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
  ...

36 files changed, 1425 insertions, 632 deletions

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index d3791a14eb9a..bb8cfddbb22d 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -5545,8 +5545,8 @@ the trailing ``'\0'``, is indicated by ``name_size`` in the header.
 The Stats Data block contains an array of 64-bit values in the same order
 as the descriptors in Descriptors block.
 
-4.42 KVM_GET_XSAVE2
-------------------
+4.134 KVM_GET_XSAVE2
+--------------------
 
 :Capability: KVM_CAP_XSAVE2
 :Architectures: x86
@@ -7363,7 +7363,7 @@ trap and emulate MSRs that are outside of the scope of KVM as well as
 limit the attack surface on KVM's MSR emulation code.
 
 8.28 KVM_CAP_ENFORCE_PV_FEATURE_CPUID
------------------------------
+-------------------------------------
 
 Architectures: x86
 
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;</