H extension definitions, shared by the KVM and RISC-V trees.

-----BEGIN PGP SIGNATURE-----
 
 iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmFawaIUHHBib256aW5p
 QHJlZGhhdC5jb20ACgkQv/vSX3jHroO7xwf9HF/zvySIRhwWsxI6RZKA5k+g0ebe
 18XzPeBMPeW1C5YLukL67cvoxgW8oHc/ZMhdUKVSEkgMkhF7c6uNgtvodtv7ZFk8
 /3wfBAERp37VKltliU2JvVs/8GXboK+uKnq0mIt52CO9+JVH/55URtz7Spxnl8Fc
 Lx7ioeKoaPw2mnyuU6sSNwt7HuUtqn8meQ1EcYLCGND7Vyu/BevRGvqRGuXqipVb
 pDlpz5Cu5T0ZCmBj/ko5PmPCU3COQw2jtiugUvKsAjPM92ViNK8B9O7cbrcEh8fi
 XCOsV1KjzF0kJCvacZMQqkjijL3UriNBRW5JAvd4boV97PGcI9KHZdEFYw==
 =65Mk
 -----END PGP SIGNATURE-----
gpgsig -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEKzw3R0RoQ7JKlDp6LhMZ81+7GIkFAmFb1ygTHHBhbG1lckBk
 YWJiZWx0LmNvbQAKCRAuExnzX7sYicKuD/9pkpLuebSwmgzDRQ4tcGKQUc+h1rCP
 U++2qb74Zi7XX5JnXwVraAC9F0ps1hOCfQzgncKd6sT/VTrbKqmPl0QF0NMniCjN
 xOk5X4AsZH/qGkgizG8o73Ok9+qclbpyTeYJ5iKBKwwhDOAsutGDsSgp5nrYJYgI
 30xX62eH0XvfyN1Un/qSqE/3TErkwOAlIcFlAr1Nkel0jnOfMzgdUjQEW/h4hxci
 8NWFLVdP1WVdlWSmbCclu1totU884VdPquE0tb6lh6dBQXsAB///AjNHZxsO7jZ0
 UGBG9d4hY40zyvu9FB+kvYyafrZXyhCc+AmphtYBY/cd3TyBXEO98mYPQB/h5Tmh
 wsi1bVIqSAYfw04jJvvtLQYWJybB1el9Mp2jeKg2tEp+j96vvax2FGuHV39lcWXj
 b79M/gd7fAyY+oQhYoFDsLUoY/FYiECvpBQQrgB8AMl+JiNMOp0pWZIGf98paLh+
 3CjX6WCjmxBNrNbM0bj+mmm3dj2Aq8OG98BVsolqqhUah55t7Wu6Hjax7wHgqORk
 FfnuemXLKE4H2AZvMcjaAqBd7/Q1SYRfO+LzcfoE8Nhwek3RaHg3wz5n8c8xT8BW
 9gK8yC/UrdVZNf41nBqKEjYKaholorBP8/qZoNZGxPP87dlLxkFup91D5MtEn+c+
 FNSX5c6BY+8vbQ==
 =ywXC
 -----END PGP SIGNATURE-----

Merge tag 'for-riscv' of https://git.kernel.org/pub/scm/virt/kvm/kvm.git into for-next

H extension definitions, shared by the KVM and RISC-V trees.

* tag 'for-riscv' of ssh://gitolite.kernel.org/pub/scm/virt/kvm/kvm: (301 commits)
  RISC-V: Add hypervisor extension related CSR defines
  KVM: selftests: Ensure all migrations are performed when test is affined
  KVM: x86: Swap order of CPUID entry "index" vs. "significant flag" checks
  ptp: Fix ptp_kvm_getcrosststamp issue for x86 ptp_kvm
  x86/kvmclock: Move this_cpu_pvti into kvmclock.h
  KVM: s390: Function documentation fixes
  selftests: KVM: Don't clobber XMM register when read
  KVM: VMX: Fix a TSX_CTRL_CPUID_CLEAR field mask issue
  selftests: KVM: Explicitly use movq to read xmm registers
  selftests: KVM: Call ucall_init when setting up in rseq_test
  KVM: Remove tlbs_dirty
  KVM: X86: Synchronize the shadow pagetable before link it
  KVM: X86: Fix missed remote tlb flush in rmap_write_protect()
  KVM: x86: nSVM: don't copy virt_ext from vmcb12
  KVM: x86: nSVM: test eax for 4K alignment for GP errata workaround
  KVM: x86: selftests: test simultaneous uses of V_IRQ from L1 and L0
  KVM: x86: nSVM: restore int_vector in svm_clear_vintr
  kvm: x86: Add AMD PMU MSRs to msrs_to_save_all[]
  KVM: x86: nVMX: re-evaluate emulation_required on nested VM exit
  KVM: x86: nVMX: don't fail nested VM entry on invalid guest state if !from_vmentry
  ...

Documentation/admin-guide/README.rst

@@ -259,7 +259,7 @@ Configuring the kernel
 Compiling the kernel
 --------------------
 
- - Make sure you have at least gcc 4.9 available.
+ - Make sure you have at least gcc 5.1 available.
    For more information, refer to :ref:`Documentation/process/changes.rst <changes>`.
 
    Please note that you can still run a.out user programs with this kernel.

Documentation/devicetree/bindings/arm/tegra.yaml

@@ -54,7 +54,7 @@ properties:
           - const: toradex,apalis_t30
           - const: nvidia,tegra30
       - items:
-          - const: toradex,apalis_t30-eval-v1.1
+          - const: toradex,apalis_t30-v1.1-eval
           - const: toradex,apalis_t30-eval
           - const: toradex,apalis_t30-v1.1
           - const: toradex,apalis_t30

Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt

@@ -9,7 +9,7 @@ function block.
 
 All DISP device tree nodes must be siblings to the central MMSYS_CONFIG node.
 For a description of the MMSYS_CONFIG binding, see
-Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.txt.
+Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.yaml.
 
 DISP function blocks
 ====================

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

@@ -19,7 +19,9 @@ properties:
       - const: allwinner,sun8i-v3s-emac
       - const: allwinner,sun50i-a64-emac
       - items:
-          - const: allwinner,sun50i-h6-emac
+          - enum:
+              - allwinner,sun20i-d1-emac
+              - allwinner,sun50i-h6-emac
           - const: allwinner,sun50i-a64-emac
 
   reg:

Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml

@@ -0,0 +1,89 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ufs/samsung,exynos-ufs.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Samsung SoC series UFS host controller Device Tree Bindings
+
+maintainers:
+  - Alim Akhtar <alim.akhtar@samsung.com>
+
+description: |
+  Each Samsung UFS host controller instance should have its own node.
+  This binding define Samsung specific binding other then what is used
+  in the common ufshcd bindings
+  [1] Documentation/devicetree/bindings/ufs/ufshcd-pltfrm.txt
+
+properties:
+
+  compatible:
+    enum:
+      - samsung,exynos7-ufs
+
+  reg:
+    items:
+      - description: HCI register
+      - description: vendor specific register
+      - description: unipro register
+      - description: UFS protector register
+
+  reg-names:
+    items:
+      - const: hci
+      - const: vs_hci
+      - const: unipro
+      - const: ufsp
+
+  clocks:
+    items:
+      - description: ufs link core clock
+      - description: unipro main clock
+
+  clock-names:
+    items:
+      - const: core_clk
+      - const: sclk_unipro_main
+
+  interrupts:
+    maxItems: 1
+
+  phys:
+    maxItems: 1
+
+  phy-names:
+    const: ufs-phy
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - phys
+  - phy-names
+  - clocks
+  - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/exynos7-clk.h>
+
+    ufs: ufs@15570000 {
+       compatible = "samsung,exynos7-ufs";
+       reg = <0x15570000 0x100>,
+             <0x15570100 0x100>,
+             <0x15571000 0x200>,
+             <0x15572000 0x300>;
+       reg-names = "hci", "vs_hci", "unipro", "ufsp";
+       interrupts = <GIC_SPI 200 IRQ_TYPE_LEVEL_HIGH>;
+       clocks = <&clock_fsys1 ACLK_UFS20_LINK>,
+                <&clock_fsys1 SCLK_UFSUNIPRO20_USER>;
+       clock-names = "core_clk", "sclk_unipro_main";
+       pinctrl-names = "default";
+       pinctrl-0 = <&ufs_rst_n &ufs_refclk_out>;
+       phys = <&ufs_phy>;
+       phy-names = "ufs-phy";
+    };
+...

Documentation/networking/dsa/sja1105.rst

@@ -296,7 +296,7 @@ not available.
 Device Tree bindings and board design
 =====================================
 
-This section references ``Documentation/devicetree/bindings/net/dsa/sja1105.txt``
+This section references ``Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml``
 and aims to showcase some potential switch caveats.
 
 RMII PHY role and out-of-band signaling

Documentation/process/changes.rst

@@ -29,7 +29,7 @@ you probably needn't concern yourself with pcmciautils.
 ====================== ===============  ========================================
         Program        Minimal version       Command to check the version
 ====================== ===============  ========================================
-GNU C                  4.9              gcc --version
+GNU C                  5.1              gcc --version
 Clang/LLVM (optional)  10.0.1           clang --version
 GNU make               3.81             make --version
 binutils               2.23             ld -v

Documentation/translations/zh_CN/admin-guide/README.rst

@@ -223,7 +223,7 @@ Linux内核5.x版本 <http://kernel.org/>
 编译内核
 ---------
 
- - 确保您至少有gcc 4.9可用。
+ - 确保您至少有gcc 5.1可用。
    有关更多信息，请参阅 :ref:`Documentation/process/changes.rst <changes>` 。
 
    请注意，您仍然可以使用此内核运行a.out用户程序。

Documentation/translations/zh_TW/admin-guide/README.rst

@@ -226,7 +226,7 @@ Linux內核5.x版本 <http://kernel.org/>
 編譯內核
 ---------
 
- - 確保您至少有gcc 4.9可用。
+ - 確保您至少有gcc 5.1可用。
    有關更多信息，請參閱 :ref:`Documentation/process/changes.rst <changes>` 。
 
    請注意，您仍然可以使用此內核運行a.out用戶程序。

MAINTAINERS

@@ -14342,7 +14342,8 @@ F:	Documentation/devicetree/bindings/pci/intel,ixp4xx-pci.yaml
 F:	drivers/pci/controller/pci-ixp4xx.c
 
 PCI DRIVER FOR INTEL VOLUME MANAGEMENT DEVICE (VMD)
-M:	Jonathan Derrick <jonathan.derrick@intel.com>
+M:	Nirmal Patel <nirmal.patel@linux.intel.com>
+R:	Jonathan Derrick <jonathan.derrick@linux.dev>
 L:	linux-pci@vger.kernel.org
 S:	Supported
 F:	drivers/pci/controller/vmd.c

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Opossums on Parade
 
 # *DOCUMENTATION*
@@ -849,12 +849,6 @@ endif
 
 DEBUG_CFLAGS	:=
 
-# Workaround for GCC versions < 5.0
-# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=61801
-ifdef CONFIG_CC_IS_GCC
-DEBUG_CFLAGS	+= $(call cc-ifversion, -lt, 0500, $(call cc-option, -fno-var-tracking-assignments))
-endif
-
 ifdef CONFIG_DEBUG_INFO
 
 ifdef CONFIG_DEBUG_INFO_SPLIT

arch/alpha/Kconfig

@@ -20,7 +20,7 @@ config ALPHA
 	select NEED_SG_DMA_LENGTH
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
-	select GENERIC_PCI_IOMAP if PCI
+	select GENERIC_PCI_IOMAP
 	select AUTO_IRQ_AFFINITY if SMP
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -199,7 +199,6 @@ config ALPHA_EIGER
 
 config ALPHA_JENSEN
 	bool "Jensen"
-	depends on BROKEN
 	select HAVE_EISA
 	help
 	  DEC PC 150 AXP (aka Jensen): This is a very old Digital system - one

arch/alpha/include/asm/asm-prototypes.h

@@ -16,3 +16,4 @@ extern void __divlu(void);
 extern void __remlu(void);
 extern void __divqu(void);
 extern void __remqu(void);
+extern unsigned long __udiv_qrnnd(unsigned long *, unsigned long, unsigned long , unsigned long);

arch/alpha/include/asm/io.h

@@ -60,7 +60,7 @@ extern inline void set_hae(unsigned long new_hae)
  * Change virtual addresses to physical addresses and vv.
  */
 #ifdef USE_48_BIT_KSEG
-static inline unsigned long virt_to_phys(void *address)
+static inline unsigned long virt_to_phys(volatile void *address)
 {
 	return (unsigned long)address - IDENT_ADDR;
 }
@@ -70,7 +70,7 @@ static inline void * phys_to_virt(unsigned long address)
 	return (void *) (address + IDENT_ADDR);
 }
 #else
-static inline unsigned long virt_to_phys(void *address)
+static inline unsigned long virt_to_phys(volatile void *address)
 {
         unsigned long phys = (unsigned long)address;
 
@@ -106,7 +106,7 @@ static inline void * phys_to_virt(unsigned long address)
 extern unsigned long __direct_map_base;
 extern unsigned long __direct_map_size;
 
-static inline unsigned long __deprecated virt_to_bus(void *address)
+static inline unsigned long __deprecated virt_to_bus(volatile void *address)
 {
 	unsigned long phys = virt_to_phys(address);
 	unsigned long bus = phys + __direct_map_base;

arch/alpha/include/asm/jensen.h

@@ -111,18 +111,18 @@ __EXTERN_INLINE void jensen_set_hae(unsigned long addr)
  * convinced that I need one of the newer machines.
  */
 
-static inline unsigned int jensen_local_inb(unsigned long addr)
+__EXTERN_INLINE unsigned int jensen_local_inb(unsigned long addr)
 {
 	return 0xff & *(vuip)((addr << 9) + EISA_VL82C106);
 }
 
-static inline void jensen_local_outb(u8 b, unsigned long addr)
+__EXTERN_INLINE void jensen_local_outb(u8 b, unsigned long addr)
 {
 	*(vuip)((addr << 9) + EISA_VL82C106) = b;
 	mb();
 }
 
-static inline unsigned int jensen_bus_inb(unsigned long addr)
+__EXTERN_INLINE unsigned int jensen_bus_inb(unsigned long addr)
 {
 	long result;
 
@@ -131,7 +131,7 @@ static inline unsigned int jensen_bus_inb(unsigned long addr)
 	return __kernel_extbl(result, addr & 3);
 }
 
-static inline void jensen_bus_outb(u8 b, unsigned long addr)
+__EXTERN_INLINE void jensen_bus_outb(u8 b, unsigned long addr)
 {
 	jensen_set_hae(0);
 	*(vuip)((addr << 7) + EISA_IO + 0x00) = b * 0x01010101;

arch/alpha/include/asm/setup.h

@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ALPHA_SETUP_H
+#define __ALPHA_SETUP_H
+
+#include <uapi/asm/setup.h>
+
+/*
+ * We leave one page for the initial stack page, and one page for
+ * the initial process structure. Also, the console eats 3 MB for
+ * the initial bootloader (one of which we can reclaim later).
+ */
+#define BOOT_PCB	0x20000000
+#define BOOT_ADDR	0x20000000
+/* Remove when official MILO sources have ELF support: */
+#define BOOT_SIZE	(16*1024)
+
+#ifdef CONFIG_ALPHA_LEGACY_START_ADDRESS
+#define KERNEL_START_PHYS	0x300000 /* Old bootloaders hardcoded this.  */
+#else
+#define KERNEL_START_PHYS	0x1000000 /* required: Wildfire/Titan/Marvel */
+#endif
+
+#define KERNEL_START	(PAGE_OFFSET+KERNEL_START_PHYS)
+#define SWAPPER_PGD	KERNEL_START
+#define INIT_STACK	(PAGE_OFFSET+KERNEL_START_PHYS+0x02000)
+#define EMPTY_PGT	(PAGE_OFFSET+KERNEL_START_PHYS+0x04000)
+#define EMPTY_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x08000)
+#define ZERO_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x0A000)
+
+#define START_ADDR	(PAGE_OFFSET+KERNEL_START_PHYS+0x10000)
+
+/*
+ * This is setup by the secondary bootstrap loader.  Because
+ * the zero page is zeroed out as soon as the vm system is
+ * initialized, we need to copy things out into a more permanent
+ * place.
+ */
+#define PARAM			ZERO_PGE
+#define COMMAND_LINE		((char *)(absolute_pointer(PARAM + 0x0000)))
+#define INITRD_START		(*(unsigned long *) (PARAM+0x100))
+#define INITRD_SIZE		(*(unsigned long *) (PARAM+0x108))
+
+#endif

arch/alpha/include/uapi/asm/setup.h

@@ -1,43 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __ALPHA_SETUP_H
-#define __ALPHA_SETUP_H
+#ifndef _UAPI__ALPHA_SETUP_H
+#define _UAPI__ALPHA_SETUP_H
 
 #define COMMAND_LINE_SIZE	256
 
-/*
- * We leave one page for the initial stack page, and one page for
- * the initial process structure. Also, the console eats 3 MB for
- * the initial bootloader (one of which we can reclaim later).
- */
-#define BOOT_PCB	0x20000000
-#define BOOT_ADDR	0x20000000
-/* Remove when official MILO sources have ELF support: */
-#define BOOT_SIZE	(16*1024)
-
-#ifdef CONFIG_ALPHA_LEGACY_START_ADDRESS
-#define KERNEL_START_PHYS	0x300000 /* Old bootloaders hardcoded this.  */
-#else
-#define KERNEL_START_PHYS	0x1000000 /* required: Wildfire/Titan/Marvel */
-#endif
-
-#define KERNEL_START	(PAGE_OFFSET+KERNEL_START_PHYS)
-#define SWAPPER_PGD	KERNEL_START
-#define INIT_STACK	(PAGE_OFFSET+KERNEL_START_PHYS+0x02000)
-#define EMPTY_PGT	(PAGE_OFFSET+KERNEL_START_PHYS+0x04000)
-#define EMPTY_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x08000)
-#define ZERO_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x0A000)
-
-#define START_ADDR	(PAGE_OFFSET+KERNEL_START_PHYS+0x10000)
-
-/*
- * This is setup by the secondary bootstrap loader.  Because
- * the zero page is zeroed out as soon as the vm system is
- * initialized, we need to copy things out into a more permanent
- * place.
- */
-#define PARAM			ZERO_PGE
-#define COMMAND_LINE		((char*)(PARAM + 0x0000))
-#define INITRD_START		(*(unsigned long *) (PARAM+0x100))
-#define INITRD_SIZE		(*(unsigned long *) (PARAM+0x108))
-
-#endif
+#endif /* _UAPI__ALPHA_SETUP_H */

arch/alpha/kernel/sys_jensen.c

@@ -7,6 +7,11 @@
  *
  * Code supporting the Jensen.
  */
+#define __EXTERN_INLINE
+#include <asm/io.h>
+#include <asm/jensen.h>
+#undef  __EXTERN_INLINE
+
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -17,11 +22,6 @@
 
 #include <asm/ptrace.h>
 
-#define __EXTERN_INLINE inline
-#include <asm/io.h>
-#include <asm/jensen.h>
-#undef  __EXTERN_INLINE
-
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>

arch/alpha/lib/Makefile

@@ -14,6 +14,7 @@ ev6-$(CONFIG_ALPHA_EV6) := ev6-
 ev67-$(CONFIG_ALPHA_EV67) := ev67-
 
 lib-y =	__divqu.o __remqu.o __divlu.o __remlu.o \
+	udiv-qrnnd.o \
 	udelay.o \
 	$(ev6-y)memset.o \
 	$(ev6-y)memcpy.o \

arch/alpha/lib/udiv-qrnnd.S

@@ -25,6 +25,7 @@
  # along with GCC; see the file COPYING.  If not, write to the 
  # Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
  # MA 02111-1307, USA.
+#include <asm/export.h>
 
         .set noreorder
         .set noat
@@ -161,3 +162,4 @@ $Odd:
 	ret	$31,($26),1
 
 	.end	__udiv_qrnnd
+EXPORT_SYMBOL(__udiv_qrnnd)

arch/alpha/math-emu/Makefile

@@ -7,4 +7,4 @@ ccflags-y := -w
 
 obj-$(CONFIG_MATHEMU) += math-emu.o
 
-math-emu-objs := math.o qrnnd.o
+math-emu-objs := math.o

arch/alpha/math-emu/math.c

@@ -403,5 +403,3 @@ alpha_fp_emul_imprecise (struct pt_regs *regs, unsigned long write_mask)
 egress:
 	return si_code;
 }
-
-EXPORT_SYMBOL(__udiv_qrnnd);

arch/arm/kernel/signal.c

@@ -628,7 +628,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 				uprobe_notify_resume(regs);
 			} else {
 				tracehook_notify_resume(regs);
-				rseq_handle_notify_resume(NULL, regs);
 			}
 		}
 		local_irq_disable();

arch/arm64/Kconfig

@@ -86,7 +86,7 @@ config ARM64
 	select ARCH_SUPPORTS_LTO_CLANG_THIN
 	select ARCH_SUPPORTS_CFI_CLANG
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
+	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
 	select ARCH_WANT_DEFAULT_BPF_JIT

arch/arm64/kernel/fpsimd.c

@@ -513,7 +513,7 @@ size_t sve_state_size(struct task_struct const *task)
 void sve_alloc(struct task_struct *task)
 {
 	if (task->thread.sve_state) {
-		memset(task->thread.sve_state, 0, sve_state_size(current));
+		memset(task->thread.sve_state, 0, sve_state_size(task));
 		return;
 	}
 

arch/arm64/kernel/process.c

@@ -18,7 +18,6 @@
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/nospec.h>
-#include <linux/sched.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
 #include <linux/unistd.h>
@@ -58,7 +57,7 @@
 
 #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
 #include <linux/stackprotector.h>
-unsigned long __stack_chk_guard __read_mostly;
+unsigned long __stack_chk_guard __ro_after_init;
 EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 

arch/arm64/kernel/signal.c

@@ -940,10 +940,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags)
 			if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
 				do_signal(regs);
 
-			if (thread_flags & _TIF_NOTIFY_RESUME) {
+			if (thread_flags & _TIF_NOTIFY_RESUME)
 				tracehook_notify_resume(regs);
-				rseq_handle_notify_resume(NULL, regs);
-			}
 
 			if (thread_flags & _TIF_FOREIGN_FPSTATE)
 				fpsimd_restore_current_state();

arch/arm64/kvm/hyp/nvhe/Makefile

@@ -54,7 +54,7 @@ $(obj)/kvm_nvhe.tmp.o: $(obj)/hyp.lds $(addprefix $(obj)/,$(hyp-obj)) FORCE
 #    runtime. Because the hypervisor is part of the kernel binary, relocations
 #    produce a kernel VA. We enumerate relocations targeting hyp at build time
 #    and convert the kernel VAs at those positions to hyp VAs.
-$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel
+$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel FORCE
 	$(call if_changed,hyprel)
 
 # 5) Compile hyp-reloc.S and link it into the existing partially linked object.

arch/arm64/kvm/perf.c

@@ -50,9 +50,6 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = {
 
 int kvm_perf_init(void)
 {
-	if (kvm_pmu_probe_pmuver() != ID_AA64DFR0_PMUVER_IMP_DEF && !is_protected_kvm_enabled())
-		static_branch_enable(&kvm_arm_pmu_available);
-
 	return perf_register_guest_info_callbacks(&kvm_guest_cbs);
 }
 

arch/arm64/kvm/pmu-emul.c

@@ -740,7 +740,14 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	kvm_pmu_create_perf_event(vcpu, select_idx);
 }
 
-int kvm_pmu_probe_pmuver(void)
+void kvm_host_pmu_init(struct arm_pmu *pmu)
+{
+	if (pmu->pmuver != 0 && pmu->pmuver != ID_AA64DFR0_PMUVER_IMP_DEF &&
+	    !kvm_arm_support_pmu_v3() && !is_protected_kvm_enabled())
+		static_branch_enable(&kvm_arm_pmu_available);
+}
+
+static int kvm_pmu_probe_pmuver(void)
 {
 	struct perf_event_attr attr = { };
 	struct perf_event *event;

arch/csky/kernel/signal.c

@@ -260,8 +260,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 	if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
 		do_signal(regs);
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-		rseq_handle_notify_resume(NULL, regs);
-	}
 }

arch/m68k/include/asm/raw_io.h

@@ -17,21 +17,21 @@
  * two accesses to memory, which may be undesirable for some devices.
  */
 #define in_8(addr) \
-    ({ u8 __v = (*(__force volatile u8 *) (addr)); __v; })
+    ({ u8 __v = (*(__force volatile u8 *) (unsigned long)(addr)); __v; })
 #define in_be16(addr) \
-    ({ u16 __v = (*(__force volatile u16 *) (addr)); __v; })
+    ({ u16 __v = (*(__force volatile u16 *) (unsigned long)(addr)); __v; })
 #define in_be32(addr) \
-    ({ u32 __v = (*(__force volatile u32 *) (addr)); __v; })
+    ({ u32 __v = (*(__force volatile u32 *) (unsigned long)(addr)); __v; })
 #define in_le16(addr) \
-    ({ u16 __v = le16_to_cpu(*(__force volatile __le16 *) (addr)); __v; })
+    ({ u16 __v = le16_to_cpu(*(__force volatile __le16 *) (unsigned long)(addr)); __v; })
 #define in_le32(addr) \
-    ({ u32 __v = le32_to_cpu(*(__force volatile __le32 *) (addr)); __v; })
+    ({ u32 __v = le32_to_cpu(*(__force volatile __le32 *) (unsigned long)(addr)); __v; })
 
-#define out_8(addr,b) (void)((*(__force volatile u8 *) (addr)) = (b))
-#define out_be16(addr,w) (void)((*(__force volatile u16 *) (addr)) = (w))
-#define out_be32(addr,l) (void)((*(__force volatile u32 *) (addr)) = (l))
-#define out_le16(addr,w) (void)((*(__force volatile __le16 *) (addr)) = cpu_to_le16(w))
-#define out_le32(addr,l) (void)((*(__force volatile __le32 *) (addr)) = cpu_to_le32(l))
+#define out_8(addr,b) (void)((*(__force volatile u8 *) (unsigned long)(addr)) = (b))
+#define out_be16(addr,w) (void)((*(__force volatile u16 *) (unsigned long)(addr)) = (w))
+#define out_be32(addr,l) (void)((*(__force volatile u32 *) (unsigned long)(addr)) = (l))
+#define out_le16(addr,w) (void)((*(__force volatile __le16 *) (unsigned long)(addr)) = cpu_to_le16(w))
+#define out_le32(addr,l) (void)((*(__force volatile __le32 *) (unsigned long)(addr)) = cpu_to_le32(l))
 
 #define raw_inb in_8
 #define raw_inw in_be16

arch/m68k/mvme147/config.c

@@ -171,7 +171,6 @@ static int bcd2int (unsigned char b)
 
 int mvme147_hwclk(int op, struct rtc_time *t)
 {
-#warning check me!
 	if (!op) {
 		m147_rtc->ctrl = RTC_READ;
 		t->tm_year = bcd2int (m147_rtc->bcd_year);
@@ -183,6 +182,9 @@ int mvme147_hwclk(int op, struct rtc_time *t)
 		m147_rtc->ctrl = 0;
 		if (t->tm_year < 70)
 			t->tm_year += 100;
+	} else {
+		/* FIXME Setting the time is not yet supported */
+		return -EOPNOTSUPP;
 	}
 	return 0;
 }

arch/m68k/mvme16x/config.c

@@ -436,7 +436,6 @@ int bcd2int (unsigned char b)
 
 int mvme16x_hwclk(int op, struct rtc_time *t)
 {
-#warning check me!
 	if (!op) {
 		rtc->ctrl = RTC_READ;
 		t->tm_year = bcd2int (rtc->bcd_year);
@@ -448,6 +447,9 @@ int mvme16x_hwclk(int op, struct rtc_time *t)
 		rtc->ctrl = 0;
 		if (t->tm_year < 70)
 			t->tm_year += 100;
+	} else {
+		/* FIXME Setting the time is not yet supported */
+		return -EOPNOTSUPP;
 	}
 	return 0;
 }

arch/mips/kernel/signal.c

@@ -906,10 +906,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
 	if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
 		do_signal(regs);
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-		rseq_handle_notify_resume(NULL, regs);
-	}
 
 	user_enter();
 }

arch/parisc/include/asm/page.h

@@ -184,7 +184,7 @@ extern int npmem_ranges;
 #include <asm-generic/getorder.h>
 #include <asm/pdc.h>
 
-#define PAGE0   ((struct zeropage *)__PAGE_OFFSET)
+#define PAGE0   ((struct zeropage *)absolute_pointer(__PAGE_OFFSET))
 
 /* DEFINITION OF THE ZERO-PAGE (PAG0) */
 /* based on work by Jason Eckhardt (jason@equator.com) */

arch/parisc/lib/iomap.c

@@ -513,12 +513,15 @@ void ioport_unmap(void __iomem *addr)
 	}
 }
 
+#ifdef CONFIG_PCI
 void pci_iounmap(struct pci_dev *dev, void __iomem * addr)
 {
 	if (!INDIRECT_ADDR(addr)) {
 		iounmap(addr);
 	}
 }
+EXPORT_SYMBOL(pci_iounmap);
+#endif
 
 EXPORT_SYMBOL(ioread8);
 EXPORT_SYMBOL(ioread16);
@@ -544,4 +547,3 @@ EXPORT_SYMBOL(iowrite16_rep);
 EXPORT_SYMBOL(iowrite32_rep);
 EXPORT_SYMBOL(ioport_map);
 EXPORT_SYMBOL(ioport_unmap);
-EXPORT_SYMBOL(pci_iounmap);

arch/powerpc/boot/Makefile

@@ -35,7 +35,6 @@ endif
 BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		 -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \
 		 -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
-		 -include $(srctree)/include/linux/compiler_attributes.h \
 		 $(LINUXINCLUDE)
 
 ifdef CONFIG_PPC64_BOOT_WRAPPER
@@ -70,6 +69,7 @@ ifeq ($(call cc-option-yn, -fstack-protector),y)
 BOOTCFLAGS	+= -fno-stack-protector
 endif
 
+BOOTCFLAGS	+= -include $(srctree)/include/linux/compiler_attributes.h
 BOOTCFLAGS	+= -I$(objtree)/$(obj) -I$(srctree)/$(obj)
 
 DTC_FLAGS	?= -p 1024

arch/powerpc/include/asm/asm-const.h

@@ -12,16 +12,6 @@
 #  define ASM_CONST(x)		__ASM_CONST(x)
 #endif
 
-/*
- * Inline assembly memory constraint
- *
- * GCC 4.9 doesn't properly handle pre update memory constraint "m<>"
- *
- */
-#if defined(GCC_VERSION) && GCC_VERSION < 50000
-#define UPD_CONSTR ""
-#else
 #define UPD_CONSTR "<>"
-#endif
 
 #endif /* _ASM_POWERPC_ASM_CONST_H */

arch/powerpc/kernel/interrupt.c

@@ -18,6 +18,7 @@
 #include <asm/switch_to.h>
 #include <asm/syscall.h>
 #include <asm/time.h>
+#include <asm/tm.h>
 #include <asm/unistd.h>
 
 #if defined(CONFIG_PPC_ADV_DEBUG_REGS) && defined(CONFIG_PPC32)
@@ -136,6 +137,48 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	 */
 	irq_soft_mask_regs_set_state(regs, IRQS_ENABLED);
 
+	/*
+	 * If system call is called with TM active, set _TIF_RESTOREALL to
+	 * prevent RFSCV being used to return to userspace, because POWER9
+	 * TM implementation has problems with this instruction returning to
+	 * transactional state. Final register values are not relevant because
+	 * the transaction will be aborted upon return anyway. Or in the case
+	 * of unsupported_scv SIGILL fault, the return state does not much
+	 * matter because it's an edge case.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+			unlikely(MSR_TM_TRANSACTIONAL(regs->msr)))
+		current_thread_info()->flags |= _TIF_RESTOREALL;
+
+	/*
+	 * If the system call was made with a transaction active, doom it and
+	 * return without performing the system call. Unless it was an
+	 * unsupported scv vector, in which case it's treated like an illegal
+	 * instruction.
+	 */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) &&
+	    !trap_is_unsupported_scv(regs)) {
+		/* Enable TM in the kernel, and disable EE (for scv) */
+		hard_irq_disable();
+		mtmsr(mfmsr() | MSR_TM);
+
+		/* tabort, this dooms the transaction, nothing else */
+		asm volatile(".long 0x7c00071d | ((%0) << 16)"
+				:: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT));
+
+		/*
+		 * Userspace will never see the return value. Execution will
+		 * resume after the tbegin. of the aborted transaction with the
+		 * checkpointed register state. A context switch could occur
+		 * or signal delivered to the process before resuming the
+		 * doomed transaction context, but that should all be handled
+		 * as expected.
+		 */
+		return -ENOSYS;
+	}
+#endif // CONFIG_PPC_TRANSACTIONAL_MEM
+
 	local_irq_enable();
 
 	if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) {

arch/powerpc/kernel/interrupt_64.S

@@ -12,7 +12,6 @@
 #include <asm/mmu.h>
 #include <asm/ppc_asm.h>
 #include <asm/ptrace.h>
-#include <asm/tm.h>
 
 	.section	".toc","aw"
 SYS_CALL_TABLE:
@@ -55,12 +54,6 @@ COMPAT_SYS_CALL_TABLE:
 	.globl system_call_vectored_\name
 system_call_vectored_\name:
 _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-BEGIN_FTR_SECTION
-	extrdi.	r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
-	bne	tabort_syscall
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
-#endif
 	SCV_INTERRUPT_TO_KERNEL
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
@@ -247,12 +240,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_common_real)
 	.globl system_call_common
 system_call_common:
 _ASM_NOKPROBE_SYMBOL(system_call_common)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-BEGIN_FTR_SECTION
-	extrdi.	r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
-	bne	tabort_syscall
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
-#endif
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
@@ -425,34 +412,6 @@ SOFT_MASK_TABLE(.Lsyscall_rst_start, 1b)
 RESTART_TABLE(.Lsyscall_rst_start, .Lsyscall_rst_end, syscall_restart)
 #endif
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-tabort_syscall:
-_ASM_NOKPROBE_SYMBOL(tabort_syscall)
-	/* Firstly we need to enable TM in the kernel */
-	mfmsr	r10
-	li	r9, 1
-	rldimi	r10, r9, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r10, 0
-
-	/* tabort, this dooms the transaction, nothing else */
-	li	r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
-	TABORT(R9)
-
-	/*
-	 * Return directly to userspace. We have corrupted user register state,
-	 * but userspace will never see that register state. Execution will
-	 * resume after the tbegin of the aborted transaction with the
-	 * checkpointed register state.
-	 */
-	li	r9, MSR_RI
-	andc	r10, r10, r9
-	mtmsrd	r10, 1
-	mtspr	SPRN_SRR0, r11
-	mtspr	SPRN_SRR1, r12
-	RFI_TO_USER
-	b	.	/* prevent speculative execution */
-#endif
-
 	/*
 	 * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not
 	 * touched, no exit work created, then this can be used.

arch/powerpc/kernel/mce.c

@@ -249,6 +249,7 @@ void machine_check_queue_event(void)
 {
 	int index;
 	struct machine_check_event evt;
+	unsigned long msr;
 
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return;
@@ -262,8 +263,20 @@ void machine_check_queue_event(void)
 	memcpy(&local_paca->mce_info->mce_event_queue[index],
 	       &evt, sizeof(evt));
 
-	/* Queue irq work to process this event later. */
+	/*
+	 * Queue irq work to process this event later. Before
+	 * queuing the work enable translation for non radix LPAR,
+	 * as irq_work_queue may try to access memory outside RMO
+	 * region.
+	 */
+	if (!radix_enabled() && firmware_has_feature(FW_FEATURE_LPAR)) {
+		msr = mfmsr();
+		mtmsr(msr | MSR_IR | MSR_DR);
 		irq_work_queue(&mce_event_process_work);
+		mtmsr(msr);
+	} else {
+		irq_work_queue(&mce_event_process_work);
+	}
 }
 
 void mce_common_process_ue(struct pt_regs *regs,

arch/powerpc/kernel/signal.c

@@ -293,10 +293,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 		do_signal(current);
 	}
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-		rseq_handle_notify_resume(NULL, regs);
-	}
 }
 
 static unsigned long get_tm_stackpointer(struct task_struct *tsk)

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -2536,7 +2536,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST)
 	/* The following code handles the fake_suspend = 1 case */
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
-	stdu	r1, -PPC_MIN_STKFRM(r1)
+	stdu	r1, -TM_FRAME_SIZE(r1)
 
 	/* Turn on TM. */
 	mfmsr	r8
@@ -2551,10 +2551,42 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 	nop
 
+	/*
+	 * It's possible that treclaim. may modify registers, if we have lost
+	 * track of fake-suspend state in the guest due to it using rfscv.
+	 * Save and restore registers in case this occurs.
+	 */
+	mfspr	r3, SPRN_DSCR
+	mfspr	r4, SPRN_XER
+	mfspr	r5, SPRN_AMR
+	/* SPRN_TAR would need to be saved here if the kernel ever used it */
+	mfcr	r12
+	SAVE_NVGPRS(r1)
+	SAVE_GPR(2, r1)
+	SAVE_GPR(3, r1)
+	SAVE_GPR(4, r1)
+	SAVE_GPR(5, r1)
+	stw	r12, 8(r1)
+	std	r1, HSTATE_HOST_R1(r13)
+
 	/* We have to treclaim here because that's the only way to do S->N */
 	li	r3, TM_CAUSE_KVM_RESCHED
 	TRECLAIM(R3)
 
+	GET_PACA(r13)
+	ld	r1, HSTATE_HOST_R1(r13)
+	REST_GPR(2, r1)
+	REST_GPR(3, r1)
+	REST_GPR(4, r1)
+	REST_GPR(5, r1)
+	lwz	r12, 8(r1)
+	REST_NVGPRS(r1)
+	mtspr	SPRN_DSCR, r3
+	mtspr	SPRN_XER, r4
+	mtspr	SPRN_AMR, r5
+	mtcr	r12
+	HMT_MEDIUM
+
 	/*
 	 * We were in fake suspend, so we are not going to save the
 	 * register state as the guest checkpointed state (since
@@ -2582,7 +2614,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 	std	r5, VCPU_TFHAR(r9)
 	std	r6, VCPU_TFIAR(r9)
 
-	addi	r1, r1, PPC_MIN_STKFRM
+	addi	r1, r1, TM_FRAME_SIZE
 	ld	r0, PPC_LR_STKOFF(r1)
 	mtlr	r0
 	blr

arch/powerpc/sysdev/xics/xics-common.c

@@ -348,9 +348,9 @@ static int xics_host_map(struct irq_domain *domain, unsigned int virq,
 	if (xics_ics->check(xics_ics, hwirq))
 		return -EINVAL;
 
-	/* No chip data for the XICS domain */
+	/* Let the ICS be the chip data for the XICS domain. For ICS native */
 	irq_domain_set_info(domain, virq, hwirq, xics_ics->chip,
-			    NULL, handle_fasteoi_irq, NULL, NULL);
+			    xics_ics, handle_fasteoi_irq, NULL, NULL);
 
 	return 0;
 }

arch/riscv/Kconfig

@@ -237,7 +237,7 @@ config ARCH_RV32I
 config ARCH_RV64I
 	bool "RV64I"
 	select 64BIT
-	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && GCC_VERSION >= 50000
+	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
 	select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && $(cc-option,-fpatchable-function-entry=8)
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL

arch/riscv/include/asm/csr.h

@@ -58,22 +58,32 @@
 
 /* Interrupt causes (minus the high bit) */
 #define IRQ_S_SOFT		1
+#define IRQ_VS_SOFT		2
 #define IRQ_M_SOFT		3
 #define IRQ_S_TIMER		5
+#define IRQ_VS_TIMER		6
 #define IRQ_M_TIMER		7
 #define IRQ_S_EXT		9
+#define IRQ_VS_EXT		10
 #define IRQ_M_EXT		11
 
 /* Exception causes */
 #define EXC_INST_MISALIGNED	0
 #define EXC_INST_ACCESS		1
+#define EXC_INST_ILLEGAL	2
 #define EXC_BREAKPOINT		3
 #define EXC_LOAD_ACCESS		5
 #define EXC_STORE_ACCESS	7
 #define EXC_SYSCALL		8
+#define EXC_HYPERVISOR_SYSCALL	9
+#define EXC_SUPERVISOR_SYSCALL	10
 #define EXC_INST_PAGE_FAULT	12
 #define EXC_LOAD_PAGE_FAULT	13
 #define EXC_STORE_PAGE_FAULT	15
+#define EXC_INST_GUEST_PAGE_FAULT	20
+#define EXC_LOAD_GUEST_PAGE_FAULT	21
+#define EXC_VIRTUAL_INST_FAULT		22
+#define EXC_STORE_GUEST_PAGE_FAULT	23
 
 /* PMP configuration */
 #define PMP_R			0x01
@@ -85,6 +95,58 @@
 #define PMP_A_NAPOT		0x18
 #define PMP_L			0x80
 
+/* HSTATUS flags */
+#ifdef CONFIG_64BIT
+#define HSTATUS_VSXL		_AC(0x300000000, UL)
+#define HSTATUS_VSXL_SHIFT	32
+#endif
+#define HSTATUS_VTSR		_AC(0x00400000, UL)
+#define HSTATUS_VTW		_AC(0x00200000, UL)
+#define HSTATUS_VTVM		_AC(0x00100000, UL)
+#define HSTATUS_VGEIN		_AC(0x0003f000, UL)
+#define HSTATUS_VGEIN_SHIFT	12
+#define HSTATUS_HU		_AC(0x00000200, UL)
+#define HSTATUS_SPVP		_AC(0x00000100, UL)
+#define HSTATUS_SPV		_AC(0x00000080, UL)
+#define HSTATUS_GVA		_AC(0x00000040, UL)
+#define HSTATUS_VSBE		_AC(0x00000020, UL)
+
+/* HGATP flags */
+#define HGATP_MODE_OFF		_AC(0, UL)
+#define HGATP_MODE_SV32X4	_AC(1, UL)
+#define HGATP_MODE_SV39X4	_AC(8, UL)
+#define HGATP_MODE_SV48X4	_AC(9, UL)
+
+#define HGATP32_MODE_SHIFT	31
+#define HGATP32_VMID_SHIFT	22
+#define HGATP32_VMID_MASK	_AC(0x1FC00000, UL)
+#define HGATP32_PPN		_AC(0x003FFFFF, UL)
+
+#define HGATP64_MODE_SHIFT	60
+#define HGATP64_VMID_SHIFT	44
+#define HGATP64_VMID_MASK	_AC(0x03FFF00000000000, UL)
+#define HGATP64_PPN		_AC(0x00000FFFFFFFFFFF, UL)
+
+#define HGATP_PAGE_SHIFT	12
+
+#ifdef CONFIG_64BIT
+#define HGATP_PPN		HGATP64_PPN
+#define HGATP_VMID_SHIFT	HGATP64_VMID_SHIFT
+#define HGATP_VMID_MASK		HGATP64_VMID_MASK
+#define HGATP_MODE_SHIFT	HGATP64_MODE_SHIFT
+#else
+#define HGATP_PPN		HGATP32_PPN
+#define HGATP_VMID_SHIFT	HGATP32_VMID_SHIFT
+#define HGATP_VMID_MASK		HGATP32_VMID_MASK
+#define HGATP_MODE_SHIFT	HGATP32_MODE_SHIFT
+#endif
+
+/* VSIP & HVIP relation */
+#define VSIP_TO_HVIP_SHIFT	(IRQ_VS_SOFT - IRQ_S_SOFT)
+#define VSIP_VALID_MASK		((_AC(1, UL) << IRQ_S_SOFT) | \
+				 (_AC(1, UL) << IRQ_S_TIMER) | \
+				 (_AC(1, UL) << IRQ_S_EXT))
+
 /* symbolic CSR names: */
 #define CSR_CYCLE		0xc00
 #define CSR_TIME		0xc01
@@ -104,6 +166,31 @@
 #define CSR_SIP			0x144
 #define CSR_SATP		0x180
 
+#define CSR_VSSTATUS		0x200
+#define CSR_VSIE		0x204
+#define CSR_VSTVEC		0x205
+#define CSR_VSSCRATCH		0x240
+#define CSR_VSEPC		0x241
+#define CSR_VSCAUSE		0x242
+#define CSR_VSTVAL		0x243
+#define CSR_VSIP		0x244
+#define CSR_VSATP		0x280
+
+#define CSR_HSTATUS		0x600
+#define CSR_HEDELEG		0x602
+#define CSR_HIDELEG		0x603
+#define CSR_HIE			0x604
+#define CSR_HTIMEDELTA		0x605
+#define CSR_HCOUNTEREN		0x606
+#define CSR_HGEIE		0x607
+#define CSR_HTIMEDELTAH		0x615
+#define CSR_HTVAL		0x643
+#define CSR_HIP			0x644
+#define CSR_HVIP		0x645
+#define CSR_HTINST		0x64a
+#define CSR_HGATP		0x680
+#define CSR_HGEIP		0xe12
+
 #define CSR_MSTATUS		0x300
 #define CSR_MISA		0x301
 #define CSR_MIE			0x304

arch/s390/Kconfig

@@ -685,16 +685,6 @@ config STACK_GUARD
 	  The minimum size for the stack guard should be 256 for 31 bit and
 	  512 for 64 bit.
 
-config WARN_DYNAMIC_STACK
-	def_bool n
-	prompt "Emit compiler warnings for function with dynamic stack usage"
-	help
-	  This option enables the compiler option -mwarn-dynamicstack. If the
-	  compiler supports this options generates warnings for functions
-	  that dynamically allocate stack space using alloca.
-
-	  Say N if you are unsure.
-
 endmenu
 
 menu "I/O subsystem"

arch/s390/Makefile

@@ -85,13 +85,6 @@ cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD)
 endif
 endif
 
-ifdef CONFIG_WARN_DYNAMIC_STACK
-  ifneq ($(call cc-option,-mwarn-dynamicstack),)
-    KBUILD_CFLAGS += -mwarn-dynamicstack
-    KBUILD_CFLAGS_DECOMPRESSOR += -mwarn-dynamicstack
-  endif
-endif
-
 ifdef CONFIG_EXPOLINE
   ifneq ($(call cc-option,$(CC_FLAGS_MARCH) -mindirect-branch=thunk),)
     CC_FLAGS_EXPOLINE := -mindirect-branch=thunk

arch/s390/configs/debug_defconfig

@@ -10,6 +10,7 @@ CONFIG_BPF_JIT=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_LSM=y
 CONFIG_PREEMPT=y
+CONFIG_SCHED_CORE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_TASKSTATS=y
@@ -503,6 +504,7 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MICROSOFT is not set
+# CONFIG_NET_VENDOR_LITEX is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 CONFIG_MLX4_EN=m
 CONFIG_MLX5_CORE=m
@@ -661,7 +663,6 @@ CONFIG_NFSD_V3_ACL=y
 CONFIG_NFSD_V4=y
 CONFIG_NFSD_V4_SECURITY_LABEL=y
 CONFIG_CIFS=m
-CONFIG_CIFS_WEAK_PW_HASH=y
 CONFIG_CIFS_UPCALL=y
 CONFIG_CIFS_XATTR=y
 CONFIG_CIFS_POSIX=y
@@ -720,6 +721,8 @@ CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_BLAKE2S=m
+CONFIG_CRYPTO_MD4=m
+CONFIG_CRYPTO_MD5=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
 CONFIG_CRYPTO_SHA3=m
@@ -774,7 +777,6 @@ CONFIG_RANDOM32_SELFTEST=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=0
 CONFIG_DMA_API_DEBUG=y
-CONFIG_STRING_SELFTEST=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_DEBUG_INFO=y
@@ -853,12 +855,12 @@ CONFIG_FAIL_FUNCTION=y
 CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
 CONFIG_LKDTM=m
 CONFIG_TEST_MIN_HEAP=y
-CONFIG_TEST_SORT=y
 CONFIG_KPROBES_SANITY_TEST=y
 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
 CONFIG_TEST_LIVEPATCH=m

arch/s390/configs/defconfig

@@ -8,6 +8,7 @@ CONFIG_BPF_SYSCALL=y
 CONFIG_BPF_JIT=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_LSM=y
+CONFIG_SCHED_CORE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_TASKSTATS=y
@@ -494,6 +495,7 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MICROSOFT is not set
+# CONFIG_NET_VENDOR_LITEX is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 CONFIG_MLX4_EN=m
 CONFIG_MLX5_CORE=m
@@ -648,7 +650,6 @@ CONFIG_NFSD_V3_ACL=y
 CONFIG_NFSD_V4=y
 CONFIG_NFSD_V4_SECURITY_LABEL=y
 CONFIG_CIFS=m
-CONFIG_CIFS_WEAK_PW_HASH=y
 CONFIG_CIFS_UPCALL=y
 CONFIG_CIFS_XATTR=y
 CONFIG_CIFS_POSIX=y
@@ -708,6 +709,8 @@ CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_BLAKE2S=m
+CONFIG_CRYPTO_MD4=m
+CONFIG_CRYPTO_MD5=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
 CONFIG_CRYPTO_SHA3=m

arch/s390/kvm/gaccess.c

@@ -894,6 +894,11 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
 
 /**
  * guest_translate_address - translate guest logical into guest absolute address
+ * @vcpu: virtual cpu
+ * @gva: Guest virtual address
+ * @ar: Access register
+ * @gpa: Guest physical address
+ * @mode: Translation access mode
  *
  * Parameter semantics are the same as the ones from guest_translate.
  * The memory contents at the guest address are not changed.
@@ -934,6 +939,11 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 
 /**
  * check_gva_range - test a range of guest virtual addresses for accessibility
+ * @vcpu: virtual cpu
+ * @gva: Guest virtual address
+ * @ar: Access register
+ * @length: Length of test range
+ * @mode: Translation access mode
  */
 int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 		    unsigned long length, enum gacc_mode mode)
@@ -956,6 +966,7 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 
 /**
  * kvm_s390_check_low_addr_prot_real - check for low-address protection
+ * @vcpu: virtual cpu
  * @gra: Guest real address
  *
  * Checks whether an address is subject to low-address protection and set
@@ -979,6 +990,7 @@ int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra)
  * @pgt: pointer to the beginning of the page table for the given address if
  *	 successful (return value 0), or to the first invalid DAT entry in
  *	 case of exceptions (return value > 0)
+ * @dat_protection: referenced memory is write protected
  * @fake: pgt references contiguous guest memory block, not a pgtable
  */
 static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,

arch/s390/kvm/intercept.c

@@ -269,6 +269,7 @@ static int handle_prog(struct kvm_vcpu *vcpu)
 
 /**
  * handle_external_interrupt - used for external interruption interceptions
+ * @vcpu: virtual cpu
  *
  * This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if
  * the new PSW does not have external interrupts disabled. In the first case,
@@ -315,7 +316,8 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
 }
 
 /**
- * Handle MOVE PAGE partial execution interception.
+ * handle_mvpg_pei - Handle MOVE PAGE partial execution interception.
+ * @vcpu: virtual cpu
  *
  * This interception can only happen for guests with DAT disabled and
  * addresses that are currently not mapped in the host. Thus we try to

arch/s390/kvm/interrupt.c

@@ -419,13 +419,13 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
 static void __set_cpu_idle(struct kvm_vcpu *vcpu)
 {
 	kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
-	set_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
+	set_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask);
 }
 
 static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
 {
 	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
-	clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
+	clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask);
 }
 
 static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)

arch/s390/kvm/kvm-s390.c

@@ -4066,7 +4066,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
 		kvm_s390_patch_guest_per_regs(vcpu);
 	}
 
-	clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.gisa_int.kicked_mask);
+	clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask);
 
 	vcpu->arch.sie_block->icptcode = 0;
 	cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);

arch/s390/kvm/kvm-s390.h

@@ -79,7 +79,7 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
 
 static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
 {
-	return test_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask);
+	return test_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask);
 }
 
 static inline int kvm_is_ucontrol(struct kvm *kvm)

arch/s390/pci/pci_mmio.c

@@ -159,7 +159,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 
 	mmap_read_lock(current->mm);
 	ret = -EINVAL;
-	vma = find_vma(current->mm, mmio_addr);
+	vma = vma_lookup(current->mm, mmio_addr);
 	if (!vma)
 		goto out_unlock_mmap;
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
@@ -298,7 +298,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 
 	mmap_read_lock(current->mm);
 	ret = -EINVAL;
-	vma = find_vma(current->mm, mmio_addr);
+	vma = vma_lookup(current->mm, mmio_addr);
 	if (!vma)
 		goto out_unlock_mmap;
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))

arch/sh/boot/Makefile

@@ -80,30 +80,30 @@ $(obj)/vmlinux.bin.xz: $(obj)/vmlinux.bin FORCE
 $(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,lzo)
 
-$(obj)/uImage.bz2: $(obj)/vmlinux.bin.bz2
+$(obj)/uImage.bz2: $(obj)/vmlinux.bin.bz2 FORCE
 	$(call if_changed,uimage,bzip2)
 
-$(obj)/uImage.gz: $(obj)/vmlinux.bin.gz
+$(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
 	$(call if_changed,uimage,gzip)
 
-$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma
+$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE
 	$(call if_changed,uimage,lzma)
 
-$(obj)/uImage.xz: $(obj)/vmlinux.bin.xz
+$(obj)/uImage.xz: $(obj)/vmlinux.bin.xz FORCE
 	$(call if_changed,uimage,xz)
 
-$(obj)/uImage.lzo: $(obj)/vmlinux.bin.lzo
+$(obj)/uImage.lzo: $(obj)/vmlinux.bin.lzo FORCE
 	$(call if_changed,uimage,lzo)
 
-$(obj)/uImage.bin: $(obj)/vmlinux.bin
+$(obj)/uImage.bin: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,uimage,none)
 
 OBJCOPYFLAGS_vmlinux.srec := -I binary -O srec
-$(obj)/vmlinux.srec: $(obj)/compressed/vmlinux
+$(obj)/vmlinux.srec: $(obj)/compressed/vmlinux FORCE
 	$(call if_changed,objcopy)
 
 OBJCOPYFLAGS_uImage.srec := -I binary -O srec
-$(obj)/uImage.srec: $(obj)/uImage
+$(obj)/uImage.srec: $(obj)/uImage FORCE
 	$(call if_changed,objcopy)
 
 $(obj)/uImage: $(obj)/uImage.$(suffix-y)

arch/sparc/kernel/ioport.c

@@ -356,7 +356,9 @@ err_nomem:
 void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs)
 {
-	if (!sparc_dma_free_resource(cpu_addr, PAGE_ALIGN(size)))
+	size = PAGE_ALIGN(size);
+
+	if (!sparc_dma_free_resource(cpu_addr, size))
 		return;
 
 	dma_make_coherent(dma_addr, size);

arch/sparc/kernel/mdesc.c

@@ -39,6 +39,7 @@ struct mdesc_hdr {
 	u32	node_sz; /* node block size */
 	u32	name_sz; /* name block size */
 	u32	data_sz; /* data block size */
+	char	data[];
 } __attribute__((aligned(16)));
 
 struct mdesc_elem {
@@ -612,7 +613,7 @@ EXPORT_SYMBOL(mdesc_get_node_info);
 
 static struct mdesc_elem *node_block(struct mdesc_hdr *mdesc)
 {
-	return (struct mdesc_elem *) (mdesc + 1);
+	return (struct mdesc_elem *) mdesc->data;
 }
 
 static void *name_block(struct mdesc_hdr *mdesc)

arch/x86/Kconfig

@@ -339,6 +339,11 @@ config NEED_PER_CPU_PAGE_FIRST_CHUNK
 config ARCH_HIBERNATION_POSSIBLE
 	def_bool y
 
+config ARCH_NR_GPIO
+	int
+	default 1024 if X86_64
+	default 512
+
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 

arch/x86/Makefile_32.cpu

@@ -4,6 +4,12 @@
 
 tune		= $(call cc-option,-mtune=$(1),$(2))
 
+ifdef CONFIG_CC_IS_CLANG
+align		:= -falign-functions=0 $(call cc-option,-falign-jumps=0) $(call cc-option,-falign-loops=0)
+else
+align		:= -falign-functions=0 -falign-jumps=0 -falign-loops=0
+endif
+
 cflags-$(CONFIG_M486SX)		+= -march=i486
 cflags-$(CONFIG_M486)		+= -march=i486
 cflags-$(CONFIG_M586)		+= -march=i586
@@ -19,11 +25,11 @@ cflags-$(CONFIG_MK6)		+= -march=k6
 # They make zero difference whatsosever to performance at this time.
 cflags-$(CONFIG_MK7)		+= -march=athlon
 cflags-$(CONFIG_MK8)		+= $(call cc-option,-march=k8,-march=athlon)
-cflags-$(CONFIG_MCRUSOE)	+= -march=i686 -falign-functions=0 -falign-jumps=0 -falign-loops=0
-cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) -falign-functions=0 -falign-jumps=0 -falign-loops=0
+cflags-$(CONFIG_MCRUSOE)	+= -march=i686 $(align)
+cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) $(align)
 cflags-$(CONFIG_MWINCHIPC6)	+= $(call cc-option,-march=winchip-c6,-march=i586)
 cflags-$(CONFIG_MWINCHIP3D)	+= $(call cc-option,-march=winchip2,-march=i586)
-cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) -falign-functions=0 -falign-jumps=0 -falign-loops=0
+cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) $(align)
 cflags-$(CONFIG_MVIAC3_2)	+= $(call cc-option,-march=c3-2,-march=i686)
 cflags-$(CONFIG_MVIAC7)		+= -march=i686
 cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call tune,core2)

arch/x86/hyperv/hv_apic.c

@@ -99,7 +99,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val)
 /*
  * IPI implementation on Hyper-V.
  */
-static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
+static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
+		bool exclude_self)
 {
 	struct hv_send_ipi_ex **arg;
 	struct hv_send_ipi_ex *ipi_arg;
@@ -123,6 +124,9 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 
 	if (!cpumask_equal(mask, cpu_present_mask)) {
 		ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+		if (exclude_self)
+			nr_bank = cpumask_to_vpset_noself(&(ipi_arg->vp_set), mask);
+		else
 			nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask);
 	}
 	if (nr_bank < 0)
@@ -138,15 +142,25 @@ ipi_mask_ex_done:
 	return hv_result_success(status);
 }
 
-static bool __send_ipi_mask(const struct cpumask *mask, int vector)
+static bool __send_ipi_mask(const struct cpumask *mask, int vector,
+		bool exclude_self)
 {
-	int cur_cpu, vcpu;
+	int cur_cpu, vcpu, this_cpu = smp_processor_id();
 	struct hv_send_ipi ipi_arg;
 	u64 status;
+	unsigned int weight;
 
 	trace_hyperv_send_ipi_mask(mask, vector);
 
-	if (cpumask_empty(mask))
+	weight = cpumask_weight(mask);
+
+	/*
+	 * Do nothing if
+	 *   1. the mask is empty
+	 *   2. the mask only contains self when exclude_self is true
+	 */
+	if (weight == 0 ||
+	    (exclude_self && weight == 1 && cpumask_test_cpu(this_cpu, mask)))
 		return true;
 
 	if (!hv_hypercall_pg)
@@ -172,6 +186,8 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	ipi_arg.cpu_mask = 0;
 
 	for_each_cpu(cur_cpu, mask) {
+		if (exclude_self && cur_cpu == this_cpu)
+			continue;
 		vcpu = hv_cpu_number_to_vp_number(cur_cpu);
 		if (vcpu == VP_INVAL)
 			return false;
@@ -191,7 +207,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	return hv_result_success(status);
 
 do_ex_hypercall:
-	return __send_ipi_mask_ex(mask, vector);
+	return __send_ipi_mask_ex(mask, vector, exclude_self);
 }
 
 static bool __send_ipi_one(int cpu, int vector)
@@ -208,7 +224,7 @@ static bool __send_ipi_one(int cpu, int vector)
 		return false;
 
 	if (vp >= 64)
-		return __send_ipi_mask_ex(cpumask_of(cpu), vector);
+		return __send_ipi_mask_ex(cpumask_of(cpu), vector, false);
 
 	status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp));
 	return hv_result_success(status);
@@ -222,20 +238,13 @@ static void hv_send_ipi(int cpu, int vector)
 
 static void hv_send_ipi_mask(const struct cpumask *mask, int vector)
 {
-	if (!__send_ipi_mask(mask, vector))
+	if (!__send_ipi_mask(mask, vector, false))
 		orig_apic.send_IPI_mask(mask, vector);
 }
 
 static void hv_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
 {
-	unsigned int this_cpu = smp_processor_id();
-	struct cpumask new_mask;
-	const struct cpumask *local_mask;
-
-	cpumask_copy(&new_mask, mask);
-	cpumask_clear_cpu(this_cpu, &new_mask);
-	local_mask = &new_mask;
-	if (!__send_ipi_mask(local_mask, vector))
+	if (!__send_ipi_mask(mask, vector, true))
 		orig_apic.send_IPI_mask_allbutself(mask, vector);
 }
 
@@ -246,7 +255,7 @@ static void hv_send_ipi_allbutself(int vector)
 
 static void hv_send_ipi_all(int vector)
 {
-	if (!__send_ipi_mask(cpu_online_mask, vector))
+	if (!__send_ipi_mask(cpu_online_mask, vector, false))
 		orig_apic.send_IPI_all(vector);
 }
 

arch/x86/include/asm/kvm_page_track.h

@@ -46,7 +46,7 @@ struct kvm_page_track_notifier_node {
 			    struct kvm_page_track_notifier_node *node);
 };
 
-void kvm_page_track_init(struct kvm *kvm);
+int kvm_page_track_init(struct kvm *kvm);
 void kvm_page_track_cleanup(struct kvm *kvm);
 
 void kvm_page_track_free_memslot(struct kvm_memory_slot *slot);

arch/x86/include/asm/kvmclock.h

@@ -2,6 +2,20 @@
 #ifndef _ASM_X86_KVM_CLOCK_H
 #define _ASM_X86_KVM_CLOCK_H
 
+#include <linux/percpu.h>
+
 extern struct clocksource kvm_clock;
 
+DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+
+static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
+{
+	return &this_cpu_read(hv_clock_per_cpu)->pvti;
+}
+
+static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
+{
+	return this_cpu_read(hv_clock_per_cpu);
+}
+
 #endif /* _ASM_X86_KVM_CLOCK_H */

arch/x86/include/asm/uaccess.h

@@ -301,8 +301,8 @@ do {									\
 	unsigned int __gu_low, __gu_high;				\
 	const unsigned int __user *__gu_ptr;				\
 	__gu_ptr = (const void __user *)(ptr);				\
-	__get_user_asm(__gu_low, ptr, "l", "=r", label);		\
-	__get_user_asm(__gu_high, ptr+1, "l", "=r", label);		\
+	__get_user_asm(__gu_low, __gu_ptr, "l", "=r", label);		\
+	__get_user_asm(__gu_high, __gu_ptr+1, "l", "=r", label);	\
 	(x) = ((unsigned long long)__gu_high << 32) | __gu_low;		\
 } while (0)
 #else

arch/x86/kernel/cpu/mce/core.c

@@ -1253,6 +1253,9 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin
 
 static void kill_me_now(struct callback_head *ch)
 {
+	struct task_struct *p = container_of(ch, struct task_struct, mce_kill_me);
+
+	p->mce_count = 0;
 	force_sig(SIGBUS);
 }
 
@@ -1262,6 +1265,7 @@ static void kill_me_maybe(struct callback_head *cb)
 	int flags = MF_ACTION_REQUIRED;
 	int ret;
 
+	p->mce_count = 0;
 	pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
 
 	if (!p->mce_ripv)
@@ -1290,8 +1294,12 @@ static void kill_me_maybe(struct callback_head *cb)
 	}
 }
 
-static void queue_task_work(struct mce *m, int kill_current_task)
+static void queue_task_work(struct mce *m, char *msg, int kill_current_task)
 {
+	int count = ++current->mce_count;
+
+	/* First call, save all the details */
+	if (count == 1) {
 		current->mce_addr = m->addr;
 		current->mce_kflags = m->kflags;
 		current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
@@ -1301,6 +1309,19 @@ static void queue_task_work(struct mce *m, int kill_current_task)
 			current->mce_kill_me.func = kill_me_now;
 		else
 			current->mce_kill_me.func = kill_me_maybe;
+	}
+
+	/* Ten is likely overkill. Don't expect more than two faults before task_work() */
+	if (count > 10)
+		mce_panic("Too many consecutive machine checks while accessing user data", m, msg);
+
+	/* Second or later call, make sure page address matches the one from first call */
+	if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT))
+		mce_panic("Consecutive machine checks to different user pages", m, msg);
+
+	/* Do not call task_work_add() more than once */
+	if (count > 1)
+		return;
 
 	task_work_add(current, &current->mce_kill_me, TWA_RESUME);
 }
@@ -1438,7 +1459,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		/* If this triggers there is no way to recover. Die hard. */
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
 
-		queue_task_work(&m, kill_current_task);
+		queue_task_work(&m, msg, kill_current_task);
 
 	} else {
 		/*
@@ -1456,7 +1477,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		}
 
 		if (m.kflags & MCE_IN_KERNEL_COPYIN)
-			queue_task_work(&m, kill_current_task);
+			queue_task_work(&m, msg, kill_current_task);
 	}
 out:
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);

arch/x86/kernel/kvmclock.c

@@ -49,18 +49,9 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
 static struct pvclock_vsyscall_time_info
 			hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE);
 static struct pvclock_wall_clock wall_clock __bss_decrypted;
-static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
 static struct pvclock_vsyscall_time_info *hvclock_mem;
-
-static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
-{
-	return &this_cpu_read(hv_clock_per_cpu)->pvti;
-}
-
-static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
-{
-	return this_cpu_read(hv_clock_per_cpu);
-}
+DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu);
 
 /*
  * The wallclock is the time of day when we booted. Since then, some time may

arch/x86/kernel/setup_percpu.c

@@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-	memblock_free(__pa(ptr), size);
+	memblock_free_ptr(ptr, size);
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)

arch/x86/kvm/cpuid.c

@@ -65,8 +65,8 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find(
 	for (i = 0; i < nent; i++) {
 		e = &entries[i];
 
-		if (e->function == function && (e->index == index ||
-		    !(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX)))
+		if (e->function == function &&
+		    (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index))
 			return e;
 	}
 

arch/x86/kvm/emulate.c

@@ -4206,7 +4206,7 @@ static int check_rdtsc(struct x86_emulate_ctxt *ctxt)
 	u64 cr4 = ctxt->ops->get_cr(ctxt, 4);
 
 	if (cr4 & X86_CR4_TSD && ctxt->ops->cpl(ctxt))
-		return emulate_ud(ctxt);
+		return emulate_gp(ctxt, 0);
 
 	return X86EMUL_CONTINUE;
 }

arch/x86/kvm/hyperv.c

@@ -939,7 +939,7 @@ static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
 	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
 		stimer_init(&hv_vcpu->stimer[i], i);
 
-	hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu);
+	hv_vcpu->vp_index = vcpu->vcpu_idx;
 
 	return 0;
 }
@@ -1444,7 +1444,6 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 	switch (msr) {
 	case HV_X64_MSR_VP_INDEX: {
 		struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
-		int vcpu_idx = kvm_vcpu_get_idx(vcpu);
 		u32 new_vp_index = (u32)data;
 
 		if (!host || new_vp_index >= KVM_MAX_VCPUS)
@@ -1459,9 +1458,9 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 		 * VP index is changing, adjust num_mismatched_vp_indexes if
 		 * it now matches or no longer matches vcpu_idx.
 		 */
-		if (hv_vcpu->vp_index == vcpu_idx)
+		if (hv_vcpu->vp_index == vcpu->vcpu_idx)
 			atomic_inc(&hv->num_mismatched_vp_indexes);
-		else if (new_vp_index == vcpu_idx)
+		else if (new_vp_index == vcpu->vcpu_idx)
 			atomic_dec(&hv->num_mismatched_vp_indexes);
 
 		hv_vcpu->vp_index = new_vp_index;

arch/x86/kvm/hyperv.h

@@ -83,7 +83,7 @@ static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 
-	return hv_vcpu ? hv_vcpu->vp_index : kvm_vcpu_get_idx(vcpu);
+	return hv_vcpu ? hv_vcpu->vp_index : vcpu->vcpu_idx;
 }
 
 int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);

arch/x86/kvm/ioapic.c

@@ -319,8 +319,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 	unsigned index;
 	bool mask_before, mask_after;
 	union kvm_ioapic_redirect_entry *e;
-	unsigned long vcpu_bitmap;
 	int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode;
+	DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
 
 	switch (ioapic->ioregsel) {
 	case IOAPIC_REG_VERSION:
@@ -384,9 +384,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 			irq.shorthand = APIC_DEST_NOSHORT;
 			irq.dest_id = e->fields.dest_id;
 			irq.msi_redir_hint = false;
-			bitmap_zero(&vcpu_bitmap, 16);
+			bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
 			kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
-						 &vcpu_bitmap);
+						 vcpu_bitmap);
 			if (old_dest_mode != e->fields.dest_mode ||
 			    old_dest_id != e->fields.dest_id) {
 				/*
@@ -399,10 +399,10 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 				    kvm_lapic_irq_dest_mode(
 					!!e->fields.dest_mode);
 				kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
-							 &vcpu_bitmap);
+							 vcpu_bitmap);
 			}
 			kvm_make_scan_ioapic_request_mask(ioapic->kvm,
-							  &vcpu_bitmap);
+							  vcpu_bitmap);
 		} else {
 			kvm_make_scan_ioapic_request(ioapic->kvm);
 		}

arch/x86/kvm/mmu/mmu.c

@@ -2027,8 +2027,8 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents)
 	} while (!sp->unsync_children);
 }
 
-static void mmu_sync_children(struct kvm_vcpu *vcpu,
-			      struct kvm_mmu_page *parent)
+static int mmu_sync_children(struct kvm_vcpu *vcpu,
+			     struct kvm_mmu_page *parent, bool can_yield)
 {
 	int i;
 	struct kvm_mmu_page *sp;
@@ -2055,12 +2055,18 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu,
 		}
 		if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) {
 			kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+			if (!can_yield) {
+				kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
+				return -EINTR;
+			}
+
 			cond_resched_rwlock_write(&vcpu->kvm->mmu_lock);
 			flush = false;
 		}
 	}
 
 	kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+	return 0;
 }
 
 static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
@@ -2146,9 +2152,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 		}
 
-		if (sp->unsync_children)
-			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
-
 		__clear_sp_write_flooding_count(sp);
 
 trace_get_page:
@@ -3684,7 +3687,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 		write_lock(&vcpu->kvm->mmu_lock);
 		kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
 
-		mmu_sync_children(vcpu, sp);
+		mmu_sync_children(vcpu, sp, true);
 
 		kvm_mmu_audit(vcpu, AUDIT_POST_SYNC);
 		write_unlock(&vcpu->kvm->mmu_lock);
@@ -3700,7 +3703,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 		if (IS_VALID_PAE_ROOT(root)) {
 			root &= PT64_BASE_ADDR_MASK;
 			sp = to_shadow_page(root);
-			mmu_sync_children(vcpu, sp);
+			mmu_sync_children(vcpu, sp, true);
 		}
 	}
 

arch/x86/kvm/mmu/page_track.c

@@ -164,13 +164,13 @@ void kvm_page_track_cleanup(struct kvm *kvm)
 	cleanup_srcu_struct(&head->track_srcu);
 }
 
-void kvm_page_track_init(struct kvm *kvm)
+int kvm_page_track_init(struct kvm *kvm)
 {
 	struct kvm_page_track_notifier_head *head;
 
 	head = &kvm->arch.track_notifier_head;
-	init_srcu_struct(&head->track_srcu);
 	INIT_HLIST_HEAD(&head->track_notifier_list);
+	return init_srcu_struct(&head->track_srcu);
 }
 
 /*

arch/x86/kvm/mmu/paging_tmpl.h

@@ -707,8 +707,27 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 		if (!is_shadow_present_pte(*it.sptep)) {
 			table_gfn = gw->table_gfn[it.level - 2];
 			access = gw->pt_access[it.level - 2];
-			sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1,
-					      false, access);
+			sp = kvm_mmu_get_page(vcpu, table_gfn, addr,
+					      it.level-1, false, access);
+			/*
+			 * We must synchronize the pagetable before linking it
+			 * because the guest doesn't need to flush tlb when
+			 * the gpte is changed from non-present to present.
+			 * Otherwise, the guest may use the wrong mapping.
+			 *
+			 * For PG_LEVEL_4K, kvm_mmu_get_page() has already
+			 * synchronized it transiently via kvm_sync_page().
+			 *
+			 * For higher level pagetable, we synchronize it via
+			 * the slower mmu_sync_children().  If it needs to
+			 * break, some progress has been made; return
+			 * RET_PF_RETRY and retry on the next #PF.
+			 * KVM_REQ_MMU_SYNC is not necessary but it
+			 * expedites the process.
+			 */
+			if (sp->unsync_children &&
+			    mmu_sync_children(vcpu, sp, false))
+				return RET_PF_RETRY;
 		}
 
 		/*
@@ -1047,14 +1066,6 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr,
  * Using the cached information from sp->gfns is safe because:
  * - The spte has a reference to the struct page, so the pfn for a given gfn
  *   can't change unless all sptes pointing to it are nuked first.
- *
- * Note:
- *   We should flush all tlbs if spte is dropped even though guest is
- *   responsible for it. Since if we don't, kvm_mmu_notifier_invalidate_page
- *   and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't
- *   used by guest then tlbs are not flushed, so guest is allowed to access the
- *   freed pages.
- *   And we increase kvm->tlbs_dirty to delay tlbs flush in this case.
  */
 static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
@@ -1107,13 +1118,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 			return 0;
 
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
-			/*
-			 * Update spte before increasing tlbs_dirty to make
-			 * sure no tlb flush is lost after spte is zapped; see
-			 * the comments in kvm_flush_remote_tlbs().
-			 */
-			smp_wmb();
-			vcpu->kvm->tlbs_dirty++;
+			set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
 			continue;
 		}
 
@@ -1128,12 +1133,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		if (gfn != sp->gfns[i]) {
 			drop_spte(vcpu->kvm, &sp->spt[i]);
-			/*
-			 * The same as above where we are doing
-			 * prefetch_invalid_gpte().
-			 */
-			smp_wmb();
-			vcpu->kvm->tlbs_dirty++;
+			set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
 			continue;
 		}
 

arch/x86/kvm/svm/nested.c

@@ -545,7 +545,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 		(svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) |
 		(svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits);
 
-	svm->vmcb->control.virt_ext            = svm->nested.ctl.virt_ext;
 	svm->vmcb->control.int_vector          = svm->nested.ctl.int_vector;
 	svm->vmcb->control.int_state           = svm->nested.ctl.int_state;
 	svm->vmcb->control.event_inj           = svm->nested.ctl.event_inj;
@@ -579,7 +578,7 @@ static void nested_svm_copy_common_state(struct vmcb *from_vmcb, struct vmcb *to
 }
 
 int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
-			 struct vmcb *vmcb12)
+			 struct vmcb *vmcb12, bool from_vmrun)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	int ret;
@@ -609,13 +608,16 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
 	nested_vmcb02_prepare_save(svm, vmcb12);
 
 	ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3,
-				  nested_npt_enabled(svm), true);
+				  nested_npt_enabled(svm), from_vmrun);
 	if (ret)
 		return ret;
 
 	if (!npt_enabled)
 		vcpu->arch.mmu->inject_page_fault = svm_inject_page_fault_nested;
 
+	if (!from_vmrun)
+		kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+
 	svm_set_gif(svm, true);
 
 	return 0;
@@ -681,7 +683,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 
 	svm->nested.nested_run_pending = 1;
 
-	if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12))
+	if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true))
 		goto out_exit_err;
 
 	if (nested_svm_vmrun_msrpm(svm))

arch/x86/kvm/svm/sev.c

@@ -595,20 +595,12 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 	return 0;
 }
 
-static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
+static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
+				    int *error)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_launch_update_vmsa vmsa;
-	struct kvm_vcpu *vcpu;
-	int i, ret;
-
-	if (!sev_es_guest(kvm))
-		return -ENOTTY;
-
-	vmsa.reserved = 0;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	int ret;
 
 	/* Perform some pre-encryption checks against the VMSA */
 	ret = sev_es_sync_vmsa(svm);
@@ -616,22 +608,37 @@ static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
 		return ret;
 
 	/*
-		 * The LAUNCH_UPDATE_VMSA command will perform in-place
-		 * encryption of the VMSA memory content (i.e it will write
-		 * the same memory region with the guest's key), so invalidate
-		 * it first.
+	 * The LAUNCH_UPDATE_VMSA command will perform in-place encryption of
+	 * the VMSA memory content (i.e it will write the same memory region
+	 * with the guest's key), so invalidate it first.
 	 */
 	clflush_cache_range(svm->vmsa, PAGE_SIZE);
 
-		vmsa.handle = sev->handle;
+	vmsa.reserved = 0;
+	vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
 	vmsa.address = __sme_pa(svm->vmsa);
 	vmsa.len = PAGE_SIZE;
-		ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa,
-				    &argp->error);
+	return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+}
+
+static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_vcpu *vcpu;
+	int i, ret;
+
+	if (!sev_es_guest(kvm))
+		return -ENOTTY;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		ret = mutex_lock_killable(&vcpu->mutex);
 		if (ret)
 			return ret;
 
-		svm->vcpu.arch.guest_state_protected = true;
+		ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error);
+
+		mutex_unlock(&vcpu->mutex);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -1397,8 +1404,10 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	/* Bind ASID to this guest */
 	ret = sev_bind_asid(kvm, start.handle, error);
-	if (ret)
+	if (ret) {
+		sev_decommission(start.handle);
 		goto e_free_session;
+	}
 
 	params.handle = start.handle;
 	if (copy_to_user((void __user *)(uintptr_t)argp->data,
@@ -1464,7 +1473,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	/* Pin guest memory */
 	guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
-				    PAGE_SIZE, &n, 0);
+				    PAGE_SIZE, &n, 1);
 	if (IS_ERR(guest_page)) {
 		ret = PTR_ERR(guest_page);
 		goto e_free_trans;
@@ -1501,6 +1510,20 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
 }
 
+static bool cmd_allowed_from_miror(u32 cmd_id)
+{
+	/*
+	 * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES
+	 * active mirror VMs. Also allow the debugging and status commands.
+	 */
+	if (cmd_id == KVM_SEV_LAUNCH_UPDATE_VMSA ||
+	    cmd_id == KVM_SEV_GUEST_STATUS || cmd_id == KVM_SEV_DBG_DECRYPT ||
+	    cmd_id == KVM_SEV_DBG_ENCRYPT)
+		return true;
+
+	return false;
+}
+
 int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;
@@ -1517,8 +1540,9 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 
 	mutex_lock(&kvm->lock);
 
-	/* enc_context_owner handles all memory enc operations */
-	if (is_mirroring_enc_context(kvm)) {
+	/* Only the enc_context_owner handles some memory enc operations. */
+	if (is_mirroring_enc_context(kvm) &&
+	    !cmd_allowed_from_miror(sev_cmd.id)) {
 		r = -EINVAL;
 		goto out;
 	}
@@ -1715,8 +1739,7 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 {
 	struct file *source_kvm_file;
 	struct kvm *source_kvm;
-	struct kvm_sev_info *mirror_sev;
-	unsigned int asid;
+	struct kvm_sev_info source_sev, *mirror_sev;
 	int ret;
 
 	source_kvm_file = fget(source_fd);
@@ -1739,7 +1762,8 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 		goto e_source_unlock;
 	}
 
-	asid = to_kvm_svm(source_kvm)->sev_info.asid;
+	memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info,
+	       sizeof(source_sev));
 
 	/*
 	 * The mirror kvm holds an enc_context_owner ref so its asid can't
@@ -1759,8 +1783,16 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 	/* Set enc_context_owner and copy its encryption context over */
 	mirror_sev = &to_kvm_svm(kvm)->sev_info;
 	mirror_sev->enc_context_owner = source_kvm;
-	mirror_sev->asid = asid;
 	mirror_sev->active = true;
+	mirror_sev->asid = source_sev.asid;
+	mirror_sev->fd = source_sev.fd;
+	mirror_sev->es_active = source_sev.es_active;
+	mirror_sev->handle = source_sev.handle;
+	/*
+	 * Do not copy ap_jump_table. Since the mirror does not share the same
+	 * KVM contexts as the original, and they may have different
+	 * memory-views.
+	 */
 
 	mutex_unlock(&kvm->lock);
 	return 0;

arch/x86/kvm/svm/svm.c

@@ -1566,6 +1566,8 @@ static void svm_clear_vintr(struct vcpu_svm *svm)
 
 		svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl &
 			V_IRQ_INJECTION_BITS_MASK;
+
+		svm->vmcb->control.int_vector = svm->nested.ctl.int_vector;
 	}
 
 	vmcb_mark_dirty(svm->vmcb, VMCB_INTR);
@@ -2222,6 +2224,10 @@ static int gp_interception(struct kvm_vcpu *vcpu)
 	if (error_code)
 		goto reinject;
 
+	/* All SVM instructions expect page aligned RAX */
+	if (svm->vmcb->save.rax & ~PAGE_MASK)
+		goto reinject;
+
 	/* Decode the instruction for usage later */
 	if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK)
 		goto reinject;
@@ -4285,7 +4291,9 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 	struct kvm_host_map map_save;
 	int ret;
 
-	if (is_guest_mode(vcpu)) {
+	if (!is_guest_mode(vcpu))
+		return 0;
+
 	/* FED8h - SVM Guest */
 	put_smstate(u64, smstate, 0x7ed8, 1);
 	/* FEE0h - SVM Guest VMCB Physical Address */
@@ -4321,7 +4329,6 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 			     &svm->vmcb01.ptr->save);
 
 	kvm_vcpu_unmap(vcpu, &map_save, true);
-	}
 	return 0;
 }
 
@@ -4329,50 +4336,54 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct kvm_host_map map, map_save;
-	int ret = 0;
-
-	if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
-		u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
-		u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
-		u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
+	u64 saved_efer, vmcb12_gpa;
 	struct vmcb *vmcb12;
+	int ret;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+		return 0;
+
+	/* Non-zero if SMI arrived while vCPU was in guest mode. */
+	if (!GET_SMSTATE(u64, smstate, 0x7ed8))
+		return 0;
 
-		if (guest) {
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
 		return 1;
 
+	saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
 	if (!(saved_efer & EFER_SVME))
 		return 1;
 
-			if (kvm_vcpu_map(vcpu,
-					 gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
+	vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
 		return 1;
 
+	ret = 1;
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL)
+		goto unmap_map;
+
 	if (svm_allocate_nested(svm))
-				return 1;
-
-			vmcb12 = map.hva;
-
-			nested_load_control_from_vmcb12(svm, &vmcb12->control);
-
-			ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12);
-			kvm_vcpu_unmap(vcpu, &map, true);
+		goto unmap_save;
 
 	/*
 	 * Restore L1 host state from L1 HSAVE area as VMCB01 was
 	 * used during SMM (see svm_enter_smm())
 	 */
-			if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
-					 &map_save) == -EINVAL)
-				return 1;
 
-			svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
-					     map_save.hva + 0x400);
+	svm_copy_vmrun_state(&svm->vmcb01.ptr->save, map_save.hva + 0x400);
 
+	/*
+	 * Enter the nested guest now
+	 */
+
+	vmcb12 = map.hva;
+	nested_load_control_from_vmcb12(svm, &vmcb12->control);
+	ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false);
+
+unmap_save:
 	kvm_vcpu_unmap(vcpu, &map_save, true);
-		}
-	}
-
+unmap_map:
+	kvm_vcpu_unmap(vcpu, &map, true);
 	return ret;
 }
 

arch/x86/kvm/svm/svm.h

@@ -459,7 +459,8 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm)
 	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI);
 }
 
-int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12);
+int enter_svm_guest_mode(struct kvm_vcpu *vcpu,
+			 u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun);
 void svm_leave_nested(struct vcpu_svm *svm);
 void svm_free_nested(struct vcpu_svm *svm);
 int svm_allocate_nested(struct vcpu_svm *svm);

arch/x86/kvm/vmx/evmcs.c

@@ -353,14 +353,20 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata)
 	switch (msr_index) {
 	case MSR_IA32_VMX_EXIT_CTLS:
 	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
-		ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+		ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
 		break;
 	case MSR_IA32_VMX_ENTRY_CTLS:
 	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
-		ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+		ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
 		break;
 	case MSR_IA32_VMX_PROCBASED_CTLS2:
-		ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+		ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
+		break;
+	case MSR_IA32_VMX_PINBASED_CTLS:
+		ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+		break;
+	case MSR_IA32_VMX_VMFUNC:
+		ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC;
 		break;
 	}
 

arch/x86/kvm/vmx/nested.c

@@ -2583,8 +2583,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * Guest state is invalid and unrestricted guest is disabled,
 	 * which means L1 attempted VMEntry to L2 with invalid state.
 	 * Fail the VMEntry.
+	 *
+	 * However when force loading the guest state (SMM exit or
+	 * loading nested state after migration, it is possible to
+	 * have invalid guest state now, which will be later fixed by
+	 * restoring L2 register state
 	 */
-	if (CC(!vmx_guest_state_valid(vcpu))) {
+	if (CC(from_vmentry && !vmx_guest_state_valid(vcpu))) {
 		*entry_failure_code = ENTRY_FAIL_DEFAULT;
 		return -EINVAL;
 	}
@@ -4351,6 +4356,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
 				vmcs12->vm_exit_msr_load_count))
 		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
+
+	to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
 }
 
 static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
@@ -4899,14 +4906,7 @@ out_vmcs02:
 	return -ENOMEM;
 }
 
-/*
- * Emulate the VMXON instruction.
- * Currently, we just remember that VMX is active, and do not save or even
- * inspect the argument to VMXON (the so-called "VMXON pointer") because we
- * do not currently need to store anything in that guest-allocated memory
- * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their
- * argument is different from the VMXON pointer (which the spec says they do).
- */
+/* Emulate the VMXON instruction. */
 static int handle_vmon(struct kvm_vcpu *vcpu)
 {
 	int ret;
@@ -5903,6 +5903,12 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 	case EXIT_REASON_VMFUNC:
 		/* VM functions are emulated through L2->L0 vmexits. */
 		return true;
+	case EXIT_REASON_BUS_LOCK:
+		/*
+		 * At present, bus lock VM exit is never exposed to L1.
+		 * Handle L2's bus locks in L0 directly.
+		 */
+		return true;
 	default:
 		break;
 	}

arch/x86/kvm/vmx/vmx.c

@@ -1323,7 +1323,7 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 	vmx_prepare_switch_to_host(to_vmx(vcpu));
 }
 
-static bool emulation_required(struct kvm_vcpu *vcpu)
+bool vmx_emulation_required(struct kvm_vcpu *vcpu)
 {
 	return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu);
 }
@@ -1367,7 +1367,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	vmcs_writel(GUEST_RFLAGS, rflags);
 
 	if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM)
-		vmx->emulation_required = emulation_required(vcpu);
+		vmx->emulation_required = vmx_emulation_required(vcpu);
 }
 
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
@@ -1837,10 +1837,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 				    &msr_info->data))
 			return 1;
 		/*
-		 * Enlightened VMCS v1 doesn't have certain fields, but buggy
-		 * Hyper-V versions are still trying to use corresponding
-		 * features when they are exposed. Filter out the essential
-		 * minimum.
+		 * Enlightened VMCS v1 doesn't have certain VMCS fields but
+		 * instead of just ignoring the features, different Hyper-V
+		 * versions are either trying to use them and fail or do some
+		 * sanity checking and refuse to boot. Filter all unsupported
+		 * features out.
 		 */
 		if (!msr_info->host_initiated &&
 		    vmx->nested.enlightened_vmcs_enabled)
@@ -3077,7 +3078,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	}
 
 	/* depends on vcpu->arch.cr0 to be set to a new value */
-	vmx->emulation_required = emulation_required(vcpu);
+	vmx->emulation_required = vmx_emulation_required(vcpu);
 }
 
 static int vmx_get_max_tdp_level(void)
@@ -3330,7 +3331,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int
 {
 	__vmx_set_segment(vcpu, var, seg);
 
-	to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
+	to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
 }
 
 static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
@@ -6621,10 +6622,24 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		     vmx->loaded_vmcs->soft_vnmi_blocked))
 		vmx->loaded_vmcs->entry_time = ktime_get();
 
-	/* Don't enter VMX if guest state is invalid, let the exit handler
-	   start emulation until we arrive back to a valid state */
-	if (vmx->emulation_required)
+	/*
+	 * Don't enter VMX if guest state is invalid, let the exit handler
+	 * start emulation until we arrive back to a valid state.  Synthesize a
+	 * consistency check VM-Exit due to invalid guest state and bail.
+	 */
+	if (unlikely(vmx->emulation_required)) {
+
+		/* We don't emulate invalid state of a nested guest */
+		vmx->fail = is_guest_mode(vcpu);
+
+		vmx->exit_reason.full = EXIT_REASON_INVALID_STATE;
+		vmx->exit_reason.failed_vmentry = 1;
+		kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1);
+		vmx->exit_qualification = ENTRY_FAIL_DEFAULT;
+		kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2);
+		vmx->exit_intr_info = 0;
 		return EXIT_FASTPATH_NONE;
+	}
 
 	trace_kvm_entry(vcpu);
 
@@ -6833,7 +6848,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 		 */
 		tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL);
 		if (tsx_ctrl)
-			vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
+			tsx_ctrl->mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
 	}
 
 	err = alloc_loaded_vmcs(&vmx->vmcs01);

arch/x86/kvm/vmx/vmx.h

@@ -248,12 +248,8 @@ struct vcpu_vmx {
 	 * only loaded into hardware when necessary, e.g. SYSCALL #UDs outside
 	 * of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to
 	 * be loaded into hardware if those conditions aren't met.
-	 * nr_active_uret_msrs tracks the number of MSRs that need to be loaded
-	 * into hardware when running the guest.  guest_uret_msrs[] is resorted
-	 * whenever the number of "active" uret MSRs is modified.
 	 */
 	struct vmx_uret_msr   guest_uret_msrs[MAX_NR_USER_RETURN_MSRS];
-	int                   nr_active_uret_msrs;
 	bool                  guest_uret_msrs_loaded;
 #ifdef CONFIG_X86_64
 	u64		      msr_host_kernel_gs_base;
@@ -359,6 +355,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
 void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
 			unsigned long fs_base, unsigned long gs_base);
 int vmx_get_cpl(struct kvm_vcpu *vcpu);
+bool vmx_emulation_required(struct kvm_vcpu *vcpu);
 unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu);
 void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu);

arch/x86/kvm/x86.c

@@ -1332,6 +1332,13 @@ static const u32 msrs_to_save_all[] = {
 	MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
+
+	MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3,
+	MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3,
+	MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2,
+	MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5,
+	MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2,
+	MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5,
 };
 
 static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
@@ -2969,7 +2976,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 				       offsetof(struct compat_vcpu_info, time));
 	if (vcpu->xen.vcpu_time_info_set)
 		kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0);
-	if (v == kvm_get_vcpu(v->kvm, 0))
+	if (!v->vcpu_idx)
 		kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
 	return 0;
 }
@@ -7658,6 +7665,13 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
 
 		/* Process a latched INIT or SMI, if any.  */
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+		/*
+		 * Even if KVM_SET_SREGS2 loaded PDPTRs out of band,
+		 * on SMM exit we still need to reload them from
+		 * guest memory
+		 */
+		vcpu->arch.pdptrs_from_userspace = false;
 	}
 
 	kvm_mmu_reset_context(vcpu);
@@ -10652,6 +10666,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	int r;
 
 	vcpu->arch.last_vmentry_cpu = -1;
+	vcpu->arch.regs_avail = ~0;
+	vcpu->arch.regs_dirty = ~0;
 
 	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -10893,6 +10909,9 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
 	kvm_rip_write(vcpu, 0xfff0);
 
+	vcpu->arch.cr3 = 0;
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);
+
 	/*
 	 * CR0.CD/NW are set on RESET, preserved on INIT.  Note, some versions
 	 * of Intel's SDM list CD/NW as being set on INIT, but they contradict
@@ -11139,9 +11158,15 @@ void kvm_arch_free_vm(struct kvm *kvm)
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
+	int ret;
+
 	if (type)
 		return -EINVAL;
 
+	ret = kvm_page_track_init(kvm);
+	if (ret)
+		return ret;
+
 	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
@@ -11174,7 +11199,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	kvm_apicv_init(kvm);
 	kvm_hv_init_vm(kvm);
-	kvm_page_track_init(kvm);
 	kvm_mmu_init_vm(kvm);
 	kvm_xen_init_vm(kvm);
 

arch/x86/mm/init_64.c

@@ -1432,18 +1432,18 @@ int kern_addr_valid(unsigned long addr)
 		return 0;
 
 	p4d = p4d_offset(pgd, addr);
-	if (p4d_none(*p4d))
+	if (!p4d_present(*p4d))
 		return 0;
 
 	pud = pud_offset(p4d, addr);
-	if (pud_none(*pud))
+	if (!pud_present(*pud))
 		return 0;
 
 	if (pud_large(*pud))
 		return pfn_valid(pud_pfn(*pud));
 
 	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	if (!pmd_present(*pmd))
 		return 0;
 
 	if (pmd_large(*pmd))

arch/x86/mm/kasan_init_64.c

@@ -49,8 +49,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
 			p = early_alloc(PMD_SIZE, nid, false);
 			if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
 				return;
-			else if (p)
-				memblock_free(__pa(p), PMD_SIZE);
+			memblock_free_ptr(p, PMD_SIZE);
 		}
 
 		p = early_alloc(PAGE_SIZE, nid, true);
@@ -86,8 +85,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
 			p = early_alloc(PUD_SIZE, nid, false);
 			if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL))
 				return;
-			else if (p)
-				memblock_free(__pa(p), PUD_SIZE);
+			memblock_free_ptr(p, PUD_SIZE);
 		}
 
 		p = early_alloc(PAGE_SIZE, nid, true);

arch/x86/mm/numa.c

@@ -355,7 +355,7 @@ void __init numa_reset_distance(void)
 
 	/* numa_distance could be 1LU marking allocation failure, test cnt */
 	if (numa_distance_cnt)
-		memblock_free(__pa(numa_distance), size);
+		memblock_free_ptr(numa_distance, size);
 	numa_distance_cnt = 0;
 	numa_distance = NULL;	/* enable table creation */
 }

arch/x86/mm/numa_emulation.c

@@ -517,8 +517,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	}
 
 	/* free the copied physical distance table */
-	if (phys_dist)
-		memblock_free(__pa(phys_dist), phys_size);
+	memblock_free_ptr(phys_dist, phys_size);
 	return;
 
 no_emu:

arch/x86/mm/pat/memtype.c

@@ -583,7 +583,12 @@ int memtype_reserve(u64 start, u64 end, enum page_cache_mode req_type,
 	int err = 0;
 
 	start = sanitize_phys(start);
-	end = sanitize_phys(end);
+
+	/*
+	 * The end address passed into this function is exclusive, but
+	 * sanitize_phys() expects an inclusive address.
+	 */
+	end = sanitize_phys(end - 1) + 1;
 	if (start >= end) {
 		WARN(1, "%s failed: [mem %#010Lx-%#010Lx], req %s\n", __func__,
 				start, end - 1, cattr_name(req_type));

arch/x86/xen/enlighten_pv.c

@@ -1214,6 +1214,11 @@ static void __init xen_dom0_set_legacy_features(void)
 	x86_platform.legacy.rtc = 1;
 }
 
+static void __init xen_domu_set_legacy_features(void)
+{
+	x86_platform.legacy.rtc = 0;
+}
+
 /* First C function to be called on Xen boot */
 asmlinkage __visible void __init xen_start_kernel(void)
 {
@@ -1359,6 +1364,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 		add_preferred_console("xenboot", 0, NULL);
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
+		x86_platform.set_legacy_features =
+				xen_domu_set_legacy_features;
 	} else {
 		const struct dom0_vga_console_info *info =
 			(void *)((char *)xen_start_info +

arch/x86/xen/mmu_pv.c

@@ -1518,14 +1518,17 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 	if (pinned) {
 		struct page *page = pfn_to_page(pfn);
 
-		if (static_branch_likely(&xen_struct_pages_ready))
+		pinned = false;
+		if (static_branch_likely(&xen_struct_pages_ready)) {
+			pinned = PagePinned(page);
 			SetPagePinned(page);
+		}
 
 		xen_mc_batch();
 
 		__set_pfn_prot(pfn, PAGE_KERNEL_RO);
 
-		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
+		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned)
 			__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 
 		xen_mc_issue(PARAVIRT_LAZY_MMU);

block/blk-cgroup.c

@@ -1182,10 +1182,6 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
-	ret = blk_iolatency_init(q);
-	if (ret)
-		goto err_destroy_all;
-
 	ret = blk_ioprio_init(q);
 	if (ret)
 		goto err_destroy_all;
@@ -1194,6 +1190,12 @@ int blkcg_init_queue(struct request_queue *q)
 	if (ret)
 		goto err_destroy_all;
 
+	ret = blk_iolatency_init(q);
+	if (ret) {
+		blk_throtl_exit(q);
+		goto err_destroy_all;
+	}
+
 	return 0;
 
 err_destroy_all:
@@ -1364,10 +1366,14 @@ enomem:
 	/* alloc failed, nothing's initialized yet, free everything */
 	spin_lock_irq(&q->queue_lock);
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
+		struct blkcg *blkcg = blkg->blkcg;
+
+		spin_lock(&blkcg->lock);
 		if (blkg->pd[pol->plid]) {
 			pol->pd_free_fn(blkg->pd[pol->plid]);
 			blkg->pd[pol->plid] = NULL;
 		}
+		spin_unlock(&blkcg->lock);
 	}
 	spin_unlock_irq(&q->queue_lock);
 	ret = -ENOMEM;
@@ -1399,12 +1405,16 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	__clear_bit(pol->plid, q->blkcg_pols);
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
+		struct blkcg *blkcg = blkg->blkcg;
+
+		spin_lock(&blkcg->lock);
 		if (blkg->pd[pol->plid]) {
 			if (pol->pd_offline_fn)
 				pol->pd_offline_fn(blkg->pd[pol->plid]);
 			pol->pd_free_fn(blkg->pd[pol->plid]);
 			blkg->pd[pol->plid] = NULL;
 		}
+		spin_unlock(&blkcg->lock);
 	}
 
 	spin_unlock_irq(&q->queue_lock);

block/blk-integrity.c

@@ -426,8 +426,15 @@ EXPORT_SYMBOL(blk_integrity_register);
  */
 void blk_integrity_unregister(struct gendisk *disk)
 {
+	struct blk_integrity *bi = &disk->queue->integrity;
+
+	if (!bi->profile)
+		return;
+
+	/* ensure all bios are off the integrity workqueue */
+	blk_flush_integrity();
 	blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
-	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
+	memset(bi, 0, sizeof(*bi));
 }
 EXPORT_SYMBOL(blk_integrity_unregister);
 

block/blk-mq-tag.c

@@ -208,7 +208,7 @@ static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags,
 
 	spin_lock_irqsave(&tags->lock, flags);
 	rq = tags->rqs[bitnr];
-	if (!rq || !refcount_inc_not_zero(&rq->ref))
+	if (!rq || rq->tag != bitnr || !refcount_inc_not_zero(&rq->ref))
 		rq = NULL;
 	spin_unlock_irqrestore(&tags->lock, flags);
 	return rq;

drivers/base/arch_numa.c

@@ -264,7 +264,7 @@ void __init numa_free_distance(void)
 	size = numa_distance_cnt * numa_distance_cnt *
 		sizeof(numa_distance[0]);
 
-	memblock_free(__pa(numa_distance), size);
+	memblock_free_ptr(numa_distance, size);
 	numa_distance_cnt = 0;
 	numa_distance = NULL;
 }

drivers/base/power/trace.c

@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/rtc.h>
 #include <linux/suspend.h>
+#include <linux/init.h>
 
 #include <linux/mc146818rtc.h>
 
@@ -165,6 +166,9 @@ void generate_pm_trace(const void *tracedata, unsigned int user)
 	const char *file = *(const char **)(tracedata + 2);
 	unsigned int user_hash_value, file_hash_value;
 
+	if (!x86_platform.legacy.rtc)
+		return;
+
 	user_hash_value = user % USERHASH;
 	file_hash_value = hash_string(lineno, file, FILEHASH);
 	set_magic_time(user_hash_value, file_hash_value, dev_hash_value);
@@ -267,6 +271,9 @@ static struct notifier_block pm_trace_nb = {
 
 static int __init early_resume_init(void)
 {
+	if (!x86_platform.legacy.rtc)
+		return 0;
+
 	hash_value_early_read = read_magic_time();
 	register_pm_notifier(&pm_trace_nb);
 	return 0;
@@ -277,6 +284,9 @@ static int __init late_resume_init(void)
 	unsigned int val = hash_value_early_read;
 	unsigned int user, file, dev;
 
+	if (!x86_platform.legacy.rtc)
+		return 0;
+
 	user = val % USERHASH;
 	val = val / USERHASH;
 	file = val % FILEHASH;

drivers/cpufreq/cpufreq_governor_attr_set.c

@@ -74,8 +74,8 @@ unsigned int gov_attr_set_put(struct gov_attr_set *attr_set, struct list_head *l
 	if (count)
 		return count;
 
-	kobject_put(&attr_set->kobj);
 	mutex_destroy(&attr_set->update_lock);
+	kobject_put(&attr_set->kobj);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(gov_attr_set_put);

drivers/cpufreq/intel_pstate.c

@@ -3205,11 +3205,15 @@ static int __init intel_pstate_init(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return -ENODEV;
 
-	if (no_load)
-		return -ENODEV;
-
 	id = x86_match_cpu(hwp_support_ids);
 	if (id) {
+		bool hwp_forced = intel_pstate_hwp_is_enabled();
+
+		if (hwp_forced)
+			pr_info("HWP enabled by BIOS\n");
+		else if (no_load)
+			return -ENODEV;
+
 		copy_cpu_funcs(&core_funcs);
 		/*
 		 * Avoid enabling HWP for processors without EPP support,
@@ -3219,8 +3223,7 @@ static int __init intel_pstate_init(void)
 		 * If HWP is enabled already, though, there is no choice but to
 		 * deal with it.
 		 */
-		if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) ||
-		    intel_pstate_hwp_is_enabled()) {
+		if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) || hwp_forced) {
 			hwp_active++;
 			hwp_mode_bdw = id->driver_data;
 			intel_pstate.attr = hwp_cpufreq_attrs;
@@ -3235,7 +3238,11 @@ static int __init intel_pstate_init(void)
 
 			goto hwp_cpu_matched;
 		}
+		pr_info("HWP not enabled\n");
 	} else {
+		if (no_load)
+			return -ENODEV;
+
 		id = x86_match_cpu(intel_pstate_cpu_ids);
 		if (!id) {
 			pr_info("CPU model not supported\n");
@@ -3314,10 +3321,9 @@ static int __init intel_pstate_setup(char *str)
 	else if (!strcmp(str, "passive"))
 		default_driver = &intel_cpufreq;
 
-	if (!strcmp(str, "no_hwp")) {
-		pr_info("HWP disabled\n");
+	if (!strcmp(str, "no_hwp"))
 		no_hwp = 1;
-	}
+
 	if (!strcmp(str, "force"))
 		force_load = 1;
 	if (!strcmp(str, "hwp_only"))