16 files changed, 195 insertions, 187 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 0544e30b4946..773132c3bf5a 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -360,14 +360,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	vcpu->arch.guest_supported_xcr0 =
 		cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
 
-	/*
-	 * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if
-	 * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't
-	 * supported by the host.
-	 */
-	vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 |
-						       XFEATURE_MASK_FPSSE;
-
 	kvm_update_pv_runtime(vcpu);
 
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index dcd60b39e794..3e977dbbf993 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2759,13 +2759,17 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
 {
 	u32 reg = kvm_lapic_get_reg(apic, lvt_type);
 	int vector, mode, trig_mode;
+	int r;
 
 	if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
 		vector = reg & APIC_VECTOR_MASK;
 		mode = reg & APIC_MODE_MASK;
 		trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
-		return __apic_accept_irq(apic, mode, vector, 1, trig_mode,
-					NULL);
+
+		r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL);
+		if (r && lvt_type == APIC_LVTPC)
+			kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED);
+		return r;
 	}
 	return 0;
 }
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index e1d011c67cc6..f7901cb4d2fa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6167,20 +6167,15 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
 	return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
 }
 
-int kvm_mmu_init_vm(struct kvm *kvm)
+void kvm_mmu_init_vm(struct kvm *kvm)
 {
-	int r;
-
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
 	INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
 	spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
 
-	if (tdp_mmu_enabled) {
-		r = kvm_mmu_init_tdp_mmu(kvm);
-		if (r < 0)
-			return r;
-	}
+	if (tdp_mmu_enabled)
+		kvm_mmu_init_tdp_mmu(kvm);
 
 	kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
 	kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO;
@@ -6189,8 +6184,6 @@ int kvm_mmu_init_vm(struct kvm *kvm)
 
 	kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache;
 	kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO;
-
-	return 0;
 }
 
 static void mmu_free_vm_memory_caches(struct kvm *kvm)
@@ -6246,7 +6239,6 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e
 void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 {
 	bool flush;
-	int i;
 
 	if (WARN_ON_ONCE(gfn_end <= gfn_start))
 		return;
@@ -6257,11 +6249,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
 	flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
 
-	if (tdp_mmu_enabled) {
-		for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
-			flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start,
-						      gfn_end, true, flush);
-	}
+	if (tdp_mmu_enabled)
+		flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush);
 
 	if (flush)
 		kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index b102014e2c60..decc1f153669 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -58,7 +58,12 @@ struct kvm_mmu_page {
 
 	bool tdp_mmu_page;
 	bool unsync;
-	u8 mmu_valid_gen;
+	union {
+		u8 mmu_valid_gen;
+
+		/* Only accessed under slots_lock.  */
+		bool tdp_mmu_scheduled_root_to_zap;
+	};
 
 	 /*
 	  * The shadow page can't be replaced by an equivalent huge page
@@ -100,13 +105,7 @@ struct kvm_mmu_page {
 		struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
 		tdp_ptep_t ptep;
 	};
-	union {
-		DECLARE_BITMAP(unsync_child_bitmap, 512);
-		struct {
-			struct work_struct tdp_mmu_async_work;
-			void *tdp_mmu_async_data;
-		};
-	};
+	DECLARE_BITMAP(unsync_child_bitmap, 512);
 
 	/*
 	 * Tracks shadow pages that, if zapped, would allow KVM to create an NX
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 6c63f2d1675f..6cd4dd631a2f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -12,18 +12,10 @@
 #include <trace/events/kvm.h>
 
 /* Initializes the TDP MMU for the VM, if enabled. */
-int kvm_mmu_init_tdp_mmu(struct kvm *kvm)
+void kvm_mmu_init_tdp_mmu(struct kvm *kvm)
 {
-	struct workqueue_struct *wq;
-
-	wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0);
-	if (!wq)
-		return -ENOMEM;
-
 	INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
 	spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
-	kvm->arch.tdp_mmu_zap_wq = wq;
-	return 1;
 }
 
 /* Arbitrarily returns true so that this may be used in if statements. */
@@ -46,20 +38,15 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 	 * ultimately frees all roots.
 	 */
 	kvm_tdp_mmu_invalidate_all_roots(kvm);
-
-	/*
-	 * Destroying a workqueue also first flushes the workqueue, i.e. no
-	 * need to invoke kvm_tdp_mmu_zap_invalidated_roots().
-	 */
-	destroy_workqueue(kvm->arch.tdp_mmu_zap_wq);
+	kvm_tdp_mmu_zap_invalidated_roots(kvm);
 
 	WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
 
 	/*
 	 * Ensure that all the outstanding RCU callbacks to free shadow pages
-	 * can run before the VM is torn down.  Work items on tdp_mmu_zap_wq
-	 * can call kvm_tdp_mmu_put_root and create new callbacks.
+	 * can run before the VM is torn down.  Putting the last reference to
+	 * zapped roots will create new callbacks.
 	 */
 	rcu_barrier();
 }
@@ -86,46 +73,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
 	tdp_mmu_free_sp(sp);
 }
 
-static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
-			     bool shared);
-
-static void tdp_mmu_zap_root_work(struct work_struct *work)
-{
-	struct kvm_mmu_page *root = container_of(work, struct kvm_mmu_page,
-						 tdp_mmu_async_work);
-	struct kvm *kvm = root->tdp_mmu_async_data;
-
-	read_lock(&kvm->mmu_lock);
-
-	/*
-	 * A TLB flush is not necessary as KVM performs a local TLB flush when
-	 * allocating a new root (see kvm_mmu_load()), and when migrating vCPU
-	 * to a different pCPU.  Note, the local TLB flush on reuse also
-	 * invalidates any paging-structure-cache entries, i.e. TLB entries for
-	 * intermediate paging structures, that may be zapped, as such entries
-	 * are associated with the ASID on both VMX and SVM.
-	 */
-	tdp_mmu_zap_root(kvm, root, true);
-
-	/*
-	 * Drop the refcount using kvm_tdp_mmu_put_root() to test its logic for
-	 * avoiding an infinite loop.  By design, the root is reachable while
-	 * it's being asynchronously zapped, thus a different task can put its
-	 * last reference, i.e. flowing through kvm_tdp_mmu_put_root() for an
-	 * asynchronously zapped root is unavoidable.
-	 */
-	kvm_tdp_mmu_put_root(kvm, root, true);
-
-	read_unlock(&kvm->mmu_lock);
-}
-
-static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root)
-{
-	root->tdp_mmu_async_data = kvm;
-	INIT_WORK(&root->tdp_mmu_async_work, tdp_mmu_zap_root_work);
-	queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work);
-}
-
 void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
 			  bool shared)
 {
@@ -211,8 +158,12 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared)	\
 	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true)
 
-#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id)			\
-	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, false, false)
+#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared)			\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false);		\
+	     _root;								\
+	     _root = tdp_mmu_next_root(_kvm, _root, _shared, false))		\
+		if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) {		\
+		} else
 
 /*
  * Iterate over all TDP MMU roots.  Requires that mmu_lock be held for write,
@@ -292,7 +243,7 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
 	 * by a memslot update or by the destruction of the VM.  Initialize the
 	 * refcount to two; one reference for the vCPU, and one reference for
 	 * the TDP MMU itself, which is held until the root is invalidated and
-	 * is ultimately put by tdp_mmu_zap_root_work().
+	 * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots().
 	 */
 	refcount_set(&root->tdp_mmu_root_count, 2);
 
@@ -877,13 +828,12 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
  * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or
  * more SPTEs were zapped since the MMU lock was last acquired.
  */
-bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
-			   bool can_yield, bool flush)
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush)
 {
 	struct kvm_mmu_page *root;
 
-	for_each_tdp_mmu_root_yield_safe(kvm, root, as_id)
-		flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush);
+	for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+		flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush);
 
 	return flush;
 }
@@ -891,7 +841,6 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
 void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 {
 	struct kvm_mmu_page *root;
-	int i;
 
 	/*
 	 * Zap all roots, including invalid roots, as all SPTEs must be dropped
@@ -905,10 +854,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 	 * is being destroyed or the userspace VMM has exited.  In both cases,
 	 * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request.
 	 */
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
-		for_each_tdp_mmu_root_yield_safe(kvm, root, i)
-			tdp_mmu_zap_root(kvm, root, false);
-	}
+	for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+		tdp_mmu_zap_root(kvm, root, false);
 }
 
 /*
@@ -917,18 +864,47 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
  */
 void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 {
-	flush_workqueue(kvm->arch.tdp_mmu_zap_wq);
+	struct kvm_mmu_page *root;
+
+	read_lock(&kvm->mmu_lock);
+
+	for_each_tdp_mmu_root_yield_safe(kvm, root, true) {
+		if (!root->tdp_mmu_scheduled_root_to_zap)
+			continue;
+
+		root->tdp_mmu_scheduled_root_to_zap = false;
+		KVM_BUG_ON(!root->role.invalid, kvm);
+
+		/*
+		 * A TLB flush is not necessary as KVM performs a local TLB
+		 * flush when allocating a new root (see kvm_mmu_load()), and
+		 * when migrating a vCPU to a different pCPU.  Note, the local
+		 * TLB flush on reuse also invalidates paging-structure-cache
+		 * entries, i.e. TLB entries for intermediate paging structures,
+		 * that may be zapped, as such entries are associated with the
+		 * ASID on both VMX and SVM.
+		 */
+		tdp_mmu_zap_root(kvm, root, true);
+
+		/*
+		 * The referenced needs to be put *after* zapping the root, as
+		 * the root must be reachable by mmu_notifiers while it's being
+		 * zapped
+		 */
+		kvm_tdp_mmu_put_root(kvm, root, true);
+	}
+
+	read_unlock(&kvm->mmu_lock);
 }
 
 /*
  * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that
  * is about to be zapped, e.g. in response to a memslots update.  The actual
- * zapping is performed asynchronously.  Using a separate workqueue makes it
- * easy to ensure that the destruction is performed before the "fast zap"
- * completes, without keeping a separate list of invalidated roots; the list is
- * effectively the list of work items in the workqueue.
+ * zapping is done separately so that it happens with mmu_lock with read,
+ * whereas invalidating roots must be done with mmu_lock held for write (unless
+ * the VM is being destroyed).
  *
- * Note, the asynchronous worker is gifted the TDP MMU's reference.
+ * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference.
  * See kvm_tdp_mmu_get_vcpu_root_hpa().
  */
 void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
@@ -953,19 +929,20 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
 	/*
 	 * As above, mmu_lock isn't held when destroying the VM!  There can't
 	 * be other references to @kvm, i.e. nothing else can invalidate roots
-	 * or be consuming roots, but walking the list of roots does need to be
-	 * guarded against roots being deleted by the asynchronous zap worker.
+	 * or get/put references to roots.
 	 */
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) {
+	list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) {
+		/*
+		 * Note, invalid roots can outlive a memslot update!  Invalid
+		 * roots must be *zapped* before the memslot update completes,
+		 * but a different task can acquire a reference and keep the
+		 * root alive after its been zapped.
+		 */
 		if (!root->role.invalid) {
+			root->tdp_mmu_scheduled_root_to_zap = true;
 			root->role.invalid = true;
-			tdp_mmu_schedule_zap_root(kvm, root);
 		}
 	}
-
-	rcu_read_unlock();
 }
 
 /*
@@ -1146,8 +1123,13 @@ retry:
 bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 				 bool flush)
 {
-	return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start,
-				     range->end, range->may_block, flush);
+	struct kvm_mmu_page *root;
+
+	__for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false)
+		flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end,
+					  range->may_block, flush);
+
+	return flush;
 }
 
 typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 0a63b1afabd3..733a3aef3a96 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -7,7 +7,7 @@
 
 #include "spte.h"
 
-int kvm_mmu_init_tdp_mmu(struct kvm *kvm);
+void kvm_mmu_init_tdp_mmu(struct kvm *kvm);
 void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm);
 
 hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
@@ -20,8 +20,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
 void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
 			  bool shared);
 
-bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start,
-				 gfn_t end, bool can_yield, bool flush);
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush);
 bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
 void kvm_tdp_mmu_zap_all(struct kvm *kvm);
 void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index edb89b51b383..9ae07db6f0f6 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -93,14 +93,6 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops)
 #undef __KVM_X86_PMU_OP
 }
 
-static void kvm_pmi_trigger_fn(struct irq_work *irq_work)
-{
-	struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work);
-	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
-
-	kvm_pmu_deliver_pmi(vcpu);
-}
-
 static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
@@ -124,20 +116,7 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 	}
 
-	if (!pmc->intr || skip_pmi)
-		return;
-
-	/*
-	 * Inject PMI. If vcpu was in a guest mode during NMI PMI
-	 * can be ejected on a guest mode re-entry. Otherwise we can't
-	 * be sure that vcpu wasn't executing hlt instruction at the
-	 * time of vmexit and is not going to re-enter guest mode until
-	 * woken up. So we should wake it, but this is impossible from
-	 * NMI context. Do it from irq work instead.
-	 */
-	if (in_pmi && !kvm_handling_nmi_from_guest(pmc->vcpu))
-		irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
-	else
+	if (pmc->intr && !skip_pmi)
 		kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
 }
 
@@ -675,9 +654,6 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
 
 void kvm_pmu_reset(struct kvm_vcpu *vcpu)
 {
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-
-	irq_work_sync(&pmu->irq_work);
 	static_call(kvm_x86_pmu_reset)(vcpu);
 }
 
@@ -687,7 +663,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
 
 	memset(pmu, 0, sizeof(*pmu));
 	static_call(kvm_x86_pmu_init)(vcpu);
-	init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
 	pmu->event_count = 0;
 	pmu->need_cleanup = false;
 	kvm_pmu_refresh(vcpu);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 7d9ba301c090..1d64113de488 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -74,6 +74,12 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
 	return counter & pmc_bitmask(pmc);
 }
 
+static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val)
+{
+	pmc->counter += val - pmc_read_counter(pmc);
+	pmc->counter &= pmc_bitmask(pmc);
+}
+
 static inline void pmc_release_perf_event(struct kvm_pmc *pmc)
 {
 	if (pmc->perf_event) {
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 2092db892d7d..4b74ea91f4e6 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -529,8 +529,11 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu)
 	case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE:
 		WARN_ONCE(1, "Invalid backing page\n");
 		break;
+	case AVIC_IPI_FAILURE_INVALID_IPI_VECTOR:
+		/* Invalid IPI with vector < 16 */
+		break;
 	default:
-		pr_err("Unknown IPI interception\n");
+		vcpu_unimpl(vcpu, "Unknown avic incomplete IPI interception\n");
 	}
 
 	return 1;
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index dd496c9e5f91..3fea8c47679e 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1253,6 +1253,9 @@ void svm_leave_nested(struct kvm_vcpu *vcpu)
 
 		nested_svm_uninit_mmu_context(vcpu);
 		vmcb_mark_all_dirty(svm->vmcb);
+
+		if (kvm_apicv_activated(vcpu->kvm))
+			kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
 	}
 
 	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index cef5a3d0abd0..373ff6a6687b 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -160,7 +160,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	/* MSR_PERFCTRn */
 	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
 	if (pmc) {
-		pmc->counter += data - pmc_read_counter(pmc);
+		pmc_write_counter(pmc, data);
 		pmc_update_sample_period(pmc);
 		return 0;
 	}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index b9a0a939d59f..4900c078045a 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2962,6 +2962,32 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 				    count, in);
 }
 
+static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+
+	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
+		bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) ||
+				 guest_cpuid_has(vcpu, X86_FEATURE_RDPID);
+
+		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
+	}
+}
+
+void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct kvm_cpuid_entry2 *best;
+
+	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
+	best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
+	if (best)
+		vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
+
+	if (sev_es_guest(svm->vcpu.kvm))
+		sev_es_vcpu_after_set_cpuid(svm);
+}
+
 static void sev_es_init_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = svm->vmcb01.ptr;
@@ -3024,14 +3050,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
-
-	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) &&
-	    (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) ||
-	     guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) {
-		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1);
-		if (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP))
-			svm_clr_intercept(svm, INTERCEPT_RDTSCP);
-	}
 }
 
 void sev_init_vmcb(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index f283eb47f6ac..beea99c8e8e0 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -683,6 +683,21 @@ static int svm_hardware_enable(void)
 
 	amd_pmu_enable_virt();
 
+	/*
+	 * If TSC_AUX virtualization is supported, TSC_AUX becomes a swap type
+	 * "B" field (see sev_es_prepare_switch_to_guest()) for SEV-ES guests.
+	 * Since Linux does not change the value of TSC_AUX once set, prime the
+	 * TSC_AUX field now to avoid a RDMSR on every vCPU run.
+	 */
+	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
+		struct sev_es_save_area *hostsa;
+		u32 __maybe_unused msr_hi;
+
+		hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400);
+
+		rdmsr(MSR_TSC_AUX, hostsa->tsc_aux, msr_hi);
+	}
+
 	return 0;
 }
 
@@ -898,8 +913,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept)
 	if (intercept == svm->x2avic_msrs_intercepted)
 		return;
 
-	if (!x2avic_enabled ||
-	    !apic_x2apic_mode(svm->vcpu.arch.apic))
+	if (!x2avic_enabled)
 		return;
 
 	for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) {
@@ -1532,7 +1546,14 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	if (tsc_scaling)
 		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 
-	if (likely(tsc_aux_uret_slot >= 0))
+	/*
+	 * TSC_AUX is always virtualized for SEV-ES guests when the feature is
+	 * available. The user return MSR support is not required in this case
+	 * because TSC_AUX is restored on #VMEXIT from the host save area
+	 * (which has been initialized in svm_hardware_enable()).
+	 */
+	if (likely(tsc_aux_uret_slot >= 0) &&
+	    (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
 		kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
 
 	svm->guest_state_loaded = true;
@@ -3087,6 +3108,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		break;
 	case MSR_TSC_AUX:
 		/*
+		 * TSC_AUX is always virtualized for SEV-ES guests when the
+		 * feature is available. The user return MSR support is not
+		 * required in this case because TSC_AUX is restored on #VMEXIT
+		 * from the host save area (which has been initialized in
+		 * svm_hardware_enable()).
+		 */
+		if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm))
+			break;
+
+		/*
 		 * TSC_AUX is usually changed only during boot and never read
 		 * directly.  Intercept TSC_AUX instead of exposing it to the
 		 * guest via direct_access_msrs, and switch it via user return.
@@ -4284,7 +4315,6 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index)
 static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct kvm_cpuid_entry2 *best;
 
 	/*
 	 * SVM doesn't provide a way to disable just XSAVES in the guest, KVM
@@ -4328,12 +4358,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0,
 				     !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D));
 
-	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
-	if (sev_guest(vcpu->kvm)) {
-		best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
-		if (best)
-			vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
-	}
+	if (sev_guest(vcpu->kvm))
+		sev_vcpu_after_set_cpuid(svm);
 
 	init_vmcb_after_set_cpuid(vcpu);
 }
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f41253958357..be67ab7fdd10 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -684,6 +684,7 @@ void __init sev_hardware_setup(void);
 void sev_hardware_unsetup(void);
 int sev_cpu_init(struct svm_cpu_data *sd);
 void sev_init_vmcb(struct vcpu_svm *svm);
+void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm);
 void sev_free_vcpu(struct kvm_vcpu *vcpu);
 int sev_handle_vmgexit(struct kvm_vcpu *vcpu);
 int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index f2efa0bf7ae8..820d3e1f6b4f 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -436,11 +436,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			if (!msr_info->host_initiated &&
 			    !(msr & MSR_PMC_FULL_WIDTH_BIT))
 				data = (s64)(s32)data;
-			pmc->counter += data - pmc_read_counter(pmc);
+			pmc_write_counter(pmc, data);
 			pmc_update_sample_period(pmc);
 			break;
 		} else if ((pmc = get_fixed_pmc(pmu, msr))) {
-			pmc->counter += data - pmc_read_counter(pmc);
+			pmc_write_counter(pmc, data);
 			pmc_update_sample_period(pmc);
 			break;
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6c9c81e82e65..41cce5031126 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5382,26 +5382,37 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
-					 struct kvm_xsave *guest_xsave)
-{
-	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
-		return;
-
-	fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
-				       guest_xsave->region,
-				       sizeof(guest_xsave->region),
-				       vcpu->arch.pkru);
-}
 
 static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
 					  u8 *state, unsigned int size)
 {
+	/*
+	 * Only copy state for features that are enabled for the guest.  The
+	 * state itself isn't problematic, but setting bits in the header for
+	 * features that are supported in *this* host but not exposed to the
+	 * guest can result in KVM_SET_XSAVE failing when live migrating to a
+	 * compatible host without the features that are NOT exposed to the
+	 * guest.
+	 *
+	 * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if
+	 * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't
+	 * supported by the host.
+	 */
+	u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 |
+			     XFEATURE_MASK_FPSSE;
+
 	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
 		return;
 
-	fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
-				       state, size, vcpu->arch.pkru);
+	fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size,
+				       supported_xcr0, vcpu->arch.pkru);
+}
+
+static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
+					 struct kvm_xsave *guest_xsave)
+{
+	return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
+					     sizeof(guest_xsave->region));
 }
 
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
@@ -12308,9 +12319,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out;
 
-	ret = kvm_mmu_init_vm(kvm);
-	if (ret)
-		goto out_page_track;
+	kvm_mmu_init_vm(kvm);
 
 	ret = static_call(kvm_x86_vm_init)(kvm);
 	if (ret)
@@ -12355,7 +12364,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 out_uninit_mmu:
 	kvm_mmu_uninit_vm(kvm);
-out_page_track:
 	kvm_page_track_cleanup(kvm);
 out:
 	return ret;
@@ -12846,6 +12854,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 		return true;
 #endif
 
+	if (kvm_test_request(KVM_REQ_PMI, vcpu))
+		return true;
+
 	if (kvm_arch_interrupt_allowed(vcpu) &&
 	    (kvm_cpu_has_interrupt(vcpu) ||
 	    kvm_guest_apic_has_interrupt(vcpu)))