURCE_MEM)
+				entry = tmp;
 
 		dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX0,
 					  PCIE_ATU_TYPE_MEM, entry->res->start,
diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index eee8283..ed13e81 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -958,25 +958,16 @@
 }
 
 /*
- * We can't use devm_of_pci_get_host_bridge_resources() because we
- * need to parse our special DT properties encoding the MEM and IO
- * apertures.
+ * devm_of_pci_get_host_bridge_resources() only sets up translateable resources,
+ * so we need extra resource setup parsing our special DT properties encoding
+ * the MEM and IO apertures.
  */
 static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie)
 {
 	struct device *dev = &pcie->pdev->dev;
-	struct device_node *np = dev->of_node;
 	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
 	int ret;
 
-	/* Get the bus range */
-	ret = of_pci_parse_bus_range(np, &pcie->busn);
-	if (ret) {
-		dev_err(dev, "failed to parse bus-range property: %d\n", ret);
-		return ret;
-	}
-	pci_add_resource(&bridge->windows, &pcie->busn);
-
 	/* Get the PCIe memory aperture */
 	mvebu_mbus_get_pcie_mem_aperture(&pcie->mem);
 	if (resource_size(&pcie->mem) == 0) {
@@ -986,6 +977,9 @@
 
 	pcie->mem.name = "PCI MEM";
 	pci_add_resource(&bridge->windows, &pcie->mem);
+	ret = devm_request_resource(dev, &iomem_resource, &pcie->mem);
+	if (ret)
+		return ret;
 
 	/* Get the PCIe IO aperture */
 	mvebu_mbus_get_pcie_io_aperture(&pcie->io);
@@ -999,9 +993,12 @@
 		pcie->realio.name = "PCI I/O";
 
 		pci_add_resource(&bridge->windows, &pcie->realio);
+		ret = devm_request_resource(dev, &ioport_resource, &pcie->realio);
+		if (ret)
+			return ret;
 	}
 
-	return devm_request_pci_bus_resources(dev, &bridge->windows);
+	return 0;
 }
 
 /*
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 6d4d5a2..e578d34 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3516,8 +3516,13 @@
 {
 	dev->acs_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
 
-	if (dev->acs_cap)
-		pci_enable_acs(dev);
+	/*
+	 * Attempt to enable ACS regardless of capability because some Root
+	 * Ports (e.g. those quirked with *_intel_pch_acs_*) do not have
+	 * the standard ACS capability but still support ACS via those
+	 * quirks.
+	 */
+	pci_enable_acs(dev);
 }
 
 /**
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
index 6a94eae..d6b8495 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
@@ -286,13 +286,14 @@
 static bool aspeed_expr_is_gpio(const struct aspeed_sig_expr *expr)
 {
 	/*
-	 * The signal type is GPIO if the signal name has "GPIO" as a prefix.
+	 * The signal type is GPIO if the signal name has "GPI" as a prefix.
 	 * strncmp (rather than strcmp) is used to implement the prefix
 	 * requirement.
 	 *
-	 * expr->signal might look like "GPIOT3" in the GPIO case.
+	 * expr->signal might look like "GPIOB1" in the GPIO case.
+	 * expr->signal might look like "GPIT0" in the GPI case.
 	 */
-	return strncmp(expr->signal, "GPIO", 4) == 0;
+	return strncmp(expr->signal, "GPI", 3) == 0;
 }
 
 static bool aspeed_gpio_in_exprs(const struct aspeed_sig_expr **exprs)
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 154ce3f..1c10ab1 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -62,10 +62,10 @@
 #define PADCFG1_TERM_UP			BIT(13)
 #define PADCFG1_TERM_SHIFT		10
 #define PADCFG1_TERM_MASK		GENMASK(12, 10)
-#define PADCFG1_TERM_20K		4
-#define PADCFG1_TERM_2K			3
-#define PADCFG1_TERM_5K			2
-#define PADCFG1_TERM_1K			1
+#define PADCFG1_TERM_20K		BIT(2)
+#define PADCFG1_TERM_5K			BIT(1)
+#define PADCFG1_TERM_1K			BIT(0)
+#define PADCFG1_TERM_833		(BIT(1) | BIT(0))
 
 #define PADCFG2				0x008
 #define PADCFG2_DEBEN			BIT(0)
@@ -549,12 +549,12 @@
 			return -EINVAL;
 
 		switch (term) {
+		case PADCFG1_TERM_833:
+			*arg = 833;
+			break;
 		case PADCFG1_TERM_1K:
 			*arg = 1000;
 			break;
-		case PADCFG1_TERM_2K:
-			*arg = 2000;
-			break;
 		case PADCFG1_TERM_5K:
 			*arg = 5000;
 			break;
@@ -570,6 +570,11 @@
 			return -EINVAL;
 
 		switch (term) {
+		case PADCFG1_TERM_833:
+			if (!(community->features & PINCTRL_FEATURE_1K_PD))
+				return -EINVAL;
+			*arg = 833;
+			break;
 		case PADCFG1_TERM_1K:
 			if (!(community->features & PINCTRL_FEATURE_1K_PD))
 				return -EINVAL;
@@ -678,6 +683,10 @@
 
 		value |= PADCFG1_TERM_UP;
 
+		/* Set default strength value in case none is given */
+		if (arg == 1)
+			arg = 5000;
+
 		switch (arg) {
 		case 20000:
 			value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT;
@@ -685,12 +694,12 @@
 		case 5000:
 			value |= PADCFG1_TERM_5K << PADCFG1_TERM_SHIFT;
 			break;
-		case 2000:
-			value |= PADCFG1_TERM_2K << PADCFG1_TERM_SHIFT;
-			break;
 		case 1000:
 			value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT;
 			break;
+		case 833:
+			value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT;
+			break;
 		default:
 			ret = -EINVAL;
 		}
@@ -700,6 +709,10 @@
 	case PIN_CONFIG_BIAS_PULL_DOWN:
 		value &= ~(PADCFG1_TERM_UP | PADCFG1_TERM_MASK);
 
+		/* Set default strength value in case none is given */
+		if (arg == 1)
+			arg = 5000;
+
 		switch (arg) {
 		case 20000:
 			value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT;
@@ -714,6 +727,13 @@
 			}
 			value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT;
 			break;
+		case 833:
+			if (!(community->features & PINCTRL_FEATURE_1K_PD)) {
+				ret = -EINVAL;
+				break;
+			}
+			value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT;
+			break;
 		default:
 			ret = -EINVAL;
 		}
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 9a760f5..4aea3e0 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -156,7 +156,7 @@
 			pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
 			pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
 		} else if (debounce < 250000) {
-			time = debounce / 15600;
+			time = debounce / 15625;
 			pin_reg |= time & DB_TMR_OUT_MASK;
 			pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF);
 			pin_reg |= BIT(DB_TMR_LARGE_OFF);
@@ -166,14 +166,14 @@
 			pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
 			pin_reg |= BIT(DB_TMR_LARGE_OFF);
 		} else {
-			pin_reg &= ~DB_CNTRl_MASK;
+			pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF);
 			ret = -EINVAL;
 		}
 	} else {
 		pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF);
 		pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
 		pin_reg &= ~DB_TMR_OUT_MASK;
-		pin_reg &= ~DB_CNTRl_MASK;
+		pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF);
 	}
 	writel(pin_reg, gpio_dev->base + offset * 4);
 	raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c
index c8e50a5..621909b 100644
--- a/drivers/pinctrl/pinctrl-ingenic.c
+++ b/drivers/pinctrl/pinctrl-ingenic.c
@@ -635,44 +635,44 @@
 static int jz4770_uart3_hwflow_pins[] = { 0x88, 0x89, };
 static int jz4770_ssi0_dt_a_pins[] = { 0x15, };
 static int jz4770_ssi0_dt_b_pins[] = { 0x35, };
-static int jz4770_ssi0_dt_d_pins[] = { 0x55, };
-static int jz4770_ssi0_dt_e_pins[] = { 0x71, };
+static int jz4770_ssi0_dt_d_pins[] = { 0x75, };
+static int jz4770_ssi0_dt_e_pins[] = { 0x91, };
 static int jz4770_ssi0_dr_a_pins[] = { 0x14, };
 static int jz4770_ssi0_dr_b_pins[] = { 0x34, };
-static int jz4770_ssi0_dr_d_pins[] = { 0x54, };
-static int jz4770_ssi0_dr_e_pins[] = { 0x6e, };
+static int jz4770_ssi0_dr_d_pins[] = { 0x74, };
+static int jz4770_ssi0_dr_e_pins[] = { 0x8e, };
 static int jz4770_ssi0_clk_a_pins[] = { 0x12, };
 static int jz4770_ssi0_clk_b_pins[] = { 0x3c, };
-static int jz4770_ssi0_clk_d_pins[] = { 0x58, };
-static int jz4770_ssi0_clk_e_pins[] = { 0x6f, };
+static int jz4770_ssi0_clk_d_pins[] = { 0x78, };
+static int jz4770_ssi0_clk_e_pins[] = { 0x8f, };
 static int jz4770_ssi0_gpc_b_pins[] = { 0x3e, };
-static int jz4770_ssi0_gpc_d_pins[] = { 0x56, };
-static int jz4770_ssi0_gpc_e_pins[] = { 0x73, };
+static int jz4770_ssi0_gpc_d_pins[] = { 0x76, };
+static int jz4770_ssi0_gpc_e_pins[] = { 0x93, };
 static int jz4770_ssi0_ce0_a_pins[] = { 0x13, };
 static int jz4770_ssi0_ce0_b_pins[] = { 0x3d, };
-static int jz4770_ssi0_ce0_d_pins[] = { 0x59, };
-static int jz4770_ssi0_ce0_e_pins[] = { 0x70, };
+static int jz4770_ssi0_ce0_d_pins[] = { 0x79, };
+static int jz4770_ssi0_ce0_e_pins[] = { 0x90, };
 static int jz4770_ssi0_ce1_b_pins[] = { 0x3f, };
-static int jz4770_ssi0_ce1_d_pins[] = { 0x57, };
-static int jz4770_ssi0_ce1_e_pins[] = { 0x72, };
+static int jz4770_ssi0_ce1_d_pins[] = { 0x77, };
+static int jz4770_ssi0_ce1_e_pins[] = { 0x92, };
 static int jz4770_ssi1_dt_b_pins[] = { 0x35, };
-static int jz4770_ssi1_dt_d_pins[] = { 0x55, };
-static int jz4770_ssi1_dt_e_pins[] = { 0x71, };
+static int jz4770_ssi1_dt_d_pins[] = { 0x75, };
+static int jz4770_ssi1_dt_e_pins[] = { 0x91, };
 static int jz4770_ssi1_dr_b_pins[] = { 0x34, };
-static int jz4770_ssi1_dr_d_pins[] = { 0x54, };
-static int jz4770_ssi1_dr_e_pins[] = { 0x6e, };
+static int jz4770_ssi1_dr_d_pins[] = { 0x74, };
+static int jz4770_ssi1_dr_e_pins[] = { 0x8e, };
 static int jz4770_ssi1_clk_b_pins[] = { 0x3c, };
-static int jz4770_ssi1_clk_d_pins[] = { 0x58, };
-static int jz4770_ssi1_clk_e_pins[] = { 0x6f, };
+static int jz4770_ssi1_clk_d_pins[] = { 0x78, };
+static int jz4770_ssi1_clk_e_pins[] = { 0x8f, };
 static int jz4770_ssi1_gpc_b_pins[] = { 0x3e, };
-static int jz4770_ssi1_gpc_d_pins[] = { 0x56, };
-static int jz4770_ssi1_gpc_e_pins[] = { 0x73, };
+static int jz4770_ssi1_gpc_d_pins[] = { 0x76, };
+static int jz4770_ssi1_gpc_e_pins[] = { 0x93, };
 static int jz4770_ssi1_ce0_b_pins[] = { 0x3d, };
-static int jz4770_ssi1_ce0_d_pins[] = { 0x59, };
-static int jz4770_ssi1_ce0_e_pins[] = { 0x70, };
+static int jz4770_ssi1_ce0_d_pins[] = { 0x79, };
+static int jz4770_ssi1_ce0_e_pins[] = { 0x90, };
 static int jz4770_ssi1_ce1_b_pins[] = { 0x3f, };
-static int jz4770_ssi1_ce1_d_pins[] = { 0x57, };
-static int jz4770_ssi1_ce1_e_pins[] = { 0x72, };
+static int jz4770_ssi1_ce1_d_pins[] = { 0x77, };
+static int jz4770_ssi1_ce1_e_pins[] = { 0x92, };
 static int jz4770_mmc0_1bit_a_pins[] = { 0x12, 0x13, 0x14, };
 static int jz4770_mmc0_4bit_a_pins[] = { 0x15, 0x16, 0x17, };
 static int jz4770_mmc0_1bit_e_pins[] = { 0x9c, 0x9d, 0x94, };
@@ -1050,35 +1050,35 @@
 static int jz4780_ssi0_dt_a_21_pins[] = { 0x15, };
 static int jz4780_ssi0_dt_a_28_pins[] = { 0x1c, };
 static int jz4780_ssi0_dt_b_pins[] = { 0x3d, };
-static int jz4780_ssi0_dt_d_pins[] = { 0x59, };
+static int jz4780_ssi0_dt_d_pins[] = { 0x79, };
 static int jz4780_ssi0_dr_a_20_pins[] = { 0x14, };
 static int jz4780_ssi0_dr_a_27_pins[] = { 0x1b, };
 static int jz4780_ssi0_dr_b_pins[] = { 0x34, };
-static int jz4780_ssi0_dr_d_pins[] = { 0x54, };
+static int jz4780_ssi0_dr_d_pins[] = { 0x74, };
 static int jz4780_ssi0_clk_a_pins[] = { 0x12, };
 static int jz4780_ssi0_clk_b_5_pins[] = { 0x25, };
 static int jz4780_ssi0_clk_b_28_pins[] = { 0x3c, };
-static int jz4780_ssi0_clk_d_pins[] = { 0x58, };
+static int jz4780_ssi0_clk_d_pins[] = { 0x78, };
 static int jz4780_ssi0_gpc_b_pins[] = { 0x3e, };
-static int jz4780_ssi0_gpc_d_pins[] = { 0x56, };
+static int jz4780_ssi0_gpc_d_pins[] = { 0x76, };
 static int jz4780_ssi0_ce0_a_23_pins[] = { 0x17, };
 static int jz4780_ssi0_ce0_a_25_pins[] = { 0x19, };
 static int jz4780_ssi0_ce0_b_pins[] = { 0x3f, };
-static int jz4780_ssi0_ce0_d_pins[] = { 0x57, };
+static int jz4780_ssi0_ce0_d_pins[] = { 0x77, };
 static int jz4780_ssi0_ce1_b_pins[] = { 0x35, };
-static int jz4780_ssi0_ce1_d_pins[] = { 0x55, };
+static int jz4780_ssi0_ce1_d_pins[] = { 0x75, };
 static int jz4780_ssi1_dt_b_pins[] = { 0x3d, };
-static int jz4780_ssi1_dt_d_pins[] = { 0x59, };
+static int jz4780_ssi1_dt_d_pins[] = { 0x79, };
 static int jz4780_ssi1_dr_b_pins[] = { 0x34, };
-static int jz4780_ssi1_dr_d_pins[] = { 0x54, };
+static int jz4780_ssi1_dr_d_pins[] = { 0x74, };
 static int jz4780_ssi1_clk_b_pins[] = { 0x3c, };
-static int jz4780_ssi1_clk_d_pins[] = { 0x58, };
+static int jz4780_ssi1_clk_d_pins[] = { 0x78, };
 static int jz4780_ssi1_gpc_b_pins[] = { 0x3e, };
-static int jz4780_ssi1_gpc_d_pins[] = { 0x56, };
+static int jz4780_ssi1_gpc_d_pins[] = { 0x76, };
 static int jz4780_ssi1_ce0_b_pins[] = { 0x3f, };
-static int jz4780_ssi1_ce0_d_pins[] = { 0x57, };
+static int jz4780_ssi1_ce0_d_pins[] = { 0x77, };
 static int jz4780_ssi1_ce1_b_pins[] = { 0x35, };
-static int jz4780_ssi1_ce1_d_pins[] = { 0x55, };
+static int jz4780_ssi1_ce1_d_pins[] = { 0x75, };
 static int jz4780_mmc0_8bit_a_pins[] = { 0x04, 0x05, 0x06, 0x07, 0x18, };
 static int jz4780_i2c3_pins[] = { 0x6a, 0x6b, };
 static int jz4780_i2c4_e_pins[] = { 0x8c, 0x8d, };
diff --git a/drivers/pinctrl/pinctrl-mcp23s08_spi.c b/drivers/pinctrl/pinctrl-mcp23s08_spi.c
index 1f47a66..9ae1031 100644
--- a/drivers/pinctrl/pinctrl-mcp23s08_spi.c
+++ b/drivers/pinctrl/pinctrl-mcp23s08_spi.c
@@ -119,13 +119,15 @@
 		return -EINVAL;
 	}
 
-	copy = devm_kmemdup(dev, &config, sizeof(config), GFP_KERNEL);
+	copy = devm_kmemdup(dev, config, sizeof(*config), GFP_KERNEL);
 	if (!copy)
 		return -ENOMEM;
 
 	copy->name = name;
 
 	mcp->regmap = devm_regmap_init(dev, &mcp23sxx_spi_regmap, mcp, copy);
+	if (IS_ERR(mcp->regmap))
+		dev_err(dev, "regmap init failed for %s\n", mcp->chip.label);
 	return PTR_ERR_OR_ZERO(mcp->regmap);
 }
 
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index 0401c1d..aa1a1c8 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -3155,7 +3155,9 @@
 	if (!bank->domain)
 		return -ENXIO;
 
+	clk_enable(bank->clk);
 	virq = irq_create_mapping(bank->domain, offset);
+	clk_disable(bank->clk);
 
 	return (virq) ? : -ENXIO;
 }
@@ -3194,7 +3196,7 @@
 
 		irq = __ffs(pend);
 		pend &= ~BIT(irq);
-		virq = irq_linear_revmap(bank->domain, irq);
+		virq = irq_find_mapping(bank->domain, irq);
 
 		if (!virq) {
 			dev_err(bank->drvdata->dev, "unmapped irq %d\n", irq);
@@ -3373,7 +3375,7 @@
 	unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
 	struct irq_chip_generic *gc;
 	int ret;
-	int i, j;
+	int i;
 
 	for (i = 0; i < ctrl->nr_banks; ++i, ++bank) {
 		if (!bank->valid) {
@@ -3400,7 +3402,7 @@
 
 		ret = irq_alloc_domain_generic_chips(bank->domain, 32, 1,
 					 "rockchip_gpio_irq", handle_level_irq,
-					 clr, 0, IRQ_GC_INIT_MASK_CACHE);
+					 clr, 0, 0);
 		if (ret) {
 			dev_err(&pdev->dev, "could not alloc generic chips for bank %s\n",
 				bank->name);
@@ -3409,14 +3411,6 @@
 			continue;
 		}
 
-		/*
-		 * Linux assumes that all interrupts start out disabled/masked.
-		 * Our driver only uses the concept of masked and always keeps
-		 * things enabled, so for us that's all masked and all enabled.
-		 */
-		writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK);
-		writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN);
-
 		gc = irq_get_domain_generic_chip(bank->domain, 0);
 		gc->reg_base = bank->reg_base;
 		gc->private = bank;
@@ -3433,13 +3427,17 @@
 		gc->chip_types[0].chip.irq_set_type = rockchip_irq_set_type;
 		gc->wake_enabled = IRQ_MSK(bank->nr_pins);
 
+		/*
+		 * Linux assumes that all interrupts start out disabled/masked.
+		 * Our driver only uses the concept of masked and always keeps
+		 * things enabled, so for us that's all masked and all enabled.
+		 */
+		writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK);
+		writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN);
+		gc->mask_cache = 0xffffffff;
+
 		irq_set_chained_handler_and_data(bank->irq,
 						 rockchip_irq_demux, bank);
-
-		/* map the gpio irqs here, when the clock is still running */
-		for (j = 0 ; j < 32 ; j++)
-			irq_create_mapping(bank->domain, j);
-
 		clk_disable(bank->clk);
 	}
 
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index c4bcda9..77a25bd 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -815,21 +815,14 @@
 
 static void msm_gpio_irq_enable(struct irq_data *d)
 {
-	/*
-	 * Clear the interrupt that may be pending before we enable
-	 * the line.
-	 * This is especially a problem with the GPIOs routed to the
-	 * PDC. These GPIOs are direct-connect interrupts to the GIC.
-	 * Disabling the interrupt line at the PDC does not prevent
-	 * the interrupt from being latched at the GIC. The state at
-	 * GIC needs to be cleared before enabling.
-	 */
-	if (d->parent_data) {
-		irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0);
-		irq_chip_enable_parent(d);
-	}
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
 
-	msm_gpio_irq_clear_unmask(d, true);
+	if (d->parent_data)
+		irq_chip_enable_parent(d);
+
+	if (!test_bit(d->hwirq, pctrl->skip_wake_irqs))
+		msm_gpio_irq_clear_unmask(d, true);
 }
 
 static void msm_gpio_irq_disable(struct irq_data *d)
@@ -1104,6 +1097,19 @@
 		ret = -EINVAL;
 		goto out;
 	}
+
+	/*
+	 * Clear the interrupt that may be pending before we enable
+	 * the line.
+	 * This is especially a problem with the GPIOs routed to the
+	 * PDC. These GPIOs are direct-connect interrupts to the GIC.
+	 * Disabling the interrupt line at the PDC does not prevent
+	 * the interrupt from being latched at the GIC. The state at
+	 * GIC needs to be cleared before enabling.
+	 */
+	if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs))
+		irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0);
+
 	return 0;
 out:
 	module_put(gc->owner);
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250.c b/drivers/pinctrl/qcom/pinctrl-sm8250.c
index 826df0d..af144e7 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8250.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8250.c
@@ -1313,6 +1313,22 @@
 	[183] = SDC_PINGROUP(sdc2_data, 0xb7000, 9, 0),
 };
 
+static const struct msm_gpio_wakeirq_map sm8250_pdc_map[] = {
+	{ 0, 79 }, { 1, 84 }, { 2, 80 }, { 3, 82 }, { 4, 107 }, { 7, 43 },
+	{ 11, 42 }, { 14, 44 }, { 15, 52 }, { 19, 67 }, { 23, 68 }, { 24, 105 },
+	{ 27, 92 }, { 28, 106 }, { 31, 69 }, { 35, 70 }, { 39, 37 },
+	{ 40, 108 }, { 43, 71 }, { 45, 72 }, { 47, 83 }, { 51, 74 }, { 55, 77 },
+	{ 59, 78 }, { 63, 75 }, { 64, 81 }, { 65, 87 }, { 66, 88 }, { 67, 89 },
+	{ 68, 54 }, { 70, 85 }, { 77, 46 }, { 80, 90 }, { 81, 91 }, { 83, 97 },
+	{ 84, 98 }, { 86, 99 }, { 87, 100 }, { 88, 101 }, { 89, 102 },
+	{ 92, 103 }, { 93, 104 }, { 100, 53 }, { 103, 47 }, { 104, 48 },
+	{ 108, 49 }, { 109, 94 }, { 110, 95 }, { 111, 96 }, { 112, 55 },
+	{ 113, 56 }, { 118, 50 }, { 121, 51 }, { 122, 57 }, { 123, 58 },
+	{ 124, 45 }, { 126, 59 }, { 128, 76 }, { 129, 86 }, { 132, 93 },
+	{ 133, 65 }, { 134, 66 }, { 136, 62 }, { 137, 63 }, { 138, 64 },
+	{ 142, 60 }, { 143, 61 }
+};
+
 static const struct msm_pinctrl_soc_data sm8250_pinctrl = {
 	.pins = sm8250_pins,
 	.npins = ARRAY_SIZE(sm8250_pins),
@@ -1323,6 +1339,8 @@
 	.ngpios = 181,
 	.tiles = sm8250_tiles,
 	.ntiles = ARRAY_SIZE(sm8250_tiles),
+	.wakeirq_map = sm8250_pdc_map,
+	.nwakeirq_map = ARRAY_SIZE(sm8250_pdc_map),
 };
 
 static int sm8250_pinctrl_probe(struct platform_device *pdev)
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 0b2830e..70d6d52 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -620,7 +620,7 @@
 	case ARBITRARY_UNIT:
 	default:
 		return value;
-	};
+	}
 
 	if (to_raw)
 		return div64_u64(value, units) * scale;
diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c
index f808c5f..3f0b8e2 100644
--- a/drivers/powercap/powercap_sys.c
+++ b/drivers/powercap/powercap_sys.c
@@ -367,9 +367,9 @@
 					&dev_attr_max_energy_range_uj.attr;
 	if (power_zone->ops->get_energy_uj) {
 		if (power_zone->ops->reset_energy_uj)
-			dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUGO;
+			dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUSR;
 		else
-			dev_attr_energy_uj.attr.mode = S_IRUGO;
+			dev_attr_energy_uj.attr.mode = S_IRUSR;
 		power_zone->zone_dev_attrs[count++] =
 					&dev_attr_energy_uj.attr;
 	}
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index a4ffd71..42bbd99 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1315,7 +1315,6 @@
 /**
  * set_machine_constraints - sets regulator constraints
  * @rdev: regulator source
- * @constraints: constraints to apply
  *
  * Allows platform initialisation code to define and constrain
  * regulator circuits e.g. valid voltage/current ranges, etc.  NOTE:
@@ -1323,21 +1322,11 @@
  * regulator operations to proceed i.e. set_voltage, set_current_limit,
  * set_mode.
  */
-static int set_machine_constraints(struct regulator_dev *rdev,
-	const struct regulation_constraints *constraints)
+static int set_machine_constraints(struct regulator_dev *rdev)
 {
 	int ret = 0;
 	const struct regulator_ops *ops = rdev->desc->ops;
 
-	if (constraints)
-		rdev->constraints = kmemdup(constraints, sizeof(*constraints),
-					    GFP_KERNEL);
-	else
-		rdev->constraints = kzalloc(sizeof(*constraints),
-					    GFP_KERNEL);
-	if (!rdev->constraints)
-		return -ENOMEM;
-
 	ret = machine_constraints_voltage(rdev, rdev->constraints);
 	if (ret != 0)
 		return ret;
@@ -1852,6 +1841,15 @@
 		}
 	}
 
+	if (r == rdev) {
+		dev_err(dev, "Supply for %s (%s) resolved to itself\n",
+			rdev->desc->name, rdev->supply_name);
+		if (!have_full_constraints())
+			return -EINVAL;
+		r = dummy_regulator_rdev;
+		get_device(&r->dev);
+	}
+
 	/*
 	 * If the supply's parent device is not the same as the
 	 * regulator's parent device, then ensure the parent device
@@ -4165,6 +4163,8 @@
 		ret = rdev->desc->fixed_uV;
 	} else if (rdev->supply) {
 		ret = regulator_get_voltage_rdev(rdev->supply->rdev);
+	} else if (rdev->supply_name) {
+		return -EPROBE_DEFER;
 	} else {
 		return -EINVAL;
 	}
@@ -5144,7 +5144,6 @@
 regulator_register(const struct regulator_desc *regulator_desc,
 		   const struct regulator_config *cfg)
 {
-	const struct regulation_constraints *constraints = NULL;
 	const struct regulator_init_data *init_data;
 	struct regulator_config *config = NULL;
 	static atomic_t regulator_no = ATOMIC_INIT(-1);
@@ -5283,14 +5282,23 @@
 
 	/* set regulator constraints */
 	if (init_data)
-		constraints = &init_data->constraints;
+		rdev->constraints = kmemdup(&init_data->constraints,
+					    sizeof(*rdev->constraints),
+					    GFP_KERNEL);
+	else
+		rdev->constraints = kzalloc(sizeof(*rdev->constraints),
+					    GFP_KERNEL);
+	if (!rdev->constraints) {
+		ret = -ENOMEM;
+		goto wash;
+	}
 
 	if (init_data && init_data->supply_regulator)
 		rdev->supply_name = init_data->supply_regulator;
 	else if (regulator_desc->supply_name)
 		rdev->supply_name = regulator_desc->supply_name;
 
-	ret = set_machine_constraints(rdev, constraints);
+	ret = set_machine_constraints(rdev);
 	if (ret == -EPROBE_DEFER) {
 		/* Regulator might be in bypass mode and so needs its supply
 		 * to set the constraints */
@@ -5299,7 +5307,7 @@
 		 * that is just being created */
 		ret = regulator_resolve_supply(rdev);
 		if (!ret)
-			ret = set_machine_constraints(rdev, constraints);
+			ret = set_machine_constraints(rdev);
 		else
 			rdev_dbg(rdev, "unable to resolve supply early: %pe\n",
 				 ERR_PTR(ret));
@@ -5841,13 +5849,14 @@
 	if (rdev->use_count)
 		goto unlock;
 
-	/* If we can't read the status assume it's on. */
+	/* If we can't read the status assume it's always on. */
 	if (ops->is_enabled)
 		enabled = ops->is_enabled(rdev);
 	else
 		enabled = 1;
 
-	if (!enabled)
+	/* But if reading the status failed, assume that it's off. */
+	if (enabled <= 0)
 		goto unlock;
 
 	if (have_full_constraints()) {
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 7e8ba92..01a12cf 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -836,11 +836,14 @@
 		 * the switched regulator till yet.
 		 */
 		if (pfuze_chip->flags & PFUZE_FLAG_DISABLE_SW) {
-			if (pfuze_chip->regulator_descs[i].sw_reg) {
-				desc->ops = &pfuze100_sw_disable_regulator_ops;
-				desc->enable_val = 0x8;
-				desc->disable_val = 0x0;
-				desc->enable_time = 500;
+			if (pfuze_chip->chip_id == PFUZE100 ||
+				pfuze_chip->chip_id == PFUZE200) {
+				if (pfuze_chip->regulator_descs[i].sw_reg) {
+					desc->ops = &pfuze100_sw_disable_regulator_ops;
+					desc->enable_val = 0x8;
+					desc->disable_val = 0x0;
+					desc->enable_time = 500;
+				}
 			}
 		}
 
diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c
index 3e60bff..9f0a4d5 100644
--- a/drivers/regulator/ti-abb-regulator.c
+++ b/drivers/regulator/ti-abb-regulator.c
@@ -342,8 +342,17 @@
 		return ret;
 	}
 
-	/* If data is exactly the same, then just update index, no change */
 	info = &abb->info[sel];
+	/*
+	 * When Linux kernel is starting up, we are'nt sure of the
+	 * Bias configuration that bootloader has configured.
+	 * So, we get to know the actual setting the first time
+	 * we are asked to transition.
+	 */
+	if (abb->current_info_idx == -EINVAL)
+		goto just_set_abb;
+
+	/* If data is exactly the same, then just update index, no change */
 	oinfo = &abb->info[abb->current_info_idx];
 	if (!memcmp(info, oinfo, sizeof(*info))) {
 		dev_dbg(dev, "%s: Same data new idx=%d, old idx=%d\n", __func__,
@@ -351,6 +360,7 @@
 		goto out;
 	}
 
+just_set_abb:
 	ret = ti_abb_set_opp(rdev, abb, info);
 
 out:
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 485cbfc..ef738b4 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -680,7 +680,10 @@
 {
 	struct ap_device *ap_dev = to_ap_dev(dev);
 	struct ap_driver *ap_drv = to_ap_drv(dev->driver);
-	int card, queue, devres, drvres, rc;
+	int card, queue, devres, drvres, rc = -ENODEV;
+
+	if (!get_device(dev))
+		return rc;
 
 	if (is_queue_dev(dev)) {
 		/*
@@ -697,7 +700,7 @@
 		mutex_unlock(&ap_perms_mutex);
 		drvres = ap_drv->flags & AP_DRIVER_FLAG_DEFAULT;
 		if (!!devres != !!drvres)
-			return -ENODEV;
+			goto out;
 	}
 
 	/* Add queue/card to list of active queues/cards */
@@ -718,6 +721,9 @@
 		ap_dev->drv = NULL;
 	}
 
+out:
+	if (rc)
+		put_device(dev);
 	return rc;
 }
 
@@ -744,6 +750,8 @@
 		hash_del(&to_ap_queue(dev)->hnode);
 	spin_unlock_bh(&ap_queues_lock);
 
+	put_device(dev);
+
 	return 0;
 }
 
@@ -1371,6 +1379,8 @@
 					    __func__, ac->id, dom);
 				goto put_dev_and_continue;
 			}
+			/* get it and thus adjust reference counter */
+			get_device(dev);
 			if (decfg)
 				AP_DBF_INFO("%s(%d,%d) new (decfg) queue device created\n",
 					    __func__, ac->id, dom);
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 99cb60e..dd84995 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -35,9 +35,6 @@
 #define PROTKEYBLOBBUFSIZE 256	/* protected key buffer size used internal */
 #define MAXAPQNSINLIST 64	/* max 64 apqns within a apqn list */
 
-/* mask of available pckmo subfunctions, fetched once at module init */
-static cpacf_mask_t pckmo_functions;
-
 /*
  * debug feature data and functions
  */
@@ -91,6 +88,9 @@
 			    const struct pkey_clrkey *clrkey,
 			    struct pkey_protkey *protkey)
 {
+	/* mask of available pckmo subfunctions */
+	static cpacf_mask_t pckmo_functions;
+
 	long fc;
 	int keysize;
 	u8 paramblock[64];
@@ -114,11 +114,13 @@
 		return -EINVAL;
 	}
 
-	/*
-	 * Check if the needed pckmo subfunction is available.
-	 * These subfunctions can be enabled/disabled by customers
-	 * in the LPAR profile or may even change on the fly.
-	 */
+	/* Did we already check for PCKMO ? */
+	if (!pckmo_functions.bytes[0]) {
+		/* no, so check now */
+		if (!cpacf_query(CPACF_PCKMO, &pckmo_functions))
+			return -ENODEV;
+	}
+	/* check for the pckmo subfunction we need now */
 	if (!cpacf_test_func(&pckmo_functions, fc)) {
 		DEBUG_ERR("%s pckmo functions not available\n", __func__);
 		return -ENODEV;
@@ -2058,7 +2060,7 @@
  */
 static int __init pkey_init(void)
 {
-	cpacf_mask_t kmc_functions;
+	cpacf_mask_t func_mask;
 
 	/*
 	 * The pckmo instruction should be available - even if we don't
@@ -2066,15 +2068,15 @@
 	 * is also the minimum level for the kmc instructions which
 	 * are able to work with protected keys.
 	 */
-	if (!cpacf_query(CPACF_PCKMO, &pckmo_functions))
+	if (!cpacf_query(CPACF_PCKMO, &func_mask))
 		return -ENODEV;
 
 	/* check for kmc instructions available */
-	if (!cpacf_query(CPACF_KMC, &kmc_functions))
+	if (!cpacf_query(CPACF_KMC, &func_mask))
 		return -ENODEV;
-	if (!cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_128) ||
-	    !cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_192) ||
-	    !cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_256))
+	if (!cpacf_test_func(&func_mask, CPACF_KMC_PAES_128) ||
+	    !cpacf_test_func(&func_mask, CPACF_KMC_PAES_192) ||
+	    !cpacf_test_func(&func_mask, CPACF_KMC_PAES_256))
 		return -ENODEV;
 
 	pkey_debug_init();
diff --git a/drivers/s390/crypto/zcrypt_card.c b/drivers/s390/crypto/zcrypt_card.c
index e342eb8..33b2388 100644
--- a/drivers/s390/crypto/zcrypt_card.c
+++ b/drivers/s390/crypto/zcrypt_card.c
@@ -157,11 +157,6 @@
 {
 	int rc;
 
-	rc = sysfs_create_group(&zc->card->ap_dev.device.kobj,
-				&zcrypt_card_attr_group);
-	if (rc)
-		return rc;
-
 	spin_lock(&zcrypt_list_lock);
 	list_add_tail(&zc->list, &zcrypt_card_list);
 	spin_unlock(&zcrypt_list_lock);
@@ -170,6 +165,14 @@
 
 	ZCRYPT_DBF(DBF_INFO, "card=%02x register online=1\n", zc->card->id);
 
+	rc = sysfs_create_group(&zc->card->ap_dev.device.kobj,
+				&zcrypt_card_attr_group);
+	if (rc) {
+		spin_lock(&zcrypt_list_lock);
+		list_del_init(&zc->list);
+		spin_unlock(&zcrypt_list_lock);
+	}
+
 	return rc;
 }
 EXPORT_SYMBOL(zcrypt_card_register);
diff --git a/drivers/s390/crypto/zcrypt_queue.c b/drivers/s390/crypto/zcrypt_queue.c
index 3c20706..5062eae 100644
--- a/drivers/s390/crypto/zcrypt_queue.c
+++ b/drivers/s390/crypto/zcrypt_queue.c
@@ -180,7 +180,6 @@
 				&zcrypt_queue_attr_group);
 	if (rc)
 		goto out;
-	get_device(&zq->queue->ap_dev.device);
 
 	if (zq->ops->rng) {
 		rc = zcrypt_rng_device_add();
@@ -192,7 +191,6 @@
 out_unregister:
 	sysfs_remove_group(&zq->queue->ap_dev.device.kobj,
 			   &zcrypt_queue_attr_group);
-	put_device(&zq->queue->ap_dev.device);
 out:
 	spin_lock(&zcrypt_list_lock);
 	list_del_init(&zq->list);
@@ -220,12 +218,10 @@
 	list_del_init(&zq->list);
 	zcrypt_device_count--;
 	spin_unlock(&zcrypt_list_lock);
-	zcrypt_card_put(zc);
 	if (zq->ops->rng)
 		zcrypt_rng_device_remove();
 	sysfs_remove_group(&zq->queue->ap_dev.device.kobj,
 			   &zcrypt_queue_attr_group);
-	put_device(&zq->queue->ap_dev.device);
-	zcrypt_queue_put(zq);
+	zcrypt_card_put(zc);
 }
 EXPORT_SYMBOL(zcrypt_queue_unregister);
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index f32da0c..308bda2e 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -658,8 +658,8 @@
 					rcu_read_lock();
 					list_for_each_entry_rcu(h,
 						&tmp_pg->dh_list, node) {
-						/* h->sdev should always be valid */
-						BUG_ON(!h->sdev);
+						if (!h->sdev)
+							continue;
 						h->sdev->access_state = desc[0];
 					}
 					rcu_read_unlock();
@@ -705,7 +705,8 @@
 			pg->expiry = 0;
 			rcu_read_lock();
 			list_for_each_entry_rcu(h, &pg->dh_list, node) {
-				BUG_ON(!h->sdev);
+				if (!h->sdev)
+					continue;
 				h->sdev->access_state =
 					(pg->state & SCSI_ACCESS_STATE_MASK);
 				if (pg->pref)
@@ -1147,7 +1148,6 @@
 	spin_lock(&h->pg_lock);
 	pg = rcu_dereference_protected(h->pg, lockdep_is_held(&h->pg_lock));
 	rcu_assign_pointer(h->pg, NULL);
-	h->sdev = NULL;
 	spin_unlock(&h->pg_lock);
 	if (pg) {
 		spin_lock_irq(&pg->lock);
@@ -1156,6 +1156,7 @@
 		kref_put(&pg->kref, release_port_group);
 	}
 	sdev->handler_data = NULL;
+	synchronize_rcu();
 	kfree(h);
 }
 
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 83ce4f1..8df70c9 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -8855,7 +8855,7 @@
 	/* hook into SCSI subsystem */
 	rc = hpsa_scsi_add_host(h);
 	if (rc)
-		goto clean7; /* perf, sg, cmd, irq, shost, pci, lu, aer/h */
+		goto clean8; /* lastlogicals, perf, sg, cmd, irq, shost, pci, lu, aer/h */
 
 	/* Monitor the controller for firmware lockups */
 	h->heartbeat_sample_interval = HEARTBEAT_SAMPLE_INTERVAL;
@@ -8870,6 +8870,8 @@
 				HPSA_EVENT_MONITOR_INTERVAL);
 	return 0;
 
+clean8: /* lastlogicals, perf, sg, cmd, irq, shost, pci, lu, aer/h */
+	kfree(h->lastlogicals);
 clean7: /* perf, sg, cmd, irq, shost, pci, lu, aer/h */
 	hpsa_free_performant_mode(h);
 	h->access.set_intr_mask(h, HPSA_INTR_OFF);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 93230cd..e4cc92b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -1740,6 +1740,13 @@
 		reply_q->irq_poll_scheduled = false;
 		reply_q->irq_line_enable = true;
 		enable_irq(reply_q->os_irq);
+		/*
+		 * Go for one more round of processing the
+		 * reply descriptor post queue incase if HBA
+		 * Firmware has posted some reply descriptors
+		 * while reenabling the IRQ.
+		 */
+		_base_process_reply_queue(reply_q);
 	}
 
 	return num_entries;
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index b8f573a..7a160b8 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -1627,12 +1627,12 @@
 		 */
 		fallthrough;
 	case CLKS_OFF:
-		ufshcd_scsi_block_requests(hba);
 		hba->clk_gating.state = REQ_CLKS_ON;
 		trace_ufshcd_clk_gating(dev_name(hba->dev),
 					hba->clk_gating.state);
-		queue_work(hba->clk_gating.clk_gating_workq,
-			   &hba->clk_gating.ungate_work);
+		if (queue_work(hba->clk_gating.clk_gating_workq,
+			       &hba->clk_gating.ungate_work))
+			ufshcd_scsi_block_requests(hba);
 		/*
 		 * fall through to check if we should wait for this
 		 * work to be done or not.
@@ -2115,10 +2115,20 @@
 	unsigned long flags;
 
 	if (wait_for_completion_timeout(&uic_cmd->done,
-					msecs_to_jiffies(UIC_CMD_TIMEOUT)))
+					msecs_to_jiffies(UIC_CMD_TIMEOUT))) {
 		ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT;
-	else
+	} else {
 		ret = -ETIMEDOUT;
+		dev_err(hba->dev,
+			"uic cmd 0x%x with arg3 0x%x completion timeout\n",
+			uic_cmd->command, uic_cmd->argument3);
+
+		if (!uic_cmd->cmd_active) {
+			dev_err(hba->dev, "%s: UIC cmd has been completed, return the result\n",
+				__func__);
+			ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT;
+		}
+	}
 
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	hba->active_uic_cmd = NULL;
@@ -2150,6 +2160,7 @@
 	if (completion)
 		init_completion(&uic_cmd->done);
 
+	uic_cmd->cmd_active = 1;
 	ufshcd_dispatch_uic_cmd(hba, uic_cmd);
 
 	return 0;
@@ -3807,10 +3818,18 @@
 		dev_err(hba->dev,
 			"pwr ctrl cmd 0x%x with mode 0x%x completion timeout\n",
 			cmd->command, cmd->argument3);
+
+		if (!cmd->cmd_active) {
+			dev_err(hba->dev, "%s: Power Mode Change operation has been completed, go check UPMCRS\n",
+				__func__);
+			goto check_upmcrs;
+		}
+
 		ret = -ETIMEDOUT;
 		goto out;
 	}
 
+check_upmcrs:
 	status = ufshcd_get_upmcrs(hba);
 	if (status != PWR_LOCAL) {
 		dev_err(hba->dev,
@@ -4902,11 +4921,14 @@
 			ufshcd_get_uic_cmd_result(hba);
 		hba->active_uic_cmd->argument3 =
 			ufshcd_get_dme_attr_val(hba);
+		if (!hba->uic_async_done)
+			hba->active_uic_cmd->cmd_active = 0;
 		complete(&hba->active_uic_cmd->done);
 		retval = IRQ_HANDLED;
 	}
 
 	if ((intr_status & UFSHCD_UIC_PWR_MASK) && hba->uic_async_done) {
+		hba->active_uic_cmd->cmd_active = 0;
 		complete(hba->uic_async_done);
 		retval = IRQ_HANDLED;
 	}
@@ -8906,6 +8928,7 @@
 	blk_mq_free_tag_set(&hba->tmf_tag_set);
 	blk_cleanup_queue(hba->cmd_queue);
 	scsi_remove_host(hba->host);
+	destroy_workqueue(hba->eh_wq);
 	/* disable interrupts */
 	ufshcd_disable_intr(hba, hba->intr_mask);
 	ufshcd_hba_stop(hba);
@@ -9206,6 +9229,7 @@
 exit_gating:
 	ufshcd_exit_clk_scaling(hba);
 	ufshcd_exit_clk_gating(hba);
+	destroy_workqueue(hba->eh_wq);
 out_disable:
 	hba->is_irq_enabled = false;
 	ufshcd_hba_exit(hba);
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 47eb143..e0f00a4 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -64,6 +64,7 @@
  * @argument1: UIC command argument 1
  * @argument2: UIC command argument 2
  * @argument3: UIC command argument 3
+ * @cmd_active: Indicate if UIC command is outstanding
  * @done: UIC command completion
  */
 struct uic_command {
@@ -71,6 +72,7 @@
 	u32 argument1;
 	u32 argument2;
 	u32 argument3;
+	int cmd_active;
 	struct completion done;
 };
 
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 14c9d01..c028446 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -1327,7 +1327,7 @@
 
 	data = of_id->data;
 
-	master = spi_alloc_master(dev, sizeof(struct bcm_qspi));
+	master = devm_spi_alloc_master(dev, sizeof(struct bcm_qspi));
 	if (!master) {
 		dev_err(dev, "error allocating spi_master\n");
 		return -ENOMEM;
@@ -1367,21 +1367,17 @@
 
 	if (res) {
 		qspi->base[MSPI]  = devm_ioremap_resource(dev, res);
-		if (IS_ERR(qspi->base[MSPI])) {
-			ret = PTR_ERR(qspi->base[MSPI]);
-			goto qspi_resource_err;
-		}
+		if (IS_ERR(qspi->base[MSPI]))
+			return PTR_ERR(qspi->base[MSPI]);
 	} else {
-		goto qspi_resource_err;
+		return 0;
 	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "bspi");
 	if (res) {
 		qspi->base[BSPI]  = devm_ioremap_resource(dev, res);
-		if (IS_ERR(qspi->base[BSPI])) {
-			ret = PTR_ERR(qspi->base[BSPI]);
-			goto qspi_resource_err;
-		}
+		if (IS_ERR(qspi->base[BSPI]))
+			return PTR_ERR(qspi->base[BSPI]);
 		qspi->bspi_mode = true;
 	} else {
 		qspi->bspi_mode = false;
@@ -1392,18 +1388,14 @@
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cs_reg");
 	if (res) {
 		qspi->base[CHIP_SELECT]  = devm_ioremap_resource(dev, res);
-		if (IS_ERR(qspi->base[CHIP_SELECT])) {
-			ret = PTR_ERR(qspi->base[CHIP_SELECT]);
-			goto qspi_resource_err;
-		}
+		if (IS_ERR(qspi->base[CHIP_SELECT]))
+			return PTR_ERR(qspi->base[CHIP_SELECT]);
 	}
 
 	qspi->dev_ids = kcalloc(num_irqs, sizeof(struct bcm_qspi_dev_id),
 				GFP_KERNEL);
-	if (!qspi->dev_ids) {
-		ret = -ENOMEM;
-		goto qspi_resource_err;
-	}
+	if (!qspi->dev_ids)
+		return -ENOMEM;
 
 	for (val = 0; val < num_irqs; val++) {
 		irq = -1;
@@ -1484,7 +1476,7 @@
 	qspi->xfer_mode.addrlen = -1;
 	qspi->xfer_mode.hp = -1;
 
-	ret = devm_spi_register_master(&pdev->dev, master);
+	ret = spi_register_master(master);
 	if (ret < 0) {
 		dev_err(dev, "can't register master\n");
 		goto qspi_reg_err;
@@ -1497,8 +1489,6 @@
 	clk_disable_unprepare(qspi->clk);
 qspi_probe_err:
 	kfree(qspi->dev_ids);
-qspi_resource_err:
-	spi_master_put(master);
 	return ret;
 }
 /* probe function to be called by SoC specific platform driver probe */
@@ -1508,10 +1498,10 @@
 {
 	struct bcm_qspi *qspi = platform_get_drvdata(pdev);
 
+	spi_unregister_master(qspi->master);
 	bcm_qspi_hw_uninit(qspi);
 	clk_disable_unprepare(qspi->clk);
 	kfree(qspi->dev_ids);
-	spi_unregister_master(qspi->master);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index b87116e..197485f 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -1193,7 +1193,6 @@
 	struct spi_controller *ctlr = spi->controller;
 	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 	struct gpio_chip *chip;
-	enum gpio_lookup_flags lflags;
 	u32 cs;
 
 	/*
@@ -1259,21 +1258,9 @@
 	if (!chip)
 		return 0;
 
-	/*
-	 * Retrieve the corresponding GPIO line used for CS.
-	 * The inversion semantics will be handled by the GPIO core
-	 * code, so we pass GPIOD_OUT_LOW for "unasserted" and
-	 * the correct flag for inversion semantics. The SPI_CS_HIGH
-	 * on spi->mode cannot be checked for polarity in this case
-	 * as the flag use_gpio_descriptors enforces SPI_CS_HIGH.
-	 */
-	if (of_property_read_bool(spi->dev.of_node, "spi-cs-high"))
-		lflags = GPIO_ACTIVE_HIGH;
-	else
-		lflags = GPIO_ACTIVE_LOW;
 	spi->cs_gpiod = gpiochip_request_own_desc(chip, 8 - spi->chip_select,
 						  DRV_NAME,
-						  lflags,
+						  GPIO_LOOKUP_FLAGS_DEFAULT,
 						  GPIOD_OUT_LOW);
 	if (IS_ERR(spi->cs_gpiod))
 		return PTR_ERR(spi->cs_gpiod);
@@ -1291,7 +1278,7 @@
 	struct bcm2835_spi *bs;
 	int err;
 
-	ctlr = spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs),
+	ctlr = devm_spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs),
 						  dma_get_cache_alignment()));
 	if (!ctlr)
 		return -ENOMEM;
@@ -1312,23 +1299,17 @@
 	bs->ctlr = ctlr;
 
 	bs->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(bs->regs)) {
-		err = PTR_ERR(bs->regs);
-		goto out_controller_put;
-	}
+	if (IS_ERR(bs->regs))
+		return PTR_ERR(bs->regs);
 
 	bs->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(bs->clk)) {
-		err = dev_err_probe(&pdev->dev, PTR_ERR(bs->clk),
-				    "could not get clk\n");
-		goto out_controller_put;
-	}
+	if (IS_ERR(bs->clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(bs->clk),
+				     "could not get clk\n");
 
 	bs->irq = platform_get_irq(pdev, 0);
-	if (bs->irq <= 0) {
-		err = bs->irq ? bs->irq : -ENODEV;
-		goto out_controller_put;
-	}
+	if (bs->irq <= 0)
+		return bs->irq ? bs->irq : -ENODEV;
 
 	clk_prepare_enable(bs->clk);
 
@@ -1362,8 +1343,6 @@
 	bcm2835_dma_release(ctlr, bs);
 out_clk_disable:
 	clk_disable_unprepare(bs->clk);
-out_controller_put:
-	spi_controller_put(ctlr);
 	return err;
 }
 
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index 03b034c..1a26865 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -494,7 +494,7 @@
 	unsigned long clk_hz;
 	int err;
 
-	master = spi_alloc_master(&pdev->dev, sizeof(*bs));
+	master = devm_spi_alloc_master(&pdev->dev, sizeof(*bs));
 	if (!master)
 		return -ENOMEM;
 
@@ -524,29 +524,25 @@
 
 	/* the main area */
 	bs->regs = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(bs->regs)) {
-		err = PTR_ERR(bs->regs);
-		goto out_master_put;
-	}
+	if (IS_ERR(bs->regs))
+		return PTR_ERR(bs->regs);
 
 	bs->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(bs->clk)) {
 		err = PTR_ERR(bs->clk);
 		dev_err(&pdev->dev, "could not get clk: %d\n", err);
-		goto out_master_put;
+		return err;
 	}
 
 	bs->irq = platform_get_irq(pdev, 0);
-	if (bs->irq <= 0) {
-		err = bs->irq ? bs->irq : -ENODEV;
-		goto out_master_put;
-	}
+	if (bs->irq <= 0)
+		return bs->irq ? bs->irq : -ENODEV;
 
 	/* this also enables the HW block */
 	err = clk_prepare_enable(bs->clk);
 	if (err) {
 		dev_err(&pdev->dev, "could not prepare clock: %d\n", err);
-		goto out_master_put;
+		return err;
 	}
 
 	/* just checking if the clock returns a sane value */
@@ -581,8 +577,6 @@
 
 out_clk_disable:
 	clk_disable_unprepare(bs->clk);
-out_master_put:
-	spi_master_put(master);
 	return err;
 }
 
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 40938cf..ba7d40c 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1260,12 +1260,14 @@
 	/* Obtain QSPI reset control */
 	rstc = devm_reset_control_get_optional_exclusive(dev, "qspi");
 	if (IS_ERR(rstc)) {
+		ret = PTR_ERR(rstc);
 		dev_err(dev, "Cannot get QSPI reset.\n");
 		goto probe_reset_failed;
 	}
 
 	rstc_ocp = devm_reset_control_get_optional_exclusive(dev, "qspi-ocp");
 	if (IS_ERR(rstc_ocp)) {
+		ret = PTR_ERR(rstc_ocp);
 		dev_err(dev, "Cannot get QSPI OCP reset.\n");
 		goto probe_reset_failed;
 	}
diff --git a/drivers/spi/spi-dw-core.c b/drivers/spi/spi-dw-core.c
index 2e50cc0..0b2236a 100644
--- a/drivers/spi/spi-dw-core.c
+++ b/drivers/spi/spi-dw-core.c
@@ -357,11 +357,11 @@
 	dw_writel(dws, DW_SPI_TXFTLR, level);
 	dw_writel(dws, DW_SPI_RXFTLR, level - 1);
 
+	dws->transfer_handler = dw_spi_transfer_handler;
+
 	imask = SPI_INT_TXEI | SPI_INT_TXOI | SPI_INT_RXUI | SPI_INT_RXOI |
 		SPI_INT_RXFI;
 	spi_umask_intr(dws, imask);
-
-	dws->transfer_handler = dw_spi_transfer_handler;
 }
 
 /*
diff --git a/drivers/spi/spi-fsi.c b/drivers/spi/spi-fsi.c
index 8a440c7..3920cd3 100644
--- a/drivers/spi/spi-fsi.c
+++ b/drivers/spi/spi-fsi.c
@@ -477,7 +477,7 @@
 
 	rc = fsi_spi_check_mux(ctx->fsi, ctx->dev);
 	if (rc)
-		return rc;
+		goto error;
 
 	list_for_each_entry(transfer, &mesg->transfers, transfer_list) {
 		struct fsi_spi_sequence seq;
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 3967afa..1a08c1d 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1080,12 +1080,11 @@
 #ifdef CONFIG_PM_SLEEP
 static int dspi_suspend(struct device *dev)
 {
-	struct spi_controller *ctlr = dev_get_drvdata(dev);
-	struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
+	struct fsl_dspi *dspi = dev_get_drvdata(dev);
 
 	if (dspi->irq)
 		disable_irq(dspi->irq);
-	spi_controller_suspend(ctlr);
+	spi_controller_suspend(dspi->ctlr);
 	clk_disable_unprepare(dspi->clk);
 
 	pinctrl_pm_select_sleep_state(dev);
@@ -1095,8 +1094,7 @@
 
 static int dspi_resume(struct device *dev)
 {
-	struct spi_controller *ctlr = dev_get_drvdata(dev);
-	struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
+	struct fsl_dspi *dspi = dev_get_drvdata(dev);
 	int ret;
 
 	pinctrl_pm_select_default_state(dev);
@@ -1104,7 +1102,7 @@
 	ret = clk_prepare_enable(dspi->clk);
 	if (ret)
 		return ret;
-	spi_controller_resume(ctlr);
+	spi_controller_resume(dspi->ctlr);
 	if (dspi->irq)
 		enable_irq(dspi->irq);
 
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 986b979..a2886ee 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -938,9 +938,6 @@
 				spi_controller_get_devdata(controller);
 
 	pm_runtime_disable(fsl_lpspi->dev);
-
-	spi_master_put(controller);
-
 	return 0;
 }
 
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 060b1f5..4b80e27 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1676,15 +1676,18 @@
 		goto out_master_put;
 	}
 
-	pm_runtime_enable(spi_imx->dev);
+	ret = clk_prepare_enable(spi_imx->clk_per);
+	if (ret)
+		goto out_master_put;
+
+	ret = clk_prepare_enable(spi_imx->clk_ipg);
+	if (ret)
+		goto out_put_per;
+
 	pm_runtime_set_autosuspend_delay(spi_imx->dev, MXC_RPM_TIMEOUT);
 	pm_runtime_use_autosuspend(spi_imx->dev);
-
-	ret = pm_runtime_get_sync(spi_imx->dev);
-	if (ret < 0) {
-		dev_err(spi_imx->dev, "failed to enable clock\n");
-		goto out_runtime_pm_put;
-	}
+	pm_runtime_set_active(spi_imx->dev);
+	pm_runtime_enable(spi_imx->dev);
 
 	spi_imx->spi_clk = clk_get_rate(spi_imx->clk_per);
 	/*
@@ -1722,8 +1725,12 @@
 		spi_imx_sdma_exit(spi_imx);
 out_runtime_pm_put:
 	pm_runtime_dont_use_autosuspend(spi_imx->dev);
-	pm_runtime_put_sync(spi_imx->dev);
+	pm_runtime_set_suspended(&pdev->dev);
 	pm_runtime_disable(spi_imx->dev);
+
+	clk_disable_unprepare(spi_imx->clk_ipg);
+out_put_per:
+	clk_disable_unprepare(spi_imx->clk_per);
 out_master_put:
 	spi_master_put(master);
 
diff --git a/drivers/spi/spi-npcm-fiu.c b/drivers/spi/spi-npcm-fiu.c
index 341f7cf..1cb9329 100644
--- a/drivers/spi/spi-npcm-fiu.c
+++ b/drivers/spi/spi-npcm-fiu.c
@@ -679,7 +679,7 @@
 	struct resource *res;
 	int id;
 
-	ctrl = spi_alloc_master(dev, sizeof(*fiu));
+	ctrl = devm_spi_alloc_master(dev, sizeof(*fiu));
 	if (!ctrl)
 		return -ENOMEM;
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 0cab239..05c75f8 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -812,18 +812,16 @@
 		enable = !enable;
 
 	if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio)) {
-		/*
-		 * Honour the SPI_NO_CS flag and invert the enable line, as
-		 * active low is default for SPI. Execution paths that handle
-		 * polarity inversion in gpiolib (such as device tree) will
-		 * enforce active high using the SPI_CS_HIGH resulting in a
-		 * double inversion through the code above.
-		 */
 		if (!(spi->mode & SPI_NO_CS)) {
 			if (spi->cs_gpiod)
+				/* polarity handled by gpiolib */
 				gpiod_set_value_cansleep(spi->cs_gpiod,
-							 !enable);
+							 enable1);
 			else
+				/*
+				 * invert the enable line, as active low is
+				 * default for SPI.
+				 */
 				gpio_set_value_cansleep(spi->cs_gpio, !enable);
 		}
 		/* Some SPI masters need both GPIO CS & slave_select */
@@ -1992,15 +1990,6 @@
 	}
 	spi->chip_select = value;
 
-	/*
-	 * For descriptors associated with the device, polarity inversion is
-	 * handled in the gpiolib, so all gpio chip selects are "active high"
-	 * in the logical sense, the gpiolib will invert the line if need be.
-	 */
-	if ((ctlr->use_gpio_descriptors) && ctlr->cs_gpiods &&
-	    ctlr->cs_gpiods[spi->chip_select])
-		spi->mode |= SPI_CS_HIGH;
-
 	/* Device speed */
 	if (!of_property_read_u32(nc, "spi-max-frequency", &value))
 		spi->max_speed_hz = value;
@@ -2453,6 +2442,49 @@
 }
 EXPORT_SYMBOL_GPL(__spi_alloc_controller);
 
+static void devm_spi_release_controller(struct device *dev, void *ctlr)
+{
+	spi_controller_put(*(struct spi_controller **)ctlr);
+}
+
+/**
+ * __devm_spi_alloc_controller - resource-managed __spi_alloc_controller()
+ * @dev: physical device of SPI controller
+ * @size: how much zeroed driver-private data to allocate
+ * @slave: whether to allocate an SPI master (false) or SPI slave (true)
+ * Context: can sleep
+ *
+ * Allocate an SPI controller and automatically release a reference on it
+ * when @dev is unbound from its driver.  Drivers are thus relieved from
+ * having to call spi_controller_put().
+ *
+ * The arguments to this function are identical to __spi_alloc_controller().
+ *
+ * Return: the SPI controller structure on success, else NULL.
+ */
+struct spi_controller *__devm_spi_alloc_controller(struct device *dev,
+						   unsigned int size,
+						   bool slave)
+{
+	struct spi_controller **ptr, *ctlr;
+
+	ptr = devres_alloc(devm_spi_release_controller, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return NULL;
+
+	ctlr = __spi_alloc_controller(dev, size, slave);
+	if (ctlr) {
+		*ptr = ctlr;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return ctlr;
+}
+EXPORT_SYMBOL_GPL(__devm_spi_alloc_controller);
+
 #ifdef CONFIG_OF
 static int of_spi_get_gpio_numbers(struct spi_controller *ctlr)
 {
@@ -2789,6 +2821,11 @@
 }
 EXPORT_SYMBOL_GPL(devm_spi_register_controller);
 
+static int devm_spi_match_controller(struct device *dev, void *res, void *ctlr)
+{
+	return *(struct spi_controller **)res == ctlr;
+}
+
 static int __unregister(struct device *dev, void *null)
 {
 	spi_unregister_device(to_spi_device(dev));
@@ -2830,7 +2867,15 @@
 	list_del(&ctlr->list);
 	mutex_unlock(&board_lock);
 
-	device_unregister(&ctlr->dev);
+	device_del(&ctlr->dev);
+
+	/* Release the last reference on the controller if its driver
+	 * has not yet been converted to devm_spi_alloc_master/slave().
+	 */
+	if (!devres_find(ctlr->dev.parent, devm_spi_release_controller,
+			 devm_spi_match_controller, ctlr))
+		put_device(&ctlr->dev);
+
 	/* free bus id */
 	mutex_lock(&board_lock);
 	if (found == ctlr)
diff --git a/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml b/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
index 43b5630..510edd1 100644
--- a/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
+++ b/drivers/staging/wfx/Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
@@ -24,7 +24,7 @@
     In addition, it is recommended to declare a mmc-pwrseq on SDIO host above
     WFx. Without it, you may encounter issues with warm boot. The mmc-pwrseq
     should be compatible with mmc-pwrseq-simple. Please consult
-    Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt for more
+    Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.yaml for more
     information.
 
   For SPI':'
diff --git a/drivers/tee/amdtee/amdtee_private.h b/drivers/tee/amdtee/amdtee_private.h
index d7f798c..337c8d8 100644
--- a/drivers/tee/amdtee/amdtee_private.h
+++ b/drivers/tee/amdtee/amdtee_private.h
@@ -64,9 +64,13 @@
 /**
  * struct amdtee_context_data - AMD-TEE driver context data
  * @sess_list:    Keeps track of sessions opened in current TEE context
+ * @shm_list:     Keeps track of buffers allocated and mapped in current TEE
+ *                context
  */
 struct amdtee_context_data {
 	struct list_head sess_list;
+	struct list_head shm_list;
+	struct mutex shm_mutex;   /* synchronizes access to @shm_list */
 };
 
 struct amdtee_driver_data {
@@ -89,10 +93,6 @@
 	u32     buf_id;
 };
 
-struct amdtee_shm_context {
-	struct list_head shmdata_list;
-};
-
 #define LOWER_TWO_BYTE_MASK	0x0000FFFF
 
 /**
diff --git a/drivers/tee/amdtee/core.c b/drivers/tee/amdtee/core.c
index 27b4cd7..8a6a8f3 100644
--- a/drivers/tee/amdtee/core.c
+++ b/drivers/tee/amdtee/core.c
@@ -20,7 +20,6 @@
 
 static struct amdtee_driver_data *drv_data;
 static DEFINE_MUTEX(session_list_mutex);
-static struct amdtee_shm_context shmctx;
 
 static void amdtee_get_version(struct tee_device *teedev,
 			       struct tee_ioctl_version_data *vers)
@@ -42,7 +41,8 @@
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&ctxdata->sess_list);
-	INIT_LIST_HEAD(&shmctx.shmdata_list);
+	INIT_LIST_HEAD(&ctxdata->shm_list);
+	mutex_init(&ctxdata->shm_mutex);
 
 	ctx->data = ctxdata;
 	return 0;
@@ -86,6 +86,7 @@
 		list_del(&sess->list_node);
 		release_session(sess);
 	}
+	mutex_destroy(&ctxdata->shm_mutex);
 	kfree(ctxdata);
 
 	ctx->data = NULL;
@@ -152,14 +153,17 @@
 
 u32 get_buffer_id(struct tee_shm *shm)
 {
-	u32 buf_id = 0;
+	struct amdtee_context_data *ctxdata = shm->ctx->data;
 	struct amdtee_shm_data *shmdata;
+	u32 buf_id = 0;
 
-	list_for_each_entry(shmdata, &shmctx.shmdata_list, shm_node)
+	mutex_lock(&ctxdata->shm_mutex);
+	list_for_each_entry(shmdata, &ctxdata->shm_list, shm_node)
 		if (shmdata->kaddr == shm->kaddr) {
 			buf_id = shmdata->buf_id;
 			break;
 		}
+	mutex_unlock(&ctxdata->shm_mutex);
 
 	return buf_id;
 }
@@ -333,8 +337,9 @@
 
 int amdtee_map_shmem(struct tee_shm *shm)
 {
-	struct shmem_desc shmem;
+	struct amdtee_context_data *ctxdata;
 	struct amdtee_shm_data *shmnode;
+	struct shmem_desc shmem;
 	int rc, count;
 	u32 buf_id;
 
@@ -362,7 +367,10 @@
 
 	shmnode->kaddr = shm->kaddr;
 	shmnode->buf_id = buf_id;
-	list_add(&shmnode->shm_node, &shmctx.shmdata_list);
+	ctxdata = shm->ctx->data;
+	mutex_lock(&ctxdata->shm_mutex);
+	list_add(&shmnode->shm_node, &ctxdata->shm_list);
+	mutex_unlock(&ctxdata->shm_mutex);
 
 	pr_debug("buf_id :[%x] kaddr[%p]\n", shmnode->buf_id, shmnode->kaddr);
 
@@ -371,6 +379,7 @@
 
 void amdtee_unmap_shmem(struct tee_shm *shm)
 {
+	struct amdtee_context_data *ctxdata;
 	struct amdtee_shm_data *shmnode;
 	u32 buf_id;
 
@@ -381,12 +390,15 @@
 	/* Unmap the shared memory from TEE */
 	handle_unmap_shmem(buf_id);
 
-	list_for_each_entry(shmnode, &shmctx.shmdata_list, shm_node)
+	ctxdata = shm->ctx->data;
+	mutex_lock(&ctxdata->shm_mutex);
+	list_for_each_entry(shmnode, &ctxdata->shm_list, shm_node)
 		if (buf_id == shmnode->buf_id) {
 			list_del(&shmnode->shm_node);
 			kfree(shmnode);
 			break;
 		}
+	mutex_unlock(&ctxdata->shm_mutex);
 }
 
 int amdtee_invoke_func(struct tee_context *ctx,
diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.c b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
index 5e59616..dcac99f 100644
--- a/drivers/thermal/ti-soc-thermal/ti-bandgap.c
+++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
@@ -20,6 +20,7 @@
 #include <linux/err.h>
 #include <linux/types.h>
 #include <linux/spinlock.h>
+#include <linux/sys_soc.h>
 #include <linux/reboot.h>
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
@@ -864,6 +865,17 @@
 	return bgp;
 }
 
+/*
+ * List of SoCs on which the CPU PM notifier can cause erros on the DTEMP
+ * readout.
+ * Enabled notifier on these machines results in erroneous, random values which
+ * could trigger unexpected thermal shutdown.
+ */
+static const struct soc_device_attribute soc_no_cpu_notifier[] = {
+	{ .machine = "OMAP4430" },
+	{ /* sentinel */ },
+};
+
 /***   Device driver call backs   ***/
 
 static
@@ -1020,7 +1032,8 @@
 
 #ifdef CONFIG_PM_SLEEP
 	bgp->nb.notifier_call = bandgap_omap_cpu_notifier;
-	cpu_pm_register_notifier(&bgp->nb);
+	if (!soc_device_match(soc_no_cpu_notifier))
+		cpu_pm_register_notifier(&bgp->nb);
 #endif
 
 	return 0;
@@ -1056,7 +1069,8 @@
 	struct ti_bandgap *bgp = platform_get_drvdata(pdev);
 	int i;
 
-	cpu_pm_unregister_notifier(&bgp->nb);
+	if (!soc_device_match(soc_no_cpu_notifier))
+		cpu_pm_unregister_notifier(&bgp->nb);
 
 	/* Remove sensor interfaces */
 	for (i = 0; i < bgp->conf->sensor_count; i++) {
diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c
index 3680b27..ed65d2b 100644
--- a/drivers/thunderbolt/debugfs.c
+++ b/drivers/thunderbolt/debugfs.c
@@ -9,6 +9,7 @@
 
 #include <linux/debugfs.h>
 #include <linux/pm_runtime.h>
+#include <linux/uaccess.h>
 
 #include "tb.h"
 
diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c
index b51fc3f..977ba91 100644
--- a/drivers/thunderbolt/icm.c
+++ b/drivers/thunderbolt/icm.c
@@ -2284,6 +2284,8 @@
 
 	case PCI_DEVICE_ID_INTEL_TGL_NHI0:
 	case PCI_DEVICE_ID_INTEL_TGL_NHI1:
+	case PCI_DEVICE_ID_INTEL_TGL_H_NHI0:
+	case PCI_DEVICE_ID_INTEL_TGL_H_NHI1:
 		icm->is_supported = icm_tgl_is_supported;
 		icm->driver_ready = icm_icl_driver_ready;
 		icm->set_uuid = icm_icl_set_uuid;
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index 3f79baa..db80dc5 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -406,12 +406,23 @@
 
 	ring->vector = ret;
 
-	ring->irq = pci_irq_vector(ring->nhi->pdev, ring->vector);
-	if (ring->irq < 0)
-		return ring->irq;
+	ret = pci_irq_vector(ring->nhi->pdev, ring->vector);
+	if (ret < 0)
+		goto err_ida_remove;
+
+	ring->irq = ret;
 
 	irqflags = no_suspend ? IRQF_NO_SUSPEND : 0;
-	return request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring);
+	ret = request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring);
+	if (ret)
+		goto err_ida_remove;
+
+	return 0;
+
+err_ida_remove:
+	ida_simple_remove(&nhi->msix_ida, ring->vector);
+
+	return ret;
 }
 
 static void ring_release_msix(struct tb_ring *ring)
@@ -1334,6 +1345,10 @@
 	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_NHI1),
 	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI0),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI1),
+	  .driver_data = (kernel_ulong_t)&icl_nhi_ops },
 
 	/* Any USB4 compliant host */
 	{ PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_USB_USB4, ~0) },
diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h
index 80162e4..4e0861d 100644
--- a/drivers/thunderbolt/nhi.h
+++ b/drivers/thunderbolt/nhi.h
@@ -75,6 +75,8 @@
 #define PCI_DEVICE_ID_INTEL_ICL_NHI0			0x8a17
 #define PCI_DEVICE_ID_INTEL_TGL_NHI0			0x9a1b
 #define PCI_DEVICE_ID_INTEL_TGL_NHI1			0x9a1d
+#define PCI_DEVICE_ID_INTEL_TGL_H_NHI0			0x9a1f
+#define PCI_DEVICE_ID_INTEL_TGL_H_NHI1			0x9a21
 
 #define PCI_CLASS_SERIAL_USB_USB4			0x0c0340
 
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index a9995e2..8ea360b 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -784,6 +784,8 @@
 		switch (sw->config.device_id) {
 		case PCI_DEVICE_ID_INTEL_TGL_NHI0:
 		case PCI_DEVICE_ID_INTEL_TGL_NHI1:
+		case PCI_DEVICE_ID_INTEL_TGL_H_NHI0:
+		case PCI_DEVICE_ID_INTEL_TGL_H_NHI1:
 			return true;
 		}
 	}
diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c
index 40f1357..f2583b4 100644
--- a/drivers/thunderbolt/usb4.c
+++ b/drivers/thunderbolt/usb4.c
@@ -421,8 +421,12 @@
 	 * upstream USB4 port.
 	 */
 	tb_switch_for_each_port(sw, port) {
+		if (!tb_port_is_null(port))
+			continue;
 		if (!route && tb_is_upstream_port(port))
 			continue;
+		if (!port->cap_usb4)
+			continue;
 
 		ret = tb_port_read(port, &val, TB_CFG_PORT,
 				   port->cap_usb4 + PORT_CS_19, 1);
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index 4890785..c00ad81 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -881,6 +881,7 @@
 
 		id = ida_simple_get(&xd->service_ids, 0, 0, GFP_KERNEL);
 		if (id < 0) {
+			kfree(svc->key);
 			kfree(svc);
 			break;
 		}
diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c
index 41f4120..fa876e2 100644
--- a/drivers/tty/serial/8250/8250_mtk.c
+++ b/drivers/tty/serial/8250/8250_mtk.c
@@ -317,7 +317,7 @@
 	 */
 	baud = tty_termios_baud_rate(termios);
 
-	serial8250_do_set_termios(port, termios, old);
+	serial8250_do_set_termios(port, termios, NULL);
 
 	tty_termios_encode_baud_rate(termios, baud, baud);
 
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 1044fc3..28f22e5 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -522,6 +522,7 @@
 	depends on OF
 	select SERIAL_EARLYCON
 	select SERIAL_CORE_CONSOLE
+	default y if SERIAL_IMX_CONSOLE
 	help
 	  If you have enabled the earlycon on the Freescale IMX
 	  CPU you can make it the earlycon by answering Y to this option.
diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c
index b4d89e3..7a07e72 100644
--- a/drivers/tty/serial/serial_txx9.c
+++ b/drivers/tty/serial/serial_txx9.c
@@ -1280,6 +1280,9 @@
 
 #ifdef ENABLE_SERIAL_TXX9_PCI
 	ret = pci_register_driver(&serial_txx9_pci_driver);
+	if (ret) {
+		platform_driver_unregister(&serial_txx9_plat_driver);
+	}
 #endif
 	if (ret == 0)
 		goto out;
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 7a4c025..9f8b9a5 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1515,10 +1515,12 @@
 		tty->ops->shutdown(tty);
 	tty_save_termios(tty);
 	tty_driver_remove_tty(tty->driver, tty);
-	tty->port->itty = NULL;
+	if (tty->port)
+		tty->port->itty = NULL;
 	if (tty->link)
 		tty->link->port->itty = NULL;
-	tty_buffer_cancel_work(tty->port);
+	if (tty->port)
+		tty_buffer_cancel_work(tty->port);
 	if (tty->link)
 		tty_buffer_cancel_work(tty->link->port);
 
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 9506a76..d04a162 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -4704,27 +4704,6 @@
 	return rc;
 }
 
-static int con_font_copy(struct vc_data *vc, struct console_font_op *op)
-{
-	int con = op->height;
-	int rc;
-
-
-	console_lock();
-	if (vc->vc_mode != KD_TEXT)
-		rc = -EINVAL;
-	else if (!vc->vc_sw->con_font_copy)
-		rc = -ENOSYS;
-	else if (con < 0 || !vc_cons_allocated(con))
-		rc = -ENOTTY;
-	else if (con == vc->vc_num)	/* nothing to do */
-		rc = 0;
-	else
-		rc = vc->vc_sw->con_font_copy(vc, con);
-	console_unlock();
-	return rc;
-}
-
 int con_font_op(struct vc_data *vc, struct console_font_op *op)
 {
 	switch (op->op) {
@@ -4735,7 +4714,8 @@
 	case KD_FONT_OP_SET_DEFAULT:
 		return con_font_default(vc, op);
 	case KD_FONT_OP_COPY:
-		return con_font_copy(vc, op);
+		/* was buggy and never really used */
+		return -EINVAL;
 	}
 	return -ENOSYS;
 }
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index 2321775..5f61b25a9 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -484,7 +484,7 @@
 	return 0;
 }
 
-static inline int do_fontx_ioctl(int cmd,
+static inline int do_fontx_ioctl(struct vc_data *vc, int cmd,
 		struct consolefontdesc __user *user_cfd,
 		struct console_font_op *op)
 {
@@ -502,15 +502,16 @@
 		op->height = cfdarg.charheight;
 		op->charcount = cfdarg.charcount;
 		op->data = cfdarg.chardata;
-		return con_font_op(vc_cons[fg_console].d, op);
-	case GIO_FONTX: {
+		return con_font_op(vc, op);
+
+	case GIO_FONTX:
 		op->op = KD_FONT_OP_GET;
 		op->flags = KD_FONT_FLAG_OLD;
 		op->width = 8;
 		op->height = cfdarg.charheight;
 		op->charcount = cfdarg.charcount;
 		op->data = cfdarg.chardata;
-		i = con_font_op(vc_cons[fg_console].d, op);
+		i = con_font_op(vc, op);
 		if (i)
 			return i;
 		cfdarg.charheight = op->height;
@@ -518,12 +519,11 @@
 		if (copy_to_user(user_cfd, &cfdarg, sizeof(struct consolefontdesc)))
 			return -EFAULT;
 		return 0;
-		}
 	}
 	return -EINVAL;
 }
 
-static int vt_io_fontreset(struct console_font_op *op)
+static int vt_io_fontreset(struct vc_data *vc, struct console_font_op *op)
 {
 	int ret;
 
@@ -537,12 +537,12 @@
 
 	op->op = KD_FONT_OP_SET_DEFAULT;
 	op->data = NULL;
-	ret = con_font_op(vc_cons[fg_console].d, op);
+	ret = con_font_op(vc, op);
 	if (ret)
 		return ret;
 
 	console_lock();
-	con_set_default_unimap(vc_cons[fg_console].d);
+	con_set_default_unimap(vc);
 	console_unlock();
 
 	return 0;
@@ -584,7 +584,7 @@
 		op.height = 0;
 		op.charcount = 256;
 		op.data = up;
-		return con_font_op(vc_cons[fg_console].d, &op);
+		return con_font_op(vc, &op);
 
 	case GIO_FONT:
 		op.op = KD_FONT_OP_GET;
@@ -593,7 +593,7 @@
 		op.height = 32;
 		op.charcount = 256;
 		op.data = up;
-		return con_font_op(vc_cons[fg_console].d, &op);
+		return con_font_op(vc, &op);
 
 	case PIO_CMAP:
                 if (!perm)
@@ -609,13 +609,13 @@
 
 		fallthrough;
 	case GIO_FONTX:
-		return do_fontx_ioctl(cmd, up, &op);
+		return do_fontx_ioctl(vc, cmd, up, &op);
 
 	case PIO_FONTRESET:
 		if (!perm)
 			return -EPERM;
 
-		return vt_io_fontreset(&op);
+		return vt_io_fontreset(vc, &op);
 
 	case PIO_SCRNMAP:
 		if (!perm)
@@ -1066,8 +1066,9 @@
 };
 
 static inline int
-compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd,
-			 int perm, struct console_font_op *op)
+compat_fontx_ioctl(struct vc_data *vc, int cmd,
+		   struct compat_consolefontdesc __user *user_cfd,
+		   int perm, struct console_font_op *op)
 {
 	struct compat_consolefontdesc cfdarg;
 	int i;
@@ -1085,7 +1086,8 @@
 		op->height = cfdarg.charheight;
 		op->charcount = cfdarg.charcount;
 		op->data = compat_ptr(cfdarg.chardata);
-		return con_font_op(vc_cons[fg_console].d, op);
+		return con_font_op(vc, op);
+
 	case GIO_FONTX:
 		op->op = KD_FONT_OP_GET;
 		op->flags = KD_FONT_FLAG_OLD;
@@ -1093,7 +1095,7 @@
 		op->height = cfdarg.charheight;
 		op->charcount = cfdarg.charcount;
 		op->data = compat_ptr(cfdarg.chardata);
-		i = con_font_op(vc_cons[fg_console].d, op);
+		i = con_font_op(vc, op);
 		if (i)
 			return i;
 		cfdarg.charheight = op->height;
@@ -1183,7 +1185,7 @@
 	 */
 	case PIO_FONTX:
 	case GIO_FONTX:
-		return compat_fontx_ioctl(cmd, up, perm, &op);
+		return compat_fontx_ioctl(vc, cmd, up, perm, &op);
 
 	case KDFONTOP:
 		return compat_kdfontop_ioctl(up, perm, &op, vc);
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index 6dca744..be06f1a 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -413,10 +413,10 @@
 	return retval;
 }
 
-static void uio_free_minor(struct uio_device *idev)
+static void uio_free_minor(unsigned long minor)
 {
 	mutex_lock(&minor_lock);
-	idr_remove(&uio_idr, idev->minor);
+	idr_remove(&uio_idr, minor);
 	mutex_unlock(&minor_lock);
 }
 
@@ -990,7 +990,7 @@
 err_uio_dev_add_attributes:
 	device_del(&idev->dev);
 err_device_create:
-	uio_free_minor(idev);
+	uio_free_minor(idev->minor);
 	put_device(&idev->dev);
 	return ret;
 }
@@ -1042,11 +1042,13 @@
 void uio_unregister_device(struct uio_info *info)
 {
 	struct uio_device *idev;
+	unsigned long minor;
 
 	if (!info || !info->uio_dev)
 		return;
 
 	idev = info->uio_dev;
+	minor = idev->minor;
 
 	mutex_lock(&idev->info_lock);
 	uio_dev_del_attributes(idev);
@@ -1062,7 +1064,7 @@
 
 	device_unregister(&idev->dev);
 
-	uio_free_minor(idev);
+	uio_free_minor(minor);
 
 	return;
 }
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 1e75688..f52f1bc 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1693,6 +1693,15 @@
 	{ USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */
 	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
 	},
+	{ USB_DEVICE(0x045b, 0x023c),	/* Renesas USB Download mode */
+	.driver_info = DISABLE_ECHO,	/* Don't echo banner */
+	},
+	{ USB_DEVICE(0x045b, 0x0248),	/* Renesas USB Download mode */
+	.driver_info = DISABLE_ECHO,	/* Don't echo banner */
+	},
+	{ USB_DEVICE(0x045b, 0x024D),	/* Renesas USB Download mode */
+	.driver_info = DISABLE_ECHO,	/* Don't echo banner */
+	},
 	{ USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov@gmail.com */
 	.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
 	},
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 10574fa..a1e3a03 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -378,6 +378,9 @@
 	{ USB_DEVICE(0x0926, 0x3333), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
 
+	/* Kingston DataTraveler 3.0 */
+	{ USB_DEVICE(0x0951, 0x1666), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* X-Rite/Gretag-Macbeth Eye-One Pro display colorimeter */
 	{ USB_DEVICE(0x0971, 0x2000), .driver_info = USB_QUIRK_NO_SET_INTF },
 
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index e282067..5f18acac 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -608,10 +608,13 @@
 #endif /* CONFIG_USB_DWC2_PERIPHERAL || CONFIG_USB_DWC2_DUAL_ROLE */
 	return 0;
 
+#if IS_ENABLED(CONFIG_USB_DWC2_PERIPHERAL) || \
+	IS_ENABLED(CONFIG_USB_DWC2_DUAL_ROLE)
 error_debugfs:
 	dwc2_debugfs_exit(hsotg);
 	if (hsotg->hcd_enabled)
 		dwc2_hcd_remove(hsotg);
+#endif
 error_drd:
 	dwc2_drd_exit(hsotg);
 
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 242b621..bae6a70 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -40,6 +40,7 @@
 #define PCI_DEVICE_ID_INTEL_TGPLP		0xa0ee
 #define PCI_DEVICE_ID_INTEL_TGPH		0x43ee
 #define PCI_DEVICE_ID_INTEL_JSP			0x4dee
+#define PCI_DEVICE_ID_INTEL_ADLS		0x7ae1
 
 #define PCI_INTEL_BXT_DSM_GUID		"732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511"
 #define PCI_INTEL_BXT_FUNC_PMU_PWR	4
@@ -367,6 +368,9 @@
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_JSP),
 	  (kernel_ulong_t) &dwc3_pci_intel_properties, },
 
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADLS),
+	  (kernel_ulong_t) &dwc3_pci_intel_properties, },
+
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_NL_USB),
 	  (kernel_ulong_t) &dwc3_pci_amd_properties, },
 	{  }	/* Terminating Entry */
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 7be3903..8b668ef 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -1058,10 +1058,11 @@
 {
 	unsigned int direction = !dwc->ep0_expect_in;
 
+	dwc->delayed_status = false;
+
 	if (dwc->ep0state != EP0_STATUS_PHASE)
 		return;
 
-	dwc->delayed_status = false;
 	__dwc3_ep0_do_control_status(dwc, dwc->eps[direction]);
 }
 
diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c
index e01e366..062dfac 100644
--- a/drivers/usb/gadget/legacy/raw_gadget.c
+++ b/drivers/usb/gadget/legacy/raw_gadget.c
@@ -564,9 +564,12 @@
 		return -ENODEV;
 	}
 	length = min(arg.length, event->length);
-	if (copy_to_user((void __user *)value, event, sizeof(*event) + length))
+	if (copy_to_user((void __user *)value, event, sizeof(*event) + length)) {
+		kfree(event);
 		return -EFAULT;
+	}
 
+	kfree(event);
 	return 0;
 }
 
diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index de528e3..ad6ff9c 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -1051,7 +1051,7 @@
 	u32 bitmask;
 	struct ep_queue_head *qh;
 
-	if (!_ep || _ep->desc || !(_ep->desc->bEndpointAddress&0xF))
+	if (!_ep || !_ep->desc || !(_ep->desc->bEndpointAddress&0xF))
 		return -ENODEV;
 
 	ep = container_of(_ep, struct fsl_ep, ep);
diff --git a/drivers/usb/gadget/udc/goku_udc.c b/drivers/usb/gadget/udc/goku_udc.c
index 25c1d6a..3e1267d3 100644
--- a/drivers/usb/gadget/udc/goku_udc.c
+++ b/drivers/usb/gadget/udc/goku_udc.c
@@ -1760,6 +1760,7 @@
 		goto err;
 	}
 
+	pci_set_drvdata(pdev, dev);
 	spin_lock_init(&dev->lock);
 	dev->pdev = pdev;
 	dev->gadget.ops = &goku_ops;
@@ -1793,7 +1794,6 @@
 	}
 	dev->regs = (struct goku_udc_regs __iomem *) base;
 
-	pci_set_drvdata(pdev, dev);
 	INFO(dev, "%s\n", driver_desc);
 	INFO(dev, "version: " DRIVER_VERSION " %s\n", dmastr());
 	INFO(dev, "irq %d, pci mem %p\n", pdev->irq, base);
diff --git a/drivers/usb/host/xhci-histb.c b/drivers/usb/host/xhci-histb.c
index 5546e7e..0836985 100644
--- a/drivers/usb/host/xhci-histb.c
+++ b/drivers/usb/host/xhci-histb.c
@@ -240,7 +240,7 @@
 	/* Initialize dma_mask and coherent_dma_mask to 32-bits */
 	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
 	if (ret)
-		return ret;
+		goto disable_pm;
 
 	hcd = usb_create_hcd(driver, dev, dev_name(dev));
 	if (!hcd) {
diff --git a/drivers/usb/misc/apple-mfi-fastcharge.c b/drivers/usb/misc/apple-mfi-fastcharge.c
index 579d8c8..9de0171 100644
--- a/drivers/usb/misc/apple-mfi-fastcharge.c
+++ b/drivers/usb/misc/apple-mfi-fastcharge.c
@@ -120,8 +120,10 @@
 	dev_dbg(&mfi->udev->dev, "prop: %d\n", psp);
 
 	ret = pm_runtime_get_sync(&mfi->udev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(&mfi->udev->dev);
 		return ret;
+	}
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_CHARGE_TYPE:
diff --git a/drivers/usb/mtu3/mtu3_gadget.c b/drivers/usb/mtu3/mtu3_gadget.c
index 1de5c9a..38f17d6 100644
--- a/drivers/usb/mtu3/mtu3_gadget.c
+++ b/drivers/usb/mtu3/mtu3_gadget.c
@@ -564,6 +564,7 @@
 
 	spin_unlock_irqrestore(&mtu->lock, flags);
 
+	synchronize_irq(mtu->irq);
 	return 0;
 }
 
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 30085b2..5892f3c 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -429,10 +429,12 @@
 	struct platform_device *parent = to_platform_device(dev->parent);
 	const struct dsps_musb_wrapper *wrp = glue->wrp;
 	void __iomem *reg_base;
+	struct resource *r;
 	u32 rev, val;
 	int ret;
 
-	reg_base = devm_platform_ioremap_resource_byname(parent, "control");
+	r = platform_get_resource_byname(parent, IORESOURCE_MEM, "control");
+	reg_base = devm_ioremap_resource(dev, r);
 	if (IS_ERR(reg_base))
 		return PTR_ERR(reg_base);
 	musb->ctrl_base = reg_base;
diff --git a/drivers/usb/serial/cyberjack.c b/drivers/usb/serial/cyberjack.c
index 8219706..2e40908 100644
--- a/drivers/usb/serial/cyberjack.c
+++ b/drivers/usb/serial/cyberjack.c
@@ -357,11 +357,12 @@
 	struct device *dev = &port->dev;
 	int status = urb->status;
 	unsigned long flags;
+	bool resubmitted = false;
 
-	set_bit(0, &port->write_urbs_free);
 	if (status) {
 		dev_dbg(dev, "%s - nonzero write bulk status received: %d\n",
 			__func__, status);
+		set_bit(0, &port->write_urbs_free);
 		return;
 	}
 
@@ -394,6 +395,8 @@
 			goto exit;
 		}
 
+		resubmitted = true;
+
 		dev_dbg(dev, "%s - priv->wrsent=%d\n", __func__, priv->wrsent);
 		dev_dbg(dev, "%s - priv->wrfilled=%d\n", __func__, priv->wrfilled);
 
@@ -410,6 +413,8 @@
 
 exit:
 	spin_unlock_irqrestore(&priv->lock, flags);
+	if (!resubmitted)
+		set_bit(0, &port->write_urbs_free);
 	usb_serial_port_softint(port);
 }
 
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 2a3bfd6..54ca85c 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -250,6 +250,7 @@
 #define QUECTEL_PRODUCT_EP06			0x0306
 #define QUECTEL_PRODUCT_EM12			0x0512
 #define QUECTEL_PRODUCT_RM500Q			0x0800
+#define QUECTEL_PRODUCT_EC200T			0x6026
 
 #define CMOTECH_VENDOR_ID			0x16d8
 #define CMOTECH_PRODUCT_6001			0x6001
@@ -1117,6 +1118,7 @@
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10),
 	  .driver_info = ZLP },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) },
 
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
@@ -1189,6 +1191,8 @@
 	  .driver_info = NCTRL(0) | RSVD(1) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1054, 0xff),	/* Telit FT980-KS */
 	  .driver_info = NCTRL(2) | RSVD(3) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1055, 0xff),	/* Telit FN980 (PCIe) */
+	  .driver_info = NCTRL(0) | RSVD(1) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
@@ -1201,6 +1205,8 @@
 	  .driver_info = NCTRL(0) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1203, 0xff),	/* Telit LE910Cx (RNDIS) */
+	  .driver_info = NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),
@@ -1215,6 +1221,10 @@
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1213, 0xff) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1214),
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) | RSVD(3) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1230, 0xff),	/* Telit LE910Cx (rmnet) */
+	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1231, 0xff),	/* Telit LE910Cx (RNDIS) */
+	  .driver_info = NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, 0x1260),
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, 0x1261),
diff --git a/drivers/usb/typec/ucsi/psy.c b/drivers/usb/typec/ucsi/psy.c
index 26ed0b5..571a51e 100644
--- a/drivers/usb/typec/ucsi/psy.c
+++ b/drivers/usb/typec/ucsi/psy.c
@@ -238,4 +238,13 @@
 		return;
 
 	power_supply_unregister(con->psy);
+	con->psy = NULL;
+}
+
+void ucsi_port_psy_changed(struct ucsi_connector *con)
+{
+	if (IS_ERR_OR_NULL(con->psy))
+		return;
+
+	power_supply_changed(con->psy);
 }
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 758b988..51a570d 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -643,8 +643,10 @@
 	role = !!(con->status.flags & UCSI_CONSTAT_PWR_DIR);
 
 	if (con->status.change & UCSI_CONSTAT_POWER_OPMODE_CHANGE ||
-	    con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE)
+	    con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE) {
 		ucsi_pwr_opmode_change(con);
+		ucsi_port_psy_changed(con);
+	}
 
 	if (con->status.change & UCSI_CONSTAT_POWER_DIR_CHANGE) {
 		typec_set_pwr_role(con->port, role);
@@ -674,6 +676,8 @@
 			ucsi_register_partner(con);
 		else
 			ucsi_unregister_partner(con);
+
+		ucsi_port_psy_changed(con);
 	}
 
 	if (con->status.change & UCSI_CONSTAT_CAM_CHANGE) {
@@ -994,6 +998,7 @@
 				  !!(con->status.flags & UCSI_CONSTAT_PWR_DIR));
 		ucsi_pwr_opmode_change(con);
 		ucsi_register_partner(con);
+		ucsi_port_psy_changed(con);
 	}
 
 	if (con->partner) {
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index cba6f77..b7a92f2 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -340,9 +340,11 @@
 #if IS_ENABLED(CONFIG_POWER_SUPPLY)
 int ucsi_register_port_psy(struct ucsi_connector *con);
 void ucsi_unregister_port_psy(struct ucsi_connector *con);
+void ucsi_port_psy_changed(struct ucsi_connector *con);
 #else
 static inline int ucsi_register_port_psy(struct ucsi_connector *con) { return 0; }
 static inline void ucsi_unregister_port_psy(struct ucsi_connector *con) { }
+static inline void ucsi_port_psy_changed(struct ucsi_connector *con) { }
 #endif /* CONFIG_POWER_SUPPLY */
 
 #if IS_ENABLED(CONFIG_TYPEC_DP_ALTMODE)
diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index d7d32b6..358f604 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -13,6 +13,7 @@
 	depends on RUNTIME_TESTING_MENU && HAS_DMA
 	select DMA_OPS
 	select VHOST_RING
+	select GENERIC_NET_UTILS
 	default n
 	help
 	  vDPA networking device simulator which loop TX traffic back
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
index 0113a98..f27e251 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
@@ -248,7 +248,9 @@
 		info.size = vdev->regions[info.index].size;
 		info.flags = vdev->regions[info.index].flags;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		if (copy_to_user((void __user *)arg, &info, minsz))
+			return -EFAULT;
+		return 0;
 	}
 	case VFIO_DEVICE_GET_IRQ_INFO:
 	{
@@ -267,7 +269,9 @@
 		info.flags = VFIO_IRQ_INFO_EVENTFD;
 		info.count = 1;
 
-		return copy_to_user((void __user *)arg, &info, minsz);
+		if (copy_to_user((void __user *)arg, &info, minsz))
+			return -EFAULT;
+		return 0;
 	}
 	case VFIO_DEVICE_SET_IRQS:
 	{
@@ -468,7 +472,7 @@
 {
 	struct vfio_fsl_mc_device *vdev = device_data;
 	struct fsl_mc_device *mc_dev = vdev->mc_dev;
-	int index;
+	unsigned int index;
 
 	index = vma->vm_pgoff >> (VFIO_FSL_MC_OFFSET_SHIFT - PAGE_SHIFT);
 
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
index c80dceb..0d9f300 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
@@ -13,7 +13,7 @@
 #include "linux/fsl/mc.h"
 #include "vfio_fsl_mc_private.h"
 
-int vfio_fsl_mc_irqs_allocate(struct vfio_fsl_mc_device *vdev)
+static int vfio_fsl_mc_irqs_allocate(struct vfio_fsl_mc_device *vdev)
 {
 	struct fsl_mc_device *mc_dev = vdev->mc_dev;
 	struct vfio_fsl_mc_irq *mc_irq;
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index fbd2b34..e619017 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -385,7 +385,7 @@
 	    pdev->vendor == PCI_VENDOR_ID_INTEL &&
 	    IS_ENABLED(CONFIG_VFIO_PCI_IGD)) {
 		ret = vfio_pci_igd_init(vdev);
-		if (ret) {
+		if (ret && ret != -ENODEV) {
 			pci_warn(pdev, "Failed to setup Intel IGD regions\n");
 			goto disable_exit;
 		}
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 9e353c4..a0b5fc8 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -356,34 +356,60 @@
 	return done;
 }
 
-static int vfio_pci_ioeventfd_handler(void *opaque, void *unused)
+static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
+					bool test_mem)
 {
-	struct vfio_pci_ioeventfd *ioeventfd = opaque;
-
 	switch (ioeventfd->count) {
 	case 1:
-		vfio_pci_iowrite8(ioeventfd->vdev, ioeventfd->test_mem,
+		vfio_pci_iowrite8(ioeventfd->vdev, test_mem,
 				  ioeventfd->data, ioeventfd->addr);
 		break;
 	case 2:
-		vfio_pci_iowrite16(ioeventfd->vdev, ioeventfd->test_mem,
+		vfio_pci_iowrite16(ioeventfd->vdev, test_mem,
 				   ioeventfd->data, ioeventfd->addr);
 		break;
 	case 4:
-		vfio_pci_iowrite32(ioeventfd->vdev, ioeventfd->test_mem,
+		vfio_pci_iowrite32(ioeventfd->vdev, test_mem,
 				   ioeventfd->data, ioeventfd->addr);
 		break;
 #ifdef iowrite64
 	case 8:
-		vfio_pci_iowrite64(ioeventfd->vdev, ioeventfd->test_mem,
+		vfio_pci_iowrite64(ioeventfd->vdev, test_mem,
 				   ioeventfd->data, ioeventfd->addr);
 		break;
 #endif
 	}
+}
+
+static int vfio_pci_ioeventfd_handler(void *opaque, void *unused)
+{
+	struct vfio_pci_ioeventfd *ioeventfd = opaque;
+	struct vfio_pci_device *vdev = ioeventfd->vdev;
+
+	if (ioeventfd->test_mem) {
+		if (!down_read_trylock(&vdev->memory_lock))
+			return 1; /* Lock contended, use thread */
+		if (!__vfio_pci_memory_enabled(vdev)) {
+			up_read(&vdev->memory_lock);
+			return 0;
+		}
+	}
+
+	vfio_pci_ioeventfd_do_write(ioeventfd, false);
+
+	if (ioeventfd->test_mem)
+		up_read(&vdev->memory_lock);
 
 	return 0;
 }
 
+static void vfio_pci_ioeventfd_thread(void *opaque, void *unused)
+{
+	struct vfio_pci_ioeventfd *ioeventfd = opaque;
+
+	vfio_pci_ioeventfd_do_write(ioeventfd, ioeventfd->test_mem);
+}
+
 long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset,
 			uint64_t data, int count, int fd)
 {
@@ -457,7 +483,8 @@
 	ioeventfd->test_mem = vdev->pdev->resource[bar].flags & IORESOURCE_MEM;
 
 	ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler,
-				 NULL, NULL, &ioeventfd->virqfd, fd);
+				 vfio_pci_ioeventfd_thread, NULL,
+				 &ioeventfd->virqfd, fd);
 	if (ret) {
 		kfree(ioeventfd);
 		goto out_unlock;
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index c0771a9..fb4b385 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -267,7 +267,7 @@
 
 		ret = pm_runtime_get_sync(vdev->device);
 		if (ret < 0)
-			goto err_pm;
+			goto err_rst;
 
 		ret = vfio_platform_call_reset(vdev, &extra_dbg);
 		if (ret && vdev->reset_required) {
@@ -284,7 +284,6 @@
 
 err_rst:
 	pm_runtime_put(vdev->device);
-err_pm:
 	vfio_platform_irq_cleanup(vdev);
 err_irq:
 	vfio_platform_regions_cleanup(vdev);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index bb2684c..67e8276 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1993,6 +1993,7 @@
 
 	list_splice_tail(iova_copy, iova);
 }
+
 static int vfio_iommu_type1_attach_group(void *iommu_data,
 					 struct iommu_group *iommu_group)
 {
@@ -2009,18 +2010,10 @@
 
 	mutex_lock(&iommu->lock);
 
-	list_for_each_entry(d, &iommu->domain_list, next) {
-		if (find_iommu_group(d, iommu_group)) {
-			mutex_unlock(&iommu->lock);
-			return -EINVAL;
-		}
-	}
-
-	if (iommu->external_domain) {
-		if (find_iommu_group(iommu->external_domain, iommu_group)) {
-			mutex_unlock(&iommu->lock);
-			return -EINVAL;
-		}
+	/* Check for duplicates */
+	if (vfio_iommu_find_iommu_group(iommu, iommu_group)) {
+		mutex_unlock(&iommu->lock);
+		return -EINVAL;
 	}
 
 	group = kzalloc(sizeof(*group), GFP_KERNEL);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index b22adf0..f22fce5 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -52,7 +52,6 @@
 #define VHOST_SCSI_VERSION  "v0.1"
 #define VHOST_SCSI_NAMELEN 256
 #define VHOST_SCSI_MAX_CDB_SIZE 32
-#define VHOST_SCSI_DEFAULT_TAGS 256
 #define VHOST_SCSI_PREALLOC_SGLS 2048
 #define VHOST_SCSI_PREALLOC_UPAGES 2048
 #define VHOST_SCSI_PREALLOC_PROT_SGLS 2048
@@ -140,6 +139,7 @@
 	struct se_portal_group se_tpg;
 	/* Pointer back to vhost_scsi, protected by tv_tpg_mutex */
 	struct vhost_scsi *vhost_scsi;
+	struct list_head tmf_queue;
 };
 
 struct vhost_scsi_tport {
@@ -189,6 +189,9 @@
 	 * Writers must also take dev mutex and flush under it.
 	 */
 	int inflight_idx;
+	struct vhost_scsi_cmd *scsi_cmds;
+	struct sbitmap scsi_tags;
+	int max_cmds;
 };
 
 struct vhost_scsi {
@@ -209,6 +212,20 @@
 	int vs_events_nr; /* num of pending events, protected by vq->mutex */
 };
 
+struct vhost_scsi_tmf {
+	struct vhost_work vwork;
+	struct vhost_scsi_tpg *tpg;
+	struct vhost_scsi *vhost;
+	struct vhost_scsi_virtqueue *svq;
+	struct list_head queue_entry;
+
+	struct se_cmd se_cmd;
+	struct vhost_scsi_inflight *inflight;
+	struct iovec resp_iov;
+	int in_iovs;
+	int vq_desc;
+};
+
 /*
  * Context for processing request and control queue operations.
  */
@@ -320,11 +337,13 @@
 	return 1;
 }
 
-static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
+static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd)
 {
 	struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd,
 				struct vhost_scsi_cmd, tvc_se_cmd);
-	struct se_session *se_sess = tv_cmd->tvc_nexus->tvn_se_sess;
+	struct vhost_scsi_virtqueue *svq = container_of(tv_cmd->tvc_vq,
+				struct vhost_scsi_virtqueue, vq);
+	struct vhost_scsi_inflight *inflight = tv_cmd->inflight;
 	int i;
 
 	if (tv_cmd->tvc_sgl_count) {
@@ -336,8 +355,36 @@
 			put_page(sg_page(&tv_cmd->tvc_prot_sgl[i]));
 	}
 
-	vhost_scsi_put_inflight(tv_cmd->inflight);
-	target_free_tag(se_sess, se_cmd);
+	sbitmap_clear_bit(&svq->scsi_tags, se_cmd->map_tag);
+	vhost_scsi_put_inflight(inflight);
+}
+
+static void vhost_scsi_release_tmf_res(struct vhost_scsi_tmf *tmf)
+{
+	struct vhost_scsi_tpg *tpg = tmf->tpg;
+	struct vhost_scsi_inflight *inflight = tmf->inflight;
+
+	mutex_lock(&tpg->tv_tpg_mutex);
+	list_add_tail(&tpg->tmf_queue, &tmf->queue_entry);
+	mutex_unlock(&tpg->tv_tpg_mutex);
+	vhost_scsi_put_inflight(inflight);
+}
+
+static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
+{
+	if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) {
+		struct vhost_scsi_tmf *tmf = container_of(se_cmd,
+					struct vhost_scsi_tmf, se_cmd);
+
+		vhost_work_queue(&tmf->vhost->dev, &tmf->vwork);
+	} else {
+		struct vhost_scsi_cmd *cmd = container_of(se_cmd,
+					struct vhost_scsi_cmd, tvc_se_cmd);
+		struct vhost_scsi *vs = cmd->tvc_vhost;
+
+		llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
+		vhost_work_queue(&vs->dev, &vs->vs_completion_work);
+	}
 }
 
 static u32 vhost_scsi_sess_get_index(struct se_session *se_sess)
@@ -362,34 +409,24 @@
 	return 0;
 }
 
-static void vhost_scsi_complete_cmd(struct vhost_scsi_cmd *cmd)
-{
-	struct vhost_scsi *vs = cmd->tvc_vhost;
-
-	llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
-
-	vhost_work_queue(&vs->dev, &vs->vs_completion_work);
-}
-
 static int vhost_scsi_queue_data_in(struct se_cmd *se_cmd)
 {
-	struct vhost_scsi_cmd *cmd = container_of(se_cmd,
-				struct vhost_scsi_cmd, tvc_se_cmd);
-	vhost_scsi_complete_cmd(cmd);
+	transport_generic_free_cmd(se_cmd, 0);
 	return 0;
 }
 
 static int vhost_scsi_queue_status(struct se_cmd *se_cmd)
 {
-	struct vhost_scsi_cmd *cmd = container_of(se_cmd,
-				struct vhost_scsi_cmd, tvc_se_cmd);
-	vhost_scsi_complete_cmd(cmd);
+	transport_generic_free_cmd(se_cmd, 0);
 	return 0;
 }
 
 static void vhost_scsi_queue_tm_rsp(struct se_cmd *se_cmd)
 {
-	return;
+	struct vhost_scsi_tmf *tmf = container_of(se_cmd, struct vhost_scsi_tmf,
+						  se_cmd);
+
+	transport_generic_free_cmd(&tmf->se_cmd, 0);
 }
 
 static void vhost_scsi_aborted_task(struct se_cmd *se_cmd)
@@ -429,15 +466,6 @@
 	return evt;
 }
 
-static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd)
-{
-	struct se_cmd *se_cmd = &cmd->tvc_se_cmd;
-
-	/* TODO locking against target/backend threads? */
-	transport_generic_free_cmd(se_cmd, 0);
-
-}
-
 static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd)
 {
 	return target_put_sess_cmd(se_cmd);
@@ -556,7 +584,7 @@
 		} else
 			pr_err("Faulted on virtio_scsi_cmd_resp\n");
 
-		vhost_scsi_free_cmd(cmd);
+		vhost_scsi_release_cmd_res(se_cmd);
 	}
 
 	vq = -1;
@@ -566,31 +594,31 @@
 }
 
 static struct vhost_scsi_cmd *
-vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
+vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
 		   unsigned char *cdb, u64 scsi_tag, u16 lun, u8 task_attr,
 		   u32 exp_data_len, int data_direction)
 {
+	struct vhost_scsi_virtqueue *svq = container_of(vq,
+					struct vhost_scsi_virtqueue, vq);
 	struct vhost_scsi_cmd *cmd;
 	struct vhost_scsi_nexus *tv_nexus;
-	struct se_session *se_sess;
 	struct scatterlist *sg, *prot_sg;
 	struct page **pages;
-	int tag, cpu;
+	int tag;
 
 	tv_nexus = tpg->tpg_nexus;
 	if (!tv_nexus) {
 		pr_err("Unable to locate active struct vhost_scsi_nexus\n");
 		return ERR_PTR(-EIO);
 	}
-	se_sess = tv_nexus->tvn_se_sess;
 
-	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
+	tag = sbitmap_get(&svq->scsi_tags, 0, false);
 	if (tag < 0) {
 		pr_err("Unable to obtain tag for vhost_scsi_cmd\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
-	cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[tag];
+	cmd = &svq->scsi_cmds[tag];
 	sg = cmd->tvc_sgl;
 	prot_sg = cmd->tvc_prot_sgl;
 	pages = cmd->tvc_upages;
@@ -599,7 +627,6 @@
 	cmd->tvc_prot_sgl = prot_sg;
 	cmd->tvc_upages = pages;
 	cmd->tvc_se_cmd.map_tag = tag;
-	cmd->tvc_se_cmd.map_cpu = cpu;
 	cmd->tvc_tag = scsi_tag;
 	cmd->tvc_lun = lun;
 	cmd->tvc_task_attr = task_attr;
@@ -907,6 +934,11 @@
 	return ret;
 }
 
+static u16 vhost_buf_to_lun(u8 *lun_buf)
+{
+	return ((lun_buf[2] << 8) | lun_buf[3]) & 0x3FFF;
+}
+
 static void
 vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 {
@@ -1045,12 +1077,12 @@
 			tag = vhost64_to_cpu(vq, v_req_pi.tag);
 			task_attr = v_req_pi.task_attr;
 			cdb = &v_req_pi.cdb[0];
-			lun = ((v_req_pi.lun[2] << 8) | v_req_pi.lun[3]) & 0x3FFF;
+			lun = vhost_buf_to_lun(v_req_pi.lun);
 		} else {
 			tag = vhost64_to_cpu(vq, v_req.tag);
 			task_attr = v_req.task_attr;
 			cdb = &v_req.cdb[0];
-			lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF;
+			lun = vhost_buf_to_lun(v_req.lun);
 		}
 		/*
 		 * Check that the received CDB size does not exceeded our
@@ -1065,11 +1097,11 @@
 				scsi_command_size(cdb), VHOST_SCSI_MAX_CDB_SIZE);
 				goto err;
 		}
-		cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr,
+		cmd = vhost_scsi_get_cmd(vq, tpg, cdb, tag, lun, task_attr,
 					 exp_data_len + prot_bytes,
 					 data_direction);
 		if (IS_ERR(cmd)) {
-			vq_err(vq, "vhost_scsi_get_tag failed %ld\n",
+			vq_err(vq, "vhost_scsi_get_cmd failed %ld\n",
 			       PTR_ERR(cmd));
 			goto err;
 		}
@@ -1088,7 +1120,7 @@
 						      &prot_iter, exp_data_len,
 						      &data_iter))) {
 				vq_err(vq, "Failed to map iov to sgl\n");
-				vhost_scsi_release_cmd(&cmd->tvc_se_cmd);
+				vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd);
 				goto err;
 			}
 		}
@@ -1124,9 +1156,9 @@
 }
 
 static void
-vhost_scsi_send_tmf_reject(struct vhost_scsi *vs,
-			   struct vhost_virtqueue *vq,
-			   struct vhost_scsi_ctx *vc)
+vhost_scsi_send_tmf_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
+			 int in_iovs, int vq_desc, struct iovec *resp_iov,
+			 int tmf_resp_code)
 {
 	struct virtio_scsi_ctrl_tmf_resp rsp;
 	struct iov_iter iov_iter;
@@ -1134,17 +1166,87 @@
 
 	pr_debug("%s\n", __func__);
 	memset(&rsp, 0, sizeof(rsp));
-	rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED;
+	rsp.response = tmf_resp_code;
 
-	iov_iter_init(&iov_iter, READ, &vq->iov[vc->out], vc->in, sizeof(rsp));
+	iov_iter_init(&iov_iter, READ, resp_iov, in_iovs, sizeof(rsp));
 
 	ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
 	if (likely(ret == sizeof(rsp)))
-		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
+		vhost_add_used_and_signal(&vs->dev, vq, vq_desc, 0);
 	else
 		pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n");
 }
 
+static void vhost_scsi_tmf_resp_work(struct vhost_work *work)
+{
+	struct vhost_scsi_tmf *tmf = container_of(work, struct vhost_scsi_tmf,
+						  vwork);
+	int resp_code;
+
+	if (tmf->se_cmd.se_tmr_req->response == TMR_FUNCTION_COMPLETE)
+		resp_code = VIRTIO_SCSI_S_FUNCTION_SUCCEEDED;
+	else
+		resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED;
+
+	vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs,
+				 tmf->vq_desc, &tmf->resp_iov, resp_code);
+	vhost_scsi_release_tmf_res(tmf);
+}
+
+static void
+vhost_scsi_handle_tmf(struct vhost_scsi *vs, struct vhost_scsi_tpg *tpg,
+		      struct vhost_virtqueue *vq,
+		      struct virtio_scsi_ctrl_tmf_req *vtmf,
+		      struct vhost_scsi_ctx *vc)
+{
+	struct vhost_scsi_virtqueue *svq = container_of(vq,
+					struct vhost_scsi_virtqueue, vq);
+	struct vhost_scsi_tmf *tmf;
+
+	if (vhost32_to_cpu(vq, vtmf->subtype) !=
+	    VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET)
+		goto send_reject;
+
+	if (!tpg->tpg_nexus || !tpg->tpg_nexus->tvn_se_sess) {
+		pr_err("Unable to locate active struct vhost_scsi_nexus for LUN RESET.\n");
+		goto send_reject;
+	}
+
+	mutex_lock(&tpg->tv_tpg_mutex);
+	if (list_empty(&tpg->tmf_queue)) {
+		pr_err("Missing reserve TMF. Could not handle LUN RESET.\n");
+		mutex_unlock(&tpg->tv_tpg_mutex);
+		goto send_reject;
+	}
+
+	tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf,
+			       queue_entry);
+	list_del_init(&tmf->queue_entry);
+	mutex_unlock(&tpg->tv_tpg_mutex);
+
+	tmf->tpg = tpg;
+	tmf->vhost = vs;
+	tmf->svq = svq;
+	tmf->resp_iov = vq->iov[vc->out];
+	tmf->vq_desc = vc->head;
+	tmf->in_iovs = vc->in;
+	tmf->inflight = vhost_scsi_get_inflight(vq);
+
+	if (target_submit_tmr(&tmf->se_cmd, tpg->tpg_nexus->tvn_se_sess, NULL,
+			      vhost_buf_to_lun(vtmf->lun), NULL,
+			      TMR_LUN_RESET, GFP_KERNEL, 0,
+			      TARGET_SCF_ACK_KREF) < 0) {
+		vhost_scsi_release_tmf_res(tmf);
+		goto send_reject;
+	}
+
+	return;
+
+send_reject:
+	vhost_scsi_send_tmf_resp(vs, vq, vc->in, vc->head, &vq->iov[vc->out],
+				 VIRTIO_SCSI_S_FUNCTION_REJECTED);
+}
+
 static void
 vhost_scsi_send_an_resp(struct vhost_scsi *vs,
 			struct vhost_virtqueue *vq,
@@ -1170,6 +1272,7 @@
 static void
 vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 {
+	struct vhost_scsi_tpg *tpg;
 	union {
 		__virtio32 type;
 		struct virtio_scsi_ctrl_an_req an;
@@ -1251,12 +1354,12 @@
 		vc.req += typ_size;
 		vc.req_size -= typ_size;
 
-		ret = vhost_scsi_get_req(vq, &vc, NULL);
+		ret = vhost_scsi_get_req(vq, &vc, &tpg);
 		if (ret)
 			goto err;
 
 		if (v_req.type == VIRTIO_SCSI_T_TMF)
-			vhost_scsi_send_tmf_reject(vs, vq, &vc);
+			vhost_scsi_handle_tmf(vs, tpg, vq, &v_req.tmf, &vc);
 		else
 			vhost_scsi_send_an_resp(vs, vq, &vc);
 err:
@@ -1373,6 +1476,83 @@
 		wait_for_completion(&old_inflight[i]->comp);
 }
 
+static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq)
+{
+	struct vhost_scsi_virtqueue *svq = container_of(vq,
+					struct vhost_scsi_virtqueue, vq);
+	struct vhost_scsi_cmd *tv_cmd;
+	unsigned int i;
+
+	if (!svq->scsi_cmds)
+		return;
+
+	for (i = 0; i < svq->max_cmds; i++) {
+		tv_cmd = &svq->scsi_cmds[i];
+
+		kfree(tv_cmd->tvc_sgl);
+		kfree(tv_cmd->tvc_prot_sgl);
+		kfree(tv_cmd->tvc_upages);
+	}
+
+	sbitmap_free(&svq->scsi_tags);
+	kfree(svq->scsi_cmds);
+	svq->scsi_cmds = NULL;
+}
+
+static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds)
+{
+	struct vhost_scsi_virtqueue *svq = container_of(vq,
+					struct vhost_scsi_virtqueue, vq);
+	struct vhost_scsi_cmd *tv_cmd;
+	unsigned int i;
+
+	if (svq->scsi_cmds)
+		return 0;
+
+	if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL,
+			      NUMA_NO_NODE))
+		return -ENOMEM;
+	svq->max_cmds = max_cmds;
+
+	svq->scsi_cmds = kcalloc(max_cmds, sizeof(*tv_cmd), GFP_KERNEL);
+	if (!svq->scsi_cmds) {
+		sbitmap_free(&svq->scsi_tags);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < max_cmds; i++) {
+		tv_cmd = &svq->scsi_cmds[i];
+
+		tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS,
+					  sizeof(struct scatterlist),
+					  GFP_KERNEL);
+		if (!tv_cmd->tvc_sgl) {
+			pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
+			goto out;
+		}
+
+		tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES,
+					     sizeof(struct page *),
+					     GFP_KERNEL);
+		if (!tv_cmd->tvc_upages) {
+			pr_err("Unable to allocate tv_cmd->tvc_upages\n");
+			goto out;
+		}
+
+		tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS,
+					       sizeof(struct scatterlist),
+					       GFP_KERNEL);
+		if (!tv_cmd->tvc_prot_sgl) {
+			pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n");
+			goto out;
+		}
+	}
+	return 0;
+out:
+	vhost_scsi_destroy_vq_cmds(vq);
+	return -ENOMEM;
+}
+
 /*
  * Called from vhost_scsi_ioctl() context to walk the list of available
  * vhost_scsi_tpg with an active struct vhost_scsi_nexus
@@ -1427,10 +1607,9 @@
 
 		if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) {
 			if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) {
-				kfree(vs_tpg);
 				mutex_unlock(&tpg->tv_tpg_mutex);
 				ret = -EEXIST;
-				goto out;
+				goto undepend;
 			}
 			/*
 			 * In order to ensure individual vhost-scsi configfs
@@ -1442,9 +1621,8 @@
 			ret = target_depend_item(&se_tpg->tpg_group.cg_item);
 			if (ret) {
 				pr_warn("target_depend_item() failed: %d\n", ret);
-				kfree(vs_tpg);
 				mutex_unlock(&tpg->tv_tpg_mutex);
-				goto out;
+				goto undepend;
 			}
 			tpg->tv_tpg_vhost_count++;
 			tpg->vhost_scsi = vs;
@@ -1457,6 +1635,16 @@
 	if (match) {
 		memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn,
 		       sizeof(vs->vs_vhost_wwpn));
+
+		for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) {
+			vq = &vs->vqs[i].vq;
+			if (!vhost_vq_is_setup(vq))
+				continue;
+
+			if (vhost_scsi_setup_vq_cmds(vq, vq->num))
+				goto destroy_vq_cmds;
+		}
+
 		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
 			vq = &vs->vqs[i].vq;
 			mutex_lock(&vq->mutex);
@@ -1476,7 +1664,22 @@
 	vhost_scsi_flush(vs);
 	kfree(vs->vs_tpg);
 	vs->vs_tpg = vs_tpg;
+	goto out;
 
+destroy_vq_cmds:
+	for (i--; i >= VHOST_SCSI_VQ_IO; i--) {
+		if (!vhost_vq_get_backend(&vs->vqs[i].vq))
+			vhost_scsi_destroy_vq_cmds(&vs->vqs[i].vq);
+	}
+undepend:
+	for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) {
+		tpg = vs_tpg[i];
+		if (tpg) {
+			tpg->tv_tpg_vhost_count--;
+			target_undepend_item(&tpg->se_tpg.tpg_group.cg_item);
+		}
+	}
+	kfree(vs_tpg);
 out:
 	mutex_unlock(&vs->dev.mutex);
 	mutex_unlock(&vhost_scsi_mutex);
@@ -1549,6 +1752,12 @@
 			mutex_lock(&vq->mutex);
 			vhost_vq_set_backend(vq, NULL);
 			mutex_unlock(&vq->mutex);
+			/*
+			 * Make sure cmds are not running before tearing them
+			 * down.
+			 */
+			vhost_scsi_flush(vs);
+			vhost_scsi_destroy_vq_cmds(vq);
 		}
 	}
 	/*
@@ -1811,11 +2020,19 @@
 {
 	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
 				struct vhost_scsi_tpg, se_tpg);
+	struct vhost_scsi_tmf *tmf;
+
+	tmf = kzalloc(sizeof(*tmf), GFP_KERNEL);
+	if (!tmf)
+		return -ENOMEM;
+	INIT_LIST_HEAD(&tmf->queue_entry);
+	vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work);
 
 	mutex_lock(&vhost_scsi_mutex);
 
 	mutex_lock(&tpg->tv_tpg_mutex);
 	tpg->tv_tpg_port_count++;
+	list_add_tail(&tmf->queue_entry, &tpg->tmf_queue);
 	mutex_unlock(&tpg->tv_tpg_mutex);
 
 	vhost_scsi_hotplug(tpg, lun);
@@ -1830,11 +2047,16 @@
 {
 	struct vhost_scsi_tpg *tpg = container_of(se_tpg,
 				struct vhost_scsi_tpg, se_tpg);
+	struct vhost_scsi_tmf *tmf;
 
 	mutex_lock(&vhost_scsi_mutex);
 
 	mutex_lock(&tpg->tv_tpg_mutex);
 	tpg->tv_tpg_port_count--;
+	tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf,
+			       queue_entry);
+	list_del(&tmf->queue_entry);
+	kfree(tmf);
 	mutex_unlock(&tpg->tv_tpg_mutex);
 
 	vhost_scsi_hotunplug(tpg, lun);
@@ -1842,23 +2064,6 @@
 	mutex_unlock(&vhost_scsi_mutex);
 }
 
-static void vhost_scsi_free_cmd_map_res(struct se_session *se_sess)
-{
-	struct vhost_scsi_cmd *tv_cmd;
-	unsigned int i;
-
-	if (!se_sess->sess_cmd_map)
-		return;
-
-	for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) {
-		tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i];
-
-		kfree(tv_cmd->tvc_sgl);
-		kfree(tv_cmd->tvc_prot_sgl);
-		kfree(tv_cmd->tvc_upages);
-	}
-}
-
 static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store(
 		struct config_item *item, const char *page, size_t count)
 {
@@ -1898,45 +2103,6 @@
 	NULL,
 };
 
-static int vhost_scsi_nexus_cb(struct se_portal_group *se_tpg,
-			       struct se_session *se_sess, void *p)
-{
-	struct vhost_scsi_cmd *tv_cmd;
-	unsigned int i;
-
-	for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) {
-		tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i];
-
-		tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS,
-					  sizeof(struct scatterlist),
-					  GFP_KERNEL);
-		if (!tv_cmd->tvc_sgl) {
-			pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
-			goto out;
-		}
-
-		tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES,
-					     sizeof(struct page *),
-					     GFP_KERNEL);
-		if (!tv_cmd->tvc_upages) {
-			pr_err("Unable to allocate tv_cmd->tvc_upages\n");
-			goto out;
-		}
-
-		tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS,
-					       sizeof(struct scatterlist),
-					       GFP_KERNEL);
-		if (!tv_cmd->tvc_prot_sgl) {
-			pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n");
-			goto out;
-		}
-	}
-	return 0;
-out:
-	vhost_scsi_free_cmd_map_res(se_sess);
-	return -ENOMEM;
-}
-
 static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg,
 				const char *name)
 {
@@ -1960,12 +2126,9 @@
 	 * struct se_node_acl for the vhost_scsi struct se_portal_group with
 	 * the SCSI Initiator port name of the passed configfs group 'name'.
 	 */
-	tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg,
-					VHOST_SCSI_DEFAULT_TAGS,
-					sizeof(struct vhost_scsi_cmd),
+	tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, 0, 0,
 					TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS,
-					(unsigned char *)name, tv_nexus,
-					vhost_scsi_nexus_cb);
+					(unsigned char *)name, tv_nexus, NULL);
 	if (IS_ERR(tv_nexus->tvn_se_sess)) {
 		mutex_unlock(&tpg->tv_tpg_mutex);
 		kfree(tv_nexus);
@@ -2015,7 +2178,6 @@
 		" %s Initiator Port: %s\n", vhost_scsi_dump_proto_id(tpg->tport),
 		tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
 
-	vhost_scsi_free_cmd_map_res(se_sess);
 	/*
 	 * Release the SCSI I_T Nexus to the emulated vhost Target Port
 	 */
@@ -2155,6 +2317,7 @@
 	}
 	mutex_init(&tpg->tv_tpg_mutex);
 	INIT_LIST_HEAD(&tpg->tv_tpg_list);
+	INIT_LIST_HEAD(&tpg->tmf_queue);
 	tpg->tport = tport;
 	tpg->tport_tpgt = tpgt;
 
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 5c835a2..a262e12 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -304,6 +304,12 @@
 	memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer));
 }
 
+bool vhost_vq_is_setup(struct vhost_virtqueue *vq)
+{
+	return vq->avail && vq->desc && vq->used && vhost_vq_access_ok(vq);
+}
+EXPORT_SYMBOL_GPL(vhost_vq_is_setup);
+
 static void vhost_vq_reset(struct vhost_dev *dev,
 			   struct vhost_virtqueue *vq)
 {
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index e016cd3..b063324 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -190,6 +190,7 @@
 		      struct vhost_log *log, unsigned int *log_num);
 void vhost_discard_vq_desc(struct vhost_virtqueue *, int n);
 
+bool vhost_vq_is_setup(struct vhost_virtqueue *vq);
 int vhost_vq_init_access(struct vhost_virtqueue *);
 int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
 int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads,
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index e36fb1a..5bc86f4 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -47,6 +47,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/vmalloc.h>
 #include <linux/init.h>
 #include <linux/completion.h>
 #include <linux/fb.h>
diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev.c b/drivers/virt/nitro_enclaves/ne_misc_dev.c
index f06622b..f1964ea 100644
--- a/drivers/virt/nitro_enclaves/ne_misc_dev.c
+++ b/drivers/virt/nitro_enclaves/ne_misc_dev.c
@@ -1505,10 +1505,8 @@
 
 	poll_wait(file, &ne_enclave->eventq, wait);
 
-	if (!ne_enclave->has_event)
-		return mask;
-
-	mask = POLLHUP;
+	if (ne_enclave->has_event)
+		mask |= EPOLLHUP;
 
 	return mask;
 }
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 71ce1b7..2b385c1 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -395,8 +395,7 @@
 	 */
 	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
 
-	map = swiotlb_tbl_map_single(dev, virt_to_phys(xen_io_tlb_start),
-				     phys, size, size, dir, attrs);
+	map = swiotlb_tbl_map_single(dev, phys, size, size, dir, attrs);
 	if (map == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 5037120..c9195fc 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -169,11 +169,14 @@
 	unsigned int f, from = pos & (PAGE_SIZE - 1);
 	unsigned int t, to = from + copied;
 	loff_t i_size, maybe_i_size;
-	int ret;
+	int ret = 0;
 
 	_enter("{%llx:%llu},{%lx}",
 	       vnode->fid.vid, vnode->fid.vnode, page->index);
 
+	if (copied == 0)
+		goto out;
+
 	maybe_i_size = pos + copied;
 
 	i_size = i_size_read(&vnode->vfs_inode);
diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c
index 38884d6..95c573d 100644
--- a/fs/afs/xattr.c
+++ b/fs/afs/xattr.c
@@ -148,11 +148,6 @@
 	.set    = afs_xattr_set_acl,
 };
 
-static void yfs_acl_put(struct afs_operation *op)
-{
-	yfs_free_opaque_acl(op->yacl);
-}
-
 static const struct afs_operation_ops yfs_fetch_opaque_acl_operation = {
 	.issue_yfs_rpc	= yfs_fs_fetch_opaque_acl,
 	.success	= afs_acl_success,
@@ -246,7 +241,7 @@
 static const struct afs_operation_ops yfs_store_opaque_acl2_operation = {
 	.issue_yfs_rpc	= yfs_fs_store_opaque_acl2,
 	.success	= afs_acl_success,
-	.put		= yfs_acl_put,
+	.put		= afs_acl_put,
 };
 
 /*
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 3b1239b..bd787e7 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -1990,6 +1990,7 @@
 	memcpy(bp, acl->data, acl->size);
 	if (acl->size != size)
 		memset((void *)bp + acl->size, 0, size - acl->size);
+	bp += size / sizeof(__be32);
 	yfs_check_req(call, bp);
 
 	trace_afs_make_fs_call(call, &vp->fid);
diff --git a/fs/aio.c b/fs/aio.c
index c45c20d..6a21d89 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1572,7 +1572,7 @@
 		 * we return to userspace.
 		 */
 		if (S_ISREG(file_inode(file)->i_mode)) {
-			__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
+			sb_start_write(file_inode(file)->i_sb);
 			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 		}
 		req->ki_flags |= IOCB_WRITE;
diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c
index 7e1549a..bc920af 100644
--- a/fs/btrfs/block-rsv.c
+++ b/fs/btrfs/block-rsv.c
@@ -511,7 +511,8 @@
 				/*DEFAULT_RATELIMIT_BURST*/ 1);
 		if (__ratelimit(&_rs))
 			WARN(1, KERN_DEBUG
-				"BTRFS: block rsv returned %d\n", ret);
+				"BTRFS: block rsv %d returned %d\n",
+				block_rsv->type, ret);
 	}
 try_reserve:
 	ret = btrfs_reserve_metadata_bytes(root, block_rsv, blocksize,
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 5b9e3f3..1063853 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -91,6 +91,17 @@
 	ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
 	if (ret) {
 no_valid_dev_replace_entry_found:
+		/*
+		 * We don't have a replace item or it's corrupted.  If there is
+		 * a replace target, fail the mount.
+		 */
+		if (btrfs_find_device(fs_info->fs_devices,
+				      BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) {
+			btrfs_err(fs_info,
+			"found replace target device without a valid replace item");
+			ret = -EUCLEAN;
+			goto out;
+		}
 		ret = 0;
 		dev_replace->replace_state =
 			BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED;
@@ -143,8 +154,19 @@
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
-		dev_replace->srcdev = NULL;
-		dev_replace->tgtdev = NULL;
+		/*
+		 * We don't have an active replace item but if there is a
+		 * replace target, fail the mount.
+		 */
+		if (btrfs_find_device(fs_info->fs_devices,
+				      BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) {
+			btrfs_err(fs_info,
+			"replace devid present without an active replace item");
+			ret = -EUCLEAN;
+		} else {
+			dev_replace->srcdev = NULL;
+			dev_replace->tgtdev = NULL;
+		}
 		break;
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index ab408a2..69a3841 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1274,6 +1274,7 @@
 	u64 page_start;
 	u64 page_end;
 	u64 page_cnt;
+	u64 start = (u64)start_index << PAGE_SHIFT;
 	int ret;
 	int i;
 	int i_done;
@@ -1290,8 +1291,7 @@
 	page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
 
 	ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved,
-			start_index << PAGE_SHIFT,
-			page_cnt << PAGE_SHIFT);
+			start, page_cnt << PAGE_SHIFT);
 	if (ret)
 		return ret;
 	i_done = 0;
@@ -1380,8 +1380,7 @@
 		btrfs_mod_outstanding_extents(BTRFS_I(inode), 1);
 		spin_unlock(&BTRFS_I(inode)->lock);
 		btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved,
-				start_index << PAGE_SHIFT,
-				(page_cnt - i_done) << PAGE_SHIFT, true);
+				start, (page_cnt - i_done) << PAGE_SHIFT, true);
 	}
 
 
@@ -1408,8 +1407,7 @@
 		put_page(pages[i]);
 	}
 	btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved,
-			start_index << PAGE_SHIFT,
-			page_cnt << PAGE_SHIFT, true);
+			start, page_cnt << PAGE_SHIFT, true);
 	btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
 	extent_changeset_free(data_reserved);
 	return ret;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index c54ea65..77c5474 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -3435,24 +3435,20 @@
 {
 	struct rb_node *node;
 	struct rb_node *next;
-	struct ulist_node *entry = NULL;
+	struct ulist_node *entry;
 	int ret = 0;
 
 	node = reserved->range_changed.root.rb_node;
+	if (!node)
+		return 0;
 	while (node) {
 		entry = rb_entry(node, struct ulist_node, rb_node);
 		if (entry->val < start)
 			node = node->rb_right;
-		else if (entry)
-			node = node->rb_left;
 		else
-			break;
+			node = node->rb_left;
 	}
 
-	/* Empty changeset */
-	if (!entry)
-		return 0;
-
 	if (entry->val > start && rb_prev(&entry->rb_node))
 		entry = rb_entry(rb_prev(&entry->rb_node), struct ulist_node,
 				 rb_node);
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 7f03dbe..78693d3 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -860,6 +860,7 @@
 "dropping a ref for a root that doesn't have a ref on the block");
 			dump_block_entry(fs_info, be);
 			dump_ref_action(fs_info, ra);
+			kfree(ref);
 			kfree(ra);
 			goto out_unlock;
 		}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 3602806..9ba92d8 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1648,6 +1648,7 @@
 	struct btrfs_root_item *root_item;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
+	int reserve_level;
 	int level;
 	int max_level;
 	int replaced = 0;
@@ -1696,7 +1697,8 @@
 	 * Thus the needed metadata size is at most root_level * nodesize,
 	 * and * 2 since we have two trees to COW.
 	 */
-	min_reserved = fs_info->nodesize * btrfs_root_level(root_item) * 2;
+	reserve_level = max_t(int, 1, btrfs_root_level(root_item));
+	min_reserved = fs_info->nodesize * reserve_level * 2;
 	memset(&next_key, 0, sizeof(next_key));
 
 	while (1) {
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index cf63f1e..e71e758 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3866,8 +3866,9 @@
 	if (!is_dev_replace && !readonly &&
 	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable",
-				rcu_str_deref(dev->name));
+		btrfs_err_in_rcu(fs_info,
+			"scrub on devid %llu: filesystem on %s is not writable",
+				 devid, rcu_str_deref(dev->name));
 		ret = -EROFS;
 		goto out;
 	}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b1e4807..a6406b3 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1056,22 +1056,13 @@
 			continue;
 		}
 
-		if (device->devid == BTRFS_DEV_REPLACE_DEVID) {
-			/*
-			 * In the first step, keep the device which has
-			 * the correct fsid and the devid that is used
-			 * for the dev_replace procedure.
-			 * In the second step, the dev_replace state is
-			 * read from the device tree and it is known
-			 * whether the procedure is really active or
-			 * not, which means whether this device is
-			 * used or whether it should be removed.
-			 */
-			if (step == 0 || test_bit(BTRFS_DEV_STATE_REPLACE_TGT,
-						  &device->dev_state)) {
-				continue;
-			}
-		}
+		/*
+		 * We have already validated the presence of BTRFS_DEV_REPLACE_DEVID,
+		 * in btrfs_init_dev_replace() so just continue.
+		 */
+		if (device->devid == BTRFS_DEV_REPLACE_DEVID)
+			continue;
+
 		if (device->bdev) {
 			blkdev_put(device->bdev, device->mode);
 			device->bdev = NULL;
@@ -1080,9 +1071,6 @@
 		if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
 			list_del_init(&device->dev_alloc_list);
 			clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
-			if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT,
-				      &device->dev_state))
-				fs_devices->rw_devices--;
 		}
 		list_del_init(&device->dev_list);
 		fs_devices->num_devices--;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 5027bbd..ded4229 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -4074,7 +4074,7 @@
 	     vino.snap, inode);
 
 	mutex_lock(&session->s_mutex);
-	session->s_seq++;
+	inc_session_sequence(session);
 	dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
 	     (unsigned)seq);
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 08f1c0c..8f1d750 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4231,7 +4231,7 @@
 	     dname.len, dname.name);
 
 	mutex_lock(&session->s_mutex);
-	session->s_seq++;
+	inc_session_sequence(session);
 
 	if (!inode) {
 		dout("handle_lease no inode %llx\n", vino.ino);
@@ -4385,29 +4385,49 @@
 
 bool check_session_state(struct ceph_mds_session *s)
 {
-	if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
-		dout("resending session close request for mds%d\n",
-				s->s_mds);
-		request_close_session(s);
-		return false;
-	}
-	if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
-		if (s->s_state == CEPH_MDS_SESSION_OPEN) {
+	switch (s->s_state) {
+	case CEPH_MDS_SESSION_OPEN:
+		if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
 			s->s_state = CEPH_MDS_SESSION_HUNG;
 			pr_info("mds%d hung\n", s->s_mds);
 		}
-	}
-	if (s->s_state == CEPH_MDS_SESSION_NEW ||
-	    s->s_state == CEPH_MDS_SESSION_RESTARTING ||
-	    s->s_state == CEPH_MDS_SESSION_CLOSED ||
-	    s->s_state == CEPH_MDS_SESSION_REJECTED)
-		/* this mds is failed or recovering, just wait */
+		break;
+	case CEPH_MDS_SESSION_CLOSING:
+		/* Should never reach this when we're unmounting */
+		WARN_ON_ONCE(true);
+		fallthrough;
+	case CEPH_MDS_SESSION_NEW:
+	case CEPH_MDS_SESSION_RESTARTING:
+	case CEPH_MDS_SESSION_CLOSED:
+	case CEPH_MDS_SESSION_REJECTED:
 		return false;
+	}
 
 	return true;
 }
 
 /*
+ * If the sequence is incremented while we're waiting on a REQUEST_CLOSE reply,
+ * then we need to retransmit that request.
+ */
+void inc_session_sequence(struct ceph_mds_session *s)
+{
+	lockdep_assert_held(&s->s_mutex);
+
+	s->s_seq++;
+
+	if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
+		int ret;
+
+		dout("resending session close request for mds%d\n", s->s_mds);
+		ret = request_close_session(s);
+		if (ret < 0)
+			pr_err("unable to close session to mds%d: %d\n",
+			       s->s_mds, ret);
+	}
+}
+
+/*
  * delayed work -- periodically trim expired leases, renew caps with mds
  */
 static void schedule_delayed(struct ceph_mds_client *mdsc)
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index cbf8af4..f5adbeb 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -480,6 +480,7 @@
 extern const char *ceph_mds_op_name(int op);
 
 extern bool check_session_state(struct ceph_mds_session *s);
+void inc_session_sequence(struct ceph_mds_session *s);
 
 extern struct ceph_mds_session *
 __ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 83cb4f2..9b785f11 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -53,7 +53,7 @@
 
 	/* increment msg sequence number */
 	mutex_lock(&session->s_mutex);
-	session->s_seq++;
+	inc_session_sequence(session);
 	mutex_unlock(&session->s_mutex);
 
 	/* lookup inode */
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 0da39c1..b611f82 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -873,7 +873,7 @@
 	     ceph_snap_op_name(op), split, trace_len);
 
 	mutex_lock(&session->s_mutex);
-	session->s_seq++;
+	inc_session_sequence(session);
 	mutex_unlock(&session->s_mutex);
 
 	down_write(&mdsc->snap_rwsem);
diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c
index 89bffa8..c57bebf 100644
--- a/fs/crypto/inline_crypt.c
+++ b/fs/crypto/inline_crypt.c
@@ -74,7 +74,7 @@
 	int i;
 
 	/* The file must need contents encryption, not filenames encryption */
-	if (!fscrypt_needs_contents_encryption(inode))
+	if (!S_ISREG(inode->i_mode))
 		return 0;
 
 	/* The crypto mode must have a blk-crypto counterpart */
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index d3c3e5d..d595abb 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -269,9 +269,7 @@
 	 * New inodes may not have an inode number assigned yet.
 	 * Hashing their inode number is delayed until later.
 	 */
-	if (ci->ci_inode->i_ino == 0)
-		WARN_ON(!(ci->ci_inode->i_state & I_CREATING));
-	else
+	if (ci->ci_inode->i_ino)
 		fscrypt_hash_inode_number(ci, mk);
 	return 0;
 }
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 139d0be..3e21c0e 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -107,11 +107,9 @@
 		i_gid_write(inode, le32_to_cpu(die->i_gid));
 		set_nlink(inode, le32_to_cpu(die->i_nlink));
 
-		/* ns timestamp */
-		inode->i_mtime.tv_sec = inode->i_ctime.tv_sec =
-			le64_to_cpu(die->i_ctime);
-		inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec =
-			le32_to_cpu(die->i_ctime_nsec);
+		/* extended inode has its own timestamp */
+		inode->i_ctime.tv_sec = le64_to_cpu(die->i_ctime);
+		inode->i_ctime.tv_nsec = le32_to_cpu(die->i_ctime_nsec);
 
 		inode->i_size = le64_to_cpu(die->i_size);
 
@@ -149,11 +147,9 @@
 		i_gid_write(inode, le16_to_cpu(dic->i_gid));
 		set_nlink(inode, le16_to_cpu(dic->i_nlink));
 
-		/* use build time to derive all file time */
-		inode->i_mtime.tv_sec = inode->i_ctime.tv_sec =
-			sbi->build_time;
-		inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec =
-			sbi->build_time_nsec;
+		/* use build time for compact inodes */
+		inode->i_ctime.tv_sec = sbi->build_time;
+		inode->i_ctime.tv_nsec = sbi->build_time_nsec;
 
 		inode->i_size = le32_to_cpu(dic->i_size);
 		if (erofs_inode_is_data_compressed(vi->datalayout))
@@ -167,6 +163,11 @@
 		goto err_out;
 	}
 
+	inode->i_mtime.tv_sec = inode->i_ctime.tv_sec;
+	inode->i_atime.tv_sec = inode->i_ctime.tv_sec;
+	inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec;
+	inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec;
+
 	if (!nblks)
 		/* measure inode.i_blocks as generic filesystems */
 		inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9;
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 50912a5..86fd3bf 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1078,8 +1078,11 @@
 		cond_resched();
 		goto repeat;
 	}
-	set_page_private(page, (unsigned long)pcl);
-	SetPagePrivate(page);
+
+	if (tocache) {
+		set_page_private(page, (unsigned long)pcl);
+		SetPagePrivate(page);
+	}
 out:	/* the only exit (for tracing and debugging) */
 	return page;
 }
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 45fcdbf..bf94294 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1028,9 +1028,6 @@
 					 * protected by sbi->s_fc_lock.
 					 */
 
-	/* Fast commit subtid when this inode was committed */
-	unsigned int i_fc_committed_subtid;
-
 	/* Start of lblk range that needs to be committed in this fast commit */
 	ext4_lblk_t i_fc_lblk_start;
 
@@ -1234,13 +1231,13 @@
 						      blocks */
 #define EXT4_MOUNT2_HURD_COMPAT		0x00000004 /* Support HURD-castrated
 						      file systems */
-#define EXT4_MOUNT2_DAX_NEVER		0x00000008 /* Do not allow Direct Access */
-#define EXT4_MOUNT2_DAX_INODE		0x00000010 /* For printing options only */
-
 #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
 						specified journal checksum */
 
 #define EXT4_MOUNT2_JOURNAL_FAST_COMMIT	0x00000010 /* Journal fast commit */
+#define EXT4_MOUNT2_DAX_NEVER		0x00000020 /* Do not allow Direct Access */
+#define EXT4_MOUNT2_DAX_INODE		0x00000040 /* For printing options only */
+
 
 #define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
 						~EXT4_MOUNT_##opt
@@ -1422,16 +1419,6 @@
 
 #ifdef __KERNEL__
 
-/*
- * run-time mount flags
- */
-#define EXT4_MF_MNTDIR_SAMPLED		0x0001
-#define EXT4_MF_FS_ABORTED		0x0002	/* Fatal error detected */
-#define EXT4_MF_FC_INELIGIBLE		0x0004	/* Fast commit ineligible */
-#define EXT4_MF_FC_COMMITTING		0x0008	/* File system underoing a fast
-						 * commit.
-						 */
-
 #ifdef CONFIG_FS_ENCRYPTION
 #define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL)
 #else
@@ -1466,7 +1453,7 @@
 	struct buffer_head * __rcu *s_group_desc;
 	unsigned int s_mount_opt;
 	unsigned int s_mount_opt2;
-	unsigned int s_mount_flags;
+	unsigned long s_mount_flags;
 	unsigned int s_def_mount_opt;
 	ext4_fsblk_t s_sb_block;
 	atomic64_t s_resv_clusters;
@@ -1695,6 +1682,34 @@
 })
 
 /*
+ * run-time mount flags
+ */
+enum {
+	EXT4_MF_MNTDIR_SAMPLED,
+	EXT4_MF_FS_ABORTED,	/* Fatal error detected */
+	EXT4_MF_FC_INELIGIBLE,	/* Fast commit ineligible */
+	EXT4_MF_FC_COMMITTING	/* File system underoing a fast
+				 * commit.
+				 */
+};
+
+static inline void ext4_set_mount_flag(struct super_block *sb, int bit)
+{
+	set_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+static inline void ext4_clear_mount_flag(struct super_block *sb, int bit)
+{
+	clear_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+static inline int ext4_test_mount_flag(struct super_block *sb, int bit)
+{
+	return test_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+
+/*
  * Simulate_fail codes
  */
 #define EXT4_SIM_BBITMAP_EIO	1
@@ -1863,6 +1878,13 @@
 #define EXT4_FEATURE_COMPAT_RESIZE_INODE	0x0010
 #define EXT4_FEATURE_COMPAT_DIR_INDEX		0x0020
 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
+/*
+ * The reason why "FAST_COMMIT" is a compat feature is that, FS becomes
+ * incompatible only if fast commit blocks are present in the FS. Since we
+ * clear the journal (and thus the fast commit blocks), we don't mark FS as
+ * incompatible. We also have a JBD2 incompat feature, which gets set when
+ * there are fast commit blocks present in the journal.
+ */
 #define EXT4_FEATURE_COMPAT_FAST_COMMIT		0x0400
 #define EXT4_FEATURE_COMPAT_STABLE_INODES	0x0800
 
@@ -2731,12 +2753,16 @@
 int ext4_fc_info_show(struct seq_file *seq, void *v);
 void ext4_fc_init(struct super_block *sb, journal_t *journal);
 void ext4_fc_init_inode(struct inode *inode);
-void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
 			 ext4_lblk_t end);
-void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_link(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_create(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_inode(struct inode *inode);
+void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode,
+	struct dentry *dentry);
+void __ext4_fc_track_link(handle_t *handle, struct inode *inode,
+	struct dentry *dentry);
+void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_link(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
 void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
 void ext4_fc_start_ineligible(struct super_block *sb, int reason);
 void ext4_fc_stop_ineligible(struct super_block *sb);
@@ -3452,7 +3478,7 @@
 extern int ext4_ci_compare(const struct inode *parent,
 			   const struct qstr *fname,
 			   const struct qstr *entry, bool quick);
-extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
 			 struct inode *inode);
 extern int __ext4_link(struct inode *dir, struct inode *inode,
 		       struct dentry *dentry);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 57cfa28..17d7096 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3724,7 +3724,6 @@
 	err = ext4_ext_dirty(handle, inode, path + path->p_depth);
 out:
 	ext4_ext_show_leaf(inode, path);
-	ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
 	return err;
 }
 
@@ -3796,7 +3795,6 @@
 	if (*allocated > map->m_len)
 		*allocated = map->m_len;
 	map->m_len = *allocated;
-	ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
 	return 0;
 }
 
@@ -4329,7 +4327,6 @@
 	map->m_len = ar.len;
 	allocated = map->m_len;
 	ext4_ext_show_leaf(inode, path);
-	ext4_fc_track_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1);
 out:
 	ext4_ext_drop_refs(path);
 	kfree(path);
@@ -4602,7 +4599,7 @@
 	ret = ext4_mark_inode_dirty(handle, inode);
 	if (unlikely(ret))
 		goto out_handle;
-	ext4_fc_track_range(inode, offset >> inode->i_sb->s_blocksize_bits,
+	ext4_fc_track_range(handle, inode, offset >> inode->i_sb->s_blocksize_bits,
 			(offset + len - 1) >> inode->i_sb->s_blocksize_bits);
 	/* Zero out partial block at the edges of the range */
 	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
@@ -4651,8 +4648,6 @@
 		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
 		     FALLOC_FL_INSERT_RANGE))
 		return -EOPNOTSUPP;
-	ext4_fc_track_range(inode, offset >> blkbits,
-			(offset + len - 1) >> blkbits);
 
 	ext4_fc_start_update(inode);
 
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 8d43058..f2033e1 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -83,7 +83,7 @@
  *
  * Atomicity of commits
  * --------------------
- * In order to gaurantee atomicity during the commit operation, fast commit
+ * In order to guarantee atomicity during the commit operation, fast commit
  * uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail
  * tag contains CRC of the contents and TID of the transaction after which
  * this fast commit should be applied. Recovery code replays fast commit
@@ -152,7 +152,31 @@
 	INIT_LIST_HEAD(&ei->i_fc_list);
 	init_waitqueue_head(&ei->i_fc_wait);
 	atomic_set(&ei->i_fc_updates, 0);
-	ei->i_fc_committed_subtid = 0;
+}
+
+/* This function must be called with sbi->s_fc_lock held. */
+static void ext4_fc_wait_committing_inode(struct inode *inode)
+__releases(&EXT4_SB(inode->i_sb)->s_fc_lock)
+{
+	wait_queue_head_t *wq;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+#if (BITS_PER_LONG < 64)
+	DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
+			EXT4_STATE_FC_COMMITTING);
+	wq = bit_waitqueue(&ei->i_state_flags,
+				EXT4_STATE_FC_COMMITTING);
+#else
+	DEFINE_WAIT_BIT(wait, &ei->i_flags,
+			EXT4_STATE_FC_COMMITTING);
+	wq = bit_waitqueue(&ei->i_flags,
+				EXT4_STATE_FC_COMMITTING);
+#endif
+	lockdep_assert_held(&EXT4_SB(inode->i_sb)->s_fc_lock);
+	prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+	spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+	schedule();
+	finish_wait(wq, &wait.wq_entry);
 }
 
 /*
@@ -176,22 +200,7 @@
 		goto out;
 
 	if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
-		wait_queue_head_t *wq;
-#if (BITS_PER_LONG < 64)
-		DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
-				EXT4_STATE_FC_COMMITTING);
-		wq = bit_waitqueue(&ei->i_state_flags,
-				   EXT4_STATE_FC_COMMITTING);
-#else
-		DEFINE_WAIT_BIT(wait, &ei->i_flags,
-				EXT4_STATE_FC_COMMITTING);
-		wq = bit_waitqueue(&ei->i_flags,
-				   EXT4_STATE_FC_COMMITTING);
-#endif
-		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
-		spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
-		schedule();
-		finish_wait(wq, &wait.wq_entry);
+		ext4_fc_wait_committing_inode(inode);
 		goto restart;
 	}
 out:
@@ -234,26 +243,10 @@
 	}
 
 	if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
-		wait_queue_head_t *wq;
-#if (BITS_PER_LONG < 64)
-		DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
-				EXT4_STATE_FC_COMMITTING);
-		wq = bit_waitqueue(&ei->i_state_flags,
-				   EXT4_STATE_FC_COMMITTING);
-#else
-		DEFINE_WAIT_BIT(wait, &ei->i_flags,
-				EXT4_STATE_FC_COMMITTING);
-		wq = bit_waitqueue(&ei->i_flags,
-				   EXT4_STATE_FC_COMMITTING);
-#endif
-		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
-		spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
-		schedule();
-		finish_wait(wq, &wait.wq_entry);
+		ext4_fc_wait_committing_inode(inode);
 		goto restart;
 	}
-	if (!list_empty(&ei->i_fc_list))
-		list_del_init(&ei->i_fc_list);
+	list_del_init(&ei->i_fc_list);
 	spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
 }
 
@@ -269,7 +262,7 @@
 	    (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
 		return;
 
-	sbi->s_mount_flags |= EXT4_MF_FC_INELIGIBLE;
+	ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 	WARN_ON(reason >= EXT4_FC_REASON_MAX);
 	sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
 }
@@ -302,14 +295,14 @@
 	    (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
 		return;
 
-	EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FC_INELIGIBLE;
+	ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 	atomic_dec(&EXT4_SB(sb)->s_fc_ineligible_updates);
 }
 
 static inline int ext4_fc_is_ineligible(struct super_block *sb)
 {
-	return (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FC_INELIGIBLE) ||
-		atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates);
+	return (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE) ||
+		atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates));
 }
 
 /*
@@ -323,13 +316,14 @@
  * If enqueue is set, this function enqueues the inode in fast commit list.
  */
 static int ext4_fc_track_template(
-	struct inode *inode, int (*__fc_track_fn)(struct inode *, void *, bool),
+	handle_t *handle, struct inode *inode,
+	int (*__fc_track_fn)(struct inode *, void *, bool),
 	void *args, int enqueue)
 {
-	tid_t running_txn_tid;
 	bool update = false;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	tid_t tid = 0;
 	int ret;
 
 	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
@@ -339,15 +333,13 @@
 	if (ext4_fc_is_ineligible(inode->i_sb))
 		return -EINVAL;
 
-	running_txn_tid = sbi->s_journal ?
-		sbi->s_journal->j_commit_sequence + 1 : 0;
-
+	tid = handle->h_transaction->t_tid;
 	mutex_lock(&ei->i_fc_lock);
-	if (running_txn_tid == ei->i_sync_tid) {
+	if (tid == ei->i_sync_tid) {
 		update = true;
 	} else {
 		ext4_fc_reset_inode(inode);
-		ei->i_sync_tid = running_txn_tid;
+		ei->i_sync_tid = tid;
 	}
 	ret = __fc_track_fn(inode, args, update);
 	mutex_unlock(&ei->i_fc_lock);
@@ -358,7 +350,7 @@
 	spin_lock(&sbi->s_fc_lock);
 	if (list_empty(&EXT4_I(inode)->i_fc_list))
 		list_add_tail(&EXT4_I(inode)->i_fc_list,
-				(sbi->s_mount_flags & EXT4_MF_FC_COMMITTING) ?
+				(ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ?
 				&sbi->s_fc_q[FC_Q_STAGING] :
 				&sbi->s_fc_q[FC_Q_MAIN]);
 	spin_unlock(&sbi->s_fc_lock);
@@ -384,7 +376,7 @@
 	mutex_unlock(&ei->i_fc_lock);
 	node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS);
 	if (!node) {
-		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_MEM);
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
 		mutex_lock(&ei->i_fc_lock);
 		return -ENOMEM;
 	}
@@ -397,7 +389,7 @@
 		if (!node->fcd_name.name) {
 			kmem_cache_free(ext4_fc_dentry_cachep, node);
 			ext4_fc_mark_ineligible(inode->i_sb,
-				EXT4_FC_REASON_MEM);
+				EXT4_FC_REASON_NOMEM);
 			mutex_lock(&ei->i_fc_lock);
 			return -ENOMEM;
 		}
@@ -411,7 +403,7 @@
 	node->fcd_name.len = dentry->d_name.len;
 
 	spin_lock(&sbi->s_fc_lock);
-	if (sbi->s_mount_flags & EXT4_MF_FC_COMMITTING)
+	if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING))
 		list_add_tail(&node->fcd_list,
 				&sbi->s_fc_dentry_q[FC_Q_STAGING]);
 	else
@@ -422,7 +414,8 @@
 	return 0;
 }
 
-void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry)
+void __ext4_fc_track_unlink(handle_t *handle,
+		struct inode *inode, struct dentry *dentry)
 {
 	struct __track_dentry_update_args args;
 	int ret;
@@ -430,12 +423,18 @@
 	args.dentry = dentry;
 	args.op = EXT4_FC_TAG_UNLINK;
 
-	ret = ext4_fc_track_template(inode, __track_dentry_update,
+	ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
 					(void *)&args, 0);
 	trace_ext4_fc_track_unlink(inode, dentry, ret);
 }
 
-void ext4_fc_track_link(struct inode *inode, struct dentry *dentry)
+void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry)
+{
+	__ext4_fc_track_unlink(handle, d_inode(dentry), dentry);
+}
+
+void __ext4_fc_track_link(handle_t *handle,
+	struct inode *inode, struct dentry *dentry)
 {
 	struct __track_dentry_update_args args;
 	int ret;
@@ -443,20 +442,26 @@
 	args.dentry = dentry;
 	args.op = EXT4_FC_TAG_LINK;
 
-	ret = ext4_fc_track_template(inode, __track_dentry_update,
+	ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
 					(void *)&args, 0);
 	trace_ext4_fc_track_link(inode, dentry, ret);
 }
 
-void ext4_fc_track_create(struct inode *inode, struct dentry *dentry)
+void ext4_fc_track_link(handle_t *handle, struct dentry *dentry)
+{
+	__ext4_fc_track_link(handle, d_inode(dentry), dentry);
+}
+
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
 {
 	struct __track_dentry_update_args args;
+	struct inode *inode = d_inode(dentry);
 	int ret;
 
 	args.dentry = dentry;
 	args.op = EXT4_FC_TAG_CREAT;
 
-	ret = ext4_fc_track_template(inode, __track_dentry_update,
+	ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
 					(void *)&args, 0);
 	trace_ext4_fc_track_create(inode, dentry, ret);
 }
@@ -472,14 +477,20 @@
 	return 0;
 }
 
-void ext4_fc_track_inode(struct inode *inode)
+void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
 {
 	int ret;
 
 	if (S_ISDIR(inode->i_mode))
 		return;
 
-	ret = ext4_fc_track_template(inode, __track_inode, NULL, 1);
+	if (ext4_should_journal_data(inode)) {
+		ext4_fc_mark_ineligible(inode->i_sb,
+					EXT4_FC_REASON_INODE_JOURNAL_DATA);
+		return;
+	}
+
+	ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1);
 	trace_ext4_fc_track_inode(inode, ret);
 }
 
@@ -515,7 +526,7 @@
 	return 0;
 }
 
-void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
 			 ext4_lblk_t end)
 {
 	struct __track_range_args args;
@@ -527,7 +538,7 @@
 	args.start = start;
 	args.end = end;
 
-	ret = ext4_fc_track_template(inode,  __track_range, &args, 1);
+	ret = ext4_fc_track_template(handle, inode,  __track_range, &args, 1);
 
 	trace_ext4_fc_track_range(inode, start, end, ret);
 }
@@ -537,10 +548,11 @@
 	int write_flags = REQ_SYNC;
 	struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
 
+	/* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */
 	if (test_opt(sb, BARRIER))
 		write_flags |= REQ_FUA | REQ_PREFLUSH;
 	lock_buffer(bh);
-	clear_buffer_dirty(bh);
+	set_buffer_dirty(bh);
 	set_buffer_uptodate(bh);
 	bh->b_end_io = ext4_end_buffer_io_sync;
 	submit_bh(REQ_OP_WRITE, write_flags, bh);
@@ -846,7 +858,7 @@
 	int ret = 0;
 
 	spin_lock(&sbi->s_fc_lock);
-	sbi->s_mount_flags |= EXT4_MF_FC_COMMITTING;
+	ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING);
 	list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) {
 		ei = list_entry(pos, struct ext4_inode_info, i_fc_list);
 		ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
@@ -900,6 +912,8 @@
 
 /* Commit all the directory entry updates */
 static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc)
+__acquires(&sbi->s_fc_lock)
+__releases(&sbi->s_fc_lock)
 {
 	struct super_block *sb = (struct super_block *)(journal->j_private);
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -996,6 +1010,13 @@
 	if (ret)
 		return ret;
 
+	/*
+	 * If file system device is different from journal device, issue a cache
+	 * flush before we start writing fast commit blocks.
+	 */
+	if (journal->j_fs_dev != journal->j_dev)
+		blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS);
+
 	blk_start_plug(&plug);
 	if (sbi->s_fc_bytes == 0) {
 		/*
@@ -1031,8 +1052,6 @@
 		if (ret)
 			goto out;
 		spin_lock(&sbi->s_fc_lock);
-		EXT4_I(inode)->i_fc_committed_subtid =
-			atomic_read(&sbi->s_fc_subtid);
 	}
 	spin_unlock(&sbi->s_fc_lock);
 
@@ -1131,7 +1150,7 @@
 		"Fast commit ended with blks = %d, reason = %d, subtid - %d",
 		nblks, reason, subtid);
 	if (reason == EXT4_FC_REASON_FC_FAILED)
-		return jbd2_fc_end_commit_fallback(journal, commit_tid);
+		return jbd2_fc_end_commit_fallback(journal);
 	if (reason == EXT4_FC_REASON_FC_START_FAILED ||
 		reason == EXT4_FC_REASON_INELIGIBLE)
 		return jbd2_complete_transaction(journal, commit_tid);
@@ -1190,8 +1209,8 @@
 	list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
 				&sbi->s_fc_q[FC_Q_STAGING]);
 
-	sbi->s_mount_flags &= ~EXT4_MF_FC_COMMITTING;
-	sbi->s_mount_flags &= ~EXT4_MF_FC_INELIGIBLE;
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 
 	if (full)
 		sbi->s_fc_bytes = 0;
@@ -1263,7 +1282,7 @@
 		return 0;
 	}
 
-	ret = __ext4_unlink(old_parent, &entry, inode);
+	ret = __ext4_unlink(NULL, old_parent, &entry, inode);
 	/* -ENOENT ok coz it might not exist anymore. */
 	if (ret == -ENOENT)
 		ret = 0;
@@ -2079,8 +2098,6 @@
 
 void ext4_fc_init(struct super_block *sb, journal_t *journal)
 {
-	int num_fc_blocks;
-
 	/*
 	 * We set replay callback even if fast commit disabled because we may
 	 * could still have fast commit blocks that need to be replayed even if
@@ -2090,21 +2107,9 @@
 	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
 		return;
 	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
-	if (!buffer_uptodate(journal->j_sb_buffer)
-		&& ext4_read_bh_lock(journal->j_sb_buffer, REQ_META | REQ_PRIO,
-					true)) {
-		ext4_msg(sb, KERN_ERR, "I/O error on journal");
-		return;
-	}
-	num_fc_blocks = be32_to_cpu(journal->j_superblock->s_num_fc_blks);
-	if (jbd2_fc_init(journal, num_fc_blocks ? num_fc_blocks :
-					EXT4_NUM_FC_BLKS)) {
-		pr_warn("Error while enabling fast commits, turning off.");
-		ext4_clear_feature_fast_commit(sb);
-	}
 }
 
-const char *fc_ineligible_reasons[] = {
+static const char *fc_ineligible_reasons[] = {
 	"Extended attributes changed",
 	"Cross rename",
 	"Journal flag changed",
@@ -2113,6 +2118,7 @@
 	"Resize",
 	"Dir renamed",
 	"Falloc range op",
+	"Data journalling",
 	"FC Commit Failed"
 };
 
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index 06907d4..3a6e5a1 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -3,9 +3,6 @@
 #ifndef __FAST_COMMIT_H__
 #define __FAST_COMMIT_H__
 
-/* Number of blocks in journal area to allocate for fast commits */
-#define EXT4_NUM_FC_BLKS		256
-
 /* Fast commit tags */
 #define EXT4_FC_TAG_ADD_RANGE		0x0001
 #define EXT4_FC_TAG_DEL_RANGE		0x0002
@@ -100,11 +97,12 @@
 	EXT4_FC_REASON_XATTR = 0,
 	EXT4_FC_REASON_CROSS_RENAME,
 	EXT4_FC_REASON_JOURNAL_FLAG_CHANGE,
-	EXT4_FC_REASON_MEM,
+	EXT4_FC_REASON_NOMEM,
 	EXT4_FC_REASON_SWAP_BOOT,
 	EXT4_FC_REASON_RESIZE,
 	EXT4_FC_REASON_RENAME_DIR,
 	EXT4_FC_REASON_FALLOC_RANGE,
+	EXT4_FC_REASON_INODE_JOURNAL_DATA,
 	EXT4_FC_COMMIT_FAILED,
 	EXT4_FC_REASON_MAX
 };
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d85412d..3ed8c04 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -761,7 +761,6 @@
 	if (!daxdev_mapping_supported(vma, dax_dev))
 		return -EOPNOTSUPP;
 
-	ext4_fc_start_update(inode);
 	file_accessed(file);
 	if (IS_DAX(file_inode(file))) {
 		vma->vm_ops = &ext4_dax_vm_ops;
@@ -769,7 +768,6 @@
 	} else {
 		vma->vm_ops = &ext4_file_vm_ops;
 	}
-	ext4_fc_stop_update(inode);
 	return 0;
 }
 
@@ -782,13 +780,13 @@
 	handle_t *handle;
 	int err;
 
-	if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED))
+	if (likely(ext4_test_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED)))
 		return 0;
 
 	if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb))
 		return 0;
 
-	sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
+	ext4_set_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED);
 	/*
 	 * Sample where the filesystem has been mounted and
 	 * store it in the superblock for sysadmin convenience
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index b232c276..4c2a9fe 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -280,7 +280,7 @@
 
 	/* Fabricate an rmap entry for the external log device. */
 	irec.fmr_physical = journal->j_blk_offset;
-	irec.fmr_length = journal->j_maxlen;
+	irec.fmr_length = journal->j_total_len;
 	irec.fmr_owner = EXT4_FMR_OWN_LOG;
 	irec.fmr_flags = 0;
 
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 81a545f..a42ca95 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -143,7 +143,7 @@
 	if (sb_rdonly(inode->i_sb)) {
 		/* Make sure that we read updated s_mount_flags value */
 		smp_rmb();
-		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
+		if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))
 			ret = -EROFS;
 		goto out;
 	}
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index caa5147..b41512d 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1880,6 +1880,7 @@
 
 	ext4_write_lock_xattr(inode, &no_expand);
 	if (!ext4_has_inline_data(inode)) {
+		ext4_write_unlock_xattr(inode, &no_expand);
 		*has_inline = 0;
 		ext4_journal_stop(handle);
 		return 0;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index b96a1867..0d8385a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -327,6 +327,8 @@
 	ext4_xattr_inode_array_free(ea_inode_array);
 	return;
 no_delete:
+	if (!list_empty(&EXT4_I(inode)->i_fc_list))
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
 	ext4_clear_inode(inode);	/* We must guarantee clearing of inode... */
 }
 
@@ -730,7 +732,7 @@
 			if (ret)
 				return ret;
 		}
-		ext4_fc_track_range(inode, map->m_lblk,
+		ext4_fc_track_range(handle, inode, map->m_lblk,
 			    map->m_lblk + map->m_len - 1);
 	}
 
@@ -2440,7 +2442,7 @@
 			struct super_block *sb = inode->i_sb;
 
 			if (ext4_forced_shutdown(EXT4_SB(sb)) ||
-			    EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+			    ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
 				goto invalidate_dirty_pages;
 			/*
 			 * Let the uper layers retry transient errors.
@@ -2674,7 +2676,7 @@
 	 * the stack trace.
 	 */
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
-		     sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+		     ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) {
 		ret = -EROFS;
 		goto out_writepages;
 	}
@@ -3310,8 +3312,7 @@
 			EXT4_I(inode)->i_datasync_tid))
 			return false;
 		if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
-			return atomic_read(&EXT4_SB(inode->i_sb)->s_fc_subtid) <
-				EXT4_I(inode)->i_fc_committed_subtid;
+			return !list_empty(&EXT4_I(inode)->i_fc_list);
 		return true;
 	}
 
@@ -4109,7 +4110,7 @@
 
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
-	ext4_fc_track_range(inode, first_block, stop_block);
+	ext4_fc_track_range(handle, inode, first_block, stop_block);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
@@ -5442,14 +5443,14 @@
 			}
 
 			if (shrink)
-				ext4_fc_track_range(inode,
+				ext4_fc_track_range(handle, inode,
 					(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
 					inode->i_sb->s_blocksize_bits,
 					(oldsize > 0 ? oldsize - 1 : 0) >>
 					inode->i_sb->s_blocksize_bits);
 			else
 				ext4_fc_track_range(
-					inode,
+					handle, inode,
 					(oldsize > 0 ? oldsize - 1 : oldsize) >>
 					inode->i_sb->s_blocksize_bits,
 					(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
@@ -5699,7 +5700,7 @@
 		put_bh(iloc->bh);
 		return -EIO;
 	}
-	ext4_fc_track_inode(inode);
+	ext4_fc_track_inode(handle, inode);
 
 	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 85abbfb..24af9ed 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4477,7 +4477,7 @@
 {
 	ext4_group_t i, ngroups;
 
-	if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+	if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
 		return;
 
 	ngroups = ext4_get_groups_count(sb);
@@ -4508,7 +4508,7 @@
 {
 	struct super_block *sb = ac->ac_sb;
 
-	if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+	if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
 		return;
 
 	mb_debug(sb, "Can't allocate:"
@@ -5167,7 +5167,7 @@
 	struct super_block *sb = ar->inode->i_sb;
 	ext4_group_t group;
 	ext4_grpblk_t blkoff;
-	int  i;
+	int i = sb->s_blocksize;
 	ext4_fsblk_t goal, block;
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index f458d1d..3350926 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2606,7 +2606,7 @@
 		       bool excl)
 {
 	handle_t *handle;
-	struct inode *inode, *inode_save;
+	struct inode *inode;
 	int err, credits, retries = 0;
 
 	err = dquot_initialize(dir);
@@ -2624,11 +2624,9 @@
 		inode->i_op = &ext4_file_inode_operations;
 		inode->i_fop = &ext4_file_operations;
 		ext4_set_aops(inode);
-		inode_save = inode;
-		ihold(inode_save);
 		err = ext4_add_nondir(handle, dentry, &inode);
-		ext4_fc_track_create(inode_save, dentry);
-		iput(inode_save);
+		if (!err)
+			ext4_fc_track_create(handle, dentry);
 	}
 	if (handle)
 		ext4_journal_stop(handle);
@@ -2643,7 +2641,7 @@
 		      umode_t mode, dev_t rdev)
 {
 	handle_t *handle;
-	struct inode *inode, *inode_save;
+	struct inode *inode;
 	int err, credits, retries = 0;
 
 	err = dquot_initialize(dir);
@@ -2660,12 +2658,9 @@
 	if (!IS_ERR(inode)) {
 		init_special_inode(inode, inode->i_mode, rdev);
 		inode->i_op = &ext4_special_inode_operations;
-		inode_save = inode;
-		ihold(inode_save);
 		err = ext4_add_nondir(handle, dentry, &inode);
 		if (!err)
-			ext4_fc_track_create(inode_save, dentry);
-		iput(inode_save);
+			ext4_fc_track_create(handle, dentry);
 	}
 	if (handle)
 		ext4_journal_stop(handle);
@@ -2829,7 +2824,6 @@
 		iput(inode);
 		goto out_retry;
 	}
-	ext4_fc_track_create(inode, dentry);
 	ext4_inc_count(dir);
 
 	ext4_update_dx_flag(dir);
@@ -2837,6 +2831,7 @@
 	if (err)
 		goto out_clear_inode;
 	d_instantiate_new(dentry, inode);
+	ext4_fc_track_create(handle, dentry);
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
@@ -3171,7 +3166,7 @@
 		goto end_rmdir;
 	ext4_dec_count(dir);
 	ext4_update_dx_flag(dir);
-	ext4_fc_track_unlink(inode, dentry);
+	ext4_fc_track_unlink(handle, dentry);
 	retval = ext4_mark_inode_dirty(handle, dir);
 
 #ifdef CONFIG_UNICODE
@@ -3192,13 +3187,12 @@
 	return retval;
 }
 
-int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
 		  struct inode *inode)
 {
 	int retval = -ENOENT;
 	struct buffer_head *bh;
 	struct ext4_dir_entry_2 *de;
-	handle_t *handle = NULL;
 	int skip_remove_dentry = 0;
 
 	bh = ext4_find_entry(dir, d_name, &de, NULL);
@@ -3217,14 +3211,7 @@
 		if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
 			skip_remove_dentry = 1;
 		else
-			goto out_bh;
-	}
-
-	handle = ext4_journal_start(dir, EXT4_HT_DIR,
-				    EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
-	if (IS_ERR(handle)) {
-		retval = PTR_ERR(handle);
-		goto out_bh;
+			goto out;
 	}
 
 	if (IS_DIRSYNC(dir))
@@ -3233,12 +3220,12 @@
 	if (!skip_remove_dentry) {
 		retval = ext4_delete_entry(handle, dir, de, bh);
 		if (retval)
-			goto out_handle;
+			goto out;
 		dir->i_ctime = dir->i_mtime = current_time(dir);
 		ext4_update_dx_flag(dir);
 		retval = ext4_mark_inode_dirty(handle, dir);
 		if (retval)
-			goto out_handle;
+			goto out;
 	} else {
 		retval = 0;
 	}
@@ -3252,15 +3239,14 @@
 	inode->i_ctime = current_time(inode);
 	retval = ext4_mark_inode_dirty(handle, inode);
 
-out_handle:
-	ext4_journal_stop(handle);
-out_bh:
+out:
 	brelse(bh);
 	return retval;
 }
 
 static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 {
+	handle_t *handle;
 	int retval;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
@@ -3278,9 +3264,16 @@
 	if (retval)
 		goto out_trace;
 
-	retval = __ext4_unlink(dir, &dentry->d_name, d_inode(dentry));
+	handle = ext4_journal_start(dir, EXT4_HT_DIR,
+				    EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
+	if (IS_ERR(handle)) {
+		retval = PTR_ERR(handle);
+		goto out_trace;
+	}
+
+	retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry));
 	if (!retval)
-		ext4_fc_track_unlink(d_inode(dentry), dentry);
+		ext4_fc_track_unlink(handle, dentry);
 #ifdef CONFIG_UNICODE
 	/* VFS negative dentries are incompatible with Encoding and
 	 * Case-insensitiveness. Eventually we'll want avoid
@@ -3291,6 +3284,8 @@
 	if (IS_CASEFOLDED(dir))
 		d_invalidate(dentry);
 #endif
+	if (handle)
+		ext4_journal_stop(handle);
 
 out_trace:
 	trace_ext4_unlink_exit(dentry, retval);
@@ -3447,7 +3442,6 @@
 
 	err = ext4_add_entry(handle, dentry, inode);
 	if (!err) {
-		ext4_fc_track_link(inode, dentry);
 		err = ext4_mark_inode_dirty(handle, inode);
 		/* this can happen only for tmpfile being
 		 * linked the first time
@@ -3455,6 +3449,7 @@
 		if (inode->i_nlink == 1)
 			ext4_orphan_del(handle, inode);
 		d_instantiate(dentry, inode);
+		ext4_fc_track_link(handle, dentry);
 	} else {
 		drop_nlink(inode);
 		iput(inode);
@@ -3915,9 +3910,9 @@
 			EXT4_FC_REASON_RENAME_DIR);
 	} else {
 		if (new.inode)
-			ext4_fc_track_unlink(new.inode, new.dentry);
-		ext4_fc_track_link(old.inode, new.dentry);
-		ext4_fc_track_unlink(old.inode, old.dentry);
+			ext4_fc_track_unlink(handle, new.dentry);
+		__ext4_fc_track_link(handle, old.inode, new.dentry);
+		__ext4_fc_track_unlink(handle, old.inode, old.dentry);
 	}
 
 	if (new.inode) {
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index ef4734b..6633b20 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -289,18 +289,7 @@
 	if (!ext4_has_metadata_csum(sb))
 		return;
 
-	/*
-	 * Locking the superblock prevents the scenario
-	 * where:
-	 *  1) a first thread pauses during checksum calculation.
-	 *  2) a second thread updates the superblock, recalculates
-	 *     the checksum, and updates s_checksum
-	 *  3) the first thread resumes and finishes its checksum calculation
-	 *     and updates s_checksum with a potentially stale or torn value.
-	 */
-	lock_buffer(EXT4_SB(sb)->s_sbh);
 	es->s_checksum = ext4_superblock_csum(sb, es);
-	unlock_buffer(EXT4_SB(sb)->s_sbh);
 }
 
 ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
@@ -686,7 +675,7 @@
 	if (!test_opt(sb, ERRORS_CONT)) {
 		journal_t *journal = EXT4_SB(sb)->s_journal;
 
-		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
 		if (journal)
 			jbd2_journal_abort(journal, -EIO);
 	}
@@ -904,7 +893,7 @@
 	va_end(args);
 
 	if (sb_rdonly(sb) == 0) {
-		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
 		if (EXT4_SB(sb)->s_journal)
 			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 
@@ -1716,11 +1705,10 @@
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
-	Opt_prefetch_block_bitmaps, Opt_no_fc,
+	Opt_prefetch_block_bitmaps,
 #ifdef CONFIG_EXT4_DEBUG
-	Opt_fc_debug_max_replay,
+	Opt_fc_debug_max_replay, Opt_fc_debug_force
 #endif
-	Opt_fc_debug_force
 };
 
 static const match_table_t tokens = {
@@ -1807,9 +1795,8 @@
 	{Opt_init_itable, "init_itable=%u"},
 	{Opt_init_itable, "init_itable"},
 	{Opt_noinit_itable, "noinit_itable"},
-	{Opt_no_fc, "no_fc"},
-	{Opt_fc_debug_force, "fc_debug_force"},
 #ifdef CONFIG_EXT4_DEBUG
+	{Opt_fc_debug_force, "fc_debug_force"},
 	{Opt_fc_debug_max_replay, "fc_debug_max_replay=%u"},
 #endif
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
@@ -2027,8 +2014,8 @@
 	{Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
 		       EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA),
 							MOPT_CLEAR | MOPT_Q},
-	{Opt_usrjquota, 0, MOPT_Q},
-	{Opt_grpjquota, 0, MOPT_Q},
+	{Opt_usrjquota, 0, MOPT_Q | MOPT_STRING},
+	{Opt_grpjquota, 0, MOPT_Q | MOPT_STRING},
 	{Opt_offusrjquota, 0, MOPT_Q},
 	{Opt_offgrpjquota, 0, MOPT_Q},
 	{Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
@@ -2039,11 +2026,9 @@
 	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
 	{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
 	 MOPT_SET},
-	{Opt_no_fc, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
-	 MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY},
+#ifdef CONFIG_EXT4_DEBUG
 	{Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
 	 MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
-#ifdef CONFIG_EXT4_DEBUG
 	{Opt_fc_debug_max_replay, 0, MOPT_GTE0},
 #endif
 	{Opt_err, 0, 0}
@@ -2153,7 +2138,7 @@
 		ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt);
 		return 1;
 	case Opt_abort:
-		sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
 		return 1;
 	case Opt_i_version:
 		sb->s_flags |= SB_I_VERSION;
@@ -3976,7 +3961,7 @@
 	 * loaded or not
 	 */
 	if (sbi->s_journal && !sbi->s_journal_bdev)
-		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
+		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len);
 	else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
 		/* j_inum for internal journal is non-zero */
 		j_inode = ext4_get_journal_inode(sb, j_inum);
@@ -4340,9 +4325,10 @@
 #endif
 
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
-		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n");
+		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, O_DIRECT and fast_commit support!\n");
 		/* can't mount with both data=journal and dioread_nolock. */
 		clear_opt(sb, DIOREAD_NOLOCK);
+		clear_opt2(sb, JOURNAL_FAST_COMMIT);
 		if (test_opt2(sb, EXPLICIT_DELALLOC)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
 				 "both data=journal and delalloc");
@@ -4777,8 +4763,8 @@
 	INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]);
 	INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]);
 	sbi->s_fc_bytes = 0;
-	sbi->s_mount_flags &= ~EXT4_MF_FC_INELIGIBLE;
-	sbi->s_mount_flags &= ~EXT4_MF_FC_COMMITTING;
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
 	spin_lock_init(&sbi->s_fc_lock);
 	memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats));
 	sbi->s_fc_replay_state.fc_regions = NULL;
@@ -4857,6 +4843,14 @@
 		goto failed_mount_wq;
 	}
 
+	if (test_opt2(sb, JOURNAL_FAST_COMMIT) &&
+		!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
+					  JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) {
+		ext4_msg(sb, KERN_ERR,
+			"Failed to set fast commit journal feature");
+		goto failed_mount_wq;
+	}
+
 	/* We have now updated the journal if required, so we can
 	 * validate the data journaling mode. */
 	switch (test_opt(sb, DATA_FLAGS)) {
@@ -5872,7 +5866,7 @@
 		goto restore_opts;
 	}
 
-	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
+	if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
 		ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user");
 
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
@@ -5886,7 +5880,7 @@
 	}
 
 	if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
-		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
+		if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) {
 			err = -EROFS;
 			goto restore_opts;
 		}
@@ -6560,10 +6554,6 @@
 	brelse(bh);
 out:
 	if (inode->i_size < off + len) {
-		ext4_fc_track_range(inode,
-			(inode->i_size > 0 ? inode->i_size - 1 : 0)
-				>> inode->i_sb->s_blocksize_bits,
-			(off + len) >> inode->i_sb->s_blocksize_bits);
 		i_size_write(inode, off + len);
 		EXT4_I(inode)->i_disksize = inode->i_size;
 		err2 = ext4_mark_inode_dirty(handle, inode);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 9cd2eca..cc4f987 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -77,7 +77,7 @@
 	if (error)
 		return error;
 	if (!buffer_mapped(bh_result))
-		return -EIO;
+		return -ENODATA;
 	return 0;
 }
 
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 8dff9cbd..62d9081 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1301,12 +1301,8 @@
 	trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
 
 	ret = gfs2_iomap_get(inode, pos, length, flags, &iomap, &mp);
-	if (!ret && iomap.type == IOMAP_HOLE) {
-		if (create)
-			ret = gfs2_iomap_alloc(inode, &iomap, &mp);
-		else
-			ret = -ENODATA;
-	}
+	if (create && !ret && iomap.type == IOMAP_HOLE)
+		ret = gfs2_iomap_alloc(inode, &iomap, &mp);
 	release_metapath(&mp);
 	if (ret)
 		goto out;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 5441c17..d98a2e5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1078,7 +1078,8 @@
 out_free:
 	kfree(gl->gl_lksb.sb_lvbptr);
 	kmem_cache_free(cachep, gl);
-	atomic_dec(&sdp->sd_glock_disposal);
+	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
+		wake_up(&sdp->sd_glock_wait);
 
 out:
 	return ret;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index aa3f523..67f2921 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -165,6 +165,31 @@
 }
 
 /**
+ * gfs2_rgrp_metasync - sync out the metadata of a resource group
+ * @gl: the glock protecting the resource group
+ *
+ */
+
+static int gfs2_rgrp_metasync(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+	struct address_space *metamapping = &sdp->sd_aspace;
+	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
+	const unsigned bsize = sdp->sd_sb.sb_bsize;
+	loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
+	loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
+	int error;
+
+	filemap_fdatawrite_range(metamapping, start, end);
+	error = filemap_fdatawait_range(metamapping, start, end);
+	WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
+	mapping_set_error(metamapping, error);
+	if (error)
+		gfs2_io_error(sdp);
+	return error;
+}
+
+/**
  * rgrp_go_sync - sync out the metadata for this glock
  * @gl: the glock
  *
@@ -176,11 +201,7 @@
 static int rgrp_go_sync(struct gfs2_glock *gl)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	struct address_space *mapping = &sdp->sd_aspace;
 	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
-	const unsigned bsize = sdp->sd_sb.sb_bsize;
-	loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
-	loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
 	int error;
 
 	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
@@ -189,10 +210,7 @@
 
 	gfs2_log_flush(sdp, gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
 		       GFS2_LFC_RGRP_GO_SYNC);
-	filemap_fdatawrite_range(mapping, start, end);
-	error = filemap_fdatawait_range(mapping, start, end);
-	WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
-	mapping_set_error(mapping, error);
+	error = gfs2_rgrp_metasync(gl);
 	if (!error)
 		error = gfs2_ail_empty_gl(gl);
 	gfs2_free_clones(rgd);
@@ -266,7 +284,24 @@
 }
 
 /**
- * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
+ * gfs2_inode_metasync - sync out the metadata of an inode
+ * @gl: the glock protecting the inode
+ *
+ */
+int gfs2_inode_metasync(struct gfs2_glock *gl)
+{
+	struct address_space *metamapping = gfs2_glock2aspace(gl);
+	int error;
+
+	filemap_fdatawrite(metamapping);
+	error = filemap_fdatawait(metamapping);
+	if (error)
+		gfs2_io_error(gl->gl_name.ln_sbd);
+	return error;
+}
+
+/**
+ * inode_go_sync - Sync the dirty metadata of an inode
  * @gl: the glock protecting the inode
  *
  */
@@ -297,8 +332,7 @@
 		error = filemap_fdatawait(mapping);
 		mapping_set_error(mapping, error);
 	}
-	ret = filemap_fdatawait(metamapping);
-	mapping_set_error(metamapping, ret);
+	ret = gfs2_inode_metasync(gl);
 	if (!error)
 		error = ret;
 	gfs2_ail_empty_gl(gl);
@@ -537,7 +571,18 @@
 	int error = 0;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
-	if (gl->gl_req == LM_ST_EXCLUSIVE && !gfs2_withdrawn(sdp)) {
+	/*
+	 * We need to check gl_state == LM_ST_SHARED here and not gl_req ==
+	 * LM_ST_EXCLUSIVE. That's because when any node does a freeze,
+	 * all the nodes should have the freeze glock in SH mode and they all
+	 * call do_xmote: One for EX and the others for UN. They ALL must
+	 * freeze locally, and they ALL must queue freeze work. The freeze_work
+	 * calls freeze_func, which tries to reacquire the freeze glock in SH,
+	 * effectively waiting for the thaw on the node who holds it in EX.
+	 * Once thawed, the work func acquires the freeze glock in
+	 * SH and everybody goes back to thawed.
+	 */
+	if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp)) {
 		atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE);
 		error = freeze_super(sdp->sd_vfs);
 		if (error) {
diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h
index 2dd192e..695898a 100644
--- a/fs/gfs2/glops.h
+++ b/fs/gfs2/glops.h
@@ -22,6 +22,7 @@
 extern const struct gfs2_glock_operations gfs2_journal_glops;
 extern const struct gfs2_glock_operations *gfs2_glops_list[];
 
+extern int gfs2_inode_metasync(struct gfs2_glock *gl);
 extern void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync);
 
 #endif /* __GLOPS_DOT_H__ */
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 6774865..077ccb1 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -180,7 +180,8 @@
 		error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
 		if (unlikely(error))
 			goto fail;
-		gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl);
+		if (blktype != GFS2_BLKST_UNLINKED)
+			gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl);
 		glock_set_object(ip->i_iopen_gh.gh_gl, ip);
 		gfs2_glock_put(io_gl);
 		io_gl = NULL;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 9133b31..2e93140 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -132,6 +132,8 @@
 		spin_unlock(&sdp->sd_ail_lock);
 		ret = generic_writepages(mapping, wbc);
 		spin_lock(&sdp->sd_ail_lock);
+		if (ret == -ENODATA) /* if a jdata write into a new hole */
+			ret = 0; /* ignore it */
 		if (ret || wbc->nr_to_write <= 0)
 			break;
 		return -EBUSY;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index ed69298..3922b26 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -22,6 +22,7 @@
 #include "incore.h"
 #include "inode.h"
 #include "glock.h"
+#include "glops.h"
 #include "log.h"
 #include "lops.h"
 #include "meta_io.h"
@@ -817,41 +818,19 @@
 	return error;
 }
 
-/**
- * gfs2_meta_sync - Sync all buffers associated with a glock
- * @gl: The glock
- *
- */
-
-void gfs2_meta_sync(struct gfs2_glock *gl)
-{
-	struct address_space *mapping = gfs2_glock2aspace(gl);
-	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	int error;
-
-	if (mapping == NULL)
-		mapping = &sdp->sd_aspace;
-
-	filemap_fdatawrite(mapping);
-	error = filemap_fdatawait(mapping);
-
-	if (error)
-		gfs2_io_error(gl->gl_name.ln_sbd);
-}
-
 static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
 {
 	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
 	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
 
 	if (error) {
-		gfs2_meta_sync(ip->i_gl);
+		gfs2_inode_metasync(ip->i_gl);
 		return;
 	}
 	if (pass != 1)
 		return;
 
-	gfs2_meta_sync(ip->i_gl);
+	gfs2_inode_metasync(ip->i_gl);
 
 	fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
 	        jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
@@ -1060,14 +1039,14 @@
 	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
 
 	if (error) {
-		gfs2_meta_sync(ip->i_gl);
+		gfs2_inode_metasync(ip->i_gl);
 		return;
 	}
 	if (pass != 1)
 		return;
 
 	/* data sync? */
-	gfs2_meta_sync(ip->i_gl);
+	gfs2_inode_metasync(ip->i_gl);
 
 	fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
 		jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index 4a3d8ae..fbdbb08 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -27,8 +27,6 @@
 extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
 extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
 			   struct gfs2_log_header_host *head, bool keep_cache);
-extern void gfs2_meta_sync(struct gfs2_glock *gl);
-
 static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
 {
 	unsigned int limit;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 7a7e3c1..61fce59 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -633,8 +633,10 @@
 	if (IS_ERR(sdp->sd_statfs_inode)) {
 		error = PTR_ERR(sdp->sd_statfs_inode);
 		fs_err(sdp, "can't read in statfs inode: %d\n", error);
-		goto fail;
+		goto out;
 	}
+	if (sdp->sd_args.ar_spectator)
+		goto out;
 
 	pn = gfs2_lookup_simple(master, "per_node");
 	if (IS_ERR(pn)) {
@@ -682,15 +684,17 @@
 	iput(pn);
 put_statfs:
 	iput(sdp->sd_statfs_inode);
-fail:
+out:
 	return error;
 }
 
 /* Uninitialize and free up memory used by the list of statfs inodes */
 static void uninit_statfs(struct gfs2_sbd *sdp)
 {
-	gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
-	free_local_statfs_inodes(sdp);
+	if (!sdp->sd_args.ar_spectator) {
+		gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+		free_local_statfs_inodes(sdp);
+	}
 	iput(sdp->sd_statfs_inode);
 }
 
@@ -704,7 +708,7 @@
 
 	if (undo) {
 		jindex = 0;
-		goto fail_jinode_gh;
+		goto fail_statfs;
 	}
 
 	sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index b5cbe21..c26c68e 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -349,7 +349,7 @@
 
 	mark_buffer_dirty(bh);
 	brelse(bh);
-	gfs2_meta_sync(ip->i_gl);
+	gfs2_inode_metasync(ip->i_gl);
 
 out:
 	return error;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index ee491bb..f7addc6 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -719,9 +719,9 @@
 		}
 
 		gfs2_free_clones(rgd);
+		return_all_reservations(rgd);
 		kfree(rgd->rd_bits);
 		rgd->rd_bits = NULL;
-		return_all_reservations(rgd);
 		kmem_cache_free(gfs2_rgrpd_cachep, rgd);
 	}
 }
@@ -1370,6 +1370,9 @@
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+		return -EROFS;
+
 	if (!blk_queue_discard(q))
 		return -EOPNOTSUPP;
 
@@ -2526,13 +2529,13 @@
 
 	rbm.rgd = rgd;
 	error = gfs2_rbm_from_block(&rbm, no_addr);
-	if (WARN_ON_ONCE(error))
-		goto fail;
-
-	if (gfs2_testbit(&rbm, false) != type)
-		error = -ESTALE;
+	if (!WARN_ON_ONCE(error)) {
+		if (gfs2_testbit(&rbm, false) != type)
+			error = -ESTALE;
+	}
 
 	gfs2_glock_dq_uninit(&rgd_gh);
+
 fail:
 	return error;
 }
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index b285192b..b3d951a 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -738,6 +738,7 @@
 	gfs2_jindex_free(sdp);
 	/*  Take apart glock structures and buffer lists  */
 	gfs2_gl_hash_clear(sdp);
+	truncate_inode_pages_final(&sdp->sd_aspace);
 	gfs2_delete_debugfs_file(sdp);
 	/*  Unmount the locking protocol  */
 	gfs2_lm_unmount(sdp);
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 02894df7..b53c055 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -482,6 +482,10 @@
 		current->files = work->identity->files;
 		current->nsproxy = work->identity->nsproxy;
 		task_unlock(current);
+		if (!work->identity->files) {
+			/* failed grabbing files, ensure work gets cancelled */
+			work->flags |= IO_WQ_WORK_CANCEL;
+		}
 	}
 	if ((work->flags & IO_WQ_WORK_FS) && current->fs != work->identity->fs)
 		current->fs = work->identity->fs;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index a7429c9..4ead291 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -995,20 +995,33 @@
 	if (mm) {
 		kthread_unuse_mm(mm);
 		mmput(mm);
+		current->mm = NULL;
 	}
 }
 
 static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx)
 {
-	if (!current->mm) {
-		if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL) ||
-			     !ctx->sqo_task->mm ||
-			     !mmget_not_zero(ctx->sqo_task->mm)))
-			return -EFAULT;
-		kthread_use_mm(ctx->sqo_task->mm);
+	struct mm_struct *mm;
+
+	if (current->mm)
+		return 0;
+
+	/* Should never happen */
+	if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL)))
+		return -EFAULT;
+
+	task_lock(ctx->sqo_task);
+	mm = ctx->sqo_task->mm;
+	if (unlikely(!mm || !mmget_not_zero(mm)))
+		mm = NULL;
+	task_unlock(ctx->sqo_task);
+
+	if (mm) {
+		kthread_use_mm(mm);
+		return 0;
 	}
 
-	return 0;
+	return -EFAULT;
 }
 
 static int io_sq_thread_acquire_mm(struct io_ring_ctx *ctx,
@@ -1274,9 +1287,12 @@
 	/* add one for this request */
 	refcount_inc(&id->count);
 
-	/* drop old identity, assign new one. one ref for req, one for tctx */
-	if (req->work.identity != tctx->identity &&
-	    refcount_sub_and_test(2, &req->work.identity->count))
+	/* drop tctx and req identity references, if needed */
+	if (tctx->identity != &tctx->__identity &&
+	    refcount_dec_and_test(&tctx->identity->count))
+		kfree(tctx->identity);
+	if (req->work.identity != &tctx->__identity &&
+	    refcount_dec_and_test(&req->work.identity->count))
 		kfree(req->work.identity);
 
 	req->work.identity = id;
@@ -1577,14 +1593,29 @@
 	}
 }
 
-static inline bool io_match_files(struct io_kiocb *req,
-				       struct files_struct *files)
+static inline bool __io_match_files(struct io_kiocb *req,
+				    struct files_struct *files)
 {
+	return ((req->flags & REQ_F_WORK_INITIALIZED) &&
+	        (req->work.flags & IO_WQ_WORK_FILES)) &&
+		req->work.identity->files == files;
+}
+
+static bool io_match_files(struct io_kiocb *req,
+			   struct files_struct *files)
+{
+	struct io_kiocb *link;
+
 	if (!files)
 		return true;
-	if ((req->flags & REQ_F_WORK_INITIALIZED) &&
-	    (req->work.flags & IO_WQ_WORK_FILES))
-		return req->work.identity->files == files;
+	if (__io_match_files(req, files))
+		return true;
+	if (req->flags & REQ_F_LINK_HEAD) {
+		list_for_each_entry(link, &req->link_list, link_list) {
+			if (__io_match_files(link, files))
+				return true;
+		}
+	}
 	return false;
 }
 
@@ -1668,7 +1699,8 @@
 		WRITE_ONCE(cqe->user_data, req->user_data);
 		WRITE_ONCE(cqe->res, res);
 		WRITE_ONCE(cqe->flags, cflags);
-	} else if (ctx->cq_overflow_flushed || req->task->io_uring->in_idle) {
+	} else if (ctx->cq_overflow_flushed ||
+		   atomic_read(&req->task->io_uring->in_idle)) {
 		/*
 		 * If we're in ring overflow flush mode, or in task cancel mode,
 		 * then we cannot store the request for later flushing, we need
@@ -1838,7 +1870,7 @@
 	io_dismantle_req(req);
 
 	percpu_counter_dec(&tctx->inflight);
-	if (tctx->in_idle)
+	if (atomic_read(&tctx->in_idle))
 		wake_up(&tctx->wait);
 	put_task_struct(req->task);
 
@@ -3515,8 +3547,7 @@
 	 * we return to userspace.
 	 */
 	if (req->flags & REQ_F_ISREG) {
-		__sb_start_write(file_inode(req->file)->i_sb,
-					SB_FREEZE_WRITE, true);
+		sb_start_write(file_inode(req->file)->i_sb);
 		__sb_writers_release(file_inode(req->file)->i_sb,
 					SB_FREEZE_WRITE);
 	}
@@ -7695,7 +7726,8 @@
 	xa_init(&tctx->xa);
 	init_waitqueue_head(&tctx->wait);
 	tctx->last = NULL;
-	tctx->in_idle = 0;
+	atomic_set(&tctx->in_idle, 0);
+	tctx->sqpoll = false;
 	io_init_identity(&tctx->__identity);
 	tctx->identity = &tctx->__identity;
 	task->io_uring = tctx;
@@ -8388,22 +8420,6 @@
 	return false;
 }
 
-static bool io_match_link_files(struct io_kiocb *req,
-				struct files_struct *files)
-{
-	struct io_kiocb *link;
-
-	if (io_match_files(req, files))
-		return true;
-	if (req->flags & REQ_F_LINK_HEAD) {
-		list_for_each_entry(link, &req->link_list, link_list) {
-			if (io_match_files(link, files))
-				return true;
-		}
-	}
-	return false;
-}
-
 /*
  * We're looking to cancel 'req' because it's holding on to our files, but
  * 'req' could be a link to another request. See if it is, and cancel that
@@ -8453,7 +8469,21 @@
 
 static bool io_cancel_link_cb(struct io_wq_work *work, void *data)
 {
-	return io_match_link(container_of(work, struct io_kiocb, work), data);
+	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+	bool ret;
+
+	if (req->flags & REQ_F_LINK_TIMEOUT) {
+		unsigned long flags;
+		struct io_ring_ctx *ctx = req->ctx;
+
+		/* protect against races with linked timeouts */
+		spin_lock_irqsave(&ctx->completion_lock, flags);
+		ret = io_match_link(req, data);
+		spin_unlock_irqrestore(&ctx->completion_lock, flags);
+	} else {
+		ret = io_match_link(req, data);
+	}
+	return ret;
 }
 
 static void io_attempt_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req)
@@ -8479,6 +8509,7 @@
 }
 
 static void io_cancel_defer_files(struct io_ring_ctx *ctx,
+				  struct task_struct *task,
 				  struct files_struct *files)
 {
 	struct io_defer_entry *de = NULL;
@@ -8486,7 +8517,8 @@
 
 	spin_lock_irq(&ctx->completion_lock);
 	list_for_each_entry_reverse(de, &ctx->defer_list, list) {
-		if (io_match_link_files(de->req, files)) {
+		if (io_task_match(de->req, task) &&
+		    io_match_files(de->req, files)) {
 			list_cut_position(&list, &ctx->defer_list, &de->list);
 			break;
 		}
@@ -8512,7 +8544,6 @@
 	if (list_empty_careful(&ctx->inflight_list))
 		return false;
 
-	io_cancel_defer_files(ctx, files);
 	/* cancel all at once, should be faster than doing it one by one*/
 	io_wq_cancel_cb(ctx->io_wq, io_wq_files_match, files, true);
 
@@ -8598,8 +8629,16 @@
 {
 	struct task_struct *task = current;
 
-	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data)
+	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
 		task = ctx->sq_data->thread;
+		atomic_inc(&task->io_uring->in_idle);
+		io_sq_thread_park(ctx->sq_data);
+	}
+
+	if (files)
+		io_cancel_defer_files(ctx, NULL, files);
+	else
+		io_cancel_defer_files(ctx, task, NULL);
 
 	io_cqring_overflow_flush(ctx, true, task, files);
 
@@ -8607,12 +8646,23 @@
 		io_run_task_work();
 		cond_resched();
 	}
+
+	if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
+		atomic_dec(&task->io_uring->in_idle);
+		/*
+		 * If the files that are going away are the ones in the thread
+		 * identity, clear them out.
+		 */
+		if (task->io_uring->identity->files == files)
+			task->io_uring->identity->files = NULL;
+		io_sq_thread_unpark(ctx->sq_data);
+	}
 }
 
 /*
  * Note that this task has used io_uring. We use it for cancelation purposes.
  */
-static int io_uring_add_task_file(struct file *file)
+static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
 {
 	struct io_uring_task *tctx = current->io_uring;
 
@@ -8634,6 +8684,14 @@
 		tctx->last = file;
 	}
 
+	/*
+	 * This is race safe in that the task itself is doing this, hence it
+	 * cannot be going through the exit/cancel paths at the same time.
+	 * This cannot be modified while exit/cancel is running.
+	 */
+	if (!tctx->sqpoll && (ctx->flags & IORING_SETUP_SQPOLL))
+		tctx->sqpoll = true;
+
 	return 0;
 }
 
@@ -8675,7 +8733,7 @@
 	unsigned long index;
 
 	/* make sure overflow events are dropped */
-	tctx->in_idle = true;
+	atomic_inc(&tctx->in_idle);
 
 	xa_for_each(&tctx->xa, index, file) {
 		struct io_ring_ctx *ctx = file->private_data;
@@ -8684,6 +8742,35 @@
 		if (files)
 			io_uring_del_task_file(file);
 	}
+
+	atomic_dec(&tctx->in_idle);
+}
+
+static s64 tctx_inflight(struct io_uring_task *tctx)
+{
+	unsigned long index;
+	struct file *file;
+	s64 inflight;
+
+	inflight = percpu_counter_sum(&tctx->inflight);
+	if (!tctx->sqpoll)
+		return inflight;
+
+	/*
+	 * If we have SQPOLL rings, then we need to iterate and find them, and
+	 * add the pending count for those.
+	 */
+	xa_for_each(&tctx->xa, index, file) {
+		struct io_ring_ctx *ctx = file->private_data;
+
+		if (ctx->flags & IORING_SETUP_SQPOLL) {
+			struct io_uring_task *__tctx = ctx->sqo_task->io_uring;
+
+			inflight += percpu_counter_sum(&__tctx->inflight);
+		}
+	}
+
+	return inflight;
 }
 
 /*
@@ -8697,11 +8784,11 @@
 	s64 inflight;
 
 	/* make sure overflow events are dropped */
-	tctx->in_idle = true;
+	atomic_inc(&tctx->in_idle);
 
 	do {
 		/* read completions before cancelations */
-		inflight = percpu_counter_sum(&tctx->inflight);
+		inflight = tctx_inflight(tctx);
 		if (!inflight)
 			break;
 		__io_uring_files_cancel(NULL);
@@ -8712,13 +8799,13 @@
 		 * If we've seen completions, retry. This avoids a race where
 		 * a completion comes in before we did prepare_to_wait().
 		 */
-		if (inflight != percpu_counter_sum(&tctx->inflight))
+		if (inflight != tctx_inflight(tctx))
 			continue;
 		schedule();
 	} while (1);
 
 	finish_wait(&tctx->wait, &wait);
-	tctx->in_idle = false;
+	atomic_dec(&tctx->in_idle);
 }
 
 static int io_uring_flush(struct file *file, void *data)
@@ -8863,7 +8950,7 @@
 			io_sqpoll_wait_sq(ctx);
 		submitted = to_submit;
 	} else if (to_submit) {
-		ret = io_uring_add_task_file(f.file);
+		ret = io_uring_add_task_file(ctx, f.file);
 		if (unlikely(ret))
 			goto out;
 		mutex_lock(&ctx->uring_lock);
@@ -8900,7 +8987,8 @@
 #ifdef CONFIG_PROC_FS
 static int io_uring_show_cred(int id, void *p, void *data)
 {
-	const struct cred *cred = p;
+	struct io_identity *iod = p;
+	const struct cred *cred = iod->creds;
 	struct seq_file *m = data;
 	struct user_namespace *uns = seq_user_ns(m);
 	struct group_info *gi;
@@ -9092,7 +9180,7 @@
 #if defined(CONFIG_UNIX)
 	ctx->ring_sock->file = file;
 #endif
-	if (unlikely(io_uring_add_task_file(file))) {
+	if (unlikely(io_uring_add_task_file(ctx, file))) {
 		file = ERR_PTR(-ENOMEM);
 		goto err_fd;
 	}
@@ -9137,6 +9225,7 @@
 		 * to a power-of-two, if it isn't already. We do NOT impose
 		 * any cq vs sq ring sizing.
 		 */
+		p->cq_entries = roundup_pow_of_two(p->cq_entries);
 		if (p->cq_entries < p->sq_entries)
 			return -EINVAL;
 		if (p->cq_entries > IORING_MAX_CQ_ENTRIES) {
@@ -9144,7 +9233,6 @@
 				return -EINVAL;
 			p->cq_entries = IORING_MAX_CQ_ENTRIES;
 		}
-		p->cq_entries = roundup_pow_of_two(p->cq_entries);
 	} else {
 		p->cq_entries = 2 * p->sq_entries;
 	}
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 8180061..10cc797 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1374,6 +1374,7 @@
 	WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list));
 	WARN_ON_ONCE(!PageLocked(page));
 	WARN_ON_ONCE(PageWriteback(page));
+	WARN_ON_ONCE(PageDirty(page));
 
 	/*
 	 * We cannot cancel the ioend directly here on error.  We may have
@@ -1382,33 +1383,22 @@
 	 * appropriately.
 	 */
 	if (unlikely(error)) {
+		/*
+		 * Let the filesystem know what portion of the current page
+		 * failed to map. If the page wasn't been added to ioend, it
+		 * won't be affected by I/O completion and we must unlock it
+		 * now.
+		 */
+		if (wpc->ops->discard_page)
+			wpc->ops->discard_page(page, file_offset);
 		if (!count) {
-			/*
-			 * If the current page hasn't been added to ioend, it
-			 * won't be affected by I/O completions and we must
-			 * discard and unlock it right here.
-			 */
-			if (wpc->ops->discard_page)
-				wpc->ops->discard_page(page);
 			ClearPageUptodate(page);
 			unlock_page(page);
 			goto done;
 		}
-
-		/*
-		 * If the page was not fully cleaned, we need to ensure that the
-		 * higher layers come back to it correctly.  That means we need
-		 * to keep the page dirty, and for WB_SYNC_ALL writeback we need
-		 * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed
-		 * so another attempt to write this page in this writeback sweep
-		 * will be made.
-		 */
-		set_page_writeback_keepwrite(page);
-	} else {
-		clear_page_dirty_for_io(page);
-		set_page_writeback(page);
 	}
 
+	set_page_writeback(page);
 	unlock_page(page);
 
 	/*
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 263f02a..472932b 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -106,6 +106,8 @@
  * for a checkpoint to free up some space in the log.
  */
 void __jbd2_log_wait_for_space(journal_t *journal)
+__acquires(&journal->j_state_lock)
+__releases(&journal->j_state_lock)
 {
 	int nblocks, space_left;
 	/* assert_spin_locked(&journal->j_state_lock); */
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index fa688e1..b121d7d 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -450,6 +450,15 @@
 		schedule();
 		write_lock(&journal->j_state_lock);
 		finish_wait(&journal->j_fc_wait, &wait);
+		/*
+		 * TODO: by blocking fast commits here, we are increasing
+		 * fsync() latency slightly. Strictly speaking, we don't need
+		 * to block fast commits until the transaction enters T_FLUSH
+		 * state. So an optimization is possible where we block new fast
+		 * commits here and wait for existing ones to complete
+		 * just before we enter T_FLUSH. That way, the existing fast
+		 * commits and this full commit can proceed parallely.
+		 */
 	}
 	write_unlock(&journal->j_state_lock);
 
@@ -801,7 +810,7 @@
 		if (first_block < journal->j_tail)
 			freed += journal->j_last - journal->j_first;
 		/* Update tail only if we free significant amount of space */
-		if (freed < journal->j_maxlen / 4)
+		if (freed < jbd2_journal_get_max_txn_bufs(journal))
 			update_tail = 0;
 	}
 	J_ASSERT(commit_transaction->t_state == T_COMMIT);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 0c7c42b..0c3d5e3 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -727,6 +727,8 @@
  */
 int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
 {
+	if (unlikely(is_journal_aborted(journal)))
+		return -EIO;
 	/*
 	 * Fast commits only allowed if at least one full commit has
 	 * been processed.
@@ -734,10 +736,12 @@
 	if (!journal->j_stats.ts_tid)
 		return -EINVAL;
 
-	if (tid <= journal->j_commit_sequence)
-		return -EALREADY;
-
 	write_lock(&journal->j_state_lock);
+	if (tid <= journal->j_commit_sequence) {
+		write_unlock(&journal->j_state_lock);
+		return -EALREADY;
+	}
+
 	if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
 	    (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) {
 		DEFINE_WAIT(wait);
@@ -777,13 +781,19 @@
 
 int jbd2_fc_end_commit(journal_t *journal)
 {
-	return __jbd2_fc_end_commit(journal, 0, 0);
+	return __jbd2_fc_end_commit(journal, 0, false);
 }
 EXPORT_SYMBOL(jbd2_fc_end_commit);
 
-int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid)
+int jbd2_fc_end_commit_fallback(journal_t *journal)
 {
-	return __jbd2_fc_end_commit(journal, tid, 1);
+	tid_t tid;
+
+	read_lock(&journal->j_state_lock);
+	tid = journal->j_running_transaction ?
+		journal->j_running_transaction->t_tid : 0;
+	read_unlock(&journal->j_state_lock);
+	return __jbd2_fc_end_commit(journal, tid, true);
 }
 EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);
 
@@ -865,7 +875,6 @@
 	int fc_off;
 
 	*bh_out = NULL;
-	write_lock(&journal->j_state_lock);
 
 	if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
 		fc_off = journal->j_fc_off;
@@ -874,7 +883,6 @@
 	} else {
 		ret = -EINVAL;
 	}
-	write_unlock(&journal->j_state_lock);
 
 	if (ret)
 		return ret;
@@ -887,11 +895,7 @@
 	if (!bh)
 		return -ENOMEM;
 
-	lock_buffer(bh);
 
-	clear_buffer_uptodate(bh);
-	set_buffer_dirty(bh);
-	unlock_buffer(bh);
 	journal->j_fc_wbuf[fc_off] = bh;
 
 	*bh_out = bh;
@@ -909,9 +913,7 @@
 	struct buffer_head *bh;
 	int i, j_fc_off;
 
-	read_lock(&journal->j_state_lock);
 	j_fc_off = journal->j_fc_off;
-	read_unlock(&journal->j_state_lock);
 
 	/*
 	 * Wait in reverse order to minimize chances of us being woken up before
@@ -939,9 +941,7 @@
 	struct buffer_head *bh;
 	int i, j_fc_off;
 
-	read_lock(&journal->j_state_lock);
 	j_fc_off = journal->j_fc_off;
-	read_unlock(&journal->j_state_lock);
 
 	/*
 	 * Wait in reverse order to minimize chances of us being woken up before
@@ -1348,23 +1348,16 @@
 	journal->j_dev = bdev;
 	journal->j_fs_dev = fs_dev;
 	journal->j_blk_offset = start;
-	journal->j_maxlen = len;
+	journal->j_total_len = len;
 	/* We need enough buffers to write out full descriptor block. */
 	n = journal->j_blocksize / jbd2_min_tag_size();
 	journal->j_wbufsize = n;
+	journal->j_fc_wbuf = NULL;
 	journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *),
 					GFP_KERNEL);
 	if (!journal->j_wbuf)
 		goto err_cleanup;
 
-	if (journal->j_fc_wbufsize > 0) {
-		journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
-					sizeof(struct buffer_head *),
-					GFP_KERNEL);
-		if (!journal->j_fc_wbuf)
-			goto err_cleanup;
-	}
-
 	bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize);
 	if (!bh) {
 		pr_err("%s: Cannot get buffer for journal superblock\n",
@@ -1378,23 +1371,11 @@
 
 err_cleanup:
 	kfree(journal->j_wbuf);
-	kfree(journal->j_fc_wbuf);
 	jbd2_journal_destroy_revoke(journal);
 	kfree(journal);
 	return NULL;
 }
 
-int jbd2_fc_init(journal_t *journal, int num_fc_blks)
-{
-	journal->j_fc_wbufsize = num_fc_blks;
-	journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
-				sizeof(struct buffer_head *), GFP_KERNEL);
-	if (!journal->j_fc_wbuf)
-		return -ENOMEM;
-	return 0;
-}
-EXPORT_SYMBOL(jbd2_fc_init);
-
 /* jbd2_journal_init_dev and jbd2_journal_init_inode:
  *
  * Create a journal structure assigned some fixed set of disk blocks to
@@ -1512,16 +1493,7 @@
 	}
 
 	journal->j_first = first;
-
-	if (jbd2_has_feature_fast_commit(journal) &&
-	    journal->j_fc_wbufsize > 0) {
-		journal->j_fc_last = last;
-		journal->j_last = last - journal->j_fc_wbufsize;
-		journal->j_fc_first = journal->j_last + 1;
-		journal->j_fc_off = 0;
-	} else {
-		journal->j_last = last;
-	}
+	journal->j_last = last;
 
 	journal->j_head = journal->j_first;
 	journal->j_tail = journal->j_first;
@@ -1531,7 +1503,14 @@
 	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
 	journal->j_commit_request = journal->j_commit_sequence;
 
-	journal->j_max_transaction_buffers = journal->j_maxlen / 4;
+	journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal);
+
+	/*
+	 * Now that journal recovery is done, turn fast commits off here. This
+	 * way, if fast commit was enabled before the crash but if now FS has
+	 * disabled it, we don't enable fast commits.
+	 */
+	jbd2_clear_feature_fast_commit(journal);
 
 	/*
 	 * As a special case, if the on-disk copy is already marked as needing
@@ -1792,15 +1771,15 @@
 		goto out;
 	}
 
-	if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
-		journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
-	else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
+	if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len)
+		journal->j_total_len = be32_to_cpu(sb->s_maxlen);
+	else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) {
 		printk(KERN_WARNING "JBD2: journal file too short\n");
 		goto out;
 	}
 
 	if (be32_to_cpu(sb->s_first) == 0 ||
-	    be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+	    be32_to_cpu(sb->s_first) >= journal->j_total_len) {
 		printk(KERN_WARNING
 			"JBD2: Invalid start block of journal: %u\n",
 			be32_to_cpu(sb->s_first));
@@ -1872,6 +1851,7 @@
 {
 	int err;
 	journal_superblock_t *sb;
+	int num_fc_blocks;
 
 	err = journal_get_superblock(journal);
 	if (err)
@@ -1883,15 +1863,17 @@
 	journal->j_tail = be32_to_cpu(sb->s_start);
 	journal->j_first = be32_to_cpu(sb->s_first);
 	journal->j_errno = be32_to_cpu(sb->s_errno);
+	journal->j_last = be32_to_cpu(sb->s_maxlen);
 
-	if (jbd2_has_feature_fast_commit(journal) &&
-	    journal->j_fc_wbufsize > 0) {
+	if (jbd2_has_feature_fast_commit(journal)) {
 		journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
-		journal->j_last = journal->j_fc_last - journal->j_fc_wbufsize;
+		num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks);
+		if (!num_fc_blocks)
+			num_fc_blocks = JBD2_MIN_FC_BLOCKS;
+		if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS)
+			journal->j_last = journal->j_fc_last - num_fc_blocks;
 		journal->j_fc_first = journal->j_last + 1;
 		journal->j_fc_off = 0;
-	} else {
-		journal->j_last = be32_to_cpu(sb->s_maxlen);
 	}
 
 	return 0;
@@ -1954,9 +1936,6 @@
 	 */
 	journal->j_flags &= ~JBD2_ABORT;
 
-	if (journal->j_fc_wbufsize > 0)
-		jbd2_journal_set_features(journal, 0, 0,
-					  JBD2_FEATURE_INCOMPAT_FAST_COMMIT);
 	/* OK, we've finished with the dynamic journal bits:
 	 * reinitialise the dynamic contents of the superblock in memory
 	 * and reset them on disk. */
@@ -2040,8 +2019,7 @@
 		jbd2_journal_destroy_revoke(journal);
 	if (journal->j_chksum_driver)
 		crypto_free_shash(journal->j_chksum_driver);
-	if (journal->j_fc_wbufsize > 0)
-		kfree(journal->j_fc_wbuf);
+	kfree(journal->j_fc_wbuf);
 	kfree(journal->j_wbuf);
 	kfree(journal);
 
@@ -2116,6 +2094,37 @@
 	return 0;
 }
 
+static int
+jbd2_journal_initialize_fast_commit(journal_t *journal)
+{
+	journal_superblock_t *sb = journal->j_superblock;
+	unsigned long long num_fc_blks;
+
+	num_fc_blks = be32_to_cpu(sb->s_num_fc_blks);
+	if (num_fc_blks == 0)
+		num_fc_blks = JBD2_MIN_FC_BLOCKS;
+	if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS)
+		return -ENOSPC;
+
+	/* Are we called twice? */
+	WARN_ON(journal->j_fc_wbuf != NULL);
+	journal->j_fc_wbuf = kmalloc_array(num_fc_blks,
+				sizeof(struct buffer_head *), GFP_KERNEL);
+	if (!journal->j_fc_wbuf)
+		return -ENOMEM;
+
+	journal->j_fc_wbufsize = num_fc_blks;
+	journal->j_fc_last = journal->j_last;
+	journal->j_last = journal->j_fc_last - num_fc_blks;
+	journal->j_fc_first = journal->j_last + 1;
+	journal->j_fc_off = 0;
+	journal->j_free = journal->j_last - journal->j_first;
+	journal->j_max_transaction_buffers =
+		jbd2_journal_get_max_txn_bufs(journal);
+
+	return 0;
+}
+
 /**
  * int jbd2_journal_set_features() - Mark a given journal feature in the superblock
  * @journal: Journal to act on.
@@ -2159,6 +2168,13 @@
 
 	sb = journal->j_superblock;
 
+	if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) {
+		if (jbd2_journal_initialize_fast_commit(journal)) {
+			pr_err("JBD2: Cannot enable fast commits.\n");
+			return 0;
+		}
+	}
+
 	/* Load the checksum driver if necessary */
 	if ((journal->j_chksum_driver == NULL) &&
 	    INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index eb26061..dc0694f 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -74,8 +74,8 @@
 
 	/* Do up to 128K of readahead */
 	max = start + (128 * 1024 / journal->j_blocksize);
-	if (max > journal->j_maxlen)
-		max = journal->j_maxlen;
+	if (max > journal->j_total_len)
+		max = journal->j_total_len;
 
 	/* Do the readahead itself.  We'll submit MAXBUF buffer_heads at
 	 * a time to the block device IO layer. */
@@ -134,7 +134,7 @@
 
 	*bhp = NULL;
 
-	if (offset >= journal->j_maxlen) {
+	if (offset >= journal->j_total_len) {
 		printk(KERN_ERR "JBD2: corrupted journal superblock\n");
 		return -EFSCORRUPTED;
 	}
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 4398573..d54f046 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -195,8 +195,10 @@
 	DEFINE_WAIT(wait);
 
 	if (WARN_ON(!journal->j_running_transaction ||
-		    journal->j_running_transaction->t_state != T_SWITCH))
+		    journal->j_running_transaction->t_state != T_SWITCH)) {
+		read_unlock(&journal->j_state_lock);
 		return;
+	}
 	prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
 			TASK_UNINTERRUPTIBLE);
 	read_unlock(&journal->j_state_lock);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index cb52db9..4e011ad 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -955,7 +955,6 @@
 
 static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 {
-	struct inode *inode = file_inode(filp);
 	struct nfs_open_dir_context *dir_ctx = filp->private_data;
 
 	dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n",
@@ -967,15 +966,15 @@
 	case SEEK_SET:
 		if (offset < 0)
 			return -EINVAL;
-		inode_lock(inode);
+		spin_lock(&filp->f_lock);
 		break;
 	case SEEK_CUR:
 		if (offset == 0)
 			return filp->f_pos;
-		inode_lock(inode);
+		spin_lock(&filp->f_lock);
 		offset += filp->f_pos;
 		if (offset < 0) {
-			inode_unlock(inode);
+			spin_unlock(&filp->f_lock);
 			return -EINVAL;
 		}
 	}
@@ -987,7 +986,7 @@
 			dir_ctx->dir_cookie = 0;
 		dir_ctx->duped = 0;
 	}
-	inode_unlock(inode);
+	spin_unlock(&filp->f_lock);
 	return offset;
 }
 
@@ -998,13 +997,9 @@
 static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end,
 			 int datasync)
 {
-	struct inode *inode = file_inode(filp);
-
 	dfprintk(FILE, "NFS: fsync dir(%pD2) datasync %d\n", filp, datasync);
 
-	inode_lock(inode);
-	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
-	inode_unlock(inode);
+	nfs_inc_stats(file_inode(filp), NFSIOS_VFSFSYNC);
 	return 0;
 }
 
diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c
index b51424f..6c2ce79 100644
--- a/fs/nfs/nfs42xattr.c
+++ b/fs/nfs/nfs42xattr.c
@@ -1047,8 +1047,10 @@
 
 void nfs4_xattr_cache_exit(void)
 {
+	unregister_shrinker(&nfs4_xattr_large_entry_shrinker);
 	unregister_shrinker(&nfs4_xattr_entry_shrinker);
 	unregister_shrinker(&nfs4_xattr_cache_shrinker);
+	list_lru_destroy(&nfs4_xattr_large_entry_lru);
 	list_lru_destroy(&nfs4_xattr_entry_lru);
 	list_lru_destroy(&nfs4_xattr_cache_lru);
 	kmem_cache_destroy(nfs4_xattr_cache_cachep);
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 0dc31ad..6e060a8 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -196,7 +196,7 @@
 				 1 + nfs4_xattr_name_maxsz + 1)
 #define decode_setxattr_maxsz   (op_decode_hdr_maxsz + decode_change_info_maxsz)
 #define encode_listxattrs_maxsz  (op_encode_hdr_maxsz + 2 + 1)
-#define decode_listxattrs_maxsz  (op_decode_hdr_maxsz + 2 + 1 + 1)
+#define decode_listxattrs_maxsz  (op_decode_hdr_maxsz + 2 + 1 + 1 + 1)
 #define encode_removexattr_maxsz (op_encode_hdr_maxsz + 1 + \
 				  nfs4_xattr_name_maxsz)
 #define decode_removexattr_maxsz (op_decode_hdr_maxsz + \
@@ -531,7 +531,7 @@
 {
 	__be32 *p;
 
-	encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz + 1, hdr);
+	encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz, hdr);
 
 	p = reserve_space(xdr, 12);
 	if (unlikely(!p))
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index 8d32788..fa14830 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -88,7 +88,13 @@
 #define NFS_ROOT		"/tftpboot/%s"
 
 /* Default NFSROOT mount options. */
+#if defined(CONFIG_NFS_V2)
 #define NFS_DEF_OPTIONS		"vers=2,tcp,rsize=4096,wsize=4096"
+#elif defined(CONFIG_NFS_V3)
+#define NFS_DEF_OPTIONS		"vers=3,tcp,rsize=4096,wsize=4096"
+#else
+#define NFS_DEF_OPTIONS		"vers=4,tcp,rsize=4096,wsize=4096"
+#endif
 
 /* Parameters passed from the kernel command line */
 static char nfs_root_parms[NFS_MAXPATHLEN + 1] __initdata = "";
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 1446861..a633044 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -316,10 +316,6 @@
 	fh_copy(&resp->dirfh, &argp->fh);
 	fh_init(&resp->fh, NFS3_FHSIZE);
 
-	if (argp->ftype == 0 || argp->ftype >= NF3BAD) {
-		resp->status = nfserr_inval;
-		goto out;
-	}
 	if (argp->ftype == NF3CHR || argp->ftype == NF3BLK) {
 		rdev = MKDEV(argp->major, argp->minor);
 		if (MAJOR(rdev) != argp->major ||
@@ -328,7 +324,7 @@
 			goto out;
 		}
 	} else if (argp->ftype != NF3SOCK && argp->ftype != NF3FIFO) {
-		resp->status = nfserr_inval;
+		resp->status = nfserr_badtype;
 		goto out;
 	}
 
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 9c23b6a..2277f83 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -1114,6 +1114,7 @@
 {
 	struct nfsd3_pathconfres *resp = rqstp->rq_resp;
 
+	*p++ = resp->status;
 	*p++ = xdr_zero;	/* no post_op_attr */
 
 	if (resp->status == 0) {
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index ad2fa1a..e83b217 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1299,7 +1299,7 @@
 			struct nfsd_file *dst)
 {
 	nfs42_ssc_close(src->nf_file);
-	nfsd_file_put(src);
+	/* 'src' is freed by nfsd4_do_async_copy */
 	nfsd_file_put(dst);
 	mntput(ss_mnt);
 }
@@ -1486,6 +1486,7 @@
 	cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
 	if (!cb_copy)
 		goto out;
+	refcount_set(&cb_copy->refcount, 1);
 	memcpy(&cb_copy->cp_res, &copy->cp_res, sizeof(copy->cp_res));
 	cb_copy->cp_clp = copy->cp_clp;
 	cb_copy->nfserr = copy->nfserr;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index b9a9d69..db52e84 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -877,7 +877,7 @@
 		goto done;
 	}
 
-	trace_ocfs2_journal_init_maxlen(j_journal->j_maxlen);
+	trace_ocfs2_journal_init_maxlen(j_journal->j_total_len);
 
 	*dirty = (le32_to_cpu(di->id1.journal1.ij_flags) &
 		  OCFS2_JOURNAL_DIRTY_FL);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 1d91dd1..2febc76 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1713,6 +1713,7 @@
 
 	oi->ip_blkno = 0ULL;
 	oi->ip_clusters = 0;
+	oi->ip_next_orphan = NULL;
 
 	ocfs2_resv_init_once(&oi->ip_la_data_resv);
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 0f70700..b362523 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1049,6 +1049,8 @@
 		oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
 			  OOM_SCORE_ADJ_MAX;
 	put_task_struct(task);
+	if (oom_adj > OOM_ADJUST_MAX)
+		oom_adj = OOM_ADJUST_MAX;
 	len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
 	return simple_read_from_buffer(buf, count, ppos, buffer, len);
 }
diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c
index d0989a4..419760f 100644
--- a/fs/proc/cpuinfo.c
+++ b/fs/proc/cpuinfo.c
@@ -19,7 +19,7 @@
 static const struct proc_ops cpuinfo_proc_ops = {
 	.proc_flags	= PROC_ENTRY_PERMANENT,
 	.proc_open	= cpuinfo_open,
-	.proc_read	= seq_read,
+	.proc_read_iter	= seq_read_iter,
 	.proc_lseek	= seq_lseek,
 	.proc_release	= seq_release,
 };
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 2f9fa17..b846632 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -590,7 +590,7 @@
 static const struct proc_ops proc_seq_ops = {
 	/* not permanent -- can call into arbitrary seq_operations */
 	.proc_open	= proc_seq_open,
-	.proc_read	= seq_read,
+	.proc_read_iter	= seq_read_iter,
 	.proc_lseek	= seq_lseek,
 	.proc_release	= proc_seq_release,
 };
@@ -621,7 +621,7 @@
 static const struct proc_ops proc_single_ops = {
 	/* not permanent -- can call into arbitrary ->single_show */
 	.proc_open	= proc_single_open,
-	.proc_read	= seq_read,
+	.proc_read_iter = seq_read_iter,
 	.proc_lseek	= seq_lseek,
 	.proc_release	= single_release,
 };
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 58c075e..bde6b6f 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -597,6 +597,7 @@
 	.llseek		= proc_reg_llseek,
 	.read_iter	= proc_reg_read_iter,
 	.write		= proc_reg_write,
+	.splice_read	= generic_file_splice_read,
 	.poll		= proc_reg_poll,
 	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
 	.mmap		= proc_reg_mmap,
@@ -622,6 +623,7 @@
 static const struct file_operations proc_iter_file_ops_compat = {
 	.llseek		= proc_reg_llseek,
 	.read_iter	= proc_reg_read_iter,
+	.splice_read	= generic_file_splice_read,
 	.write		= proc_reg_write,
 	.poll		= proc_reg_poll,
 	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 46b3293..4695b6d 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -226,7 +226,7 @@
 static const struct proc_ops stat_proc_ops = {
 	.proc_flags	= PROC_ENTRY_PERMANENT,
 	.proc_open	= stat_open,
-	.proc_read	= seq_read,
+	.proc_read_iter	= seq_read_iter,
 	.proc_lseek	= seq_lseek,
 	.proc_release	= single_release,
 };
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 31219c1..3b20e21 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -18,6 +18,7 @@
 #include <linux/mm.h>
 #include <linux/printk.h>
 #include <linux/string_helpers.h>
+#include <linux/uio.h>
 
 #include <linux/uaccess.h>
 #include <asm/page.h>
@@ -146,7 +147,28 @@
  */
 ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 {
-	struct seq_file *m = file->private_data;
+	struct iovec iov = { .iov_base = buf, .iov_len = size};
+	struct kiocb kiocb;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	init_sync_kiocb(&kiocb, file);
+	iov_iter_init(&iter, READ, &iov, 1, size);
+
+	kiocb.ki_pos = *ppos;
+	ret = seq_read_iter(&kiocb, &iter);
+	*ppos = kiocb.ki_pos;
+	return ret;
+}
+EXPORT_SYMBOL(seq_read);
+
+/*
+ * Ready-made ->f_op->read_iter()
+ */
+ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct seq_file *m = iocb->ki_filp->private_data;
+	size_t size = iov_iter_count(iter);
 	size_t copied = 0;
 	size_t n;
 	void *p;
@@ -158,14 +180,14 @@
 	 * if request is to read from zero offset, reset iterator to first
 	 * record as it might have been already advanced by previous requests
 	 */
-	if (*ppos == 0) {
+	if (iocb->ki_pos == 0) {
 		m->index = 0;
 		m->count = 0;
 	}
 
-	/* Don't assume *ppos is where we left it */
-	if (unlikely(*ppos != m->read_pos)) {
-		while ((err = traverse(m, *ppos)) == -EAGAIN)
+	/* Don't assume ki_pos is where we left it */
+	if (unlikely(iocb->ki_pos != m->read_pos)) {
+		while ((err = traverse(m, iocb->ki_pos)) == -EAGAIN)
 			;
 		if (err) {
 			/* With prejudice... */
@@ -174,7 +196,7 @@
 			m->count = 0;
 			goto Done;
 		} else {
-			m->read_pos = *ppos;
+			m->read_pos = iocb->ki_pos;
 		}
 	}
 
@@ -187,13 +209,11 @@
 	/* if not empty - flush it first */
 	if (m->count) {
 		n = min(m->count, size);
-		err = copy_to_user(buf, m->buf + m->from, n);
-		if (err)
+		if (copy_to_iter(m->buf + m->from, n, iter) != n)
 			goto Efault;
 		m->count -= n;
 		m->from += n;
 		size -= n;
-		buf += n;
 		copied += n;
 		if (!size)
 			goto Done;
@@ -254,8 +274,7 @@
 	}
 	m->op->stop(m, p);
 	n = min(m->count, size);
-	err = copy_to_user(buf, m->buf, n);
-	if (err)
+	if (copy_to_iter(m->buf, n, iter) != n)
 		goto Efault;
 	copied += n;
 	m->count -= n;
@@ -264,7 +283,7 @@
 	if (!copied)
 		copied = err;
 	else {
-		*ppos += copied;
+		iocb->ki_pos += copied;
 		m->read_pos += copied;
 	}
 	mutex_unlock(&m->lock);
@@ -276,7 +295,7 @@
 	err = -EFAULT;
 	goto Done;
 }
-EXPORT_SYMBOL(seq_read);
+EXPORT_SYMBOL(seq_read_iter);
 
 /**
  *	seq_lseek -	->llseek() method for sequential files.
diff --git a/fs/super.c b/fs/super.c
index a51c208..98bb062 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1631,55 +1631,6 @@
 }
 EXPORT_SYMBOL(super_setup_bdi);
 
-/*
- * This is an internal function, please use sb_end_{write,pagefault,intwrite}
- * instead.
- */
-void __sb_end_write(struct super_block *sb, int level)
-{
-	percpu_up_read(sb->s_writers.rw_sem + level-1);
-}
-EXPORT_SYMBOL(__sb_end_write);
-
-/*
- * This is an internal function, please use sb_start_{write,pagefault,intwrite}
- * instead.
- */
-int __sb_start_write(struct super_block *sb, int level, bool wait)
-{
-	bool force_trylock = false;
-	int ret = 1;
-
-#ifdef CONFIG_LOCKDEP
-	/*
-	 * We want lockdep to tell us about possible deadlocks with freezing
-	 * but it's it bit tricky to properly instrument it. Getting a freeze
-	 * protection works as getting a read lock but there are subtle
-	 * problems. XFS for example gets freeze protection on internal level
-	 * twice in some cases, which is OK only because we already hold a
-	 * freeze protection also on higher level. Due to these cases we have
-	 * to use wait == F (trylock mode) which must not fail.
-	 */
-	if (wait) {
-		int i;
-
-		for (i = 0; i < level - 1; i++)
-			if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) {
-				force_trylock = true;
-				break;
-			}
-	}
-#endif
-	if (wait && !force_trylock)
-		percpu_down_read(sb->s_writers.rw_sem + level-1);
-	else
-		ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1);
-
-	WARN_ON(force_trylock && !ret);
-	return ret;
-}
-EXPORT_SYMBOL(__sb_start_write);
-
 /**
  * sb_wait_write - wait until all writers to given file system finish
  * @sb: the super for which we wait
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 852b536..1564001 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2467,6 +2467,7 @@
 	new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
 	new->xefi_blockcount = 1;
 	new->xefi_oinfo = *oinfo;
+	new->xefi_skip_discard = false;
 
 	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
 
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index e1bd484..6747e97 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -52,9 +52,9 @@
 {
 	xfs_fsblock_t		xefi_startblock;/* starting fs block number */
 	xfs_extlen_t		xefi_blockcount;/* number of blocks in extent */
+	bool			xefi_skip_discard;
 	struct list_head	xefi_list;
 	struct xfs_owner_info	xefi_oinfo;	/* extent owner */
-	bool			xefi_skip_discard;
 };
 
 #define	XFS_BMAP_MAX_NMAP	4
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 340c83f..2668ebe 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -1514,7 +1514,7 @@
 	 * record for our insertion point. This will also give us the record for
 	 * start block contiguity tests.
 	 */
-	error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags,
+	error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, oldext,
 			&PREV, &i);
 	if (error)
 		goto done;
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index beb81c8..577a663 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -243,8 +243,8 @@
 	else if (y > x)
 		return -1;
 
-	x = XFS_RMAP_OFF(be64_to_cpu(kp->rm_offset));
-	y = rec->rm_offset;
+	x = be64_to_cpu(kp->rm_offset);
+	y = xfs_rmap_irec_offset_pack(rec);
 	if (x > y)
 		return 1;
 	else if (y > x)
@@ -275,8 +275,8 @@
 	else if (y > x)
 		return -1;
 
-	x = XFS_RMAP_OFF(be64_to_cpu(kp1->rm_offset));
-	y = XFS_RMAP_OFF(be64_to_cpu(kp2->rm_offset));
+	x = be64_to_cpu(kp1->rm_offset);
+	y = be64_to_cpu(kp2->rm_offset);
 	if (x > y)
 		return 1;
 	else if (y > x)
@@ -390,8 +390,8 @@
 		return 1;
 	else if (a > b)
 		return 0;
-	a = XFS_RMAP_OFF(be64_to_cpu(k1->rmap.rm_offset));
-	b = XFS_RMAP_OFF(be64_to_cpu(k2->rmap.rm_offset));
+	a = be64_to_cpu(k1->rmap.rm_offset);
+	b = be64_to_cpu(k2->rmap.rm_offset);
 	if (a <= b)
 		return 1;
 	return 0;
@@ -420,8 +420,8 @@
 		return 1;
 	else if (a > b)
 		return 0;
-	a = XFS_RMAP_OFF(be64_to_cpu(r1->rmap.rm_offset));
-	b = XFS_RMAP_OFF(be64_to_cpu(r2->rmap.rm_offset));
+	a = be64_to_cpu(r1->rmap.rm_offset);
+	b = be64_to_cpu(r2->rmap.rm_offset);
 	if (a <= b)
 		return 1;
 	return 0;
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 955302e..412e2ec 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -113,6 +113,8 @@
 
 	if (info->whichfork == XFS_ATTR_FORK)
 		rflags |= XFS_RMAP_ATTR_FORK;
+	if (irec->br_state == XFS_EXT_UNWRITTEN)
+		rflags |= XFS_RMAP_UNWRITTEN;
 
 	/*
 	 * CoW staging extents are owned (on disk) by the refcountbt, so
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 3aa85b6..bb25ff1 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -121,8 +121,7 @@
 		goto bad;
 
 	/* rt flags require rt device */
-	if ((flags & (XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT)) &&
-	    !mp->m_rtdev_targp)
+	if ((flags & XFS_DIFLAG_REALTIME) && !mp->m_rtdev_targp)
 		goto bad;
 
 	/* new rt bitmap flag only valid for rbmino */
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index beaeb6f..dd672e6 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -170,7 +170,6 @@
 	 */
 	INIT_LIST_HEAD(&worklist);
 	rbno = NULLAGBLOCK;
-	nr = 1;
 
 	/* Make sure the fragments actually /are/ in agbno order. */
 	bno = 0;
@@ -184,15 +183,14 @@
 	 * Find all the rmaps that start at or before the refc extent,
 	 * and put them on the worklist.
 	 */
+	nr = 0;
 	list_for_each_entry_safe(frag, n, &refchk->fragments, list) {
-		if (frag->rm.rm_startblock > refchk->bno)
-			goto done;
+		if (frag->rm.rm_startblock > refchk->bno || nr > target_nr)
+			break;
 		bno = frag->rm.rm_startblock + frag->rm.rm_blockcount;
 		if (bno < rbno)
 			rbno = bno;
 		list_move_tail(&frag->list, &worklist);
-		if (nr == target_nr)
-			break;
 		nr++;
 	}
 
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 55d126d..4304c64 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -346,8 +346,8 @@
 	ssize_t			count = i_blocksize(inode);
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
-	xfs_fileoff_t		cow_fsb = NULLFILEOFF;
-	int			whichfork = XFS_DATA_FORK;
+	xfs_fileoff_t		cow_fsb;
+	int			whichfork;
 	struct xfs_bmbt_irec	imap;
 	struct xfs_iext_cursor	icur;
 	int			retries = 0;
@@ -381,6 +381,8 @@
 	 * landed in a hole and we skip the block.
 	 */
 retry:
+	cow_fsb = NULLFILEOFF;
+	whichfork = XFS_DATA_FORK;
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
@@ -527,13 +529,15 @@
  */
 static void
 xfs_discard_page(
-	struct page		*page)
+	struct page		*page,
+	loff_t			fileoff)
 {
 	struct inode		*inode = page->mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	loff_t			offset = page_offset(page);
-	xfs_fileoff_t		start_fsb = XFS_B_TO_FSBT(mp, offset);
+	unsigned int		pageoff = offset_in_page(fileoff);
+	xfs_fileoff_t		start_fsb = XFS_B_TO_FSBT(mp, fileoff);
+	xfs_fileoff_t		pageoff_fsb = XFS_B_TO_FSBT(mp, pageoff);
 	int			error;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -541,14 +545,14 @@
 
 	xfs_alert_ratelimited(mp,
 		"page discard on page "PTR_FMT", inode 0x%llx, offset %llu.",
-			page, ip->i_ino, offset);
+			page, ip->i_ino, fileoff);
 
 	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
-			i_blocks_per_page(inode, page));
+			i_blocks_per_page(inode, page) - pageoff_fsb);
 	if (error && !XFS_FORCED_SHUTDOWN(mp))
 		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:
-	iomap_invalidatepage(page, 0, PAGE_SIZE);
+	iomap_invalidatepage(page, pageoff, PAGE_SIZE - pageoff);
 }
 
 static const struct iomap_writeback_ops xfs_writeback_ops = {
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 5e16545..1414ab7 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -911,6 +911,16 @@
 		error = iomap_zero_range(inode, oldsize, newsize - oldsize,
 				&did_zeroing, &xfs_buffered_write_iomap_ops);
 	} else {
+		/*
+		 * iomap won't detect a dirty page over an unwritten block (or a
+		 * cow block over a hole) and subsequently skips zeroing the
+		 * newly post-EOF portion of the page. Flush the new EOF to
+		 * convert the block before the pagecache truncate.
+		 */
+		error = filemap_write_and_wait_range(inode->i_mapping, newsize,
+						     newsize);
+		if (error)
+			return error;
 		error = iomap_truncate_page(inode, newsize, &did_zeroing,
 				&xfs_buffered_write_iomap_ops);
 	}
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index b101feb..f3082a9 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -134,7 +134,7 @@
 		goto out_unlock;
 	error = invalidate_inode_pages2(inode->i_mapping);
 	if (WARN_ON_ONCE(error))
-		return error;
+		goto out_unlock;
 
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 16098dc..6fa05fb 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1502,7 +1502,8 @@
 			&xfs_buffered_write_iomap_ops);
 	if (error)
 		goto out;
-	error = filemap_write_and_wait(inode->i_mapping);
+
+	error = filemap_write_and_wait_range(inode->i_mapping, offset, len);
 	if (error)
 		goto out;
 
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 798027b..640f094 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -13,6 +13,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/compiler.h>
 #include <asm/rwonce.h>
 
 #ifndef nop
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 35e4a53..6432a7f 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -114,21 +114,21 @@
 
 #define __this_cpu_generic_read_nopreempt(pcp)				\
 ({									\
-	typeof(pcp) __ret;						\
+	typeof(pcp) ___ret;						\
 	preempt_disable_notrace();					\
-	__ret = READ_ONCE(*raw_cpu_ptr(&(pcp)));			\
+	___ret = READ_ONCE(*raw_cpu_ptr(&(pcp)));			\
 	preempt_enable_notrace();					\
-	__ret;								\
+	___ret;								\
 })
 
 #define __this_cpu_generic_read_noirq(pcp)				\
 ({									\
-	typeof(pcp) __ret;						\
-	unsigned long __flags;						\
-	raw_local_irq_save(__flags);					\
-	__ret = raw_cpu_generic_read(pcp);				\
-	raw_local_irq_restore(__flags);					\
-	__ret;								\
+	typeof(pcp) ___ret;						\
+	unsigned long ___flags;						\
+	raw_local_irq_save(___flags);					\
+	___ret = raw_cpu_generic_read(pcp);				\
+	raw_local_irq_restore(___flags);				\
+	___ret;								\
 })
 
 #define this_cpu_generic_read(pcp)					\
diff --git a/include/kunit/test.h b/include/kunit/test.h
index 9197da7..df60be7 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -252,13 +252,14 @@
 }
 #endif /* IS_BUILTIN(CONFIG_KUNIT) */
 
+#ifdef MODULE
 /**
- * kunit_test_suites() - used to register one or more &struct kunit_suite
- *			 with KUnit.
+ * kunit_test_suites_for_module() - used to register one or more
+ *			 &struct kunit_suite with KUnit.
  *
- * @suites_list...: a statically allocated list of &struct kunit_suite.
+ * @__suites: a statically allocated list of &struct kunit_suite.
  *
- * Registers @suites_list with the test framework. See &struct kunit_suite for
+ * Registers @__suites with the test framework. See &struct kunit_suite for
  * more information.
  *
  * If a test suite is built-in, module_init() gets translated into
@@ -267,7 +268,6 @@
  * module_{init|exit} functions for the builtin case when registering
  * suites via kunit_test_suites() below.
  */
-#ifdef MODULE
 #define kunit_test_suites_for_module(__suites)				\
 	static int __init kunit_test_suites_init(void)			\
 	{								\
@@ -294,7 +294,7 @@
  * kunit_test_suites() - used to register one or more &struct kunit_suite
  *			 with KUnit.
  *
- * @suites: a statically allocated list of &struct kunit_suite.
+ * @__suites: a statically allocated list of &struct kunit_suite.
  *
  * Registers @suites with the test framework. See &struct kunit_suite for
  * more information.
@@ -308,10 +308,10 @@
  * module.
  *
  */
-#define kunit_test_suites(...)						\
+#define kunit_test_suites(__suites...)						\
 	__kunit_test_suites(__UNIQUE_ID(array),				\
 			    __UNIQUE_ID(suites),			\
-			    __VA_ARGS__)
+			    ##__suites)
 
 #define kunit_test_suite(suite)	kunit_test_suites(&suite)
 
@@ -1105,7 +1105,7 @@
 	KUNIT_ASSERTION(test,						       \
 			strcmp(__left, __right) op 0,			       \
 			kunit_binary_str_assert,			       \
-			KUNIT_INIT_BINARY_ASSERT_STRUCT(test,		       \
+			KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(test,	       \
 							assert_type,	       \
 							#op,		       \
 							#left,		       \
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index b23eeca..794b2a3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -235,6 +235,8 @@
  * @flags:	   Zero or more BLK_MQ_F_* flags.
  * @driver_data:   Pointer to data owned by the block driver that created this
  *		   tag set.
+ * @active_queues_shared_sbitmap:
+ * 		   number of active request queues per tag set.
  * @__bitmap_tags: A shared tags sbitmap, used over all hctx's
  * @__breserved_tags:
  *		   A shared reserved tags sbitmap, used over all hctx's
diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index 900b9f4..fc61cf4 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -61,21 +61,17 @@
  */
 static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb)
 {
-	if (skb_shared(skb)) {
-		struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+	struct sk_buff *nskb;
 
-		if (likely(nskb)) {
-			can_skb_set_owner(nskb, skb->sk);
-			consume_skb(skb);
-			return nskb;
-		} else {
-			kfree_skb(skb);
-			return NULL;
-		}
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (unlikely(!nskb)) {
+		kfree_skb(skb);
+		return NULL;
 	}
 
-	/* we can assume to have an unshared skb with proper owner */
-	return skb;
+	can_skb_set_owner(nskb, skb->sk);
+	consume_skb(skb);
+	return nskb;
 }
 
 #endif /* !_CAN_SKB_H */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 230604e..dd7233c 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -60,12 +60,6 @@
 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
 #endif
 
-/* The following are for compatibility with GCC, from compiler-gcc.h,
- * and may be redefined here because they should not be shared with other
- * compilers, like ICC.
- */
-#define barrier() __asm__ __volatile__("" : : : "memory")
-
 #if __has_feature(shadow_call_stack)
 # define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index d1e3c68..74c6c04 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -15,25 +15,6 @@
 # error Sorry, your version of GCC is too old - please use 4.9 or newer.
 #endif
 
-/* Optimization barrier */
-
-/* The "volatile" is due to gcc bugs */
-#define barrier() __asm__ __volatile__("": : :"memory")
-/*
- * This version is i.e. to prevent dead stores elimination on @ptr
- * where gcc and llvm may behave differently when otherwise using
- * normal barrier(): while gcc behavior gets along with a normal
- * barrier(), llvm needs an explicit input variable to be assumed
- * clobbered. The issue is as follows: while the inline asm might
- * access any memory it wants, the compiler could have fit all of
- * @ptr into memory registers instead, and since @ptr never escaped
- * from that, it proved that the inline asm wasn't touching any of
- * it. This version works well with both compilers, i.e. we're telling
- * the compiler that the inline asm absolutely may see the contents
- * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495
- */
-#define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory")
-
 /*
  * This macro obfuscates arithmetic on a variable address so that gcc
  * shouldn't recognize the original var, and make assumptions about it.
@@ -175,5 +156,3 @@
 #else
 #define __diag_GCC_8(s)
 #endif
-
-#define __no_fgcse __attribute__((optimize("-fno-gcse")))
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index e512f55..b8fe0c2 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -80,11 +80,25 @@
 
 /* Optimization barrier */
 #ifndef barrier
-# define barrier() __memory_barrier()
+/* The "volatile" is due to gcc bugs */
+# define barrier() __asm__ __volatile__("": : :"memory")
 #endif
 
 #ifndef barrier_data
-# define barrier_data(ptr) barrier()
+/*
+ * This version is i.e. to prevent dead stores elimination on @ptr
+ * where gcc and llvm may behave differently when otherwise using
+ * normal barrier(): while gcc behavior gets along with a normal
+ * barrier(), llvm needs an explicit input variable to be assumed
+ * clobbered. The issue is as follows: while the inline asm might
+ * access any memory it wants, the compiler could have fit all of
+ * @ptr into memory registers instead, and since @ptr never escaped
+ * from that, it proved that the inline asm wasn't touching any of
+ * it. This version works well with both compilers, i.e. we're telling
+ * the compiler that the inline asm absolutely may see the contents
+ * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495
+ */
+# define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory")
 #endif
 
 /* workaround for GCC PR82365 if needed */
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 6e390d5..ac3fa37 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -247,10 +247,6 @@
 #define asm_inline asm
 #endif
 
-#ifndef __no_fgcse
-# define __no_fgcse
-#endif
-
 /* Are two types/vars the same type (ignoring qualifiers)? */
 #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 1eaa04f..acbad3b 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -110,6 +110,12 @@
 	bool			fast_switch_enabled;
 
 	/*
+	 * Set if the CPUFREQ_GOV_STRICT_TARGET flag is set for the current
+	 * governor.
+	 */
+	bool			strict_target;
+
+	/*
 	 * Preferred average time interval between consecutive invocations of
 	 * the driver to set the frequency for this policy.  To be set by the
 	 * scaling driver (0, which is the default, means no preference).
@@ -570,12 +576,20 @@
 					 char *buf);
 	int	(*store_setspeed)	(struct cpufreq_policy *policy,
 					 unsigned int freq);
-	/* For governors which change frequency dynamically by themselves */
-	bool			dynamic_switching;
 	struct list_head	governor_list;
 	struct module		*owner;
+	u8			flags;
 };
 
+/* Governor flags */
+
+/* For governors which change frequency dynamically by themselves */
+#define CPUFREQ_GOV_DYNAMIC_SWITCHING	BIT(0)
+
+/* For governors wanting the target frequency to be set exactly */
+#define CPUFREQ_GOV_STRICT_TARGET	BIT(1)
+
+
 /* Pass a target to the cpufreq driver */
 unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 					unsigned int target_freq);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 72d62cb..1b62397 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -558,21 +558,21 @@
 DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
 
 #define __BPF_PROG_RUN(prog, ctx, dfunc)	({			\
-	u32 ret;							\
+	u32 __ret;							\
 	cant_migrate();							\
 	if (static_branch_unlikely(&bpf_stats_enabled_key)) {		\
-		struct bpf_prog_stats *stats;				\
-		u64 start = sched_clock();				\
-		ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func);	\
-		stats = this_cpu_ptr(prog->aux->stats);			\
-		u64_stats_update_begin(&stats->syncp);			\
-		stats->cnt++;						\
-		stats->nsecs += sched_clock() - start;			\
-		u64_stats_update_end(&stats->syncp);			\
+		struct bpf_prog_stats *__stats;				\
+		u64 __start = sched_clock();				\
+		__ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func);	\
+		__stats = this_cpu_ptr(prog->aux->stats);		\
+		u64_stats_update_begin(&__stats->syncp);		\
+		__stats->cnt++;						\
+		__stats->nsecs += sched_clock() - __start;		\
+		u64_stats_update_end(&__stats->syncp);			\
 	} else {							\
-		ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func);	\
+		__ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func);	\
 	}								\
-	ret; })
+	__ret; })
 
 #define BPF_PROG_RUN(prog, ctx)						\
 	__BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 21cc971..8667d0c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1580,8 +1580,24 @@
  * Snapshotting support.
  */
 
-void __sb_end_write(struct super_block *sb, int level);
-int __sb_start_write(struct super_block *sb, int level, bool wait);
+/*
+ * These are internal functions, please use sb_start_{write,pagefault,intwrite}
+ * instead.
+ */
+static inline void __sb_end_write(struct super_block *sb, int level)
+{
+	percpu_up_read(sb->s_writers.rw_sem + level-1);
+}
+
+static inline void __sb_start_write(struct super_block *sb, int level)
+{
+	percpu_down_read(sb->s_writers.rw_sem + level - 1);
+}
+
+static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
+{
+	return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
+}
 
 #define __sb_writers_acquired(sb, lev)	\
 	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
@@ -1645,12 +1661,12 @@
  */
 static inline void sb_start_write(struct super_block *sb)
 {
-	__sb_start_write(sb, SB_FREEZE_WRITE, true);
+	__sb_start_write(sb, SB_FREEZE_WRITE);
 }
 
-static inline int sb_start_write_trylock(struct super_block *sb)
+static inline bool sb_start_write_trylock(struct super_block *sb)
 {
-	return __sb_start_write(sb, SB_FREEZE_WRITE, false);
+	return __sb_start_write_trylock(sb, SB_FREEZE_WRITE);
 }
 
 /**
@@ -1674,7 +1690,7 @@
  */
 static inline void sb_start_pagefault(struct super_block *sb)
 {
-	__sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);
+	__sb_start_write(sb, SB_FREEZE_PAGEFAULT);
 }
 
 /*
@@ -1692,12 +1708,12 @@
  */
 static inline void sb_start_intwrite(struct super_block *sb)
 {
-	__sb_start_write(sb, SB_FREEZE_FS, true);
+	__sb_start_write(sb, SB_FREEZE_FS);
 }
 
-static inline int sb_start_intwrite_trylock(struct super_block *sb)
+static inline bool sb_start_intwrite_trylock(struct super_block *sb)
 {
-	return __sb_start_write(sb, SB_FREEZE_FS, false);
+	return __sb_start_write_trylock(sb, SB_FREEZE_FS);
 }
 
 
@@ -2756,14 +2772,14 @@
 {
 	if (!S_ISREG(file_inode(file)->i_mode))
 		return;
-	__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
+	sb_start_write(file_inode(file)->i_sb);
 }
 
 static inline bool file_start_write_trylock(struct file *file)
 {
 	if (!S_ISREG(file_inode(file)->i_mode))
 		return true;
-	return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false);
+	return sb_start_write_trylock(file_inode(file)->i_sb);
 }
 
 static inline void file_end_write(struct file *file)
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 38f23d7..03da3f6 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -315,7 +315,7 @@
 extern void disk_block_events(struct gendisk *disk);
 extern void disk_unblock_events(struct gendisk *disk);
 extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
-void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
 		bool update_bdev);
 
 /* drivers/char/random.c */
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 868364c..35b2d84 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -30,7 +30,8 @@
 	struct percpu_counter	inflight;
 	struct io_identity	__identity;
 	struct io_identity	*identity;
-	bool			in_idle;
+	atomic_t		in_idle;
+	bool			sqpoll;
 };
 
 #if defined(CONFIG_IO_URING)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 172b339..5bd3cac 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -221,7 +221,7 @@
 	 * Optional, allows the file system to discard state on a page where
 	 * we failed to submit any I/O.
 	 */
-	void (*discard_page)(struct page *page);
+	void (*discard_page)(struct page *page, loff_t fileoff);
 };
 
 struct iomap_writepage_ctx {
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 1d5566a..1c49fd6 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -68,6 +68,7 @@
 extern void jbd2_free(void *ptr, size_t size);
 
 #define JBD2_MIN_JOURNAL_BLOCKS 1024
+#define JBD2_MIN_FC_BLOCKS	256
 
 #ifdef __KERNEL__
 
@@ -944,8 +945,9 @@
 	/**
 	 * @j_fc_off:
 	 *
-	 * Number of fast commit blocks currently allocated.
-	 * [j_state_lock].
+	 * Number of fast commit blocks currently allocated. Accessed only
+	 * during fast commit. Currently only process can do fast commit, so
+	 * this field is not protected by any lock.
 	 */
 	unsigned long		j_fc_off;
 
@@ -988,9 +990,9 @@
 	struct block_device	*j_fs_dev;
 
 	/**
-	 * @j_maxlen: Total maximum capacity of the journal region on disk.
+	 * @j_total_len: Total maximum capacity of the journal region on disk.
 	 */
-	unsigned int		j_maxlen;
+	unsigned int		j_total_len;
 
 	/**
 	 * @j_reserved_credits:
@@ -1108,8 +1110,9 @@
 	struct buffer_head	**j_wbuf;
 
 	/**
-	 * @j_fc_wbuf: Array of fast commit bhs for
-	 * jbd2_journal_commit_transaction.
+	 * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only
+	 * during a fast commit. Currently only process can do fast commit, so
+	 * this field is not protected by any lock.
 	 */
 	struct buffer_head	**j_fc_wbuf;
 
@@ -1614,16 +1617,20 @@
 extern int jbd2_cleanup_journal_tail(journal_t *);
 
 /* Fast commit related APIs */
-int jbd2_fc_init(journal_t *journal, int num_fc_blks);
 int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
 int jbd2_fc_end_commit(journal_t *journal);
-int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid);
+int jbd2_fc_end_commit_fallback(journal_t *journal);
 int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
 int jbd2_submit_inode_data(struct jbd2_inode *jinode);
 int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
 int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
 int jbd2_fc_release_bufs(journal_t *journal);
 
+static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal)
+{
+	return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
+}
+
 /*
  * is_journal_abort
  *
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e391e3c..a80c59a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -900,12 +900,19 @@
 static inline void memcg_memory_event(struct mem_cgroup *memcg,
 				      enum memcg_memory_event event)
 {
+	bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX ||
+			  event == MEMCG_SWAP_FAIL;
+
 	atomic_long_inc(&memcg->memory_events_local[event]);
-	cgroup_file_notify(&memcg->events_local_file);
+	if (!swap_event)
+		cgroup_file_notify(&memcg->events_local_file);
 
 	do {
 		atomic_long_inc(&memcg->memory_events[event]);
-		cgroup_file_notify(&memcg->events_file);
+		if (swap_event)
+			cgroup_file_notify(&memcg->swap_events_file);
+		else
+			cgroup_file_notify(&memcg->events_file);
 
 		if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
 			break;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ef360fe..db6ae4d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2759,6 +2759,15 @@
 	return VM_FAULT_NOPAGE;
 }
 
+#ifndef io_remap_pfn_range
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+				     unsigned long addr, unsigned long pfn,
+				     unsigned long size, pgprot_t prot)
+{
+	return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot));
+}
+#endif
+
 static inline vm_fault_t vmf_error(int err)
 {
 	if (err == -ENOMEM)
diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 89016d0..f6267e2 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -24,6 +24,12 @@
 	const u_int16_t attr_count;		/* number of nlattr's */
 };
 
+enum nfnl_abort_action {
+	NFNL_ABORT_NONE		= 0,
+	NFNL_ABORT_AUTOLOAD,
+	NFNL_ABORT_VALIDATE,
+};
+
 struct nfnetlink_subsystem {
 	const char *name;
 	__u8 subsys_id;			/* nfnetlink subsystem ID */
@@ -31,7 +37,8 @@
 	const struct nfnl_callback *cb;	/* callback for individual types */
 	struct module *owner;
 	int (*commit)(struct net *net, struct sk_buff *skb);
-	int (*abort)(struct net *net, struct sk_buff *skb, bool autoload);
+	int (*abort)(struct net *net, struct sk_buff *skb,
+		     enum nfnl_abort_action action);
 	void (*cleanup)(struct net *net);
 	bool (*valid_genid)(struct net *net, u32 genid);
 };
diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h
index 082e2c4..5b70ca8 100644
--- a/include/linux/netfilter_ipv4.h
+++ b/include/linux/netfilter_ipv4.h
@@ -16,7 +16,7 @@
 	u_int32_t mark;
 };
 
-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type);
+int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned addr_type);
 
 struct nf_queue_entry;
 
diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index 9b67394..48314ad 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -42,7 +42,7 @@
 #if IS_MODULE(CONFIG_IPV6)
 	int (*chk_addr)(struct net *net, const struct in6_addr *addr,
 			const struct net_device *dev, int strict);
-	int (*route_me_harder)(struct net *net, struct sk_buff *skb);
+	int (*route_me_harder)(struct net *net, struct sock *sk, struct sk_buff *skb);
 	int (*dev_get_saddr)(struct net *net, const struct net_device *dev,
 		       const struct in6_addr *daddr, unsigned int srcprefs,
 		       struct in6_addr *saddr);
@@ -143,9 +143,9 @@
 #endif
 }
 
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb);
+int ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb);
 
-static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+static inline int nf_ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 #if IS_MODULE(CONFIG_IPV6)
 	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
@@ -153,9 +153,9 @@
 	if (!v6_ops)
 		return -EHOSTUNREACH;
 
-	return v6_ops->route_me_harder(net, skb);
+	return v6_ops->route_me_harder(net, sk, skb);
 #elif IS_BUILTIN(CONFIG_IPV6)
-	return ip6_route_me_harder(net, skb);
+	return ip6_route_me_harder(net, sk, skb);
 #else
 	return -EHOSTUNREACH;
 #endif
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c77b7c31..e1e19c1 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -344,9 +344,9 @@
 /**
  * find_lock_page - locate, pin and lock a pagecache page
  * @mapping: the address_space to search
- * @offset: the page index
+ * @index: the page index
  *
- * Looks up the page cache entry at @mapping & @offset.  If there is a
+ * Looks up the page cache entry at @mapping & @index.  If there is a
  * page cache page, it is returned locked and with an increased
  * refcount.
  *
@@ -363,9 +363,9 @@
 /**
  * find_lock_head - Locate, pin and lock a pagecache page.
  * @mapping: The address_space to search.
- * @offset: The page index.
+ * @index: The page index.
  *
- * Looks up the page cache entry at @mapping & @offset.  If there is a
+ * Looks up the page cache entry at @mapping & @index.  If there is a
  * page cache page, its head page is returned locked and with an increased
  * refcount.
  *
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0c19d27..96450f6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1022,13 +1022,7 @@
 	struct perf_callchain_entry	*callchain;
 	u64				aux_size;
 
-	/*
-	 * regs_user may point to task_pt_regs or to regs_user_copy, depending
-	 * on arch details.
-	 */
 	struct perf_regs		regs_user;
-	struct pt_regs			regs_user_copy;
-
 	struct perf_regs		regs_intr;
 	u64				stack_user_size;
 
@@ -1400,11 +1394,14 @@
 extern void perf_event_addr_filters_sync(struct perf_event *event);
 
 extern int perf_output_begin(struct perf_output_handle *handle,
+			     struct perf_sample_data *data,
 			     struct perf_event *event, unsigned int size);
 extern int perf_output_begin_forward(struct perf_output_handle *handle,
-				    struct perf_event *event,
-				    unsigned int size);
+				     struct perf_sample_data *data,
+				     struct perf_event *event,
+				     unsigned int size);
 extern int perf_output_begin_backward(struct perf_output_handle *handle,
+				      struct perf_sample_data *data,
 				      struct perf_event *event,
 				      unsigned int size);
 
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 2d12e97..f632c57 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -20,8 +20,7 @@
 int perf_reg_validate(u64 mask);
 u64 perf_reg_abi(struct task_struct *task);
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy);
+			struct pt_regs *regs);
 #else
 
 #define PERF_REG_EXTENDED_MASK	0
@@ -42,8 +41,7 @@
 }
 
 static inline void perf_get_regs_user(struct perf_regs *regs_user,
-				      struct pt_regs *regs,
-				      struct pt_regs *regs_user_copy)
+				      struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 38c33ea..71125a4 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1427,10 +1427,6 @@
 
 #endif /* !__ASSEMBLY__ */
 
-#ifndef io_remap_pfn_range
-#define io_remap_pfn_range remap_pfn_range
-#endif
-
 #ifndef has_transparent_hugepage
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define has_transparent_hugepage() 1
diff --git a/include/linux/phy.h b/include/linux/phy.h
index eb3cb1a..56563e5e0 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -147,16 +147,8 @@
 	PHY_INTERFACE_MODE_MAX,
 } phy_interface_t;
 
-/**
+/*
  * phy_supported_speeds - return all speeds currently supported by a PHY device
- * @phy: The PHY device to return supported speeds of.
- * @speeds: buffer to store supported speeds in.
- * @size: size of speeds buffer.
- *
- * Description: Returns the number of supported speeds, and fills
- * the speeds buffer with the supported speeds. If speeds buffer is
- * too small to contain all currently supported speeds, will return as
- * many speeds as can fit.
  */
 unsigned int phy_supported_speeds(struct phy_device *phy,
 				      unsigned int *speeds,
@@ -1022,14 +1014,9 @@
 					regnum, mask, set);
 }
 
-/**
+/*
  * phy_read_mmd - Convenience function for reading a register
  * from an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to read from
- * @regnum: The register on the MMD to read
- *
- * Same rules as for phy_read();
  */
 int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
 
@@ -1064,38 +1051,21 @@
 	__ret; \
 })
 
-/**
+/*
  * __phy_read_mmd - Convenience function for reading a register
  * from an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to read from
- * @regnum: The register on the MMD to read
- *
- * Same rules as for __phy_read();
  */
 int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
 
-/**
+/*
  * phy_write_mmd - Convenience function for writing a register
  * on an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to write to
- * @regnum: The register on the MMD to read
- * @val: value to write to @regnum
- *
- * Same rules as for phy_write();
  */
 int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
 
-/**
+/*
  * __phy_write_mmd - Convenience function for writing a register
  * on an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to write to
- * @regnum: The register on the MMD to read
- * @val: value to write to @regnum
- *
- * Same rules as for __phy_write();
  */
 int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
 
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 18b02dc..4b708f4 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -54,11 +54,10 @@
 extern void pm_runtime_update_max_time_suspended(struct device *dev,
 						 s64 delta_ns);
 extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable);
-extern void pm_runtime_clean_up_links(struct device *dev);
 extern void pm_runtime_get_suppliers(struct device *dev);
 extern void pm_runtime_put_suppliers(struct device *dev);
 extern void pm_runtime_new_link(struct device *dev);
-extern void pm_runtime_drop_link(struct device *dev);
+extern void pm_runtime_drop_link(struct device_link *link);
 
 /**
  * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter.
@@ -276,11 +275,10 @@
 				struct device *dev) { return 0; }
 static inline void pm_runtime_set_memalloc_noio(struct device *dev,
 						bool enable){}
-static inline void pm_runtime_clean_up_links(struct device *dev) {}
 static inline void pm_runtime_get_suppliers(struct device *dev) {}
 static inline void pm_runtime_put_suppliers(struct device *dev) {}
 static inline void pm_runtime_new_link(struct device *dev) {}
-static inline void pm_runtime_drop_link(struct device *dev) {}
+static inline void pm_runtime_drop_link(struct device_link *link) {}
 
 #endif /* !CONFIG_PM */
 
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 7fabb1a..497990c 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -147,24 +147,6 @@
 	return atomic_read(&r->refs);
 }
 
-/**
- * refcount_add_not_zero - add a value to a refcount unless it is 0
- * @i: the value to add to the refcount
- * @r: the refcount
- *
- * Will saturate at REFCOUNT_SATURATED and WARN.
- *
- * Provides no memory ordering, it is assumed the caller has guaranteed the
- * object memory to be stable (RCU, etc.). It does provide a control dependency
- * and thereby orders future stores. See the comment on top.
- *
- * Use of this function is not recommended for the normal reference counting
- * use case in which references are taken and released one at a time.  In these
- * cases, refcount_inc(), or one of its variants, should instead be used to
- * increment a reference count.
- *
- * Return: false if the passed refcount is 0, true otherwise
- */
 static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp)
 {
 	int old = refcount_read(r);
@@ -183,11 +165,42 @@
 	return old;
 }
 
+/**
+ * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Will saturate at REFCOUNT_SATURATED and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time.  In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ *
+ * Return: false if the passed refcount is 0, true otherwise
+ */
 static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
 {
 	return __refcount_add_not_zero(i, r, NULL);
 }
 
+static inline void __refcount_add(int i, refcount_t *r, int *oldp)
+{
+	int old = atomic_fetch_add_relaxed(i, &r->refs);
+
+	if (oldp)
+		*oldp = old;
+
+	if (unlikely(!old))
+		refcount_warn_saturate(r, REFCOUNT_ADD_UAF);
+	else if (unlikely(old < 0 || old + i < 0))
+		refcount_warn_saturate(r, REFCOUNT_ADD_OVF);
+}
+
 /**
  * refcount_add - add a value to a refcount
  * @i: the value to add to the refcount
@@ -204,24 +217,16 @@
  * cases, refcount_inc(), or one of its variants, should instead be used to
  * increment a reference count.
  */
-static inline void __refcount_add(int i, refcount_t *r, int *oldp)
-{
-	int old = atomic_fetch_add_relaxed(i, &r->refs);
-
-	if (oldp)
-		*oldp = old;
-
-	if (unlikely(!old))
-		refcount_warn_saturate(r, REFCOUNT_ADD_UAF);
-	else if (unlikely(old < 0 || old + i < 0))
-		refcount_warn_saturate(r, REFCOUNT_ADD_OVF);
-}
-
 static inline void refcount_add(int i, refcount_t *r)
 {
 	__refcount_add(i, r, NULL);
 }
 
+static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
+{
+	return __refcount_add_not_zero(1, r, oldp);
+}
+
 /**
  * refcount_inc_not_zero - increment a refcount unless it is 0
  * @r: the refcount to increment
@@ -235,16 +240,16 @@
  *
  * Return: true if the increment was successful, false otherwise
  */
-static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
-{
-	return __refcount_add_not_zero(1, r, oldp);
-}
-
 static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
 {
 	return __refcount_inc_not_zero(r, NULL);
 }
 
+static inline void __refcount_inc(refcount_t *r, int *oldp)
+{
+	__refcount_add(1, r, oldp);
+}
+
 /**
  * refcount_inc - increment a refcount
  * @r: the refcount to increment
@@ -257,16 +262,29 @@
  * Will WARN if the refcount is 0, as this represents a possible use-after-free
  * condition.
  */
-static inline void __refcount_inc(refcount_t *r, int *oldp)
-{
-	__refcount_add(1, r, oldp);
-}
-
 static inline void refcount_inc(refcount_t *r)
 {
 	__refcount_inc(r, NULL);
 }
 
+static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
+{
+	int old = atomic_fetch_sub_release(i, &r->refs);
+
+	if (oldp)
+		*oldp = old;
+
+	if (old == i) {
+		smp_acquire__after_ctrl_dep();
+		return true;
+	}
+
+	if (unlikely(old < 0 || old - i < 0))
+		refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
+
+	return false;
+}
+
 /**
  * refcount_sub_and_test - subtract from a refcount and test if it is 0
  * @i: amount to subtract from the refcount
@@ -287,29 +305,16 @@
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
-{
-	int old = atomic_fetch_sub_release(i, &r->refs);
-
-	if (oldp)
-		*oldp = old;
-
-	if (old == i) {
-		smp_acquire__after_ctrl_dep();
-		return true;
-	}
-
-	if (unlikely(old < 0 || old - i < 0))
-		refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
-
-	return false;
-}
-
 static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
 {
 	return __refcount_sub_and_test(i, r, NULL);
 }
 
+static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
+{
+	return __refcount_sub_and_test(1, r, oldp);
+}
+
 /**
  * refcount_dec_and_test - decrement a refcount and test if it is 0
  * @r: the refcount
@@ -323,16 +328,22 @@
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
-{
-	return __refcount_sub_and_test(1, r, oldp);
-}
-
 static inline __must_check bool refcount_dec_and_test(refcount_t *r)
 {
 	return __refcount_dec_and_test(r, NULL);
 }
 
+static inline void __refcount_dec(refcount_t *r, int *oldp)
+{
+	int old = atomic_fetch_sub_release(1, &r->refs);
+
+	if (oldp)
+		*oldp = old;
+
+	if (unlikely(old <= 1))
+		refcount_warn_saturate(r, REFCOUNT_DEC_LEAK);
+}
+
 /**
  * refcount_dec - decrement a refcount
  * @r: the refcount
@@ -343,17 +354,6 @@
  * Provides release memory ordering, such that prior loads and stores are done
  * before.
  */
-static inline void __refcount_dec(refcount_t *r, int *oldp)
-{
-	int old = atomic_fetch_sub_release(1, &r->refs);
-
-	if (oldp)
-		*oldp = old;
-
-	if (unlikely(old <= 1))
-		refcount_warn_saturate(r, REFCOUNT_DEC_LEAK);
-}
-
 static inline void refcount_dec(refcount_t *r)
 {
 	__refcount_dec(r, NULL);
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 813614d..b83b3ae3 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -107,6 +107,7 @@
 char *mangle_path(char *s, const char *p, const char *esc);
 int seq_open(struct file *, const struct seq_operations *);
 ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
+ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter);
 loff_t seq_lseek(struct file *, loff_t, int);
 int seq_release(struct inode *, struct file *);
 int seq_write(struct seq_file *seq, const void *data, size_t len);
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 99380c0..b390fda 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -734,6 +734,25 @@
 	return __spi_alloc_controller(host, size, true);
 }
 
+struct spi_controller *__devm_spi_alloc_controller(struct device *dev,
+						   unsigned int size,
+						   bool slave);
+
+static inline struct spi_controller *devm_spi_alloc_master(struct device *dev,
+							   unsigned int size)
+{
+	return __devm_spi_alloc_controller(dev, size, false);
+}
+
+static inline struct spi_controller *devm_spi_alloc_slave(struct device *dev,
+							  unsigned int size)
+{
+	if (!IS_ENABLED(CONFIG_SPI_SLAVE))
+		return NULL;
+
+	return __devm_spi_alloc_controller(dev, size, true);
+}
+
 extern int spi_register_controller(struct spi_controller *ctlr);
 extern int devm_spi_register_controller(struct device *dev,
 					struct spi_controller *ctlr);
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 513913f..fbdc657 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -5,6 +5,7 @@
 #include <linux/dma-direction.h>
 #include <linux/init.h>
 #include <linux/types.h>
+#include <linux/limits.h>
 
 struct device;
 struct page;
@@ -45,13 +46,9 @@
 	SYNC_FOR_DEVICE = 1,
 };
 
-extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
-					  dma_addr_t tbl_dma_addr,
-					  phys_addr_t phys,
-					  size_t mapping_size,
-					  size_t alloc_size,
-					  enum dma_data_direction dir,
-					  unsigned long attrs);
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
+		size_t mapping_size, size_t alloc_size,
+		enum dma_data_direction dir, unsigned long attrs);
 
 extern void swiotlb_tbl_unmap_single(struct device *hwdev,
 				     phys_addr_t tlb_addr,
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 661edfc..d5ab8d9 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1444,7 +1444,7 @@
 				  enum cfg80211_station_type statype);
 
 /**
- * enum station_info_rate_flags - bitrate info flags
+ * enum rate_info_flags - bitrate info flags
  *
  * Used by the driver to indicate the specific rate transmission
  * type for 802.11n transmissions.
@@ -1517,7 +1517,7 @@
 };
 
 /**
- * enum station_info_rate_flags - bitrate info flags
+ * enum bss_param_flags - bitrate info flags
  *
  * Used by the driver to indicate the specific rate transmission
  * type for 802.11n transmissions.
@@ -6467,7 +6467,8 @@
 			  struct ieee80211_channel *channel, gfp_t gfp);
 
 /**
- * cfg80211_notify_new_candidate - notify cfg80211 of a new mesh peer candidate
+ * cfg80211_notify_new_peer_candidate - notify cfg80211 of a new mesh peer
+ * 					candidate
  *
  * @dev: network device
  * @macaddr: the MAC address of the new candidate
@@ -7606,7 +7607,7 @@
 void cfg80211_unregister_wdev(struct wireless_dev *wdev);
 
 /**
- * struct cfg80211_ft_event - FT Information Elements
+ * struct cfg80211_ft_event_params - FT Information Elements
  * @ies: FT IEs
  * @ies_len: length of the FT IE in bytes
  * @target_ap: target AP's MAC address
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index e8e295d..dcdba968 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3311,7 +3311,7 @@
 };
 
 /**
- * enum ieee80211_reconfig_complete_type - reconfig type
+ * enum ieee80211_reconfig_type - reconfig type
  *
  * This enum is used by the reconfig_complete() callback to indicate what
  * reconfiguration type was completed.
@@ -6334,7 +6334,8 @@
 			      int band, struct ieee80211_sta **sta);
 
 /**
- * Sanity-check and parse the radiotap header of injected frames
+ * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header
+ *				 of injected frames
  * @skb: packet injected by userspace
  * @dev: the &struct device of this 802.11 device
  */
@@ -6389,7 +6390,7 @@
 void ieee80211_update_p2p_noa(struct ieee80211_noa_data *data, u32 tsf);
 
 /**
- * ieee80211_tdls_oper - request userspace to perform a TDLS operation
+ * ieee80211_tdls_oper_request - request userspace to perform a TDLS operation
  * @vif: virtual interface
  * @peer: the peer's destination address
  * @oper: the requested TDLS operation
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 0140d08..01755b8 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -86,7 +86,7 @@
 void xp_destroy(struct xsk_buff_pool *pool);
 void xp_release(struct xdp_buff_xsk *xskb);
 void xp_get_pool(struct xsk_buff_pool *pool);
-void xp_put_pool(struct xsk_buff_pool *pool);
+bool xp_put_pool(struct xsk_buff_pool *pool);
 void xp_clear_dev(struct xsk_buff_pool *pool);
 void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
 void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
diff --git a/include/sound/control.h b/include/sound/control.h
index e128cff..77d9fa1 100644
--- a/include/sound/control.h
+++ b/include/sound/control.h
@@ -42,7 +42,7 @@
 	snd_ctl_elem_iface_t iface;	/* interface identifier */
 	unsigned int device;		/* device/client number */
 	unsigned int subdevice;		/* subdevice (substream) number */
-	const unsigned char *name;	/* ASCII name of item */
+	const char *name;		/* ASCII name of item */
 	unsigned int index;		/* index of item */
 	unsigned int access;		/* access rights */
 	unsigned int count;		/* count of same elements */
diff --git a/include/sound/core.h b/include/sound/core.h
index 381a010..0462c57 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -332,7 +332,8 @@
 #define snd_BUG()		WARN(1, "BUG?\n")
 
 /**
- * Suppress high rates of output when CONFIG_SND_DEBUG is enabled.
+ * snd_printd_ratelimit - Suppress high rates of output when
+ * 			  CONFIG_SND_DEBUG is enabled.
  */
 #define snd_printd_ratelimit() printk_ratelimit()
 
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 2ba5df2..2336bf9 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -1284,8 +1284,8 @@
 }
 
 /**
- * snd_pcm_sgbuf_chunk_size - Compute the max size that fits within the contig.
- * page from the given size
+ * snd_pcm_sgbuf_get_chunk_size - Compute the max size that fits within the
+ * contig. page from the given size
  * @substream: PCM substream
  * @ofs: byte offset
  * @size: byte size to examine
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index b14314fc..70ae549 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -100,11 +100,12 @@
 		{ EXT4_FC_REASON_XATTR,		"XATTR"},		\
 		{ EXT4_FC_REASON_CROSS_RENAME,	"CROSS_RENAME"},	\
 		{ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \
-		{ EXT4_FC_REASON_MEM,	"NO_MEM"},			\
+		{ EXT4_FC_REASON_NOMEM,	"NO_MEM"},			\
 		{ EXT4_FC_REASON_SWAP_BOOT,	"SWAP_BOOT"},		\
 		{ EXT4_FC_REASON_RESIZE,	"RESIZE"},		\
 		{ EXT4_FC_REASON_RENAME_DIR,	"RENAME_DIR"},		\
-		{ EXT4_FC_REASON_FALLOC_RANGE,	"FALLOC_RANGE"})
+		{ EXT4_FC_REASON_FALLOC_RANGE,	"FALLOC_RANGE"},	\
+		{ EXT4_FC_REASON_INODE_JOURNAL_DATA,	"INODE_JOURNAL_DATA"})
 
 TRACE_EVENT(ext4_other_inode_update_time,
 	TP_PROTO(struct inode *inode, ino_t orig_ino),
@@ -2917,17 +2918,18 @@
 		    ),
 
 	    TP_printk("dev %d:%d fc ineligible reasons:\n"
-		      "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s,%d; "
+		      "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d; "
 		      "num_commits:%ld, ineligible: %ld, numblks: %ld",
 		      MAJOR(__entry->dev), MINOR(__entry->dev),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE),
-		      FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR),
 		      FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA),
 		      __entry->sbi->s_fc_stats.fc_num_commits,
 		      __entry->sbi->s_fc_stats.fc_ineligible_commits,
 		      __entry->sbi->s_fc_stats.fc_numblks)
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index f45b3c0..2a03263 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -68,7 +68,8 @@
 
 	TP_fast_assign(
 		__entry->task_id = task->tk_pid;
-		__entry->client_id = task->tk_client->cl_clid;
+		__entry->client_id = task->tk_client ?
+				     task->tk_client->cl_clid : -1;
 		__entry->head_base = xdr->head[0].iov_base;
 		__entry->head_len = xdr->head[0].iov_len;
 		__entry->tail_base = xdr->tail[0].iov_base;
@@ -655,10 +656,10 @@
 		__field(size_t, tail_len)
 		__field(unsigned int, page_len)
 		__field(unsigned int, len)
-		__string(progname,
-			 xdr->rqst->rq_task->tk_client->cl_program->name)
-		__string(procedure,
-			 xdr->rqst->rq_task->tk_msg.rpc_proc->p_name)
+		__string(progname, xdr->rqst ?
+			 xdr->rqst->rq_task->tk_client->cl_program->name : "unknown")
+		__string(procedure, xdr->rqst ?
+			 xdr->rqst->rq_task->tk_msg.rpc_proc->p_name : "unknown")
 	),
 
 	TP_fast_assign(
diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h
index 07865c6..2072c26 100644
--- a/include/uapi/linux/gpio.h
+++ b/include/uapi/linux/gpio.h
@@ -26,7 +26,7 @@
  * struct gpiochip_info - Information about a certain GPIO chip
  * @name: the Linux kernel name of this GPIO chip
  * @label: a functional name for this GPIO chip, such as a product
- * number, may be empty
+ * number, may be empty (i.e. label[0] == '\0')
  * @lines: number of GPIO lines on this chip
  */
 struct gpiochip_info {
@@ -98,7 +98,7 @@
  * identifying which field of the attribute union is in use.
  * @GPIO_V2_LINE_ATTR_ID_FLAGS: flags field is in use
  * @GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES: values field is in use
- * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us is in use
+ * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us field is in use
  */
 enum gpio_v2_line_attr_id {
 	GPIO_V2_LINE_ATTR_ID_FLAGS		= 1,
@@ -110,17 +110,17 @@
  * struct gpio_v2_line_attribute - a configurable attribute of a line
  * @id: attribute identifier with value from &enum gpio_v2_line_attr_id
  * @padding: reserved for future use and must be zero filled
- * @flags: if id is GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO
- * line, with values from enum gpio_v2_line_flag, such as
- * GPIO_V2_LINE_FLAG_ACTIVE_LOW, GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed
+ * @flags: if id is %GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO
+ * line, with values from &enum gpio_v2_line_flag, such as
+ * %GPIO_V2_LINE_FLAG_ACTIVE_LOW, %GPIO_V2_LINE_FLAG_OUTPUT etc, added
  * together.  This overrides the default flags contained in the &struct
  * gpio_v2_line_config for the associated line.
- * @values: if id is GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap
+ * @values: if id is %GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap
  * containing the values to which the lines will be set, with each bit
  * number corresponding to the index into &struct
  * gpio_v2_line_request.offsets.
- * @debounce_period_us: if id is GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the desired
- * debounce period, in microseconds
+ * @debounce_period_us: if id is %GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the
+ * desired debounce period, in microseconds
  */
 struct gpio_v2_line_attribute {
 	__u32 id;
@@ -147,12 +147,12 @@
 
 /**
  * struct gpio_v2_line_config - Configuration for GPIO lines
- * @flags: flags for the GPIO lines, with values from enum
- * gpio_v2_line_flag, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW,
- * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together.  This is the default for
+ * @flags: flags for the GPIO lines, with values from &enum
+ * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW,
+ * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together.  This is the default for
  * all requested lines but may be overridden for particular lines using
- * attrs.
- * @num_attrs: the number of attributes in attrs
+ * @attrs.
+ * @num_attrs: the number of attributes in @attrs
  * @padding: reserved for future use and must be zero filled
  * @attrs: the configuration attributes associated with the requested
  * lines.  Any attribute should only be associated with a particular line
@@ -175,17 +175,17 @@
  * "my-bitbanged-relay"
  * @config: requested configuration for the lines.
  * @num_lines: number of lines requested in this request, i.e. the number
- * of valid fields in the GPIO_V2_LINES_MAX sized arrays, set to 1 to
+ * of valid fields in the %GPIO_V2_LINES_MAX sized arrays, set to 1 to
  * request a single line
  * @event_buffer_size: a suggested minimum number of line events that the
  * kernel should buffer.  This is only relevant if edge detection is
  * enabled in the configuration. Note that this is only a suggested value
  * and the kernel may allocate a larger buffer or cap the size of the
  * buffer. If this field is zero then the buffer size defaults to a minimum
- * of num_lines*16.
+ * of @num_lines * 16.
  * @padding: reserved for future use and must be zero filled
  * @fd: if successful this field will contain a valid anonymous file handle
- * after a GPIO_GET_LINE_IOCTL operation, zero or negative value means
+ * after a %GPIO_GET_LINE_IOCTL operation, zero or negative value means
  * error
  */
 struct gpio_v2_line_request {
@@ -203,15 +203,16 @@
  * struct gpio_v2_line_info - Information about a certain GPIO line
  * @name: the name of this GPIO line, such as the output pin of the line on
  * the chip, a rail or a pin header name on a board, as specified by the
- * GPIO chip, may be empty
+ * GPIO chip, may be empty (i.e. name[0] == '\0')
  * @consumer: a functional name for the consumer of this GPIO line as set
  * by whatever is using it, will be empty if there is no current user but
  * may also be empty if the consumer doesn't set this up
- * @flags: flags for the GPIO line, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW,
- * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together
  * @offset: the local offset on this GPIO chip, fill this in when
  * requesting the line information from the kernel
- * @num_attrs: the number of attributes in attrs
+ * @num_attrs: the number of attributes in @attrs
+ * @flags: flags for the GPIO lines, with values from &enum
+ * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW,
+ * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together.
  * @attrs: the configuration attributes associated with the line
  * @padding: reserved for future use
  */
@@ -244,7 +245,7 @@
  * of a GPIO line
  * @info: updated line information
  * @timestamp_ns: estimate of time of status change occurrence, in nanoseconds
- * @event_type: the type of change with a value from enum
+ * @event_type: the type of change with a value from &enum
  * gpio_v2_line_changed_type
  * @padding: reserved for future use
  */
@@ -269,10 +270,10 @@
 /**
  * struct gpio_v2_line_event - The actual event being pushed to userspace
  * @timestamp_ns: best estimate of time of event occurrence, in nanoseconds.
- * The timestamp_ns is read from CLOCK_MONOTONIC and is intended to allow the
- * accurate measurement of the time between events.  It does not provide
+ * The @timestamp_ns is read from %CLOCK_MONOTONIC and is intended to allow
+ * the accurate measurement of the time between events. It does not provide
  * the wall-clock time.
- * @id: event identifier with value from enum gpio_v2_line_event_id
+ * @id: event identifier with value from &enum gpio_v2_line_event_id
  * @offset: the offset of the line that triggered the event
  * @seqno: the sequence number for this event in the sequence of events for
  * all the lines in this line request
@@ -291,7 +292,7 @@
 };
 
 /*
- *  ABI v1
+ * ABI v1
  *
  * This version of the ABI is deprecated.
  * Use the latest version of the ABI, defined above, instead.
@@ -314,13 +315,13 @@
  * @flags: various flags for this line
  * @name: the name of this GPIO line, such as the output pin of the line on the
  * chip, a rail or a pin header name on a board, as specified by the gpio
- * chip, may be empty
+ * chip, may be empty (i.e. name[0] == '\0')
  * @consumer: a functional name for the consumer of this GPIO line as set by
  * whatever is using it, will be empty if there is no current user but may
  * also be empty if the consumer doesn't set this up
  *
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_info instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_info instead.
  */
 struct gpioline_info {
 	__u32 line_offset;
@@ -344,17 +345,18 @@
  * of a GPIO line
  * @info: updated line information
  * @timestamp: estimate of time of status change occurrence, in nanoseconds
- * @event_type: one of GPIOLINE_CHANGED_REQUESTED, GPIOLINE_CHANGED_RELEASED
- * and GPIOLINE_CHANGED_CONFIG
+ * @event_type: one of %GPIOLINE_CHANGED_REQUESTED,
+ * %GPIOLINE_CHANGED_RELEASED and %GPIOLINE_CHANGED_CONFIG
+ * @padding: reserved for future use
  *
- * Note: struct gpioline_info embedded here has 32-bit alignment on its own,
+ * The &struct gpioline_info embedded here has 32-bit alignment on its own,
  * but it works fine with 64-bit alignment too. With its 72 byte size, we can
  * guarantee there are no implicit holes between it and subsequent members.
  * The 20-byte padding at the end makes sure we don't add any implicit padding
  * at the end of the structure on 64-bit architectures.
  *
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_info_changed instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_info_changed instead.
  */
 struct gpioline_info_changed {
 	struct gpioline_info info;
@@ -378,13 +380,13 @@
  * @lineoffsets: an array of desired lines, specified by offset index for the
  * associated GPIO device
  * @flags: desired flags for the desired GPIO lines, such as
- * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed
+ * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added
  * together. Note that even if multiple lines are requested, the same flags
  * must be applicable to all of them, if you want lines with individual
  * flags set, request them one by one. It is possible to select
  * a batch of input or output lines, but they must all have the same
  * characteristics, i.e. all inputs or all outputs, all active low etc
- * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set for a requested
+ * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set for a requested
  * line, this specifies the default output value, should be 0 (low) or
  * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high)
  * @consumer_label: a desired consumer label for the selected GPIO line(s)
@@ -392,11 +394,11 @@
  * @lines: number of lines requested in this request, i.e. the number of
  * valid fields in the above arrays, set to 1 to request a single line
  * @fd: if successful this field will contain a valid anonymous file handle
- * after a GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value
+ * after a %GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value
  * means error
  *
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_request instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_request instead.
  */
 struct gpiohandle_request {
 	__u32 lineoffsets[GPIOHANDLES_MAX];
@@ -410,15 +412,15 @@
 /**
  * struct gpiohandle_config - Configuration for a GPIO handle request
  * @flags: updated flags for the requested GPIO lines, such as
- * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed
+ * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added
  * together
- * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set in flags,
+ * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set in flags,
  * this specifies the default output value, should be 0 (low) or
  * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high)
  * @padding: reserved for future use and should be zero filled
  *
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_config instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_config instead.
  */
 struct gpiohandle_config {
 	__u32 flags;
@@ -432,8 +434,8 @@
  * state of a line, when setting the state of lines these should contain
  * the desired target state
  *
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_values instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_values instead.
  */
 struct gpiohandle_data {
 	__u8 values[GPIOHANDLES_MAX];
@@ -449,17 +451,17 @@
  * @lineoffset: the desired line to subscribe to events from, specified by
  * offset index for the associated GPIO device
  * @handleflags: desired handle flags for the desired GPIO line, such as
- * GPIOHANDLE_REQUEST_ACTIVE_LOW or GPIOHANDLE_REQUEST_OPEN_DRAIN
+ * %GPIOHANDLE_REQUEST_ACTIVE_LOW or %GPIOHANDLE_REQUEST_OPEN_DRAIN
  * @eventflags: desired flags for the desired GPIO event line, such as
- * GPIOEVENT_REQUEST_RISING_EDGE or GPIOEVENT_REQUEST_FALLING_EDGE
+ * %GPIOEVENT_REQUEST_RISING_EDGE or %GPIOEVENT_REQUEST_FALLING_EDGE
  * @consumer_label: a desired consumer label for the selected GPIO line(s)
  * such as "my-listener"
  * @fd: if successful this field will contain a valid anonymous file handle
- * after a GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value
+ * after a %GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value
  * means error
  *
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_request instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_request instead.
  */
 struct gpioevent_request {
 	__u32 lineoffset;
@@ -469,7 +471,7 @@
 	int fd;
 };
 
-/**
+/*
  * GPIO event types
  */
 #define GPIOEVENT_EVENT_RISING_EDGE 0x01
@@ -480,8 +482,8 @@
  * @timestamp: best estimate of time of event occurrence, in nanoseconds
  * @id: event identifier
  *
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_event instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_event instead.
  */
 struct gpioevent_data {
 	__u64 timestamp;
diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h
index c1661fe..0564fd7 100644
--- a/include/uapi/linux/icmpv6.h
+++ b/include/uapi/linux/icmpv6.h
@@ -138,6 +138,7 @@
 #define ICMPV6_HDR_FIELD		0
 #define ICMPV6_UNK_NEXTHDR		1
 #define ICMPV6_UNK_OPTION		2
+#define ICMPV6_HDR_INCOMP		3
 
 /*
  *	constants for (set|get)sockopt
diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h
index 7184265..9555f31 100644
--- a/include/uapi/sound/compress_offload.h
+++ b/include/uapi/sound/compress_offload.h
@@ -144,7 +144,7 @@
 	 __u32 value[8];
 } __attribute__((packed, aligned(4)));
 
-/**
+/*
  * compress path ioctl definitions
  * SNDRV_COMPRESS_GET_CAPS: Query capability of DSP
  * SNDRV_COMPRESS_GET_CODEC_CAPS: Query capability of a codec
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 06b0b57e..d1b3889 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -484,9 +484,6 @@
 
 enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc);
 enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat);
-enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code);
-int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat);
-bool ipu_pixelformat_is_planar(u32 pixelformat);
 int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
 			    bool hflip, bool vflip);
 int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode,
diff --git a/init/main.c b/init/main.c
index 130376e..20baced 100644
--- a/init/main.c
+++ b/init/main.c
@@ -269,14 +269,24 @@
 	u32 size, csum;
 	char *data;
 	u32 *hdr;
+	int i;
 
 	if (!initrd_end)
 		return NULL;
 
 	data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN;
-	if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
-		return NULL;
+	/*
+	 * Since Grub may align the size of initrd to 4, we must
+	 * check the preceding 3 bytes as well.
+	 */
+	for (i = 0; i < 4; i++) {
+		if (!memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
+			goto found;
+		data--;
+	}
+	return NULL;
 
+found:
 	hdr = (u32 *)(data - 8);
 	size = hdr[0];
 	csum = hdr[1];
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index bdc8cd1..c1b9f71 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,6 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-y := core.o
-CFLAGS_core.o += $(call cc-disable-warning, override-init)
+ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y)
+# ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details
+cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
+endif
+CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 78ea8a7..56cc5a9 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -13,6 +13,7 @@
 #include <linux/bpf_verifier.h>
 #include <net/bpf_sk_storage.h>
 #include <linux/bpf_local_storage.h>
+#include <linux/btf_ids.h>
 
 /* For every LSM hook that allows attachment of BPF programs, declare a nop
  * function where a BPF program can be attached.
@@ -26,7 +27,11 @@
 #include <linux/lsm_hook_defs.h>
 #undef LSM_HOOK
 
-#define BPF_LSM_SYM_PREFX  "bpf_lsm_"
+#define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME)
+BTF_SET_START(bpf_lsm_hooks)
+#include <linux/lsm_hook_defs.h>
+#undef LSM_HOOK
+BTF_SET_END(bpf_lsm_hooks)
 
 int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
 			const struct bpf_prog *prog)
@@ -37,8 +42,7 @@
 		return -EINVAL;
 	}
 
-	if (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name,
-		    sizeof(BPF_LSM_SYM_PREFX) - 1)) {
+	if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) {
 		bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n",
 			prog->aux->attach_btf_id, prog->aux->attach_func_name);
 		return -EINVAL;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9268d77..55454d2 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1369,7 +1369,7 @@
  *
  * Decode and execute eBPF instructions.
  */
-static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
+static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 {
 #define BPF_INSN_2_LBL(x, y)    [BPF_##x | BPF_##y] = &&x##_##y
 #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 1815e97..1fccba6 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -821,6 +821,32 @@
 	}
 }
 
+static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
+			    void *value, bool onallcpus)
+{
+	/* When using prealloc and not setting the initial value on all cpus,
+	 * zero-fill element values for other cpus (just as what happens when
+	 * not using prealloc). Otherwise, bpf program has no way to ensure
+	 * known initial values for cpus other than current one
+	 * (onallcpus=false always when coming from bpf prog).
+	 */
+	if (htab_is_prealloc(htab) && !onallcpus) {
+		u32 size = round_up(htab->map.value_size, 8);
+		int current_cpu = raw_smp_processor_id();
+		int cpu;
+
+		for_each_possible_cpu(cpu) {
+			if (cpu == current_cpu)
+				bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value,
+						size);
+			else
+				memset(per_cpu_ptr(pptr, cpu), 0, size);
+		}
+	} else {
+		pcpu_copy_value(htab, pptr, value, onallcpus);
+	}
+}
+
 static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
 {
 	return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS &&
@@ -891,7 +917,7 @@
 			}
 		}
 
-		pcpu_copy_value(htab, pptr, value, onallcpus);
+		pcpu_init_value(htab, pptr, value, onallcpus);
 
 		if (!prealloc)
 			htab_elem_set_ptr(l_new, key_size, pptr);
@@ -1183,7 +1209,7 @@
 		pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
 				value, onallcpus);
 	} else {
-		pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size),
+		pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size),
 				value, onallcpus);
 		hlist_nulls_add_head_rcu(&l_new->hash_node, head);
 		l_new = NULL;
diff --git a/kernel/bpf/preload/Kconfig b/kernel/bpf/preload/Kconfig
index ace4911..26bced2 100644
--- a/kernel/bpf/preload/Kconfig
+++ b/kernel/bpf/preload/Kconfig
@@ -6,6 +6,7 @@
 menuconfig BPF_PRELOAD
 	bool "Preload BPF file system with kernel specific program and map iterators"
 	depends on BPF
+	depends on BPF_SYSCALL
 	# The dependency on !COMPILE_TEST prevents it from being enabled
 	# in allmodconfig or allyesconfig configurations
 	depends on !COMPILE_TEST
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index b4eea0a..781b9dc 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -229,6 +229,7 @@
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
+	no_iotlb_memory = false;
 
 	if (verbose)
 		swiotlb_print_info();
@@ -260,9 +261,11 @@
 	if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
 		return;
 
-	if (io_tlb_start)
+	if (io_tlb_start) {
 		memblock_free_early(io_tlb_start,
 				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+		io_tlb_start = 0;
+	}
 	pr_warn("Cannot allocate buffer");
 	no_iotlb_memory = true;
 }
@@ -360,6 +363,7 @@
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
+	no_iotlb_memory = false;
 
 	swiotlb_print_info();
 
@@ -441,14 +445,11 @@
 	}
 }
 
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
-				   dma_addr_t tbl_dma_addr,
-				   phys_addr_t orig_addr,
-				   size_t mapping_size,
-				   size_t alloc_size,
-				   enum dma_data_direction dir,
-				   unsigned long attrs)
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
+		size_t mapping_size, size_t alloc_size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
+	dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start);
 	unsigned long flags;
 	phys_addr_t tlb_addr;
 	unsigned int nslots, stride, index, wrap;
@@ -667,9 +668,8 @@
 	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
 			      swiotlb_force);
 
-	swiotlb_addr = swiotlb_tbl_map_single(dev,
-			phys_to_dma_unencrypted(dev, io_tlb_start),
-			paddr, size, size, dir, attrs);
+	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir,
+			attrs);
 	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 2b83666..e9e2df3 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -337,10 +337,10 @@
 	 * already contains a warning when RCU is not watching, so no point
 	 * in having another one here.
 	 */
+	lockdep_hardirqs_off(CALLER_ADDR0);
 	instrumentation_begin();
 	rcu_irq_enter_check_tick();
-	/* Use the combo lockdep/tracing function */
-	trace_hardirqs_off();
+	trace_hardirqs_off_finish();
 	instrumentation_end();
 
 	return ret;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index da467e1..dc568ca 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2312,9 +2312,6 @@
 		event_sched_out(event, cpuctx, ctx);
 
 	perf_pmu_enable(ctx->pmu);
-
-	if (group_event->attr.exclusive)
-		cpuctx->exclusive = 0;
 }
 
 #define DETACH_GROUP	0x01UL
@@ -2583,11 +2580,8 @@
 
 	pmu->start_txn(pmu, PERF_PMU_TXN_ADD);
 
-	if (event_sched_in(group_event, cpuctx, ctx)) {
-		pmu->cancel_txn(pmu);
-		perf_mux_hrtimer_restart(cpuctx);
-		return -EAGAIN;
-	}
+	if (event_sched_in(group_event, cpuctx, ctx))
+		goto error;
 
 	/*
 	 * Schedule in siblings as one group (if any):
@@ -2616,10 +2610,8 @@
 	}
 	event_sched_out(group_event, cpuctx, ctx);
 
+error:
 	pmu->cancel_txn(pmu);
-
-	perf_mux_hrtimer_restart(cpuctx);
-
 	return -EAGAIN;
 }
 
@@ -2645,7 +2637,7 @@
 	 * If this group is exclusive and there are already
 	 * events on the CPU, it can't go on.
 	 */
-	if (event->attr.exclusive && cpuctx->active_oncpu)
+	if (event->attr.exclusive && !list_empty(get_event_list(event)))
 		return 0;
 	/*
 	 * Otherwise, try to add it if all previous groups were able
@@ -3679,6 +3671,7 @@
 
 		*can_add_hw = 0;
 		ctx->rotate_necessary = 1;
+		perf_mux_hrtimer_restart(cpuctx);
 	}
 
 	return 0;
@@ -6374,14 +6367,13 @@
 }
 
 static void perf_sample_regs_user(struct perf_regs *regs_user,
-				  struct pt_regs *regs,
-				  struct pt_regs *regs_user_copy)
+				  struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
 	} else if (!(current->flags & PF_KTHREAD)) {
-		perf_get_regs_user(regs_user, regs, regs_user_copy);
+		perf_get_regs_user(regs_user, regs);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
 		regs_user->regs = NULL;
@@ -7083,8 +7075,7 @@
 	}
 
 	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
-		perf_sample_regs_user(&data->regs_user, regs,
-				      &data->regs_user_copy);
+		perf_sample_regs_user(&data->regs_user, regs);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
@@ -7186,6 +7177,7 @@
 		    struct perf_sample_data *data,
 		    struct pt_regs *regs,
 		    int (*output_begin)(struct perf_output_handle *,
+					struct perf_sample_data *,
 					struct perf_event *,
 					unsigned int))
 {
@@ -7198,7 +7190,7 @@
 
 	perf_prepare_sample(&header, data, event, regs);
 
-	err = output_begin(&handle, event, header.size);
+	err = output_begin(&handle, data, event, header.size);
 	if (err)
 		goto exit;
 
@@ -7264,7 +7256,7 @@
 	int ret;
 
 	perf_event_header__init_id(&read_event.header, &sample, event);
-	ret = perf_output_begin(&handle, event, read_event.header.size);
+	ret = perf_output_begin(&handle, &sample, event, read_event.header.size);
 	if (ret)
 		return;
 
@@ -7533,7 +7525,7 @@
 
 	perf_event_header__init_id(&task_event->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				task_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7636,7 +7628,7 @@
 		return;
 
 	perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				comm_event->event_id.header.size);
 
 	if (ret)
@@ -7736,7 +7728,7 @@
 
 	perf_event_header__init_id(&namespaces_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				namespaces_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7863,7 +7855,7 @@
 
 	perf_event_header__init_id(&cgroup_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				cgroup_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7989,7 +7981,7 @@
 	}
 
 	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				mmap_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -8299,7 +8291,7 @@
 	int ret;
 
 	perf_event_header__init_id(&rec.header, &sample, event);
-	ret = perf_output_begin(&handle, event, rec.header.size);
+	ret = perf_output_begin(&handle, &sample, event, rec.header.size);
 
 	if (ret)
 		return;
@@ -8333,7 +8325,7 @@
 
 	perf_event_header__init_id(&lost_samples_event.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				lost_samples_event.header.size);
 	if (ret)
 		return;
@@ -8388,7 +8380,7 @@
 
 	perf_event_header__init_id(&se->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event, se->event_id.header.size);
+	ret = perf_output_begin(&handle, &sample, event, se->event_id.header.size);
 	if (ret)
 		return;
 
@@ -8463,7 +8455,7 @@
 
 	perf_event_header__init_id(&throttle_event.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				throttle_event.header.size);
 	if (ret)
 		return;
@@ -8506,7 +8498,7 @@
 
 	perf_event_header__init_id(&ksymbol_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				ksymbol_event->event_id.header.size);
 	if (ret)
 		return;
@@ -8596,7 +8588,7 @@
 
 	perf_event_header__init_id(&bpf_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, data, event,
 				bpf_event->event_id.header.size);
 	if (ret)
 		return;
@@ -8705,7 +8697,8 @@
 
 	perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size);
+	ret = perf_output_begin(&handle, &sample, event,
+				text_poke_event->event_id.header.size);
 	if (ret)
 		return;
 
@@ -8786,7 +8779,7 @@
 	rec.tid	= perf_event_tid(event, current);
 
 	perf_event_header__init_id(&rec.header, &sample, event);
-	ret = perf_output_begin(&handle, event, rec.header.size);
+	ret = perf_output_begin(&handle, &sample, event, rec.header.size);
 
 	if (ret)
 		return;
@@ -10085,6 +10078,7 @@
 			if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) {
 				int fpos = token == IF_SRC_FILE ? 2 : 1;
 
+				kfree(filename);
 				filename = match_strdup(&args[fpos]);
 				if (!filename) {
 					ret = -ENOMEM;
@@ -10131,16 +10125,13 @@
 				 */
 				ret = -EOPNOTSUPP;
 				if (!event->ctx->task)
-					goto fail_free_name;
+					goto fail;
 
 				/* look up the path and grab its inode */
 				ret = kern_path(filename, LOOKUP_FOLLOW,
 						&filter->path);
 				if (ret)
-					goto fail_free_name;
-
-				kfree(filename);
-				filename = NULL;
+					goto fail;
 
 				ret = -EINVAL;
 				if (!filter->path.dentry ||
@@ -10160,13 +10151,13 @@
 	if (state != IF_STATE_ACTION)
 		goto fail;
 
+	kfree(filename);
 	kfree(orig);
 
 	return 0;
 
-fail_free_name:
-	kfree(filename);
 fail:
+	kfree(filename);
 	free_filters_list(filters);
 	kfree(orig);
 
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index fcbf561..228801e 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -205,16 +205,12 @@
 
 static inline int get_recursion_context(int *recursion)
 {
-	int rctx;
+	unsigned int pc = preempt_count();
+	unsigned char rctx = 0;
 
-	if (unlikely(in_nmi()))
-		rctx = 3;
-	else if (in_irq())
-		rctx = 2;
-	else if (in_softirq())
-		rctx = 1;
-	else
-		rctx = 0;
+	rctx += !!(pc & (NMI_MASK));
+	rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK));
+	rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
 
 	if (recursion[rctx])
 		return -1;
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 192b8ab..ef91ae7 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -147,6 +147,7 @@
 
 static __always_inline int
 __perf_output_begin(struct perf_output_handle *handle,
+		    struct perf_sample_data *data,
 		    struct perf_event *event, unsigned int size,
 		    bool backward)
 {
@@ -237,18 +238,16 @@
 	handle->size = (1UL << page_shift) - offset;
 
 	if (unlikely(have_lost)) {
-		struct perf_sample_data sample_data;
-
 		lost_event.header.size = sizeof(lost_event);
 		lost_event.header.type = PERF_RECORD_LOST;
 		lost_event.header.misc = 0;
 		lost_event.id          = event->id;
 		lost_event.lost        = local_xchg(&rb->lost, 0);
 
-		perf_event_header__init_id(&lost_event.header,
-					   &sample_data, event);
+		/* XXX mostly redundant; @data is already fully initializes */
+		perf_event_header__init_id(&lost_event.header, data, event);
 		perf_output_put(handle, lost_event);
-		perf_event__output_id_sample(event, handle, &sample_data);
+		perf_event__output_id_sample(event, handle, data);
 	}
 
 	return 0;
@@ -263,22 +262,25 @@
 }
 
 int perf_output_begin_forward(struct perf_output_handle *handle,
-			     struct perf_event *event, unsigned int size)
+			      struct perf_sample_data *data,
+			      struct perf_event *event, unsigned int size)
 {
-	return __perf_output_begin(handle, event, size, false);
+	return __perf_output_begin(handle, data, event, size, false);
 }
 
 int perf_output_begin_backward(struct perf_output_handle *handle,
+			       struct perf_sample_data *data,
 			       struct perf_event *event, unsigned int size)
 {
-	return __perf_output_begin(handle, event, size, true);
+	return __perf_output_begin(handle, data, event, size, true);
 }
 
 int perf_output_begin(struct perf_output_handle *handle,
+		      struct perf_sample_data *data,
 		      struct perf_event *event, unsigned int size)
 {
 
-	return __perf_output_begin(handle, event, size,
+	return __perf_output_begin(handle, data, event, size,
 				   unlikely(is_write_backward(event)));
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 87a2d51..1f236ed 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -454,7 +454,10 @@
 		mmap_read_unlock(mm);
 
 		self.task = current;
-		self.next = xchg(&core_state->dumper.next, &self);
+		if (self.task->flags & PF_SIGNALED)
+			self.next = xchg(&core_state->dumper.next, &self);
+		else
+			self.task = NULL;
 		/*
 		 * Implies mb(), the result of xchg() must be visible
 		 * to core_state->dumper.
diff --git a/kernel/fork.c b/kernel/fork.c
index 32083db..6d26638 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2167,14 +2167,9 @@
 	/* ok, now we should be set up.. */
 	p->pid = pid_nr(pid);
 	if (clone_flags & CLONE_THREAD) {
-		p->exit_signal = -1;
 		p->group_leader = current->group_leader;
 		p->tgid = current->tgid;
 	} else {
-		if (clone_flags & CLONE_PARENT)
-			p->exit_signal = current->group_leader->exit_signal;
-		else
-			p->exit_signal = args->exit_signal;
 		p->group_leader = p;
 		p->tgid = p->pid;
 	}
@@ -2218,9 +2213,14 @@
 	if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
 		p->real_parent = current->real_parent;
 		p->parent_exec_id = current->parent_exec_id;
+		if (clone_flags & CLONE_THREAD)
+			p->exit_signal = -1;
+		else
+			p->exit_signal = current->group_leader->exit_signal;
 	} else {
 		p->real_parent = current;
 		p->parent_exec_id = current->self_exec_id;
+		p->exit_signal = args->exit_signal;
 	}
 
 	klp_copy_process(p);
diff --git a/kernel/futex.c b/kernel/futex.c
index f8614ef..00259c7 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -788,8 +788,9 @@
 	 */
 	if (pi_state->owner) {
 		struct task_struct *owner;
+		unsigned long flags;
 
-		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+		raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags);
 		owner = pi_state->owner;
 		if (owner) {
 			raw_spin_lock(&owner->pi_lock);
@@ -797,7 +798,7 @@
 			raw_spin_unlock(&owner->pi_lock);
 		}
 		rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner);
-		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+		raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags);
 	}
 
 	if (current->pi_state_cache) {
@@ -2380,10 +2381,22 @@
 		}
 
 		/*
-		 * Since we just failed the trylock; there must be an owner.
+		 * The trylock just failed, so either there is an owner or
+		 * there is a higher priority waiter than this one.
 		 */
 		newowner = rt_mutex_owner(&pi_state->pi_mutex);
-		BUG_ON(!newowner);
+		/*
+		 * If the higher priority waiter has not yet taken over the
+		 * rtmutex then newowner is NULL. We can't return here with
+		 * that state because it's inconsistent vs. the user space
+		 * state. So drop the locks and try again. It's a valid
+		 * situation and not any different from the other retry
+		 * conditions.
+		 */
+		if (unlikely(!newowner)) {
+			err = -EAGAIN;
+			goto handle_err;
+		}
 	} else {
 		WARN_ON_ONCE(argowner != current);
 		if (oldowner == current) {
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index ce76f49..396ebae 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -225,8 +225,7 @@
  * Process updating of timeout sysctl
  */
 int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
-				  void __user *buffer,
-				  size_t *lenp, loff_t *ppos)
+				  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret;
 
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 10a5aff..164a031 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -82,6 +82,7 @@
 # Generic IRQ IPI support
 config GENERIC_IRQ_IPI
 	bool
+	select IRQ_DOMAIN_HIERARCHY
 
 # Generic MSI interrupt support
 config GENERIC_MSI_IRQ
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 8a12a25..41fdbb7 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1249,7 +1249,13 @@
 
 	*head = &kretprobe_inst_table[hash];
 	hlist_lock = kretprobe_table_lock_ptr(hash);
-	raw_spin_lock_irqsave(hlist_lock, *flags);
+	/*
+	 * Nested is a workaround that will soon not be needed.
+	 * There's other protections that make sure the same lock
+	 * is not taken on the same CPU that lockdep is unaware of.
+	 * Differentiate when it is taken in NMI context.
+	 */
+	raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi());
 }
 NOKPROBE_SYMBOL(kretprobe_hash_lock);
 
@@ -1258,7 +1264,13 @@
 __acquires(hlist_lock)
 {
 	raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
-	raw_spin_lock_irqsave(hlist_lock, *flags);
+	/*
+	 * Nested is a workaround that will soon not be needed.
+	 * There's other protections that make sure the same lock
+	 * is not taken on the same CPU that lockdep is unaware of.
+	 * Differentiate when it is taken in NMI context.
+	 */
+	raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi());
 }
 NOKPROBE_SYMBOL(kretprobe_table_lock);
 
@@ -2028,7 +2040,12 @@
 
 	/* TODO: consider to only swap the RA after the last pre_handler fired */
 	hash = hash_ptr(current, KPROBE_HASH_BITS);
-	raw_spin_lock_irqsave(&rp->lock, flags);
+	/*
+	 * Nested is a workaround that will soon not be needed.
+	 * There's other protections that make sure the same lock
+	 * is not taken on the same CPU that lockdep is unaware of.
+	 */
+	raw_spin_lock_irqsave_nested(&rp->lock, flags, 1);
 	if (!hlist_empty(&rp->free_instances)) {
 		ri = hlist_entry(rp->free_instances.first,
 				struct kretprobe_instance, hlist);
@@ -2039,7 +2056,7 @@
 		ri->task = current;
 
 		if (rp->entry_handler && rp->entry_handler(ri, regs)) {
-			raw_spin_lock_irqsave(&rp->lock, flags);
+			raw_spin_lock_irqsave_nested(&rp->lock, flags, 1);
 			hlist_add_head(&ri->hlist, &rp->free_instances);
 			raw_spin_unlock_irqrestore(&rp->lock, flags);
 			return 0;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index e29773c..933a625 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -897,7 +897,8 @@
 	/* Move the work from worker->delayed_work_list. */
 	WARN_ON_ONCE(list_empty(&work->node));
 	list_del_init(&work->node);
-	kthread_insert_work(worker, work, &worker->work_list);
+	if (!work->canceling)
+		kthread_insert_work(worker, work, &worker->work_list);
 
 	raw_spin_unlock_irqrestore(&worker->lock, flags);
 }
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index b71ad8d..d9fb9e1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2765,7 +2765,9 @@
  * (Note that this has to be done separately, because the graph cannot
  * detect such classes of deadlocks.)
  *
- * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read
+ * Returns: 0 on deadlock detected, 1 on OK, 2 if another lock with the same
+ * lock class is held but nest_lock is also held, i.e. we rely on the
+ * nest_lock to avoid the deadlock.
  */
 static int
 check_deadlock(struct task_struct *curr, struct held_lock *next)
@@ -2788,7 +2790,7 @@
 		 * lock class (i.e. read_lock(lock)+read_lock(lock)):
 		 */
 		if ((next->read == 2) && prev->read)
-			return 2;
+			continue;
 
 		/*
 		 * We're holding the nest_lock, which serializes this lock's
@@ -3593,15 +3595,12 @@
 		if (!ret)
 			return 0;
 		/*
-		 * Mark recursive read, as we jump over it when
-		 * building dependencies (just like we jump over
-		 * trylock entries):
-		 */
-		if (ret == 2)
-			hlock->read = 2;
-		/*
 		 * Add dependency only if this lock is not the head
-		 * of the chain, and if it's not a secondary read-lock:
+		 * of the chain, and if the new lock introduces no more
+		 * lock dependency (because we already hold a lock with the
+		 * same lock class) nor deadlock (because the nest_lock
+		 * serializes nesting locks), see the comments for
+		 * check_deadlock().
 		 */
 		if (!chain_head && ret != 2) {
 			if (!check_prevs_add(curr, hlock))
diff --git a/kernel/panic.c b/kernel/panic.c
index 396142e..332736a 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -605,7 +605,8 @@
 		panic("panic_on_warn set ...\n");
 	}
 
-	dump_stack();
+	if (!regs)
+		dump_stack();
 
 	print_irqtrace_events(current);
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 2a52f42..bd04b09 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -4077,7 +4077,6 @@
 	smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
 /*
  * The outgoing function has no further need of RCU, so remove it from
  * the rcu_node tree's ->qsmaskinitnext bit masks.
@@ -4117,6 +4116,7 @@
 	rdp->cpu_started = false;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * The outgoing CPU has just passed through the dying-idle state, and we
  * are being invoked from the CPU that was IPIed to continue the offline
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 0fde39b8..ca21d28 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -249,13 +249,16 @@
 
 /*
  * Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each.
+ * sections, printing out the tid of each of the first few of them.
  */
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
 {
+	int i = 0;
 	int ndetected = 0;
 	struct rcu_stall_chk_rdr rscr;
 	struct task_struct *t;
+	struct task_struct *ts[8];
 
 	if (!rcu_preempt_blocked_readers_cgp(rnp))
 		return 0;
@@ -264,6 +267,14 @@
 	t = list_entry(rnp->gp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+		get_task_struct(t);
+		ts[i++] = t;
+		if (i >= ARRAY_SIZE(ts))
+			break;
+	}
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	for (i--; i; i--) {
+		t = ts[i];
 		if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr))
 			pr_cont(" P%d", t->pid);
 		else
@@ -273,6 +284,7 @@
 				".q"[rscr.rs.b.need_qs],
 				".e"[rscr.rs.b.exp_hint],
 				".l"[rscr.on_blkd_list]);
+		put_task_struct(t);
 		ndetected++;
 	}
 	pr_cont("\n");
@@ -293,8 +305,9 @@
  * Because preemptible RCU does not exist, we never have to check for
  * tasks blocked within RCU read-side critical sections.
  */
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
 {
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	return 0;
 }
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
@@ -472,7 +485,6 @@
 	pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
 	rcu_for_each_leaf_node(rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		ndetected += rcu_print_task_stall(rnp);
 		if (rnp->qsmask != 0) {
 			for_each_leaf_node_possible_cpu(rnp, cpu)
 				if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
@@ -480,7 +492,7 @@
 					ndetected++;
 				}
 		}
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		ndetected += rcu_print_task_stall(rnp, flags); // Releases rnp->lock.
 	}
 
 	for_each_possible_cpu(cpu)
diff --git a/kernel/reboot.c b/kernel/reboot.c
index e7b78d5..af6f23d 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -551,22 +551,22 @@
 			break;
 
 		case 's':
-		{
-			int rc;
-
-			if (isdigit(*(str+1))) {
-				rc = kstrtoint(str+1, 0, &reboot_cpu);
-				if (rc)
-					return rc;
-			} else if (str[1] == 'm' && str[2] == 'p' &&
-				   isdigit(*(str+3))) {
-				rc = kstrtoint(str+3, 0, &reboot_cpu);
-				if (rc)
-					return rc;
-			} else
+			if (isdigit(*(str+1)))
+				reboot_cpu = simple_strtoul(str+1, NULL, 0);
+			else if (str[1] == 'm' && str[2] == 'p' &&
+							isdigit(*(str+3)))
+				reboot_cpu = simple_strtoul(str+3, NULL, 0);
+			else
 				*mode = REBOOT_SOFT;
+			if (reboot_cpu >= num_possible_cpus()) {
+				pr_err("Ignoring the CPU number in reboot= option. "
+				       "CPU %d exceeds possible cpu number %d\n",
+				       reboot_cpu, num_possible_cpus());
+				reboot_cpu = 0;
+				break;
+			}
 			break;
-		}
+
 		case 'g':
 			*mode = REBOOT_GPIO;
 			break;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index c03a5775..97d318b 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -102,9 +102,12 @@
 static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
 				   unsigned int next_freq)
 {
-	if (sg_policy->next_freq == next_freq &&
-	    !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
-		return false;
+	if (!sg_policy->need_freq_update) {
+		if (sg_policy->next_freq == next_freq)
+			return false;
+	} else {
+		sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+	}
 
 	sg_policy->next_freq = next_freq;
 	sg_policy->last_freq_update_time = time;
@@ -162,11 +165,9 @@
 
 	freq = map_util_freq(util, freq, max);
 
-	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update &&
-	    !cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS))
+	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
 		return sg_policy->next_freq;
 
-	sg_policy->need_freq_update = false;
 	sg_policy->cached_raw_freq = freq;
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
@@ -442,7 +443,6 @@
 	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
 	unsigned long util, max;
 	unsigned int next_f;
-	bool busy;
 	unsigned int cached_freq = sg_policy->cached_raw_freq;
 
 	sugov_iowait_boost(sg_cpu, time, flags);
@@ -453,9 +453,6 @@
 	if (!sugov_should_update_freq(sg_policy, time))
 		return;
 
-	/* Limits may have changed, don't skip frequency update */
-	busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
-
 	util = sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
 	util = sugov_iowait_apply(sg_cpu, time, util, max);
@@ -464,7 +461,7 @@
 	 * Do not reduce the frequency if the CPU has not been idle
 	 * recently, as the reduction is likely to be premature then.
 	 */
-	if (busy && next_f < sg_policy->next_freq) {
+	if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
 		next_f = sg_policy->next_freq;
 
 		/* Restore cached freq as next_freq has changed */
@@ -829,9 +826,10 @@
 	sg_policy->next_freq			= 0;
 	sg_policy->work_in_progress		= false;
 	sg_policy->limits_changed		= false;
-	sg_policy->need_freq_update		= false;
 	sg_policy->cached_raw_freq		= 0;
 
+	sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+
 	for_each_cpu(cpu, policy->cpus) {
 		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
 
@@ -883,7 +881,7 @@
 struct cpufreq_governor schedutil_gov = {
 	.name			= "schedutil",
 	.owner			= THIS_MODULE,
-	.dynamic_switching	= true,
+	.flags			= CPUFREQ_GOV_DYNAMIC_SWITCHING,
 	.init			= sugov_init,
 	.exit			= sugov_exit,
 	.start			= sugov_start,
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 0655524..2357921 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -251,7 +251,7 @@
 	unsigned long flags = *(unsigned long *)table->data;
 	size_t data_size = 0;
 	size_t len = 0;
-	char *tmp;
+	char *tmp, *buf;
 	int idx;
 
 	if (write)
@@ -269,17 +269,17 @@
 		return 0;
 	}
 
-	tmp = kcalloc(data_size + 1, sizeof(*tmp), GFP_KERNEL);
-	if (!tmp)
+	buf = kcalloc(data_size + 1, sizeof(*buf), GFP_KERNEL);
+	if (!buf)
 		return -ENOMEM;
 
 	for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
 		char *name = sd_flag_debug[idx].name;
 
-		len += snprintf(tmp + len, strlen(name) + 2, "%s ", name);
+		len += snprintf(buf + len, strlen(name) + 2, "%s ", name);
 	}
 
-	tmp += *ppos;
+	tmp = buf + *ppos;
 	len -= *ppos;
 
 	if (len > *lenp)
@@ -294,7 +294,7 @@
 	*lenp = len;
 	*ppos += len;
 
-	kfree(tmp);
+	kfree(buf);
 
 	return 0;
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 290f9e3..8917d2d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6172,21 +6172,21 @@
 static int
 select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 {
-	unsigned long best_cap = 0;
+	unsigned long task_util, best_cap = 0;
 	int cpu, best_cpu = -1;
 	struct cpumask *cpus;
 
-	sync_entity_load_avg(&p->se);
-
 	cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
 
+	task_util = uclamp_task_util(p);
+
 	for_each_cpu_wrap(cpu, cpus, target) {
 		unsigned long cpu_cap = capacity_of(cpu);
 
 		if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
 			continue;
-		if (task_fits_capacity(p, cpu_cap))
+		if (fits_capacity(task_util, cpu_cap))
 			return cpu;
 
 		if (cpu_cap > best_cap) {
@@ -6198,44 +6198,42 @@
 	return best_cpu;
 }
 
+static inline bool asym_fits_capacity(int task_util, int cpu)
+{
+	if (static_branch_unlikely(&sched_asym_cpucapacity))
+		return fits_capacity(task_util, capacity_of(cpu));
+
+	return true;
+}
+
 /*
  * Try and locate an idle core/thread in the LLC cache domain.
  */
 static int select_idle_sibling(struct task_struct *p, int prev, int target)
 {
 	struct sched_domain *sd;
+	unsigned long task_util;
 	int i, recent_used_cpu;
 
 	/*
-	 * For asymmetric CPU capacity systems, our domain of interest is
-	 * sd_asym_cpucapacity rather than sd_llc.
+	 * On asymmetric system, update task utilization because we will check
+	 * that the task fits with cpu's capacity.
 	 */
 	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
-		sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
-		/*
-		 * On an asymmetric CPU capacity system where an exclusive
-		 * cpuset defines a symmetric island (i.e. one unique
-		 * capacity_orig value through the cpuset), the key will be set
-		 * but the CPUs within that cpuset will not have a domain with
-		 * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
-		 * capacity path.
-		 */
-		if (!sd)
-			goto symmetric;
-
-		i = select_idle_capacity(p, sd, target);
-		return ((unsigned)i < nr_cpumask_bits) ? i : target;
+		sync_entity_load_avg(&p->se);
+		task_util = uclamp_task_util(p);
 	}
 
-symmetric:
-	if (available_idle_cpu(target) || sched_idle_cpu(target))
+	if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
+	    asym_fits_capacity(task_util, target))
 		return target;
 
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:
 	 */
 	if (prev != target && cpus_share_cache(prev, target) &&
-	    (available_idle_cpu(prev) || sched_idle_cpu(prev)))
+	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
+	    asym_fits_capacity(task_util, prev))
 		return prev;
 
 	/*
@@ -6258,7 +6256,8 @@
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
-	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
+	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
+	    asym_fits_capacity(task_util, recent_used_cpu)) {
 		/*
 		 * Replace recent_used_cpu with prev as it is a potential
 		 * candidate for the next wake:
@@ -6267,6 +6266,26 @@
 		return recent_used_cpu;
 	}
 
+	/*
+	 * For asymmetric CPU capacity systems, our domain of interest is
+	 * sd_asym_cpucapacity rather than sd_llc.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+		sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
+		/*
+		 * On an asymmetric CPU capacity system where an exclusive
+		 * cpuset defines a symmetric island (i.e. one unique
+		 * capacity_orig value through the cpuset), the key will be set
+		 * but the CPUs within that cpuset will not have a domain with
+		 * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
+		 * capacity path.
+		 */
+		if (sd) {
+			i = select_idle_capacity(p, sd, target);
+			return ((unsigned)i < nr_cpumask_bits) ? i : target;
+		}
+	}
+
 	sd = rcu_dereference(per_cpu(sd_llc, target));
 	if (!sd)
 		return target;
@@ -9031,7 +9050,8 @@
 	 * emptying busiest.
 	 */
 	if (local->group_type == group_has_spare) {
-		if (busiest->group_type > group_fully_busy) {
+		if ((busiest->group_type > group_fully_busy) &&
+		    !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) {
 			/*
 			 * If busiest is overloaded, try to fill spare
 			 * capacity. This might end up creating spare capacity
diff --git a/kernel/signal.c b/kernel/signal.c
index a38b3ed..ef8f2a2 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -391,16 +391,17 @@
 
 void task_join_group_stop(struct task_struct *task)
 {
+	unsigned long mask = current->jobctl & JOBCTL_STOP_SIGMASK;
+	struct signal_struct *sig = current->signal;
+
+	if (sig->group_stop_count) {
+		sig->group_stop_count++;
+		mask |= JOBCTL_STOP_CONSUME;
+	} else if (!(sig->flags & SIGNAL_STOP_STOPPED))
+		return;
+
 	/* Have the new thread join an on-going signal group stop */
-	unsigned long jobctl = current->jobctl;
-	if (jobctl & JOBCTL_STOP_PENDING) {
-		struct signal_struct *sig = current->signal;
-		unsigned long signr = jobctl & JOBCTL_STOP_SIGMASK;
-		unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
-		if (task_set_jobctl_pending(task, signr | gstop)) {
-			sig->group_stop_count++;
-		}
-	}
+	task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING);
 }
 
 /*
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 7f45fd9..dc83b3f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -438,14 +438,16 @@
 };
 /*
  * Used for which event context the event is in.
- *  NMI     = 0
- *  IRQ     = 1
- *  SOFTIRQ = 2
- *  NORMAL  = 3
+ *  TRANSITION = 0
+ *  NMI     = 1
+ *  IRQ     = 2
+ *  SOFTIRQ = 3
+ *  NORMAL  = 4
  *
  * See trace_recursive_lock() comment below for more details.
  */
 enum {
+	RB_CTX_TRANSITION,
 	RB_CTX_NMI,
 	RB_CTX_IRQ,
 	RB_CTX_SOFTIRQ,
@@ -3014,10 +3016,10 @@
  * a bit of overhead in something as critical as function tracing,
  * we use a bitmask trick.
  *
- *  bit 0 =  NMI context
- *  bit 1 =  IRQ context
- *  bit 2 =  SoftIRQ context
- *  bit 3 =  normal context.
+ *  bit 1 =  NMI context
+ *  bit 2 =  IRQ context
+ *  bit 3 =  SoftIRQ context
+ *  bit 4 =  normal context.
  *
  * This works because this is the order of contexts that can
  * preempt other contexts. A SoftIRQ never preempts an IRQ
@@ -3040,6 +3042,30 @@
  * The least significant bit can be cleared this way, and it
  * just so happens that it is the same bit corresponding to
  * the current context.
+ *
+ * Now the TRANSITION bit breaks the above slightly. The TRANSITION bit
+ * is set when a recursion is detected at the current context, and if
+ * the TRANSITION bit is already set, it will fail the recursion.
+ * This is needed because there's a lag between the changing of
+ * interrupt context and updating the preempt count. In this case,
+ * a false positive will be found. To handle this, one extra recursion
+ * is allowed, and this is done by the TRANSITION bit. If the TRANSITION
+ * bit is already set, then it is considered a recursion and the function
+ * ends. Otherwise, the TRANSITION bit is set, and that bit is returned.
+ *
+ * On the trace_recursive_unlock(), the TRANSITION bit will be the first
+ * to be cleared. Even if it wasn't the context that set it. That is,
+ * if an interrupt comes in while NORMAL bit is set and the ring buffer
+ * is called before preempt_count() is updated, since the check will
+ * be on the NORMAL bit, the TRANSITION bit will then be set. If an
+ * NMI then comes in, it will set the NMI bit, but when the NMI code
+ * does the trace_recursive_unlock() it will clear the TRANSTION bit
+ * and leave the NMI bit set. But this is fine, because the interrupt
+ * code that set the TRANSITION bit will then clear the NMI bit when it
+ * calls trace_recursive_unlock(). If another NMI comes in, it will
+ * set the TRANSITION bit and continue.
+ *
+ * Note: The TRANSITION bit only handles a single transition between context.
  */
 
 static __always_inline int
@@ -3055,8 +3081,16 @@
 		bit = pc & NMI_MASK ? RB_CTX_NMI :
 			pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ;
 
-	if (unlikely(val & (1 << (bit + cpu_buffer->nest))))
-		return 1;
+	if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) {
+		/*
+		 * It is possible that this was called by transitioning
+		 * between interrupt context, and preempt_count() has not
+		 * been updated yet. In this case, use the TRANSITION bit.
+		 */
+		bit = RB_CTX_TRANSITION;
+		if (val & (1 << (bit + cpu_buffer->nest)))
+			return 1;
+	}
 
 	val |= (1 << (bit + cpu_buffer->nest));
 	cpu_buffer->current_context = val;
@@ -3071,8 +3105,8 @@
 		cpu_buffer->current_context - (1 << cpu_buffer->nest);
 }
 
-/* The recursive locking above uses 4 bits */
-#define NESTED_BITS 4
+/* The recursive locking above uses 5 bits */
+#define NESTED_BITS 5
 
 /**
  * ring_buffer_nest_start - Allow to trace while nested
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5289717..410cfeb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2750,7 +2750,7 @@
 	/*
 	 * If tracing is off, but we have triggers enabled
 	 * we still need to look at the event data. Use the temp_buffer
-	 * to store the trace event for the tigger to use. It's recusive
+	 * to store the trace event for the trigger to use. It's recursive
 	 * safe and will not be recorded anywhere.
 	 */
 	if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) {
@@ -2952,7 +2952,7 @@
 	stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1;
 
 	/* This should never happen. If it does, yell once and skip */
-	if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING))
+	if (WARN_ON_ONCE(stackidx >= FTRACE_KSTACK_NESTING))
 		goto out;
 
 	/*
@@ -3132,7 +3132,7 @@
 
 	/* Interrupts must see nesting incremented before we use the buffer */
 	barrier();
-	return &buffer->buffer[buffer->nesting][0];
+	return &buffer->buffer[buffer->nesting - 1][0];
 }
 
 static void put_trace_buf(void)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f3f5e77..1dadef4 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -637,6 +637,12 @@
 	 * function is called to clear it.
 	 */
 	TRACE_GRAPH_NOTRACE_BIT,
+
+	/*
+	 * When transitioning between context, the preempt_count() may
+	 * not be correct. Allow for a single recursion to cover this case.
+	 */
+	TRACE_TRANSITION_BIT,
 };
 
 #define trace_recursion_set(bit)	do { (current)->trace_recursion |= (1<<(bit)); } while (0)
@@ -691,14 +697,27 @@
 		return 0;
 
 	bit = trace_get_context_bit() + start;
-	if (unlikely(val & (1 << bit)))
-		return -1;
+	if (unlikely(val & (1 << bit))) {
+		/*
+		 * It could be that preempt_count has not been updated during
+		 * a switch between contexts. Allow for a single recursion.
+		 */
+		bit = TRACE_TRANSITION_BIT;
+		if (trace_recursion_test(bit))
+			return -1;
+		trace_recursion_set(bit);
+		barrier();
+		return bit + 1;
+	}
+
+	/* Normal check passed, clear the transition to allow it again */
+	trace_recursion_clear(TRACE_TRANSITION_BIT);
 
 	val |= 1 << bit;
 	current->trace_recursion = val;
 	barrier();
 
-	return bit;
+	return bit + 1;
 }
 
 static __always_inline void trace_clear_recursion(int bit)
@@ -708,6 +727,7 @@
 	if (!bit)
 		return;
 
+	bit--;
 	bit = 1 << bit;
 	val &= ~bit;
 
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 84b7cab..881df99 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -584,7 +584,7 @@
 {
 	struct synth_field *field;
 	const char *prefix = NULL, *field_type = argv[0], *field_name, *array;
-	int len, ret = 0;
+	int len, ret = -ENOMEM;
 	struct seq_buf s;
 	ssize_t size;
 
@@ -617,10 +617,9 @@
 		len--;
 
 	field->name = kmemdup_nul(field_name, len, GFP_KERNEL);
-	if (!field->name) {
-		ret = -ENOMEM;
+	if (!field->name)
 		goto free;
-	}
+
 	if (!is_good_name(field->name)) {
 		synth_err(SYNTH_ERR_BAD_NAME, errpos(field_name));
 		ret = -EINVAL;
@@ -638,10 +637,9 @@
 		len += strlen(prefix);
 
 	field->type = kzalloc(len, GFP_KERNEL);
-	if (!field->type) {
-		ret = -ENOMEM;
+	if (!field->type)
 		goto free;
-	}
+
 	seq_buf_init(&s, field->type, len);
 	if (prefix)
 		seq_buf_puts(&s, prefix);
@@ -653,6 +651,7 @@
 	}
 	if (WARN_ON_ONCE(!seq_buf_buffer_left(&s)))
 		goto free;
+
 	s.buffer[s.len] = '\0';
 
 	size = synth_field_size(field->type);
@@ -666,10 +665,8 @@
 
 			len = sizeof("__data_loc ") + strlen(field->type) + 1;
 			type = kzalloc(len, GFP_KERNEL);
-			if (!type) {
-				ret = -ENOMEM;
+			if (!type)
 				goto free;
-			}
 
 			seq_buf_init(&s, type, len);
 			seq_buf_puts(&s, "__data_loc ");
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index b5e3496..4738ad4 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -492,8 +492,13 @@
 	unregister_ftrace_function(&test_rec_probe);
 
 	ret = -1;
-	if (trace_selftest_recursion_cnt != 1) {
-		pr_cont("*callback not called once (%d)* ",
+	/*
+	 * Recursion allows for transitions between context,
+	 * and may call the callback twice.
+	 */
+	if (trace_selftest_recursion_cnt != 1 &&
+	    trace_selftest_recursion_cnt != 2) {
+		pr_cont("*callback not called once (or twice) (%d)* ",
 			trace_selftest_recursion_cnt);
 		goto out;
 	}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 5abb5b2..7110906 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -44,8 +44,6 @@
 int __read_mostly watchdog_thresh = 10;
 static int __read_mostly nmi_watchdog_available;
 
-static struct cpumask watchdog_allowed_mask __read_mostly;
-
 struct cpumask watchdog_cpumask __read_mostly;
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 
@@ -162,6 +160,8 @@
 int __read_mostly sysctl_softlockup_all_cpu_backtrace;
 #endif
 
+static struct cpumask watchdog_allowed_mask __read_mostly;
+
 /* Global variables, exported for sysctl */
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
diff --git a/lib/crc32test.c b/lib/crc32test.c
index 97d6a57..61ddce2 100644
--- a/lib/crc32test.c
+++ b/lib/crc32test.c
@@ -683,7 +683,6 @@
 
 	/* reduce OS noise */
 	local_irq_save(flags);
-	local_irq_disable();
 
 	nsec = ktime_get_ns();
 	for (i = 0; i < 100; i++) {
@@ -694,7 +693,6 @@
 	nsec = ktime_get_ns() - nsec;
 
 	local_irq_restore(flags);
-	local_irq_enable();
 
 	pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS);
 
@@ -768,7 +766,6 @@
 
 	/* reduce OS noise */
 	local_irq_save(flags);
-	local_irq_disable();
 
 	nsec = ktime_get_ns();
 	for (i = 0; i < 100; i++) {
@@ -783,7 +780,6 @@
 	nsec = ktime_get_ns() - nsec;
 
 	local_irq_restore(flags);
-	local_irq_enable();
 
 	pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n",
 		 CRC_LE_BITS, CRC_BE_BITS);
diff --git a/lib/fonts/font_10x18.c b/lib/fonts/font_10x18.c
index 0e2deac..e02f9df 100644
--- a/lib/fonts/font_10x18.c
+++ b/lib/fonts/font_10x18.c
@@ -8,7 +8,7 @@
 
 #define FONTDATAMAX 9216
 
-static struct font_data fontdata_10x18 = {
+static const struct font_data fontdata_10x18 = {
 	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, 0x00, /* 0000000000 */
diff --git a/lib/fonts/font_6x10.c b/lib/fonts/font_6x10.c
index 87da8ac..6e3c4b7 100644
--- a/lib/fonts/font_6x10.c
+++ b/lib/fonts/font_6x10.c
@@ -3,7 +3,7 @@
 
 #define FONTDATAMAX 2560
 
-static struct font_data fontdata_6x10 = {
+static const struct font_data fontdata_6x10 = {
 	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
diff --git a/lib/fonts/font_6x11.c b/lib/fonts/font_6x11.c
index 5e975df..2d22a24 100644
--- a/lib/fonts/font_6x11.c
+++ b/lib/fonts/font_6x11.c
@@ -9,7 +9,7 @@
 
 #define FONTDATAMAX (11*256)
 
-static struct font_data fontdata_6x11 = {
+static const struct font_data fontdata_6x11 = {
 	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
diff --git a/lib/fonts/font_6x8.c b/lib/fonts/font_6x8.c
index 700039a9..e7442a0 100644
--- a/lib/fonts/font_6x8.c
+++ b/lib/fonts/font_6x8.c
@@ -3,7 +3,7 @@
 
 #define FONTDATAMAX 2048
 
-static struct font_data fontdata_6x8 = {
+static const struct font_data fontdata_6x8 = {
 	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 000000 */
diff --git a/lib/fonts/font_7x14.c b/lib/fonts/font_7x14.c
index 86d298f..9cc7ae2 100644
--- a/lib/fonts/font_7x14.c
+++ b/lib/fonts/font_7x14.c
@@ -8,7 +8,7 @@
 
 #define FONTDATAMAX 3584
 
-static struct font_data fontdata_7x14 = {
+static const struct font_data fontdata_7x14 = {
 	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 0000000 */
diff --git a/lib/fonts/font_8x16.c b/lib/fonts/font_8x16.c
index 37cedd3..bab25dc 100644
--- a/lib/fonts/font_8x16.c
+++ b/lib/fonts/font_8x16.c
@@ -10,7 +10,7 @@
 
 #define FONTDATAMAX 4096
 
-static struct font_data fontdata_8x16 = {
+static const struct font_data fontdata_8x16 = {
 	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
diff --git a/lib/fonts/font_8x8.c b/lib/fonts/font_8x8.c
index 8ab6955..109d057 100644
--- a/lib/fonts/font_8x8.c
+++ b/lib/fonts/font_8x8.c
@@ -9,7 +9,7 @@
 
 #define FONTDATAMAX 2048
 
-static struct font_data fontdata_8x8 = {
+static const struct font_data fontdata_8x8 = {
 	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, /* 00000000 */
diff --git a/lib/fonts/font_acorn_8x8.c b/lib/fonts/font_acorn_8x8.c
index 069b3e8..fb395f0 100644
--- a/lib/fonts/font_acorn_8x8.c
+++ b/lib/fonts/font_acorn_8x8.c
@@ -5,7 +5,7 @@
 
 #define FONTDATAMAX 2048
 
-static struct font_data acorndata_8x8 = {
+static const struct font_data acorndata_8x8 = {
 { 0, 0, FONTDATAMAX, 0 }, {
 /* 00 */  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* ^@ */
 /* 01 */  0x7e, 0x81, 0xa5, 0x81, 0xbd, 0x99, 0x81, 0x7e, /* ^A */
diff --git a/lib/fonts/font_mini_4x6.c b/lib/fonts/font_mini_4x6.c
index 1449876..592774a 100644
--- a/lib/fonts/font_mini_4x6.c
+++ b/lib/fonts/font_mini_4x6.c
@@ -43,7 +43,7 @@
 
 #define FONTDATAMAX 1536
 
-static struct font_data fontdata_mini_4x6 = {
+static const struct font_data fontdata_mini_4x6 = {
 	{ 0, 0, FONTDATAMAX, 0 }, {
 	/*{*/
 	  	/*   Char 0: ' '  */
diff --git a/lib/fonts/font_pearl_8x8.c b/lib/fonts/font_pearl_8x8.c
index 32d6555..a6f95eb 100644
--- a/lib/fonts/font_pearl_8x8.c
+++ b/lib/fonts/font_pearl_8x8.c
@@ -14,7 +14,7 @@
 
 #define FONTDATAMAX 2048
 
-static struct font_data fontdata_pearl8x8 = {
+static const struct font_data fontdata_pearl8x8 = {
    { 0, 0, FONTDATAMAX, 0 }, {
    /* 0 0x00 '^@' */
    0x00, /* 00000000 */
diff --git a/lib/fonts/font_sun12x22.c b/lib/fonts/font_sun12x22.c
index 641a6b4..a5b65bd 100644
--- a/lib/fonts/font_sun12x22.c
+++ b/lib/fonts/font_sun12x22.c
@@ -3,7 +3,7 @@
 
 #define FONTDATAMAX 11264
 
-static struct font_data fontdata_sun12x22 = {
+static const struct font_data fontdata_sun12x22 = {
 	{ 0, 0, FONTDATAMAX, 0 }, {
 	/* 0 0x00 '^@' */
 	0x00, 0x00, /* 000000000000 */
diff --git a/lib/fonts/font_sun8x16.c b/lib/fonts/font_sun8x16.c
index 193fe6d..e577e76 100644
--- a/lib/fonts/font_sun8x16.c
+++ b/lib/fonts/font_sun8x16.c
@@ -3,7 +3,7 @@
 
 #define FONTDATAMAX 4096
 
-static struct font_data fontdata_sun8x16 = {
+static const struct font_data fontdata_sun8x16 = {
 { 0, 0, FONTDATAMAX, 0 }, {
 /* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
 /* */ 0x00,0x00,0x7e,0x81,0xa5,0x81,0x81,0xbd,0x99,0x81,0x81,0x7e,0x00,0x00,0x00,0x00,
diff --git a/lib/fonts/font_ter16x32.c b/lib/fonts/font_ter16x32.c
index 91b9c28..f7c3abb 100644
--- a/lib/fonts/font_ter16x32.c
+++ b/lib/fonts/font_ter16x32.c
@@ -4,7 +4,7 @@
 
 #define FONTDATAMAX 16384
 
-static struct font_data fontdata_ter16x32 = {
+static const struct font_data fontdata_ter16x32 = {
 	{ 0, 0, FONTDATAMAX, 0 }, {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x7f, 0xfc, 0x7f, 0xfc,
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 63c2617..662f862 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -216,6 +216,12 @@
 		u64 words[2];
 	} *ptr1, *ptr2;
 
+	/* This test is specifically crafted for the generic mode. */
+	if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+		kunit_info(test, "CONFIG_KASAN_GENERIC required\n");
+		return;
+	}
+
 	ptr1 = kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1);
 
@@ -227,6 +233,23 @@
 	kfree(ptr2);
 }
 
+static void kmalloc_uaf_16(struct kunit *test)
+{
+	struct {
+		u64 words[2];
+	} *ptr1, *ptr2;
+
+	ptr1 = kmalloc(sizeof(*ptr1), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1);
+
+	ptr2 = kmalloc(sizeof(*ptr2), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2);
+	kfree(ptr2);
+
+	KUNIT_EXPECT_KASAN_FAIL(test, *ptr1 = *ptr2);
+	kfree(ptr1);
+}
+
 static void kmalloc_oob_memset_2(struct kunit *test)
 {
 	char *ptr;
@@ -429,6 +452,12 @@
 	volatile int i = 3;
 	char *p = &global_array[ARRAY_SIZE(global_array) + i];
 
+	/* Only generic mode instruments globals. */
+	if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+		kunit_info(test, "CONFIG_KASAN_GENERIC required");
+		return;
+	}
+
 	KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p);
 }
 
@@ -467,6 +496,12 @@
 	char alloca_array[i];
 	char *p = alloca_array - 1;
 
+	/* Only generic mode instruments dynamic allocas. */
+	if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+		kunit_info(test, "CONFIG_KASAN_GENERIC required");
+		return;
+	}
+
 	if (!IS_ENABLED(CONFIG_KASAN_STACK)) {
 		kunit_info(test, "CONFIG_KASAN_STACK is not enabled");
 		return;
@@ -481,6 +516,12 @@
 	char alloca_array[i];
 	char *p = alloca_array + i;
 
+	/* Only generic mode instruments dynamic allocas. */
+	if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+		kunit_info(test, "CONFIG_KASAN_GENERIC required");
+		return;
+	}
+
 	if (!IS_ENABLED(CONFIG_KASAN_STACK)) {
 		kunit_info(test, "CONFIG_KASAN_STACK is not enabled");
 		return;
@@ -551,6 +592,9 @@
 		return;
 	}
 
+	if (OOB_TAG_OFF)
+		size = round_up(size, OOB_TAG_OFF);
+
 	ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
@@ -573,6 +617,9 @@
 		return;
 	}
 
+	if (OOB_TAG_OFF)
+		size = round_up(size, OOB_TAG_OFF);
+
 	ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 	memset(arr, 0, sizeof(arr));
@@ -619,13 +666,50 @@
 	KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = strnlen(ptr, 1));
 }
 
-static void kasan_bitops(struct kunit *test)
+static void kasan_bitops_modify(struct kunit *test, int nr, void *addr)
 {
+	KUNIT_EXPECT_KASAN_FAIL(test, set_bit(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, change_bit(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(nr, addr));
+}
+
+static void kasan_bitops_test_and_modify(struct kunit *test, int nr, void *addr)
+{
+	KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, __test_and_set_bit(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit_lock(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, test_and_clear_bit(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, __test_and_clear_bit(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, test_and_change_bit(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, __test_and_change_bit(nr, addr));
+	KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = test_bit(nr, addr));
+
+#if defined(clear_bit_unlock_is_negative_byte)
+	KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result =
+				clear_bit_unlock_is_negative_byte(nr, addr));
+#endif
+}
+
+static void kasan_bitops_generic(struct kunit *test)
+{
+	long *bits;
+
+	/* This test is specifically crafted for the generic mode. */
+	if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+		kunit_info(test, "CONFIG_KASAN_GENERIC required\n");
+		return;
+	}
+
 	/*
 	 * Allocate 1 more byte, which causes kzalloc to round up to 16-bytes;
 	 * this way we do not actually corrupt other memory.
 	 */
-	long *bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL);
+	bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits);
 
 	/*
@@ -633,55 +717,34 @@
 	 * below accesses are still out-of-bounds, since bitops are defined to
 	 * operate on the whole long the bit is in.
 	 */
-	KUNIT_EXPECT_KASAN_FAIL(test, set_bit(BITS_PER_LONG, bits));
-
-	KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(BITS_PER_LONG, bits));
-
-	KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(BITS_PER_LONG, bits));
-
-	KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(BITS_PER_LONG, bits));
-
-	KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(BITS_PER_LONG, bits));
-
-	KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(BITS_PER_LONG, bits));
-
-	KUNIT_EXPECT_KASAN_FAIL(test, change_bit(BITS_PER_LONG, bits));
-
-	KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(BITS_PER_LONG, bits));
+	kasan_bitops_modify(test, BITS_PER_LONG, bits);
 
 	/*
 	 * Below calls try to access bit beyond allocated memory.
 	 */
-	KUNIT_EXPECT_KASAN_FAIL(test,
-		test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+	kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, bits);
 
-	KUNIT_EXPECT_KASAN_FAIL(test,
-		__test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+	kfree(bits);
+}
 
-	KUNIT_EXPECT_KASAN_FAIL(test,
-		test_and_set_bit_lock(BITS_PER_LONG + BITS_PER_BYTE, bits));
+static void kasan_bitops_tags(struct kunit *test)
+{
+	long *bits;
 
-	KUNIT_EXPECT_KASAN_FAIL(test,
-		test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+	/* This test is specifically crafted for the tag-based mode. */
+	if (IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+		kunit_info(test, "CONFIG_KASAN_SW_TAGS required\n");
+		return;
+	}
 
-	KUNIT_EXPECT_KASAN_FAIL(test,
-		__test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+	/* Allocation size will be rounded to up granule size, which is 16. */
+	bits = kzalloc(sizeof(*bits), GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits);
 
-	KUNIT_EXPECT_KASAN_FAIL(test,
-		test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+	/* Do the accesses past the 16 allocated bytes. */
+	kasan_bitops_modify(test, BITS_PER_LONG, &bits[1]);
+	kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, &bits[1]);
 
-	KUNIT_EXPECT_KASAN_FAIL(test,
-		__test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
-
-	KUNIT_EXPECT_KASAN_FAIL(test,
-		kasan_int_result =
-			test_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
-
-#if defined(clear_bit_unlock_is_negative_byte)
-	KUNIT_EXPECT_KASAN_FAIL(test,
-		kasan_int_result = clear_bit_unlock_is_negative_byte(
-			BITS_PER_LONG + BITS_PER_BYTE, bits));
-#endif
 	kfree(bits);
 }
 
@@ -728,6 +791,7 @@
 	KUNIT_CASE(kmalloc_oob_krealloc_more),
 	KUNIT_CASE(kmalloc_oob_krealloc_less),
 	KUNIT_CASE(kmalloc_oob_16),
+	KUNIT_CASE(kmalloc_uaf_16),
 	KUNIT_CASE(kmalloc_oob_in_memset),
 	KUNIT_CASE(kmalloc_oob_memset_2),
 	KUNIT_CASE(kmalloc_oob_memset_4),
@@ -751,7 +815,8 @@
 	KUNIT_CASE(kasan_memchr),
 	KUNIT_CASE(kasan_memcmp),
 	KUNIT_CASE(kasan_strings),
-	KUNIT_CASE(kasan_bitops),
+	KUNIT_CASE(kasan_bitops_generic),
+	KUNIT_CASE(kasan_bitops_tags),
 	KUNIT_CASE(kmalloc_double_kzfree),
 	KUNIT_CASE(vmalloc_oob),
 	{}
diff --git a/mm/compaction.c b/mm/compaction.c
index 6e0ee56..13cb7a9 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -817,6 +817,10 @@
 	 * delay for some time until fewer pages are isolated
 	 */
 	while (unlikely(too_many_isolated(pgdat))) {
+		/* stop isolation if there are still pages not migrated */
+		if (cc->nr_migratepages)
+			return 0;
+
 		/* async migration should just abort */
 		if (cc->mode == MIGRATE_ASYNC)
 			return 0;
@@ -1012,8 +1016,8 @@
 
 isolate_success:
 		list_add(&page->lru, &cc->migratepages);
-		cc->nr_migratepages++;
-		nr_isolated++;
+		cc->nr_migratepages += compound_nr(page);
+		nr_isolated += compound_nr(page);
 
 		/*
 		 * Avoid isolating too much unless this block is being
@@ -1021,7 +1025,7 @@
 		 * or a lock is contended. For contention, isolate quickly to
 		 * potentially remove one source of contention.
 		 */
-		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX &&
+		if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX &&
 		    !cc->rescan && !cc->contended) {
 			++low_pfn;
 			break;
@@ -1132,7 +1136,7 @@
 		if (!pfn)
 			break;
 
-		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
+		if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX)
 			break;
 	}
 
diff --git a/mm/gup.c b/mm/gup.c
index 102877e..98eb8e6 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1647,8 +1647,11 @@
 		/*
 		 * drop the above get_user_pages reference.
 		 */
-		for (i = 0; i < nr_pages; i++)
-			put_page(pages[i]);
+		if (gup_flags & FOLL_PIN)
+			unpin_user_pages(pages, nr_pages);
+		else
+			for (i = 0; i < nr_pages; i++)
+				put_page(pages[i]);
 
 		if (migrate_pages(&cma_page_list, alloc_migration_target, NULL,
 			(unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
@@ -1728,8 +1731,11 @@
 			goto out;
 
 		if (check_dax_vmas(vmas_tmp, rc)) {
-			for (i = 0; i < rc; i++)
-				put_page(pages[i]);
+			if (gup_flags & FOLL_PIN)
+				unpin_user_pages(pages, rc);
+			else
+				for (i = 0; i < rc; i++)
+					put_page(pages[i]);
 			rc = -EOPNOTSUPP;
 			goto out;
 		}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fe76f8f..37f15c3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -648,6 +648,8 @@
 			}
 
 			del += t - f;
+			hugetlb_cgroup_uncharge_file_region(
+				resv, rg, t - f);
 
 			/* New entry for end of split region */
 			nrg->from = t;
@@ -660,9 +662,6 @@
 			/* Original entry is trimmed */
 			rg->to = f;
 
-			hugetlb_cgroup_uncharge_file_region(
-				resv, rg, nrg->to - nrg->from);
-
 			list_add(&nrg->link, &rg->link);
 			nrg = NULL;
 			break;
@@ -678,17 +677,17 @@
 		}
 
 		if (f <= rg->from) {	/* Trim beginning of region */
-			del += t - rg->from;
-			rg->from = t;
-
 			hugetlb_cgroup_uncharge_file_region(resv, rg,
 							    t - rg->from);
-		} else {		/* Trim end of region */
-			del += rg->to - f;
-			rg->to = f;
 
+			del += t - rg->from;
+			rg->from = t;
+		} else {		/* Trim end of region */
 			hugetlb_cgroup_uncharge_file_region(resv, rg,
 							    rg->to - f);
+
+			del += rg->to - f;
+			rg->to = f;
 		}
 	}
 
@@ -1569,103 +1568,23 @@
 }
 
 /*
- * Find address_space associated with hugetlbfs page.
- * Upon entry page is locked and page 'was' mapped although mapped state
- * could change.  If necessary, use anon_vma to find vma and associated
- * address space.  The returned mapping may be stale, but it can not be
- * invalid as page lock (which is held) is required to destroy mapping.
- */
-static struct address_space *_get_hugetlb_page_mapping(struct page *hpage)
-{
-	struct anon_vma *anon_vma;
-	pgoff_t pgoff_start, pgoff_end;
-	struct anon_vma_chain *avc;
-	struct address_space *mapping = page_mapping(hpage);
-
-	/* Simple file based mapping */
-	if (mapping)
-		return mapping;
-
-	/*
-	 * Even anonymous hugetlbfs mappings are associated with an
-	 * underlying hugetlbfs file (see hugetlb_file_setup in mmap
-	 * code).  Find a vma associated with the anonymous vma, and
-	 * use the file pointer to get address_space.
-	 */
-	anon_vma = page_lock_anon_vma_read(hpage);
-	if (!anon_vma)
-		return mapping;  /* NULL */
-
-	/* Use first found vma */
-	pgoff_start = page_to_pgoff(hpage);
-	pgoff_end = pgoff_start + pages_per_huge_page(page_hstate(hpage)) - 1;
-	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
-					pgoff_start, pgoff_end) {
-		struct vm_area_struct *vma = avc->vma;
-
-		mapping = vma->vm_file->f_mapping;
-		break;
-	}
-
-	anon_vma_unlock_read(anon_vma);
-	return mapping;
-}
-
-/*
  * Find and lock address space (mapping) in write mode.
  *
- * Upon entry, the page is locked which allows us to find the mapping
- * even in the case of an anon page.  However, locking order dictates
- * the i_mmap_rwsem be acquired BEFORE the page lock.  This is hugetlbfs
- * specific.  So, we first try to lock the sema while still holding the
- * page lock.  If this works, great!  If not, then we need to drop the
- * page lock and then acquire i_mmap_rwsem and reacquire page lock.  Of
- * course, need to revalidate state along the way.
+ * Upon entry, the page is locked which means that page_mapping() is
+ * stable.  Due to locking order, we can only trylock_write.  If we can
+ * not get the lock, simply return NULL to caller.
  */
 struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage)
 {
-	struct address_space *mapping, *mapping2;
+	struct address_space *mapping = page_mapping(hpage);
 
-	mapping = _get_hugetlb_page_mapping(hpage);
-retry:
 	if (!mapping)
 		return mapping;
 
-	/*
-	 * If no contention, take lock and return
-	 */
 	if (i_mmap_trylock_write(mapping))
 		return mapping;
 
-	/*
-	 * Must drop page lock and wait on mapping sema.
-	 * Note:  Once page lock is dropped, mapping could become invalid.
-	 * As a hack, increase map count until we lock page again.
-	 */
-	atomic_inc(&hpage->_mapcount);
-	unlock_page(hpage);
-	i_mmap_lock_write(mapping);
-	lock_page(hpage);
-	atomic_add_negative(-1, &hpage->_mapcount);
-
-	/* verify page is still mapped */
-	if (!page_mapped(hpage)) {
-		i_mmap_unlock_write(mapping);
-		return NULL;
-	}
-
-	/*
-	 * Get address space again and verify it is the same one
-	 * we locked.  If not, drop lock and retry.
-	 */
-	mapping2 = _get_hugetlb_page_mapping(hpage);
-	if (mapping2 != mapping) {
-		i_mmap_unlock_write(mapping);
-		mapping = mapping2;
-		goto retry;
-	}
-
-	return mapping;
+	return NULL;
 }
 
 pgoff_t __basepage_index(struct page *page)
@@ -2443,6 +2362,9 @@
 
 		rsv_adjust = hugepage_subpool_put_pages(spool, 1);
 		hugetlb_acct_memory(h, -rsv_adjust);
+		if (deferred_reserve)
+			hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
+					pages_per_huge_page(h), page);
 	}
 	return page;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3a24e3b..3dcbf24 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4110,11 +4110,17 @@
 			   (u64)memsw * PAGE_SIZE);
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
+		unsigned long nr;
+
 		if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
 			continue;
+		nr = memcg_page_state(memcg, memcg1_stats[i]);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		if (memcg1_stats[i] == NR_ANON_THPS)
+			nr *= HPAGE_PMD_NR;
+#endif
 		seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i],
-			   (u64)memcg_page_state(memcg, memcg1_stats[i]) *
-			   PAGE_SIZE);
+						(u64)nr * PAGE_SIZE);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
@@ -5339,17 +5345,22 @@
 		memcg->swappiness = mem_cgroup_swappiness(parent);
 		memcg->oom_kill_disable = parent->oom_kill_disable;
 	}
-	if (parent && parent->use_hierarchy) {
+	if (!parent) {
+		page_counter_init(&memcg->memory, NULL);
+		page_counter_init(&memcg->swap, NULL);
+		page_counter_init(&memcg->kmem, NULL);
+		page_counter_init(&memcg->tcpmem, NULL);
+	} else if (parent->use_hierarchy) {
 		memcg->use_hierarchy = true;
 		page_counter_init(&memcg->memory, &parent->memory);
 		page_counter_init(&memcg->swap, &parent->swap);
 		page_counter_init(&memcg->kmem, &parent->kmem);
 		page_counter_init(&memcg->tcpmem, &parent->tcpmem);
 	} else {
-		page_counter_init(&memcg->memory, NULL);
-		page_counter_init(&memcg->swap, NULL);
-		page_counter_init(&memcg->kmem, NULL);
-		page_counter_init(&memcg->tcpmem, NULL);
+		page_counter_init(&memcg->memory, &root_mem_cgroup->memory);
+		page_counter_init(&memcg->swap, &root_mem_cgroup->swap);
+		page_counter_init(&memcg->kmem, &root_mem_cgroup->kmem);
+		page_counter_init(&memcg->tcpmem, &root_mem_cgroup->tcpmem);
 		/*
 		 * Deeper hierachy with use_hierarchy == false doesn't make
 		 * much sense so let cgroup subsystem know about this
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c0bb186..5d880d4 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1057,27 +1057,25 @@
 	if (!PageHuge(hpage)) {
 		unmap_success = try_to_unmap(hpage, ttu);
 	} else {
-		/*
-		 * For hugetlb pages, try_to_unmap could potentially call
-		 * huge_pmd_unshare.  Because of this, take semaphore in
-		 * write mode here and set TTU_RMAP_LOCKED to indicate we
-		 * have taken the lock at this higer level.
-		 *
-		 * Note that the call to hugetlb_page_mapping_lock_write
-		 * is necessary even if mapping is already set.  It handles
-		 * ugliness of potentially having to drop page lock to obtain
-		 * i_mmap_rwsem.
-		 */
-		mapping = hugetlb_page_mapping_lock_write(hpage);
-
-		if (mapping) {
-			unmap_success = try_to_unmap(hpage,
+		if (!PageAnon(hpage)) {
+			/*
+			 * For hugetlb pages in shared mappings, try_to_unmap
+			 * could potentially call huge_pmd_unshare.  Because of
+			 * this, take semaphore in write mode here and set
+			 * TTU_RMAP_LOCKED to indicate we have taken the lock
+			 * at this higer level.
+			 */
+			mapping = hugetlb_page_mapping_lock_write(hpage);
+			if (mapping) {
+				unmap_success = try_to_unmap(hpage,
 						     ttu|TTU_RMAP_LOCKED);
-			i_mmap_unlock_write(mapping);
+				i_mmap_unlock_write(mapping);
+			} else {
+				pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn);
+				unmap_success = false;
+			}
 		} else {
-			pr_info("Memory failure: %#lx: could not find mapping for mapped huge page\n",
-				pfn);
-			unmap_success = false;
+			unmap_success = try_to_unmap(hpage, ttu);
 		}
 	}
 	if (!unmap_success)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 3fde772..3ca4898 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -525,7 +525,7 @@
 	unsigned long flags = qp->flags;
 	int ret;
 	bool has_unmovable = false;
-	pte_t *pte;
+	pte_t *pte, *mapped_pte;
 	spinlock_t *ptl;
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
@@ -539,7 +539,7 @@
 	if (pmd_trans_unstable(pmd))
 		return 0;
 
-	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		if (!pte_present(*pte))
 			continue;
@@ -571,7 +571,7 @@
 		} else
 			break;
 	}
-	pte_unmap_unlock(pte - 1, ptl);
+	pte_unmap_unlock(mapped_pte, ptl);
 	cond_resched();
 
 	if (has_unmovable)
diff --git a/mm/memremap.c b/mm/memremap.c
index 73a206d..16b2fb4 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -41,28 +41,24 @@
 DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
 EXPORT_SYMBOL(devmap_managed_key);
 
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
 {
-	static_branch_dec(&devmap_managed_key);
+	if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+	    pgmap->type == MEMORY_DEVICE_FS_DAX)
+		static_branch_dec(&devmap_managed_key);
 }
 
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
 {
-	if (pgmap->type == MEMORY_DEVICE_PRIVATE &&
-	    (!pgmap->ops || !pgmap->ops->page_free)) {
-		WARN(1, "Missing page_free method\n");
-		return -EINVAL;
-	}
-
-	static_branch_inc(&devmap_managed_key);
-	return 0;
+	if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+	    pgmap->type == MEMORY_DEVICE_FS_DAX)
+		static_branch_inc(&devmap_managed_key);
 }
 #else
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
 {
-	return -EINVAL;
 }
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
 {
 }
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
@@ -169,7 +165,7 @@
 		pageunmap_range(pgmap, i);
 
 	WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
-	devmap_managed_enable_put();
+	devmap_managed_enable_put(pgmap);
 }
 EXPORT_SYMBOL_GPL(memunmap_pages);
 
@@ -307,7 +303,6 @@
 		.pgprot = PAGE_KERNEL,
 	};
 	const int nr_range = pgmap->nr_range;
-	bool need_devmap_managed = true;
 	int error, i;
 
 	if (WARN_ONCE(!nr_range, "nr_range must be specified\n"))
@@ -323,6 +318,10 @@
 			WARN(1, "Missing migrate_to_ram method\n");
 			return ERR_PTR(-EINVAL);
 		}
+		if (!pgmap->ops->page_free) {
+			WARN(1, "Missing page_free method\n");
+			return ERR_PTR(-EINVAL);
+		}
 		if (!pgmap->owner) {
 			WARN(1, "Missing owner\n");
 			return ERR_PTR(-EINVAL);
@@ -336,11 +335,9 @@
 		}
 		break;
 	case MEMORY_DEVICE_GENERIC:
-		need_devmap_managed = false;
 		break;
 	case MEMORY_DEVICE_PCI_P2PDMA:
 		params.pgprot = pgprot_noncached(params.pgprot);
-		need_devmap_managed = false;
 		break;
 	default:
 		WARN(1, "Invalid pgmap type %d\n", pgmap->type);
@@ -364,11 +361,7 @@
 		}
 	}
 
-	if (need_devmap_managed) {
-		error = devmap_managed_enable_get(pgmap);
-		if (error)
-			return ERR_PTR(error);
-	}
+	devmap_managed_enable_get(pgmap);
 
 	/*
 	 * Clear the pgmap nr_range as it will be incremented for each
diff --git a/mm/migrate.c b/mm/migrate.c
index 5ca5842..5795cb8 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1328,34 +1328,38 @@
 		goto put_anon;
 
 	if (page_mapped(hpage)) {
-		/*
-		 * try_to_unmap could potentially call huge_pmd_unshare.
-		 * Because of this, take semaphore in write mode here and
-		 * set TTU_RMAP_LOCKED to let lower levels know we have
-		 * taken the lock.
-		 */
-		mapping = hugetlb_page_mapping_lock_write(hpage);
-		if (unlikely(!mapping))
-			goto unlock_put_anon;
+		bool mapping_locked = false;
+		enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK|
+					TTU_IGNORE_ACCESS;
 
-		try_to_unmap(hpage,
-			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS|
-			TTU_RMAP_LOCKED);
+		if (!PageAnon(hpage)) {
+			/*
+			 * In shared mappings, try_to_unmap could potentially
+			 * call huge_pmd_unshare.  Because of this, take
+			 * semaphore in write mode here and set TTU_RMAP_LOCKED
+			 * to let lower levels know we have taken the lock.
+			 */
+			mapping = hugetlb_page_mapping_lock_write(hpage);
+			if (unlikely(!mapping))
+				goto unlock_put_anon;
+
+			mapping_locked = true;
+			ttu |= TTU_RMAP_LOCKED;
+		}
+
+		try_to_unmap(hpage, ttu);
 		page_was_mapped = 1;
-		/*
-		 * Leave mapping locked until after subsequent call to
-		 * remove_migration_ptes()
-		 */
+
+		if (mapping_locked)
+			i_mmap_unlock_write(mapping);
 	}
 
 	if (!page_mapped(hpage))
 		rc = move_to_new_page(new_hpage, hpage, mode);
 
-	if (page_was_mapped) {
+	if (page_was_mapped)
 		remove_migration_ptes(hpage,
-			rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, true);
-		i_mmap_unlock_write(mapping);
-	}
+			rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false);
 
 unlock_put_anon:
 	unlock_page(new_hpage);
diff --git a/mm/percpu.c b/mm/percpu.c
index 66a93f0..ad7a37e 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1315,8 +1315,8 @@
 	region_size = ALIGN(start_offset + map_size, lcm_align);
 
 	/* allocate chunk */
-	alloc_size = sizeof(struct pcpu_chunk) +
-		BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long);
+	alloc_size = struct_size(chunk, populated,
+				 BITS_TO_LONGS(region_size >> PAGE_SHIFT));
 	chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
 	if (!chunk)
 		panic("%s: Failed to allocate %zu bytes\n", __func__,
@@ -2521,8 +2521,8 @@
 	pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
 	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
 	pcpu_atom_size = ai->atom_size;
-	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
-		BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);
+	pcpu_chunk_struct_size = struct_size(chunk, populated,
+					     BITS_TO_LONGS(pcpu_unit_pages));
 
 	pcpu_stats_save_ai(ai);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 1b84945..31b2932 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1413,9 +1413,6 @@
 		/*
 		 * If sharing is possible, start and end will be adjusted
 		 * accordingly.
-		 *
-		 * If called for a huge page, caller must hold i_mmap_rwsem
-		 * in write mode as it is possible to call huge_pmd_unshare.
 		 */
 		adjust_range_if_pmd_sharing_possible(vma, &range.start,
 						     &range.end);
@@ -1462,7 +1459,7 @@
 		subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
 		address = pvmw.address;
 
-		if (PageHuge(page)) {
+		if (PageHuge(page) && !PageAnon(page)) {
 			/*
 			 * To call huge_pmd_unshare, i_mmap_rwsem must be
 			 * held in write mode.  Caller needs to explicitly
diff --git a/mm/slub.c b/mm/slub.c
index b30be23..34dcc09 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2852,7 +2852,7 @@
 
 	object = c->freelist;
 	page = c->page;
-	if (unlikely(!object || !node_match(page, node))) {
+	if (unlikely(!object || !page || !node_match(page, node))) {
 		object = __slab_alloc(s, gfpflags, node, addr, c);
 	} else {
 		void *next_object = get_freepointer_safe(s, object);
diff --git a/mm/truncate.c b/mm/truncate.c
index 18cec39..960edf5 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -528,7 +528,7 @@
 }
 EXPORT_SYMBOL(truncate_inode_pages_final);
 
-unsigned long __invalidate_mapping_pages(struct address_space *mapping,
+static unsigned long __invalidate_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t end, unsigned long *nr_pagevec)
 {
 	pgoff_t indices[PAGEVEC_SIZE];
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1b8f0e0..7b4e31e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1516,7 +1516,8 @@
 	nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
 			TTU_IGNORE_ACCESS, &stat, true);
 	list_splice(&clean_pages, page_list);
-	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -nr_reclaimed);
+	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
+			    -(long)nr_reclaimed);
 	/*
 	 * Since lazyfree pages are isolated from file LRU from the beginning,
 	 * they will rotate back to anonymous LRU in the end if it failed to
@@ -1526,7 +1527,7 @@
 	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON,
 			    stat.nr_lazyfree_fail);
 	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
-			    -stat.nr_lazyfree_fail);
+			    -(long)stat.nr_lazyfree_fail);
 	return nr_reclaimed;
 }
 
diff --git a/net/atm/lec.c b/net/atm/lec.c
index dbabb65..7226c78 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -954,9 +954,8 @@
 {
 	struct lec_state *state = seq->private;
 
-	v = lec_get_idx(state, 1);
-	*pos += !!PTR_ERR(v);
-	return v;
+	++*pos;
+	return lec_get_idx(state, 1);
 }
 
 static int lec_seq_show(struct seq_file *seq, void *v)
diff --git a/net/can/Kconfig b/net/can/Kconfig
index 224e5e0..7c9958d 100644
--- a/net/can/Kconfig
+++ b/net/can/Kconfig
@@ -62,8 +62,9 @@
 	  communication between CAN nodes via two defined CAN Identifiers.
 	  As CAN frames can only transport a small amount of data bytes
 	  (max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this
-	  segmentation is needed to transport longer PDUs as needed e.g. for
-	  vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic.
+	  segmentation is needed to transport longer Protocol Data Units (PDU)
+	  as needed e.g. for vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN
+	  traffic.
 	  This protocol driver implements data transfers according to
 	  ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types.
 	  If you want to perform automotive vehicle diagnostic services (UDS),
diff --git a/net/can/isotp.c b/net/can/isotp.c
index 4c20628..d78ab13 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -252,14 +252,16 @@
 
 static u8 padlen(u8 datalen)
 {
-	const u8 plen[] = {8, 8, 8, 8, 8, 8, 8, 8, 8,		/* 0 - 8 */
-			   12, 12, 12, 12,			/* 9 - 12 */
-			   16, 16, 16, 16,			/* 13 - 16 */
-			   20, 20, 20, 20,			/* 17 - 20 */
-			   24, 24, 24, 24,			/* 21 - 24 */
-			   32, 32, 32, 32, 32, 32, 32, 32,	/* 25 - 32 */
-			   48, 48, 48, 48, 48, 48, 48, 48,	/* 33 - 40 */
-			   48, 48, 48, 48, 48, 48, 48, 48};	/* 41 - 48 */
+	static const u8 plen[] = {
+		8, 8, 8, 8, 8, 8, 8, 8, 8,	/* 0 - 8 */
+		12, 12, 12, 12,			/* 9 - 12 */
+		16, 16, 16, 16,			/* 13 - 16 */
+		20, 20, 20, 20,			/* 17 - 20 */
+		24, 24, 24, 24,			/* 21 - 24 */
+		32, 32, 32, 32, 32, 32, 32, 32,	/* 25 - 32 */
+		48, 48, 48, 48, 48, 48, 48, 48,	/* 33 - 40 */
+		48, 48, 48, 48, 48, 48, 48, 48	/* 41 - 48 */
+	};
 
 	if (datalen > 48)
 		return 64;
@@ -569,10 +571,6 @@
 		return 0;
 	}
 
-	/* no creation of flow control frames */
-	if (so->opt.flags & CAN_ISOTP_LISTEN_MODE)
-		return 0;
-
 	/* perform blocksize handling, if enabled */
 	if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) {
 		/* start rx timeout watchdog */
@@ -581,6 +579,10 @@
 		return 0;
 	}
 
+	/* no creation of flow control frames */
+	if (so->opt.flags & CAN_ISOTP_LISTEN_MODE)
+		return 0;
+
 	/* we reached the specified blocksize so->rxfc.bs */
 	isotp_send_fc(sk, ae, ISOTP_FC_CTS);
 	return 0;
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 1be4c89..f239665 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -475,6 +475,12 @@
 			goto out_release_sock;
 		}
 
+		if (!(ndev->flags & IFF_UP)) {
+			dev_put(ndev);
+			ret = -ENETDOWN;
+			goto out_release_sock;
+		}
+
 		priv = j1939_netdev_start(ndev);
 		dev_put(ndev);
 		if (IS_ERR(priv)) {
diff --git a/net/can/proc.c b/net/can/proc.c
index 550928b..5ea8695 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -462,6 +462,9 @@
  */
 void can_remove_proc(struct net *net)
 {
+	if (!net->can.proc_dir)
+		return;
+
 	if (net->can.pde_stats)
 		remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir);
 
@@ -486,6 +489,5 @@
 	if (net->can.pde_rcvlist_sff)
 		remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir);
 
-	if (net->can.proc_dir)
-		remove_proc_entry("can", net->proc_net);
+	remove_proc_entry("can", net->proc_net);
 }
diff --git a/net/core/devlink.c b/net/core/devlink.c
index a932d95..ab4b136 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -8254,8 +8254,6 @@
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 
-	if (WARN_ON(devlink_port->registered))
-		return -EEXIST;
 	devlink_port->attrs_set = true;
 	attrs->flavour = flavour;
 	if (attrs->switch_id.id_len) {
@@ -8279,6 +8277,8 @@
 {
 	int ret;
 
+	if (WARN_ON(devlink_port->registered))
+		return;
 	devlink_port->attrs = *attrs;
 	ret = __devlink_port_attrs_set(devlink_port, attrs->flavour);
 	if (ret)
@@ -8301,6 +8301,8 @@
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
 
+	if (WARN_ON(devlink_port->registered))
+		return;
 	ret = __devlink_port_attrs_set(devlink_port,
 				       DEVLINK_PORT_FLAVOUR_PCI_PF);
 	if (ret)
@@ -8326,6 +8328,8 @@
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
 
+	if (WARN_ON(devlink_port->registered))
+		return;
 	ret = __devlink_port_attrs_set(devlink_port,
 				       DEVLINK_PORT_FLAVOUR_PCI_VF);
 	if (ret)
diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index 8ee4cdb..1c9f4df 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -280,7 +280,7 @@
 					  active_diff_mask, compact);
 	}
 	if (mod)
-		ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF, NULL);
+		netdev_features_change(dev);
 
 out_rtnl:
 	rtnl_unlock();
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 8b04d1d..ee65c92 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -608,9 +608,6 @@
 			ttl = ip4_dst_hoplimit(&rt->dst);
 	}
 
-	if (!df && skb->protocol == htons(ETH_P_IP))
-		df = inner_iph->frag_off & htons(IP_DF);
-
 	headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
 	if (headroom > dev->needed_headroom)
 		dev->needed_headroom = headroom;
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 25f1caf..e25be2d 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -263,7 +263,7 @@
 	const struct icmphdr *icmph = icmp_hdr(skb);
 	const struct iphdr *iph = ip_hdr(skb);
 
-	if (mtu <= 576 || iph->frag_off != htons(IP_DF))
+	if (mtu < 576 || iph->frag_off != htons(IP_DF))
 		return 0;
 
 	if (ipv4_is_lbcast(iph->daddr)  || ipv4_is_multicast(iph->daddr) ||
@@ -359,7 +359,7 @@
 	__be16 frag_off;
 	int offset;
 
-	if (mtu <= IPV6_MIN_MTU)
+	if (mtu < IPV6_MIN_MTU)
 		return 0;
 
 	if (stype == IPV6_ADDR_ANY || stype == IPV6_ADDR_MULTICAST ||
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index a058213..7c84103 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -17,17 +17,19 @@
 #include <net/netfilter/nf_queue.h>
 
 /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type)
+int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 	struct flowi4 fl4 = {};
 	__be32 saddr = iph->saddr;
-	const struct sock *sk = skb_to_full_sk(skb);
-	__u8 flags = sk ? inet_sk_flowi_flags(sk) : 0;
+	__u8 flags;
 	struct net_device *dev = skb_dst(skb)->dev;
 	unsigned int hh_len;
 
+	sk = sk_to_full_sk(sk);
+	flags = sk ? inet_sk_flowi_flags(sk) : 0;
+
 	if (addr_type == RTN_UNSPEC)
 		addr_type = inet_addr_type_dev_table(net, dev, saddr);
 	if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index f703a71..8330795 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -62,7 +62,7 @@
 		    iph->daddr != daddr ||
 		    skb->mark != mark ||
 		    iph->tos != tos) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 9dcfa4e..93b0773 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -145,7 +145,7 @@
 				   ip4_dst_hoplimit(skb_dst(nskb)));
 	nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
 
-	if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+	if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
 		goto free_nskb;
 
 	niph = ip_hdr(nskb);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 6ac473b..00dc3f9 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -331,7 +331,7 @@
 	__u32 cookie = ntohl(th->ack_seq) - 1;
 	struct sock *ret = sk;
 	struct request_sock *req;
-	int mss;
+	int full_space, mss;
 	struct rtable *rt;
 	__u8 rcv_wscale;
 	struct flowi4 fl4;
@@ -427,8 +427,13 @@
 
 	/* Try to redo what tcp_v4_send_synack did. */
 	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
+	/* limit the window selection if the user enforce a smaller rx buffer */
+	full_space = tcp_full_space(sk);
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+	    (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+		req->rsk_window_clamp = full_space;
 
-	tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
+	tcp_select_initial_window(sk, full_space, req->mss,
 				  &req->rsk_rcv_wnd, &req->rsk_window_clamp,
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(&rt->dst, RTAX_INITRWND));
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index e67a66f..c62805c 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -366,7 +366,7 @@
 static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 					       struct sk_buff *skb)
 {
-	struct udphdr *uh = udp_hdr(skb);
+	struct udphdr *uh = udp_gro_udphdr(skb);
 	struct sk_buff *pp = NULL;
 	struct udphdr *uh2;
 	struct sk_buff *p;
@@ -500,12 +500,22 @@
 }
 EXPORT_SYMBOL(udp_gro_receive);
 
+static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+					__be16 dport)
+{
+	const struct iphdr *iph = skb_gro_network_header(skb);
+
+	return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
+				 iph->daddr, dport, inet_iif(skb),
+				 inet_sdif(skb), &udp_table, NULL);
+}
+
 INDIRECT_CALLABLE_SCOPE
 struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
+	struct sock *sk = NULL;
 	struct sk_buff *pp;
-	struct sock *sk;
 
 	if (unlikely(!uh))
 		goto flush;
@@ -523,7 +533,10 @@
 skip:
 	NAPI_GRO_CB(skb)->is_ipv6 = 0;
 	rcu_read_lock();
-	sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+	if (static_branch_unlikely(&udp_encap_needed_key))
+		sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest);
+
 	pp = udp_gro_receive(head, skb, uh, sk);
 	rcu_read_unlock();
 	return pp;
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index dc19aff..fb0648e 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -64,14 +64,14 @@
 static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = {
 	.handler	=	xfrm_tunnel_rcv,
 	.err_handler	=	xfrm_tunnel_err,
-	.priority	=	3,
+	.priority	=	4,
 };
 
 #if IS_ENABLED(CONFIG_IPV6)
 static struct xfrm_tunnel xfrm64_tunnel_handler __read_mostly = {
 	.handler	=	xfrm_tunnel_rcv,
 	.err_handler	=	xfrm_tunnel_err,
-	.priority	=	2,
+	.priority	=	3,
 };
 #endif
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index ec448b7..8956144 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -158,7 +158,13 @@
 		tp = skb_header_pointer(skb,
 			ptr+offsetof(struct icmp6hdr, icmp6_type),
 			sizeof(_type), &_type);
-		if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
+
+		/* Based on RFC 8200, Section 4.5 Fragment Header, return
+		 * false if this is a fragment packet with no icmp header info.
+		 */
+		if (!tp && frag_off != 0)
+			return false;
+		else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
 			return true;
 	}
 	return false;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a0217e5..648db3f 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1271,6 +1271,8 @@
 	if (max_headroom > dev->needed_headroom)
 		dev->needed_headroom = max_headroom;
 
+	skb_set_inner_ipproto(skb, proto);
+
 	err = ip6_tnl_encap(skb, t, &proto, fl6);
 	if (err)
 		return err;
@@ -1280,8 +1282,6 @@
 		ipv6_push_frag_opts(skb, &opt.ops, &proto);
 	}
 
-	skb_set_inner_ipproto(skb, proto);
-
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 6d0e942..ab9a279 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -20,10 +20,10 @@
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #include "../bridge/br_private.h"
 
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct sock *sk = sk_to_full_sk(skb->sk);
+	struct sock *sk = sk_to_full_sk(sk_partial);
 	unsigned int hh_len;
 	struct dst_entry *dst;
 	int strict = (ipv6_addr_type(&iph->daddr) &
@@ -84,7 +84,7 @@
 		if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
 		    !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
 		    skb->mark != rt_info->mark)
-			return ip6_route_me_harder(entry->state.net, skb);
+			return ip6_route_me_harder(entry->state.net, entry->state.sk, skb);
 	}
 	return 0;
 }
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 1a27486..cee7480 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -57,7 +57,7 @@
 	     skb->mark != mark ||
 	     ipv6_hdr(skb)->hop_limit != hop_limit ||
 	     flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
-		err = ip6_route_me_harder(state->net, skb);
+		err = ip6_route_me_harder(state->net, state->sk, skb);
 		if (err < 0)
 			ret = NF_DROP_ERR(err);
 	}
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 1f5d4d1..c8cf1bb 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -42,6 +42,8 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
 
 #include <net/sock.h>
 #include <net/snmp.h>
@@ -322,7 +324,9 @@
 	struct frag_queue *fq;
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct net *net = dev_net(skb_dst(skb)->dev);
-	int iif;
+	__be16 frag_off;
+	int iif, offset;
+	u8 nexthdr;
 
 	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
 		goto fail_hdr;
@@ -351,6 +355,33 @@
 		return 1;
 	}
 
+	/* RFC 8200, Section 4.5 Fragment Header:
+	 * If the first fragment does not include all headers through an
+	 * Upper-Layer header, then that fragment should be discarded and
+	 * an ICMP Parameter Problem, Code 3, message should be sent to
+	 * the source of the fragment, with the Pointer field set to zero.
+	 */
+	nexthdr = hdr->nexthdr;
+	offset = ipv6_skip_exthdr(skb, skb_transport_offset(skb), &nexthdr, &frag_off);
+	if (offset >= 0) {
+		/* Check some common protocols' header */
+		if (nexthdr == IPPROTO_TCP)
+			offset += sizeof(struct tcphdr);
+		else if (nexthdr == IPPROTO_UDP)
+			offset += sizeof(struct udphdr);
+		else if (nexthdr == IPPROTO_ICMPV6)
+			offset += sizeof(struct icmp6hdr);
+		else
+			offset += 1;
+
+		if (!(frag_off & htons(IP6_OFFSET)) && offset > skb->len) {
+			__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
+					IPSTATS_MIB_INHDRERRORS);
+			icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0);
+			return -1;
+		}
+	}
+
 	iif = skb->dev ? skb->dev->ifindex : 0;
 	fq = fq_find(net, fhdr->identification, hdr, iif);
 	if (fq) {
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 5e2c34c..5e7983c 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1128,7 +1128,6 @@
 	if (tdev && !netif_is_l3_master(tdev)) {
 		int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
-		dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
 		dev->mtu = tdev->mtu - t_hlen;
 		if (dev->mtu < IPV6_MIN_MTU)
 			dev->mtu = IPV6_MIN_MTU;
@@ -1426,7 +1425,6 @@
 	dev->priv_destructor	= ipip6_dev_free;
 
 	dev->type		= ARPHRD_SIT;
-	dev->hard_header_len	= LL_MAX_HEADER + t_hlen;
 	dev->mtu		= ETH_DATA_LEN - t_hlen;
 	dev->min_mtu		= IPV6_MIN_MTU;
 	dev->max_mtu		= IP6_MAX_MTU - t_hlen;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index e796a64..9b6cae1 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -136,7 +136,7 @@
 	__u32 cookie = ntohl(th->ack_seq) - 1;
 	struct sock *ret = sk;
 	struct request_sock *req;
-	int mss;
+	int full_space, mss;
 	struct dst_entry *dst;
 	__u8 rcv_wscale;
 	u32 tsoff = 0;
@@ -241,7 +241,13 @@
 	}
 
 	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
-	tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
+	/* limit the window selection if the user enforce a smaller rx buffer */
+	full_space = tcp_full_space(sk);
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+	    (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+		req->rsk_window_clamp = full_space;
+
+	tcp_select_initial_window(sk, full_space, req->mss,
 				  &req->rsk_rcv_wnd, &req->rsk_window_clamp,
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(dst, RTAX_INITRWND));
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 584157a..f9e888d 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -111,12 +111,22 @@
 	return segs;
 }
 
+static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+					__be16 dport)
+{
+	const struct ipv6hdr *iph = skb_gro_network_header(skb);
+
+	return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
+				 &iph->daddr, dport, inet6_iif(skb),
+				 inet6_sdif(skb), &udp_table, NULL);
+}
+
 INDIRECT_CALLABLE_SCOPE
 struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
+	struct sock *sk = NULL;
 	struct sk_buff *pp;
-	struct sock *sk;
 
 	if (unlikely(!uh))
 		goto flush;
@@ -135,7 +145,10 @@
 skip:
 	NAPI_GRO_CB(skb)->is_ipv6 = 1;
 	rcu_read_lock();
-	sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+	if (static_branch_unlikely(&udpv6_encap_needed_key))
+		sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest);
+
 	pp = udp_gro_receive(head, skb, uh, sk);
 	rcu_read_unlock();
 	return pp;
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 25b7ebd..f696d46 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -303,13 +303,13 @@
 static struct xfrm6_tunnel xfrm6_tunnel_handler __read_mostly = {
 	.handler	= xfrm6_tunnel_rcv,
 	.err_handler	= xfrm6_tunnel_err,
-	.priority	= 2,
+	.priority	= 3,
 };
 
 static struct xfrm6_tunnel xfrm46_tunnel_handler __read_mostly = {
 	.handler	= xfrm6_tunnel_rcv,
 	.err_handler	= xfrm6_tunnel_err,
-	.priority	= 2,
+	.priority	= 3,
 };
 
 static int __net_init xfrm6_tunnel_net_init(struct net *net)
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index d805720..047238f 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1434,7 +1434,8 @@
 		break;
 	}
 
-	if (how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) {
+	if ((how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) &&
+	    sk->sk_state == IUCV_CONNECTED) {
 		if (iucv->transport == AF_IUCV_TRANS_IUCV) {
 			txmsg.class = 0;
 			txmsg.tag = 0;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index f400240..6adfcb9 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -5464,6 +5464,7 @@
 			struct cfg80211_assoc_request *req)
 {
 	bool is_6ghz = req->bss->channel->band == NL80211_BAND_6GHZ;
+	bool is_5ghz = req->bss->channel->band == NL80211_BAND_5GHZ;
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_bss *bss = (void *)req->bss->priv;
@@ -5616,7 +5617,7 @@
 	if (vht_ie && vht_ie[1] >= sizeof(struct ieee80211_vht_cap))
 		memcpy(&assoc_data->ap_vht_cap, vht_ie + 2,
 		       sizeof(struct ieee80211_vht_cap));
-	else if (!is_6ghz)
+	else if (is_5ghz)
 		ifmgd->flags |= IEEE80211_STA_DISABLE_VHT |
 				IEEE80211_STA_DISABLE_HE;
 	rcu_read_unlock();
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index fb4f2b9..4fe284f 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -258,6 +258,24 @@
  */
 void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 {
+	/*
+	 * If we had used sta_info_pre_move_state() then we might not
+	 * have gone through the state transitions down again, so do
+	 * it here now (and warn if it's inserted).
+	 *
+	 * This will clear state such as fast TX/RX that may have been
+	 * allocated during state transitions.
+	 */
+	while (sta->sta_state > IEEE80211_STA_NONE) {
+		int ret;
+
+		WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED));
+
+		ret = sta_info_move_state(sta, sta->sta_state - 1);
+		if (WARN_ONCE(ret, "sta_info_move_state() returned %d\n", ret))
+			break;
+	}
+
 	if (sta->rate_ctrl)
 		rate_control_free_sta(sta);
 
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 00ae81e..7afd076 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -785,7 +785,7 @@
 void sta_info_stop(struct ieee80211_local *local);
 
 /**
- * sta_info_flush - flush matching STA entries from the STA table
+ * __sta_info_flush - flush matching STA entries from the STA table
  *
  * Returns the number of removed STA entries.
  *
@@ -794,6 +794,13 @@
  */
 int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans);
 
+/**
+ * sta_info_flush - flush matching STA entries from the STA table
+ *
+ * Returns the number of removed STA entries.
+ *
+ * @sdata: sdata to remove all stations from
+ */
 static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata)
 {
 	return __sta_info_flush(sdata, false);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 8ba10a4..56a4d0d 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1942,19 +1942,24 @@
 
 /* device xmit handlers */
 
+enum ieee80211_encrypt {
+	ENCRYPT_NO,
+	ENCRYPT_MGMT,
+	ENCRYPT_DATA,
+};
+
 static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
 				struct sk_buff *skb,
-				int head_need, bool may_encrypt)
+				int head_need,
+				enum ieee80211_encrypt encrypt)
 {
 	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_hdr *hdr;
 	bool enc_tailroom;
 	int tail_need = 0;
 
-	hdr = (struct ieee80211_hdr *) skb->data;
-	enc_tailroom = may_encrypt &&
-		       (sdata->crypto_tx_tailroom_needed_cnt ||
-			ieee80211_is_mgmt(hdr->frame_control));
+	enc_tailroom = encrypt == ENCRYPT_MGMT ||
+		       (encrypt == ENCRYPT_DATA &&
+			sdata->crypto_tx_tailroom_needed_cnt);
 
 	if (enc_tailroom) {
 		tail_need = IEEE80211_ENCRYPT_TAILROOM;
@@ -1985,23 +1990,29 @@
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_hdr *hdr;
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 	int headroom;
-	bool may_encrypt;
+	enum ieee80211_encrypt encrypt;
 
-	may_encrypt = !(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT);
+	if (info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)
+		encrypt = ENCRYPT_NO;
+	else if (ieee80211_is_mgmt(hdr->frame_control))
+		encrypt = ENCRYPT_MGMT;
+	else
+		encrypt = ENCRYPT_DATA;
 
 	headroom = local->tx_headroom;
-	if (may_encrypt)
+	if (encrypt != ENCRYPT_NO)
 		headroom += sdata->encrypt_headroom;
 	headroom -= skb_headroom(skb);
 	headroom = max_t(int, 0, headroom);
 
-	if (ieee80211_skb_resize(sdata, skb, headroom, may_encrypt)) {
+	if (ieee80211_skb_resize(sdata, skb, headroom, encrypt)) {
 		ieee80211_free_txskb(&local->hw, skb);
 		return;
 	}
 
+	/* reload after potential resize */
 	hdr = (struct ieee80211_hdr *) skb->data;
 	info->control.vif = &sdata->vif;
 
@@ -2828,7 +2839,7 @@
 		head_need += sdata->encrypt_headroom;
 		head_need += local->tx_headroom;
 		head_need = max_t(int, 0, head_need);
-		if (ieee80211_skb_resize(sdata, skb, head_need, true)) {
+		if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) {
 			ieee80211_free_txskb(&local->hw, skb);
 			skb = NULL;
 			return ERR_PTR(-ENOMEM);
@@ -3502,7 +3513,7 @@
 	if (unlikely(ieee80211_skb_resize(sdata, skb,
 					  max_t(int, extra_head + hw_headroom -
 						     skb_headroom(skb), 0),
-					  false))) {
+					  ENCRYPT_NO))) {
 		kfree_skb(skb);
 		return true;
 	}
@@ -3619,13 +3630,14 @@
 	tx.skb = skb;
 	tx.sdata = vif_to_sdata(info->control.vif);
 
-	if (txq->sta && !(info->flags & IEEE80211_TX_CTL_INJECTED)) {
+	if (txq->sta) {
 		tx.sta = container_of(txq->sta, struct sta_info, sta);
 		/*
 		 * Drop unicast frames to unauthorised stations unless they are
-		 * EAPOL frames from the local station.
+		 * injected frames or EAPOL frames from the local station.
 		 */
-		if (unlikely(ieee80211_is_data(hdr->frame_control) &&
+		if (unlikely(!(info->flags & IEEE80211_TX_CTL_INJECTED) &&
+			     ieee80211_is_data(hdr->frame_control) &&
 			     !ieee80211_vif_is_mesh(&tx.sdata->vif) &&
 			     tx.sdata->vif.type != NL80211_IFTYPE_OCB &&
 			     !is_multicast_ether_addr(hdr->addr1) &&
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e7419fd..88f2a7a 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2467,6 +2467,7 @@
 	.memory_pressure	= &tcp_memory_pressure,
 	.stream_memory_free	= mptcp_memory_free,
 	.sysctl_wmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_wmem),
+	.sysctl_rmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_rmem),
 	.sysctl_mem	= sysctl_tcp_mem,
 	.obj_size	= sizeof(struct mptcp_sock),
 	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
diff --git a/net/mptcp/token.c b/net/mptcp/token.c
index 8b47c4b..feb4b9f 100644
--- a/net/mptcp/token.c
+++ b/net/mptcp/token.c
@@ -291,7 +291,7 @@
 {
 	struct mptcp_sock *ret = NULL;
 	struct hlist_nulls_node *pos;
-	int slot, num;
+	int slot, num = 0;
 
 	for (slot = *s_slot; slot <= token_mask; *s_num = 0, slot++) {
 		struct token_bucket *bucket = &token_hash[slot];
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 6f35832..7cff6e5 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -637,13 +637,14 @@
 	if (SET_WITH_COUNTER(set)) {
 		struct ip_set_counter *counter = ext_counter(data, set);
 
+		ip_set_update_counter(counter, ext, flags);
+
 		if (flags & IPSET_FLAG_MATCH_COUNTERS &&
 		    !(ip_set_match_counter(ip_set_get_packets(counter),
 				mext->packets, mext->packets_op) &&
 		      ip_set_match_counter(ip_set_get_bytes(counter),
 				mext->bytes, mext->bytes_op)))
 			return false;
-		ip_set_update_counter(counter, ext, flags);
 	}
 	if (SET_WITH_SKBINFO(set))
 		ip_set_get_skbinfo(ext_skbinfo(data, set),
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index cc3c275..c0b8215 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -742,12 +742,12 @@
 		struct dst_entry *dst = skb_dst(skb);
 
 		if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
-		    ip6_route_me_harder(ipvs->net, skb) != 0)
+		    ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0)
 			return 1;
 	} else
 #endif
 		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
-		    ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0)
+		    ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0)
 			return 1;
 
 	return 0;
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 59151dc..e87b6bd 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -715,7 +715,7 @@
 
 		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
 		    ct->tuplehash[!dir].tuple.src.u3.ip) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
@@ -953,7 +953,7 @@
 
 		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
 				      &ct->tuplehash[!dir].tuple.src.u3)) {
-			err = nf_ip6_route_me_harder(state->net, skb);
+			err = nf_ip6_route_me_harder(state->net, state->sk, skb);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 9cca35d2..d7d34a6 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -446,7 +446,7 @@
 
 	skb_dst_set_noref(nskb, skb_dst(skb));
 	nskb->protocol = htons(ETH_P_IP);
-	if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+	if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
 		goto free_nskb;
 
 	if (nfct) {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 65cb8e3..0f58e98 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7137,7 +7137,7 @@
 			GFP_KERNEL);
 	kfree(buf);
 
-	if (ctx->report &&
+	if (!ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return;
 
@@ -7259,7 +7259,7 @@
 	audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq,
 			AUDIT_NFT_OP_GEN_REGISTER, GFP_KERNEL);
 
-	if (nlmsg_report(nlh) &&
+	if (!nlmsg_report(nlh) &&
 	    !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
 		return;
 
@@ -8053,12 +8053,16 @@
 	kfree(trans);
 }
 
-static int __nf_tables_abort(struct net *net, bool autoload)
+static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 {
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
 	struct nft_hook *hook;
 
+	if (action == NFNL_ABORT_VALIDATE &&
+	    nf_tables_validate(net) < 0)
+		return -EAGAIN;
+
 	list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list,
 					 list) {
 		switch (trans->msg_type) {
@@ -8190,7 +8194,7 @@
 		nf_tables_abort_release(trans);
 	}
 
-	if (autoload)
+	if (action == NFNL_ABORT_AUTOLOAD)
 		nf_tables_module_autoload(net);
 	else
 		nf_tables_module_autoload_cleanup(net);
@@ -8203,9 +8207,10 @@
 	nft_validate_state_update(net, NFT_VALIDATE_SKIP);
 }
 
-static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload)
+static int nf_tables_abort(struct net *net, struct sk_buff *skb,
+			   enum nfnl_abort_action action)
 {
-	int ret = __nf_tables_abort(net, autoload);
+	int ret = __nf_tables_abort(net, action);
 
 	mutex_unlock(&net->nft.commit_mutex);
 
@@ -8836,7 +8841,7 @@
 {
 	mutex_lock(&net->nft.commit_mutex);
 	if (!list_empty(&net->nft.commit_list))
-		__nf_tables_abort(net, false);
+		__nf_tables_abort(net, NFNL_ABORT_NONE);
 	__nft_release_tables(net);
 	mutex_unlock(&net->nft.commit_mutex);
 	WARN_ON_ONCE(!list_empty(&net->nft.tables));
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 2daa1f6..d3df66a 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -333,7 +333,7 @@
 		return netlink_ack(skb, nlh, -EINVAL, NULL);
 replay:
 	status = 0;
-
+replay_abort:
 	skb = netlink_skb_clone(oskb, GFP_KERNEL);
 	if (!skb)
 		return netlink_ack(oskb, nlh, -ENOMEM, NULL);
@@ -499,7 +499,7 @@
 	}
 done:
 	if (status & NFNL_BATCH_REPLAY) {
-		ss->abort(net, oskb, true);
+		ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD);
 		nfnl_err_reset(&err_list);
 		kfree_skb(skb);
 		module_put(ss->owner);
@@ -510,11 +510,25 @@
 			status |= NFNL_BATCH_REPLAY;
 			goto done;
 		} else if (err) {
-			ss->abort(net, oskb, false);
+			ss->abort(net, oskb, NFNL_ABORT_NONE);
 			netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
 		}
 	} else {
-		ss->abort(net, oskb, false);
+		enum nfnl_abort_action abort_action;
+
+		if (status & NFNL_BATCH_FAILURE)
+			abort_action = NFNL_ABORT_NONE;
+		else
+			abort_action = NFNL_ABORT_VALIDATE;
+
+		err = ss->abort(net, oskb, abort_action);
+		if (err == -EAGAIN) {
+			nfnl_err_reset(&err_list);
+			kfree_skb(skb);
+			module_put(ss->owner);
+			status |= NFNL_BATCH_FAILURE;
+			goto replay_abort;
+		}
 	}
 	if (ss->cleanup)
 		ss->cleanup(net);
diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c
index 8826bbe..edd02cd 100644
--- a/net/netfilter/nft_chain_route.c
+++ b/net/netfilter/nft_chain_route.c
@@ -42,7 +42,7 @@
 		    iph->daddr != daddr ||
 		    skb->mark != mark ||
 		    iph->tos != tos) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
@@ -92,7 +92,7 @@
 	     skb->mark != mark ||
 	     ipv6_hdr(skb)->hop_limit != hop_limit ||
 	     flowlabel != *((u32 *)ipv6_hdr(skb)))) {
-		err = nf_ip6_route_me_harder(state->net, skb);
+		err = nf_ip6_route_me_harder(state->net, state->sk, skb);
 		if (err < 0)
 			ret = NF_DROP_ERR(err);
 	}
diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c
index cedf47a..2182d36 100644
--- a/net/netfilter/utils.c
+++ b/net/netfilter/utils.c
@@ -191,8 +191,8 @@
 		      skb->mark == rt_info->mark &&
 		      iph->daddr == rt_info->daddr &&
 		      iph->saddr == rt_info->saddr))
-			return ip_route_me_harder(entry->state.net, skb,
-						  RTN_UNSPEC);
+			return ip_route_me_harder(entry->state.net, entry->state.sk,
+						  skb, RTN_UNSPEC);
 	}
 #endif
 	return 0;
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index 2e8e3f7..fc55c91 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -1166,12 +1166,13 @@
 	struct netlbl_unlhsh_walk_arg cb_arg;
 	u32 skip_bkt = cb->args[0];
 	u32 skip_chain = cb->args[1];
-	u32 iter_bkt;
-	u32 iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0;
+	u32 skip_addr4 = cb->args[2];
+	u32 iter_bkt, iter_chain, iter_addr4 = 0, iter_addr6 = 0;
 	struct netlbl_unlhsh_iface *iface;
 	struct list_head *iter_list;
 	struct netlbl_af4list *addr4;
 #if IS_ENABLED(CONFIG_IPV6)
+	u32 skip_addr6 = cb->args[3];
 	struct netlbl_af6list *addr6;
 #endif
 
@@ -1182,7 +1183,7 @@
 	rcu_read_lock();
 	for (iter_bkt = skip_bkt;
 	     iter_bkt < rcu_dereference(netlbl_unlhsh)->size;
-	     iter_bkt++, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0) {
+	     iter_bkt++) {
 		iter_list = &rcu_dereference(netlbl_unlhsh)->tbl[iter_bkt];
 		list_for_each_entry_rcu(iface, iter_list, list) {
 			if (!iface->valid ||
@@ -1190,7 +1191,7 @@
 				continue;
 			netlbl_af4list_foreach_rcu(addr4,
 						   &iface->addr4_list) {
-				if (iter_addr4++ < cb->args[2])
+				if (iter_addr4++ < skip_addr4)
 					continue;
 				if (netlbl_unlabel_staticlist_gen(
 					      NLBL_UNLABEL_C_STATICLIST,
@@ -1203,10 +1204,12 @@
 					goto unlabel_staticlist_return;
 				}
 			}
+			iter_addr4 = 0;
+			skip_addr4 = 0;
 #if IS_ENABLED(CONFIG_IPV6)
 			netlbl_af6list_foreach_rcu(addr6,
 						   &iface->addr6_list) {
-				if (iter_addr6++ < cb->args[3])
+				if (iter_addr6++ < skip_addr6)
 					continue;
 				if (netlbl_unlabel_staticlist_gen(
 					      NLBL_UNLABEL_C_STATICLIST,
@@ -1219,8 +1222,12 @@
 					goto unlabel_staticlist_return;
 				}
 			}
+			iter_addr6 = 0;
+			skip_addr6 = 0;
 #endif /* IPv6 */
 		}
+		iter_chain = 0;
+		skip_chain = 0;
 	}
 
 unlabel_staticlist_return:
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 832f898..9d6ef6c 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1703,13 +1703,13 @@
 	parms.port_no = OVSP_LOCAL;
 	parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID];
 
-	err = ovs_dp_change(dp, a);
-	if (err)
-		goto err_destroy_meters;
-
 	/* So far only local changes have been made, now need the lock. */
 	ovs_lock();
 
+	err = ovs_dp_change(dp, a);
+	if (err)
+		goto err_unlock_and_destroy_meters;
+
 	vport = new_vport(&parms);
 	if (IS_ERR(vport)) {
 		err = PTR_ERR(vport);
@@ -1725,8 +1725,7 @@
 				ovs_dp_reset_user_features(skb, info);
 		}
 
-		ovs_unlock();
-		goto err_destroy_meters;
+		goto err_unlock_and_destroy_meters;
 	}
 
 	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
@@ -1741,7 +1740,8 @@
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 	return 0;
 
-err_destroy_meters:
+err_unlock_and_destroy_meters:
+	ovs_unlock();
 	ovs_meters_exit(dp);
 err_destroy_ports:
 	kfree(dp->ports);
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index f3486a3..c89c8da 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -390,7 +390,7 @@
 }
 int ovs_flow_tbl_masks_cache_resize(struct flow_table *table, u32 size)
 {
-	struct mask_cache *mc = rcu_dereference(table->mask_cache);
+	struct mask_cache *mc = rcu_dereference_ovsl(table->mask_cache);
 	struct mask_cache *new;
 
 	if (size == mc->cache_size)
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index aa821e7..813d307 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1601,12 +1601,12 @@
 			break;
 
 		case SCTP_CMD_INIT_FAILED:
-			sctp_cmd_init_failed(commands, asoc, cmd->obj.u32);
+			sctp_cmd_init_failed(commands, asoc, cmd->obj.u16);
 			break;
 
 		case SCTP_CMD_ASSOC_FAILED:
 			sctp_cmd_assoc_failed(commands, asoc, event_type,
-					      subtype, chunk, cmd->obj.u32);
+					      subtype, chunk, cmd->obj.u16);
 			break;
 
 		case SCTP_CMD_INIT_COUNTER_INC:
diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c
index a18b36b..3aad6ef 100644
--- a/net/sunrpc/sysctl.c
+++ b/net/sunrpc/sysctl.c
@@ -63,19 +63,20 @@
 			void *buffer, size_t *lenp, loff_t *ppos)
 {
 	char tmpbuf[256];
-	size_t len;
+	ssize_t len;
 
-	if ((*ppos && !write) || !*lenp) {
+	if (write || *ppos) {
 		*lenp = 0;
 		return 0;
 	}
 	len = svc_print_xprts(tmpbuf, sizeof(tmpbuf));
-	*lenp = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len);
+	len = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len);
 
-	if (*lenp < 0) {
+	if (len < 0) {
 		*lenp = 0;
 		return -EINVAL;
 	}
+	*lenp = len;
 	return 0;
 }
 
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 5f6f860..13f3143 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -664,12 +664,18 @@
 
 	ret = tipc_topsrv_work_start(srv);
 	if (ret < 0)
-		return ret;
+		goto err_start;
 
 	ret = tipc_topsrv_create_listener(srv);
 	if (ret < 0)
-		tipc_topsrv_work_stop(srv);
+		goto err_create;
 
+	return 0;
+
+err_create:
+	tipc_topsrv_work_stop(srv);
+err_start:
+	kfree(srv);
 	return ret;
 }
 
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 9f23923..240282c 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1250,8 +1250,7 @@
 }
 EXPORT_SYMBOL(cfg80211_stop_iface);
 
-void cfg80211_init_wdev(struct cfg80211_registered_device *rdev,
-			struct wireless_dev *wdev)
+void cfg80211_init_wdev(struct wireless_dev *wdev)
 {
 	mutex_init(&wdev->mtx);
 	INIT_LIST_HEAD(&wdev->event_list);
@@ -1262,6 +1261,30 @@
 	spin_lock_init(&wdev->pmsr_lock);
 	INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk);
 
+#ifdef CONFIG_CFG80211_WEXT
+	wdev->wext.default_key = -1;
+	wdev->wext.default_mgmt_key = -1;
+	wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC;
+#endif
+
+	if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT)
+		wdev->ps = true;
+	else
+		wdev->ps = false;
+	/* allow mac80211 to determine the timeout */
+	wdev->ps_timeout = -1;
+
+	if ((wdev->iftype == NL80211_IFTYPE_STATION ||
+	     wdev->iftype == NL80211_IFTYPE_P2P_CLIENT ||
+	     wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr)
+		wdev->netdev->priv_flags |= IFF_DONT_BRIDGE;
+
+	INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk);
+}
+
+void cfg80211_register_wdev(struct cfg80211_registered_device *rdev,
+			    struct wireless_dev *wdev)
+{
 	/*
 	 * We get here also when the interface changes network namespaces,
 	 * as it's registered into the new one, but we don't want it to
@@ -1295,6 +1318,11 @@
 	switch (state) {
 	case NETDEV_POST_INIT:
 		SET_NETDEV_DEVTYPE(dev, &wiphy_type);
+		wdev->netdev = dev;
+		/* can only change netns with wiphy */
+		dev->features |= NETIF_F_NETNS_LOCAL;
+
+		cfg80211_init_wdev(wdev);
 		break;
 	case NETDEV_REGISTER:
 		/*
@@ -1302,35 +1330,12 @@
 		 * called within code protected by it when interfaces
 		 * are added with nl80211.
 		 */
-		/* can only change netns with wiphy */
-		dev->features |= NETIF_F_NETNS_LOCAL;
-
 		if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj,
 				      "phy80211")) {
 			pr_err("failed to add phy80211 symlink to netdev!\n");
 		}
-		wdev->netdev = dev;
-#ifdef CONFIG_CFG80211_WEXT
-		wdev->wext.default_key = -1;
-		wdev->wext.default_mgmt_key = -1;
-		wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC;
-#endif
 
-		if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT)
-			wdev->ps = true;
-		else
-			wdev->ps = false;
-		/* allow mac80211 to determine the timeout */
-		wdev->ps_timeout = -1;
-
-		if ((wdev->iftype == NL80211_IFTYPE_STATION ||
-		     wdev->iftype == NL80211_IFTYPE_P2P_CLIENT ||
-		     wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr)
-			dev->priv_flags |= IFF_DONT_BRIDGE;
-
-		INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk);
-
-		cfg80211_init_wdev(rdev, wdev);
+		cfg80211_register_wdev(rdev, wdev);
 		break;
 	case NETDEV_GOING_DOWN:
 		cfg80211_leave(rdev, wdev);
diff --git a/net/wireless/core.h b/net/wireless/core.h
index e1ec9ac..e3e9686 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -209,8 +209,9 @@
 int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
 			  struct net *net);
 
-void cfg80211_init_wdev(struct cfg80211_registered_device *rdev,
-			struct wireless_dev *wdev);
+void cfg80211_init_wdev(struct wireless_dev *wdev);
+void cfg80211_register_wdev(struct cfg80211_registered_device *rdev,
+			    struct wireless_dev *wdev);
 
 static inline void wdev_lock(struct wireless_dev *wdev)
 	__acquires(wdev)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 554796a..a77174b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3885,7 +3885,8 @@
 		 * P2P Device and NAN do not have a netdev, so don't go
 		 * through the netdev notifier and must be added here
 		 */
-		cfg80211_init_wdev(rdev, wdev);
+		cfg80211_init_wdev(wdev);
+		cfg80211_register_wdev(rdev, wdev);
 		break;
 	default:
 		break;
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 3dab859..a04fdfb 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -3616,7 +3616,7 @@
 		power_rule = &reg_rule->power_rule;
 
 		if (reg_rule->flags & NL80211_RRF_AUTO_BW)
-			snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO",
+			snprintf(bw, sizeof(bw), "%d KHz, %u KHz AUTO",
 				 freq_range->max_bandwidth_khz,
 				 reg_get_max_bandwidth(rd, reg_rule));
 		else
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 0bbb283f..046d3fe 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -825,7 +825,7 @@
 	sock->state = SS_CONNECTED;
 	rc = 0;
 out_put_neigh:
-	if (rc) {
+	if (rc && x25->neighbour) {
 		read_lock_bh(&x25_list_lock);
 		x25_neigh_put(x25->neighbour);
 		x25->neighbour = NULL;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index b71a32e..cfbec39 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1146,7 +1146,8 @@
 	if (!sock_flag(sk, SOCK_DEAD))
 		return;
 
-	xp_put_pool(xs->pool);
+	if (!xp_put_pool(xs->pool))
+		xdp_put_umem(xs->umem);
 
 	sk_refcnt_debug_dec(sk);
 }
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 64c9e55..8a3bf4e 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -251,15 +251,18 @@
 	refcount_inc(&pool->users);
 }
 
-void xp_put_pool(struct xsk_buff_pool *pool)
+bool xp_put_pool(struct xsk_buff_pool *pool)
 {
 	if (!pool)
-		return;
+		return false;
 
 	if (refcount_dec_and_test(&pool->users)) {
 		INIT_WORK(&pool->work, xp_release_deferred);
 		schedule_work(&pool->work);
+		return true;
 	}
+
+	return false;
 }
 
 static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool)
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index aa4cdcf..9b8e292 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -803,14 +803,14 @@
 	.handler	=	xfrmi6_rcv_tunnel,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi6_err,
-	.priority	=	-1,
+	.priority	=	2,
 };
 
 static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = {
 	.handler	=	xfrmi6_rcv_tunnel,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi6_err,
-	.priority	=	-1,
+	.priority	=	2,
 };
 #endif
 
@@ -848,14 +848,14 @@
 	.handler	=	xfrmi4_rcv_tunnel,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi4_err,
-	.priority	=	-1,
+	.priority	=	3,
 };
 
 static struct xfrm_tunnel xfrmi_ipip6_handler __read_mostly = {
 	.handler	=	xfrmi4_rcv_tunnel,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi4_err,
-	.priority	=	-1,
+	.priority	=	2,
 };
 #endif
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index bbd4643..a77da7a 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2004,6 +2004,7 @@
 	int err = -ENOENT;
 	__be32 minspi = htonl(low);
 	__be32 maxspi = htonl(high);
+	__be32 newspi = 0;
 	u32 mark = x->mark.v & x->mark.m;
 
 	spin_lock_bh(&x->lock);
@@ -2022,21 +2023,22 @@
 			xfrm_state_put(x0);
 			goto unlock;
 		}
-		x->id.spi = minspi;
+		newspi = minspi;
 	} else {
 		u32 spi = 0;
 		for (h = 0; h < high-low+1; h++) {
 			spi = low + prandom_u32()%(high-low+1);
 			x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
 			if (x0 == NULL) {
-				x->id.spi = htonl(spi);
+				newspi = htonl(spi);
 				break;
 			}
 			xfrm_state_put(x0);
 		}
 	}
-	if (x->id.spi) {
+	if (newspi) {
 		spin_lock_bh(&net->xfrm.xfrm_state_lock);
+		x->id.spi = newspi;
 		h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
 		hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c
index 4a74531..b68bd2f 100644
--- a/samples/bpf/task_fd_query_user.c
+++ b/samples/bpf/task_fd_query_user.c
@@ -290,7 +290,7 @@
 
 int main(int argc, char **argv)
 {
-	struct rlimit r = {1024*1024, RLIM_INFINITY};
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	extern char __executable_start;
 	char filename[256], buf[256];
 	__u64 uprobe_file_offset;
diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c
index 3e36b3e..3d6eab7 100644
--- a/samples/bpf/tracex2_user.c
+++ b/samples/bpf/tracex2_user.c
@@ -116,7 +116,7 @@
 
 int main(int ac, char **argv)
 {
-	struct rlimit r = {1024*1024, RLIM_INFINITY};
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	long key, next_key, value;
 	struct bpf_link *links[2];
 	struct bpf_program *prog;
diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c
index 70e9877..83e0fecb 100644
--- a/samples/bpf/tracex3_user.c
+++ b/samples/bpf/tracex3_user.c
@@ -107,7 +107,7 @@
 
 int main(int ac, char **argv)
 {
-	struct rlimit r = {1024*1024, RLIM_INFINITY};
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	struct bpf_link *links[2];
 	struct bpf_program *prog;
 	struct bpf_object *obj;
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index 6fb8dbd..f78cb18 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -765,7 +765,7 @@
 
 int main(int argc, char **argv)
 {
-	struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs";
 	char *mprog_filename = "xdp_redirect_kern.o";
 	char *redir_interface = NULL, *redir_map = NULL;
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index caa4e7f..93fa1bc 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/samples/bpf/xdp_rxq_info_user.c
@@ -450,7 +450,7 @@
 int main(int argc, char **argv)
 {
 	__u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */
-	struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	struct bpf_prog_load_attr prog_load_attr = {
 		.prog_type	= BPF_PROG_TYPE_XDP,
 	};
diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py
index 6769caa..3148437 100755
--- a/scripts/bpf_helpers_doc.py
+++ b/scripts/bpf_helpers_doc.py
@@ -408,6 +408,7 @@
             'struct bpf_perf_event_data',
             'struct bpf_perf_event_value',
             'struct bpf_pidns_info',
+            'struct bpf_redir_neigh',
             'struct bpf_sock',
             'struct bpf_sock_addr',
             'struct bpf_sock_ops',
diff --git a/scripts/get_abi.pl b/scripts/get_abi.pl
index 2cb592f..68dab82 100755
--- a/scripts/get_abi.pl
+++ b/scripts/get_abi.pl
@@ -287,6 +287,8 @@
 sub output_rest {
 	create_labels();
 
+	my $part = "";
+
 	foreach my $what (sort {
 				($data{$a}->{type} eq "File") cmp ($data{$b}->{type} eq "File") ||
 				$a cmp $b
@@ -306,6 +308,21 @@
 		$w =~ s/([\(\)\_\-\*\=\^\~\\])/\\$1/g;
 
 		if ($type ne "File") {
+			my $cur_part = $what;
+			if ($what =~ '/') {
+				if ($what =~ m#^(\/?(?:[\w\-]+\/?){1,2})#) {
+					$cur_part = "Symbols under $1";
+					$cur_part =~ s,/$,,;
+				}
+			}
+
+			if ($cur_part ne "" && $part ne $cur_part) {
+			    $part = $cur_part;
+			    my $bar = $part;
+			    $bar =~ s/./-/g;
+			    print "$part\n$bar\n\n";
+			}
+
 			printf ".. _%s:\n\n", $data{$what}->{label};
 
 			my @names = split /, /,$w;
@@ -352,6 +369,12 @@
 
 		if (!($desc =~ /^\s*$/)) {
 			if ($description_is_rst) {
+				# Remove title markups from the description
+				# Having titles inside ABI files will only work if extra
+				# care would be taken in order to strictly follow the same
+				# level order for each markup.
+				$desc =~ s/\n[\-\*\=\^\~]+\n/\n\n/g;
+
 				# Enrich text by creating cross-references
 
 				$desc =~ s,Documentation/(?!devicetree)(\S+)\.rst,:doc:`/$1`,g;
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index c8f6b11..f699cf0 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1092,7 +1092,11 @@
 	print "\n\n.. c:type:: " . $name . "\n\n";
     } else {
 	my $name = $args{'struct'};
-	print "\n\n.. c:struct:: " . $name . "\n\n";
+	if ($args{'type'} eq 'union') {
+	    print "\n\n.. c:union:: " . $name . "\n\n";
+	} else {
+	    print "\n\n.. c:struct:: " . $name . "\n\n";
+	}
     }
     print_lineno($declaration_start_line);
     $lineprefix = "   ";
@@ -1427,20 +1431,25 @@
     }
 }
 
+my $typedef_type = qr { ((?:\s+[\w\*]+){1,8})\s* }x;
+my $typedef_ident = qr { \*?\s*(\w\S+)\s* }x;
+my $typedef_args = qr { \s*\((.*)\); }x;
+
+my $typedef1 = qr { typedef$typedef_type\($typedef_ident\)$typedef_args }x;
+my $typedef2 = qr { typedef$typedef_type$typedef_ident$typedef_args }x;
+
 sub dump_typedef($$) {
     my $x = shift;
     my $file = shift;
 
     $x =~ s@/\*.*?\*/@@gos;	# strip comments.
 
-    # Parse function prototypes
-    if ($x =~ /typedef\s+(\w+)\s*\(\*\s*(\w\S+)\s*\)\s*\((.*)\);/ ||
-	$x =~ /typedef\s+(\w+)\s*(\w\S+)\s*\s*\((.*)\);/) {
-
-	# Function typedefs
+    # Parse function typedef prototypes
+    if ($x =~ $typedef1 || $x =~ $typedef2) {
 	$return_type = $1;
 	$declaration_name = $2;
 	my $args = $3;
+	$return_type =~ s/^\s+//;
 
 	create_parameterlist($args, ',', $file, $declaration_name);
 
diff --git a/security/selinux/ibpkey.c b/security/selinux/ibpkey.c
index f68a761..3a63a98 100644
--- a/security/selinux/ibpkey.c
+++ b/security/selinux/ibpkey.c
@@ -151,8 +151,10 @@
 	 * is valid, it just won't be added to the cache.
 	 */
 	new = kzalloc(sizeof(*new), GFP_ATOMIC);
-	if (!new)
+	if (!new) {
+		ret = -ENOMEM;
 		goto out;
+	}
 
 	new->psec.subnet_prefix = subnet_prefix;
 	new->psec.pkey = pkey_num;
diff --git a/sound/core/control.c b/sound/core/control.c
index 421ddc7..4373de4 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -1925,8 +1925,8 @@
 
 #ifdef CONFIG_COMPAT
 /**
- * snd_ctl_unregister_ioctl - de-register the device-specific compat 32bit
- * control-ioctls
+ * snd_ctl_unregister_ioctl_compat - de-register the device-specific compat
+ * 32bit control-ioctls
  * @fcn: ioctl callback function to unregister
  */
 int snd_ctl_unregister_ioctl_compat(snd_kctl_ioctl_func_t fcn)
diff --git a/sound/core/pcm_dmaengine.c b/sound/core/pcm_dmaengine.c
index 4d059ff..4d0e8fe5 100644
--- a/sound/core/pcm_dmaengine.c
+++ b/sound/core/pcm_dmaengine.c
@@ -356,7 +356,8 @@
 EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_close);
 
 /**
- * snd_dmaengine_pcm_release_chan_close - Close a dmaengine based PCM substream and release channel
+ * snd_dmaengine_pcm_close_release_chan - Close a dmaengine based PCM
+ *					  substream and release channel
  * @substream: PCM substream
  *
  * Releases the DMA channel associated with the PCM substream.
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index d531e1b..bda3514 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -490,7 +490,7 @@
 EXPORT_SYMBOL(snd_pcm_set_ops);
 
 /**
- * snd_pcm_sync - set the PCM sync id
+ * snd_pcm_set_sync - set the PCM sync id
  * @substream: the pcm substream
  *
  * Sets the PCM sync identifier for the card.
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 9e0b2d7..47b155a 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -112,7 +112,7 @@
 EXPORT_SYMBOL_GPL(snd_pcm_stream_lock);
 
 /**
- * snd_pcm_stream_lock - Unlock the PCM stream
+ * snd_pcm_stream_unlock - Unlock the PCM stream
  * @substream: PCM substream
  *
  * This unlocks the PCM stream that has been locked via snd_pcm_stream_lock().
@@ -595,7 +595,7 @@
 }
 
 /**
- * snd_pcm_hw_param_choose - choose a configuration defined by @params
+ * snd_pcm_hw_params_choose - choose a configuration defined by @params
  * @pcm: PCM instance
  * @params: the hw_params instance
  *
diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c
index 4d060d5..b0c0ef824 100644
--- a/sound/hda/ext/hdac_ext_controller.c
+++ b/sound/hda/ext/hdac_ext_controller.c
@@ -148,6 +148,8 @@
 		return NULL;
 	if (bus->idx != bus_idx)
 		return NULL;
+	if (addr < 0 || addr > 31)
+		return NULL;
 
 	list_for_each_entry(hlink, &bus->hlink_list, list) {
 		for (i = 0; i < HDA_MAX_CODECS; i++) {
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index a356c21..4bb58e8 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -2934,7 +2934,7 @@
 	snd_hdac_leave_pm(&codec->core);
 }
 
-static int hda_codec_runtime_suspend(struct device *dev)
+static int hda_codec_suspend(struct device *dev)
 {
 	struct hda_codec *codec = dev_to_hda_codec(dev);
 	unsigned int state;
@@ -2953,7 +2953,7 @@
 	return 0;
 }
 
-static int hda_codec_runtime_resume(struct device *dev)
+static int hda_codec_resume(struct device *dev)
 {
 	struct hda_codec *codec = dev_to_hda_codec(dev);
 
@@ -2967,57 +2967,70 @@
 	pm_runtime_mark_last_busy(dev);
 	return 0;
 }
+
+static int hda_codec_runtime_suspend(struct device *dev)
+{
+	return hda_codec_suspend(dev);
+}
+
+static int hda_codec_runtime_resume(struct device *dev)
+{
+	return hda_codec_resume(dev);
+}
+
 #endif /* CONFIG_PM */
 
 #ifdef CONFIG_PM_SLEEP
-static int hda_codec_force_resume(struct device *dev)
+static int hda_codec_pm_prepare(struct device *dev)
+{
+	return pm_runtime_suspended(dev);
+}
+
+static void hda_codec_pm_complete(struct device *dev)
 {
 	struct hda_codec *codec = dev_to_hda_codec(dev);
-	int ret;
 
-	ret = pm_runtime_force_resume(dev);
-	/* schedule jackpoll work for jack detection update */
-	if (codec->jackpoll_interval ||
-	    (pm_runtime_suspended(dev) && hda_codec_need_resume(codec)))
-		schedule_delayed_work(&codec->jackpoll_work,
-				      codec->jackpoll_interval);
-	return ret;
+	if (pm_runtime_suspended(dev) && (codec->jackpoll_interval ||
+	    hda_codec_need_resume(codec) || codec->forced_resume))
+		pm_request_resume(dev);
 }
 
 static int hda_codec_pm_suspend(struct device *dev)
 {
 	dev->power.power_state = PMSG_SUSPEND;
-	return pm_runtime_force_suspend(dev);
+	return hda_codec_suspend(dev);
 }
 
 static int hda_codec_pm_resume(struct device *dev)
 {
 	dev->power.power_state = PMSG_RESUME;
-	return hda_codec_force_resume(dev);
+	return hda_codec_resume(dev);
 }
 
 static int hda_codec_pm_freeze(struct device *dev)
 {
 	dev->power.power_state = PMSG_FREEZE;
-	return pm_runtime_force_suspend(dev);
+	return hda_codec_suspend(dev);
 }
 
 static int hda_codec_pm_thaw(struct device *dev)
 {
 	dev->power.power_state = PMSG_THAW;
-	return hda_codec_force_resume(dev);
+	return hda_codec_resume(dev);
 }
 
 static int hda_codec_pm_restore(struct device *dev)
 {
 	dev->power.power_state = PMSG_RESTORE;
-	return hda_codec_force_resume(dev);
+	return hda_codec_resume(dev);
 }
 #endif /* CONFIG_PM_SLEEP */
 
 /* referred in hda_bind.c */
 const struct dev_pm_ops hda_codec_driver_pm = {
 #ifdef CONFIG_PM_SLEEP
+	.prepare = hda_codec_pm_prepare,
+	.complete = hda_codec_pm_complete,
 	.suspend = hda_codec_pm_suspend,
 	.resume = hda_codec_pm_resume,
 	.freeze = hda_codec_pm_freeze,
diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h
index be63ead..68f96687 100644
--- a/sound/pci/hda/hda_controller.h
+++ b/sound/pci/hda/hda_controller.h
@@ -41,7 +41,7 @@
 /* 24 unused */
 #define AZX_DCAPS_COUNT_LPIB_DELAY  (1 << 25)	/* Take LPIB as delay */
 #define AZX_DCAPS_PM_RUNTIME	(1 << 26)	/* runtime PM support */
-#define AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP (1 << 27) /* Workaround for spurious wakeups after suspend */
+/* 27 unused */
 #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28)	/* CORBRP clears itself after reset */
 #define AZX_DCAPS_NO_MSI64      (1 << 29)	/* Stick to 32-bit MSIs */
 #define AZX_DCAPS_SEPARATE_STREAM_TAG	(1 << 30) /* capture and playback use separate stream tag */
@@ -143,6 +143,7 @@
 	unsigned int align_buffer_size:1;
 	unsigned int region_requested:1;
 	unsigned int disabled:1; /* disabled by vga_switcheroo */
+	unsigned int pm_prepared:1;
 
 	/* GTS present */
 	unsigned int gts_present:1;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 749b880..d539f52 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -297,8 +297,7 @@
 /* PCH for HSW/BDW; with runtime PM */
 /* no i915 binding for this as HSW/BDW has another controller for HDMI */
 #define AZX_DCAPS_INTEL_PCH \
-	(AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\
-	 AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
+	(AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME)
 
 /* HSW HDMI */
 #define AZX_DCAPS_INTEL_HASWELL \
@@ -985,7 +984,7 @@
 	display_power(chip, false);
 }
 
-static void __azx_runtime_resume(struct azx *chip, bool from_rt)
+static void __azx_runtime_resume(struct azx *chip)
 {
 	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
 	struct hdac_bus *bus = azx_bus(chip);
@@ -1002,7 +1001,8 @@
 	azx_init_pci(chip);
 	hda_intel_init_chip(chip, true);
 
-	if (from_rt) {
+	/* Avoid codec resume if runtime resume is for system suspend */
+	if (!chip->pm_prepared) {
 		list_for_each_codec(codec, &chip->bus) {
 			if (codec->relaxed_resume)
 				continue;
@@ -1018,6 +1018,29 @@
 }
 
 #ifdef CONFIG_PM_SLEEP
+static int azx_prepare(struct device *dev)
+{
+	struct snd_card *card = dev_get_drvdata(dev);
+	struct azx *chip;
+
+	chip = card->private_data;
+	chip->pm_prepared = 1;
+
+	/* HDA controller always requires different WAKEEN for runtime suspend
+	 * and system suspend, so don't use direct-complete here.
+	 */
+	return 0;
+}
+
+static void azx_complete(struct device *dev)
+{
+	struct snd_card *card = dev_get_drvdata(dev);
+	struct azx *chip;
+
+	chip = card->private_data;
+	chip->pm_prepared = 0;
+}
+
 static int azx_suspend(struct device *dev)
 {
 	struct snd_card *card = dev_get_drvdata(dev);
@@ -1029,15 +1052,7 @@
 
 	chip = card->private_data;
 	bus = azx_bus(chip);
-	snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
-	/* An ugly workaround: direct call of __azx_runtime_suspend() and
-	 * __azx_runtime_resume() for old Intel platforms that suffer from
-	 * spurious wakeups after S3 suspend
-	 */
-	if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
-		__azx_runtime_suspend(chip);
-	else
-		pm_runtime_force_suspend(dev);
+	__azx_runtime_suspend(chip);
 	if (bus->irq >= 0) {
 		free_irq(bus->irq, chip);
 		bus->irq = -1;
@@ -1066,11 +1081,7 @@
 	if (azx_acquire_irq(chip, 1) < 0)
 		return -EIO;
 
-	if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
-		__azx_runtime_resume(chip, false);
-	else
-		pm_runtime_force_resume(dev);
-	snd_power_change_state(card, SNDRV_CTL_POWER_D0);
+	__azx_runtime_resume(chip);
 
 	trace_azx_resume(chip);
 	return 0;
@@ -1118,10 +1129,7 @@
 	chip = card->private_data;
 
 	/* enable controller wake up event */
-	if (snd_power_get_state(card) == SNDRV_CTL_POWER_D0) {
-		azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) |
-			   STATESTS_INT_MASK);
-	}
+	azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) | STATESTS_INT_MASK);
 
 	__azx_runtime_suspend(chip);
 	trace_azx_runtime_suspend(chip);
@@ -1132,18 +1140,14 @@
 {
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip;
-	bool from_rt = snd_power_get_state(card) == SNDRV_CTL_POWER_D0;
 
 	if (!azx_is_pm_ready(card))
 		return 0;
 	chip = card->private_data;
-	__azx_runtime_resume(chip, from_rt);
+	__azx_runtime_resume(chip);
 
 	/* disable controller Wake Up event*/
-	if (from_rt) {
-		azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) &
-			   ~STATESTS_INT_MASK);
-	}
+	azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & ~STATESTS_INT_MASK);
 
 	trace_azx_runtime_resume(chip);
 	return 0;
@@ -1177,6 +1181,8 @@
 static const struct dev_pm_ops azx_pm = {
 	SET_SYSTEM_SLEEP_PM_OPS(azx_suspend, azx_resume)
 #ifdef CONFIG_PM_SLEEP
+	.prepare = azx_prepare,
+	.complete = azx_complete,
 	.freeze_noirq = azx_freeze_noirq,
 	.thaw_noirq = azx_thaw_noirq,
 #endif
@@ -2356,6 +2362,7 @@
 
 	if (azx_has_pm_runtime(chip)) {
 		pm_runtime_use_autosuspend(&pci->dev);
+		pm_runtime_allow(&pci->dev);
 		pm_runtime_put_autosuspend(&pci->dev);
 	}
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f239872..6899089 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6008,6 +6008,27 @@
 	snd_hda_override_wcaps(codec, 0x03, 0);
 }
 
+static void alc_combo_jack_hp_jd_restart(struct hda_codec *codec)
+{
+	switch (codec->core.vendor_id) {
+	case 0x10ec0274:
+	case 0x10ec0294:
+	case 0x10ec0225:
+	case 0x10ec0295:
+	case 0x10ec0299:
+		alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */
+		alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15);
+		break;
+	case 0x10ec0235:
+	case 0x10ec0236:
+	case 0x10ec0255:
+	case 0x10ec0256:
+		alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
+		alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
+		break;
+	}
+}
+
 static void alc295_fixup_chromebook(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
@@ -6018,16 +6039,7 @@
 		spec->ultra_low_power = true;
 		break;
 	case HDA_FIXUP_ACT_INIT:
-		switch (codec->core.vendor_id) {
-		case 0x10ec0295:
-			alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */
-			alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15);
-			break;
-		case 0x10ec0236:
-			alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
-			alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
-			break;
-		}
+		alc_combo_jack_hp_jd_restart(codec);
 		break;
 	}
 }
@@ -6083,6 +6095,16 @@
 	alc_write_coef_idx(codec, 0x65, 0x0);
 }
 
+static void alc274_fixup_hp_headset_mic(struct hda_codec *codec,
+				    const struct hda_fixup *fix, int action)
+{
+	switch (action) {
+	case HDA_FIXUP_ACT_INIT:
+		alc_combo_jack_hp_jd_restart(codec);
+		break;
+	}
+}
+
 /* for hda_fixup_thinkpad_acpi() */
 #include "thinkpad_helper.c"
 
@@ -6277,6 +6299,8 @@
 	ALC256_FIXUP_INTEL_NUC8_RUGGED,
 	ALC255_FIXUP_XIAOMI_HEADSET_MIC,
 	ALC274_FIXUP_HP_MIC,
+	ALC274_FIXUP_HP_HEADSET_MIC,
+	ALC256_FIXUP_ASUS_HPE,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -7664,6 +7688,23 @@
 			{ }
 		},
 	},
+	[ALC274_FIXUP_HP_HEADSET_MIC] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc274_fixup_hp_headset_mic,
+		.chained = true,
+		.chain_id = ALC274_FIXUP_HP_MIC
+	},
+	[ALC256_FIXUP_ASUS_HPE] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			/* Set EAPD high */
+			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x0f },
+			{ 0x20, AC_VERB_SET_PROC_COEF, 0x7778 },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -7815,7 +7856,6 @@
 	SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT),
-	SND_PCI_QUIRK(0x103c, 0x874e, "HP", ALC274_FIXUP_HP_MIC),
 	SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED),
@@ -7848,6 +7888,7 @@
 	SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
 	SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
 	SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS),
@@ -8339,6 +8380,10 @@
 		{0x1a, 0x90a70130},
 		{0x1b, 0x90170110},
 		{0x21, 0x03211020}),
+       SND_HDA_PIN_QUIRK(0x10ec0274, 0x103c, "HP", ALC274_FIXUP_HP_HEADSET_MIC,
+		{0x17, 0x90170110},
+		{0x19, 0x03a11030},
+		{0x21, 0x03211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4,
 		{0x12, 0x90a60130},
 		{0x14, 0x90170110},
diff --git a/sound/soc/atmel/mchp-spdiftx.c b/sound/soc/atmel/mchp-spdiftx.c
index 82c1eec..3bd350a 100644
--- a/sound/soc/atmel/mchp-spdiftx.c
+++ b/sound/soc/atmel/mchp-spdiftx.c
@@ -487,7 +487,6 @@
 	}
 	mchp_spdiftx_channel_status_write(dev);
 	spin_unlock_irqrestore(&ctrl->lock, flags);
-	mr |= SPDIFTX_MR_VALID1 | SPDIFTX_MR_VALID2;
 
 	if (dev->gclk_enabled) {
 		clk_disable_unprepare(dev->gclk);
diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c
index 097c4e8..c61b17d 100644
--- a/sound/soc/codecs/cs42l51.c
+++ b/sound/soc/codecs/cs42l51.c
@@ -254,8 +254,28 @@
 		&cs42l51_adcr_mux_controls),
 };
 
+static int mclk_event(struct snd_soc_dapm_widget *w,
+		      struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *comp = snd_soc_dapm_to_component(w->dapm);
+	struct cs42l51_private *cs42l51 = snd_soc_component_get_drvdata(comp);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		return clk_prepare_enable(cs42l51->mclk_handle);
+	case SND_SOC_DAPM_POST_PMD:
+		/* Delay mclk shutdown to fulfill power-down sequence requirements */
+		msleep(20);
+		clk_disable_unprepare(cs42l51->mclk_handle);
+		break;
+	}
+
+	return 0;
+}
+
 static const struct snd_soc_dapm_widget cs42l51_dapm_mclk_widgets[] = {
-	SND_SOC_DAPM_CLOCK_SUPPLY("MCLK")
+	SND_SOC_DAPM_SUPPLY("MCLK", SND_SOC_NOPM, 0, 0, mclk_event,
+			    SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
 };
 
 static const struct snd_soc_dapm_route cs42l51_routes[] = {
diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c
index f2d9d52..4d2b1ec7 100644
--- a/sound/soc/codecs/wcd9335.c
+++ b/sound/soc/codecs/wcd9335.c
@@ -618,7 +618,7 @@
 	"ZERO", "RX_MIX_TX8", "DEC8", "DEC8_192"
 };
 
-static const DECLARE_TLV_DB_SCALE(digital_gain, 0, 1, 0);
+static const DECLARE_TLV_DB_SCALE(digital_gain, -8400, 100, -8400);
 static const DECLARE_TLV_DB_SCALE(line_gain, 0, 7, 1);
 static const DECLARE_TLV_DB_SCALE(analog_gain, 0, 25, 1);
 static const DECLARE_TLV_DB_SCALE(ear_pa_gain, 0, 150, 0);
diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c
index 35697b0..40f682f 100644
--- a/sound/soc/codecs/wcd934x.c
+++ b/sound/soc/codecs/wcd934x.c
@@ -551,7 +551,7 @@
 	struct soc_bytes_ext bytes_ext;
 };
 
-static const DECLARE_TLV_DB_SCALE(digital_gain, 0, 1, 0);
+static const DECLARE_TLV_DB_SCALE(digital_gain, -8400, 100, -8400);
 static const DECLARE_TLV_DB_SCALE(line_gain, 0, 7, 1);
 static const DECLARE_TLV_DB_SCALE(analog_gain, 0, 25, 1);
 static const DECLARE_TLV_DB_SCALE(ear_pa_gain, 0, 150, 0);
diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c
index 68e774e..4530b74 100644
--- a/sound/soc/codecs/wsa881x.c
+++ b/sound/soc/codecs/wsa881x.c
@@ -1026,6 +1026,8 @@
 		.id = 0,
 		.playback = {
 			.stream_name = "SPKR Playback",
+			.rates = SNDRV_PCM_RATE_48000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
 			.rate_max = 48000,
 			.rate_min = 48000,
 			.channels_min = 1,
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index d5bae5d..a5b446d 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -15,22 +15,6 @@
 
 if SND_SOC_INTEL_SST_TOPLEVEL
 
-config SND_SST_IPC
-	tristate
-	# This option controls the IPC core for HiFi2 platforms
-
-config SND_SST_IPC_PCI
-	tristate
-	select SND_SST_IPC
-	# This option controls the PCI-based IPC for HiFi2 platforms
-	#  (Medfield, Merrifield).
-
-config SND_SST_IPC_ACPI
-	tristate
-	select SND_SST_IPC
-	# This option controls the ACPI-based IPC for HiFi2 platforms
-	# (Baytrail, Cherrytrail)
-
 config SND_SOC_INTEL_SST
 	tristate
 
@@ -57,7 +41,6 @@
 config SND_SST_ATOM_HIFI2_PLATFORM_PCI
 	tristate "PCI HiFi2 (Merrifield) Platforms"
 	depends on X86 && PCI
-	select SND_SST_IPC_PCI
 	select SND_SST_ATOM_HIFI2_PLATFORM
 	help
 	  If you have a Intel Merrifield/Edison platform, then
@@ -70,7 +53,6 @@
 	tristate "ACPI HiFi2 (Baytrail, Cherrytrail) Platforms"
 	default ACPI
 	depends on X86 && ACPI && PCI
-	select SND_SST_IPC_ACPI
 	select SND_SST_ATOM_HIFI2_PLATFORM
 	select SND_SOC_ACPI_INTEL_MATCH
 	select IOSF_MBI
diff --git a/sound/soc/intel/atom/Makefile b/sound/soc/intel/atom/Makefile
index a9326d5..c66f03f 100644
--- a/sound/soc/intel/atom/Makefile
+++ b/sound/soc/intel/atom/Makefile
@@ -6,4 +6,4 @@
 obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += snd-soc-sst-atom-hifi2-platform.o
 
 # DSP driver
-obj-$(CONFIG_SND_SST_IPC) += sst/
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += sst/
diff --git a/sound/soc/intel/atom/sst/Makefile b/sound/soc/intel/atom/sst/Makefile
index f17c905..5761d30 100644
--- a/sound/soc/intel/atom/sst/Makefile
+++ b/sound/soc/intel/atom/sst/Makefile
@@ -3,6 +3,6 @@
 snd-intel-sst-pci-objs += sst_pci.o
 snd-intel-sst-acpi-objs += sst_acpi.o
 
-obj-$(CONFIG_SND_SST_IPC) += snd-intel-sst-core.o
-obj-$(CONFIG_SND_SST_IPC_PCI) += snd-intel-sst-pci.o
-obj-$(CONFIG_SND_SST_IPC_ACPI) += snd-intel-sst-acpi.o
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += snd-intel-sst-core.o
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM_PCI) += snd-intel-sst-pci.o
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM_ACPI) += snd-intel-sst-acpi.o
diff --git a/sound/soc/intel/boards/kbl_rt5663_max98927.c b/sound/soc/intel/boards/kbl_rt5663_max98927.c
index 3ea4602..9a4b3d0 100644
--- a/sound/soc/intel/boards/kbl_rt5663_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_max98927.c
@@ -401,17 +401,40 @@
 	struct snd_interval *chan = hw_param_interval(params,
 			SNDRV_PCM_HW_PARAM_CHANNELS);
 	struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
-	struct snd_soc_dpcm *dpcm = container_of(
-			params, struct snd_soc_dpcm, hw_params);
-	struct snd_soc_dai_link *fe_dai_link = dpcm->fe->dai_link;
-	struct snd_soc_dai_link *be_dai_link = dpcm->be->dai_link;
+	struct snd_soc_dpcm *dpcm, *rtd_dpcm = NULL;
+
+	/*
+	 * The following loop will be called only for playback stream
+	 * In this platform, there is only one playback device on every SSP
+	 */
+	for_each_dpcm_fe(rtd, SNDRV_PCM_STREAM_PLAYBACK, dpcm) {
+		rtd_dpcm = dpcm;
+		break;
+	}
+
+	/*
+	 * This following loop will be called only for capture stream
+	 * In this platform, there is only one capture device on every SSP
+	 */
+	for_each_dpcm_fe(rtd, SNDRV_PCM_STREAM_CAPTURE, dpcm) {
+		rtd_dpcm = dpcm;
+		break;
+	}
+
+	if (!rtd_dpcm)
+		return -EINVAL;
+
+	/*
+	 * The above 2 loops are mutually exclusive based on the stream direction,
+	 * thus rtd_dpcm variable will never be overwritten
+	 */
 
 	/*
 	 * The ADSP will convert the FE rate to 48k, stereo, 24 bit
 	 */
-	if (!strcmp(fe_dai_link->name, "Kbl Audio Port") ||
-	    !strcmp(fe_dai_link->name, "Kbl Audio Headset Playback") ||
-	    !strcmp(fe_dai_link->name, "Kbl Audio Capture Port")) {
+	if (!strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Port") ||
+	    !strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Headset Playback") ||
+	    !strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Capture Port")) {
 		rate->min = rate->max = 48000;
 		chan->min = chan->max = 2;
 		snd_mask_none(fmt);
@@ -421,7 +444,7 @@
 	 * The speaker on the SSP0 supports S16_LE and not S24_LE.
 	 * thus changing the mask here
 	 */
-	if (!strcmp(be_dai_link->name, "SSP0-Codec"))
+	if (!strcmp(rtd_dpcm->be->dai_link->name, "SSP0-Codec"))
 		snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S16_LE);
 
 	return 0;
diff --git a/sound/soc/intel/catpt/dsp.c b/sound/soc/intel/catpt/dsp.c
index 7d29685..9e807b9 100644
--- a/sound/soc/intel/catpt/dsp.c
+++ b/sound/soc/intel/catpt/dsp.c
@@ -267,9 +267,12 @@
 					    reg, (reg & CATPT_ISD_DCPWM),
 					    500, 10000);
 		if (ret) {
-			dev_err(cdev->dev, "await WAITI timeout\n");
-			mutex_unlock(&cdev->clk_mutex);
-			return ret;
+			dev_warn(cdev->dev, "await WAITI timeout\n");
+			/* no signal - only high clock selection allowed */
+			if (lp) {
+				mutex_unlock(&cdev->clk_mutex);
+				return 0;
+			}
 		}
 	}
 
diff --git a/sound/soc/intel/catpt/pcm.c b/sound/soc/intel/catpt/pcm.c
index f78018c..ba653eb 100644
--- a/sound/soc/intel/catpt/pcm.c
+++ b/sound/soc/intel/catpt/pcm.c
@@ -667,7 +667,17 @@
 		break;
 	}
 
+	/* see if this is a new configuration */
+	if (!memcmp(&cdev->devfmt[devfmt.iface], &devfmt, sizeof(devfmt)))
+		return 0;
+
+	pm_runtime_get_sync(cdev->dev);
+
 	ret = catpt_ipc_set_device_format(cdev, &devfmt);
+
+	pm_runtime_mark_last_busy(cdev->dev);
+	pm_runtime_put_autosuspend(cdev->dev);
+
 	if (ret)
 		return CATPT_IPC_ERROR(ret);
 
diff --git a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c
index c2c1eb16..26e7d9a 100644
--- a/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c
+++ b/sound/soc/mediatek/mt8183/mt8183-da7219-max98357.c
@@ -630,15 +630,34 @@
 	},
 };
 
+static const struct snd_kcontrol_new mt8183_da7219_rt1015_snd_controls[] = {
+	SOC_DAPM_PIN_SWITCH("Left Spk"),
+	SOC_DAPM_PIN_SWITCH("Right Spk"),
+};
+
+static const
+struct snd_soc_dapm_widget mt8183_da7219_rt1015_dapm_widgets[] = {
+	SND_SOC_DAPM_SPK("Left Spk", NULL),
+	SND_SOC_DAPM_SPK("Right Spk", NULL),
+	SND_SOC_DAPM_PINCTRL("TDM_OUT_PINCTRL",
+			     "aud_tdm_out_on", "aud_tdm_out_off"),
+};
+
+static const struct snd_soc_dapm_route mt8183_da7219_rt1015_dapm_routes[] = {
+	{"Left Spk", NULL, "Left SPO"},
+	{"Right Spk", NULL, "Right SPO"},
+	{"I2S Playback", NULL, "TDM_OUT_PINCTRL"},
+};
+
 static struct snd_soc_card mt8183_da7219_rt1015_card = {
 	.name = "mt8183_da7219_rt1015",
 	.owner = THIS_MODULE,
-	.controls = mt8183_da7219_max98357_snd_controls,
-	.num_controls = ARRAY_SIZE(mt8183_da7219_max98357_snd_controls),
-	.dapm_widgets = mt8183_da7219_max98357_dapm_widgets,
-	.num_dapm_widgets = ARRAY_SIZE(mt8183_da7219_max98357_dapm_widgets),
-	.dapm_routes = mt8183_da7219_max98357_dapm_routes,
-	.num_dapm_routes = ARRAY_SIZE(mt8183_da7219_max98357_dapm_routes),
+	.controls = mt8183_da7219_rt1015_snd_controls,
+	.num_controls = ARRAY_SIZE(mt8183_da7219_rt1015_snd_controls),
+	.dapm_widgets = mt8183_da7219_rt1015_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(mt8183_da7219_rt1015_dapm_widgets),
+	.dapm_routes = mt8183_da7219_rt1015_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(mt8183_da7219_rt1015_dapm_routes),
 	.dai_link = mt8183_da7219_dai_links,
 	.num_links = ARRAY_SIZE(mt8183_da7219_dai_links),
 	.aux_dev = &mt8183_da7219_max98357_headset_dev,
diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c
index ba2aca3..9d17c87 100644
--- a/sound/soc/qcom/lpass-cpu.c
+++ b/sound/soc/qcom/lpass-cpu.c
@@ -80,6 +80,12 @@
 		dev_err(dai->dev, "error in enabling mi2s osr clk: %d\n", ret);
 		return ret;
 	}
+	ret = clk_prepare(drvdata->mi2s_bit_clk[dai->driver->id]);
+	if (ret) {
+		dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret);
+		clk_disable_unprepare(drvdata->mi2s_osr_clk[dai->driver->id]);
+		return ret;
+	}
 	return 0;
 }
 
@@ -88,9 +94,8 @@
 {
 	struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai);
 
-	clk_disable_unprepare(drvdata->mi2s_bit_clk[dai->driver->id]);
-
 	clk_disable_unprepare(drvdata->mi2s_osr_clk[dai->driver->id]);
+	clk_unprepare(drvdata->mi2s_bit_clk[dai->driver->id]);
 }
 
 static int lpass_cpu_daiops_hw_params(struct snd_pcm_substream *substream,
@@ -303,10 +308,10 @@
 			dev_err(dai->dev, "error writing to i2sctl reg: %d\n",
 				ret);
 
-		ret = clk_prepare_enable(drvdata->mi2s_bit_clk[id]);
+		ret = clk_enable(drvdata->mi2s_bit_clk[id]);
 		if (ret) {
 			dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret);
-			clk_disable_unprepare(drvdata->mi2s_osr_clk[id]);
+			clk_disable(drvdata->mi2s_osr_clk[id]);
 			return ret;
 		}
 
@@ -324,6 +329,7 @@
 		if (ret)
 			dev_err(dai->dev, "error writing to i2sctl reg: %d\n",
 				ret);
+		clk_disable(drvdata->mi2s_bit_clk[dai->driver->id]);
 		break;
 	}
 
diff --git a/sound/soc/qcom/lpass-sc7180.c b/sound/soc/qcom/lpass-sc7180.c
index c6292f9e..bc998d5 100644
--- a/sound/soc/qcom/lpass-sc7180.c
+++ b/sound/soc/qcom/lpass-sc7180.c
@@ -188,7 +188,7 @@
 	.micmode		= REG_FIELD_ID(0x1000, 4, 8, 3, 0x1000),
 	.micmono		= REG_FIELD_ID(0x1000, 3, 3, 3, 0x1000),
 	.wssrc			= REG_FIELD_ID(0x1000, 2, 2, 3, 0x1000),
-	.bitwidth		= REG_FIELD_ID(0x1000, 0, 0, 3, 0x1000),
+	.bitwidth		= REG_FIELD_ID(0x1000, 0, 1, 3, 0x1000),
 
 	.rdma_dyncclk		= REG_FIELD_ID(0xC000, 21, 21, 5, 0x1000),
 	.rdma_bursten		= REG_FIELD_ID(0xC000, 20, 20, 5, 0x1000),
diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
index ab1bf23..6c2760e 100644
--- a/sound/soc/qcom/sdm845.c
+++ b/sound/soc/qcom/sdm845.c
@@ -17,6 +17,7 @@
 #include "qdsp6/q6afe.h"
 #include "../codecs/rt5663.h"
 
+#define DRIVER_NAME	"sdm845"
 #define DEFAULT_SAMPLE_RATE_48K		48000
 #define DEFAULT_MCLK_RATE		24576000
 #define TDM_BCLK_RATE		6144000
@@ -552,6 +553,7 @@
 	if (!data)
 		return -ENOMEM;
 
+	card->driver_name = DRIVER_NAME;
 	card->dapm_widgets = sdm845_snd_widgets;
 	card->num_dapm_widgets = ARRAY_SIZE(sdm845_snd_widgets);
 	card->dev = dev;
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index ea3986a..05a085f 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2341,7 +2341,7 @@
 }
 
 /**
- * snd_soc_unregister_dai - Unregister DAIs from the ASoC core
+ * snd_soc_unregister_dais - Unregister DAIs from the ASoC core
  *
  * @component: The component for which the DAIs should be unregistered
  */
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 980f2c3..7f87b44 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1276,7 +1276,7 @@
 }
 
 /**
- * snd_soc_dapm_get_connected_widgets - query audio path and it's widgets.
+ * snd_soc_dapm_dai_get_connected_widgets - query audio path and it's widgets.
  * @dai: the soc DAI.
  * @stream: stream direction.
  * @list: list of active widgets for this stream.
diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c
index 68ed454..ba9ed66 100644
--- a/sound/soc/sof/loader.c
+++ b/sound/soc/sof/loader.c
@@ -118,6 +118,11 @@
 		case SOF_IPC_EXT_CC_INFO:
 			ret = get_cc_info(sdev, ext_hdr);
 			break;
+		case SOF_IPC_EXT_UNUSED:
+		case SOF_IPC_EXT_PROBE_INFO:
+		case SOF_IPC_EXT_USER_ABI_INFO:
+			/* They are supported but we don't do anything here */
+			break;
 		default:
 			dev_warn(sdev->dev, "warning: unknown ext header type %d size 0x%x\n",
 				 ext_hdr->type, ext_hdr->hdr.size);
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index b401ee8..a860303 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -336,6 +336,7 @@
 	switch (subs->stream->chip->usb_id) {
 	case USB_ID(0x0763, 0x2030): /* M-Audio Fast Track C400 */
 	case USB_ID(0x0763, 0x2031): /* M-Audio Fast Track C600 */
+	case USB_ID(0x22f0, 0x0006): /* Allen&Heath Qu-16 */
 		ep = 0x81;
 		ifnum = 3;
 		goto add_sync_ep_from_ifnum;
@@ -345,6 +346,7 @@
 		ifnum = 2;
 		goto add_sync_ep_from_ifnum;
 	case USB_ID(0x2466, 0x8003): /* Fractal Audio Axe-Fx II */
+	case USB_ID(0x0499, 0x172a): /* Yamaha MODX */
 		ep = 0x86;
 		ifnum = 2;
 		goto add_sync_ep_from_ifnum;
@@ -352,6 +354,10 @@
 		ep = 0x81;
 		ifnum = 2;
 		goto add_sync_ep_from_ifnum;
+	case USB_ID(0x1686, 0xf029): /* Zoom UAC-2 */
+		ep = 0x82;
+		ifnum = 2;
+		goto add_sync_ep_from_ifnum;
 	case USB_ID(0x1397, 0x0001): /* Behringer UFX1604 */
 	case USB_ID(0x1397, 0x0002): /* Behringer UFX1204 */
 		ep = 0x81;
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index b4fa80e..c989ad8 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1800,6 +1800,7 @@
 	case 0x278b:  /* Rotel? */
 	case 0x292b:  /* Gustard/Ess based devices */
 	case 0x2ab6:  /* T+A devices */
+	case 0x3353:  /* Khadas devices */
 	case 0x3842:  /* EVGA */
 	case 0xc502:  /* HiBy devices */
 		if (fp->dsd_raw)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index ba85bb2..1c17c3a 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -159,6 +159,21 @@
 struct kvm_arch_memory_slot {
 };
 
+/*
+ * PMU filter structure. Describe a range of events with a particular
+ * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.
+ */
+struct kvm_pmu_event_filter {
+	__u16	base_event;
+	__u16	nevents;
+
+#define KVM_PMU_EVENT_ALLOW	0
+#define KVM_PMU_EVENT_DENY	1
+
+	__u8	action;
+	__u8	pad[3];
+};
+
 /* for KVM_GET/SET_VCPU_EVENTS */
 struct kvm_vcpu_events {
 	struct {
@@ -242,6 +257,15 @@
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL		0
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL		1
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED	2
+
+/*
+ * Only two states can be presented by the host kernel:
+ * - NOT_REQUIRED: the guest doesn't need to do anything
+ * - NOT_AVAIL: the guest isn't mitigated (it can still use SSBS if available)
+ *
+ * All the other values are deprecated. The host still accepts all
+ * values (they are ABI), but will narrow them to the above two.
+ */
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2	KVM_REG_ARM_FW_REG(2)
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL		0
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN		1
@@ -329,6 +353,7 @@
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
 #define   KVM_ARM_VCPU_PMU_V3_IRQ	0
 #define   KVM_ARM_VCPU_PMU_V3_INIT	1
+#define   KVM_ARM_VCPU_PMU_V3_FILTER	2
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h
index 6ca1e68..ede3186 100644
--- a/tools/arch/s390/include/uapi/asm/sie.h
+++ b/tools/arch/s390/include/uapi/asm/sie.h
@@ -29,7 +29,7 @@
 	{ 0x13, "SIGP conditional emergency signal" },		\
 	{ 0x15, "SIGP sense running" },				\
 	{ 0x16, "SIGP set multithreading"},			\
-	{ 0x17, "SIGP store additional status ait address"}
+	{ 0x17, "SIGP store additional status at address"}
 
 #define icpt_prog_codes						\
 	{ 0x0001, "Prog Operation" },				\
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 2901d5d..dad350d 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -96,7 +96,7 @@
 #define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in IA32 userspace */
 #define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
 #define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
-/* free					( 3*32+17) */
+#define X86_FEATURE_SME_COHERENT	( 3*32+17) /* "" AMD hardware-enforced cache coherency */
 #define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
 #define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
 #define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
@@ -236,6 +236,7 @@
 #define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 #define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
 #define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_SEV_ES		( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -288,6 +289,7 @@
 #define X86_FEATURE_FENCE_SWAPGS_USER	(11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
 #define X86_FEATURE_FENCE_SWAPGS_KERNEL	(11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
 #define X86_FEATURE_SPLIT_LOCK_DETECT	(11*32+ 6) /* #AC for split lock */
+#define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
@@ -353,6 +355,7 @@
 #define X86_FEATURE_CLDEMOTE		(16*32+25) /* CLDEMOTE instruction */
 #define X86_FEATURE_MOVDIRI		(16*32+27) /* MOVDIRI instruction */
 #define X86_FEATURE_MOVDIR64B		(16*32+28) /* MOVDIR64B instruction */
+#define X86_FEATURE_ENQCMD		(16*32+29) /* ENQCMD and ENQCMDS instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
@@ -368,6 +371,7 @@
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_SERIALIZE		(18*32+14) /* SERIALIZE instruction */
+#define X86_FEATURE_TSXLDTRK		(18*32+16) /* TSX Suspend Load Address Tracking */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_ARCH_LBR		(18*32+19) /* Intel ARCH LBR */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 4ea8584..5861d34 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -56,6 +56,12 @@
 # define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
 #endif
 
+#ifdef CONFIG_IOMMU_SUPPORT
+# define DISABLE_ENQCMD	0
+#else
+# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -75,7 +81,8 @@
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
+			 DISABLE_ENQCMD)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK18	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 2859ee4..972a34d 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -257,6 +257,9 @@
 #define MSR_IA32_LASTINTFROMIP		0x000001dd
 #define MSR_IA32_LASTINTTOIP		0x000001de
 
+#define MSR_IA32_PASID			0x00000d93
+#define MSR_IA32_PASID_VALID		BIT_ULL(31)
+
 /* DEBUGCTLMSR bits (others vary by model): */
 #define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
 #define DEBUGCTLMSR_BTF_SHIFT		1
@@ -464,11 +467,15 @@
 #define MSR_AMD64_IBSOP_REG_MASK	((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
 #define MSR_AMD64_IBSCTL		0xc001103a
 #define MSR_AMD64_IBSBRTARGET		0xc001103b
+#define MSR_AMD64_ICIBSEXTDCTL		0xc001103c
 #define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SEV_ES_GHCB		0xc0010130
 #define MSR_AMD64_SEV			0xc0010131
 #define MSR_AMD64_SEV_ENABLED_BIT	0
+#define MSR_AMD64_SEV_ES_ENABLED_BIT	1
 #define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_SEV_ES_ENABLED	BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
 
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 
@@ -857,11 +864,14 @@
 #define MSR_CORE_PERF_FIXED_CTR0	0x00000309
 #define MSR_CORE_PERF_FIXED_CTR1	0x0000030a
 #define MSR_CORE_PERF_FIXED_CTR2	0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR3	0x0000030c
 #define MSR_CORE_PERF_FIXED_CTR_CTRL	0x0000038d
 #define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
 #define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
 
+#define MSR_PERF_METRICS		0x00000329
+
 /* PERF_GLOBAL_OVF_CTL bits */
 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT	55
 #define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI		(1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT)
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index 6847d85..3ff0d48 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -54,7 +54,7 @@
 #endif
 
 #ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
 /* Paravirtualized systems may not have PSE or PGE available */
 #define NEED_PSE	0
 #define NEED_PGE	0
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 0780f97..89e5f3d 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -192,6 +192,26 @@
 	__u32 indices[0];
 };
 
+/* Maximum size of any access bitmap in bytes */
+#define KVM_MSR_FILTER_MAX_BITMAP_SIZE 0x600
+
+/* for KVM_X86_SET_MSR_FILTER */
+struct kvm_msr_filter_range {
+#define KVM_MSR_FILTER_READ  (1 << 0)
+#define KVM_MSR_FILTER_WRITE (1 << 1)
+	__u32 flags;
+	__u32 nmsrs; /* number of msrs in bitmap */
+	__u32 base;  /* MSR index the bitmap starts at */
+	__u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
+};
+
+#define KVM_MSR_FILTER_MAX_RANGES 16
+struct kvm_msr_filter {
+#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#define KVM_MSR_FILTER_DEFAULT_DENY  (1 << 0)
+	__u32 flags;
+	struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
+};
 
 struct kvm_cpuid_entry {
 	__u32 function;
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index 2e8a30f..f1d8307 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -29,6 +29,7 @@
 #define SVM_EXIT_WRITE_DR6     0x036
 #define SVM_EXIT_WRITE_DR7     0x037
 #define SVM_EXIT_EXCP_BASE     0x040
+#define SVM_EXIT_LAST_EXCP     0x05f
 #define SVM_EXIT_INTR          0x060
 #define SVM_EXIT_NMI           0x061
 #define SVM_EXIT_SMI           0x062
@@ -76,10 +77,21 @@
 #define SVM_EXIT_MWAIT_COND    0x08c
 #define SVM_EXIT_XSETBV        0x08d
 #define SVM_EXIT_RDPRU         0x08e
+#define SVM_EXIT_INVPCID       0x0a2
 #define SVM_EXIT_NPF           0x400
 #define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS	0x402
 
+/* SEV-ES software-defined VMGEXIT events */
+#define SVM_VMGEXIT_MMIO_READ			0x80000001
+#define SVM_VMGEXIT_MMIO_WRITE			0x80000002
+#define SVM_VMGEXIT_NMI_COMPLETE		0x80000003
+#define SVM_VMGEXIT_AP_HLT_LOOP			0x80000004
+#define SVM_VMGEXIT_AP_JUMP_TABLE		0x80000005
+#define SVM_VMGEXIT_SET_AP_JUMP_TABLE		0
+#define SVM_VMGEXIT_GET_AP_JUMP_TABLE		1
+#define SVM_VMGEXIT_UNSUPPORTED_EVENT		0x8000ffff
+
 #define SVM_EXIT_ERR           -1
 
 #define SVM_EXIT_REASONS \
@@ -171,6 +183,7 @@
 	{ SVM_EXIT_MONITOR,     "monitor" }, \
 	{ SVM_EXIT_MWAIT,       "mwait" }, \
 	{ SVM_EXIT_XSETBV,      "xsetbv" }, \
+	{ SVM_EXIT_INVPCID,     "invpcid" }, \
 	{ SVM_EXIT_NPF,         "npf" }, \
 	{ SVM_EXIT_AVIC_INCOMPLETE_IPI,		"avic_incomplete_ipi" }, \
 	{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS,   "avic_unaccelerated_access" }, \
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 0b5b8ae..1e299ac 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -16,8 +16,6 @@
  * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
  */
 
-.weak memcpy
-
 /*
  * memcpy - Copy a memory block.
  *
@@ -30,7 +28,7 @@
  * rax original destination
  */
 SYM_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_LOCAL(memcpy)
+SYM_FUNC_START_WEAK(memcpy)
 	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memcpy_erms", X86_FEATURE_ERMS
 
@@ -51,14 +49,14 @@
  * memcpy_erms() - enhanced fast string memcpy. This is faster and
  * simpler than memcpy. Use memcpy_erms when possible.
  */
-SYM_FUNC_START(memcpy_erms)
+SYM_FUNC_START_LOCAL(memcpy_erms)
 	movq %rdi, %rax
 	movq %rdx, %rcx
 	rep movsb
 	ret
 SYM_FUNC_END(memcpy_erms)
 
-SYM_FUNC_START(memcpy_orig)
+SYM_FUNC_START_LOCAL(memcpy_orig)
 	movq %rdi, %rax
 
 	cmpq $0x20, %rdx
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index fd5d25a..0bfd26e 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -4,8 +4,7 @@
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
-
-.weak memset
+#include <asm/export.h>
 
 /*
  * ISO C memset - set a memory block to a byte value. This function uses fast
@@ -18,7 +17,7 @@
  *
  * rax   original destination
  */
-SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START_WEAK(memset)
 SYM_FUNC_START(__memset)
 	/*
 	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
@@ -44,6 +43,8 @@
 	ret
 SYM_FUNC_END(__memset)
 SYM_FUNC_END_ALIAS(memset)
+EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL(__memset)
 
 /*
  * ISO C memset - set a memory block to a byte value. This function uses
@@ -56,7 +57,7 @@
  *
  * rax   original destination
  */
-SYM_FUNC_START(memset_erms)
+SYM_FUNC_START_LOCAL(memset_erms)
 	movq %rdi,%r9
 	movb %sil,%al
 	movq %rdx,%rcx
@@ -65,7 +66,7 @@
 	ret
 SYM_FUNC_END(memset_erms)
 
-SYM_FUNC_START(memset_orig)
+SYM_FUNC_START_LOCAL(memset_orig)
 	movq %rdi,%r10
 
 	/* expand byte value  */
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index a43a6f1..359960a 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -843,9 +843,14 @@
 		else
 			p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'",
 			      capability_msg(bpf_caps, 0),
+#ifdef CAP_BPF
 			      capability_msg(bpf_caps, 1),
 			      capability_msg(bpf_caps, 2),
-			      capability_msg(bpf_caps, 3));
+			      capability_msg(bpf_caps, 3)
+#else
+				"", "", "", "", "", ""
+#endif /* CAP_BPF */
+				);
 		goto exit_free;
 	}
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index d942c1e..acdb2c24 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -940,7 +940,7 @@
 	}
 
 	if (*attach_type == BPF_FLOW_DISSECTOR) {
-		*mapfd = -1;
+		*mapfd = 0;
 		return 0;
 	}
 
diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c
index 4e3512f..ce5b65e 100644
--- a/tools/bpf/bpftool/skeleton/profiler.bpf.c
+++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c
@@ -70,7 +70,7 @@
 static inline void
 fexit_update_maps(u32 id, struct bpf_perf_event_value *after)
 {
-	struct bpf_perf_event_value *before, diff, *accum;
+	struct bpf_perf_event_value *before, diff;
 
 	before = bpf_map_lookup_elem(&fentry_readings, &id);
 	/* only account samples with a valid fentry_reading */
@@ -95,7 +95,7 @@
 {
 	struct bpf_perf_event_value readings[MAX_NUM_MATRICS];
 	u32 cpu = bpf_get_smp_processor_id();
-	u32 i, one = 1, zero = 0;
+	u32 i, zero = 0;
 	int err;
 	u64 *count;
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index a04e813..4648738 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -185,7 +185,6 @@
 	main_test_libperl();
 	main_test_hello();
 	main_test_libelf();
-	main_test_libelf_mmap();
 	main_test_get_current_dir_name();
 	main_test_gettid();
 	main_test_glibc();
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index b9d4322..95c072b 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -27,18 +27,6 @@
 #define  __pure		__attribute__((pure))
 #endif
 #define  noinline	__attribute__((noinline))
-#ifdef __has_attribute
-#if __has_attribute(disable_tail_calls)
-#define __no_tail_call	__attribute__((disable_tail_calls))
-#endif
-#endif
-#ifndef __no_tail_call
-#if GCC_VERSION > 40201
-#define __no_tail_call	__attribute__((optimize("no-optimize-sibling-calls")))
-#else
-#define __no_tail_call
-#endif
-#endif
 #ifndef __packed
 #define __packed	__attribute__((packed))
 #endif
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 2b3f735..d22a974 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -47,9 +47,6 @@
 #ifndef noinline
 #define noinline
 #endif
-#ifndef __no_tail_call
-#define __no_tail_call
-#endif
 
 /* Are two types/vars the same type (ignoring qualifiers)? */
 #ifndef __same_type
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index f2b5d72..2056318 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -857,9 +857,11 @@
 __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 #define __NR_faccessat2 439
 __SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
 
 #undef __NR_syscalls
-#define __NR_syscalls 440
+#define __NR_syscalls 441
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 0054606..fa1f3d6 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -619,6 +619,12 @@
  */
 #define I915_PARAM_PERF_REVISION	54
 
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
+ * I915_EXEC_USE_EXTENSIONS.
+ */
+#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
+
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -1046,6 +1052,38 @@
 	__u32 flags;
 };
 
+/**
+ * See drm_i915_gem_execbuffer_ext_timeline_fences.
+ */
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+
+/**
+ * This structure describes an array of drm_syncobj and associated points for
+ * timeline variants of drm_syncobj. It is invalid to append this structure to
+ * the execbuf if I915_EXEC_FENCE_ARRAY is set.
+ */
+struct drm_i915_gem_execbuffer_ext_timeline_fences {
+	struct i915_user_extension base;
+
+	/**
+	 * Number of element in the handles_ptr & value_ptr arrays.
+	 */
+	__u64 fence_count;
+
+	/**
+	 * Pointer to an array of struct drm_i915_gem_exec_fence of length
+	 * fence_count.
+	 */
+	__u64 handles_ptr;
+
+	/**
+	 * Pointer to an array of u64 values of length fence_count. Values
+	 * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
+	 * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
+	 */
+	__u64 values_ptr;
+};
+
 struct drm_i915_gem_execbuffer2 {
 	/**
 	 * List of gem_exec_object2 structs
@@ -1062,8 +1100,14 @@
 	__u32 num_cliprects;
 	/**
 	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
-	 * is not set.  If I915_EXEC_FENCE_ARRAY is set, then this is a
-	 * struct drm_i915_gem_exec_fence *fences.
+	 * & I915_EXEC_USE_EXTENSIONS are not set.
+	 *
+	 * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
+	 * of struct drm_i915_gem_exec_fence and num_cliprects is the length
+	 * of the array.
+	 *
+	 * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
+	 * single struct i915_user_extension and num_cliprects is 0.
 	 */
 	__u64 cliprects_ptr;
 #define I915_EXEC_RING_MASK              (0x3f)
@@ -1181,7 +1225,16 @@
  */
 #define I915_EXEC_FENCE_SUBMIT		(1 << 20)
 
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1))
+/*
+ * Setting I915_EXEC_USE_EXTENSIONS implies that
+ * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
+ * list of i915_user_extension. Each i915_user_extension node is the base of a
+ * larger structure. The list of supported structures are listed in the
+ * drm_i915_gem_execbuffer_ext enum.
+ */
+#define I915_EXEC_USE_EXTENSIONS	(1 << 21)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 7875709..e5de603 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -45,7 +45,6 @@
 	__u8 flags;
 	__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
 };
-#define fscrypt_policy	fscrypt_policy_v1
 
 /*
  * Process-subscribed "logon" key description prefix and payload format.
@@ -156,9 +155,9 @@
 	__u32 __out_reserved[13];
 };
 
-#define FS_IOC_SET_ENCRYPTION_POLICY		_IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_SET_ENCRYPTION_POLICY		_IOR('f', 19, struct fscrypt_policy_v1)
 #define FS_IOC_GET_ENCRYPTION_PWSALT		_IOW('f', 20, __u8[16])
-#define FS_IOC_GET_ENCRYPTION_POLICY		_IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY		_IOW('f', 21, struct fscrypt_policy_v1)
 #define FS_IOC_GET_ENCRYPTION_POLICY_EX		_IOWR('f', 22, __u8[9]) /* size + version */
 #define FS_IOC_ADD_ENCRYPTION_KEY		_IOWR('f', 23, struct fscrypt_add_key_arg)
 #define FS_IOC_REMOVE_ENCRYPTION_KEY		_IOWR('f', 24, struct fscrypt_remove_key_arg)
@@ -170,6 +169,7 @@
 
 /* old names; don't add anything new here! */
 #ifndef __KERNEL__
+#define fscrypt_policy			fscrypt_policy_v1
 #define FS_KEY_DESCRIPTOR_SIZE		FSCRYPT_KEY_DESCRIPTOR_SIZE
 #define FS_POLICY_FLAGS_PAD_4		FSCRYPT_POLICY_FLAGS_PAD_4
 #define FS_POLICY_FLAGS_PAD_8		FSCRYPT_POLICY_FLAGS_PAD_8
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 7d8eced..ca41220 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -248,6 +248,8 @@
 #define KVM_EXIT_IOAPIC_EOI       26
 #define KVM_EXIT_HYPERV           27
 #define KVM_EXIT_ARM_NISV         28
+#define KVM_EXIT_X86_RDMSR        29
+#define KVM_EXIT_X86_WRMSR        30
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -413,6 +415,17 @@
 			__u64 esr_iss;
 			__u64 fault_ipa;
 		} arm_nisv;
+		/* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+		struct {
+			__u8 error; /* user -> kernel */
+			__u8 pad[7];
+#define KVM_MSR_EXIT_REASON_INVAL	(1 << 0)
+#define KVM_MSR_EXIT_REASON_UNKNOWN	(1 << 1)
+#define KVM_MSR_EXIT_REASON_FILTER	(1 << 2)
+			__u32 reason; /* kernel -> user */
+			__u32 index; /* kernel -> user */
+			__u64 data; /* kernel <-> user */
+		} msr;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1037,6 +1050,9 @@
 #define KVM_CAP_SMALLER_MAXPHYADDR 185
 #define KVM_CAP_S390_DIAG318 186
 #define KVM_CAP_STEAL_TIME 187
+#define KVM_CAP_X86_USER_SPACE_MSR 188
+#define KVM_CAP_X86_MSR_FILTER 189
+#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1538,6 +1554,9 @@
 /* Available with KVM_CAP_S390_PROTECTED */
 #define KVM_S390_PV_COMMAND		_IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
 
+/* Available with KVM_CAP_X86_MSR_FILTER */
+#define KVM_X86_SET_MSR_FILTER	_IOW(KVMIO,  0xc6, struct kvm_msr_filter)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index 923cc16..f55bc68 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -27,6 +27,7 @@
 #define MAP_HUGE_SHIFT	HUGETLB_FLAG_ENCODE_SHIFT
 #define MAP_HUGE_MASK	HUGETLB_FLAG_ENCODE_MASK
 
+#define MAP_HUGE_16KB	HUGETLB_FLAG_ENCODE_16KB
 #define MAP_HUGE_64KB	HUGETLB_FLAG_ENCODE_64KB
 #define MAP_HUGE_512KB	HUGETLB_FLAG_ENCODE_512KB
 #define MAP_HUGE_1MB	HUGETLB_FLAG_ENCODE_1MB
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
index 96a0240..dd8306e 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/include/uapi/linux/mount.h
@@ -16,6 +16,7 @@
 #define MS_REMOUNT	32	/* Alter flags of a mounted FS */
 #define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
 #define MS_DIRSYNC	128	/* Directory modifications are synchronous */
+#define MS_NOSYMFOLLOW	256	/* Do not follow symlinks */
 #define MS_NOATIME	1024	/* Do not update access times. */
 #define MS_NODIRATIME	2048	/* Do not update directory access times */
 #define MS_BIND		4096
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 3e5dcdd..b95d3c4 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1196,7 +1196,7 @@
 
 #define PERF_MEM_SNOOPX_FWD	0x01 /* forward */
 /* 1 free */
-#define PERF_MEM_SNOOPX_SHIFT	38
+#define PERF_MEM_SNOOPX_SHIFT  38
 
 /* locked instruction */
 #define PERF_MEM_LOCK_NA	0x01 /* not available */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index 07b4f81..7f08277 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -233,6 +233,15 @@
 #define PR_SET_TAGGED_ADDR_CTRL		55
 #define PR_GET_TAGGED_ADDR_CTRL		56
 # define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
+/* MTE tag check fault modes */
+# define PR_MTE_TCF_SHIFT		1
+# define PR_MTE_TCF_NONE		(0UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_SYNC		(1UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_ASYNC		(2UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_MASK		(3UL << PR_MTE_TCF_SHIFT)
+/* MTE tag inclusion mask */
+# define PR_MTE_TAG_SHIFT		3
+# define PR_MTE_TAG_MASK		(0xffffUL << PR_MTE_TAG_SHIFT)
 
 /* Control reclaim behavior when allocating memory */
 #define PR_SET_IO_FLUSHER		57
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index 7523218..c998860 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -146,4 +146,8 @@
 
 /* Set event fd for config interrupt*/
 #define VHOST_VDPA_SET_CONFIG_CALL	_IOW(VHOST_VIRTIO, 0x77, int)
+
+/* Get the valid iova range */
+#define VHOST_VDPA_GET_IOVA_RANGE	_IOR(VHOST_VIRTIO, 0x78, \
+					     struct vhost_vdpa_iova_range)
 #endif
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index d9b385f..10a4c4c 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -15,6 +15,9 @@
 static inline size_t hash_bits(size_t h, int bits)
 {
 	/* shuffle bits and return requested number of upper bits */
+	if (bits == 0)
+		return 0;
+
 #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__)
 	/* LP64 case */
 	return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits);
@@ -174,17 +177,17 @@
  * @key: key to iterate entries for
  */
 #define hashmap__for_each_key_entry(map, cur, _key)			    \
-	for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
-					     map->cap_bits);		    \
-		     map->buckets ? map->buckets[bkt] : NULL; });	    \
+	for (cur = map->buckets						    \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+		     : NULL;						    \
 	     cur;							    \
 	     cur = cur->next)						    \
 		if (map->equal_fn(cur->key, (_key), map->ctx))
 
 #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key)		    \
-	for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
-					     map->cap_bits);		    \
-		     cur = map->buckets ? map->buckets[bkt] : NULL; });	    \
+	for (cur = map->buckets						    \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+		     : NULL;						    \
 	     cur && ({ tmp = cur->next; true; });			    \
 	     cur = tmp)							    \
 		if (map->equal_fn(cur->key, (_key), map->ctx))
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index e3c98c0..9bc537d 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -891,13 +891,16 @@
 void xsk_socket__delete(struct xsk_socket *xsk)
 {
 	size_t desc_sz = sizeof(struct xdp_desc);
-	struct xsk_ctx *ctx = xsk->ctx;
 	struct xdp_mmap_offsets off;
+	struct xsk_umem *umem;
+	struct xsk_ctx *ctx;
 	int err;
 
 	if (!xsk)
 		return;
 
+	ctx = xsk->ctx;
+	umem = ctx->umem;
 	if (ctx->prog_fd != -1) {
 		xsk_delete_bpf_maps(xsk);
 		close(ctx->prog_fd);
@@ -917,11 +920,11 @@
 
 	xsk_put_ctx(ctx);
 
-	ctx->umem->refcount--;
+	umem->refcount--;
 	/* Do not close an fd that also has an associated umem connected
 	 * to it.
 	 */
-	if (xsk->fd != ctx->umem->fd)
+	if (xsk->fd != umem->fd)
 		close(xsk->fd);
 	free(xsk);
 }
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 6890fc4b..ce8516e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -749,6 +749,7 @@
   PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
   PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
   PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+  PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS))
   PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
   FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 3478096..3798192 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -361,12 +361,13 @@
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd		sys_pidfd_getfd
 439	common	faccessat2		sys_faccessat2
+440	common	process_madvise		sys_process_madvise
 
 #
-# x32-specific system call numbers start at 512 to avoid cache impact
-# for native 64-bit operation. The __x32_compat_sys stubs are created
-# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
-# is defined.
+# Due to a historical design error, certain syscalls are numbered differently
+# in x32 as compared to native x86_64.  These syscalls have numbers 512-547.
+# Do not add new syscalls to this range.  Numbers 548 and above are available
+# for non-x32 use.
 #
 512	x32	rt_sigaction		compat_sys_rt_sigaction
 513	x32	rt_sigreturn		compat_sys_x32_rt_sigreturn
@@ -404,3 +405,5 @@
 545	x32	execveat		compat_sys_execveat
 546	x32	preadv2			compat_sys_preadv64v2
 547	x32	pwritev2		compat_sys_pwritev64v2
+# This is the end of the legacy x32 range.  Numbers 548 and above are
+# not special and are not to be used for x32-specific syscalls.
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 4e40402..478078f 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -38,6 +38,13 @@
 	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
 
 	memcpy(buf, (void *) sp, stack_size);
+#ifdef MEMORY_SANITIZER
+	/*
+	 * Copying the stack may copy msan poison, avoid false positives in the
+	 * unwinder by removing the poison here.
+	 */
+	__msan_unpoison(buf, stack_size);
+#endif
 	stack->data = (char *) buf;
 	stack->size = stack_size;
 	return 0;
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index 9ad015a..6eb45a2 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -2,6 +2,9 @@
 
 /* Various wrappers to make the kernel .S file build in user-space: */
 
+// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it
+#define SYM_FUNC_START_LOCAL(name)                      \
+        SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
 #define memcpy MEMCPY /* don't hide glibc's memcpy() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
index d550bd5..6f093c4 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm.S
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -1,4 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it
+#define SYM_FUNC_START_LOCAL(name)                      \
+        SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
 #define memset MEMSET /* don't hide glibc's memset() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 452a75f..0462dc8 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -779,25 +779,15 @@
 			dsos__hit_all(session);
 		/*
 		 * The AUX areas have been removed and replaced with
-		 * synthesized hardware events, so clear the feature flag and
-		 * remove the evsel.
+		 * synthesized hardware events, so clear the feature flag.
 		 */
 		if (inject->itrace_synth_opts.set) {
-			struct evsel *evsel;
-
 			perf_header__clear_feat(&session->header,
 						HEADER_AUXTRACE);
 			if (inject->itrace_synth_opts.last_branch ||
 			    inject->itrace_synth_opts.add_last_branch)
 				perf_header__set_feat(&session->header,
 						      HEADER_BRANCH_STACK);
-			evsel = perf_evlist__id2evsel_strict(session->evlist,
-							     inject->aux_id);
-			if (evsel) {
-				pr_debug("Deleting %s\n", evsel__name(evsel));
-				evlist__remove(session->evlist, evsel);
-				evsel__delete(evsel);
-			}
 		}
 		session->header.data_offset = output_data_offset;
 		session->header.data_size = inject->bytes_written;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index f0a1dba..a2f1e53 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -406,7 +406,7 @@
 	struct lock_seq_stat *seq;
 	const char *name = evsel__strval(evsel, sample, "name");
 	u64 tmp	 = evsel__intval(evsel, sample, "lockdep_addr");
-	int flag = evsel__intval(evsel, sample, "flag");
+	int flag = evsel__intval(evsel, sample, "flags");
 
 	memcpy(&addr, &tmp, sizeof(void *));
 
@@ -621,7 +621,7 @@
 	case SEQ_STATE_READ_ACQUIRED:
 		seq->read_count--;
 		BUG_ON(seq->read_count < 0);
-		if (!seq->read_count) {
+		if (seq->read_count) {
 			ls->nr_release++;
 			goto end;
 		}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 44a75f2..de80534 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -4639,9 +4639,9 @@
 	err = 0;
 
 	if (lists[0]) {
-		struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
-					       "event selector. use 'perf list' to list available events",
-					       parse_events_option);
+		struct option o = {
+			.value = &trace->evlist,
+		};
 		err = parse_events_option(&o, lists[0], 0);
 	}
 out:
@@ -4655,9 +4655,12 @@
 {
 	struct trace *trace = opt->value;
 
-	if (!list_empty(&trace->evlist->core.entries))
-		return parse_cgroups(opt, str, unset);
-
+	if (!list_empty(&trace->evlist->core.entries)) {
+		struct option o = {
+			.value = &trace->evlist,
+		};
+		return parse_cgroups(&o, str, unset);
+	}
 	trace->cgroup = evlist__findnew_cgroup(trace->evlist, str);
 
 	return 0;
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index de31935..00f4fcf 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -329,7 +329,7 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
         "MetricGroup": "Memory_BW;SoC",
         "MetricName": "DRAM_BW_Use"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index f31794d..0dd8b13 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -323,7 +323,7 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
         "MetricGroup": "Memory_BW;SoC",
         "MetricName": "DRAM_BW_Use"
     },
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 2491d16..8363809 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -95,7 +95,7 @@
 	return strcmp((const char *) symbol, funcs[idx]);
 }
 
-__no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread)
+noinline int test_dwarf_unwind__thread(struct thread *thread)
 {
 	struct perf_sample sample;
 	unsigned long cnt = 0;
@@ -126,7 +126,7 @@
 
 static int global_unwind_retval = -INT_MAX;
 
-__no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2)
+noinline int test_dwarf_unwind__compare(void *p1, void *p2)
 {
 	/* Any possible value should be 'thread' */
 	struct thread *thread = *(struct thread **)p1;
@@ -145,7 +145,7 @@
 	return p1 - p2;
 }
 
-__no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread)
+noinline int test_dwarf_unwind__krava_3(struct thread *thread)
 {
 	struct thread *array[2] = {thread, thread};
 	void *fp = &bsearch;
@@ -164,12 +164,12 @@
 	return global_unwind_retval;
 }
 
-__no_tail_call noinline int test_dwarf_unwind__krava_2(struct thread *thread)
+noinline int test_dwarf_unwind__krava_2(struct thread *thread)
 {
 	return test_dwarf_unwind__krava_3(thread);
 }
 
-__no_tail_call noinline int test_dwarf_unwind__krava_1(struct thread *thread)
+noinline int test_dwarf_unwind__krava_1(struct thread *thread)
 {
 	return test_dwarf_unwind__krava_2(thread);
 }
diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
index 8d84fdb..18fde2f 100755
--- a/tools/perf/tests/shell/test_arm_coresight.sh
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -44,7 +44,7 @@
 	#   touch  6512          1         branches:u:      ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so)
 	#   touch  6512          1         branches:u:      ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so)
 	perf script -F,-time -i ${perfdata} | \
-		egrep " +$1 +[0-9]+ .* +branches:([u|k]:)? +"
+		egrep " +$1 +[0-9]+ .* +branches:(.*:)? +"
 }
 
 perf_report_branch_samples() {
@@ -105,7 +105,7 @@
 		#     `> device_name = 'tmc_etf0'
 		device_name=$(basename $path)
 
-		if is_device_sink $path $devce_name; then
+		if is_device_sink $path $device_name; then
 
 			record_touch_file $device_name $2 &&
 			perf_script_branch_samples touch &&
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a07626f..b0e1880 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2963,7 +2963,7 @@
 	struct popup_action actions[MAX_OPTIONS];
 	int nr_options = 0;
 	int key = -1;
-	char buf[64];
+	char buf[128];
 	int delay_secs = hbt ? hbt->refresh : 0;
 
 #define HIST_BROWSER_HELP_COMMON					\
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 8763772..6b410c3 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -102,6 +102,8 @@
 	const u8 *raw = build_id->data;
 	size_t i;
 
+	bf[0] = 0x0;
+
 	for (i = 0; i < build_id->size; ++i) {
 		sprintf(bid, "%02x", *raw);
 		++raw;
diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c
index a405dad..3c20b12 100644
--- a/tools/perf/util/hashmap.c
+++ b/tools/perf/util/hashmap.c
@@ -15,6 +15,9 @@
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
+/* prevent accidental re-addition of reallocarray() */
+#pragma GCC poison reallocarray
+
 /* start with 4 buckets */
 #define HASHMAP_MIN_CAP_BITS 2
 
diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h
index e0af36b..d9b385f 100644
--- a/tools/perf/util/hashmap.h
+++ b/tools/perf/util/hashmap.h
@@ -25,6 +25,18 @@
 #endif
 }
 
+/* generic C-string hashing function */
+static inline size_t str_hash(const char *s)
+{
+	size_t h = 0;
+
+	while (*s) {
+		h = h * 31 + *s;
+		s++;
+	}
+	return h;
+}
+
 typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
 typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
 
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index b8a5159..5acf053 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -25,6 +25,7 @@
 
 /* SYM_L_* -- linkage of symbols */
 #define SYM_L_GLOBAL(name)			.globl name
+#define SYM_L_WEAK(name)			.weak name
 #define SYM_L_LOCAL(name)			/* nothing */
 
 #define ALIGN __ALIGN
@@ -84,6 +85,12 @@
 	SYM_END(name, SYM_T_FUNC)
 #endif
 
+/* SYM_FUNC_START_WEAK -- use for weak functions */
+#ifndef SYM_FUNC_START_WEAK
+#define SYM_FUNC_START_WEAK(name)			\
+	SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)
+#endif
+
 /*
  * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START,
  * SYM_FUNC_START_WEAK, ...
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7d4194f..15385ea 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -786,11 +786,20 @@
 					       union perf_event *event,
 					       struct perf_sample *sample __maybe_unused)
 {
+	struct symbol *sym;
 	struct map *map;
 
 	map = maps__find(&machine->kmaps, event->ksymbol.addr);
-	if (map)
+	if (!map)
+		return 0;
+
+	if (map != machine->vmlinux_map)
 		maps__remove(&machine->kmaps, map);
+	else {
+		sym = dso__find_symbol(map->dso, map->map_ip(map, map->start));
+		if (sym)
+			dso__delete_symbol(map->dso, sym);
+	}
 
 	return 0;
 }
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 7cbd024..c83c2c6 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1592,7 +1592,6 @@
 static int python_start_script(const char *script, int argc, const char **argv)
 {
 	struct tables *tables = &tables_global;
-	PyMODINIT_FUNC (*initfunc)(void);
 #if PY_MAJOR_VERSION < 3
 	const char **command_line;
 #else
@@ -1607,20 +1606,18 @@
 	FILE *fp;
 
 #if PY_MAJOR_VERSION < 3
-	initfunc = initperf_trace_context;
 	command_line = malloc((argc + 1) * sizeof(const char *));
 	command_line[0] = script;
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = argv[i - 1];
+	PyImport_AppendInittab(name, initperf_trace_context);
 #else
-	initfunc = PyInit_perf_trace_context;
 	command_line = malloc((argc + 1) * sizeof(wchar_t *));
 	command_line[0] = Py_DecodeLocale(script, NULL);
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
+	PyImport_AppendInittab(name, PyInit_perf_trace_context);
 #endif
-
-	PyImport_AppendInittab(name, initfunc);
 	Py_Initialize();
 
 #if PY_MAJOR_VERSION < 3
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7a5f037..0980802 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -595,6 +595,7 @@
 	event->mmap2.maj   = bswap_32(event->mmap2.maj);
 	event->mmap2.min   = bswap_32(event->mmap2.min);
 	event->mmap2.ino   = bswap_64(event->mmap2.ino);
+	event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation);
 
 	if (sample_id_all) {
 		void *data = &event->mmap2.filename;
@@ -710,6 +711,18 @@
 		swap_sample_id_all(event, &event->namespaces.link_info[i]);
 }
 
+static void perf_event__cgroup_swap(union perf_event *event, bool sample_id_all)
+{
+	event->cgroup.id = bswap_64(event->cgroup.id);
+
+	if (sample_id_all) {
+		void *data = &event->cgroup.path;
+
+		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+		swap_sample_id_all(event, data);
+	}
+}
+
 static u8 revbyte(u8 b)
 {
 	int rev = (b >> 4) | ((b & 0xf) << 4);
@@ -952,6 +965,7 @@
 	[PERF_RECORD_SWITCH]		  = perf_event__switch_swap,
 	[PERF_RECORD_SWITCH_CPU_WIDE]	  = perf_event__switch_swap,
 	[PERF_RECORD_NAMESPACES]	  = perf_event__namespaces_swap,
+	[PERF_RECORD_CGROUP]		  = perf_event__cgroup_swap,
 	[PERF_RECORD_TEXT_POKE]		  = perf_event__text_poke_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 6138866..0d14abd 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -515,6 +515,13 @@
 	}
 }
 
+void dso__delete_symbol(struct dso *dso, struct symbol *sym)
+{
+	rb_erase_cached(&sym->rb_node, &dso->symbols);
+	symbol__delete(sym);
+	dso__reset_find_symbol_cache(dso);
+}
+
 struct symbol *dso__find_symbol(struct dso *dso, u64 addr)
 {
 	if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f4801c4..954d6a0 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -131,6 +131,8 @@
 
 void dso__insert_symbol(struct dso *dso,
 			struct symbol *sym);
+void dso__delete_symbol(struct dso *dso,
+			struct symbol *sym);
 
 struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index 2b65512..f3e3c94 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -12,11 +12,12 @@
 override CFLAGS +=	-O2 -Wall -I../../../include
 override CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
 override CFLAGS +=	-DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"'
+override CFLAGS +=	-D_FILE_OFFSET_BITS=64
 override CFLAGS +=	-D_FORTIFY_SOURCE=2
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
-	$(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap
+	$(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap -lrt
 
 .PHONY : clean
 clean :
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index a6db83a..f6b7e85 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -335,7 +335,7 @@
 
 .SH REFERENCES
 Volume 3B: System Programming Guide"
-http://www.intel.com/products/processor/manuals/
+https://www.intel.com/products/processor/manuals/
 
 .SH FILES
 .ta
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 33b3708..f3a1746 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -79,6 +79,7 @@
 unsigned long long cpuidle_cur_cpu_lpi_us;
 unsigned long long cpuidle_cur_sys_lpi_us;
 unsigned int gfx_cur_mhz;
+unsigned int gfx_act_mhz;
 unsigned int tcc_activation_temp;
 unsigned int tcc_activation_temp_override;
 double rapl_power_units, rapl_time_units;
@@ -210,13 +211,14 @@
 	unsigned long long pkg_both_core_gfxe_c0;
 	long long gfx_rc6_ms;
 	unsigned int gfx_mhz;
+	unsigned int gfx_act_mhz;
 	unsigned int package_id;
-	unsigned int energy_pkg;	/* MSR_PKG_ENERGY_STATUS */
-	unsigned int energy_dram;	/* MSR_DRAM_ENERGY_STATUS */
-	unsigned int energy_cores;	/* MSR_PP0_ENERGY_STATUS */
-	unsigned int energy_gfx;	/* MSR_PP1_ENERGY_STATUS */
-	unsigned int rapl_pkg_perf_status;	/* MSR_PKG_PERF_STATUS */
-	unsigned int rapl_dram_perf_status;	/* MSR_DRAM_PERF_STATUS */
+	unsigned long long energy_pkg;	/* MSR_PKG_ENERGY_STATUS */
+	unsigned long long energy_dram;	/* MSR_DRAM_ENERGY_STATUS */
+	unsigned long long energy_cores;	/* MSR_PP0_ENERGY_STATUS */
+	unsigned long long energy_gfx;	/* MSR_PP1_ENERGY_STATUS */
+	unsigned long long rapl_pkg_perf_status;	/* MSR_PKG_PERF_STATUS */
+	unsigned long long rapl_dram_perf_status;	/* MSR_DRAM_PERF_STATUS */
 	unsigned int pkg_temp_c;
 	unsigned long long counter[MAX_ADDED_COUNTERS];
 } *package_even, *package_odd;
@@ -259,6 +261,113 @@
 #define	SYSFS_PERCPU	(1 << 1)
 };
 
+/*
+ * The accumulated sum of MSR is defined as a monotonic
+ * increasing MSR, it will be accumulated periodically,
+ * despite its register's bit width.
+ */
+enum {
+	IDX_PKG_ENERGY,
+	IDX_DRAM_ENERGY,
+	IDX_PP0_ENERGY,
+	IDX_PP1_ENERGY,
+	IDX_PKG_PERF,
+	IDX_DRAM_PERF,
+	IDX_COUNT,
+};
+
+int get_msr_sum(int cpu, off_t offset, unsigned long long *msr);
+
+struct msr_sum_array {
+	/* get_msr_sum() = sum + (get_msr() - last) */
+	struct {
+		/*The accumulated MSR value is updated by the timer*/
+		unsigned long long sum;
+		/*The MSR footprint recorded in last timer*/
+		unsigned long long last;
+	} entries[IDX_COUNT];
+};
+
+/* The percpu MSR sum array.*/
+struct msr_sum_array *per_cpu_msr_sum;
+
+int idx_to_offset(int idx)
+{
+	int offset;
+
+	switch (idx) {
+	case IDX_PKG_ENERGY:
+		offset = MSR_PKG_ENERGY_STATUS;
+		break;
+	case IDX_DRAM_ENERGY:
+		offset = MSR_DRAM_ENERGY_STATUS;
+		break;
+	case IDX_PP0_ENERGY:
+		offset = MSR_PP0_ENERGY_STATUS;
+		break;
+	case IDX_PP1_ENERGY:
+		offset = MSR_PP1_ENERGY_STATUS;
+		break;
+	case IDX_PKG_PERF:
+		offset = MSR_PKG_PERF_STATUS;
+		break;
+	case IDX_DRAM_PERF:
+		offset = MSR_DRAM_PERF_STATUS;
+		break;
+	default:
+		offset = -1;
+	}
+	return offset;
+}
+
+int offset_to_idx(int offset)
+{
+	int idx;
+
+	switch (offset) {
+	case MSR_PKG_ENERGY_STATUS:
+		idx = IDX_PKG_ENERGY;
+		break;
+	case MSR_DRAM_ENERGY_STATUS:
+		idx = IDX_DRAM_ENERGY;
+		break;
+	case MSR_PP0_ENERGY_STATUS:
+		idx = IDX_PP0_ENERGY;
+		break;
+	case MSR_PP1_ENERGY_STATUS:
+		idx = IDX_PP1_ENERGY;
+		break;
+	case MSR_PKG_PERF_STATUS:
+		idx = IDX_PKG_PERF;
+		break;
+	case MSR_DRAM_PERF_STATUS:
+		idx = IDX_DRAM_PERF;
+		break;
+	default:
+		idx = -1;
+	}
+	return idx;
+}
+
+int idx_valid(int idx)
+{
+	switch (idx) {
+	case IDX_PKG_ENERGY:
+		return do_rapl & RAPL_PKG;
+	case IDX_DRAM_ENERGY:
+		return do_rapl & RAPL_DRAM;
+	case IDX_PP0_ENERGY:
+		return do_rapl & RAPL_CORES_ENERGY_STATUS;
+	case IDX_PP1_ENERGY:
+		return do_rapl & RAPL_GFX;
+	case IDX_PKG_PERF:
+		return do_rapl & RAPL_PKG_PERF_STATUS;
+	case IDX_DRAM_PERF:
+		return do_rapl & RAPL_DRAM_PERF_STATUS;
+	default:
+		return 0;
+	}
+}
 struct sys_counters {
 	unsigned int added_thread_counters;
 	unsigned int added_core_counters;
@@ -451,6 +560,7 @@
 	{ 0x0, "APIC" },
 	{ 0x0, "X2APIC" },
 	{ 0x0, "Die" },
+	{ 0x0, "GFXAMHz" },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -505,6 +615,7 @@
 #define	BIC_APIC	(1ULL << 48)
 #define	BIC_X2APIC	(1ULL << 49)
 #define	BIC_Die		(1ULL << 50)
+#define	BIC_GFXACTMHz	(1ULL << 51)
 
 #define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
 
@@ -724,6 +835,9 @@
 	if (DO_BIC(BIC_GFXMHz))
 		outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : ""));
 
+	if (DO_BIC(BIC_GFXACTMHz))
+		outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : ""));
+
 	if (DO_BIC(BIC_Totl_c0))
 		outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Any_c0))
@@ -858,13 +972,13 @@
 		outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
 		outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
 		outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
-		outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg);
-		outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores);
-		outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx);
-		outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram);
-		outp += sprintf(outp, "Throttle PKG: %0X\n",
+		outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg);
+		outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores);
+		outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx);
+		outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram);
+		outp += sprintf(outp, "Throttle PKG: %0llX\n",
 			p->rapl_pkg_perf_status);
-		outp += sprintf(outp, "Throttle RAM: %0X\n",
+		outp += sprintf(outp, "Throttle RAM: %0llX\n",
 			p->rapl_dram_perf_status);
 		outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c);
 
@@ -1062,14 +1176,7 @@
 		}
 	}
 
-	/*
-	 * If measurement interval exceeds minimum RAPL Joule Counter range,
-	 * indicate that results are suspect by printing "**" in fraction place.
-	 */
-	if (interval_float < rapl_joule_counter_range)
-		fmt8 = "%s%.2f";
-	else
-		fmt8 = "%6.0f**";
+	fmt8 = "%s%.2f";
 
 	if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
@@ -1098,6 +1205,10 @@
 	if (DO_BIC(BIC_GFXMHz))
 		outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz);
 
+	/* GFXACTMHz */
+	if (DO_BIC(BIC_GFXACTMHz))
+		outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz);
+
 	/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
 	if (DO_BIC(BIC_Totl_c0))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc);
@@ -1210,11 +1321,7 @@
 }
 
 #define DELTA_WRAP32(new, old)			\
-	if (new > old) {			\
-		old = new - old;		\
-	} else {				\
-		old = 0x100000000 + new - old;	\
-	}
+	old = ((((unsigned long long)new << 32) - ((unsigned long long)old << 32)) >> 32);
 
 int
 delta_package(struct pkg_data *new, struct pkg_data *old)
@@ -1253,13 +1360,14 @@
 		old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms;
 
 	old->gfx_mhz = new->gfx_mhz;
+	old->gfx_act_mhz = new->gfx_act_mhz;
 
-	DELTA_WRAP32(new->energy_pkg, old->energy_pkg);
-	DELTA_WRAP32(new->energy_cores, old->energy_cores);
-	DELTA_WRAP32(new->energy_gfx, old->energy_gfx);
-	DELTA_WRAP32(new->energy_dram, old->energy_dram);
-	DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status);
-	DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status);
+	old->energy_pkg = new->energy_pkg - old->energy_pkg;
+	old->energy_cores = new->energy_cores - old->energy_cores;
+	old->energy_gfx = new->energy_gfx - old->energy_gfx;
+	old->energy_dram = new->energy_dram - old->energy_dram;
+	old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status;
+	old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status;
 
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
@@ -1469,6 +1577,7 @@
 
 	p->gfx_rc6_ms = 0;
 	p->gfx_mhz = 0;
+	p->gfx_act_mhz = 0;
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next)
 		t->counter[i] = 0;
 
@@ -1564,6 +1673,7 @@
 
 	average.packages.gfx_rc6_ms = p->gfx_rc6_ms;
 	average.packages.gfx_mhz = p->gfx_mhz;
+	average.packages.gfx_act_mhz = p->gfx_act_mhz;
 
 	average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c);
 
@@ -1784,7 +1894,7 @@
 	int i;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -1966,39 +2076,39 @@
 		p->sys_lpi = cpuidle_cur_sys_lpi_us;
 
 	if (do_rapl & RAPL_PKG) {
-		if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr))
+		if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr))
 			return -13;
-		p->energy_pkg = msr & 0xFFFFFFFF;
+		p->energy_pkg = msr;
 	}
 	if (do_rapl & RAPL_CORES_ENERGY_STATUS) {
-		if (get_msr(cpu, MSR_PP0_ENERGY_STATUS, &msr))
+		if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr))
 			return -14;
-		p->energy_cores = msr & 0xFFFFFFFF;
+		p->energy_cores = msr;
 	}
 	if (do_rapl & RAPL_DRAM) {
-		if (get_msr(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
+		if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
 			return -15;
-		p->energy_dram = msr & 0xFFFFFFFF;
+		p->energy_dram = msr;
 	}
 	if (do_rapl & RAPL_GFX) {
-		if (get_msr(cpu, MSR_PP1_ENERGY_STATUS, &msr))
+		if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr))
 			return -16;
-		p->energy_gfx = msr & 0xFFFFFFFF;
+		p->energy_gfx = msr;
 	}
 	if (do_rapl & RAPL_PKG_PERF_STATUS) {
-		if (get_msr(cpu, MSR_PKG_PERF_STATUS, &msr))
+		if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr))
 			return -16;
-		p->rapl_pkg_perf_status = msr & 0xFFFFFFFF;
+		p->rapl_pkg_perf_status = msr;
 	}
 	if (do_rapl & RAPL_DRAM_PERF_STATUS) {
-		if (get_msr(cpu, MSR_DRAM_PERF_STATUS, &msr))
+		if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr))
 			return -16;
-		p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
+		p->rapl_dram_perf_status = msr;
 	}
 	if (do_rapl & RAPL_AMD_F17H) {
-		if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr))
+		if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr))
 			return -13;
-		p->energy_pkg = msr & 0xFFFFFFFF;
+		p->energy_pkg = msr;
 	}
 	if (DO_BIC(BIC_PkgTmp)) {
 		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
@@ -2012,6 +2122,9 @@
 	if (DO_BIC(BIC_GFXMHz))
 		p->gfx_mhz = gfx_cur_mhz;
 
+	if (DO_BIC(BIC_GFXACTMHz))
+		p->gfx_act_mhz = gfx_act_mhz;
+
 	for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
 		if (get_mp(cpu, mp, &p->counter[i]))
 			return -10;
@@ -2173,6 +2286,7 @@
 	case INTEL_FAM6_ATOM_GOLDMONT:
 	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_ATOM_GOLDMONT_D:
+	case INTEL_FAM6_ATOM_TREMONT_D:
 		return 1;
 	}
 	return 0;
@@ -2650,7 +2764,12 @@
 
 	sprintf(path,
 		"/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu);
-	filep = fopen_or_die(path, "r");
+	filep = fopen(path, "r");
+
+	if (!filep) {
+		warnx("%s: open failed", path);
+		return -1;
+	}
 	do {
 		offset -= BITMASK_SIZE;
 		if (fscanf(filep, "%lx%c", &map, &character) != 2)
@@ -2763,18 +2882,25 @@
 {
 	free_all_buffers();
 	setup_all_buffers();
-	printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
+	fprintf(outf, "turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
 }
 
 void set_max_cpu_num(void)
 {
 	FILE *filep;
+	int base_cpu;
 	unsigned long dummy;
+	char pathname[64];
 
+	base_cpu = sched_getcpu();
+	if (base_cpu < 0)
+		err(1, "cannot find calling cpu ID");
+	sprintf(pathname,
+		"/sys/devices/system/cpu/cpu%d/topology/thread_siblings",
+		base_cpu);
+
+	filep = fopen_or_die(pathname, "r");
 	topo.max_cpu_num = 0;
-	filep = fopen_or_die(
-			"/sys/devices/system/cpu/cpu0/topology/thread_siblings",
-			"r");
 	while (fscanf(filep, "%lx,", &dummy) == 1)
 		topo.max_cpu_num += BITMASK_SIZE;
 	fclose(filep);
@@ -2916,6 +3042,33 @@
 }
 
 /*
+ * snapshot_gfx_cur_mhz()
+ *
+ * record snapshot of
+ * /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_gfx_act_mhz(void)
+{
+	static FILE *fp;
+	int retval;
+
+	if (fp == NULL)
+		fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r");
+	else {
+		rewind(fp);
+		fflush(fp);
+	}
+
+	retval = fscanf(fp, "%d", &gfx_act_mhz);
+	if (retval != 1)
+		err(1, "GFX ACT MHz");
+
+	return 0;
+}
+
+/*
  * snapshot_cpu_lpi()
  *
  * record snapshot of
@@ -2980,6 +3133,9 @@
 	if (DO_BIC(BIC_GFXMHz))
 		snapshot_gfx_mhz();
 
+	if (DO_BIC(BIC_GFXACTMHz))
+		snapshot_gfx_act_mhz();
+
 	if (DO_BIC(BIC_CPU_LPI))
 		snapshot_cpu_lpi_us();
 
@@ -3057,6 +3213,111 @@
 	}
 }
 
+int get_msr_sum(int cpu, off_t offset, unsigned long long *msr)
+{
+	int ret, idx;
+	unsigned long long msr_cur, msr_last;
+
+	if (!per_cpu_msr_sum)
+		return 1;
+
+	idx = offset_to_idx(offset);
+	if (idx < 0)
+		return idx;
+	/* get_msr_sum() = sum + (get_msr() - last) */
+	ret = get_msr(cpu, offset, &msr_cur);
+	if (ret)
+		return ret;
+	msr_last = per_cpu_msr_sum[cpu].entries[idx].last;
+	DELTA_WRAP32(msr_cur, msr_last);
+	*msr = msr_last + per_cpu_msr_sum[cpu].entries[idx].sum;
+
+	return 0;
+}
+
+timer_t timerid;
+
+/* Timer callback, update the sum of MSRs periodically. */
+static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+	int i, ret;
+	int cpu = t->cpu_id;
+
+	for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) {
+		unsigned long long msr_cur, msr_last;
+		int offset;
+
+		if (!idx_valid(i))
+			continue;
+		offset = idx_to_offset(i);
+		if (offset < 0)
+			continue;
+		ret = get_msr(cpu, offset, &msr_cur);
+		if (ret) {
+			fprintf(outf, "Can not update msr(0x%x)\n", offset);
+			continue;
+		}
+
+		msr_last = per_cpu_msr_sum[cpu].entries[i].last;
+		per_cpu_msr_sum[cpu].entries[i].last = msr_cur & 0xffffffff;
+
+		DELTA_WRAP32(msr_cur, msr_last);
+		per_cpu_msr_sum[cpu].entries[i].sum += msr_last;
+	}
+	return 0;
+}
+
+static void
+msr_record_handler(union sigval v)
+{
+	for_all_cpus(update_msr_sum, EVEN_COUNTERS);
+}
+
+void msr_sum_record(void)
+{
+	struct itimerspec its;
+	struct sigevent sev;
+
+	per_cpu_msr_sum = calloc(topo.max_cpu_num + 1, sizeof(struct msr_sum_array));
+	if (!per_cpu_msr_sum) {
+		fprintf(outf, "Can not allocate memory for long time MSR.\n");
+		return;
+	}
+	/*
+	 * Signal handler might be restricted, so use thread notifier instead.
+	 */
+	memset(&sev, 0, sizeof(struct sigevent));
+	sev.sigev_notify = SIGEV_THREAD;
+	sev.sigev_notify_function = msr_record_handler;
+
+	sev.sigev_value.sival_ptr = &timerid;
+	if (timer_create(CLOCK_REALTIME, &sev, &timerid) == -1) {
+		fprintf(outf, "Can not create timer.\n");
+		goto release_msr;
+	}
+
+	its.it_value.tv_sec = 0;
+	its.it_value.tv_nsec = 1;
+	/*
+	 * A wraparound time has been calculated early.
+	 * Some sources state that the peak power for a
+	 * microprocessor is usually 1.5 times the TDP rating,
+	 * use 2 * TDP for safety.
+	 */
+	its.it_interval.tv_sec = rapl_joule_counter_range / 2;
+	its.it_interval.tv_nsec = 0;
+
+	if (timer_settime(timerid, 0, &its, NULL) == -1) {
+		fprintf(outf, "Can not set timer.\n");
+		goto release_timer;
+	}
+	return;
+
+ release_timer:
+	timer_delete(timerid);
+ release_msr:
+	free(per_cpu_msr_sum);
+}
 
 void turbostat_loop()
 {
@@ -3075,7 +3336,7 @@
 	if (retval < -1) {
 		exit(retval);
 	} else if (retval == -1) {
-		if (restarted > 1) {
+		if (restarted > 10) {
 			exit(retval);
 		}
 		re_initialize();
@@ -3279,6 +3540,7 @@
 	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 	case INTEL_FAM6_ATOM_GOLDMONT_D:	/* DNV */
 	case INTEL_FAM6_ATOM_TREMONT:	/* EHL */
+	case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */
 		pkg_cstate_limits = glm_pkg_cstate_limits;
 		break;
 	default:
@@ -3361,6 +3623,17 @@
 	}
 	return 0;
 }
+int is_jvl(unsigned int family, unsigned int model)
+{
+	if (!genuine_intel)
+		return 0;
+
+	switch (model) {
+	case INTEL_FAM6_ATOM_TREMONT_D:
+		return 1;
+	}
+	return 0;
+}
 
 int has_turbo_ratio_limit(unsigned int family, unsigned int model)
 {
@@ -3475,6 +3748,20 @@
 }
 
 static void
+remove_underbar(char *s)
+{
+	char *to = s;
+
+	while (*s) {
+		if (*s != '_')
+			*to++ = *s;
+		s++;
+	}
+
+	*to = 0;
+}
+
+static void
 dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
 {
 	if (!do_nhm_platform_info)
@@ -3530,9 +3817,6 @@
 	int state;
 	char *sp;
 
-	if (!DO_BIC(BIC_sysfs))
-		return;
-
 	if (access("/sys/devices/system/cpu/cpuidle", R_OK)) {
 		fprintf(outf, "cpuidle not loaded\n");
 		return;
@@ -3559,6 +3843,8 @@
 		*sp = '\0';
 		fclose(input);
 
+		remove_underbar(name_buf);
+
 		sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc",
 			base_cpu, state);
 		input = fopen(path, "r");
@@ -3645,7 +3931,7 @@
 		return 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "print_epb: Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -3689,7 +3975,7 @@
 		return 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "print_hwp: Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -3777,7 +4063,7 @@
 		return 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "print_perf_limit: Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -3881,13 +4167,8 @@
 
 double get_tdp_amd(unsigned int family)
 {
-	switch (family) {
-	case 0x17:
-	case 0x18:
-	default:
-		/* This is the max stock TDP of HEDT/Server Fam17h chips */
-		return 250.0;
-	}
+	/* This is the max stock TDP of HEDT/Server Fam17h+ chips */
+	return 280.0;
 }
 
 /*
@@ -3959,6 +4240,14 @@
 			BIC_PRESENT(BIC_GFXWatt);
 		}
 		break;
+	case INTEL_FAM6_ATOM_TREMONT_D:	/* JVL */
+		do_rapl = RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+		BIC_PRESENT(BIC_PKG__);
+		if (rapl_joules)
+			BIC_PRESENT(BIC_Pkg_J);
+		else
+			BIC_PRESENT(BIC_PkgWatt);
+		break;
 	case INTEL_FAM6_SKYLAKE_L:	/* SKL */
 	case INTEL_FAM6_CANNONLAKE_L:	/* CNL */
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
@@ -4069,27 +4358,20 @@
 
 	if (max_extended_level >= 0x80000007) {
 		__cpuid(0x80000007, eax, ebx, ecx, edx);
-		/* RAPL (Fam 17h) */
+		/* RAPL (Fam 17h+) */
 		has_rapl = edx & (1 << 14);
 	}
 
-	if (!has_rapl)
+	if (!has_rapl || family < 0x17)
 		return;
 
-	switch (family) {
-	case 0x17: /* Zen, Zen+ */
-	case 0x18: /* Hygon Dhyana */
-		do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
-		if (rapl_joules) {
-			BIC_PRESENT(BIC_Pkg_J);
-			BIC_PRESENT(BIC_Cor_J);
-		} else {
-			BIC_PRESENT(BIC_PkgWatt);
-			BIC_PRESENT(BIC_CorWatt);
-		}
-		break;
-	default:
-		return;
+	do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
+	if (rapl_joules) {
+		BIC_PRESENT(BIC_Pkg_J);
+		BIC_PRESENT(BIC_Cor_J);
+	} else {
+		BIC_PRESENT(BIC_PkgWatt);
+		BIC_PRESENT(BIC_CorWatt);
 	}
 
 	if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr))
@@ -4162,7 +4444,7 @@
 		return 0;
 
 	if (cpu_migrate(cpu)) {
-		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -4234,7 +4516,7 @@
 
 	cpu = t->cpu_id;
 	if (cpu_migrate(cpu)) {
-		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+		fprintf(outf, "print_rapl: Could not migrate to CPU %d\n", cpu);
 		return -1;
 	}
 
@@ -4361,6 +4643,7 @@
 	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
 	case INTEL_FAM6_ATOM_GOLDMONT_D:	/* DNV */
 	case INTEL_FAM6_ATOM_TREMONT:		/* EHL */
+	case INTEL_FAM6_ATOM_TREMONT_D:		/* JVL */
 		return 1;
 	}
 	return 0;
@@ -4507,12 +4790,33 @@
  * below this value, including the Digital Thermal Sensor (DTS),
  * Package Thermal Management Sensor (PTM), and thermal event thresholds.
  */
-int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+int read_tcc_activation_temp()
 {
 	unsigned long long msr;
-	unsigned int target_c_local;
-	int cpu;
+	unsigned int tcc, target_c, offset_c;
 
+	/* Temperature Target MSR is Nehalem and newer only */
+	if (!do_nhm_platform_info)
+		return 0;
+
+	if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
+		return 0;
+
+	target_c = (msr >> 16) & 0xFF;
+
+	offset_c = (msr >> 24) & 0xF;
+
+	tcc = target_c - offset_c;
+
+	if (!quiet)
+		fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n",
+			base_cpu, msr, tcc, target_c, offset_c);
+
+	return tcc;
+}
+
+int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
 	/* tcc_activation_temp is used only for dts or ptm */
 	if (!(do_dts || do_ptm))
 		return 0;
@@ -4521,43 +4825,18 @@
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		return 0;
 
-	cpu = t->cpu_id;
-	if (cpu_migrate(cpu)) {
-		fprintf(outf, "Could not migrate to CPU %d\n", cpu);
-		return -1;
-	}
-
 	if (tcc_activation_temp_override != 0) {
 		tcc_activation_temp = tcc_activation_temp_override;
-		fprintf(outf, "cpu%d: Using cmdline TCC Target (%d C)\n",
-			cpu, tcc_activation_temp);
+		fprintf(outf, "Using cmdline TCC Target (%d C)\n", tcc_activation_temp);
 		return 0;
 	}
 
-	/* Temperature Target MSR is Nehalem and newer only */
-	if (!do_nhm_platform_info)
-		goto guess;
+	tcc_activation_temp = read_tcc_activation_temp();
+	if (tcc_activation_temp)
+		return 0;
 
-	if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
-		goto guess;
-
-	target_c_local = (msr >> 16) & 0xFF;
-
-	if (!quiet)
-		fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n",
-			cpu, msr, target_c_local);
-
-	if (!target_c_local)
-		goto guess;
-
-	tcc_activation_temp = target_c_local;
-
-	return 0;
-
-guess:
 	tcc_activation_temp = TJMAX_DEFAULT;
-	fprintf(outf, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n",
-		cpu, tcc_activation_temp);
+	fprintf(outf, "Guessing tjMax %d C, Please use -T to specify\n", tcc_activation_temp);
 
 	return 0;
 }
@@ -4685,19 +4964,46 @@
 	case INTEL_FAM6_ICELAKE_NNPI:
 	case INTEL_FAM6_TIGERLAKE_L:
 	case INTEL_FAM6_TIGERLAKE:
+	case INTEL_FAM6_ROCKETLAKE:
+	case INTEL_FAM6_LAKEFIELD:
+	case INTEL_FAM6_ALDERLAKE:
 		return INTEL_FAM6_CANNONLAKE_L;
 
-	case INTEL_FAM6_ATOM_TREMONT_D:
-		return INTEL_FAM6_ATOM_GOLDMONT_D;
-
 	case INTEL_FAM6_ATOM_TREMONT_L:
 		return INTEL_FAM6_ATOM_TREMONT;
 
 	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_SAPPHIRERAPIDS_X:
 		return INTEL_FAM6_SKYLAKE_X;
 	}
 	return model;
 }
+
+void print_dev_latency(void)
+{
+	char *path = "/dev/cpu_dma_latency";
+	int fd;
+	int value;
+	int retval;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		warn("fopen %s\n", path);
+		return;
+	}
+
+	retval = read(fd, (void *)&value, sizeof(int));
+	if (retval != sizeof(int)) {
+		warn("read %s\n", path);
+		close(fd);
+		return;
+	}
+	fprintf(outf, "/dev/cpu_dma_latency: %d usec (%s)\n",
+		value, value == 2000000000 ? "default" : "constrained");
+
+	close(fd);
+}
+
 void process_cpuid()
 {
 	unsigned int eax, ebx, ecx, edx;
@@ -4916,6 +5222,14 @@
 		BIC_PRESENT(BIC_Mod_c6);
 		use_c1_residency_msr = 1;
 	}
+	if (is_jvl(family, model)) {
+		BIC_NOT_PRESENT(BIC_CPU_c3);
+		BIC_NOT_PRESENT(BIC_CPU_c7);
+		BIC_NOT_PRESENT(BIC_Pkgpc2);
+		BIC_NOT_PRESENT(BIC_Pkgpc3);
+		BIC_NOT_PRESENT(BIC_Pkgpc6);
+		BIC_NOT_PRESENT(BIC_Pkgpc7);
+	}
 	if (is_dnv(family, model)) {
 		BIC_PRESENT(BIC_CPU_c1);
 		BIC_NOT_PRESENT(BIC_CPU_c3);
@@ -4935,9 +5249,12 @@
 		BIC_NOT_PRESENT(BIC_Pkgpc7);
 	}
 	if (has_c8910_msrs(family, model)) {
-		BIC_PRESENT(BIC_Pkgpc8);
-		BIC_PRESENT(BIC_Pkgpc9);
-		BIC_PRESENT(BIC_Pkgpc10);
+		if (pkg_cstate_limit >= PCL__8)
+			BIC_PRESENT(BIC_Pkgpc8);
+		if (pkg_cstate_limit >= PCL__9)
+			BIC_PRESENT(BIC_Pkgpc9);
+		if (pkg_cstate_limit >= PCL_10)
+			BIC_PRESENT(BIC_Pkgpc10);
 	}
 	do_irtl_hsw = has_c8910_msrs(family, model);
 	if (has_skl_msrs(family, model)) {
@@ -4967,6 +5284,8 @@
 		dump_cstate_pstate_config_info(family, model);
 
 	if (!quiet)
+		print_dev_latency();
+	if (!quiet)
 		dump_sysfs_cstate_config();
 	if (!quiet)
 		dump_sysfs_pstate_config();
@@ -4980,6 +5299,9 @@
 	if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
 		BIC_PRESENT(BIC_GFXMHz);
 
+	if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
+		BIC_PRESENT(BIC_GFXACTMHz);
+
 	if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK))
 		BIC_PRESENT(BIC_CPU_LPI);
 	else
@@ -5390,7 +5712,7 @@
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 20.03.20"
+	fprintf(outf, "turbostat version 20.09.30"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
@@ -5597,6 +5919,8 @@
 		*sp = '%';
 		*(sp + 1) = '\0';
 
+		remove_underbar(name_buf);
+
 		fclose(input);
 
 		sprintf(path, "cpuidle/state%d/time", state);
@@ -5624,6 +5948,8 @@
 		*sp = '\0';
 		fclose(input);
 
+		remove_underbar(name_buf);
+
 		sprintf(path, "cpuidle/state%d/usage", state);
 
 		if (is_deferred_skip(name_buf))
@@ -5868,6 +6194,7 @@
 		return 0;
 	}
 
+	msr_sum_record();
 	/*
 	 * if any params left, it must be a command to fork
 	 */
diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
index 3fe1eed..ff6c666 100644
--- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
+++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c
@@ -622,6 +622,57 @@
 	}
 }
 
+/*
+ * Open a file, and exit on failure
+ */
+FILE *fopen_or_die(const char *path, const char *mode)
+{
+	FILE *filep = fopen(path, "r");
+
+	if (!filep)
+		err(1, "%s: open failed", path);
+	return filep;
+}
+
+void err_on_hypervisor(void)
+{
+	FILE *cpuinfo;
+	char *flags, *hypervisor;
+	char *buffer;
+
+	/* On VMs /proc/cpuinfo contains a "flags" entry for hypervisor */
+	cpuinfo = fopen_or_die("/proc/cpuinfo", "ro");
+
+	buffer = malloc(4096);
+	if (!buffer) {
+		fclose(cpuinfo);
+		err(-ENOMEM, "buffer malloc fail");
+	}
+
+	if (!fread(buffer, 1024, 1, cpuinfo)) {
+		fclose(cpuinfo);
+		free(buffer);
+		err(1, "Reading /proc/cpuinfo failed");
+	}
+
+	flags = strstr(buffer, "flags");
+	rewind(cpuinfo);
+	fseek(cpuinfo, flags - buffer, SEEK_SET);
+	if (!fgets(buffer, 4096, cpuinfo)) {
+		fclose(cpuinfo);
+		free(buffer);
+		err(1, "Reading /proc/cpuinfo failed");
+	}
+	fclose(cpuinfo);
+
+	hypervisor = strstr(buffer, "hypervisor");
+
+	free(buffer);
+
+	if (hypervisor)
+		err(-1,
+		    "not supported on this virtual machine");
+}
 
 int get_msr(int cpu, int offset, unsigned long long *msr)
 {
@@ -635,8 +686,10 @@
 		err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname);
 
 	retval = pread(fd, msr, sizeof(*msr), offset);
-	if (retval != sizeof(*msr))
+	if (retval != sizeof(*msr)) {
+		err_on_hypervisor();
 		err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset);
+	}
 
 	if (debug > 1)
 		fprintf(stderr, "get_msr(cpu%d, 0x%X, 0x%llX)\n", cpu, offset, *msr);
@@ -1086,18 +1139,6 @@
 	return 0;
 }
 
-/*
- * Open a file, and exit on failure
- */
-FILE *fopen_or_die(const char *path, const char *mode)
-{
-	FILE *filep = fopen(path, "r");
-
-	if (!filep)
-		err(1, "%s: open failed", path);
-	return filep;
-}
-
 unsigned int get_pkg_num(int cpu)
 {
 	FILE *fp;
diff --git a/tools/testing/kunit/.gitattributes b/tools/testing/kunit/.gitattributes
deleted file mode 100644
index 5b7da1f..0000000
--- a/tools/testing/kunit/.gitattributes
+++ /dev/null
@@ -1 +0,0 @@
-test_data/* binary
diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py
index ebf5f57..d4f7846 100755
--- a/tools/testing/kunit/kunit.py
+++ b/tools/testing/kunit/kunit.py
@@ -11,7 +11,6 @@
 import sys
 import os
 import time
-import shutil
 
 from collections import namedtuple
 from enum import Enum, auto
@@ -44,11 +43,6 @@
 	BUILD_FAILURE = auto()
 	TEST_FAILURE = auto()
 
-def create_default_kunitconfig():
-	if not os.path.exists(kunit_kernel.kunitconfig_path):
-		shutil.copyfile('arch/um/configs/kunit_defconfig',
-				kunit_kernel.kunitconfig_path)
-
 def get_kernel_root_path():
 	parts = sys.argv[0] if not __file__ else __file__
 	parts = os.path.realpath(parts).split('tools/testing/kunit')
@@ -61,7 +55,6 @@
 	kunit_parser.print_with_timestamp('Configuring KUnit Kernel ...')
 
 	config_start = time.time()
-	create_default_kunitconfig()
 	success = linux.build_reconfig(request.build_dir, request.make_options)
 	config_end = time.time()
 	if not success:
@@ -262,12 +255,12 @@
 		if not os.path.exists(cli_args.build_dir):
 			os.mkdir(cli_args.build_dir)
 
-		if not os.path.exists(kunit_kernel.kunitconfig_path):
-			create_default_kunitconfig()
-
 		if not linux:
 			linux = kunit_kernel.LinuxSourceTree()
 
+		linux.create_kunitconfig(cli_args.build_dir)
+		linux.read_kunitconfig(cli_args.build_dir)
+
 		request = KunitRequest(cli_args.raw_output,
 				       cli_args.timeout,
 				       cli_args.jobs,
@@ -283,12 +276,12 @@
 				not os.path.exists(cli_args.build_dir)):
 			os.mkdir(cli_args.build_dir)
 
-		if not os.path.exists(kunit_kernel.kunitconfig_path):
-			create_default_kunitconfig()
-
 		if not linux:
 			linux = kunit_kernel.LinuxSourceTree()
 
+		linux.create_kunitconfig(cli_args.build_dir)
+		linux.read_kunitconfig(cli_args.build_dir)
+
 		request = KunitConfigRequest(cli_args.build_dir,
 					     cli_args.make_options)
 		result = config_tests(linux, request)
@@ -301,6 +294,9 @@
 		if not linux:
 			linux = kunit_kernel.LinuxSourceTree()
 
+		linux.create_kunitconfig(cli_args.build_dir)
+		linux.read_kunitconfig(cli_args.build_dir)
+
 		request = KunitBuildRequest(cli_args.jobs,
 					    cli_args.build_dir,
 					    cli_args.alltests,
@@ -315,6 +311,9 @@
 		if not linux:
 			linux = kunit_kernel.LinuxSourceTree()
 
+		linux.create_kunitconfig(cli_args.build_dir)
+		linux.read_kunitconfig(cli_args.build_dir)
+
 		exec_request = KunitExecRequest(cli_args.timeout,
 						cli_args.build_dir,
 						cli_args.alltests)
@@ -337,7 +336,7 @@
 				kunit_output = f.read().splitlines()
 		request = KunitParseRequest(cli_args.raw_output,
 					    kunit_output,
-					    cli_args.build_dir,
+					    None,
 					    cli_args.json)
 		result = parse_tests(request)
 		if result.status != KunitStatus.SUCCESS:
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index b557b1e..2e3cc0f 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -6,10 +6,10 @@
 # Author: Felix Guo <felixguoxiuping@gmail.com>
 # Author: Brendan Higgins <brendanhiggins@google.com>
 
-
 import logging
 import subprocess
 import os
+import shutil
 import signal
 
 from contextlib import ExitStack
@@ -18,8 +18,10 @@
 import kunit_parser
 
 KCONFIG_PATH = '.config'
-kunitconfig_path = '.kunitconfig'
+KUNITCONFIG_PATH = '.kunitconfig'
+DEFAULT_KUNITCONFIG_PATH = 'arch/um/configs/kunit_defconfig'
 BROKEN_ALLCONFIG_PATH = 'tools/testing/kunit/configs/broken_on_uml.config'
+OUTFILE_PATH = 'test.log'
 
 class ConfigError(Exception):
 	"""Represents an error trying to configure the Linux kernel."""
@@ -82,36 +84,51 @@
 		if build_dir:
 			command += ['O=' + build_dir]
 		try:
-			subprocess.check_output(command, stderr=subprocess.STDOUT)
+			proc = subprocess.Popen(command,
+						stderr=subprocess.PIPE,
+						stdout=subprocess.DEVNULL)
 		except OSError as e:
-			raise BuildError('Could not call execute make: ' + str(e))
-		except subprocess.CalledProcessError as e:
-			raise BuildError(e.output.decode())
+			raise BuildError('Could not call make command: ' + str(e))
+		_, stderr = proc.communicate()
+		if proc.returncode != 0:
+			raise BuildError(stderr.decode())
+		if stderr:  # likely only due to build warnings
+			print(stderr.decode())
 
-	def linux_bin(self, params, timeout, build_dir, outfile):
+	def linux_bin(self, params, timeout, build_dir):
 		"""Runs the Linux UML binary. Must be named 'linux'."""
 		linux_bin = './linux'
 		if build_dir:
 			linux_bin = os.path.join(build_dir, 'linux')
+		outfile = get_outfile_path(build_dir)
 		with open(outfile, 'w') as output:
 			process = subprocess.Popen([linux_bin] + params,
 						   stdout=output,
 						   stderr=subprocess.STDOUT)
 			process.wait(timeout)
 
-
 def get_kconfig_path(build_dir):
 	kconfig_path = KCONFIG_PATH
 	if build_dir:
 		kconfig_path = os.path.join(build_dir, KCONFIG_PATH)
 	return kconfig_path
 
+def get_kunitconfig_path(build_dir):
+	kunitconfig_path = KUNITCONFIG_PATH
+	if build_dir:
+		kunitconfig_path = os.path.join(build_dir, KUNITCONFIG_PATH)
+	return kunitconfig_path
+
+def get_outfile_path(build_dir):
+	outfile_path = OUTFILE_PATH
+	if build_dir:
+		outfile_path = os.path.join(build_dir, OUTFILE_PATH)
+	return outfile_path
+
 class LinuxSourceTree(object):
 	"""Represents a Linux kernel source tree with KUnit tests."""
 
 	def __init__(self):
-		self._kconfig = kunit_config.Kconfig()
-		self._kconfig.read_from_file(kunitconfig_path)
 		self._ops = LinuxSourceTreeOperations()
 		signal.signal(signal.SIGINT, self.signal_handler)
 
@@ -123,6 +140,16 @@
 			return False
 		return True
 
+	def create_kunitconfig(self, build_dir, defconfig=DEFAULT_KUNITCONFIG_PATH):
+		kunitconfig_path = get_kunitconfig_path(build_dir)
+		if not os.path.exists(kunitconfig_path):
+			shutil.copyfile(defconfig, kunitconfig_path)
+
+	def read_kunitconfig(self, build_dir):
+		kunitconfig_path = get_kunitconfig_path(build_dir)
+		self._kconfig = kunit_config.Kconfig()
+		self._kconfig.read_from_file(kunitconfig_path)
+
 	def validate_config(self, build_dir):
 		kconfig_path = get_kconfig_path(build_dir)
 		validated_kconfig = kunit_config.Kconfig()
@@ -178,8 +205,8 @@
 
 	def run_kernel(self, args=[], build_dir='', timeout=None):
 		args.extend(['mem=1G'])
-		outfile = 'test.log'
-		self._ops.linux_bin(args, timeout, build_dir, outfile)
+		self._ops.linux_bin(args, timeout, build_dir)
+		outfile = get_outfile_path(build_dir)
 		subprocess.call(['stty', 'sane'])
 		with open(outfile, 'r') as file:
 			for line in file:
diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
index 8019e3d..bbfe1b4 100644
--- a/tools/testing/kunit/kunit_parser.py
+++ b/tools/testing/kunit/kunit_parser.py
@@ -12,7 +12,7 @@
 from datetime import datetime
 from enum import Enum, auto
 from functools import reduce
-from typing import List
+from typing import List, Optional, Tuple
 
 TestResult = namedtuple('TestResult', ['status','suites','log'])
 
@@ -54,6 +54,7 @@
 def isolate_kunit_output(kernel_output):
 	started = False
 	for line in kernel_output:
+		line = line.rstrip()  # line always has a trailing \n
 		if kunit_start_re.search(line):
 			prefix_len = len(line.split('TAP version')[0])
 			started = True
@@ -65,8 +66,7 @@
 
 def raw_output(kernel_output):
 	for line in kernel_output:
-		print(line)
-		yield line
+		print(line.rstrip())
 
 DIVIDER = '=' * 60
 
@@ -152,7 +152,7 @@
 	else:
 		return False
 
-def parse_test_case(lines: List[str]) -> TestCase:
+def parse_test_case(lines: List[str]) -> Optional[TestCase]:
 	test_case = TestCase()
 	save_non_diagnositic(lines, test_case)
 	while parse_diagnostic(lines, test_case):
@@ -164,7 +164,7 @@
 
 SUBTEST_HEADER = re.compile(r'^[\s]+# Subtest: (.*)$')
 
-def parse_subtest_header(lines: List[str]) -> str:
+def parse_subtest_header(lines: List[str]) -> Optional[str]:
 	consume_non_diagnositic(lines)
 	if not lines:
 		return None
@@ -177,7 +177,7 @@
 
 SUBTEST_PLAN = re.compile(r'[\s]+[0-9]+\.\.([0-9]+)')
 
-def parse_subtest_plan(lines: List[str]) -> int:
+def parse_subtest_plan(lines: List[str]) -> Optional[int]:
 	consume_non_diagnositic(lines)
 	match = SUBTEST_PLAN.match(lines[0])
 	if match:
@@ -231,7 +231,7 @@
 	max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases)
 	return max_status(max_test_case_status, test_suite.status)
 
-def parse_test_suite(lines: List[str], expected_suite_index: int) -> TestSuite:
+def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[TestSuite]:
 	if not lines:
 		return None
 	consume_non_diagnositic(lines)
@@ -242,7 +242,7 @@
 		return None
 	test_suite.name = name
 	expected_test_case_num = parse_subtest_plan(lines)
-	if not expected_test_case_num:
+	if expected_test_case_num is None:
 		return None
 	while expected_test_case_num > 0:
 		test_case = parse_test_case(lines)
@@ -272,7 +272,7 @@
 
 TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)')
 
-def parse_test_plan(lines: List[str]) -> int:
+def parse_test_plan(lines: List[str]) -> Optional[int]:
 	consume_non_diagnositic(lines)
 	match = TEST_PLAN.match(lines[0])
 	if match:
@@ -311,7 +311,7 @@
 	else:
 		return TestResult(TestStatus.NO_TESTS, [], lines)
 
-def print_and_count_results(test_result: TestResult) -> None:
+def print_and_count_results(test_result: TestResult) -> Tuple[int, int, int]:
 	total_tests = 0
 	failed_tests = 0
 	crashed_tests = 0
diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py
index 99c3c56..497ab51 100755
--- a/tools/testing/kunit/kunit_tool_test.py
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -102,7 +102,7 @@
 			'test_data/test_output_isolated_correctly.log')
 		file = open(log_path)
 		result = kunit_parser.isolate_kunit_output(file.readlines())
-		self.assertContains('TAP version 14\n', result)
+		self.assertContains('TAP version 14', result)
 		self.assertContains('	# Subtest: example', result)
 		self.assertContains('	1..2', result)
 		self.assertContains('	ok 1 - example_simple_test', result)
@@ -115,7 +115,7 @@
 			'test_data/test_pound_sign.log')
 		with open(log_path) as file:
 			result = kunit_parser.isolate_kunit_output(file.readlines())
-		self.assertContains('TAP version 14\n', result)
+		self.assertContains('TAP version 14', result)
 		self.assertContains('	# Subtest: kunit-resource-test', result)
 		self.assertContains('	1..5', result)
 		self.assertContains('	ok 1 - kunit_resource_test_init_resources', result)
@@ -179,7 +179,7 @@
 		print_mock = mock.patch('builtins.print').start()
 		result = kunit_parser.parse_run_tests(
 			kunit_parser.isolate_kunit_output(file.readlines()))
-		print_mock.assert_any_call(StrContains("no kunit output detected"))
+		print_mock.assert_any_call(StrContains('no tests run!'))
 		print_mock.stop()
 		file.close()
 
@@ -198,39 +198,57 @@
 			'test_data/test_config_printk_time.log')
 		with open(prefix_log) as file:
 			result = kunit_parser.parse_run_tests(file.readlines())
-		self.assertEqual('kunit-resource-test', result.suites[0].name)
+			self.assertEqual(
+				kunit_parser.TestStatus.SUCCESS,
+				result.status)
+			self.assertEqual('kunit-resource-test', result.suites[0].name)
 
 	def test_ignores_multiple_prefixes(self):
 		prefix_log = get_absolute_path(
 			'test_data/test_multiple_prefixes.log')
 		with open(prefix_log) as file:
 			result = kunit_parser.parse_run_tests(file.readlines())
-		self.assertEqual('kunit-resource-test', result.suites[0].name)
+			self.assertEqual(
+				kunit_parser.TestStatus.SUCCESS,
+				result.status)
+			self.assertEqual('kunit-resource-test', result.suites[0].name)
 
 	def test_prefix_mixed_kernel_output(self):
 		mixed_prefix_log = get_absolute_path(
 			'test_data/test_interrupted_tap_output.log')
 		with open(mixed_prefix_log) as file:
 			result = kunit_parser.parse_run_tests(file.readlines())
-		self.assertEqual('kunit-resource-test', result.suites[0].name)
+			self.assertEqual(
+				kunit_parser.TestStatus.SUCCESS,
+				result.status)
+			self.assertEqual('kunit-resource-test', result.suites[0].name)
 
 	def test_prefix_poundsign(self):
 		pound_log = get_absolute_path('test_data/test_pound_sign.log')
 		with open(pound_log) as file:
 			result = kunit_parser.parse_run_tests(file.readlines())
-		self.assertEqual('kunit-resource-test', result.suites[0].name)
+			self.assertEqual(
+				kunit_parser.TestStatus.SUCCESS,
+				result.status)
+			self.assertEqual('kunit-resource-test', result.suites[0].name)
 
 	def test_kernel_panic_end(self):
 		panic_log = get_absolute_path('test_data/test_kernel_panic_interrupt.log')
 		with open(panic_log) as file:
 			result = kunit_parser.parse_run_tests(file.readlines())
-		self.assertEqual('kunit-resource-test', result.suites[0].name)
+			self.assertEqual(
+				kunit_parser.TestStatus.TEST_CRASHED,
+				result.status)
+			self.assertEqual('kunit-resource-test', result.suites[0].name)
 
 	def test_pound_no_prefix(self):
 		pound_log = get_absolute_path('test_data/test_pound_no_prefix.log')
 		with open(pound_log) as file:
 			result = kunit_parser.parse_run_tests(file.readlines())
-		self.assertEqual('kunit-resource-test', result.suites[0].name)
+			self.assertEqual(
+				kunit_parser.TestStatus.SUCCESS,
+				result.status)
+			self.assertEqual('kunit-resource-test', result.suites[0].name)
 
 class KUnitJsonTest(unittest.TestCase):
 
diff --git a/tools/testing/kunit/test_data/test_config_printk_time.log b/tools/testing/kunit/test_data/test_config_printk_time.log
index c02ca77..6bdb57f 100644
--- a/tools/testing/kunit/test_data/test_config_printk_time.log
+++ b/tools/testing/kunit/test_data/test_config_printk_time.log
@@ -1,6 +1,7 @@
 [    0.060000] printk: console [mc-1] enabled
 [    0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
 [    0.060000] TAP version 14
+[    0.060000] 1..3
 [    0.060000] 	# Subtest: kunit-resource-test
 [    0.060000] 	1..5
 [    0.060000] 	ok 1 - kunit_resource_test_init_resources
@@ -28,4 +29,4 @@
 [    0.060000] Stack:
 [    0.060000]  602086f8 601bc260 705c0000 705c0000
 [    0.060000]  602086f8 6005fcec 705c0000 6002c6ab
-[    0.060000]  6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[    0.060000]  6005fcec 601bc260 705c0000 3000000010
diff --git a/tools/testing/kunit/test_data/test_interrupted_tap_output.log b/tools/testing/kunit/test_data/test_interrupted_tap_output.log
index 5c73fb3..1fb6777 100644
--- a/tools/testing/kunit/test_data/test_interrupted_tap_output.log
+++ b/tools/testing/kunit/test_data/test_interrupted_tap_output.log
@@ -1,6 +1,7 @@
 [    0.060000] printk: console [mc-1] enabled
 [    0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
 [    0.060000] TAP version 14
+[    0.060000] 1..3
 [    0.060000] 	# Subtest: kunit-resource-test
 [    0.060000] 	1..5
 [    0.060000] 	ok 1 - kunit_resource_test_init_resources
@@ -34,4 +35,4 @@
 [    0.060000] Stack:
 [    0.060000]  602086f8 601bc260 705c0000 705c0000
 [    0.060000]  602086f8 6005fcec 705c0000 6002c6ab
-[    0.060000]  6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[    0.060000]  6005fcec 601bc260 705c0000 3000000010
diff --git a/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log b/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log
index c045eee..a014ffe 100644
--- a/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log
+++ b/tools/testing/kunit/test_data/test_kernel_panic_interrupt.log
@@ -1,6 +1,7 @@
 [    0.060000] printk: console [mc-1] enabled
 [    0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
 [    0.060000] TAP version 14
+[    0.060000] 1..3
 [    0.060000] 	# Subtest: kunit-resource-test
 [    0.060000] 	1..5
 [    0.060000] 	ok 1 - kunit_resource_test_init_resources
@@ -22,4 +23,4 @@
 [    0.060000] Stack:
 [    0.060000]  602086f8 601bc260 705c0000 705c0000
 [    0.060000]  602086f8 6005fcec 705c0000 6002c6ab
-[    0.060000]  6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[    0.060000]  6005fcec 601bc260 705c0000 3000000010
diff --git a/tools/testing/kunit/test_data/test_multiple_prefixes.log b/tools/testing/kunit/test_data/test_multiple_prefixes.log
index bc48407..0ad7848 100644
--- a/tools/testing/kunit/test_data/test_multiple_prefixes.log
+++ b/tools/testing/kunit/test_data/test_multiple_prefixes.log
@@ -1,6 +1,7 @@
 [    0.060000][    T1] printk: console [mc-1] enabled
 [    0.060000][    T1] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
 [    0.060000][    T1] TAP version 14
+[    0.060000][    T1] 1..3
 [    0.060000][    T1] 	# Subtest: kunit-resource-test
 [    0.060000][    T1] 	1..5
 [    0.060000][    T1] 	ok 1 - kunit_resource_test_init_resources
@@ -28,4 +29,4 @@
 [    0.060000][    T1] Stack:
 [    0.060000][    T1]  602086f8 601bc260 705c0000 705c0000
 [    0.060000][    T1]  602086f8 6005fcec 705c0000 6002c6ab
-[    0.060000][    T1]  6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[    0.060000][    T1]  6005fcec 601bc260 705c0000 3000000010
diff --git a/tools/testing/kunit/test_data/test_pound_no_prefix.log b/tools/testing/kunit/test_data/test_pound_no_prefix.log
index 2ceb360..dc4cf09 100644
--- a/tools/testing/kunit/test_data/test_pound_no_prefix.log
+++ b/tools/testing/kunit/test_data/test_pound_no_prefix.log
@@ -1,6 +1,7 @@
  printk: console [mc-1] enabled
  random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
  TAP version 14
+ 1..3
  	# Subtest: kunit-resource-test
  	1..5
  	ok 1 - kunit_resource_test_init_resources
@@ -30,4 +31,4 @@
  Stack:
   602086f8 601bc260 705c0000 705c0000
   602086f8 6005fcec 705c0000 6002c6ab
-  6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+  6005fcec 601bc260 705c0000 3000000010
diff --git a/tools/testing/kunit/test_data/test_pound_sign.log b/tools/testing/kunit/test_data/test_pound_sign.log
index 28ffa5b..3f358e3a7 100644
--- a/tools/testing/kunit/test_data/test_pound_sign.log
+++ b/tools/testing/kunit/test_data/test_pound_sign.log
@@ -1,6 +1,7 @@
 [    0.060000] printk: console [mc-1] enabled
 [    0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
 [    0.060000] TAP version 14
+[    0.060000] 1..3
 [    0.060000] 	# Subtest: kunit-resource-test
 [    0.060000] 	1..5
 [    0.060000] 	ok 1 - kunit_resource_test_init_resources
diff --git a/tools/testing/selftests/bpf/prog_tests/map_init.c b/tools/testing/selftests/bpf/prog_tests/map_init.c
new file mode 100644
index 0000000..14a3110
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_init.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */
+
+#include <test_progs.h>
+#include "test_map_init.skel.h"
+
+#define TEST_VALUE 0x1234
+#define FILL_VALUE 0xdeadbeef
+
+static int nr_cpus;
+static int duration;
+
+typedef unsigned long long map_key_t;
+typedef unsigned long long map_value_t;
+typedef struct {
+	map_value_t v; /* padding */
+} __bpf_percpu_val_align pcpu_map_value_t;
+
+
+static int map_populate(int map_fd, int num)
+{
+	pcpu_map_value_t value[nr_cpus];
+	int i, err;
+	map_key_t key;
+
+	for (i = 0; i < nr_cpus; i++)
+		bpf_percpu(value, i) = FILL_VALUE;
+
+	for (key = 1; key <= num; key++) {
+		err = bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			return -1;
+	}
+
+	return 0;
+}
+
+static struct test_map_init *setup(enum bpf_map_type map_type, int map_sz,
+			    int *map_fd, int populate)
+{
+	struct test_map_init *skel;
+	int err;
+
+	skel = test_map_init__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return NULL;
+
+	err = bpf_map__set_type(skel->maps.hashmap1, map_type);
+	if (!ASSERT_OK(err, "bpf_map__set_type"))
+		goto error;
+
+	err = bpf_map__set_max_entries(skel->maps.hashmap1, map_sz);
+	if (!ASSERT_OK(err, "bpf_map__set_max_entries"))
+		goto error;
+
+	err = test_map_init__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto error;
+
+	*map_fd = bpf_map__fd(skel->maps.hashmap1);
+	if (CHECK(*map_fd < 0, "bpf_map__fd", "failed\n"))
+		goto error;
+
+	err = map_populate(*map_fd, populate);
+	if (!ASSERT_OK(err, "map_populate"))
+		goto error_map;
+
+	return skel;
+
+error_map:
+	close(*map_fd);
+error:
+	test_map_init__destroy(skel);
+	return NULL;
+}
+
+/* executes bpf program that updates map with key, value */
+static int prog_run_insert_elem(struct test_map_init *skel, map_key_t key,
+				map_value_t value)
+{
+	struct test_map_init__bss *bss;
+
+	bss = skel->bss;
+
+	bss->inKey = key;
+	bss->inValue = value;
+	bss->inPid = getpid();
+
+	if (!ASSERT_OK(test_map_init__attach(skel), "skel_attach"))
+		return -1;
+
+	/* Let tracepoint trigger */
+	syscall(__NR_getpgid);
+
+	test_map_init__detach(skel);
+
+	return 0;
+}
+
+static int check_values_one_cpu(pcpu_map_value_t *value, map_value_t expected)
+{
+	int i, nzCnt = 0;
+	map_value_t val;
+
+	for (i = 0; i < nr_cpus; i++) {
+		val = bpf_percpu(value, i);
+		if (val) {
+			if (CHECK(val != expected, "map value",
+				  "unexpected for cpu %d: 0x%llx\n", i, val))
+				return -1;
+			nzCnt++;
+		}
+	}
+
+	if (CHECK(nzCnt != 1, "map value", "set for %d CPUs instead of 1!\n",
+		  nzCnt))
+		return -1;
+
+	return 0;
+}
+
+/* Add key=1 elem with values set for all CPUs
+ * Delete elem key=1
+ * Run bpf prog that inserts new key=1 elem with value=0x1234
+ *   (bpf prog can only set value for current CPU)
+ * Lookup Key=1 and check value is as expected for all CPUs:
+ *   value set by bpf prog for one CPU, 0 for all others
+ */
+static void test_pcpu_map_init(void)
+{
+	pcpu_map_value_t value[nr_cpus];
+	struct test_map_init *skel;
+	int map_fd, err;
+	map_key_t key;
+
+	/* max 1 elem in map so insertion is forced to reuse freed entry */
+	skel = setup(BPF_MAP_TYPE_PERCPU_HASH, 1, &map_fd, 1);
+	if (!ASSERT_OK_PTR(skel, "prog_setup"))
+		return;
+
+	/* delete element so the entry can be re-used*/
+	key = 1;
+	err = bpf_map_delete_elem(map_fd, &key);
+	if (!ASSERT_OK(err, "bpf_map_delete_elem"))
+		goto cleanup;
+
+	/* run bpf prog that inserts new elem, re-using the slot just freed */
+	err = prog_run_insert_elem(skel, key, TEST_VALUE);
+	if (!ASSERT_OK(err, "prog_run_insert_elem"))
+		goto cleanup;
+
+	/* check that key=1 was re-created by bpf prog */
+	err = bpf_map_lookup_elem(map_fd, &key, value);
+	if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+	/* and has expected values */
+	check_values_one_cpu(value, TEST_VALUE);
+
+cleanup:
+	test_map_init__destroy(skel);
+}
+
+/* Add key=1 and key=2 elems with values set for all CPUs
+ * Run bpf prog that inserts new key=3 elem
+ *   (only for current cpu; other cpus should have initial value = 0)
+ * Lookup Key=1 and check value is as expected for all CPUs
+ */
+static void test_pcpu_lru_map_init(void)
+{
+	pcpu_map_value_t value[nr_cpus];
+	struct test_map_init *skel;
+	int map_fd, err;
+	map_key_t key;
+
+	/* Set up LRU map with 2 elements, values filled for all CPUs.
+	 * With these 2 elements, the LRU map is full
+	 */
+	skel = setup(BPF_MAP_TYPE_LRU_PERCPU_HASH, 2, &map_fd, 2);
+	if (!ASSERT_OK_PTR(skel, "prog_setup"))
+		return;
+
+	/* run bpf prog that inserts new key=3 element, re-using LRU slot */
+	key = 3;
+	err = prog_run_insert_elem(skel, key, TEST_VALUE);
+	if (!ASSERT_OK(err, "prog_run_insert_elem"))
+		goto cleanup;
+
+	/* check that key=3 replaced one of earlier elements */
+	err = bpf_map_lookup_elem(map_fd, &key, value);
+	if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
+		goto cleanup;
+
+	/* and has expected values */
+	check_values_one_cpu(value, TEST_VALUE);
+
+cleanup:
+	test_map_init__destroy(skel);
+}
+
+void test_map_init(void)
+{
+	nr_cpus = bpf_num_possible_cpus();
+	if (nr_cpus <= 1) {
+		printf("%s:SKIP: >1 cpu needed for this test\n", __func__);
+		test__skip();
+		return;
+	}
+
+	if (test__start_subtest("pcpu_map_init"))
+		test_pcpu_map_init();
+	if (test__start_subtest("pcpu_lru_map_init"))
+		test_pcpu_lru_map_init();
+}
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 0057831..30982a7 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -243,7 +243,10 @@
 	}
 }
 
-int pids_cgrp_id = 1;
+extern bool CONFIG_CGROUP_PIDS __kconfig __weak;
+enum cgroup_subsys_id___local {
+	pids_cgrp_id___local = 123, /* value doesn't matter */
+};
 
 static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 					 struct task_struct* task,
@@ -253,7 +256,9 @@
 		BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn);
 	struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn);
 
-	if (ENABLE_CGROUP_V1_RESOLVER) {
+	if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) {
+		int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local,
+						  pids_cgrp_id___local);
 #ifdef UNROLL
 #pragma unroll
 #endif
@@ -262,7 +267,7 @@
 				BPF_CORE_READ(task, cgroups, subsys[i]);
 			if (subsys != NULL) {
 				int subsys_id = BPF_CORE_READ(subsys, ss, id);
-				if (subsys_id == pids_cgrp_id) {
+				if (subsys_id == cgrp_id) {
 					proc_kernfs = BPF_CORE_READ(subsys, cgroup, kn);
 					root_kernfs = BPF_CORE_READ(subsys, ss, root, kf_root, kn);
 					break;
diff --git a/tools/testing/selftests/bpf/progs/test_map_init.c b/tools/testing/selftests/bpf/progs/test_map_init.c
new file mode 100644
index 0000000..c89d28ea
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_map_init.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+__u64 inKey = 0;
+__u64 inValue = 0;
+__u32 inPid = 0;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(max_entries, 2);
+	__type(key, __u64);
+	__type(value, __u64);
+} hashmap1 SEC(".maps");
+
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int sysenter_getpgid(const void *ctx)
+{
+	/* Just do it for once, when called from our own test prog. This
+	 * ensures the map value is only updated for a single CPU.
+	 */
+	int cur_pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (cur_pid == inPid)
+		bpf_map_update_elem(&hashmap1, &inKey, &inValue, BPF_NOEXIST);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c
index 55bd387..52d3f03 100644
--- a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c
+++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c
@@ -145,7 +145,7 @@
 	test_clone3_supported();
 
 	EXPECT_EQ(getuid(), 0)
-		XFAIL(return, "Skipping all tests as non-root\n");
+		SKIP(return, "Skipping all tests as non-root");
 
 	memset(&set_tid, 0, sizeof(set_tid));
 
diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
index c99b98b..575b391 100644
--- a/tools/testing/selftests/core/close_range_test.c
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -44,7 +44,7 @@
 		fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
 		ASSERT_GE(fd, 0) {
 			if (errno == ENOENT)
-				XFAIL(return, "Skipping test since /dev/null does not exist");
+				SKIP(return, "Skipping test since /dev/null does not exist");
 		}
 
 		open_fds[i] = fd;
@@ -52,7 +52,7 @@
 
 	EXPECT_EQ(-1, sys_close_range(open_fds[0], open_fds[100], -1)) {
 		if (errno == ENOSYS)
-			XFAIL(return, "close_range() syscall not supported");
+			SKIP(return, "close_range() syscall not supported");
 	}
 
 	EXPECT_EQ(0, sys_close_range(open_fds[0], open_fds[50], 0));
@@ -108,7 +108,7 @@
 		fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
 		ASSERT_GE(fd, 0) {
 			if (errno == ENOENT)
-				XFAIL(return, "Skipping test since /dev/null does not exist");
+				SKIP(return, "Skipping test since /dev/null does not exist");
 		}
 
 		open_fds[i] = fd;
@@ -197,7 +197,7 @@
 		fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
 		ASSERT_GE(fd, 0) {
 			if (errno == ENOENT)
-				XFAIL(return, "Skipping test since /dev/null does not exist");
+				SKIP(return, "Skipping test since /dev/null does not exist");
 		}
 
 		open_fds[i] = fd;
diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
index 1d27f52..477cbb0 100644
--- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
+++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c
@@ -74,7 +74,7 @@
 	ret = mount(NULL, binderfs_mntpt, "binder", 0, 0);
 	EXPECT_EQ(ret, 0) {
 		if (errno == ENODEV)
-			XFAIL(goto out, "binderfs missing");
+			SKIP(goto out, "binderfs missing");
 		TH_LOG("%s - Failed to mount binderfs", strerror(errno));
 		goto rmdir;
 	}
@@ -475,10 +475,10 @@
 TEST(binderfs_test_privileged)
 {
 	if (geteuid() != 0)
-		XFAIL(return, "Tests are not run as root. Skipping privileged tests");
+		SKIP(return, "Tests are not run as root. Skipping privileged tests");
 
 	if (__do_binderfs_test(_metadata))
-		XFAIL(return, "The Android binderfs filesystem is not available");
+		SKIP(return, "The Android binderfs filesystem is not available");
 }
 
 TEST(binderfs_test_unprivileged)
@@ -511,7 +511,7 @@
 	ret = wait_for_pid(pid);
 	if (ret) {
 		if (ret == 2)
-			XFAIL(return, "The Android binderfs filesystem is not available");
+			SKIP(return, "The Android binderfs filesystem is not available");
 		ASSERT_EQ(ret, 0) {
 			TH_LOG("wait_for_pid() failed");
 		}
diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
index d979ff1..8f82f99 100644
--- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
+++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c
@@ -3282,4 +3282,99 @@
 	close(ctx.epfd);
 }
 
+struct epoll61_ctx {
+	int epfd;
+	int evfd;
+};
+
+static void *epoll61_write_eventfd(void *ctx_)
+{
+	struct epoll61_ctx *ctx = ctx_;
+	int64_t l = 1;
+
+	usleep(10950);
+	write(ctx->evfd, &l, sizeof(l));
+	return NULL;
+}
+
+static void *epoll61_epoll_with_timeout(void *ctx_)
+{
+	struct epoll61_ctx *ctx = ctx_;
+	struct epoll_event events[1];
+	int n;
+
+	n = epoll_wait(ctx->epfd, events, 1, 11);
+	/*
+	 * If epoll returned the eventfd, write on the eventfd to wake up the
+	 * blocking poller.
+	 */
+	if (n == 1) {
+		int64_t l = 1;
+
+		write(ctx->evfd, &l, sizeof(l));
+	}
+	return NULL;
+}
+
+static void *epoll61_blocking_epoll(void *ctx_)
+{
+	struct epoll61_ctx *ctx = ctx_;
+	struct epoll_event events[1];
+
+	epoll_wait(ctx->epfd, events, 1, -1);
+	return NULL;
+}
+
+TEST(epoll61)
+{
+	struct epoll61_ctx ctx;
+	struct epoll_event ev;
+	int i, r;
+
+	ctx.epfd = epoll_create1(0);
+	ASSERT_GE(ctx.epfd, 0);
+	ctx.evfd = eventfd(0, EFD_NONBLOCK);
+	ASSERT_GE(ctx.evfd, 0);
+
+	ev.events = EPOLLIN | EPOLLET | EPOLLERR | EPOLLHUP;
+	ev.data.ptr = NULL;
+	r = epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd, &ev);
+	ASSERT_EQ(r, 0);
+
+	/*
+	 * We are testing a race.  Repeat the test case 1000 times to make it
+	 * more likely to fail in case of a bug.
+	 */
+	for (i = 0; i < 1000; i++) {
+		pthread_t threads[3];
+		int n;
+
+		/*
+		 * Start 3 threads:
+		 * Thread 1 sleeps for 10.9ms and writes to the evenfd.
+		 * Thread 2 calls epoll with a timeout of 11ms.
+		 * Thread 3 calls epoll with a timeout of -1.
+		 *
+		 * The eventfd write by Thread 1 should either wakeup Thread 2
+		 * or Thread 3.  If it wakes up Thread 2, Thread 2 writes on the
+		 * eventfd to wake up Thread 3.
+		 *
+		 * If no events are missed, all three threads should eventually
+		 * be joinable.
+		 */
+		ASSERT_EQ(pthread_create(&threads[0], NULL,
+					 epoll61_write_eventfd, &ctx), 0);
+		ASSERT_EQ(pthread_create(&threads[1], NULL,
+					 epoll61_epoll_with_timeout, &ctx), 0);
+		ASSERT_EQ(pthread_create(&threads[2], NULL,
+					 epoll61_blocking_epoll, &ctx), 0);
+
+		for (n = 0; n < ARRAY_SIZE(threads); ++n)
+			ASSERT_EQ(pthread_join(threads[n], NULL), 0);
+	}
+
+	close(ctx.epfd);
+	close(ctx.evfd);
+}
+
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc
index 3bcd4c3..b4da41d 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_kprobe.tc
@@ -6,7 +6,7 @@
 echo 0 > events/enable
 echo > dynamic_events
 
-PLACE=kernel_clone
+PLACE=$FUNCTION_FORK
 
 echo "p:myevent1 $PLACE" >> dynamic_events
 echo "r:myevent2 $PLACE" >> dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc b/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc
index 4389619..3a0e288 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/clear_select_events.tc
@@ -6,7 +6,7 @@
 echo 0 > events/enable
 echo > dynamic_events
 
-PLACE=kernel_clone
+PLACE=$FUNCTION_FORK
 
 setup_events() {
 echo "p:myevent1 $PLACE" >> dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc b/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc
index a8603bd..d3e138e 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/generic_clear_event.tc
@@ -6,7 +6,7 @@
 echo 0 > events/enable
 echo > dynamic_events
 
-PLACE=kernel_clone
+PLACE=$FUNCTION_FORK
 
 setup_events() {
 echo "p:myevent1 $PLACE" >> dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc
index acb17ce..8054196 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc
@@ -39,7 +39,7 @@
     disable_tracing
 
     echo do_execve* > set_ftrace_filter
-    echo *do_fork >> set_ftrace_filter
+    echo $FUNCTION_FORK >> set_ftrace_filter
 
     echo $PID > set_ftrace_notrace_pid
     echo function > current_tracer
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
index 9f0a968..2f72112 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc
@@ -39,7 +39,7 @@
     disable_tracing
 
     echo do_execve* > set_ftrace_filter
-    echo *do_fork >> set_ftrace_filter
+    echo $FUNCTION_FORK >> set_ftrace_filter
 
     echo $PID > set_ftrace_pid
     echo function > current_tracer
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
index 98305d7..191d116 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-stacktrace.tc
@@ -4,9 +4,9 @@
 # requires: set_ftrace_filter
 # flags: instance
 
-echo kernel_clone:stacktrace >> set_ftrace_filter
+echo $FUNCTION_FORK:stacktrace >> set_ftrace_filter
 
-grep -q "kernel_clone:stacktrace:unlimited" set_ftrace_filter
+grep -q "$FUNCTION_FORK:stacktrace:unlimited" set_ftrace_filter
 
 (echo "forked"; sleep 1)
 
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index c5dec55..a6fac92 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -133,6 +133,13 @@
     ping $LOCALHOST -c 1 || sleep .001 || usleep 1 || sleep 1
 }
 
+# The fork function in the kernel was renamed from "_do_fork" to
+# "kernel_fork". As older tests should still work with older kernels
+# as well as newer kernels, check which version of fork is used on this
+# kernel so that the tests can use the fork function for the running kernel.
+FUNCTION_FORK=`(if grep '\bkernel_clone\b' /proc/kallsyms > /dev/null; then
+                echo kernel_clone; else echo '_do_fork'; fi)`
+
 # Since probe event command may include backslash, explicitly use printf "%s"
 # to NOT interpret it.
 ftrace_errlog_check() { # err-prefix command-with-error-pos-by-^ command-file
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
index 9737cd0..2428a3ed 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc
@@ -3,7 +3,7 @@
 # description: Kprobe dynamic event - adding and removing
 # requires: kprobe_events
 
-echo p:myevent kernel_clone > kprobe_events
+echo p:myevent $FUNCTION_FORK > kprobe_events
 grep myevent kprobe_events
 test -d events/kprobes/myevent
 echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
index f9a40af..010a8b1 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc
@@ -3,7 +3,7 @@
 # description: Kprobe dynamic event - busy event check
 # requires: kprobe_events
 
-echo p:myevent kernel_clone > kprobe_events
+echo p:myevent $FUNCTION_FORK > kprobe_events
 test -d events/kprobes/myevent
 echo 1 > events/kprobes/myevent/enable
 echo > kprobe_events && exit_fail # this must fail
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
index eb543d3..a96a1dc 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc
@@ -3,13 +3,13 @@
 # description: Kprobe dynamic event with arguments
 # requires: kprobe_events
 
-echo 'p:testprobe kernel_clone $stack $stack0 +0($stack)' > kprobe_events
+echo "p:testprobe $FUNCTION_FORK \$stack \$stack0 +0(\$stack)" > kprobe_events
 grep testprobe kprobe_events | grep -q 'arg1=\$stack arg2=\$stack0 arg3=+0(\$stack)'
 test -d events/kprobes/testprobe
 
 echo 1 > events/kprobes/testprobe/enable
 ( echo "forked")
-grep testprobe trace | grep 'kernel_clone' | \
+grep testprobe trace | grep "$FUNCTION_FORK" | \
   grep -q 'arg1=0x[[:xdigit:]]* arg2=0x[[:xdigit:]]* arg3=0x[[:xdigit:]]*$'
 
 echo 0 > events/kprobes/testprobe/enable
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc
index 4e5b63b..a053ee2 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_comm.tc
@@ -5,7 +5,7 @@
 
 grep -A1 "fetcharg:" README | grep -q "\$comm" || exit_unsupported # this is too old
 
-echo 'p:testprobe kernel_clone comm=$comm ' > kprobe_events
+echo "p:testprobe $FUNCTION_FORK comm=\$comm " > kprobe_events
 grep testprobe kprobe_events | grep -q 'comm=$comm'
 test -d events/kprobes/testprobe
 
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
index a1d7058..84285a6 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
@@ -30,13 +30,13 @@
 : "Test get argument (1)"
 echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string" > kprobe_events
 echo 1 > events/kprobes/testprobe/enable
-echo "p:test kernel_clone" >> kprobe_events
+echo "p:test $FUNCTION_FORK" >> kprobe_events
 grep -qe "testprobe.* arg1=\"test\"" trace
 
 echo 0 > events/kprobes/testprobe/enable
 : "Test get argument (2)"
 echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string arg2=+0(${ARG1}):string" > kprobe_events
 echo 1 > events/kprobes/testprobe/enable
-echo "p:test kernel_clone" >> kprobe_events
+echo "p:test $FUNCTION_FORK" >> kprobe_events
 grep -qe "testprobe.* arg1=\"test\" arg2=\"test\"" trace
 
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc
index bd25dd0..717130e 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_symbol.tc
@@ -14,12 +14,12 @@
 fi
 
 : "Test get basic types symbol argument"
-echo "p:testprobe_u kernel_clone arg1=@linux_proc_banner:u64 arg2=@linux_proc_banner:u32 arg3=@linux_proc_banner:u16 arg4=@linux_proc_banner:u8" > kprobe_events
-echo "p:testprobe_s kernel_clone arg1=@linux_proc_banner:s64 arg2=@linux_proc_banner:s32 arg3=@linux_proc_banner:s16 arg4=@linux_proc_banner:s8" >> kprobe_events
+echo "p:testprobe_u $FUNCTION_FORK arg1=@linux_proc_banner:u64 arg2=@linux_proc_banner:u32 arg3=@linux_proc_banner:u16 arg4=@linux_proc_banner:u8" > kprobe_events
+echo "p:testprobe_s $FUNCTION_FORK arg1=@linux_proc_banner:s64 arg2=@linux_proc_banner:s32 arg3=@linux_proc_banner:s16 arg4=@linux_proc_banner:s8" >> kprobe_events
 if grep -q "x8/16/32/64" README; then
-  echo "p:testprobe_x kernel_clone arg1=@linux_proc_banner:x64 arg2=@linux_proc_banner:x32 arg3=@linux_proc_banner:x16 arg4=@linux_proc_banner:x8" >> kprobe_events
+  echo "p:testprobe_x $FUNCTION_FORK arg1=@linux_proc_banner:x64 arg2=@linux_proc_banner:x32 arg3=@linux_proc_banner:x16 arg4=@linux_proc_banner:x8" >> kprobe_events
 fi
-echo "p:testprobe_bf kernel_clone arg1=@linux_proc_banner:b8@4/32" >> kprobe_events
+echo "p:testprobe_bf $FUNCTION_FORK arg1=@linux_proc_banner:b8@4/32" >> kprobe_events
 echo 1 > events/kprobes/enable
 (echo "forked")
 echo 0 > events/kprobes/enable
@@ -27,7 +27,7 @@
 grep "testprobe_bf:.* arg1=.*" trace
 
 : "Test get string symbol argument"
-echo "p:testprobe_str kernel_clone arg1=@linux_proc_banner:string" > kprobe_events
+echo "p:testprobe_str $FUNCTION_FORK arg1=@linux_proc_banner:string" > kprobe_events
 echo 1 > events/kprobes/enable
 (echo "forked")
 echo 0 > events/kprobes/enable
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
index 91fcce1c..25b7708 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc
@@ -4,7 +4,7 @@
 # requires: kprobe_events "x8/16/32/64":README
 
 gen_event() { # Bitsize
-  echo "p:testprobe kernel_clone \$stack0:s$1 \$stack0:u$1 \$stack0:x$1 \$stack0:b4@4/$1"
+  echo "p:testprobe $FUNCTION_FORK \$stack0:s$1 \$stack0:u$1 \$stack0:x$1 \$stack0:b4@4/$1"
 }
 
 check_types() { # s-type u-type x-type bf-type width
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc
index a30a9c0..d25d01a 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc
@@ -9,12 +9,16 @@
 :;: "user-memory access syntax and ustring working on user memory";:
 echo 'p:myevent do_sys_open path=+0($arg2):ustring path2=+u0($arg2):string' \
 	> kprobe_events
+echo 'p:myevent2 do_sys_openat2 path=+0($arg2):ustring path2=+u0($arg2):string' \
+	>> kprobe_events
 
 grep myevent kprobe_events | \
 	grep -q 'path=+0($arg2):ustring path2=+u0($arg2):string'
 echo 1 > events/kprobes/myevent/enable
+echo 1 > events/kprobes/myevent2/enable
 echo > /dev/null
 echo 0 > events/kprobes/myevent/enable
+echo 0 > events/kprobes/myevent2/enable
 
 grep myevent trace | grep -q 'path="/dev/null" path2="/dev/null"'
 
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
index 0d17909..5556292 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_ftrace.tc
@@ -5,29 +5,29 @@
 
 # prepare
 echo nop > current_tracer
-echo kernel_clone > set_ftrace_filter
-echo 'p:testprobe kernel_clone' > kprobe_events
+echo $FUNCTION_FORK > set_ftrace_filter
+echo "p:testprobe $FUNCTION_FORK" > kprobe_events
 
 # kprobe on / ftrace off
 echo 1 > events/kprobes/testprobe/enable
 echo > trace
 ( echo "forked")
 grep testprobe trace
-! grep 'kernel_clone <-' trace
+! grep "$FUNCTION_FORK <-" trace
 
 # kprobe on / ftrace on
 echo function > current_tracer
 echo > trace
 ( echo "forked")
 grep testprobe trace
-grep 'kernel_clone <-' trace
+grep "$FUNCTION_FORK <-" trace
 
 # kprobe off / ftrace on
 echo 0 > events/kprobes/testprobe/enable
 echo > trace
 ( echo "forked")
 ! grep testprobe trace
-grep 'kernel_clone <-' trace
+grep "$FUNCTION_FORK <-" trace
 
 # kprobe on / ftrace on
 echo 1 > events/kprobes/testprobe/enable
@@ -35,11 +35,11 @@
 echo > trace
 ( echo "forked")
 grep testprobe trace
-grep 'kernel_clone <-' trace
+grep "$FUNCTION_FORK <-" trace
 
 # kprobe on / ftrace off
 echo nop > current_tracer
 echo > trace
 ( echo "forked")
 grep testprobe trace
-! grep 'kernel_clone <-' trace
+! grep "$FUNCTION_FORK <-" trace
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc
index 45d90b6..f0d5b77 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc
@@ -4,7 +4,7 @@
 # requires: kprobe_events "Create/append/":README
 
 # Choose 2 symbols for target
-SYM1=kernel_clone
+SYM1=$FUNCTION_FORK
 SYM2=do_exit
 EVENT_NAME=kprobes/testevent
 
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
index 1b5550e..fa928b4 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
@@ -86,15 +86,15 @@
 
 # multiprobe errors
 if grep -q "Create/append/" README && grep -q "imm-value" README; then
-echo 'p:kprobes/testevent kernel_clone' > kprobe_events
+echo "p:kprobes/testevent $FUNCTION_FORK" > kprobe_events
 check_error '^r:kprobes/testevent do_exit'	# DIFF_PROBE_TYPE
 
 # Explicitly use printf "%s" to not interpret \1
-printf "%s" 'p:kprobes/testevent kernel_clone abcd=\1' > kprobe_events
-check_error 'p:kprobes/testevent kernel_clone ^bcd=\1'	# DIFF_ARG_TYPE
-check_error 'p:kprobes/testevent kernel_clone ^abcd=\1:u8'	# DIFF_ARG_TYPE
-check_error 'p:kprobes/testevent kernel_clone ^abcd=\"foo"'	# DIFF_ARG_TYPE
-check_error '^p:kprobes/testevent kernel_clone abcd=\1'	# SAME_PROBE
+printf "%s" "p:kprobes/testevent $FUNCTION_FORK abcd=\\1" > kprobe_events
+check_error "p:kprobes/testevent $FUNCTION_FORK ^bcd=\\1"	# DIFF_ARG_TYPE
+check_error "p:kprobes/testevent $FUNCTION_FORK ^abcd=\\1:u8"	# DIFF_ARG_TYPE
+check_error "p:kprobes/testevent $FUNCTION_FORK ^abcd=\\\"foo\"" # DIFF_ARG_TYPE
+check_error "^p:kprobes/testevent $FUNCTION_FORK abcd=\\1"	# SAME_PROBE
 fi
 
 # %return suffix errors
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
index 7ae492c..197cc2a 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc
@@ -4,14 +4,14 @@
 # requires: kprobe_events
 
 # Add new kretprobe event
-echo 'r:testprobe2 kernel_clone $retval' > kprobe_events
+echo "r:testprobe2 $FUNCTION_FORK \$retval" > kprobe_events
 grep testprobe2 kprobe_events | grep -q 'arg1=\$retval'
 test -d events/kprobes/testprobe2
 
 echo 1 > events/kprobes/testprobe2/enable
 ( echo "forked")
 
-cat trace | grep testprobe2 | grep -q '<- kernel_clone'
+cat trace | grep testprobe2 | grep -q "<- $FUNCTION_FORK"
 
 echo 0 > events/kprobes/testprobe2/enable
 echo '-:testprobe2' >> kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc b/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc
index c4093fc..98166fa 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/profile.tc
@@ -4,7 +4,7 @@
 # requires: kprobe_events
 
 ! grep -q 'myevent' kprobe_profile
-echo p:myevent kernel_clone > kprobe_events
+echo "p:myevent $FUNCTION_FORK" > kprobe_events
 grep -q 'myevent[[:space:]]*0[[:space:]]*0$' kprobe_profile
 echo 1 > events/kprobes/myevent/enable
 ( echo "forked" )
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index f19804d..edce854 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -126,7 +126,7 @@
 	snprintf(_metadata->results->reason, \
 		 sizeof(_metadata->results->reason), fmt, ##__VA_ARGS__); \
 	if (TH_LOG_ENABLED) { \
-		fprintf(TH_LOG_STREAM, "#      SKIP     %s\n", \
+		fprintf(TH_LOG_STREAM, "#      SKIP      %s\n", \
 			_metadata->results->reason); \
 	} \
 	_metadata->passed = 1; \
@@ -432,7 +432,7 @@
  */
 
 /**
- * ASSERT_EQ(expected, seen)
+ * ASSERT_EQ()
  *
  * @expected: expected value
  * @seen: measured value
@@ -443,7 +443,7 @@
 	__EXPECT(expected, #expected, seen, #seen, ==, 1)
 
 /**
- * ASSERT_NE(expected, seen)
+ * ASSERT_NE()
  *
  * @expected: expected value
  * @seen: measured value
@@ -454,7 +454,7 @@
 	__EXPECT(expected, #expected, seen, #seen, !=, 1)
 
 /**
- * ASSERT_LT(expected, seen)
+ * ASSERT_LT()
  *
  * @expected: expected value
  * @seen: measured value
@@ -465,7 +465,7 @@
 	__EXPECT(expected, #expected, seen, #seen, <, 1)
 
 /**
- * ASSERT_LE(expected, seen)
+ * ASSERT_LE()
  *
  * @expected: expected value
  * @seen: measured value
@@ -476,7 +476,7 @@
 	__EXPECT(expected, #expected, seen, #seen, <=, 1)
 
 /**
- * ASSERT_GT(expected, seen)
+ * ASSERT_GT()
  *
  * @expected: expected value
  * @seen: measured value
@@ -487,7 +487,7 @@
 	__EXPECT(expected, #expected, seen, #seen, >, 1)
 
 /**
- * ASSERT_GE(expected, seen)
+ * ASSERT_GE()
  *
  * @expected: expected value
  * @seen: measured value
@@ -498,7 +498,7 @@
 	__EXPECT(expected, #expected, seen, #seen, >=, 1)
 
 /**
- * ASSERT_NULL(seen)
+ * ASSERT_NULL()
  *
  * @seen: measured value
  *
@@ -508,7 +508,7 @@
 	__EXPECT(NULL, "NULL", seen, #seen, ==, 1)
 
 /**
- * ASSERT_TRUE(seen)
+ * ASSERT_TRUE()
  *
  * @seen: measured value
  *
@@ -518,7 +518,7 @@
 	__EXPECT(0, "0", seen, #seen, !=, 1)
 
 /**
- * ASSERT_FALSE(seen)
+ * ASSERT_FALSE()
  *
  * @seen: measured value
  *
@@ -528,7 +528,7 @@
 	__EXPECT(0, "0", seen, #seen, ==, 1)
 
 /**
- * ASSERT_STREQ(expected, seen)
+ * ASSERT_STREQ()
  *
  * @expected: expected value
  * @seen: measured value
@@ -539,7 +539,7 @@
 	__EXPECT_STR(expected, seen, ==, 1)
 
 /**
- * ASSERT_STRNE(expected, seen)
+ * ASSERT_STRNE()
  *
  * @expected: expected value
  * @seen: measured value
@@ -550,7 +550,7 @@
 	__EXPECT_STR(expected, seen, !=, 1)
 
 /**
- * EXPECT_EQ(expected, seen)
+ * EXPECT_EQ()
  *
  * @expected: expected value
  * @seen: measured value
@@ -561,7 +561,7 @@
 	__EXPECT(expected, #expected, seen, #seen, ==, 0)
 
 /**
- * EXPECT_NE(expected, seen)
+ * EXPECT_NE()
  *
  * @expected: expected value
  * @seen: measured value
@@ -572,7 +572,7 @@
 	__EXPECT(expected, #expected, seen, #seen, !=, 0)
 
 /**
- * EXPECT_LT(expected, seen)
+ * EXPECT_LT()
  *
  * @expected: expected value
  * @seen: measured value
@@ -583,7 +583,7 @@
 	__EXPECT(expected, #expected, seen, #seen, <, 0)
 
 /**
- * EXPECT_LE(expected, seen)
+ * EXPECT_LE()
  *
  * @expected: expected value
  * @seen: measured value
@@ -594,7 +594,7 @@
 	__EXPECT(expected, #expected, seen, #seen, <=, 0)
 
 /**
- * EXPECT_GT(expected, seen)
+ * EXPECT_GT()
  *
  * @expected: expected value
  * @seen: measured value
@@ -605,7 +605,7 @@
 	__EXPECT(expected, #expected, seen, #seen, >, 0)
 
 /**
- * EXPECT_GE(expected, seen)
+ * EXPECT_GE()
  *
  * @expected: expected value
  * @seen: measured value
@@ -616,7 +616,7 @@
 	__EXPECT(expected, #expected, seen, #seen, >=, 0)
 
 /**
- * EXPECT_NULL(seen)
+ * EXPECT_NULL()
  *
  * @seen: measured value
  *
@@ -626,7 +626,7 @@
 	__EXPECT(NULL, "NULL", seen, #seen, ==, 0)
 
 /**
- * EXPECT_TRUE(seen)
+ * EXPECT_TRUE()
  *
  * @seen: measured value
  *
@@ -636,7 +636,7 @@
 	__EXPECT(0, "0", seen, #seen, !=, 0)
 
 /**
- * EXPECT_FALSE(seen)
+ * EXPECT_FALSE()
  *
  * @seen: measured value
  *
@@ -646,7 +646,7 @@
 	__EXPECT(0, "0", seen, #seen, ==, 0)
 
 /**
- * EXPECT_STREQ(expected, seen)
+ * EXPECT_STREQ()
  *
  * @expected: expected value
  * @seen: measured value
@@ -657,7 +657,7 @@
 	__EXPECT_STR(expected, seen, ==, 0)
 
 /**
- * EXPECT_STRNE(expected, seen)
+ * EXPECT_STRNE()
  *
  * @expected: expected value
  * @seen: measured value
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index d2c2d62..7a2c242 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,10 +1,13 @@
 # SPDX-License-Identifier: GPL-2.0-only
+/aarch64/get-reg-list
+/aarch64/get-reg-list-sve
 /s390x/memop
 /s390x/resets
 /s390x/sync_regs_test
 /x86_64/cr4_cpuid_sync_test
 /x86_64/debug_regs
 /x86_64/evmcs_test
+/x86_64/kvm_pv_test
 /x86_64/hyperv_cpuid
 /x86_64/mmio_warning_test
 /x86_64/platform_info_test
@@ -24,6 +27,7 @@
 /clear_dirty_log_test
 /demand_paging_test
 /dirty_log_test
+/dirty_log_perf_test
 /kvm_create_max_vcpus
 /set_memory_region_test
 /steal_time
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 30afbad..3d14ef7 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -34,13 +34,14 @@
 endif
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c
-LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c
+LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
 LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
 LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
+TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
 TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
 TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
 TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
@@ -58,14 +59,15 @@
 TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
 TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
 TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test
-TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
+TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_x86_64 += set_memory_region_test
 TEST_GEN_PROGS_x86_64 += steal_time
 
-TEST_GEN_PROGS_aarch64 += clear_dirty_log_test
+TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
+TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
 TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
@@ -111,14 +113,21 @@
 include ../lib.mk
 
 STATIC_LIBS := $(OUTPUT)/libkvm.a
-LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM))
-EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.*
+LIBKVM_C := $(filter %.c,$(LIBKVM))
+LIBKVM_S := $(filter %.S,$(LIBKVM))
+LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
+LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
+EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.*
 
-x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ))))
-$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
+x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
+$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
-$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
+$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
+$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS)
 	$(AR) crs $@ $^
 
 x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c
new file mode 100644
index 0000000..efba766
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c
@@ -0,0 +1,3 @@
+// SPDX-License-Identifier: GPL-2.0
+#define REG_LIST_SVE
+#include "get-reg-list.c"
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
new file mode 100644
index 0000000..33218a3
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -0,0 +1,841 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Check for KVM_GET_REG_LIST regressions.
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ *
+ * When attempting to migrate from a host with an older kernel to a host
+ * with a newer kernel we allow the newer kernel on the destination to
+ * list new registers with get-reg-list. We assume they'll be unused, at
+ * least until the guest reboots, and so they're relatively harmless.
+ * However, if the destination host with the newer kernel is missing
+ * registers which the source host with the older kernel has, then that's
+ * a regression in get-reg-list. This test checks for that regression by
+ * checking the current list against a blessed list. We should never have
+ * missing registers, but if new ones appear then they can probably be
+ * added to the blessed list. A completely new blessed list can be created
+ * by running the test with the --list command line argument.
+ *
+ * Note, the blessed list should be created from the oldest possible
+ * kernel. We can't go older than v4.15, though, because that's the first
+ * release to expose the ID system registers in KVM_GET_REG_LIST, see
+ * commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU features
+ * from guests"). Also, one must use the --core-reg-fixup command line
+ * option when running on an older kernel that doesn't include df205b5c6328
+ * ("KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST")
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "kvm_util.h"
+#include "test_util.h"
+#include "processor.h"
+
+#ifdef REG_LIST_SVE
+#define reg_list_sve() (true)
+#else
+#define reg_list_sve() (false)
+#endif
+
+#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK)
+
+#define for_each_reg(i)								\
+	for ((i) = 0; (i) < reg_list->n; ++(i))
+
+#define for_each_missing_reg(i)							\
+	for ((i) = 0; (i) < blessed_n; ++(i))					\
+		if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i]))
+
+#define for_each_new_reg(i)							\
+	for ((i) = 0; (i) < reg_list->n; ++(i))					\
+		if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i]))
+
+
+static struct kvm_reg_list *reg_list;
+
+static __u64 base_regs[], vregs[], sve_regs[], rejects_set[];
+static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n;
+static __u64 *blessed_reg, blessed_n;
+
+static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg)
+{
+	int i;
+
+	for (i = 0; i < nr_regs; ++i)
+		if (reg == regs[i])
+			return true;
+	return false;
+}
+
+static const char *str_with_index(const char *template, __u64 index)
+{
+	char *str, *p;
+	int n;
+
+	str = strdup(template);
+	p = strstr(str, "##");
+	n = sprintf(p, "%lld", index);
+	strcat(p + n, strstr(template, "##") + 2);
+
+	return (const char *)str;
+}
+
+#define CORE_REGS_XX_NR_WORDS	2
+#define CORE_SPSR_XX_NR_WORDS	2
+#define CORE_FPREGS_XX_NR_WORDS	4
+
+static const char *core_id_to_str(__u64 id)
+{
+	__u64 core_off = id & ~REG_MASK, idx;
+
+	/*
+	 * core_off is the offset into struct kvm_regs
+	 */
+	switch (core_off) {
+	case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
+		idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS;
+		TEST_ASSERT(idx < 31, "Unexpected regs.regs index: %lld", idx);
+		return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx);
+	case KVM_REG_ARM_CORE_REG(regs.sp):
+		return "KVM_REG_ARM_CORE_REG(regs.sp)";
+	case KVM_REG_ARM_CORE_REG(regs.pc):
+		return "KVM_REG_ARM_CORE_REG(regs.pc)";
+	case KVM_REG_ARM_CORE_REG(regs.pstate):
+		return "KVM_REG_ARM_CORE_REG(regs.pstate)";
+	case KVM_REG_ARM_CORE_REG(sp_el1):
+		return "KVM_REG_ARM_CORE_REG(sp_el1)";
+	case KVM_REG_ARM_CORE_REG(elr_el1):
+		return "KVM_REG_ARM_CORE_REG(elr_el1)";
+	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+		idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS;
+		TEST_ASSERT(idx < KVM_NR_SPSR, "Unexpected spsr index: %lld", idx);
+		return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx);
+	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+		idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS;
+		TEST_ASSERT(idx < 32, "Unexpected fp_regs.vregs index: %lld", idx);
+		return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx);
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+		return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)";
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+		return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)";
+	}
+
+	TEST_FAIL("Unknown core reg id: 0x%llx", id);
+	return NULL;
+}
+
+static const char *sve_id_to_str(__u64 id)
+{
+	__u64 sve_off, n, i;
+
+	if (id == KVM_REG_ARM64_SVE_VLS)
+		return "KVM_REG_ARM64_SVE_VLS";
+
+	sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1));
+	i = id & (KVM_ARM64_SVE_MAX_SLICES - 1);
+
+	TEST_ASSERT(i == 0, "Currently we don't expect slice > 0, reg id 0x%llx", id);
+
+	switch (sve_off) {
+	case KVM_REG_ARM64_SVE_ZREG_BASE ...
+	     KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1:
+		n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1);
+		TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0),
+			    "Unexpected bits set in SVE ZREG id: 0x%llx", id);
+		return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n);
+	case KVM_REG_ARM64_SVE_PREG_BASE ...
+	     KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1:
+		n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1);
+		TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0),
+			    "Unexpected bits set in SVE PREG id: 0x%llx", id);
+		return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n);
+	case KVM_REG_ARM64_SVE_FFR_BASE:
+		TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0),
+			    "Unexpected bits set in SVE FFR id: 0x%llx", id);
+		return "KVM_REG_ARM64_SVE_FFR(0)";
+	}
+
+	return NULL;
+}
+
+static void print_reg(__u64 id)
+{
+	unsigned op0, op1, crn, crm, op2;
+	const char *reg_size = NULL;
+
+	TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64,
+		    "KVM_REG_ARM64 missing in reg id: 0x%llx", id);
+
+	switch (id & KVM_REG_SIZE_MASK) {
+	case KVM_REG_SIZE_U8:
+		reg_size = "KVM_REG_SIZE_U8";
+		break;
+	case KVM_REG_SIZE_U16:
+		reg_size = "KVM_REG_SIZE_U16";
+		break;
+	case KVM_REG_SIZE_U32:
+		reg_size = "KVM_REG_SIZE_U32";
+		break;
+	case KVM_REG_SIZE_U64:
+		reg_size = "KVM_REG_SIZE_U64";
+		break;
+	case KVM_REG_SIZE_U128:
+		reg_size = "KVM_REG_SIZE_U128";
+		break;
+	case KVM_REG_SIZE_U256:
+		reg_size = "KVM_REG_SIZE_U256";
+		break;
+	case KVM_REG_SIZE_U512:
+		reg_size = "KVM_REG_SIZE_U512";
+		break;
+	case KVM_REG_SIZE_U1024:
+		reg_size = "KVM_REG_SIZE_U1024";
+		break;
+	case KVM_REG_SIZE_U2048:
+		reg_size = "KVM_REG_SIZE_U2048";
+		break;
+	default:
+		TEST_FAIL("Unexpected reg size: 0x%llx in reg id: 0x%llx",
+			  (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id);
+	}
+
+	switch (id & KVM_REG_ARM_COPROC_MASK) {
+	case KVM_REG_ARM_CORE:
+		printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(id));
+		break;
+	case KVM_REG_ARM_DEMUX:
+		TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)),
+			    "Unexpected bits set in DEMUX reg id: 0x%llx", id);
+		printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n",
+		       reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK);
+		break;
+	case KVM_REG_ARM64_SYSREG:
+		op0 = (id & KVM_REG_ARM64_SYSREG_OP0_MASK) >> KVM_REG_ARM64_SYSREG_OP0_SHIFT;
+		op1 = (id & KVM_REG_ARM64_SYSREG_OP1_MASK) >> KVM_REG_ARM64_SYSREG_OP1_SHIFT;
+		crn = (id & KVM_REG_ARM64_SYSREG_CRN_MASK) >> KVM_REG_ARM64_SYSREG_CRN_SHIFT;
+		crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT;
+		op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT;
+		TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2),
+			    "Unexpected bits set in SYSREG reg id: 0x%llx", id);
+		printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2);
+		break;
+	case KVM_REG_ARM_FW:
+		TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff),
+			    "Unexpected bits set in FW reg id: 0x%llx", id);
+		printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff);
+		break;
+	case KVM_REG_ARM64_SVE:
+		if (reg_list_sve())
+			printf("\t%s,\n", sve_id_to_str(id));
+		else
+			TEST_FAIL("KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", id);
+		break;
+	default:
+		TEST_FAIL("Unexpected coproc type: 0x%llx in reg id: 0x%llx",
+			  (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id);
+	}
+}
+
+/*
+ * Older kernels listed each 32-bit word of CORE registers separately.
+ * For 64 and 128-bit registers we need to ignore the extra words. We
+ * also need to fixup the sizes, because the older kernels stated all
+ * registers were 64-bit, even when they weren't.
+ */
+static void core_reg_fixup(void)
+{
+	struct kvm_reg_list *tmp;
+	__u64 id, core_off;
+	int i;
+
+	tmp = calloc(1, sizeof(*tmp) + reg_list->n * sizeof(__u64));
+
+	for (i = 0; i < reg_list->n; ++i) {
+		id = reg_list->reg[i];
+
+		if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM_CORE) {
+			tmp->reg[tmp->n++] = id;
+			continue;
+		}
+
+		core_off = id & ~REG_MASK;
+
+		switch (core_off) {
+		case 0x52: case 0xd2: case 0xd6:
+			/*
+			 * These offsets are pointing at padding.
+			 * We need to ignore them too.
+			 */
+			continue;
+		case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+		     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+			if (core_off & 3)
+				continue;
+			id &= ~KVM_REG_SIZE_MASK;
+			id |= KVM_REG_SIZE_U128;
+			tmp->reg[tmp->n++] = id;
+			continue;
+		case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+		case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+			id &= ~KVM_REG_SIZE_MASK;
+			id |= KVM_REG_SIZE_U32;
+			tmp->reg[tmp->n++] = id;
+			continue;
+		default:
+			if (core_off & 1)
+				continue;
+			tmp->reg[tmp->n++] = id;
+			break;
+		}
+	}
+
+	free(reg_list);
+	reg_list = tmp;
+}
+
+static void prepare_vcpu_init(struct kvm_vcpu_init *init)
+{
+	if (reg_list_sve())
+		init->features[0] |= 1 << KVM_ARM_VCPU_SVE;
+}
+
+static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	int feature;
+
+	if (reg_list_sve()) {
+		feature = KVM_ARM_VCPU_SVE;
+		vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature);
+	}
+}
+
+static void check_supported(void)
+{
+	if (reg_list_sve() && !kvm_check_cap(KVM_CAP_ARM_SVE)) {
+		fprintf(stderr, "SVE not available, skipping tests\n");
+		exit(KSFT_SKIP);
+	}
+}
+
+int main(int ac, char **av)
+{
+	struct kvm_vcpu_init init = { .target = -1, };
+	int new_regs = 0, missing_regs = 0, i;
+	int failed_get = 0, failed_set = 0, failed_reject = 0;
+	bool print_list = false, fixup_core_regs = false;
+	struct kvm_vm *vm;
+	__u64 *vec_regs;
+
+	check_supported();
+
+	for (i = 1; i < ac; ++i) {
+		if (strcmp(av[i], "--core-reg-fixup") == 0)
+			fixup_core_regs = true;
+		else if (strcmp(av[i], "--list") == 0)
+			print_list = true;
+		else
+			fprintf(stderr, "Ignoring unknown option: %s\n", av[i]);
+	}
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	prepare_vcpu_init(&init);
+	aarch64_vcpu_add_default(vm, 0, &init, NULL);
+	finalize_vcpu(vm, 0);
+
+	reg_list = vcpu_get_reg_list(vm, 0);
+
+	if (fixup_core_regs)
+		core_reg_fixup();
+
+	if (print_list) {
+		putchar('\n');
+		for_each_reg(i)
+			print_reg(reg_list->reg[i]);
+		putchar('\n');
+		return 0;
+	}
+
+	/*
+	 * We only test that we can get the register and then write back the
+	 * same value. Some registers may allow other values to be written
+	 * back, but others only allow some bits to be changed, and at least
+	 * for ID registers set will fail if the value does not exactly match
+	 * what was returned by get. If registers that allow other values to
+	 * be written need to have the other values tested, then we should
+	 * create a new set of tests for those in a new independent test
+	 * executable.
+	 */
+	for_each_reg(i) {
+		uint8_t addr[2048 / 8];
+		struct kvm_one_reg reg = {
+			.id = reg_list->reg[i],
+			.addr = (__u64)&addr,
+		};
+		int ret;
+
+		ret = _vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, &reg);
+		if (ret) {
+			puts("Failed to get ");
+			print_reg(reg.id);
+			putchar('\n');
+			++failed_get;
+		}
+
+		/* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */
+		if (find_reg(rejects_set, rejects_set_n, reg.id)) {
+			ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, &reg);
+			if (ret != -1 || errno != EPERM) {
+				printf("Failed to reject (ret=%d, errno=%d) ", ret, errno);
+				print_reg(reg.id);
+				putchar('\n');
+				++failed_reject;
+			}
+			continue;
+		}
+
+		ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, &reg);
+		if (ret) {
+			puts("Failed to set ");
+			print_reg(reg.id);
+			putchar('\n');
+			++failed_set;
+		}
+	}
+
+	if (reg_list_sve()) {
+		blessed_n = base_regs_n + sve_regs_n;
+		vec_regs = sve_regs;
+	} else {
+		blessed_n = base_regs_n + vregs_n;
+		vec_regs = vregs;
+	}
+
+	blessed_reg = calloc(blessed_n, sizeof(__u64));
+	for (i = 0; i < base_regs_n; ++i)
+		blessed_reg[i] = base_regs[i];
+	for (i = 0; i < blessed_n - base_regs_n; ++i)
+		blessed_reg[base_regs_n + i] = vec_regs[i];
+
+	for_each_new_reg(i)
+		++new_regs;
+
+	for_each_missing_reg(i)
+		++missing_regs;
+
+	if (new_regs || missing_regs) {
+		printf("Number blessed registers: %5lld\n", blessed_n);
+		printf("Number registers:         %5lld\n", reg_list->n);
+	}
+
+	if (new_regs) {
+		printf("\nThere are %d new registers.\n"
+		       "Consider adding them to the blessed reg "
+		       "list with the following lines:\n\n", new_regs);
+		for_each_new_reg(i)
+			print_reg(reg_list->reg[i]);
+		putchar('\n');
+	}
+
+	if (missing_regs) {
+		printf("\nThere are %d missing registers.\n"
+		       "The following lines are missing registers:\n\n", missing_regs);
+		for_each_missing_reg(i)
+			print_reg(blessed_reg[i]);
+		putchar('\n');
+	}
+
+	TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject,
+		    "There are %d missing registers; "
+		    "%d registers failed get; %d registers failed set; %d registers failed reject",
+		    missing_regs, failed_get, failed_set, failed_reject);
+
+	return 0;
+}
+
+/*
+ * The current blessed list was primed with the output of kernel version
+ * v4.15 with --core-reg-fixup and then later updated with new registers.
+ */
+static __u64 base_regs[] = {
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[1]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[2]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[3]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[4]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[5]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[6]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[7]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[8]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[9]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[10]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[11]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[12]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[13]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[14]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[15]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[16]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[17]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[18]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[19]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[20]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[21]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[22]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[23]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[24]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[25]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[26]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[27]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[28]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[29]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[30]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.sp),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pc),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pstate),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(sp_el1),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(elr_el1),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[0]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[1]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[2]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[3]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr),
+	KVM_REG_ARM_FW_REG(0),
+	KVM_REG_ARM_FW_REG(1),
+	KVM_REG_ARM_FW_REG(2),
+	ARM64_SYS_REG(3, 3, 14, 3, 1),	/* CNTV_CTL_EL0 */
+	ARM64_SYS_REG(3, 3, 14, 3, 2),	/* CNTV_CVAL_EL0 */
+	ARM64_SYS_REG(3, 3, 14, 0, 2),
+	ARM64_SYS_REG(3, 0, 0, 0, 0),	/* MIDR_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 0, 6),	/* REVIDR_EL1 */
+	ARM64_SYS_REG(3, 1, 0, 0, 1),	/* CLIDR_EL1 */
+	ARM64_SYS_REG(3, 1, 0, 0, 7),	/* AIDR_EL1 */
+	ARM64_SYS_REG(3, 3, 0, 0, 1),	/* CTR_EL0 */
+	ARM64_SYS_REG(2, 0, 0, 0, 4),
+	ARM64_SYS_REG(2, 0, 0, 0, 5),
+	ARM64_SYS_REG(2, 0, 0, 0, 6),
+	ARM64_SYS_REG(2, 0, 0, 0, 7),
+	ARM64_SYS_REG(2, 0, 0, 1, 4),
+	ARM64_SYS_REG(2, 0, 0, 1, 5),
+	ARM64_SYS_REG(2, 0, 0, 1, 6),
+	ARM64_SYS_REG(2, 0, 0, 1, 7),
+	ARM64_SYS_REG(2, 0, 0, 2, 0),	/* MDCCINT_EL1 */
+	ARM64_SYS_REG(2, 0, 0, 2, 2),	/* MDSCR_EL1 */
+	ARM64_SYS_REG(2, 0, 0, 2, 4),
+	ARM64_SYS_REG(2, 0, 0, 2, 5),
+	ARM64_SYS_REG(2, 0, 0, 2, 6),
+	ARM64_SYS_REG(2, 0, 0, 2, 7),
+	ARM64_SYS_REG(2, 0, 0, 3, 4),
+	ARM64_SYS_REG(2, 0, 0, 3, 5),
+	ARM64_SYS_REG(2, 0, 0, 3, 6),
+	ARM64_SYS_REG(2, 0, 0, 3, 7),
+	ARM64_SYS_REG(2, 0, 0, 4, 4),
+	ARM64_SYS_REG(2, 0, 0, 4, 5),
+	ARM64_SYS_REG(2, 0, 0, 4, 6),
+	ARM64_SYS_REG(2, 0, 0, 4, 7),
+	ARM64_SYS_REG(2, 0, 0, 5, 4),
+	ARM64_SYS_REG(2, 0, 0, 5, 5),
+	ARM64_SYS_REG(2, 0, 0, 5, 6),
+	ARM64_SYS_REG(2, 0, 0, 5, 7),
+	ARM64_SYS_REG(2, 0, 0, 6, 4),
+	ARM64_SYS_REG(2, 0, 0, 6, 5),
+	ARM64_SYS_REG(2, 0, 0, 6, 6),
+	ARM64_SYS_REG(2, 0, 0, 6, 7),
+	ARM64_SYS_REG(2, 0, 0, 7, 4),
+	ARM64_SYS_REG(2, 0, 0, 7, 5),
+	ARM64_SYS_REG(2, 0, 0, 7, 6),
+	ARM64_SYS_REG(2, 0, 0, 7, 7),
+	ARM64_SYS_REG(2, 0, 0, 8, 4),
+	ARM64_SYS_REG(2, 0, 0, 8, 5),
+	ARM64_SYS_REG(2, 0, 0, 8, 6),
+	ARM64_SYS_REG(2, 0, 0, 8, 7),
+	ARM64_SYS_REG(2, 0, 0, 9, 4),
+	ARM64_SYS_REG(2, 0, 0, 9, 5),
+	ARM64_SYS_REG(2, 0, 0, 9, 6),
+	ARM64_SYS_REG(2, 0, 0, 9, 7),
+	ARM64_SYS_REG(2, 0, 0, 10, 4),
+	ARM64_SYS_REG(2, 0, 0, 10, 5),
+	ARM64_SYS_REG(2, 0, 0, 10, 6),
+	ARM64_SYS_REG(2, 0, 0, 10, 7),
+	ARM64_SYS_REG(2, 0, 0, 11, 4),
+	ARM64_SYS_REG(2, 0, 0, 11, 5),
+	ARM64_SYS_REG(2, 0, 0, 11, 6),
+	ARM64_SYS_REG(2, 0, 0, 11, 7),
+	ARM64_SYS_REG(2, 0, 0, 12, 4),
+	ARM64_SYS_REG(2, 0, 0, 12, 5),
+	ARM64_SYS_REG(2, 0, 0, 12, 6),
+	ARM64_SYS_REG(2, 0, 0, 12, 7),
+	ARM64_SYS_REG(2, 0, 0, 13, 4),
+	ARM64_SYS_REG(2, 0, 0, 13, 5),
+	ARM64_SYS_REG(2, 0, 0, 13, 6),
+	ARM64_SYS_REG(2, 0, 0, 13, 7),
+	ARM64_SYS_REG(2, 0, 0, 14, 4),
+	ARM64_SYS_REG(2, 0, 0, 14, 5),
+	ARM64_SYS_REG(2, 0, 0, 14, 6),
+	ARM64_SYS_REG(2, 0, 0, 14, 7),
+	ARM64_SYS_REG(2, 0, 0, 15, 4),
+	ARM64_SYS_REG(2, 0, 0, 15, 5),
+	ARM64_SYS_REG(2, 0, 0, 15, 6),
+	ARM64_SYS_REG(2, 0, 0, 15, 7),
+	ARM64_SYS_REG(2, 4, 0, 7, 0),	/* DBGVCR32_EL2 */
+	ARM64_SYS_REG(3, 0, 0, 0, 5),	/* MPIDR_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 0),	/* ID_PFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 1),	/* ID_PFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 2),	/* ID_DFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 3),	/* ID_AFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 4),	/* ID_MMFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 5),	/* ID_MMFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 6),	/* ID_MMFR2_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 1, 7),	/* ID_MMFR3_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 0),	/* ID_ISAR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 1),	/* ID_ISAR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 2),	/* ID_ISAR2_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 3),	/* ID_ISAR3_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 4),	/* ID_ISAR4_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 5),	/* ID_ISAR5_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 6),	/* ID_MMFR4_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 2, 7),	/* ID_ISAR6_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 0),	/* MVFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 1),	/* MVFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 2),	/* MVFR2_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 3),
+	ARM64_SYS_REG(3, 0, 0, 3, 4),	/* ID_PFR2_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 5),	/* ID_DFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 6),	/* ID_MMFR5_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 3, 7),
+	ARM64_SYS_REG(3, 0, 0, 4, 0),	/* ID_AA64PFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 4, 1),	/* ID_AA64PFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 4, 2),
+	ARM64_SYS_REG(3, 0, 0, 4, 3),
+	ARM64_SYS_REG(3, 0, 0, 4, 4),	/* ID_AA64ZFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 4, 5),
+	ARM64_SYS_REG(3, 0, 0, 4, 6),
+	ARM64_SYS_REG(3, 0, 0, 4, 7),
+	ARM64_SYS_REG(3, 0, 0, 5, 0),	/* ID_AA64DFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 5, 1),	/* ID_AA64DFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 5, 2),
+	ARM64_SYS_REG(3, 0, 0, 5, 3),
+	ARM64_SYS_REG(3, 0, 0, 5, 4),	/* ID_AA64AFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 5, 5),	/* ID_AA64AFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 5, 6),
+	ARM64_SYS_REG(3, 0, 0, 5, 7),
+	ARM64_SYS_REG(3, 0, 0, 6, 0),	/* ID_AA64ISAR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 6, 1),	/* ID_AA64ISAR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 6, 2),
+	ARM64_SYS_REG(3, 0, 0, 6, 3),
+	ARM64_SYS_REG(3, 0, 0, 6, 4),
+	ARM64_SYS_REG(3, 0, 0, 6, 5),
+	ARM64_SYS_REG(3, 0, 0, 6, 6),
+	ARM64_SYS_REG(3, 0, 0, 6, 7),
+	ARM64_SYS_REG(3, 0, 0, 7, 0),	/* ID_AA64MMFR0_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 7, 1),	/* ID_AA64MMFR1_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 7, 2),	/* ID_AA64MMFR2_EL1 */
+	ARM64_SYS_REG(3, 0, 0, 7, 3),
+	ARM64_SYS_REG(3, 0, 0, 7, 4),
+	ARM64_SYS_REG(3, 0, 0, 7, 5),
+	ARM64_SYS_REG(3, 0, 0, 7, 6),
+	ARM64_SYS_REG(3, 0, 0, 7, 7),
+	ARM64_SYS_REG(3, 0, 1, 0, 0),	/* SCTLR_EL1 */
+	ARM64_SYS_REG(3, 0, 1, 0, 1),	/* ACTLR_EL1 */
+	ARM64_SYS_REG(3, 0, 1, 0, 2),	/* CPACR_EL1 */
+	ARM64_SYS_REG(3, 0, 2, 0, 0),	/* TTBR0_EL1 */
+	ARM64_SYS_REG(3, 0, 2, 0, 1),	/* TTBR1_EL1 */
+	ARM64_SYS_REG(3, 0, 2, 0, 2),	/* TCR_EL1 */
+	ARM64_SYS_REG(3, 0, 5, 1, 0),	/* AFSR0_EL1 */
+	ARM64_SYS_REG(3, 0, 5, 1, 1),	/* AFSR1_EL1 */
+	ARM64_SYS_REG(3, 0, 5, 2, 0),	/* ESR_EL1 */
+	ARM64_SYS_REG(3, 0, 6, 0, 0),	/* FAR_EL1 */
+	ARM64_SYS_REG(3, 0, 7, 4, 0),	/* PAR_EL1 */
+	ARM64_SYS_REG(3, 0, 9, 14, 1),	/* PMINTENSET_EL1 */
+	ARM64_SYS_REG(3, 0, 9, 14, 2),	/* PMINTENCLR_EL1 */
+	ARM64_SYS_REG(3, 0, 10, 2, 0),	/* MAIR_EL1 */
+	ARM64_SYS_REG(3, 0, 10, 3, 0),	/* AMAIR_EL1 */
+	ARM64_SYS_REG(3, 0, 12, 0, 0),	/* VBAR_EL1 */
+	ARM64_SYS_REG(3, 0, 12, 1, 1),	/* DISR_EL1 */
+	ARM64_SYS_REG(3, 0, 13, 0, 1),	/* CONTEXTIDR_EL1 */
+	ARM64_SYS_REG(3, 0, 13, 0, 4),	/* TPIDR_EL1 */
+	ARM64_SYS_REG(3, 0, 14, 1, 0),	/* CNTKCTL_EL1 */
+	ARM64_SYS_REG(3, 2, 0, 0, 0),	/* CSSELR_EL1 */
+	ARM64_SYS_REG(3, 3, 9, 12, 0),	/* PMCR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 12, 1),	/* PMCNTENSET_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 12, 2),	/* PMCNTENCLR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 12, 3),	/* PMOVSCLR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 12, 4),	/* PMSWINC_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 12, 5),	/* PMSELR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 13, 0),	/* PMCCNTR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 14, 0),	/* PMUSERENR_EL0 */
+	ARM64_SYS_REG(3, 3, 9, 14, 3),	/* PMOVSSET_EL0 */
+	ARM64_SYS_REG(3, 3, 13, 0, 2),	/* TPIDR_EL0 */
+	ARM64_SYS_REG(3, 3, 13, 0, 3),	/* TPIDRRO_EL0 */
+	ARM64_SYS_REG(3, 3, 14, 8, 0),
+	ARM64_SYS_REG(3, 3, 14, 8, 1),
+	ARM64_SYS_REG(3, 3, 14, 8, 2),
+	ARM64_SYS_REG(3, 3, 14, 8, 3),
+	ARM64_SYS_REG(3, 3, 14, 8, 4),
+	ARM64_SYS_REG(3, 3, 14, 8, 5),
+	ARM64_SYS_REG(3, 3, 14, 8, 6),
+	ARM64_SYS_REG(3, 3, 14, 8, 7),
+	ARM64_SYS_REG(3, 3, 14, 9, 0),
+	ARM64_SYS_REG(3, 3, 14, 9, 1),
+	ARM64_SYS_REG(3, 3, 14, 9, 2),
+	ARM64_SYS_REG(3, 3, 14, 9, 3),
+	ARM64_SYS_REG(3, 3, 14, 9, 4),
+	ARM64_SYS_REG(3, 3, 14, 9, 5),
+	ARM64_SYS_REG(3, 3, 14, 9, 6),
+	ARM64_SYS_REG(3, 3, 14, 9, 7),
+	ARM64_SYS_REG(3, 3, 14, 10, 0),
+	ARM64_SYS_REG(3, 3, 14, 10, 1),
+	ARM64_SYS_REG(3, 3, 14, 10, 2),
+	ARM64_SYS_REG(3, 3, 14, 10, 3),
+	ARM64_SYS_REG(3, 3, 14, 10, 4),
+	ARM64_SYS_REG(3, 3, 14, 10, 5),
+	ARM64_SYS_REG(3, 3, 14, 10, 6),
+	ARM64_SYS_REG(3, 3, 14, 10, 7),
+	ARM64_SYS_REG(3, 3, 14, 11, 0),
+	ARM64_SYS_REG(3, 3, 14, 11, 1),
+	ARM64_SYS_REG(3, 3, 14, 11, 2),
+	ARM64_SYS_REG(3, 3, 14, 11, 3),
+	ARM64_SYS_REG(3, 3, 14, 11, 4),
+	ARM64_SYS_REG(3, 3, 14, 11, 5),
+	ARM64_SYS_REG(3, 3, 14, 11, 6),
+	ARM64_SYS_REG(3, 3, 14, 12, 0),
+	ARM64_SYS_REG(3, 3, 14, 12, 1),
+	ARM64_SYS_REG(3, 3, 14, 12, 2),
+	ARM64_SYS_REG(3, 3, 14, 12, 3),
+	ARM64_SYS_REG(3, 3, 14, 12, 4),
+	ARM64_SYS_REG(3, 3, 14, 12, 5),
+	ARM64_SYS_REG(3, 3, 14, 12, 6),
+	ARM64_SYS_REG(3, 3, 14, 12, 7),
+	ARM64_SYS_REG(3, 3, 14, 13, 0),
+	ARM64_SYS_REG(3, 3, 14, 13, 1),
+	ARM64_SYS_REG(3, 3, 14, 13, 2),
+	ARM64_SYS_REG(3, 3, 14, 13, 3),
+	ARM64_SYS_REG(3, 3, 14, 13, 4),
+	ARM64_SYS_REG(3, 3, 14, 13, 5),
+	ARM64_SYS_REG(3, 3, 14, 13, 6),
+	ARM64_SYS_REG(3, 3, 14, 13, 7),
+	ARM64_SYS_REG(3, 3, 14, 14, 0),
+	ARM64_SYS_REG(3, 3, 14, 14, 1),
+	ARM64_SYS_REG(3, 3, 14, 14, 2),
+	ARM64_SYS_REG(3, 3, 14, 14, 3),
+	ARM64_SYS_REG(3, 3, 14, 14, 4),
+	ARM64_SYS_REG(3, 3, 14, 14, 5),
+	ARM64_SYS_REG(3, 3, 14, 14, 6),
+	ARM64_SYS_REG(3, 3, 14, 14, 7),
+	ARM64_SYS_REG(3, 3, 14, 15, 0),
+	ARM64_SYS_REG(3, 3, 14, 15, 1),
+	ARM64_SYS_REG(3, 3, 14, 15, 2),
+	ARM64_SYS_REG(3, 3, 14, 15, 3),
+	ARM64_SYS_REG(3, 3, 14, 15, 4),
+	ARM64_SYS_REG(3, 3, 14, 15, 5),
+	ARM64_SYS_REG(3, 3, 14, 15, 6),
+	ARM64_SYS_REG(3, 3, 14, 15, 7),	/* PMCCFILTR_EL0 */
+	ARM64_SYS_REG(3, 4, 3, 0, 0),	/* DACR32_EL2 */
+	ARM64_SYS_REG(3, 4, 5, 0, 1),	/* IFSR32_EL2 */
+	ARM64_SYS_REG(3, 4, 5, 3, 0),	/* FPEXC32_EL2 */
+	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 0,
+	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 1,
+	KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 2,
+};
+static __u64 base_regs_n = ARRAY_SIZE(base_regs);
+
+static __u64 vregs[] = {
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[1]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[2]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[3]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[4]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[5]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[6]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[7]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[8]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[9]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[10]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[11]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[12]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[13]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[14]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[15]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[16]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[17]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[18]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[19]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[20]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[21]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[22]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[23]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[24]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[25]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[26]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[27]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[28]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[29]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[30]),
+	KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]),
+};
+static __u64 vregs_n = ARRAY_SIZE(vregs);
+
+static __u64 sve_regs[] = {
+	KVM_REG_ARM64_SVE_VLS,
+	KVM_REG_ARM64_SVE_ZREG(0, 0),
+	KVM_REG_ARM64_SVE_ZREG(1, 0),
+	KVM_REG_ARM64_SVE_ZREG(2, 0),
+	KVM_REG_ARM64_SVE_ZREG(3, 0),
+	KVM_REG_ARM64_SVE_ZREG(4, 0),
+	KVM_REG_ARM64_SVE_ZREG(5, 0),
+	KVM_REG_ARM64_SVE_ZREG(6, 0),
+	KVM_REG_ARM64_SVE_ZREG(7, 0),
+	KVM_REG_ARM64_SVE_ZREG(8, 0),
+	KVM_REG_ARM64_SVE_ZREG(9, 0),
+	KVM_REG_ARM64_SVE_ZREG(10, 0),
+	KVM_REG_ARM64_SVE_ZREG(11, 0),
+	KVM_REG_ARM64_SVE_ZREG(12, 0),
+	KVM_REG_ARM64_SVE_ZREG(13, 0),
+	KVM_REG_ARM64_SVE_ZREG(14, 0),
+	KVM_REG_ARM64_SVE_ZREG(15, 0),
+	KVM_REG_ARM64_SVE_ZREG(16, 0),
+	KVM_REG_ARM64_SVE_ZREG(17, 0),
+	KVM_REG_ARM64_SVE_ZREG(18, 0),
+	KVM_REG_ARM64_SVE_ZREG(19, 0),
+	KVM_REG_ARM64_SVE_ZREG(20, 0),
+	KVM_REG_ARM64_SVE_ZREG(21, 0),
+	KVM_REG_ARM64_SVE_ZREG(22, 0),
+	KVM_REG_ARM64_SVE_ZREG(23, 0),
+	KVM_REG_ARM64_SVE_ZREG(24, 0),
+	KVM_REG_ARM64_SVE_ZREG(25, 0),
+	KVM_REG_ARM64_SVE_ZREG(26, 0),
+	KVM_REG_ARM64_SVE_ZREG(27, 0),
+	KVM_REG_ARM64_SVE_ZREG(28, 0),
+	KVM_REG_ARM64_SVE_ZREG(29, 0),
+	KVM_REG_ARM64_SVE_ZREG(30, 0),
+	KVM_REG_ARM64_SVE_ZREG(31, 0),
+	KVM_REG_ARM64_SVE_PREG(0, 0),
+	KVM_REG_ARM64_SVE_PREG(1, 0),
+	KVM_REG_ARM64_SVE_PREG(2, 0),
+	KVM_REG_ARM64_SVE_PREG(3, 0),
+	KVM_REG_ARM64_SVE_PREG(4, 0),
+	KVM_REG_ARM64_SVE_PREG(5, 0),
+	KVM_REG_ARM64_SVE_PREG(6, 0),
+	KVM_REG_ARM64_SVE_PREG(7, 0),
+	KVM_REG_ARM64_SVE_PREG(8, 0),
+	KVM_REG_ARM64_SVE_PREG(9, 0),
+	KVM_REG_ARM64_SVE_PREG(10, 0),
+	KVM_REG_ARM64_SVE_PREG(11, 0),
+	KVM_REG_ARM64_SVE_PREG(12, 0),
+	KVM_REG_ARM64_SVE_PREG(13, 0),
+	KVM_REG_ARM64_SVE_PREG(14, 0),
+	KVM_REG_ARM64_SVE_PREG(15, 0),
+	KVM_REG_ARM64_SVE_FFR(0),
+	ARM64_SYS_REG(3, 0, 1, 2, 0),   /* ZCR_EL1 */
+};
+static __u64 sve_regs_n = ARRAY_SIZE(sve_regs);
+
+static __u64 rejects_set[] = {
+#ifdef REG_LIST_SVE
+	KVM_REG_ARM64_SVE_VLS,
+#endif
+};
+static __u64 rejects_set_n = ARRAY_SIZE(rejects_set);
diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c
deleted file mode 100644
index 11672ec..0000000
--- a/tools/testing/selftests/kvm/clear_dirty_log_test.c
+++ /dev/null
@@ -1,6 +0,0 @@
-#define USE_CLEAR_DIRTY_LOG
-#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
-#define KVM_DIRTY_LOG_INITIALLY_SET         (1 << 1)
-#define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
-		KVM_DIRTY_LOG_INITIALLY_SET)
-#include "dirty_log_test.c"
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 360cd3e..3d96a7b 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -21,20 +21,12 @@
 #include <linux/bitops.h>
 #include <linux/userfaultfd.h>
 
-#include "test_util.h"
-#include "kvm_util.h"
+#include "perf_test_util.h"
 #include "processor.h"
+#include "test_util.h"
 
 #ifdef __NR_userfaultfd
 
-/* The memory slot index demand page */
-#define TEST_MEM_SLOT_INDEX		1
-
-/* Default guest test virtual memory offset */
-#define DEFAULT_GUEST_TEST_MEM		0xc0000000
-
-#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */
-
 #ifdef PRINT_PER_PAGE_UPDATES
 #define PER_PAGE_DEBUG(...) printf(__VA_ARGS__)
 #else
@@ -47,77 +39,17 @@
 #define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
 #endif
 
-#define MAX_VCPUS 512
-
-/*
- * Guest/Host shared variables. Ensure addr_gva2hva() and/or
- * sync_global_to/from_guest() are used when accessing from
- * the host. READ/WRITE_ONCE() should also be used with anything
- * that may change.
- */
-static uint64_t host_page_size;
-static uint64_t guest_page_size;
-
 static char *guest_data_prototype;
 
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-static uint64_t guest_test_phys_mem;
-
-/*
- * Guest virtual memory offset of the testing memory slot.
- * Must not conflict with identity mapped test code.
- */
-static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
-
-struct vcpu_args {
-	uint64_t gva;
-	uint64_t pages;
-
-	/* Only used by the host userspace part of the vCPU thread */
-	int vcpu_id;
-	struct kvm_vm *vm;
-};
-
-static struct vcpu_args vcpu_args[MAX_VCPUS];
-
-/*
- * Continuously write to the first 8 bytes of each page in the demand paging
- * memory region.
- */
-static void guest_code(uint32_t vcpu_id)
-{
-	uint64_t gva;
-	uint64_t pages;
-	int i;
-
-	/* Make sure vCPU args data structure is not corrupt. */
-	GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id);
-
-	gva = vcpu_args[vcpu_id].gva;
-	pages = vcpu_args[vcpu_id].pages;
-
-	for (i = 0; i < pages; i++) {
-		uint64_t addr = gva + (i * guest_page_size);
-
-		addr &= ~(host_page_size - 1);
-		*(uint64_t *)addr = 0x0123456789ABCDEF;
-	}
-
-	GUEST_SYNC(1);
-}
-
 static void *vcpu_worker(void *data)
 {
 	int ret;
-	struct vcpu_args *args = (struct vcpu_args *)data;
-	struct kvm_vm *vm = args->vm;
-	int vcpu_id = args->vcpu_id;
+	struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+	int vcpu_id = vcpu_args->vcpu_id;
+	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
-	struct timespec start, end, ts_diff;
+	struct timespec start;
+	struct timespec ts_diff;
 
 	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
 	run = vcpu_state(vm, vcpu_id);
@@ -133,52 +65,18 @@
 			    exit_reason_str(run->exit_reason));
 	}
 
-	clock_gettime(CLOCK_MONOTONIC, &end);
-	ts_diff = timespec_sub(end, start);
+	ts_diff = timespec_diff_now(start);
 	PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
 		       ts_diff.tv_sec, ts_diff.tv_nsec);
 
 	return NULL;
 }
 
-#define PAGE_SHIFT_4K  12
-#define PTES_PER_4K_PT 512
-
-static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
-				uint64_t vcpu_memory_bytes)
-{
-	struct kvm_vm *vm;
-	uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
-
-	/* Account for a few pages per-vCPU for stacks */
-	pages += DEFAULT_STACK_PGS * vcpus;
-
-	/*
-	 * Reserve twice the ammount of memory needed to map the test region and
-	 * the page table / stacks region, at 4k, for page tables. Do the
-	 * calculation with 4K page size: the smallest of all archs. (e.g., 64K
-	 * page size guest will need even less memory for page tables).
-	 */
-	pages += (2 * pages) / PTES_PER_4K_PT;
-	pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
-		 PTES_PER_4K_PT;
-	pages = vm_adjust_num_guest_pages(mode, pages);
-
-	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
-
-	vm = _vm_create(mode, pages, O_RDWR);
-	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-#ifdef __x86_64__
-	vm_create_irqchip(vm);
-#endif
-	return vm;
-}
-
 static int handle_uffd_page_request(int uffd, uint64_t addr)
 {
 	pid_t tid;
 	struct timespec start;
-	struct timespec end;
+	struct timespec ts_diff;
 	struct uffdio_copy copy;
 	int r;
 
@@ -186,7 +84,7 @@
 
 	copy.src = (uint64_t)guest_data_prototype;
 	copy.dst = addr;
-	copy.len = host_page_size;
+	copy.len = perf_test_args.host_page_size;
 	copy.mode = 0;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
@@ -198,12 +96,12 @@
 		return r;
 	}
 
-	clock_gettime(CLOCK_MONOTONIC, &end);
+	ts_diff = timespec_diff_now(start);
 
 	PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid,
-		       timespec_to_ns(timespec_sub(end, start)));
+		       timespec_to_ns(ts_diff));
 	PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n",
-		       host_page_size, addr, tid);
+		       perf_test_args.host_page_size, addr, tid);
 
 	return 0;
 }
@@ -223,7 +121,8 @@
 	int pipefd = uffd_args->pipefd;
 	useconds_t delay = uffd_args->delay;
 	int64_t pages = 0;
-	struct timespec start, end, ts_diff;
+	struct timespec start;
+	struct timespec ts_diff;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
 	while (!quit_uffd_thread) {
@@ -292,8 +191,7 @@
 		pages++;
 	}
 
-	clock_gettime(CLOCK_MONOTONIC, &end);
-	ts_diff = timespec_sub(end, start);
+	ts_diff = timespec_diff_now(start);
 	PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
 		       pages, ts_diff.tv_sec, ts_diff.tv_nsec,
 		       pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
@@ -351,99 +249,54 @@
 }
 
 static void run_test(enum vm_guest_mode mode, bool use_uffd,
-		     useconds_t uffd_delay, int vcpus,
-		     uint64_t vcpu_memory_bytes)
+		     useconds_t uffd_delay)
 {
 	pthread_t *vcpu_threads;
 	pthread_t *uffd_handler_threads = NULL;
 	struct uffd_handler_args *uffd_args = NULL;
-	struct timespec start, end, ts_diff;
+	struct timespec start;
+	struct timespec ts_diff;
 	int *pipefds = NULL;
 	struct kvm_vm *vm;
-	uint64_t guest_num_pages;
 	int vcpu_id;
 	int r;
 
-	vm = create_vm(mode, vcpus, vcpu_memory_bytes);
+	vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
 
-	guest_page_size = vm_get_page_size(vm);
+	perf_test_args.wr_fract = 1;
 
-	TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0,
-		    "Guest memory size is not guest page size aligned.");
-
-	guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size;
-	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
-
-	/*
-	 * If there should be more memory in the guest test region than there
-	 * can be pages in the guest, it will definitely cause problems.
-	 */
-	TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
-		    "Requested more guest memory than address space allows.\n"
-		    "    guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
-		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
-		    vcpu_memory_bytes);
-
-	host_page_size = getpagesize();
-	TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0,
-		    "Guest memory size is not host page size aligned.");
-
-	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
-			      guest_page_size;
-	guest_test_phys_mem &= ~(host_page_size - 1);
-
-#ifdef __s390x__
-	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
-#endif
-
-	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
-
-	/* Add an extra memory slot for testing demand paging */
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    guest_test_phys_mem,
-				    TEST_MEM_SLOT_INDEX,
-				    guest_num_pages, 0);
-
-	/* Do mapping for the demand paging memory slot */
-	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
-
-	ucall_init(vm, NULL);
-
-	guest_data_prototype = malloc(host_page_size);
+	guest_data_prototype = malloc(perf_test_args.host_page_size);
 	TEST_ASSERT(guest_data_prototype,
 		    "Failed to allocate buffer for guest data pattern");
-	memset(guest_data_prototype, 0xAB, host_page_size);
+	memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size);
 
-	vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads));
+	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
+	add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+
 	if (use_uffd) {
 		uffd_handler_threads =
-			malloc(vcpus * sizeof(*uffd_handler_threads));
+			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
 		TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
 
-		uffd_args = malloc(vcpus * sizeof(*uffd_args));
+		uffd_args = malloc(nr_vcpus * sizeof(*uffd_args));
 		TEST_ASSERT(uffd_args, "Memory allocation failed");
 
-		pipefds = malloc(sizeof(int) * vcpus * 2);
+		pipefds = malloc(sizeof(int) * nr_vcpus * 2);
 		TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
-	}
 
-	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
-		vm_paddr_t vcpu_gpa;
-		void *vcpu_hva;
+		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+			vm_paddr_t vcpu_gpa;
+			void *vcpu_hva;
 
-		vm_vcpu_add_default(vm, vcpu_id, guest_code);
+			vcpu_gpa = guest_test_phys_mem + (vcpu_id * guest_percpu_mem_size);
+			PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+				       vcpu_id, vcpu_gpa, vcpu_gpa + guest_percpu_mem_size);
 
-		vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
-		PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-			       vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+			/* Cache the HVA pointer of the region */
+			vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
 
-		/* Cache the HVA pointer of the region */
-		vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
-
-		if (use_uffd) {
 			/*
 			 * Set up user fault fd to handle demand paging
 			 * requests.
@@ -456,53 +309,41 @@
 						&uffd_handler_threads[vcpu_id],
 						pipefds[vcpu_id * 2],
 						uffd_delay, &uffd_args[vcpu_id],
-						vcpu_hva, vcpu_memory_bytes);
+						vcpu_hva, guest_percpu_mem_size);
 			if (r < 0)
 				exit(-r);
 		}
-
-#ifdef __x86_64__
-		vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
-#endif
-
-		vcpu_args[vcpu_id].vm = vm;
-		vcpu_args[vcpu_id].vcpu_id = vcpu_id;
-		vcpu_args[vcpu_id].gva = guest_test_virt_mem +
-					 (vcpu_id * vcpu_memory_bytes);
-		vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size;
 	}
 
 	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, host_page_size);
-	sync_global_to_guest(vm, guest_page_size);
-	sync_global_to_guest(vm, vcpu_args);
+	sync_global_to_guest(vm, perf_test_args);
 
 	pr_info("Finished creating vCPUs and starting uffd threads\n");
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
 
-	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
 		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &vcpu_args[vcpu_id]);
+			       &perf_test_args.vcpu_args[vcpu_id]);
 	}
 
 	pr_info("Started all vCPUs\n");
 
 	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
 		pthread_join(vcpu_threads[vcpu_id], NULL);
 		PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
 	}
 
-	pr_info("All vCPU threads joined\n");
+	ts_diff = timespec_diff_now(start);
 
-	clock_gettime(CLOCK_MONOTONIC, &end);
+	pr_info("All vCPU threads joined\n");
 
 	if (use_uffd) {
 		char c;
 
 		/* Tell the user fault fd handler threads to quit */
-		for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
 			r = write(pipefds[vcpu_id * 2 + 1], &c, 1);
 			TEST_ASSERT(r == 1, "Unable to write to pipefd");
 
@@ -510,11 +351,11 @@
 		}
 	}
 
-	ts_diff = timespec_sub(end, start);
 	pr_info("Total guest execution time: %ld.%.9lds\n",
 		ts_diff.tv_sec, ts_diff.tv_nsec);
 	pr_info("Overall demand paging rate: %f pgs/sec\n",
-		guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+		perf_test_args.vcpu_args[0].pages * nr_vcpus /
+		((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
 
 	ucall_uninit(vm);
 	kvm_vm_free(vm);
@@ -568,9 +409,8 @@
 
 int main(int argc, char *argv[])
 {
+	int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
 	bool mode_selected = false;
-	uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE;
-	int vcpus = 1;
 	unsigned int mode;
 	int opt, i;
 	bool use_uffd = false;
@@ -619,15 +459,12 @@
 				    "A negative UFFD delay is not supported.");
 			break;
 		case 'b':
-			vcpu_memory_bytes = parse_size(optarg);
+			guest_percpu_mem_size = parse_size(optarg);
 			break;
 		case 'v':
-			vcpus = atoi(optarg);
-			TEST_ASSERT(vcpus > 0,
-				    "Must have a positive number of vCPUs");
-			TEST_ASSERT(vcpus <= MAX_VCPUS,
-				    "This test does not currently support\n"
-				    "more than %d vCPUs.", MAX_VCPUS);
+			nr_vcpus = atoi(optarg);
+			TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
+				    "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
 			break;
 		case 'h':
 		default:
@@ -642,7 +479,7 @@
 		TEST_ASSERT(guest_modes[i].supported,
 			    "Guest mode ID %d (%s) not supported.",
 			    i, vm_guest_mode_string(i));
-		run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes);
+		run_test(i, use_uffd, uffd_delay);
 	}
 
 	return 0;
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
new file mode 100644
index 0000000..85c9b8f
--- /dev/null
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -0,0 +1,376 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM dirty page logging performance test
+ *
+ * Based on dirty_log_test.c
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2020, Google, Inc.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "kvm_util.h"
+#include "perf_test_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
+#define TEST_HOST_LOOP_N		2UL
+
+/* Host variables */
+static bool host_quit;
+static uint64_t iteration;
+static uint64_t vcpu_last_completed_iteration[MAX_VCPUS];
+
+static void *vcpu_worker(void *data)
+{
+	int ret;
+	struct kvm_vm *vm = perf_test_args.vm;
+	uint64_t pages_count = 0;
+	struct kvm_run *run;
+	struct timespec start;
+	struct timespec ts_diff;
+	struct timespec total = (struct timespec){0};
+	struct timespec avg;
+	struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+	int vcpu_id = vcpu_args->vcpu_id;
+
+	vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+	run = vcpu_state(vm, vcpu_id);
+
+	while (!READ_ONCE(host_quit)) {
+		uint64_t current_iteration = READ_ONCE(iteration);
+
+		clock_gettime(CLOCK_MONOTONIC, &start);
+		ret = _vcpu_run(vm, vcpu_id);
+		ts_diff = timespec_diff_now(start);
+
+		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+		TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC,
+			    "Invalid guest sync status: exit_reason=%s\n",
+			    exit_reason_str(run->exit_reason));
+
+		pr_debug("Got sync event from vCPU %d\n", vcpu_id);
+		vcpu_last_completed_iteration[vcpu_id] = current_iteration;
+		pr_debug("vCPU %d updated last completed iteration to %lu\n",
+			 vcpu_id, vcpu_last_completed_iteration[vcpu_id]);
+
+		if (current_iteration) {
+			pages_count += vcpu_args->pages;
+			total = timespec_add(total, ts_diff);
+			pr_debug("vCPU %d iteration %lu dirty memory time: %ld.%.9lds\n",
+				vcpu_id, current_iteration, ts_diff.tv_sec,
+				ts_diff.tv_nsec);
+		} else {
+			pr_debug("vCPU %d iteration %lu populate memory time: %ld.%.9lds\n",
+				vcpu_id, current_iteration, ts_diff.tv_sec,
+				ts_diff.tv_nsec);
+		}
+
+		while (current_iteration == READ_ONCE(iteration) &&
+		       !READ_ONCE(host_quit)) {}
+	}
+
+	avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_id]);
+	pr_debug("\nvCPU %d dirtied 0x%lx pages over %lu iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+		vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id],
+		total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+
+	return NULL;
+}
+
+#ifdef USE_CLEAR_DIRTY_LOG
+static u64 dirty_log_manual_caps;
+#endif
+
+static void run_test(enum vm_guest_mode mode, unsigned long iterations,
+		     uint64_t phys_offset, int wr_fract)
+{
+	pthread_t *vcpu_threads;
+	struct kvm_vm *vm;
+	unsigned long *bmap;
+	uint64_t guest_num_pages;
+	uint64_t host_num_pages;
+	int vcpu_id;
+	struct timespec start;
+	struct timespec ts_diff;
+	struct timespec get_dirty_log_total = (struct timespec){0};
+	struct timespec vcpu_dirty_total = (struct timespec){0};
+	struct timespec avg;
+#ifdef USE_CLEAR_DIRTY_LOG
+	struct kvm_enable_cap cap = {};
+	struct timespec clear_dirty_log_total = (struct timespec){0};
+#endif
+
+	vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+
+	perf_test_args.wr_fract = wr_fract;
+
+	guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
+	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
+	bmap = bitmap_alloc(host_num_pages);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
+	cap.args[0] = dirty_log_manual_caps;
+	vm_enable_cap(vm, &cap);
+#endif
+
+	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
+	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
+
+	add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+
+	sync_global_to_guest(vm, perf_test_args);
+
+	/* Start the iterations */
+	iteration = 0;
+	host_quit = false;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
+			       &perf_test_args.vcpu_args[vcpu_id]);
+	}
+
+	/* Allow the vCPU to populate memory */
+	pr_debug("Starting iteration %lu - Populating\n", iteration);
+	while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration)
+		pr_debug("Waiting for vcpu_last_completed_iteration == %lu\n",
+			iteration);
+
+	ts_diff = timespec_diff_now(start);
+	pr_info("Populate memory time: %ld.%.9lds\n",
+		ts_diff.tv_sec, ts_diff.tv_nsec);
+
+	/* Enable dirty logging */
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX,
+				KVM_MEM_LOG_DIRTY_PAGES);
+	ts_diff = timespec_diff_now(start);
+	pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
+		ts_diff.tv_sec, ts_diff.tv_nsec);
+
+	while (iteration < iterations) {
+		/*
+		 * Incrementing the iteration number will start the vCPUs
+		 * dirtying memory again.
+		 */
+		clock_gettime(CLOCK_MONOTONIC, &start);
+		iteration++;
+
+		pr_debug("Starting iteration %lu\n", iteration);
+		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+			while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration)
+				pr_debug("Waiting for vCPU %d vcpu_last_completed_iteration == %lu\n",
+					 vcpu_id, iteration);
+		}
+
+		ts_diff = timespec_diff_now(start);
+		vcpu_dirty_total = timespec_add(vcpu_dirty_total, ts_diff);
+		pr_info("Iteration %lu dirty memory time: %ld.%.9lds\n",
+			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+
+		clock_gettime(CLOCK_MONOTONIC, &start);
+		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+
+		ts_diff = timespec_diff_now(start);
+		get_dirty_log_total = timespec_add(get_dirty_log_total,
+						   ts_diff);
+		pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n",
+			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+		clock_gettime(CLOCK_MONOTONIC, &start);
+		kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
+				       host_num_pages);
+
+		ts_diff = timespec_diff_now(start);
+		clear_dirty_log_total = timespec_add(clear_dirty_log_total,
+						     ts_diff);
+		pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n",
+			iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+#endif
+	}
+
+	/* Tell the vcpu thread to quit */
+	host_quit = true;
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
+		pthread_join(vcpu_threads[vcpu_id], NULL);
+
+	/* Disable dirty logging */
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0);
+	ts_diff = timespec_diff_now(start);
+	pr_info("Disabling dirty logging time: %ld.%.9lds\n",
+		ts_diff.tv_sec, ts_diff.tv_nsec);
+
+	avg = timespec_div(get_dirty_log_total, iterations);
+	pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+		iterations, get_dirty_log_total.tv_sec,
+		get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+	avg = timespec_div(clear_dirty_log_total, iterations);
+	pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+		iterations, clear_dirty_log_total.tv_sec,
+		clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+#endif
+
+	free(bmap);
+	free(vcpu_threads);
+	ucall_uninit(vm);
+	kvm_vm_free(vm);
+}
+
+struct guest_mode {
+	bool supported;
+	bool enabled;
+};
+static struct guest_mode guest_modes[NUM_VM_MODES];
+
+#define guest_mode_init(mode, supported, enabled) ({ \
+	guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+})
+
+static void help(char *name)
+{
+	int i;
+
+	puts("");
+	printf("usage: %s [-h] [-i iterations] [-p offset] "
+	       "[-m mode] [-b vcpu bytes] [-v vcpus]\n", name);
+	puts("");
+	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+	       TEST_HOST_LOOP_N);
+	printf(" -p: specify guest physical test memory offset\n"
+	       "     Warning: a low offset can conflict with the loaded test code.\n");
+	printf(" -m: specify the guest mode ID to test "
+	       "(default: test all supported modes)\n"
+	       "     This option may be used multiple times.\n"
+	       "     Guest mode IDs:\n");
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		printf("         %d:    %s%s\n", i, vm_guest_mode_string(i),
+		       guest_modes[i].supported ? " (supported)" : "");
+	}
+	printf(" -b: specify the size of the memory region which should be\n"
+	       "     dirtied by each vCPU. e.g. 10M or 3G.\n"
+	       "     (default: 1G)\n");
+	printf(" -f: specify the fraction of pages which should be written to\n"
+	       "     as opposed to simply read, in the form\n"
+	       "     1/<fraction of pages to write>.\n"
+	       "     (default: 1 i.e. all pages are written to.)\n");
+	printf(" -v: specify the number of vCPUs to run.\n");
+	puts("");
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	unsigned long iterations = TEST_HOST_LOOP_N;
+	bool mode_selected = false;
+	uint64_t phys_offset = 0;
+	unsigned int mode;
+	int opt, i;
+	int wr_fract = 1;
+
+#ifdef USE_CLEAR_DIRTY_LOG
+	dirty_log_manual_caps =
+		kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+	if (!dirty_log_manual_caps) {
+		print_skip("KVM_CLEAR_DIRTY_LOG not available");
+		exit(KSFT_SKIP);
+	}
+	dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+				  KVM_DIRTY_LOG_INITIALLY_SET);
+#endif
+
+#ifdef __x86_64__
+	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
+#endif
+#ifdef __aarch64__
+	guest_mode_init(VM_MODE_P40V48_4K, true, true);
+	guest_mode_init(VM_MODE_P40V48_64K, true, true);
+
+	{
+		unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+
+		if (limit >= 52)
+			guest_mode_init(VM_MODE_P52V48_64K, true, true);
+		if (limit >= 48) {
+			guest_mode_init(VM_MODE_P48V48_4K, true, true);
+			guest_mode_init(VM_MODE_P48V48_64K, true, true);
+		}
+	}
+#endif
+#ifdef __s390x__
+	guest_mode_init(VM_MODE_P40V48_4K, true, true);
+#endif
+
+	while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) {
+		switch (opt) {
+		case 'i':
+			iterations = strtol(optarg, NULL, 10);
+			break;
+		case 'p':
+			phys_offset = strtoull(optarg, NULL, 0);
+			break;
+		case 'm':
+			if (!mode_selected) {
+				for (i = 0; i < NUM_VM_MODES; ++i)
+					guest_modes[i].enabled = false;
+				mode_selected = true;
+			}
+			mode = strtoul(optarg, NULL, 10);
+			TEST_ASSERT(mode < NUM_VM_MODES,
+				    "Guest mode ID %d too big", mode);
+			guest_modes[mode].enabled = true;
+			break;
+		case 'b':
+			guest_percpu_mem_size = parse_size(optarg);
+			break;
+		case 'f':
+			wr_fract = atoi(optarg);
+			TEST_ASSERT(wr_fract >= 1,
+				    "Write fraction cannot be less than one");
+			break;
+		case 'v':
+			nr_vcpus = atoi(optarg);
+			TEST_ASSERT(nr_vcpus > 0,
+				    "Must have a positive number of vCPUs");
+			TEST_ASSERT(nr_vcpus <= MAX_VCPUS,
+				    "This test does not currently support\n"
+				    "more than %d vCPUs.", MAX_VCPUS);
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
+
+	TEST_ASSERT(iterations >= 2, "The test should have at least two iterations");
+
+	pr_info("Test iterations: %"PRIu64"\n",	iterations);
+
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		if (!guest_modes[i].enabled)
+			continue;
+		TEST_ASSERT(guest_modes[i].supported,
+			    "Guest mode ID %d (%s) not supported.",
+			    i, vm_guest_mode_string(i));
+		run_test(i, iterations, phys_offset, wr_fract);
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 752ec15..54da9cc2 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -128,6 +128,78 @@
 static uint64_t host_clear_count;
 static uint64_t host_track_next_count;
 
+enum log_mode_t {
+	/* Only use KVM_GET_DIRTY_LOG for logging */
+	LOG_MODE_DIRTY_LOG = 0,
+
+	/* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */
+	LOG_MODE_CLEAR_LOG = 1,
+
+	LOG_MODE_NUM,
+
+	/* Run all supported modes */
+	LOG_MODE_ALL = LOG_MODE_NUM,
+};
+
+/* Mode of logging to test.  Default is to run all supported modes */
+static enum log_mode_t host_log_mode_option = LOG_MODE_ALL;
+/* Logging mode for current run */
+static enum log_mode_t host_log_mode;
+
+static bool clear_log_supported(void)
+{
+	return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+}
+
+static void clear_log_create_vm_done(struct kvm_vm *vm)
+{
+	struct kvm_enable_cap cap = {};
+	u64 manual_caps;
+
+	manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+	TEST_ASSERT(manual_caps, "MANUAL_CAPS is zero!");
+	manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+			KVM_DIRTY_LOG_INITIALLY_SET);
+	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
+	cap.args[0] = manual_caps;
+	vm_enable_cap(vm, &cap);
+}
+
+static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					  void *bitmap, uint32_t num_pages)
+{
+	kvm_vm_get_dirty_log(vm, slot, bitmap);
+}
+
+static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					  void *bitmap, uint32_t num_pages)
+{
+	kvm_vm_get_dirty_log(vm, slot, bitmap);
+	kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
+}
+
+struct log_mode {
+	const char *name;
+	/* Return true if this mode is supported, otherwise false */
+	bool (*supported)(void);
+	/* Hook when the vm creation is done (before vcpu creation) */
+	void (*create_vm_done)(struct kvm_vm *vm);
+	/* Hook to collect the dirty pages into the bitmap provided */
+	void (*collect_dirty_pages) (struct kvm_vm *vm, int slot,
+				     void *bitmap, uint32_t num_pages);
+} log_modes[LOG_MODE_NUM] = {
+	{
+		.name = "dirty-log",
+		.collect_dirty_pages = dirty_log_collect_dirty_pages,
+	},
+	{
+		.name = "clear-log",
+		.supported = clear_log_supported,
+		.create_vm_done = clear_log_create_vm_done,
+		.collect_dirty_pages = clear_log_collect_dirty_pages,
+	},
+};
+
 /*
  * We use this bitmap to track some pages that should have its dirty
  * bit set in the _next_ iteration.  For example, if we detected the
@@ -137,6 +209,44 @@
  */
 static unsigned long *host_bmap_track;
 
+static void log_modes_dump(void)
+{
+	int i;
+
+	printf("all");
+	for (i = 0; i < LOG_MODE_NUM; i++)
+		printf(", %s", log_modes[i].name);
+	printf("\n");
+}
+
+static bool log_mode_supported(void)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->supported)
+		return mode->supported();
+
+	return true;
+}
+
+static void log_mode_create_vm_done(struct kvm_vm *vm)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->create_vm_done)
+		mode->create_vm_done(vm);
+}
+
+static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					 void *bitmap, uint32_t num_pages)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	TEST_ASSERT(mode->collect_dirty_pages != NULL,
+		    "collect_dirty_pages() is required for any log mode!");
+	mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
+}
+
 static void generate_random_array(uint64_t *guest_array, uint64_t size)
 {
 	uint64_t i;
@@ -195,7 +305,7 @@
 				    page);
 		}
 
-		if (test_bit_le(page, bmap)) {
+		if (test_and_clear_bit_le(page, bmap)) {
 			host_dirty_count++;
 			/*
 			 * If the bit is set, the value written onto
@@ -252,11 +362,12 @@
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+	vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
 	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
 #ifdef __x86_64__
 	vm_create_irqchip(vm);
 #endif
+	log_mode_create_vm_done(vm);
 	vm_vcpu_add_default(vm, vcpuid, guest_code);
 	return vm;
 }
@@ -264,10 +375,6 @@
 #define DIRTY_MEM_BITS 30 /* 1G */
 #define PAGE_SHIFT_4K  12
 
-#ifdef USE_CLEAR_DIRTY_LOG
-static u64 dirty_log_manual_caps;
-#endif
-
 static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		     unsigned long interval, uint64_t phys_offset)
 {
@@ -275,6 +382,12 @@
 	struct kvm_vm *vm;
 	unsigned long *bmap;
 
+	if (!log_mode_supported()) {
+		print_skip("Log mode '%s' not supported",
+			   log_modes[host_log_mode].name);
+		return;
+	}
+
 	/*
 	 * We reserve page table for 2 times of extra dirty mem which
 	 * will definitely cover the original (1G+) test range.  Here
@@ -317,14 +430,6 @@
 	bmap = bitmap_alloc(host_num_pages);
 	host_bmap_track = bitmap_alloc(host_num_pages);
 
-#ifdef USE_CLEAR_DIRTY_LOG
-	struct kvm_enable_cap cap = {};
-
-	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
-	cap.args[0] = dirty_log_manual_caps;
-	vm_enable_cap(vm, &cap);
-#endif
-
 	/* Add an extra memory slot for testing dirty logging */
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
 				    guest_test_phys_mem,
@@ -362,11 +467,8 @@
 	while (iteration < iterations) {
 		/* Give the vcpu thread some time to dirty some pages */
 		usleep(interval * 1000);
-		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
-#ifdef USE_CLEAR_DIRTY_LOG
-		kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
-				       host_num_pages);
-#endif
+		log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
+					     bmap, host_num_pages);
 		vm_dirty_log_verify(mode, bmap);
 		iteration++;
 		sync_global_to_guest(vm, iteration);
@@ -410,6 +512,9 @@
 	       TEST_HOST_LOOP_INTERVAL);
 	printf(" -p: specify guest physical test memory offset\n"
 	       "     Warning: a low offset can conflict with the loaded test code.\n");
+	printf(" -M: specify the host logging mode "
+	       "(default: run all log modes).  Supported modes: \n\t");
+	log_modes_dump();
 	printf(" -m: specify the guest mode ID to test "
 	       "(default: test all supported modes)\n"
 	       "     This option may be used multiple times.\n"
@@ -429,18 +534,7 @@
 	bool mode_selected = false;
 	uint64_t phys_offset = 0;
 	unsigned int mode;
-	int opt, i;
-
-#ifdef USE_CLEAR_DIRTY_LOG
-	dirty_log_manual_caps =
-		kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
-	if (!dirty_log_manual_caps) {
-		print_skip("KVM_CLEAR_DIRTY_LOG not available");
-		exit(KSFT_SKIP);
-	}
-	dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
-				  KVM_DIRTY_LOG_INITIALLY_SET);
-#endif
+	int opt, i, j;
 
 #ifdef __x86_64__
 	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
@@ -464,7 +558,7 @@
 	guest_mode_init(VM_MODE_P40V48_4K, true, true);
 #endif
 
-	while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) {
+	while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) {
 		switch (opt) {
 		case 'i':
 			iterations = strtol(optarg, NULL, 10);
@@ -486,6 +580,26 @@
 				    "Guest mode ID %d too big", mode);
 			guest_modes[mode].enabled = true;
 			break;
+		case 'M':
+			if (!strcmp(optarg, "all")) {
+				host_log_mode_option = LOG_MODE_ALL;
+				break;
+			}
+			for (i = 0; i < LOG_MODE_NUM; i++) {
+				if (!strcmp(optarg, log_modes[i].name)) {
+					pr_info("Setting log mode to: '%s'\n",
+						optarg);
+					host_log_mode_option = i;
+					break;
+				}
+			}
+			if (i == LOG_MODE_NUM) {
+				printf("Log mode '%s' invalid. Please choose "
+				       "from: ", optarg);
+				log_modes_dump();
+				exit(1);
+			}
+			break;
 		case 'h':
 		default:
 			help(argv[0]);
@@ -507,7 +621,18 @@
 		TEST_ASSERT(guest_modes[i].supported,
 			    "Guest mode ID %d (%s) not supported.",
 			    i, vm_guest_mode_string(i));
-		run_test(i, iterations, interval, phys_offset);
+		if (host_log_mode_option == LOG_MODE_ALL) {
+			/* Run each log mode */
+			for (j = 0; j < LOG_MODE_NUM; j++) {
+				pr_info("Testing Log Mode '%s'\n",
+					log_modes[j].name);
+				host_log_mode = j;
+				run_test(i, iterations, interval, phys_offset);
+			}
+		} else {
+			host_log_mode = host_log_mode_option;
+			run_test(i, iterations, interval, phys_offset);
+		}
 	}
 
 	return 0;
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 919e161..7d29aa7 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -63,9 +63,11 @@
 
 int kvm_check_cap(long cap);
 int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+		    struct kvm_enable_cap *cap);
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
 
 struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
-struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
 void kvm_vm_free(struct kvm_vm *vmp);
 void kvm_vm_restart(struct kvm_vm *vmp, int perm);
 void kvm_vm_release(struct kvm_vm *vmp);
@@ -149,6 +151,7 @@
 			  struct kvm_guest_debug *debug);
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		       struct kvm_mp_state *mp_state);
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
 void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
 
@@ -294,6 +297,8 @@
 	memcpy(&(g), _p, sizeof(g));				\
 })
 
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid);
+
 /* Common ucalls */
 enum {
 	UCALL_NONE,
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
new file mode 100644
index 0000000..2618052
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * tools/testing/selftests/kvm/include/perf_test_util.h
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
+#define SELFTEST_KVM_PERF_TEST_UTIL_H
+
+#include "kvm_util.h"
+#include "processor.h"
+
+#define MAX_VCPUS 512
+
+#define PAGE_SHIFT_4K  12
+#define PTES_PER_4K_PT 512
+
+#define TEST_MEM_SLOT_INDEX		1
+
+/* Default guest test virtual memory offset */
+#define DEFAULT_GUEST_TEST_MEM		0xc0000000
+
+#define DEFAULT_PER_VCPU_MEM_SIZE	(1 << 30) /* 1G */
+
+/*
+ * Guest physical memory offset of the testing memory slot.
+ * This will be set to the topmost valid physical address minus
+ * the test memory size.
+ */
+static uint64_t guest_test_phys_mem;
+
+/*
+ * Guest virtual memory offset of the testing memory slot.
+ * Must not conflict with identity mapped test code.
+ */
+static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
+static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+
+/* Number of VCPUs for the test */
+static int nr_vcpus = 1;
+
+struct vcpu_args {
+	uint64_t gva;
+	uint64_t pages;
+
+	/* Only used by the host userspace part of the vCPU thread */
+	int vcpu_id;
+};
+
+struct perf_test_args {
+	struct kvm_vm *vm;
+	uint64_t host_page_size;
+	uint64_t guest_page_size;
+	int wr_fract;
+
+	struct vcpu_args vcpu_args[MAX_VCPUS];
+};
+
+static struct perf_test_args perf_test_args;
+
+/*
+ * Continuously write to the first 8 bytes of each page in the
+ * specified region.
+ */
+static void guest_code(uint32_t vcpu_id)
+{
+	struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+	uint64_t gva;
+	uint64_t pages;
+	int i;
+
+	/* Make sure vCPU args data structure is not corrupt. */
+	GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id);
+
+	gva = vcpu_args->gva;
+	pages = vcpu_args->pages;
+
+	while (true) {
+		for (i = 0; i < pages; i++) {
+			uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+
+			if (i % perf_test_args.wr_fract == 0)
+				*(uint64_t *)addr = 0x0123456789ABCDEF;
+			else
+				READ_ONCE(*(uint64_t *)addr);
+		}
+
+		GUEST_SYNC(1);
+	}
+}
+
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
+				uint64_t vcpu_memory_bytes)
+{
+	struct kvm_vm *vm;
+	uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
+	uint64_t guest_num_pages;
+
+	/* Account for a few pages per-vCPU for stacks */
+	pages += DEFAULT_STACK_PGS * vcpus;
+
+	/*
+	 * Reserve twice the ammount of memory needed to map the test region and
+	 * the page table / stacks region, at 4k, for page tables. Do the
+	 * calculation with 4K page size: the smallest of all archs. (e.g., 64K
+	 * page size guest will need even less memory for page tables).
+	 */
+	pages += (2 * pages) / PTES_PER_4K_PT;
+	pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
+		 PTES_PER_4K_PT;
+	pages = vm_adjust_num_guest_pages(mode, pages);
+
+	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
+	vm = vm_create(mode, pages, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+
+	perf_test_args.vm = vm;
+	perf_test_args.guest_page_size = vm_get_page_size(vm);
+	perf_test_args.host_page_size = getpagesize();
+
+	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+		    "Guest memory size is not guest page size aligned.");
+
+	guest_num_pages = (vcpus * vcpu_memory_bytes) /
+			  perf_test_args.guest_page_size;
+	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+
+	/*
+	 * If there should be more memory in the guest test region than there
+	 * can be pages in the guest, it will definitely cause problems.
+	 */
+	TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
+		    "Requested more guest memory than address space allows.\n"
+		    "    guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
+		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
+		    vcpu_memory_bytes);
+
+	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+		    "Guest memory size is not host page size aligned.");
+
+	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
+			      perf_test_args.guest_page_size;
+	guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+
+#ifdef __s390x__
+	/* Align to 1M (segment size) */
+	guest_test_phys_mem &= ~((1 << 20) - 1);
+#endif
+
+	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+
+	/* Add an extra memory slot for testing */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    guest_test_phys_mem,
+				    TEST_MEM_SLOT_INDEX,
+				    guest_num_pages, 0);
+
+	/* Do mapping for the demand paging memory slot */
+	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
+
+	ucall_init(vm, NULL);
+
+	return vm;
+}
+
+static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes)
+{
+	vm_paddr_t vcpu_gpa;
+	struct vcpu_args *vcpu_args;
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+
+		vm_vcpu_add_default(vm, vcpu_id, guest_code);
+
+#ifdef __x86_64__
+		vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
+#endif
+
+		vcpu_args->vcpu_id = vcpu_id;
+		vcpu_args->gva = guest_test_virt_mem +
+				 (vcpu_id * vcpu_memory_bytes);
+		vcpu_args->pages = vcpu_memory_bytes /
+				   perf_test_args.guest_page_size;
+
+		vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
+		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+			 vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+	}
+}
+
+#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 5eb01bf..ffffa56 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -64,5 +64,7 @@
 struct timespec timespec_add_ns(struct timespec ts, int64_t ns);
 struct timespec timespec_add(struct timespec ts1, struct timespec ts2);
 struct timespec timespec_sub(struct timespec ts1, struct timespec ts2);
+struct timespec timespec_diff_now(struct timespec start);
+struct timespec timespec_div(struct timespec ts, int divisor);
 
 #endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 82b7fe1..8e61340 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -36,6 +36,8 @@
 #define X86_CR4_SMAP		(1ul << 21)
 #define X86_CR4_PKE		(1ul << 22)
 
+#define UNEXPECTED_VECTOR_PORT 0xfff0u
+
 /* General Registers in 64-Bit Mode */
 struct gpr64_regs {
 	u64 rax;
@@ -59,7 +61,7 @@
 struct desc64 {
 	uint16_t limit0;
 	uint16_t base0;
-	unsigned base1:8, s:1, type:4, dpl:2, p:1;
+	unsigned base1:8, type:4, s:1, dpl:2, p:1;
 	unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8;
 	uint32_t base3;
 	uint32_t zero1;
@@ -239,6 +241,11 @@
 	return idt;
 }
 
+static inline void outl(uint16_t port, uint32_t value)
+{
+	__asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value));
+}
+
 #define SET_XMM(__var, __xmm) \
 	asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
 
@@ -338,6 +345,35 @@
 uint32_t kvm_get_cpuid_max_extended(void);
 void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
 
+struct ex_regs {
+	uint64_t rax, rcx, rdx, rbx;
+	uint64_t rbp, rsi, rdi;
+	uint64_t r8, r9, r10, r11;
+	uint64_t r12, r13, r14, r15;
+	uint64_t vector;
+	uint64_t error_code;
+	uint64_t rip;
+	uint64_t cs;
+	uint64_t rflags;
+};
+
+void vm_init_descriptor_tables(struct kvm_vm *vm);
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
+void vm_handle_exception(struct kvm_vm *vm, int vector,
+			void (*handler)(struct ex_regs *));
+
+/*
+ * set_cpuid() - overwrites a matching cpuid entry with the provided value.
+ *		 matches based on ent->function && ent->index. returns true
+ *		 if a match was found and successfully overwritten.
+ * @cpuid: the kvm cpuid list to modify.
+ * @ent: cpuid entry to insert
+ */
+bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent);
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+		       uint64_t a3);
+
 /*
  * Basic CPU control in CR0
  */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 2afa661..d6c32c3 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -350,3 +350,7 @@
 
 	va_end(ap);
 }
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index c8e0ec2..2f37b90 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -94,6 +94,9 @@
 	struct kvm_run *run = vcpu_state(vm, vcpu_id);
 	struct ucall ucall = {};
 
+	if (uc)
+		memset(uc, 0, sizeof(*uc));
+
 	if (run->exit_reason == KVM_EXIT_MMIO &&
 	    run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) {
 		vm_vaddr_t gva;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 3327ceb..126c672 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -86,6 +86,34 @@
 	return ret;
 }
 
+/* VCPU Enable Capability
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpu_id - VCPU
+ *   cap - Capability
+ *
+ * Output Args: None
+ *
+ * Return: On success, 0. On failure a TEST_ASSERT failure is produced.
+ *
+ * Enables a capability (KVM_CAP_*) on the VCPU.
+ */
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+		    struct kvm_enable_cap *cap)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpu_id);
+	int r;
+
+	TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id);
+
+	r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap);
+	TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n"
+			"  rc: %i, errno: %i", r, errno);
+
+	return r;
+}
+
 static void vm_open(struct kvm_vm *vm, int perm)
 {
 	vm->kvm_fd = open(KVM_DEV_PATH, perm);
@@ -152,7 +180,7 @@
  * descriptor to control the created VM is created with the permissions
  * given by perm (e.g. O_RDWR).
  */
-struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
+struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 {
 	struct kvm_vm *vm;
 
@@ -243,11 +271,6 @@
 	return vm;
 }
 
-struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
-{
-	return _vm_create(mode, phy_pages, perm);
-}
-
 /*
  * VM Restart
  *
@@ -1204,6 +1227,9 @@
 	do {
 		rc = ioctl(vcpu->fd, KVM_RUN, NULL);
 	} while (rc == -1 && errno == EINTR);
+
+	assert_on_unhandled_exception(vm, vcpuid);
+
 	return rc;
 }
 
@@ -1261,6 +1287,35 @@
 }
 
 /*
+ * VM VCPU Get Reg List
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *
+ * Output Args:
+ *   None
+ *
+ * Return:
+ *   A pointer to an allocated struct kvm_reg_list
+ *
+ * Get the list of guest registers which are supported for
+ * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls
+ */
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list;
+	int ret;
+
+	ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, &reg_list_n);
+	TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0");
+	reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64));
+	reg_list->n = reg_list_n.n;
+	vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list);
+	return reg_list;
+}
+
+/*
  * VM VCPU Regs Get
  *
  * Input Args:
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 2ef44652..f07d383 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -50,6 +50,8 @@
 	vm_paddr_t pgd;
 	vm_vaddr_t gdt;
 	vm_vaddr_t tss;
+	vm_vaddr_t idt;
+	vm_vaddr_t handlers;
 };
 
 struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index a88c5d6..7349bb2 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -241,3 +241,7 @@
 	fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n",
 		indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr);
 }
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}
diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c
index fd589dc..9d3b0f1 100644
--- a/tools/testing/selftests/kvm/lib/s390x/ucall.c
+++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c
@@ -38,6 +38,9 @@
 	struct kvm_run *run = vcpu_state(vm, vcpu_id);
 	struct ucall ucall = {};
 
+	if (uc)
+		memset(uc, 0, sizeof(*uc));
+
 	if (run->exit_reason == KVM_EXIT_S390_SIEIC &&
 	    run->s390_sieic.icptcode == 4 &&
 	    (run->s390_sieic.ipa >> 8) == 0x83 &&    /* 0x83 means DIAGNOSE */
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 689e97c..8e04c0b 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -4,10 +4,13 @@
  *
  * Copyright (C) 2020, Google LLC.
  */
-#include <stdlib.h>
+
+#include <assert.h>
 #include <ctype.h>
 #include <limits.h>
-#include <assert.h>
+#include <stdlib.h>
+#include <time.h>
+
 #include "test_util.h"
 
 /*
@@ -81,6 +84,21 @@
 	return timespec_add_ns((struct timespec){0}, ns1 - ns2);
 }
 
+struct timespec timespec_diff_now(struct timespec start)
+{
+	struct timespec end;
+
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	return timespec_sub(end, start);
+}
+
+struct timespec timespec_div(struct timespec ts, int divisor)
+{
+	int64_t ns = timespec_to_ns(ts) / divisor;
+
+	return timespec_add_ns((struct timespec){0}, ns);
+}
+
 void print_skip(const char *fmt, ...)
 {
 	va_list ap;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
new file mode 100644
index 0000000..aaf7bc7
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
@@ -0,0 +1,81 @@
+handle_exception:
+	push %r15
+	push %r14
+	push %r13
+	push %r12
+	push %r11
+	push %r10
+	push %r9
+	push %r8
+
+	push %rdi
+	push %rsi
+	push %rbp
+	push %rbx
+	push %rdx
+	push %rcx
+	push %rax
+	mov %rsp, %rdi
+
+	call route_exception
+
+	pop %rax
+	pop %rcx
+	pop %rdx
+	pop %rbx
+	pop %rbp
+	pop %rsi
+	pop %rdi
+	pop %r8
+	pop %r9
+	pop %r10
+	pop %r11
+	pop %r12
+	pop %r13
+	pop %r14
+	pop %r15
+
+	/* Discard vector and error code. */
+	add $16, %rsp
+	iretq
+
+/*
+ * Build the handle_exception wrappers which push the vector/error code on the
+ * stack and an array of pointers to those wrappers.
+ */
+.pushsection .rodata
+.globl idt_handlers
+idt_handlers:
+.popsection
+
+.macro HANDLERS has_error from to
+	vector = \from
+	.rept \to - \from + 1
+	.align 8
+
+	/* Fetch current address and append it to idt_handlers. */
+	current_handler = .
+.pushsection .rodata
+.quad current_handler
+.popsection
+
+	.if ! \has_error
+	pushq $0
+	.endif
+	pushq $vector
+	jmp handle_exception
+	vector = vector + 1
+	.endr
+.endm
+
+.global idt_handler_code
+idt_handler_code:
+	HANDLERS has_error=0 from=0  to=7
+	HANDLERS has_error=1 from=8  to=8
+	HANDLERS has_error=0 from=9  to=9
+	HANDLERS has_error=1 from=10 to=14
+	HANDLERS has_error=0 from=15 to=16
+	HANDLERS has_error=1 from=17 to=17
+	HANDLERS has_error=0 from=18 to=255
+
+.section        .note.GNU-stack, "", %progbits
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index f6eb34e..d10c5c0 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -12,9 +12,18 @@
 #include "../kvm_util_internal.h"
 #include "processor.h"
 
+#ifndef NUM_INTERRUPTS
+#define NUM_INTERRUPTS 256
+#endif
+
+#define DEFAULT_CODE_SELECTOR 0x8
+#define DEFAULT_DATA_SELECTOR 0x10
+
 /* Minimum physical address used for virtual translation tables. */
 #define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
 
+vm_vaddr_t exception_handlers;
+
 /* Virtual translation table structure declarations */
 struct pageMapL4Entry {
 	uint64_t present:1;
@@ -392,11 +401,12 @@
 	desc->limit0 = segp->limit & 0xFFFF;
 	desc->base0 = segp->base & 0xFFFF;
 	desc->base1 = segp->base >> 16;
-	desc->s = segp->s;
 	desc->type = segp->type;
+	desc->s = segp->s;
 	desc->dpl = segp->dpl;
 	desc->p = segp->present;
 	desc->limit1 = segp->limit >> 16;
+	desc->avl = segp->avl;
 	desc->l = segp->l;
 	desc->db = segp->db;
 	desc->g = segp->g;
@@ -556,9 +566,9 @@
 		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
 
 		kvm_seg_set_unusable(&sregs.ldt);
-		kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs);
-		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds);
-		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es);
+		kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs);
+		kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds);
+		kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es);
 		kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot);
 		break;
 
@@ -1118,3 +1128,131 @@
 		*va_bits = (entry->eax >> 8) & 0xff;
 	}
 }
+
+struct idt_entry {
+	uint16_t offset0;
+	uint16_t selector;
+	uint16_t ist : 3;
+	uint16_t : 5;
+	uint16_t type : 4;
+	uint16_t : 1;
+	uint16_t dpl : 2;
+	uint16_t p : 1;
+	uint16_t offset1;
+	uint32_t offset2; uint32_t reserved;
+};
+
+static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
+			  int dpl, unsigned short selector)
+{
+	struct idt_entry *base =
+		(struct idt_entry *)addr_gva2hva(vm, vm->idt);
+	struct idt_entry *e = &base[vector];
+
+	memset(e, 0, sizeof(*e));
+	e->offset0 = addr;
+	e->selector = selector;
+	e->ist = 0;
+	e->type = 14;
+	e->dpl = dpl;
+	e->p = 1;
+	e->offset1 = addr >> 16;
+	e->offset2 = addr >> 32;
+}
+
+void kvm_exit_unexpected_vector(uint32_t value)
+{
+	outl(UNEXPECTED_VECTOR_PORT, value);
+}
+
+void route_exception(struct ex_regs *regs)
+{
+	typedef void(*handler)(struct ex_regs *);
+	handler *handlers = (handler *)exception_handlers;
+
+	if (handlers && handlers[regs->vector]) {
+		handlers[regs->vector](regs);
+		return;
+	}
+
+	kvm_exit_unexpected_vector(regs->vector);
+}
+
+void vm_init_descriptor_tables(struct kvm_vm *vm)
+{
+	extern void *idt_handlers;
+	int i;
+
+	vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0);
+	vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0);
+	/* Handlers have the same address in both address spaces.*/
+	for (i = 0; i < NUM_INTERRUPTS; i++)
+		set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0,
+			DEFAULT_CODE_SELECTOR);
+}
+
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct kvm_sregs sregs;
+
+	vcpu_sregs_get(vm, vcpuid, &sregs);
+	sregs.idt.base = vm->idt;
+	sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1;
+	sregs.gdt.base = vm->gdt;
+	sregs.gdt.limit = getpagesize() - 1;
+	kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs);
+	vcpu_sregs_set(vm, vcpuid, &sregs);
+	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
+}
+
+void vm_handle_exception(struct kvm_vm *vm, int vector,
+			 void (*handler)(struct ex_regs *))
+{
+	vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers);
+
+	handlers[vector] = (vm_vaddr_t)handler;
+}
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO
+		&& vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT
+		&& vcpu_state(vm, vcpuid)->io.size == 4) {
+		/* Grab pointer to io data */
+		uint32_t *data = (void *)vcpu_state(vm, vcpuid)
+			+ vcpu_state(vm, vcpuid)->io.data_offset;
+
+		TEST_ASSERT(false,
+			    "Unexpected vectored event in guest (vector:0x%x)",
+			    *data);
+	}
+}
+
+bool set_cpuid(struct kvm_cpuid2 *cpuid,
+	       struct kvm_cpuid_entry2 *ent)
+{
+	int i;
+
+	for (i = 0; i < cpuid->nent; i++) {
+		struct kvm_cpuid_entry2 *cur = &cpuid->entries[i];
+
+		if (cur->function != ent->function || cur->index != ent->index)
+			continue;
+
+		memcpy(cur, ent, sizeof(struct kvm_cpuid_entry2));
+		return true;
+	}
+
+	return false;
+}
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+		       uint64_t a3)
+{
+	uint64_t r;
+
+	asm volatile("vmcall"
+		     : "=a"(r)
+		     : "b"(a0), "c"(a1), "d"(a2), "S"(a3));
+	return r;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
index da4d89a..a348997 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
@@ -40,6 +40,9 @@
 	struct kvm_run *run = vcpu_state(vm, vcpu_id);
 	struct ucall ucall = {};
 
+	if (uc)
+		memset(uc, 0, sizeof(*uc));
+
 	if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) {
 		struct kvm_regs regs;
 
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
new file mode 100644
index 0000000..b10a274
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020, Google LLC.
+ *
+ * Tests for KVM paravirtual feature disablement
+ */
+#include <asm/kvm_para.h>
+#include <linux/kvm_para.h>
+#include <stdint.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+extern unsigned char rdmsr_start;
+extern unsigned char rdmsr_end;
+
+static u64 do_rdmsr(u32 idx)
+{
+	u32 lo, hi;
+
+	asm volatile("rdmsr_start: rdmsr;"
+		     "rdmsr_end:"
+		     : "=a"(lo), "=c"(hi)
+		     : "c"(idx));
+
+	return (((u64) hi) << 32) | lo;
+}
+
+extern unsigned char wrmsr_start;
+extern unsigned char wrmsr_end;
+
+static void do_wrmsr(u32 idx, u64 val)
+{
+	u32 lo, hi;
+
+	lo = val;
+	hi = val >> 32;
+
+	asm volatile("wrmsr_start: wrmsr;"
+		     "wrmsr_end:"
+		     : : "a"(lo), "c"(idx), "d"(hi));
+}
+
+static int nr_gp;
+
+static void guest_gp_handler(struct ex_regs *regs)
+{
+	unsigned char *rip = (unsigned char *)regs->rip;
+	bool r, w;
+
+	r = rip == &rdmsr_start;
+	w = rip == &wrmsr_start;
+	GUEST_ASSERT(r || w);
+
+	nr_gp++;
+
+	if (r)
+		regs->rip = (uint64_t)&rdmsr_end;
+	else
+		regs->rip = (uint64_t)&wrmsr_end;
+}
+
+struct msr_data {
+	uint32_t idx;
+	const char *name;
+};
+
+#define TEST_MSR(msr) { .idx = msr, .name = #msr }
+#define UCALL_PR_MSR 0xdeadbeef
+#define PR_MSR(msr) ucall(UCALL_PR_MSR, 1, msr)
+
+/*
+ * KVM paravirtual msrs to test. Expect a #GP if any of these msrs are read or
+ * written, as the KVM_CPUID_FEATURES leaf is cleared.
+ */
+static struct msr_data msrs_to_test[] = {
+	TEST_MSR(MSR_KVM_SYSTEM_TIME),
+	TEST_MSR(MSR_KVM_SYSTEM_TIME_NEW),
+	TEST_MSR(MSR_KVM_WALL_CLOCK),
+	TEST_MSR(MSR_KVM_WALL_CLOCK_NEW),
+	TEST_MSR(MSR_KVM_ASYNC_PF_EN),
+	TEST_MSR(MSR_KVM_STEAL_TIME),
+	TEST_MSR(MSR_KVM_PV_EOI_EN),
+	TEST_MSR(MSR_KVM_POLL_CONTROL),
+	TEST_MSR(MSR_KVM_ASYNC_PF_INT),
+	TEST_MSR(MSR_KVM_ASYNC_PF_ACK),
+};
+
+static void test_msr(struct msr_data *msr)
+{
+	PR_MSR(msr);
+	do_rdmsr(msr->idx);
+	GUEST_ASSERT(READ_ONCE(nr_gp) == 1);
+
+	nr_gp = 0;
+	do_wrmsr(msr->idx, 0);
+	GUEST_ASSERT(READ_ONCE(nr_gp) == 1);
+	nr_gp = 0;
+}
+
+struct hcall_data {
+	uint64_t nr;
+	const char *name;
+};
+
+#define TEST_HCALL(hc) { .nr = hc, .name = #hc }
+#define UCALL_PR_HCALL 0xdeadc0de
+#define PR_HCALL(hc) ucall(UCALL_PR_HCALL, 1, hc)
+
+/*
+ * KVM hypercalls to test. Expect -KVM_ENOSYS when called, as the corresponding
+ * features have been cleared in KVM_CPUID_FEATURES.
+ */
+static struct hcall_data hcalls_to_test[] = {
+	TEST_HCALL(KVM_HC_KICK_CPU),
+	TEST_HCALL(KVM_HC_SEND_IPI),
+	TEST_HCALL(KVM_HC_SCHED_YIELD),
+};
+
+static void test_hcall(struct hcall_data *hc)
+{
+	uint64_t r;
+
+	PR_HCALL(hc);
+	r = kvm_hypercall(hc->nr, 0, 0, 0, 0);
+	GUEST_ASSERT(r == -KVM_ENOSYS);
+}
+
+static void guest_main(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(msrs_to_test); i++) {
+		test_msr(&msrs_to_test[i]);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(hcalls_to_test); i++) {
+		test_hcall(&hcalls_to_test[i]);
+	}
+
+	GUEST_DONE();
+}
+
+static void clear_kvm_cpuid_features(struct kvm_cpuid2 *cpuid)
+{
+	struct kvm_cpuid_entry2 ent = {0};
+
+	ent.function = KVM_CPUID_FEATURES;
+	TEST_ASSERT(set_cpuid(cpuid, &ent),
+		    "failed to clear KVM_CPUID_FEATURES leaf");
+}
+
+static void pr_msr(struct ucall *uc)
+{
+	struct msr_data *msr = (struct msr_data *)uc->args[0];
+
+	pr_info("testing msr: %s (%#x)\n", msr->name, msr->idx);
+}
+
+static void pr_hcall(struct ucall *uc)
+{
+	struct hcall_data *hc = (struct hcall_data *)uc->args[0];
+
+	pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr);
+}
+
+static void handle_abort(struct ucall *uc)
+{
+	TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0],
+		  __FILE__, uc->args[1]);
+}
+
+#define VCPU_ID 0
+
+static void enter_guest(struct kvm_vm *vm)
+{
+	struct kvm_run *run;
+	struct ucall uc;
+	int r;
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	while (true) {
+		r = _vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(!r, "vcpu_run failed: %d\n", r);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "unexpected exit reason: %u (%s)",
+			    run->exit_reason, exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_PR_MSR:
+			pr_msr(&uc);
+			break;
+		case UCALL_PR_HCALL:
+			pr_hcall(&uc);
+			break;
+		case UCALL_ABORT:
+			handle_abort(&uc);
+			return;
+		case UCALL_DONE:
+			return;
+		}
+	}
+}
+
+int main(void)
+{
+	struct kvm_enable_cap cap = {0};
+	struct kvm_cpuid2 *best;
+	struct kvm_vm *vm;
+
+	if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) {
+		pr_info("will skip kvm paravirt restriction tests.\n");
+		return 0;
+	}
+
+	vm = vm_create_default(VCPU_ID, 0, guest_main);
+
+	cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID;
+	cap.args[0] = 1;
+	vcpu_enable_cap(vm, VCPU_ID, &cap);
+
+	best = kvm_get_supported_cpuid();
+	clear_kvm_cpuid_features(best);
+	vcpu_set_cpuid(vm, VCPU_ID, best);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+
+	enter_guest(vm);
+	kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 30848ca..a5ce26d 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -136,7 +136,7 @@
 ifeq ($(OVERRIDE_TARGETS),)
 LOCAL_HDRS := $(selfdir)/kselftest_harness.h $(selfdir)/kselftest.h
 $(OUTPUT)/%:%.c $(LOCAL_HDRS)
-	$(LINK.c) $^ $(LDLIBS) -o $@
+	$(LINK.c) $(filter-out $(LOCAL_HDRS),$^) $(LDLIBS) -o $@
 
 $(OUTPUT)/%.o:%.S
 	$(COMPILE.S) $^ -o $@
diff --git a/tools/testing/selftests/pidfd/config b/tools/testing/selftests/pidfd/config
index bb11de9..f6f2965 100644
--- a/tools/testing/selftests/pidfd/config
+++ b/tools/testing/selftests/pidfd/config
@@ -4,3 +4,4 @@
 CONFIG_PID_NS=y
 CONFIG_NET_NS=y
 CONFIG_CGROUPS=y
+CONFIG_CHECKPOINT_RESTORE=y
diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
index 7758c98..0930e24 100644
--- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
@@ -204,7 +204,10 @@
 	fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0);
 	ASSERT_GE(fd, 0);
 
-	EXPECT_EQ(0, sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd));
+	ret = sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd);
+	if (ret < 0 && errno == ENOSYS)
+		SKIP(return, "kcmp() syscall not supported");
+	EXPECT_EQ(ret, 0);
 
 	ret = fcntl(fd, F_GETFD);
 	ASSERT_GE(ret, 0);
diff --git a/tools/testing/selftests/pidfd/pidfd_open_test.c b/tools/testing/selftests/pidfd/pidfd_open_test.c
index b9fe75f..8a59438 100644
--- a/tools/testing/selftests/pidfd/pidfd_open_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_open_test.c
@@ -6,7 +6,6 @@
 #include <inttypes.h>
 #include <limits.h>
 #include <linux/types.h>
-#include <linux/wait.h>
 #include <sched.h>
 #include <signal.h>
 #include <stdbool.h>
diff --git a/tools/testing/selftests/pidfd/pidfd_poll_test.c b/tools/testing/selftests/pidfd/pidfd_poll_test.c
index 4b11544..6108112 100644
--- a/tools/testing/selftests/pidfd/pidfd_poll_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_poll_test.c
@@ -3,7 +3,6 @@
 #define _GNU_SOURCE
 #include <errno.h>
 #include <linux/types.h>
-#include <linux/wait.h>
 #include <poll.h>
 #include <signal.h>
 #include <stdbool.h>
diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c
index 1f085b9..6e2f2cd 100644
--- a/tools/testing/selftests/pidfd/pidfd_setns_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c
@@ -16,7 +16,6 @@
 #include <unistd.h>
 #include <sys/socket.h>
 #include <sys/stat.h>
-#include <linux/kcmp.h>
 
 #include "pidfd.h"
 #include "../clone3/clone3_selftests.h"
diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c
index c585aaa..529eb70 100644
--- a/tools/testing/selftests/pidfd/pidfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_test.c
@@ -330,7 +330,7 @@
 		ksft_exit_fail_msg("%s test: Failed to recycle pid %d\n",
 				   test_name, PID_RECYCLE);
 	case PIDFD_SKIP:
-		ksft_print_msg("%s test: Skipping test\n", test_name);
+		ksft_test_result_skip("%s test: Skipping test\n", test_name);
 		ret = 0;
 		break;
 	case PIDFD_XFAIL:
diff --git a/tools/testing/selftests/proc/proc-loadavg-001.c b/tools/testing/selftests/proc/proc-loadavg-001.c
index 471e2aa..fb4fe91 100644
--- a/tools/testing/selftests/proc/proc-loadavg-001.c
+++ b/tools/testing/selftests/proc/proc-loadavg-001.c
@@ -14,7 +14,6 @@
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
 /* Test that /proc/loadavg correctly reports last pid in pid namespace. */
-#define _GNU_SOURCE
 #include <errno.h>
 #include <sched.h>
 #include <sys/types.h>
diff --git a/tools/testing/selftests/proc/proc-self-syscall.c b/tools/testing/selftests/proc/proc-self-syscall.c
index 9f6d000..8511dcf 100644
--- a/tools/testing/selftests/proc/proc-self-syscall.c
+++ b/tools/testing/selftests/proc/proc-self-syscall.c
@@ -13,7 +13,6 @@
  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
-#define _GNU_SOURCE
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <sys/types.h>
diff --git a/tools/testing/selftests/proc/proc-uptime-002.c b/tools/testing/selftests/proc/proc-uptime-002.c
index 30e2b78..e7ceabe 100644
--- a/tools/testing/selftests/proc/proc-uptime-002.c
+++ b/tools/testing/selftests/proc/proc-uptime-002.c
@@ -15,7 +15,6 @@
  */
 // Test that values in /proc/uptime increment monotonically
 // while shifting across CPUs.
-#define _GNU_SOURCE
 #undef NDEBUG
 #include <assert.h>
 #include <unistd.h>
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index bb543bf..361235a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -100,7 +100,7 @@
         ],
         "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
         "expExitCode": "0",
-        "verifyCmd": "$TC filter show terse dev $DEV2 ingress",
+        "verifyCmd": "$TC -br filter show dev $DEV2 ingress",
         "matchPattern": "filter protocol ip pref 1 flower.*handle",
         "matchCount": "1",
         "teardown": [
@@ -119,7 +119,7 @@
         ],
         "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
         "expExitCode": "0",
-        "verifyCmd": "$TC filter show terse dev $DEV2 ingress",
+        "verifyCmd": "$TC -br filter show dev $DEV2 ingress",
         "matchPattern": "  dst_mac e4:11:22:11:4a:51",
         "matchCount": "0",
         "teardown": [
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index d77f482..74c69b7 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -316,6 +316,14 @@
 n2 ping -W 1 -c 1 192.168.241.1
 n1 wg set wg0 peer "$pub2" persistent-keepalive 0
 
+# Test that sk_bound_dev_if works
+n1 ping -I wg0 -c 1 -W 1 192.168.241.2
+# What about when the mark changes and the packet must be rerouted?
+n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1
+n1 ping -c 1 -W 1 192.168.241.2 # First the boring case
+n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case
+n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1
+
 # Test that onion routing works, even when it loops
 n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5
 ip1 addr add 192.168.242.1/24 dev wg0
diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config
index d531de1..4eecb43 100644
--- a/tools/testing/selftests/wireguard/qemu/kernel.config
+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
@@ -18,10 +18,12 @@
 CONFIG_NETFILTER_XTABLES=y
 CONFIG_NETFILTER_XT_NAT=y
 CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MARK=y
 CONFIG_NF_CONNTRACK_IPV4=y
 CONFIG_NF_NAT_IPV4=y
 CONFIG_IP_NF_IPTABLES=y
 CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_MANGLE=y
 CONFIG_IP_NF_NAT=y
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTIPLE_TABLES=y