Merge branch 'sched/urgent' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

49 files changed, 340 insertions, 216 deletions

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index c77c5d8a7b3e..307529417021 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -178,11 +178,6 @@ ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1)
 	KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,)
 endif
 
-ifdef CONFIG_LTO_CLANG
-KBUILD_LDFLAGS	+= -plugin-opt=-code-model=kernel \
-		   -plugin-opt=-stack-alignment=$(if $(CONFIG_X86_32),4,8)
-endif
-
 # Workaround for a gcc prelease that unfortunately was shipped in a suse release
 KBUILD_CFLAGS += -Wno-sign-compare
 #
@@ -202,7 +197,12 @@ ifdef CONFIG_RETPOLINE
   endif
 endif
 
-KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE)
+KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE)
+
+ifdef CONFIG_LTO_CLANG
+KBUILD_LDFLAGS	+= -plugin-opt=-code-model=kernel \
+		   -plugin-opt=-stack-alignment=$(if $(CONFIG_X86_32),4,8)
+endif
 
 ifdef CONFIG_X86_NEED_RELOCS
 LDFLAGS_vmlinux := --emit-relocs --discard-none
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 6e5522aebbbd..431bf7f846c3 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -30,6 +30,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
 
 KBUILD_CFLAGS := -m$(BITS) -O2
 KBUILD_CFLAGS += -fno-strict-aliasing -fPIE
+KBUILD_CFLAGS += -Wundef
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small -mno-red-zone
@@ -48,10 +49,10 @@ KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no)
 KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
 KBUILD_CFLAGS += $(CLANG_FLAGS)
 
-# sev-es.c indirectly inludes inat-table.h which is generated during
+# sev.c indirectly inludes inat-table.h which is generated during
 # compilation and stored in $(objtree). Add the directory to the includes so
 # that the compiler finds it even with out-of-tree builds (make O=/some/path).
-CFLAGS_sev-es.o += -I$(objtree)/arch/x86/lib/
+CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
@@ -93,7 +94,7 @@ ifdef CONFIG_X86_64
 	vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o
 	vmlinux-objs-y += $(obj)/mem_encrypt.o
 	vmlinux-objs-y += $(obj)/pgtable_64.o
-	vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev-es.o
+	vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o
 endif
 
 vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index dde042f64cca..743f13ea25c1 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -172,7 +172,7 @@ void __puthex(unsigned long value)
 	}
 }
 
-#if CONFIG_X86_NEED_RELOCS
+#ifdef CONFIG_X86_NEED_RELOCS
 static void handle_relocations(void *output, unsigned long output_len,
 			       unsigned long virt_addr)
 {
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index e5612f035498..31139256859f 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -79,7 +79,7 @@ struct mem_vector {
 	u64 size;
 };
 
-#if CONFIG_RANDOMIZE_BASE
+#ifdef CONFIG_RANDOMIZE_BASE
 /* kaslr.c */
 void choose_random_location(unsigned long input,
 			    unsigned long input_size,
diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev.c
index 82041bd380e5..670e998fe930 100644
--- a/arch/x86/boot/compressed/sev-es.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -13,7 +13,7 @@
 #include "misc.h"
 
 #include <asm/pgtable_types.h>
-#include <asm/sev-es.h>
+#include <asm/sev.h>
 #include <asm/trapnr.h>
 #include <asm/trap_pf.h>
 #include <asm/msr-index.h>
@@ -117,7 +117,7 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 #include "../../lib/insn.c"
 
 /* Include code for early handlers */
-#include "../../kernel/sev-es-shared.c"
+#include "../../kernel/sev-shared.c"
 
 static bool early_setup_sev_es(void)
 {
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 28a1423ce32e..4bbc267fb36b 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -447,7 +447,7 @@
 440	i386	process_madvise		sys_process_madvise
 441	i386	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
 442	i386	mount_setattr		sys_mount_setattr
-443	i386	quotactl_path		sys_quotactl_path
+# 443 reserved for quotactl_path
 444	i386	landlock_create_ruleset	sys_landlock_create_ruleset
 445	i386	landlock_add_rule	sys_landlock_add_rule
 446	i386	landlock_restrict_self	sys_landlock_restrict_self
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index ecd551b08d05..ce18119ea0d0 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -364,7 +364,7 @@
 440	common	process_madvise		sys_process_madvise
 441	common	epoll_pwait2		sys_epoll_pwait2
 442	common	mount_setattr		sys_mount_setattr
-443	common	quotactl_path		sys_quotactl_path
+# 443 reserved for quotactl_path
 444	common	landlock_create_ruleset	sys_landlock_create_ruleset
 445	common	landlock_add_rule	sys_landlock_add_rule
 446	common	landlock_restrict_self	sys_landlock_restrict_self
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8e509325c2c3..8f71dd72ef95 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -396,10 +396,12 @@ int x86_reserve_hardware(void)
 	if (!atomic_inc_not_zero(&pmc_refcount)) {
 		mutex_lock(&pmc_reserve_mutex);
 		if (atomic_read(&pmc_refcount) == 0) {
-			if (!reserve_pmc_hardware())
+			if (!reserve_pmc_hardware()) {
 				err = -EBUSY;
-			else
+			} else {
 				reserve_ds_buffers();
+				reserve_lbr_buffers();
+			}
 		}
 		if (!err)
 			atomic_inc(&pmc_refcount);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2521d03de5e0..e28892270c58 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -6253,7 +6253,7 @@ __init int intel_pmu_init(void)
 	 * Check all LBT MSR here.
 	 * Disable LBR access if any LBR MSRs can not be accessed.
 	 */
-	if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL))
+	if (x86_pmu.lbr_tos && !check_msr(x86_pmu.lbr_tos, 0x3UL))
 		x86_pmu.lbr_nr = 0;
 	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) &&
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 76dbab6ac9fb..4409d2cccfda 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -658,7 +658,6 @@ static inline bool branch_user_callstack(unsigned br_sel)
 
 void intel_pmu_lbr_add(struct perf_event *event)
 {
-	struct kmem_cache *kmem_cache = event->pmu->task_ctx_cache;
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (!x86_pmu.lbr_nr)
@@ -696,11 +695,6 @@ void intel_pmu_lbr_add(struct perf_event *event)
 	perf_sched_cb_inc(event->ctx->pmu);
 	if (!cpuc->lbr_users++ && !event->total_time_running)
 		intel_pmu_lbr_reset();
-
-	if (static_cpu_has(X86_FEATURE_ARCH_LBR) &&
-	    kmem_cache && !cpuc->lbr_xsave &&
-	    (cpuc->lbr_users != cpuc->lbr_pebs_users))
-		cpuc->lbr_xsave = kmem_cache_alloc(kmem_cache, GFP_KERNEL);
 }
 
 void release_lbr_buffers(void)
@@ -722,6 +716,26 @@ void release_lbr_buffers(void)
 	}
 }
 
+void reserve_lbr_buffers(void)
+{
+	struct kmem_cache *kmem_cache;
+	struct cpu_hw_events *cpuc;
+	int cpu;
+
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
+		return;
+
+	for_each_possible_cpu(cpu) {
+		cpuc = per_cpu_ptr(&cpu_hw_events, cpu);
+		kmem_cache = x86_get_pmu(cpu)->task_ctx_cache;
+		if (!kmem_cache || cpuc->lbr_xsave)
+			continue;
+
+		cpuc->lbr_xsave = kmem_cache_alloc_node(kmem_cache, GFP_KERNEL,
+							cpu_to_node(cpu));
+	}
+}
+
 void intel_pmu_lbr_del(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 27fa85e7d4fd..ad87cb36f7c8 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1244,6 +1244,8 @@ void reserve_ds_buffers(void);
 
 void release_lbr_buffers(void);
 
+void reserve_lbr_buffers(void);
+
 extern struct event_constraint bts_constraint;
 extern struct event_constraint vlbr_constraint;
 
@@ -1393,6 +1395,10 @@ static inline void release_lbr_buffers(void)
 {
 }
 
+static inline void reserve_lbr_buffers(void)
+{
+}
+
 static inline int intel_pmu_init(void)
 {
 	return 0;
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 323641097f63..e7bef91cee04 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -99,6 +99,7 @@ KVM_X86_OP_NULL(post_block)
 KVM_X86_OP_NULL(vcpu_blocking)
 KVM_X86_OP_NULL(vcpu_unblocking)
 KVM_X86_OP_NULL(update_pi_irte)
+KVM_X86_OP_NULL(start_assignment)
 KVM_X86_OP_NULL(apicv_post_state_restore)
 KVM_X86_OP_NULL(dy_apicv_has_pending_interrupt)
 KVM_X86_OP_NULL(set_hv_timer)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 55efbacfc244..9c7ced0e3171 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1352,6 +1352,7 @@ struct kvm_x86_ops {
 
 	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
 			      uint32_t guest_irq, bool set);
+	void (*start_assignment)(struct kvm *kvm);
 	void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
 	bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 742d89a00721..211ba3375ee9 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -537,9 +537,9 @@
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1			0xc001001a
 #define MSR_K8_TOP_MEM2			0xc001001d
-#define MSR_K8_SYSCFG			0xc0010010
-#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT	23
-#define MSR_K8_SYSCFG_MEM_ENCRYPT	BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT)
+#define MSR_AMD64_SYSCFG		0xc0010010
+#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT	23
+#define MSR_AMD64_SYSCFG_MEM_ENCRYPT	BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT)
 #define MSR_K8_INT_PENDING_MSG		0xc0010055
 /* C1E active bits in int pending message */
 #define K8_INTP_C1E_ACTIVE_MASK		0x18000000
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 154321d29050..556b2b17c3e2 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -787,8 +787,10 @@ DECLARE_PER_CPU(u64, msr_misc_features_shadow);
 
 #ifdef CONFIG_CPU_SUP_AMD
 extern u32 amd_get_nodes_per_socket(void);
+extern u32 amd_get_highest_perf(void);
 #else
 static inline u32 amd_get_nodes_per_socket(void)	{ return 0; }
+static inline u32 amd_get_highest_perf(void)		{ return 0; }
 #endif
 
 static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
new file mode 100644
index 000000000000..629c3df243f0
--- /dev/null
+++ b/arch/x86/include/asm/sev-common.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AMD SEV header common between the guest and the hypervisor.
+ *
+ * Author: Brijesh Singh <brijesh.singh@amd.com>
+ */
+
+#ifndef __ASM_X86_SEV_COMMON_H
+#define __ASM_X86_SEV_COMMON_H
+
+#define GHCB_MSR_INFO_POS		0
+#define GHCB_MSR_INFO_MASK		(BIT_ULL(12) - 1)
+
+#define GHCB_MSR_SEV_INFO_RESP		0x001
+#define GHCB_MSR_SEV_INFO_REQ		0x002
+#define GHCB_MSR_VER_MAX_POS		48
+#define GHCB_MSR_VER_MAX_MASK		0xffff
+#define GHCB_MSR_VER_MIN_POS		32
+#define GHCB_MSR_VER_MIN_MASK		0xffff
+#define GHCB_MSR_CBIT_POS		24
+#define GHCB_MSR_CBIT_MASK		0xff
+#define GHCB_MSR_SEV_INFO(_max, _min, _cbit)				\
+	((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) |	\
+	 (((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) |	\
+	 (((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) |	\
+	 GHCB_MSR_SEV_INFO_RESP)
+#define GHCB_MSR_INFO(v)		((v) & 0xfffUL)
+#define GHCB_MSR_PROTO_MAX(v)		(((v) >> GHCB_MSR_VER_MAX_POS) & GHCB_MSR_VER_MAX_MASK)
+#define GHCB_MSR_PROTO_MIN(v)		(((v) >> GHCB_MSR_VER_MIN_POS) & GHCB_MSR_VER_MIN_MASK)
+
+#define GHCB_MSR_CPUID_REQ		0x004
+#define GHCB_MSR_CPUID_RESP		0x005
+#define GHCB_MSR_CPUID_FUNC_POS		32
+#define GHCB_MSR_CPUID_FUNC_MASK	0xffffffff
+#define GHCB_MSR_CPUID_VALUE_POS	32
+#define GHCB_MSR_CPUID_VALUE_MASK	0xffffffff
+#define GHCB_MSR_CPUID_REG_POS		30
+#define GHCB_MSR_CPUID_REG_MASK		0x3
+#define GHCB_CPUID_REQ_EAX		0
+#define GHCB_CPUID_REQ_EBX		1
+#define GHCB_CPUID_REQ_ECX		2
+#define GHCB_CPUID_REQ_EDX		3
+#define GHCB_CPUID_REQ(fn, reg)		\
+		(GHCB_MSR_CPUID_REQ | \
+		(((unsigned long)reg & GHCB_MSR_CPUID_REG_MASK) << GHCB_MSR_CPUID_REG_POS) | \
+		(((unsigned long)fn) << GHCB_MSR_CPUID_FUNC_POS))
+
+#define GHCB_MSR_TERM_REQ		0x100
+#define GHCB_MSR_TERM_REASON_SET_POS	12
+#define GHCB_MSR_TERM_REASON_SET_MASK	0xf
+#define GHCB_MSR_TERM_REASON_POS	16
+#define GHCB_MSR_TERM_REASON_MASK	0xff
+#define GHCB_SEV_TERM_REASON(reason_set, reason_val)						  \
+	(((((u64)reason_set) &  GHCB_MSR_TERM_REASON_SET_MASK) << GHCB_MSR_TERM_REASON_SET_POS) | \
+	((((u64)reason_val) & GHCB_MSR_TERM_REASON_MASK) << GHCB_MSR_TERM_REASON_POS))
+
+#define GHCB_SEV_ES_REASON_GENERAL_REQUEST	0
+#define GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED	1
+
+#define GHCB_RESP_CODE(v)		((v) & GHCB_MSR_INFO_MASK)
+
+#endif
diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev.h
index cf1d957c7091..fa5cd05d3b5b 100644
--- a/arch/x86/include/asm/sev-es.h
+++ b/arch/x86/include/asm/sev.h
@@ -10,34 +10,12 @@
 
 #include <linux/types.h>
 #include <asm/insn.h>
+#include <asm/sev-common.h>
 
-#define GHCB_SEV_INFO		0x001UL
-#define GHCB_SEV_INFO_REQ	0x002UL
-#define		GHCB_INFO(v)		((v) & 0xfffUL)
-#define		GHCB_PROTO_MAX(v)	(((v) >> 48) & 0xffffUL)
-#define		GHCB_PROTO_MIN(v)	(((v) >> 32) & 0xffffUL)
-#define		GHCB_PROTO_OUR		0x0001UL
-#define GHCB_SEV_CPUID_REQ	0x004UL
-#define		GHCB_CPUID_REQ_EAX	0
-#define		GHCB_CPUID_REQ_EBX	1
-#define		GHCB_CPUID_REQ_ECX	2
-#define		GHCB_CPUID_REQ_EDX	3
-#define		GHCB_CPUID_REQ(fn, reg) (GHCB_SEV_CPUID_REQ | \
-					(((unsigned long)reg & 3) << 30) | \
-					(((unsigned long)fn) << 32))
+#define GHCB_PROTO_OUR		0x0001UL
+#define GHCB_PROTOCOL_MAX	1ULL
+#define GHCB_DEFAULT_USAGE	0ULL
 
-#define	GHCB_PROTOCOL_MAX	0x0001UL
-#define GHCB_DEFAULT_USAGE	0x0000UL
-
-#define GHCB_SEV_CPUID_RESP	0x005UL
-#define GHCB_SEV_TERMINATE	0x100UL
-#define		GHCB_SEV_TERMINATE_REASON(reason_set, reason_val)	\
-			(((((u64)reason_set) &  0x7) << 12) |		\
-			 ((((u64)reason_val) & 0xff) << 16))
-#define		GHCB_SEV_ES_REASON_GENERAL_REQUEST	0
-#define		GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED	1
-
-#define	GHCB_SEV_GHCB_RESP_CODE(v)	((v) & 0xfff)
 #define	VMGEXIT()			{ asm volatile("rep; vmmcall\n\r"); }
 
 enum es_result {
diff --git a/arch/x86/include/asm/vdso/clocksource.h b/arch/x86/include/asm/vdso/clocksource.h
index 119ac8612d89..136e5e57cfe1 100644
--- a/arch/x86/include/asm/vdso/clocksource.h
+++ b/arch/x86/include/asm/vdso/clocksource.h
@@ -7,4 +7,6 @@
 	VDSO_CLOCKMODE_PVCLOCK,	\
 	VDSO_CLOCKMODE_HVCLOCK
 
+#define HAVE_VDSO_CLOCKMODE_HVCLOCK
+
 #endif /* __ASM_VDSO_CLOCKSOURCE_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 0704c2a94272..0f66682ac02a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -20,7 +20,7 @@ CFLAGS_REMOVE_kvmclock.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 CFLAGS_REMOVE_head64.o = -pg
-CFLAGS_REMOVE_sev-es.o = -pg
+CFLAGS_REMOVE_sev.o = -pg
 endif
 
 KASAN_SANITIZE_head$(BITS).o				:= n
@@ -28,7 +28,7 @@ KASAN_SANITIZE_dumpstack.o				:= n
 KASAN_SANITIZE_dumpstack_$(BITS).o			:= n
 KASAN_SANITIZE_stacktrace.o				:= n
 KASAN_SANITIZE_paravirt.o				:= n
-KASAN_SANITIZE_sev-es.o					:= n
+KASAN_SANITIZE_sev.o					:= n
 
 # With some compiler versions the generated code results in boot hangs, caused
 # by several compilation units. To be safe, disable all instrumentation.
@@ -148,7 +148,7 @@ obj-$(CONFIG_UNWINDER_ORC)		+= unwind_orc.o
 obj-$(CONFIG_UNWINDER_FRAME_POINTER)	+= unwind_frame.o
 obj-$(CONFIG_UNWINDER_GUESS)		+= unwind_guess.o
 
-obj-$(CONFIG_AMD_MEM_ENCRYPT)		+= sev-es.o
+obj-$(CONFIG_AMD_MEM_ENCRYPT)		+= sev.o
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 2d11384dc9ab..c06ac56eae4d 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -593,8 +593,8 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
 	 */
 	if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) {
 		/* Check if memory encryption is enabled */
-		rdmsrl(MSR_K8_SYSCFG, msr);
-		if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
+		rdmsrl(MSR_AMD64_SYSCFG, msr);
+		if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
 			goto clear_all;
 
 		/*
@@ -1165,3 +1165,19 @@ void set_dr_addr_mask(unsigned long mask, int dr)
 		break;
 	}
 }
+
+u32 amd_get_highest_perf(void)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) ||
+			       (c->x86_model >= 0x70 && c->x86_model < 0x80)))
+		return 166;
+
+	if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) ||
+			       (c->x86_model >= 0x40 && c->x86_model < 0x70)))
+		return 166;
+
+	return 255;
+}
+EXPORT_SYMBOL_GPL(amd_get_highest_perf);
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 0c3b372318b7..b5f43049fa5f 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -836,7 +836,7 @@ int __init amd_special_default_mtrr(void)
 	if (boot_cpu_data.x86 < 0xf)
 		return 0;
 	/* In case some hypervisor doesn't pass SYSCFG through: */
-	if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0)
+	if (rdmsr_safe(MSR_AMD64_SYSCFG, &l, &h) < 0)
 		return 0;
 	/*
 	 * Memory between 4GB and top of mem is forced WB by this magic bit.
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index b90f3f437765..558108296f3c 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -53,13 +53,13 @@ static inline void k8_check_syscfg_dram_mod_en(void)
 	      (boot_cpu_data.x86 >= 0x0f)))
 		return;
 
-	rdmsr(MSR_K8_SYSCFG, lo, hi);
+	rdmsr(MSR_AMD64_SYSCFG, lo, hi);
 	if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) {
 		pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]"
 		       " not cleared by BIOS, clearing this bit\n",
 		       smp_processor_id());
 		lo &= ~K8_MTRRFIXRANGE_DRAM_MODIFY;
-		mtrr_wrmsr(MSR_K8_SYSCFG, lo, hi);
+		mtrr_wrmsr(MSR_AMD64_SYSCFG, lo, hi);
 	}
 }
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 18be44163a50..de01903c3735 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -39,7 +39,7 @@
 #include <asm/realmode.h>
 #include <asm/extable.h>
 #include <asm/trapnr.h>
-#include <asm/sev-es.h>
+#include <asm/sev.h>
 
 /*
  * Manage page tables very early on.
diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index b5cb49e57df8..c94dec6a1834 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -95,7 +95,7 @@ static void get_fam10h_pci_mmconf_base(void)
 		return;
 
 	/* SYS_CFG */
-	address = MSR_K8_SYSCFG;
+	address = MSR_AMD64_SYSCFG;
 	rdmsrl(address, val);
 
 	/* TOP_MEM2 is not enabled? */
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 2ef961cf4cfc..4bce802d25fb 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -33,7 +33,7 @@
 #include <asm/reboot.h>
 #include <asm/cache.h>
 #include <asm/nospec-branch.h>
-#include <asm/sev-es.h>
+#include <asm/sev.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-shared.c
index 0aa9f13efd57..9f90f460a28c 100644
--- a/arch/x86/kernel/sev-es-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -26,13 +26,13 @@ static bool __init sev_es_check_cpu_features(void)
 
 static void __noreturn sev_es_terminate(unsigned int reason)
 {
-	u64 val = GHCB_SEV_TERMINATE;
+	u64 val = GHCB_MSR_TERM_REQ;
 
 	/*
 	 * Tell the hypervisor what went wrong - only reason-set 0 is
 	 * currently supported.
 	 */
-	val |= GHCB_SEV_TERMINATE_REASON(0, reason);
+	val |= GHCB_SEV_TERM_REASON(0, reason);
 
 	/* Request Guest Termination from Hypvervisor */
 	sev_es_wr_ghcb_msr(val);
@@ -47,15 +47,15 @@ static bool sev_es_negotiate_protocol(void)
 	u64 val;
 
 	/* Do the GHCB protocol version negotiation */
-	sev_es_wr_ghcb_msr(GHCB_SEV_INFO_REQ);
+	sev_es_wr_ghcb_msr(GHCB_MSR_SEV_INFO_REQ);
 	VMGEXIT();
 	val = sev_es_rd_ghcb_msr();
 
-	if (GHCB_INFO(val) != GHCB_SEV_INFO)
+	if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP)
 		return false;
 
-	if (GHCB_PROTO_MAX(val) < GHCB_PROTO_OUR ||
-	    GHCB_PROTO_MIN(val) > GHCB_PROTO_OUR)
+	if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTO_OUR ||
+	    GHCB_MSR_PROTO_MIN(val) > GHCB_PROTO_OUR)
 		return false;
 
 	return true;
@@ -63,6 +63,7 @@ static bool sev_es_negotiate_protocol(void)
 
 static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb)
 {
+	ghcb->save.sw_exit_code = 0;
 	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
 }
 
@@ -153,28 +154,28 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
 	sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EAX));
 	VMGEXIT();
 	val = sev_es_rd_ghcb_msr();
-	if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP)
+	if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
 		goto fail;
 	regs->ax = val >> 32;
 
 	sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EBX));
 	VMGEXIT();
 	val = sev_es_rd_ghcb_msr();
-	if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP)
+	if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
 		goto fail;
 	regs->bx = val >> 32;
 
 	sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_ECX));
 	VMGEXIT();
 	val = sev_es_rd_ghcb_msr();
-	if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP)
+	if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
 		goto fail;
 	regs->cx = val >> 32;
 
 	sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EDX));
 	VMGEXIT();
 	val = sev_es_rd_ghcb_msr();
-	if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP)
+	if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP)
 		goto fail;
 	regs->dx = val >> 32;
 
diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev.c
index 73873b007838..651b81cd648e 100644
--- a/arch/x86/kernel/sev-es.c
+++ b/arch/x86/kernel/sev.c
@@ -22,7 +22,7 @@
 
 #include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
-#include <asm/sev-es.h>
+#include <asm/sev.h>
 #include <asm/insn-eval.h>
 #include <asm/fpu/internal.h>
 #include <asm/processor.h>
@@ -203,8 +203,18 @@ static __always_inline struct ghcb *sev_es_get_ghcb(struct ghcb_state *state)
 	if (unlikely(data->ghcb_active)) {
 		/* GHCB is already in use - save its contents */
 
-		if (unlikely(data->backup_ghcb_active))
-			return NULL;
+		if (unlikely(data->backup_ghcb_active)) {
+			/*
+			 * Backup-GHCB is also already in use. There is no way
+			 * to continue here so just kill the machine. To make
+			 * panic() work, mark GHCBs inactive so that messages
+			 * can be printed out.
+			 */
+			data->ghcb_active        = false;
+			data->backup_ghcb_active = false;
+
+			panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
+		}
 
 		/* Mark backup_ghcb active before writing to it */
 		data->backup_ghcb_active = true;
@@ -221,24 +231,6 @@ static __always_inline struct ghcb *sev_es_get_ghcb(struct ghcb_state *state)
 	return ghcb;
 }
 
-static __always_inline void sev_es_put_ghcb(struct ghcb_state *state)
-{
-	struct sev_es_runtime_data *data;
-	struct ghcb *ghcb;
-
-	data = this_cpu_read(runtime_data);
-	ghcb = &data->ghcb_page;
-
-	if (state->ghcb) {
-		/* Restore GHCB from Backup */
-		*ghcb = *state->ghcb;
-		data->backup_ghcb_active = false;
-		state->ghcb = NULL;
-	} else {
-		data->ghcb_active = false;
-	}
-}
-
 /* Needed in vc_early_forward_exception */
 void do_early_exception(struct pt_regs *regs, int trapnr);
 
@@ -323,31 +315,44 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
 	u16 d2;
 	u8  d1;
 
-	/* If instruction ran in kernel mode and the I/O buffer is in kernel space */
-	if (!user_mode(ctxt->regs) && !access_ok(target, size)) {
-		memcpy(dst, buf, size);
-		return ES_OK;
-	}
-
+	/*
+	 * This function uses __put_user() independent of whether kernel or user
+	 * memory is accessed. This works fine because __put_user() does no
+	 * sanity checks of the pointer being accessed. All that it does is
+	 * to report when the access failed.
+	 *
+	 * Also, this function runs in atomic context, so __put_user() is not
+	 * allowed to sleep. The page-fault handler detects that it is running
+	 * in atomic context and will not try to take mmap_sem and handle the
+	 * fault, so additional pagefault_enable()/disable() calls are not
+	 * needed.
+	 *
+	 * The access can't be done via copy_to_user() here because
+	 * vc_write_mem() must not use string instructions to access unsafe
+	 * memory. The reason is that MOVS is emulated by the #VC handler by
+	 * splitting the move up into a read and a write and taking a nested #VC
+	 * exception on whatever of them is the MMIO access. Using string
+	 * instructions here would cause infinite nesting.
+	 */
 	switch (size) {
 	case 1:
 		memcpy(&d1, buf, 1);
-		if (put_user(d1, target))
+		if (__put_user(d1, target))
 			goto fault;
 		break;
 	case 2:
 		memcpy(&d2, buf, 2);
-		if (put_user(d2, target))
+		if (__put_user(d2, target))
 			goto fault;
 		break;
 	case 4:
 		memcpy(&d4, buf, 4);
-		if (put_user(d4, target))
+		if (__put_user(d4, target))
 			goto fault;
 		break;
 	case 8:
 		memcpy(&d8, buf, 8);
-		if (put_user(d8, target))
+		if (__put_user(d8, target))
 			goto fault;
 		break;
 	default:
@@ -378,30 +383,43 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 	u16 d2;
 	u8  d1;
 
-	/* If instruction ran in kernel mode and the I/O buffer is in kernel space */
-	if (!user_mode(ctxt->regs) && !access_ok(s, size)) {
-		memcpy(buf, src, size);
-		return ES_OK;
-	}
-
+	/*
+	 * This function uses __get_user() independent of whether kernel or user
+	 * memory is accessed. This works fine because __get_user() does no
+	 * sanity checks of the pointer being accessed. All that it does is
+	 * to report when the access failed.
+	 *
+	 * Also, this function runs in atomic context, so __get_user() is not
+	 * allowed to sleep. The page-fault handler detects that it is running
+	 * in atomic context and will not try to take mmap_sem and handle the
+	 * fault, so additional pagefault_enable()/disable() calls are not
+	 * needed.
+	 *
+	 * The access can't be done via copy_from_user() here because
+	 * vc_read_mem() must not use string instructions to access unsafe
+	 * memory. The reason is that MOVS is emulated by the #VC handler by
+	 * splitting the move up into a read and a write and taking a nested #VC
+	 * exception on whatever of them is the MMIO access. Using string
+	 * instructions here would cause infinite nesting.
+	 */
 	switch (size) {
 	case 1:
-		if (get_user(d1, s))
+		if (__get_user(d1, s))
 			goto fault;
 		memcpy(buf, &d1, 1);
 		break;
 	case 2:
-		if (get_user(d2, s))
+		if (__get_user(d2, s))
 			goto fault;
 		memcpy(buf, &d2, 2);
 		break;
 	case 4:
-		if (get_user(d4, s))
+		if (__get_user(d4, s))
 			goto fault;
 		memcpy(buf, &d4, 4);
 		break;
 	case 8:
-		if (get_user(d8, s))
+		if (__get_user(d8, s))
 			goto fault;
 		memcpy(buf, &d8, 8);
 		break;
@@ -459,7 +477,30 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt
 }
 
 /* Include code shared with pre-decompression boot stage */
-#include "sev-es-shared.c"
+#include "sev-shared.c"
+
+static __always_inline void sev_es_put_ghcb(struct ghcb_state *state)
+{
+	struct sev_es_runtime_data *data;
+	struct ghcb *ghcb;
+
+	data = this_cpu_read(runtime_data);
+	ghcb = &data->ghcb_page;
+
+	if (state->ghcb) {
+		/* Restore GHCB from Backup */
+		*ghcb = *state->ghcb;
+		data->backup_ghcb_active = false;
+		state->ghcb = NULL;
+	} else {
+		/*
+		 * Invalidate the GHCB so a VMGEXIT instruction issued
+		 * from userspace won't appear to be valid.
+		 */
+		vc_ghcb_invalidate(ghcb);
+		data->ghcb_active = false;
+	}
+}
 
 void noinstr __sev_es_nmi_complete(void)
 {
@@ -1255,6 +1296,10 @@ static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt)
 	case X86_TRAP_UD:
 		exc_invalid_op(ctxt->regs);
 		break;
+	case X86_TRAP_PF:
+		write_cr2(ctxt->fi.cr2);
+		exc_page_fault(ctxt->regs, error_code);
+		break;
 	case X86_TRAP_AC:
 		exc_alignment_check(ctxt->regs, error_code);
 		break;
@@ -1284,7 +1329,6 @@ static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs)
  */
 DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
 {
-	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
 	irqentry_state_t irq_state;
 	struct ghcb_state state;
 	struct es_em_ctxt ctxt;
@@ -1310,16 +1354,6 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
 	 */
 
 	ghcb = sev_es_get_ghcb(&state);
-	if (!ghcb) {
-		/*
-		 * Mark GHCBs inactive so that panic() is able to print the
-		 * message.
-		 */
-		data->ghcb_active        = false;
-		data->backup_ghcb_active = false;
-
-		panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
-	}
 
 	vc_ghcb_invalidate(ghcb);
 	result = vc_init_em_ctxt(&ctxt, regs, error_code);
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index 0e5d0a7e203b..06743ec054d2 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -127,6 +127,9 @@ static inline void signal_compat_build_tests(void)
 	BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10);
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C);
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_trapno) != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_trapno) != 0x10);
+
 	BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18);
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10);
 
@@ -138,8 +141,10 @@ static inline void signal_compat_build_tests(void)
 	BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20);
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14);
 
-	BUILD_BUG_ON(offsetof(siginfo_t, si_perf) != 0x18);
-	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x18);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x20);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_data) != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_type) != 0x14);
 
 	CHECK_CSI_OFFSET(_sigpoll);
 	CHECK_CSI_SIZE  (_sigpoll, 2*sizeof(int));
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 0936f5ba3222..ec2d64aa2163 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -2042,7 +2042,7 @@ static bool amd_set_max_freq_ratio(void)
 		return false;
 	}
 
-	highest_perf = perf_caps.highest_perf;
+	highest_perf = amd_get_highest_perf();
 	nominal_perf = perf_caps.nominal_perf;
 
 	if (!highest_perf || !nominal_perf) {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8a0ccdb56076..5e5de05a8fbf 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -5111,7 +5111,7 @@ done:
 	return rc;
 }
 
-int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type)
 {
 	int rc = X86EMUL_CONTINUE;
 	int mode = ctxt->mode;
@@ -5322,7 +5322,8 @@ done_prefixes:
 
 	ctxt->execute = opcode.u.execute;
 
-	if (unlikely(ctxt->ud) && likely(!(ctxt->d & EmulateOnUD)))
+	if (unlikely(emulation_type & EMULTYPE_TRAP_UD) &&
+	    likely(!(ctxt->d & EmulateOnUD)))
 		return EMULATION_FAILED;
 
 	if (unlikely(ctxt->d &
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index f98370a39936..f00830e5202f 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1172,6 +1172,7 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
 {
 	struct kvm_hv *hv = to_kvm_hv(kvm);
 	u64 gfn;
+	int idx;
 
 	if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
 	    hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET ||
@@ -1190,9 +1191,16 @@ void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
 	gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
 
 	hv->tsc_ref.tsc_sequence = 0;
+
+	/*
+	 * Take the srcu lock as memslots will be accessed to check the gfn
+	 * cache generation against the memslots generation.
+	 */
+	idx = srcu_read_lock(&kvm->srcu);
 	if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
 			    &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
 		hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
+	srcu_read_unlock(&kvm->srcu, idx);
 
 out_unlock:
 	mutex_unlock(&hv->hv_lock);
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index f016838faedd..3e870bf9ca4d 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -314,7 +314,6 @@ struct x86_emulate_ctxt {
 	int interruptibility;
 
 	bool perm_ok; /* do not check permissions if true */
-	bool ud;	/* inject an #UD if host doesn't support insn */
 	bool tf;	/* TF value before instruction (after for syscall/sysret) */
 
 	bool have_exception;
@@ -491,7 +490,7 @@ enum x86_intercept {
 #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64
 #endif
 
-int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len);
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len, int emulation_type);
 bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt);
 #define EMULATION_FAILED -1
 #define EMULATION_OK 0
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c0ebef560bd1..8120e8614b92 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1598,11 +1598,19 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
 	apic->lapic_timer.advance_expire_delta = guest_tsc - tsc_deadline;
 
+	if (lapic_timer_advance_dynamic) {
+		adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta);
+		/*
+		 * If the timer fired early, reread the TSC to account for the
+		 * overhead of the above adjustment to avoid waiting longer
+		 * than is necessary.
+		 */
+		if (guest_tsc < tsc_deadline)
+			guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
+	}
+
 	if (guest_tsc < tsc_deadline)
 		__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
-
-	if (lapic_timer_advance_dynamic)
-		adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta);
 }
 
 void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
@@ -1661,7 +1669,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
 	}
 
 	atomic_inc(&apic->lapic_timer.pending);
-	kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+	kvm_make_request(KVM_REQ_UNBLOCK, vcpu);
 	if (from_timer_fn)
 		kvm_vcpu_kick(vcpu);
 }
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 95eeb5ac6a8a..237317b1eddd 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1192,9 +1192,9 @@ bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 }
 
 /*
- * Remove write access from all the SPTEs mapping GFNs [start, end). If
- * skip_4k is set, SPTEs that map 4k pages, will not be write-protected.
- * Returns true if an SPTE has been changed and the TLBs need to be flushed.
+ * Remove write access from all SPTEs at or above min_level that map GFNs
+ * [start, end). Returns true if an SPTE has been changed and the TLBs need to
+ * be flushed.
  */
 static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 			     gfn_t start, gfn_t end, int min_level)
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 712b4e0de481..0e62e6a2438c 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -28,10 +28,8 @@
 #include "svm.h"
 
 /* enable / disable AVIC */
-int avic;
-#ifdef CONFIG_X86_LOCAL_APIC
-module_param(avic, int, S_IRUGO);
-#endif
+bool avic;
+module_param(avic, bool, S_IRUGO);
 
 #define SVM_AVIC_DOORBELL	0xc001011b
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index dfa351e605de..e088086f3de6 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -863,8 +863,8 @@ static __init void svm_adjust_mmio_mask(void)
 		return;
 
 	/* If memory encryption is not enabled, use existing mask */
-	rdmsrl(MSR_K8_SYSCFG, msr);
-	if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
+	rdmsrl(MSR_AMD64_SYSCFG, msr);
+	if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
 		return;
 
 	enc_bit = cpuid_ebx(0x8000001f) & 0x3f;
@@ -1010,9 +1010,7 @@ static __init int svm_hardware_setup(void)
 	}
 
 	if (avic) {
-		if (!npt_enabled ||
-		    !boot_cpu_has(X86_FEATURE_AVIC) ||
-		    !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) {
+		if (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC)) {
 			avic = false;
 		} else {
 			pr_info("AVIC enabled\n");
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index e44567ceb865..2908c6ab5bb4 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -20,6 +20,7 @@
 #include <linux/bits.h>
 
 #include <asm/svm.h>
+#include <asm/sev-common.h>
 
 #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
 
@@ -479,7 +480,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops;
 
 #define VMCB_AVIC_APIC_BAR_MASK		0xFFFFFFFFFF000ULL
 
-extern int avic;
+extern bool avic;
 
 static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data)
 {
@@ -525,40 +526,9 @@ void svm_vcpu_unblocking(struct kvm_vcpu *vcpu);
 
 /* sev.c */
 
-#define GHCB_VERSION_MAX		1ULL
-#define GHCB_VERSION_MIN		1ULL
-
-#define GHCB_MSR_INFO_POS		0
-#define GHCB_MSR_INFO_MASK		(BIT_ULL(12) - 1)
-
-#define GHCB_MSR_SEV_INFO_RESP		0x001
-#define GHCB_MSR_SEV_INFO_REQ		0x002
-#define GHCB_MSR_VER_MAX_POS		48
-#define GHCB_MSR_VER_MAX_MASK		0xffff
-#define GHCB_MSR_VER_MIN_POS		32
-#define GHCB_MSR_VER_MIN_MASK		0xffff
-#define GHCB_MSR_CBIT_POS		24
-#define GHCB_MSR_CBIT_MASK		0xff
-#define GHCB_MSR_SEV_INFO(_max, _min, _cbit)				\
-	((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) |	\
-	 (((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) |	\
-	 (((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) |	\
-	 GHCB_MSR_SEV_INFO_RESP)
-
-#define GHCB_MSR_CPUID_REQ		0x004
-#define GHCB_MSR_CPUID_RESP		0x005
-#define GHCB_MSR_CPUID_FUNC_POS		32
-#define GHCB_MSR_CPUID_FUNC_MASK	0xffffffff
-#define GHCB_MSR_CPUID_VALUE_POS	32
-#define GHCB_MSR_CPUID_VALUE_MASK	0xffffffff
-#define GHCB_MSR_CPUID_REG_POS		30
-#define GHCB_MSR_CPUID_REG_MASK		0x3
-
-#define GHCB_MSR_TERM_REQ		0x100
-#define GHCB_MSR_TERM_REASON_SET_POS	12
-#define GHCB_MSR_TERM_REASON_SET_MASK	0xf
-#define GHCB_MSR_TERM_REASON_POS	16
-#define GHCB_MSR_TERM_REASON_MASK	0xff
+#define GHCB_VERSION_MAX	1ULL
+#define GHCB_VERSION_MIN	1ULL
+
 
 extern unsigned int max_sev_asid;
 
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 8dee8a5fbc17..aa0e7872fcc9 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -90,8 +90,7 @@ static inline bool cpu_has_vmx_preemption_timer(void)
 
 static inline bool cpu_has_vmx_posted_intr(void)
 {
-	return IS_ENABLED(CONFIG_X86_LOCAL_APIC) &&
-		vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR;
+	return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR;
 }
 
 static inline bool cpu_has_load_ia32_efer(void)
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 459748680daf..5f81ef092bd4 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -238,6 +238,20 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
 
 
 /*
+ * Bail out of the block loop if the VM has an assigned
+ * device, but the blocking vCPU didn't reconfigure the
+ * PI.NV to the wakeup vector, i.e. the assigned device
+ * came along after the initial check in pi_pre_block().
+ */
+void vmx_pi_start_assignment(struct kvm *kvm)
+{
+	if (!irq_remapping_cap(IRQ_POSTING_CAP))
+		return;
+
+	kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK);
+}
+
+/*
  * pi_update_irte - set IRTE for Posted-Interrupts
  *
  * @kvm: kvm
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 0bdc41391c5b..7f7b2326caf5 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -95,5 +95,6 @@ void __init pi_init_cpu(int cpu);
 bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu);
 int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq,
 		   bool set);
+void vmx_pi_start_assignment(struct kvm *kvm);
 
 #endif /* __KVM_X86_VMX_POSTED_INTR_H */
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4bceb5ca3a89..50b42d7a8a11 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4843,7 +4843,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct kvm_run *kvm_run = vcpu->run;
 	u32 intr_info, ex_no, error_code;
-	unsigned long cr2, rip, dr6;
+	unsigned long cr2, dr6;
 	u32 vect_info;
 
 	vect_info = vmx->idt_vectoring_info;
@@ -4933,8 +4933,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 		vmx->vcpu.arch.event_exit_inst_len =
 			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
-		rip = kvm_rip_read(vcpu);
-		kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
+		kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu);
 		kvm_run->debug.arch.exception = ex_no;
 		break;
 	case AC_VECTOR:
@@ -7721,6 +7720,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.nested_ops = &vmx_nested_ops,
 
 	.update_pi_irte = pi_update_irte,
+	.start_assignment = vmx_pi_start_assignment,
 
 #ifdef CONFIG_X86_64
 	.set_hv_timer = vmx_set_hv_timer,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9b6bca616929..b594275d49b5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3105,6 +3105,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 				       st->preempted & KVM_VCPU_FLUSH_TLB);
 		if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
 			kvm_vcpu_flush_tlb_guest(vcpu);
+	} else {
+		st->preempted = 0;
 	}
 
 	vcpu->arch.st.preempted = 0;
@@ -3468,7 +3470,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_LASTBRANCHTOIP:
 	case MSR_IA32_LASTINTFROMIP:
 	case MSR_IA32_LASTINTTOIP:
-	case MSR_K8_SYSCFG:
+	case MSR_AMD64_SYSCFG:
 	case MSR_K8_TSEG_ADDR:
 	case MSR_K8_TSEG_MASK:
 	case MSR_VM_HSAVE_PA:
@@ -7226,6 +7228,11 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 	BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
 	BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
 
+	ctxt->interruptibility = 0;
+	ctxt->have_exception = false;
+	ctxt->exception.vector = -1;
+	ctxt->perm_ok = false;
+
 	init_decode_cache(ctxt);
 	vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
 }
@@ -7561,14 +7568,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type,
 	    kvm_vcpu_check_breakpoint(vcpu, &r))
 		return r;
 
-	ctxt->interruptibility = 0;
-	ctxt->have_exception = false;
-	ctxt->exception.vector = -1;
-	ctxt->perm_ok = false;
-
-	ctxt->ud = emulation_type & EMULTYPE_TRAP_UD;
-
-	r = x86_decode_insn(ctxt, insn, insn_len);
+	r = x86_decode_insn(ctxt, insn, insn_len, emulation_type);
 
 	trace_kvm_emulate_insn_start(vcpu);
 	++vcpu->stat.insn_emulation;
@@ -8360,6 +8360,9 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
 
 	vcpu->stat.directed_yield_attempted++;
 
+	if (single_task_running())
+		goto no_yield;
+
 	rcu_read_lock();
 	map = rcu_dereference(vcpu->kvm->arch.apic_map);
 
@@ -9496,7 +9499,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 		if (r <= 0)
 			break;
 
-		kvm_clear_request(KVM_REQ_PENDING_TIMER, vcpu);
+		kvm_clear_request(KVM_REQ_UNBLOCK, vcpu);
 		if (kvm_cpu_has_pending_timer(vcpu))
 			kvm_inject_pending_timer_irqs(vcpu);
 
@@ -10115,8 +10118,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	kvm_update_dr7(vcpu);
 
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) +
-			get_segment_base(vcpu, VCPU_SREG_CS);
+		vcpu->arch.singlestep_rip = kvm_get_linear_rip(vcpu);
 
 	/*
 	 * Trigger an rflags update that will inject or remove the trace
@@ -11499,7 +11501,8 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu)
 
 void kvm_arch_start_assignment(struct kvm *kvm)
 {
-	atomic_inc(&kvm->arch.assigned_device_count);
+	if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1)
+		static_call_cond(kvm_x86_start_assignment)(kvm);
 }
 EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);
 
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index b93d6cd08a7f..121921b2927c 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -5,7 +5,7 @@
 #include <xen/xen.h>
 
 #include <asm/fpu/internal.h>
-#include <asm/sev-es.h>
+#include <asm/sev.h>
 #include <asm/traps.h>
 #include <asm/kdebug.h>
 
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 04aba7e80a36..a9639f663d25 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -529,7 +529,7 @@ void __init sme_enable(struct boot_params *bp)
 		/*
 		 * No SME if Hypervisor bit is set. This check is here to
 		 * prevent a guest from trying to enable SME. For running as a
-		 * KVM guest the MSR_K8_SYSCFG will be sufficient, but there
+		 * KVM guest the MSR_AMD64_SYSCFG will be sufficient, but there
 		 * might be other hypervisors which emulate that MSR as non-zero
 		 * or even pass it through to the guest.
 		 * A malicious hypervisor can still trick a guest into this
@@ -542,8 +542,8 @@ void __init sme_enable(struct boot_params *bp)
 			return;
 
 		/* For SME, check the SYSCFG MSR */
-		msr = __rdmsr(MSR_K8_SYSCFG);
-		if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
+		msr = __rdmsr(MSR_AMD64_SYSCFG);
+		if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
 			return;
 	} else {
 		/* SEV state cannot be controlled by a command line option */
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index ae744b6a0785..dd40d3fea74e 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -284,7 +284,7 @@ static int __init early_root_info_init(void)
 
 	/* need to take out [4G, TOM2) for RAM*/
 	/* SYS_CFG */
-	address = MSR_K8_SYSCFG;
+	address = MSR_AMD64_SYSCFG;
 	rdmsrl(address, val);
 	/* TOP_MEM2 is enabled? */
 	if (val & (1<<21)) {
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index df7b5477fc4f..7515e78ef898 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -47,7 +47,7 @@
 #include <asm/realmode.h>
 #include <asm/time.h>
 #include <asm/pgalloc.h>
-#include <asm/sev-es.h>
+#include <asm/sev.h>
 
 /*
  * We allocate runtime services regions top-down, starting from -4G, i.e.
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 1be71ef5e4c4..2e1c1bec0f9e 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -9,7 +9,7 @@
 #include <asm/realmode.h>
 #include <asm/tlbflush.h>
 #include <asm/crash.h>
-#include <asm/sev-es.h>
+#include <asm/sev.h>
 
 struct real_mode_header *real_mode_header;
 u32 *trampoline_cr4_features;
diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S
index 84c5d1b33d10..cc8391f86cdb 100644
--- a/arch/x86/realmode/rm/trampoline_64.S
+++ b/arch/x86/realmode/rm/trampoline_64.S
@@ -123,9 +123,9 @@ SYM_CODE_START(startup_32)
 	 */
 	btl	$TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags
 	jnc	.Ldone
-	movl	$MSR_K8_SYSCFG, %ecx
+	movl	$MSR_AMD64_SYSCFG, %ecx
 	rdmsr
-	bts	$MSR_K8_SYSCFG_MEM_ENCRYPT_BIT, %eax
+	bts	$MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT, %eax
 	jc	.Ldone
 
 	/*
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 17503fed2017..e87699aa2dc8 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1273,16 +1273,16 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	/* Get mfn list */
 	xen_build_dynamic_phys_to_machine();
 
+	/* Work out if we support NX */
+	get_cpu_cap(&boot_cpu_data);
+	x86_configure_nx();
+
 	/*
 	 * Set up kernel GDT and segment registers, mainly so that
 	 * -fstack-protector code can be executed.
 	 */
 	xen_setup_gdt(0);
 
-	/* Work out if we support NX */
-	get_cpu_cap(&boot_cpu_data);
-	x86_configure_nx();
-
 	/* Determine virtual and physical address sizes */
 	get_cpu_address_sizes(&boot_cpu_data);