Linux 6.10-rc4

2025-01-01 18:52:02 +00:00 · 2024-06-17 08:31:12 +02:00 · 2024-06-17 08:31:12 +02:00 · 2046047295
commit 2046047295
parent 2db573c5dc 6ba59ff422
572 changed files with 5891 additions and 3318 deletions
--- a/.editorconfig
+++ b/.editorconfig
@ -5,7 +5,6 @@ root = true
 [{*.{awk,c,dts,dtsi,dtso,h,mk,s,S},Kconfig,Makefile,Makefile.*}]
 charset = utf-8
 end_of_line = lf
-trim_trailing_whitespace = true
 insert_final_newline = true
 indent_style = tab
 indent_size = 8
@ -13,7 +12,6 @@ indent_size = 8
 [*.{json,py,rs}]
 charset = utf-8
 end_of_line = lf
-trim_trailing_whitespace = true
 insert_final_newline = true
 indent_style = space
 indent_size = 4
@ -26,7 +24,6 @@ indent_size = 8
 [*.yaml]
 charset = utf-8
 end_of_line = lf
-trim_trailing_whitespace = unset
 insert_final_newline = true
 indent_style = space
 indent_size = 2
--- a/.mailmap
+++ b/.mailmap
@ -72,6 +72,8 @@ Andrey Ryabinin <ryabinin.a.a@gmail.com> <aryabinin@virtuozzo.com>
 Andrzej Hajda <andrzej.hajda@intel.com> <a.hajda@samsung.com>
 André Almeida <andrealmeid@igalia.com> <andrealmeid@collabora.com>
 Andy Adamson <andros@citi.umich.edu>
+Andy Shevchenko <andy@kernel.org> <andy@smile.org.ua>
+Andy Shevchenko <andy@kernel.org> <ext-andriy.shevchenko@nokia.com>
 Anilkumar Kolli <quic_akolli@quicinc.com> <akolli@codeaurora.org>
 Anirudh Ghayal <quic_aghayal@quicinc.com> <aghayal@codeaurora.org>
 Antoine Tenart <atenart@kernel.org> <antoine.tenart@bootlin.com>
@ -217,6 +219,7 @@ Geliang Tang <geliang@kernel.org> <geliang.tang@suse.com>
 Geliang Tang <geliang@kernel.org> <geliangtang@xiaomi.com>
 Geliang Tang <geliang@kernel.org> <geliangtang@gmail.com>
 Geliang Tang <geliang@kernel.org> <geliangtang@163.com>
+Geliang Tang <geliang@kernel.org> <tanggeliang@kylinos.cn>
 Georgi Djakov <djakov@kernel.org> <georgi.djakov@linaro.org>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
--- a/Documentation/admin-guide/LSM/tomoyo.rst
+++ b/Documentation/admin-guide/LSM/tomoyo.rst
@ -9,8 +9,8 @@ TOMOYO is a name-based MAC extension (LSM module) for the Linux kernel.

 LiveCD-based tutorials are available at

-http://tomoyo.sourceforge.jp/1.8/ubuntu12.04-live.html
-http://tomoyo.sourceforge.jp/1.8/centos6-live.html
+https://tomoyo.sourceforge.net/1.8/ubuntu12.04-live.html
+https://tomoyo.sourceforge.net/1.8/centos6-live.html

 Though these tutorials use non-LSM version of TOMOYO, they are useful for you
 to know what TOMOYO is.
@ -21,45 +21,32 @@ How to enable TOMOYO?
 Build the kernel with ``CONFIG_SECURITY_TOMOYO=y`` and pass ``security=tomoyo`` on
 kernel's command line.

-Please see http://tomoyo.osdn.jp/2.5/ for details.
+Please see https://tomoyo.sourceforge.net/2.6/ for details.

 Where is documentation?
 =======================

 User <-> Kernel interface documentation is available at
-https://tomoyo.osdn.jp/2.5/policy-specification/index.html .
+https://tomoyo.sourceforge.net/2.6/policy-specification/index.html .

 Materials we prepared for seminars and symposiums are available at
-https://osdn.jp/projects/tomoyo/docs/?category_id=532&language_id=1 .
+https://sourceforge.net/projects/tomoyo/files/docs/ .
 Below lists are chosen from three aspects.

 What is TOMOYO?
  TOMOYO Linux Overview
-    https://osdn.jp/projects/tomoyo/docs/lca2009-takeda.pdf
+    https://sourceforge.net/projects/tomoyo/files/docs/lca2009-takeda.pdf
  TOMOYO Linux: pragmatic and manageable security for Linux
-    https://osdn.jp/projects/tomoyo/docs/freedomhectaipei-tomoyo.pdf
+    https://sourceforge.net/projects/tomoyo/files/docs/freedomhectaipei-tomoyo.pdf
  TOMOYO Linux: A Practical Method to Understand and Protect Your Own Linux Box
-    https://osdn.jp/projects/tomoyo/docs/PacSec2007-en-no-demo.pdf
+    https://sourceforge.net/projects/tomoyo/files/docs/PacSec2007-en-no-demo.pdf

 What can TOMOYO do?
  Deep inside TOMOYO Linux
-    https://osdn.jp/projects/tomoyo/docs/lca2009-kumaneko.pdf
+    https://sourceforge.net/projects/tomoyo/files/docs/lca2009-kumaneko.pdf
  The role of "pathname based access control" in security.
-    https://osdn.jp/projects/tomoyo/docs/lfj2008-bof.pdf
+    https://sourceforge.net/projects/tomoyo/files/docs/lfj2008-bof.pdf

 History of TOMOYO?
  Realities of Mainlining
-    https://osdn.jp/projects/tomoyo/docs/lfj2008.pdf
-
-What is future plan?
-====================
-
-We believe that inode based security and name based security are complementary
-and both should be used together. But unfortunately, so far, we cannot enable
-multiple LSM modules at the same time. We feel sorry that you have to give up
-SELinux/SMACK/AppArmor etc. when you want to use TOMOYO.
-
-We hope that LSM becomes stackable in future. Meanwhile, you can use non-LSM
-version of TOMOYO, available at http://tomoyo.osdn.jp/1.8/ .
-LSM version of TOMOYO is a subset of non-LSM version of TOMOYO. We are planning
-to port non-LSM version's functionalities to LSM versions.
+    https://sourceforge.net/projects/tomoyo/files/docs/lfj2008.pdf
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@ -467,11 +467,11 @@ anon_fault_fallback_charge
 	instead falls back to using huge pages with lower orders or
 	small pages even though the allocation was successful.

-anon_swpout
+swpout
 	is incremented every time a huge page is swapped out in one
 	piece without splitting.

-anon_swpout_fallback
+swpout_fallback
 	is incremented if a huge page has to be split before swapout.
 	Usually because failed to allocate some continuous swap space
 	for the huge page.
--- a/Documentation/cdrom/cdrom-standard.rst
+++ b/Documentation/cdrom/cdrom-standard.rst
@ -217,7 +217,7 @@ current *struct* is::
 		int (*media_changed)(struct cdrom_device_info *, int);
 		int (*tray_move)(struct cdrom_device_info *, int);
 		int (*lock_door)(struct cdrom_device_info *, int);
-		int (*select_speed)(struct cdrom_device_info *, int);
+		int (*select_speed)(struct cdrom_device_info *, unsigned long);
 		int (*get_last_session) (struct cdrom_device_info *,
 					 struct cdrom_multisession *);
 		int (*get_mcn)(struct cdrom_device_info *, struct cdrom_mcn *);
@ -396,7 +396,7 @@ action need be taken, and the return value should be 0.

 ::

-	int select_speed(struct cdrom_device_info *cdi, int speed)
+	int select_speed(struct cdrom_device_info *cdi, unsigned long speed)

 Some CD-ROM drives are capable of changing their head-speed. There
 are several reasons for changing the speed of a CD-ROM drive. Badly
--- a/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml
+++ b/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml
@ -54,11 +54,10 @@ unevaluatedProperties: false

 examples:
  - |
-    mlahb: ahb@38000000 {
+    ahb {
      compatible = "st,mlahb", "simple-bus";
      #address-cells = <1>;
      #size-cells = <1>;
-      reg = <0x10000000 0x40000>;
      ranges;
      dma-ranges = <0x00000000 0x38000000 0x10000>,
                   <0x10000000 0x10000000 0x60000>,
--- a/Documentation/devicetree/bindings/arm/sunxi.yaml
+++ b/Documentation/devicetree/bindings/arm/sunxi.yaml
@ -57,17 +57,17 @@ properties:
          - const: allwinner,sun8i-v3s

      - description: Anbernic RG35XX (2024)
-      - items:
+        items:
          - const: anbernic,rg35xx-2024
          - const: allwinner,sun50i-h700

      - description: Anbernic RG35XX Plus
-      - items:
+        items:
          - const: anbernic,rg35xx-plus
          - const: allwinner,sun50i-h700

      - description: Anbernic RG35XX H
-      - items:
+        items:
          - const: anbernic,rg35xx-h
          - const: allwinner,sun50i-h700

--- a/Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml
+++ b/Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml
@ -145,7 +145,7 @@ allOf:
                Voltage output range of the channel as <minimum, maximum>
                Required connections:
                  Rfb1x for: 0 to 2.5 V; 0 to 3V; 0 to 5 V;
-                  Rfb2x for: 0 to 10 V; 2.5 to 7.5V; -5 to 5 V;
+                  Rfb2x for: 0 to 10 V; -2.5 to 7.5V; -5 to 5 V;
              oneOf:
                - items:
                    - const: 0
--- a/Documentation/devicetree/bindings/input/elan,ekth6915.yaml
+++ b/Documentation/devicetree/bindings/input/elan,ekth6915.yaml
@ -18,9 +18,12 @@ allOf:

 properties:
  compatible:
-    enum:
-      - elan,ekth6915
-      - ilitek,ili2901
+    oneOf:
+      - items:
+          - enum:
+              - elan,ekth5015m
+          - const: elan,ekth6915
+      - const: elan,ekth6915

  reg:
    const: 0x10
@ -33,6 +36,12 @@ properties:
  reset-gpios:
    description: Reset GPIO; not all touchscreens using eKTH6915 hook this up.

+  no-reset-on-power-off:
+    type: boolean
+    description:
+      Reset line is wired so that it can (and should) be left deasserted when
+      the power supply is off.
+
  vcc33-supply:
    description: The 3.3V supply to the touchscreen.

@ -58,8 +67,8 @@ examples:
      #address-cells = <1>;
      #size-cells = <0>;

-      ap_ts: touchscreen@10 {
-        compatible = "elan,ekth6915";
+      touchscreen@10 {
+        compatible = "elan,ekth5015m", "elan,ekth6915";
        reg = <0x10>;

        interrupt-parent = <&tlmm>;
--- a/Documentation/devicetree/bindings/input/ilitek,ili2901.yaml
+++ b/Documentation/devicetree/bindings/input/ilitek,ili2901.yaml
@ -0,0 +1,66 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/ilitek,ili2901.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Ilitek ILI2901 touchscreen controller
+
+maintainers:
+  - Jiri Kosina <jkosina@suse.com>
+
+description:
+  Supports the Ilitek ILI2901 touchscreen controller.
+  This touchscreen controller uses the i2c-hid protocol with a reset GPIO.
+
+allOf:
+  - $ref: /schemas/input/touchscreen/touchscreen.yaml#
+
+properties:
+  compatible:
+    enum:
+      - ilitek,ili2901
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  panel: true
+
+  reset-gpios:
+    maxItems: 1
+
+  vcc33-supply: true
+
+  vccio-supply: true
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - vcc33-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    i2c {
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      touchscreen@41 {
+        compatible = "ilitek,ili2901";
+        reg = <0x41>;
+
+        interrupt-parent = <&tlmm>;
+        interrupts = <9 IRQ_TYPE_LEVEL_LOW>;
+
+        reset-gpios = <&tlmm 8 GPIO_ACTIVE_LOW>;
+        vcc33-supply = <&pp3300_ts>;
+      };
+    };
--- a/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml
+++ b/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml
@ -65,6 +65,7 @@ patternProperties:
    description: The hard wired USB devices
    type: object
    $ref: /schemas/usb/usb-device.yaml
+    additionalProperties: true

 required:
  - peer-hub
--- a/Documentation/kbuild/kconfig-language.rst
+++ b/Documentation/kbuild/kconfig-language.rst
@ -150,6 +150,12 @@ applicable everywhere (see syntax).
 	That will limit the usefulness but on the other hand avoid
 	the illegal configurations all over.

+	If "select" <symbol> is followed by "if" <expr>, <symbol> will be
+	selected by the logical AND of the value of the current menu symbol
+	and <expr>. This means, the lower limit can be downgraded due to the
+	presence of "if" <expr>. This behavior may seem weird, but we rely on
+	it. (The future of this behavior is undecided.)
+
 - weak reverse dependencies: "imply" <symbol> ["if" <expr>]

  This is similar to "select" as it enforces a lower limit on another
@ -184,7 +190,7 @@ applicable everywhere (see syntax).
  ability to hook into a secondary subsystem while allowing the user to
  configure that subsystem out without also having to unset these drivers.

-  Note: If the combination of FOO=y and BAR=m causes a link error,
+  Note: If the combination of FOO=y and BAZ=m causes a link error,
  you can guard the function call with IS_REACHABLE()::

 	foo_init()
@ -202,6 +208,10 @@ applicable everywhere (see syntax).
 	imply BAR
 	imply BAZ

+  Note: If "imply" <symbol> is followed by "if" <expr>, the default of <symbol>
+  will be the logical AND of the value of the current menu symbol and <expr>.
+  (The future of this behavior is undecided.)
+
 - limiting menu display: "visible if" <expr>

  This attribute is only applicable to menu blocks, if the condition is
--- a/Documentation/networking/af_xdp.rst
+++ b/Documentation/networking/af_xdp.rst
@ -329,24 +329,23 @@ XDP_SHARED_UMEM option and provide the initial socket's fd in the
 sxdp_shared_umem_fd field as you registered the UMEM on that
 socket. These two sockets will now share one and the same UMEM.

-In this case, it is possible to use the NIC's packet steering
-capabilities to steer the packets to the right queue. This is not
-possible in the previous example as there is only one queue shared
-among sockets, so the NIC cannot do this steering as it can only steer
-between queues.
+There is no need to supply an XDP program like the one in the previous
+case where sockets were bound to the same queue id and
+device. Instead, use the NIC's packet steering capabilities to steer
+the packets to the right queue. In the previous example, there is only
+one queue shared among sockets, so the NIC cannot do this steering. It
+can only steer between queues.

-In libxdp (or libbpf prior to version 1.0), you need to use the
-xsk_socket__create_shared() API as it takes a reference to a FILL ring
-and a COMPLETION ring that will be created for you and bound to the
-shared UMEM. You can use this function for all the sockets you create,
-or you can use it for the second and following ones and use
-xsk_socket__create() for the first one. Both methods yield the same
-result.
+In libbpf, you need to use the xsk_socket__create_shared() API as it
+takes a reference to a FILL ring and a COMPLETION ring that will be
+created for you and bound to the shared UMEM. You can use this
+function for all the sockets you create, or you can use it for the
+second and following ones and use xsk_socket__create() for the first
+one. Both methods yield the same result.

 Note that a UMEM can be shared between sockets on the same queue id
 and device, as well as between queues on the same device and between
-devices at the same time. It is also possible to redirect to any
-socket as long as it is bound to the same umem with XDP_SHARED_UMEM.
+devices at the same time.

 XDP_USE_NEED_WAKEUP bind flag
 -----------------------------
@ -823,10 +822,6 @@ A: The short answer is no, that is not supported at the moment. The
   switch, or other distribution mechanism, in your NIC to direct
   traffic to the correct queue id and socket.

-   Note that if you are using the XDP_SHARED_UMEM option, it is
-   possible to switch traffic between any socket bound to the same
-   umem.
-
 Q: My packets are sometimes corrupted. What is wrong?

 A: Care has to be taken not to feed the same buffer in the UMEM into
--- a/Documentation/userspace-api/media/v4l/dev-subdev.rst
+++ b/Documentation/userspace-api/media/v4l/dev-subdev.rst
@ -582,7 +582,7 @@ depending on the hardware. In all cases, however, only routes that have the
 Devices generating the streams may allow enabling and disabling some of the
 routes or have a fixed routing configuration. If the routes can be disabled, not
 declaring the routes (or declaring them without
-``VIDIOC_SUBDEV_STREAM_FL_ACTIVE`` flag set) in ``VIDIOC_SUBDEV_S_ROUTING`` will
+``V4L2_SUBDEV_STREAM_FL_ACTIVE`` flag set) in ``VIDIOC_SUBDEV_S_ROUTING`` will
 disable the routes. ``VIDIOC_SUBDEV_S_ROUTING`` will still return such routes
 back to the user in the routes array, with the ``V4L2_SUBDEV_STREAM_FL_ACTIVE``
 flag unset.
--- a/8
+++ b/8
@ -1117,7 +1117,6 @@ L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	Documentation/admin-guide/pm/amd-pstate.rst
 F:	drivers/cpufreq/amd-pstate*
-F:	include/linux/amd-pstate.h
 F:	tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py

 AMD PTDMA DRIVER
@ -11045,8 +11044,8 @@ F:	include/uapi/drm/i915_drm.h

 INTEL DRM XE DRIVER (Lunar Lake and newer)
 M:	Lucas De Marchi <lucas.demarchi@intel.com>
-M:	Oded Gabbay <ogabbay@kernel.org>
 M:	Thomas Hellström <thomas.hellstrom@linux.intel.com>
+M:	Rodrigo Vivi <rodrigo.vivi@intel.com>
 L:	intel-xe@lists.freedesktop.org
 S:	Supported
 W:	https://drm.pages.freedesktop.org/intel-docs/
@ -15249,7 +15248,6 @@ F:	drivers/staging/most/
 F:	include/linux/most.h

 MOTORCOMM PHY DRIVER
-M:	Peter Geis <pgwipeout@gmail.com>
 M:	Frank <Frank.Sae@motor-comm.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
@ -15838,7 +15836,7 @@ F:	drivers/nfc/virtual_ncidev.c
 F:	tools/testing/selftests/nci/

 NFS, SUNRPC, AND LOCKD CLIENTS
-M:	Trond Myklebust <trond.myklebust@hammerspace.com>
+M:	Trond Myklebust <trondmy@kernel.org>
 M:	Anna Schumaker <anna@kernel.org>
 L:	linux-nfs@vger.kernel.org
 S:	Maintained
@ -22698,7 +22696,7 @@ L:	tomoyo-users-en@lists.osdn.me (subscribers-only, for users in English)
 L:	tomoyo-dev@lists.osdn.me (subscribers-only, for developers in Japanese)
 L:	tomoyo-users@lists.osdn.me (subscribers-only, for users in Japanese)
 S:	Maintained
-W:	https://tomoyo.osdn.jp/
+W:	https://tomoyo.sourceforge.net/
 F:	security/tomoyo/

 TOPSTAR LAPTOP EXTRAS DRIVER
--- a/2
+++ b/2
@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
 NAME = Baby Opossum Posse

 # *DOCUMENTATION*
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@ -232,11 +232,24 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	unsigned long old;

 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+err_out:
 		return;

 	if (IS_ENABLED(CONFIG_UNWINDER_FRAME_POINTER)) {
-		/* FP points one word below parent's top of stack */
-		frame_pointer += 4;
+		/*
+		 * Usually, the stack frames are contiguous in memory but cases
+		 * have been observed where the next stack frame does not live
+		 * at 'frame_pointer + 4' as this code used to assume.
+		 *
+		 * Instead, dereference the field in the stack frame that
+		 * stores the SP of the calling frame: to avoid unbounded
+		 * recursion, this cannot involve any ftrace instrumented
+		 * functions, so use the __get_kernel_nofault() primitive
+		 * directly.
+		 */
+		__get_kernel_nofault(&frame_pointer,
+				     (unsigned long *)(frame_pointer - 8),
+				     unsigned long, err_out);
 	} else {
 		struct stackframe frame = {
 			.fp = frame_pointer,
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@ -146,7 +146,7 @@
 /* Coprocessor traps */
 .macro __init_el2_cptr
 	__check_hvhe .LnVHE_\@, x1
-	mov	x0, #(CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN)
+	mov	x0, #CPACR_ELx_FPEN
 	msr	cpacr_el1, x0
 	b	.Lskip_set_cptr_\@
 .LnVHE_\@:
@ -277,7 +277,7 @@

 	// (h)VHE case
 	mrs	x0, cpacr_el1			// Disable SVE traps
-	orr	x0, x0, #(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)
+	orr	x0, x0, #CPACR_ELx_ZEN
 	msr	cpacr_el1, x0
 	b	.Lskip_set_cptr_\@

@ -298,7 +298,7 @@

 	// (h)VHE case
 	mrs	x0, cpacr_el1			// Disable SME traps
-	orr	x0, x0, #(CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN)
+	orr	x0, x0, #CPACR_ELx_SMEN
 	msr	cpacr_el1, x0
 	b	.Lskip_set_cptr_sme_\@

--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@ -153,8 +153,9 @@ extern void __memset_io(volatile void __iomem *, int, size_t);
 * emit the large TLP from the CPU.
 */

-static inline void __const_memcpy_toio_aligned32(volatile u32 __iomem *to,
-						 const u32 *from, size_t count)
+static __always_inline void
+__const_memcpy_toio_aligned32(volatile u32 __iomem *to, const u32 *from,
+			      size_t count)
 {
 	switch (count) {
 	case 8:
@ -196,24 +197,22 @@ static inline void __const_memcpy_toio_aligned32(volatile u32 __iomem *to,

 void __iowrite32_copy_full(void __iomem *to, const void *from, size_t count);

-static inline void __const_iowrite32_copy(void __iomem *to, const void *from,
-					  size_t count)
+static __always_inline void
+__iowrite32_copy(void __iomem *to, const void *from, size_t count)
 {
-	if (count == 8 || count == 4 || count == 2 || count == 1) {
+	if (__builtin_constant_p(count) &&
+	    (count == 8 || count == 4 || count == 2 || count == 1)) {
 		__const_memcpy_toio_aligned32(to, from, count);
 		dgh();
 	} else {
 		__iowrite32_copy_full(to, from, count);
 	}
 }
+#define __iowrite32_copy __iowrite32_copy

-#define __iowrite32_copy(to, from, count)                  \
-	(__builtin_constant_p(count) ?                     \
-		 __const_iowrite32_copy(to, from, count) : \
-		 __iowrite32_copy_full(to, from, count))
-
-static inline void __const_memcpy_toio_aligned64(volatile u64 __iomem *to,
-						 const u64 *from, size_t count)
+static __always_inline void
+__const_memcpy_toio_aligned64(volatile u64 __iomem *to, const u64 *from,
+			      size_t count)
 {
 	switch (count) {
 	case 8:
@ -255,21 +254,18 @@ static inline void __const_memcpy_toio_aligned64(volatile u64 __iomem *to,

 void __iowrite64_copy_full(void __iomem *to, const void *from, size_t count);

-static inline void __const_iowrite64_copy(void __iomem *to, const void *from,
-					  size_t count)
+static __always_inline void
+__iowrite64_copy(void __iomem *to, const void *from, size_t count)
 {
-	if (count == 8 || count == 4 || count == 2 || count == 1) {
+	if (__builtin_constant_p(count) &&
+	    (count == 8 || count == 4 || count == 2 || count == 1)) {
 		__const_memcpy_toio_aligned64(to, from, count);
 		dgh();
 	} else {
 		__iowrite64_copy_full(to, from, count);
 	}
 }
-
-#define __iowrite64_copy(to, from, count)                  \
-	(__builtin_constant_p(count) ?                     \
-		 __const_iowrite64_copy(to, from, count) : \
-		 __iowrite64_copy_full(to, from, count))
+#define __iowrite64_copy __iowrite64_copy

 /*
 * I/O memory mapping functions.
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@ -305,6 +305,12 @@
 				 GENMASK(19, 14) |	\
 				 BIT(11))

+#define CPTR_VHE_EL2_RES0	(GENMASK(63, 32) |	\
+				 GENMASK(27, 26) |	\
+				 GENMASK(23, 22) |	\
+				 GENMASK(19, 18) |	\
+				 GENMASK(15, 0))
+
 /* Hyp Debug Configuration Register bits */
 #define MDCR_EL2_E2TB_MASK	(UL(0x3))
 #define MDCR_EL2_E2TB_SHIFT	(UL(24))
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@ -557,6 +557,68 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
 		vcpu_set_flag((v), e);					\
 	} while (0)

+#define __build_check_all_or_none(r, bits)				\
+	BUILD_BUG_ON(((r) & (bits)) && ((r) & (bits)) != (bits))
+
+#define __cpacr_to_cptr_clr(clr, set)					\
+	({								\
+		u64 cptr = 0;						\
+									\
+		if ((set) & CPACR_ELx_FPEN)				\
+			cptr |= CPTR_EL2_TFP;				\
+		if ((set) & CPACR_ELx_ZEN)				\
+			cptr |= CPTR_EL2_TZ;				\
+		if ((set) & CPACR_ELx_SMEN)				\
+			cptr |= CPTR_EL2_TSM;				\
+		if ((clr) & CPACR_ELx_TTA)				\
+			cptr |= CPTR_EL2_TTA;				\
+		if ((clr) & CPTR_EL2_TAM)				\
+			cptr |= CPTR_EL2_TAM;				\
+		if ((clr) & CPTR_EL2_TCPAC)				\
+			cptr |= CPTR_EL2_TCPAC;				\
+									\
+		cptr;							\
+	})
+
+#define __cpacr_to_cptr_set(clr, set)					\
+	({								\
+		u64 cptr = 0;						\
+									\
+		if ((clr) & CPACR_ELx_FPEN)				\
+			cptr |= CPTR_EL2_TFP;				\
+		if ((clr) & CPACR_ELx_ZEN)				\
+			cptr |= CPTR_EL2_TZ;				\
+		if ((clr) & CPACR_ELx_SMEN)				\
+			cptr |= CPTR_EL2_TSM;				\
+		if ((set) & CPACR_ELx_TTA)				\
+			cptr |= CPTR_EL2_TTA;				\
+		if ((set) & CPTR_EL2_TAM)				\
+			cptr |= CPTR_EL2_TAM;				\
+		if ((set) & CPTR_EL2_TCPAC)				\
+			cptr |= CPTR_EL2_TCPAC;				\
+									\
+		cptr;							\
+	})
+
+#define cpacr_clear_set(clr, set)					\
+	do {								\
+		BUILD_BUG_ON((set) & CPTR_VHE_EL2_RES0);		\
+		BUILD_BUG_ON((clr) & CPACR_ELx_E0POE);			\
+		__build_check_all_or_none((clr), CPACR_ELx_FPEN);	\
+		__build_check_all_or_none((set), CPACR_ELx_FPEN);	\
+		__build_check_all_or_none((clr), CPACR_ELx_ZEN);	\
+		__build_check_all_or_none((set), CPACR_ELx_ZEN);	\
+		__build_check_all_or_none((clr), CPACR_ELx_SMEN);	\
+		__build_check_all_or_none((set), CPACR_ELx_SMEN);	\
+									\
+		if (has_vhe() || has_hvhe())				\
+			sysreg_clear_set(cpacr_el1, clr, set);		\
+		else							\
+			sysreg_clear_set(cptr_el2,			\
+					 __cpacr_to_cptr_clr(clr, set),	\
+					 __cpacr_to_cptr_set(clr, set));\
+	} while (0)
+
 static __always_inline void kvm_write_cptr_el2(u64 val)
 {
 	if (has_vhe() || has_hvhe())
@ -570,17 +632,16 @@ static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu)
 	u64 val;

 	if (has_vhe()) {
-		val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |
-		       CPACR_EL1_ZEN_EL1EN);
+		val = (CPACR_ELx_FPEN | CPACR_EL1_ZEN_EL1EN);
 		if (cpus_have_final_cap(ARM64_SME))
 			val |= CPACR_EL1_SMEN_EL1EN;
 	} else if (has_hvhe()) {
-		val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN);
+		val = CPACR_ELx_FPEN;

 		if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs())
-			val |= CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN;
+			val |= CPACR_ELx_ZEN;
 		if (cpus_have_final_cap(ARM64_SME))
-			val |= CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN;
+			val |= CPACR_ELx_SMEN;
 	} else {
 		val = CPTR_NVHE_EL2_RES1;

--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@ -76,6 +76,7 @@ static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; };
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);

 extern unsigned int __ro_after_init kvm_sve_max_vl;
+extern unsigned int __ro_after_init kvm_host_sve_max_vl;
 int __init kvm_arm_init_sve(void);

 u32 __attribute_const__ kvm_target_cpu(void);
@ -521,6 +522,20 @@ struct kvm_cpu_context {
 	u64 *vncr_array;
 };

+struct cpu_sve_state {
+	__u64 zcr_el1;
+
+	/*
+	 * Ordering is important since __sve_save_state/__sve_restore_state
+	 * relies on it.
+	 */
+	__u32 fpsr;
+	__u32 fpcr;
+
+	/* Must be SVE_VQ_BYTES (128 bit) aligned. */
+	__u8 sve_regs[];
+};
+
 /*
 * This structure is instantiated on a per-CPU basis, and contains
 * data that is:
@ -534,7 +549,15 @@ struct kvm_cpu_context {
 */
 struct kvm_host_data {
 	struct kvm_cpu_context host_ctxt;
-	struct user_fpsimd_state *fpsimd_state;	/* hyp VA */
+
+	/*
+	 * All pointers in this union are hyp VA.
+	 * sve_state is only used in pKVM and if system_supports_sve().
+	 */
+	union {
+		struct user_fpsimd_state *fpsimd_state;
+		struct cpu_sve_state *sve_state;
+	};

 	/* Ownership of the FP regs */
 	enum {
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@ -111,7 +111,8 @@ void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);

 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
-void __sve_restore_state(void *sve_pffr, u32 *fpsr);
+void __sve_save_state(void *sve_pffr, u32 *fpsr, int save_ffr);
+void __sve_restore_state(void *sve_pffr, u32 *fpsr, int restore_ffr);

 u64 __guest_enter(struct kvm_vcpu *vcpu);

@ -142,5 +143,6 @@ extern u64 kvm_nvhe_sym(id_aa64smfr0_el1_sys_val);

 extern unsigned long kvm_nvhe_sym(__icache_flags);
 extern unsigned int kvm_nvhe_sym(kvm_arm_vmid_bits);
+extern unsigned int kvm_nvhe_sym(kvm_host_sve_max_vl);

 #endif /* __ARM64_KVM_HYP_H__ */
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@ -128,4 +128,13 @@ static inline unsigned long hyp_ffa_proxy_pages(void)
 	return (2 * KVM_FFA_MBOX_NR_PAGES) + DIV_ROUND_UP(desc_max, PAGE_SIZE);
 }

+static inline size_t pkvm_host_sve_state_size(void)
+{
+	if (!system_supports_sve())
+		return 0;
+
+	return size_add(sizeof(struct cpu_sve_state),
+			SVE_SIG_REGS_SIZE(sve_vq_from_vl(kvm_host_sve_max_vl)));
+}
+
 #endif	/* __ARM64_KVM_PKVM_H__ */
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@ -462,6 +462,9 @@ static int run_all_insn_set_hw_mode(unsigned int cpu)
 	for (int i = 0; i < ARRAY_SIZE(insn_emulations); i++) {
 		struct insn_emulation *insn = insn_emulations[i];
 		bool enable = READ_ONCE(insn->current_mode) == INSN_HW;
+		if (insn->status == INSN_UNAVAILABLE)
+			continue;
+
 		if (insn->set_hw_mode && insn->set_hw_mode(enable)) {
 			pr_warn("CPU[%u] cannot support the emulation of %s",
 				cpu, insn->name);
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@ -1931,6 +1931,11 @@ static unsigned long nvhe_percpu_order(void)
 	return size ? get_order(size) : 0;
 }

+static size_t pkvm_host_sve_state_order(void)
+{
+	return get_order(pkvm_host_sve_state_size());
+}
+
 /* A lookup table holding the hypervisor VA for each vector slot */
 static void *hyp_spectre_vector_selector[BP_HARDEN_EL2_SLOTS];

@ -2310,12 +2315,20 @@ static void __init teardown_subsystems(void)

 static void __init teardown_hyp_mode(void)
 {
+	bool free_sve = system_supports_sve() && is_protected_kvm_enabled();
 	int cpu;

 	free_hyp_pgds();
 	for_each_possible_cpu(cpu) {
 		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
 		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
+		if (free_sve) {
+			struct cpu_sve_state *sve_state;
+
+			sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
+			free_pages((unsigned long) sve_state, pkvm_host_sve_state_order());
+		}
 	}
 }

@ -2398,6 +2411,58 @@ static int __init kvm_hyp_init_protection(u32 hyp_va_bits)
 	return 0;
 }

+static int init_pkvm_host_sve_state(void)
+{
+	int cpu;
+
+	if (!system_supports_sve())
+		return 0;
+
+	/* Allocate pages for host sve state in protected mode. */
+	for_each_possible_cpu(cpu) {
+		struct page *page = alloc_pages(GFP_KERNEL, pkvm_host_sve_state_order());
+
+		if (!page)
+			return -ENOMEM;
+
+		per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = page_address(page);
+	}
+
+	/*
+	 * Don't map the pages in hyp since these are only used in protected
+	 * mode, which will (re)create its own mapping when initialized.
+	 */
+
+	return 0;
+}
+
+/*
+ * Finalizes the initialization of hyp mode, once everything else is initialized
+ * and the initialziation process cannot fail.
+ */
+static void finalize_init_hyp_mode(void)
+{
+	int cpu;
+
+	if (system_supports_sve() && is_protected_kvm_enabled()) {
+		for_each_possible_cpu(cpu) {
+			struct cpu_sve_state *sve_state;
+
+			sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
+			per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state =
+				kern_hyp_va(sve_state);
+		}
+	} else {
+		for_each_possible_cpu(cpu) {
+			struct user_fpsimd_state *fpsimd_state;
+
+			fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs;
+			per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state =
+				kern_hyp_va(fpsimd_state);
+		}
+	}
+}
+
 static void pkvm_hyp_init_ptrauth(void)
 {
 	struct kvm_cpu_context *hyp_ctxt;
@ -2566,6 +2631,10 @@ static int __init init_hyp_mode(void)
 			goto out_err;
 		}

+		err = init_pkvm_host_sve_state();
+		if (err)
+			goto out_err;
+
 		err = kvm_hyp_init_protection(hyp_va_bits);
 		if (err) {
 			kvm_err("Failed to init hyp memory protection\n");
@ -2730,6 +2799,13 @@ static __init int kvm_arm_init(void)
 	if (err)
 		goto out_subs;

+	/*
+	 * This should be called after initialization is done and failure isn't
+	 * possible anymore.
+	 */
+	if (!in_hyp_mode)
+		finalize_init_hyp_mode();
+
 	kvm_arm_initialised = true;

 	return 0;
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@ -2181,16 +2181,23 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	if (forward_traps(vcpu, HCR_NV))
 		return;

+	spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2);
+	spsr = kvm_check_illegal_exception_return(vcpu, spsr);
+
 	/* Check for an ERETAx */
 	esr = kvm_vcpu_get_esr(vcpu);
 	if (esr_iss_is_eretax(esr) && !kvm_auth_eretax(vcpu, &elr)) {
 		/*
-		 * Oh no, ERETAx failed to authenticate.  If we have
-		 * FPACCOMBINE, deliver an exception right away.  If we
-		 * don't, then let the mangled ELR value trickle down the
+		 * Oh no, ERETAx failed to authenticate.
+		 *
+		 * If we have FPACCOMBINE and we don't have a pending
+		 * Illegal Execution State exception (which has priority
+		 * over FPAC), deliver an exception right away.
+		 *
+		 * Otherwise, let the mangled ELR value trickle down the
 		 * ERET handling, and the guest will have a little surprise.
 		 */
-		if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE)) {
+		if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE) && !(spsr & PSR_IL_BIT)) {
 			esr &= ESR_ELx_ERET_ISS_ERETA;
 			esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_FPAC);
 			kvm_inject_nested_sync(vcpu, esr);
@ -2201,17 +2208,11 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	preempt_disable();
 	kvm_arch_vcpu_put(vcpu);

-	spsr = __vcpu_sys_reg(vcpu, SPSR_EL2);
-	spsr = kvm_check_illegal_exception_return(vcpu, spsr);
 	if (!esr_iss_is_eretax(esr))
 		elr = __vcpu_sys_reg(vcpu, ELR_EL2);

 	trace_kvm_nested_eret(vcpu, elr, spsr);

-	/*
-	 * Note that the current exception level is always the virtual EL2,
-	 * since we set HCR_EL2.NV bit only when entering the virtual EL2.
-	 */
 	*vcpu_pc(vcpu) = elr;
 	*vcpu_cpsr(vcpu) = spsr;

--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@ -90,6 +90,13 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 			fpsimd_save_and_flush_cpu_state();
 		}
 	}
+
+	/*
+	 * If normal guests gain SME support, maintain this behavior for pKVM
+	 * guests, which don't support SME.
+	 */
+	WARN_ON(is_protected_kvm_enabled() && system_supports_sme() &&
+		read_sysreg_s(SYS_SVCR));
 }

 /*
@ -161,9 +168,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 	if (has_vhe() && system_supports_sme()) {
 		/* Also restore EL0 state seen on entry */
 		if (vcpu_get_flag(vcpu, HOST_SME_ENABLED))
-			sysreg_clear_set(CPACR_EL1, 0,
-					 CPACR_EL1_SMEN_EL0EN |
-					 CPACR_EL1_SMEN_EL1EN);
+			sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_SMEN);
 		else
 			sysreg_clear_set(CPACR_EL1,
 					 CPACR_EL1_SMEN_EL0EN,
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@ -251,6 +251,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		case PSR_AA32_MODE_SVC:
 		case PSR_AA32_MODE_ABT:
 		case PSR_AA32_MODE_UND:
+		case PSR_AA32_MODE_SYS:
 			if (!vcpu_el1_is_32bit(vcpu))
 				return -EINVAL;
 			break;
@ -276,7 +277,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
 		int i, nr_reg;

-		switch (*vcpu_cpsr(vcpu)) {
+		switch (*vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK) {
 		/*
 		 * Either we are dealing with user mode, and only the
 		 * first 15 registers (+ PC) must be narrowed to 32bit.
--- a/arch/arm64/kvm/hyp/aarch32.c
+++ b/arch/arm64/kvm/hyp/aarch32.c
@ -50,9 +50,23 @@ bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
 	u32 cpsr_cond;
 	int cond;

-	/* Top two bits non-zero?  Unconditional. */
-	if (kvm_vcpu_get_esr(vcpu) >> 30)
+	/*
+	 * These are the exception classes that could fire with a
+	 * conditional instruction.
+	 */
+	switch (kvm_vcpu_trap_get_class(vcpu)) {
+	case ESR_ELx_EC_CP15_32:
+	case ESR_ELx_EC_CP15_64:
+	case ESR_ELx_EC_CP14_MR:
+	case ESR_ELx_EC_CP14_LS:
+	case ESR_ELx_EC_FP_ASIMD:
+	case ESR_ELx_EC_CP10_ID:
+	case ESR_ELx_EC_CP14_64:
+	case ESR_ELx_EC_SVC32:
+		break;
+	default:
 		return true;
+	}

 	/* Is condition field valid? */
 	cond = kvm_vcpu_get_condition(vcpu);
--- a/arch/arm64/kvm/hyp/fpsimd.S
+++ b/arch/arm64/kvm/hyp/fpsimd.S
@ -25,3 +25,9 @@ SYM_FUNC_START(__sve_restore_state)
 	sve_load 0, x1, x2, 3
 	ret
 SYM_FUNC_END(__sve_restore_state)
+
+SYM_FUNC_START(__sve_save_state)
+	mov	x2, #1
+	sve_save 0, x1, x2, 3
+	ret
+SYM_FUNC_END(__sve_save_state)
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@ -316,10 +316,24 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 {
 	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
 	__sve_restore_state(vcpu_sve_pffr(vcpu),
-			    &vcpu->arch.ctxt.fp_regs.fpsr);
+			    &vcpu->arch.ctxt.fp_regs.fpsr,
+			    true);
 	write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
 }

+static inline void __hyp_sve_save_host(void)
+{
+	struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
+
+	sve_state->zcr_el1 = read_sysreg_el1(SYS_ZCR);
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+	__sve_save_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
+			 &sve_state->fpsr,
+			 true);
+}
+
+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu);
+
 /*
 * We trap the first access to the FP/SIMD to save the host context and
 * restore the guest context lazily.
@ -330,7 +344,6 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	bool sve_guest;
 	u8 esr_ec;
-	u64 reg;

 	if (!system_supports_fpsimd())
 		return false;
@ -353,24 +366,15 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	/* Valid trap.  Switch the context: */

 	/* First disable enough traps to allow us to update the registers */
-	if (has_vhe() || has_hvhe()) {
-		reg = CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN;
-		if (sve_guest)
-			reg |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
-
-		sysreg_clear_set(cpacr_el1, 0, reg);
-	} else {
-		reg = CPTR_EL2_TFP;
-		if (sve_guest)
-			reg |= CPTR_EL2_TZ;
-
-		sysreg_clear_set(cptr_el2, reg, 0);
-	}
+	if (sve_guest || (is_protected_kvm_enabled() && system_supports_sve()))
+		cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
+	else
+		cpacr_clear_set(0, CPACR_ELx_FPEN);
 	isb();

 	/* Write out the host state if it's in the registers */
 	if (host_owns_fp_regs())
-		__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+		kvm_hyp_save_fpsimd_host(vcpu);

 	/* Restore the guest state */
 	if (sve_guest)
--- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
@ -59,7 +59,6 @@ static inline bool pkvm_hyp_vcpu_is_protected(struct pkvm_hyp_vcpu *hyp_vcpu)
 }

 void pkvm_hyp_vm_table_init(void *tbl);
-void pkvm_host_fpsimd_state_init(void);

 int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
 		   unsigned long pgd_hva);
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@ -23,20 +23,80 @@ DEFINE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);

 void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt);

+static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu)
+{
+	__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
+	/*
+	 * On saving/restoring guest sve state, always use the maximum VL for
+	 * the guest. The layout of the data when saving the sve state depends
+	 * on the VL, so use a consistent (i.e., the maximum) guest VL.
+	 */
+	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
+	__sve_save_state(vcpu_sve_pffr(vcpu), &vcpu->arch.ctxt.fp_regs.fpsr, true);
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+}
+
+static void __hyp_sve_restore_host(void)
+{
+	struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
+
+	/*
+	 * On saving/restoring host sve state, always use the maximum VL for
+	 * the host. The layout of the data when saving the sve state depends
+	 * on the VL, so use a consistent (i.e., the maximum) host VL.
+	 *
+	 * Setting ZCR_EL2 to ZCR_ELx_LEN_MASK sets the effective length
+	 * supported by the system (or limited at EL3).
+	 */
+	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+	__sve_restore_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
+			    &sve_state->fpsr,
+			    true);
+	write_sysreg_el1(sve_state->zcr_el1, SYS_ZCR);
+}
+
+static void fpsimd_sve_flush(void)
+{
+	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
+}
+
+static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
+{
+	if (!guest_owns_fp_regs())
+		return;
+
+	cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN);
+	isb();
+
+	if (vcpu_has_sve(vcpu))
+		__hyp_sve_save_guest(vcpu);
+	else
+		__fpsimd_save_state(&vcpu->arch.ctxt.fp_regs);
+
+	if (system_supports_sve())
+		__hyp_sve_restore_host();
+	else
+		__fpsimd_restore_state(*host_data_ptr(fpsimd_state));
+
+	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
+}
+
 static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
 	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;

+	fpsimd_sve_flush();
+
 	hyp_vcpu->vcpu.arch.ctxt	= host_vcpu->arch.ctxt;

 	hyp_vcpu->vcpu.arch.sve_state	= kern_hyp_va(host_vcpu->arch.sve_state);
-	hyp_vcpu->vcpu.arch.sve_max_vl	= host_vcpu->arch.sve_max_vl;
+	/* Limit guest vector length to the maximum supported by the host.  */
+	hyp_vcpu->vcpu.arch.sve_max_vl	= min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl);

 	hyp_vcpu->vcpu.arch.hw_mmu	= host_vcpu->arch.hw_mmu;

 	hyp_vcpu->vcpu.arch.hcr_el2	= host_vcpu->arch.hcr_el2;
 	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
-	hyp_vcpu->vcpu.arch.cptr_el2	= host_vcpu->arch.cptr_el2;

 	hyp_vcpu->vcpu.arch.iflags	= host_vcpu->arch.iflags;

@ -54,10 +114,11 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	struct vgic_v3_cpu_if *host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3;
 	unsigned int i;

+	fpsimd_sve_sync(&hyp_vcpu->vcpu);
+
 	host_vcpu->arch.ctxt		= hyp_vcpu->vcpu.arch.ctxt;

 	host_vcpu->arch.hcr_el2		= hyp_vcpu->vcpu.arch.hcr_el2;
-	host_vcpu->arch.cptr_el2	= hyp_vcpu->vcpu.arch.cptr_el2;

 	host_vcpu->arch.fault		= hyp_vcpu->vcpu.arch.fault;

@ -79,6 +140,17 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 		struct pkvm_hyp_vcpu *hyp_vcpu;
 		struct kvm *host_kvm;

+		/*
+		 * KVM (and pKVM) doesn't support SME guests for now, and
+		 * ensures that SME features aren't enabled in pstate when
+		 * loading a vcpu. Therefore, if SME features enabled the host
+		 * is misbehaving.
+		 */
+		if (unlikely(system_supports_sme() && read_sysreg_s(SYS_SVCR))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
 		host_kvm = kern_hyp_va(host_vcpu->kvm);
 		hyp_vcpu = pkvm_load_hyp_vcpu(host_kvm->arch.pkvm.handle,
 					      host_vcpu->vcpu_idx);
@ -405,11 +477,7 @@ void handle_trap(struct kvm_cpu_context *host_ctxt)
 		handle_host_smc(host_ctxt);
 		break;
 	case ESR_ELx_EC_SVE:
-		if (has_hvhe())
-			sysreg_clear_set(cpacr_el1, 0, (CPACR_EL1_ZEN_EL1EN |
-							CPACR_EL1_ZEN_EL0EN));
-		else
-			sysreg_clear_set(cptr_el2, CPTR_EL2_TZ, 0);
+		cpacr_clear_set(0, CPACR_ELx_ZEN);
 		isb();
 		sve_cond_update_zcr_vq(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
 		break;
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@ -18,6 +18,8 @@ unsigned long __icache_flags;
 /* Used by kvm_get_vttbr(). */
 unsigned int kvm_arm_vmid_bits;

+unsigned int kvm_host_sve_max_vl;
+
 /*
 * Set trap register values based on features in ID_AA64PFR0.
 */
@ -63,7 +65,7 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
 	/* Trap SVE */
 	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids)) {
 		if (has_hvhe())
-			cptr_clear |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
+			cptr_clear |= CPACR_ELx_ZEN;
 		else
 			cptr_set |= CPTR_EL2_TZ;
 	}
@ -247,17 +249,6 @@ void pkvm_hyp_vm_table_init(void *tbl)
 	vm_table = tbl;
 }

-void pkvm_host_fpsimd_state_init(void)
-{
-	unsigned long i;
-
-	for (i = 0; i < hyp_nr_cpus; i++) {
-		struct kvm_host_data *host_data = per_cpu_ptr(&kvm_host_data, i);
-
-		host_data->fpsimd_state = &host_data->host_ctxt.fp_regs;
-	}
-}
-
 /*
 * Return the hyp vm structure corresponding to the handle.
 */
@ -586,6 +577,8 @@ int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu,
 	if (ret)
 		unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu));

+	hyp_vcpu->vcpu.arch.cptr_el2 = kvm_get_reset_cptr_el2(&hyp_vcpu->vcpu);
+
 	return ret;
 }

--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@ -67,6 +67,28 @@ static int divide_memory_pool(void *virt, unsigned long size)
 	return 0;
 }

+static int pkvm_create_host_sve_mappings(void)
+{
+	void *start, *end;
+	int ret, i;
+
+	if (!system_supports_sve())
+		return 0;
+
+	for (i = 0; i < hyp_nr_cpus; i++) {
+		struct kvm_host_data *host_data = per_cpu_ptr(&kvm_host_data, i);
+		struct cpu_sve_state *sve_state = host_data->sve_state;
+
+		start = kern_hyp_va(sve_state);
+		end = start + PAGE_ALIGN(pkvm_host_sve_state_size());
+		ret = pkvm_create_mappings(start, end, PAGE_HYP);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 				 unsigned long *per_cpu_base,
 				 u32 hyp_va_bits)
@ -125,6 +147,8 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
 			return ret;
 	}

+	pkvm_create_host_sve_mappings();
+
 	/*
 	 * Map the host sections RO in the hypervisor, but transfer the
 	 * ownership from the host to the hypervisor itself to make sure they
@ -300,7 +324,6 @@ void __noreturn __pkvm_init_finalise(void)
 		goto out;

 	pkvm_hyp_vm_table_init(vm_table_base);
-	pkvm_host_fpsimd_state_init();
 out:
 	/*
 	 * We tail-called to here from handle___pkvm_init() and will not return,
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@ -48,15 +48,14 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 	val |= has_hvhe() ? CPACR_EL1_TTA : CPTR_EL2_TTA;
 	if (cpus_have_final_cap(ARM64_SME)) {
 		if (has_hvhe())
-			val &= ~(CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN);
+			val &= ~CPACR_ELx_SMEN;
 		else
 			val |= CPTR_EL2_TSM;
 	}

 	if (!guest_owns_fp_regs()) {
 		if (has_hvhe())
-			val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |
-				 CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN);
+			val &= ~(CPACR_ELx_FPEN | CPACR_ELx_ZEN);
 		else
 			val |= CPTR_EL2_TFP | CPTR_EL2_TZ;

@ -182,6 +181,25 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
 		kvm_handle_pvm_sysreg(vcpu, exit_code));
 }

+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Non-protected kvm relies on the host restoring its sve state.
+	 * Protected kvm restores the host's sve state as not to reveal that
+	 * fpsimd was used by a guest nor leak upper sve bits.
+	 */
+	if (unlikely(is_protected_kvm_enabled() && system_supports_sve())) {
+		__hyp_sve_save_host();
+
+		/* Re-enable SVE traps if not supported for the guest vcpu. */
+		if (!vcpu_has_sve(vcpu))
+			cpacr_clear_set(CPACR_ELx_ZEN, 0);
+
+	} else {
+		__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+	}
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@ -93,8 +93,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)

 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_ELx_TTA;
-	val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN |
-		 CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN);
+	val &= ~(CPACR_ELx_ZEN | CPACR_ELx_SMEN);

 	/*
 	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
@ -109,9 +108,9 @@ static void __activate_traps(struct kvm_vcpu *vcpu)

 	if (guest_owns_fp_regs()) {
 		if (vcpu_has_sve(vcpu))
-			val |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
+			val |= CPACR_ELx_ZEN;
 	} else {
-		val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN);
+		val &= ~CPACR_ELx_FPEN;
 		__activate_traps_fpsimd32(vcpu);
 	}

@ -262,6 +261,11 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return true;
 }

+static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
+{
+	__fpsimd_save_state(*host_data_ptr(fpsimd_state));
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@ -58,8 +58,10 @@ static u64 limit_nv_id_reg(u32 id, u64 val)
 		break;

 	case SYS_ID_AA64PFR1_EL1:
-		/* Only support SSBS */
-		val &= NV_FTR(PFR1, SSBS);
+		/* Only support BTI, SSBS, CSV2_frac */
+		val &= (NV_FTR(PFR1, BT)	|
+			NV_FTR(PFR1, SSBS)	|
+			NV_FTR(PFR1, CSV2_frac));
 		break;

 	case SYS_ID_AA64MMFR0_EL1:
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@ -32,6 +32,7 @@

 /* Maximum phys_shift supported for any VM on this host */
 static u32 __ro_after_init kvm_ipa_limit;
+unsigned int __ro_after_init kvm_host_sve_max_vl;

 /*
 * ARMv8 Reset Values
@ -51,6 +52,8 @@ int __init kvm_arm_init_sve(void)
 {
 	if (system_supports_sve()) {
 		kvm_sve_max_vl = sve_max_virtualisable_vl();
+		kvm_host_sve_max_vl = sve_max_vl();
+		kvm_nvhe_sym(kvm_host_sve_max_vl) = kvm_host_sve_max_vl;

 		/*
 		 * The get_sve_reg()/set_sve_reg() ioctl interface will need
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@ -376,7 +376,7 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma,
 	 * clearing access/dirty for the whole block.
 	 */
 	unsigned long start = addr;
-	unsigned long end = start + nr;
+	unsigned long end = start + nr * PAGE_SIZE;

 	if (pte_cont(__ptep_get(ptep + nr - 1)))
 		end = ALIGN(end, CONT_PTE_SIZE);
@ -386,7 +386,7 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma,
 		ptep = contpte_align_down(ptep);
 	}

-	__clear_young_dirty_ptes(vma, start, ptep, end - start, flags);
+	__clear_young_dirty_ptes(vma, start, ptep, (end - start) / PAGE_SIZE, flags);
 }
 EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes);

--- a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
@ -44,14 +44,14 @@ linux,cma {
 &gmac0 {
 	status = "okay";

-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	bus_id = <0x0>;
 };

 &gmac1 {
 	status = "okay";

-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	bus_id = <0x1>;
 };

--- a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
@ -43,7 +43,7 @@ linux,cma {
 &gmac0 {
 	status = "okay";

-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&phy0>;
 	mdio {
 		compatible = "snps,dwmac-mdio";
@ -58,7 +58,7 @@ phy0: ethernet-phy@0 {
 &gmac1 {
 	status = "okay";

-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&phy1>;
 	mdio {
 		compatible = "snps,dwmac-mdio";
--- a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
@ -92,7 +92,7 @@ phy1: ethernet-phy@1 {
 &gmac2 {
 	status = "okay";

-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&phy2>;
 	mdio {
 		compatible = "snps,dwmac-mdio";
--- a/arch/loongarch/include/asm/numa.h
+++ b/arch/loongarch/include/asm/numa.h
@ -56,6 +56,7 @@ extern int early_cpu_to_node(int cpu);
 static inline void early_numa_add_cpu(int cpuid, s16 node)	{ }
 static inline void numa_add_cpu(unsigned int cpu)		{ }
 static inline void numa_remove_cpu(unsigned int cpu)		{ }
+static inline void set_cpuid_to_node(int cpuid, s16 node)	{ }

 static inline int early_cpu_to_node(int cpu)
 {
--- a/arch/loongarch/include/asm/stackframe.h
+++ b/arch/loongarch/include/asm/stackframe.h
@ -42,7 +42,7 @@
 	.macro JUMP_VIRT_ADDR temp1 temp2
 	li.d	\temp1, CACHE_BASE
 	pcaddi	\temp2, 0
-	or	\temp1, \temp1, \temp2
+	bstrins.d  \temp1, \temp2, (DMW_PABITS - 1), 0
 	jirl	zero, \temp1, 0xc
 	.endm

--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@ -22,7 +22,7 @@
 _head:
 	.word	MZ_MAGIC		/* "MZ", MS-DOS header */
 	.org	0x8
-	.dword	kernel_entry		/* Kernel entry point */
+	.dword	_kernel_entry		/* Kernel entry point (physical address) */
 	.dword	_kernel_asize		/* Kernel image effective size */
 	.quad	PHYS_LINK_KADDR		/* Kernel image load offset from start of RAM */
 	.org	0x38			/* 0x20 ~ 0x37 reserved */
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@ -282,7 +282,7 @@ static void __init fdt_setup(void)
 		return;

 	/* Prefer to use built-in dtb, checking its legality first. */
-	if (!fdt_check_header(__dtb_start))
+	if (IS_ENABLED(CONFIG_BUILTIN_DTB) && !fdt_check_header(__dtb_start))
 		fdt_pointer = __dtb_start;
 	else
 		fdt_pointer = efi_fdt_pointer(); /* Fallback to firmware dtb */
@ -351,10 +351,8 @@ void __init platform_init(void)
 	arch_reserve_vmcore();
 	arch_reserve_crashkernel();

-#ifdef CONFIG_ACPI_TABLE_UPGRADE
-	acpi_table_upgrade();
-#endif
 #ifdef CONFIG_ACPI
+	acpi_table_upgrade();
 	acpi_gbl_use_default_register_widths = false;
 	acpi_boot_table_init();
 #endif
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@ -273,7 +273,6 @@ static void __init fdt_smp_setup(void)

 		if (cpuid == loongson_sysconf.boot_cpu_id) {
 			cpu = 0;
-			numa_add_cpu(cpu);
 		} else {
 			cpu = cpumask_next_zero(-1, cpu_present_mask);
 		}
@ -283,6 +282,9 @@ static void __init fdt_smp_setup(void)
 		set_cpu_present(cpu, true);
 		__cpu_number_map[cpuid] = cpu;
 		__cpu_logical_map[cpu] = cpuid;
+
+		early_numa_add_cpu(cpu, 0);
+		set_cpuid_to_node(cpuid, 0);
 	}

 	loongson_sysconf.nr_cpus = num_processors;
@ -468,6 +470,7 @@ void smp_prepare_boot_cpu(void)
 	set_cpu_possible(0, true);
 	set_cpu_online(0, true);
 	set_my_cpu_offset(per_cpu_offset(0));
+	numa_add_cpu(0);

 	rr_node = first_node(node_online_map);
 	for_each_possible_cpu(cpu) {
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@ -6,6 +6,7 @@

 #define PAGE_SIZE _PAGE_SIZE
 #define RO_EXCEPTION_TABLE_ALIGN	4
+#define PHYSADDR_MASK			0xffffffffffff /* 48-bit */

 /*
 * Put .bss..swapper_pg_dir as the first thing in .bss. This will
@ -142,10 +143,11 @@ SECTIONS

 #ifdef CONFIG_EFI_STUB
 	/* header symbols */
-	_kernel_asize = _end - _text;
-	_kernel_fsize = _edata - _text;
-	_kernel_vsize = _end - __initdata_begin;
-	_kernel_rsize = _edata - __initdata_begin;
+	_kernel_entry = ABSOLUTE(kernel_entry & PHYSADDR_MASK);
+	_kernel_asize = ABSOLUTE(_end - _text);
+	_kernel_fsize = ABSOLUTE(_edata - _text);
+	_kernel_vsize = ABSOLUTE(_end - __initdata_begin);
+	_kernel_rsize = ABSOLUTE(_edata - __initdata_begin);
 #endif

 	.gptab.sdata : {
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@ -31,18 +31,17 @@ void flush_cache_all_local(void);
 void flush_cache_all(void);
 void flush_cache_mm(struct mm_struct *mm);

-void flush_kernel_dcache_page_addr(const void *addr);
-
 #define flush_kernel_dcache_range(start,size) \
 	flush_kernel_dcache_range_asm((start), (start)+(size));

+/* The only way to flush a vmap range is to flush whole cache */
 #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1
 void flush_kernel_vmap_range(void *vaddr, int size);
 void invalidate_kernel_vmap_range(void *vaddr, int size);

-#define flush_cache_vmap(start, end)		flush_cache_all()
+void flush_cache_vmap(unsigned long start, unsigned long end);
 #define flush_cache_vmap_early(start, end)	do { } while (0)
-#define flush_cache_vunmap(start, end)		flush_cache_all()
+void flush_cache_vunmap(unsigned long start, unsigned long end);

 void flush_dcache_folio(struct folio *folio);
 #define flush_dcache_folio flush_dcache_folio
@ -77,17 +76,11 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 void flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end);

-/* defined in pacache.S exported in cache.c used by flush_anon_page */
-void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
-
 #define ARCH_HAS_FLUSH_ANON_PAGE
 void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr);

 #define ARCH_HAS_FLUSH_ON_KUNMAP
-static inline void kunmap_flush_on_unmap(const void *addr)
-{
-	flush_kernel_dcache_page_addr(addr);
-}
+void kunmap_flush_on_unmap(const void *addr);

 #endif /* _PARISC_CACHEFLUSH_H */

--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@ -448,14 +448,17 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 	return pte;
 }

+static inline pte_t ptep_get(pte_t *ptep)
+{
+	return READ_ONCE(*ptep);
+}
+#define ptep_get ptep_get
+
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;

-	if (!pte_young(*ptep))
-		return 0;
-
-	pte = *ptep;
+	pte = ptep_get(ptep);
 	if (!pte_young(pte)) {
 		return 0;
 	}
@ -463,17 +466,10 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned
 	return 1;
 }

+int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep);
+pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep);
+
 struct mm_struct;
-static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	pte_t old_pte;
-
-	old_pte = *ptep;
-	set_pte(ptep, __pte(0));
-
-	return old_pte;
-}
-
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	set_pte(ptep, pte_wrprotect(*ptep));
@ -511,7 +507,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN

 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+#define __HAVE_ARCH_PTEP_CLEAR_FLUSH
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 #define __HAVE_ARCH_PTE_SAME

--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@ -20,6 +20,7 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/syscalls.h>
+#include <linux/vmalloc.h>
 #include <asm/pdc.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
@ -31,20 +32,31 @@
 #include <asm/mmu_context.h>
 #include <asm/cachectl.h>

+#define PTR_PAGE_ALIGN_DOWN(addr) PTR_ALIGN_DOWN(addr, PAGE_SIZE)
+
+/*
+ * When nonzero, use _PAGE_ACCESSED bit to try to reduce the number
+ * of page flushes done flush_cache_page_if_present. There are some
+ * pros and cons in using this option. It may increase the risk of
+ * random segmentation faults.
+ */
+#define CONFIG_FLUSH_PAGE_ACCESSED	0
+
 int split_tlb __ro_after_init;
 int dcache_stride __ro_after_init;
 int icache_stride __ro_after_init;
 EXPORT_SYMBOL(dcache_stride);

+/* Internal implementation in arch/parisc/kernel/pacache.S */
 void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
 EXPORT_SYMBOL(flush_dcache_page_asm);
 void purge_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
 void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr);
-
-/* Internal implementation in arch/parisc/kernel/pacache.S */
 void flush_data_cache_local(void *);  /* flushes local data-cache only */
 void flush_instruction_cache_local(void); /* flushes local code-cache only */

+static void flush_kernel_dcache_page_addr(const void *addr);
+
 /* On some machines (i.e., ones with the Merced bus), there can be
 * only a single PxTLB broadcast at a time; this must be guaranteed
 * by software. We need a spinlock around all TLB flushes to ensure
@ -321,6 +333,18 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 {
 	if (!static_branch_likely(&parisc_has_cache))
 		return;
+
+	/*
+	 * The TLB is the engine of coherence on parisc.  The CPU is
+	 * entitled to speculate any page with a TLB mapping, so here
+	 * we kill the mapping then flush the page along a special flush
+	 * only alias mapping. This guarantees that the page is no-longer
+	 * in the cache for any process and nor may it be speculatively
+	 * read in (until the user or kernel specifically accesses it,
+	 * of course).
+	 */
+	flush_tlb_page(vma, vmaddr);
+
 	preempt_disable();
 	flush_dcache_page_asm(physaddr, vmaddr);
 	if (vma->vm_flags & VM_EXEC)
@ -328,46 +352,44 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 	preempt_enable();
 }

-static void flush_user_cache_page(struct vm_area_struct *vma, unsigned long vmaddr)
+static void flush_kernel_dcache_page_addr(const void *addr)
 {
-	unsigned long flags, space, pgd, prot;
-#ifdef CONFIG_TLB_PTLOCK
-	unsigned long pgd_lock;
-#endif
+	unsigned long vaddr = (unsigned long)addr;
+	unsigned long flags;

-	vmaddr &= PAGE_MASK;
+	/* Purge TLB entry to remove translation on all CPUs */
+	purge_tlb_start(flags);
+	pdtlb(SR_KERNEL, addr);
+	purge_tlb_end(flags);

+	/* Use tmpalias flush to prevent data cache move-in */
 	preempt_disable();
-
-	/* Set context for flush */
-	local_irq_save(flags);
-	prot = mfctl(8);
-	space = mfsp(SR_USER);
-	pgd = mfctl(25);
-#ifdef CONFIG_TLB_PTLOCK
-	pgd_lock = mfctl(28);
-#endif
-	switch_mm_irqs_off(NULL, vma->vm_mm, NULL);
-	local_irq_restore(flags);
-
-	flush_user_dcache_range_asm(vmaddr, vmaddr + PAGE_SIZE);
-	if (vma->vm_flags & VM_EXEC)
-		flush_user_icache_range_asm(vmaddr, vmaddr + PAGE_SIZE);
-	flush_tlb_page(vma, vmaddr);
-
-	/* Restore previous context */
-	local_irq_save(flags);
-#ifdef CONFIG_TLB_PTLOCK
-	mtctl(pgd_lock, 28);
-#endif
-	mtctl(pgd, 25);
-	mtsp(space, SR_USER);
-	mtctl(prot, 8);
-	local_irq_restore(flags);
-
+	flush_dcache_page_asm(__pa(vaddr), vaddr);
 	preempt_enable();
 }

+static void flush_kernel_icache_page_addr(const void *addr)
+{
+	unsigned long vaddr = (unsigned long)addr;
+	unsigned long flags;
+
+	/* Purge TLB entry to remove translation on all CPUs */
+	purge_tlb_start(flags);
+	pdtlb(SR_KERNEL, addr);
+	purge_tlb_end(flags);
+
+	/* Use tmpalias flush to prevent instruction cache move-in */
+	preempt_disable();
+	flush_icache_page_asm(__pa(vaddr), vaddr);
+	preempt_enable();
+}
+
+void kunmap_flush_on_unmap(const void *addr)
+{
+	flush_kernel_dcache_page_addr(addr);
+}
+EXPORT_SYMBOL(kunmap_flush_on_unmap);
+
 void flush_icache_pages(struct vm_area_struct *vma, struct page *page,
 		unsigned int nr)
 {
@ -375,13 +397,16 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page,

 	for (;;) {
 		flush_kernel_dcache_page_addr(kaddr);
-		flush_kernel_icache_page(kaddr);
+		flush_kernel_icache_page_addr(kaddr);
 		if (--nr == 0)
 			break;
 		kaddr += PAGE_SIZE;
 	}
 }

+/*
+ * Walk page directory for MM to find PTEP pointer for address ADDR.
+ */
 static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr)
 {
 	pte_t *ptep = NULL;
@ -410,6 +435,41 @@ static inline bool pte_needs_flush(pte_t pte)
 		== (_PAGE_PRESENT | _PAGE_ACCESSED);
 }

+/*
+ * Return user physical address. Returns 0 if page is not present.
+ */
+static inline unsigned long get_upa(struct mm_struct *mm, unsigned long addr)
+{
+	unsigned long flags, space, pgd, prot, pa;
+#ifdef CONFIG_TLB_PTLOCK
+	unsigned long pgd_lock;
+#endif
+
+	/* Save context */
+	local_irq_save(flags);
+	prot = mfctl(8);
+	space = mfsp(SR_USER);
+	pgd = mfctl(25);
+#ifdef CONFIG_TLB_PTLOCK
+	pgd_lock = mfctl(28);
+#endif
+
+	/* Set context for lpa_user */
+	switch_mm_irqs_off(NULL, mm, NULL);
+	pa = lpa_user(addr);
+
+	/* Restore previous context */
+#ifdef CONFIG_TLB_PTLOCK
+	mtctl(pgd_lock, 28);
+#endif
+	mtctl(pgd, 25);
+	mtsp(space, SR_USER);
+	mtctl(prot, 8);
+	local_irq_restore(flags);
+
+	return pa;
+}
+
 void flush_dcache_folio(struct folio *folio)
 {
 	struct address_space *mapping = folio_flush_mapping(folio);
@ -458,50 +518,23 @@ void flush_dcache_folio(struct folio *folio)
 		if (addr + nr * PAGE_SIZE > vma->vm_end)
 			nr = (vma->vm_end - addr) / PAGE_SIZE;

-		if (parisc_requires_coherency()) {
-			for (i = 0; i < nr; i++) {
-				pte_t *ptep = get_ptep(vma->vm_mm,
-							addr + i * PAGE_SIZE);
-				if (!ptep)
-					continue;
-				if (pte_needs_flush(*ptep))
-					flush_user_cache_page(vma,
-							addr + i * PAGE_SIZE);
-				/* Optimise accesses to the same table? */
-				pte_unmap(ptep);
-			}
-		} else {
-			/*
-			 * The TLB is the engine of coherence on parisc:
-			 * The CPU is entitled to speculate any page
-			 * with a TLB mapping, so here we kill the
-			 * mapping then flush the page along a special
-			 * flush only alias mapping. This guarantees that
-			 * the page is no-longer in the cache for any
-			 * process and nor may it be speculatively read
-			 * in (until the user or kernel specifically
-			 * accesses it, of course)
-			 */
-			for (i = 0; i < nr; i++)
-				flush_tlb_page(vma, addr + i * PAGE_SIZE);
-			if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1))
+		if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1))
 					!= (addr & (SHM_COLOUR - 1))) {
-				for (i = 0; i < nr; i++)
-					__flush_cache_page(vma,
-						addr + i * PAGE_SIZE,
-						(pfn + i) * PAGE_SIZE);
-				/*
-				 * Software is allowed to have any number
-				 * of private mappings to a page.
-				 */
-				if (!(vma->vm_flags & VM_SHARED))
-					continue;
-				if (old_addr)
-					pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n",
-						old_addr, addr, vma->vm_file);
-				if (nr == folio_nr_pages(folio))
-					old_addr = addr;
-			}
+			for (i = 0; i < nr; i++)
+				__flush_cache_page(vma,
+					addr + i * PAGE_SIZE,
+					(pfn + i) * PAGE_SIZE);
+			/*
+			 * Software is allowed to have any number
+			 * of private mappings to a page.
+			 */
+			if (!(vma->vm_flags & VM_SHARED))
+				continue;
+			if (old_addr)
+				pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n",
+					old_addr, addr, vma->vm_file);
+			if (nr == folio_nr_pages(folio))
+				old_addr = addr;
 		}
 		WARN_ON(++count == 4096);
 	}
@ -591,35 +624,28 @@ extern void purge_kernel_dcache_page_asm(unsigned long);
 extern void clear_user_page_asm(void *, unsigned long);
 extern void copy_user_page_asm(void *, void *, unsigned long);

-void flush_kernel_dcache_page_addr(const void *addr)
-{
-	unsigned long flags;
-
-	flush_kernel_dcache_page_asm(addr);
-	purge_tlb_start(flags);
-	pdtlb(SR_KERNEL, addr);
-	purge_tlb_end(flags);
-}
-EXPORT_SYMBOL(flush_kernel_dcache_page_addr);
-
 static void flush_cache_page_if_present(struct vm_area_struct *vma,
-	unsigned long vmaddr, unsigned long pfn)
+	unsigned long vmaddr)
 {
+#if CONFIG_FLUSH_PAGE_ACCESSED
 	bool needs_flush = false;
-	pte_t *ptep;
+	pte_t *ptep, pte;

-	/*
-	 * The pte check is racy and sometimes the flush will trigger
-	 * a non-access TLB miss. Hopefully, the page has already been
-	 * flushed.
-	 */
 	ptep = get_ptep(vma->vm_mm, vmaddr);
 	if (ptep) {
-		needs_flush = pte_needs_flush(*ptep);
+		pte = ptep_get(ptep);
+		needs_flush = pte_needs_flush(pte);
 		pte_unmap(ptep);
 	}
 	if (needs_flush)
-		flush_cache_page(vma, vmaddr, pfn);
+		__flush_cache_page(vma, vmaddr, PFN_PHYS(pte_pfn(pte)));
+#else
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long physaddr = get_upa(mm, vmaddr);
+
+	if (physaddr)
+		__flush_cache_page(vma, vmaddr, PAGE_ALIGN_DOWN(physaddr));
+#endif
 }

 void copy_user_highpage(struct page *to, struct page *from,
@ -629,7 +655,7 @@ void copy_user_highpage(struct page *to, struct page *from,

 	kfrom = kmap_local_page(from);
 	kto = kmap_local_page(to);
-	flush_cache_page_if_present(vma, vaddr, page_to_pfn(from));
+	__flush_cache_page(vma, vaddr, PFN_PHYS(page_to_pfn(from)));
 	copy_page_asm(kto, kfrom);
 	kunmap_local(kto);
 	kunmap_local(kfrom);
@ -638,16 +664,17 @@ void copy_user_highpage(struct page *to, struct page *from,
 void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 		unsigned long user_vaddr, void *dst, void *src, int len)
 {
-	flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page));
+	__flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page)));
 	memcpy(dst, src, len);
-	flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len);
+	flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(dst));
 }

 void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
 		unsigned long user_vaddr, void *dst, void *src, int len)
 {
-	flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page));
+	__flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page)));
 	memcpy(dst, src, len);
+	flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(src));
 }

 /* __flush_tlb_range()
@ -681,32 +708,10 @@ int __flush_tlb_range(unsigned long sid, unsigned long start,

 static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
-	unsigned long addr, pfn;
-	pte_t *ptep;
+	unsigned long addr;

-	for (addr = start; addr < end; addr += PAGE_SIZE) {
-		bool needs_flush = false;
-		/*
-		 * The vma can contain pages that aren't present. Although
-		 * the pte search is expensive, we need the pte to find the
-		 * page pfn and to check whether the page should be flushed.
-		 */
-		ptep = get_ptep(vma->vm_mm, addr);
-		if (ptep) {
-			needs_flush = pte_needs_flush(*ptep);
-			pfn = pte_pfn(*ptep);
-			pte_unmap(ptep);
-		}
-		if (needs_flush) {
-			if (parisc_requires_coherency()) {
-				flush_user_cache_page(vma, addr);
-			} else {
-				if (WARN_ON(!pfn_valid(pfn)))
-					return;
-				__flush_cache_page(vma, addr, PFN_PHYS(pfn));
-			}
-		}
-	}
+	for (addr = start; addr < end; addr += PAGE_SIZE)
+		flush_cache_page_if_present(vma, addr);
 }

 static inline unsigned long mm_total_size(struct mm_struct *mm)
@ -757,21 +762,19 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned
 		if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled()))
 			return;
 		flush_tlb_range(vma, start, end);
-		flush_cache_all();
+		if (vma->vm_flags & VM_EXEC)
+			flush_cache_all();
+		else
+			flush_data_cache();
 		return;
 	}

-	flush_cache_pages(vma, start, end);
+	flush_cache_pages(vma, start & PAGE_MASK, end);
 }

 void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn)
 {
-	if (WARN_ON(!pfn_valid(pfn)))
-		return;
-	if (parisc_requires_coherency())
-		flush_user_cache_page(vma, vmaddr);
-	else
-		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
+	__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
 }

 void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
@ -779,34 +782,133 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned lon
 	if (!PageAnon(page))
 		return;

-	if (parisc_requires_coherency()) {
-		if (vma->vm_flags & VM_SHARED)
-			flush_data_cache();
-		else
-			flush_user_cache_page(vma, vmaddr);
+	__flush_cache_page(vma, vmaddr, PFN_PHYS(page_to_pfn(page)));
+}
+
+int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr,
+			   pte_t *ptep)
+{
+	pte_t pte = ptep_get(ptep);
+
+	if (!pte_young(pte))
+		return 0;
+	set_pte(ptep, pte_mkold(pte));
+#if CONFIG_FLUSH_PAGE_ACCESSED
+	__flush_cache_page(vma, addr, PFN_PHYS(pte_pfn(pte)));
+#endif
+	return 1;
+}
+
+/*
+ * After a PTE is cleared, we have no way to flush the cache for
+ * the physical page. On PA8800 and PA8900 processors, these lines
+ * can cause random cache corruption. Thus, we must flush the cache
+ * as well as the TLB when clearing a PTE that's valid.
+ */
+pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr,
+		       pte_t *ptep)
+{
+	struct mm_struct *mm = (vma)->vm_mm;
+	pte_t pte = ptep_get_and_clear(mm, addr, ptep);
+	unsigned long pfn = pte_pfn(pte);
+
+	if (pfn_valid(pfn))
+		__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+	else if (pte_accessible(mm, pte))
+		flush_tlb_page(vma, addr);
+
+	return pte;
+}
+
+/*
+ * The physical address for pages in the ioremap case can be obtained
+ * from the vm_struct struct. I wasn't able to successfully handle the
+ * vmalloc and vmap cases. We have an array of struct page pointers in
+ * the uninitialized vmalloc case but the flush failed using page_to_pfn.
+ */
+void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+	unsigned long addr, physaddr;
+	struct vm_struct *vm;
+
+	/* Prevent cache move-in */
+	flush_tlb_kernel_range(start, end);
+
+	if (end - start >= parisc_cache_flush_threshold) {
+		flush_cache_all();
 		return;
 	}

-	flush_tlb_page(vma, vmaddr);
-	preempt_disable();
-	flush_dcache_page_asm(page_to_phys(page), vmaddr);
-	preempt_enable();
-}
+	if (WARN_ON_ONCE(!is_vmalloc_addr((void *)start))) {
+		flush_cache_all();
+		return;
+	}

+	vm = find_vm_area((void *)start);
+	if (WARN_ON_ONCE(!vm)) {
+		flush_cache_all();
+		return;
+	}
+
+	/* The physical addresses of IOREMAP regions are contiguous */
+	if (vm->flags & VM_IOREMAP) {
+		physaddr = vm->phys_addr;
+		for (addr = start; addr < end; addr += PAGE_SIZE) {
+			preempt_disable();
+			flush_dcache_page_asm(physaddr, start);
+			flush_icache_page_asm(physaddr, start);
+			preempt_enable();
+			physaddr += PAGE_SIZE;
+		}
+		return;
+	}
+
+	flush_cache_all();
+}
+EXPORT_SYMBOL(flush_cache_vmap);
+
+/*
+ * The vm_struct has been retired and the page table is set up. The
+ * last page in the range is a guard page. Its physical address can't
+ * be determined using lpa, so there is no way to flush the range
+ * using flush_dcache_page_asm.
+ */
+void flush_cache_vunmap(unsigned long start, unsigned long end)
+{
+	/* Prevent cache move-in */
+	flush_tlb_kernel_range(start, end);
+	flush_data_cache();
+}
+EXPORT_SYMBOL(flush_cache_vunmap);
+
+/*
+ * On systems with PA8800/PA8900 processors, there is no way to flush
+ * a vmap range other than using the architected loop to flush the
+ * entire cache. The page directory is not set up, so we can't use
+ * fdc, etc. FDCE/FICE don't work to flush a portion of the cache.
+ * L2 is physically indexed but FDCE/FICE instructions in virtual
+ * mode output their virtual address on the core bus, not their
+ * real address. As a result, the L2 cache index formed from the
+ * virtual address will most likely not be the same as the L2 index
+ * formed from the real address.
+ */
 void flush_kernel_vmap_range(void *vaddr, int size)
 {
 	unsigned long start = (unsigned long)vaddr;
 	unsigned long end = start + size;

-	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
-	    (unsigned long)size >= parisc_cache_flush_threshold) {
-		flush_tlb_kernel_range(start, end);
-		flush_data_cache();
+	flush_tlb_kernel_range(start, end);
+
+	if (!static_branch_likely(&parisc_has_dcache))
+		return;
+
+	/* If interrupts are disabled, we can only do local flush */
+	if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) {
+		flush_data_cache_local(NULL);
 		return;
 	}

-	flush_kernel_dcache_range_asm(start, end);
-	flush_tlb_kernel_range(start, end);
+	flush_data_cache();
 }
 EXPORT_SYMBOL(flush_kernel_vmap_range);

@ -818,15 +920,18 @@ void invalidate_kernel_vmap_range(void *vaddr, int size)
 	/* Ensure DMA is complete */
 	asm_syncdma();

-	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
-	    (unsigned long)size >= parisc_cache_flush_threshold) {
-		flush_tlb_kernel_range(start, end);
-		flush_data_cache();
+	flush_tlb_kernel_range(start, end);
+
+	if (!static_branch_likely(&parisc_has_dcache))
+		return;
+
+	/* If interrupts are disabled, we can only do local flush */
+	if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) {
+		flush_data_cache_local(NULL);
 		return;
 	}

-	purge_kernel_dcache_range_asm(start, end);
-	flush_tlb_kernel_range(start, end);
+	flush_data_cache();
 }
 EXPORT_SYMBOL(invalidate_kernel_vmap_range);

--- a/arch/riscv/kvm/aia_device.c
+++ b/arch/riscv/kvm/aia_device.c
@ -237,10 +237,11 @@ static gpa_t aia_imsic_ppn(struct kvm_aia *aia, gpa_t addr)

 static u32 aia_imsic_hart_index(struct kvm_aia *aia, gpa_t addr)
 {
-	u32 hart, group = 0;
+	u32 hart = 0, group = 0;

-	hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) &
-		GENMASK_ULL(aia->nr_hart_bits - 1, 0);
+	if (aia->nr_hart_bits)
+		hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) &
+		       GENMASK_ULL(aia->nr_hart_bits - 1, 0);
 	if (aia->nr_group_bits)
 		group = (addr >> aia->nr_group_shift) &
 			GENMASK_ULL(aia->nr_group_bits - 1, 0);
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@ -724,9 +724,9 @@ static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
 	switch (reg_subtype) {
 	case KVM_REG_RISCV_ISA_SINGLE:
 		return riscv_vcpu_set_isa_ext_single(vcpu, reg_num, reg_val);
-	case KVM_REG_RISCV_SBI_MULTI_EN:
+	case KVM_REG_RISCV_ISA_MULTI_EN:
 		return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, true);
-	case KVM_REG_RISCV_SBI_MULTI_DIS:
+	case KVM_REG_RISCV_ISA_MULTI_DIS:
 		return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, false);
 	default:
 		return -ENOENT;
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@ -293,8 +293,8 @@ void handle_page_fault(struct pt_regs *regs)
 	if (unlikely(access_error(cause, vma))) {
 		vma_end_read(vma);
 		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
-		tsk->thread.bad_cause = SEGV_ACCERR;
-		bad_area_nosemaphore(regs, code, addr);
+		tsk->thread.bad_cause = cause;
+		bad_area_nosemaphore(regs, SEGV_ACCERR, addr);
 		return;
 	}

--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@ -250,18 +250,19 @@ static void __init setup_bootmem(void)
 		kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base;

 	/*
-	 * memblock allocator is not aware of the fact that last 4K bytes of
-	 * the addressable memory can not be mapped because of IS_ERR_VALUE
-	 * macro. Make sure that last 4k bytes are not usable by memblock
-	 * if end of dram is equal to maximum addressable memory.  For 64-bit
-	 * kernel, this problem can't happen here as the end of the virtual
-	 * address space is occupied by the kernel mapping then this check must
-	 * be done as soon as the kernel mapping base address is determined.
+	 * Reserve physical address space that would be mapped to virtual
+	 * addresses greater than (void *)(-PAGE_SIZE) because:
+	 *  - This memory would overlap with ERR_PTR
+	 *  - This memory belongs to high memory, which is not supported
+	 *
+	 * This is not applicable to 64-bit kernel, because virtual addresses
+	 * after (void *)(-PAGE_SIZE) are not linearly mapped: they are
+	 * occupied by kernel mapping. Also it is unrealistic for high memory
+	 * to exist on 64-bit platforms.
 	 */
 	if (!IS_ENABLED(CONFIG_64BIT)) {
-		max_mapped_addr = __pa(~(ulong)0);
-		if (max_mapped_addr == (phys_ram_end - 1))
-			memblock_set_current_limit(max_mapped_addr - 4096);
+		max_mapped_addr = __va_to_pa_nodebug(-PAGE_SIZE);
+		memblock_reserve(max_mapped_addr, (phys_addr_t)-max_mapped_addr);
 	}

 	min_low_pfn = PFN_UP(phys_ram_base);
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@ -384,7 +384,7 @@ static void fixup_vmlinux_info(void)
 void startup_kernel(void)
 {
 	unsigned long kernel_size = vmlinux.image_size + vmlinux.bss_size;
-	unsigned long nokaslr_offset_phys = mem_safe_offset();
+	unsigned long nokaslr_offset_phys, kaslr_large_page_offset;
 	unsigned long amode31_lma = 0;
 	unsigned long max_physmem_end;
 	unsigned long asce_limit;
@ -393,6 +393,12 @@ void startup_kernel(void)

 	fixup_vmlinux_info();
 	setup_lpp();
+
+	/*
+	 * Non-randomized kernel physical start address must be _SEGMENT_SIZE
+	 * aligned (see blow).
+	 */
+	nokaslr_offset_phys = ALIGN(mem_safe_offset(), _SEGMENT_SIZE);
 	safe_addr = PAGE_ALIGN(nokaslr_offset_phys + kernel_size);

 	/*
@ -425,10 +431,25 @@ void startup_kernel(void)
 	save_ipl_cert_comp_list();
 	rescue_initrd(safe_addr, ident_map_size);

-	if (kaslr_enabled())
-		__kaslr_offset_phys = randomize_within_range(kernel_size, THREAD_SIZE, 0, ident_map_size);
+	/*
+	 * __kaslr_offset_phys must be _SEGMENT_SIZE aligned, so the lower
+	 * 20 bits (the offset within a large page) are zero. Copy the last
+	 * 20 bits of __kaslr_offset, which is THREAD_SIZE aligned, to
+	 * __kaslr_offset_phys.
+	 *
+	 * With this the last 20 bits of __kaslr_offset_phys and __kaslr_offset
+	 * are identical, which is required to allow for large mappings of the
+	 * kernel image.
+	 */
+	kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK;
+	if (kaslr_enabled()) {
+		unsigned long end = ident_map_size - kaslr_large_page_offset;
+
+		__kaslr_offset_phys = randomize_within_range(kernel_size, _SEGMENT_SIZE, 0, end);
+	}
 	if (!__kaslr_offset_phys)
 		__kaslr_offset_phys = nokaslr_offset_phys;
+	__kaslr_offset_phys |= kaslr_large_page_offset;
 	kaslr_adjust_vmlinux_info(__kaslr_offset_phys);
 	physmem_reserve(RR_VMLINUX, __kaslr_offset_phys, kernel_size);
 	deploy_kernel((void *)__kaslr_offset_phys);
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@ -261,21 +261,27 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m

 static bool large_allowed(enum populate_mode mode)
 {
-	return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY);
+	return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY) || (mode == POPULATE_KERNEL);
 }

 static bool can_large_pud(pud_t *pu_dir, unsigned long addr, unsigned long end,
 			  enum populate_mode mode)
 {
+	unsigned long size = end - addr;
+
 	return machine.has_edat2 && large_allowed(mode) &&
-	       IS_ALIGNED(addr, PUD_SIZE) && (end - addr) >= PUD_SIZE;
+	       IS_ALIGNED(addr, PUD_SIZE) && (size >= PUD_SIZE) &&
+	       IS_ALIGNED(_pa(addr, size, mode), PUD_SIZE);
 }

 static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end,
 			  enum populate_mode mode)
 {
+	unsigned long size = end - addr;
+
 	return machine.has_edat1 && large_allowed(mode) &&
-	       IS_ALIGNED(addr, PMD_SIZE) && (end - addr) >= PMD_SIZE;
+	       IS_ALIGNED(addr, PMD_SIZE) && (size >= PMD_SIZE) &&
+	       IS_ALIGNED(_pa(addr, size, mode), PMD_SIZE);
 }

 static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end,
--- a/arch/s390/boot/vmlinux.lds.S
+++ b/arch/s390/boot/vmlinux.lds.S
@ -109,6 +109,7 @@ SECTIONS
 #ifdef CONFIG_KERNEL_UNCOMPRESSED
 	. = ALIGN(PAGE_SIZE);
 	. += AMODE31_SIZE;		/* .amode31 section */
+	. = ALIGN(1 << 20);		/* _SEGMENT_SIZE */
 #else
 	. = ALIGN(8);
 #endif
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@ -43,7 +43,6 @@ CONFIG_PROFILING=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
-CONFIG_CRASH_DUMP=y
 CONFIG_LIVEPATCH=y
 CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=512
@ -51,6 +50,7 @@ CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_CERT_STORE=y
 CONFIG_EXPOLINE=y
+# CONFIG_EXPOLINE_EXTERN is not set
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_CHSC_SCH=y
 CONFIG_VFIO_CCW=m
@ -76,6 +76,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_MODULE_SIG_SHA256=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
@ -100,7 +101,6 @@ CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
-CONFIG_CMA_DEBUG=y
 CONFIG_CMA_DEBUGFS=y
 CONFIG_CMA_SYSFS=y
 CONFIG_CMA_AREAS=7
@ -119,6 +119,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_XFRM_USER=m
 CONFIG_NET_KEY=m
 CONFIG_SMC_DIAG=m
+CONFIG_SMC_LO=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_ADVANCED_ROUTER=y
@ -133,7 +134,6 @@ CONFIG_IP_MROUTE=y
 CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
 CONFIG_IP_PIMSM_V1=y
 CONFIG_IP_PIMSM_V2=y
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@ -167,6 +167,7 @@ CONFIG_BRIDGE_NETFILTER=m
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_ZONES=y
 CONFIG_NF_CONNTRACK_PROCFS=y
 CONFIG_NF_CONNTRACK_EVENTS=y
 CONFIG_NF_CONNTRACK_TIMEOUT=y
@ -183,17 +184,39 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
+CONFIG_NF_CT_NETLINK_HELPER=m
+CONFIG_NETFILTER_NETLINK_GLUE_CT=y
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
+CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
+CONFIG_NFT_FLOW_OFFLOAD=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
+CONFIG_NFT_MASQ=m
+CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_TUNNEL=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
-CONFIG_NETFILTER_XTABLES_COMPAT=y
+CONFIG_NFT_XFRM=m
+CONFIG_NFT_SOCKET=m
+CONFIG_NFT_OSF=m
+CONFIG_NFT_TPROXY=m
+CONFIG_NFT_SYNPROXY=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
+CONFIG_NFT_FIB_NETDEV=m
+CONFIG_NFT_REJECT_NETDEV=m
+CONFIG_NF_FLOW_TABLE_INET=m
+CONFIG_NF_FLOW_TABLE=m
+CONFIG_NF_FLOW_TABLE_PROCFS=y
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_AUDIT=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@ -206,8 +229,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m
 CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
 CONFIG_NETFILTER_XT_TARGET_LOG=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
+CONFIG_NETFILTER_XT_TARGET_NETMAP=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
+CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
@ -216,6 +241,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
 CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
 CONFIG_NETFILTER_XT_MATCH_BPF=m
+CONFIG_NETFILTER_XT_MATCH_CGROUP=m
 CONFIG_NETFILTER_XT_MATCH_CLUSTER=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
 CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
@ -230,6 +256,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_IPVS=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
@ -247,6 +274,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@ -302,7 +330,6 @@ CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
 CONFIG_IP_NF_SECURITY=m
-CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_FIB_IPV6=m
@ -373,7 +400,6 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
@ -462,6 +488,7 @@ CONFIG_DM_VERITY=m
 CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
 CONFIG_DM_SWITCH=m
 CONFIG_DM_INTEGRITY=m
+CONFIG_DM_VDO=m
 CONFIG_NETDEVICES=y
 CONFIG_BONDING=m
 CONFIG_DUMMY=m
@ -574,7 +601,6 @@ CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
 CONFIG_DIAG288_WATCHDOG=m
-# CONFIG_DRM_DEBUG_MODESET_LOCK is not set
 CONFIG_FB=y
 # CONFIG_FB_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
@ -645,7 +671,6 @@ CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_EXFAT_FS=m
 CONFIG_NTFS_FS=m
-CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
@ -663,6 +688,7 @@ CONFIG_SQUASHFS_XZ=y
 CONFIG_SQUASHFS_ZSTD=y
 CONFIG_ROMFS_FS=m
 CONFIG_NFS_FS=m
+CONFIG_NFS_V2=m
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@ -879,6 +905,5 @@ CONFIG_RBTREE_TEST=y
 CONFIG_INTERVAL_TREE_TEST=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
-CONFIG_STRING_SELFTEST=y
 CONFIG_TEST_BITOPS=m
 CONFIG_TEST_BPF=m
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@ -41,7 +41,6 @@ CONFIG_PROFILING=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
-CONFIG_CRASH_DUMP=y
 CONFIG_LIVEPATCH=y
 CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=512
@ -49,6 +48,7 @@ CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_CERT_STORE=y
 CONFIG_EXPOLINE=y
+# CONFIG_EXPOLINE_EXTERN is not set
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_CHSC_SCH=y
 CONFIG_VFIO_CCW=m
@ -71,6 +71,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_MODULE_SIG_SHA256=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
@ -110,6 +111,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_XFRM_USER=m
 CONFIG_NET_KEY=m
 CONFIG_SMC_DIAG=m
+CONFIG_SMC_LO=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_ADVANCED_ROUTER=y
@ -124,7 +126,6 @@ CONFIG_IP_MROUTE=y
 CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
 CONFIG_IP_PIMSM_V1=y
 CONFIG_IP_PIMSM_V2=y
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@ -158,6 +159,7 @@ CONFIG_BRIDGE_NETFILTER=m
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_ZONES=y
 CONFIG_NF_CONNTRACK_PROCFS=y
 CONFIG_NF_CONNTRACK_EVENTS=y
 CONFIG_NF_CONNTRACK_TIMEOUT=y
@ -174,17 +176,39 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
+CONFIG_NF_CT_NETLINK_HELPER=m
+CONFIG_NETFILTER_NETLINK_GLUE_CT=y
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
+CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
+CONFIG_NFT_FLOW_OFFLOAD=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
+CONFIG_NFT_MASQ=m
+CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_TUNNEL=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
-CONFIG_NETFILTER_XTABLES_COMPAT=y
+CONFIG_NFT_XFRM=m
+CONFIG_NFT_SOCKET=m
+CONFIG_NFT_OSF=m
+CONFIG_NFT_TPROXY=m
+CONFIG_NFT_SYNPROXY=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
+CONFIG_NFT_FIB_NETDEV=m
+CONFIG_NFT_REJECT_NETDEV=m
+CONFIG_NF_FLOW_TABLE_INET=m
+CONFIG_NF_FLOW_TABLE=m
+CONFIG_NF_FLOW_TABLE_PROCFS=y
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_AUDIT=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@ -197,8 +221,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m
 CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
 CONFIG_NETFILTER_XT_TARGET_LOG=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
+CONFIG_NETFILTER_XT_TARGET_NETMAP=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
+CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
@ -207,6 +233,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
 CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
 CONFIG_NETFILTER_XT_MATCH_BPF=m
+CONFIG_NETFILTER_XT_MATCH_CGROUP=m
 CONFIG_NETFILTER_XT_MATCH_CLUSTER=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
 CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
@ -221,6 +248,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_IPVS=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
@ -238,6 +266,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@ -293,7 +322,6 @@ CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
 CONFIG_IP_NF_SECURITY=m
-CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_FIB_IPV6=m
@ -363,7 +391,6 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
@ -452,6 +479,7 @@ CONFIG_DM_VERITY=m
 CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
 CONFIG_DM_SWITCH=m
 CONFIG_DM_INTEGRITY=m
+CONFIG_DM_VDO=m
 CONFIG_NETDEVICES=y
 CONFIG_BONDING=m
 CONFIG_DUMMY=m
@ -630,7 +658,6 @@ CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_EXFAT_FS=m
 CONFIG_NTFS_FS=m
-CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
@ -649,6 +676,7 @@ CONFIG_SQUASHFS_XZ=y
 CONFIG_SQUASHFS_ZSTD=y
 CONFIG_ROMFS_FS=m
 CONFIG_NFS_FS=m
+CONFIG_NFS_V2=m
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@ -9,25 +9,22 @@ CONFIG_BPF_SYSCALL=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_KEXEC=y
-CONFIG_CRASH_DUMP=y
 CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=2
 CONFIG_HZ_100=y
 # CONFIG_CHSC_SCH is not set
 # CONFIG_SCM_BUS is not set
+# CONFIG_AP is not set
 # CONFIG_PFAULT is not set
 # CONFIG_S390_HYPFS is not set
 # CONFIG_VIRTUALIZATION is not set
 # CONFIG_S390_GUEST is not set
 # CONFIG_SECCOMP is not set
-# CONFIG_GCC_PLUGINS is not set
 # CONFIG_BLOCK_LEGACY_AUTOLOAD is not set
 CONFIG_PARTITION_ADVANCED=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_SWAP is not set
 # CONFIG_COMPAT_BRK is not set
-# CONFIG_COMPACTION is not set
-# CONFIG_MIGRATION is not set
 CONFIG_NET=y
 # CONFIG_IUCV is not set
 # CONFIG_PCPU_DEV_REFCNT is not set
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@ -451,7 +451,7 @@ static void *nt_final(void *ptr)
 /*
 * Initialize ELF header (new kernel)
 */
-static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt)
+static void *ehdr_init(Elf64_Ehdr *ehdr, int phdr_count)
 {
 	memset(ehdr, 0, sizeof(*ehdr));
 	memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
@ -465,11 +465,8 @@ static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt)
 	ehdr->e_phoff = sizeof(Elf64_Ehdr);
 	ehdr->e_ehsize = sizeof(Elf64_Ehdr);
 	ehdr->e_phentsize = sizeof(Elf64_Phdr);
-	/*
-	 * Number of memory chunk PT_LOAD program headers plus one kernel
-	 * image PT_LOAD program header plus one PT_NOTE program header.
-	 */
-	ehdr->e_phnum = mem_chunk_cnt + 1 + 1;
+	/* Number of PT_LOAD program headers plus PT_NOTE program header */
+	ehdr->e_phnum = phdr_count + 1;
 	return ehdr + 1;
 }

@ -503,12 +500,14 @@ static int get_mem_chunk_cnt(void)
 /*
 * Initialize ELF loads (new kernel)
 */
-static void loads_init(Elf64_Phdr *phdr)
+static void loads_init(Elf64_Phdr *phdr, bool os_info_has_vm)
 {
-	unsigned long old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE);
+	unsigned long old_identity_base = 0;
 	phys_addr_t start, end;
 	u64 idx;

+	if (os_info_has_vm)
+		old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE);
 	for_each_physmem_range(idx, &oldmem_type, &start, &end) {
 		phdr->p_type = PT_LOAD;
 		phdr->p_vaddr = old_identity_base + start;
@ -522,6 +521,11 @@ static void loads_init(Elf64_Phdr *phdr)
 	}
 }

+static bool os_info_has_vm(void)
+{
+	return os_info_old_value(OS_INFO_KASLR_OFFSET);
+}
+
 /*
 * Prepare PT_LOAD type program header for kernel image region
 */
@ -566,7 +570,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 	return ptr;
 }

-static size_t get_elfcorehdr_size(int mem_chunk_cnt)
+static size_t get_elfcorehdr_size(int phdr_count)
 {
 	size_t size;

@ -581,10 +585,8 @@ static size_t get_elfcorehdr_size(int mem_chunk_cnt)
 	size += nt_vmcoreinfo_size();
 	/* nt_final */
 	size += sizeof(Elf64_Nhdr);
-	/* PT_LOAD type program header for kernel text region */
-	size += sizeof(Elf64_Phdr);
 	/* PT_LOADS */
-	size += mem_chunk_cnt * sizeof(Elf64_Phdr);
+	size += phdr_count * sizeof(Elf64_Phdr);

 	return size;
 }
@ -595,8 +597,8 @@ static size_t get_elfcorehdr_size(int mem_chunk_cnt)
 int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 {
 	Elf64_Phdr *phdr_notes, *phdr_loads, *phdr_text;
+	int mem_chunk_cnt, phdr_text_cnt;
 	size_t alloc_size;
-	int mem_chunk_cnt;
 	void *ptr, *hdr;
 	u64 hdr_off;

@ -615,12 +617,14 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 	}

 	mem_chunk_cnt = get_mem_chunk_cnt();
+	phdr_text_cnt = os_info_has_vm() ? 1 : 0;

-	alloc_size = get_elfcorehdr_size(mem_chunk_cnt);
+	alloc_size = get_elfcorehdr_size(mem_chunk_cnt + phdr_text_cnt);

 	hdr = kzalloc(alloc_size, GFP_KERNEL);

-	/* Without elfcorehdr /proc/vmcore cannot be created. Thus creating
+	/*
+	 * Without elfcorehdr /proc/vmcore cannot be created. Thus creating
 	 * a dump with this crash kernel will fail. Panic now to allow other
 	 * dump mechanisms to take over.
 	 */
@ -628,21 +632,23 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 		panic("s390 kdump allocating elfcorehdr failed");

 	/* Init elf header */
-	ptr = ehdr_init(hdr, mem_chunk_cnt);
+	phdr_notes = ehdr_init(hdr, mem_chunk_cnt + phdr_text_cnt);
 	/* Init program headers */
-	phdr_notes = ptr;
-	ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr));
-	phdr_text = ptr;
-	ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr));
-	phdr_loads = ptr;
-	ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr) * mem_chunk_cnt);
+	if (phdr_text_cnt) {
+		phdr_text = phdr_notes + 1;
+		phdr_loads = phdr_text + 1;
+	} else {
+		phdr_loads = phdr_notes + 1;
+	}
+	ptr = PTR_ADD(phdr_loads, sizeof(Elf64_Phdr) * mem_chunk_cnt);
 	/* Init notes */
 	hdr_off = PTR_DIFF(ptr, hdr);
 	ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off);
 	/* Init kernel text program header */
-	text_init(phdr_text);
+	if (phdr_text_cnt)
+		text_init(phdr_text);
 	/* Init loads */
-	loads_init(phdr_loads);
+	loads_init(phdr_loads, phdr_text_cnt);
 	/* Finalize program headers */
 	hdr_off = PTR_DIFF(ptr, hdr);
 	*addr = (unsigned long long) hdr;
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@ -105,9 +105,9 @@ vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o

 vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o
 vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o
-vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
+vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a

-$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
+$(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE
 	$(call if_changed,ld)

 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@ -2154,6 +2154,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);

 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len);
+void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			     u64 addr, unsigned long roots);
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@ -78,10 +78,10 @@ extern int __get_user_bad(void);
 	int __ret_gu;							\
 	register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX);		\
 	__chk_user_ptr(ptr);						\
-	asm volatile("call __" #fn "_%c4"				\
+	asm volatile("call __" #fn "_%c[size]"				\
 		     : "=a" (__ret_gu), "=r" (__val_gu),		\
 			ASM_CALL_CONSTRAINT				\
-		     : "0" (ptr), "i" (sizeof(*(ptr))));		\
+		     : "0" (ptr), [size] "i" (sizeof(*(ptr))));		\
 	instrument_get_user(__val_gu);					\
 	(x) = (__force __typeof__(*(ptr))) __val_gu;			\
 	__builtin_expect(__ret_gu, 0);					\
--- a/arch/x86/include/asm/vmxfeatures.h
+++ b/arch/x86/include/asm/vmxfeatures.h
@ -77,7 +77,7 @@
 #define VMX_FEATURE_ENCLS_EXITING	( 2*32+ 15) /* "" VM-Exit on ENCLS (leaf dependent) */
 #define VMX_FEATURE_RDSEED_EXITING	( 2*32+ 16) /* "" VM-Exit on RDSEED */
 #define VMX_FEATURE_PAGE_MOD_LOGGING	( 2*32+ 17) /* "pml" Log dirty pages into buffer */
-#define VMX_FEATURE_EPT_VIOLATION_VE	( 2*32+ 18) /* "" Conditionally reflect EPT violations as #VE exceptions */
+#define VMX_FEATURE_EPT_VIOLATION_VE	( 2*32+ 18) /* Conditionally reflect EPT violations as #VE exceptions */
 #define VMX_FEATURE_PT_CONCEAL_VMX	( 2*32+ 19) /* "" Suppress VMX indicators in Processor Trace */
 #define VMX_FEATURE_XSAVES		( 2*32+ 20) /* "" Enable XSAVES and XRSTORS in guest */
 #define VMX_FEATURE_MODE_BASED_EPT_EXEC	( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@ -215,7 +215,14 @@ static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write)

 int amd_smn_read(u16 node, u32 address, u32 *value)
 {
-	return __amd_smn_rw(node, address, value, false);
+	int err = __amd_smn_rw(node, address, value, false);
+
+	if (PCI_POSSIBLE_ERROR(*value)) {
+		err = -ENODEV;
+		*value = 0;
+	}
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(amd_smn_read);

--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@ -295,8 +295,15 @@ void machine_kexec_cleanup(struct kimage *image)
 void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list[PAGES_NR];
-	void *control_page;
+	unsigned int host_mem_enc_active;
 	int save_ftrace_enabled;
+	void *control_page;
+
+	/*
+	 * This must be done before load_segments() since if call depth tracking
+	 * is used then GS must be valid to make any function calls.
+	 */
+	host_mem_enc_active = cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT);

 #ifdef CONFIG_KEXEC_JUMP
 	if (image->preserve_context)
@ -358,7 +365,7 @@ void machine_kexec(struct kimage *image)
 				       (unsigned long)page_list,
 				       image->start,
 				       image->preserve_context,
-				       cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT));
+				       host_mem_enc_active);

 #ifdef CONFIG_KEXEC_JUMP
 	if (image->preserve_context)
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@ -44,6 +44,7 @@ config KVM
 	select KVM_VFIO
 	select HAVE_KVM_PM_NOTIFIER if PM
 	select KVM_GENERIC_HARDWARE_ENABLING
+	select KVM_WERROR if WERROR
 	help
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
@ -66,7 +67,7 @@ config KVM_WERROR
 	# FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning.
 	# Building KVM with -Werror and KASAN is still doable via enabling
 	# the kernel-wide WERROR=y.
-	depends on KVM && EXPERT && !KASAN
+	depends on KVM && ((EXPERT && !KASAN) || WERROR)
 	help
 	  Add -Werror to the build flags for KVM.

@ -97,15 +98,17 @@ config KVM_INTEL

 config KVM_INTEL_PROVE_VE
        bool "Check that guests do not receive #VE exceptions"
-        default KVM_PROVE_MMU || DEBUG_KERNEL
-        depends on KVM_INTEL
+        depends on KVM_INTEL && EXPERT
        help
-
          Checks that KVM's page table management code will not incorrectly
          let guests receive a virtualization exception.  Virtualization
          exceptions will be trapped by the hypervisor rather than injected
          in the guest.

+          Note: some CPUs appear to generate spurious EPT Violations #VEs
+          that trigger KVM's WARN, in particular with eptad=0 and/or nested
+          virtualization.
+
          If unsure, say N.

 config X86_SGX_KVM
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@ -59,7 +59,17 @@
 #define MAX_APIC_VECTOR			256
 #define APIC_VECTORS_PER_REG		32

-static bool lapic_timer_advance_dynamic __read_mostly;
+/*
+ * Enable local APIC timer advancement (tscdeadline mode only) with adaptive
+ * tuning.  When enabled, KVM programs the host timer event to fire early, i.e.
+ * before the deadline expires, to account for the delay between taking the
+ * VM-Exit (to inject the guest event) and the subsequent VM-Enter to resume
+ * the guest, i.e. so that the interrupt arrives in the guest with minimal
+ * latency relative to the deadline programmed by the guest.
+ */
+static bool lapic_timer_advance __read_mostly = true;
+module_param(lapic_timer_advance, bool, 0444);
+
 #define LAPIC_TIMER_ADVANCE_ADJUST_MIN	100	/* clock cycles */
 #define LAPIC_TIMER_ADVANCE_ADJUST_MAX	10000	/* clock cycles */
 #define LAPIC_TIMER_ADVANCE_NS_INIT	1000
@ -1854,16 +1864,14 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
 	trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);

-	if (lapic_timer_advance_dynamic) {
-		adjust_lapic_timer_advance(vcpu, guest_tsc - tsc_deadline);
-		/*
-		 * If the timer fired early, reread the TSC to account for the
-		 * overhead of the above adjustment to avoid waiting longer
-		 * than is necessary.
-		 */
-		if (guest_tsc < tsc_deadline)
-			guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
-	}
+	adjust_lapic_timer_advance(vcpu, guest_tsc - tsc_deadline);
+
+	/*
+	 * If the timer fired early, reread the TSC to account for the overhead
+	 * of the above adjustment to avoid waiting longer than is necessary.
+	 */
+	if (guest_tsc < tsc_deadline)
+		guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());

 	if (guest_tsc < tsc_deadline)
 		__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
@ -2812,7 +2820,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
 		return HRTIMER_NORESTART;
 }

-int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
+int kvm_create_lapic(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic;

@ -2845,13 +2853,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_ABS_HARD);
 	apic->lapic_timer.timer.function = apic_timer_fn;
-	if (timer_advance_ns == -1) {
+	if (lapic_timer_advance)
 		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
-		lapic_timer_advance_dynamic = true;
-	} else {
-		apic->lapic_timer.timer_advance_ns = timer_advance_ns;
-		lapic_timer_advance_dynamic = false;
-	}

 	/*
 	 * Stuff the APIC ENABLE bit in lieu of temporarily incrementing
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@ -85,7 +85,7 @@ struct kvm_lapic {

 struct dest_map;

-int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns);
+int kvm_create_lapic(struct kvm_vcpu *vcpu);
 void kvm_free_lapic(struct kvm_vcpu *vcpu);

 int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@ -336,16 +336,19 @@ static int is_cpuid_PSE36(void)
 #ifdef CONFIG_X86_64
 static void __set_spte(u64 *sptep, u64 spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
 	WRITE_ONCE(*sptep, spte);
 }

 static void __update_clear_spte_fast(u64 *sptep, u64 spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
 	WRITE_ONCE(*sptep, spte);
 }

 static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
 	return xchg(sptep, spte);
 }

@ -4101,6 +4104,22 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level
 	return leaf;
 }

+static int get_sptes_lockless(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			      int *root_level)
+{
+	int leaf;
+
+	walk_shadow_page_lockless_begin(vcpu);
+
+	if (is_tdp_mmu_active(vcpu))
+		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, root_level);
+	else
+		leaf = get_walk(vcpu, addr, sptes, root_level);
+
+	walk_shadow_page_lockless_end(vcpu);
+	return leaf;
+}
+
 /* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
 static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
@ -4109,15 +4128,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 	int root, leaf, level;
 	bool reserved = false;

-	walk_shadow_page_lockless_begin(vcpu);
-
-	if (is_tdp_mmu_active(vcpu))
-		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
-	else
-		leaf = get_walk(vcpu, addr, sptes, &root);
-
-	walk_shadow_page_lockless_end(vcpu);
-
+	leaf = get_sptes_lockless(vcpu, addr, sptes, &root);
 	if (unlikely(leaf < 0)) {
 		*sptep = 0ull;
 		return reserved;
@ -4400,9 +4411,6 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 			return RET_PF_EMULATE;
 	}

-	fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
-	smp_rmb();
-
 	/*
 	 * Check for a relevant mmu_notifier invalidation event before getting
 	 * the pfn from the primary MMU, and before acquiring mmu_lock.
@ -5921,6 +5929,22 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);

+void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg)
+{
+	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
+	int root_level, leaf, level;
+
+	leaf = get_sptes_lockless(vcpu, gpa, sptes, &root_level);
+	if (unlikely(leaf < 0))
+		return;
+
+	pr_err("%s %llx", msg, gpa);
+	for (level = root_level; level >= leaf; level--)
+		pr_cont(", spte[%d] = 0x%llx", level, sptes[level]);
+	pr_cont("\n");
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_print_sptes);
+
 static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 				      u64 addr, hpa_t root_hpa)
 {
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@ -3,6 +3,8 @@
 #ifndef KVM_X86_MMU_SPTE_H
 #define KVM_X86_MMU_SPTE_H

+#include <asm/vmx.h>
+
 #include "mmu.h"
 #include "mmu_internal.h"

@ -276,6 +278,13 @@ static inline bool is_shadow_present_pte(u64 pte)
 	return !!(pte & SPTE_MMU_PRESENT_MASK);
 }

+static inline bool is_ept_ve_possible(u64 spte)
+{
+	return (shadow_present_mask & VMX_EPT_SUPPRESS_VE_BIT) &&
+	       !(spte & VMX_EPT_SUPPRESS_VE_BIT) &&
+	       (spte & VMX_EPT_RWX_MASK) != VMX_EPT_MISCONFIG_WX_VALUE;
+}
+
 /*
 * Returns true if A/D bits are supported in hardware and are enabled by KVM.
 * When enabled, KVM uses A/D bits for all non-nested MMUs.  Because L1 can
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@ -21,11 +21,13 @@ static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep)

 static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
 	return xchg(rcu_dereference(sptep), new_spte);
 }

 static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
 	WRITE_ONCE(*rcu_dereference(sptep), new_spte);
 }

--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@ -626,7 +626,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
 	 * SPTEs.
 	 */
 	handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
-			    0, iter->level, true);
+			    SHADOW_NONPRESENT_VALUE, iter->level, true);

 	return 0;
 }
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@ -779,6 +779,14 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
 	 */
 	fpstate_set_confidential(&vcpu->arch.guest_fpu);
 	vcpu->arch.guest_state_protected = true;
+
+	/*
+	 * SEV-ES guest mandates LBR Virtualization to be _always_ ON. Enable it
+	 * only after setting guest_state_protected because KVM_SET_MSRS allows
+	 * dynamic toggling of LBRV (for performance reason) on write access to
+	 * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set.
+	 */
+	svm_enable_lbrv(vcpu);
 	return 0;
 }

@ -2406,6 +2414,12 @@ void __init sev_hardware_setup(void)
 	if (!boot_cpu_has(X86_FEATURE_SEV_ES))
 		goto out;

+	if (!lbrv) {
+		WARN_ONCE(!boot_cpu_has(X86_FEATURE_LBRV),
+			  "LBRV must be present for SEV-ES support");
+		goto out;
+	}
+
 	/* Has the system been allocated ASIDs for SEV-ES? */
 	if (min_sev_asid == 1)
 		goto out;
@ -3216,7 +3230,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	struct kvm_vcpu *vcpu = &svm->vcpu;

 	svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE;
-	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;

 	/*
 	 * An SEV-ES guest requires a VMSA area that is a separate from the
@ -3268,10 +3281,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	/* Clear intercepts on selected MSRs */
 	set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
-	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
 }

 void sev_init_vmcb(struct vcpu_svm *svm)
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@ -99,6 +99,7 @@ static const struct svm_direct_access_msrs {
 	{ .index = MSR_IA32_SPEC_CTRL,			.always = false },
 	{ .index = MSR_IA32_PRED_CMD,			.always = false },
 	{ .index = MSR_IA32_FLUSH_CMD,			.always = false },
+	{ .index = MSR_IA32_DEBUGCTLMSR,		.always = false },
 	{ .index = MSR_IA32_LASTBRANCHFROMIP,		.always = false },
 	{ .index = MSR_IA32_LASTBRANCHTOIP,		.always = false },
 	{ .index = MSR_IA32_LASTINTFROMIP,		.always = false },
@ -215,7 +216,7 @@ int vgif = true;
 module_param(vgif, int, 0444);

 /* enable/disable LBR virtualization */
-static int lbrv = true;
+int lbrv = true;
 module_param(lbrv, int, 0444);

 static int tsc_scaling = true;
@ -990,7 +991,7 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
 	vmcb_mark_dirty(to_vmcb, VMCB_LBR);
 }

-static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
+void svm_enable_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);

@ -1000,6 +1001,9 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);

+	if (sev_es_guest(vcpu->kvm))
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1);
+
 	/* Move the LBR msrs to the vmcb02 so that the guest can see them. */
 	if (is_guest_mode(vcpu))
 		svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr);
@ -1009,6 +1013,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);

+	KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm);
+
 	svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
@ -2822,10 +2828,24 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr)
 	return 0;
 }

+static bool
+sev_es_prevent_msr_access(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	return sev_es_guest(vcpu->kvm) &&
+	       vcpu->arch.guest_state_protected &&
+	       svm_msrpm_offset(msr_info->index) != MSR_INVALID &&
+	       !msr_write_intercepted(vcpu, msr_info->index);
+}
+
 static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);

+	if (sev_es_prevent_msr_access(vcpu, msr_info)) {
+		msr_info->data = 0;
+		return -EINVAL;
+	}
+
 	switch (msr_info->index) {
 	case MSR_AMD64_TSC_RATIO:
 		if (!msr_info->host_initiated &&
@ -2976,6 +2996,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)

 	u32 ecx = msr->index;
 	u64 data = msr->data;
+
+	if (sev_es_prevent_msr_access(vcpu, msr))
+		return -EINVAL;
+
 	switch (ecx) {
 	case MSR_AMD64_TSC_RATIO:

@ -3846,16 +3870,27 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);

 	/*
-	 * KVM should never request an NMI window when vNMI is enabled, as KVM
-	 * allows at most one to-be-injected NMI and one pending NMI, i.e. if
-	 * two NMIs arrive simultaneously, KVM will inject one and set
-	 * V_NMI_PENDING for the other.  WARN, but continue with the standard
-	 * single-step approach to try and salvage the pending NMI.
+	 * If NMIs are outright masked, i.e. the vCPU is already handling an
+	 * NMI, and KVM has not yet intercepted an IRET, then there is nothing
+	 * more to do at this time as KVM has already enabled IRET intercepts.
+	 * If KVM has already intercepted IRET, then single-step over the IRET,
+	 * as NMIs aren't architecturally unmasked until the IRET completes.
+	 *
+	 * If vNMI is enabled, KVM should never request an NMI window if NMIs
+	 * are masked, as KVM allows at most one to-be-injected NMI and one
+	 * pending NMI.  If two NMIs arrive simultaneously, KVM will inject one
+	 * NMI and set V_NMI_PENDING for the other, but if and only if NMIs are
+	 * unmasked.  KVM _will_ request an NMI window in some situations, e.g.
+	 * if the vCPU is in an STI shadow or if GIF=0, KVM can't immediately
+	 * inject the NMI.  In those situations, KVM needs to single-step over
+	 * the STI shadow or intercept STGI.
 	 */
-	WARN_ON_ONCE(is_vnmi_enabled(svm));
+	if (svm_get_nmi_mask(vcpu)) {
+		WARN_ON_ONCE(is_vnmi_enabled(svm));

-	if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion)
-		return; /* IRET will cause a vm exit */
+		if (!svm->awaiting_iret_completion)
+			return; /* IRET will cause a vm exit */
+	}

 	/*
 	 * SEV-ES guests are responsible for signaling when a vCPU is ready to
@ -5265,6 +5300,12 @@ static __init int svm_hardware_setup(void)

 	nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS);

+	if (lbrv) {
+		if (!boot_cpu_has(X86_FEATURE_LBRV))
+			lbrv = false;
+		else
+			pr_info("LBR virtualization supported\n");
+	}
 	/*
 	 * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which
 	 * may be modified by svm_adjust_mmio_mask()), as well as nrips.
@ -5318,14 +5359,6 @@ static __init int svm_hardware_setup(void)
 		svm_x86_ops.set_vnmi_pending = NULL;
 	}

-
-	if (lbrv) {
-		if (!boot_cpu_has(X86_FEATURE_LBRV))
-			lbrv = false;
-		else
-			pr_info("LBR virtualization supported\n");
-	}
-
 	if (!enable_pmu)
 		pr_info("PMU virtualization is disabled\n");

--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@ -30,7 +30,7 @@
 #define	IOPM_SIZE PAGE_SIZE * 3
 #define	MSRPM_SIZE PAGE_SIZE * 2

-#define MAX_DIRECT_ACCESS_MSRS	47
+#define MAX_DIRECT_ACCESS_MSRS	48
 #define MSRPM_OFFSETS	32
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
@ -39,6 +39,7 @@ extern int vgif;
 extern bool intercept_smi;
 extern bool x2avic_enabled;
 extern bool vnmi;
+extern int lbrv;

 /*
 * Clean bits in VMCB.
@ -552,6 +553,7 @@ u32 *svm_vcpu_alloc_msrpm(void);
 void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm);
 void svm_vcpu_free_msrpm(u32 *msrpm);
 void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
+void svm_enable_lbrv(struct kvm_vcpu *vcpu);
 void svm_update_lbrv(struct kvm_vcpu *vcpu);

 int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer);
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@ -2242,6 +2242,9 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
 		vmcs_write64(EPT_POINTER,
 			     construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL));

+	if (vmx->ve_info)
+		vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info));
+
 	/* All VMFUNCs are currently emulated through L0 vmexits.  */
 	if (cpu_has_vmx_vmfunc())
 		vmcs_write64(VM_FUNCTION_CONTROL, 0);
@ -6230,6 +6233,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 		else if (is_alignment_check(intr_info) &&
 			 !vmx_guest_inject_ac(vcpu))
 			return true;
+		else if (is_ve_fault(intr_info))
+			return true;
 		return false;
 	case EXIT_REASON_EXTERNAL_INTERRUPT:
 		return true;
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@ -5218,8 +5218,15 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	if (is_invalid_opcode(intr_info))
 		return handle_ud(vcpu);

-	if (KVM_BUG_ON(is_ve_fault(intr_info), vcpu->kvm))
-		return -EIO;
+	if (WARN_ON_ONCE(is_ve_fault(intr_info))) {
+		struct vmx_ve_information *ve_info = vmx->ve_info;
+
+		WARN_ONCE(ve_info->exit_reason != EXIT_REASON_EPT_VIOLATION,
+			  "Unexpected #VE on VM-Exit reason 0x%x", ve_info->exit_reason);
+		dump_vmcs(vcpu);
+		kvm_mmu_print_sptes(vcpu, ve_info->guest_physical_address, "#VE");
+		return 1;
+	}

 	error_code = 0;
 	if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@ -164,15 +164,6 @@ module_param(kvmclock_periodic_sync, bool, 0444);
 static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, 0644);

-/*
- * lapic timer advance (tscdeadline mode only) in nanoseconds.  '-1' enables
- * adaptive tuning starting from default advancement of 1000ns.  '0' disables
- * advancement entirely.  Any other value is used as-is and disables adaptive
- * tuning, i.e. allows privileged userspace to set an exact advancement time.
- */
-static int __read_mostly lapic_timer_advance_ns = -1;
-module_param(lapic_timer_advance_ns, int, 0644);
-
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, 0444);

@ -12169,7 +12160,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (r < 0)
 		return r;

-	r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
+	r = kvm_create_lapic(vcpu);
 	if (r < 0)
 		goto fail_mmu_destroy;

--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@ -44,7 +44,11 @@
 	or %rdx, %rax
 .else
 	cmp $TASK_SIZE_MAX-\size+1, %eax
+.if \size != 8
 	jae .Lbad_get_user
+.else
+	jae .Lbad_get_user_8
+.endif
 	sbb %edx, %edx		/* array_index_mask_nospec() */
 	and %edx, %eax
 .endif
@ -154,7 +158,7 @@ SYM_CODE_END(__get_user_handle_exception)
 #ifdef CONFIG_X86_32
 SYM_CODE_START_LOCAL(__get_user_8_handle_exception)
 	ASM_CLAC
-bad_get_user_8:
+.Lbad_get_user_8:
 	xor %edx,%edx
 	xor %ecx,%ecx
 	mov $(-EFAULT),%_ASM_AX
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@ -493,7 +493,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
 	for_each_reserved_mem_region(mb_region) {
 		int nid = memblock_get_region_node(mb_region);

-		if (nid != MAX_NUMNODES)
+		if (nid != NUMA_NO_NODE)
 			node_set(nid, reserved_nodemask);
 	}

@ -614,9 +614,9 @@ static int __init numa_init(int (*init_func)(void))
 	nodes_clear(node_online_map);
 	memset(&numa_meminfo, 0, sizeof(numa_meminfo));
 	WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory,
-				  MAX_NUMNODES));
+				  NUMA_NO_NODE));
 	WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved,
-				  MAX_NUMNODES));
+				  NUMA_NO_NODE));
 	/* In case that parsing SRAT failed. */
 	WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX));
 	numa_reset_distance();
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@ -144,16 +144,38 @@ void bio_integrity_free(struct bio *bio)
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_set *bs = bio->bi_pool;

+	if (bip->bip_flags & BIP_INTEGRITY_USER)
+		return;
 	if (bip->bip_flags & BIP_BLOCK_INTEGRITY)
 		kfree(bvec_virt(bip->bip_vec));
-	else if (bip->bip_flags & BIP_INTEGRITY_USER)
-		bio_integrity_unmap_user(bip);

 	__bio_integrity_free(bs, bip);
 	bio->bi_integrity = NULL;
 	bio->bi_opf &= ~REQ_INTEGRITY;
 }

+/**
+ * bio_integrity_unmap_free_user - Unmap and free bio user integrity payload
+ * @bio:	bio containing bip to be unmapped and freed
+ *
+ * Description: Used to unmap and free the user mapped integrity portion of a
+ * bio. Submitter attaching the user integrity buffer is responsible for
+ * unmapping and freeing it during completion.
+ */
+void bio_integrity_unmap_free_user(struct bio *bio)
+{
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	struct bio_set *bs = bio->bi_pool;
+
+	if (WARN_ON_ONCE(!(bip->bip_flags & BIP_INTEGRITY_USER)))
+		return;
+	bio_integrity_unmap_user(bip);
+	__bio_integrity_free(bs, bip);
+	bio->bi_integrity = NULL;
+	bio->bi_opf &= ~REQ_INTEGRITY;
+}
+EXPORT_SYMBOL(bio_integrity_unmap_free_user);
+
 /**
 * bio_integrity_add_page - Attach integrity metadata
 * @bio:	bio to update
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@ -185,7 +185,7 @@ static void blk_flush_complete_seq(struct request *rq,
 		/* queue for flush */
 		if (list_empty(pending))
 			fq->flush_pending_since = jiffies;
-		list_move_tail(&rq->queuelist, pending);
+		list_add_tail(&rq->queuelist, pending);
 		break;

 	case REQ_FSEQ_DATA:
@ -263,6 +263,7 @@ static enum rq_end_io_ret flush_end_io(struct request *flush_rq,
 		unsigned int seq = blk_flush_cur_seq(rq);

 		BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH);
+		list_del_init(&rq->queuelist);
 		blk_flush_complete_seq(rq, fq, seq, error);
 	}

--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@ -1552,6 +1552,9 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk)

 void disk_free_zone_resources(struct gendisk *disk)
 {
+	if (!disk->zone_wplugs_pool)
+		return;
+
 	cancel_work_sync(&disk->zone_wplugs_work);

 	if (disk->zone_wplugs_wq) {
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@ -314,7 +314,7 @@ static int read_sed_opal_key(const char *key_name, u_char *buffer, int buflen)
 			      &key_type_user, key_name, true);

 	if (IS_ERR(kref))
-		ret = PTR_ERR(kref);
+		return PTR_ERR(kref);

 	key = key_ref_to_ptr(kref);
 	down_read(&key->sem);
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@ -145,7 +145,7 @@ static void acpi_ac_notify(acpi_handle handle, u32 event, void *data)
 						  dev_name(&adev->dev), event,
 						  (u32) ac->state);
 		acpi_notifier_call_chain(adev, event, (u32) ac->state);
-		kobject_uevent(&ac->charger->dev.kobj, KOBJ_CHANGE);
+		power_supply_changed(ac->charger);
 	}
 }

@ -268,7 +268,7 @@ static int acpi_ac_resume(struct device *dev)
 	if (acpi_ac_get_state(ac))
 		return 0;
 	if (old_state != ac->state)
-		kobject_uevent(&ac->charger->dev.kobj, KOBJ_CHANGE);
+		power_supply_changed(ac->charger);

 	return 0;
 }
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@ -191,6 +191,10 @@ void
 acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
 			    acpi_adr_space_type space_id, u32 function);

+void
+acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *node,
+				  acpi_adr_space_type space_id);
+
 acpi_status
 acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function);

--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@ -20,10 +20,6 @@ extern u8 acpi_gbl_default_address_spaces[];

 /* Local prototypes */

-static void
-acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node,
-				  acpi_adr_space_type space_id);
-
 static acpi_status
 acpi_ev_reg_run(acpi_handle obj_handle,
 		u32 level, void *context, void **return_value);
@ -818,7 +814,7 @@ acpi_ev_reg_run(acpi_handle obj_handle,
 *
 ******************************************************************************/

-static void
+void
 acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node,
 				  acpi_adr_space_type space_id)
 {
--- a/drivers/acpi/acpica/evxfregn.c
+++ b/drivers/acpi/acpica/evxfregn.c
@ -306,3 +306,57 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)
 }

 ACPI_EXPORT_SYMBOL(acpi_execute_reg_methods)
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_execute_orphan_reg_method
+ *
+ * PARAMETERS:  device          - Handle for the device
+ *              space_id        - The address space ID
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Execute an "orphan" _REG method that appears under an ACPI
+ *              device. This is a _REG method that has no corresponding region
+ *              within the device's scope.
+ *
+ ******************************************************************************/
+acpi_status
+acpi_execute_orphan_reg_method(acpi_handle device, acpi_adr_space_type space_id)
+{
+	struct acpi_namespace_node *node;
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_execute_orphan_reg_method);
+
+	/* Parameter validation */
+
+	if (!device) {
+		return_ACPI_STATUS(AE_BAD_PARAMETER);
+	}
+
+	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
+
+	/* Convert and validate the device handle */
+
+	node = acpi_ns_validate_handle(device);
+	if (node) {
+
+		/*
+		 * If an "orphan" _REG method is present in the device's scope
+		 * for the given address space ID, run it.
+		 */
+
+		acpi_ev_execute_orphan_reg_method(node, space_id);
+	} else {
+		status = AE_BAD_PARAMETER;
+	}
+
+	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_execute_orphan_reg_method)
--- a/drivers/acpi/apei/einj-core.c
+++ b/drivers/acpi/apei/einj-core.c
@ -909,7 +909,7 @@ static void __exit einj_exit(void)
 	if (einj_initialized)
 		platform_driver_unregister(&einj_driver);

-	platform_device_del(einj_dev);
+	platform_device_unregister(einj_dev);
 }

 module_init(einj_init);
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@ -1333,10 +1333,13 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 	if (ec->busy_polling || bits > 8)
 		acpi_ec_burst_enable(ec);

-	for (i = 0; i < bytes; ++i, ++address, ++value)
+	for (i = 0; i < bytes; ++i, ++address, ++value) {
 		result = (function == ACPI_READ) ?
 			acpi_ec_read(ec, address, value) :
 			acpi_ec_write(ec, address, *value);
+		if (result < 0)
+			break;
+	}

 	if (ec->busy_polling || bits > 8)
 		acpi_ec_burst_disable(ec);
@ -1348,8 +1351,10 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 		return AE_NOT_FOUND;
 	case -ETIME:
 		return AE_TIME;
-	default:
+	case 0:
 		return AE_OK;
+	default:
+		return AE_ERROR;
 	}
 }

@ -1502,6 +1507,9 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device,

 	if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) {
 		acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC);
+		if (scope_handle != ec->handle)
+			acpi_execute_orphan_reg_method(ec->handle, ACPI_ADR_SPACE_EC);
+
 		set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags);
 	}

--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@ -610,7 +610,7 @@ static void acpi_sbs_callback(void *context)
 	if (sbs->charger_exists) {
 		acpi_ac_get_present(sbs);
 		if (sbs->charger_present != saved_charger_state)
-			kobject_uevent(&sbs->charger->dev.kobj, KOBJ_CHANGE);
+			power_supply_changed(sbs->charger);
 	}

 	if (sbs->manager_present) {
@ -622,7 +622,7 @@ static void acpi_sbs_callback(void *context)
 			acpi_battery_read(bat);
 			if (saved_battery_state == bat->present)
 				continue;
-			kobject_uevent(&bat->bat->dev.kobj, KOBJ_CHANGE);
+			power_supply_changed(bat->bat);
 		}
 	}
 }
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@ -168,11 +168,17 @@ static int acpi_thermal_get_polling_frequency(struct acpi_thermal *tz)

 static int acpi_thermal_temp(struct acpi_thermal *tz, int temp_deci_k)
 {
+	int temp;
+
 	if (temp_deci_k == THERMAL_TEMP_INVALID)
 		return THERMAL_TEMP_INVALID;

-	return deci_kelvin_to_millicelsius_with_offset(temp_deci_k,
+	temp = deci_kelvin_to_millicelsius_with_offset(temp_deci_k,
 						       tz->kelvin_offset);
+	if (temp <= 0)
+		return THERMAL_TEMP_INVALID;
+
+	return temp;
 }

 static bool acpi_thermal_trip_valid(struct acpi_thermal_trip *acpi_trip)
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@ -206,16 +206,16 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s
 }

 /*
- * AMD systems from Renoir and Lucienne *require* that the NVME controller
+ * AMD systems from Renoir onwards *require* that the NVME controller
 * is put into D3 over a Modern Standby / suspend-to-idle cycle.
 *
 * This is "typically" accomplished using the `StorageD3Enable`
 * property in the _DSD that is checked via the `acpi_storage_d3` function
- * but this property was introduced after many of these systems launched
- * and most OEM systems don't have it in their BIOS.
+ * but some OEM systems still don't have it in their BIOS.
 *
 * The Microsoft documentation for StorageD3Enable mentioned that Windows has
- * a hardcoded allowlist for D3 support, which was used for these platforms.
+ * a hardcoded allowlist for D3 support as well as a registry key to override
+ * the BIOS, which has been used for these cases.
 *
 * This allows quirking on Linux in a similar fashion.
 *
@ -228,19 +228,15 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s
 *    https://bugzilla.kernel.org/show_bug.cgi?id=216773
 *    https://bugzilla.kernel.org/show_bug.cgi?id=217003
 * 2) On at least one HP system StorageD3Enable is missing on the second NVME
-      disk in the system.
+ *    disk in the system.
+ * 3) On at least one HP Rembrandt system StorageD3Enable is missing on the only
+ *    NVME device.
 */
-static const struct x86_cpu_id storage_d3_cpu_ids[] = {
-	X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 24, NULL),  /* Picasso */
-	X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL),	/* Renoir */
-	X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL),	/* Lucienne */
-	X86_MATCH_VENDOR_FAM_MODEL(AMD, 25, 80, NULL),	/* Cezanne */
-	{}
-};
-
 bool force_storage_d3(void)
 {
-	return x86_match_cpu(storage_d3_cpu_ids);
+	if (!cpu_feature_enabled(X86_FEATURE_ZEN))
+		return false;
+	return acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0;
 }

 /*
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@ -1831,11 +1831,11 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf)
 		2
 	};

-	/* set scsi removable (RMB) bit per ata bit, or if the
-	 * AHCI port says it's external (Hotplug-capable, eSATA).
+	/*
+	 * Set the SCSI Removable Media Bit (RMB) if the ATA removable media
+	 * device bit (obsolete since ATA-8 ACS) is set.
 	 */
-	if (ata_id_removable(args->id) ||
-	    (args->dev->link->ap->pflags & ATA_PFLAG_EXTERNAL))
+	if (ata_id_removable(args->id))
 		hdr[1] |= (1 << 7);

 	if (args->dev->class == ATA_DEV_ZAC) {
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@ -915,10 +915,13 @@ static const struct scsi_host_template pata_macio_sht = {
 	.sg_tablesize		= MAX_DCMDS,
 	/* We may not need that strict one */
 	.dma_boundary		= ATA_DMA_BOUNDARY,
-	/* Not sure what the real max is but we know it's less than 64K, let's
-	 * use 64K minus 256
+	/*
+	 * The SCSI core requires the segment size to cover at least a page, so
+	 * for 64K page size kernels this must be at least 64K. However the
+	 * hardware can't handle 64K, so pata_macio_qc_prep() will split large
+	 * requests.
 	 */
-	.max_segment_size	= MAX_DBDMA_SEG,
+	.max_segment_size	= SZ_64K,
 	.device_configure	= pata_macio_device_configure,
 	.sdev_groups		= ata_common_sdev_groups,
 	.can_queue		= ATA_DEF_QUEUE,
--- a/Show More
+++ b/Show More