Linux 6.16-rc7

-----BEGIN PGP SIGNATURE-----
 
 iQFSBAABCgA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmh9azkeHHRvcnZhbGRz
 QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiG7GIH/0lpQtHRl6N+q2Qs
 v75iG2ZouWyw2JlhUOHAToKU58MZqqTXLZzc8ZdY6fAd7DpXWKRGSDsyWVyLbUkt
 UKGzXEIJsHXYvw2QIPbhkY9gQBWpdZTh4tHztFyKb0QLn81qkibVP6ChOwSzOGa/
 xUyQ5v6yH+JvQlnQaCgy6hi7cMrLNSNZmuIjy0yc5Y153YPEtX5OUPO2PstpUx5r
 AuiOhU4ewW9QCe07X/Pk7tdn0T2Jg8Kwk1FViaM0RBUf/0GXGfsovIxpUP/eCyMc
 MA+9SXXLlDa/4Z8w3EsQYx6m2MnNmm0HPeevCmWqq3+Ocooik4si1BpzHfUaE6n/
 /0D8zBg=
 =NzEi
 -----END PGP SIGNATURE-----

Merge tag 'v6.16-rc7' into usb-next

We need the USB/Thunderbolt fixes in here for other patches to be on top
of.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

.mailmap

@@ -416,6 +416,7 @@ Kenneth W Chen <kenneth.w.chen@intel.com>
 Kenneth Westfield <quic_kwestfie@quicinc.com> <kwestfie@codeaurora.org>
 Kiran Gunda <quic_kgunda@quicinc.com> <kgunda@codeaurora.org>
 Kirill Tkhai <tkhai@ya.ru> <ktkhai@virtuozzo.com>
+Kirill A. Shutemov <kas@kernel.org> <kirill.shutemov@linux.intel.com>
 Kishon Vijay Abraham I <kishon@kernel.org> <kishon@ti.com>
 Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@linaro.org>
 Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@somainline.org>

Documentation/ABI/testing/sysfs-devices-power

@@ -56,7 +56,7 @@ Date:		January 2009
 Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../async attribute allows the user space to
-		enable or diasble the device's suspend and resume callbacks to
+		enable or disable the device's suspend and resume callbacks to
 		be executed asynchronously (ie. in separate threads, in parallel
 		with the main suspend/resume thread) during system-wide power
 		transitions (eg. suspend to RAM, hibernation).

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -584,6 +584,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spectre_v1
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
 		/sys/devices/system/cpu/vulnerabilities/srbds
+		/sys/devices/system/cpu/vulnerabilities/tsa
 		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>

Documentation/admin-guide/cgroup-v2.rst

@@ -1732,12 +1732,6 @@ The following nested keys are defined.
 	  numa_hint_faults (npn)
 		Number of NUMA hinting faults.
 
-	  numa_task_migrated (npn)
-		Number of task migration by NUMA balancing.
-
-	  numa_task_swapped (npn)
-		Number of task swap by NUMA balancing.
-
 	  pgdemote_kswapd
 		Number of pages demoted by kswapd.
 

Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst

@@ -157,9 +157,7 @@ This is achieved by using the otherwise unused and obsolete VERW instruction in
 combination with a microcode update. The microcode clears the affected CPU
 buffers when the VERW instruction is executed.
 
-Kernel reuses the MDS function to invoke the buffer clearing:
+Kernel does the buffer clearing with x86_clear_cpu_buffers().
-
-	mds_clear_cpu_buffers()
 
 On MDS affected CPUs, the kernel already invokes CPU buffer clear on
 kernel/userspace, hypervisor/guest and C-state (idle) transitions. No

Documentation/admin-guide/kernel-parameters.txt

@@ -7488,6 +7488,19 @@
 			having this key zero'ed is acceptable. E.g. in testing
 			scenarios.
 
+	tsa=		[X86] Control mitigation for Transient Scheduler
+			Attacks on AMD CPUs. Search the following in your
+			favourite search engine for more details:
+
+			"Technical guidance for mitigating transient scheduler
+			attacks".
+
+			off		- disable the mitigation
+			on		- enable the mitigation (default)
+			user		- mitigate only user/kernel transitions
+			vm		- mitigate only guest/host transitions
+
+
 	tsc=		Disable clocksource stability checks for TSC.
 			Format: <string>
 			[x86] reliable: mark tsc clocksource as reliable, this

Documentation/arch/x86/mds.rst

@@ -93,7 +93,7 @@ enters a C-state.
 
 The kernel provides a function to invoke the buffer clearing:
 
-    mds_clear_cpu_buffers()
+    x86_clear_cpu_buffers()
 
 Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path.
 Other than CFLAGS.ZF, this macro doesn't clobber any registers.
@@ -185,9 +185,9 @@ Mitigation points
    idle clearing would be a window dressing exercise and is therefore not
    activated.
 
-   The invocation is controlled by the static key mds_idle_clear which is
+   The invocation is controlled by the static key cpu_buf_idle_clear which is
-   switched depending on the chosen mitigation mode and the SMT state of
+   switched depending on the chosen mitigation mode and the SMT state of the
-   the system.
+   system.
 
    The buffer clear is only invoked before entering the C-State to prevent
    that stale data from the idling CPU from spilling to the Hyper-Thread

Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml

@@ -52,6 +52,9 @@ properties:
   '#clock-cells':
     const: 1
 
+  '#reset-cells':
+    const: 1
+
 required:
   - compatible
   - reg

Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml

@@ -26,7 +26,8 @@ properties:
       - const: realtek,rtl9301-i2c
 
   reg:
-    description: Register offset and size this I2C controller.
+    items:
+      - description: Register offset and size this I2C controller.
 
   "#address-cells":
     const: 1

Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml

@@ -223,12 +223,6 @@ allOf:
       - required:
           - pwms
 
-  - oneOf:
-      - required:
-          - interrupts
-      - required:
-          - io-backends
-
   - if:
       properties:
         compatible:

Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.yaml

@@ -21,7 +21,7 @@ properties:
   vlogic-supply: true
 
   interrupts:
-    minItems: 1
+    maxItems: 1
     description:
       Interrupt mapping for the trigger interrupt from the internal oscillator.
 

Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml

@@ -23,7 +23,7 @@ properties:
               - allwinner,sun20i-d1-emac
               - allwinner,sun50i-h6-emac
               - allwinner,sun50i-h616-emac0
-              - allwinner,sun55i-a523-emac0
+              - allwinner,sun55i-a523-gmac0
           - const: allwinner,sun50i-a64-emac
 
   reg:

Documentation/hwmon/ina238.rst

@@ -65,7 +65,7 @@ Additional sysfs entries for sq52206
 ------------------------------------
 
 ======================= =======================================================
-energy1_input		Energy measurement (mJ)
+energy1_input		Energy measurement (uJ)
 
 power1_input_highest	Peak Power (uW)
 ======================= =======================================================

Documentation/netlink/specs/ovpn.yaml

@@ -160,6 +160,66 @@ attribute-sets:
         name: link-tx-packets
         type: uint
         doc: Number of packets transmitted at the transport level
+  -
+    name: peer-new-input
+    subset-of: peer
+    attributes:
+      -
+        name: id
+      -
+        name: remote-ipv4
+      -
+        name: remote-ipv6
+      -
+        name: remote-ipv6-scope-id
+      -
+        name: remote-port
+      -
+        name: socket
+      -
+        name: vpn-ipv4
+      -
+        name: vpn-ipv6
+      -
+        name: local-ipv4
+      -
+        name: local-ipv6
+      -
+        name: keepalive-interval
+      -
+        name: keepalive-timeout
+  -
+    name: peer-set-input
+    subset-of: peer
+    attributes:
+      -
+        name: id
+      -
+        name: remote-ipv4
+      -
+        name: remote-ipv6
+      -
+        name: remote-ipv6-scope-id
+      -
+        name: remote-port
+      -
+        name: vpn-ipv4
+      -
+        name: vpn-ipv6
+      -
+        name: local-ipv4
+      -
+        name: local-ipv6
+      -
+        name: keepalive-interval
+      -
+        name: keepalive-timeout
+  -
+    name: peer-del-input
+    subset-of: peer
+    attributes:
+      -
+        name: id
   -
     name: keyconf
     attributes:
@@ -216,6 +276,33 @@ attribute-sets:
           obtain the actual cipher IV
         checks:
           exact-len: nonce-tail-size
+
+  -
+    name: keyconf-get
+    subset-of: keyconf
+    attributes:
+      -
+        name: peer-id
+      -
+        name: slot
+      -
+        name: key-id
+      -
+        name: cipher-alg
+  -
+    name: keyconf-swap-input
+    subset-of: keyconf
+    attributes:
+      -
+        name: peer-id
+  -
+    name: keyconf-del-input
+    subset-of: keyconf
+    attributes:
+      -
+        name: peer-id
+      -
+        name: slot
   -
     name: ovpn
     attributes:
@@ -235,12 +322,66 @@ attribute-sets:
         type: nest
         doc: Peer specific cipher configuration
         nested-attributes: keyconf
+  -
+    name: ovpn-peer-new-input
+    subset-of: ovpn
+    attributes:
+      -
+        name: ifindex
+      -
+        name: peer
+        nested-attributes: peer-new-input
+  -
+    name: ovpn-peer-set-input
+    subset-of: ovpn
+    attributes:
+      -
+        name: ifindex
+      -
+        name: peer
+        nested-attributes: peer-set-input
+  -
+    name: ovpn-peer-del-input
+    subset-of: ovpn
+    attributes:
+      -
+        name: ifindex
+      -
+        name: peer
+        nested-attributes: peer-del-input
+  -
+    name: ovpn-keyconf-get
+    subset-of: ovpn
+    attributes:
+      -
+        name: ifindex
+      -
+        name: keyconf
+        nested-attributes: keyconf-get
+  -
+    name: ovpn-keyconf-swap-input
+    subset-of: ovpn
+    attributes:
+      -
+        name: ifindex
+      -
+        name: keyconf
+        nested-attributes: keyconf-swap-input
+  -
+    name: ovpn-keyconf-del-input
+    subset-of: ovpn
+    attributes:
+      -
+        name: ifindex
+      -
+        name: keyconf
+        nested-attributes: keyconf-del-input
 
 operations:
   list:
     -
       name: peer-new
-      attribute-set: ovpn
+      attribute-set: ovpn-peer-new-input
       flags: [ admin-perm ]
       doc: Add a remote peer
       do:
@@ -252,7 +393,7 @@ operations:
             - peer
     -
       name: peer-set
-      attribute-set: ovpn
+      attribute-set: ovpn-peer-set-input
       flags: [ admin-perm ]
       doc: modify a remote peer
       do:
@@ -286,7 +427,7 @@ operations:
             - peer
     -
       name: peer-del
-      attribute-set: ovpn
+      attribute-set: ovpn-peer-del-input
       flags: [ admin-perm ]
       doc: Delete existing remote peer
       do:
@@ -316,7 +457,7 @@ operations:
             - keyconf
     -
       name: key-get
-      attribute-set: ovpn
+      attribute-set: ovpn-keyconf-get
       flags: [ admin-perm ]
       doc: Retrieve non-sensitive data about peer key and cipher
       do:
@@ -331,7 +472,7 @@ operations:
             - keyconf
     -
       name: key-swap
-      attribute-set: ovpn
+      attribute-set: ovpn-keyconf-swap-input
       flags: [ admin-perm ]
       doc: Swap primary and secondary session keys for a specific peer
       do:
@@ -350,7 +491,7 @@ operations:
       mcgrp: peers
     -
       name: key-del
-      attribute-set: ovpn
+      attribute-set: ovpn-keyconf-del-input
       flags: [ admin-perm ]
       doc: Delete cipher key for a specific peer
       do:

Documentation/virt/kvm/api.rst

@@ -2008,6 +2008,13 @@ If the KVM_CAP_VM_TSC_CONTROL capability is advertised, this can also
 be used as a vm ioctl to set the initial tsc frequency of subsequently
 created vCPUs.
 
+For TSC protected Confidential Computing (CoCo) VMs where TSC frequency
+is configured once at VM scope and remains unchanged during VM's
+lifetime, the vm ioctl should be used to configure the TSC frequency
+and the vcpu ioctl is not supported.
+
+Example of such CoCo VMs: TDX guests.
+
 4.56 KVM_GET_TSC_KHZ
 --------------------
 
@@ -7196,6 +7203,10 @@ The valid value for 'flags' is:
 					u64 leaf;
 					u64 r11, r12, r13, r14;
 				} get_tdvmcall_info;
+				struct {
+					u64 ret;
+					u64 vector;
+				} setup_event_notify;
 			};
 		} tdx;
 
@@ -7210,21 +7221,24 @@ number from register R11.  The remaining field of the union provide the
 inputs and outputs of the TDVMCALL.  Currently the following values of
 ``nr`` are defined:
 
-* ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote
+ * ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote
-signed by a service hosting TD-Quoting Enclave operating on the host.
+   signed by a service hosting TD-Quoting Enclave operating on the host.
-Parameters and return value are in the ``get_quote`` field of the union.
+   Parameters and return value are in the ``get_quote`` field of the union.
-The ``gpa`` field and ``size`` specify the guest physical address
+   The ``gpa`` field and ``size`` specify the guest physical address
-(without the shared bit set) and the size of a shared-memory buffer, in
+   (without the shared bit set) and the size of a shared-memory buffer, in
-which the TDX guest passes a TD Report.  The ``ret`` field represents
+   which the TDX guest passes a TD Report.  The ``ret`` field represents
-the return value of the GetQuote request.  When the request has been
+   the return value of the GetQuote request.  When the request has been
-queued successfully, the TDX guest can poll the status field in the
+   queued successfully, the TDX guest can poll the status field in the
-shared-memory area to check whether the Quote generation is completed or
+   shared-memory area to check whether the Quote generation is completed or
-not. When completed, the generated Quote is returned via the same buffer.
+   not. When completed, the generated Quote is returned via the same buffer.
 
-* ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support
+ * ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support
-status of TDVMCALLs.  The output values for the given leaf should be
+   status of TDVMCALLs.  The output values for the given leaf should be
-placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``
+   placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``
-field of the union.
+   field of the union.
+
+ * ``TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT``: the guest has requested to
+   set up a notification interrupt for vector ``vector``.
 
 KVM may add support for more values in the future that may cause a userspace
 exit, even without calls to ``KVM_ENABLE_CAP`` or similar.  In this case,

Documentation/virt/kvm/review-checklist.rst

@@ -7,7 +7,7 @@ Review checklist for kvm patches
 1.  The patch must follow Documentation/process/coding-style.rst and
     Documentation/process/submitting-patches.rst.
 
-2.  Patches should be against kvm.git master branch.
+2.  Patches should be against kvm.git master or next branches.
 
 3.  If the patch introduces or modifies a new userspace API:
     - the API must be documented in Documentation/virt/kvm/api.rst
@@ -18,10 +18,10 @@ Review checklist for kvm patches
 5.  New features must default to off (userspace should explicitly request them).
     Performance improvements can and should default to on.
 
-6.  New cpu features should be exposed via KVM_GET_SUPPORTED_CPUID2
+6.  New cpu features should be exposed via KVM_GET_SUPPORTED_CPUID2,
+    or its equivalent for non-x86 architectures
 
-7.  Emulator changes should be accompanied by unit tests for qemu-kvm.git
+7.  The feature should be testable (see below).
-    kvm/test directory.
 
 8.  Changes should be vendor neutral when possible.  Changes to common code
     are better than duplicating changes to vendor code.
@@ -36,6 +36,87 @@ Review checklist for kvm patches
 11. New guest visible features must either be documented in a hardware manual
     or be accompanied by documentation.
 
-12. Features must be robust against reset and kexec - for example, shared
+Testing of KVM code
-    host/guest memory must be unshared to prevent the host from writing to
+-------------------
-    guest memory that the guest has not reserved for this purpose.
+
+All features contributed to KVM, and in many cases bugfixes too, should be
+accompanied by some kind of tests and/or enablement in open source guests
+and VMMs.  KVM is covered by multiple test suites:
+
+*Selftests*
+  These are low level tests that allow granular testing of kernel APIs.
+  This includes API failure scenarios, invoking APIs after specific
+  guest instructions, and testing multiple calls to ``KVM_CREATE_VM``
+  within a single test.  They are included in the kernel tree at
+  ``tools/testing/selftests/kvm``.
+
+``kvm-unit-tests``
+  A collection of small guests that test CPU and emulated device features
+  from a guest's perspective.  They run under QEMU or ``kvmtool``, and
+  are generally not KVM-specific: they can be run with any accelerator
+  that QEMU support or even on bare metal, making it possible to compare
+  behavior across hypervisors and processor families.
+
+Functional test suites
+  Various sets of functional tests exist, such as QEMU's ``tests/functional``
+  suite and `avocado-vt <https://avocado-vt.readthedocs.io/en/latest/>`__.
+  These typically involve running a full operating system in a virtual
+  machine.
+
+The best testing approach depends on the feature's complexity and
+operation. Here are some examples and guidelines:
+
+New instructions (no new registers or APIs)
+  The corresponding CPU features (if applicable) should be made available
+  in QEMU.  If the instructions require emulation support or other code in
+  KVM, it is worth adding coverage to ``kvm-unit-tests`` or selftests;
+  the latter can be a better choice if the instructions relate to an API
+  that already has good selftest coverage.
+
+New hardware features (new registers, no new APIs)
+  These should be tested via ``kvm-unit-tests``; this more or less implies
+  supporting them in QEMU and/or ``kvmtool``.  In some cases selftests
+  can be used instead, similar to the previous case, or specifically to
+  test corner cases in guest state save/restore.
+
+Bug fixes and performance improvements
+  These usually do not introduce new APIs, but it's worth sharing
+  any benchmarks and tests that will validate your contribution,
+  ideally in the form of regression tests.  Tests and benchmarks
+  can be included in either ``kvm-unit-tests`` or selftests, depending
+  on the specifics of your change.  Selftests are especially useful for
+  regression tests because they are included directly in Linux's tree.
+
+Large scale internal changes
+  While it's difficult to provide a single policy, you should ensure that
+  the changed code is covered by either ``kvm-unit-tests`` or selftests.
+  In some cases the affected code is run for any guests and functional
+  tests suffice.  Explain your testing process in the cover letter,
+  as that can help identify gaps in existing test suites.
+
+New APIs
+  It is important to demonstrate your use case.  This can be as simple as
+  explaining that the feature is already in use on bare metal, or it can be
+  a proof-of-concept implementation in userspace.  The latter need not be
+  open source, though that is of course preferrable for easier testing.
+  Selftests should test corner cases of the APIs, and should also cover
+  basic host and guest operation if no open source VMM uses the feature.
+
+Bigger features, usually spanning host and guest
+  These should be supported by Linux guests, with limited exceptions for
+  Hyper-V features that are testable on Windows guests.  It is strongly
+  suggested that the feature be usable with an open source host VMM, such
+  as at least one of QEMU or crosvm, and guest firmware.  Selftests should
+  test at least API error cases.  Guest operation can be covered by
+  either selftests of ``kvm-unit-tests`` (this is especially important for
+  paravirtualized and Windows-only features).  Strong selftest coverage
+  can also be a replacement for implementation in an open source VMM,
+  but this is generally not recommended.
+
+Following the above suggestions for testing in selftests and
+``kvm-unit-tests`` will make it easier for the maintainers to review
+and accept your code.  In fact, even before you contribute your changes
+upstream it will make it easier for you to develop for KVM.
+
+Of course, the KVM maintainers reserve the right to require more tests,
+though they may also waive the requirement from time to time.

Documentation/virt/kvm/x86/intel-tdx.rst

@@ -79,7 +79,20 @@ to be configured to the TDX guest.
   struct kvm_tdx_capabilities {
         __u64 supported_attrs;
         __u64 supported_xfam;
-        __u64 reserved[254];
+
+        /* TDG.VP.VMCALL hypercalls executed in kernel and forwarded to
+         * userspace, respectively
+         */
+        __u64 kernel_tdvmcallinfo_1_r11;
+        __u64 user_tdvmcallinfo_1_r11;
+
+        /* TDG.VP.VMCALL instruction executions subfunctions executed in kernel
+         * and forwarded to userspace, respectively
+         */
+        __u64 kernel_tdvmcallinfo_1_r12;
+        __u64 user_tdvmcallinfo_1_r12;
+
+        __u64 reserved[250];
 
         /* Configurable CPUID bits for userspace */
         struct kvm_cpuid2 cpuid;

Documentation/wmi/acpi-interface.rst

@@ -36,7 +36,7 @@ Offset  Size (in bytes) Content
 
 The WMI object flags control whether the method or notification ID is used:
 
-- 0x1: Data block usage is expensive and must be explicitly enabled/disabled.
+- 0x1: Data block is expensive to collect.
 - 0x2: Data block contains WMI methods.
 - 0x4: Data block contains ASCIZ string.
 - 0x8: Data block describes a WMI event, use notification ID instead
@@ -83,14 +83,18 @@ event as hexadecimal value. Their first parameter is an integer with a value
 of 0 if the WMI event should be disabled, other values will enable
 the WMI event.
 
+Those ACPI methods are always called even for WMI events not registered as
+being expensive to collect to match the behavior of the Windows driver.
+
 WCxx ACPI methods
 -----------------
-Similar to the ``WExx`` ACPI methods, except that it controls data collection
+Similar to the ``WExx`` ACPI methods, except that instead of WMI events it controls
-instead of events and thus the last two characters of the ACPI method name are
+data collection of data blocks registered as being expensive to collect. Thus the
-the method ID of the data block to enable/disable.
+last two characters of the ACPI method name are the method ID of the data block
+to enable/disable.
 
 Those ACPI methods are also called before setting data blocks to match the
-behaviour of the Windows driver.
+behavior of the Windows driver.
 
 _WED ACPI method
 ----------------

MAINTAINERS

@@ -4181,6 +4181,7 @@ F:	include/linux/cpumask_types.h
 F:	include/linux/find.h
 F:	include/linux/nodemask.h
 F:	include/linux/nodemask_types.h
+F:	include/uapi/linux/bits.h
 F:	include/vdso/bits.h
 F:	lib/bitmap-str.c
 F:	lib/bitmap.c
@@ -4193,6 +4194,7 @@ F:	tools/include/linux/bitfield.h
 F:	tools/include/linux/bitmap.h
 F:	tools/include/linux/bits.h
 F:	tools/include/linux/find.h
+F:	tools/include/uapi/linux/bits.h
 F:	tools/include/vdso/bits.h
 F:	tools/lib/bitmap.c
 F:	tools/lib/find_bit.c
@@ -5568,6 +5570,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
 F:	drivers/char/
 F:	drivers/misc/
 F:	include/linux/miscdevice.h
+F:	rust/kernel/miscdevice.rs
 F:	samples/rust/rust_misc_device.rs
 X:	drivers/char/agp/
 X:	drivers/char/hw_random/
@@ -10504,7 +10507,7 @@ S:	Maintained
 F:	block/partitions/efi.*
 
 HABANALABS PCI DRIVER
-M:	Ofir Bitton <obitton@habana.ai>
+M:	Yaron Avizrat <yaron.avizrat@intel.com>
 L:	dri-devel@lists.freedesktop.org
 S:	Supported
 C:	irc://irc.oftc.net/dri-devel
@@ -16822,8 +16825,8 @@ F:	include/dt-bindings/clock/mobileye,eyeq5-clk.h
 MODULE SUPPORT
 M:	Luis Chamberlain <mcgrof@kernel.org>
 M:	Petr Pavlu <petr.pavlu@suse.com>
+M:	Daniel Gomez <da.gomez@kernel.org>
 R:	Sami Tolvanen <samitolvanen@google.com>
-R:	Daniel Gomez <da.gomez@samsung.com>
 L:	linux-modules@vger.kernel.org
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
@@ -17222,10 +17225,10 @@ F:	drivers/rtc/rtc-ntxec.c
 F:	include/linux/mfd/ntxec.h
 
 NETRONOME ETHERNET DRIVERS
-M:	Louis Peens <louis.peens@corigine.com>
 R:	Jakub Kicinski <kuba@kernel.org>
+R:	Simon Horman <horms@kernel.org>
 L:	oss-drivers@corigine.com
-S:	Maintained
+S:	Odd Fixes
 F:	drivers/net/ethernet/netronome/
 
 NETWORK BLOCK DEVICE (NBD)
@@ -19601,8 +19604,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pinctrl/intel.git
 F:	drivers/pinctrl/intel/
 
 PIN CONTROLLER - KEEMBAY
-M:	Lakshmi Sowjanya D <lakshmi.sowjanya.d@intel.com>
+S:	Orphan
-S:	Supported
 F:	drivers/pinctrl/pinctrl-keembay*
 
 PIN CONTROLLER - MEDIATEK
@@ -20155,21 +20157,15 @@ S:	Supported
 F:	Documentation/devicetree/bindings/soc/qcom/qcom,apr*
 F:	Documentation/devicetree/bindings/sound/qcom,*
 F:	drivers/soc/qcom/apr.c
-F:	include/dt-bindings/sound/qcom,wcd9335.h
+F:	drivers/soundwire/qcom.c
-F:	include/dt-bindings/sound/qcom,wcd934x.h
+F:	include/dt-bindings/sound/qcom,wcd93*
-F:	sound/soc/codecs/lpass-rx-macro.*
+F:	sound/soc/codecs/lpass-*.*
-F:	sound/soc/codecs/lpass-tx-macro.*
-F:	sound/soc/codecs/lpass-va-macro.c
-F:	sound/soc/codecs/lpass-wsa-macro.*
 F:	sound/soc/codecs/msm8916-wcd-analog.c
 F:	sound/soc/codecs/msm8916-wcd-digital.c
 F:	sound/soc/codecs/wcd-clsh-v2.*
 F:	sound/soc/codecs/wcd-mbhc-v2.*
-F:	sound/soc/codecs/wcd9335.*
+F:	sound/soc/codecs/wcd93*.*
-F:	sound/soc/codecs/wcd934x.c
+F:	sound/soc/codecs/wsa88*.*
-F:	sound/soc/codecs/wsa881x.c
-F:	sound/soc/codecs/wsa883x.c
-F:	sound/soc/codecs/wsa884x.c
 F:	sound/soc/qcom/
 
 QCOM EMBEDDED USB DEBUGGER (EUD)
@@ -25907,6 +25903,8 @@ F:	fs/hostfs/
 
 USERSPACE COPYIN/COPYOUT (UIOVEC)
 M:	Alexander Viro <viro@zeniv.linux.org.uk>
+L:	linux-block@vger.kernel.org
+L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 F:	include/linux/uio.h
 F:	lib/iov_iter.c
@@ -26944,7 +26942,7 @@ F:	arch/x86/kernel/stacktrace.c
 F:	arch/x86/kernel/unwind_*.c
 
 X86 TRUST DOMAIN EXTENSIONS (TDX)
-M:	Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+M:	Kirill A. Shutemov <kas@kernel.org>
 R:	Dave Hansen <dave.hansen@linux.intel.com>
 L:	x86@kernel.org
 L:	linux-coco@lists.linux.dev
@@ -27313,13 +27311,6 @@ S:	Supported
 W:	http://www.marvell.com
 F:	drivers/i2c/busses/i2c-xlp9xx.c
 
-XRA1403 GPIO EXPANDER
-M:	Nandor Han <nandor.han@ge.com>
-L:	linux-gpio@vger.kernel.org
-S:	Maintained
-F:	Documentation/devicetree/bindings/gpio/gpio-xra1403.txt
-F:	drivers/gpio/gpio-xra1403.c
-
 XTENSA XTFPGA PLATFORM SUPPORT
 M:	Max Filippov <jcmvbkbc@gmail.com>
 S:	Maintained

Makefile

@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc7
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

arch/arm64/Kconfig

@@ -256,6 +256,7 @@ config ARM64
 	select HOTPLUG_SMT if HOTPLUG_CPU
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
+	select JUMP_LABEL
 	select KASAN_VMALLOC if KASAN
 	select LOCK_MM_AND_FIND_VMA
 	select MODULES_USE_ELF_RELA

arch/arm64/boot/dts/apple/spi1-nvram.dtsi

@@ -20,8 +20,6 @@
 		compatible = "jedec,spi-nor";
 		reg = <0x0>;
 		spi-max-frequency = <25000000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
 
 		partitions {
 			compatible = "fixed-partitions";

arch/arm64/boot/dts/apple/t8103-j293.dts

@@ -100,6 +100,8 @@
 
 &displaydfr_mipi {
 	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
 
 	dfr_panel: panel@0 {
 		compatible = "apple,j293-summit", "apple,summit";

arch/arm64/boot/dts/apple/t8103-jxxx.dtsi

@@ -71,7 +71,7 @@
  */
 &port00 {
 	bus-range = <1 1>;
-	wifi0: network@0,0 {
+	wifi0: wifi@0,0 {
 		compatible = "pci14e4,4425";
 		reg = <0x10000 0x0 0x0 0x0 0x0>;
 		/* To be filled by the loader */

arch/arm64/boot/dts/apple/t8103.dtsi

@@ -405,8 +405,6 @@
 			compatible = "apple,t8103-display-pipe-mipi", "apple,h7-display-pipe-mipi";
 			reg = <0x2 0x28600000 0x0 0x100000>;
 			power-domains = <&ps_mipi_dsi>;
-			#address-cells = <1>;
-			#size-cells = <0>;
 			status = "disabled";
 
 			ports {

arch/arm64/boot/dts/apple/t8112-j493.dts

@@ -63,6 +63,8 @@
 
 &displaydfr_mipi {
 	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
 
 	dfr_panel: panel@0 {
 		compatible = "apple,j493-summit", "apple,summit";

arch/arm64/boot/dts/apple/t8112.dtsi

@@ -420,8 +420,6 @@
 			compatible = "apple,t8112-display-pipe-mipi", "apple,h7-display-pipe-mipi";
 			reg = <0x2 0x28600000 0x0 0x100000>;
 			power-domains = <&ps_mipi_dsi>;
-			#address-cells = <1>;
-			#size-cells = <0>;
 			status = "disabled";
 
 			ports {

arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi

@@ -687,11 +687,12 @@
 		};
 
 		wdog0: watchdog@2ad0000 {
-			compatible = "fsl,imx21-wdt";
+			compatible = "fsl,ls1046a-wdt", "fsl,imx21-wdt";
 			reg = <0x0 0x2ad0000 0x0 0x10000>;
 			interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
 					    QORIQ_CLK_PLL_DIV(2)>;
+			big-endian;
 		};
 
 		edma0: dma-controller@2c00000 {

arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi

@@ -464,6 +464,7 @@
 			};
 
 			reg_nvcc_sd: LDO5 {
+				regulator-always-on;
 				regulator-max-microvolt = <3300000>;
 				regulator-min-microvolt = <1800000>;
 				regulator-name = "On-module +V3.3_1.8_SD (LDO5)";

arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi

@@ -70,7 +70,7 @@
 	tpm@1 {
 		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x1>;
-		spi-max-frequency = <36000000>;
+		spi-max-frequency = <25000000>;
 	};
 };
 

arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi

@@ -110,7 +110,7 @@
 	tpm@1 {
 		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x1>;
-		spi-max-frequency = <36000000>;
+		spi-max-frequency = <25000000>;
 	};
 };
 

arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi

@@ -122,7 +122,7 @@
 	tpm@1 {
 		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x1>;
-		spi-max-frequency = <36000000>;
+		spi-max-frequency = <25000000>;
 	};
 };
 

arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts

@@ -201,7 +201,7 @@
 	tpm@0 {
 		compatible = "atmel,attpm20p", "tcg,tpm_tis-spi";
 		reg = <0x0>;
-		spi-max-frequency = <36000000>;
+		spi-max-frequency = <25000000>;
 	};
 };
 

arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts

@@ -574,17 +574,17 @@
 &scmi_iomuxc {
 	pinctrl_emdio: emdiogrp {
 		fsl,pins = <
-			IMX95_PAD_ENET2_MDC__NETCMIX_TOP_NETC_MDC		0x57e
+			IMX95_PAD_ENET2_MDC__NETCMIX_TOP_NETC_MDC		0x50e
-			IMX95_PAD_ENET2_MDIO__NETCMIX_TOP_NETC_MDIO		0x97e
+			IMX95_PAD_ENET2_MDIO__NETCMIX_TOP_NETC_MDIO		0x90e
 		>;
 	};
 
 	pinctrl_enetc0: enetc0grp {
 		fsl,pins = <
-			IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3		0x57e
+			IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3		0x50e
-			IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2		0x57e
+			IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2		0x50e
-			IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1		0x57e
+			IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1		0x50e
-			IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0		0x57e
+			IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0		0x50e
 			IMX95_PAD_ENET1_TX_CTL__NETCMIX_TOP_ETH0_RGMII_TX_CTL	0x57e
 			IMX95_PAD_ENET1_TXC__NETCMIX_TOP_ETH0_RGMII_TX_CLK	0x58e
 			IMX95_PAD_ENET1_RX_CTL__NETCMIX_TOP_ETH0_RGMII_RX_CTL	0x57e
@@ -598,10 +598,10 @@
 
 	pinctrl_enetc1: enetc1grp {
 		fsl,pins = <
-			IMX95_PAD_ENET2_TD3__NETCMIX_TOP_ETH1_RGMII_TD3		0x57e
+			IMX95_PAD_ENET2_TD3__NETCMIX_TOP_ETH1_RGMII_TD3		0x50e
-			IMX95_PAD_ENET2_TD2__NETCMIX_TOP_ETH1_RGMII_TD2		0x57e
+			IMX95_PAD_ENET2_TD2__NETCMIX_TOP_ETH1_RGMII_TD2		0x50e
-			IMX95_PAD_ENET2_TD1__NETCMIX_TOP_ETH1_RGMII_TD1		0x57e
+			IMX95_PAD_ENET2_TD1__NETCMIX_TOP_ETH1_RGMII_TD1		0x50e
-			IMX95_PAD_ENET2_TD0__NETCMIX_TOP_ETH1_RGMII_TD0		0x57e
+			IMX95_PAD_ENET2_TD0__NETCMIX_TOP_ETH1_RGMII_TD0		0x50e
 			IMX95_PAD_ENET2_TX_CTL__NETCMIX_TOP_ETH1_RGMII_TX_CTL	0x57e
 			IMX95_PAD_ENET2_TXC__NETCMIX_TOP_ETH1_RGMII_TX_CLK	0x58e
 			IMX95_PAD_ENET2_RX_CTL__NETCMIX_TOP_ETH1_RGMII_RX_CTL	0x57e

arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts

@@ -566,17 +566,17 @@
 &scmi_iomuxc {
 	pinctrl_emdio: emdiogrp{
 		fsl,pins = <
-			IMX95_PAD_ENET1_MDC__NETCMIX_TOP_NETC_MDC		0x57e
+			IMX95_PAD_ENET1_MDC__NETCMIX_TOP_NETC_MDC		0x50e
-			IMX95_PAD_ENET1_MDIO__NETCMIX_TOP_NETC_MDIO		0x97e
+			IMX95_PAD_ENET1_MDIO__NETCMIX_TOP_NETC_MDIO		0x90e
 		>;
 	};
 
 	pinctrl_enetc0: enetc0grp {
 		fsl,pins = <
-			IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3		0x57e
+			IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3		0x50e
-			IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2		0x57e
+			IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2		0x50e
-			IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1		0x57e
+			IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1		0x50e
-			IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0		0x57e
+			IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0		0x50e
 			IMX95_PAD_ENET1_TX_CTL__NETCMIX_TOP_ETH0_RGMII_TX_CTL	0x57e
 			IMX95_PAD_ENET1_TXC__NETCMIX_TOP_ETH0_RGMII_TX_CLK	0x58e
 			IMX95_PAD_ENET1_RX_CTL__NETCMIX_TOP_ETH0_RGMII_RX_CTL	0x57e

arch/arm64/boot/dts/freescale/imx95.dtsi

@@ -1708,7 +1708,7 @@
 			      <0x9 0 1 0>;
 			reg-names = "dbi","atu", "dbi2", "app", "dma", "addr_space";
 			num-lanes = <1>;
-			interrupts = <GIC_SPI 317 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_SPI 311 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "dma";
 			clocks = <&scmi_clk IMX95_CLK_HSIO>,
 				 <&scmi_clk IMX95_CLK_HSIOPLL>,

arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts

@@ -1090,6 +1090,8 @@
 };
 
 &pmk8280_rtc {
+	qcom,uefi-rtc-info;
+
 	status = "okay";
 };
 

arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi

@@ -224,6 +224,7 @@
 			reg-names = "rtc", "alarm";
 			interrupts = <0x0 0x62 0x1 IRQ_TYPE_EDGE_RISING>;
 			qcom,no-alarm; /* alarm owned by ADSP */
+			qcom,uefi-rtc-info;
 		};
 
 		pmk8550_sdam_2: nvram@7100 {

arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi

@@ -379,6 +379,18 @@
 				<0 RK_PA7 RK_FUNC_GPIO &pcfg_pull_up>;
 		};
 	};
+
+	spi1 {
+		spi1_csn0_gpio_pin: spi1-csn0-gpio-pin {
+			rockchip,pins =
+				<3 RK_PB1 RK_FUNC_GPIO &pcfg_pull_up_4ma>;
+		};
+
+		spi1_csn1_gpio_pin: spi1-csn1-gpio-pin {
+			rockchip,pins =
+				<3 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up_4ma>;
+		};
+	};
 };
 
 &pmu_io_domains {
@@ -396,6 +408,17 @@
 	vqmmc-supply = <&vccio_sd>;
 };
 
+&spi1 {
+	/*
+	 * Hardware CS has a very slow rise time of about 6us,
+	 * causing transmission errors.
+	 * With cs-gpios we have a rise time of about 20ns.
+	 */
+	cs-gpios = <&gpio3 RK_PB1 GPIO_ACTIVE_LOW>, <&gpio3 RK_PB2 GPIO_ACTIVE_LOW>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&spi1_clk &spi1_csn0_gpio_pin &spi1_csn1_gpio_pin &spi1_miso &spi1_mosi>;
+};
+
 &tsadc {
 	status = "okay";
 };

arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts

@@ -30,6 +30,7 @@
 
 	fan: gpio_fan {
 		compatible = "gpio-fan";
+		fan-supply = <&vcc12v_dcin>;
 		gpios = <&gpio0 RK_PD5 GPIO_ACTIVE_HIGH>;
 		gpio-fan,speed-map =
 				<   0 0>,

arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts

@@ -211,10 +211,38 @@
 	status = "okay";
 };
 
+&cpu_b0 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
+&cpu_b1 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
+&cpu_b2 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
+&cpu_b3 {
+	cpu-supply = <&vdd_cpu_big_s0>;
+};
+
 &cpu_l0 {
 	cpu-supply = <&vdd_cpu_lit_s0>;
 };
 
+&cpu_l1 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l2 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
+&cpu_l3 {
+	cpu-supply = <&vdd_cpu_lit_s0>;
+};
+
 &gmac0 {
 	phy-mode = "rgmii-id";
 	clock_in_out = "output";

arch/arm64/boot/dts/rockchip/rk3576.dtsi

@@ -615,7 +615,7 @@
 					<0 0 0 2 &pcie1_intc 1>,
 					<0 0 0 3 &pcie1_intc 2>,
 					<0 0 0 4 &pcie1_intc 3>;
-			linux,pci-domain = <0>;
+			linux,pci-domain = <1>;
 			max-link-speed = <2>;
 			num-ib-windows = <8>;
 			num-viewport = <8>;

arch/arm64/boot/dts/rockchip/rk3588-base-pinctrl.dtsi

@@ -578,14 +578,14 @@
 		hdmim0_tx0_scl: hdmim0-tx0-scl {
 			rockchip,pins =
 				/* hdmim0_tx0_scl */
-				<4 RK_PB7 5 &pcfg_pull_none>;
+				<4 RK_PB7 5 &pcfg_pull_none_drv_level_5_smt>;
 		};
 
 		/omit-if-no-ref/
 		hdmim0_tx0_sda: hdmim0-tx0-sda {
 			rockchip,pins =
 				/* hdmim0_tx0_sda */
-				<4 RK_PC0 5 &pcfg_pull_none>;
+				<4 RK_PC0 5 &pcfg_pull_none_drv_level_1_smt>;
 		};
 
 		/omit-if-no-ref/
@@ -640,14 +640,14 @@
 		hdmim1_tx0_scl: hdmim1-tx0-scl {
 			rockchip,pins =
 				/* hdmim1_tx0_scl */
-				<0 RK_PD5 11 &pcfg_pull_none>;
+				<0 RK_PD5 11 &pcfg_pull_none_drv_level_5_smt>;
 		};
 
 		/omit-if-no-ref/
 		hdmim1_tx0_sda: hdmim1-tx0-sda {
 			rockchip,pins =
 				/* hdmim1_tx0_sda */
-				<0 RK_PD4 11 &pcfg_pull_none>;
+				<0 RK_PD4 11 &pcfg_pull_none_drv_level_1_smt>;
 		};
 
 		/omit-if-no-ref/
@@ -668,14 +668,14 @@
 		hdmim1_tx1_scl: hdmim1-tx1-scl {
 			rockchip,pins =
 				/* hdmim1_tx1_scl */
-				<3 RK_PC6 5 &pcfg_pull_none>;
+				<3 RK_PC6 5 &pcfg_pull_none_drv_level_5_smt>;
 		};
 
 		/omit-if-no-ref/
 		hdmim1_tx1_sda: hdmim1-tx1-sda {
 			rockchip,pins =
 				/* hdmim1_tx1_sda */
-				<3 RK_PC5 5 &pcfg_pull_none>;
+				<3 RK_PC5 5 &pcfg_pull_none_drv_level_1_smt>;
 		};
 		/omit-if-no-ref/
 		hdmim2_rx_cec: hdmim2-rx-cec {
@@ -709,14 +709,14 @@
 		hdmim2_tx0_scl: hdmim2-tx0-scl {
 			rockchip,pins =
 				/* hdmim2_tx0_scl */
-				<3 RK_PC7 5 &pcfg_pull_none>;
+				<3 RK_PC7 5 &pcfg_pull_none_drv_level_5_smt>;
 		};
 
 		/omit-if-no-ref/
 		hdmim2_tx0_sda: hdmim2-tx0-sda {
 			rockchip,pins =
 				/* hdmim2_tx0_sda */
-				<3 RK_PD0 5 &pcfg_pull_none>;
+				<3 RK_PD0 5 &pcfg_pull_none_drv_level_1_smt>;
 		};
 
 		/omit-if-no-ref/
@@ -730,14 +730,14 @@
 		hdmim2_tx1_scl: hdmim2-tx1-scl {
 			rockchip,pins =
 				/* hdmim2_tx1_scl */
-				<1 RK_PA4 5 &pcfg_pull_none>;
+				<1 RK_PA4 5 &pcfg_pull_none_drv_level_5_smt>;
 		};
 
 		/omit-if-no-ref/
 		hdmim2_tx1_sda: hdmim2-tx1-sda {
 			rockchip,pins =
 				/* hdmim2_tx1_sda */
-				<1 RK_PA3 5 &pcfg_pull_none>;
+				<1 RK_PA3 5 &pcfg_pull_none_drv_level_1_smt>;
 		};
 
 		/omit-if-no-ref/

arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi

@@ -321,6 +321,7 @@
 	bus-width = <4>;
 	cap-mmc-highspeed;
 	cap-sd-highspeed;
+	cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
 	disable-wp;
 	max-frequency = <150000000>;
 	no-sdio;

arch/arm64/boot/dts/rockchip/rk3588-extra-pinctrl.dtsi

@@ -160,14 +160,15 @@
 		hdmim0_tx1_scl: hdmim0-tx1-scl {
 			rockchip,pins =
 				/* hdmim0_tx1_scl */
-				<2 RK_PB5 4 &pcfg_pull_none>;
+				<2 RK_PB5 4 &pcfg_pull_none_drv_level_3_smt>;
 		};
 
 		/omit-if-no-ref/
 		hdmim0_tx1_sda: hdmim0-tx1-sda {
 			rockchip,pins =
 				/* hdmim0_tx1_sda */
-				<2 RK_PB4 4 &pcfg_pull_none>;
+				<2 RK_PB4 4 &pcfg_pull_none_drv_level_1_smt>;
+
 		};
 	};
 

arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts

@@ -474,6 +474,7 @@
 	bus-width = <4>;
 	cap-mmc-highspeed;
 	cap-sd-highspeed;
+	cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>;
 	disable-wp;
 	max-frequency = <150000000>;
 	no-sdio;

arch/arm64/boot/dts/rockchip/rockchip-pinconf.dtsi

@@ -332,6 +332,41 @@
 		input-schmitt-enable;
 	};
 
+	/omit-if-no-ref/
+	pcfg_pull_none_drv_level_1_smt: pcfg-pull-none-drv-level-1-smt {
+		bias-disable;
+		drive-strength = <1>;
+		input-schmitt-enable;
+	};
+
+	/omit-if-no-ref/
+	pcfg_pull_none_drv_level_2_smt: pcfg-pull-none-drv-level-2-smt {
+		bias-disable;
+		drive-strength = <2>;
+		input-schmitt-enable;
+	};
+
+	/omit-if-no-ref/
+	pcfg_pull_none_drv_level_3_smt: pcfg-pull-none-drv-level-3-smt {
+		bias-disable;
+		drive-strength = <3>;
+		input-schmitt-enable;
+	};
+
+	/omit-if-no-ref/
+	pcfg_pull_none_drv_level_4_smt: pcfg-pull-none-drv-level-4-smt {
+		bias-disable;
+		drive-strength = <4>;
+		input-schmitt-enable;
+	};
+
+	/omit-if-no-ref/
+	pcfg_pull_none_drv_level_5_smt: pcfg-pull-none-drv-level-5-smt {
+		bias-disable;
+		drive-strength = <5>;
+		input-schmitt-enable;
+	};
+
 	/omit-if-no-ref/
 	pcfg_output_high: pcfg-output-high {
 		output-high;

arch/arm64/configs/defconfig

@@ -1444,6 +1444,7 @@ CONFIG_PLATFORM_MHU=y
 CONFIG_BCM2835_MBOX=y
 CONFIG_QCOM_APCS_IPC=y
 CONFIG_MTK_ADSP_MBOX=m
+CONFIG_QCOM_CPUCP_MBOX=m
 CONFIG_QCOM_IPCC=y
 CONFIG_ROCKCHIP_IOMMU=y
 CONFIG_TEGRA_IOMMU_SMMU=y
@@ -1573,6 +1574,7 @@ CONFIG_RESET_QCOM_AOSS=y
 CONFIG_RESET_QCOM_PDC=m
 CONFIG_RESET_RZG2L_USBPHY_CTRL=y
 CONFIG_RESET_TI_SCI=y
+CONFIG_PHY_SNPS_EUSB2=m
 CONFIG_PHY_XGENE=y
 CONFIG_PHY_CAN_TRANSCEIVER=m
 CONFIG_PHY_NXP_PTN3222=m
@@ -1597,7 +1599,6 @@ CONFIG_PHY_QCOM_EDP=m
 CONFIG_PHY_QCOM_PCIE2=m
 CONFIG_PHY_QCOM_QMP=m
 CONFIG_PHY_QCOM_QUSB2=m
-CONFIG_PHY_QCOM_SNPS_EUSB2=m
 CONFIG_PHY_QCOM_EUSB2_REPEATER=m
 CONFIG_PHY_QCOM_M31_USB=m
 CONFIG_PHY_QCOM_USB_HS=m

arch/arm64/include/asm/el2_setup.h

@@ -287,17 +287,6 @@
 .Lskip_fgt2_\@:
 .endm
 
-.macro __init_el2_gcs
-	mrs_s	x1, SYS_ID_AA64PFR1_EL1
-	ubfx	x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
-	cbz	x1, .Lskip_gcs_\@
-
-	/* Ensure GCS is not enabled when we start trying to do BLs */
-	msr_s	SYS_GCSCR_EL1, xzr
-	msr_s	SYS_GCSCRE0_EL1, xzr
-.Lskip_gcs_\@:
-.endm
-
 /**
  * Initialize EL2 registers to sane values. This should be called early on all
  * cores that were booted in EL2. Note that everything gets initialised as
@@ -319,7 +308,6 @@
 	__init_el2_cptr
 	__init_el2_fgt
 	__init_el2_fgt2
-        __init_el2_gcs
 .endm
 
 #ifndef __KVM_NVHE_HYPERVISOR__
@@ -371,6 +359,13 @@
 	msr_s   SYS_MPAMHCR_EL2, xzr		// clear TRAP_MPAMIDR_EL1 -> EL2
 
 .Lskip_mpam_\@:
+	check_override id_aa64pfr1, ID_AA64PFR1_EL1_GCS_SHIFT, .Linit_gcs_\@, .Lskip_gcs_\@, x1, x2
+
+.Linit_gcs_\@:
+	msr_s	SYS_GCSCR_EL1, xzr
+	msr_s	SYS_GCSCRE0_EL1, xzr
+
+.Lskip_gcs_\@:
 	check_override id_aa64pfr0, ID_AA64PFR0_EL1_SVE_SHIFT, .Linit_sve_\@, .Lskip_sve_\@, x1, x2
 
 .Linit_sve_\@:	/* SVE register access */

arch/arm64/include/asm/kvm_host.h

@@ -1480,7 +1480,6 @@ int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm,
 					struct reg_mask_range *range);
 
 /* Guest/host FPSIMD coordination helpers */
-int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu);

arch/arm64/kernel/Makefile

@@ -34,7 +34,7 @@ obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
 			   smp.o smp_spin_table.o topology.o smccc-call.o	\
 			   syscall.o proton-pack.o idle.o patching.o pi/	\
-			   rsi.o
+			   rsi.o jump_label.o
 
 obj-$(CONFIG_COMPAT)			+= sys32.o signal32.o			\
 					   sys_compat.o
@@ -47,7 +47,6 @@ obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o perf_callchain.o
 obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF)	+= watchdog_hld.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_CPU_PM)			+= sleep.o suspend.o
-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 obj-$(CONFIG_KGDB)			+= kgdb.o
 obj-$(CONFIG_EFI)			+= efi.o efi-rt-wrapper.o
 obj-$(CONFIG_PCI)			+= pci.o

arch/arm64/kernel/cpufeature.c

@@ -3135,6 +3135,13 @@ static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope)
 }
 #endif
 
+#ifdef CONFIG_ARM64_SME
+static bool has_sme_feature(const struct arm64_cpu_capabilities *cap, int scope)
+{
+	return system_supports_sme() && has_user_cpuid_feature(cap, scope);
+}
+#endif
+
 static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL),
 	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES),
@@ -3223,31 +3230,31 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC),
 #ifdef CONFIG_ARM64_SME
 	HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4),
 #endif /* CONFIG_ARM64_SME */
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT),
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA),

arch/arm64/kernel/efi.c

@@ -15,6 +15,7 @@
 
 #include <asm/efi.h>
 #include <asm/stacktrace.h>
+#include <asm/vmap_stack.h>
 
 static bool region_is_misaligned(const efi_memory_desc_t *md)
 {
@@ -214,9 +215,13 @@ static int __init arm64_efi_rt_init(void)
 	if (!efi_enabled(EFI_RUNTIME_SERVICES))
 		return 0;
 
-	p = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_KERNEL,
+	if (!IS_ENABLED(CONFIG_VMAP_STACK)) {
-			   NUMA_NO_NODE, &&l);
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
-l:	if (!p) {
+		return -ENOMEM;
+	}
+
+	p = arch_alloc_vmap_stack(THREAD_SIZE, NUMA_NO_NODE);
+	if (!p) {
 		pr_warn("Failed to allocate EFI runtime stack\n");
 		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 		return -ENOMEM;

arch/arm64/kernel/process.c

@@ -673,6 +673,11 @@ static void permission_overlay_switch(struct task_struct *next)
 	current->thread.por_el0 = read_sysreg_s(SYS_POR_EL0);
 	if (current->thread.por_el0 != next->thread.por_el0) {
 		write_sysreg_s(next->thread.por_el0, SYS_POR_EL0);
+		/*
+		 * No ISB required as we can tolerate spurious Overlay faults -
+		 * the fault handler will check again based on the new value
+		 * of POR_EL0.
+		 */
 	}
 }
 

arch/arm64/kernel/smp.c

@@ -1143,7 +1143,7 @@ static inline unsigned int num_other_online_cpus(void)
 void smp_send_stop(void)
 {
 	static unsigned long stop_in_progress;
-	cpumask_t mask;
+	static cpumask_t mask;
 	unsigned long timeout;
 
 	/*

arch/arm64/kvm/arm.c

@@ -825,10 +825,6 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 	if (!kvm_arm_vcpu_is_finalized(vcpu))
 		return -EPERM;
 
-	ret = kvm_arch_vcpu_run_map_fp(vcpu);
-	if (ret)
-		return ret;
-
 	if (likely(vcpu_has_run_once(vcpu)))
 		return 0;
 
@@ -2129,7 +2125,7 @@ static void cpu_hyp_init(void *discard)
 
 static void cpu_hyp_uninit(void *discard)
 {
-	if (__this_cpu_read(kvm_hyp_initialized)) {
+	if (!is_protected_kvm_enabled() && __this_cpu_read(kvm_hyp_initialized)) {
 		cpu_hyp_reset();
 		__this_cpu_write(kvm_hyp_initialized, 0);
 	}
@@ -2345,8 +2341,13 @@ static void __init teardown_hyp_mode(void)
 
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu) {
+		if (per_cpu(kvm_hyp_initialized, cpu))
+			continue;
+
 		free_pages(per_cpu(kvm_arm_hyp_stack_base, cpu), NVHE_STACK_SHIFT - PAGE_SHIFT);
-		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
+		if (!kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu])
+			continue;
 
 		if (free_sve) {
 			struct cpu_sve_state *sve_state;
@@ -2354,6 +2355,9 @@ static void __init teardown_hyp_mode(void)
 			sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
 			free_pages((unsigned long) sve_state, pkvm_host_sve_state_order());
 		}
+
+		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
 	}
 }
 

arch/arm64/kvm/fpsimd.c

@@ -14,32 +14,6 @@
 #include <asm/kvm_mmu.h>
 #include <asm/sysreg.h>
 
-/*
- * Called on entry to KVM_RUN unless this vcpu previously ran at least
- * once and the most recent prior KVM_RUN for this vcpu was called from
- * the same task as current (highly likely).
- *
- * This is guaranteed to execute before kvm_arch_vcpu_load_fp(vcpu),
- * such that on entering hyp the relevant parts of current are already
- * mapped.
- */
-int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu)
-{
-	struct user_fpsimd_state *fpsimd = &current->thread.uw.fpsimd_state;
-	int ret;
-
-	/* pKVM has its own tracking of the host fpsimd state. */
-	if (is_protected_kvm_enabled())
-		return 0;
-
-	/* Make sure the host task fpsimd state is visible to hyp: */
-	ret = kvm_share_hyp(fpsimd, fpsimd + 1);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
 /*
  * Prepare vcpu for saving the host's FPSIMD state and loading the guest's.
  * The actual loading is done by the FPSIMD access trap taken to hyp.

arch/arm64/kvm/hyp/nvhe/mem_protect.c

@@ -479,6 +479,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 {
 	struct kvm_mem_range cur;
 	kvm_pte_t pte;
+	u64 granule;
 	s8 level;
 	int ret;
 
@@ -496,18 +497,21 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 		return -EPERM;
 	}
 
-	do {
+	for (; level <= KVM_PGTABLE_LAST_LEVEL; level++) {
-		u64 granule = kvm_granule_size(level);
+		if (!kvm_level_supports_block_mapping(level))
+			continue;
+		granule = kvm_granule_size(level);
 		cur.start = ALIGN_DOWN(addr, granule);
 		cur.end = cur.start + granule;
-		level++;
+		if (!range_included(&cur, range))
-	} while ((level <= KVM_PGTABLE_LAST_LEVEL) &&
+			continue;
-			!(kvm_level_supports_block_mapping(level) &&
-			  range_included(&cur, range)));
-
 		*range = cur;
-
 		return 0;
+	}
+
+	WARN_ON(1);
+
+	return -EINVAL;
 }
 
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size,

arch/arm64/kvm/nested.c

@@ -1402,6 +1402,21 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
 	}
 }
 
+#define has_tgran_2(__r, __sz)						\
+	({								\
+		u64 _s1, _s2, _mmfr0 = __r;				\
+									\
+		_s2 = SYS_FIELD_GET(ID_AA64MMFR0_EL1,			\
+				    TGRAN##__sz##_2, _mmfr0);		\
+									\
+		_s1 = SYS_FIELD_GET(ID_AA64MMFR0_EL1,			\
+				    TGRAN##__sz, _mmfr0);		\
+									\
+		((_s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_NI &&		\
+		  _s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz) || \
+		 (_s2 == ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz && \
+		  _s1 != ID_AA64MMFR0_EL1_TGRAN##__sz##_NI));		\
+	})
 /*
  * Our emulated CPU doesn't support all the possible features. For the
  * sake of simplicity (and probably mental sanity), wipe out a number
@@ -1411,6 +1426,8 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
  */
 u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val)
 {
+	u64 orig_val = val;
+
 	switch (reg) {
 	case SYS_ID_AA64ISAR0_EL1:
 		/* Support everything but TME */
@@ -1480,12 +1497,15 @@ u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val)
 		 */
 		switch (PAGE_SIZE) {
 		case SZ_4K:
+			if (has_tgran_2(orig_val, 4))
 				val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP);
 			fallthrough;
 		case SZ_16K:
+			if (has_tgran_2(orig_val, 16))
 				val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP);
 			fallthrough;
 		case SZ_64K:
+			if (has_tgran_2(orig_val, 64))
 				val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP);
 			break;
 		}

arch/arm64/kvm/sys_regs.c

@@ -2624,7 +2624,7 @@ static bool access_mdcr(struct kvm_vcpu *vcpu,
 	 */
 	if (hpmn > vcpu->kvm->arch.nr_pmu_counters) {
 		hpmn = vcpu->kvm->arch.nr_pmu_counters;
-		u64_replace_bits(val, hpmn, MDCR_EL2_HPMN);
+		u64p_replace_bits(&val, hpmn, MDCR_EL2_HPMN);
 	}
 
 	__vcpu_assign_sys_reg(vcpu, MDCR_EL2, val);

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

@@ -401,9 +401,7 @@ void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu)
 {
 	bool level;
 
-	level  = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En;
+	level = (__vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En) && vgic_v3_get_misr(vcpu);
-	if (level)
-		level &= vgic_v3_get_misr(vcpu);
 	kvm_vgic_inject_irq(vcpu->kvm, vcpu,
 			    vcpu->kvm->arch.vgic.mi_intid, level, vcpu);
 }

arch/arm64/mm/fault.c

@@ -487,17 +487,29 @@ static void do_bad_area(unsigned long far, unsigned long esr,
 	}
 }
 
-static bool fault_from_pkey(unsigned long esr, struct vm_area_struct *vma,
+static bool fault_from_pkey(struct vm_area_struct *vma, unsigned int mm_flags)
-			unsigned int mm_flags)
 {
-	unsigned long iss2 = ESR_ELx_ISS2(esr);
-
 	if (!system_supports_poe())
 		return false;
 
-	if (esr_fsc_is_permission_fault(esr) && (iss2 & ESR_ELx_Overlay))
+	/*
-		return true;
+	 * We do not check whether an Overlay fault has occurred because we
-
+	 * cannot make a decision based solely on its value:
+	 *
+	 * - If Overlay is set, a fault did occur due to POE, but it may be
+	 *   spurious in those cases where we update POR_EL0 without ISB (e.g.
+	 *   on context-switch). We would then need to manually check POR_EL0
+	 *   against vma_pkey(vma), which is exactly what
+	 *   arch_vma_access_permitted() does.
+	 *
+	 * - If Overlay is not set, we may still need to report a pkey fault.
+	 *   This is the case if an access was made within a mapping but with no
+	 *   page mapped, and POR_EL0 forbids the access (according to
+	 *   vma_pkey()). Such access will result in a SIGSEGV regardless
+	 *   because core code checks arch_vma_access_permitted(), but in order
+	 *   to report the correct error code - SEGV_PKUERR - we must handle
+	 *   that case here.
+	 */
 	return !arch_vma_access_permitted(vma,
 			mm_flags & FAULT_FLAG_WRITE,
 			mm_flags & FAULT_FLAG_INSTRUCTION,
@@ -635,7 +647,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 		goto bad_area;
 	}
 
-	if (fault_from_pkey(esr, vma, mm_flags)) {
+	if (fault_from_pkey(vma, mm_flags)) {
 		pkey = vma_pkey(vma);
 		vma_end_read(vma);
 		fault = 0;
@@ -679,7 +691,7 @@ retry:
 		goto bad_area;
 	}
 
-	if (fault_from_pkey(esr, vma, mm_flags)) {
+	if (fault_from_pkey(vma, mm_flags)) {
 		pkey = vma_pkey(vma);
 		mmap_read_unlock(mm);
 		fault = 0;

arch/arm64/mm/proc.S

@@ -518,7 +518,6 @@ alternative_else_nop_endif
 	msr	REG_PIR_EL1, x0
 
 	orr	tcr2, tcr2, TCR2_EL1_PIE
-	msr	REG_TCR2_EL1, x0
 
 .Lskip_indirection:
 

arch/riscv/Kconfig

@@ -63,7 +63,8 @@ config RISCV
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_CFI_CLANG
+	# clang >= 17: https://github.com/llvm/llvm-project/commit/62fa708ceb027713b386c7e0efda994f8bdc27e2
+	select ARCH_SUPPORTS_CFI_CLANG if CLANG_VERSION >= 170000
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
 	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_HUGETLBFS if MMU
@@ -97,6 +98,7 @@ config RISCV
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND
+	select DYNAMIC_FTRACE if FUNCTION_TRACER
 	select EDAC_SUPPORT
 	select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE)
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE
@@ -161,7 +163,7 @@ config RISCV
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	select HAVE_FUNCTION_GRAPH_FREGS
-	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
+	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && HAVE_DYNAMIC_FTRACE
 	select HAVE_EBPF_JIT if MMU
 	select HAVE_GUP_FAST if MMU
 	select HAVE_FUNCTION_ARG_ACCESS_API

arch/riscv/include/asm/kvm_aia.h

@@ -87,6 +87,9 @@ DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available);
 
 extern struct kvm_device_ops kvm_riscv_aia_device_ops;
 
+bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu);
+void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu);
 int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu);
 
@@ -161,7 +164,6 @@ void kvm_riscv_aia_destroy_vm(struct kvm *kvm);
 int kvm_riscv_aia_alloc_hgei(int cpu, struct kvm_vcpu *owner,
 			     void __iomem **hgei_va, phys_addr_t *hgei_pa);
 void kvm_riscv_aia_free_hgei(int cpu, int hgei);
-void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable);
 
 void kvm_riscv_aia_enable(void);
 void kvm_riscv_aia_disable(void);

arch/riscv/include/asm/kvm_host.h

@@ -306,6 +306,9 @@ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
 	return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu;
 }
 
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
+
 #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
 
 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,

arch/riscv/include/asm/uaccess.h

@@ -311,8 +311,8 @@ do {								\
 do {								\
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&	\
 	    !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) {	\
-		__inttype(x) val = (__inttype(x))x;			\
+		__inttype(x) ___val = (__inttype(x))x;			\
-		if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(val), sizeof(*__gu_ptr))) \
+		if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(___val), sizeof(*__gu_ptr))) \
 			goto label;				\
 		break;						\
 	}							\

arch/riscv/kernel/cpu_ops_sbi.c

@@ -18,10 +18,10 @@ const struct cpu_operations cpu_ops_sbi;
 
 /*
  * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can
- * be invoked from multiple threads in parallel. Define a per cpu data
+ * be invoked from multiple threads in parallel. Define an array of boot data
  * to handle that.
  */
-static DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data);
+static struct sbi_hart_boot_data boot_data[NR_CPUS];
 
 static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
 			      unsigned long priv)
@@ -67,7 +67,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
 	unsigned long hartid = cpuid_to_hartid_map(cpuid);
 	unsigned long hsm_data;
-	struct sbi_hart_boot_data *bdata = &per_cpu(boot_data, cpuid);
+	struct sbi_hart_boot_data *bdata = &boot_data[cpuid];
 
 	/* Make sure tidle is updated */
 	smp_mb();

arch/riscv/kernel/ftrace.c

@@ -14,6 +14,18 @@
 #include <asm/text-patching.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+void ftrace_arch_code_modify_prepare(void)
+	__acquires(&text_mutex)
+{
+	mutex_lock(&text_mutex);
+}
+
+void ftrace_arch_code_modify_post_process(void)
+	__releases(&text_mutex)
+{
+	mutex_unlock(&text_mutex);
+}
+
 unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
@@ -29,10 +41,8 @@ unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip)
 
 void arch_ftrace_update_code(int command)
 {
-	mutex_lock(&text_mutex);
 	command |= FTRACE_MAY_SLEEP;
 	ftrace_modify_all_code(command);
-	mutex_unlock(&text_mutex);
 	flush_icache_all();
 }
 
@@ -149,6 +159,8 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
 	unsigned int nops[2], offset;
 	int ret;
 
+	guard(mutex)(&text_mutex);
+
 	ret = ftrace_rec_set_nop_ops(rec);
 	if (ret)
 		return ret;
@@ -157,9 +169,7 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
 	nops[0] = to_auipc_t0(offset);
 	nops[1] = RISCV_INSN_NOP4;
 
-	mutex_lock(&text_mutex);
 	ret = patch_insn_write((void *)pc, nops, 2 * MCOUNT_INSN_SIZE);
-	mutex_unlock(&text_mutex);
 
 	return ret;
 }

arch/riscv/kernel/traps.c

@@ -6,6 +6,7 @@
 #include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/irqflags.h>
 #include <linux/randomize_kstack.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
@@ -151,7 +152,9 @@ asmlinkage __visible __trap_section void name(struct pt_regs *regs)		\
 {										\
 	if (user_mode(regs)) {							\
 		irqentry_enter_from_user_mode(regs);				\
+		local_irq_enable();						\
 		do_trap_error(regs, signo, code, regs->epc, "Oops - " str);	\
+		local_irq_disable();						\
 		irqentry_exit_to_user_mode(regs);				\
 	} else {								\
 		irqentry_state_t state = irqentry_nmi_enter(regs);		\
@@ -173,17 +176,14 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re
 
 	if (user_mode(regs)) {
 		irqentry_enter_from_user_mode(regs);
-
 		local_irq_enable();
 
 		handled = riscv_v_first_use_handler(regs);
-
-		local_irq_disable();
-
 		if (!handled)
 			do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc,
 				      "Oops - illegal instruction");
 
+		local_irq_disable();
 		irqentry_exit_to_user_mode(regs);
 	} else {
 		irqentry_state_t state = irqentry_nmi_enter(regs);
@@ -308,9 +308,11 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		irqentry_enter_from_user_mode(regs);
+		local_irq_enable();
 
 		handle_break(regs);
 
+		local_irq_disable();
 		irqentry_exit_to_user_mode(regs);
 	} else {
 		irqentry_state_t state = irqentry_nmi_enter(regs);

arch/riscv/kernel/traps_misaligned.c

@@ -461,7 +461,7 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs)
 	}
 
 	if (!fp)
-		SET_RD(insn, regs, val.data_ulong << shift >> shift);
+		SET_RD(insn, regs, (long)(val.data_ulong << shift) >> shift);
 	else if (len == 8)
 		set_f64_rd(insn, regs, val.data_u64);
 	else

arch/riscv/kvm/aia.c

@@ -30,28 +30,6 @@ unsigned int kvm_riscv_aia_nr_hgei;
 unsigned int kvm_riscv_aia_max_ids;
 DEFINE_STATIC_KEY_FALSE(kvm_riscv_aia_available);
 
-static int aia_find_hgei(struct kvm_vcpu *owner)
-{
-	int i, hgei;
-	unsigned long flags;
-	struct aia_hgei_control *hgctrl = get_cpu_ptr(&aia_hgei);
-
-	raw_spin_lock_irqsave(&hgctrl->lock, flags);
-
-	hgei = -1;
-	for (i = 1; i <= kvm_riscv_aia_nr_hgei; i++) {
-		if (hgctrl->owners[i] == owner) {
-			hgei = i;
-			break;
-		}
-	}
-
-	raw_spin_unlock_irqrestore(&hgctrl->lock, flags);
-
-	put_cpu_ptr(&aia_hgei);
-	return hgei;
-}
-
 static inline unsigned long aia_hvictl_value(bool ext_irq_pending)
 {
 	unsigned long hvictl;
@@ -95,7 +73,6 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu)
 
 bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
 {
-	int hgei;
 	unsigned long seip;
 
 	if (!kvm_riscv_aia_available())
@@ -114,11 +91,7 @@ bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
 	if (!kvm_riscv_aia_initialized(vcpu->kvm) || !seip)
 		return false;
 
-	hgei = aia_find_hgei(vcpu);
+	return kvm_riscv_vcpu_aia_imsic_has_interrupt(vcpu);
-	if (hgei > 0)
-		return !!(ncsr_read(CSR_HGEIP) & BIT(hgei));
-
-	return false;
 }
 
 void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu)
@@ -164,6 +137,9 @@ void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu)
 		csr_write(CSR_HVIPRIO2H, csr->hviprio2h);
 #endif
 	}
+
+	if (kvm_riscv_aia_initialized(vcpu->kvm))
+		kvm_riscv_vcpu_aia_imsic_load(vcpu, cpu);
 }
 
 void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu)
@@ -174,6 +150,9 @@ void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu)
 	if (!kvm_riscv_aia_available())
 		return;
 
+	if (kvm_riscv_aia_initialized(vcpu->kvm))
+		kvm_riscv_vcpu_aia_imsic_put(vcpu);
+
 	if (kvm_riscv_nacl_available()) {
 		nsh = nacl_shmem();
 		csr->vsiselect = nacl_csr_read(nsh, CSR_VSISELECT);
@@ -472,22 +451,6 @@ void kvm_riscv_aia_free_hgei(int cpu, int hgei)
 	raw_spin_unlock_irqrestore(&hgctrl->lock, flags);
 }
 
-void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable)
-{
-	int hgei;
-
-	if (!kvm_riscv_aia_available())
-		return;
-
-	hgei = aia_find_hgei(owner);
-	if (hgei > 0) {
-		if (enable)
-			csr_set(CSR_HGEIE, BIT(hgei));
-		else
-			csr_clear(CSR_HGEIE, BIT(hgei));
-	}
-}
-
 static irqreturn_t hgei_interrupt(int irq, void *dev_id)
 {
 	int i;

arch/riscv/kvm/aia_imsic.c

@@ -676,6 +676,48 @@ static void imsic_swfile_update(struct kvm_vcpu *vcpu,
 	imsic_swfile_extirq_update(vcpu);
 }
 
+bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
+	unsigned long flags;
+	bool ret = false;
+
+	/*
+	 * The IMSIC SW-file directly injects interrupt via hvip so
+	 * only check for interrupt when IMSIC VS-file is being used.
+	 */
+
+	read_lock_irqsave(&imsic->vsfile_lock, flags);
+	if (imsic->vsfile_cpu > -1)
+		ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei));
+	read_unlock_irqrestore(&imsic->vsfile_lock, flags);
+
+	return ret;
+}
+
+void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	/*
+	 * No need to explicitly clear HGEIE CSR bits because the
+	 * hgei interrupt handler (aka hgei_interrupt()) will always
+	 * clear it for us.
+	 */
+}
+
+void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu)
+{
+	struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
+	unsigned long flags;
+
+	if (!kvm_vcpu_is_blocking(vcpu))
+		return;
+
+	read_lock_irqsave(&imsic->vsfile_lock, flags);
+	if (imsic->vsfile_cpu > -1)
+		csr_set(CSR_HGEIE, BIT(imsic->vsfile_hgei));
+	read_unlock_irqrestore(&imsic->vsfile_lock, flags);
+}
+
 void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu)
 {
 	unsigned long flags;
@@ -781,6 +823,9 @@ int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu)
 	 * producers to the new IMSIC VS-file.
 	 */
 
+	/* Ensure HGEIE CSR bit is zero before using the new IMSIC VS-file */
+	csr_clear(CSR_HGEIE, BIT(new_vsfile_hgei));
+
 	/* Zero-out new IMSIC VS-file */
 	imsic_vsfile_local_clear(new_vsfile_hgei, imsic->nr_hw_eix);
 

arch/riscv/kvm/vcpu.c

@@ -207,16 +207,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return kvm_riscv_vcpu_timer_pending(vcpu);
 }
 
-void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
-{
-	kvm_riscv_aia_wakeon_hgei(vcpu, true);
-}
-
-void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
-{
-	kvm_riscv_aia_wakeon_hgei(vcpu, false);
-}
-
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
 	return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) &&

arch/riscv/kvm/vcpu_timer.c

@@ -345,8 +345,24 @@ void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu)
 	/*
 	 * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync()
 	 * upon every VM exit so no need to save here.
+	 *
+	 * If VS-timer expires when no VCPU running on a host CPU then
+	 * WFI executed by such host CPU will be effective NOP resulting
+	 * in no power savings. This is because as-per RISC-V Privileged
+	 * specificaiton: "WFI is also required to resume execution for
+	 * locally enabled interrupts pending at any privilege level,
+	 * regardless of the global interrupt enable at each privilege
+	 * level."
+	 *
+	 * To address the above issue, vstimecmp CSR must be set to -1UL
+	 * over here when VCPU is scheduled-out or exits to user space.
 	 */
 
+	csr_write(CSR_VSTIMECMP, -1UL);
+#if defined(CONFIG_32BIT)
+	csr_write(CSR_VSTIMECMPH, -1UL);
+#endif
+
 	/* timer should be enabled for the remaining operations */
 	if (unlikely(!t->init_done))
 		return;

arch/riscv/tools/relocs_check.sh

@@ -14,7 +14,9 @@ bad_relocs=$(
 ${srctree}/scripts/relocs_check.sh "$@" |
 	# These relocations are okay
 	#	R_RISCV_RELATIVE
-	grep -F -w -v 'R_RISCV_RELATIVE'
+	#	R_RISCV_NONE
+	grep -F -w -v 'R_RISCV_RELATIVE
+R_RISCV_NONE'
 )
 
 if [ -z "$bad_relocs" ]; then

arch/s390/crypto/sha1_s390.c

@@ -38,6 +38,7 @@ static int s390_sha1_init(struct shash_desc *desc)
 	sctx->state[4] = SHA1_H4;
 	sctx->count = 0;
 	sctx->func = CPACF_KIMD_SHA_1;
+	sctx->first_message_part = 0;
 
 	return 0;
 }
@@ -60,6 +61,7 @@ static int s390_sha1_import(struct shash_desc *desc, const void *in)
 	sctx->count = ictx->count;
 	memcpy(sctx->state, ictx->state, sizeof(ictx->state));
 	sctx->func = CPACF_KIMD_SHA_1;
+	sctx->first_message_part = 0;
 	return 0;
 }
 

arch/s390/crypto/sha512_s390.c

@@ -32,6 +32,7 @@ static int sha512_init(struct shash_desc *desc)
 	ctx->count = 0;
 	ctx->sha512.count_hi = 0;
 	ctx->func = CPACF_KIMD_SHA_512;
+	ctx->first_message_part = 0;
 
 	return 0;
 }
@@ -57,6 +58,7 @@ static int sha512_import(struct shash_desc *desc, const void *in)
 
 	memcpy(sctx->state, ictx->state, sizeof(ictx->state));
 	sctx->func = CPACF_KIMD_SHA_512;
+	sctx->first_message_part = 0;
 	return 0;
 }
 
@@ -97,6 +99,7 @@ static int sha384_init(struct shash_desc *desc)
 	ctx->count = 0;
 	ctx->sha512.count_hi = 0;
 	ctx->func = CPACF_KIMD_SHA_512;
+	ctx->first_message_part = 0;
 
 	return 0;
 }

arch/s390/net/bpf_jit_comp.c

@@ -566,7 +566,15 @@ static void bpf_jit_plt(struct bpf_plt *plt, void *ret, void *target)
 {
 	memcpy(plt, &bpf_plt, sizeof(*plt));
 	plt->ret = ret;
-	plt->target = target;
+	/*
+	 * (target == NULL) implies that the branch to this PLT entry was
+	 * patched and became a no-op. However, some CPU could have jumped
+	 * to this PLT entry before patching and may be still executing it.
+	 *
+	 * Since the intention in this case is to make the PLT entry a no-op,
+	 * make the target point to the return label instead of NULL.
+	 */
+	plt->target = target ?: ret;
 }
 
 /*

arch/x86/Kconfig

@@ -147,7 +147,7 @@ config X86
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANT_GENERAL_HUGETLB
-	select ARCH_WANT_HUGE_PMD_SHARE
+	select ARCH_WANT_HUGE_PMD_SHARE		if X86_64
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP	if X86_64
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP	if X86_64
@@ -2695,6 +2695,15 @@ config MITIGATION_ITS
 	  disabled, mitigation cannot be enabled via cmdline.
 	  See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst>
 
+config MITIGATION_TSA
+	bool "Mitigate Transient Scheduler Attacks"
+	depends on CPU_SUP_AMD
+	default y
+	help
+	  Enable mitigation for Transient Scheduler Attacks. TSA is a hardware
+	  security vulnerability on AMD CPUs which can lead to forwarding of
+	  invalid info to subsequent instructions and thus can affect their
+	  timing and thereby cause a leakage.
 endif
 
 config ARCH_HAS_ADD_PAGES

arch/x86/coco/sev/Makefile

@@ -5,5 +5,6 @@ obj-y += core.o sev-nmi.o vc-handle.o
 # Clang 14 and older may fail to respect __no_sanitize_undefined when inlining
 UBSAN_SANITIZE_sev-nmi.o	:= n
 
-# GCC may fail to respect __no_sanitize_address when inlining
+# GCC may fail to respect __no_sanitize_address or __no_kcsan when inlining
 KASAN_SANITIZE_sev-nmi.o	:= n
+KCSAN_SANITIZE_sev-nmi.o	:= n

arch/x86/coco/sev/core.c

@@ -88,7 +88,7 @@ static const char * const sev_status_feat_names[] = {
  */
 static u64 snp_tsc_scale __ro_after_init;
 static u64 snp_tsc_offset __ro_after_init;
-static u64 snp_tsc_freq_khz __ro_after_init;
+static unsigned long snp_tsc_freq_khz __ro_after_init;
 
 DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
 DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
@@ -2167,15 +2167,31 @@ static unsigned long securetsc_get_tsc_khz(void)
 
 void __init snp_secure_tsc_init(void)
 {
-	unsigned long long tsc_freq_mhz;
+	struct snp_secrets_page *secrets;
+	unsigned long tsc_freq_mhz;
+	void *mem;
 
 	if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC))
 		return;
 
+	mem = early_memremap_encrypted(sev_secrets_pa, PAGE_SIZE);
+	if (!mem) {
+		pr_err("Unable to get TSC_FACTOR: failed to map the SNP secrets page.\n");
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECURE_TSC);
+	}
+
+	secrets = (__force struct snp_secrets_page *)mem;
+
 	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
 	rdmsrq(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz);
-	snp_tsc_freq_khz = (unsigned long)(tsc_freq_mhz * 1000);
+
+	/* Extract the GUEST TSC MHZ from BIT[17:0], rest is reserved space */
+	tsc_freq_mhz &= GENMASK_ULL(17, 0);
+
+	snp_tsc_freq_khz = SNP_SCALE_TSC_FREQ(tsc_freq_mhz * 1000, secrets->tsc_factor);
 
 	x86_platform.calibrate_cpu = securetsc_get_tsc_khz;
 	x86_platform.calibrate_tsc = securetsc_get_tsc_khz;
+
+	early_memunmap(mem, PAGE_SIZE);
 }

arch/x86/entry/entry.S

@@ -36,20 +36,20 @@ EXPORT_SYMBOL_GPL(write_ibpb);
 
 /*
  * Define the VERW operand that is disguised as entry code so that
- * it can be referenced with KPTI enabled. This ensure VERW can be
+ * it can be referenced with KPTI enabled. This ensures VERW can be
  * used late in exit-to-user path after page tables are switched.
  */
 .pushsection .entry.text, "ax"
 
 .align L1_CACHE_BYTES, 0xcc
-SYM_CODE_START_NOALIGN(mds_verw_sel)
+SYM_CODE_START_NOALIGN(x86_verw_sel)
 	UNWIND_HINT_UNDEFINED
 	ANNOTATE_NOENDBR
 	.word __KERNEL_DS
 .align L1_CACHE_BYTES, 0xcc
-SYM_CODE_END(mds_verw_sel);
+SYM_CODE_END(x86_verw_sel);
 /* For KVM */
-EXPORT_SYMBOL_GPL(mds_verw_sel);
+EXPORT_SYMBOL_GPL(x86_verw_sel);
 
 .popsection
 

arch/x86/hyperv/hv_init.c

@@ -34,6 +34,7 @@
 #include <linux/syscore_ops.h>
 #include <clocksource/hyperv_timer.h>
 #include <linux/highmem.h>
+#include <linux/export.h>
 
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);

arch/x86/hyperv/irqdomain.c

@@ -10,6 +10,7 @@
 
 #include <linux/pci.h>
 #include <linux/irq.h>
+#include <linux/export.h>
 #include <asm/mshyperv.h>
 
 static int hv_map_interrupt(union hv_device_id device_id, bool level,
@@ -46,7 +47,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
 	if (nr_bank < 0) {
 		local_irq_restore(flags);
 		pr_err("%s: unable to generate VP set\n", __func__);
-		return EINVAL;
+		return -EINVAL;
 	}
 	intr_desc->target.flags = HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
 
@@ -66,7 +67,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
 	if (!hv_result_success(status))
 		hv_status_err(status, "\n");
 
-	return hv_result(status);
+	return hv_result_to_errno(status);
 }
 
 static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry)
@@ -88,7 +89,10 @@ static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry)
 	status = hv_do_hypercall(HVCALL_UNMAP_DEVICE_INTERRUPT, input, NULL);
 	local_irq_restore(flags);
 
-	return hv_result(status);
+	if (!hv_result_success(status))
+		hv_status_err(status, "\n");
+
+	return hv_result_to_errno(status);
 }
 
 #ifdef CONFIG_PCI_MSI
@@ -169,13 +173,34 @@ static union hv_device_id hv_build_pci_dev_id(struct pci_dev *dev)
 	return dev_id;
 }
 
-static int hv_map_msi_interrupt(struct pci_dev *dev, int cpu, int vector,
+/**
-				struct hv_interrupt_entry *entry)
+ * hv_map_msi_interrupt() - "Map" the MSI IRQ in the hypervisor.
+ * @data:      Describes the IRQ
+ * @out_entry: Hypervisor (MSI) interrupt entry (can be NULL)
+ *
+ * Map the IRQ in the hypervisor by issuing a MAP_DEVICE_INTERRUPT hypercall.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_map_msi_interrupt(struct irq_data *data,
+			 struct hv_interrupt_entry *out_entry)
 {
-	union hv_device_id device_id = hv_build_pci_dev_id(dev);
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct hv_interrupt_entry dummy;
+	union hv_device_id device_id;
+	struct msi_desc *msidesc;
+	struct pci_dev *dev;
+	int cpu;
 
-	return hv_map_interrupt(device_id, false, cpu, vector, entry);
+	msidesc = irq_data_get_msi_desc(data);
+	dev = msi_desc_to_pci_dev(msidesc);
+	device_id = hv_build_pci_dev_id(dev);
+	cpu = cpumask_first(irq_data_get_effective_affinity_mask(data));
+
+	return hv_map_interrupt(device_id, false, cpu, cfg->vector,
+				out_entry ? out_entry : &dummy);
 }
+EXPORT_SYMBOL_GPL(hv_map_msi_interrupt);
 
 static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi_msg *msg)
 {
@@ -188,13 +213,11 @@ static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi
 static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry);
 static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
+	struct hv_interrupt_entry *stored_entry;
+	struct irq_cfg *cfg = irqd_cfg(data);
 	struct msi_desc *msidesc;
 	struct pci_dev *dev;
-	struct hv_interrupt_entry out_entry, *stored_entry;
+	int ret;
-	struct irq_cfg *cfg = irqd_cfg(data);
-	const cpumask_t *affinity;
-	int cpu;
-	u64 status;
 
 	msidesc = irq_data_get_msi_desc(data);
 	dev = msi_desc_to_pci_dev(msidesc);
@@ -204,9 +227,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		return;
 	}
 
-	affinity = irq_data_get_effective_affinity_mask(data);
-	cpu = cpumask_first_and(affinity, cpu_online_mask);
-
 	if (data->chip_data) {
 		/*
 		 * This interrupt is already mapped. Let's unmap first.
@@ -219,15 +239,13 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		stored_entry = data->chip_data;
 		data->chip_data = NULL;
 
-		status = hv_unmap_msi_interrupt(dev, stored_entry);
+		ret = hv_unmap_msi_interrupt(dev, stored_entry);
 
 		kfree(stored_entry);
 
-		if (status != HV_STATUS_SUCCESS) {
+		if (ret)
-			hv_status_debug(status, "failed to unmap\n");
 			return;
 	}
-	}
 
 	stored_entry = kzalloc(sizeof(*stored_entry), GFP_ATOMIC);
 	if (!stored_entry) {
@@ -235,15 +253,14 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		return;
 	}
 
-	status = hv_map_msi_interrupt(dev, cpu, cfg->vector, &out_entry);
+	ret = hv_map_msi_interrupt(data, stored_entry);
-	if (status != HV_STATUS_SUCCESS) {
+	if (ret) {
 		kfree(stored_entry);
 		return;
 	}
 
-	*stored_entry = out_entry;
 	data->chip_data = stored_entry;
-	entry_to_msi_msg(&out_entry, msg);
+	entry_to_msi_msg(data->chip_data, msg);
 
 	return;
 }
@@ -257,7 +274,6 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
 {
 	struct hv_interrupt_entry old_entry;
 	struct msi_msg msg;
-	u64 status;
 
 	if (!irqd->chip_data) {
 		pr_debug("%s: no chip data\n!", __func__);
@@ -270,10 +286,7 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
 	kfree(irqd->chip_data);
 	irqd->chip_data = NULL;
 
-	status = hv_unmap_msi_interrupt(dev, &old_entry);
+	(void)hv_unmap_msi_interrupt(dev, &old_entry);
-
-	if (status != HV_STATUS_SUCCESS)
-		hv_status_err(status, "\n");
 }
 
 static void hv_msi_free_irq(struct irq_domain *domain,

arch/x86/hyperv/ivm.c

@@ -10,6 +10,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/export.h>
 #include <asm/svm.h>
 #include <asm/sev.h>
 #include <asm/io.h>

arch/x86/hyperv/nested.c

@@ -11,6 +11,7 @@
 
 
 #include <linux/types.h>
+#include <linux/export.h>
 #include <hyperv/hvhdk.h>
 #include <asm/mshyperv.h>
 #include <asm/tlbflush.h>

arch/x86/include/asm/cpufeatures.h

@@ -456,6 +456,7 @@
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* No Nested Data Breakpoints */
 #define X86_FEATURE_WRMSR_XX_BASE_NS	(20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
 #define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_VERW_CLEAR		(20*32+ 5) /* The memory form of VERW mitigates TSA */
 #define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* Null Selector Clears Base */
 #define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* Automatic IBRS */
 #define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* SMM_CTL MSR is not present */
@@ -487,6 +488,9 @@
 #define X86_FEATURE_PREFER_YMM		(21*32+ 8) /* Avoid ZMM registers due to downclocking */
 #define X86_FEATURE_APX			(21*32+ 9) /* Advanced Performance Extensions */
 #define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32+10) /* Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_TSA_SQ_NO		(21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
+#define X86_FEATURE_TSA_L1_NO		(21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
+#define X86_FEATURE_CLEAR_CPU_BUF_VM	(21*32+13) /* Clear CPU buffers using VERW before VMRUN */
 
 /*
  * BUG word(s)
@@ -542,5 +546,5 @@
 #define X86_BUG_OLD_MICROCODE		X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
 #define X86_BUG_ITS			X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
 #define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
-
+#define X86_BUG_TSA			X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
 #endif /* _ASM_X86_CPUFEATURES_H */

arch/x86/include/asm/irqflags.h

@@ -44,13 +44,13 @@ static __always_inline void native_irq_enable(void)
 
 static __always_inline void native_safe_halt(void)
 {
-	mds_idle_clear_cpu_buffers();
+	x86_idle_clear_cpu_buffers();
 	asm volatile("sti; hlt": : :"memory");
 }
 
 static __always_inline void native_halt(void)
 {
-	mds_idle_clear_cpu_buffers();
+	x86_idle_clear_cpu_buffers();
 	asm volatile("hlt": : :"memory");
 }
 

arch/x86/include/asm/kvm_host.h

@@ -700,8 +700,13 @@ struct kvm_vcpu_hv {
 
 	struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS];
 
-	/* Preallocated buffer for handling hypercalls passing sparse vCPU set */
+	/*
+	 * Preallocated buffers for handling hypercalls that pass sparse vCPU
+	 * sets (for high vCPU counts, they're too large to comfortably fit on
+	 * the stack).
+	 */
 	u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS];
+	DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
 
 	struct hv_vp_assist_page vp_assist_page;
 
@@ -764,6 +769,7 @@ enum kvm_only_cpuid_leafs {
 	CPUID_8000_0022_EAX,
 	CPUID_7_2_EDX,
 	CPUID_24_0_EBX,
+	CPUID_8000_0021_ECX,
 	NR_KVM_CPU_CAPS,
 
 	NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,

arch/x86/include/asm/mshyperv.h

@@ -112,12 +112,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	return hv_status;
 }
 
-/* Hypercall to the L0 hypervisor */
-static inline u64 hv_do_nested_hypercall(u64 control, void *input, void *output)
-{
-	return hv_do_hypercall(control | HV_HYPERCALL_NESTED, input, output);
-}
-
 /* Fast hypercall with 8 bytes of input and no output */
 static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1)
 {
@@ -165,13 +159,6 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 	return _hv_do_fast_hypercall8(control, input1);
 }
 
-static inline u64 hv_do_fast_nested_hypercall8(u16 code, u64 input1)
-{
-	u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
-
-	return _hv_do_fast_hypercall8(control, input1);
-}
-
 /* Fast hypercall with 16 bytes of input */
 static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
 {
@@ -223,13 +210,6 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
 	return _hv_do_fast_hypercall16(control, input1, input2);
 }
 
-static inline u64 hv_do_fast_nested_hypercall16(u16 code, u64 input1, u64 input2)
-{
-	u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
-
-	return _hv_do_fast_hypercall16(control, input1, input2);
-}
-
 extern struct hv_vp_assist_page **hv_vp_assist_page;
 
 static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
@@ -262,6 +242,8 @@ static inline void hv_apic_init(void) {}
 
 struct irq_domain *hv_create_pci_msi_domain(void);
 
+int hv_map_msi_interrupt(struct irq_data *data,
+			 struct hv_interrupt_entry *out_entry);
 int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector,
 		struct hv_interrupt_entry *entry);
 int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);

arch/x86/include/asm/msr-index.h

@@ -628,6 +628,7 @@
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
 #define MSR_AMD_PPIN_CTL		0xc00102f0
 #define MSR_AMD_PPIN			0xc00102f1
+#define MSR_AMD64_CPUID_FN_7		0xc0011002
 #define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022

arch/x86/include/asm/mwait.h

@@ -43,8 +43,6 @@ static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx)
 
 static __always_inline void __mwait(u32 eax, u32 ecx)
 {
-	mds_idle_clear_cpu_buffers();
-
 	/*
 	 * Use the instruction mnemonic with implicit operands, as the LLVM
 	 * assembler fails to assemble the mnemonic with explicit operands:
@@ -80,7 +78,7 @@ static __always_inline void __mwait(u32 eax, u32 ecx)
  */
 static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
 {
-	/* No MDS buffer clear as this is AMD/HYGON only */
+	/* No need for TSA buffer clearing on AMD */
 
 	/* "mwaitx %eax, %ebx, %ecx" */
 	asm volatile(".byte 0x0f, 0x01, 0xfb"
@@ -98,7 +96,6 @@ static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
  */
 static __always_inline void __sti_mwait(u32 eax, u32 ecx)
 {
-	mds_idle_clear_cpu_buffers();
 
 	asm volatile("sti; mwait" :: "a" (eax), "c" (ecx));
 }
@@ -115,13 +112,20 @@ static __always_inline void __sti_mwait(u32 eax, u32 ecx)
  */
 static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx)
 {
+	if (need_resched())
+		return;
+
+	x86_idle_clear_cpu_buffers();
+
 	if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
 		const void *addr = &current_thread_info()->flags;
 
 		alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
 		__monitor(addr, 0, 0);
 
-		if (!need_resched()) {
+		if (need_resched())
+			goto out;
+
 		if (ecx & 1) {
 			__mwait(eax, ecx);
 		} else {
@@ -129,7 +133,8 @@ static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx)
 			raw_local_irq_disable();
 		}
 	}
-	}
+
+out:
 	current_clr_polling();
 }
 

arch/x86/include/asm/nospec-branch.h

@@ -302,25 +302,31 @@
 .endm
 
 /*
- * Macro to execute VERW instruction that mitigate transient data sampling
+ * Macro to execute VERW insns that mitigate transient data sampling
- * attacks such as MDS. On affected systems a microcode update overloaded VERW
+ * attacks such as MDS or TSA. On affected systems a microcode update
- * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
+ * overloaded VERW insns to also clear the CPU buffers. VERW clobbers
- *
+ * CFLAGS.ZF.
  * Note: Only the memory operand variant of VERW clears the CPU buffers.
  */
-.macro CLEAR_CPU_BUFFERS
+.macro __CLEAR_CPU_BUFFERS feature
 #ifdef CONFIG_X86_64
-	ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF
+	ALTERNATIVE "", "verw x86_verw_sel(%rip)", \feature
 #else
 	/*
 	 * In 32bit mode, the memory operand must be a %cs reference. The data
 	 * segments may not be usable (vm86 mode), and the stack segment may not
 	 * be flat (ESPFIX32).
 	 */
-	ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF
+	ALTERNATIVE "", "verw %cs:x86_verw_sel", \feature
 #endif
 .endm
 
+#define CLEAR_CPU_BUFFERS \
+	__CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF
+
+#define VM_CLEAR_CPU_BUFFERS \
+	__CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF_VM
+
 #ifdef CONFIG_X86_64
 .macro CLEAR_BRANCH_HISTORY
 	ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
@@ -567,24 +573,24 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
 DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
 
-DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
+DECLARE_STATIC_KEY_FALSE(cpu_buf_idle_clear);
 
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
 
 DECLARE_STATIC_KEY_FALSE(cpu_buf_vm_clear);
 
-extern u16 mds_verw_sel;
+extern u16 x86_verw_sel;
 
 #include <asm/segment.h>
 
 /**
- * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
+ * x86_clear_cpu_buffers - Buffer clearing support for different x86 CPU vulns
  *
  * This uses the otherwise unused and obsolete VERW instruction in
  * combination with microcode which triggers a CPU buffer flush when the
  * instruction is executed.
  */
-static __always_inline void mds_clear_cpu_buffers(void)
+static __always_inline void x86_clear_cpu_buffers(void)
 {
 	static const u16 ds = __KERNEL_DS;
 
@@ -601,14 +607,15 @@ static __always_inline void mds_clear_cpu_buffers(void)
 }
 
 /**
- * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
+ * x86_idle_clear_cpu_buffers - Buffer clearing support in idle for the MDS
+ * and TSA vulnerabilities.
  *
  * Clear CPU buffers if the corresponding static key is enabled
  */
-static __always_inline void mds_idle_clear_cpu_buffers(void)
+static __always_inline void x86_idle_clear_cpu_buffers(void)
 {
-	if (static_branch_likely(&mds_idle_clear))
+	if (static_branch_likely(&cpu_buf_idle_clear))
-		mds_clear_cpu_buffers();
+		x86_clear_cpu_buffers();
 }
 
 #endif /* __ASSEMBLER__ */

arch/x86/include/asm/sev.h

@@ -223,6 +223,18 @@ struct snp_tsc_info_resp {
 	u8 rsvd2[100];
 } __packed;
 
+/*
+ * Obtain the mean TSC frequency by decreasing the nominal TSC frequency with
+ * TSC_FACTOR as documented in the SNP Firmware ABI specification:
+ *
+ * GUEST_TSC_FREQ * (1 - (TSC_FACTOR * 0.00001))
+ *
+ * which is equivalent to:
+ *
+ * GUEST_TSC_FREQ -= (GUEST_TSC_FREQ * TSC_FACTOR) / 100000;
+ */
+#define SNP_SCALE_TSC_FREQ(freq, factor) ((freq) - (freq) * (factor) / 100000)
+
 struct snp_guest_req {
 	void *req_buf;
 	size_t req_sz;
@@ -282,8 +294,11 @@ struct snp_secrets_page {
 	u8 svsm_guest_vmpl;
 	u8 rsvd3[3];
 
+	/* The percentage decrease from nominal to mean TSC frequency. */
+	u32 tsc_factor;
+
 	/* Remainder of page */
-	u8 rsvd4[3744];
+	u8 rsvd4[3740];
 } __packed;
 
 struct snp_msg_desc {

arch/x86/include/asm/shared/tdx.h

@@ -72,6 +72,7 @@
 #define TDVMCALL_MAP_GPA		0x10001
 #define TDVMCALL_GET_QUOTE		0x10002
 #define TDVMCALL_REPORT_FATAL_ERROR	0x10003
+#define TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT 0x10004ULL
 
 /*
  * TDG.VP.VMCALL Status Codes (returned in R10)

arch/x86/include/uapi/asm/kvm.h

@@ -965,7 +965,13 @@ struct kvm_tdx_cmd {
 struct kvm_tdx_capabilities {
 	__u64 supported_attrs;
 	__u64 supported_xfam;
-	__u64 reserved[254];
+
+	__u64 kernel_tdvmcallinfo_1_r11;
+	__u64 user_tdvmcallinfo_1_r11;
+	__u64 kernel_tdvmcallinfo_1_r12;
+	__u64 user_tdvmcallinfo_1_r12;
+
+	__u64 reserved[250];
 
 	/* Configurable CPUID bits for userspace */
 	struct kvm_cpuid2 cpuid;

arch/x86/kernel/cpu/amd.c

@@ -9,7 +9,7 @@
 #include <linux/sched/clock.h>
 #include <linux/random.h>
 #include <linux/topology.h>
-#include <asm/amd/fch.h>
+#include <linux/platform_data/x86/amd-fch.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cacheinfo.h>
@@ -377,6 +377,47 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c)
 #endif
 }
 
+#define ZEN_MODEL_STEP_UCODE(fam, model, step, ucode) \
+	X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, fam, model), \
+			    step, step, ucode)
+
+static const struct x86_cpu_id amd_tsa_microcode[] = {
+	ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x1, 0x0a0011d7),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x2, 0x0a00123b),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x08, 0x2, 0x0a00820d),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x1, 0x0a10114c),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x2, 0x0a10124c),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x18, 0x1, 0x0a108109),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x0, 0x0a20102e),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x2, 0x0a201211),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x44, 0x1, 0x0a404108),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x50, 0x0, 0x0a500012),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x61, 0x2, 0x0a60120a),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x74, 0x1, 0x0a704108),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x75, 0x2, 0x0a705208),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x78, 0x0, 0x0a708008),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x7c, 0x0, 0x0a70c008),
+	ZEN_MODEL_STEP_UCODE(0x19, 0xa0, 0x2, 0x0aa00216),
+	{},
+};
+
+static void tsa_init(struct cpuinfo_x86 *c)
+{
+	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+		return;
+
+	if (cpu_has(c, X86_FEATURE_ZEN3) ||
+	    cpu_has(c, X86_FEATURE_ZEN4)) {
+		if (x86_match_min_microcode_rev(amd_tsa_microcode))
+			setup_force_cpu_cap(X86_FEATURE_VERW_CLEAR);
+		else
+			pr_debug("%s: current revision: 0x%x\n", __func__, c->microcode);
+	} else {
+		setup_force_cpu_cap(X86_FEATURE_TSA_SQ_NO);
+		setup_force_cpu_cap(X86_FEATURE_TSA_L1_NO);
+	}
+}
+
 static void bsp_init_amd(struct cpuinfo_x86 *c)
 {
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
@@ -489,6 +530,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 	}
 
 	bsp_determine_snp(c);
+
+	tsa_init(c);
+
 	return;
 
 warn:
@@ -930,6 +974,16 @@ static void init_amd_zen2(struct cpuinfo_x86 *c)
 	init_spectral_chicken(c);
 	fix_erratum_1386(c);
 	zen2_zenbleed_check(c);
+
+	/* Disable RDSEED on AMD Cyan Skillfish because of an error. */
+	if (c->x86_model == 0x47 && c->x86_stepping == 0x0) {
+		clear_cpu_cap(c, X86_FEATURE_RDSEED);
+		msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18);
+		pr_emerg("RDSEED is not reliable on this platform; disabling.\n");
+	}
+
+	/* Correct misconfigured CPUID on some clients. */
+	clear_cpu_cap(c, X86_FEATURE_INVLPGB);
 }
 
 static void init_amd_zen3(struct cpuinfo_x86 *c)

arch/x86/kernel/cpu/bugs.c

@@ -94,6 +94,8 @@ static void __init bhi_apply_mitigation(void);
 static void __init its_select_mitigation(void);
 static void __init its_update_mitigation(void);
 static void __init its_apply_mitigation(void);
+static void __init tsa_select_mitigation(void);
+static void __init tsa_apply_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR without task-specific bits set */
 u64 x86_spec_ctrl_base;
@@ -169,9 +171,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 DEFINE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
 EXPORT_SYMBOL_GPL(switch_vcpu_ibpb);
 
-/* Control MDS CPU buffer clear before idling (halt, mwait) */
+/* Control CPU buffer clear before idling (halt, mwait) */
-DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
+DEFINE_STATIC_KEY_FALSE(cpu_buf_idle_clear);
-EXPORT_SYMBOL_GPL(mds_idle_clear);
+EXPORT_SYMBOL_GPL(cpu_buf_idle_clear);
 
 /*
  * Controls whether l1d flush based mitigations are enabled,
@@ -225,6 +227,7 @@ void __init cpu_select_mitigations(void)
 	gds_select_mitigation();
 	its_select_mitigation();
 	bhi_select_mitigation();
+	tsa_select_mitigation();
 
 	/*
 	 * After mitigations are selected, some may need to update their
@@ -272,6 +275,7 @@ void __init cpu_select_mitigations(void)
 	gds_apply_mitigation();
 	its_apply_mitigation();
 	bhi_apply_mitigation();
+	tsa_apply_mitigation();
 }
 
 /*
@@ -637,7 +641,7 @@ static void __init mmio_apply_mitigation(void)
 	 * is required irrespective of SMT state.
 	 */
 	if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO))
-		static_branch_enable(&mds_idle_clear);
+		static_branch_enable(&cpu_buf_idle_clear);
 
 	if (mmio_nosmt || cpu_mitigations_auto_nosmt())
 		cpu_smt_disable(false);
@@ -1487,6 +1491,94 @@ static void __init its_apply_mitigation(void)
 	set_return_thunk(its_return_thunk);
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt)	"Transient Scheduler Attacks: " fmt
+
+enum tsa_mitigations {
+	TSA_MITIGATION_NONE,
+	TSA_MITIGATION_AUTO,
+	TSA_MITIGATION_UCODE_NEEDED,
+	TSA_MITIGATION_USER_KERNEL,
+	TSA_MITIGATION_VM,
+	TSA_MITIGATION_FULL,
+};
+
+static const char * const tsa_strings[] = {
+	[TSA_MITIGATION_NONE]		= "Vulnerable",
+	[TSA_MITIGATION_UCODE_NEEDED]	= "Vulnerable: No microcode",
+	[TSA_MITIGATION_USER_KERNEL]	= "Mitigation: Clear CPU buffers: user/kernel boundary",
+	[TSA_MITIGATION_VM]		= "Mitigation: Clear CPU buffers: VM",
+	[TSA_MITIGATION_FULL]		= "Mitigation: Clear CPU buffers",
+};
+
+static enum tsa_mitigations tsa_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_TSA) ? TSA_MITIGATION_AUTO : TSA_MITIGATION_NONE;
+
+static int __init tsa_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		tsa_mitigation = TSA_MITIGATION_NONE;
+	else if (!strcmp(str, "on"))
+		tsa_mitigation = TSA_MITIGATION_FULL;
+	else if (!strcmp(str, "user"))
+		tsa_mitigation = TSA_MITIGATION_USER_KERNEL;
+	else if (!strcmp(str, "vm"))
+		tsa_mitigation = TSA_MITIGATION_VM;
+	else
+		pr_err("Ignoring unknown tsa=%s option.\n", str);
+
+	return 0;
+}
+early_param("tsa", tsa_parse_cmdline);
+
+static void __init tsa_select_mitigation(void)
+{
+	if (cpu_mitigations_off() || !boot_cpu_has_bug(X86_BUG_TSA)) {
+		tsa_mitigation = TSA_MITIGATION_NONE;
+		return;
+	}
+
+	if (tsa_mitigation == TSA_MITIGATION_NONE)
+		return;
+
+	if (!boot_cpu_has(X86_FEATURE_VERW_CLEAR)) {
+		tsa_mitigation = TSA_MITIGATION_UCODE_NEEDED;
+		goto out;
+	}
+
+	if (tsa_mitigation == TSA_MITIGATION_AUTO)
+		tsa_mitigation = TSA_MITIGATION_FULL;
+
+	/*
+	 * No need to set verw_clear_cpu_buf_mitigation_selected - it
+	 * doesn't fit all cases here and it is not needed because this
+	 * is the only VERW-based mitigation on AMD.
+	 */
+out:
+	pr_info("%s\n", tsa_strings[tsa_mitigation]);
+}
+
+static void __init tsa_apply_mitigation(void)
+{
+	switch (tsa_mitigation) {
+	case TSA_MITIGATION_USER_KERNEL:
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+		break;
+	case TSA_MITIGATION_VM:
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+		break;
+	case TSA_MITIGATION_FULL:
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+		break;
+	default:
+		break;
+	}
+}
+
 #undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V2 : " fmt
 
@@ -2249,10 +2341,10 @@ static void update_mds_branch_idle(void)
 		return;
 
 	if (sched_smt_active()) {
-		static_branch_enable(&mds_idle_clear);
+		static_branch_enable(&cpu_buf_idle_clear);
 	} else if (mmio_mitigation == MMIO_MITIGATION_OFF ||
 		   (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) {
-		static_branch_disable(&mds_idle_clear);
+		static_branch_disable(&cpu_buf_idle_clear);
 	}
 }
 
@@ -2316,6 +2408,25 @@ void cpu_bugs_smt_update(void)
 		break;
 	}
 
+	switch (tsa_mitigation) {
+	case TSA_MITIGATION_USER_KERNEL:
+	case TSA_MITIGATION_VM:
+	case TSA_MITIGATION_AUTO:
+	case TSA_MITIGATION_FULL:
+		/*
+		 * TSA-SQ can potentially lead to info leakage between
+		 * SMT threads.
+		 */
+		if (sched_smt_active())
+			static_branch_enable(&cpu_buf_idle_clear);
+		else
+			static_branch_disable(&cpu_buf_idle_clear);
+		break;
+	case TSA_MITIGATION_NONE:
+	case TSA_MITIGATION_UCODE_NEEDED:
+		break;
+	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }
 
@@ -3265,6 +3376,11 @@ static ssize_t gds_show_state(char *buf)
 	return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]);
 }
 
+static ssize_t tsa_show_state(char *buf)
+{
+	return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]);
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -3328,6 +3444,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_ITS:
 		return its_show_state(buf);
 
+	case X86_BUG_TSA:
+		return tsa_show_state(buf);
+
 	default:
 		break;
 	}
@@ -3414,6 +3533,11 @@ ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_att
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_ITS);
 }
+
+ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_TSA);
+}
 #endif
 
 void __warn_thunk(void)

arch/x86/kernel/cpu/common.c

@@ -1233,6 +1233,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define ITS		BIT(8)
 /* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */
 #define ITS_NATIVE_ONLY	BIT(9)
+/* CPU is affected by Transient Scheduler Attacks */
+#define TSA		BIT(10)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE,	     X86_STEP_MAX,	SRBDS),
@@ -1280,7 +1282,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_AMD(0x16, RETBLEED),
 	VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
 	VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
-	VULNBL_AMD(0x19, SRSO),
+	VULNBL_AMD(0x19, SRSO | TSA),
 	VULNBL_AMD(0x1a, SRSO),
 	{}
 };
@@ -1530,6 +1532,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 			setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY);
 	}
 
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		if (!cpu_has(c, X86_FEATURE_TSA_SQ_NO) ||
+		    !cpu_has(c, X86_FEATURE_TSA_L1_NO)) {
+			if (cpu_matches(cpu_vuln_blacklist, TSA) ||
+			    /* Enable bug on Zen guests to allow for live migration. */
+			    (cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_ZEN)))
+				setup_force_cpu_bug(X86_BUG_TSA);
+		}
+	}
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;