Merge branch 'perf/vlbr'

54 files changed, 410 insertions, 258 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a0cc524882d..883da0abf779 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -67,7 +67,7 @@ config X86
 	select ARCH_HAS_FILTER_PGPROT
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
-	select ARCH_HAS_KCOV			if X86_64
+	select ARCH_HAS_KCOV			if X86_64 && STACK_VALIDATION
 	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index e821a7d7d5c4..97d37f0a34f5 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -213,7 +213,6 @@ SYM_FUNC_START(startup_32)
 	 * We place all of the values on our mini stack so lret can
 	 * used to perform that far jump.
 	 */
-	pushl	$__KERNEL_CS
 	leal	startup_64(%ebp), %eax
 #ifdef CONFIG_EFI_MIXED
 	movl	efi32_boot_args(%ebp), %edi
@@ -224,11 +223,20 @@ SYM_FUNC_START(startup_32)
 	movl	efi32_boot_args+8(%ebp), %edx	// saved bootparams pointer
 	cmpl	$0, %edx
 	jnz	1f
+	/*
+	 * efi_pe_entry uses MS calling convention, which requires 32 bytes of
+	 * shadow space on the stack even if all arguments are passed in
+	 * registers. We also need an additional 8 bytes for the space that
+	 * would be occupied by the return address, and this also results in
+	 * the correct stack alignment for entry.
+	 */
+	subl	$40, %esp
 	leal	efi_pe_entry(%ebp), %eax
 	movl	%edi, %ecx			// MS calling convention
 	movl	%esi, %edx
 1:
 #endif
+	pushl	$__KERNEL_CS
 	pushl	%eax
 
 	/* Enter paged protected Mode, activating Long Mode */
@@ -784,6 +792,7 @@ SYM_DATA_LOCAL(boot_heap,	.fill BOOT_HEAP_SIZE, 1, 0)
 
 SYM_DATA_START_LOCAL(boot_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
+	.balign 16
 SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end)
 
 /*
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 12c42eba77ec..9933c0e8e97a 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y					+= core.o probe.o
-obj-$(PERF_EVENTS_INTEL_RAPL)		+= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= rapl.o
 obj-y					+= amd/
 obj-$(CONFIG_X86_LOCAL_APIC)            += msr.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 4103665c6e03..d740c861724c 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -71,10 +71,9 @@ u64 x86_perf_event_update(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int shift = 64 - x86_pmu.cntval_bits;
 	u64 prev_raw_count, new_raw_count;
-	int idx = hwc->idx;
 	u64 delta;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
@@ -1097,22 +1096,31 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 				struct cpu_hw_events *cpuc, int i)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	int idx;
 
-	hwc->idx = cpuc->assign[i];
+	idx = hwc->idx = cpuc->assign[i];
 	hwc->last_cpu = smp_processor_id();
 	hwc->last_tag = ++cpuc->tags[i];
 
-	if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) {
+	switch (hwc->idx) {
+	case INTEL_PMC_IDX_FIXED_BTS:
+	case INTEL_PMC_IDX_FIXED_VLBR:
 		hwc->config_base = 0;
 		hwc->event_base	= 0;
-	} else if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
+		break;
+
+	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1:
 		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED);
-		hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30;
-	} else {
+		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 +
+				(idx - INTEL_PMC_IDX_FIXED);
+		hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) | 1<<30;
+		break;
+
+	default:
 		hwc->config_base = x86_pmu_config_addr(hwc->idx);
 		hwc->event_base  = x86_pmu_event_addr(hwc->idx);
 		hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx);
+		break;
 	}
 }
 
@@ -1233,7 +1241,7 @@ int x86_perf_event_set_period(struct perf_event *event)
 	s64 period = hwc->sample_period;
 	int ret = 0, idx = hwc->idx;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ca35c8b5ee10..582ddff9a359 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2136,8 +2136,35 @@ static inline void intel_pmu_ack_status(u64 ack)
 	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
 }
 
-static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
+static inline bool event_is_checkpointed(struct perf_event *event)
+{
+	return unlikely(event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
+}
+
+static inline void intel_set_masks(struct perf_event *event, int idx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (event->attr.exclude_host)
+		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+	if (event->attr.exclude_guest)
+		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+	if (event_is_checkpointed(event))
+		__set_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static inline void intel_clear_masks(struct perf_event *event, int idx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static void intel_pmu_disable_fixed(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
 
@@ -2148,30 +2175,22 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 	wrmsrl(hwc->config_base, ctrl_val);
 }
 
-static inline bool event_is_checkpointed(struct perf_event *event)
-{
-	return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
-}
-
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int idx = hwc->idx;
 
-	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_clear_masks(event, idx);
+		x86_pmu_disable_event(event);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_clear_masks(event, idx);
+		intel_pmu_disable_fixed(event);
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
 		intel_pmu_disable_bts();
 		intel_pmu_drain_bts_buffer();
-		return;
-	}
-
-	cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
-	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
-	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
-
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL))
-		intel_pmu_disable_fixed(hwc);
-	else
-		x86_pmu_disable_event(event);
+	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		intel_clear_masks(event, idx);
 
 	/*
 	 * Needs to be called after x86_pmu_disable_event,
@@ -2238,33 +2257,23 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-
-	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
-		if (!__this_cpu_read(cpu_hw_events.enabled))
-			return;
-
-		intel_pmu_enable_bts(hwc->config);
-		return;
-	}
-
-	if (event->attr.exclude_host)
-		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
-	if (event->attr.exclude_guest)
-		cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
-
-	if (unlikely(event_is_checkpointed(event)))
-		cpuc->intel_cp_status |= (1ull << hwc->idx);
+	int idx = hwc->idx;
 
 	if (unlikely(event->attr.precise_ip))
 		intel_pmu_pebs_enable(event);
 
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_set_masks(event, idx);
+		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_set_masks(event, idx);
 		intel_pmu_enable_fixed(event);
-		return;
-	}
-
-	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
+		if (!__this_cpu_read(cpu_hw_events.enabled))
+			return;
+		intel_pmu_enable_bts(hwc->config);
+	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		intel_set_masks(event, idx);
 }
 
 static void intel_pmu_add_event(struct perf_event *event)
@@ -2614,6 +2623,20 @@ intel_bts_constraints(struct perf_event *event)
 	return NULL;
 }
 
+/*
+ * Note: matches a fake event, like Fixed2.
+ */
+static struct event_constraint *
+intel_vlbr_constraints(struct perf_event *event)
+{
+	struct event_constraint *c = &vlbr_constraint;
+
+	if (unlikely(constraint_match(c, event->hw.config)))
+		return c;
+
+	return NULL;
+}
+
 static int intel_alt_er(int idx, u64 config)
 {
 	int alt_idx = idx;
@@ -2804,6 +2827,10 @@ __intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 {
 	struct event_constraint *c;
 
+	c = intel_vlbr_constraints(event);
+	if (c)
+		return c;
+
 	c = intel_bts_constraints(event);
 	if (c)
 		return c;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 65113b16804a..d03de7539957 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -383,6 +383,9 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 
 	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
+
+	if (cpuc->lbr_select)
+		wrmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
 }
 
 static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
@@ -415,6 +418,9 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 	cpuc->last_task_ctx = task_ctx;
 	cpuc->last_log_id = ++task_ctx->log_id;
+
+	if (cpuc->lbr_select)
+		rdmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
 }
 
 void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
@@ -485,6 +491,9 @@ void intel_pmu_lbr_add(struct perf_event *event)
 	if (!x86_pmu.lbr_nr)
 		return;
 
+	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
+		cpuc->lbr_select = 1;
+
 	cpuc->br_sel = event->hw.branch_reg.reg;
 
 	if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) {
@@ -532,6 +541,9 @@ void intel_pmu_lbr_del(struct perf_event *event)
 		task_ctx->lbr_callstack_users--;
 	}
 
+	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
+		cpuc->lbr_select = 0;
+
 	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
 		cpuc->lbr_pebs_users--;
 	cpuc->lbr_users--;
@@ -540,11 +552,19 @@ void intel_pmu_lbr_del(struct perf_event *event)
 	perf_sched_cb_dec(event->ctx->pmu);
 }
 
+static inline bool vlbr_exclude_host(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	return test_bit(INTEL_PMC_IDX_FIXED_VLBR,
+		(unsigned long *)&cpuc->intel_ctrl_guest_mask);
+}
+
 void intel_pmu_lbr_enable_all(bool pmi)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (cpuc->lbr_users)
+	if (cpuc->lbr_users && !vlbr_exclude_host())
 		__intel_pmu_lbr_enable(pmi);
 }
 
@@ -552,7 +572,7 @@ void intel_pmu_lbr_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (cpuc->lbr_users)
+	if (cpuc->lbr_users && !vlbr_exclude_host())
 		__intel_pmu_lbr_disable();
 }
 
@@ -694,7 +714,8 @@ void intel_pmu_lbr_read(void)
 	 * This could be smarter and actually check the event,
 	 * but this simple approach seems to work for now.
 	 */
-	if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
+	if (!cpuc->lbr_users || vlbr_exclude_host() ||
+	    cpuc->lbr_users == cpuc->lbr_pebs_users)
 		return;
 
 	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
@@ -1343,3 +1364,27 @@ void intel_pmu_lbr_init_knl(void)
 	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP)
 		x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS;
 }
+
+/**
+ * x86_perf_get_lbr - get the LBR records information
+ *
+ * @lbr: the caller's memory to store the LBR records information
+ *
+ * Returns: 0 indicates the LBR info has been successfully obtained
+ */
+int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
+{
+	int lbr_fmt = x86_pmu.intel_cap.lbr_format;
+
+	lbr->nr = x86_pmu.lbr_nr;
+	lbr->from = x86_pmu.lbr_from;
+	lbr->to = x86_pmu.lbr_to;
+	lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? MSR_LBR_INFO_0 : 0;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(x86_perf_get_lbr);
+
+struct event_constraint vlbr_constraint =
+	__EVENT_CONSTRAINT(INTEL_FIXED_VLBR_EVENT, (1ULL << INTEL_PMC_IDX_FIXED_VLBR),
+			  FIXED_EVENT_FLAGS, 1, 0, PERF_X86_EVENT_LBR_SELECT);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index e17a3d8a47ed..81475963df99 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -78,6 +78,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode)
 #define PERF_X86_EVENT_LARGE_PEBS	0x0400 /* use large PEBS */
 #define PERF_X86_EVENT_PEBS_VIA_PT	0x0800 /* use PT buffer for PEBS */
 #define PERF_X86_EVENT_PAIR		0x1000 /* Large Increment per Cycle */
+#define PERF_X86_EVENT_LBR_SELECT	0x2000 /* Save/Restore MSR_LBR_SELECT */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -237,6 +238,7 @@ struct cpu_hw_events {
 	u64				br_sel;
 	struct x86_perf_task_context	*last_task_ctx;
 	int				last_log_id;
+	int				lbr_select;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -673,8 +675,8 @@ struct x86_pmu {
 	/*
 	 * Intel LBR
 	 */
-	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
-	int		lbr_nr;			   /* hardware stack size */
+	unsigned int	lbr_tos, lbr_from, lbr_to,
+			lbr_nr;			   /* LBR base regs and size */
 	u64		lbr_sel_mask;		   /* LBR_SELECT valid bits */
 	const int	*lbr_sel_map;		   /* lbr_select mappings */
 	bool		lbr_double_abort;	   /* duplicated lbr aborts */
@@ -722,6 +724,7 @@ struct x86_perf_task_context {
 	u64 lbr_from[MAX_LBR_ENTRIES];
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
+	u64 lbr_sel;
 	int tos;
 	int valid_lbrs;
 	int lbr_callstack_users;
@@ -990,6 +993,7 @@ void release_ds_buffers(void);
 void reserve_ds_buffers(void);
 
 extern struct event_constraint bts_constraint;
+extern struct event_constraint vlbr_constraint;
 
 void intel_pmu_enable_bts(u64 config);
 
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index a54c6a401581..2bdc72e6890e 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -375,7 +375,9 @@ void __init hyperv_init(void)
 	guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0);
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
 
-	hv_hypercall_pg = vmalloc_exec(PAGE_SIZE);
+	hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START,
+			VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX,
+			VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __func__);
 	if (hv_hypercall_pg == NULL) {
 		wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
 		goto remove_cpuhp_state;
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 35460fef39b8..0367efdc5b7a 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -201,12 +201,8 @@ arch_test_and_change_bit(long nr, volatile unsigned long *addr)
 	return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
-static __no_kcsan_or_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
 {
-	/*
-	 * Because this is a plain access, we need to disable KCSAN here to
-	 * avoid double instrumentation via instrumented bitops.
-	 */
 	return ((1UL << (nr & (BITS_PER_LONG-1))) &
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index fb34ff641e0a..028189575560 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -75,6 +75,12 @@ do {								\
 	unreachable();						\
 } while (0)
 
+/*
+ * This instrumentation_begin() is strictly speaking incorrect; but it
+ * suppresses the complaints from WARN()s in noinstr code. If such a WARN()
+ * were to trigger, we'd rather wreck the machine in an attempt to get the
+ * message out than not know about it.
+ */
 #define __WARN_FLAGS(flags)					\
 do {								\
 	instrumentation_begin();				\
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index dd17c2da1af5..da78ccbd493b 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -58,4 +58,9 @@ static inline bool handle_guest_split_lock(unsigned long ip)
 	return false;
 }
 #endif
+#ifdef CONFIG_IA32_FEAT_CTL
+void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
+#else
+static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {}
+#endif
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index 6722ffcef2e6..3afa990d756b 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -11,5 +11,23 @@ extern cpumask_var_t cpu_sibling_setup_mask;
 
 extern void setup_cpu_local_masks(void);
 
+/*
+ * NMI and MCE exceptions need cpu_is_offline() _really_ early,
+ * provide an arch_ special for them to avoid instrumentation.
+ */
+#if NR_CPUS > 1
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return arch_test_bit(cpu, cpumask_bits(cpu_online_mask));
+}
+#else
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return cpu == 0;
+}
+#endif
+
+#define arch_cpu_is_offline(cpu)	unlikely(!arch_cpu_online(cpu))
+
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f8998e97457f..be5363b21540 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -943,7 +943,7 @@ struct kvm_arch {
 	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
 	struct kvm_apic_map *apic_map;
-	bool apic_map_dirty;
+	atomic_t apic_map_dirty;
 
 	bool apic_access_page_done;
 	unsigned long apicv_inhibit_reasons;
@@ -1220,7 +1220,7 @@ struct kvm_x86_ops {
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
-	int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 73d997aa2966..e039a933aca3 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -25,8 +25,6 @@
 #define TPAUSE_C01_STATE		1
 #define TPAUSE_C02_STATE		0
 
-u32 get_umwait_control_msr(void);
-
 static inline void __monitor(const void *eax, unsigned long ecx,
 			     unsigned long edx)
 {
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index e855e9cf2c37..2df707311d17 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -192,10 +192,30 @@ struct x86_pmu_capability {
 #define GLOBAL_STATUS_UNC_OVF				BIT_ULL(61)
 #define GLOBAL_STATUS_ASIF				BIT_ULL(60)
 #define GLOBAL_STATUS_COUNTERS_FROZEN			BIT_ULL(59)
-#define GLOBAL_STATUS_LBRS_FROZEN			BIT_ULL(58)
+#define GLOBAL_STATUS_LBRS_FROZEN_BIT			58
+#define GLOBAL_STATUS_LBRS_FROZEN			BIT_ULL(GLOBAL_STATUS_LBRS_FROZEN_BIT)
 #define GLOBAL_STATUS_TRACE_TOPAPMI			BIT_ULL(55)
 
 /*
+ * We model guest LBR event tracing as another fixed-mode PMC like BTS.
+ *
+ * We choose bit 58 because it's used to indicate LBR stack frozen state
+ * for architectural perfmon v4, also we unconditionally mask that bit in
+ * the handle_pmi_common(), so it'll never be set in the overflow handling.
+ *
+ * With this fake counter assigned, the guest LBR event user (such as KVM),
+ * can program the LBR registers on its own, and we don't actually do anything
+ * with then in the host context.
+ */
+#define INTEL_PMC_IDX_FIXED_VLBR	(GLOBAL_STATUS_LBRS_FROZEN_BIT)
+
+/*
+ * Pseudo-encoding the guest LBR event as event=0x00,umask=0x1b,
+ * since it would claim bit 58 which is effectively Fixed26.
+ */
+#define INTEL_FIXED_VLBR_EVENT	0x1b00
+
+/*
  * Adaptive PEBS v4
  */
 
@@ -333,6 +353,13 @@ struct perf_guest_switch_msr {
 	u64 host, guest;
 };
 
+struct x86_pmu_lbr {
+	unsigned int	nr;
+	unsigned int	from;
+	unsigned int	to;
+	unsigned int	info;
+};
+
 extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
 extern void perf_check_microcode(void);
 extern int x86_perf_rdpmc_index(struct perf_event *event);
@@ -348,12 +375,17 @@ static inline void perf_check_microcode(void) { }
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
 extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
+extern int x86_perf_get_lbr(struct x86_pmu_lbr *lbr);
 #else
 static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
 	*nr = 0;
 	return NULL;
 }
+static inline int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
+{
+	return -1;
+}
 #endif
 
 #ifdef CONFIG_CPU_SUP_INTEL
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 2da1f95b88d7..816b31c68550 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -194,6 +194,7 @@ enum page_cache_mode {
 #define _PAGE_TABLE_NOENC	 (__PP|__RW|_USR|___A|   0|___D|   0|   0)
 #define _PAGE_TABLE		 (__PP|__RW|_USR|___A|   0|___D|   0|   0| _ENC)
 #define __PAGE_KERNEL_RO	 (__PP|   0|   0|___A|__NX|___D|   0|___G)
+#define __PAGE_KERNEL_ROX	 (__PP|   0|   0|___A|   0|___D|   0|___G)
 #define __PAGE_KERNEL_NOCACHE	 (__PP|__RW|   0|___A|__NX|___D|   0|___G| __NC)
 #define __PAGE_KERNEL_VVAR	 (__PP|   0|_USR|___A|__NX|___D|   0|___G)
 #define __PAGE_KERNEL_LARGE	 (__PP|__RW|   0|___A|__NX|___D|_PSE|___G)
@@ -219,6 +220,7 @@ enum page_cache_mode {
 #define PAGE_KERNEL_RO		__pgprot_mask(__PAGE_KERNEL_RO         | _ENC)
 #define PAGE_KERNEL_EXEC	__pgprot_mask(__PAGE_KERNEL_EXEC       | _ENC)
 #define PAGE_KERNEL_EXEC_NOENC	__pgprot_mask(__PAGE_KERNEL_EXEC       |    0)
+#define PAGE_KERNEL_ROX		__pgprot_mask(__PAGE_KERNEL_ROX        | _ENC)
 #define PAGE_KERNEL_NOCACHE	__pgprot_mask(__PAGE_KERNEL_NOCACHE    | _ENC)
 #define PAGE_KERNEL_LARGE	__pgprot_mask(__PAGE_KERNEL_LARGE      | _ENC)
 #define PAGE_KERNEL_LARGE_EXEC	__pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 42cd333616c4..03b7c4ca425a 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -370,7 +370,7 @@ struct x86_hw_tss {
 #define IO_BITMAP_OFFSET_INVALID	(__KERNEL_TSS_LIMIT + 1)
 
 struct entry_stack {
-	unsigned long		words[64];
+	char	stack[PAGE_SIZE];
 };
 
 struct entry_stack_page {
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index ebedeab48704..255b2dde2c1b 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -278,7 +278,7 @@ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs
 }
 
 /* To avoid include hell, we can't include uaccess.h */
-extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size);
 
 /**
  * regs_get_kernel_stack_nth() - get Nth entry of the stack
@@ -298,7 +298,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 
 	addr = regs_get_kernel_stack_nth_addr(regs, n);
 	if (addr) {
-		ret = probe_kernel_read(&val, addr, sizeof(val));
+		ret = copy_from_kernel_nofault(&val, addr, sizeof(val));
 		if (!ret)
 			return val;
 	}
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 426792565d86..c5cf336e5077 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -3,6 +3,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 
+#include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/e820/api.h>
 #include <asm/mtrr.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 043d93cdcaad..95c090a45b4b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -347,6 +347,9 @@ out:
 	cr4_clear_bits(X86_CR4_UMIP);
 }
 
+/* These bits should not change their value after CPU init is finished. */
+static const unsigned long cr4_pinned_mask =
+	X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE;
 static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
 static unsigned long cr4_pinned_bits __ro_after_init;
 
@@ -371,20 +374,20 @@ EXPORT_SYMBOL(native_write_cr0);
 
 void native_write_cr4(unsigned long val)
 {
-	unsigned long bits_missing = 0;
+	unsigned long bits_changed = 0;
 
 set_register:
 	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
 
 	if (static_branch_likely(&cr_pinning)) {
-		if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) {
-			bits_missing = ~val & cr4_pinned_bits;
-			val |= bits_missing;
+		if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) {
+			bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits;
+			val = (val & ~cr4_pinned_mask) | cr4_pinned_bits;
 			goto set_register;
 		}
-		/* Warn after we've set the missing bits. */
-		WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n",
-			  bits_missing);
+		/* Warn after we've corrected the changed bits. */
+		WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n",
+			  bits_changed);
 	}
 }
 #if IS_MODULE(CONFIG_LKDTM)
@@ -419,7 +422,7 @@ void cr4_init(void)
 	if (boot_cpu_has(X86_FEATURE_PCID))
 		cr4 |= X86_CR4_PCIDE;
 	if (static_branch_likely(&cr_pinning))
-		cr4 |= cr4_pinned_bits;
+		cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits;
 
 	__write_cr4(cr4);
 
@@ -434,10 +437,7 @@ void cr4_init(void)
  */
 static void __init setup_cr_pinning(void)
 {
-	unsigned long mask;
-
-	mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP);
-	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask;
+	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask;
 	static_key_enable(&cr_pinning.key);
 }
 
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index fb538fccd24c..9d033693519a 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -81,8 +81,4 @@ extern void update_srbds_msr(void);
 
 extern u64 x86_read_arch_cap_msr(void);
 
-#ifdef CONFIG_IA32_FEAT_CTL
-void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
-#endif
-
 #endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index ce9120c4f740..fbe89a92ff36 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1083,7 +1083,7 @@ static noinstr bool mce_check_crashing_cpu(void)
 {
 	unsigned int cpu = smp_processor_id();
 
-	if (cpu_is_offline(cpu) ||
+	if (arch_cpu_is_offline(cpu) ||
 	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
 		u64 mcgstatus;
 
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 12f967c6b603..6a9df71c1b9e 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -981,10 +981,10 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c)
 
 		c->x86_cache_max_rmid  = ecx;
 		c->x86_cache_occ_scale = ebx;
-		if (c->x86_vendor == X86_VENDOR_INTEL)
-			c->x86_cache_mbm_width_offset = eax & 0xff;
-		else
-			c->x86_cache_mbm_width_offset = -1;
+		c->x86_cache_mbm_width_offset = eax & 0xff;
+
+		if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset)
+			c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD;
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index f20a47d120b1..5ffa32256b3b 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -37,6 +37,7 @@
 #define MBA_IS_LINEAR			0x4
 #define MBA_MAX_MBPS			U32_MAX
 #define MAX_MBA_BW_AMD			0x800
+#define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 23b4b61319d3..3f844f14fc0a 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1117,6 +1117,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d,
 	_d_cdp = rdt_find_domain(_r_cdp, d->id, NULL);
 	if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) {
 		_r_cdp = NULL;
+		_d_cdp = NULL;
 		ret = -EINVAL;
 	}
 
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
index 300e3fd5ade3..ec8064c0ae03 100644
--- a/arch/x86/kernel/cpu/umwait.c
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -18,12 +18,6 @@
  */
 static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
 
-u32 get_umwait_control_msr(void)
-{
-	return umwait_control_cached;
-}
-EXPORT_SYMBOL_GPL(get_umwait_control_msr);
-
 /*
  * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by
  * hardware or BIOS before kernel boot.
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
index df1358ba622b..05fa4ef63490 100644
--- a/arch/x86/kernel/cpu/zhaoxin.c
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -2,6 +2,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 
+#include <asm/cpu.h>
 #include <asm/cpufeature.h>
 
 #include "cpu.h"
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 456511b2284e..b037cfa7c0c5 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -106,7 +106,7 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl)
 	bad_ip = user_mode(regs) &&
 		__chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX);
 
-	if (bad_ip || probe_kernel_read(opcodes, (u8 *)prologue,
+	if (bad_ip || copy_from_kernel_nofault(opcodes, (u8 *)prologue,
 					OPCODE_BUFSIZE)) {
 		printk("%sCode: Bad RIP value.\n", loglvl);
 	} else {
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c84d28e90a58..51504566b3a6 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -86,7 +86,7 @@ static int ftrace_verify_code(unsigned long ip, const char *old_code)
 	 * sure what we read is what we expected it to be before modifying it.
 	 */
 	/* read the text we want to modify */
-	if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) {
+	if (copy_from_kernel_nofault(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) {
 		WARN_ON(1);
 		return -EFAULT;
 	}
@@ -355,7 +355,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
 
 	/* Copy ftrace_caller onto the trampoline memory */
-	ret = probe_kernel_read(trampoline, (void *)start_offset, size);
+	ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size);
 	if (WARN_ON(ret < 0))
 		goto fail;
 
@@ -363,13 +363,13 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 
 	/* The trampoline ends with ret(q) */
 	retq = (unsigned long)ftrace_stub;
-	ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+	ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE);
 	if (WARN_ON(ret < 0))
 		goto fail;
 
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
 		ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller);
-		ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+		ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE);
 		if (WARN_ON(ret < 0))
 			goto fail;
 	}
@@ -506,7 +506,7 @@ static void *addr_from_call(void *ptr)
 	union text_poke_insn call;
 	int ret;
 
-	ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE);
+	ret = copy_from_kernel_nofault(&call, ptr, CALL_INSN_SIZE);
 	if (WARN_ON_ONCE(ret < 0))
 		return NULL;
 
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index c44fe7d8d9a4..68acd30c6b87 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -732,11 +732,11 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	int err;
 
 	bpt->type = BP_BREAKPOINT;
-	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+	err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr,
 				BREAK_INSTR_SIZE);
 	if (err)
 		return err;
-	err = probe_kernel_write((char *)bpt->bpt_addr,
+	err = copy_to_kernel_nofault((char *)bpt->bpt_addr,
 				 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
 	if (!err)
 		return err;
@@ -768,7 +768,7 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 	return 0;
 
 knl_write:
-	return probe_kernel_write((char *)bpt->bpt_addr,
+	return copy_to_kernel_nofault((char *)bpt->bpt_addr,
 				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
 }
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index bcc53c0d17c1..fdadc37d72af 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -244,7 +244,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 	 * Fortunately, we know that the original code is the ideal 5-byte
 	 * long NOP.
 	 */
-	if (probe_kernel_read(buf, (void *)addr,
+	if (copy_from_kernel_nofault(buf, (void *)addr,
 		MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
 		return 0UL;
 
@@ -347,7 +347,8 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 		return 0;
 
 	/* This can access kernel text if given address is not recovered */
-	if (probe_kernel_read(dest, (void *)recovered_insn, MAX_INSN_SIZE))
+	if (copy_from_kernel_nofault(dest, (void *)recovered_insn,
+			MAX_INSN_SIZE))
 		return 0;
 
 	kernel_insn_init(insn, dest, MAX_INSN_SIZE);
@@ -766,16 +767,11 @@ asm(
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
-static struct kprobe kretprobe_kprobe = {
-	.addr = (void *)kretprobe_trampoline,
-};
-
 /*
  * Called from kretprobe_trampoline
  */
 __used __visible void *trampoline_handler(struct pt_regs *regs)
 {
-	struct kprobe_ctlblk *kcb;
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
 	struct hlist_node *tmp;
@@ -785,16 +781,12 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 	void *frame_pointer;
 	bool skipped = false;
 
-	preempt_disable();
-
 	/*
 	 * Set a dummy kprobe for avoiding kretprobe recursion.
 	 * Since kretprobe never run in kprobe handler, kprobe must not
 	 * be running at this point.
 	 */
-	kcb = get_kprobe_ctlblk();
-	__this_cpu_write(current_kprobe, &kretprobe_kprobe);
-	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+	kprobe_busy_begin();
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
@@ -870,7 +862,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
 			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, &kretprobe_kprobe);
+			__this_cpu_write(current_kprobe, &kprobe_busy);
 		}
 
 		recycle_rp_inst(ri, &empty_rp);
@@ -886,8 +878,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_hash_unlock(current, &flags);
 
-	__this_cpu_write(current_kprobe, NULL);
-	preempt_enable();
+	kprobe_busy_end();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 3239b6a80bce..40f380461e6d 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -57,7 +57,7 @@ found:
 	 * overwritten by jump destination address. In this case, original
 	 * bytes must be recovered from op->optinsn.copied_insn buffer.
 	 */
-	if (probe_kernel_read(buf, (void *)addr,
+	if (copy_from_kernel_nofault(buf, (void *)addr,
 		MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
 		return 0UL;
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 2de365f15684..d7c5e44b26f7 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -478,7 +478,7 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7);
 
 DEFINE_IDTENTRY_RAW(exc_nmi)
 {
-	if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id()))
+	if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id()))
 		return;
 
 	if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index ee0286390a4c..9e1def3744f2 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -94,12 +94,12 @@ static bool match_id(struct pci_dev *pdev, unsigned short vendor, unsigned short
 }
 
 static bool probe_list(struct pci_dev *pdev, unsigned short vendor,
-		       const unsigned char *rom_list)
+		       const void *rom_list)
 {
 	unsigned short device;
 
 	do {
-		if (probe_kernel_address(rom_list, device) != 0)
+		if (get_kernel_nofault(device, rom_list) != 0)
 			device = 0;
 
 		if (device && match_id(pdev, vendor, device))
@@ -119,19 +119,19 @@ static struct resource *find_oprom(struct pci_dev *pdev)
 	for (i = 0; i < ARRAY_SIZE(adapter_rom_resources); i++) {
 		struct resource *res = &adapter_rom_resources[i];
 		unsigned short offset, vendor, device, list, rev;
-		const unsigned char *rom;
+		const void *rom;
 
 		if (res->end == 0)
 			break;
 
 		rom = isa_bus_to_virt(res->start);
-		if (probe_kernel_address(rom + 0x18, offset) != 0)
+		if (get_kernel_nofault(offset, rom + 0x18) != 0)
 			continue;
 
-		if (probe_kernel_address(rom + offset + 0x4, vendor) != 0)
+		if (get_kernel_nofault(vendor, rom + offset + 0x4) != 0)
 			continue;
 
-		if (probe_kernel_address(rom + offset + 0x6, device) != 0)
+		if (get_kernel_nofault(device, rom + offset + 0x6) != 0)
 			continue;
 
 		if (match_id(pdev, vendor, device)) {
@@ -139,8 +139,8 @@ static struct resource *find_oprom(struct pci_dev *pdev)
 			break;
 		}
 
-		if (probe_kernel_address(rom + offset + 0x8, list) == 0 &&
-		    probe_kernel_address(rom + offset + 0xc, rev) == 0 &&
+		if (get_kernel_nofault(list, rom + offset + 0x8) == 0 &&
+		    get_kernel_nofault(rev, rom + offset + 0xc) == 0 &&
 		    rev >= 3 && list &&
 		    probe_list(pdev, vendor, rom + offset + list)) {
 			oprom = res;
@@ -183,14 +183,14 @@ static int __init romsignature(const unsigned char *rom)
 	const unsigned short * const ptr = (const unsigned short *)rom;
 	unsigned short sig;
 
-	return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE;
+	return get_kernel_nofault(sig, ptr) == 0 && sig == ROMSIGNATURE;
 }
 
 static int __init romchecksum(const unsigned char *rom, unsigned long length)
 {
 	unsigned char sum, c;
 
-	for (sum = 0; length && probe_kernel_address(rom++, c) == 0; length--)
+	for (sum = 0; length && get_kernel_nofault(c, rom++) == 0; length--)
 		sum += c;
 	return !length && !sum;
 }
@@ -211,7 +211,7 @@ void __init probe_roms(void)
 
 		video_rom_resource.start = start;
 
-		if (probe_kernel_address(rom + 2, c) != 0)
+		if (get_kernel_nofault(c, rom + 2) != 0)
 			continue;
 
 		/* 0 < length <= 0x7f * 512, historically */
@@ -249,7 +249,7 @@ void __init probe_roms(void)
 		if (!romsignature(rom))
 			continue;
 
-		if (probe_kernel_address(rom + 2, c) != 0)
+		if (get_kernel_nofault(c, rom + 2) != 0)
 			continue;
 
 		/* 0 < length <= 0x7f * 512, historically */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index af75109485c2..f58679e487f6 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -84,17 +84,16 @@ static inline void cond_local_irq_disable(struct pt_regs *regs)
 		local_irq_disable();
 }
 
-int is_valid_bugaddr(unsigned long addr)
+__always_inline int is_valid_bugaddr(unsigned long addr)
 {
-	unsigned short ud;
-
 	if (addr < TASK_SIZE_MAX)
 		return 0;
 
-	if (probe_kernel_address((unsigned short *)addr, ud))
-		return 0;
-
-	return ud == INSN_UD0 || ud == INSN_UD2;
+	/*
+	 * We got #UD, if the text isn't readable we'd have gotten
+	 * a different exception.
+	 */
+	return *(unsigned short *)addr == INSN_UD2;
 }
 
 static nokprobe_inline int
@@ -216,40 +215,45 @@ static inline void handle_invalid_op(struct pt_regs *regs)
 		      ILL_ILLOPN, error_get_trap_addr(regs));
 }
 
-DEFINE_IDTENTRY_RAW(exc_invalid_op)
+static noinstr bool handle_bug(struct pt_regs *regs)
 {
-	bool rcu_exit;
+	bool handled = false;
+
+	if (!is_valid_bugaddr(regs->ip))
+		return handled;
 
 	/*
-	 * Handle BUG/WARN like NMIs instead of like normal idtentries:
-	 * if we bugged/warned in a bad RCU context, for example, the last
-	 * thing we want is to BUG/WARN again in the idtentry code, ad
-	 * infinitum.
+	 * All lies, just get the WARN/BUG out.
 	 */
-	if (!user_mode(regs) && is_valid_bugaddr(regs->ip)) {
-		enum bug_trap_type type;
+	instrumentation_begin();
+	/*
+	 * Since we're emulating a CALL with exceptions, restore the interrupt
+	 * state to what it was at the exception site.
+	 */
+	if (regs->flags & X86_EFLAGS_IF)
+		raw_local_irq_enable();
+	if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
+		regs->ip += LEN_UD2;
+		handled = true;
+	}
+	if (regs->flags & X86_EFLAGS_IF)
+		raw_local_irq_disable();
+	instrumentation_end();
 
-		nmi_enter();
-		instrumentation_begin();
-		trace_hardirqs_off_finish();
-		type = report_bug(regs->ip, regs);
-		if (regs->flags & X86_EFLAGS_IF)
-			trace_hardirqs_on_prepare();
-		instrumentation_end();
-		nmi_exit();
+	return handled;
+}
 
-		if (type == BUG_TRAP_TYPE_WARN) {
-			/* Skip the ud2. */
-			regs->ip += LEN_UD2;
-			return;
-		}
+DEFINE_IDTENTRY_RAW(exc_invalid_op)
+{
+	bool rcu_exit;
 
-		/*
-		 * Else, if this was a BUG and report_bug returns or if this
-		 * was just a normal #UD, we want to continue onward and
-		 * crash.
-		 */
-	}
+	/*
+	 * We use UD2 as a short encoding for 'CALL __WARN', as such
+	 * handle it before exception entry to avoid recursive WARN
+	 * in case exception entry is the one triggering WARNs.
+	 */
+	if (!user_mode(regs) && handle_bug(regs))
+		return;
 
 	rcu_exit = idtentry_enter_cond_rcu(regs);
 	instrumentation_begin();
@@ -488,7 +492,8 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs,
 	u8 insn_buf[MAX_INSN_SIZE];
 	struct insn insn;
 
-	if (probe_kernel_read(insn_buf, (void *)regs->ip, MAX_INSN_SIZE))
+	if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip,
+			MAX_INSN_SIZE))
 		return GP_NO_HINT;
 
 	kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE);
@@ -690,13 +695,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 		(struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
 
 	/* Copy the IRET target to the temporary storage. */
-	memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
+	__memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
 
 	/* Copy the remainder of the stack from the current stack. */
-	memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
+	__memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
 
 	/* Update the entry stack */
-	memcpy(new_stack, &tmp, sizeof(tmp));
+	__memcpy(new_stack, &tmp, sizeof(tmp));
 
 	BUG_ON(!user_mode(&new_stack->regs));
 	return new_stack;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 34a7e0533dad..5bf72fc86a8e 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -169,6 +169,18 @@ static void kvm_apic_map_free(struct rcu_head *rcu)
 	kvfree(map);
 }
 
+/*
+ * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock.
+ *
+ * DIRTY -> UPDATE_IN_PROGRESS and UPDATE_IN_PROGRESS -> CLEAN happen with
+ * apic_map_lock_held.
+ */
+enum {
+	CLEAN,
+	UPDATE_IN_PROGRESS,
+	DIRTY
+};
+
 void kvm_recalculate_apic_map(struct kvm *kvm)
 {
 	struct kvm_apic_map *new, *old = NULL;
@@ -176,17 +188,17 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 	int i;
 	u32 max_id = 255; /* enough space for any xAPIC ID */
 
-	if (!kvm->arch.apic_map_dirty) {
-		/*
-		 * Read kvm->arch.apic_map_dirty before
-		 * kvm->arch.apic_map
-		 */
-		smp_rmb();
+	/* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map.  */
+	if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN)
 		return;
-	}
 
 	mutex_lock(&kvm->arch.apic_map_lock);
-	if (!kvm->arch.apic_map_dirty) {
+	/*
+	 * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map
+	 * (if clean) or the APIC registers (if dirty).
+	 */
+	if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty,
+				   DIRTY, UPDATE_IN_PROGRESS) == CLEAN) {
 		/* Someone else has updated the map. */
 		mutex_unlock(&kvm->arch.apic_map_lock);
 		return;
@@ -256,11 +268,11 @@ out:
 			lockdep_is_held(&kvm->arch.apic_map_lock));
 	rcu_assign_pointer(kvm->arch.apic_map, new);
 	/*
-	 * Write kvm->arch.apic_map before
-	 * clearing apic->apic_map_dirty
+	 * Write kvm->arch.apic_map before clearing apic->apic_map_dirty.
+	 * If another update has come in, leave it DIRTY.
 	 */
-	smp_wmb();
-	kvm->arch.apic_map_dirty = false;
+	atomic_cmpxchg_release(&kvm->arch.apic_map_dirty,
+			       UPDATE_IN_PROGRESS, CLEAN);
 	mutex_unlock(&kvm->arch.apic_map_lock);
 
 	if (old)
@@ -282,20 +294,20 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
 		else
 			static_key_slow_inc(&apic_sw_disabled.key);
 
-		apic->vcpu->kvm->arch.apic_map_dirty = true;
+		atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 	}
 }
 
 static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id)
 {
 	kvm_lapic_set_reg(apic, APIC_ID, id << 24);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
 {
 	kvm_lapic_set_reg(apic, APIC_LDR, id);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
@@ -311,7 +323,7 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id)
 
 	kvm_lapic_set_reg(apic, APIC_ID, id);
 	kvm_lapic_set_reg(apic, APIC_LDR, ldr);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
@@ -1976,7 +1988,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	case APIC_DFR:
 		if (!apic_x2apic_mode(apic)) {
 			kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
-			apic->vcpu->kvm->arch.apic_map_dirty = true;
+			atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 		} else
 			ret = 1;
 		break;
@@ -2232,7 +2244,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 			static_key_slow_dec_deferred(&apic_hw_disabled);
 		} else {
 			static_key_slow_inc(&apic_hw_disabled.key);
-			vcpu->kvm->arch.apic_map_dirty = true;
+			atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 		}
 	}
 
@@ -2273,7 +2285,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 	if (!apic)
 		return;
 
-	vcpu->kvm->arch.apic_map_dirty = false;
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
 
@@ -2567,6 +2578,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 	}
 	memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s));
 
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 	kvm_recalculate_apic_map(vcpu->kvm);
 	kvm_apic_set_version(vcpu);
 
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 0ad06bfe2c2c..444bb9c54548 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -222,7 +222,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn);
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 int kvm_mmu_post_init_vm(struct kvm *kvm);
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index fdd05c233308..76817d13c86e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1745,10 +1745,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
  * Emulate arch specific page modification logging for the
  * nested hypervisor
  */
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa)
 {
 	if (kvm_x86_ops.write_log_dirty)
-		return kvm_x86_ops.write_log_dirty(vcpu);
+		return kvm_x86_ops.write_log_dirty(vcpu, l2_gpa);
 
 	return 0;
 }
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index a6d484ea110b..bd70ece1ef8b 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -235,7 +235,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte)
 static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 					     struct kvm_mmu *mmu,
 					     struct guest_walker *walker,
-					     int write_fault)
+					     gpa_t addr, int write_fault)
 {
 	unsigned level, index;
 	pt_element_t pte, orig_pte;
@@ -260,7 +260,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 				!(pte & PT_GUEST_DIRTY_MASK)) {
 			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
 #if PTTYPE == PTTYPE_EPT
-			if (kvm_arch_write_log_dirty(vcpu))
+			if (kvm_arch_write_log_dirty(vcpu, addr))
 				return -EINVAL;
 #endif
 			pte |= PT_GUEST_DIRTY_MASK;
@@ -360,7 +360,6 @@ retry_walk:
 	++walker->level;
 
 	do {
-		gfn_t real_gfn;
 		unsigned long host_addr;
 
 		pt_access = pte_access;
@@ -375,7 +374,7 @@ retry_walk:
 		walker->table_gfn[walker->level - 1] = table_gfn;
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
 
-		real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
+		real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
 					      nested_access,
 					      &walker->fault);
 
@@ -389,12 +388,10 @@ retry_walk:
 		 * information to fix the exit_qualification or exit_info_1
 		 * fields.
 		 */
-		if (unlikely(real_gfn == UNMAPPED_GVA))
+		if (unlikely(real_gpa == UNMAPPED_GVA))
 			return 0;
 
-		real_gfn = gpa_to_gfn(real_gfn);
-
-		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn,
+		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa),
 					    &walker->pte_writable[walker->level - 1]);
 		if (unlikely(kvm_is_error_hva(host_addr)))
 			goto error;
@@ -457,7 +454,8 @@ retry_walk:
 			(PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
-		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
+		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker,
+							addr, write_fault);
 		if (unlikely(ret < 0))
 			goto error;
 		else if (ret)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 8ccfa4197d9c..c0da4dd78ac5 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3344,7 +3344,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 
 void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
 
-static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
+static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	fastpath_t exit_fastpath;
 	struct vcpu_svm *svm = to_svm(vcpu);
diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h
index 5c0ff80b85c0..7a3675fddec2 100644
--- a/arch/x86/kvm/vmx/vmcs.h
+++ b/arch/x86/kvm/vmx/vmcs.h
@@ -72,11 +72,24 @@ struct loaded_vmcs {
 	struct vmcs_controls_shadow controls_shadow;
 };
 
+static inline bool is_intr_type(u32 intr_info, u32 type)
+{
+	const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK;
+
+	return (intr_info & mask) == (INTR_INFO_VALID_MASK | type);
+}
+
+static inline bool is_intr_type_n(u32 intr_info, u32 type, u8 vector)
+{
+	const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK |
+			 INTR_INFO_VECTOR_MASK;
+
+	return (intr_info & mask) == (INTR_INFO_VALID_MASK | type | vector);
+}
+
 static inline bool is_exception_n(u32 intr_info, u8 vector)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
+	return is_intr_type_n(intr_info, INTR_TYPE_HARD_EXCEPTION, vector);
 }
 
 static inline bool is_debug(u32 intr_info)
@@ -106,28 +119,23 @@ static inline bool is_gp_fault(u32 intr_info)
 
 static inline bool is_machine_check(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
+	return is_exception_n(intr_info, MC_VECTOR);
 }
 
 /* Undocumented: icebp/int1 */
 static inline bool is_icebp(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK);
+	return is_intr_type(intr_info, INTR_TYPE_PRIV_SW_EXCEPTION);
 }
 
 static inline bool is_nmi(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
+	return is_intr_type(intr_info, INTR_TYPE_NMI_INTR);
 }
 
 static inline bool is_external_intr(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
-		== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR);
+	return is_intr_type(intr_info, INTR_TYPE_EXT_INTR);
 }
 
 enum vmcs_field_width {
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 36c771728c8c..cb22f33bf1d8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6606,23 +6606,6 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host, false);
 }
 
-static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx)
-{
-	u32 host_umwait_control;
-
-	if (!vmx_has_waitpkg(vmx))
-		return;
-
-	host_umwait_control = get_umwait_control_msr();
-
-	if (vmx->msr_ia32_umwait_control != host_umwait_control)
-		add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL,
-			vmx->msr_ia32_umwait_control,
-			host_umwait_control, false);
-	else
-		clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL);
-}
-
 static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6728,9 +6711,7 @@ reenter_guest:
 
 	pt_guest_enter(vmx);
 
-	if (vcpu_to_pmu(vcpu)->version)
-		atomic_switch_perf_msrs(vmx);
-	atomic_switch_umwait_control_msr(vmx);
+	atomic_switch_perf_msrs(vmx);
 
 	if (enable_preemption_timer)
 		vmx_update_hv_timer(vcpu);
@@ -7501,11 +7482,11 @@ static void vmx_flush_log_dirty(struct kvm *kvm)
 	kvm_flush_pml_buffers(kvm);
 }
 
-static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
 	struct vmcs12 *vmcs12;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gpa_t gpa, dst;
+	gpa_t dst;
 
 	if (is_guest_mode(vcpu)) {
 		WARN_ON_ONCE(vmx->nested.pml_full);
@@ -7524,7 +7505,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
 			return 1;
 		}
 
-		gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+		gpa &= ~0xFFFull;
 		dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index;
 
 		if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa,
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 8a83b5edc820..639798e4a6ca 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -288,8 +288,6 @@ struct vcpu_vmx {
 
 	u64 current_tsc_ratio;
 
-	u32 host_pkru;
-
 	unsigned long host_debugctlmsr;
 
 	/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 00c88c2f34e4..3b92db412335 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2856,7 +2856,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		return kvm_mtrr_set_msr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
 		return kvm_set_apic_base(vcpu, msr_info);
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_write(vcpu, msr, data);
 	case MSR_IA32_TSCDEADLINE:
 		kvm_set_lapic_tscdeadline_msr(vcpu, data);
@@ -3196,7 +3196,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_APICBASE:
 		msr_info->data = kvm_get_apic_base(vcpu);
 		break;
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
 	case MSR_IA32_TSCDEADLINE:
 		msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu);
@@ -4603,7 +4603,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EINVAL;
 		user_tsc_khz = (u32)arg;
 
-		if (user_tsc_khz >= kvm_max_guest_tsc_khz)
+		if (kvm_has_tsc_control &&
+		    user_tsc_khz >= kvm_max_guest_tsc_khz)
 			goto out;
 
 		if (user_tsc_khz == 0)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 56b243b14c3a..bbcc05bcefad 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -8,6 +8,8 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
+.pushsection .noinstr.text, "ax"
+
 /*
  * We build a jump to memcpy_orig by default which gets NOPped out on
  * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
@@ -184,6 +186,8 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	retq
 SYM_FUNC_END(memcpy_orig)
 
+.popsection
+
 #ifndef CONFIG_UML
 
 MCSAFE_TEST_CTL
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index fff28c6f73a2..b0dfac3d3df7 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -24,6 +24,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
 	asm volatile(
 		"	testq  %[size8],%[size8]\n"
 		"	jz     4f\n"
+		"	.align 16\n"
 		"0:	movq $0,(%[dst])\n"
 		"	addq   $8,%[dst]\n"
 		"	decl %%ecx ; jnz   0b\n"
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 66be9bd60307..1ead568c0101 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -99,7 +99,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
 		return !instr_lo || (instr_lo>>1) == 1;
 	case 0x00:
 		/* Prefetch instruction is 0x0F0D or 0x0F18 */
-		if (probe_kernel_address(instr, opcode))
+		if (get_kernel_nofault(opcode, instr))
 			return 0;
 
 		*prefetch = (instr_lo == 0xF) &&
@@ -133,7 +133,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
 	while (instr < max_instr) {
 		unsigned char opcode;
 
-		if (probe_kernel_address(instr, opcode))
+		if (get_kernel_nofault(opcode, instr))
 			break;
 
 		instr++;
@@ -301,7 +301,7 @@ static int bad_address(void *p)
 {
 	unsigned long dummy;
 
-	return probe_kernel_address((unsigned long *)p, dummy);
+	return get_kernel_nofault(dummy, (unsigned long *)p);
 }
 
 static void dump_pagetable(unsigned long address)
@@ -442,7 +442,7 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index)
 		return;
 	}
 
-	if (probe_kernel_read(&desc, (void *)(gdt->address + offset),
+	if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset),
 			      sizeof(struct ldttss_desc))) {
 		pr_alert("%s: 0x%hx -- GDT entry is not readable\n",
 			 name, index);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index bda909e3e37e..8b4afad84f4a 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -737,7 +737,7 @@ static void __init test_wp_bit(void)
 
 	__set_fixmap(FIX_WP_TEST, __pa_symbol(empty_zero_page), PAGE_KERNEL_RO);
 
-	if (probe_kernel_write((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) {
+	if (copy_to_kernel_nofault((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) {
 		clear_fixmap(FIX_WP_TEST);
 		printk(KERN_CONT "Ok.\n");
 		return;
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index e1d7d7477c22..92ec176a7293 100644
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -9,7 +9,7 @@ static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits)
 	return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
 }
 
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
 	unsigned long vaddr = (unsigned long)unsafe_src;
 
@@ -22,7 +22,7 @@ bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
 	       canonical_address(vaddr, boot_cpu_data.x86_virt_bits) == vaddr;
 }
 #else
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
 	return (unsigned long)unsafe_src >= TASK_SIZE_MAX;
 }
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 9c97d814125e..4f15280732ed 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -302,7 +302,7 @@ static const struct pci_raw_ops *__init pci_find_bios(void)
 	     check <= (union bios32 *) __va(0xffff0);
 	     ++check) {
 		long sig;
-		if (probe_kernel_address(&check->fields.signature, sig))
+		if (get_kernel_nofault(sig, &check->fields.signature))
 			continue;
 
 		if (check->fields.signature != BIOS32_SIGNATURE)
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index b8f7f193f383..30bd5714a3d4 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -287,8 +287,8 @@ void intel_scu_devices_create(void)
 
 		adapter = i2c_get_adapter(i2c_bus[i]);
 		if (adapter) {
-			client = i2c_new_device(adapter, i2c_devs[i]);
-			if (!client)
+			client = i2c_new_client_device(adapter, i2c_devs[i]);
+			if (IS_ERR(client))
 				pr_err("can't create i2c device %s\n",
 					i2c_devs[i]->type);
 		} else
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 7c65102debaf..db1378c6ff26 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -193,6 +193,8 @@ static void fix_processor_context(void)
  */
 static void notrace __restore_processor_state(struct saved_context *ctxt)
 {
+	struct cpuinfo_x86 *c;
+
 	if (ctxt->misc_enable_saved)
 		wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
 	/*
@@ -263,6 +265,10 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	mtrr_bp_restore();
 	perf_restore_debug_store();
 	msr_restore_context(ctxt);
+
+	c = &cpu_data(smp_processor_id());
+	if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL))
+		init_ia32_feat_ctl(c);
 }
 
 /* Needed by apm.c */
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index b04e6e72a592..088bd764e0b7 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -34,6 +34,7 @@ KCOV_INSTRUMENT := n
 PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
 PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss
 PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
+PURGATORY_CFLAGS += $(call cc-option,-fno-stack-protector)
 
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
 # in turn leaves some undefined symbols like __fentry__ in purgatory and not
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 33b309d65955..acc49fa6a097 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -386,7 +386,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 
 	preempt_disable();
 
-	probe_kernel_read(&dummy, v, 1);
+	copy_from_kernel_nofault(&dummy, v, 1);
 
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();