Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini: "ARM: - data abort report and injection - steal time support - GICv4 performance improvements - vgic ITS emulation fixes - simplify FWB handling - enable halt polling counters - make the emulated timer PREEMPT_RT compliant s390: - small fixes and cleanups - selftest improvements - yield improvements PPC: - add capability to tell userspace whether we can single-step the guest - improve the allocation of XIVE virtual processor IDs - rewrite interrupt synthesis code to deliver interrupts in virtual mode when appropriate. - minor cleanups and improvements. x86: - XSAVES support for AMD - more accurate report of nested guest TSC to the nested hypervisor - retpoline optimizations - support for nested 5-level page tables - PMU virtualization optimizations, and improved support for nested PMU virtualization - correct latching of INITs for nested virtualization - IOAPIC optimization - TSX_CTRL virtualization for more TAA happiness - improved allocation and flushing of SEV ASIDs - many bugfixes and cleanups" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (127 commits) kvm: nVMX: Relax guest IA32_FEATURE_CONTROL constraints KVM: x86: Grab KVM's srcu lock when setting nested state KVM: x86: Open code shared_msr_update() in its only caller KVM: Fix jump label out_free_* in kvm_init() KVM: x86: Remove a spurious export of a static function KVM: x86: create mmu/ subdirectory KVM: nVMX: Remove unnecessary TLB flushes on L1<->L2 switches when L1 use apic-access-page KVM: x86: remove set but not used variable 'called' KVM: nVMX: Do not mark vmcs02->apic_access_page as dirty when unpinning KVM: vmx: use MSR_IA32_TSX_CTRL to hard-disable TSX on guest that lack it KVM: vmx: implement MSR_IA32_TSX_CTRL disable RTM functionality KVM: x86: implement MSR_IA32_TSX_CTRL effect on CPUID KVM: x86: do not modify masked bits of shared MSRs KVM: x86: fix presentation of TSX feature in ARCH_CAPABILITIES KVM: PPC: Book3S HV: XIVE: Fix potential page leak on error path KVM: PPC: Book3S HV: XIVE: Free previous EQ page when setting up a new one KVM: nVMX: Assume TLB entries of L1 and L2 are tagged differently if L0 use EPT KVM: x86: Unexport kvm_vcpu_reload_apic_access_page() KVM: nVMX: add CR4_LA57 bit to nested CR4_FIXED1 KVM: nVMX: Use semi-colon instead of comma for exit-handlers initialization ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2019-11-25 18:02:36 -0800
committer: Linus Torvalds <torvalds@linux-foundation.org> 2019-11-25 18:02:36 -0800
commit: 752272f16dd18f2cac58a583a8673c8e2fb93abb (patch)
tree: 1a2bae3067e1133c1d1b8e0bbbaea8c34e3321b2 /arch/x86
parent: Merge tag 'for-linus-5.5a-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip (diff)
parent: Merge tag 'kvm-ppc-next-5.5-2' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD (diff)
download: linux-dev-752272f16dd18f2cac58a583a8673c8e2fb93abb.tar.xz
linux-dev-752272f16dd18f2cac58a583a8673c8e2fb93abb.zip
24 files changed, 1033 insertions, 452 deletions
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index fcef678c3423..937363b803c1 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3323,8 +3323,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	return 0;
 }
 
+#ifdef CONFIG_RETPOLINE
+static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr);
+static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr);
+#endif
+
 struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
+#ifdef CONFIG_RETPOLINE
+	if (x86_pmu.guest_get_msrs == intel_guest_get_msrs)
+		return intel_guest_get_msrs(nr);
+	else if (x86_pmu.guest_get_msrs == core_guest_get_msrs)
+		return core_guest_get_msrs(nr);
+#endif
 	if (x86_pmu.guest_get_msrs)
 		return x86_pmu.guest_get_msrs(nr);
 	*nr = 0;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4fc61483919a..b79cd6aa4075 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -156,10 +156,8 @@ enum kvm_reg {
 	VCPU_REGS_R15 = __VCPU_REGS_R15,
 #endif
 	VCPU_REGS_RIP,
-	NR_VCPU_REGS
-};
+	NR_VCPU_REGS,
 
-enum kvm_reg_ex {
 	VCPU_EXREG_PDPTR = NR_VCPU_REGS,
 	VCPU_EXREG_CR3,
 	VCPU_EXREG_RFLAGS,
@@ -454,6 +452,11 @@ struct kvm_pmc {
 	u64 eventsel;
 	struct perf_event *perf_event;
 	struct kvm_vcpu *vcpu;
+	/*
+	 * eventsel value for general purpose counters,
+	 * ctrl value for fixed counters.
+	 */
+	u64 current_config;
 };
 
 struct kvm_pmu {
@@ -472,7 +475,21 @@ struct kvm_pmu {
 	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
 	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
 	struct irq_work irq_work;
-	u64 reprogram_pmi;
+	DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
+	DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
+	DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
+
+	/*
+	 * The gate to release perf_events not marked in
+	 * pmc_in_use only once in a vcpu time slice.
+	 */
+	bool need_cleanup;
+
+	/*
+	 * The total number of programmed perf_events and it helps to avoid
+	 * redundant check before cleanup if guest don't use vPMU at all.
+	 */
+	u8 event_count;
 };
 
 struct kvm_pmu_ops;
@@ -565,6 +582,7 @@ struct kvm_vcpu_arch {
 	u64 smbase;
 	u64 smi_count;
 	bool tpr_access_reporting;
+	bool xsaves_enabled;
 	u64 ia32_xss;
 	u64 microcode_version;
 	u64 arch_capabilities;
@@ -1041,7 +1059,6 @@ struct kvm_x86_ops {
 			    struct kvm_segment *var, int seg);
 	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
 	void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
-	void (*decache_cr3)(struct kvm_vcpu *vcpu);
 	void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
 	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -1090,7 +1107,7 @@ struct kvm_x86_ops {
 	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
 	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
 	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
-	bool (*get_enable_apicv)(struct kvm_vcpu *vcpu);
+	bool (*get_enable_apicv)(struct kvm *kvm);
 	void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
 	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
 	void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
@@ -1357,6 +1374,7 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
 
 void kvm_enable_efer_bits(u64);
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
+int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data);
 int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data);
 int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu);
@@ -1577,6 +1595,8 @@ bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
 
 void kvm_make_mclock_inprogress_request(struct kvm *kvm);
 void kvm_make_scan_ioapic_request(struct kvm *kvm);
+void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
+				       unsigned long *vcpu_bitmap);
 
 void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 				     struct kvm_async_pf *work);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index e820568ed4d5..32ef1ee733b7 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -33,6 +33,7 @@
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
 #include <asm/tlb.h>
+#include <asm/cpuidle_haltpoll.h>
 
 static int kvmapf = 1;
 
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 31ecf7a76d5a..b19ef421084d 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -8,9 +8,9 @@ kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
 				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
-kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
+kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
-			   hyperv.o page_track.o debugfs.o
+			   hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o
 
 kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o
 kvm-amd-y		+= svm.o pmu_amd.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index f68c0c753c38..c0aa07487eb8 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -816,8 +816,6 @@ static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func,
 	return __do_cpuid_func(entry, func, nent, maxnent);
 }
 
-#undef F
-
 struct kvm_cpuid_param {
 	u32 func;
 	bool (*qualifier)(const struct kvm_cpuid_param *param);
@@ -1015,6 +1013,12 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 		*ebx = entry->ebx;
 		*ecx = entry->ecx;
 		*edx = entry->edx;
+		if (function == 7 && index == 0) {
+			u64 data;
+		        if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) &&
+			    (data & TSX_CTRL_CPUID_CLEAR))
+				*ebx &= ~(F(RTM) | F(HLE));
+		}
 	} else {
 		*eax = *ebx = *ecx = *edx = 0;
 		/*
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 698efb8c3897..952d1a4f4d7e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2770,11 +2770,10 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
 		return emulate_ud(ctxt);
 
 	ops->get_msr(ctxt, MSR_EFER, &efer);
-	setup_syscalls_segments(ctxt, &cs, &ss);
-
 	if (!(efer & EFER_SCE))
 		return emulate_ud(ctxt);
 
+	setup_syscalls_segments(ctxt, &cs, &ss);
 	ops->get_msr(ctxt, MSR_STAR, &msr_data);
 	msr_data >>= 32;
 	cs_sel = (u16)(msr_data & 0xfffc);
@@ -2838,12 +2837,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->mode == X86EMUL_MODE_PROT64)
 		return X86EMUL_UNHANDLEABLE;
 
-	setup_syscalls_segments(ctxt, &cs, &ss);
-
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
 	if ((msr_data & 0xfffc) == 0x0)
 		return emulate_gp(ctxt, 0);
 
+	setup_syscalls_segments(ctxt, &cs, &ss);
 	ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF);
 	cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK;
 	ss_sel = cs_sel + 8;
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index d859ae8890d0..9fd2dd89a1c5 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -271,8 +271,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 {
 	unsigned index;
 	bool mask_before, mask_after;
-	int old_remote_irr, old_delivery_status;
 	union kvm_ioapic_redirect_entry *e;
+	unsigned long vcpu_bitmap;
+	int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode;
 
 	switch (ioapic->ioregsel) {
 	case IOAPIC_REG_VERSION:
@@ -296,6 +297,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		/* Preserve read-only fields */
 		old_remote_irr = e->fields.remote_irr;
 		old_delivery_status = e->fields.delivery_status;
+		old_dest_id = e->fields.dest_id;
+		old_dest_mode = e->fields.dest_mode;
 		if (ioapic->ioregsel & 1) {
 			e->bits &= 0xffffffff;
 			e->bits |= (u64) val << 32;
@@ -321,7 +324,34 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
 		    && ioapic->irr & (1 << index))
 			ioapic_service(ioapic, index, false);
-		kvm_make_scan_ioapic_request(ioapic->kvm);
+		if (e->fields.delivery_mode == APIC_DM_FIXED) {
+			struct kvm_lapic_irq irq;
+
+			irq.shorthand = 0;
+			irq.vector = e->fields.vector;
+			irq.delivery_mode = e->fields.delivery_mode << 8;
+			irq.dest_id = e->fields.dest_id;
+			irq.dest_mode = e->fields.dest_mode;
+			bitmap_zero(&vcpu_bitmap, 16);
+			kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
+						 &vcpu_bitmap);
+			if (old_dest_mode != e->fields.dest_mode ||
+			    old_dest_id != e->fields.dest_id) {
+				/*
+				 * Update vcpu_bitmap with vcpus specified in
+				 * the previous request as well. This is done to
+				 * keep ioapic_handled_vectors synchronized.
+				 */
+				irq.dest_id = old_dest_id;
+				irq.dest_mode = old_dest_mode;
+				kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
+							 &vcpu_bitmap);
+			}
+			kvm_make_scan_ioapic_request_mask(ioapic->kvm,
+							  &vcpu_bitmap);
+		} else {
+			kvm_make_scan_ioapic_request(ioapic->kvm);
+		}
 		break;
 	}
 }
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 1cc6c47dc77e..58767020de41 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -37,22 +37,50 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14)
 BUILD_KVM_GPR_ACCESSORS(r15, R15)
 #endif
 
-static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu,
-					      enum kvm_reg reg)
+static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu,
+					     enum kvm_reg reg)
 {
-	if (!test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail))
+	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu,
+					 enum kvm_reg reg)
+{
+	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
+static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu,
+					       enum kvm_reg reg)
+{
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+}
+
+static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu,
+					   enum kvm_reg reg)
+{
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
+}
+
+static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg)
+{
+	if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS))
+		return 0;
+
+	if (!kvm_register_is_available(vcpu, reg))
 		kvm_x86_ops->cache_reg(vcpu, reg);
 
 	return vcpu->arch.regs[reg];
 }
 
-static inline void kvm_register_write(struct kvm_vcpu *vcpu,
-				      enum kvm_reg reg,
+static inline void kvm_register_write(struct kvm_vcpu *vcpu, int reg,
 				      unsigned long val)
 {
+	if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS))
+		return;
+
 	vcpu->arch.regs[reg] = val;
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	kvm_register_mark_dirty(vcpu, reg);
 }
 
 static inline unsigned long kvm_rip_read(struct kvm_vcpu *vcpu)
@@ -79,9 +107,8 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
 {
 	might_sleep();  /* on svm */
 
-	if (!test_bit(VCPU_EXREG_PDPTR,
-		      (unsigned long *)&vcpu->arch.regs_avail))
-		kvm_x86_ops->cache_reg(vcpu, (enum kvm_reg)VCPU_EXREG_PDPTR);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR))
+		kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR);
 
 	return vcpu->arch.walk_mmu->pdptrs[index];
 }
@@ -109,8 +136,8 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask)
 
 static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu)
 {
-	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
-		kvm_x86_ops->decache_cr3(vcpu);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3))
+		kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_CR3);
 	return vcpu->arch.cr3;
 }
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b29d00b661ff..cf9177b4a07f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -557,60 +557,53 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
 			irq->level, irq->trig_mode, dest_map);
 }
 
+static int __pv_send_ipi(unsigned long *ipi_bitmap, struct kvm_apic_map *map,
+			 struct kvm_lapic_irq *irq, u32 min)
+{
+	int i, count = 0;
+	struct kvm_vcpu *vcpu;
+
+	if (min > map->max_apic_id)
+		return 0;
+
+	for_each_set_bit(i, ipi_bitmap,
+		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
+		if (map->phys_map[min + i]) {
+			vcpu = map->phys_map[min + i]->vcpu;
+			count += kvm_apic_set_irq(vcpu, irq, NULL);
+		}
+	}
+
+	return count;
+}
+
 int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
 		    unsigned long ipi_bitmap_high, u32 min,
 		    unsigned long icr, int op_64_bit)
 {
-	int i;
 	struct kvm_apic_map *map;
-	struct kvm_vcpu *vcpu;
 	struct kvm_lapic_irq irq = {0};
 	int cluster_size = op_64_bit ? 64 : 32;
-	int count = 0;
+	int count;
+
+	if (icr & (APIC_DEST_MASK | APIC_SHORT_MASK))
+		return -KVM_EINVAL;
 
 	irq.vector = icr & APIC_VECTOR_MASK;
 	irq.delivery_mode = icr & APIC_MODE_MASK;
 	irq.level = (icr & APIC_INT_ASSERT) != 0;
 	irq.trig_mode = icr & APIC_INT_LEVELTRIG;
 
-	if (icr & APIC_DEST_MASK)
-		return -KVM_EINVAL;
-	if (icr & APIC_SHORT_MASK)
-		return -KVM_EINVAL;
-
 	rcu_read_lock();
 	map = rcu_dereference(kvm->arch.apic_map);
 
-	if (unlikely(!map)) {
-		count = -EOPNOTSUPP;
-		goto out;
-	}
-
-	if (min > map->max_apic_id)
-		goto out;
-	/* Bits above cluster_size are masked in the caller.  */
-	for_each_set_bit(i, &ipi_bitmap_low,
-		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
-		if (map->phys_map[min + i]) {
-			vcpu = map->phys_map[min + i]->vcpu;
-			count += kvm_apic_set_irq(vcpu, &irq, NULL);
-		}
+	count = -EOPNOTSUPP;
+	if (likely(map)) {
+		count = __pv_send_ipi(&ipi_bitmap_low, map, &irq, min);
+		min += cluster_size;
+		count += __pv_send_ipi(&ipi_bitmap_high, map, &irq, min);
 	}
 
-	min += cluster_size;
-
-	if (min > map->max_apic_id)
-		goto out;
-
-	for_each_set_bit(i, &ipi_bitmap_high,
-		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
-		if (map->phys_map[min + i]) {
-			vcpu = map->phys_map[min + i]->vcpu;
-			count += kvm_apic_set_irq(vcpu, &irq, NULL);
-		}
-	}
-
-out:
 	rcu_read_unlock();
 	return count;
 }
@@ -1124,6 +1117,50 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	return result;
 }
 
+/*
+ * This routine identifies the destination vcpus mask meant to receive the
+ * IOAPIC interrupts. It either uses kvm_apic_map_get_dest_lapic() to find
+ * out the destination vcpus array and set the bitmap or it traverses to
+ * each available vcpu to identify the same.
+ */
+void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq,
+			      unsigned long *vcpu_bitmap)
+{
+	struct kvm_lapic **dest_vcpu = NULL;
+	struct kvm_lapic *src = NULL;
+	struct kvm_apic_map *map;
+	struct kvm_vcpu *vcpu;
+	unsigned long bitmap;
+	int i, vcpu_idx;
+	bool ret;
+
+	rcu_read_lock();
+	map = rcu_dereference(kvm->arch.apic_map);
+
+	ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dest_vcpu,
+					  &bitmap);
+	if (ret) {
+		for_each_set_bit(i, &bitmap, 16) {
+			if (!dest_vcpu[i])
+				continue;
+			vcpu_idx = dest_vcpu[i]->vcpu->vcpu_idx;
+			__set_bit(vcpu_idx, vcpu_bitmap);
+		}
+	} else {
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			if (!kvm_apic_present(vcpu))
+				continue;
+			if (!kvm_apic_match_dest(vcpu, NULL,
+						 irq->delivery_mode,
+						 irq->dest_id,
+						 irq->dest_mode))
+				continue;
+			__set_bit(i, vcpu_bitmap);
+		}
+	}
+	rcu_read_unlock();
+}
+
 int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 {
 	return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio;
@@ -2709,7 +2746,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 	 * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs
 	 * and leave the INIT pending.
 	 */
-	if (is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu)) {
+	if (kvm_vcpu_latch_init(vcpu)) {
 		WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED);
 		if (test_bit(KVM_APIC_SIPI, &apic->pending_events))
 			clear_bit(KVM_APIC_SIPI, &apic->pending_events);
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 1f5014852e20..39925afdfcdc 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -226,6 +226,9 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
 
 void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu);
 
+void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq,
+			      unsigned long *vcpu_bitmap);
+
 bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			struct kvm_vcpu **dest_vcpu);
 int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2ce9da58611e..6f92b40d798c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4395,7 +4395,7 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3,
 			kvm_make_request(KVM_REQ_LOAD_CR3, vcpu);
 			if (!skip_tlb_flush) {
 				kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
-				kvm_x86_ops->tlb_flush(vcpu, true);
+				kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 			}
 
 			/*
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 3521e2d176f2..3521e2d176f2 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 97b21e7fd013..97b21e7fd013 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 46875bbd0419..d5e6d5b3f06f 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -62,8 +62,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 
-	if (!test_and_set_bit(pmc->idx,
-			      (unsigned long *)&pmu->reprogram_pmi)) {
+	if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 	}
@@ -76,8 +75,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event,
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
 
-	if (!test_and_set_bit(pmc->idx,
-			      (unsigned long *)&pmu->reprogram_pmi)) {
+	if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 
@@ -137,7 +135,37 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 	}
 
 	pmc->perf_event = event;
-	clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi);
+	pmc_to_pmu(pmc)->event_count++;
+	clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
+}
+
+static void pmc_pause_counter(struct kvm_pmc *pmc)
+{
+	u64 counter = pmc->counter;
+
+	if (!pmc->perf_event)
+		return;
+
+	/* update counter, reset event value to avoid redundant accumulation */
+	counter += perf_event_pause(pmc->perf_event, true);
+	pmc->counter = counter & pmc_bitmask(pmc);
+}
+
+static bool pmc_resume_counter(struct kvm_pmc *pmc)
+{
+	if (!pmc->perf_event)
+		return false;
+
+	/* recalibrate sample period and check if it's accepted by perf core */
+	if (perf_event_period(pmc->perf_event,
+			(-pmc->counter) & pmc_bitmask(pmc)))
+		return false;
+
+	/* reuse perf_event to serve as pmc_reprogram_counter() does*/
+	perf_event_enable(pmc->perf_event);
+
+	clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
+	return true;
 }
 
 void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
@@ -154,7 +182,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 
 	pmc->eventsel = eventsel;
 
-	pmc_stop_counter(pmc);
+	pmc_pause_counter(pmc);
 
 	if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
 		return;
@@ -193,6 +221,12 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	if (type == PERF_TYPE_RAW)
 		config = eventsel & X86_RAW_EVENT_MASK;
 
+	if (pmc->current_config == eventsel && pmc_resume_counter(pmc))
+		return;
+
+	pmc_release_perf_event(pmc);
+
+	pmc->current_config = eventsel;
 	pmc_reprogram_counter(pmc, type, config,
 			      !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
 			      !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
@@ -209,7 +243,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
 	struct kvm_pmu_event_filter *filter;
 	struct kvm *kvm = pmc->vcpu->kvm;
 
-	pmc_stop_counter(pmc);
+	pmc_pause_counter(pmc);
 
 	if (!en_field || !pmc_is_enabled(pmc))
 		return;
@@ -224,6 +258,12 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
 			return;
 	}
 
+	if (pmc->current_config == (u64)ctrl && pmc_resume_counter(pmc))
+		return;
+
+	pmc_release_perf_event(pmc);
+
+	pmc->current_config = (u64)ctrl;
 	pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
 			      kvm_x86_ops->pmu_ops->find_fixed_event(idx),
 			      !(en_field & 0x2), /* exclude user */
@@ -253,27 +293,32 @@ EXPORT_SYMBOL_GPL(reprogram_counter);
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	u64 bitmask;
 	int bit;
 
-	bitmask = pmu->reprogram_pmi;
-
-	for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) {
+	for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) {
 		struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit);
 
 		if (unlikely(!pmc || !pmc->perf_event)) {
-			clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi);
+			clear_bit(bit, pmu->reprogram_pmi);
 			continue;
 		}
 
 		reprogram_counter(pmu, bit);
 	}
+
+	/*
+	 * Unused perf_events are only released if the corresponding MSRs
+	 * weren't accessed during the last vCPU time slice. kvm_arch_sched_in
+	 * triggers KVM_REQ_PMU if cleanup is needed.
+	 */
+	if (unlikely(pmu->need_cleanup))
+		kvm_pmu_cleanup(vcpu);
 }
 
 /* check if idx is a valid index to access PMU */
-int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
-	return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx);
+	return kvm_x86_ops->pmu_ops->is_valid_rdpmc_ecx(vcpu, idx);
 }
 
 bool is_vmware_backdoor_pmc(u32 pmc_idx)
@@ -323,7 +368,7 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 	if (is_vmware_backdoor_pmc(idx))
 		return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
 
-	pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask);
+	pmc = kvm_x86_ops->pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask);
 	if (!pmc)
 		return 1;
 
@@ -339,7 +384,17 @@ void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
 
 bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 {
-	return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr);
+	return kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr) ||
+		kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr);
+}
+
+static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr);
+
+	if (pmc)
+		__set_bit(pmc->idx, pmu->pmc_in_use);
 }
 
 int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
@@ -349,6 +404,7 @@ int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
 
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
+	kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index);
 	return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info);
 }
 
@@ -376,9 +432,45 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
 	memset(pmu, 0, sizeof(*pmu));
 	kvm_x86_ops->pmu_ops->init(vcpu);
 	init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
+	pmu->event_count = 0;
+	pmu->need_cleanup = false;
 	kvm_pmu_refresh(vcpu);
 }
 
+static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+	if (pmc_is_fixed(pmc))
+		return fixed_ctrl_field(pmu->fixed_ctr_ctrl,
+			pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3;
+
+	return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE;
+}
+
+/* Release perf_events for vPMCs that have been unused for a full time slice.  */
+void kvm_pmu_cleanup(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc = NULL;
+	DECLARE_BITMAP(bitmask, X86_PMC_IDX_MAX);
+	int i;
+
+	pmu->need_cleanup = false;
+
+	bitmap_andnot(bitmask, pmu->all_valid_pmc_idx,
+		      pmu->pmc_in_use, X86_PMC_IDX_MAX);
+
+	for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) {
+		pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, i);
+
+		if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc))
+			pmc_stop_counter(pmc);
+	}
+
+	bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX);
+}
+
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_pmu_reset(vcpu);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 58265f761c3b..7ebb62326c14 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -25,9 +25,10 @@ struct kvm_pmu_ops {
 	unsigned (*find_fixed_event)(int idx);
 	bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
 	struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
-	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx,
-					  u64 *mask);
-	int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx);
+	struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu,
+		unsigned int idx, u64 *mask);
+	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr);
+	int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx);
 	bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
 	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
@@ -55,12 +56,21 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
 	return counter & pmc_bitmask(pmc);
 }
 
-static inline void pmc_stop_counter(struct kvm_pmc *pmc)
+static inline void pmc_release_perf_event(struct kvm_pmc *pmc)
 {
 	if (pmc->perf_event) {
-		pmc->counter = pmc_read_counter(pmc);
 		perf_event_release_kernel(pmc->perf_event);
 		pmc->perf_event = NULL;
+		pmc->current_config = 0;
+		pmc_to_pmu(pmc)->event_count--;
+	}
+}
+
+static inline void pmc_stop_counter(struct kvm_pmc *pmc)
+{
+	if (pmc->perf_event) {
+		pmc->counter = pmc_read_counter(pmc);
+		pmc_release_perf_event(pmc);
 	}
 }
 
@@ -79,6 +89,12 @@ static inline bool pmc_is_enabled(struct kvm_pmc *pmc)
 	return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc);
 }
 
+static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu,
+						 u64 data)
+{
+	return !(pmu->global_ctrl_mask & data);
+}
+
 /* returns general purpose PMC with the specified MSR. Note that it can be
  * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a
  * paramenter to tell them apart.
@@ -110,13 +126,14 @@ void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx);
 void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
-int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx);
+int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx);
 bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr);
 int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 void kvm_pmu_refresh(struct kvm_vcpu *vcpu);
 void kvm_pmu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_init(struct kvm_vcpu *vcpu);
+void kvm_pmu_cleanup(struct kvm_vcpu *vcpu);
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp);
 
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
index c8388389a3b0..ce0b10fe5e2b 100644
--- a/arch/x86/kvm/pmu_amd.c
+++ b/arch/x86/kvm/pmu_amd.c
@@ -174,7 +174,7 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 }
 
 /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
-static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 
@@ -184,7 +184,8 @@ static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
 }
 
 /* idx is the ECX register of RDPMC instruction */
-static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *mask)
+static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
+	unsigned int idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *counters;
@@ -199,13 +200,19 @@ static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u
 
 static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 {
+	/* All MSRs refer to exactly one PMC, so msr_idx_to_pmc is enough.  */
+	return false;
+}
+
+static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr)
+{
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-	int ret = false;
+	struct kvm_pmc *pmc;
 
-	ret = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER) ||
-		get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
+	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
+	pmc = pmc ? pmc : get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
 
-	return ret;
+	return pmc;
 }
 
 static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
@@ -272,6 +279,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->nr_arch_fixed_counters = 0;
 	pmu->global_status = 0;
+	bitmap_set(pmu->all_valid_pmc_idx, 0, pmu->nr_arch_gp_counters);
 }
 
 static void amd_pmu_init(struct kvm_vcpu *vcpu)
@@ -285,6 +293,7 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu)
 		pmu->gp_counters[i].type = KVM_PMC_GP;
 		pmu->gp_counters[i].vcpu = vcpu;
 		pmu->gp_counters[i].idx = i;
+		pmu->gp_counters[i].current_config = 0;
 	}
 }
 
@@ -306,8 +315,9 @@ struct kvm_pmu_ops amd_pmu_ops = {
 	.find_fixed_event = amd_find_fixed_event,
 	.pmc_is_enabled = amd_pmc_is_enabled,
 	.pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
+	.rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc,
 	.msr_idx_to_pmc = amd_msr_idx_to_pmc,
-	.is_valid_msr_idx = amd_is_valid_msr_idx,
+	.is_valid_rdpmc_ecx = amd_is_valid_rdpmc_ecx,
 	.is_valid_msr = amd_is_valid_msr,
 	.get_msr = amd_pmu_get_msr,
 	.set_msr = amd_pmu_set_msr,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index c5673bda4b66..362e874297e4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -38,6 +38,7 @@
 #include <linux/file.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
+#include <linux/rwsem.h>
 
 #include <asm/apic.h>
 #include <asm/perf_event.h>
@@ -418,9 +419,13 @@ enum {
 
 #define VMCB_AVIC_APIC_BAR_MASK		0xFFFFFFFFFF000ULL
 
+static int sev_flush_asids(void);
+static DECLARE_RWSEM(sev_deactivate_lock);
+static DEFINE_MUTEX(sev_bitmap_lock);
 static unsigned int max_sev_asid;
 static unsigned int min_sev_asid;
 static unsigned long *sev_asid_bitmap;
+static unsigned long *sev_reclaim_asid_bitmap;
 #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
 
 struct enc_region {
@@ -1235,11 +1240,15 @@ static __init int sev_hardware_setup(void)
 	/* Minimum ASID value that should be used for SEV guest */
 	min_sev_asid = cpuid_edx(0x8000001F);
 
-	/* Initialize SEV ASID bitmap */
+	/* Initialize SEV ASID bitmaps */
 	sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
 	if (!sev_asid_bitmap)
 		return 1;
 
+	sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+	if (!sev_reclaim_asid_bitmap)
+		return 1;
+
 	status = kmalloc(sizeof(*status), GFP_KERNEL);
 	if (!status)
 		return 1;
@@ -1418,8 +1427,12 @@ static __exit void svm_hardware_unsetup(void)
 {
 	int cpu;
 
-	if (svm_sev_enabled())
+	if (svm_sev_enabled()) {
 		bitmap_free(sev_asid_bitmap);
+		bitmap_free(sev_reclaim_asid_bitmap);
+
+		sev_flush_asids();
+	}
 
 	for_each_possible_cpu(cpu)
 		svm_cpu_uninit(cpu);
@@ -1729,25 +1742,22 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static void __sev_asid_free(int asid)
+static void sev_asid_free(int asid)
 {
 	struct svm_cpu_data *sd;
 	int cpu, pos;
 
+	mutex_lock(&sev_bitmap_lock);
+
 	pos = asid - 1;
-	clear_bit(pos, sev_asid_bitmap);
+	__set_bit(pos, sev_reclaim_asid_bitmap);
 
 	for_each_possible_cpu(cpu) {
 		sd = per_cpu(svm_data, cpu);
 		sd->sev_vmcbs[pos] = NULL;
 	}
-}
 
-static void sev_asid_free(struct kvm *kvm)
-{
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-
-	__sev_asid_free(sev->asid);
+	mutex_unlock(&sev_bitmap_lock);
 }
 
 static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
@@ -1764,10 +1774,12 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
 
 	/* deactivate handle */
 	data->handle = handle;
+
+	/* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */
+	down_read(&sev_deactivate_lock);
 	sev_guest_deactivate(data, NULL);
+	up_read(&sev_deactivate_lock);
 
-	wbinvd_on_all_cpus();
-	sev_guest_df_flush(NULL);
 	kfree(data);
 
 	decommission = kzalloc(sizeof(*decommission), GFP_KERNEL);
@@ -1916,7 +1928,7 @@ static void sev_vm_destroy(struct kvm *kvm)
 	mutex_unlock(&kvm->lock);
 
 	sev_unbind_asid(kvm, sev->handle);
-	sev_asid_free(kvm);
+	sev_asid_free(sev->asid);
 }
 
 static void avic_vm_destroy(struct kvm *kvm)
@@ -2370,7 +2382,7 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
 		break;
 	default:
-		BUG();
+		WARN_ON_ONCE(1);
 	}
 }
 
@@ -2523,10 +2535,6 @@ static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 {
 }
 
-static void svm_decache_cr3(struct kvm_vcpu *vcpu)
-{
-}
-
 static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 {
 }
@@ -4997,6 +5005,18 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
+#ifdef CONFIG_RETPOLINE
+	if (exit_code == SVM_EXIT_MSR)
+		return msr_interception(svm);
+	else if (exit_code == SVM_EXIT_VINTR)
+		return interrupt_window_interception(svm);
+	else if (exit_code == SVM_EXIT_INTR)
+		return intr_interception(svm);
+	else if (exit_code == SVM_EXIT_HLT)
+		return halt_interception(svm);
+	else if (exit_code == SVM_EXIT_NPF)
+		return npf_interception(svm);
+#endif
 	return svm_exit_handlers[exit_code](svm);
 }
 
@@ -5092,8 +5112,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (svm_nested_virtualize_tpr(vcpu) ||
-	    kvm_vcpu_apicv_active(vcpu))
+	if (svm_nested_virtualize_tpr(vcpu))
 		return;
 
 	clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
@@ -5110,9 +5129,9 @@ static void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 	return;
 }
 
-static bool svm_get_enable_apicv(struct kvm_vcpu *vcpu)
+static bool svm_get_enable_apicv(struct kvm *kvm)
 {
-	return avic && irqchip_split(vcpu->kvm);
+	return avic && irqchip_split(kvm);
 }
 
 static void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
@@ -5634,7 +5653,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	svm->vmcb->save.cr2 = vcpu->arch.cr2;
 
 	clgi();
-	kvm_load_guest_xcr0(vcpu);
+	kvm_load_guest_xsave_state(vcpu);
 
 	if (lapic_in_kernel(vcpu) &&
 		vcpu->arch.apic->lapic_timer.timer_advance_ns)
@@ -5784,7 +5803,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(&svm->vcpu);
 
-	kvm_put_guest_xcr0(vcpu);
+	kvm_load_host_xsave_state(vcpu);
 	stgi();
 
 	/* Any pending NMI will happen here */
@@ -5893,6 +5912,9 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+				    boot_cpu_has(X86_FEATURE_XSAVES);
+
 	/* Update nrips enabled cache */
 	svm->nrips_enabled = !!guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS);
 
@@ -5968,7 +5990,7 @@ static bool svm_mpx_supported(void)
 
 static bool svm_xsaves_supported(void)
 {
-	return false;
+	return boot_cpu_has(X86_FEATURE_XSAVES);
 }
 
 static bool svm_umip_emulated(void)
@@ -6270,18 +6292,73 @@ static int enable_smi_window(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int sev_flush_asids(void)
+{
+	int ret, error;
+
+	/*
+	 * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail,
+	 * so it must be guarded.
+	 */
+	down_write(&sev_deactivate_lock);
+
+	wbinvd_on_all_cpus();
+	ret = sev_guest_df_flush(&error);
+
+	up_write(&sev_deactivate_lock);
+
+	if (ret)
+		pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error);
+
+	return ret;
+}
+
+/* Must be called with the sev_bitmap_lock held */
+static bool __sev_recycle_asids(void)
+{
+	int pos;
+
+	/* Check if there are any ASIDs to reclaim before performing a flush */
+	pos = find_next_bit(sev_reclaim_asid_bitmap,
+			    max_sev_asid, min_sev_asid - 1);
+	if (pos >= max_sev_asid)
+		return false;
+
+	if (sev_flush_asids())
+		return false;
+
+	bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
+		   max_sev_asid);
+	bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid);
+
+	return true;
+}
+
 static int sev_asid_new(void)
 {
+	bool retry = true;
 	int pos;
 
+	mutex_lock(&sev_bitmap_lock);
+
 	/*
 	 * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid.
 	 */
+again:
 	pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1);
-	if (pos >= max_sev_asid)
+	if (pos >= max_sev_asid) {
+		if (retry && __sev_recycle_asids()) {
+			retry = false;
+			goto again;
+		}
+		mutex_unlock(&sev_bitmap_lock);
 		return -EBUSY;
+	}
+
+	__set_bit(pos, sev_asid_bitmap);
+
+	mutex_unlock(&sev_bitmap_lock);
 
-	set_bit(pos, sev_asid_bitmap);
 	return pos + 1;
 }
 
@@ -6309,7 +6386,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return 0;
 
 e_free:
-	__sev_asid_free(asid);
+	sev_asid_free(asid);
 	return ret;
 }
 
@@ -6319,12 +6396,6 @@ static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
 	int asid = sev_get_asid(kvm);
 	int ret;
 
-	wbinvd_on_all_cpus();
-
-	ret = sev_guest_df_flush(error);
-	if (ret)
-		return ret;
-
 	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		return -ENOMEM;
@@ -7214,7 +7285,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.get_cpl = svm_get_cpl,
 	.get_cs_db_l_bits = kvm_get_cs_db_l_bits,
 	.decache_cr0_guest_bits = svm_decache_cr0_guest_bits,
-	.decache_cr3 = svm_decache_cr3,
 	.decache_cr4_guest_bits = svm_decache_cr4_guest_bits,
 	.set_cr0 = svm_set_cr0,
 	.set_cr3 = svm_set_cr3,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0e7c9301fe86..4aea7d304beb 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -10,6 +10,7 @@
 #include "hyperv.h"
 #include "mmu.h"
 #include "nested.h"
+#include "pmu.h"
 #include "trace.h"
 #include "x86.h"
 
@@ -27,6 +28,16 @@ module_param(nested_early_check, bool, S_IRUGO);
 	failed;								\
 })
 
+#define SET_MSR_OR_WARN(vcpu, idx, data)				\
+({									\
+	bool failed = kvm_set_msr(vcpu, idx, data);			\
+	if (failed)							\
+		pr_warn_ratelimited(					\
+				"%s cannot write MSR (0x%x, 0x%llx)\n",	\
+				__func__, idx, data);			\
+	failed;								\
+})
+
 /*
  * Hyper-V requires all of these, so mark them as supported even though
  * they are just treated the same as all-context.
@@ -257,7 +268,7 @@ static void free_nested(struct kvm_vcpu *vcpu)
 	vmx->nested.cached_shadow_vmcs12 = NULL;
 	/* Unpin physical memory we referred to in the vmcs02 */
 	if (vmx->nested.apic_access_page) {
-		kvm_release_page_dirty(vmx->nested.apic_access_page);
+		kvm_release_page_clean(vmx->nested.apic_access_page);
 		vmx->nested.apic_access_page = NULL;
 	}
 	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
@@ -929,6 +940,57 @@ fail:
 	return i + 1;
 }
 
+static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu,
+					    u32 msr_index,
+					    u64 *data)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * If the L0 hypervisor stored a more accurate value for the TSC that
+	 * does not include the time taken for emulation of the L2->L1
+	 * VM-exit in L0, use the more accurate value.
+	 */
+	if (msr_index == MSR_IA32_TSC) {
+		int index = vmx_find_msr_index(&vmx->msr_autostore.guest,
+					       MSR_IA32_TSC);
+
+		if (index >= 0) {
+			u64 val = vmx->msr_autostore.guest.val[index].value;
+
+			*data = kvm_read_l1_tsc(vcpu, val);
+			return true;
+		}
+	}
+
+	if (kvm_get_msr(vcpu, msr_index, data)) {
+		pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__,
+			msr_index);
+		return false;
+	}
+	return true;
+}
+
+static bool read_and_check_msr_entry(struct kvm_vcpu *vcpu, u64 gpa, int i,
+				     struct vmx_msr_entry *e)
+{
+	if (kvm_vcpu_read_guest(vcpu,
+				gpa + i * sizeof(*e),
+				e, 2 * sizeof(u32))) {
+		pr_debug_ratelimited(
+			"%s cannot read MSR entry (%u, 0x%08llx)\n",
+			__func__, i, gpa + i * sizeof(*e));
+		return false;
+	}
+	if (nested_vmx_store_msr_check(vcpu, e)) {
+		pr_debug_ratelimited(
+			"%s check failed (%u, 0x%x, 0x%x)\n",
+			__func__, i, e->index, e->reserved);
+		return false;
+	}
+	return true;
+}
+
 static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 {
 	u64 data;
@@ -940,26 +1002,12 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 		if (unlikely(i >= max_msr_list_size))
 			return -EINVAL;
 
-		if (kvm_vcpu_read_guest(vcpu,
-					gpa + i * sizeof(e),
-					&e, 2 * sizeof(u32))) {
-			pr_debug_ratelimited(
-				"%s cannot read MSR entry (%u, 0x%08llx)\n",
-				__func__, i, gpa + i * sizeof(e));
+		if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
 			return -EINVAL;
-		}
-		if (nested_vmx_store_msr_check(vcpu, &e)) {
-			pr_debug_ratelimited(
-				"%s check failed (%u, 0x%x, 0x%x)\n",
-				__func__, i, e.index, e.reserved);
-			return -EINVAL;
-		}
-		if (kvm_get_msr(vcpu, e.index, &data)) {
-			pr_debug_ratelimited(
-				"%s cannot read MSR (%u, 0x%x)\n",
-				__func__, i, e.index);
+
+		if (!nested_vmx_get_vmexit_msr_value(vcpu, e.index, &data))
 			return -EINVAL;
-		}
+
 		if (kvm_vcpu_write_guest(vcpu,
 					 gpa + i * sizeof(e) +
 					     offsetof(struct vmx_msr_entry, value),
@@ -973,6 +1021,60 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 	return 0;
 }
 
+static bool nested_msr_store_list_has_msr(struct kvm_vcpu *vcpu, u32 msr_index)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	u32 count = vmcs12->vm_exit_msr_store_count;
+	u64 gpa = vmcs12->vm_exit_msr_store_addr;
+	struct vmx_msr_entry e;
+	u32 i;
+
+	for (i = 0; i < count; i++) {
+		if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
+			return false;
+
+		if (e.index == msr_index)
+			return true;
+	}
+	return false;
+}
+
+static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu,
+					   u32 msr_index)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmx_msrs *autostore = &vmx->msr_autostore.guest;
+	bool in_vmcs12_store_list;
+	int msr_autostore_index;
+	bool in_autostore_list;
+	int last;
+
+	msr_autostore_index = vmx_find_msr_index(autostore, msr_index);
+	in_autostore_list = msr_autostore_index >= 0;
+	in_vmcs12_store_list = nested_msr_store_list_has_msr(vcpu, msr_index);
+
+	if (in_vmcs12_store_list && !in_autostore_list) {
+		if (autostore->nr == NR_LOADSTORE_MSRS) {
+			/*
+			 * Emulated VMEntry does not fail here.  Instead a less
+			 * accurate value will be returned by
+			 * nested_vmx_get_vmexit_msr_value() using kvm_get_msr()
+			 * instead of reading the value from the vmcs02 VMExit
+			 * MSR-store area.
+			 */
+			pr_warn_ratelimited(
+				"Not enough msr entries in msr_autostore.  Can't add msr %x\n",
+				msr_index);
+			return;
+		}
+		last = autostore->nr++;
+		autostore->val[last].index = msr_index;
+	} else if (!in_vmcs12_store_list && in_autostore_list) {
+		last = --autostore->nr;
+		autostore->val[msr_autostore_index] = autostore->val[last];
+	}
+}
+
 static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	unsigned long invalid_mask;
@@ -1012,7 +1114,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne
 		kvm_mmu_new_cr3(vcpu, cr3, false);
 
 	vcpu->arch.cr3 = cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	kvm_init_mmu(vcpu, false);
 
@@ -1024,7 +1126,9 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne
  * populated by L2 differently than TLB entries populated
  * by L1.
  *
- * If L1 uses EPT, then TLB entries are tagged with different EPTP.
+ * If L0 uses EPT, L1 and L2 run with different EPTP because
+ * guest_mode is part of kvm_mmu_page_role. Thus, TLB entries
+ * are tagged with different EPTP.
  *
  * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged
  * with different VPID (L1 entries are tagged with vmx->vpid
@@ -1034,7 +1138,7 @@ static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
-	return nested_cpu_has_ept(vmcs12) ||
+	return enable_ept ||
 	       (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02);
 }
 
@@ -2018,7 +2122,7 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
 	 * addresses are constant (for vmcs02), the counts can change based
 	 * on L2's behavior, e.g. switching to/from long mode.
 	 */
-	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
+	vmcs_write64(VM_EXIT_MSR_STORE_ADDR, __pa(vmx->msr_autostore.guest.val));
 	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
 	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
 
@@ -2073,6 +2177,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 	exec_control &= ~CPU_BASED_TPR_SHADOW;
 	exec_control |= vmcs12->cpu_based_vm_exec_control;
 
+	vmx->nested.l1_tpr_threshold = -1;
 	if (exec_control & CPU_BASED_TPR_SHADOW)
 		vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
 #ifdef CONFIG_X86_64
@@ -2285,6 +2390,13 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 		vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
 	}
 
+	/*
+	 * Make sure the msr_autostore list is up to date before we set the
+	 * count in the vmcs02.
+	 */
+	prepare_vmx_msr_autostore_list(&vmx->vcpu, MSR_IA32_TSC);
+
+	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, vmx->msr_autostore.guest.nr);
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 
@@ -2381,9 +2493,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	if (nested_cpu_has_ept(vmcs12))
 		nested_ept_init_mmu_context(vcpu);
-	else if (nested_cpu_has2(vmcs12,
-				 SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
-		vmx_flush_tlb(vcpu, true);
 
 	/*
 	 * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
@@ -2418,6 +2527,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 				entry_failure_code))
 		return -EINVAL;
 
+	/*
+	 * Immediately write vmcs02.GUEST_CR3.  It will be propagated to vmcs12
+	 * on nested VM-Exit, which can occur without actually running L2 and
+	 * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with
+	 * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the
+	 * transition to HLT instead of running L2.
+	 */
+	if (enable_ept)
+		vmcs_writel(GUEST_CR3, vmcs12->guest_cr3);
+
 	/* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */
 	if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) &&
 	    is_pae_paging(vcpu)) {
@@ -2430,6 +2549,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	if (!enable_ept)
 		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
 
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	    SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
+			    vmcs12->guest_ia32_perf_global_ctrl))
+		return -EINVAL;
+
 	kvm_rsp_write(vcpu, vmcs12->guest_rsp);
 	kvm_rip_write(vcpu, vmcs12->guest_rip);
 	return 0;
@@ -2664,6 +2788,11 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 	    CC(!kvm_pat_valid(vmcs12->host_ia32_pat)))
 		return -EINVAL;
 
+	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	    CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu),
+					   vmcs12->host_ia32_perf_global_ctrl)))
+		return -EINVAL;
+
 #ifdef CONFIG_X86_64
 	ia32e = !!(vcpu->arch.efer & EFER_LMA);
 #else
@@ -2779,6 +2908,11 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+	    CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu),
+					   vmcs12->guest_ia32_perf_global_ctrl)))
+		return -EINVAL;
+
 	/*
 	 * If the load IA32_EFER VM-entry control is 1, the following checks
 	 * are performed on the field for the IA32_EFER MSR:
@@ -2933,7 +3067,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		 * to it so we can release it later.
 		 */
 		if (vmx->nested.apic_access_page) { /* shouldn't happen */
-			kvm_release_page_dirty(vmx->nested.apic_access_page);
+			kvm_release_page_clean(vmx->nested.apic_access_page);
 			vmx->nested.apic_access_page = NULL;
 		}
 		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr);
@@ -3461,6 +3595,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 		test_bit(KVM_APIC_INIT, &apic->pending_events)) {
 		if (block_nested_events)
 			return -EBUSY;
+		clear_bit(KVM_APIC_INIT, &apic->pending_events);
 		nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
 		return 0;
 	}
@@ -3864,8 +3999,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 		vcpu->arch.pat = vmcs12->host_ia32_pat;
 	}
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
-		vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL,
-			vmcs12->host_ia32_perf_global_ctrl);
+		SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
+				vmcs12->host_ia32_perf_global_ctrl);
 
 	/* Set L1 segment info according to Intel SDM
 	    27.5.2 Loading Host Segment and Descriptor-Table Registers */
@@ -3984,7 +4119,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 
 	nested_ept_uninit_mmu_context(vcpu);
 	vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	/*
 	 * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
@@ -4112,6 +4247,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+	if (vmx->nested.l1_tpr_threshold != -1)
+		vmcs_write32(TPR_THRESHOLD, vmx->nested.l1_tpr_threshold);
 
 	if (kvm_has_tsc_control)
 		decache_tsc_multiplier(vmx);
@@ -4119,15 +4256,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	if (vmx->nested.change_vmcs01_virtual_apic_mode) {
 		vmx->nested.change_vmcs01_virtual_apic_mode = false;
 		vmx_set_virtual_apic_mode(vcpu);
-	} else if (!nested_cpu_has_ept(vmcs12) &&
-		   nested_cpu_has2(vmcs12,
-				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb(vcpu, true);
 	}
 
 	/* Unpin physical memory we referred to in vmcs02 */
 	if (vmx->nested.apic_access_page) {
-		kvm_release_page_dirty(vmx->nested.apic_access_page);
+		kvm_release_page_clean(vmx->nested.apic_access_page);
 		vmx->nested.apic_access_page = NULL;
 	}
 	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
@@ -4327,6 +4460,27 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 	return 0;
 }
 
+void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx;
+
+	if (!nested_vmx_allowed(vcpu))
+		return;
+
+	vmx = to_vmx(vcpu);
+	if (kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) {
+		vmx->nested.msrs.entry_ctls_high |=
+				VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+		vmx->nested.msrs.exit_ctls_high |=
+				VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+	} else {
+		vmx->nested.msrs.entry_ctls_high &=
+				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+		vmx->nested.msrs.exit_ctls_high &=
+				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+	}
+}
+
 static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
 {
 	gva_t gva;
@@ -5766,7 +5920,7 @@ error_guest_mode:
 	return ret;
 }
 
-void nested_vmx_vcpu_setup(void)
+void nested_vmx_set_vmcs_shadowing_bitmap(void)
 {
 	if (enable_shadow_vmcs) {
 		vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap));
@@ -6047,23 +6201,23 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
 		init_vmcs_shadow_fields();
 	}
 
-	exit_handlers[EXIT_REASON_VMCLEAR]	= handle_vmclear,
-	exit_handlers[EXIT_REASON_VMLAUNCH]	= handle_vmlaunch,
-	exit_handlers[EXIT_REASON_VMPTRLD]	= handle_vmptrld,
-	exit_handlers[EXIT_REASON_VMPTRST]	= handle_vmptrst,
-	exit_handlers[EXIT_REASON_VMREAD]	= handle_vmread,
-	exit_handlers[EXIT_REASON_VMRESUME]	= handle_vmresume,
-	exit_handlers[EXIT_REASON_VMWRITE]	= handle_vmwrite,
-	exit_handlers[EXIT_REASON_VMOFF]	= handle_vmoff,
-	exit_handlers[EXIT_REASON_VMON]		= handle_vmon,
-	exit_handlers[EXIT_REASON_INVEPT]	= handle_invept,
-	exit_handlers[EXIT_REASON_INVVPID]	= handle_invvpid,
-	exit_handlers[EXIT_REASON_VMFUNC]	= handle_vmfunc,
+	exit_handlers[EXIT_REASON_VMCLEAR]	= handle_vmclear;
+	exit_handlers[EXIT_REASON_VMLAUNCH]	= handle_vmlaunch;
+	exit_handlers[EXIT_REASON_VMPTRLD]	= handle_vmptrld;
+	exit_handlers[EXIT_REASON_VMPTRST]	= handle_vmptrst;
+	exit_handlers[EXIT_REASON_VMREAD]	= handle_vmread;
+	exit_handlers[EXIT_REASON_VMRESUME]	= handle_vmresume;
+	exit_handlers[EXIT_REASON_VMWRITE]	= handle_vmwrite;
+	exit_handlers[EXIT_REASON_VMOFF]	= handle_vmoff;
+	exit_handlers[EXIT_REASON_VMON]		= handle_vmon;
+	exit_handlers[EXIT_REASON_INVEPT]	= handle_invept;
+	exit_handlers[EXIT_REASON_INVVPID]	= handle_invvpid;
+	exit_handlers[EXIT_REASON_VMFUNC]	= handle_vmfunc;
 
 	kvm_x86_ops->check_nested_events = vmx_check_nested_events;
 	kvm_x86_ops->get_nested_state = vmx_get_nested_state;
 	kvm_x86_ops->set_nested_state = vmx_set_nested_state;
-	kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages,
+	kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages;
 	kvm_x86_ops->nested_enable_evmcs = nested_enable_evmcs;
 	kvm_x86_ops->nested_get_evmcs_version = nested_get_evmcs_version;
 
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 6280f33e5fa6..fc874d4ead0f 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -21,7 +21,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 				bool apicv);
 void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
-void nested_vmx_vcpu_setup(void);
+void nested_vmx_set_vmcs_shadowing_bitmap(void);
 void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu);
 enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 						     bool from_vmentry);
@@ -33,6 +33,7 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata);
 int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 			u32 vmx_instruction_info, bool wr, int len, gva_t *ret);
+void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu);
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 {
@@ -256,7 +257,7 @@ static inline bool fixed_bits_valid(u64 val, u64 fixed0, u64 fixed1)
 	return ((val & fixed1) | fixed0) == val;
 }
 
-static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
+static inline bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0;
 	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1;
@@ -270,7 +271,7 @@ static bool nested_guest_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 	return fixed_bits_valid(val, fixed0, fixed1);
 }
 
-static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
+static inline bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr0_fixed0;
 	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr0_fixed1;
@@ -278,7 +279,7 @@ static bool nested_host_cr0_valid(struct kvm_vcpu *vcpu, unsigned long val)
 	return fixed_bits_valid(val, fixed0, fixed1);
 }
 
-static bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
+static inline bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	u64 fixed0 = to_vmx(vcpu)->nested.msrs.cr4_fixed0;
 	u64 fixed1 = to_vmx(vcpu)->nested.msrs.cr4_fixed1;
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 3e9c059099e9..7023138b1cb0 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -15,6 +15,7 @@
 #include "x86.h"
 #include "cpuid.h"
 #include "lapic.h"
+#include "nested.h"
 #include "pmu.h"
 
 static struct kvm_event_hw_type_mapping intel_arch_events[] = {
@@ -46,6 +47,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
 		if (old_ctrl == new_ctrl)
 			continue;
 
+		__set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use);
 		reprogram_fixed_counter(pmc, new_ctrl, i);
 	}
 
@@ -111,7 +113,7 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 }
 
 /* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
-static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+static int intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	bool fixed = idx & (1u << 30);
@@ -122,8 +124,8 @@ static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
 		(fixed && idx >= pmu->nr_arch_fixed_counters);
 }
 
-static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu,
-					    unsigned idx, u64 *mask)
+static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
+					    unsigned int idx, u64 *mask)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	bool fixed = idx & (1u << 30);
@@ -162,6 +164,18 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	return ret;
 }
 
+static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+
+	pmc = get_fixed_pmc(pmu, msr);
+	pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0);
+	pmc = pmc ? pmc : get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0);
+
+	return pmc;
+}
+
 static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -223,7 +237,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_GLOBAL_CTRL:
 		if (pmu->global_ctrl == data)
 			return 0;
-		if (!(data & pmu->global_ctrl_mask)) {
+		if (kvm_valid_perf_global_ctrl(pmu, data)) {
 			global_ctrl_changed(pmu, data);
 			return 0;
 		}
@@ -317,6 +331,13 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
 	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
 		pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
+
+	bitmap_set(pmu->all_valid_pmc_idx,
+		0, pmu->nr_arch_gp_counters);
+	bitmap_set(pmu->all_valid_pmc_idx,
+		INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters);
+
+	nested_vmx_pmu_entry_exit_ctls_update(vcpu);
 }
 
 static void intel_pmu_init(struct kvm_vcpu *vcpu)
@@ -328,12 +349,14 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 		pmu->gp_counters[i].type = KVM_PMC_GP;
 		pmu->gp_counters[i].vcpu = vcpu;
 		pmu->gp_counters[i].idx = i;
+		pmu->gp_counters[i].current_config = 0;
 	}
 
 	for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) {
 		pmu->fixed_counters[i].type = KVM_PMC_FIXED;
 		pmu->fixed_counters[i].vcpu = vcpu;
 		pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED;
+		pmu->fixed_counters[i].current_config = 0;
 	}
 }
 
@@ -366,8 +389,9 @@ struct kvm_pmu_ops intel_pmu_ops = {
 	.find_fixed_event = intel_find_fixed_event,
 	.pmc_is_enabled = intel_pmc_is_enabled,
 	.pmc_idx_to_pmc = intel_pmc_idx_to_pmc,
+	.rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc,
 	.msr_idx_to_pmc = intel_msr_idx_to_pmc,
-	.is_valid_msr_idx = intel_is_valid_msr_idx,
+	.is_valid_rdpmc_ecx = intel_is_valid_rdpmc_ecx,
 	.is_valid_msr = intel_is_valid_msr,
 	.get_msr = intel_pmu_get_msr,
 	.set_msr = intel_pmu_set_msr,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 04a8212704c1..d175429c91b0 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -106,8 +106,6 @@ module_param(enable_apicv, bool, S_IRUGO);
 static bool __read_mostly nested = 1;
 module_param(nested, bool, S_IRUGO);
 
-static u64 __read_mostly host_xss;
-
 bool __read_mostly enable_pml = 1;
 module_param_named(pml, enable_pml, bool, S_IRUGO);
 
@@ -450,6 +448,7 @@ const u32 vmx_msr_index[] = {
 	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
 #endif
 	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
+	MSR_IA32_TSX_CTRL,
 };
 
 #if IS_ENABLED(CONFIG_HYPERV)
@@ -638,6 +637,23 @@ struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
 	return NULL;
 }
 
+static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, u64 data)
+{
+	int ret = 0;
+
+	u64 old_msr_data = msr->data;
+	msr->data = data;
+	if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
+		preempt_disable();
+		ret = kvm_set_shared_msr(msr->index, msr->data,
+					 msr->mask);
+		preempt_enable();
+		if (ret)
+			msr->data = old_msr_data;
+	}
+	return ret;
+}
+
 void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs)
 {
 	vmcs_clear(loaded_vmcs->vmcs);
@@ -726,8 +742,8 @@ static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg,
 	bool ret;
 	u32 mask = 1 << (seg * SEG_FIELD_NR + field);
 
-	if (!(vmx->vcpu.arch.regs_avail & (1 << VCPU_EXREG_SEGMENTS))) {
-		vmx->vcpu.arch.regs_avail |= (1 << VCPU_EXREG_SEGMENTS);
+	if (!kvm_register_is_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS)) {
+		kvm_register_mark_available(&vmx->vcpu, VCPU_EXREG_SEGMENTS);
 		vmx->segment_cache.bitmask = 0;
 	}
 	ret = vmx->segment_cache.bitmask & mask;
@@ -835,7 +851,7 @@ static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 	vm_exit_controls_clearbit(vmx, exit);
 }
 
-static int find_msr(struct vmx_msrs *m, unsigned int msr)
+int vmx_find_msr_index(struct vmx_msrs *m, u32 msr)
 {
 	unsigned int i;
 
@@ -869,7 +885,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 		}
 		break;
 	}
-	i = find_msr(&m->guest, msr);
+	i = vmx_find_msr_index(&m->guest, msr);
 	if (i < 0)
 		goto skip_guest;
 	--m->guest.nr;
@@ -877,7 +893,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
 
 skip_guest:
-	i = find_msr(&m->host, msr);
+	i = vmx_find_msr_index(&m->host, msr);
 	if (i < 0)
 		return;
 
@@ -936,12 +952,12 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
-	i = find_msr(&m->guest, msr);
+	i = vmx_find_msr_index(&m->guest, msr);
 	if (!entry_only)
-		j = find_msr(&m->host, msr);
+		j = vmx_find_msr_index(&m->host, msr);
 
-	if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) ||
-		(j < 0 &&  m->host.nr == NR_AUTOLOAD_MSRS)) {
+	if ((i < 0 && m->guest.nr == NR_LOADSTORE_MSRS) ||
+		(j < 0 &&  m->host.nr == NR_LOADSTORE_MSRS)) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
@@ -1418,35 +1434,44 @@ static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu);
 
 unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long rflags, save_rflags;
 
-	if (!test_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail)) {
-		__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_RFLAGS)) {
+		kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS);
 		rflags = vmcs_readl(GUEST_RFLAGS);
-		if (to_vmx(vcpu)->rmode.vm86_active) {
+		if (vmx->rmode.vm86_active) {
 			rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
-			save_rflags = to_vmx(vcpu)->rmode.save_rflags;
+			save_rflags = vmx->rmode.save_rflags;
 			rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
 		}
-		to_vmx(vcpu)->rflags = rflags;
+		vmx->rflags = rflags;
 	}
-	return to_vmx(vcpu)->rflags;
+	return vmx->rflags;
 }
 
 void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
-	unsigned long old_rflags = vmx_get_rflags(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long old_rflags;
 
-	__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
-	to_vmx(vcpu)->rflags = rflags;
-	if (to_vmx(vcpu)->rmode.vm86_active) {
-		to_vmx(vcpu)->rmode.save_rflags = rflags;
+	if (enable_unrestricted_guest) {
+		kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS);
+		vmx->rflags = rflags;
+		vmcs_writel(GUEST_RFLAGS, rflags);
+		return;
+	}
+
+	old_rflags = vmx_get_rflags(vcpu);
+	vmx->rflags = rflags;
+	if (vmx->rmode.vm86_active) {
+		vmx->rmode.save_rflags = rflags;
 		rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
 	}
 	vmcs_writel(GUEST_RFLAGS, rflags);
 
-	if ((old_rflags ^ to_vmx(vcpu)->rflags) & X86_EFLAGS_VM)
-		to_vmx(vcpu)->emulation_required = emulation_required(vcpu);
+	if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM)
+		vmx->emulation_required = emulation_required(vcpu);
 }
 
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
@@ -1683,6 +1708,9 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 	index = __find_msr_index(vmx, MSR_TSC_AUX);
 	if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP))
 		move_msr_up(vmx, index, save_nmsrs++);
+	index = __find_msr_index(vmx, MSR_IA32_TSX_CTRL);
+	if (index >= 0)
+		move_msr_up(vmx, index, save_nmsrs++);
 
 	vmx->save_nmsrs = save_nmsrs;
 	vmx->guest_msrs_ready = false;
@@ -1782,6 +1810,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 #endif
 	case MSR_EFER:
 		return kvm_get_msr_common(vcpu, msr_info);
+	case MSR_IA32_TSX_CTRL:
+		if (!msr_info->host_initiated &&
+		    !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR))
+			return 1;
+		goto find_shared_msr;
 	case MSR_IA32_UMWAIT_CONTROL:
 		if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx))
 			return 1;
@@ -1826,14 +1859,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		return vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index,
 				       &msr_info->data);
-	case MSR_IA32_XSS:
-		if (!vmx_xsaves_supported() ||
-		    (!msr_info->host_initiated &&
-		     !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-		       guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))))
-			return 1;
-		msr_info->data = vcpu->arch.ia32_xss;
-		break;
 	case MSR_IA32_RTIT_CTL:
 		if (pt_mode != PT_MODE_HOST_GUEST)
 			return 1;
@@ -1884,8 +1909,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
 			return 1;
-		/* Else, falls through */
+		goto find_shared_msr;
 	default:
+	find_shared_msr:
 		msr = find_msr_entry(vmx, msr_info->index);
 		if (msr) {
 			msr_info->data = msr->data;
@@ -2001,6 +2027,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 					      MSR_IA32_SPEC_CTRL,
 					      MSR_TYPE_RW);
 		break;
+	case MSR_IA32_TSX_CTRL:
+		if (!msr_info->host_initiated &&
+		    !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR))
+			return 1;
+		if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR))
+			return 1;
+		goto find_shared_msr;
 	case MSR_IA32_PRED_CMD:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
@@ -2069,25 +2102,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!nested_vmx_allowed(vcpu))
 			return 1;
 		return vmx_set_vmx_msr(vcpu, msr_index, data);
-	case MSR_IA32_XSS:
-		if (!vmx_xsaves_supported() ||
-		    (!msr_info->host_initiated &&
-		     !(guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-		       guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))))
-			return 1;
-		/*
-		 * The only supported bit as of Skylake is bit 8, but
-		 * it is not supported on KVM.
-		 */
-		if (data != 0)
-			return 1;
-		vcpu->arch.ia32_xss = data;
-		if (vcpu->arch.ia32_xss != host_xss)
-			add_atomic_switch_msr(vmx, MSR_IA32_XSS,
-				vcpu->arch.ia32_xss, host_xss, false);
-		else
-			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
-		break;
 	case MSR_IA32_RTIT_CTL:
 		if ((pt_mode != PT_MODE_HOST_GUEST) ||
 			vmx_rtit_ctl_check(vcpu, data) ||
@@ -2152,23 +2166,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		/* Check reserved bit, higher 32 bits should be zero */
 		if ((data >> 32) != 0)
 			return 1;
-		/* Else, falls through */
+		goto find_shared_msr;
+
 	default:
+	find_shared_msr:
 		msr = find_msr_entry(vmx, msr_index);
-		if (msr) {
-			u64 old_msr_data = msr->data;
-			msr->data = data;
-			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
-				preempt_disable();
-				ret = kvm_set_shared_msr(msr->index, msr->data,
-							 msr->mask);
-				preempt_enable();
-				if (ret)
-					msr->data = old_msr_data;
-			}
-			break;
-		}
-		ret = kvm_set_msr_common(vcpu, msr_info);
+		if (msr)
+			ret = vmx_set_guest_msr(vmx, msr, data);
+		else
+			ret = kvm_set_msr_common(vcpu, msr_info);
 	}
 
 	return ret;
@@ -2176,7 +2182,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 {
-	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, reg);
+
 	switch (reg) {
 	case VCPU_REGS_RSP:
 		vcpu->arch.regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP);
@@ -2188,7 +2195,12 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 		if (enable_ept)
 			ept_save_pdptrs(vcpu);
 		break;
+	case VCPU_EXREG_CR3:
+		if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu)))
+			vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+		break;
 	default:
+		WARN_ON_ONCE(1);
 		break;
 	}
 }
@@ -2859,13 +2871,6 @@ static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits;
 }
 
-static void vmx_decache_cr3(struct kvm_vcpu *vcpu)
-{
-	if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu)))
-		vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
-}
-
 static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 {
 	ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits;
@@ -2878,8 +2883,7 @@ static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
 
-	if (!test_bit(VCPU_EXREG_PDPTR,
-		      (unsigned long *)&vcpu->arch.regs_dirty))
+	if (!kvm_register_is_dirty(vcpu, VCPU_EXREG_PDPTR))
 		return;
 
 	if (is_pae_paging(vcpu)) {
@@ -2901,10 +2905,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 		mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
 	}
 
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_avail);
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_dirty);
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR);
 }
 
 static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
@@ -2913,8 +2914,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
-		vmx_decache_cr3(vcpu);
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3))
+		vmx_cache_reg(vcpu, VCPU_EXREG_CR3);
 	if (!(cr0 & X86_CR0_PG)) {
 		/* From paging/starting to nonpaging */
 		exec_controls_setbit(vmx, CPU_BASED_CR3_LOAD_EXITING |
@@ -2995,6 +2996,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
 void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 	struct kvm *kvm = vcpu->kvm;
+	bool update_guest_cr3 = true;
 	unsigned long guest_cr3;
 	u64 eptp;
 
@@ -3011,15 +3013,20 @@ void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 			spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
 		}
 
-		if (enable_unrestricted_guest || is_paging(vcpu) ||
-		    is_guest_mode(vcpu))
-			guest_cr3 = kvm_read_cr3(vcpu);
-		else
+		/* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */
+		if (is_guest_mode(vcpu))
+			update_guest_cr3 = false;
+		else if (!enable_unrestricted_guest && !is_paging(vcpu))
 			guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr;
+		else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
+			guest_cr3 = vcpu->arch.cr3;
+		else /* vmcs01.GUEST_CR3 is already up-to-date. */
+			update_guest_cr3 = false;
 		ept_load_pdptrs(vcpu);
 	}
 
-	vmcs_writel(GUEST_CR3, guest_cr3);
+	if (update_guest_cr3)
+		vmcs_writel(GUEST_CR3, guest_cr3);
 }
 
 int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
@@ -3753,7 +3760,7 @@ void pt_update_intercept_for_msr(struct vcpu_vmx *vmx)
 	}
 }
 
-static bool vmx_get_enable_apicv(struct kvm_vcpu *vcpu)
+static bool vmx_get_enable_apicv(struct kvm *kvm)
 {
 	return enable_apicv;
 }
@@ -4046,6 +4053,8 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 			guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
 			guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);
 
+		vcpu->arch.xsaves_enabled = xsaves_enabled;
+
 		if (!xsaves_enabled)
 			exec_control &= ~SECONDARY_EXEC_XSAVES;
 
@@ -4158,14 +4167,13 @@ static void ept_set_mmio_spte_mask(void)
 #define VMX_XSS_EXIT_BITMAP 0
 
 /*
- * Sets up the vmcs for emulated real mode.
+ * Noting that the initialization of Guest-state Area of VMCS is in
+ * vmx_vcpu_reset().
  */
-static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
+static void init_vmcs(struct vcpu_vmx *vmx)
 {
-	int i;
-
 	if (nested)
-		nested_vmx_vcpu_setup();
+		nested_vmx_set_vmcs_shadowing_bitmap();
 
 	if (cpu_has_vmx_msr_bitmap())
 		vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));
@@ -4174,7 +4182,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	/* Control */
 	pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx));
-	vmx->hv_deadline_tsc = -1;
 
 	exec_controls_set(vmx, vmx_exec_control(vmx));
 
@@ -4223,21 +4230,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
 
-	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
-		u32 index = vmx_msr_index[i];
-		u32 data_low, data_high;
-		int j = vmx->nmsrs;
-
-		if (rdmsr_safe(index, &data_low, &data_high) < 0)
-			continue;
-		if (wrmsr_safe(index, data_low, data_high) < 0)
-			continue;
-		vmx->guest_msrs[j].index = i;
-		vmx->guest_msrs[j].data = 0;
-		vmx->guest_msrs[j].mask = -1ull;
-		++vmx->nmsrs;
-	}
-
 	vm_exit_controls_set(vmx, vmx_vmexit_ctrl());
 
 	/* 22.2.1, 20.8.1 */
@@ -4248,6 +4240,9 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	set_cr4_guest_host_mask(vmx);
 
+	if (vmx->vpid != 0)
+		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+
 	if (vmx_xsaves_supported())
 		vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
 
@@ -4350,9 +4345,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 
-	if (vmx->vpid != 0)
-		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
-
 	cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
 	vmx->vcpu.arch.cr0 = cr0;
 	vmx_set_cr0(vcpu, cr0); /* enter rmode */
@@ -4707,7 +4699,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int handle_external_interrupt(struct kvm_vcpu *vcpu)
+static __always_inline int handle_external_interrupt(struct kvm_vcpu *vcpu)
 {
 	++vcpu->stat.irq_exits;
 	return 1;
@@ -4979,21 +4971,6 @@ static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
 	vmcs_writel(GUEST_DR7, val);
 }
 
-static int handle_cpuid(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_cpuid(vcpu);
-}
-
-static int handle_rdmsr(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_rdmsr(vcpu);
-}
-
-static int handle_wrmsr(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_wrmsr(vcpu);
-}
-
 static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
 {
 	kvm_apic_update_ppr(vcpu);
@@ -5010,11 +4987,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int handle_halt(struct kvm_vcpu *vcpu)
-{
-	return kvm_emulate_halt(vcpu);
-}
-
 static int handle_vmcall(struct kvm_vcpu *vcpu)
 {
 	return kvm_emulate_hypercall(vcpu);
@@ -5562,11 +5534,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_IO_INSTRUCTION]          = handle_io,
 	[EXIT_REASON_CR_ACCESS]               = handle_cr,
 	[EXIT_REASON_DR_ACCESS]               = handle_dr,
-	[EXIT_REASON_CPUID]                   = handle_cpuid,
-	[EXIT_REASON_MSR_READ]                = handle_rdmsr,
-	[EXIT_REASON_MSR_WRITE]               = handle_wrmsr,
+	[EXIT_REASON_CPUID]                   = kvm_emulate_cpuid,
+	[EXIT_REASON_MSR_READ]                = kvm_emulate_rdmsr,
+	[EXIT_REASON_MSR_WRITE]               = kvm_emulate_wrmsr,
 	[EXIT_REASON_PENDING_INTERRUPT]       = handle_interrupt_window,
-	[EXIT_REASON_HLT]                     = handle_halt,
+	[EXIT_REASON_HLT]                     = kvm_emulate_halt,
 	[EXIT_REASON_INVD]		      = handle_invd,
 	[EXIT_REASON_INVLPG]		      = handle_invlpg,
 	[EXIT_REASON_RDPMC]                   = handle_rdpmc,
@@ -5939,9 +5911,23 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	}
 
 	if (exit_reason < kvm_vmx_max_exit_handlers
-	    && kvm_vmx_exit_handlers[exit_reason])
+	    && kvm_vmx_exit_handlers[exit_reason]) {
+#ifdef CONFIG_RETPOLINE
+		if (exit_reason == EXIT_REASON_MSR_WRITE)
+			return kvm_emulate_wrmsr(vcpu);
+		else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER)
+			return handle_preemption_timer(vcpu);
+		else if (exit_reason == EXIT_REASON_PENDING_INTERRUPT)
+			return handle_interrupt_window(vcpu);
+		else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
+			return handle_external_interrupt(vcpu);
+		else if (exit_reason == EXIT_REASON_HLT)
+			return kvm_emulate_halt(vcpu);
+		else if (exit_reason == EXIT_REASON_EPT_MISCONFIG)
+			return handle_ept_misconfig(vcpu);
+#endif
 		return kvm_vmx_exit_handlers[exit_reason](vcpu);
-	else {
+	} else {
 		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
 				exit_reason);
 		dump_vmcs();
@@ -6027,17 +6013,17 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	int tpr_threshold;
 
 	if (is_guest_mode(vcpu) &&
 		nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
 		return;
 
-	if (irr == -1 || tpr < irr) {
-		vmcs_write32(TPR_THRESHOLD, 0);
-		return;
-	}
-
-	vmcs_write32(TPR_THRESHOLD, irr);
+	tpr_threshold = (irr == -1 || tpr < irr) ? 0 : irr;
+	if (is_guest_mode(vcpu))
+		to_vmx(vcpu)->nested.l1_tpr_threshold = tpr_threshold;
+	else
+		vmcs_write32(TPR_THRESHOLD, tpr_threshold);
 }
 
 void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
@@ -6514,9 +6500,9 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vmx->nested.need_vmcs12_to_shadow_sync)
 		nested_sync_vmcs12_to_shadow(vcpu);
 
-	if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP))
 		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
-	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP))
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
 	cr3 = __get_current_cr3_fast();
@@ -6539,7 +6525,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		vmx_set_interrupt_shadow(vcpu, 0);
 
-	kvm_load_guest_xcr0(vcpu);
+	kvm_load_guest_xsave_state(vcpu);
 
 	if (static_cpu_has(X86_FEATURE_PKU) &&
 	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
@@ -6646,7 +6632,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 			__write_pkru(vmx->host_pkru);
 	}
 
-	kvm_put_guest_xcr0(vcpu);
+	kvm_load_host_xsave_state(vcpu);
 
 	vmx->nested.nested_run_pending = 0;
 	vmx->idt_vectoring_info = 0;
@@ -6700,7 +6686,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	int err;
 	struct vcpu_vmx *vmx;
 	unsigned long *msr_bitmap;
-	int cpu;
+	int i, cpu;
 
 	BUILD_BUG_ON_MSG(offsetof(struct vcpu_vmx, vcpu) != 0,
 		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
@@ -6752,6 +6738,34 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (!vmx->guest_msrs)
 		goto free_pml;
 
+	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
+		u32 index = vmx_msr_index[i];
+		u32 data_low, data_high;
+		int j = vmx->nmsrs;
+
+		if (rdmsr_safe(index, &data_low, &data_high) < 0)
+			continue;
+		if (wrmsr_safe(index, data_low, data_high) < 0)
+			continue;
+
+		vmx->guest_msrs[j].index = i;
+		vmx->guest_msrs[j].data = 0;
+		switch (index) {
+		case MSR_IA32_TSX_CTRL:
+			/*
+			 * No need to pass TSX_CTRL_CPUID_CLEAR through, so
+			 * let's avoid changing CPUID bits under the host
+			 * kernel's feet.
+			 */
+			vmx->guest_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
+			break;
+		default:
+			vmx->guest_msrs[j].mask = -1ull;
+			break;
+		}
+		++vmx->nmsrs;
+	}
+
 	err = alloc_loaded_vmcs(&vmx->vmcs01);
 	if (err < 0)
 		goto free_msrs;
@@ -6776,7 +6790,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	cpu = get_cpu();
 	vmx_vcpu_load(&vmx->vcpu, cpu);
 	vmx->vcpu.cpu = cpu;
-	vmx_vcpu_setup(vmx);
+	init_vmcs(vmx);
 	vmx_vcpu_put(&vmx->vcpu);
 	put_cpu();
 	if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
@@ -6996,6 +7010,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 	cr4_fixed1_update(X86_CR4_SMAP,       ebx, bit(X86_FEATURE_SMAP));
 	cr4_fixed1_update(X86_CR4_PKE,        ecx, bit(X86_FEATURE_PKU));
 	cr4_fixed1_update(X86_CR4_UMIP,       ecx, bit(X86_FEATURE_UMIP));
+	cr4_fixed1_update(X86_CR4_LA57,       ecx, bit(X86_FEATURE_LA57));
 
 #undef cr4_fixed1_update
 }
@@ -7090,6 +7105,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	/* xsaves_enabled is recomputed in vmx_compute_secondary_exec_control(). */
+	vcpu->arch.xsaves_enabled = false;
+
 	if (cpu_has_secondary_exec_ctrls()) {
 		vmx_compute_secondary_exec_control(vmx);
 		vmcs_set_secondary_exec_control(vmx);
@@ -7097,10 +7115,12 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 
 	if (nested_vmx_allowed(vcpu))
 		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
+			FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX |
 			FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
 	else
 		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
-			~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+			~(FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX |
+			  FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX);
 
 	if (nested_vmx_allowed(vcpu)) {
 		nested_vmx_cr_fixed1_bits_update(vcpu);
@@ -7110,6 +7130,15 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
 			guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT))
 		update_intel_pt_cfg(vcpu);
+
+	if (boot_cpu_has(X86_FEATURE_RTM)) {
+		struct shared_msr_entry *msr;
+		msr = find_msr_entry(vmx, MSR_IA32_TSX_CTRL);
+		if (msr) {
+			bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM);
+			vmx_set_guest_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE);
+		}
+	}
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -7598,9 +7627,6 @@ static __init int hardware_setup(void)
 		WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost");
 	}
 
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		rdmsrl(MSR_IA32_XSS, host_xss);
-
 	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
 	    !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
 		enable_vpid = 0;
@@ -7781,7 +7807,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.get_cpl = vmx_get_cpl,
 	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
 	.decache_cr0_guest_bits = vmx_decache_cr0_guest_bits,
-	.decache_cr3 = vmx_decache_cr3,
 	.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
 	.set_cr0 = vmx_set_cr0,
 	.set_cr3 = vmx_set_cr3,
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 5a0f34b1e226..7c1b978b2df4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -22,11 +22,11 @@ extern u32 get_umwait_control_msr(void);
 
 #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
 
-#define NR_AUTOLOAD_MSRS 8
+#define NR_LOADSTORE_MSRS 8
 
 struct vmx_msrs {
 	unsigned int		nr;
-	struct vmx_msr_entry	val[NR_AUTOLOAD_MSRS];
+	struct vmx_msr_entry	val[NR_LOADSTORE_MSRS];
 };
 
 struct shared_msr_entry {
@@ -167,6 +167,9 @@ struct nested_vmx {
 	u64 vmcs01_debugctl;
 	u64 vmcs01_guest_bndcfgs;
 
+	/* to migrate it to L1 if L2 writes to L1's CR8 directly */
+	int l1_tpr_threshold;
+
 	u16 vpid02;
 	u16 last_vpid;
 
@@ -230,6 +233,10 @@ struct vcpu_vmx {
 		struct vmx_msrs host;
 	} msr_autoload;
 
+	struct msr_autostore {
+		struct vmx_msrs guest;
+	} msr_autostore;
+
 	struct {
 		int vm86_active;
 		ulong save_rflags;
@@ -334,6 +341,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
 struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr);
 void pt_update_intercept_for_msr(struct vcpu_vmx *vmx);
 void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
+int vmx_find_msr_index(struct vmx_msrs *m, u32 msr);
 
 #define POSTED_INTR_ON  0
 #define POSTED_INTR_SN  1
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5d530521f11d..3ed167e039e5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -176,6 +176,8 @@ struct kvm_shared_msrs {
 static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
 static struct kvm_shared_msrs __percpu *shared_msrs;
 
+static u64 __read_mostly host_xss;
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "pf_fixed", VCPU_STAT(pf_fixed) },
 	{ "pf_guest", VCPU_STAT(pf_guest) },
@@ -260,23 +262,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	}
 }
 
-static void shared_msr_update(unsigned slot, u32 msr)
-{
-	u64 value;
-	unsigned int cpu = smp_processor_id();
-	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
-
-	/* only read, and nobody should modify it at this time,
-	 * so don't need lock */
-	if (slot >= shared_msrs_global.nr) {
-		printk(KERN_ERR "kvm: invalid MSR slot!");
-		return;
-	}
-	rdmsrl_safe(msr, &value);
-	smsr->values[slot].host = value;
-	smsr->values[slot].curr = value;
-}
-
 void kvm_define_shared_msr(unsigned slot, u32 msr)
 {
 	BUG_ON(slot >= KVM_NR_SHARED_MSRS);
@@ -288,10 +273,16 @@ EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
 
 static void kvm_shared_msr_cpu_online(void)
 {
-	unsigned i;
+	unsigned int cpu = smp_processor_id();
+	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	u64 value;
+	int i;
 
-	for (i = 0; i < shared_msrs_global.nr; ++i)
-		shared_msr_update(i, shared_msrs_global.msrs[i]);
+	for (i = 0; i < shared_msrs_global.nr; ++i) {
+		rdmsrl_safe(shared_msrs_global.msrs[i], &value);
+		smsr->values[i].host = value;
+		smsr->values[i].curr = value;
+	}
 }
 
 int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
@@ -300,13 +291,14 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 	int err;
 
-	if (((value ^ smsr->values[slot].curr) & mask) == 0)
+	value = (value & mask) | (smsr->values[slot].host & ~mask);
+	if (value == smsr->values[slot].curr)
 		return 0;
-	smsr->values[slot].curr = value;
 	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
 	if (err)
 		return 1;
 
+	smsr->values[slot].curr = value;
 	if (!smsr->registered) {
 		smsr->urn.on_user_return = kvm_on_user_return;
 		user_return_notifier_register(&smsr->urn);
@@ -709,10 +701,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
 	ret = 1;
 
 	memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs));
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_avail);
-	__set_bit(VCPU_EXREG_PDPTR,
-		  (unsigned long *)&vcpu->arch.regs_dirty);
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR);
+
 out:
 
 	return ret;
@@ -722,7 +712,6 @@ EXPORT_SYMBOL_GPL(load_pdptrs);
 bool pdptrs_changed(struct kvm_vcpu *vcpu)
 {
 	u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)];
-	bool changed = true;
 	int offset;
 	gfn_t gfn;
 	int r;
@@ -730,8 +719,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	if (!is_pae_paging(vcpu))
 		return false;
 
-	if (!test_bit(VCPU_EXREG_PDPTR,
-		      (unsigned long *)&vcpu->arch.regs_avail))
+	if (!kvm_register_is_available(vcpu, VCPU_EXREG_PDPTR))
 		return true;
 
 	gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT;
@@ -739,11 +727,9 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
 				       PFERR_USER_MASK | PFERR_WRITE_MASK);
 	if (r < 0)
-		goto out;
-	changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
-out:
+		return true;
 
-	return changed;
+	return memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
 }
 EXPORT_SYMBOL_GPL(pdptrs_changed);
 
@@ -812,27 +798,34 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
-void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 {
-	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
-			!vcpu->guest_xcr0_loaded) {
-		/* kvm_set_xcr() also depends on this */
+	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
+
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
-		vcpu->guest_xcr0_loaded = 1;
+
+		if (vcpu->arch.xsaves_enabled &&
+		    vcpu->arch.ia32_xss != host_xss)
+			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
 	}
 }
-EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
+EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);
 
-void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->guest_xcr0_loaded) {
+	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
+
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
-		vcpu->guest_xcr0_loaded = 0;
+
+		if (vcpu->arch.xsaves_enabled &&
+		    vcpu->arch.ia32_xss != host_xss)
+			wrmsrl(MSR_IA32_XSS, host_xss);
 	}
+
 }
-EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
+EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);
 
 static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
@@ -984,7 +977,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 	kvm_mmu_new_cr3(vcpu, cr3, skip_tlb_flush);
 	vcpu->arch.cr3 = cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	return 0;
 }
@@ -1313,23 +1306,15 @@ static u64 kvm_get_arch_capabilities(void)
 		data |= ARCH_CAP_MDS_NO;
 
 	/*
-	 * On TAA affected systems, export MDS_NO=0 when:
-	 *	- TSX is enabled on the host, i.e. X86_FEATURE_RTM=1.
-	 *	- Updated microcode is present. This is detected by
-	 *	  the presence of ARCH_CAP_TSX_CTRL_MSR and ensures
-	 *	  that VERW clears CPU buffers.
-	 *
-	 * When MDS_NO=0 is exported, guests deploy clear CPU buffer
-	 * mitigation and don't complain:
-	 *
-	 *	"Vulnerable: Clear CPU buffers attempted, no microcode"
-	 *
-	 * If TSX is disabled on the system, guests are also mitigated against
-	 * TAA and clear CPU buffer mitigation is not required for guests.
+	 * On TAA affected systems:
+	 *      - nothing to do if TSX is disabled on the host.
+	 *      - we emulate TSX_CTRL if present on the host.
+	 *	  This lets the guest use VERW to clear CPU buffers.
 	 */
-	if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) &&
-	    (data & ARCH_CAP_TSX_CTRL_MSR))
-		data &= ~ARCH_CAP_MDS_NO;
+	if (!boot_cpu_has(X86_FEATURE_RTM))
+		data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR);
+	else if (!boot_cpu_has_bug(X86_BUG_TAA))
+		data |= ARCH_CAP_TAA_NO;
 
 	return data;
 }
@@ -1477,8 +1462,8 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
  * Returns 0 on success, non-0 otherwise.
  * Assumes vcpu_load() was already called.
  */
-static int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
-			 bool host_initiated)
+int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
+		  bool host_initiated)
 {
 	struct msr_data msr;
 	int ret;
@@ -1553,20 +1538,25 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 }
 
 #ifdef CONFIG_X86_64
+struct pvclock_clock {
+	int vclock_mode;
+	u64 cycle_last;
+	u64 mask;
+	u32 mult;
+	u32 shift;
+};
+
 struct pvclock_gtod_data {
 	seqcount_t	seq;
 
-	struct { /* extract of a clocksource struct */
-		int vclock_mode;
-		u64	cycle_last;
-		u64	mask;
-		u32	mult;
-		u32	shift;
-	} clock;
+	struct pvclock_clock clock; /* extract of a clocksource struct */
+	struct pvclock_clock raw_clock; /* extract of a clocksource struct */
 
+	u64		boot_ns_raw;
 	u64		boot_ns;
 	u64		nsec_base;
 	u64		wall_time_sec;
+	u64		monotonic_raw_nsec;
 };
 
 static struct pvclock_gtod_data pvclock_gtod_data;
@@ -1574,9 +1564,10 @@ static struct pvclock_gtod_data pvclock_gtod_data;
 static void update_pvclock_gtod(struct timekeeper *tk)
 {
 	struct pvclock_gtod_data *vdata = &pvclock_gtod_data;
-	u64 boot_ns;
+	u64 boot_ns, boot_ns_raw;
 
 	boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot));
+	boot_ns_raw = ktime_to_ns(ktime_add(tk->tkr_raw.base, tk->offs_boot));
 
 	write_seqcount_begin(&vdata->seq);
 
@@ -1587,11 +1578,20 @@ static void update_pvclock_gtod(struct timekeeper *tk)
 	vdata->clock.mult		= tk->tkr_mono.mult;
 	vdata->clock.shift		= tk->tkr_mono.shift;
 
+	vdata->raw_clock.vclock_mode	= tk->tkr_raw.clock->archdata.vclock_mode;
+	vdata->raw_clock.cycle_last	= tk->tkr_raw.cycle_last;
+	vdata->raw_clock.mask		= tk->tkr_raw.mask;
+	vdata->raw_clock.mult		= tk->tkr_raw.mult;
+	vdata->raw_clock.shift		= tk->tkr_raw.shift;
+
 	vdata->boot_ns			= boot_ns;
 	vdata->nsec_base		= tk->tkr_mono.xtime_nsec;
 
 	vdata->wall_time_sec            = tk->xtime_sec;
 
+	vdata->boot_ns_raw		= boot_ns_raw;
+	vdata->monotonic_raw_nsec	= tk->tkr_raw.xtime_nsec;
+
 	write_seqcount_end(&vdata->seq);
 }
 #endif
@@ -2015,21 +2015,21 @@ static u64 read_tsc(void)
 	return last;
 }
 
-static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
+static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp,
+			  int *mode)
 {
 	long v;
-	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	u64 tsc_pg_val;
 
-	switch (gtod->clock.vclock_mode) {
+	switch (clock->vclock_mode) {
 	case VCLOCK_HVCLOCK:
 		tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(),
 						  tsc_timestamp);
 		if (tsc_pg_val != U64_MAX) {
 			/* TSC page valid */
 			*mode = VCLOCK_HVCLOCK;
-			v = (tsc_pg_val - gtod->clock.cycle_last) &
-				gtod->clock.mask;
+			v = (tsc_pg_val - clock->cycle_last) &
+				clock->mask;
 		} else {
 			/* TSC page invalid */
 			*mode = VCLOCK_NONE;
@@ -2038,8 +2038,8 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
 	case VCLOCK_TSC:
 		*mode = VCLOCK_TSC;
 		*tsc_timestamp = read_tsc();
-		v = (*tsc_timestamp - gtod->clock.cycle_last) &
-			gtod->clock.mask;
+		v = (*tsc_timestamp - clock->cycle_last) &
+			clock->mask;
 		break;
 	default:
 		*mode = VCLOCK_NONE;
@@ -2048,10 +2048,10 @@ static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
 	if (*mode == VCLOCK_NONE)
 		*tsc_timestamp = v = 0;
 
-	return v * gtod->clock.mult;
+	return v * clock->mult;
 }
 
-static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
+static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp)
 {
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	unsigned long seq;
@@ -2060,10 +2060,10 @@ static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
 
 	do {
 		seq = read_seqcount_begin(&gtod->seq);
-		ns = gtod->nsec_base;
-		ns += vgettsc(tsc_timestamp, &mode);
+		ns = gtod->monotonic_raw_nsec;
+		ns += vgettsc(&gtod->raw_clock, tsc_timestamp, &mode);
 		ns >>= gtod->clock.shift;
-		ns += gtod->boot_ns;
+		ns += gtod->boot_ns_raw;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 	*t = ns;
 
@@ -2081,7 +2081,7 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp)
 		seq = read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_sec;
 		ns = gtod->nsec_base;
-		ns += vgettsc(tsc_timestamp, &mode);
+		ns += vgettsc(&gtod->clock, tsc_timestamp, &mode);
 		ns >>= gtod->clock.shift;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 
@@ -2098,7 +2098,7 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
 	if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
 		return false;
 
-	return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns,
+	return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns,
 						      tsc_timestamp));
 }
 
@@ -2721,6 +2721,20 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		kvm_write_tsc(vcpu, msr_info);
 		break;
+	case MSR_IA32_XSS:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+			return 1;
+		/*
+		 * We do support PT if kvm_x86_ops->pt_supported(), but we do
+		 * not support IA32_XSS[bit 8]. Guests will have to use
+		 * RDMSR/WRMSR rather than XSAVES/XRSTORS to save/restore PT
+		 * MSRs.
+		 */
+		if (data != 0)
+			return 1;
+		vcpu->arch.ia32_xss = data;
+		break;
 	case MSR_SMI_COUNT:
 		if (!msr_info->host_initiated)
 			return 1;
@@ -3048,6 +3062,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
 		return get_msr_mce(vcpu, msr_info->index, &msr_info->data,
 				   msr_info->host_initiated);
+	case MSR_IA32_XSS:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+			return 1;
+		msr_info->data = vcpu->arch.ia32_xss;
+		break;
 	case MSR_K7_CLK_CTL:
 		/*
 		 * Provide expected ramp-up count for K7. All other
@@ -3825,12 +3845,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 				vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
 			else
 				vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
-			if (lapic_in_kernel(vcpu)) {
-				if (events->smi.latched_init)
-					set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
-				else
-					clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
-			}
+		}
+
+		if (lapic_in_kernel(vcpu)) {
+			if (events->smi.latched_init)
+				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+			else
+				clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
 		}
 	}
 
@@ -4421,6 +4442,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_SET_NESTED_STATE: {
 		struct kvm_nested_state __user *user_kvm_nested_state = argp;
 		struct kvm_nested_state kvm_state;
+		int idx;
 
 		r = -EINVAL;
 		if (!kvm_x86_ops->set_nested_state)
@@ -4444,7 +4466,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		    && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE))
 			break;
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_GET_SUPPORTED_HV_CPUID: {
@@ -4946,9 +4970,6 @@ set_identity_unlock:
 		if (!irqchip_kernel(kvm))
 			goto set_irqchip_out;
 		r = kvm_vm_ioctl_set_irqchip(kvm, chip);
-		if (r)
-			goto set_irqchip_out;
-		r = 0;
 	set_irqchip_out:
 		kfree(chip);
 		break;
@@ -6136,7 +6157,7 @@ static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase)
 static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
 			      u32 pmc)
 {
-	return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc);
+	return kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc);
 }
 
 static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt,
@@ -7866,6 +7887,19 @@ static void process_smi(struct kvm_vcpu *vcpu)
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 
+void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
+				       unsigned long *vcpu_bitmap)
+{
+	cpumask_var_t cpus;
+
+	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
+
+	kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC,
+				    vcpu_bitmap, cpus);
+
+	free_cpumask_var(cpus);
+}
+
 void kvm_make_scan_ioapic_request(struct kvm *kvm)
 {
 	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
@@ -7943,7 +7977,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 	 */
 	put_page(page);
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
 
 void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu)
 {
@@ -8702,8 +8735,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	    mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
 		goto out;
 
-	/* INITs are latched while in SMM */
-	if ((is_smm(vcpu) || vcpu->arch.smi_pending) &&
+	/*
+	 * KVM_MP_STATE_INIT_RECEIVED means the processor is in
+	 * INIT state; latched init should be reported using
+	 * KVM_SET_VCPU_EVENTS, so reject it here.
+	 */
+	if ((kvm_vcpu_latch_init(vcpu) || vcpu->arch.smi_pending) &&
 	    (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
 	     mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
 		goto out;
@@ -8795,7 +8832,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	vcpu->arch.cr2 = sregs->cr2;
 	mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3;
 	vcpu->arch.cr3 = sregs->cr3;
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	kvm_set_cr8(vcpu, sregs->cr8);
 
@@ -9322,6 +9359,9 @@ int kvm_arch_hardware_setup(void)
 		kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		rdmsrl(MSR_IA32_XSS, host_xss);
+
 	kvm_init_msr_list();
 	return 0;
 }
@@ -9375,7 +9415,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		goto fail_free_pio_data;
 
 	if (irqchip_in_kernel(vcpu->kvm)) {
-		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
+		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu->kvm);
 		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
 		if (r < 0)
 			goto fail_mmu_destroy;
@@ -9444,7 +9484,13 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
 	vcpu->arch.l1tf_flush_l1d = true;
+	if (pmu->version && unlikely(pmu->event_count)) {
+		pmu->need_cleanup = true;
+		kvm_make_request(KVM_REQ_PMU, vcpu);
+	}
 	kvm_x86_ops->sched_in(vcpu, cpu);
 }
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index dbf7442a822b..29391af8871d 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -238,8 +238,7 @@ static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
 	return false;
 }
 
-static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu,
-					       enum kvm_reg reg)
+static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu, int reg)
 {
 	unsigned long val = kvm_register_read(vcpu, reg);
 
@@ -247,8 +246,7 @@ static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu,
 }
 
 static inline void kvm_register_writel(struct kvm_vcpu *vcpu,
-				       enum kvm_reg reg,
-				       unsigned long val)
+				       int reg, unsigned long val)
 {
 	if (!is_64_bit_mode(vcpu))
 		val = (u32)val;
@@ -260,6 +258,11 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
 	return !(kvm->arch.disabled_quirks & quirk);
 }
 
+static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu)
+{
+	return is_smm(vcpu) || kvm_x86_ops->apic_init_signal_blocked(vcpu);
+}
+
 void kvm_set_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
 
@@ -366,7 +369,7 @@ static inline bool kvm_pat_valid(u64 data)
 	return (data | ((data & 0x0202020202020202ull) << 1)) == data;
 }
 
-void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
-void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
+void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu);
+void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu);
 
 #endif
author	Linus Torvalds <torvalds@linux-foundation.org>	2019-11-25 18:02:36 -0800
committer	Linus Torvalds <torvalds@linux-foundation.org>	2019-11-25 18:02:36 -0800
commit	752272f16dd18f2cac58a583a8673c8e2fb93abb (patch)
tree	1a2bae3067e1133c1d1b8e0bbbaea8c34e3321b2 /arch/x86
parent	Merge tag 'for-linus-5.5a-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip (diff)
parent	Merge tag 'kvm-ppc-next-5.5-2' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD (diff)
download	linux-dev-752272f16dd18f2cac58a583a8673c8e2fb93abb.tar.xz linux-dev-752272f16dd18f2cac58a583a8673c8e2fb93abb.zip