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

Pull more kvm updates from Paolo Bonzini:
 "Generic:

   - selftest compilation fix for non-x86

   - KVM: avoid warning on s390 in mark_page_dirty

 x86:

   - fix page write-protection bug and improve comments

   - use binary search to lookup the PMU event filter, add test

   - enable_pmu module parameter support for Intel CPUs

   - switch blocked_vcpu_on_cpu_lock to raw spinlock

   - cleanups of blocked vCPU logic

   - partially allow KVM_SET_CPUID{,2} after KVM_RUN (5.16 regression)

   - various small fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (46 commits)
  docs: kvm: fix WARNINGs from api.rst
  selftests: kvm/x86: Fix the warning in lib/x86_64/processor.c
  selftests: kvm/x86: Fix the warning in pmu_event_filter_test.c
  kvm: selftests: Do not indent with spaces
  kvm: selftests: sync uapi/linux/kvm.h with Linux header
  selftests: kvm: add amx_test to .gitignore
  KVM: SVM: Nullify vcpu_(un)blocking() hooks if AVIC is disabled
  KVM: SVM: Move svm_hardware_setup() and its helpers below svm_x86_ops
  KVM: SVM: Drop AVIC's intermediate avic_set_running() helper
  KVM: VMX: Don't do full kick when handling posted interrupt wakeup
  KVM: VMX: Fold fallback path into triggering posted IRQ helper
  KVM: VMX: Pass desired vector instead of bool for triggering posted IRQ
  KVM: VMX: Don't do full kick when triggering posted interrupt "fails"
  KVM: SVM: Skip AVIC and IRTE updates when loading blocking vCPU
  KVM: SVM: Use kvm_vcpu_is_blocking() in AVIC load to handle preemption
  KVM: SVM: Remove unnecessary APICv/AVIC update in vCPU unblocking path
  KVM: SVM: Don't bother checking for "running" AVIC when kicking for IPIs
  KVM: SVM: Signal AVIC doorbell iff vCPU is in guest mode
  KVM: x86: Remove defunct pre_block/post_block kvm_x86_ops hooks
  KVM: x86: Unexport LAPIC's switch_to_{hv,sw}_timer() helpers
  ...

21 files changed, 664 insertions, 535 deletions

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index f658bb4dbb74..631d5040b31e 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -55,6 +55,7 @@ KVM_X86_OP_NULL(tlb_remote_flush)
 KVM_X86_OP_NULL(tlb_remote_flush_with_range)
 KVM_X86_OP(tlb_flush_gva)
 KVM_X86_OP(tlb_flush_guest)
+KVM_X86_OP(vcpu_pre_run)
 KVM_X86_OP(run)
 KVM_X86_OP_NULL(handle_exit)
 KVM_X86_OP_NULL(skip_emulated_instruction)
@@ -98,8 +99,6 @@ KVM_X86_OP(handle_exit_irqoff)
 KVM_X86_OP_NULL(request_immediate_exit)
 KVM_X86_OP(sched_in)
 KVM_X86_OP_NULL(update_cpu_dirty_logging)
-KVM_X86_OP_NULL(pre_block)
-KVM_X86_OP_NULL(post_block)
 KVM_X86_OP_NULL(vcpu_blocking)
 KVM_X86_OP_NULL(vcpu_unblocking)
 KVM_X86_OP_NULL(update_pi_irte)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0677b9ea01c9..1384517d7709 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1381,6 +1381,7 @@ struct kvm_x86_ops {
 	 */
 	void (*tlb_flush_guest)(struct kvm_vcpu *vcpu);
 
+	int (*vcpu_pre_run)(struct kvm_vcpu *vcpu);
 	enum exit_fastpath_completion (*run)(struct kvm_vcpu *vcpu);
 	int (*handle_exit)(struct kvm_vcpu *vcpu,
 		enum exit_fastpath_completion exit_fastpath);
@@ -1454,18 +1455,6 @@ struct kvm_x86_ops {
 	const struct kvm_pmu_ops *pmu_ops;
 	const struct kvm_x86_nested_ops *nested_ops;
 
-	/*
-	 * Architecture specific hooks for vCPU blocking due to
-	 * HLT instruction.
-	 * Returns for .pre_block():
-	 *    - 0 means continue to block the vCPU.
-	 *    - 1 means we cannot block the vCPU since some event
-	 *        happens during this period, such as, 'ON' bit in
-	 *        posted-interrupts descriptor is set.
-	 */
-	int (*pre_block)(struct kvm_vcpu *vcpu);
-	void (*post_block)(struct kvm_vcpu *vcpu);
-
 	void (*vcpu_blocking)(struct kvm_vcpu *vcpu);
 	void (*vcpu_unblocking)(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index c55e57b30e81..3902c28fb6cb 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -119,6 +119,28 @@ static int kvm_check_cpuid(struct kvm_vcpu *vcpu,
 	return fpu_enable_guest_xfd_features(&vcpu->arch.guest_fpu, xfeatures);
 }
 
+/* Check whether the supplied CPUID data is equal to what is already set for the vCPU. */
+static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
+				 int nent)
+{
+	struct kvm_cpuid_entry2 *orig;
+	int i;
+
+	if (nent != vcpu->arch.cpuid_nent)
+		return -EINVAL;
+
+	for (i = 0; i < nent; i++) {
+		orig = &vcpu->arch.cpuid_entries[i];
+		if (e2[i].function != orig->function ||
+		    e2[i].index != orig->index ||
+		    e2[i].eax != orig->eax || e2[i].ebx != orig->ebx ||
+		    e2[i].ecx != orig->ecx || e2[i].edx != orig->edx)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu)
 {
 	u32 function;
@@ -145,14 +167,21 @@ static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu)
 	}
 }
 
-static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
+static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu,
+					      struct kvm_cpuid_entry2 *entries, int nent)
 {
 	u32 base = vcpu->arch.kvm_cpuid_base;
 
 	if (!base)
 		return NULL;
 
-	return kvm_find_cpuid_entry(vcpu, base | KVM_CPUID_FEATURES, 0);
+	return cpuid_entry2_find(entries, nent, base | KVM_CPUID_FEATURES, 0);
+}
+
+static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
+{
+	return __kvm_find_kvm_cpuid_features(vcpu, vcpu->arch.cpuid_entries,
+					     vcpu->arch.cpuid_nent);
 }
 
 void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
@@ -167,11 +196,12 @@ void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
 		vcpu->arch.pv_cpuid.features = best->eax;
 }
 
-void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
+static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries,
+				       int nent)
 {
 	struct kvm_cpuid_entry2 *best;
 
-	best = kvm_find_cpuid_entry(vcpu, 1, 0);
+	best = cpuid_entry2_find(entries, nent, 1, 0);
 	if (best) {
 		/* Update OSXSAVE bit */
 		if (boot_cpu_has(X86_FEATURE_XSAVE))
@@ -182,33 +212,38 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
 			   vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE);
 	}
 
-	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	best = cpuid_entry2_find(entries, nent, 7, 0);
 	if (best && boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7)
 		cpuid_entry_change(best, X86_FEATURE_OSPKE,
 				   kvm_read_cr4_bits(vcpu, X86_CR4_PKE));
 
-	best = kvm_find_cpuid_entry(vcpu, 0xD, 0);
+	best = cpuid_entry2_find(entries, nent, 0xD, 0);
 	if (best)
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, false);
 
-	best = kvm_find_cpuid_entry(vcpu, 0xD, 1);
+	best = cpuid_entry2_find(entries, nent, 0xD, 1);
 	if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) ||
 		     cpuid_entry_has(best, X86_FEATURE_XSAVEC)))
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
-	best = kvm_find_kvm_cpuid_features(vcpu);
+	best = __kvm_find_kvm_cpuid_features(vcpu, entries, nent);
 	if (kvm_hlt_in_guest(vcpu->kvm) && best &&
 		(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
 		best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
 
 	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
-		best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
+		best = cpuid_entry2_find(entries, nent, 0x1, 0);
 		if (best)
 			cpuid_entry_change(best, X86_FEATURE_MWAIT,
 					   vcpu->arch.ia32_misc_enable_msr &
 					   MSR_IA32_MISC_ENABLE_MWAIT);
 	}
 }
+
+void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
+{
+	__kvm_update_cpuid_runtime(vcpu, vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
+}
 EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime);
 
 static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
@@ -298,6 +333,22 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
 {
 	int r;
 
+	__kvm_update_cpuid_runtime(vcpu, e2, nent);
+
+	/*
+	 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
+	 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
+	 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
+	 * faults due to reusing SPs/SPTEs. In practice no sane VMM mucks with
+	 * the core vCPU model on the fly. It would've been better to forbid any
+	 * KVM_SET_CPUID{,2} calls after KVM_RUN altogether but unfortunately
+	 * some VMMs (e.g. QEMU) reuse vCPU fds for CPU hotplug/unplug and do
+	 * KVM_SET_CPUID{,2} again. To support this legacy behavior, check
+	 * whether the supplied CPUID data is equal to what's already set.
+	 */
+	if (vcpu->arch.last_vmentry_cpu != -1)
+		return kvm_cpuid_check_equal(vcpu, e2, nent);
+
 	r = kvm_check_cpuid(vcpu, e2, nent);
 	if (r)
 		return r;
@@ -307,7 +358,6 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
 	vcpu->arch.cpuid_nent = nent;
 
 	kvm_update_kvm_cpuid_base(vcpu);
-	kvm_update_cpuid_runtime(vcpu);
 	kvm_vcpu_after_set_cpuid(vcpu);
 
 	return 0;
@@ -795,10 +845,10 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		perf_get_x86_pmu_capability(&cap);
 
 		/*
-		 * Only support guest architectural pmu on a host
-		 * with architectural pmu.
+		 * The guest architecture pmu is only supported if the architecture
+		 * pmu exists on the host and the module parameters allow it.
 		 */
-		if (!cap.version)
+		if (!cap.version || !enable_pmu)
 			memset(&cap, 0, sizeof(cap));
 
 		eax.split.version_id = min(cap.version, 2);
@@ -886,6 +936,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 				--array->nent;
 				continue;
 			}
+
+			if (!kvm_cpu_cap_has(X86_FEATURE_XFD))
+				entry->ecx &= ~BIT_ULL(2);
 			entry->edx = 0;
 		}
 		break;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c5028e6b0f96..baca9fa37a91 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1950,7 +1950,6 @@ void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu)
 {
 	restart_apic_timer(vcpu->arch.apic);
 }
-EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer);
 
 void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
 {
@@ -1962,7 +1961,6 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
 		start_sw_timer(apic);
 	preempt_enable();
 }
-EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);
 
 void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1d275e9d76b5..593093b52395 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5756,6 +5756,7 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 				continue;
 
 			flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp,
+
 							PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL,
 							start, end - 1, true, flush);
 		}
@@ -5825,15 +5826,27 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
 	}
 
 	/*
-	 * We can flush all the TLBs out of the mmu lock without TLB
-	 * corruption since we just change the spte from writable to
-	 * readonly so that we only need to care the case of changing
-	 * spte from present to present (changing the spte from present
-	 * to nonpresent will flush all the TLBs immediately), in other
-	 * words, the only case we care is mmu_spte_update() where we
-	 * have checked Host-writable | MMU-writable instead of
-	 * PT_WRITABLE_MASK, that means it does not depend on PT_WRITABLE_MASK
-	 * anymore.
+	 * Flush TLBs if any SPTEs had to be write-protected to ensure that
+	 * guest writes are reflected in the dirty bitmap before the memslot
+	 * update completes, i.e. before enabling dirty logging is visible to
+	 * userspace.
+	 *
+	 * Perform the TLB flush outside the mmu_lock to reduce the amount of
+	 * time the lock is held. However, this does mean that another CPU can
+	 * now grab mmu_lock and encounter a write-protected SPTE while CPUs
+	 * still have a writable mapping for the associated GFN in their TLB.
+	 *
+	 * This is safe but requires KVM to be careful when making decisions
+	 * based on the write-protection status of an SPTE. Specifically, KVM
+	 * also write-protects SPTEs to monitor changes to guest page tables
+	 * during shadow paging, and must guarantee no CPUs can write to those
+	 * page before the lock is dropped. As mentioned in the previous
+	 * paragraph, a write-protected SPTE is no guarantee that CPU cannot
+	 * perform writes. So to determine if a TLB flush is truly required, KVM
+	 * will clear a separate software-only bit (MMU-writable) and skip the
+	 * flush if-and-only-if this bit was already clear.
+	 *
+	 * See DEFAULT_SPTE_MMU_WRITEABLE for more details.
 	 */
 	if (flush)
 		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 351b04ad62a1..73cfe62fdad1 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -216,6 +216,7 @@ u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn)
 
 	new_spte &= ~PT_WRITABLE_MASK;
 	new_spte &= ~shadow_host_writable_mask;
+	new_spte &= ~shadow_mmu_writable_mask;
 
 	new_spte = mark_spte_for_access_track(new_spte);
 
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index a4af2a42695c..be6a007a4af3 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -60,10 +60,6 @@ static_assert(SPTE_TDP_AD_ENABLED_MASK == 0);
 	(((address) >> PT64_LEVEL_SHIFT(level)) & ((1 << PT64_LEVEL_BITS) - 1))
 #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
 
-/* Bits 9 and 10 are ignored by all non-EPT PTEs. */
-#define DEFAULT_SPTE_HOST_WRITEABLE	BIT_ULL(9)
-#define DEFAULT_SPTE_MMU_WRITEABLE	BIT_ULL(10)
-
 /*
  * The mask/shift to use for saving the original R/X bits when marking the PTE
  * as not-present for access tracking purposes. We do not save the W bit as the
@@ -79,6 +75,35 @@ static_assert(SPTE_TDP_AD_ENABLED_MASK == 0);
 static_assert(!(SPTE_TDP_AD_MASK & SHADOW_ACC_TRACK_SAVED_MASK));
 
 /*
+ * *_SPTE_HOST_WRITEABLE (aka Host-writable) indicates whether the host permits
+ * writes to the guest page mapped by the SPTE. This bit is cleared on SPTEs
+ * that map guest pages in read-only memslots and read-only VMAs.
+ *
+ * Invariants:
+ *  - If Host-writable is clear, PT_WRITABLE_MASK must be clear.
+ *
+ *
+ * *_SPTE_MMU_WRITEABLE (aka MMU-writable) indicates whether the shadow MMU
+ * allows writes to the guest page mapped by the SPTE. This bit is cleared when
+ * the guest page mapped by the SPTE contains a page table that is being
+ * monitored for shadow paging. In this case the SPTE can only be made writable
+ * by unsyncing the shadow page under the mmu_lock.
+ *
+ * Invariants:
+ *  - If MMU-writable is clear, PT_WRITABLE_MASK must be clear.
+ *  - If MMU-writable is set, Host-writable must be set.
+ *
+ * If MMU-writable is set, PT_WRITABLE_MASK is normally set but can be cleared
+ * to track writes for dirty logging. For such SPTEs, KVM will locklessly set
+ * PT_WRITABLE_MASK upon the next write from the guest and record the write in
+ * the dirty log (see fast_page_fault()).
+ */
+
+/* Bits 9 and 10 are ignored by all non-EPT PTEs. */
+#define DEFAULT_SPTE_HOST_WRITEABLE	BIT_ULL(9)
+#define DEFAULT_SPTE_MMU_WRITEABLE	BIT_ULL(10)
+
+/*
  * Low ignored bits are at a premium for EPT, use high ignored bits, taking care
  * to not overlap the A/D type mask or the saved access bits of access-tracked
  * SPTEs when A/D bits are disabled.
@@ -316,8 +341,13 @@ static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check,
 
 static inline bool spte_can_locklessly_be_made_writable(u64 spte)
 {
-	return (spte & shadow_host_writable_mask) &&
-	       (spte & shadow_mmu_writable_mask);
+	if (spte & shadow_mmu_writable_mask) {
+		WARN_ON_ONCE(!(spte & shadow_host_writable_mask));
+		return true;
+	}
+
+	WARN_ON_ONCE(spte & PT_WRITABLE_MASK);
+	return false;
 }
 
 static inline u64 get_mmio_spte_generation(u64 spte)
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 7b1bc816b7c3..bc9e3553fba2 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1442,12 +1442,12 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root,
 		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
 
-		if (!is_writable_pte(iter.old_spte))
-			break;
-
 		new_spte = iter.old_spte &
 			~(PT_WRITABLE_MASK | shadow_mmu_writable_mask);
 
+		if (new_spte == iter.old_spte)
+			break;
+
 		tdp_mmu_set_spte(kvm, &iter, new_spte);
 		spte_set = true;
 	}
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 261b39cbef6e..f614f95acc6b 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -13,6 +13,8 @@
 #include <linux/types.h>
 #include <linux/kvm_host.h>
 #include <linux/perf_event.h>
+#include <linux/bsearch.h>
+#include <linux/sort.h>
 #include <asm/perf_event.h>
 #include "x86.h"
 #include "cpuid.h"
@@ -109,6 +111,9 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		.config = config,
 	};
 
+	if (type == PERF_TYPE_HARDWARE && config >= PERF_COUNT_HW_MAX)
+		return;
+
 	attr.sample_period = get_sample_period(pmc, pmc->counter);
 
 	if (in_tx)
@@ -169,12 +174,16 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
 	return true;
 }
 
+static int cmp_u64(const void *a, const void *b)
+{
+	return *(__u64 *)a - *(__u64 *)b;
+}
+
 void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 {
 	unsigned config, type = PERF_TYPE_RAW;
 	struct kvm *kvm = pmc->vcpu->kvm;
 	struct kvm_pmu_event_filter *filter;
-	int i;
 	bool allow_event = true;
 
 	if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
@@ -189,16 +198,13 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 
 	filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
 	if (filter) {
-		for (i = 0; i < filter->nevents; i++)
-			if (filter->events[i] ==
-			    (eventsel & AMD64_RAW_EVENT_MASK_NB))
-				break;
-		if (filter->action == KVM_PMU_EVENT_ALLOW &&
-		    i == filter->nevents)
-			allow_event = false;
-		if (filter->action == KVM_PMU_EVENT_DENY &&
-		    i < filter->nevents)
-			allow_event = false;
+		__u64 key = eventsel & AMD64_RAW_EVENT_MASK_NB;
+
+		if (bsearch(&key, filter->events, filter->nevents,
+			    sizeof(__u64), cmp_u64))
+			allow_event = filter->action == KVM_PMU_EVENT_ALLOW;
+		else
+			allow_event = filter->action == KVM_PMU_EVENT_DENY;
 	}
 	if (!allow_event)
 		return;
@@ -573,6 +579,11 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
 	/* Ensure nevents can't be changed between the user copies. */
 	*filter = tmp;
 
+	/*
+	 * Sort the in-kernel list so that we can search it with bsearch.
+	 */
+	sort(&filter->events, filter->nevents, sizeof(__u64), cmp_u64, NULL);
+
 	mutex_lock(&kvm->lock);
 	filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter,
 				     mutex_is_locked(&kvm->lock));
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 0e5b49294086..90364d02f22a 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -295,13 +295,16 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source,
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
 
+	/*
+	 * Wake any target vCPUs that are blocking, i.e. waiting for a wake
+	 * event.  There's no need to signal doorbells, as hardware has handled
+	 * vCPUs that were in guest at the time of the IPI, and vCPUs that have
+	 * since entered the guest will have processed pending IRQs at VMRUN.
+	 */
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		bool m = kvm_apic_match_dest(vcpu, source,
-					     icrl & APIC_SHORT_MASK,
-					     GET_APIC_DEST_FIELD(icrh),
-					     icrl & APIC_DEST_MASK);
-
-		if (m && !avic_vcpu_is_running(vcpu))
+		if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK,
+					GET_APIC_DEST_FIELD(icrh),
+					icrl & APIC_DEST_MASK))
 			kvm_vcpu_wake_up(vcpu);
 	}
 }
@@ -672,9 +675,22 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 		return -1;
 
 	kvm_lapic_set_irr(vec, vcpu->arch.apic);
+
+	/*
+	 * Pairs with the smp_mb_*() after setting vcpu->guest_mode in
+	 * vcpu_enter_guest() to ensure the write to the vIRR is ordered before
+	 * the read of guest_mode, which guarantees that either VMRUN will see
+	 * and process the new vIRR entry, or that the below code will signal
+	 * the doorbell if the vCPU is already running in the guest.
+	 */
 	smp_mb__after_atomic();
 
-	if (avic_vcpu_is_running(vcpu)) {
+	/*
+	 * Signal the doorbell to tell hardware to inject the IRQ if the vCPU
+	 * is in the guest.  If the vCPU is not in the guest, hardware will
+	 * automatically process AVIC interrupts at VMRUN.
+	 */
+	if (vcpu->mode == IN_GUEST_MODE) {
 		int cpu = READ_ONCE(vcpu->cpu);
 
 		/*
@@ -688,8 +704,13 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 		if (cpu != get_cpu())
 			wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu));
 		put_cpu();
-	} else
+	} else {
+		/*
+		 * Wake the vCPU if it was blocking.  KVM will then detect the
+		 * pending IRQ when checking if the vCPU has a wake event.
+		 */
 		kvm_vcpu_wake_up(vcpu);
+	}
 
 	return 0;
 }
@@ -957,6 +978,8 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	int h_physical_id = kvm_cpu_get_apicid(cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	lockdep_assert_preemption_disabled();
+
 	/*
 	 * Since the host physical APIC id is 8 bits,
 	 * we can support host APIC ID upto 255.
@@ -964,19 +987,25 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
 		return;
 
+	/*
+	 * No need to update anything if the vCPU is blocking, i.e. if the vCPU
+	 * is being scheduled in after being preempted.  The CPU entries in the
+	 * Physical APIC table and IRTE are consumed iff IsRun{ning} is '1'.
+	 * If the vCPU was migrated, its new CPU value will be stuffed when the
+	 * vCPU unblocks.
+	 */
+	if (kvm_vcpu_is_blocking(vcpu))
+		return;
+
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
 	WARN_ON(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
 
 	entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
 	entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK);
-
-	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
-	if (svm->avic_is_running)
-		entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+	entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
 
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
-	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id,
-					svm->avic_is_running);
+	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
 }
 
 void avic_vcpu_put(struct kvm_vcpu *vcpu)
@@ -984,42 +1013,56 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 	u64 entry;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	lockdep_assert_preemption_disabled();
+
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
-	if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
-		avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
+
+	/* Nothing to do if IsRunning == '0' due to vCPU blocking. */
+	if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK))
+		return;
+
+	avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
 
 	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
 }
 
-/*
- * This function is called during VCPU halt/unhalt.
- */
-static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
+void avic_vcpu_blocking(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_svm *svm = to_svm(vcpu);
-	int cpu = get_cpu();
-
-	WARN_ON(cpu != vcpu->cpu);
-	svm->avic_is_running = is_run;
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return;
 
-	if (kvm_vcpu_apicv_active(vcpu)) {
-		if (is_run)
-			avic_vcpu_load(vcpu, cpu);
-		else
-			avic_vcpu_put(vcpu);
-	}
-	put_cpu();
+	preempt_disable();
+
+       /*
+        * Unload the AVIC when the vCPU is about to block, _before_
+        * the vCPU actually blocks.
+        *
+        * Any IRQs that arrive before IsRunning=0 will not cause an
+        * incomplete IPI vmexit on the source, therefore vIRR will also
+        * be checked by kvm_vcpu_check_block() before blocking.  The
+        * memory barrier implicit in set_current_state orders writing
+        * IsRunning=0 before reading the vIRR.  The processor needs a
+        * matching memory barrier on interrupt delivery between writing
+        * IRR and reading IsRunning; the lack of this barrier might be
+        * the cause of errata #1235).
+        */
+	avic_vcpu_put(vcpu);
+
+	preempt_enable();
 }
 
-void svm_vcpu_blocking(struct kvm_vcpu *vcpu)
+void avic_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
-	avic_set_running(vcpu, false);
-}
+	int cpu;
 
-void svm_vcpu_unblocking(struct kvm_vcpu *vcpu)
-{
-	if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu))
-		kvm_vcpu_update_apicv(vcpu);
-	avic_set_running(vcpu, true);
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+	cpu = get_cpu();
+	WARN_ON(cpu != vcpu->cpu);
+
+	avic_vcpu_load(vcpu, cpu);
+
+	put_cpu();
 }
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 12d8b301065a..5aa45f13b16d 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -101,7 +101,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 {
 	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
 
-	if (!pmu)
+	if (!enable_pmu)
 		return NULL;
 
 	switch (msr) {
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 46bcc706f257..2c99b18d76c0 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -192,10 +192,6 @@ module_param(vgif, int, 0444);
 static int lbrv = true;
 module_param(lbrv, int, 0444);
 
-/* enable/disable PMU virtualization */
-bool pmu = true;
-module_param(pmu, bool, 0444);
-
 static int tsc_scaling = true;
 module_param(tsc_scaling, int, 0444);
 
@@ -873,47 +869,6 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
 	}
 }
 
-/*
- * The default MMIO mask is a single bit (excluding the present bit),
- * which could conflict with the memory encryption bit. Check for
- * memory encryption support and override the default MMIO mask if
- * memory encryption is enabled.
- */
-static __init void svm_adjust_mmio_mask(void)
-{
-	unsigned int enc_bit, mask_bit;
-	u64 msr, mask;
-
-	/* If there is no memory encryption support, use existing mask */
-	if (cpuid_eax(0x80000000) < 0x8000001f)
-		return;
-
-	/* If memory encryption is not enabled, use existing mask */
-	rdmsrl(MSR_AMD64_SYSCFG, msr);
-	if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
-		return;
-
-	enc_bit = cpuid_ebx(0x8000001f) & 0x3f;
-	mask_bit = boot_cpu_data.x86_phys_bits;
-
-	/* Increment the mask bit if it is the same as the encryption bit */
-	if (enc_bit == mask_bit)
-		mask_bit++;
-
-	/*
-	 * If the mask bit location is below 52, then some bits above the
-	 * physical addressing limit will always be reserved, so use the
-	 * rsvd_bits() function to generate the mask. This mask, along with
-	 * the present bit, will be used to generate a page fault with
-	 * PFER.RSV = 1.
-	 *
-	 * If the mask bit location is 52 (or above), then clear the mask.
-	 */
-	mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0;
-
-	kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
-}
-
 static void svm_hardware_teardown(void)
 {
 	int cpu;
@@ -928,198 +883,6 @@ static void svm_hardware_teardown(void)
 	iopm_base = 0;
 }
 
-static __init void svm_set_cpu_caps(void)
-{
-	kvm_set_cpu_caps();
-
-	supported_xss = 0;
-
-	/* CPUID 0x80000001 and 0x8000000A (SVM features) */
-	if (nested) {
-		kvm_cpu_cap_set(X86_FEATURE_SVM);
-
-		if (nrips)
-			kvm_cpu_cap_set(X86_FEATURE_NRIPS);
-
-		if (npt_enabled)
-			kvm_cpu_cap_set(X86_FEATURE_NPT);
-
-		if (tsc_scaling)
-			kvm_cpu_cap_set(X86_FEATURE_TSCRATEMSR);
-
-		/* Nested VM can receive #VMEXIT instead of triggering #GP */
-		kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
-	}
-
-	/* CPUID 0x80000008 */
-	if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
-	    boot_cpu_has(X86_FEATURE_AMD_SSBD))
-		kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD);
-
-	/* AMD PMU PERFCTR_CORE CPUID */
-	if (pmu && boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
-		kvm_cpu_cap_set(X86_FEATURE_PERFCTR_CORE);
-
-	/* CPUID 0x8000001F (SME/SEV features) */
-	sev_set_cpu_caps();
-}
-
-static __init int svm_hardware_setup(void)
-{
-	int cpu;
-	struct page *iopm_pages;
-	void *iopm_va;
-	int r;
-	unsigned int order = get_order(IOPM_SIZE);
-
-	/*
-	 * NX is required for shadow paging and for NPT if the NX huge pages
-	 * mitigation is enabled.
-	 */
-	if (!boot_cpu_has(X86_FEATURE_NX)) {
-		pr_err_ratelimited("NX (Execute Disable) not supported\n");
-		return -EOPNOTSUPP;
-	}
-	kvm_enable_efer_bits(EFER_NX);
-
-	iopm_pages = alloc_pages(GFP_KERNEL, order);
-
-	if (!iopm_pages)
-		return -ENOMEM;
-
-	iopm_va = page_address(iopm_pages);
-	memset(iopm_va, 0xff, PAGE_SIZE * (1 << order));
-	iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
-
-	init_msrpm_offsets();
-
-	supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
-
-	if (boot_cpu_has(X86_FEATURE_FXSR_OPT))
-		kvm_enable_efer_bits(EFER_FFXSR);
-
-	if (tsc_scaling) {
-		if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) {
-			tsc_scaling = false;
-		} else {
-			pr_info("TSC scaling supported\n");
-			kvm_has_tsc_control = true;
-			kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX;
-			kvm_tsc_scaling_ratio_frac_bits = 32;
-		}
-	}
-
-	tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX);
-
-	/* Check for pause filtering support */
-	if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) {
-		pause_filter_count = 0;
-		pause_filter_thresh = 0;
-	} else if (!boot_cpu_has(X86_FEATURE_PFTHRESHOLD)) {
-		pause_filter_thresh = 0;
-	}
-
-	if (nested) {
-		printk(KERN_INFO "kvm: Nested Virtualization enabled\n");
-		kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE);
-	}
-
-	/*
-	 * KVM's MMU doesn't support using 2-level paging for itself, and thus
-	 * NPT isn't supported if the host is using 2-level paging since host
-	 * CR4 is unchanged on VMRUN.
-	 */
-	if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE))
-		npt_enabled = false;
-
-	if (!boot_cpu_has(X86_FEATURE_NPT))
-		npt_enabled = false;
-
-	/* Force VM NPT level equal to the host's paging level */
-	kvm_configure_mmu(npt_enabled, get_npt_level(),
-			  get_npt_level(), PG_LEVEL_1G);
-	pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis");
-
-	/* Note, SEV setup consumes npt_enabled. */
-	sev_hardware_setup();
-
-	svm_hv_hardware_setup();
-
-	svm_adjust_mmio_mask();
-
-	for_each_possible_cpu(cpu) {
-		r = svm_cpu_init(cpu);
-		if (r)
-			goto err;
-	}
-
-	if (nrips) {
-		if (!boot_cpu_has(X86_FEATURE_NRIPS))
-			nrips = false;
-	}
-
-	enable_apicv = avic = avic && npt_enabled && boot_cpu_has(X86_FEATURE_AVIC);
-
-	if (enable_apicv) {
-		pr_info("AVIC enabled\n");
-
-		amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
-	}
-
-	if (vls) {
-		if (!npt_enabled ||
-		    !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) ||
-		    !IS_ENABLED(CONFIG_X86_64)) {
-			vls = false;
-		} else {
-			pr_info("Virtual VMLOAD VMSAVE supported\n");
-		}
-	}
-
-	if (boot_cpu_has(X86_FEATURE_SVME_ADDR_CHK))
-		svm_gp_erratum_intercept = false;
-
-	if (vgif) {
-		if (!boot_cpu_has(X86_FEATURE_VGIF))
-			vgif = false;
-		else
-			pr_info("Virtual GIF supported\n");
-	}
-
-	if (lbrv) {
-		if (!boot_cpu_has(X86_FEATURE_LBRV))
-			lbrv = false;
-		else
-			pr_info("LBR virtualization supported\n");
-	}
-
-	if (!pmu)
-		pr_info("PMU virtualization is disabled\n");
-
-	svm_set_cpu_caps();
-
-	/*
-	 * It seems that on AMD processors PTE's accessed bit is
-	 * being set by the CPU hardware before the NPF vmexit.
-	 * This is not expected behaviour and our tests fail because
-	 * of it.
-	 * A workaround here is to disable support for
-	 * GUEST_MAXPHYADDR < HOST_MAXPHYADDR if NPT is enabled.
-	 * In this case userspace can know if there is support using
-	 * KVM_CAP_SMALLER_MAXPHYADDR extension and decide how to handle
-	 * it
-	 * If future AMD CPU models change the behaviour described above,
-	 * this variable can be changed accordingly
-	 */
-	allow_smaller_maxphyaddr = !npt_enabled;
-
-	return 0;
-
-err:
-	svm_hardware_teardown();
-	return r;
-}
-
 static void init_seg(struct vmcb_seg *seg)
 {
 	seg->selector = 0;
@@ -1444,12 +1207,6 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 	if (err)
 		goto error_free_vmsa_page;
 
-	/* We initialize this flag to true to make sure that the is_running
-	 * bit would be set the first time the vcpu is loaded.
-	 */
-	if (irqchip_in_kernel(vcpu->kvm) && kvm_apicv_activated(vcpu->kvm))
-		svm->avic_is_running = true;
-
 	svm->msrpm = svm_vcpu_alloc_msrpm();
 	if (!svm->msrpm) {
 		err = -ENOMEM;
@@ -3833,6 +3590,11 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu)
 	svm_complete_interrupts(vcpu);
 }
 
+static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu)
+{
+	return 1;
+}
+
 static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 {
 	if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR &&
@@ -4629,8 +4391,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.prepare_guest_switch = svm_prepare_guest_switch,
 	.vcpu_load = svm_vcpu_load,
 	.vcpu_put = svm_vcpu_put,
-	.vcpu_blocking = svm_vcpu_blocking,
-	.vcpu_unblocking = svm_vcpu_unblocking,
+	.vcpu_blocking = avic_vcpu_blocking,
+	.vcpu_unblocking = avic_vcpu_unblocking,
 
 	.update_exception_bitmap = svm_update_exception_bitmap,
 	.get_msr_feature = svm_get_msr_feature,
@@ -4662,6 +4424,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.tlb_flush_gva = svm_flush_tlb_gva,
 	.tlb_flush_guest = svm_flush_tlb,
 
+	.vcpu_pre_run = svm_vcpu_pre_run,
 	.run = svm_vcpu_run,
 	.handle_exit = handle_exit,
 	.skip_emulated_instruction = skip_emulated_instruction,
@@ -4742,6 +4505,243 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
 };
 
+/*
+ * The default MMIO mask is a single bit (excluding the present bit),
+ * which could conflict with the memory encryption bit. Check for
+ * memory encryption support and override the default MMIO mask if
+ * memory encryption is enabled.
+ */
+static __init void svm_adjust_mmio_mask(void)
+{
+	unsigned int enc_bit, mask_bit;
+	u64 msr, mask;
+
+	/* If there is no memory encryption support, use existing mask */
+	if (cpuid_eax(0x80000000) < 0x8000001f)
+		return;
+
+	/* If memory encryption is not enabled, use existing mask */
+	rdmsrl(MSR_AMD64_SYSCFG, msr);
+	if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
+		return;
+
+	enc_bit = cpuid_ebx(0x8000001f) & 0x3f;
+	mask_bit = boot_cpu_data.x86_phys_bits;
+
+	/* Increment the mask bit if it is the same as the encryption bit */
+	if (enc_bit == mask_bit)
+		mask_bit++;
+
+	/*
+	 * If the mask bit location is below 52, then some bits above the
+	 * physical addressing limit will always be reserved, so use the
+	 * rsvd_bits() function to generate the mask. This mask, along with
+	 * the present bit, will be used to generate a page fault with
+	 * PFER.RSV = 1.
+	 *
+	 * If the mask bit location is 52 (or above), then clear the mask.
+	 */
+	mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0;
+
+	kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
+}
+
+static __init void svm_set_cpu_caps(void)
+{
+	kvm_set_cpu_caps();
+
+	supported_xss = 0;
+
+	/* CPUID 0x80000001 and 0x8000000A (SVM features) */
+	if (nested) {
+		kvm_cpu_cap_set(X86_FEATURE_SVM);
+
+		if (nrips)
+			kvm_cpu_cap_set(X86_FEATURE_NRIPS);
+
+		if (npt_enabled)
+			kvm_cpu_cap_set(X86_FEATURE_NPT);
+
+		if (tsc_scaling)
+			kvm_cpu_cap_set(X86_FEATURE_TSCRATEMSR);
+
+		/* Nested VM can receive #VMEXIT instead of triggering #GP */
+		kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
+	}
+
+	/* CPUID 0x80000008 */
+	if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
+	    boot_cpu_has(X86_FEATURE_AMD_SSBD))
+		kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD);
+
+	/* AMD PMU PERFCTR_CORE CPUID */
+	if (enable_pmu && boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
+		kvm_cpu_cap_set(X86_FEATURE_PERFCTR_CORE);
+
+	/* CPUID 0x8000001F (SME/SEV features) */
+	sev_set_cpu_caps();
+}
+
+static __init int svm_hardware_setup(void)
+{
+	int cpu;
+	struct page *iopm_pages;
+	void *iopm_va;
+	int r;
+	unsigned int order = get_order(IOPM_SIZE);
+
+	/*
+	 * NX is required for shadow paging and for NPT if the NX huge pages
+	 * mitigation is enabled.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_NX)) {
+		pr_err_ratelimited("NX (Execute Disable) not supported\n");
+		return -EOPNOTSUPP;
+	}
+	kvm_enable_efer_bits(EFER_NX);
+
+	iopm_pages = alloc_pages(GFP_KERNEL, order);
+
+	if (!iopm_pages)
+		return -ENOMEM;
+
+	iopm_va = page_address(iopm_pages);
+	memset(iopm_va, 0xff, PAGE_SIZE * (1 << order));
+	iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
+
+	init_msrpm_offsets();
+
+	supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR);
+
+	if (boot_cpu_has(X86_FEATURE_FXSR_OPT))
+		kvm_enable_efer_bits(EFER_FFXSR);
+
+	if (tsc_scaling) {
+		if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) {
+			tsc_scaling = false;
+		} else {
+			pr_info("TSC scaling supported\n");
+			kvm_has_tsc_control = true;
+			kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX;
+			kvm_tsc_scaling_ratio_frac_bits = 32;
+		}
+	}
+
+	tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX);
+
+	/* Check for pause filtering support */
+	if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) {
+		pause_filter_count = 0;
+		pause_filter_thresh = 0;
+	} else if (!boot_cpu_has(X86_FEATURE_PFTHRESHOLD)) {
+		pause_filter_thresh = 0;
+	}
+
+	if (nested) {
+		printk(KERN_INFO "kvm: Nested Virtualization enabled\n");
+		kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE);
+	}
+
+	/*
+	 * KVM's MMU doesn't support using 2-level paging for itself, and thus
+	 * NPT isn't supported if the host is using 2-level paging since host
+	 * CR4 is unchanged on VMRUN.
+	 */
+	if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE))
+		npt_enabled = false;
+
+	if (!boot_cpu_has(X86_FEATURE_NPT))
+		npt_enabled = false;
+
+	/* Force VM NPT level equal to the host's paging level */
+	kvm_configure_mmu(npt_enabled, get_npt_level(),
+			  get_npt_level(), PG_LEVEL_1G);
+	pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis");
+
+	/* Note, SEV setup consumes npt_enabled. */
+	sev_hardware_setup();
+
+	svm_hv_hardware_setup();
+
+	svm_adjust_mmio_mask();
+
+	for_each_possible_cpu(cpu) {
+		r = svm_cpu_init(cpu);
+		if (r)
+			goto err;
+	}
+
+	if (nrips) {
+		if (!boot_cpu_has(X86_FEATURE_NRIPS))
+			nrips = false;
+	}
+
+	enable_apicv = avic = avic && npt_enabled && boot_cpu_has(X86_FEATURE_AVIC);
+
+	if (enable_apicv) {
+		pr_info("AVIC enabled\n");
+
+		amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
+	} else {
+		svm_x86_ops.vcpu_blocking = NULL;
+		svm_x86_ops.vcpu_unblocking = NULL;
+	}
+
+	if (vls) {
+		if (!npt_enabled ||
+		    !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) ||
+		    !IS_ENABLED(CONFIG_X86_64)) {
+			vls = false;
+		} else {
+			pr_info("Virtual VMLOAD VMSAVE supported\n");
+		}
+	}
+
+	if (boot_cpu_has(X86_FEATURE_SVME_ADDR_CHK))
+		svm_gp_erratum_intercept = false;
+
+	if (vgif) {
+		if (!boot_cpu_has(X86_FEATURE_VGIF))
+			vgif = false;
+		else
+			pr_info("Virtual GIF supported\n");
+	}
+
+	if (lbrv) {
+		if (!boot_cpu_has(X86_FEATURE_LBRV))
+			lbrv = false;
+		else
+			pr_info("LBR virtualization supported\n");
+	}
+
+	if (!enable_pmu)
+		pr_info("PMU virtualization is disabled\n");
+
+	svm_set_cpu_caps();
+
+	/*
+	 * It seems that on AMD processors PTE's accessed bit is
+	 * being set by the CPU hardware before the NPF vmexit.
+	 * This is not expected behaviour and our tests fail because
+	 * of it.
+	 * A workaround here is to disable support for
+	 * GUEST_MAXPHYADDR < HOST_MAXPHYADDR if NPT is enabled.
+	 * In this case userspace can know if there is support using
+	 * KVM_CAP_SMALLER_MAXPHYADDR extension and decide how to handle
+	 * it
+	 * If future AMD CPU models change the behaviour described above,
+	 * this variable can be changed accordingly
+	 */
+	allow_smaller_maxphyaddr = !npt_enabled;
+
+	return 0;
+
+err:
+	svm_hardware_teardown();
+	return r;
+}
+
+
 static struct kvm_x86_init_ops svm_init_ops __initdata = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 9f153c59f2c8..47ef8f4a9358 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -32,7 +32,6 @@
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
 extern bool intercept_smi;
-extern bool pmu;
 
 /*
  * Clean bits in VMCB.
@@ -226,7 +225,6 @@ struct vcpu_svm {
 	u32 dfr_reg;
 	struct page *avic_backing_page;
 	u64 *avic_physical_id_cache;
-	bool avic_is_running;
 
 	/*
 	 * Per-vcpu list of struct amd_svm_iommu_ir:
@@ -574,17 +572,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops;
 
 #define VMCB_AVIC_APIC_BAR_MASK		0xFFFFFFFFFF000ULL
 
-static inline bool avic_vcpu_is_running(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-	u64 *entry = svm->avic_physical_id_cache;
-
-	if (!entry)
-		return false;
-
-	return (READ_ONCE(*entry) & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
-}
-
 int avic_ga_log_notifier(u32 ga_tag);
 void avic_vm_destroy(struct kvm *kvm);
 int avic_vm_init(struct kvm *kvm);
@@ -605,8 +592,8 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec);
 bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu);
 int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		       uint32_t guest_irq, bool set);
-void svm_vcpu_blocking(struct kvm_vcpu *vcpu);
-void svm_vcpu_unblocking(struct kvm_vcpu *vcpu);
+void avic_vcpu_blocking(struct kvm_vcpu *vcpu);
+void avic_vcpu_unblocking(struct kvm_vcpu *vcpu);
 
 /* sev.c */
 
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index c8029b7845b6..959b59d13b5a 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -5,6 +5,7 @@
 #include <asm/vmx.h>
 
 #include "lapic.h"
+#include "x86.h"
 
 extern bool __read_mostly enable_vpid;
 extern bool __read_mostly flexpriority_enabled;
@@ -389,6 +390,9 @@ static inline u64 vmx_get_perf_capabilities(void)
 {
 	u64 perf_cap = 0;
 
+	if (!enable_pmu)
+		return perf_cap;
+
 	if (boot_cpu_has(X86_FEATURE_PDCM))
 		rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_cap);
 
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 5e0ac57d6d1b..466d18fc0c5d 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -21,7 +21,6 @@
 #define MSR_PMC_FULL_WIDTH_BIT      (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0)
 
 static struct kvm_event_hw_type_mapping intel_arch_events[] = {
-	/* Index must match CPUID 0x0A.EBX bit vector */
 	[0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES },
 	[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
 	[2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES  },
@@ -29,6 +28,7 @@ static struct kvm_event_hw_type_mapping intel_arch_events[] = {
 	[4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
 	[5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
 	[6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
+	/* The above index must match CPUID 0x0A.EBX bit vector */
 	[7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES },
 };
 
@@ -75,11 +75,17 @@ static unsigned int intel_pmc_perf_hw_id(struct kvm_pmc *pmc)
 	u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++)
-		if (intel_arch_events[i].eventsel == event_select &&
-		    intel_arch_events[i].unit_mask == unit_mask &&
-		    (pmc_is_fixed(pmc) || pmu->available_event_types & (1 << i)))
-			break;
+	for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++) {
+		if (intel_arch_events[i].eventsel != event_select ||
+		    intel_arch_events[i].unit_mask != unit_mask)
+			continue;
+
+		/* disable event that reported as not present by cpuid */
+		if ((i < 7) && !(pmu->available_event_types & (1 << i)))
+			return PERF_COUNT_HW_MAX + 1;
+
+		break;
+	}
 
 	if (i == ARRAY_SIZE(intel_arch_events))
 		return PERF_COUNT_HW_MAX;
@@ -481,7 +487,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	pmu->reserved_bits = 0xffffffff00200000ull;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
-	if (!entry)
+	if (!entry || !enable_pmu)
 		return;
 	eax.full = entry->eax;
 	edx.full = entry->edx;
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 88c53c521094..aa1fe9085d77 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -19,7 +19,7 @@
  * wake the target vCPUs.  vCPUs are removed from the list and the notification
  * vector is reset when the vCPU is scheduled in.
  */
-static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
+static DEFINE_PER_CPU(struct list_head, wakeup_vcpus_on_cpu);
 /*
  * Protect the per-CPU list with a per-CPU spinlock to handle task migration.
  * When a blocking vCPU is awakened _and_ migrated to a different pCPU, the
@@ -27,7 +27,7 @@ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
  * CPU.  IRQs must be disabled when taking this lock, otherwise deadlock will
  * occur if a wakeup IRQ arrives and attempts to acquire the lock.
  */
-static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
+static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock);
 
 static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
 {
@@ -51,7 +51,9 @@ static int pi_try_set_control(struct pi_desc *pi_desc, u64 old, u64 new)
 void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct pi_desc old, new;
+	unsigned long flags;
 	unsigned int dest;
 
 	/*
@@ -62,23 +64,34 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	if (!enable_apicv || !lapic_in_kernel(vcpu))
 		return;
 
-	/* Nothing to do if PI.SN and PI.NDST both have the desired value. */
-	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
+	/*
+	 * If the vCPU wasn't on the wakeup list and wasn't migrated, then the
+	 * full update can be skipped as neither the vector nor the destination
+	 * needs to be changed.
+	 */
+	if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR && vcpu->cpu == cpu) {
+		/*
+		 * Clear SN if it was set due to being preempted.  Again, do
+		 * this even if there is no assigned device for simplicity.
+		 */
+		if (pi_test_and_clear_sn(pi_desc))
+			goto after_clear_sn;
 		return;
+	}
+
+	local_irq_save(flags);
 
 	/*
-	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
-	 * PI.NDST: pi_post_block is the one expected to change PID.NDST and the
-	 * wakeup handler expects the vCPU to be on the blocked_vcpu_list that
-	 * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up
-	 * correctly.
+	 * If the vCPU was waiting for wakeup, remove the vCPU from the wakeup
+	 * list of the _previous_ pCPU, which will not be the same as the
+	 * current pCPU if the task was migrated.
 	 */
-	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) {
-		pi_clear_sn(pi_desc);
-		goto after_clear_sn;
+	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) {
+		raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+		list_del(&vmx->pi_wakeup_list);
+		raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
 	}
 
-	/* The full case.  Set the new destination and clear SN. */
 	dest = cpu_physical_id(cpu);
 	if (!x2apic_mode)
 		dest = (dest << 8) & 0xFF00;
@@ -86,10 +99,22 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	do {
 		old.control = new.control = READ_ONCE(pi_desc->control);
 
+		/*
+		 * Clear SN (as above) and refresh the destination APIC ID to
+		 * handle task migration (@cpu != vcpu->cpu).
+		 */
 		new.ndst = dest;
 		new.sn = 0;
+
+		/*
+		 * Restore the notification vector; in the blocking case, the
+		 * descriptor was modified on "put" to use the wakeup vector.
+		 */
+		new.nv = POSTED_INTR_VECTOR;
 	} while (pi_try_set_control(pi_desc, old.control, new.control));
 
+	local_irq_restore(flags);
+
 after_clear_sn:
 
 	/*
@@ -111,83 +136,25 @@ static bool vmx_can_use_vtd_pi(struct kvm *kvm)
 		irq_remapping_cap(IRQ_POSTING_CAP);
 }
 
-void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
-{
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-
-	if (!vmx_can_use_vtd_pi(vcpu->kvm))
-		return;
-
-	/* Set SN when the vCPU is preempted */
-	if (vcpu->preempted)
-		pi_set_sn(pi_desc);
-}
-
-static void __pi_post_block(struct kvm_vcpu *vcpu)
-{
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-	struct pi_desc old, new;
-	unsigned int dest;
-
-	/*
-	 * Remove the vCPU from the wakeup list of the _previous_ pCPU, which
-	 * will not be the same as the current pCPU if the task was migrated.
-	 */
-	spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-	list_del(&vcpu->blocked_vcpu_list);
-	spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-
-	dest = cpu_physical_id(vcpu->cpu);
-	if (!x2apic_mode)
-		dest = (dest << 8) & 0xFF00;
-
-	WARN(pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR,
-	     "Wakeup handler not enabled while the vCPU was blocking");
-
-	do {
-		old.control = new.control = READ_ONCE(pi_desc->control);
-
-		new.ndst = dest;
-
-		/* set 'NV' to 'notification vector' */
-		new.nv = POSTED_INTR_VECTOR;
-	} while (pi_try_set_control(pi_desc, old.control, new.control));
-
-	vcpu->pre_pcpu = -1;
-}
-
 /*
- * This routine does the following things for vCPU which is going
- * to be blocked if VT-d PI is enabled.
- * - Store the vCPU to the wakeup list, so when interrupts happen
- *   we can find the right vCPU to wake up.
- * - Change the Posted-interrupt descriptor as below:
- *      'NV' <-- POSTED_INTR_WAKEUP_VECTOR
- * - If 'ON' is set during this process, which means at least one
- *   interrupt is posted for this vCPU, we cannot block it, in
- *   this case, return 1, otherwise, return 0.
- *
+ * Put the vCPU on this pCPU's list of vCPUs that needs to be awakened and set
+ * WAKEUP as the notification vector in the PI descriptor.
  */
-int pi_pre_block(struct kvm_vcpu *vcpu)
+static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
 {
-	struct pi_desc old, new;
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct pi_desc old, new;
 	unsigned long flags;
 
-	if (!vmx_can_use_vtd_pi(vcpu->kvm) ||
-	    vmx_interrupt_blocked(vcpu))
-		return 0;
-
 	local_irq_save(flags);
 
-	vcpu->pre_pcpu = vcpu->cpu;
-	spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
-	list_add_tail(&vcpu->blocked_vcpu_list,
-		      &per_cpu(blocked_vcpu_on_cpu, vcpu->cpu));
-	spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
+	raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
+	list_add_tail(&vmx->pi_wakeup_list,
+		      &per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu));
+	raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
 
-	WARN(pi_desc->sn == 1,
-	     "Posted Interrupt Suppress Notification set before blocking");
+	WARN(pi_desc->sn, "PI descriptor SN field set before blocking");
 
 	do {
 		old.control = new.control = READ_ONCE(pi_desc->control);
@@ -196,24 +163,37 @@ int pi_pre_block(struct kvm_vcpu *vcpu)
 		new.nv = POSTED_INTR_WAKEUP_VECTOR;
 	} while (pi_try_set_control(pi_desc, old.control, new.control));
 
-	/* We should not block the vCPU if an interrupt is posted for it.  */
-	if (pi_test_on(pi_desc))
-		__pi_post_block(vcpu);
+	/*
+	 * Send a wakeup IPI to this CPU if an interrupt may have been posted
+	 * before the notification vector was updated, in which case the IRQ
+	 * will arrive on the non-wakeup vector.  An IPI is needed as calling
+	 * try_to_wake_up() from ->sched_out() isn't allowed (IRQs are not
+	 * enabled until it is safe to call try_to_wake_up() on the task being
+	 * scheduled out).
+	 */
+	if (pi_test_on(&new))
+		apic->send_IPI_self(POSTED_INTR_WAKEUP_VECTOR);
 
 	local_irq_restore(flags);
-	return (vcpu->pre_pcpu == -1);
 }
 
-void pi_post_block(struct kvm_vcpu *vcpu)
+void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
 {
-	unsigned long flags;
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (vcpu->pre_pcpu == -1)
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
 		return;
 
-	local_irq_save(flags);
-	__pi_post_block(vcpu);
-	local_irq_restore(flags);
+	if (kvm_vcpu_is_blocking(vcpu) && !vmx_interrupt_blocked(vcpu))
+		pi_enable_wakeup_handler(vcpu);
+
+	/*
+	 * Set SN when the vCPU is preempted.  Note, the vCPU can both be seen
+	 * as blocking and preempted, e.g. if it's preempted between setting
+	 * its wait state and manually scheduling out.
+	 */
+	if (vcpu->preempted)
+		pi_set_sn(pi_desc);
 }
 
 /*
@@ -221,24 +201,23 @@ void pi_post_block(struct kvm_vcpu *vcpu)
  */
 void pi_wakeup_handler(void)
 {
-	struct kvm_vcpu *vcpu;
 	int cpu = smp_processor_id();
+	struct vcpu_vmx *vmx;
 
-	spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-	list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu),
-			blocked_vcpu_list) {
-		struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
+	list_for_each_entry(vmx, &per_cpu(wakeup_vcpus_on_cpu, cpu),
+			    pi_wakeup_list) {
 
-		if (pi_test_on(pi_desc))
-			kvm_vcpu_kick(vcpu);
+		if (pi_test_on(&vmx->pi_desc))
+			kvm_vcpu_wake_up(&vmx->vcpu);
 	}
-	spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
 }
 
 void __init pi_init_cpu(int cpu)
 {
-	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
-	spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	INIT_LIST_HEAD(&per_cpu(wakeup_vcpus_on_cpu, cpu));
+	raw_spin_lock_init(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
 }
 
 bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
@@ -254,7 +233,7 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
  * Bail out of the block loop if the VM has an assigned
  * device, but the blocking vCPU didn't reconfigure the
  * PI.NV to the wakeup vector, i.e. the assigned device
- * came along after the initial check in pi_pre_block().
+ * came along after the initial check in vmx_vcpu_pi_put().
  */
 void vmx_pi_start_assignment(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 36ae035f14aa..eb14e76b84ef 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -40,6 +40,12 @@ static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc)
 			(unsigned long *)&pi_desc->control);
 }
 
+static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc)
+{
+	return test_and_clear_bit(POSTED_INTR_SN,
+			(unsigned long *)&pi_desc->control);
+}
+
 static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
 {
 	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
@@ -88,8 +94,6 @@ static inline bool pi_test_sn(struct pi_desc *pi_desc)
 
 void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
 void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu);
-int pi_pre_block(struct kvm_vcpu *vcpu);
-void pi_post_block(struct kvm_vcpu *vcpu);
 void pi_wakeup_handler(void);
 void __init pi_init_cpu(int cpu);
 bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 1b2e9d8c5cc9..4ac676066d60 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3931,12 +3931,10 @@ static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu)
 	pt_update_intercept_for_msr(vcpu);
 }
 
-static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
-						     bool nested)
+static inline void kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
+						     int pi_vec)
 {
 #ifdef CONFIG_SMP
-	int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
-
 	if (vcpu->mode == IN_GUEST_MODE) {
 		/*
 		 * The vector of interrupt to be delivered to vcpu had
@@ -3964,10 +3962,15 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
 		 */
 
 		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
-		return true;
+		return;
 	}
 #endif
-	return false;
+	/*
+	 * The vCPU isn't in the guest; wake the vCPU in case it is blocking,
+	 * otherwise do nothing as KVM will grab the highest priority pending
+	 * IRQ via ->sync_pir_to_irr() in vcpu_enter_guest().
+	 */
+	kvm_vcpu_wake_up(vcpu);
 }
 
 static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
@@ -3997,8 +4000,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
 		smp_mb__after_atomic();
 
 		/* the PIR and ON have been set by L1. */
-		if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true))
-			kvm_vcpu_kick(vcpu);
+		kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_NESTED_VECTOR);
 		return 0;
 	}
 	return -1;
@@ -4035,9 +4037,7 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 	 * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a
 	 * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE.
 	 */
-	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
-		kvm_vcpu_kick(vcpu);
-
+	kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_VECTOR);
 	return 0;
 }
 
@@ -5426,6 +5426,14 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	return vmx->emulation_required && !vmx->rmode.vm86_active &&
+	       vcpu->arch.exception.pending;
+}
+
 static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -5445,8 +5453,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		if (!kvm_emulate_instruction(vcpu, 0))
 			return 0;
 
-		if (vmx->emulation_required && !vmx->rmode.vm86_active &&
-		    vcpu->arch.exception.pending) {
+		if (vmx_emulation_required_with_pending_exception(vcpu)) {
 			kvm_prepare_emulation_failure_exit(vcpu);
 			return 0;
 		}
@@ -5468,6 +5475,16 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu)
+{
+	if (vmx_emulation_required_with_pending_exception(vcpu)) {
+		kvm_prepare_emulation_failure_exit(vcpu);
+		return 0;
+	}
+
+	return 1;
+}
+
 static void grow_ple_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6928,6 +6945,8 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 	BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0);
 	vmx = to_vmx(vcpu);
 
+	INIT_LIST_HEAD(&vmx->pi_wakeup_list);
+
 	err = -ENOMEM;
 
 	vmx->vpid = allocate_vpid();
@@ -7549,25 +7568,6 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
 		secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML);
 }
 
-static int vmx_pre_block(struct kvm_vcpu *vcpu)
-{
-	if (pi_pre_block(vcpu))
-		return 1;
-
-	if (kvm_lapic_hv_timer_in_use(vcpu))
-		kvm_lapic_switch_to_sw_timer(vcpu);
-
-	return 0;
-}
-
-static void vmx_post_block(struct kvm_vcpu *vcpu)
-{
-	if (kvm_x86_ops.set_hv_timer)
-		kvm_lapic_switch_to_hv_timer(vcpu);
-
-	pi_post_block(vcpu);
-}
-
 static void vmx_setup_mce(struct kvm_vcpu *vcpu)
 {
 	if (vcpu->arch.mcg_cap & MCG_LMCE_P)
@@ -7710,6 +7710,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.tlb_flush_gva = vmx_flush_tlb_gva,
 	.tlb_flush_guest = vmx_flush_tlb_guest,
 
+	.vcpu_pre_run = vmx_vcpu_pre_run,
 	.run = vmx_vcpu_run,
 	.handle_exit = vmx_handle_exit,
 	.skip_emulated_instruction = vmx_skip_emulated_instruction,
@@ -7768,9 +7769,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.cpu_dirty_log_size = PML_ENTITY_NUM,
 	.update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
 
-	.pre_block = vmx_pre_block,
-	.post_block = vmx_post_block,
-
 	.pmu_ops = &intel_pmu_ops,
 	.nested_ops = &vmx_nested_ops,
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index f8fc7441baea..7f2c82e7f38f 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -317,6 +317,9 @@ struct vcpu_vmx {
 	/* Posted interrupt descriptor */
 	struct pi_desc pi_desc;
 
+	/* Used if this vCPU is waiting for PI notification wakeup. */
+	struct list_head pi_wakeup_list;
+
 	/* Support for a guest hypervisor (nested VMX) */
 	struct nested_vmx nested;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 76b4803dd3bd..9e43d756312f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -187,6 +187,11 @@ module_param(force_emulation_prefix, bool, S_IRUGO);
 int __read_mostly pi_inject_timer = -1;
 module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR);
 
+/* Enable/disable PMU virtualization */
+bool __read_mostly enable_pmu = true;
+EXPORT_SYMBOL_GPL(enable_pmu);
+module_param(enable_pmu, bool, 0444);
+
 /*
  * Restoring the host value for MSRs that are only consumed when running in
  * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU
@@ -5230,17 +5235,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid __user *cpuid_arg = argp;
 		struct kvm_cpuid cpuid;
 
-		/*
-		 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
-		 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
-		 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
-		 * faults due to reusing SPs/SPTEs.  In practice no sane VMM mucks with
-		 * the core vCPU model on the fly, so fail.
-		 */
-		r = -EINVAL;
-		if (vcpu->arch.last_vmentry_cpu != -1)
-			goto out;
-
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
@@ -5251,14 +5245,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid2 __user *cpuid_arg = argp;
 		struct kvm_cpuid2 cpuid;
 
-		/*
-		 * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in
-		 * KVM_SET_CPUID case above.
-		 */
-		r = -EINVAL;
-		if (vcpu->arch.last_vmentry_cpu != -1)
-			goto out;
-
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
@@ -9945,10 +9931,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	smp_mb__after_srcu_read_unlock();
 
 	/*
-	 * This handles the case where a posted interrupt was
-	 * notified with kvm_vcpu_kick.  Assigned devices can
-	 * use the POSTED_INTR_VECTOR even if APICv is disabled,
-	 * so do it even if APICv is disabled on this vCPU.
+	 * Process pending posted interrupts to handle the case where the
+	 * notification IRQ arrived in the host, or was never sent (because the
+	 * target vCPU wasn't running).  Do this regardless of the vCPU's APICv
+	 * status, KVM doesn't update assigned devices when APICv is inhibited,
+	 * i.e. they can post interrupts even if APICv is temporarily disabled.
 	 */
 	if (kvm_lapic_enabled(vcpu))
 		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
@@ -10113,8 +10100,20 @@ out:
 
 static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 {
-	if (!kvm_arch_vcpu_runnable(vcpu) &&
-	    (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) {
+	bool hv_timer;
+
+	if (!kvm_arch_vcpu_runnable(vcpu)) {
+		/*
+		 * Switch to the software timer before halt-polling/blocking as
+		 * the guest's timer may be a break event for the vCPU, and the
+		 * hypervisor timer runs only when the CPU is in guest mode.
+		 * Switch before halt-polling so that KVM recognizes an expired
+		 * timer before blocking.
+		 */
+		hv_timer = kvm_lapic_hv_timer_in_use(vcpu);
+		if (hv_timer)
+			kvm_lapic_switch_to_sw_timer(vcpu);
+
 		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 		if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
 			kvm_vcpu_halt(vcpu);
@@ -10122,8 +10121,8 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 			kvm_vcpu_block(vcpu);
 		vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 
-		if (kvm_x86_ops.post_block)
-			static_call(kvm_x86_post_block)(vcpu);
+		if (hv_timer)
+			kvm_lapic_switch_to_hv_timer(vcpu);
 
 		if (!kvm_check_request(KVM_REQ_UNHALT, vcpu))
 			return 1;
@@ -10316,6 +10315,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			r = -EINTR;
 			goto out;
 		}
+		/*
+		 * It should be impossible for the hypervisor timer to be in
+		 * use before KVM has ever run the vCPU.
+		 */
+		WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu));
 		kvm_vcpu_block(vcpu);
 		if (kvm_apic_accept_events(vcpu) < 0) {
 			r = 0;
@@ -10360,10 +10364,16 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	} else
 		WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
 
-	if (kvm_run->immediate_exit)
+	if (kvm_run->immediate_exit) {
 		r = -EINTR;
-	else
-		r = vcpu_run(vcpu);
+		goto out;
+	}
+
+	r = static_call(kvm_x86_vcpu_pre_run)(vcpu);
+	if (r <= 0)
+		goto out;
+
+	r = vcpu_run(vcpu);
 
 out:
 	kvm_put_guest_fpu(vcpu);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index bec8ed090abc..635b75f9e145 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -336,6 +336,7 @@ extern u64 host_xcr0;
 extern u64 supported_xcr0;
 extern u64 host_xss;
 extern u64 supported_xss;
+extern bool enable_pmu;
 
 static inline bool kvm_mpx_supported(void)
 {