Merge tag 'irqchip-5.16' into irq/core

Merge irqchip updates for Linux 5.16 from Marc Zyngier:

- A large cross-arch rework to move irq_enter()/irq_exit() into
  the arch code, and removing it from the generic irq code.
  Thanks to Mark Rutland for the huge effort!

- A few irqchip drivers are made modular (broadcom, meson), because
  that's apparently a thing...

- A new driver for the Microchip External Interrupt Controller

- The irq_cpu_offline()/irq_cpu_online() API is now deprecated and
  can only be selected on the Cavium Octeon platform. Once this
  platform is removed, the API will be removed at the same time.

- A sprinkle of devm_* helper, as people seem to love that.

- The usual spattering of small fixes and minor improvements.

* tag 'irqchip-5.16': (912 commits)
  h8300: Fix linux/irqchip.h include mess
  dt-bindings: irqchip: renesas-irqc: Document r8a774e1 bindings
  MIPS: irq: Avoid an unused-variable error
  genirq: Hide irq_cpu_{on,off}line() behind a deprecated option
  irqchip/mips-gic: Get rid of the reliance on irq_cpu_online()
  MIPS: loongson64: Drop call to irq_cpu_offline()
  irq: remove handle_domain_{irq,nmi}()
  irq: remove CONFIG_HANDLE_DOMAIN_IRQ_IRQENTRY
  irq: riscv: perform irqentry in entry code
  irq: openrisc: perform irqentry in entry code
  irq: csky: perform irqentry in entry code
  irq: arm64: perform irqentry in entry code
  irq: arm: perform irqentry in entry code
  irq: add a (temporary) CONFIG_HANDLE_DOMAIN_IRQ_IRQENTRY
  irq: nds32: avoid CONFIG_HANDLE_DOMAIN_IRQ
  irq: arc: avoid CONFIG_HANDLE_DOMAIN_IRQ
  irq: add generic_handle_arch_irq()
  irq: unexport handle_irq_desc()
  irq: simplify handle_domain_{irq,nmi}()
  irq: mips: simplify do_domain_IRQ()
  ...

Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211029083332.3680101-1-maz@kernel.org

45 files changed, 486 insertions, 296 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4e001bbbb425..ab83c22d274e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -339,6 +339,11 @@ config NEED_PER_CPU_PAGE_FIRST_CHUNK
 config ARCH_HIBERNATION_POSSIBLE
 	def_bool y
 
+config ARCH_NR_GPIO
+	int
+	default 1024 if X86_64
+	default 512
+
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 
@@ -2605,7 +2610,6 @@ config PCI_OLPC
 config PCI_XEN
 	def_bool y
 	depends on PCI && XEN
-	select SWIOTLB_XEN
 
 config MMCONF_FAM10H
 	def_bool y
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index e7355f8b51c2..94834c4b5e5e 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -4,6 +4,12 @@
 
 tune		= $(call cc-option,-mtune=$(1),$(2))
 
+ifdef CONFIG_CC_IS_CLANG
+align		:= -falign-functions=0 $(call cc-option,-falign-jumps=0) $(call cc-option,-falign-loops=0)
+else
+align		:= -falign-functions=0 -falign-jumps=0 -falign-loops=0
+endif
+
 cflags-$(CONFIG_M486SX)		+= -march=i486
 cflags-$(CONFIG_M486)		+= -march=i486
 cflags-$(CONFIG_M586)		+= -march=i586
@@ -19,11 +25,11 @@ cflags-$(CONFIG_MK6)		+= -march=k6
 # They make zero difference whatsosever to performance at this time.
 cflags-$(CONFIG_MK7)		+= -march=athlon
 cflags-$(CONFIG_MK8)		+= $(call cc-option,-march=k8,-march=athlon)
-cflags-$(CONFIG_MCRUSOE)	+= -march=i686 -falign-functions=0 -falign-jumps=0 -falign-loops=0
-cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) -falign-functions=0 -falign-jumps=0 -falign-loops=0
+cflags-$(CONFIG_MCRUSOE)	+= -march=i686 $(align)
+cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) $(align)
 cflags-$(CONFIG_MWINCHIPC6)	+= $(call cc-option,-march=winchip-c6,-march=i586)
 cflags-$(CONFIG_MWINCHIP3D)	+= $(call cc-option,-march=winchip2,-march=i586)
-cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) -falign-functions=0 -falign-jumps=0 -falign-loops=0
+cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) $(align)
 cflags-$(CONFIG_MVIAC3_2)	+= $(call cc-option,-march=c3-2,-march=i686)
 cflags-$(CONFIG_MVIAC7)		+= -march=i686
 cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call tune,core2)
diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
index fa2c3f50aecb..18d2f5199194 100644
--- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
@@ -367,10 +367,11 @@ SYM_FUNC_START(sm4_aesni_avx_crypt8)
 	 *	%rdx: src (1..8 blocks)
 	 *	%rcx: num blocks (1..8)
 	 */
-	FRAME_BEGIN
-
 	cmpq $5, %rcx;
 	jb sm4_aesni_avx_crypt4;
+
+	FRAME_BEGIN
+
 	vmovdqu (0 * 16)(%rdx), RA0;
 	vmovdqu (1 * 16)(%rdx), RA1;
 	vmovdqu (2 * 16)(%rdx), RA2;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 2a57dbed4894..6dfa8ddaa60f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2465,6 +2465,7 @@ static int x86_pmu_event_init(struct perf_event *event)
 	if (err) {
 		if (event->destroy)
 			event->destroy(event);
+		event->destroy = NULL;
 	}
 
 	if (READ_ONCE(x86_pmu.attr_rdpmc) &&
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7011e87be6d0..9a044438072b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -263,6 +263,7 @@ static struct event_constraint intel_icl_event_constraints[] = {
 	INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf),
 	INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf),
 	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf),
+	INTEL_EVENT_CONSTRAINT(0xef, 0xf),
 	INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf),
 	EVENT_CONSTRAINT_END
 };
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 90e682a92820..32a1ad356c18 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -99,7 +99,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val)
 /*
  * IPI implementation on Hyper-V.
  */
-static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
+static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
+		bool exclude_self)
 {
 	struct hv_send_ipi_ex **arg;
 	struct hv_send_ipi_ex *ipi_arg;
@@ -123,7 +124,10 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 
 	if (!cpumask_equal(mask, cpu_present_mask)) {
 		ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
-		nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask);
+		if (exclude_self)
+			nr_bank = cpumask_to_vpset_noself(&(ipi_arg->vp_set), mask);
+		else
+			nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask);
 	}
 	if (nr_bank < 0)
 		goto ipi_mask_ex_done;
@@ -138,15 +142,25 @@ ipi_mask_ex_done:
 	return hv_result_success(status);
 }
 
-static bool __send_ipi_mask(const struct cpumask *mask, int vector)
+static bool __send_ipi_mask(const struct cpumask *mask, int vector,
+		bool exclude_self)
 {
-	int cur_cpu, vcpu;
+	int cur_cpu, vcpu, this_cpu = smp_processor_id();
 	struct hv_send_ipi ipi_arg;
 	u64 status;
+	unsigned int weight;
 
 	trace_hyperv_send_ipi_mask(mask, vector);
 
-	if (cpumask_empty(mask))
+	weight = cpumask_weight(mask);
+
+	/*
+	 * Do nothing if
+	 *   1. the mask is empty
+	 *   2. the mask only contains self when exclude_self is true
+	 */
+	if (weight == 0 ||
+	    (exclude_self && weight == 1 && cpumask_test_cpu(this_cpu, mask)))
 		return true;
 
 	if (!hv_hypercall_pg)
@@ -172,6 +186,8 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	ipi_arg.cpu_mask = 0;
 
 	for_each_cpu(cur_cpu, mask) {
+		if (exclude_self && cur_cpu == this_cpu)
+			continue;
 		vcpu = hv_cpu_number_to_vp_number(cur_cpu);
 		if (vcpu == VP_INVAL)
 			return false;
@@ -191,7 +207,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	return hv_result_success(status);
 
 do_ex_hypercall:
-	return __send_ipi_mask_ex(mask, vector);
+	return __send_ipi_mask_ex(mask, vector, exclude_self);
 }
 
 static bool __send_ipi_one(int cpu, int vector)
@@ -208,7 +224,7 @@ static bool __send_ipi_one(int cpu, int vector)
 		return false;
 
 	if (vp >= 64)
-		return __send_ipi_mask_ex(cpumask_of(cpu), vector);
+		return __send_ipi_mask_ex(cpumask_of(cpu), vector, false);
 
 	status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp));
 	return hv_result_success(status);
@@ -222,20 +238,13 @@ static void hv_send_ipi(int cpu, int vector)
 
 static void hv_send_ipi_mask(const struct cpumask *mask, int vector)
 {
-	if (!__send_ipi_mask(mask, vector))
+	if (!__send_ipi_mask(mask, vector, false))
 		orig_apic.send_IPI_mask(mask, vector);
 }
 
 static void hv_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
 {
-	unsigned int this_cpu = smp_processor_id();
-	struct cpumask new_mask;
-	const struct cpumask *local_mask;
-
-	cpumask_copy(&new_mask, mask);
-	cpumask_clear_cpu(this_cpu, &new_mask);
-	local_mask = &new_mask;
-	if (!__send_ipi_mask(local_mask, vector))
+	if (!__send_ipi_mask(mask, vector, true))
 		orig_apic.send_IPI_mask_allbutself(mask, vector);
 }
 
@@ -246,7 +255,7 @@ static void hv_send_ipi_allbutself(int vector)
 
 static void hv_send_ipi_all(int vector)
 {
-	if (!__send_ipi_mask(cpu_online_mask, vector))
+	if (!__send_ipi_mask(cpu_online_mask, vector, false))
 		orig_apic.send_IPI_all(vector);
 }
 
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index 87bd6025d91d..6a5f3acf2b33 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -46,7 +46,7 @@ struct kvm_page_track_notifier_node {
 			    struct kvm_page_track_notifier_node *node);
 };
 
-void kvm_page_track_init(struct kvm *kvm);
+int kvm_page_track_init(struct kvm *kvm);
 void kvm_page_track_cleanup(struct kvm *kvm);
 
 void kvm_page_track_free_memslot(struct kvm_memory_slot *slot);
diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h
index eceea9299097..6c5765192102 100644
--- a/arch/x86/include/asm/kvmclock.h
+++ b/arch/x86/include/asm/kvmclock.h
@@ -2,6 +2,20 @@
 #ifndef _ASM_X86_KVM_CLOCK_H
 #define _ASM_X86_KVM_CLOCK_H
 
+#include <linux/percpu.h>
+
 extern struct clocksource kvm_clock;
 
+DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+
+static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
+{
+	return &this_cpu_read(hv_clock_per_cpu)->pvti;
+}
+
+static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
+{
+	return this_cpu_read(hv_clock_per_cpu);
+}
+
 #endif /* _ASM_X86_KVM_CLOCK_H */
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index 5c7bcaa79623..1d5f14aff5f6 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -2,8 +2,6 @@
 #ifndef _ASM_X86_PKEYS_H
 #define _ASM_X86_PKEYS_H
 
-#define ARCH_DEFAULT_PKEY	0
-
 /*
  * If more than 16 keys are ever supported, a thorough audit
  * will be necessary to ensure that the types that store key
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index f3fbb84ff8a7..68c257a3de0d 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -275,7 +275,7 @@ static inline int enqcmds(void __iomem *dst, const void *src)
 {
 	const struct { char _[64]; } *__src = src;
 	struct { char _[64]; } __iomem *__dst = dst;
-	int zf;
+	bool zf;
 
 	/*
 	 * ENQCMDS %(rdx), rax
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index c9fa7be3df82..5c95d242f38d 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -301,8 +301,8 @@ do {									\
 	unsigned int __gu_low, __gu_high;				\
 	const unsigned int __user *__gu_ptr;				\
 	__gu_ptr = (const void __user *)(ptr);				\
-	__get_user_asm(__gu_low, ptr, "l", "=r", label);		\
-	__get_user_asm(__gu_high, ptr+1, "l", "=r", label);		\
+	__get_user_asm(__gu_low, __gu_ptr, "l", "=r", label);		\
+	__get_user_asm(__gu_high, __gu_ptr+1, "l", "=r", label);	\
 	(x) = ((unsigned long long)__gu_high << 32) | __gu_low;		\
 } while (0)
 #else
diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h
index 6b56d0d45d15..66b4ddde7743 100644
--- a/arch/x86/include/asm/xen/swiotlb-xen.h
+++ b/arch/x86/include/asm/xen/swiotlb-xen.h
@@ -3,14 +3,10 @@
 #define _ASM_X86_SWIOTLB_XEN_H
 
 #ifdef CONFIG_SWIOTLB_XEN
-extern int xen_swiotlb;
 extern int __init pci_xen_swiotlb_detect(void);
-extern void __init pci_xen_swiotlb_init(void);
 extern int pci_xen_swiotlb_init_late(void);
 #else
-#define xen_swiotlb (0)
-static inline int __init pci_xen_swiotlb_detect(void) { return 0; }
-static inline void __init pci_xen_swiotlb_init(void) { }
+#define pci_xen_swiotlb_detect NULL
 static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; }
 #endif
 
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 8cb7816d03b4..193204aee880 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1253,6 +1253,9 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin
 
 static void kill_me_now(struct callback_head *ch)
 {
+	struct task_struct *p = container_of(ch, struct task_struct, mce_kill_me);
+
+	p->mce_count = 0;
 	force_sig(SIGBUS);
 }
 
@@ -1262,6 +1265,7 @@ static void kill_me_maybe(struct callback_head *cb)
 	int flags = MF_ACTION_REQUIRED;
 	int ret;
 
+	p->mce_count = 0;
 	pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
 
 	if (!p->mce_ripv)
@@ -1290,17 +1294,34 @@ static void kill_me_maybe(struct callback_head *cb)
 	}
 }
 
-static void queue_task_work(struct mce *m, int kill_current_task)
+static void queue_task_work(struct mce *m, char *msg, int kill_current_task)
 {
-	current->mce_addr = m->addr;
-	current->mce_kflags = m->kflags;
-	current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
-	current->mce_whole_page = whole_page(m);
+	int count = ++current->mce_count;
 
-	if (kill_current_task)
-		current->mce_kill_me.func = kill_me_now;
-	else
-		current->mce_kill_me.func = kill_me_maybe;
+	/* First call, save all the details */
+	if (count == 1) {
+		current->mce_addr = m->addr;
+		current->mce_kflags = m->kflags;
+		current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
+		current->mce_whole_page = whole_page(m);
+
+		if (kill_current_task)
+			current->mce_kill_me.func = kill_me_now;
+		else
+			current->mce_kill_me.func = kill_me_maybe;
+	}
+
+	/* Ten is likely overkill. Don't expect more than two faults before task_work() */
+	if (count > 10)
+		mce_panic("Too many consecutive machine checks while accessing user data", m, msg);
+
+	/* Second or later call, make sure page address matches the one from first call */
+	if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT))
+		mce_panic("Consecutive machine checks to different user pages", m, msg);
+
+	/* Do not call task_work_add() more than once */
+	if (count > 1)
+		return;
 
 	task_work_add(current, &current->mce_kill_me, TWA_RESUME);
 }
@@ -1438,7 +1459,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		/* If this triggers there is no way to recover. Die hard. */
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
 
-		queue_task_work(&m, kill_current_task);
+		queue_task_work(&m, msg, kill_current_task);
 
 	} else {
 		/*
@@ -1456,7 +1477,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		}
 
 		if (m.kflags & MCE_IN_KERNEL_COPYIN)
-			queue_task_work(&m, kill_current_task);
+			queue_task_work(&m, msg, kill_current_task);
 	}
 out:
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index ad273e5861c1..73c74b961d0f 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -49,18 +49,9 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
 static struct pvclock_vsyscall_time_info
 			hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE);
 static struct pvclock_wall_clock wall_clock __bss_decrypted;
-static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
 static struct pvclock_vsyscall_time_info *hvclock_mem;
-
-static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
-{
-	return &this_cpu_read(hv_clock_per_cpu)->pvti;
-}
-
-static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
-{
-	return this_cpu_read(hv_clock_per_cpu);
-}
+DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu);
 
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 79f164141116..40ed44ead063 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -830,6 +830,20 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_init.oem.arch_setup();
 
+	/*
+	 * Do some memory reservations *before* memory is added to memblock, so
+	 * memblock allocations won't overwrite it.
+	 *
+	 * After this point, everything still needed from the boot loader or
+	 * firmware or kernel text should be early reserved or marked not RAM in
+	 * e820. All other memory is free game.
+	 *
+	 * This call needs to happen before e820__memory_setup() which calls the
+	 * xen_memory_setup() on Xen dom0 which relies on the fact that those
+	 * early reservations have happened already.
+	 */
+	early_reserve_memory();
+
 	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
 	e820__memory_setup();
 	parse_setup_data();
@@ -876,18 +890,6 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
-	/*
-	 * Do some memory reservations *before* memory is added to
-	 * memblock, so memblock allocations won't overwrite it.
-	 * Do it after early param, so we could get (unlikely) panic from
-	 * serial.
-	 *
-	 * After this point everything still needed from the boot loader or
-	 * firmware or kernel text should be early reserved or marked not
-	 * RAM in e820. All other memory is free game.
-	 */
-	early_reserve_memory();
-
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/*
 	 * Memory used by the kernel cannot be hot-removed because Linux
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 78a32b956e81..5afd98559193 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-	memblock_free(__pa(ptr), size);
+	memblock_free_ptr(ptr, size);
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index fe03bd978761..751aa85a3001 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -65,8 +65,8 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find(
 	for (i = 0; i < nent; i++) {
 		e = &entries[i];
 
-		if (e->function == function && (e->index == index ||
-		    !(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX)))
+		if (e->function == function &&
+		    (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index))
 			return e;
 	}
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2837110e66ed..9a144ca8e146 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -435,7 +435,6 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	__FOP_RET(#op)
 
 asm(".pushsection .fixup, \"ax\"\n"
-    ".global kvm_fastop_exception \n"
     "kvm_fastop_exception: xor %esi, %esi; ret\n"
     ".popsection");
 
@@ -4206,7 +4205,7 @@ static int check_rdtsc(struct x86_emulate_ctxt *ctxt)
 	u64 cr4 = ctxt->ops->get_cr(ctxt, 4);
 
 	if (cr4 & X86_CR4_TSD && ctxt->ops->cpl(ctxt))
-		return emulate_ud(ctxt);
+		return emulate_gp(ctxt, 0);
 
 	return X86EMUL_CONTINUE;
 }
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 232a86a6faaf..d5124b520f76 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -939,7 +939,7 @@ static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
 	for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++)
 		stimer_init(&hv_vcpu->stimer[i], i);
 
-	hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu);
+	hv_vcpu->vp_index = vcpu->vcpu_idx;
 
 	return 0;
 }
@@ -1444,7 +1444,6 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 	switch (msr) {
 	case HV_X64_MSR_VP_INDEX: {
 		struct kvm_hv *hv = to_kvm_hv(vcpu->kvm);
-		int vcpu_idx = kvm_vcpu_get_idx(vcpu);
 		u32 new_vp_index = (u32)data;
 
 		if (!host || new_vp_index >= KVM_MAX_VCPUS)
@@ -1459,9 +1458,9 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 		 * VP index is changing, adjust num_mismatched_vp_indexes if
 		 * it now matches or no longer matches vcpu_idx.
 		 */
-		if (hv_vcpu->vp_index == vcpu_idx)
+		if (hv_vcpu->vp_index == vcpu->vcpu_idx)
 			atomic_inc(&hv->num_mismatched_vp_indexes);
-		else if (new_vp_index == vcpu_idx)
+		else if (new_vp_index == vcpu->vcpu_idx)
 			atomic_dec(&hv->num_mismatched_vp_indexes);
 
 		hv_vcpu->vp_index = new_vp_index;
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 730da8537d05..ed1c4e546d04 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -83,7 +83,7 @@ static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
 
-	return hv_vcpu ? hv_vcpu->vp_index : kvm_vcpu_get_idx(vcpu);
+	return hv_vcpu ? hv_vcpu->vp_index : vcpu->vcpu_idx;
 }
 
 int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index ff005fe738a4..8c065da73f8e 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -319,8 +319,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 	unsigned index;
 	bool mask_before, mask_after;
 	union kvm_ioapic_redirect_entry *e;
-	unsigned long vcpu_bitmap;
 	int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode;
+	DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
 
 	switch (ioapic->ioregsel) {
 	case IOAPIC_REG_VERSION:
@@ -384,9 +384,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 			irq.shorthand = APIC_DEST_NOSHORT;
 			irq.dest_id = e->fields.dest_id;
 			irq.msi_redir_hint = false;
-			bitmap_zero(&vcpu_bitmap, 16);
+			bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
 			kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
-						 &vcpu_bitmap);
+						 vcpu_bitmap);
 			if (old_dest_mode != e->fields.dest_mode ||
 			    old_dest_id != e->fields.dest_id) {
 				/*
@@ -399,10 +399,10 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 				    kvm_lapic_irq_dest_mode(
 					!!e->fields.dest_mode);
 				kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
-							 &vcpu_bitmap);
+							 vcpu_bitmap);
 			}
 			kvm_make_scan_ioapic_request_mask(ioapic->kvm,
-							  &vcpu_bitmap);
+							  vcpu_bitmap);
 		} else {
 			kvm_make_scan_ioapic_request(ioapic->kvm);
 		}
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2d7e61122af8..1a64ba5b9437 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2027,8 +2027,8 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents)
 	} while (!sp->unsync_children);
 }
 
-static void mmu_sync_children(struct kvm_vcpu *vcpu,
-			      struct kvm_mmu_page *parent)
+static int mmu_sync_children(struct kvm_vcpu *vcpu,
+			     struct kvm_mmu_page *parent, bool can_yield)
 {
 	int i;
 	struct kvm_mmu_page *sp;
@@ -2055,12 +2055,18 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu,
 		}
 		if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) {
 			kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+			if (!can_yield) {
+				kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
+				return -EINTR;
+			}
+
 			cond_resched_rwlock_write(&vcpu->kvm->mmu_lock);
 			flush = false;
 		}
 	}
 
 	kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
+	return 0;
 }
 
 static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
@@ -2146,9 +2152,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 		}
 
-		if (sp->unsync_children)
-			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
-
 		__clear_sp_write_flooding_count(sp);
 
 trace_get_page:
@@ -3684,7 +3687,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 		write_lock(&vcpu->kvm->mmu_lock);
 		kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
 
-		mmu_sync_children(vcpu, sp);
+		mmu_sync_children(vcpu, sp, true);
 
 		kvm_mmu_audit(vcpu, AUDIT_POST_SYNC);
 		write_unlock(&vcpu->kvm->mmu_lock);
@@ -3700,7 +3703,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 		if (IS_VALID_PAE_ROOT(root)) {
 			root &= PT64_BASE_ADDR_MASK;
 			sp = to_shadow_page(root);
-			mmu_sync_children(vcpu, sp);
+			mmu_sync_children(vcpu, sp, true);
 		}
 	}
 
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 269f11f92fd0..21427e84a82e 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -164,13 +164,13 @@ void kvm_page_track_cleanup(struct kvm *kvm)
 	cleanup_srcu_struct(&head->track_srcu);
 }
 
-void kvm_page_track_init(struct kvm *kvm)
+int kvm_page_track_init(struct kvm *kvm)
 {
 	struct kvm_page_track_notifier_head *head;
 
 	head = &kvm->arch.track_notifier_head;
-	init_srcu_struct(&head->track_srcu);
 	INIT_HLIST_HEAD(&head->track_notifier_list);
+	return init_srcu_struct(&head->track_srcu);
 }
 
 /*
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 7d03e9b7ccfa..913d52a7923e 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -707,8 +707,27 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 		if (!is_shadow_present_pte(*it.sptep)) {
 			table_gfn = gw->table_gfn[it.level - 2];
 			access = gw->pt_access[it.level - 2];
-			sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1,
-					      false, access);
+			sp = kvm_mmu_get_page(vcpu, table_gfn, addr,
+					      it.level-1, false, access);
+			/*
+			 * We must synchronize the pagetable before linking it
+			 * because the guest doesn't need to flush tlb when
+			 * the gpte is changed from non-present to present.
+			 * Otherwise, the guest may use the wrong mapping.
+			 *
+			 * For PG_LEVEL_4K, kvm_mmu_get_page() has already
+			 * synchronized it transiently via kvm_sync_page().
+			 *
+			 * For higher level pagetable, we synchronize it via
+			 * the slower mmu_sync_children().  If it needs to
+			 * break, some progress has been made; return
+			 * RET_PF_RETRY and retry on the next #PF.
+			 * KVM_REQ_MMU_SYNC is not necessary but it
+			 * expedites the process.
+			 */
+			if (sp->unsync_children &&
+			    mmu_sync_children(vcpu, sp, false))
+				return RET_PF_RETRY;
 		}
 
 		/*
@@ -1047,14 +1066,6 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr,
  * Using the cached information from sp->gfns is safe because:
  * - The spte has a reference to the struct page, so the pfn for a given gfn
  *   can't change unless all sptes pointing to it are nuked first.
- *
- * Note:
- *   We should flush all tlbs if spte is dropped even though guest is
- *   responsible for it. Since if we don't, kvm_mmu_notifier_invalidate_page
- *   and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't
- *   used by guest then tlbs are not flushed, so guest is allowed to access the
- *   freed pages.
- *   And we increase kvm->tlbs_dirty to delay tlbs flush in this case.
  */
 static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
@@ -1107,13 +1118,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 			return 0;
 
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
-			/*
-			 * Update spte before increasing tlbs_dirty to make
-			 * sure no tlb flush is lost after spte is zapped; see
-			 * the comments in kvm_flush_remote_tlbs().
-			 */
-			smp_wmb();
-			vcpu->kvm->tlbs_dirty++;
+			set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
 			continue;
 		}
 
@@ -1128,12 +1133,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		if (gfn != sp->gfns[i]) {
 			drop_spte(vcpu->kvm, &sp->spt[i]);
-			/*
-			 * The same as above where we are doing
-			 * prefetch_invalid_gpte().
-			 */
-			smp_wmb();
-			vcpu->kvm->tlbs_dirty++;
+			set_spte_ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
 			continue;
 		}
 
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 2545d0c61985..510b833cbd39 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -545,7 +545,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 		(svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) |
 		(svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits);
 
-	svm->vmcb->control.virt_ext            = svm->nested.ctl.virt_ext;
 	svm->vmcb->control.int_vector          = svm->nested.ctl.int_vector;
 	svm->vmcb->control.int_state           = svm->nested.ctl.int_state;
 	svm->vmcb->control.event_inj           = svm->nested.ctl.event_inj;
@@ -579,7 +578,7 @@ static void nested_svm_copy_common_state(struct vmcb *from_vmcb, struct vmcb *to
 }
 
 int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
-			 struct vmcb *vmcb12)
+			 struct vmcb *vmcb12, bool from_vmrun)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	int ret;
@@ -609,13 +608,16 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
 	nested_vmcb02_prepare_save(svm, vmcb12);
 
 	ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3,
-				  nested_npt_enabled(svm), true);
+				  nested_npt_enabled(svm), from_vmrun);
 	if (ret)
 		return ret;
 
 	if (!npt_enabled)
 		vcpu->arch.mmu->inject_page_fault = svm_inject_page_fault_nested;
 
+	if (!from_vmrun)
+		kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+
 	svm_set_gif(svm, true);
 
 	return 0;
@@ -681,7 +683,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 
 	svm->nested.nested_run_pending = 1;
 
-	if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12))
+	if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true))
 		goto out_exit_err;
 
 	if (nested_svm_vmrun_msrpm(svm))
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 75e0b21ad07c..c36b5fe4c27c 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -595,43 +595,50 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 	return 0;
 }
 
-static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
+static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
+				    int *error)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_data_launch_update_vmsa vmsa;
+	struct vcpu_svm *svm = to_svm(vcpu);
+	int ret;
+
+	/* Perform some pre-encryption checks against the VMSA */
+	ret = sev_es_sync_vmsa(svm);
+	if (ret)
+		return ret;
+
+	/*
+	 * The LAUNCH_UPDATE_VMSA command will perform in-place encryption of
+	 * the VMSA memory content (i.e it will write the same memory region
+	 * with the guest's key), so invalidate it first.
+	 */
+	clflush_cache_range(svm->vmsa, PAGE_SIZE);
+
+	vmsa.reserved = 0;
+	vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
+	vmsa.address = __sme_pa(svm->vmsa);
+	vmsa.len = PAGE_SIZE;
+	return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+}
+
+static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
 	struct kvm_vcpu *vcpu;
 	int i, ret;
 
 	if (!sev_es_guest(kvm))
 		return -ENOTTY;
 
-	vmsa.reserved = 0;
-
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		struct vcpu_svm *svm = to_svm(vcpu);
-
-		/* Perform some pre-encryption checks against the VMSA */
-		ret = sev_es_sync_vmsa(svm);
+		ret = mutex_lock_killable(&vcpu->mutex);
 		if (ret)
 			return ret;
 
-		/*
-		 * The LAUNCH_UPDATE_VMSA command will perform in-place
-		 * encryption of the VMSA memory content (i.e it will write
-		 * the same memory region with the guest's key), so invalidate
-		 * it first.
-		 */
-		clflush_cache_range(svm->vmsa, PAGE_SIZE);
+		ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error);
 
-		vmsa.handle = sev->handle;
-		vmsa.address = __sme_pa(svm->vmsa);
-		vmsa.len = PAGE_SIZE;
-		ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa,
-				    &argp->error);
+		mutex_unlock(&vcpu->mutex);
 		if (ret)
 			return ret;
-
-		svm->vcpu.arch.guest_state_protected = true;
 	}
 
 	return 0;
@@ -1397,8 +1404,10 @@ static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	/* Bind ASID to this guest */
 	ret = sev_bind_asid(kvm, start.handle, error);
-	if (ret)
+	if (ret) {
+		sev_decommission(start.handle);
 		goto e_free_session;
+	}
 
 	params.handle = start.handle;
 	if (copy_to_user((void __user *)(uintptr_t)argp->data,
@@ -1464,7 +1473,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	/* Pin guest memory */
 	guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
-				    PAGE_SIZE, &n, 0);
+				    PAGE_SIZE, &n, 1);
 	if (IS_ERR(guest_page)) {
 		ret = PTR_ERR(guest_page);
 		goto e_free_trans;
@@ -1501,6 +1510,20 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
 }
 
+static bool cmd_allowed_from_miror(u32 cmd_id)
+{
+	/*
+	 * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES
+	 * active mirror VMs. Also allow the debugging and status commands.
+	 */
+	if (cmd_id == KVM_SEV_LAUNCH_UPDATE_VMSA ||
+	    cmd_id == KVM_SEV_GUEST_STATUS || cmd_id == KVM_SEV_DBG_DECRYPT ||
+	    cmd_id == KVM_SEV_DBG_ENCRYPT)
+		return true;
+
+	return false;
+}
+
 int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;
@@ -1517,8 +1540,9 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 
 	mutex_lock(&kvm->lock);
 
-	/* enc_context_owner handles all memory enc operations */
-	if (is_mirroring_enc_context(kvm)) {
+	/* Only the enc_context_owner handles some memory enc operations. */
+	if (is_mirroring_enc_context(kvm) &&
+	    !cmd_allowed_from_miror(sev_cmd.id)) {
 		r = -EINVAL;
 		goto out;
 	}
@@ -1715,8 +1739,7 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 {
 	struct file *source_kvm_file;
 	struct kvm *source_kvm;
-	struct kvm_sev_info *mirror_sev;
-	unsigned int asid;
+	struct kvm_sev_info source_sev, *mirror_sev;
 	int ret;
 
 	source_kvm_file = fget(source_fd);
@@ -1739,7 +1762,8 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 		goto e_source_unlock;
 	}
 
-	asid = to_kvm_svm(source_kvm)->sev_info.asid;
+	memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info,
+	       sizeof(source_sev));
 
 	/*
 	 * The mirror kvm holds an enc_context_owner ref so its asid can't
@@ -1759,8 +1783,16 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 	/* Set enc_context_owner and copy its encryption context over */
 	mirror_sev = &to_kvm_svm(kvm)->sev_info;
 	mirror_sev->enc_context_owner = source_kvm;
-	mirror_sev->asid = asid;
 	mirror_sev->active = true;
+	mirror_sev->asid = source_sev.asid;
+	mirror_sev->fd = source_sev.fd;
+	mirror_sev->es_active = source_sev.es_active;
+	mirror_sev->handle = source_sev.handle;
+	/*
+	 * Do not copy ap_jump_table. Since the mirror does not share the same
+	 * KVM contexts as the original, and they may have different
+	 * memory-views.
+	 */
 
 	mutex_unlock(&kvm->lock);
 	return 0;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 05e8d4d27969..989685098b3e 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1566,6 +1566,8 @@ static void svm_clear_vintr(struct vcpu_svm *svm)
 
 		svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl &
 			V_IRQ_INJECTION_BITS_MASK;
+
+		svm->vmcb->control.int_vector = svm->nested.ctl.int_vector;
 	}
 
 	vmcb_mark_dirty(svm->vmcb, VMCB_INTR);
@@ -2222,6 +2224,10 @@ static int gp_interception(struct kvm_vcpu *vcpu)
 	if (error_code)
 		goto reinject;
 
+	/* All SVM instructions expect page aligned RAX */
+	if (svm->vmcb->save.rax & ~PAGE_MASK)
+		goto reinject;
+
 	/* Decode the instruction for usage later */
 	if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK)
 		goto reinject;
@@ -4285,43 +4291,44 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 	struct kvm_host_map map_save;
 	int ret;
 
-	if (is_guest_mode(vcpu)) {
-		/* FED8h - SVM Guest */
-		put_smstate(u64, smstate, 0x7ed8, 1);
-		/* FEE0h - SVM Guest VMCB Physical Address */
-		put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
+	if (!is_guest_mode(vcpu))
+		return 0;
 
-		svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
-		svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
-		svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
+	/* FED8h - SVM Guest */
+	put_smstate(u64, smstate, 0x7ed8, 1);
+	/* FEE0h - SVM Guest VMCB Physical Address */
+	put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
 
-		ret = nested_svm_vmexit(svm);
-		if (ret)
-			return ret;
+	svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
+	svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
+	svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
 
-		/*
-		 * KVM uses VMCB01 to store L1 host state while L2 runs but
-		 * VMCB01 is going to be used during SMM and thus the state will
-		 * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save
-		 * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the
-		 * format of the area is identical to guest save area offsetted
-		 * by 0x400 (matches the offset of 'struct vmcb_save_area'
-		 * within 'struct vmcb'). Note: HSAVE area may also be used by
-		 * L1 hypervisor to save additional host context (e.g. KVM does
-		 * that, see svm_prepare_guest_switch()) which must be
-		 * preserved.
-		 */
-		if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
-				 &map_save) == -EINVAL)
-			return 1;
+	ret = nested_svm_vmexit(svm);
+	if (ret)
+		return ret;
 
-		BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
+	/*
+	 * KVM uses VMCB01 to store L1 host state while L2 runs but
+	 * VMCB01 is going to be used during SMM and thus the state will
+	 * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save
+	 * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the
+	 * format of the area is identical to guest save area offsetted
+	 * by 0x400 (matches the offset of 'struct vmcb_save_area'
+	 * within 'struct vmcb'). Note: HSAVE area may also be used by
+	 * L1 hypervisor to save additional host context (e.g. KVM does
+	 * that, see svm_prepare_guest_switch()) which must be
+	 * preserved.
+	 */
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
+			 &map_save) == -EINVAL)
+		return 1;
 
-		svm_copy_vmrun_state(map_save.hva + 0x400,
-				     &svm->vmcb01.ptr->save);
+	BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
 
-		kvm_vcpu_unmap(vcpu, &map_save, true);
-	}
+	svm_copy_vmrun_state(map_save.hva + 0x400,
+			     &svm->vmcb01.ptr->save);
+
+	kvm_vcpu_unmap(vcpu, &map_save, true);
 	return 0;
 }
 
@@ -4329,50 +4336,54 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct kvm_host_map map, map_save;
-	int ret = 0;
+	u64 saved_efer, vmcb12_gpa;
+	struct vmcb *vmcb12;
+	int ret;
 
-	if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
-		u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
-		u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
-		u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
-		struct vmcb *vmcb12;
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+		return 0;
 
-		if (guest) {
-			if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
-				return 1;
+	/* Non-zero if SMI arrived while vCPU was in guest mode. */
+	if (!GET_SMSTATE(u64, smstate, 0x7ed8))
+		return 0;
 
-			if (!(saved_efer & EFER_SVME))
-				return 1;
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+		return 1;
 
-			if (kvm_vcpu_map(vcpu,
-					 gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
-				return 1;
+	saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
+	if (!(saved_efer & EFER_SVME))
+		return 1;
 
-			if (svm_allocate_nested(svm))
-				return 1;
+	vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
+		return 1;
 
-			vmcb12 = map.hva;
+	ret = 1;
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL)
+		goto unmap_map;
 
-			nested_load_control_from_vmcb12(svm, &vmcb12->control);
+	if (svm_allocate_nested(svm))
+		goto unmap_save;
 
-			ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12);
-			kvm_vcpu_unmap(vcpu, &map, true);
+	/*
+	 * Restore L1 host state from L1 HSAVE area as VMCB01 was
+	 * used during SMM (see svm_enter_smm())
+	 */
 
-			/*
-			 * Restore L1 host state from L1 HSAVE area as VMCB01 was
-			 * used during SMM (see svm_enter_smm())
-			 */
-			if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
-					 &map_save) == -EINVAL)
-				return 1;
+	svm_copy_vmrun_state(&svm->vmcb01.ptr->save, map_save.hva + 0x400);
 
-			svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
-					     map_save.hva + 0x400);
+	/*
+	 * Enter the nested guest now
+	 */
 
-			kvm_vcpu_unmap(vcpu, &map_save, true);
-		}
-	}
+	vmcb12 = map.hva;
+	nested_load_control_from_vmcb12(svm, &vmcb12->control);
+	ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false);
 
+unmap_save:
+	kvm_vcpu_unmap(vcpu, &map_save, true);
+unmap_map:
+	kvm_vcpu_unmap(vcpu, &map, true);
 	return ret;
 }
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 524d943f3efc..128a54b1fbf1 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -459,7 +459,8 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm)
 	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI);
 }
 
-int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12);
+int enter_svm_guest_mode(struct kvm_vcpu *vcpu,
+			 u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun);
 void svm_leave_nested(struct vcpu_svm *svm);
 void svm_free_nested(struct vcpu_svm *svm);
 int svm_allocate_nested(struct vcpu_svm *svm);
diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c
index 0dab1b7b529f..ba6f99f584ac 100644
--- a/arch/x86/kvm/vmx/evmcs.c
+++ b/arch/x86/kvm/vmx/evmcs.c
@@ -353,14 +353,20 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata)
 	switch (msr_index) {
 	case MSR_IA32_VMX_EXIT_CTLS:
 	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
-		ctl_high &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+		ctl_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
 		break;
 	case MSR_IA32_VMX_ENTRY_CTLS:
 	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
-		ctl_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+		ctl_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
 		break;
 	case MSR_IA32_VMX_PROCBASED_CTLS2:
-		ctl_high &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+		ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
+		break;
+	case MSR_IA32_VMX_PINBASED_CTLS:
+		ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+		break;
+	case MSR_IA32_VMX_VMFUNC:
+		ctl_low &= ~EVMCS1_UNSUPPORTED_VMFUNC;
 		break;
 	}
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index ccb03d69546c..eedcebf58004 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2583,8 +2583,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * Guest state is invalid and unrestricted guest is disabled,
 	 * which means L1 attempted VMEntry to L2 with invalid state.
 	 * Fail the VMEntry.
+	 *
+	 * However when force loading the guest state (SMM exit or
+	 * loading nested state after migration, it is possible to
+	 * have invalid guest state now, which will be later fixed by
+	 * restoring L2 register state
 	 */
-	if (CC(!vmx_guest_state_valid(vcpu))) {
+	if (CC(from_vmentry && !vmx_guest_state_valid(vcpu))) {
 		*entry_failure_code = ENTRY_FAIL_DEFAULT;
 		return -EINVAL;
 	}
@@ -4351,6 +4356,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
 				vmcs12->vm_exit_msr_load_count))
 		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
+
+	to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
 }
 
 static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
@@ -4899,14 +4906,7 @@ out_vmcs02:
 	return -ENOMEM;
 }
 
-/*
- * Emulate the VMXON instruction.
- * Currently, we just remember that VMX is active, and do not save or even
- * inspect the argument to VMXON (the so-called "VMXON pointer") because we
- * do not currently need to store anything in that guest-allocated memory
- * region. Consequently, VMCLEAR and VMPTRLD also do not verify that the their
- * argument is different from the VMXON pointer (which the spec says they do).
- */
+/* Emulate the VMXON instruction. */
 static int handle_vmon(struct kvm_vcpu *vcpu)
 {
 	int ret;
@@ -5903,6 +5903,12 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 	case EXIT_REASON_VMFUNC:
 		/* VM functions are emulated through L2->L0 vmexits. */
 		return true;
+	case EXIT_REASON_BUS_LOCK:
+		/*
+		 * At present, bus lock VM exit is never exposed to L1.
+		 * Handle L2's bus locks in L0 directly.
+		 */
+		return true;
 	default:
 		break;
 	}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 0c2c0d5ae873..116b08904ac3 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1323,7 +1323,7 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 	vmx_prepare_switch_to_host(to_vmx(vcpu));
 }
 
-static bool emulation_required(struct kvm_vcpu *vcpu)
+bool vmx_emulation_required(struct kvm_vcpu *vcpu)
 {
 	return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu);
 }
@@ -1367,7 +1367,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	vmcs_writel(GUEST_RFLAGS, rflags);
 
 	if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM)
-		vmx->emulation_required = emulation_required(vcpu);
+		vmx->emulation_required = vmx_emulation_required(vcpu);
 }
 
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
@@ -1837,10 +1837,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 				    &msr_info->data))
 			return 1;
 		/*
-		 * Enlightened VMCS v1 doesn't have certain fields, but buggy
-		 * Hyper-V versions are still trying to use corresponding
-		 * features when they are exposed. Filter out the essential
-		 * minimum.
+		 * Enlightened VMCS v1 doesn't have certain VMCS fields but
+		 * instead of just ignoring the features, different Hyper-V
+		 * versions are either trying to use them and fail or do some
+		 * sanity checking and refuse to boot. Filter all unsupported
+		 * features out.
 		 */
 		if (!msr_info->host_initiated &&
 		    vmx->nested.enlightened_vmcs_enabled)
@@ -3077,7 +3078,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	}
 
 	/* depends on vcpu->arch.cr0 to be set to a new value */
-	vmx->emulation_required = emulation_required(vcpu);
+	vmx->emulation_required = vmx_emulation_required(vcpu);
 }
 
 static int vmx_get_max_tdp_level(void)
@@ -3330,7 +3331,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int
 {
 	__vmx_set_segment(vcpu, var, seg);
 
-	to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
+	to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
 }
 
 static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
@@ -6621,10 +6622,24 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		     vmx->loaded_vmcs->soft_vnmi_blocked))
 		vmx->loaded_vmcs->entry_time = ktime_get();
 
-	/* Don't enter VMX if guest state is invalid, let the exit handler
-	   start emulation until we arrive back to a valid state */
-	if (vmx->emulation_required)
+	/*
+	 * Don't enter VMX if guest state is invalid, let the exit handler
+	 * start emulation until we arrive back to a valid state.  Synthesize a
+	 * consistency check VM-Exit due to invalid guest state and bail.
+	 */
+	if (unlikely(vmx->emulation_required)) {
+
+		/* We don't emulate invalid state of a nested guest */
+		vmx->fail = is_guest_mode(vcpu);
+
+		vmx->exit_reason.full = EXIT_REASON_INVALID_STATE;
+		vmx->exit_reason.failed_vmentry = 1;
+		kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1);
+		vmx->exit_qualification = ENTRY_FAIL_DEFAULT;
+		kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2);
+		vmx->exit_intr_info = 0;
 		return EXIT_FASTPATH_NONE;
+	}
 
 	trace_kvm_entry(vcpu);
 
@@ -6833,7 +6848,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 		 */
 		tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL);
 		if (tsx_ctrl)
-			vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
+			tsx_ctrl->mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
 	}
 
 	err = alloc_loaded_vmcs(&vmx->vmcs01);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 4858c5fd95f2..592217fd7d92 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -248,12 +248,8 @@ struct vcpu_vmx {
 	 * only loaded into hardware when necessary, e.g. SYSCALL #UDs outside
 	 * of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to
 	 * be loaded into hardware if those conditions aren't met.
-	 * nr_active_uret_msrs tracks the number of MSRs that need to be loaded
-	 * into hardware when running the guest.  guest_uret_msrs[] is resorted
-	 * whenever the number of "active" uret MSRs is modified.
 	 */
 	struct vmx_uret_msr   guest_uret_msrs[MAX_NR_USER_RETURN_MSRS];
-	int                   nr_active_uret_msrs;
 	bool                  guest_uret_msrs_loaded;
 #ifdef CONFIG_X86_64
 	u64		      msr_host_kernel_gs_base;
@@ -359,6 +355,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
 void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
 			unsigned long fs_base, unsigned long gs_base);
 int vmx_get_cpl(struct kvm_vcpu *vcpu);
+bool vmx_emulation_required(struct kvm_vcpu *vcpu);
 unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu);
 void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 28ef14155726..aabd3a2ec1bc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1332,6 +1332,13 @@ static const u32 msrs_to_save_all[] = {
 	MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
+
+	MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3,
+	MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3,
+	MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2,
+	MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5,
+	MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2,
+	MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5,
 };
 
 static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
@@ -2969,7 +2976,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 				       offsetof(struct compat_vcpu_info, time));
 	if (vcpu->xen.vcpu_time_info_set)
 		kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0);
-	if (v == kvm_get_vcpu(v->kvm, 0))
+	if (!v->vcpu_idx)
 		kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
 	return 0;
 }
@@ -7658,6 +7665,13 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
 
 		/* Process a latched INIT or SMI, if any.  */
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+		/*
+		 * Even if KVM_SET_SREGS2 loaded PDPTRs out of band,
+		 * on SMM exit we still need to reload them from
+		 * guest memory
+		 */
+		vcpu->arch.pdptrs_from_userspace = false;
 	}
 
 	kvm_mmu_reset_context(vcpu);
@@ -10652,6 +10666,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	int r;
 
 	vcpu->arch.last_vmentry_cpu = -1;
+	vcpu->arch.regs_avail = ~0;
+	vcpu->arch.regs_dirty = ~0;
 
 	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -10893,6 +10909,9 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
 	kvm_rip_write(vcpu, 0xfff0);
 
+	vcpu->arch.cr3 = 0;
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);
+
 	/*
 	 * CR0.CD/NW are set on RESET, preserved on INIT.  Note, some versions
 	 * of Intel's SDM list CD/NW as being set on INIT, but they contradict
@@ -11139,9 +11158,15 @@ void kvm_arch_free_vm(struct kvm *kvm)
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
+	int ret;
+
 	if (type)
 		return -EINVAL;
 
+	ret = kvm_page_track_init(kvm);
+	if (ret)
+		return ret;
+
 	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
@@ -11174,7 +11199,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	kvm_apicv_init(kvm);
 	kvm_hv_init_vm(kvm);
-	kvm_page_track_init(kvm);
 	kvm_mmu_init_vm(kvm);
 	kvm_xen_init_vm(kvm);
 
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 058f19b20465..c565def611e2 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -37,10 +37,10 @@
 	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
 
 #define __get_next(t, insn)	\
-	({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); leXX_to_cpu(t, r); })
+	({ t r; memcpy(&r, insn->next_byte, sizeof(t)); insn->next_byte += sizeof(t); leXX_to_cpu(t, r); })
 
 #define __peek_nbyte_next(t, insn, n)	\
-	({ t r = *(t*)((insn)->next_byte + n); leXX_to_cpu(t, r); })
+	({ t r; memcpy(&r, (insn)->next_byte + n, sizeof(t)); leXX_to_cpu(t, r); })
 
 #define get_next(t, insn)	\
 	({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index b2eefdefc108..84a2c8c4af73 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -710,7 +710,8 @@ oops:
 
 static noinline void
 kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code,
-			 unsigned long address, int signal, int si_code)
+			 unsigned long address, int signal, int si_code,
+			 u32 pkey)
 {
 	WARN_ON_ONCE(user_mode(regs));
 
@@ -735,8 +736,12 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code,
 
 			set_signal_archinfo(address, error_code);
 
-			/* XXX: hwpoison faults will set the wrong code. */
-			force_sig_fault(signal, si_code, (void __user *)address);
+			if (si_code == SEGV_PKUERR) {
+				force_sig_pkuerr((void __user *)address, pkey);
+			} else {
+				/* XXX: hwpoison faults will set the wrong code. */
+				force_sig_fault(signal, si_code, (void __user *)address);
+			}
 		}
 
 		/*
@@ -798,7 +803,8 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 	struct task_struct *tsk = current;
 
 	if (!user_mode(regs)) {
-		kernelmode_fixup_or_oops(regs, error_code, address, pkey, si_code);
+		kernelmode_fixup_or_oops(regs, error_code, address,
+					 SIGSEGV, si_code, pkey);
 		return;
 	}
 
@@ -930,7 +936,8 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 {
 	/* Kernel mode? Handle exceptions or die: */
 	if (!user_mode(regs)) {
-		kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR);
+		kernelmode_fixup_or_oops(regs, error_code, address,
+					 SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY);
 		return;
 	}
 
@@ -1396,7 +1403,8 @@ good_area:
 		 */
 		if (!user_mode(regs))
 			kernelmode_fixup_or_oops(regs, error_code, address,
-						 SIGBUS, BUS_ADRERR);
+						 SIGBUS, BUS_ADRERR,
+						 ARCH_DEFAULT_PKEY);
 		return;
 	}
 
@@ -1416,7 +1424,8 @@ good_area:
 		return;
 
 	if (fatal_signal_pending(current) && !user_mode(regs)) {
-		kernelmode_fixup_or_oops(regs, error_code, address, 0, 0);
+		kernelmode_fixup_or_oops(regs, error_code, address,
+					 0, 0, ARCH_DEFAULT_PKEY);
 		return;
 	}
 
@@ -1424,7 +1433,8 @@ good_area:
 		/* Kernel mode? Handle exceptions or die: */
 		if (!user_mode(regs)) {
 			kernelmode_fixup_or_oops(regs, error_code, address,
-						 SIGSEGV, SEGV_MAPERR);
+						 SIGSEGV, SEGV_MAPERR,
+						 ARCH_DEFAULT_PKEY);
 			return;
 		}
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a6e11763763f..36098226a957 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1432,18 +1432,18 @@ int kern_addr_valid(unsigned long addr)
 		return 0;
 
 	p4d = p4d_offset(pgd, addr);
-	if (p4d_none(*p4d))
+	if (!p4d_present(*p4d))
 		return 0;
 
 	pud = pud_offset(p4d, addr);
-	if (pud_none(*pud))
+	if (!pud_present(*pud))
 		return 0;
 
 	if (pud_large(*pud))
 		return pfn_valid(pud_pfn(*pud));
 
 	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	if (!pmd_present(*pmd))
 		return 0;
 
 	if (pmd_large(*pmd))
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 1a50434c8a4d..ef885370719a 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -49,8 +49,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
 			p = early_alloc(PMD_SIZE, nid, false);
 			if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
 				return;
-			else if (p)
-				memblock_free(__pa(p), PMD_SIZE);
+			memblock_free_ptr(p, PMD_SIZE);
 		}
 
 		p = early_alloc(PAGE_SIZE, nid, true);
@@ -86,8 +85,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
 			p = early_alloc(PUD_SIZE, nid, false);
 			if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL))
 				return;
-			else if (p)
-				memblock_free(__pa(p), PUD_SIZE);
+			memblock_free_ptr(p, PUD_SIZE);
 		}
 
 		p = early_alloc(PAGE_SIZE, nid, true);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index a1b5c71099e6..1e9b93b088db 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -355,7 +355,7 @@ void __init numa_reset_distance(void)
 
 	/* numa_distance could be 1LU marking allocation failure, test cnt */
 	if (numa_distance_cnt)
-		memblock_free(__pa(numa_distance), size);
+		memblock_free_ptr(numa_distance, size);
 	numa_distance_cnt = 0;
 	numa_distance = NULL;	/* enable table creation */
 }
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index 737491b13728..e801e30089c4 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -517,8 +517,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	}
 
 	/* free the copied physical distance table */
-	if (phys_dist)
-		memblock_free(__pa(phys_dist), phys_size);
+	memblock_free_ptr(phys_dist, phys_size);
 	return;
 
 no_emu:
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 3112ca7786ed..4ba2a3ee4bce 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -583,7 +583,12 @@ int memtype_reserve(u64 start, u64 end, enum page_cache_mode req_type,
 	int err = 0;
 
 	start = sanitize_phys(start);
-	end = sanitize_phys(end);
+
+	/*
+	 * The end address passed into this function is exclusive, but
+	 * sanitize_phys() expects an inclusive address.
+	 */
+	end = sanitize_phys(end - 1) + 1;
 	if (start >= end) {
 		WARN(1, "%s failed: [mem %#010Lx-%#010Lx], req %s\n", __func__,
 				start, end - 1, cattr_name(req_type));
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 0fe6aacef3db..9ea57389c554 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1341,9 +1341,10 @@ st:			if (is_imm8(insn->off))
 			if (insn->imm == (BPF_AND | BPF_FETCH) ||
 			    insn->imm == (BPF_OR | BPF_FETCH) ||
 			    insn->imm == (BPF_XOR | BPF_FETCH)) {
-				u8 *branch_target;
 				bool is64 = BPF_SIZE(insn->code) == BPF_DW;
 				u32 real_src_reg = src_reg;
+				u32 real_dst_reg = dst_reg;
+				u8 *branch_target;
 
 				/*
 				 * Can't be implemented with a single x86 insn.
@@ -1354,11 +1355,13 @@ st:			if (is_imm8(insn->off))
 				emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0);
 				if (src_reg == BPF_REG_0)
 					real_src_reg = BPF_REG_AX;
+				if (dst_reg == BPF_REG_0)
+					real_dst_reg = BPF_REG_AX;
 
 				branch_target = prog;
 				/* Load old value */
 				emit_ldx(&prog, BPF_SIZE(insn->code),
-					 BPF_REG_0, dst_reg, insn->off);
+					 BPF_REG_0, real_dst_reg, insn->off);
 				/*
 				 * Perform the (commutative) operation locally,
 				 * put the result in the AUX_REG.
@@ -1369,7 +1372,8 @@ st:			if (is_imm8(insn->off))
 				      add_2reg(0xC0, AUX_REG, real_src_reg));
 				/* Attempt to swap in new value */
 				err = emit_atomic(&prog, BPF_CMPXCHG,
-						  dst_reg, AUX_REG, insn->off,
+						  real_dst_reg, AUX_REG,
+						  insn->off,
 						  BPF_SIZE(insn->code));
 				if (WARN_ON(err))
 					return err;
@@ -1383,11 +1387,10 @@ st:			if (is_imm8(insn->off))
 				/* Restore R0 after clobbering RAX */
 				emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX);
 				break;
-
 			}
 
 			err = emit_atomic(&prog, insn->imm, dst_reg, src_reg,
-						  insn->off, BPF_SIZE(insn->code));
+					  insn->off, BPF_SIZE(insn->code));
 			if (err)
 				return err;
 			break;
@@ -1744,7 +1747,7 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
 }
 
 static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
-			   struct bpf_prog *p, int stack_size, bool mod_ret)
+			   struct bpf_prog *p, int stack_size, bool save_ret)
 {
 	u8 *prog = *pprog;
 	u8 *jmp_insn;
@@ -1777,11 +1780,15 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	if (emit_call(&prog, p->bpf_func, prog))
 		return -EINVAL;
 
-	/* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return
+	/*
+	 * BPF_TRAMP_MODIFY_RETURN trampolines can modify the return
 	 * of the previous call which is then passed on the stack to
 	 * the next BPF program.
+	 *
+	 * BPF_TRAMP_FENTRY trampoline may need to return the return
+	 * value of BPF_PROG_TYPE_STRUCT_OPS prog.
 	 */
-	if (mod_ret)
+	if (save_ret)
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 
 	/* replace 2 nops with JE insn, since jmp target is known */
@@ -1828,13 +1835,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
 }
 
 static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
-		      struct bpf_tramp_progs *tp, int stack_size)
+		      struct bpf_tramp_progs *tp, int stack_size,
+		      bool save_ret)
 {
 	int i;
 	u8 *prog = *pprog;
 
 	for (i = 0; i < tp->nr_progs; i++) {
-		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false))
+		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size,
+				    save_ret))
 			return -EINVAL;
 	}
 	*pprog = prog;
@@ -1877,6 +1886,23 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
 	return 0;
 }
 
+static bool is_valid_bpf_tramp_flags(unsigned int flags)
+{
+	if ((flags & BPF_TRAMP_F_RESTORE_REGS) &&
+	    (flags & BPF_TRAMP_F_SKIP_FRAME))
+		return false;
+
+	/*
+	 * BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops,
+	 * and it must be used alone.
+	 */
+	if ((flags & BPF_TRAMP_F_RET_FENTRY_RET) &&
+	    (flags & ~BPF_TRAMP_F_RET_FENTRY_RET))
+		return false;
+
+	return true;
+}
+
 /* Example:
  * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
  * its 'struct btf_func_model' will be nr_args=2
@@ -1949,17 +1975,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN];
 	u8 **branches = NULL;
 	u8 *prog;
+	bool save_ret;
 
 	/* x86-64 supports up to 6 arguments. 7+ can be added in the future */
 	if (nr_args > 6)
 		return -ENOTSUPP;
 
-	if ((flags & BPF_TRAMP_F_RESTORE_REGS) &&
-	    (flags & BPF_TRAMP_F_SKIP_FRAME))
+	if (!is_valid_bpf_tramp_flags(flags))
 		return -EINVAL;
 
-	if (flags & BPF_TRAMP_F_CALL_ORIG)
-		stack_size += 8; /* room for return value of orig_call */
+	/* room for return value of orig_call or fentry prog */
+	save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET);
+	if (save_ret)
+		stack_size += 8;
 
 	if (flags & BPF_TRAMP_F_IP_ARG)
 		stack_size += 8; /* room for IP address argument */
@@ -2005,7 +2033,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	}
 
 	if (fentry->nr_progs)
-		if (invoke_bpf(m, &prog, fentry, stack_size))
+		if (invoke_bpf(m, &prog, fentry, stack_size,
+			       flags & BPF_TRAMP_F_RET_FENTRY_RET))
 			return -EINVAL;
 
 	if (fmod_ret->nr_progs) {
@@ -2052,7 +2081,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	}
 
 	if (fexit->nr_progs)
-		if (invoke_bpf(m, &prog, fexit, stack_size)) {
+		if (invoke_bpf(m, &prog, fexit, stack_size, false)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
@@ -2072,9 +2101,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 			ret = -EINVAL;
 			goto cleanup;
 		}
-		/* restore original return value back into RAX */
-		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
 	}
+	/* restore return value of orig_call or fentry prog back into RAX */
+	if (save_ret)
+		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
 
 	EMIT1(0x5B); /* pop rbx */
 	EMIT1(0xC9); /* leave */
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 753f63734c13..6e0d0754f94f 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -755,8 +755,8 @@ static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g)
 	preempt_enable();
 }
 
-static void xen_convert_trap_info(const struct desc_ptr *desc,
-				  struct trap_info *traps)
+static unsigned xen_convert_trap_info(const struct desc_ptr *desc,
+				      struct trap_info *traps, bool full)
 {
 	unsigned in, out, count;
 
@@ -766,17 +766,18 @@ static void xen_convert_trap_info(const struct desc_ptr *desc,
 	for (in = out = 0; in < count; in++) {
 		gate_desc *entry = (gate_desc *)(desc->address) + in;
 
-		if (cvt_gate_to_trap(in, entry, &traps[out]))
+		if (cvt_gate_to_trap(in, entry, &traps[out]) || full)
 			out++;
 	}
-	traps[out].address = 0;
+
+	return out;
 }
 
 void xen_copy_trap_info(struct trap_info *traps)
 {
 	const struct desc_ptr *desc = this_cpu_ptr(&idt_desc);
 
-	xen_convert_trap_info(desc, traps);
+	xen_convert_trap_info(desc, traps, true);
 }
 
 /* Load a new IDT into Xen.  In principle this can be per-CPU, so we
@@ -786,6 +787,7 @@ static void xen_load_idt(const struct desc_ptr *desc)
 {
 	static DEFINE_SPINLOCK(lock);
 	static struct trap_info traps[257];
+	unsigned out;
 
 	trace_xen_cpu_load_idt(desc);
 
@@ -793,7 +795,8 @@ static void xen_load_idt(const struct desc_ptr *desc)
 
 	memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc));
 
-	xen_convert_trap_info(desc, traps);
+	out = xen_convert_trap_info(desc, traps, false);
+	memset(&traps[out], 0, sizeof(traps[0]));
 
 	xen_mc_flush();
 	if (HYPERVISOR_set_trap_table(traps))
@@ -1214,6 +1217,11 @@ static void __init xen_dom0_set_legacy_features(void)
 	x86_platform.legacy.rtc = 1;
 }
 
+static void __init xen_domu_set_legacy_features(void)
+{
+	x86_platform.legacy.rtc = 0;
+}
+
 /* First C function to be called on Xen boot */
 asmlinkage __visible void __init xen_start_kernel(void)
 {
@@ -1359,6 +1367,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 		add_preferred_console("xenboot", 0, NULL);
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
+		x86_platform.set_legacy_features =
+				xen_domu_set_legacy_features;
 	} else {
 		const struct dom0_vga_console_info *info =
 			(void *)((char *)xen_start_info +
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 1df5f01529e5..8d751939c6f3 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1518,14 +1518,17 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 	if (pinned) {
 		struct page *page = pfn_to_page(pfn);
 
-		if (static_branch_likely(&xen_struct_pages_ready))
+		pinned = false;
+		if (static_branch_likely(&xen_struct_pages_ready)) {
+			pinned = PagePinned(page);
 			SetPagePinned(page);
+		}
 
 		xen_mc_batch();
 
 		__set_pfn_prot(pfn, PAGE_KERNEL_RO);
 
-		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
+		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned)
 			__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 
 		xen_mc_issue(PARAVIRT_LAZY_MMU);
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 54f9aa7e8457..46df59aeaa06 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -18,7 +18,7 @@
 #endif
 #include <linux/export.h>
 
-int xen_swiotlb __read_mostly;
+static int xen_swiotlb __read_mostly;
 
 /*
  * pci_xen_swiotlb_detect - set xen_swiotlb to 1 if necessary
@@ -56,7 +56,7 @@ int __init pci_xen_swiotlb_detect(void)
 	return xen_swiotlb;
 }
 
-void __init pci_xen_swiotlb_init(void)
+static void __init pci_xen_swiotlb_init(void)
 {
 	if (xen_swiotlb) {
 		xen_swiotlb_init_early();
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 96afadf9878e..7ed56c6075b0 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -290,8 +290,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 
 	gdt = get_cpu_gdt_rw(cpu);
 
-	memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
-
 	/*
 	 * Bring up the CPU in cpu_bringup_and_idle() with the stack
 	 * pointing just below where pt_regs would be if it were a normal
@@ -308,8 +306,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 
 	xen_copy_trap_info(ctxt->trap_ctxt);
 
-	ctxt->ldt_ents = 0;
-
 	BUG_ON((unsigned long)gdt & ~PAGE_MASK);
 
 	gdt_mfn = arbitrary_virt_to_mfn(gdt);