irqchip updates for 6.3

- New and improved irqdomain locking, closing a number of races that became apparent now that we are able to probe drivers in parallel - A bunch of OF node refcounting bugs have been fixed - We now have a new IPI mux, lifted from the Apple AIC code and made common. It is expected that riscv will eventually benefit from it - Two small fixes for the Broadcom L2 drivers - Various cleanups and minor bug fixes -----BEGIN PGP SIGNATURE----- iQJDBAABCgAtFiEEn9UcU+C1Yxj9lZw9I9DQutE9ekMFAmPw4OgPHG1hekBrZXJu ZWwub3JnAAoJECPQ0LrRPXpDYVgP/iVFxCPs+DCWUYvyTC8rvNzOj51COHUV/7yD mY5BTIjH3yTQPDhQmFvITCAjKaMYc3eDLml/nF4tTCU0MFig+KsRsWNIEFXtSsI0 wO+S19QhHzj5odUok5IDC+cNTXScp2HV+vFoOhhf0zDzXqwVxRr7lO5i+n37ELMp Mm9g2+EeUt43xTQxzbmNn5Kkpq9PMEnQFU2UkvJleg+KCgzSYThcR8/KUDKySZpk TP+mcR5PevcqGhLt7vYS2lGh8Ye1warzp54C7Je8P8Txg3BM8xBynT1d3fgrlKfm AOAPVW3PV6bPhgVYXZJopH3ykfmYM4ZiIvhRcgLyf6tbZAU6Twpiq823TAOVHyPI SRcW8dehuvgq1VJIpRGZOSB2qIvFrqLhl0B1CtT04gFWJW9bSa2n5Y1h4Gcqy29o SLJiKscx2KqvPmQqarLUUnuOZ5hhIrtYhkhhJuuwqZqzS1Kkz/mSB1MkPQEGxJi1 MpoTfbQ/0KTYXCqqgs/GBnDJ0mYrcvtBoGP7bjnVYnXpANP2bs+ZpQVPVq+17uuQ k0gjxe8iENqXjW6JMlFX5K3dxG5ygXjfECMWsCJ+JdCtJdaIL8I46X/u7wHU2mfY bohhb7xS2+HIPxz6w8aRu3IQG00mMv06vCYPBbPh+W0dUtocdM3U2kpe5gPYm1iz kWx3WLaM =ONcj -----END PGP SIGNATURE----- Merge tag 'irqchip-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core Pull irqchip updates from Marc Zyngier: - New and improved irqdomain locking, closing a number of races that became apparent now that we are able to probe drivers in parallel - A bunch of OF node refcounting bugs have been fixed - We now have a new IPI mux, lifted from the Apple AIC code and made common. It is expected that riscv will eventually benefit from it - Two small fixes for the Broadcom L2 drivers - Various cleanups and minor bug fixes Link: https://lore.kernel.org/r/20230218143452.3817627-1-maz@kernel.org
2025-01-06 05:06:29 +00:00 · 2023-02-19 00:07:56 +01:00 · 2023-02-19 00:07:56 +01:00 · 6f3ee0e22b
commit 6f3ee0e22b
parent 188a569658 a83bf176fe
410 changed files with 5089 additions and 4485 deletions
--- a/.mailmap
+++ b/.mailmap
@ -422,6 +422,7 @@ Tony Luck <tony.luck@intel.com>
 TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org>
 TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
 Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
+Tudor Ambarus <tudor.ambarus@linaro.org> <tudor.ambarus@microchip.com>
 Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
 Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@ -120,6 +120,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A710     | #2224489        | ARM64_ERRATUM_2224489       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A715     | #2645198        | ARM64_ERRATUM_2645198       |
+----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-X2       | #2119858        | ARM64_ERRATUM_2119858       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-X2       | #2224489        | ARM64_ERRATUM_2224489       |
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@ -31,6 +31,12 @@ def have_command(cmd):
 # Get Sphinx version
 major, minor, patch = sphinx.version_info[:3]

+#
+# Warn about older versions that we don't want to support for much
+# longer.
+#
+if (major < 2) or (major == 2 and minor < 4):
+    print('WARNING: support for Sphinx < 2.4 will be removed soon.')

 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
@ -339,7 +345,11 @@ html_use_smartypants = False

 # Custom sidebar templates, maps document names to template names.
 # Note that the RTD theme ignores this
-html_sidebars = { '**': ["about.html", 'searchbox.html', 'localtoc.html', 'sourcelink.html']}
+html_sidebars = { '**': ['searchbox.html', 'localtoc.html', 'sourcelink.html']}
+
+# about.html is available for alabaster theme. Add it at the front.
+if html_theme == 'alabaster':
+    html_sidebars['**'].insert(0, 'about.html')

 # Output file base name for HTML help builder.
 htmlhelp_basename = 'TheLinuxKerneldoc'
--- a/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml
+++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml
@ -54,6 +54,17 @@ properties:
      - const: xo
      - const: alternate

+  interrupts:
+    minItems: 1
+    maxItems: 3
+
+  interrupt-names:
+    minItems: 1
+    items:
+      - const: dcvsh-irq-0
+      - const: dcvsh-irq-1
+      - const: dcvsh-irq-2
+
  '#freq-domain-cells':
    const: 1

--- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml
+++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml
@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Atmel Advanced Encryption Standard (AES) HW cryptographic accelerator

 maintainers:
-  - Tudor Ambarus <tudor.ambarus@microchip.com>
+  - Tudor Ambarus <tudor.ambarus@linaro.org>

 properties:
  compatible:
--- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml
+++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml
@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Atmel Secure Hash Algorithm (SHA) HW cryptographic accelerator

 maintainers:
-  - Tudor Ambarus <tudor.ambarus@microchip.com>
+  - Tudor Ambarus <tudor.ambarus@linaro.org>

 properties:
  compatible:
--- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml
+++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml
@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Atmel Triple Data Encryption Standard (TDES) HW cryptographic accelerator

 maintainers:
-  - Tudor Ambarus <tudor.ambarus@microchip.com>
+  - Tudor Ambarus <tudor.ambarus@linaro.org>

 properties:
  compatible:
--- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
@ -32,7 +32,7 @@ properties:
      - description: Display byte clock
      - description: Display byte interface clock
      - description: Display pixel clock
-      - description: Display escape clock
+      - description: Display core clock
      - description: Display AHB clock
      - description: Display AXI clock

@ -137,8 +137,6 @@ required:
  - phys
  - assigned-clocks
  - assigned-clock-parents
-  - power-domains
-  - operating-points-v2
  - ports

 additionalProperties: false
--- a/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml
@ -69,7 +69,6 @@ required:
  - compatible
  - reg
  - reg-names
-  - vdds-supply

 unevaluatedProperties: false

--- a/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml
@ -39,7 +39,6 @@ required:
  - compatible
  - reg
  - reg-names
-  - vcca-supply

 unevaluatedProperties: false

--- a/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml
@ -34,6 +34,10 @@ properties:
  vddio-supply:
    description: Phandle to vdd-io regulator device node.

+  qcom,dsi-phy-regulator-ldo-mode:
+    type: boolean
+    description: Indicates if the LDO mode PHY regulator is wanted.
+
 required:
  - compatible
  - reg
--- a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml
@ -72,7 +72,7 @@ examples:
    #include <dt-bindings/interconnect/qcom,qcm2290.h>
    #include <dt-bindings/power/qcom-rpmpd.h>

-    mdss@5e00000 {
+    display-subsystem@5e00000 {
        #address-cells = <1>;
        #size-cells = <1>;
        compatible = "qcom,qcm2290-mdss";
--- a/Documentation/devicetree/bindings/display/msm/qcom,sm6115-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,sm6115-mdss.yaml
@ -62,7 +62,7 @@ examples:
    #include <dt-bindings/interrupt-controller/arm-gic.h>
    #include <dt-bindings/power/qcom-rpmpd.h>

-    mdss@5e00000 {
+    display-subsystem@5e00000 {
        #address-cells = <1>;
        #size-cells = <1>;
        compatible = "qcom,sm6115-mdss";
--- a/Documentation/devicetree/bindings/sound/mt8186-mt6366-rt1019-rt5682s.yaml
+++ b/Documentation/devicetree/bindings/sound/mt8186-mt6366-rt1019-rt5682s.yaml
@ -16,6 +16,7 @@ properties:
  compatible:
    enum:
      - mediatek,mt8186-mt6366-rt1019-rt5682s-sound
+      - mediatek,mt8186-mt6366-rt5682s-max98360-sound

  mediatek,platform:
    $ref: "/schemas/types.yaml#/definitions/phandle"
--- a/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml
+++ b/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml
@ -30,7 +30,9 @@ properties:
    const: 0

  clocks:
-    maxItems: 5
+    oneOf:
+      - maxItems: 3
+      - maxItems: 5

  clock-names:
    oneOf:
--- a/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml
+++ b/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml
@ -9,9 +9,6 @@ title: LPASS(Low Power Audio Subsystem) VA Macro audio codec
 maintainers:
  - Srinivas Kandagatla <srinivas.kandagatla@linaro.org>

-allOf:
-  - $ref: dai-common.yaml#
-
 properties:
  compatible:
    enum:
@ -30,15 +27,12 @@ properties:
    const: 0

  clocks:
-    maxItems: 5
+    minItems: 5
+    maxItems: 6

  clock-names:
-    items:
-      - const: mclk
-      - const: npl
-      - const: macro
-      - const: dcodec
-      - const: fsgen
+    minItems: 5
+    maxItems: 6

  clock-output-names:
    maxItems: 1
@ -55,10 +49,51 @@ required:
  - reg
  - "#sound-dai-cells"

+allOf:
+  - $ref: dai-common.yaml#
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - qcom,sc7280-lpass-wsa-macro
+            - qcom,sm8450-lpass-wsa-macro
+            - qcom,sc8280xp-lpass-wsa-macro
+    then:
+      properties:
+        clocks:
+          maxItems: 5
+        clock-names:
+          items:
+            - const: mclk
+            - const: npl
+            - const: macro
+            - const: dcodec
+            - const: fsgen
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - qcom,sm8250-lpass-wsa-macro
+    then:
+      properties:
+        clocks:
+          minItems: 6
+        clock-names:
+          items:
+            - const: mclk
+            - const: npl
+            - const: macro
+            - const: dcodec
+            - const: va
+            - const: fsgen
+
 unevaluatedProperties: false

 examples:
  - |
+    #include <dt-bindings/clock/qcom,sm8250-lpass-aoncc.h>
    #include <dt-bindings/sound/qcom,q6afe.h>
    codec@3240000 {
      compatible = "qcom,sm8250-lpass-wsa-macro";
@ -69,7 +104,8 @@ examples:
               <&audiocc 0>,
               <&q6afecc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
               <&q6afecc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+               <&aoncc LPASS_CDC_VA_MCLK>,
               <&vamacro>;
-      clock-names = "mclk", "npl", "macro", "dcodec", "fsgen";
+      clock-names = "mclk", "npl", "macro", "dcodec", "va", "fsgen";
      clock-output-names = "mclk";
    };
--- a/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml
@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Atmel SPI device

 maintainers:
-  - Tudor Ambarus <tudor.ambarus@microchip.com>
+  - Tudor Ambarus <tudor.ambarus@linaro.org>

 allOf:
  - $ref: spi-controller.yaml#
--- a/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml
+++ b/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml
@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Atmel Quad Serial Peripheral Interface (QSPI)

 maintainers:
-  - Tudor Ambarus <tudor.ambarus@microchip.com>
+  - Tudor Ambarus <tudor.ambarus@linaro.org>

 allOf:
  - $ref: spi-controller.yaml#
--- a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
@ -44,9 +44,9 @@ properties:
    description:
      Maximum SPI clocking speed of the device in Hz.

-  spi-cs-setup-ns:
+  spi-cs-setup-delay-ns:
    description:
-      Delay in nanosecods to be introduced by the controller after CS is
+      Delay in nanoseconds to be introduced by the controller after CS is
      asserted.

  spi-rx-bus-width:
--- a/Documentation/networking/rxrpc.rst
+++ b/Documentation/networking/rxrpc.rst
@ -880,8 +880,8 @@ The kernel interface functions are as follows:

     notify_end_rx can be NULL or it can be used to specify a function to be
     called when the call changes state to end the Tx phase.  This function is
-     called with the call-state spinlock held to prevent any reply or final ACK
-     from being delivered first.
+     called with a spinlock held to prevent the last DATA packet from being
+     transmitted until the function returns.

 (#) Receive data from a call::

--- a/Documentation/sphinx/load_config.py
+++ b/Documentation/sphinx/load_config.py
@ -3,7 +3,7 @@

 import os
 import sys
-from sphinx.util.pycompat import execfile_
+from sphinx.util.osutil import fs_encoding

 # ------------------------------------------------------------------------------
 def loadConfig(namespace):
@ -48,7 +48,9 @@ def loadConfig(namespace):
            sys.stdout.write("load additional sphinx-config: %s\n" % config_file)
            config = namespace.copy()
            config['__file__'] = config_file
-            execfile_(config_file, config)
+            with open(config_file, 'rb') as f:
+                code = compile(f.read(), fs_encoding, 'exec')
+                exec(code, config)
            del config['__file__']
            namespace.update(config)
        else:
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@ -1354,6 +1354,14 @@ the memory region are automatically reflected into the guest.  For example, an
 mmap() that affects the region will be made visible immediately.  Another
 example is madvise(MADV_DROP).

+Note: On arm64, a write generated by the page-table walker (to update
+the Access and Dirty flags, for example) never results in a
+KVM_EXIT_MMIO exit when the slot has the KVM_MEM_READONLY flag. This
+is because KVM cannot provide the data that would be written by the
+page-table walker, making it impossible to emulate the access.
+Instead, an abort (data abort if the cause of the page-table update
+was a load or a store, instruction abort if it was an instruction
+fetch) is injected in the guest.

 4.36 KVM_SET_TSS_ADDR
 ---------------------
@ -8310,6 +8318,20 @@ CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by ``KVM_GET_SUPPORTED_CPUID``
 It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel
 has enabled in-kernel emulation of the local APIC.

+CPU topology
+~~~~~~~~~~~~
+
+Several CPUID values include topology information for the host CPU:
+0x0b and 0x1f for Intel systems, 0x8000001e for AMD systems.  Different
+versions of KVM return different values for this information and userspace
+should not rely on it.  Currently they return all zeroes.
+
+If userspace wishes to set up a guest topology, it should be careful that
+the values of these three leaves differ for each CPU.  In particular,
+the APIC ID is found in EDX for all subleaves of 0x0b and 0x1f, and in EAX
+for 0x8000001e; the latter also encodes the core id and node id in bits
+7:0 of EBX and ECX respectively.
+
 Obsolete ioctls and capabilities
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- a/Documentation/virt/kvm/locking.rst
+++ b/Documentation/virt/kvm/locking.rst
@ -24,21 +24,22 @@ The acquisition orders for mutexes are as follows:

 For SRCU:

- ``synchronize_srcu(&kvm->srcu)`` is called _inside_
-  the kvm->slots_lock critical section, therefore kvm->slots_lock
-  cannot be taken inside a kvm->srcu read-side critical section.
-  Instead, kvm->slots_arch_lock is released before the call
-  to ``synchronize_srcu()`` and _can_ be taken inside a
-  kvm->srcu read-side critical section.
+- ``synchronize_srcu(&kvm->srcu)`` is called inside critical sections
+  for kvm->lock, vcpu->mutex and kvm->slots_lock.  These locks _cannot_
+  be taken inside a kvm->srcu read-side critical section; that is, the
+  following is broken::

- kvm->lock is taken inside kvm->srcu, therefore
-  ``synchronize_srcu(&kvm->srcu)`` cannot be called inside
-  a kvm->lock critical section.  If you cannot delay the
-  call until after kvm->lock is released, use ``call_srcu``.
+      srcu_read_lock(&kvm->srcu);
+      mutex_lock(&kvm->slots_lock);
+
+- kvm->slots_arch_lock instead is released before the call to
+  ``synchronize_srcu()``.  It _can_ therefore be taken inside a
+  kvm->srcu read-side critical section, for example while processing
+  a vmexit.

 On x86:

- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock
+- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock and kvm->arch.xen.xen_lock

 - kvm->arch.mmu_lock is an rwlock.  kvm->arch.tdp_mmu_pages_lock and
  kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and
--- a/15
+++ b/15
@ -11358,9 +11358,9 @@ F:	virt/kvm/*
 KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
 M:	Marc Zyngier <maz@kernel.org>
 R:	James Morse <james.morse@arm.com>
-R:	Alexandru Elisei <alexandru.elisei@arm.com>
 R:	Suzuki K Poulose <suzuki.poulose@arm.com>
 R:	Oliver Upton <oliver.upton@linux.dev>
+R:	Zenghui Yu <yuzenghui@huawei.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	kvmarm@lists.linux.dev
 L:	kvmarm@lists.cs.columbia.edu (deprecated, moderated for non-subscribers)
@ -13622,7 +13622,7 @@ F:	arch/microblaze/

 MICROCHIP AT91 DMA DRIVERS
 M:	Ludovic Desroches <ludovic.desroches@microchip.com>
-M:	Tudor Ambarus <tudor.ambarus@microchip.com>
+M:	Tudor Ambarus <tudor.ambarus@linaro.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	dmaengine@vger.kernel.org
 S:	Supported
@ -13667,7 +13667,7 @@ F:	Documentation/devicetree/bindings/media/microchip,csi2dc.yaml
 F:	drivers/media/platform/microchip/microchip-csi2dc.c

 MICROCHIP ECC DRIVER
-M:	Tudor Ambarus <tudor.ambarus@microchip.com>
+M:	Tudor Ambarus <tudor.ambarus@linaro.org>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
 F:	drivers/crypto/atmel-ecc.*
@ -13764,7 +13764,7 @@ S:	Maintained
 F:	drivers/mmc/host/atmel-mci.c

 MICROCHIP NAND DRIVER
-M:	Tudor Ambarus <tudor.ambarus@microchip.com>
+M:	Tudor Ambarus <tudor.ambarus@linaro.org>
 L:	linux-mtd@lists.infradead.org
 S:	Supported
 F:	Documentation/devicetree/bindings/mtd/atmel-nand.txt
@ -13816,7 +13816,7 @@ S:	Supported
 F:	drivers/power/reset/at91-sama5d2_shdwc.c

 MICROCHIP SPI DRIVER
-M:	Tudor Ambarus <tudor.ambarus@microchip.com>
+M:	Tudor Ambarus <tudor.ambarus@linaro.org>
 S:	Supported
 F:	drivers/spi/spi-atmel.*

@ -14921,7 +14921,8 @@ T:	git://git.infradead.org/nvme.git
 F:	Documentation/nvme/
 F:	drivers/nvme/host/
 F:	drivers/nvme/common/
-F:	include/linux/nvme*
+F:	include/linux/nvme.h
+F:	include/linux/nvme-*.h
 F:	include/uapi/linux/nvme_ioctl.h

 NVM EXPRESS FABRICS AUTHENTICATION
@ -19674,7 +19675,7 @@ F:	drivers/clk/spear/
 F:	drivers/pinctrl/spear/

 SPI NOR SUBSYSTEM
-M:	Tudor Ambarus <tudor.ambarus@microchip.com>
+M:	Tudor Ambarus <tudor.ambarus@linaro.org>
 M:	Pratyush Yadav <pratyush@kernel.org>
 R:	Michael Walle <michael@walle.cc>
 L:	linux-mtd@lists.infradead.org
--- a/2
+++ b/2
@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 2
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Hurr durr I'ma ninja sloth

 # *DOCUMENTATION*
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@ -184,8 +184,6 @@ config ARM64
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_DYNAMIC_FTRACE_WITH_ARGS \
-		if $(cc-option,-fpatchable-function-entry=2)
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
 		if DYNAMIC_FTRACE_WITH_ARGS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
@ -972,6 +970,22 @@ config ARM64_ERRATUM_2457168

 	  If unsure, say Y.

+config ARM64_ERRATUM_2645198
+	bool "Cortex-A715: 2645198: Workaround possible [ESR|FAR]_ELx corruption"
+	default y
+	help
+	  This option adds the workaround for ARM Cortex-A715 erratum 2645198.
+
+	  If a Cortex-A715 cpu sees a page mapping permissions change from executable
+	  to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers on the
+	  next instruction abort caused by permission fault.
+
+	  Only user-space does executable to non-executable permission transition via
+	  mprotect() system call. Workaround the problem by doing a break-before-make
+	  TLB invalidation, for all changes to executable user space mappings.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@ -315,7 +315,7 @@ __ll_sc__cmpxchg_double##name(unsigned long old1,			\
 	"	cbnz	%w0, 1b\n"					\
 	"	" #mb "\n"						\
 	"2:"								\
-	: "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr)	\
+	: "=&r" (tmp), "=&r" (ret), "+Q" (*(__uint128_t *)ptr)		\
 	: "r" (old1), "r" (old2), "r" (new1), "r" (new2)		\
 	: cl);								\
 									\
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@ -311,7 +311,7 @@ __lse__cmpxchg_double##name(unsigned long old1,				\
 	"	eor	%[old2], %[old2], %[oldval2]\n"			\
 	"	orr	%[old1], %[old1], %[old2]"			\
 	: [old1] "+&r" (x0), [old2] "+&r" (x1),				\
-	  [v] "+Q" (*(unsigned long *)ptr)				\
+	  [v] "+Q" (*(__uint128_t *)ptr)				\
 	: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4),		\
 	  [oldval1] "r" (oldval1), [oldval2] "r" (oldval2)		\
 	: cl);								\
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@ -124,6 +124,8 @@
 #define APPLE_CPU_PART_M1_FIRESTORM_PRO	0x025
 #define APPLE_CPU_PART_M1_ICESTORM_MAX	0x028
 #define APPLE_CPU_PART_M1_FIRESTORM_MAX	0x029
+#define APPLE_CPU_PART_M2_BLIZZARD	0x032
+#define APPLE_CPU_PART_M2_AVALANCHE	0x033

 #define AMPERE_CPU_PART_AMPERE1		0xAC3

@ -177,6 +179,8 @@
 #define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO)
 #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX)
 #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
+#define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD)
+#define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE)
 #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)

 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@ -114,6 +114,15 @@
 #define ESR_ELx_FSC_ACCESS	(0x08)
 #define ESR_ELx_FSC_FAULT	(0x04)
 #define ESR_ELx_FSC_PERM	(0x0C)
+#define ESR_ELx_FSC_SEA_TTW0	(0x14)
+#define ESR_ELx_FSC_SEA_TTW1	(0x15)
+#define ESR_ELx_FSC_SEA_TTW2	(0x16)
+#define ESR_ELx_FSC_SEA_TTW3	(0x17)
+#define ESR_ELx_FSC_SECC	(0x18)
+#define ESR_ELx_FSC_SECC_TTW0	(0x1c)
+#define ESR_ELx_FSC_SECC_TTW1	(0x1d)
+#define ESR_ELx_FSC_SECC_TTW2	(0x1e)
+#define ESR_ELx_FSC_SECC_TTW3	(0x1f)

 /* ISS field definitions for Data Aborts */
 #define ESR_ELx_ISV_SHIFT	(24)
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@ -49,6 +49,15 @@ extern pte_t huge_ptep_get(pte_t *ptep);

 void __init arm64_hugetlb_cma_reserve(void);

+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t new_pte);
+
 #include <asm-generic/hugetlb.h>

 #endif /* __ASM_HUGETLB_H */
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@ -319,21 +319,6 @@
 				 BIT(18) |		\
 				 GENMASK(16, 15))

-/* For compatibility with fault code shared with 32-bit */
-#define FSC_FAULT	ESR_ELx_FSC_FAULT
-#define FSC_ACCESS	ESR_ELx_FSC_ACCESS
-#define FSC_PERM	ESR_ELx_FSC_PERM
-#define FSC_SEA		ESR_ELx_FSC_EXTABT
-#define FSC_SEA_TTW0	(0x14)
-#define FSC_SEA_TTW1	(0x15)
-#define FSC_SEA_TTW2	(0x16)
-#define FSC_SEA_TTW3	(0x17)
-#define FSC_SECC	(0x18)
-#define FSC_SECC_TTW0	(0x1c)
-#define FSC_SECC_TTW1	(0x1d)
-#define FSC_SECC_TTW2	(0x1e)
-#define FSC_SECC_TTW3	(0x1f)
-
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
 /*
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@ -349,16 +349,16 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *v
 static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
 {
 	switch (kvm_vcpu_trap_get_fault(vcpu)) {
-	case FSC_SEA:
-	case FSC_SEA_TTW0:
-	case FSC_SEA_TTW1:
-	case FSC_SEA_TTW2:
-	case FSC_SEA_TTW3:
-	case FSC_SECC:
-	case FSC_SECC_TTW0:
-	case FSC_SECC_TTW1:
-	case FSC_SECC_TTW2:
-	case FSC_SECC_TTW3:
+	case ESR_ELx_FSC_EXTABT:
+	case ESR_ELx_FSC_SEA_TTW0:
+	case ESR_ELx_FSC_SEA_TTW1:
+	case ESR_ELx_FSC_SEA_TTW2:
+	case ESR_ELx_FSC_SEA_TTW3:
+	case ESR_ELx_FSC_SECC:
+	case ESR_ELx_FSC_SECC_TTW0:
+	case ESR_ELx_FSC_SECC_TTW1:
+	case ESR_ELx_FSC_SECC_TTW2:
+	case ESR_ELx_FSC_SECC_TTW3:
 		return true;
 	default:
 		return false;
@ -373,8 +373,26 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)

 static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 {
-	if (kvm_vcpu_abt_iss1tw(vcpu))
-		return true;
+	if (kvm_vcpu_abt_iss1tw(vcpu)) {
+		/*
+		 * Only a permission fault on a S1PTW should be
+		 * considered as a write. Otherwise, page tables baked
+		 * in a read-only memslot will result in an exception
+		 * being delivered in the guest.
+		 *
+		 * The drawback is that we end-up faulting twice if the
+		 * guest is using any of HW AF/DB: a translation fault
+		 * to map the page containing the PT (read only at
+		 * first), then a permission fault to allow the flags
+		 * to be set.
+		 */
+		switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
+		case ESR_ELx_FSC_PERM:
+			return true;
+		default:
+			return false;
+		}
+	}

 	if (kvm_vcpu_trap_is_iabt(vcpu))
 		return false;
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@ -681,7 +681,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 #define pud_leaf(pud)		(pud_present(pud) && !pud_table(pud))
 #define pud_valid(pud)		pte_valid(pud_pte(pud))
 #define pud_user(pud)		pte_user(pud_pte(pud))
-
+#define pud_user_exec(pud)	pte_user_exec(pud_pte(pud))

 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
@ -730,6 +730,7 @@ static inline pmd_t *pud_pgtable(pud_t pud)
 #else

 #define pud_page_paddr(pud)	({ BUILD_BUG(); 0; })
+#define pud_user_exec(pud)	pud_user(pud) /* Always 0 with folding */

 /* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */
 #define pmd_set_fixmap(addr)		NULL
@ -862,12 +863,12 @@ static inline bool pte_user_accessible_page(pte_t pte)

 static inline bool pmd_user_accessible_page(pmd_t pmd)
 {
-	return pmd_leaf(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
+	return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
 }

 static inline bool pud_user_accessible_page(pud_t pud)
 {
-	return pud_leaf(pud) && pud_user(pud);
+	return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud));
 }
 #endif

@ -1093,6 +1094,15 @@ static inline bool pud_sect_supported(void)
 }


+#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+#define ptep_modify_prot_start ptep_modify_prot_start
+extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep);
+
+#define ptep_modify_prot_commit ptep_modify_prot_commit
+extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep,
+				    pte_t old_pte, pte_t new_pte);
 #endif /* !__ASSEMBLY__ */

 #endif /* __ASM_PGTABLE_H */
--- a/arch/arm64/include/asm/uprobes.h
+++ b/arch/arm64/include/asm/uprobes.h
@ -16,7 +16,7 @@
 #define UPROBE_SWBP_INSN_SIZE	AARCH64_INSN_SIZE
 #define UPROBE_XOL_SLOT_BYTES	MAX_UINSN_BYTES

-typedef u32 uprobe_opcode_t;
+typedef __le32 uprobe_opcode_t;

 struct arch_uprobe_task {
 };
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@ -661,6 +661,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_2645198
+	{
+		.desc = "ARM erratum 2645198",
+		.capability = ARM64_WORKAROUND_2645198,
+		ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715)
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_2077057
 	{
 		.desc = "ARM erratum 2077057",
--- a/arch/arm64/kernel/efi-rt-wrapper.S
+++ b/arch/arm64/kernel/efi-rt-wrapper.S
@ -4,6 +4,7 @@
 */

 #include <linux/linkage.h>
+#include <asm/assembler.h>

 SYM_FUNC_START(__efi_rt_asm_wrapper)
 	stp	x29, x30, [sp, #-112]!
--- a/arch/arm64/kernel/elfcore.c
+++ b/arch/arm64/kernel/elfcore.c
@ -8,28 +8,27 @@
 #include <asm/cpufeature.h>
 #include <asm/mte.h>

-#define for_each_mte_vma(vmi, vma)					\
+#define for_each_mte_vma(cprm, i, m)					\
 	if (system_supports_mte())					\
-		for_each_vma(vmi, vma)					\
-			if (vma->vm_flags & VM_MTE)
+		for (i = 0, m = cprm->vma_meta;				\
+		     i < cprm->vma_count;				\
+		     i++, m = cprm->vma_meta + i)			\
+			if (m->flags & VM_MTE)

-static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma)
+static unsigned long mte_vma_tag_dump_size(struct core_vma_metadata *m)
 {
-	if (vma->vm_flags & VM_DONTDUMP)
-		return 0;
-
-	return vma_pages(vma) * MTE_PAGE_TAG_STORAGE;
+	return (m->dump_size >> PAGE_SHIFT) * MTE_PAGE_TAG_STORAGE;
 }

 /* Derived from dump_user_range(); start/end must be page-aligned */
 static int mte_dump_tag_range(struct coredump_params *cprm,
-			      unsigned long start, unsigned long end)
+			      unsigned long start, unsigned long len)
 {
 	int ret = 1;
 	unsigned long addr;
 	void *tags = NULL;

-	for (addr = start; addr < end; addr += PAGE_SIZE) {
+	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
 		struct page *page = get_dump_page(addr);

 		/*
@ -65,7 +64,6 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
 		mte_save_page_tags(page_address(page), tags);
 		put_page(page);
 		if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) {
-			mte_free_tag_storage(tags);
 			ret = 0;
 			break;
 		}
@ -77,13 +75,13 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
 	return ret;
 }

-Elf_Half elf_core_extra_phdrs(void)
+Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm)
 {
-	struct vm_area_struct *vma;
+	int i;
+	struct core_vma_metadata *m;
 	int vma_count = 0;
-	VMA_ITERATOR(vmi, current->mm, 0);

-	for_each_mte_vma(vmi, vma)
+	for_each_mte_vma(cprm, i, m)
 		vma_count++;

 	return vma_count;
@ -91,18 +89,18 @@ Elf_Half elf_core_extra_phdrs(void)

 int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 {
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, current->mm, 0);
+	int i;
+	struct core_vma_metadata *m;

-	for_each_mte_vma(vmi, vma) {
+	for_each_mte_vma(cprm, i, m) {
 		struct elf_phdr phdr;

 		phdr.p_type = PT_AARCH64_MEMTAG_MTE;
 		phdr.p_offset = offset;
-		phdr.p_vaddr = vma->vm_start;
+		phdr.p_vaddr = m->start;
 		phdr.p_paddr = 0;
-		phdr.p_filesz = mte_vma_tag_dump_size(vma);
-		phdr.p_memsz = vma->vm_end - vma->vm_start;
+		phdr.p_filesz = mte_vma_tag_dump_size(m);
+		phdr.p_memsz = m->end - m->start;
 		offset += phdr.p_filesz;
 		phdr.p_flags = 0;
 		phdr.p_align = 0;
@ -114,28 +112,25 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
 	return 1;
 }

-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
 {
-	struct vm_area_struct *vma;
+	int i;
+	struct core_vma_metadata *m;
 	size_t data_size = 0;
-	VMA_ITERATOR(vmi, current->mm, 0);

-	for_each_mte_vma(vmi, vma)
-		data_size += mte_vma_tag_dump_size(vma);
+	for_each_mte_vma(cprm, i, m)
+		data_size += mte_vma_tag_dump_size(m);

 	return data_size;
 }

 int elf_core_write_extra_data(struct coredump_params *cprm)
 {
-	struct vm_area_struct *vma;
-	VMA_ITERATOR(vmi, current->mm, 0);
+	int i;
+	struct core_vma_metadata *m;

-	for_each_mte_vma(vmi, vma) {
-		if (vma->vm_flags & VM_DONTDUMP)
-			continue;
-
-		if (!mte_dump_tag_range(cprm, vma->vm_start, vma->vm_end))
+	for_each_mte_vma(cprm, i, m) {
+		if (!mte_dump_tag_range(cprm, m->start, m->dump_size))
 			return 0;
 	}

--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@ -385,7 +385,7 @@ static void task_fpsimd_load(void)
 	WARN_ON(!system_supports_fpsimd());
 	WARN_ON(!have_cpu_fpsimd_context());

-	if (system_supports_sve()) {
+	if (system_supports_sve() || system_supports_sme()) {
 		switch (current->thread.fp_type) {
 		case FP_STATE_FPSIMD:
 			/* Stop tracking SVE for this task until next use. */
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@ -1357,7 +1357,7 @@ enum aarch64_regset {
 #ifdef CONFIG_ARM64_SVE
 	REGSET_SVE,
 #endif
-#ifdef CONFIG_ARM64_SVE
+#ifdef CONFIG_ARM64_SME
 	REGSET_SSVE,
 	REGSET_ZA,
 #endif
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@ -281,7 +281,12 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)

 		vl = task_get_sme_vl(current);
 	} else {
-		if (!system_supports_sve())
+		/*
+		 * A SME only system use SVE for streaming mode so can
+		 * have a SVE formatted context with a zero VL and no
+		 * payload data.
+		 */
+		if (!system_supports_sve() && !system_supports_sme())
 			return -EINVAL;

 		vl = task_get_sve_vl(current);
@ -732,7 +737,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
 			return err;
 	}

-	if (system_supports_sve()) {
+	if (system_supports_sve() || system_supports_sme()) {
 		unsigned int vq = 0;

 		if (add_all || test_thread_flag(TIF_SVE) ||
--- a/arch/arm64/kvm/hyp/include/hyp/fault.h
+++ b/arch/arm64/kvm/hyp/include/hyp/fault.h
@ -60,7 +60,7 @@ static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
 	 */
 	if (!(esr & ESR_ELx_S1PTW) &&
 	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
-	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+	     (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) {
 		if (!__translate_far_to_hpfar(far, &hpfar))
 			return false;
 	} else {
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@ -367,7 +367,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
 		bool valid;

-		valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+		valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
 			!kvm_vcpu_abt_issea(vcpu) &&
 			!kvm_vcpu_abt_iss1tw(vcpu);
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@ -1212,7 +1212,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);

-	if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
+	if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
 	}
@ -1277,7 +1277,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * only exception to this is when dirty logging is enabled at runtime
 	 * and a write fault needs to collapse a block entry into a table.
 	 */
-	if (fault_status != FSC_PERM || (logging_active && write_fault)) {
+	if (fault_status != ESR_ELx_FSC_PERM ||
+	    (logging_active && write_fault)) {
 		ret = kvm_mmu_topup_memory_cache(memcache,
 						 kvm_mmu_cache_min_pages(kvm));
 		if (ret)
@ -1342,7 +1343,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * backed by a THP and thus use block mapping if possible.
 	 */
 	if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
-		if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE)
+		if (fault_status ==  ESR_ELx_FSC_PERM &&
+		    fault_granule > PAGE_SIZE)
 			vma_pagesize = fault_granule;
 		else
 			vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
@ -1350,7 +1352,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 								   &fault_ipa);
 	}

-	if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {
+	if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {
 		/* Check the VMM hasn't introduced a new disallowed VMA */
 		if (kvm_vma_mte_allowed(vma)) {
 			sanitise_mte_tags(kvm, pfn, vma_pagesize);
@ -1376,7 +1378,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * permissions only if vma_pagesize equals fault_granule. Otherwise,
 	 * kvm_pgtable_stage2_map() should be called to change block size.
 	 */
-	if (fault_status == FSC_PERM && vma_pagesize == fault_granule)
+	if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule)
 		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
 	else
 		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
@ -1441,7 +1443,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
 	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);

-	if (fault_status == FSC_FAULT) {
+	if (fault_status == ESR_ELx_FSC_FAULT) {
 		/* Beyond sanitised PARange (which is the IPA limit) */
 		if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
 			kvm_inject_size_fault(vcpu);
@ -1476,8 +1478,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);

 	/* Check the stage-2 fault is trans. fault or write fault */
-	if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
-	    fault_status != FSC_ACCESS) {
+	if (fault_status != ESR_ELx_FSC_FAULT &&
+	    fault_status != ESR_ELx_FSC_PERM &&
+	    fault_status != ESR_ELx_FSC_ACCESS) {
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
@ -1539,7 +1542,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	/* Userspace should not be able to register out-of-bounds IPAs */
 	VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));

-	if (fault_status == FSC_ACCESS) {
+	if (fault_status == ESR_ELx_FSC_ACCESS) {
 		handle_access_fault(vcpu, fault_ipa);
 		ret = 1;
 		goto out_unlock;
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@ -646,7 +646,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 		return;

 	/* Only preserve PMCR_EL0.N, and reset the rest to 0 */
-	pmcr = read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_N_MASK;
+	pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
 	if (!kvm_supports_32bit_el0())
 		pmcr |= ARMV8_PMU_PMCR_LC;

--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@ -616,6 +616,8 @@ static const struct midr_range broken_seis[] = {
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO),
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX),
 	MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
+	MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
 	{},
 };

--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@ -559,3 +559,24 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 {
 	return __hugetlb_valid_size(size);
 }
+
+pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+	if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
+	    cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+		/*
+		 * Break-before-make (BBM) is required for all user space mappings
+		 * when the permission changes from executable to non-executable
+		 * in cases where cpu is affected with errata #2645198.
+		 */
+		if (pte_user_exec(READ_ONCE(*ptep)))
+			return huge_ptep_clear_flush(vma, addr, ptep);
+	}
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+
+void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+				  pte_t old_pte, pte_t pte)
+{
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@ -1630,3 +1630,24 @@ static int __init prevent_bootmem_remove_init(void)
 }
 early_initcall(prevent_bootmem_remove_init);
 #endif
+
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+	if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
+	    cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+		/*
+		 * Break-before-make (BBM) is required for all user space mappings
+		 * when the permission changes from executable to non-executable
+		 * in cases where cpu is affected with errata #2645198.
+		 */
+		if (pte_user_exec(READ_ONCE(*ptep)))
+			return ptep_clear_flush(vma, addr, ptep);
+	}
+	return ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+			     pte_t old_pte, pte_t pte)
+{
+	set_pte_at(vma->vm_mm, addr, ptep, pte);
+}
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@ -71,6 +71,7 @@ WORKAROUND_2038923
 WORKAROUND_2064142
 WORKAROUND_2077057
 WORKAROUND_2457168
+WORKAROUND_2645198
 WORKAROUND_2658417
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 WORKAROUND_TSB_FLUSH_FAILURE
--- a/arch/ia64/kernel/elfcore.c
+++ b/arch/ia64/kernel/elfcore.c
@ -7,7 +7,7 @@
 #include <asm/elf.h>


-Elf64_Half elf_core_extra_phdrs(void)
+Elf64_Half elf_core_extra_phdrs(struct coredump_params *cprm)
 {
 	return GATE_EHDR->e_phnum;
 }
@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm)
 	return 1;
 }

-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
 {
 	const struct elf_phdr *const gate_phdrs =
 		(const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff);
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@ -210,6 +210,10 @@ ld_version()
 	gsub(".*version ", "");
 	gsub("-.*", "");
 	split($1,a, ".");
+	if( length(a[3]) == "8" )
+		# a[3] is probably a date of format yyyymmdd used for release snapshots. We
+		# can assume it to be zero as it does not signify a new version as such.
+		a[3] = 0;
 	print a[1]*100000000 + a[2]*1000000 + a[3]*10000;
 	exit
    }'
--- a/arch/powerpc/include/asm/imc-pmu.h
+++ b/arch/powerpc/include/asm/imc-pmu.h
@ -137,7 +137,7 @@ struct imc_pmu {
 * are inited.
 */
 struct imc_pmu_ref {
-	struct mutex lock;
+	spinlock_t lock;
 	unsigned int id;
 	int refc;
 };
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@ -1012,7 +1012,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table,

 void hpt_clear_stress(void);
 static struct timer_list stress_hpt_timer;
-void stress_hpt_timer_fn(struct timer_list *timer)
+static void stress_hpt_timer_fn(struct timer_list *timer)
 {
 	int next_cpu;

--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@ -14,6 +14,7 @@
 #include <asm/cputhreads.h>
 #include <asm/smp.h>
 #include <linux/string.h>
+#include <linux/spinlock.h>

 /* Nest IMC data structures and variables */

@ -21,7 +22,7 @@
 * Used to avoid races in counting the nest-pmu units during hotplug
 * register and unregister
 */
-static DEFINE_MUTEX(nest_init_lock);
+static DEFINE_SPINLOCK(nest_init_lock);
 static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc);
 static struct imc_pmu **per_nest_pmu_arr;
 static cpumask_t nest_imc_cpumask;
@ -50,7 +51,7 @@ static int trace_imc_mem_size;
 * core and trace-imc
 */
 static struct imc_pmu_ref imc_global_refc = {
-	.lock = __MUTEX_INITIALIZER(imc_global_refc.lock),
+	.lock = __SPIN_LOCK_INITIALIZER(imc_global_refc.lock),
 	.id = 0,
 	.refc = 0,
 };
@ -400,7 +401,7 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu)
 				       get_hard_smp_processor_id(cpu));
 		/*
 		 * If this is the last cpu in this chip then, skip the reference
-		 * count mutex lock and make the reference count on this chip zero.
+		 * count lock and make the reference count on this chip zero.
 		 */
 		ref = get_nest_pmu_ref(cpu);
 		if (!ref)
@ -462,15 +463,15 @@ static void nest_imc_counters_release(struct perf_event *event)
 	/*
 	 * See if we need to disable the nest PMU.
 	 * If no events are currently in use, then we have to take a
-	 * mutex to ensure that we don't race with another task doing
+	 * lock to ensure that we don't race with another task doing
 	 * enable or disable the nest counters.
 	 */
 	ref = get_nest_pmu_ref(event->cpu);
 	if (!ref)
 		return;

-	/* Take the mutex lock for this node and then decrement the reference count */
-	mutex_lock(&ref->lock);
+	/* Take the lock for this node and then decrement the reference count */
+	spin_lock(&ref->lock);
 	if (ref->refc == 0) {
 		/*
 		 * The scenario where this is true is, when perf session is
@ -482,7 +483,7 @@ static void nest_imc_counters_release(struct perf_event *event)
 		 * an OPAL call to disable the engine in that node.
 		 *
 		 */
-		mutex_unlock(&ref->lock);
+		spin_unlock(&ref->lock);
 		return;
 	}
 	ref->refc--;
@ -490,7 +491,7 @@ static void nest_imc_counters_release(struct perf_event *event)
 		rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
 					    get_hard_smp_processor_id(event->cpu));
 		if (rc) {
-			mutex_unlock(&ref->lock);
+			spin_unlock(&ref->lock);
 			pr_err("nest-imc: Unable to stop the counters for core %d\n", node_id);
 			return;
 		}
@ -498,7 +499,7 @@ static void nest_imc_counters_release(struct perf_event *event)
 		WARN(1, "nest-imc: Invalid event reference count\n");
 		ref->refc = 0;
 	}
-	mutex_unlock(&ref->lock);
+	spin_unlock(&ref->lock);
 }

 static int nest_imc_event_init(struct perf_event *event)
@ -557,26 +558,25 @@ static int nest_imc_event_init(struct perf_event *event)

 	/*
 	 * Get the imc_pmu_ref struct for this node.
-	 * Take the mutex lock and then increment the count of nest pmu events
-	 * inited.
+	 * Take the lock and then increment the count of nest pmu events inited.
 	 */
 	ref = get_nest_pmu_ref(event->cpu);
 	if (!ref)
 		return -EINVAL;

-	mutex_lock(&ref->lock);
+	spin_lock(&ref->lock);
 	if (ref->refc == 0) {
 		rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_NEST,
 					     get_hard_smp_processor_id(event->cpu));
 		if (rc) {
-			mutex_unlock(&ref->lock);
+			spin_unlock(&ref->lock);
 			pr_err("nest-imc: Unable to start the counters for node %d\n",
 									node_id);
 			return rc;
 		}
 	}
 	++ref->refc;
-	mutex_unlock(&ref->lock);
+	spin_unlock(&ref->lock);

 	event->destroy = nest_imc_counters_release;
 	return 0;
@ -612,9 +612,8 @@ static int core_imc_mem_init(int cpu, int size)
 		return -ENOMEM;
 	mem_info->vbase = page_address(page);

-	/* Init the mutex */
 	core_imc_refc[core_id].id = core_id;
-	mutex_init(&core_imc_refc[core_id].lock);
+	spin_lock_init(&core_imc_refc[core_id].lock);

 	rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_CORE,
 				__pa((void *)mem_info->vbase),
@ -703,9 +702,8 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu)
 		perf_pmu_migrate_context(&core_imc_pmu->pmu, cpu, ncpu);
 	} else {
 		/*
-		 * If this is the last cpu in this core then, skip taking refernce
-		 * count mutex lock for this core and directly zero "refc" for
-		 * this core.
+		 * If this is the last cpu in this core then skip taking reference
+		 * count lock for this core and directly zero "refc" for this core.
 		 */
 		opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
 				       get_hard_smp_processor_id(cpu));
@ -720,11 +718,11 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu)
 		 * last cpu in this core and core-imc event running
 		 * in this cpu.
 		 */
-		mutex_lock(&imc_global_refc.lock);
+		spin_lock(&imc_global_refc.lock);
 		if (imc_global_refc.id == IMC_DOMAIN_CORE)
 			imc_global_refc.refc--;

-		mutex_unlock(&imc_global_refc.lock);
+		spin_unlock(&imc_global_refc.lock);
 	}
 	return 0;
 }
@ -739,7 +737,7 @@ static int core_imc_pmu_cpumask_init(void)

 static void reset_global_refc(struct perf_event *event)
 {
-		mutex_lock(&imc_global_refc.lock);
+		spin_lock(&imc_global_refc.lock);
 		imc_global_refc.refc--;

 		/*
@ -751,7 +749,7 @@ static void reset_global_refc(struct perf_event *event)
 			imc_global_refc.refc = 0;
 			imc_global_refc.id = 0;
 		}
-		mutex_unlock(&imc_global_refc.lock);
+		spin_unlock(&imc_global_refc.lock);
 }

 static void core_imc_counters_release(struct perf_event *event)
@ -764,17 +762,17 @@ static void core_imc_counters_release(struct perf_event *event)
 	/*
 	 * See if we need to disable the IMC PMU.
 	 * If no events are currently in use, then we have to take a
-	 * mutex to ensure that we don't race with another task doing
+	 * lock to ensure that we don't race with another task doing
 	 * enable or disable the core counters.
 	 */
 	core_id = event->cpu / threads_per_core;

-	/* Take the mutex lock and decrement the refernce count for this core */
+	/* Take the lock and decrement the refernce count for this core */
 	ref = &core_imc_refc[core_id];
 	if (!ref)
 		return;

-	mutex_lock(&ref->lock);
+	spin_lock(&ref->lock);
 	if (ref->refc == 0) {
 		/*
 		 * The scenario where this is true is, when perf session is
@ -786,7 +784,7 @@ static void core_imc_counters_release(struct perf_event *event)
 		 * an OPAL call to disable the engine in that core.
 		 *
 		 */
-		mutex_unlock(&ref->lock);
+		spin_unlock(&ref->lock);
 		return;
 	}
 	ref->refc--;
@ -794,7 +792,7 @@ static void core_imc_counters_release(struct perf_event *event)
 		rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
 					    get_hard_smp_processor_id(event->cpu));
 		if (rc) {
-			mutex_unlock(&ref->lock);
+			spin_unlock(&ref->lock);
 			pr_err("IMC: Unable to stop the counters for core %d\n", core_id);
 			return;
 		}
@ -802,7 +800,7 @@ static void core_imc_counters_release(struct perf_event *event)
 		WARN(1, "core-imc: Invalid event reference count\n");
 		ref->refc = 0;
 	}
-	mutex_unlock(&ref->lock);
+	spin_unlock(&ref->lock);

 	reset_global_refc(event);
 }
@ -840,7 +838,6 @@ static int core_imc_event_init(struct perf_event *event)
 	if ((!pcmi->vbase))
 		return -ENODEV;

-	/* Get the core_imc mutex for this core */
 	ref = &core_imc_refc[core_id];
 	if (!ref)
 		return -EINVAL;
@ -848,22 +845,22 @@ static int core_imc_event_init(struct perf_event *event)
 	/*
 	 * Core pmu units are enabled only when it is used.
 	 * See if this is triggered for the first time.
-	 * If yes, take the mutex lock and enable the core counters.
+	 * If yes, take the lock and enable the core counters.
 	 * If not, just increment the count in core_imc_refc struct.
 	 */
-	mutex_lock(&ref->lock);
+	spin_lock(&ref->lock);
 	if (ref->refc == 0) {
 		rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE,
 					     get_hard_smp_processor_id(event->cpu));
 		if (rc) {
-			mutex_unlock(&ref->lock);
+			spin_unlock(&ref->lock);
 			pr_err("core-imc: Unable to start the counters for core %d\n",
 									core_id);
 			return rc;
 		}
 	}
 	++ref->refc;
-	mutex_unlock(&ref->lock);
+	spin_unlock(&ref->lock);

 	/*
 	 * Since the system can run either in accumulation or trace-mode
@ -874,7 +871,7 @@ static int core_imc_event_init(struct perf_event *event)
 	 * to know whether any other trace/thread imc
 	 * events are running.
 	 */
-	mutex_lock(&imc_global_refc.lock);
+	spin_lock(&imc_global_refc.lock);
 	if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) {
 		/*
 		 * No other trace/thread imc events are running in
@ -883,10 +880,10 @@ static int core_imc_event_init(struct perf_event *event)
 		imc_global_refc.id = IMC_DOMAIN_CORE;
 		imc_global_refc.refc++;
 	} else {
-		mutex_unlock(&imc_global_refc.lock);
+		spin_unlock(&imc_global_refc.lock);
 		return -EBUSY;
 	}
-	mutex_unlock(&imc_global_refc.lock);
+	spin_unlock(&imc_global_refc.lock);

 	event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK);
 	event->destroy = core_imc_counters_release;
@ -958,10 +955,10 @@ static int ppc_thread_imc_cpu_offline(unsigned int cpu)
 	mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));

 	/* Reduce the refc if thread-imc event running on this cpu */
-	mutex_lock(&imc_global_refc.lock);
+	spin_lock(&imc_global_refc.lock);
 	if (imc_global_refc.id == IMC_DOMAIN_THREAD)
 		imc_global_refc.refc--;
-	mutex_unlock(&imc_global_refc.lock);
+	spin_unlock(&imc_global_refc.lock);

 	return 0;
 }
@ -1001,7 +998,7 @@ static int thread_imc_event_init(struct perf_event *event)
 	if (!target)
 		return -EINVAL;

-	mutex_lock(&imc_global_refc.lock);
+	spin_lock(&imc_global_refc.lock);
 	/*
 	 * Check if any other trace/core imc events are running in the
 	 * system, if not set the global id to thread-imc.
@ -1010,10 +1007,10 @@ static int thread_imc_event_init(struct perf_event *event)
 		imc_global_refc.id = IMC_DOMAIN_THREAD;
 		imc_global_refc.refc++;
 	} else {
-		mutex_unlock(&imc_global_refc.lock);
+		spin_unlock(&imc_global_refc.lock);
 		return -EBUSY;
 	}
-	mutex_unlock(&imc_global_refc.lock);
+	spin_unlock(&imc_global_refc.lock);

 	event->pmu->task_ctx_nr = perf_sw_context;
 	event->destroy = reset_global_refc;
@ -1135,25 +1132,25 @@ static int thread_imc_event_add(struct perf_event *event, int flags)
 	/*
 	 * imc pmus are enabled only when it is used.
 	 * See if this is triggered for the first time.
-	 * If yes, take the mutex lock and enable the counters.
+	 * If yes, take the lock and enable the counters.
 	 * If not, just increment the count in ref count struct.
 	 */
 	ref = &core_imc_refc[core_id];
 	if (!ref)
 		return -EINVAL;

-	mutex_lock(&ref->lock);
+	spin_lock(&ref->lock);
 	if (ref->refc == 0) {
 		if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE,
 		    get_hard_smp_processor_id(smp_processor_id()))) {
-			mutex_unlock(&ref->lock);
+			spin_unlock(&ref->lock);
 			pr_err("thread-imc: Unable to start the counter\
 				for core %d\n", core_id);
 			return -EINVAL;
 		}
 	}
 	++ref->refc;
-	mutex_unlock(&ref->lock);
+	spin_unlock(&ref->lock);
 	return 0;
 }

@ -1170,12 +1167,12 @@ static void thread_imc_event_del(struct perf_event *event, int flags)
 		return;
 	}

-	mutex_lock(&ref->lock);
+	spin_lock(&ref->lock);
 	ref->refc--;
 	if (ref->refc == 0) {
 		if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
 		    get_hard_smp_processor_id(smp_processor_id()))) {
-			mutex_unlock(&ref->lock);
+			spin_unlock(&ref->lock);
 			pr_err("thread-imc: Unable to stop the counters\
 				for core %d\n", core_id);
 			return;
@ -1183,7 +1180,7 @@ static void thread_imc_event_del(struct perf_event *event, int flags)
 	} else if (ref->refc < 0) {
 		ref->refc = 0;
 	}
-	mutex_unlock(&ref->lock);
+	spin_unlock(&ref->lock);

 	/* Set bit 0 of LDBAR to zero, to stop posting updates to memory */
 	mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
@ -1224,9 +1221,8 @@ static int trace_imc_mem_alloc(int cpu_id, int size)
 		}
 	}

-	/* Init the mutex, if not already */
 	trace_imc_refc[core_id].id = core_id;
-	mutex_init(&trace_imc_refc[core_id].lock);
+	spin_lock_init(&trace_imc_refc[core_id].lock);

 	mtspr(SPRN_LDBAR, 0);
 	return 0;
@ -1246,10 +1242,10 @@ static int ppc_trace_imc_cpu_offline(unsigned int cpu)
 	 * Reduce the refc if any trace-imc event running
 	 * on this cpu.
 	 */
-	mutex_lock(&imc_global_refc.lock);
+	spin_lock(&imc_global_refc.lock);
 	if (imc_global_refc.id == IMC_DOMAIN_TRACE)
 		imc_global_refc.refc--;
-	mutex_unlock(&imc_global_refc.lock);
+	spin_unlock(&imc_global_refc.lock);

 	return 0;
 }
@ -1371,17 +1367,17 @@ static int trace_imc_event_add(struct perf_event *event, int flags)
 	}

 	mtspr(SPRN_LDBAR, ldbar_value);
-	mutex_lock(&ref->lock);
+	spin_lock(&ref->lock);
 	if (ref->refc == 0) {
 		if (opal_imc_counters_start(OPAL_IMC_COUNTERS_TRACE,
 				get_hard_smp_processor_id(smp_processor_id()))) {
-			mutex_unlock(&ref->lock);
+			spin_unlock(&ref->lock);
 			pr_err("trace-imc: Unable to start the counters for core %d\n", core_id);
 			return -EINVAL;
 		}
 	}
 	++ref->refc;
-	mutex_unlock(&ref->lock);
+	spin_unlock(&ref->lock);
 	return 0;
 }

@ -1414,19 +1410,19 @@ static void trace_imc_event_del(struct perf_event *event, int flags)
 		return;
 	}

-	mutex_lock(&ref->lock);
+	spin_lock(&ref->lock);
 	ref->refc--;
 	if (ref->refc == 0) {
 		if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_TRACE,
 				get_hard_smp_processor_id(smp_processor_id()))) {
-			mutex_unlock(&ref->lock);
+			spin_unlock(&ref->lock);
 			pr_err("trace-imc: Unable to stop the counters for core %d\n", core_id);
 			return;
 		}
 	} else if (ref->refc < 0) {
 		ref->refc = 0;
 	}
-	mutex_unlock(&ref->lock);
+	spin_unlock(&ref->lock);

 	trace_imc_event_stop(event, flags);
 }
@ -1448,7 +1444,7 @@ static int trace_imc_event_init(struct perf_event *event)
 	 * no other thread is running any core/thread imc
 	 * events
 	 */
-	mutex_lock(&imc_global_refc.lock);
+	spin_lock(&imc_global_refc.lock);
 	if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) {
 		/*
 		 * No core/thread imc events are running in the
@ -1457,10 +1453,10 @@ static int trace_imc_event_init(struct perf_event *event)
 		imc_global_refc.id = IMC_DOMAIN_TRACE;
 		imc_global_refc.refc++;
 	} else {
-		mutex_unlock(&imc_global_refc.lock);
+		spin_unlock(&imc_global_refc.lock);
 		return -EBUSY;
 	}
-	mutex_unlock(&imc_global_refc.lock);
+	spin_unlock(&imc_global_refc.lock);

 	event->hw.idx = -1;

@ -1533,10 +1529,10 @@ static int init_nest_pmu_ref(void)
 	i = 0;
 	for_each_node(nid) {
 		/*
-		 * Mutex lock to avoid races while tracking the number of
+		 * Take the lock to avoid races while tracking the number of
 		 * sessions using the chip's nest pmu units.
 		 */
-		mutex_init(&nest_imc_refc[i].lock);
+		spin_lock_init(&nest_imc_refc[i].lock);

 		/*
 		 * Loop to init the "id" with the node_id. Variable "i" initialized to
@ -1633,7 +1629,7 @@ static void imc_common_mem_free(struct imc_pmu *pmu_ptr)
 static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 {
 	if (pmu_ptr->domain == IMC_DOMAIN_NEST) {
-		mutex_lock(&nest_init_lock);
+		spin_lock(&nest_init_lock);
 		if (nest_pmus == 1) {
 			cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE);
 			kfree(nest_imc_refc);
@ -1643,7 +1639,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)

 		if (nest_pmus > 0)
 			nest_pmus--;
-		mutex_unlock(&nest_init_lock);
+		spin_unlock(&nest_init_lock);
 	}

 	/* Free core_imc memory */
@ -1800,11 +1796,11 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 		* rest. To handle the cpuhotplug callback unregister, we track
 		* the number of nest pmus in "nest_pmus".
 		*/
-		mutex_lock(&nest_init_lock);
+		spin_lock(&nest_init_lock);
 		if (nest_pmus == 0) {
 			ret = init_nest_pmu_ref();
 			if (ret) {
-				mutex_unlock(&nest_init_lock);
+				spin_unlock(&nest_init_lock);
 				kfree(per_nest_pmu_arr);
 				per_nest_pmu_arr = NULL;
 				goto err_free_mem;
@ -1812,7 +1808,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 			/* Register for cpu hotplug notification. */
 			ret = nest_pmu_cpumask_init();
 			if (ret) {
-				mutex_unlock(&nest_init_lock);
+				spin_unlock(&nest_init_lock);
 				kfree(nest_imc_refc);
 				kfree(per_nest_pmu_arr);
 				per_nest_pmu_arr = NULL;
@ -1820,7 +1816,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 			}
 		}
 		nest_pmus++;
-		mutex_unlock(&nest_init_lock);
+		spin_unlock(&nest_init_lock);
 		break;
 	case IMC_DOMAIN_CORE:
 		ret = core_imc_pmu_cpumask_init();
--- a/arch/s390/boot/decompressor.c
+++ b/arch/s390/boot/decompressor.c
@ -23,9 +23,9 @@
 #define memmove memmove
 #define memzero(s, n) memset((s), 0, (n))

-#ifdef CONFIG_KERNEL_BZIP2
+#if defined(CONFIG_KERNEL_BZIP2)
 #define BOOT_HEAP_SIZE	0x400000
-#elif CONFIG_KERNEL_ZSTD
+#elif defined(CONFIG_KERNEL_ZSTD)
 #define BOOT_HEAP_SIZE	0x30000
 #else
 #define BOOT_HEAP_SIZE	0x10000
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@ -190,7 +190,6 @@ CONFIG_NFT_CT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
-CONFIG_NFT_OBJREF=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
@ -569,6 +568,7 @@ CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 CONFIG_LEGACY_PTY_COUNT=0
+# CONFIG_LEGACY_TIOCSTI is not set
 CONFIG_VIRTIO_CONSOLE=m
 CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_HANGCHECK_TIMER=m
@ -660,6 +660,7 @@ CONFIG_CONFIGFS_FS=m
 CONFIG_ECRYPT_FS=m
 CONFIG_CRAMFS=m
 CONFIG_SQUASHFS=m
+CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y
 CONFIG_SQUASHFS_XATTR=y
 CONFIG_SQUASHFS_LZ4=y
 CONFIG_SQUASHFS_LZO=y
@ -705,6 +706,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
 CONFIG_SECURITY_LANDLOCK=y
 CONFIG_INTEGRITY_SIGNATURE=y
 CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
+CONFIG_INTEGRITY_PLATFORM_KEYRING=y
 CONFIG_IMA=y
 CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
@ -781,6 +783,7 @@ CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
 CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_DEV_VIRTIO=m
+CONFIG_SYSTEM_BLACKLIST_KEYRING=y
 CONFIG_CORDIC=m
 CONFIG_CRYPTO_LIB_CURVE25519=m
 CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
@ -848,7 +851,6 @@ CONFIG_PREEMPT_TRACER=y
 CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_FTRACE_STARTUP_TEST=y
 # CONFIG_EVENT_TRACE_STARTUP_TEST is not set
@ -870,7 +872,6 @@ CONFIG_FAIL_MAKE_REQUEST=y
 CONFIG_FAIL_IO_TIMEOUT=y
 CONFIG_FAIL_FUTEX=y
 CONFIG_FAULT_INJECTION_DEBUG_FS=y
-CONFIG_FAIL_FUNCTION=y
 CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
 CONFIG_LKDTM=m
 CONFIG_TEST_MIN_HEAP=y
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@ -181,7 +181,6 @@ CONFIG_NFT_CT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
-CONFIG_NFT_OBJREF=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
@ -559,6 +558,7 @@ CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 CONFIG_LEGACY_PTY_COUNT=0
+# CONFIG_LEGACY_TIOCSTI is not set
 CONFIG_VIRTIO_CONSOLE=m
 CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_HANGCHECK_TIMER=m
@ -645,6 +645,7 @@ CONFIG_CONFIGFS_FS=m
 CONFIG_ECRYPT_FS=m
 CONFIG_CRAMFS=m
 CONFIG_SQUASHFS=m
+CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y
 CONFIG_SQUASHFS_XATTR=y
 CONFIG_SQUASHFS_LZ4=y
 CONFIG_SQUASHFS_LZO=y
@ -688,6 +689,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
 CONFIG_SECURITY_LANDLOCK=y
 CONFIG_INTEGRITY_SIGNATURE=y
 CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
+CONFIG_INTEGRITY_PLATFORM_KEYRING=y
 CONFIG_IMA=y
 CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
@ -766,6 +768,7 @@ CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
 CONFIG_CRYPTO_PAES_S390=m
 CONFIG_CRYPTO_DEV_VIRTIO=m
+CONFIG_SYSTEM_BLACKLIST_KEYRING=y
 CONFIG_CORDIC=m
 CONFIG_PRIME_NUMBERS=m
 CONFIG_CRYPTO_LIB_CURVE25519=m
@ -798,7 +801,6 @@ CONFIG_STACK_TRACER=y
 CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_SAMPLES=y
 CONFIG_SAMPLE_TRACE_PRINTK=m
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@ -13,7 +13,6 @@ CONFIG_TUNE_ZEC12=y
 # CONFIG_COMPAT is not set
 CONFIG_NR_CPUS=2
 CONFIG_HZ_100=y
-# CONFIG_RELOCATABLE is not set
 # CONFIG_CHSC_SCH is not set
 # CONFIG_SCM_BUS is not set
 CONFIG_CRASH_DUMP=y
@ -50,6 +49,7 @@ CONFIG_ZFCP=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
+# CONFIG_LEGACY_TIOCSTI is not set
 # CONFIG_HVC_IUCV is not set
 # CONFIG_HW_RANDOM_S390 is not set
 # CONFIG_HMC_DRV is not set
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@ -131,19 +131,21 @@ struct hws_combined_entry {
 	struct hws_diag_entry	diag;	/* Diagnostic-sampling data entry */
 } __packed;

-struct hws_trailer_entry {
-	union {
-		struct {
-			unsigned int f:1;	/* 0 - Block Full Indicator   */
-			unsigned int a:1;	/* 1 - Alert request control  */
-			unsigned int t:1;	/* 2 - Timestamp format	      */
-			unsigned int :29;	/* 3 - 31: Reserved	      */
-			unsigned int bsdes:16;	/* 32-47: size of basic SDE   */
-			unsigned int dsdes:16;	/* 48-63: size of diagnostic SDE */
-		};
-		unsigned long long flags;	/* 0 - 63: All indicators     */
+union hws_trailer_header {
+	struct {
+		unsigned int f:1;	/* 0 - Block Full Indicator   */
+		unsigned int a:1;	/* 1 - Alert request control  */
+		unsigned int t:1;	/* 2 - Timestamp format	      */
+		unsigned int :29;	/* 3 - 31: Reserved	      */
+		unsigned int bsdes:16;	/* 32-47: size of basic SDE   */
+		unsigned int dsdes:16;	/* 48-63: size of diagnostic SDE */
+		unsigned long long overflow; /* 64 - Overflow Count   */
 	};
-	unsigned long long overflow;	 /* 64 - sample Overflow count	      */
+	__uint128_t val;
+};
+
+struct hws_trailer_entry {
+	union hws_trailer_header header; /* 0 - 15 Flags + Overflow Count     */
 	unsigned char timestamp[16];	 /* 16 - 31 timestamp		      */
 	unsigned long long reserved1;	 /* 32 -Reserved		      */
 	unsigned long long reserved2;	 /*				      */
@ -290,14 +292,11 @@ static inline unsigned long sample_rate_to_freq(struct hws_qsi_info_block *qsi,
 	return USEC_PER_SEC * qsi->cpu_speed / rate;
 }

-#define SDB_TE_ALERT_REQ_MASK	0x4000000000000000UL
-#define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL
-
 /* Return TOD timestamp contained in an trailer entry */
 static inline unsigned long long trailer_timestamp(struct hws_trailer_entry *te)
 {
 	/* TOD in STCKE format */
-	if (te->t)
+	if (te->header.t)
 		return *((unsigned long long *) &te->timestamp[1]);

 	/* TOD in STCK format */
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@ -4,8 +4,8 @@
 *
 *    Copyright IBM Corp. 1999, 2020
 */
-#ifndef DEBUG_H
-#define DEBUG_H
+#ifndef _ASM_S390_DEBUG_H
+#define _ASM_S390_DEBUG_H

 #include <linux/string.h>
 #include <linux/spinlock.h>
@ -487,4 +487,4 @@ void debug_register_static(debug_info_t *id, int pages_per_area, int nr_areas);

 #endif /* MODULE */

-#endif /* DEBUG_H */
+#endif /* _ASM_S390_DEBUG_H */
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@ -31,7 +31,7 @@
 	pcp_op_T__ *ptr__;						\
 	preempt_disable_notrace();					\
 	ptr__ = raw_cpu_ptr(&(pcp));					\
-	prev__ = *ptr__;						\
+	prev__ = READ_ONCE(*ptr__);					\
 	do {								\
 		old__ = prev__;						\
 		new__ = old__ op (val);					\
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@ -187,8 +187,6 @@ static int kexec_file_add_ipl_report(struct kimage *image,

 	data->memsz = ALIGN(data->memsz, PAGE_SIZE);
 	buf.mem = data->memsz;
-	if (image->type == KEXEC_TYPE_CRASH)
-		buf.mem += crashk_res.start;

 	ptr = (void *)ipl_cert_list_addr;
 	end = ptr + ipl_cert_list_size;
@ -225,6 +223,9 @@ static int kexec_file_add_ipl_report(struct kimage *image,
 		data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr);
 	*lc_ipl_parmblock_ptr = (__u32)buf.mem;

+	if (image->type == KEXEC_TYPE_CRASH)
+		buf.mem += crashk_res.start;
+
 	ret = kexec_add_buffer(&buf);
 out:
 	return ret;
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@ -163,14 +163,15 @@ static void free_sampling_buffer(struct sf_buffer *sfb)

 static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags)
 {
-	unsigned long sdb, *trailer;
+	struct hws_trailer_entry *te;
+	unsigned long sdb;

 	/* Allocate and initialize sample-data-block */
 	sdb = get_zeroed_page(gfp_flags);
 	if (!sdb)
 		return -ENOMEM;
-	trailer = trailer_entry_ptr(sdb);
-	*trailer = SDB_TE_ALERT_REQ_MASK;
+	te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb);
+	te->header.a = 1;

 	/* Link SDB into the sample-data-block-table */
 	*sdbt = sdb;
@ -1206,7 +1207,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
 					    "%s: Found unknown"
 					    " sampling data entry: te->f %i"
 					    " basic.def %#4x (%p)\n", __func__,
-					    te->f, sample->def, sample);
+					    te->header.f, sample->def, sample);
 			/* Sample slot is not yet written or other record.
 			 *
 			 * This condition can occur if the buffer was reused
@ -1217,7 +1218,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
 			 * that are not full.  Stop processing if the first
 			 * invalid format was detected.
 			 */
-			if (!te->f)
+			if (!te->header.f)
 				break;
 		}

@ -1227,6 +1228,16 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
 	}
 }

+static inline __uint128_t __cdsg(__uint128_t *ptr, __uint128_t old, __uint128_t new)
+{
+	asm volatile(
+		"	cdsg	%[old],%[new],%[ptr]\n"
+		: [old] "+d" (old), [ptr] "+QS" (*ptr)
+		: [new] "d" (new)
+		: "memory", "cc");
+	return old;
+}
+
 /* hw_perf_event_update() - Process sampling buffer
 * @event:	The perf event
 * @flush_all:	Flag to also flush partially filled sample-data-blocks
@ -1243,10 +1254,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
 */
 static void hw_perf_event_update(struct perf_event *event, int flush_all)
 {
+	unsigned long long event_overflow, sampl_overflow, num_sdb;
+	union hws_trailer_header old, prev, new;
 	struct hw_perf_event *hwc = &event->hw;
 	struct hws_trailer_entry *te;
 	unsigned long *sdbt;
-	unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags;
 	int done;

 	/*
@ -1266,25 +1278,25 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 		te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt);

 		/* Leave loop if no more work to do (block full indicator) */
-		if (!te->f) {
+		if (!te->header.f) {
 			done = 1;
 			if (!flush_all)
 				break;
 		}

 		/* Check the sample overflow count */
-		if (te->overflow)
+		if (te->header.overflow)
 			/* Account sample overflows and, if a particular limit
 			 * is reached, extend the sampling buffer.
 			 * For details, see sfb_account_overflows().
 			 */
-			sampl_overflow += te->overflow;
+			sampl_overflow += te->header.overflow;

 		/* Timestamps are valid for full sample-data-blocks only */
 		debug_sprintf_event(sfdbg, 6, "%s: sdbt %#lx "
 				    "overflow %llu timestamp %#llx\n",
-				    __func__, (unsigned long)sdbt, te->overflow,
-				    (te->f) ? trailer_timestamp(te) : 0ULL);
+				    __func__, (unsigned long)sdbt, te->header.overflow,
+				    (te->header.f) ? trailer_timestamp(te) : 0ULL);

 		/* Collect all samples from a single sample-data-block and
 		 * flag if an (perf) event overflow happened.  If so, the PMU
@ -1294,12 +1306,16 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 		num_sdb++;

 		/* Reset trailer (using compare-double-and-swap) */
+		/* READ_ONCE() 16 byte header */
+		prev.val = __cdsg(&te->header.val, 0, 0);
 		do {
-			te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK;
-			te_flags |= SDB_TE_ALERT_REQ_MASK;
-		} while (!cmpxchg_double(&te->flags, &te->overflow,
-					 te->flags, te->overflow,
-					 te_flags, 0ULL));
+			old.val = prev.val;
+			new.val = prev.val;
+			new.f = 0;
+			new.a = 1;
+			new.overflow = 0;
+			prev.val = __cdsg(&te->header.val, old.val, new.val);
+		} while (prev.val != old.val);

 		/* Advance to next sample-data-block */
 		sdbt++;
@ -1384,7 +1400,7 @@ static void aux_output_end(struct perf_output_handle *handle)
 	range_scan = AUX_SDB_NUM_ALERT(aux);
 	for (i = 0, idx = aux->head; i < range_scan; i++, idx++) {
 		te = aux_sdb_trailer(aux, idx);
-		if (!(te->flags & SDB_TE_BUFFER_FULL_MASK))
+		if (!te->header.f)
 			break;
 	}
 	/* i is num of SDBs which are full */
@ -1392,7 +1408,7 @@ static void aux_output_end(struct perf_output_handle *handle)

 	/* Remove alert indicators in the buffer */
 	te = aux_sdb_trailer(aux, aux->alert_mark);
-	te->flags &= ~SDB_TE_ALERT_REQ_MASK;
+	te->header.a = 0;

 	debug_sprintf_event(sfdbg, 6, "%s: SDBs %ld range %ld head %ld\n",
 			    __func__, i, range_scan, aux->head);
@ -1437,9 +1453,9 @@ static int aux_output_begin(struct perf_output_handle *handle,
 		idx = aux->empty_mark + 1;
 		for (i = 0; i < range_scan; i++, idx++) {
 			te = aux_sdb_trailer(aux, idx);
-			te->flags &= ~(SDB_TE_BUFFER_FULL_MASK |
-				       SDB_TE_ALERT_REQ_MASK);
-			te->overflow = 0;
+			te->header.f = 0;
+			te->header.a = 0;
+			te->header.overflow = 0;
 		}
 		/* Save the position of empty SDBs */
 		aux->empty_mark = aux->head + range - 1;
@ -1448,7 +1464,7 @@ static int aux_output_begin(struct perf_output_handle *handle,
 	/* Set alert indicator */
 	aux->alert_mark = aux->head + range/2 - 1;
 	te = aux_sdb_trailer(aux, aux->alert_mark);
-	te->flags = te->flags | SDB_TE_ALERT_REQ_MASK;
+	te->header.a = 1;

 	/* Reset hardware buffer head */
 	head = AUX_SDB_INDEX(aux, aux->head);
@ -1475,14 +1491,17 @@ static int aux_output_begin(struct perf_output_handle *handle,
 static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index,
 			  unsigned long long *overflow)
 {
-	unsigned long long orig_overflow, orig_flags, new_flags;
+	union hws_trailer_header old, prev, new;
 	struct hws_trailer_entry *te;

 	te = aux_sdb_trailer(aux, alert_index);
+	/* READ_ONCE() 16 byte header */
+	prev.val = __cdsg(&te->header.val, 0, 0);
 	do {
-		orig_flags = te->flags;
-		*overflow = orig_overflow = te->overflow;
-		if (orig_flags & SDB_TE_BUFFER_FULL_MASK) {
+		old.val = prev.val;
+		new.val = prev.val;
+		*overflow = old.overflow;
+		if (old.f) {
 			/*
 			 * SDB is already set by hardware.
 			 * Abort and try to set somewhere
@ -1490,10 +1509,10 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index,
 			 */
 			return false;
 		}
-		new_flags = orig_flags | SDB_TE_ALERT_REQ_MASK;
-	} while (!cmpxchg_double(&te->flags, &te->overflow,
-				 orig_flags, orig_overflow,
-				 new_flags, 0ULL));
+		new.a = 1;
+		new.overflow = 0;
+		prev.val = __cdsg(&te->header.val, old.val, new.val);
+	} while (prev.val != old.val);
 	return true;
 }

@ -1522,8 +1541,9 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index,
 static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range,
 			     unsigned long long *overflow)
 {
-	unsigned long long orig_overflow, orig_flags, new_flags;
 	unsigned long i, range_scan, idx, idx_old;
+	union hws_trailer_header old, prev, new;
+	unsigned long long orig_overflow;
 	struct hws_trailer_entry *te;

 	debug_sprintf_event(sfdbg, 6, "%s: range %ld head %ld alert %ld "
@ -1554,17 +1574,20 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range,
 	idx_old = idx = aux->empty_mark + 1;
 	for (i = 0; i < range_scan; i++, idx++) {
 		te = aux_sdb_trailer(aux, idx);
+		/* READ_ONCE() 16 byte header */
+		prev.val = __cdsg(&te->header.val, 0, 0);
 		do {
-			orig_flags = te->flags;
-			orig_overflow = te->overflow;
-			new_flags = orig_flags & ~SDB_TE_BUFFER_FULL_MASK;
+			old.val = prev.val;
+			new.val = prev.val;
+			orig_overflow = old.overflow;
+			new.f = 0;
+			new.overflow = 0;
 			if (idx == aux->alert_mark)
-				new_flags |= SDB_TE_ALERT_REQ_MASK;
+				new.a = 1;
 			else
-				new_flags &= ~SDB_TE_ALERT_REQ_MASK;
-		} while (!cmpxchg_double(&te->flags, &te->overflow,
-					 orig_flags, orig_overflow,
-					 new_flags, 0ULL));
+				new.a = 0;
+			prev.val = __cdsg(&te->header.val, old.val, new.val);
+		} while (prev.val != old.val);
 		*overflow += orig_overflow;
 	}

--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@ -17,6 +17,8 @@
 /* Handle ro_after_init data on our own. */
 #define RO_AFTER_INIT_DATA

+#define RUNTIME_DISCARD_EXIT
+
 #define EMITS_PT_NOTE

 #include <asm-generic/vmlinux.lds.h>
@ -79,6 +81,7 @@ SECTIONS
 		_end_amode31_refs = .;
 	}

+	. = ALIGN(PAGE_SIZE);
 	_edata = .;		/* End of data section */

 	/* will be freed after init */
@ -193,6 +196,7 @@ SECTIONS

 	BSS_SECTION(PAGE_SIZE, 4 * PAGE_SIZE, PAGE_SIZE)

+	. = ALIGN(PAGE_SIZE);
 	_end = . ;

 	/*
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@ -83,8 +83,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 		struct esca_block *sca = vcpu->kvm->arch.sca;
 		union esca_sigp_ctrl *sigp_ctrl =
 			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
-		union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+		union esca_sigp_ctrl new_val = {0}, old_val;

+		old_val = READ_ONCE(*sigp_ctrl);
 		new_val.scn = src_id;
 		new_val.c = 1;
 		old_val.c = 0;
@ -95,8 +96,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 		struct bsca_block *sca = vcpu->kvm->arch.sca;
 		union bsca_sigp_ctrl *sigp_ctrl =
 			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
-		union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+		union bsca_sigp_ctrl new_val = {0}, old_val;

+		old_val = READ_ONCE(*sigp_ctrl);
 		new_val.scn = src_id;
 		new_val.c = 1;
 		old_val.c = 0;
@ -126,16 +128,18 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
 		struct esca_block *sca = vcpu->kvm->arch.sca;
 		union esca_sigp_ctrl *sigp_ctrl =
 			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
-		union esca_sigp_ctrl old = *sigp_ctrl;
+		union esca_sigp_ctrl old;

+		old = READ_ONCE(*sigp_ctrl);
 		expect = old.value;
 		rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
 	} else {
 		struct bsca_block *sca = vcpu->kvm->arch.sca;
 		union bsca_sigp_ctrl *sigp_ctrl =
 			&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
-		union bsca_sigp_ctrl old = *sigp_ctrl;
+		union bsca_sigp_ctrl old;

+		old = READ_ONCE(*sigp_ctrl);
 		expect = old.value;
 		rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
 	}
--- a/arch/sh/include/asm/pgtable-3level.h
+++ b/arch/sh/include/asm/pgtable-3level.h
@ -28,7 +28,7 @@
 #define pmd_ERROR(e) \
 	printk("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e))

-typedef struct {
+typedef union {
 	struct {
 		unsigned long pmd_low;
 		unsigned long pmd_high;
--- a/arch/x86/boot/bioscall.S
+++ b/arch/x86/boot/bioscall.S
@ -32,7 +32,7 @@ intcall:
 	movw	%dx, %si
 	movw	%sp, %di
 	movw	$11, %cx
-	rep; movsd
+	rep; movsl

 	/* Pop full state from the stack */
 	popal
@ -67,7 +67,7 @@ intcall:
 	jz	4f
 	movw	%sp, %si
 	movw	$11, %cx
-	rep; movsd
+	rep; movsl
 4:	addw	$44, %sp

 	/* Restore state and return */
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@ -41,6 +41,7 @@
 *	MSR_CORE_C1_RES: CORE C1 Residency Counter
 *			 perf code: 0x00
 *			 Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL
+ *					  MTL
 *			 Scope: Core (each processor core has a MSR)
 *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
 *			       perf code: 0x01
@ -51,50 +52,50 @@
 *			       perf code: 0x02
 *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
 *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- *						TGL,TNT,RKL,ADL,RPL,SPR
+ *						TGL,TNT,RKL,ADL,RPL,SPR,MTL
 *			       Scope: Core
 *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
 *			       perf code: 0x03
 *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
- *						ICL,TGL,RKL,ADL,RPL
+ *						ICL,TGL,RKL,ADL,RPL,MTL
 *			       Scope: Core
 *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
 *			       perf code: 0x00
 *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
 *						KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL,
- *						RPL,SPR
+ *						RPL,SPR,MTL
 *			       Scope: Package (physical package)
 *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
 *			       perf code: 0x01
 *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
 *						GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL,
- *						ADL,RPL
+ *						ADL,RPL,MTL
 *			       Scope: Package (physical package)
 *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
 *			       perf code: 0x02
 *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
 *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- *						TGL,TNT,RKL,ADL,RPL,SPR
+ *						TGL,TNT,RKL,ADL,RPL,SPR,MTL
 *			       Scope: Package (physical package)
 *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
 *			       perf code: 0x03
 *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
- *						KBL,CML,ICL,TGL,RKL,ADL,RPL
+ *						KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL
 *			       Scope: Package (physical package)
 *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
 *			       perf code: 0x04
 *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- *						ADL,RPL
+ *						ADL,RPL,MTL
 *			       Scope: Package (physical package)
 *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
 *			       perf code: 0x05
 *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- *						ADL,RPL
+ *						ADL,RPL,MTL
 *			       Scope: Package (physical package)
 *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
 *			       perf code: 0x06
 *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
- *						TNT,RKL,ADL,RPL
+ *						TNT,RKL,ADL,RPL,MTL
 *			       Scope: Package (physical package)
 *
 */
@ -686,6 +687,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_cstates),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&adl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE,		&adl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&adl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@ -1833,6 +1833,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&spr_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&snr_uncore_init),
 	{},
 };
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@ -69,6 +69,7 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_BROADWELL_G:
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SAPPHIRERAPIDS_X:
+	case INTEL_FAM6_EMERALDRAPIDS_X:

 	case INTEL_FAM6_ATOM_SILVERMONT:
 	case INTEL_FAM6_ATOM_SILVERMONT_D:
@ -107,6 +108,8 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_RAPTORLAKE:
 	case INTEL_FAM6_RAPTORLAKE_P:
 	case INTEL_FAM6_RAPTORLAKE_S:
+	case INTEL_FAM6_METEORLAKE:
+	case INTEL_FAM6_METEORLAKE_L:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@ -1111,6 +1111,7 @@ struct msr_bitmap_range {

 /* Xen emulation context */
 struct kvm_xen {
+	struct mutex xen_lock;
 	u32 xen_version;
 	bool long_mode;
 	bool runstate_update_flag;
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@ -2364,9 +2364,8 @@ static int mp_irqdomain_create(int ioapic)
 		return -ENODEV;
 	}

-	ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops,
-						 (void *)(long)ioapic);
-
+	ip->irqdomain = irq_domain_create_hierarchy(parent, 0, hwirqs, fn, cfg->ops,
+						    (void *)(long)ioapic);
 	if (!ip->irqdomain) {
 		/* Release fw handle if it was allocated above */
 		if (!cfg->dev)
@ -2374,8 +2373,6 @@ static int mp_irqdomain_create(int ioapic)
 		return -ENOMEM;
 	}

-	ip->irqdomain->parent = parent;
-
 	if (cfg->type == IOAPIC_DOMAIN_LEGACY ||
 	    cfg->type == IOAPIC_DOMAIN_STRICT)
 		ioapic_dynirq_base = max(ioapic_dynirq_base,
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@ -146,6 +146,30 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
 	return entry;
 }

+static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
+{
+	u64 msr_val;
+
+	/*
+	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
+	 * with a valid event code for supported resource type and the bits
+	 * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
+	 * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
+	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
+	 * are error bits.
+	 */
+	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+	rdmsrl(MSR_IA32_QM_CTR, msr_val);
+
+	if (msr_val & RMID_VAL_ERROR)
+		return -EIO;
+	if (msr_val & RMID_VAL_UNAVAIL)
+		return -EINVAL;
+
+	*val = msr_val;
+	return 0;
+}
+
 static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
 						 u32 rmid,
 						 enum resctrl_event_id eventid)
@ -172,8 +196,12 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
 	struct arch_mbm_state *am;

 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
-	if (am)
+	if (am) {
 		memset(am, 0, sizeof(*am));
+
+		/* Record any initial, non-zero count value. */
+		__rmid_read(rmid, eventid, &am->prev_msr);
+	}
 }

 static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
@ -191,25 +219,14 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
 	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
 	struct arch_mbm_state *am;
 	u64 msr_val, chunks;
+	int ret;

 	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
 		return -EINVAL;

-	/*
-	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
-	 * with a valid event code for supported resource type and the bits
-	 * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
-	 * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
-	 * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
-	 * are error bits.
-	 */
-	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
-	rdmsrl(MSR_IA32_QM_CTR, msr_val);
-
-	if (msr_val & RMID_VAL_ERROR)
-		return -EIO;
-	if (msr_val & RMID_VAL_UNAVAIL)
-		return -EINVAL;
+	ret = __rmid_read(rmid, eventid, &msr_val);
+	if (ret)
+		return ret;

 	am = get_arch_mbm_state(hw_dom, rmid, eventid);
 	if (am) {
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@ -580,8 +580,10 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	/*
 	 * Ensure the task's closid and rmid are written before determining if
 	 * the task is current that will decide if it will be interrupted.
+	 * This pairs with the full barrier between the rq->curr update and
+	 * resctrl_sched_in() during context switch.
 	 */
-	barrier();
+	smp_mb();

 	/*
 	 * By now, the task's closid and rmid are set. If the task is current
@ -2401,6 +2403,14 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
 			WRITE_ONCE(t->closid, to->closid);
 			WRITE_ONCE(t->rmid, to->mon.rmid);

+			/*
+			 * Order the closid/rmid stores above before the loads
+			 * in task_curr(). This pairs with the full barrier
+			 * between the rq->curr update and resctrl_sched_in()
+			 * during context switch.
+			 */
+			smp_mb();
+
 			/*
 			 * If the task is on a CPU, set the CPU in the mask.
 			 * The detection is inaccurate as tasks might move or
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@ -770,15 +770,21 @@ struct kvm_cpuid_array {
 	int nent;
 };

-static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
-					      u32 function, u32 index)
+static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array)
 {
-	struct kvm_cpuid_entry2 *entry;
-
 	if (array->nent >= array->maxnent)
 		return NULL;

-	entry = &array->entries[array->nent++];
+	return &array->entries[array->nent++];
+}
+
+static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
+					      u32 function, u32 index)
+{
+	struct kvm_cpuid_entry2 *entry = get_next_cpuid(array);
+
+	if (!entry)
+		return NULL;

 	memset(entry, 0, sizeof(*entry));
 	entry->function = function;
@ -956,22 +962,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		entry->edx = edx.full;
 		break;
 	}
-	/*
-	 * Per Intel's SDM, the 0x1f is a superset of 0xb,
-	 * thus they can be handled by common code.
-	 */
 	case 0x1f:
 	case 0xb:
 		/*
-		 * Populate entries until the level type (ECX[15:8]) of the
-		 * previous entry is zero.  Note, CPUID EAX.{0x1f,0xb}.0 is
-		 * the starting entry, filled by the primary do_host_cpuid().
+		 * No topology; a valid topology is indicated by the presence
+		 * of subleaf 1.
 		 */
-		for (i = 1; entry->ecx & 0xff00; ++i) {
-			entry = do_host_cpuid(array, function, i);
-			if (!entry)
-				goto out;
-		}
+		entry->eax = entry->ebx = entry->ecx = 0;
 		break;
 	case 0xd: {
 		u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm();
@ -1202,6 +1199,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		entry->ebx = entry->ecx = entry->edx = 0;
 		break;
 	case 0x8000001e:
+		/* Do not return host topology information.  */
+		entry->eax = entry->ebx = entry->ecx = 0;
+		entry->edx = 0; /* reserved */
 		break;
 	case 0x8000001F:
 		if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@ -138,15 +138,13 @@ void recalc_intercepts(struct vcpu_svm *svm)
 		c->intercepts[i] = h->intercepts[i];

 	if (g->int_ctl & V_INTR_MASKING_MASK) {
-		/* We only want the cr8 intercept bits of L1 */
-		vmcb_clr_intercept(c, INTERCEPT_CR8_READ);
-		vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
-
 		/*
-		 * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not
-		 * affect any interrupt we may want to inject; therefore,
-		 * interrupt window vmexits are irrelevant to L0.
+		 * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8
+		 * does not affect any interrupt we may want to inject;
+		 * therefore, writes to CR8 are irrelevant to L0, as are
+		 * interrupt window vmexits.
 		 */
+		vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
 		vmcb_clr_intercept(c, INTERCEPT_VINTR);
 	}

--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@ -271,7 +271,15 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic)
 	 * Attempt to obtain the GPC lock on *both* (if there are two)
 	 * gfn_to_pfn caches that cover the region.
 	 */
-	read_lock_irqsave(&gpc1->lock, flags);
+	if (atomic) {
+		local_irq_save(flags);
+		if (!read_trylock(&gpc1->lock)) {
+			local_irq_restore(flags);
+			return;
+		}
+	} else {
+		read_lock_irqsave(&gpc1->lock, flags);
+	}
 	while (!kvm_gpc_check(gpc1, user_len1)) {
 		read_unlock_irqrestore(&gpc1->lock, flags);

@ -304,9 +312,18 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic)
 		 * The guest's runstate_info is split across two pages and we
 		 * need to hold and validate both GPCs simultaneously. We can
 		 * declare a lock ordering GPC1 > GPC2 because nothing else
-		 * takes them more than one at a time.
+		 * takes them more than one at a time. Set a subclass on the
+		 * gpc1 lock to make lockdep shut up about it.
 		 */
-		read_lock(&gpc2->lock);
+		lock_set_subclass(&gpc1->lock.dep_map, 1, _THIS_IP_);
+		if (atomic) {
+			if (!read_trylock(&gpc2->lock)) {
+				read_unlock_irqrestore(&gpc1->lock, flags);
+				return;
+			}
+		} else {
+			read_lock(&gpc2->lock);
+		}

 		if (!kvm_gpc_check(gpc2, user_len2)) {
 			read_unlock(&gpc2->lock);
@ -590,26 +607,26 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) {
 			r = -EINVAL;
 		} else {
-			mutex_lock(&kvm->lock);
+			mutex_lock(&kvm->arch.xen.xen_lock);
 			kvm->arch.xen.long_mode = !!data->u.long_mode;
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->arch.xen.xen_lock);
 			r = 0;
 		}
 		break;

 	case KVM_XEN_ATTR_TYPE_SHARED_INFO:
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.xen.xen_lock);
 		r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn);
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		break;

 	case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
 		if (data->u.vector && data->u.vector < 0x10)
 			r = -EINVAL;
 		else {
-			mutex_lock(&kvm->lock);
+			mutex_lock(&kvm->arch.xen.xen_lock);
 			kvm->arch.xen.upcall_vector = data->u.vector;
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->arch.xen.xen_lock);
 			r = 0;
 		}
 		break;
@ -619,9 +636,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		break;

 	case KVM_XEN_ATTR_TYPE_XEN_VERSION:
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.xen.xen_lock);
 		kvm->arch.xen.xen_version = data->u.xen_version;
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		r = 0;
 		break;

@ -630,9 +647,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 			r = -EOPNOTSUPP;
 			break;
 		}
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.xen.xen_lock);
 		kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag;
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		r = 0;
 		break;

@ -647,7 +664,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 {
 	int r = -ENOENT;

-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);

 	switch (data->type) {
 	case KVM_XEN_ATTR_TYPE_LONG_MODE:
@ -686,7 +703,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		break;
 	}

-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	return r;
 }

@ -694,7 +711,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 {
 	int idx, r = -ENOENT;

-	mutex_lock(&vcpu->kvm->lock);
+	mutex_lock(&vcpu->kvm->arch.xen.xen_lock);
 	idx = srcu_read_lock(&vcpu->kvm->srcu);

 	switch (data->type) {
@ -922,7 +939,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 	}

 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-	mutex_unlock(&vcpu->kvm->lock);
+	mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
 	return r;
 }

@ -930,7 +947,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 {
 	int r = -ENOENT;

-	mutex_lock(&vcpu->kvm->lock);
+	mutex_lock(&vcpu->kvm->arch.xen.xen_lock);

 	switch (data->type) {
 	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO:
@ -1013,7 +1030,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
 		break;
 	}

-	mutex_unlock(&vcpu->kvm->lock);
+	mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
 	return r;
 }

@ -1106,7 +1123,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 	     xhc->blob_size_32 || xhc->blob_size_64))
 		return -EINVAL;

-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);

 	if (xhc->msr && !kvm->arch.xen_hvm_config.msr)
 		static_branch_inc(&kvm_xen_enabled.key);
@ -1115,7 +1132,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)

 	memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));

-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	return 0;
 }

@ -1658,15 +1675,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm)
 		mm_borrowed = true;
 	}

-	/*
-	 * For the irqfd workqueue, using the main kvm->lock mutex is
-	 * fine since this function is invoked from kvm_set_irq() with
-	 * no other lock held, no srcu. In future if it will be called
-	 * directly from a vCPU thread (e.g. on hypercall for an IPI)
-	 * then it may need to switch to using a leaf-node mutex for
-	 * serializing the shared_info mapping.
-	 */
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);

 	/*
 	 * It is theoretically possible for the page to be unmapped
@ -1695,7 +1704,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm)
 		srcu_read_unlock(&kvm->srcu, idx);
 	} while(!rc);

-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);

 	if (mm_borrowed)
 		kthread_unuse_mm(kvm->mm);
@ -1811,7 +1820,7 @@ static int kvm_xen_eventfd_update(struct kvm *kvm,
 	int ret;

 	/* Protect writes to evtchnfd as well as the idr lookup.  */
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 	evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port);

 	ret = -ENOENT;
@ -1842,7 +1851,7 @@ static int kvm_xen_eventfd_update(struct kvm *kvm,
 	}
 	ret = 0;
 out_unlock:
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	return ret;
 }

@ -1905,10 +1914,10 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm,
 		evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority;
 	}

-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 	ret = idr_alloc(&kvm->arch.xen.evtchn_ports, evtchnfd, port, port + 1,
 			GFP_KERNEL);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);
 	if (ret >= 0)
 		return 0;

@ -1926,9 +1935,9 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port)
 {
 	struct evtchnfd *evtchnfd;

-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);
 	evtchnfd = idr_remove(&kvm->arch.xen.evtchn_ports, port);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);

 	if (!evtchnfd)
 		return -ENOENT;
@ -1946,7 +1955,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)
 	int i;
 	int n = 0;

-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.xen.xen_lock);

 	/*
 	 * Because synchronize_srcu() cannot be called inside the
@ -1958,7 +1967,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)

 	all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL);
 	if (!all_evtchnfds) {
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.xen.xen_lock);
 		return -ENOMEM;
 	}

@ -1967,7 +1976,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)
 		all_evtchnfds[n++] = evtchnfd;
 		idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port);
 	}
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.xen.xen_lock);

 	synchronize_srcu(&kvm->srcu);

@ -2069,6 +2078,7 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)

 void kvm_xen_init_vm(struct kvm *kvm)
 {
+	mutex_init(&kvm->arch.xen.xen_lock);
 	idr_init(&kvm->arch.xen.evtchn_ports);
 	kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN);
 }
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@ -26,6 +26,7 @@
 #include <asm/pti.h>
 #include <asm/text-patching.h>
 #include <asm/memtype.h>
+#include <asm/paravirt.h>

 /*
 * We need to define the tracepoints somewhere, and tlb.c
@ -804,6 +805,9 @@ void __init poking_init(void)
 	poking_mm = mm_alloc();
 	BUG_ON(!poking_mm);

+	/* Xen PV guests need the PGD to be pinned. */
+	paravirt_arch_dup_mmap(NULL, poking_mm);
+
 	/*
 	 * Randomize the poking address, but make sure that the following page
 	 * will be mapped at the same PMD. We need 2 pages, so find space for 3,
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@ -387,7 +387,8 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end,
 		u8 mtrr_type, uniform;

 		mtrr_type = mtrr_type_lookup(start, end, &uniform);
-		if (mtrr_type != MTRR_TYPE_WRBACK)
+		if (mtrr_type != MTRR_TYPE_WRBACK &&
+		    mtrr_type != MTRR_TYPE_INVALID)
 			return _PAGE_CACHE_MODE_UC_MINUS;

 		return _PAGE_CACHE_MODE_WB;
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@ -12,6 +12,7 @@
 */

 #include <linux/acpi.h>
+#include <linux/efi.h>
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/bitmap.h>
@ -442,17 +443,42 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used)
 	return mcfg_res.flags;
 }

+static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used)
+{
+#ifdef CONFIG_EFI
+	efi_memory_desc_t *md;
+	u64 size, mmio_start, mmio_end;
+
+	for_each_efi_memory_desc(md) {
+		if (md->type == EFI_MEMORY_MAPPED_IO) {
+			size = md->num_pages << EFI_PAGE_SHIFT;
+			mmio_start = md->phys_addr;
+			mmio_end = mmio_start + size;
+
+			/*
+			 * N.B. Caller supplies (start, start + size),
+			 * so to match, mmio_end is the first address
+			 * *past* the EFI_MEMORY_MAPPED_IO area.
+			 */
+			if (mmio_start <= start && end <= mmio_end)
+				return true;
+		}
+	}
+#endif
+
+	return false;
+}
+
 typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type);

 static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
 				     struct pci_mmcfg_region *cfg,
-				     struct device *dev, int with_e820)
+				     struct device *dev, const char *method)
 {
 	u64 addr = cfg->res.start;
 	u64 size = resource_size(&cfg->res);
 	u64 old_size = size;
 	int num_buses;
-	char *method = with_e820 ? "E820" : "ACPI motherboard resources";

 	while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) {
 		size >>= 1;
@ -464,10 +490,10 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
 		return false;

 	if (dev)
-		dev_info(dev, "MMCONFIG at %pR reserved in %s\n",
+		dev_info(dev, "MMCONFIG at %pR reserved as %s\n",
 			 &cfg->res, method);
 	else
-		pr_info(PREFIX "MMCONFIG at %pR reserved in %s\n",
+		pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n",
 		       &cfg->res, method);

 	if (old_size != size) {
@ -500,7 +526,8 @@ static bool __ref
 pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early)
 {
 	if (!early && !acpi_disabled) {
-		if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0))
+		if (is_mmconf_reserved(is_acpi_reserved, cfg, dev,
+				       "ACPI motherboard resource"))
 			return true;

 		if (dev)
@ -513,6 +540,10 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e
 			       "MMCONFIG at %pR not reserved in "
 			       "ACPI motherboard resources\n",
 			       &cfg->res);
+
+		if (is_mmconf_reserved(is_efi_mmio, cfg, dev,
+				       "EfiMemoryMappedIO"))
+			return true;
 	}

 	/*
@ -527,7 +558,8 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e
 	/* Don't try to do this check unless configuration
 	   type 1 is available. how about type 2 ?*/
 	if (raw_pci_ops)
-		return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1);
+		return is_mmconf_reserved(e820__mapped_all, cfg, dev,
+					  "E820 entry");

 	return false;
 }
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@ -166,10 +166,9 @@ static struct irq_domain *uv_get_irq_domain(void)
 	if (!fn)
 		goto out;

-	uv_domain = irq_domain_create_tree(fn, &uv_domain_ops, NULL);
-	if (uv_domain)
-		uv_domain->parent = x86_vector_domain;
-	else
+	uv_domain = irq_domain_create_hierarchy(x86_vector_domain, 0, 0, fn,
+						&uv_domain_ops, NULL);
+	if (!uv_domain)
 		irq_domain_free_fwnode(fn);
 out:
 	mutex_unlock(&uv_lock);
--- a/arch/x86/um/elfcore.c
+++ b/arch/x86/um/elfcore.c
@ -7,7 +7,7 @@
 #include <asm/elf.h>


-Elf32_Half elf_core_extra_phdrs(void)
+Elf32_Half elf_core_extra_phdrs(struct coredump_params *cprm)
 {
 	return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0;
 }
@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm)
 	return 1;
 }

-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
 {
 	if ( vsyscall_ehdr ) {
 		const struct elfhdr *const ehdrp =
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@ -134,11 +134,6 @@ static inline unsigned p2m_mid_index(unsigned long pfn)
 	return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
 }

-static inline unsigned p2m_index(unsigned long pfn)
-{
-	return pfn % P2M_PER_PAGE;
-}
-
 static void p2m_top_mfn_init(unsigned long *top)
 {
 	unsigned i;
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@ -154,11 +154,6 @@ struct thread_struct {
 	unsigned long ra; /* kernel's a0: return address and window call size */
 	unsigned long sp; /* kernel's a1: stack pointer */

-	/* struct xtensa_cpuinfo info; */
-
-	unsigned long bad_vaddr; /* last user fault */
-	unsigned long bad_uaddr; /* last kernel fault accessing user space */
-	unsigned long error_code;
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	struct perf_event *ptrace_bp[XCHAL_NUM_IBREAK];
 	struct perf_event *ptrace_wp[XCHAL_NUM_DBREAK];
@ -176,10 +171,6 @@ struct thread_struct {
 {									\
 	ra:		0, 						\
 	sp:		sizeof(init_stack) + (long) &init_stack,	\
-	/*info:		{0}, */						\
-	bad_vaddr:	0,						\
-	bad_uaddr:	0,						\
-	error_code:	0,						\
 }


--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@ -362,8 +362,6 @@ static void do_unaligned_user(struct pt_regs *regs)
 	__die_if_kernel("Unhandled unaligned exception in kernel",
 			regs, SIGKILL);

-	current->thread.bad_vaddr = regs->excvaddr;
-	current->thread.error_code = -3;
 	pr_info_ratelimited("Unaligned memory access to %08lx in '%s' "
 			    "(pid = %d, pc = %#010lx)\n",
 			    regs->excvaddr, current->comm,
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@ -206,8 +206,6 @@ void do_page_fault(struct pt_regs *regs)
 bad_area:
 	mmap_read_unlock(mm);
 	if (user_mode(regs)) {
-		current->thread.bad_vaddr = address;
-		current->thread.error_code = is_write;
 		force_sig_fault(SIGSEGV, code, (void *) address);
 		return;
 	}
@ -232,7 +230,6 @@ void do_page_fault(struct pt_regs *regs)
 	/* Send a sigbus, regardless of whether we were in kernel
 	 * or user mode.
 	 */
-	current->thread.bad_vaddr = address;
 	force_sig_fault(SIGBUS, BUS_ADRERR, (void *) address);

 	/* Kernel mode? Handle exceptions or die */
@ -252,7 +249,6 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 	if ((entry = search_exception_tables(regs->pc)) != NULL) {
 		pr_debug("%s: Exception at pc=%#010lx (%lx)\n",
 			 current->comm, regs->pc, entry->fixup);
-		current->thread.bad_uaddr = address;
 		regs->pc = entry->fixup;
 		return;
 	}
--- a/block/blk-core.c
+++ b/block/blk-core.c
@ -283,12 +283,9 @@ static void blk_free_queue(struct request_queue *q)
 *
 * Decrements the refcount of the request_queue and free it when the refcount
 * reaches 0.
- *
- * Context: Can sleep.
 */
 void blk_put_queue(struct request_queue *q)
 {
-	might_sleep();
 	if (refcount_dec_and_test(&q->refs))
 		blk_free_queue(q);
 }
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@ -75,7 +75,8 @@ static struct acpi_bus_type *acpi_get_bus_type(struct device *dev)
 }

 #define FIND_CHILD_MIN_SCORE	1
-#define FIND_CHILD_MAX_SCORE	2
+#define FIND_CHILD_MID_SCORE	2
+#define FIND_CHILD_MAX_SCORE	3

 static int match_any(struct acpi_device *adev, void *not_used)
 {
@ -96,8 +97,17 @@ static int find_child_checks(struct acpi_device *adev, bool check_children)
 		return -ENODEV;

 	status = acpi_evaluate_integer(adev->handle, "_STA", NULL, &sta);
-	if (status == AE_NOT_FOUND)
+	if (status == AE_NOT_FOUND) {
+		/*
+		 * Special case: backlight device objects without _STA are
+		 * preferred to other objects with the same _ADR value, because
+		 * it is more likely that they are actually useful.
+		 */
+		if (adev->pnp.type.backlight)
+			return FIND_CHILD_MID_SCORE;
+
 		return FIND_CHILD_MIN_SCORE;
+	}

 	if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED))
 		return -ENODEV;
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@ -432,6 +432,13 @@ static const struct dmi_system_id asus_laptop[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"),
 		},
 	},
+	{
+		.ident = "Asus ExpertBook B2402CBA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "B2402CBA"),
+		},
+	},
 	{
 		.ident = "Asus ExpertBook B2502",
 		.matches = {
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@ -1370,9 +1370,12 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp,
 		 * Some devices don't reliably have _HIDs & _CIDs, so add
 		 * synthetic HIDs to make sure drivers can find them.
 		 */
-		if (acpi_is_video_device(handle))
+		if (acpi_is_video_device(handle)) {
 			acpi_add_id(pnp, ACPI_VIDEO_HID);
-		else if (acpi_bay_match(handle))
+			pnp->type.backlight = 1;
+			break;
+		}
+		if (acpi_bay_match(handle))
 			acpi_add_id(pnp, ACPI_BAY_HID);
 		else if (acpi_dock_match(handle))
 			acpi_add_id(pnp, ACPI_DOCK_HID);
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@ -50,6 +50,10 @@ static void acpi_video_parse_cmdline(void)
 		acpi_backlight_cmdline = acpi_backlight_video;
 	if (!strcmp("native", acpi_video_backlight_string))
 		acpi_backlight_cmdline = acpi_backlight_native;
+	if (!strcmp("nvidia_wmi_ec", acpi_video_backlight_string))
+		acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec;
+	if (!strcmp("apple_gmux", acpi_video_backlight_string))
+		acpi_backlight_cmdline = acpi_backlight_apple_gmux;
 	if (!strcmp("none", acpi_video_backlight_string))
 		acpi_backlight_cmdline = acpi_backlight_none;
 }
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@ -640,6 +640,7 @@ config PATA_CS5530
 config PATA_CS5535
 	tristate "CS5535 PATA support (Experimental)"
 	depends on PCI && (X86_32 || (X86_64 && COMPILE_TEST))
+	depends on !UML
 	help
 	  This option enables support for the NatSemi/AMD CS5535
 	  companion chip used with the Geode processor family.
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@ -524,7 +524,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	return 0;
 }

-static int xen_blkbk_remove(struct xenbus_device *dev)
+static void xen_blkbk_remove(struct xenbus_device *dev)
 {
 	struct backend_info *be = dev_get_drvdata(&dev->dev);

@ -547,8 +547,6 @@ static int xen_blkbk_remove(struct xenbus_device *dev)
 		/* Put the reference we set in xen_blkif_alloc(). */
 		xen_blkif_put(be->blkif);
 	}
-
-	return 0;
 }

 int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@ -2467,7 +2467,7 @@ static void blkback_changed(struct xenbus_device *dev,
 	}
 }

-static int blkfront_remove(struct xenbus_device *xbdev)
+static void blkfront_remove(struct xenbus_device *xbdev)
 {
 	struct blkfront_info *info = dev_get_drvdata(&xbdev->dev);

@ -2488,7 +2488,6 @@ static int blkfront_remove(struct xenbus_device *xbdev)
 	}

 	kfree(info);
-	return 0;
 }

 static int blkfront_is_ready(struct xenbus_device *dev)
--- a/drivers/char/tpm/xen-tpmfront.c
+++ b/drivers/char/tpm/xen-tpmfront.c
@ -360,14 +360,13 @@ static int tpmfront_probe(struct xenbus_device *dev,
 	return tpm_chip_register(priv->chip);
 }

-static int tpmfront_remove(struct xenbus_device *dev)
+static void tpmfront_remove(struct xenbus_device *dev)
 {
 	struct tpm_chip *chip = dev_get_drvdata(&dev->dev);
 	struct tpm_private *priv = dev_get_drvdata(&chip->dev);
 	tpm_chip_unregister(chip);
 	ring_free(priv);
 	dev_set_drvdata(&chip->dev, NULL);
-	return 0;
 }

 static int tpmfront_resume(struct xenbus_device *dev)
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@ -307,6 +307,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 		max_perf = min_perf;

 	amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true);
+	cpufreq_cpu_put(policy);
 }

 static int amd_get_min_freq(struct amd_cpudata *cpudata)
--- a/drivers/cpufreq/apple-soc-cpufreq.c
+++ b/drivers/cpufreq/apple-soc-cpufreq.c
@ -280,6 +280,7 @@ static int apple_soc_cpufreq_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency = transition_latency;
 	policy->dvfs_possible_from_any_cpu = true;
 	policy->fast_switch_possible = true;
+	policy->suspend_freq = freq_table[0].frequency;

 	if (policy_has_boost_freq(policy)) {
 		ret = cpufreq_enable_boost_support();
@ -321,7 +322,6 @@ static struct cpufreq_driver apple_soc_cpufreq_driver = {
 	.flags		= CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
 			  CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV,
 	.verify		= cpufreq_generic_frequency_table_verify,
-	.attr		= cpufreq_generic_attr,
 	.get		= apple_soc_cpufreq_get_rate,
 	.init		= apple_soc_cpufreq_init,
 	.exit		= apple_soc_cpufreq_exit,
@ -329,6 +329,7 @@ static struct cpufreq_driver apple_soc_cpufreq_driver = {
 	.fast_switch	= apple_soc_cpufreq_fast_switch,
 	.register_em	= cpufreq_register_em_with_opp,
 	.attr		= apple_soc_cpufreq_hw_attr,
+	.suspend	= cpufreq_generic_suspend,
 };

 static int __init apple_soc_cpufreq_module_init(void)
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@ -445,7 +445,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 		return -ENODEV;
 	}

-	clk = clk_get(cpu_dev, 0);
+	clk = clk_get(cpu_dev, NULL);
 	if (IS_ERR(clk)) {
 		dev_err(cpu_dev, "Cannot get clock for CPU0\n");
 		return PTR_ERR(clk);
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@ -487,7 +487,8 @@ static unsigned int get_perf_level_count(struct cpufreq_policy *policy)
 	cpu_data = policy->driver_data;
 	perf_caps = &cpu_data->perf_caps;
 	max_cap = arch_scale_cpu_capacity(cpu);
-	min_cap = div_u64(max_cap * perf_caps->lowest_perf, perf_caps->highest_perf);
+	min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf,
+			  perf_caps->highest_perf);
 	if ((min_cap == 0) || (max_cap < min_cap))
 		return 0;
 	return 1 + max_cap / CPPC_EM_CAP_STEP - min_cap / CPPC_EM_CAP_STEP;
@ -519,10 +520,10 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
 	cpu_data = policy->driver_data;
 	perf_caps = &cpu_data->perf_caps;
 	max_cap = arch_scale_cpu_capacity(cpu_dev->id);
-	min_cap = div_u64(max_cap * perf_caps->lowest_perf,
-			perf_caps->highest_perf);
-
-	perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap;
+	min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf,
+			  perf_caps->highest_perf);
+	perf_step = div_u64((u64)CPPC_EM_CAP_STEP * perf_caps->highest_perf,
+			    max_cap);
 	min_step = min_cap / CPPC_EM_CAP_STEP;
 	max_step = max_cap / CPPC_EM_CAP_STEP;

--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@ -137,6 +137,7 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "nvidia,tegra30", },
 	{ .compatible = "nvidia,tegra124", },
 	{ .compatible = "nvidia,tegra210", },
+	{ .compatible = "nvidia,tegra234", },

 	{ .compatible = "qcom,apq8096", },
 	{ .compatible = "qcom,msm8996", },
@ -150,6 +151,7 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "qcom,sdm845", },
 	{ .compatible = "qcom,sm6115", },
 	{ .compatible = "qcom,sm6350", },
+	{ .compatible = "qcom,sm6375", },
 	{ .compatible = "qcom,sm8150", },
 	{ .compatible = "qcom,sm8250", },
 	{ .compatible = "qcom,sm8350", },
--- a/Show More
+++ b/Show More