Merge branch 'linus' into irq/core, to fix conflict

Conflicts:
	drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

21 files changed, 506 insertions, 348 deletions

diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index 54a83a744538..f33c804a922a 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -95,6 +95,9 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v)
 	unsigned int *log[KVM_NR_PAGE_SIZES], *cur;
 	int i, j, k, l, ret;
 
+	if (!kvm_memslots_have_rmaps(kvm))
+		return 0;
+
 	ret = -ENOMEM;
 	memset(log, 0, sizeof(log));
 	for (i = 0; i < KVM_NR_PAGE_SIZES; i++) {
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 5e19e6e4c2ce..8d8c1cc7cb53 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1922,11 +1922,13 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 
 		all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL;
 
+		if (all_cpus)
+			goto check_and_send_ipi;
+
 		if (!sparse_banks_len)
 			goto ret_success;
 
-		if (!all_cpus &&
-		    kvm_read_guest(kvm,
+		if (kvm_read_guest(kvm,
 				   hc->ingpa + offsetof(struct hv_send_ipi_ex,
 							vp_set.bank_contents),
 				   sparse_banks,
@@ -1934,6 +1936,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 	}
 
+check_and_send_ipi:
 	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
 		return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index e66e620c3bed..539333ac4b38 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -81,7 +81,6 @@ struct kvm_ioapic {
 	unsigned long irq_states[IOAPIC_NUM_PINS];
 	struct kvm_io_device dev;
 	struct kvm *kvm;
-	void (*ack_notifier)(void *opaque, int irq);
 	spinlock_t lock;
 	struct rtc_status rtc_status;
 	struct delayed_work eoi_inject;
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 650642b18d15..c2d7cfe82d00 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -56,7 +56,6 @@ struct kvm_pic {
 	struct kvm_io_device dev_master;
 	struct kvm_io_device dev_slave;
 	struct kvm_io_device dev_elcr;
-	void (*ack_notifier)(void *opaque, int irq);
 	unsigned long irq_states[PIC_NUM_PINS];
 };
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 759952dd1222..f206fc35deff 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -707,7 +707,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr)
 {
 	int highest_irr;
-	if (apic->vcpu->arch.apicv_active)
+	if (kvm_x86_ops.sync_pir_to_irr)
 		highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu);
 	else
 		highest_irr = apic_find_highest_irr(apic);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3be9beea838d..fcdf3f8bb59a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1582,7 +1582,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 		flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp);
 
 	if (is_tdp_mmu_enabled(kvm))
-		flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
+		flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
 
 	return flush;
 }
@@ -1936,7 +1936,11 @@ static void mmu_audit_disable(void) { }
 
 static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	return sp->role.invalid ||
+	if (sp->role.invalid)
+		return true;
+
+	/* TDP MMU pages due not use the MMU generation. */
+	return !sp->tdp_mmu_page &&
 	       unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
 }
 
@@ -2173,10 +2177,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
 	iterator->shadow_addr = root;
 	iterator->level = vcpu->arch.mmu->shadow_root_level;
 
-	if (iterator->level == PT64_ROOT_4LEVEL &&
+	if (iterator->level >= PT64_ROOT_4LEVEL &&
 	    vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
 	    !vcpu->arch.mmu->direct_map)
-		--iterator->level;
+		iterator->level = PT32E_ROOT_LEVEL;
 
 	if (iterator->level == PT32E_ROOT_LEVEL) {
 		/*
@@ -3976,6 +3980,34 @@ out_retry:
 	return true;
 }
 
+/*
+ * Returns true if the page fault is stale and needs to be retried, i.e. if the
+ * root was invalidated by a memslot update or a relevant mmu_notifier fired.
+ */
+static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
+				struct kvm_page_fault *fault, int mmu_seq)
+{
+	struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root_hpa);
+
+	/* Special roots, e.g. pae_root, are not backed by shadow pages. */
+	if (sp && is_obsolete_sp(vcpu->kvm, sp))
+		return true;
+
+	/*
+	 * Roots without an associated shadow page are considered invalid if
+	 * there is a pending request to free obsolete roots.  The request is
+	 * only a hint that the current root _may_ be obsolete and needs to be
+	 * reloaded, e.g. if the guest frees a PGD that KVM is tracking as a
+	 * previous root, then __kvm_mmu_prepare_zap_page() signals all vCPUs
+	 * to reload even if no vCPU is actively using the root.
+	 */
+	if (!sp && kvm_test_request(KVM_REQ_MMU_RELOAD, vcpu))
+		return true;
+
+	return fault->slot &&
+	       mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
+}
+
 static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu);
@@ -4013,8 +4045,9 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	else
 		write_lock(&vcpu->kvm->mmu_lock);
 
-	if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva))
+	if (is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
+
 	r = make_mmu_pages_available(vcpu);
 	if (r)
 		goto out_unlock;
@@ -4855,7 +4888,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0,
 	struct kvm_mmu *context = &vcpu->arch.guest_mmu;
 	struct kvm_mmu_role_regs regs = {
 		.cr0 = cr0,
-		.cr4 = cr4,
+		.cr4 = cr4 & ~X86_CR4_PKE,
 		.efer = efer,
 	};
 	union kvm_mmu_role new_role;
@@ -4919,7 +4952,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 	context->direct_map = false;
 
 	update_permission_bitmask(context, true);
-	update_pkru_bitmask(context);
+	context->pkru_mask = 0;
 	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
 	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
 }
@@ -5025,6 +5058,14 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	/*
 	 * Invalidate all MMU roles to force them to reinitialize as CPUID
 	 * information is factored into reserved bit calculations.
+	 *
+	 * Correctly handling multiple vCPU models with respect to paging and
+	 * physical address properties) in a single VM would require tracking
+	 * all relevant CPUID information in kvm_mmu_page_role. That is very
+	 * undesirable as it would increase the memory requirements for
+	 * gfn_track (see struct kvm_mmu_page_role comments).  For now that
+	 * problem is swept under the rug; KVM's CPUID API is horrific and
+	 * it's all but impossible to solve it without introducing a new API.
 	 */
 	vcpu->arch.root_mmu.mmu_role.ext.valid = 0;
 	vcpu->arch.guest_mmu.mmu_role.ext.valid = 0;
@@ -5032,24 +5073,10 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	kvm_mmu_reset_context(vcpu);
 
 	/*
-	 * 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.  Alert userspace, but otherwise
-	 * sweep the problem under the rug.
-	 *
-	 * KVM's horrific CPUID ABI makes the problem all but impossible to
-	 * solve, as correctly handling multiple vCPU models (with respect to
-	 * paging and physical address properties) in a single VM would require
-	 * tracking all relevant CPUID information in kvm_mmu_page_role.  That
-	 * is very undesirable as it would double the memory requirements for
-	 * gfn_track (see struct kvm_mmu_page_role comments), and in practice
-	 * no sane VMM mucks with the core vCPU model on the fly.
+	 * Changing guest CPUID after KVM_RUN is forbidden, see the comment in
+	 * kvm_arch_vcpu_ioctl().
 	 */
-	if (vcpu->arch.last_vmentry_cpu != -1) {
-		pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} after KVM_RUN may cause guest instability\n");
-		pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} will fail after KVM_RUN starting with Linux 5.16\n");
-	}
+	KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm);
 }
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
@@ -5369,7 +5396,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	kvm_mmu_invalidate_gva(vcpu, vcpu->arch.mmu, gva, INVALID_PAGE);
+	kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE);
 	++vcpu->stat.invlpg;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
@@ -5854,8 +5881,6 @@ restart:
 void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 				   const struct kvm_memory_slot *slot)
 {
-	bool flush = false;
-
 	if (kvm_memslots_have_rmaps(kvm)) {
 		write_lock(&kvm->mmu_lock);
 		/*
@@ -5863,17 +5888,14 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 		 * logging at a 4k granularity and never creates collapsible
 		 * 2m SPTEs during dirty logging.
 		 */
-		flush = slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true);
-		if (flush)
+		if (slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true))
 			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
 		write_unlock(&kvm->mmu_lock);
 	}
 
 	if (is_tdp_mmu_enabled(kvm)) {
 		read_lock(&kvm->mmu_lock);
-		flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush);
-		if (flush)
-			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+		kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot);
 		read_unlock(&kvm->mmu_lock);
 	}
 }
@@ -6182,23 +6204,46 @@ void kvm_mmu_module_exit(void)
 	mmu_audit_disable();
 }
 
+/*
+ * Calculate the effective recovery period, accounting for '0' meaning "let KVM
+ * select a halving time of 1 hour".  Returns true if recovery is enabled.
+ */
+static bool calc_nx_huge_pages_recovery_period(uint *period)
+{
+	/*
+	 * Use READ_ONCE to get the params, this may be called outside of the
+	 * param setters, e.g. by the kthread to compute its next timeout.
+	 */
+	bool enabled = READ_ONCE(nx_huge_pages);
+	uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
+
+	if (!enabled || !ratio)
+		return false;
+
+	*period = READ_ONCE(nx_huge_pages_recovery_period_ms);
+	if (!*period) {
+		/* Make sure the period is not less than one second.  */
+		ratio = min(ratio, 3600u);
+		*period = 60 * 60 * 1000 / ratio;
+	}
+	return true;
+}
+
 static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp)
 {
 	bool was_recovery_enabled, is_recovery_enabled;
 	uint old_period, new_period;
 	int err;
 
-	was_recovery_enabled = nx_huge_pages_recovery_ratio;
-	old_period = nx_huge_pages_recovery_period_ms;
+	was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period);
 
 	err = param_set_uint(val, kp);
 	if (err)
 		return err;
 
-	is_recovery_enabled = nx_huge_pages_recovery_ratio;
-	new_period = nx_huge_pages_recovery_period_ms;
+	is_recovery_enabled = calc_nx_huge_pages_recovery_period(&new_period);
 
-	if (READ_ONCE(nx_huge_pages) && is_recovery_enabled &&
+	if (is_recovery_enabled &&
 	    (!was_recovery_enabled || old_period > new_period)) {
 		struct kvm *kvm;
 
@@ -6262,18 +6307,13 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 
 static long get_nx_lpage_recovery_timeout(u64 start_time)
 {
-	uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
-	uint period = READ_ONCE(nx_huge_pages_recovery_period_ms);
+	bool enabled;
+	uint period;
 
-	if (!period && ratio) {
-		/* Make sure the period is not less than one second.  */
-		ratio = min(ratio, 3600u);
-		period = 60 * 60 * 1000 / ratio;
-	}
+	enabled = calc_nx_huge_pages_recovery_period(&period);
 
-	return READ_ONCE(nx_huge_pages) && ratio
-		? start_time + msecs_to_jiffies(period) - get_jiffies_64()
-		: MAX_SCHEDULE_TIMEOUT;
+	return enabled ? start_time + msecs_to_jiffies(period) - get_jiffies_64()
+		       : MAX_SCHEDULE_TIMEOUT;
 }
 
 static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index f87d36898c44..708a5d297fe1 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -911,7 +911,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 
 	r = RET_PF_RETRY;
 	write_lock(&vcpu->kvm->mmu_lock);
-	if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva))
+
+	if (is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
 
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index b3ed302c1a35..caa96c270b95 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -26,6 +26,7 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level)
  */
 void tdp_iter_restart(struct tdp_iter *iter)
 {
+	iter->yielded = false;
 	iter->yielded_gfn = iter->next_last_level_gfn;
 	iter->level = iter->root_level;
 
@@ -160,6 +161,11 @@ static bool try_step_up(struct tdp_iter *iter)
  */
 void tdp_iter_next(struct tdp_iter *iter)
 {
+	if (iter->yielded) {
+		tdp_iter_restart(iter);
+		return;
+	}
+
 	if (try_step_down(iter))
 		return;
 
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index b1748b988d3a..e19cabbcb65c 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -45,6 +45,12 @@ struct tdp_iter {
 	 * iterator walks off the end of the paging structure.
 	 */
 	bool valid;
+	/*
+	 * True if KVM dropped mmu_lock and yielded in the middle of a walk, in
+	 * which case tdp_iter_next() needs to restart the walk at the root
+	 * level instead of advancing to the next entry.
+	 */
+	bool yielded;
 };
 
 /*
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index a54c3491af42..1beb4ca90560 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -317,9 +317,6 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 	struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
 	int level = sp->role.level;
 	gfn_t base_gfn = sp->gfn;
-	u64 old_child_spte;
-	u64 *sptep;
-	gfn_t gfn;
 	int i;
 
 	trace_kvm_mmu_prepare_zap_page(sp);
@@ -327,8 +324,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 	tdp_mmu_unlink_page(kvm, sp, shared);
 
 	for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
-		sptep = rcu_dereference(pt) + i;
-		gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
+		u64 *sptep = rcu_dereference(pt) + i;
+		gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
+		u64 old_child_spte;
 
 		if (shared) {
 			/*
@@ -374,7 +372,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 				    shared);
 	}
 
-	kvm_flush_remote_tlbs_with_address(kvm, gfn,
+	kvm_flush_remote_tlbs_with_address(kvm, base_gfn,
 					   KVM_PAGES_PER_HPAGE(level + 1));
 
 	call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
@@ -504,6 +502,8 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
 					   struct tdp_iter *iter,
 					   u64 new_spte)
 {
+	WARN_ON_ONCE(iter->yielded);
+
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
 	/*
@@ -577,6 +577,8 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 				      u64 new_spte, bool record_acc_track,
 				      bool record_dirty_log)
 {
+	WARN_ON_ONCE(iter->yielded);
+
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	/*
@@ -642,18 +644,19 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
  * If this function should yield and flush is set, it will perform a remote
  * TLB flush before yielding.
  *
- * If this function yields, it will also reset the tdp_iter's walk over the
- * paging structure and the calling function should skip to the next
- * iteration to allow the iterator to continue its traversal from the
- * paging structure root.
+ * If this function yields, iter->yielded is set and the caller must skip to
+ * the next iteration, where tdp_iter_next() will reset the tdp_iter's walk
+ * over the paging structures to allow the iterator to continue its traversal
+ * from the paging structure root.
  *
- * Return true if this function yielded and the iterator's traversal was reset.
- * Return false if a yield was not needed.
+ * Returns true if this function yielded.
  */
-static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
-					     struct tdp_iter *iter, bool flush,
-					     bool shared)
+static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm,
+							  struct tdp_iter *iter,
+							  bool flush, bool shared)
 {
+	WARN_ON(iter->yielded);
+
 	/* Ensure forward progress has been made before yielding. */
 	if (iter->next_last_level_gfn == iter->yielded_gfn)
 		return false;
@@ -673,12 +676,10 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
 
 		WARN_ON(iter->gfn > iter->next_last_level_gfn);
 
-		tdp_iter_restart(iter);
-
-		return true;
+		iter->yielded = true;
 	}
 
-	return false;
+	return iter->yielded;
 }
 
 /*
@@ -1033,9 +1034,9 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 {
 	struct kvm_mmu_page *root;
 
-	for_each_tdp_mmu_root(kvm, root, range->slot->as_id)
-		flush |= zap_gfn_range(kvm, root, range->start, range->end,
-				       range->may_block, flush, false);
+	for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false)
+		flush = zap_gfn_range(kvm, root, range->start, range->end,
+				      range->may_block, flush, false);
 
 	return flush;
 }
@@ -1364,10 +1365,9 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
  * Clear leaf entries which could be replaced by large mappings, for
  * GFNs within the slot.
  */
-static bool zap_collapsible_spte_range(struct kvm *kvm,
+static void zap_collapsible_spte_range(struct kvm *kvm,
 				       struct kvm_mmu_page *root,
-				       const struct kvm_memory_slot *slot,
-				       bool flush)
+				       const struct kvm_memory_slot *slot)
 {
 	gfn_t start = slot->base_gfn;
 	gfn_t end = start + slot->npages;
@@ -1378,10 +1378,8 @@ static bool zap_collapsible_spte_range(struct kvm *kvm,
 
 	tdp_root_for_each_pte(iter, root, start, end) {
 retry:
-		if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) {
-			flush = false;
+		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
 			continue;
-		}
 
 		if (!is_shadow_present_pte(iter.old_spte) ||
 		    !is_last_spte(iter.old_spte, iter.level))
@@ -1393,6 +1391,7 @@ retry:
 							    pfn, PG_LEVEL_NUM))
 			continue;
 
+		/* Note, a successful atomic zap also does a remote TLB flush. */
 		if (!tdp_mmu_zap_spte_atomic(kvm, &iter)) {
 			/*
 			 * The iter must explicitly re-read the SPTE because
@@ -1401,30 +1400,24 @@ retry:
 			iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
 			goto retry;
 		}
-		flush = true;
 	}
 
 	rcu_read_unlock();
-
-	return flush;
 }
 
 /*
  * Clear non-leaf entries (and free associated page tables) which could
  * be replaced by large mappings, for GFNs within the slot.
  */
-bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot,
-				       bool flush)
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot)
 {
 	struct kvm_mmu_page *root;
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
-		flush = zap_collapsible_spte_range(kvm, root, slot, flush);
-
-	return flush;
+		zap_collapsible_spte_range(kvm, root, slot);
 }
 
 /*
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 476b133544dd..3899004a5d91 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -64,9 +64,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 				       struct kvm_memory_slot *slot,
 				       gfn_t gfn, unsigned long mask,
 				       bool wrprot);
-bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot,
-				       bool flush);
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot);
 
 bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn,
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index affc0ea98d30..8f9af7b7dbbe 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -900,6 +900,7 @@ out:
 bool svm_check_apicv_inhibit_reasons(ulong bit)
 {
 	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
+			  BIT(APICV_INHIBIT_REASON_ABSENT) |
 			  BIT(APICV_INHIBIT_REASON_HYPERV) |
 			  BIT(APICV_INHIBIT_REASON_NESTED) |
 			  BIT(APICV_INHIBIT_REASON_IRQWIN) |
@@ -989,16 +990,18 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
 {
 	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 (is_run)
-		avic_vcpu_load(vcpu, vcpu->cpu);
-	else
-		avic_vcpu_put(vcpu);
+	if (kvm_vcpu_apicv_active(vcpu)) {
+		if (is_run)
+			avic_vcpu_load(vcpu, cpu);
+		else
+			avic_vcpu_put(vcpu);
+	}
+	put_cpu();
 }
 
 void svm_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 871c426ec389..b4095dfeeee6 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -281,7 +281,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 		pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS;
 
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
-	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->reserved_bits = 0xfffffff000280000ull;
 	pmu->version = 1;
 	/* not applicable to AMD; but clean them to prevent any fall out */
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 21ac0a5de4e0..be2883141220 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1543,28 +1543,50 @@ static bool is_cmd_allowed_from_mirror(u32 cmd_id)
 	return false;
 }
 
-static int sev_lock_for_migration(struct kvm *kvm)
+static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info;
+	struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info;
+	int r = -EBUSY;
+
+	if (dst_kvm == src_kvm)
+		return -EINVAL;
 
 	/*
-	 * Bail if this VM is already involved in a migration to avoid deadlock
-	 * between two VMs trying to migrate to/from each other.
+	 * Bail if these VMs are already involved in a migration to avoid
+	 * deadlock between two VMs trying to migrate to/from each other.
 	 */
-	if (atomic_cmpxchg_acquire(&sev->migration_in_progress, 0, 1))
+	if (atomic_cmpxchg_acquire(&dst_sev->migration_in_progress, 0, 1))
 		return -EBUSY;
 
-	mutex_lock(&kvm->lock);
+	if (atomic_cmpxchg_acquire(&src_sev->migration_in_progress, 0, 1))
+		goto release_dst;
 
+	r = -EINTR;
+	if (mutex_lock_killable(&dst_kvm->lock))
+		goto release_src;
+	if (mutex_lock_killable_nested(&src_kvm->lock, SINGLE_DEPTH_NESTING))
+		goto unlock_dst;
 	return 0;
+
+unlock_dst:
+	mutex_unlock(&dst_kvm->lock);
+release_src:
+	atomic_set_release(&src_sev->migration_in_progress, 0);
+release_dst:
+	atomic_set_release(&dst_sev->migration_in_progress, 0);
+	return r;
 }
 
-static void sev_unlock_after_migration(struct kvm *kvm)
+static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
 {
-	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info;
+	struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info;
 
-	mutex_unlock(&kvm->lock);
-	atomic_set_release(&sev->migration_in_progress, 0);
+	mutex_unlock(&dst_kvm->lock);
+	mutex_unlock(&src_kvm->lock);
+	atomic_set_release(&dst_sev->migration_in_progress, 0);
+	atomic_set_release(&src_sev->migration_in_progress, 0);
 }
 
 
@@ -1607,14 +1629,15 @@ static void sev_migrate_from(struct kvm_sev_info *dst,
 	dst->asid = src->asid;
 	dst->handle = src->handle;
 	dst->pages_locked = src->pages_locked;
+	dst->enc_context_owner = src->enc_context_owner;
 
 	src->asid = 0;
 	src->active = false;
 	src->handle = 0;
 	src->pages_locked = 0;
+	src->enc_context_owner = NULL;
 
-	INIT_LIST_HEAD(&dst->regions_list);
-	list_replace_init(&src->regions_list, &dst->regions_list);
+	list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list);
 }
 
 static int sev_es_migrate_from(struct kvm *dst, struct kvm *src)
@@ -1666,15 +1689,6 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd)
 	bool charged = false;
 	int ret;
 
-	ret = sev_lock_for_migration(kvm);
-	if (ret)
-		return ret;
-
-	if (sev_guest(kvm)) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
 	source_kvm_file = fget(source_fd);
 	if (!file_is_kvm(source_kvm_file)) {
 		ret = -EBADF;
@@ -1682,16 +1696,26 @@ int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd)
 	}
 
 	source_kvm = source_kvm_file->private_data;
-	ret = sev_lock_for_migration(source_kvm);
+	ret = sev_lock_two_vms(kvm, source_kvm);
 	if (ret)
 		goto out_fput;
 
-	if (!sev_guest(source_kvm)) {
+	if (sev_guest(kvm) || !sev_guest(source_kvm)) {
 		ret = -EINVAL;
-		goto out_source;
+		goto out_unlock;
 	}
 
 	src_sev = &to_kvm_svm(source_kvm)->sev_info;
+
+	/*
+	 * VMs mirroring src's encryption context rely on it to keep the
+	 * ASID allocated, but below we are clearing src_sev->asid.
+	 */
+	if (src_sev->num_mirrored_vms) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
 	dst_sev->misc_cg = get_current_misc_cg();
 	cg_cleanup_sev = dst_sev;
 	if (dst_sev->misc_cg != src_sev->misc_cg) {
@@ -1728,13 +1752,11 @@ out_dst_cgroup:
 		sev_misc_cg_uncharge(cg_cleanup_sev);
 	put_misc_cg(cg_cleanup_sev->misc_cg);
 	cg_cleanup_sev->misc_cg = NULL;
-out_source:
-	sev_unlock_after_migration(source_kvm);
+out_unlock:
+	sev_unlock_two_vms(kvm, source_kvm);
 out_fput:
 	if (source_kvm_file)
 		fput(source_kvm_file);
-out_unlock:
-	sev_unlock_after_migration(kvm);
 	return ret;
 }
 
@@ -1953,76 +1975,60 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 {
 	struct file *source_kvm_file;
 	struct kvm *source_kvm;
-	struct kvm_sev_info source_sev, *mirror_sev;
+	struct kvm_sev_info *source_sev, *mirror_sev;
 	int ret;
 
 	source_kvm_file = fget(source_fd);
 	if (!file_is_kvm(source_kvm_file)) {
 		ret = -EBADF;
-		goto e_source_put;
+		goto e_source_fput;
 	}
 
 	source_kvm = source_kvm_file->private_data;
-	mutex_lock(&source_kvm->lock);
-
-	if (!sev_guest(source_kvm)) {
-		ret = -EINVAL;
-		goto e_source_unlock;
-	}
+	ret = sev_lock_two_vms(kvm, source_kvm);
+	if (ret)
+		goto e_source_fput;
 
-	/* Mirrors of mirrors should work, but let's not get silly */
-	if (is_mirroring_enc_context(source_kvm) || source_kvm == kvm) {
+	/*
+	 * Mirrors of mirrors should work, but let's not get silly.  Also
+	 * disallow out-of-band SEV/SEV-ES init if the target is already an
+	 * SEV guest, or if vCPUs have been created.  KVM relies on vCPUs being
+	 * created after SEV/SEV-ES initialization, e.g. to init intercepts.
+	 */
+	if (sev_guest(kvm) || !sev_guest(source_kvm) ||
+	    is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) {
 		ret = -EINVAL;
-		goto e_source_unlock;
+		goto e_unlock;
 	}
 
-	memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info,
-	       sizeof(source_sev));
-
 	/*
 	 * The mirror kvm holds an enc_context_owner ref so its asid can't
 	 * disappear until we're done with it
 	 */
+	source_sev = &to_kvm_svm(source_kvm)->sev_info;
 	kvm_get_kvm(source_kvm);
-
-	fput(source_kvm_file);
-	mutex_unlock(&source_kvm->lock);
-	mutex_lock(&kvm->lock);
-
-	/*
-	 * Disallow out-of-band SEV/SEV-ES init if the target is already an
-	 * SEV guest, or if vCPUs have been created.  KVM relies on vCPUs being
-	 * created after SEV/SEV-ES initialization, e.g. to init intercepts.
-	 */
-	if (sev_guest(kvm) || kvm->created_vcpus) {
-		ret = -EINVAL;
-		goto e_mirror_unlock;
-	}
+	source_sev->num_mirrored_vms++;
 
 	/* Set enc_context_owner and copy its encryption context over */
 	mirror_sev = &to_kvm_svm(kvm)->sev_info;
 	mirror_sev->enc_context_owner = source_kvm;
 	mirror_sev->active = true;
-	mirror_sev->asid = source_sev.asid;
-	mirror_sev->fd = source_sev.fd;
-	mirror_sev->es_active = source_sev.es_active;
-	mirror_sev->handle = source_sev.handle;
+	mirror_sev->asid = source_sev->asid;
+	mirror_sev->fd = source_sev->fd;
+	mirror_sev->es_active = source_sev->es_active;
+	mirror_sev->handle = source_sev->handle;
+	INIT_LIST_HEAD(&mirror_sev->regions_list);
+	ret = 0;
+
 	/*
 	 * Do not copy ap_jump_table. Since the mirror does not share the same
 	 * KVM contexts as the original, and they may have different
 	 * memory-views.
 	 */
 
-	mutex_unlock(&kvm->lock);
-	return 0;
-
-e_mirror_unlock:
-	mutex_unlock(&kvm->lock);
-	kvm_put_kvm(source_kvm);
-	return ret;
-e_source_unlock:
-	mutex_unlock(&source_kvm->lock);
-e_source_put:
+e_unlock:
+	sev_unlock_two_vms(kvm, source_kvm);
+e_source_fput:
 	if (source_kvm_file)
 		fput(source_kvm_file);
 	return ret;
@@ -2034,17 +2040,24 @@ void sev_vm_destroy(struct kvm *kvm)
 	struct list_head *head = &sev->regions_list;
 	struct list_head *pos, *q;
 
+	WARN_ON(sev->num_mirrored_vms);
+
 	if (!sev_guest(kvm))
 		return;
 
 	/* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */
 	if (is_mirroring_enc_context(kvm)) {
-		kvm_put_kvm(sev->enc_context_owner);
+		struct kvm *owner_kvm = sev->enc_context_owner;
+		struct kvm_sev_info *owner_sev = &to_kvm_svm(owner_kvm)->sev_info;
+
+		mutex_lock(&owner_kvm->lock);
+		if (!WARN_ON(!owner_sev->num_mirrored_vms))
+			owner_sev->num_mirrored_vms--;
+		mutex_unlock(&owner_kvm->lock);
+		kvm_put_kvm(owner_kvm);
 		return;
 	}
 
-	mutex_lock(&kvm->lock);
-
 	/*
 	 * Ensure that all guest tagged cache entries are flushed before
 	 * releasing the pages back to the system for use. CLFLUSH will
@@ -2064,8 +2077,6 @@ void sev_vm_destroy(struct kvm *kvm)
 		}
 	}
 
-	mutex_unlock(&kvm->lock);
-
 	sev_unbind_asid(kvm, sev->handle);
 	sev_asid_free(sev);
 }
@@ -2249,7 +2260,7 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_page(virt_to_page(svm->sev_es.vmsa));
 
 	if (svm->sev_es.ghcb_sa_free)
-		kfree(svm->sev_es.ghcb_sa);
+		kvfree(svm->sev_es.ghcb_sa);
 }
 
 static void dump_ghcb(struct vcpu_svm *svm)
@@ -2341,24 +2352,29 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
 }
 
-static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
+static bool sev_es_validate_vmgexit(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu;
 	struct ghcb *ghcb;
-	u64 exit_code = 0;
+	u64 exit_code;
+	u64 reason;
 
 	ghcb = svm->sev_es.ghcb;
 
-	/* Only GHCB Usage code 0 is supported */
-	if (ghcb->ghcb_usage)
-		goto vmgexit_err;
-
 	/*
-	 * Retrieve the exit code now even though is may not be marked valid
+	 * Retrieve the exit code now even though it may not be marked valid
 	 * as it could help with debugging.
 	 */
 	exit_code = ghcb_get_sw_exit_code(ghcb);
 
+	/* Only GHCB Usage code 0 is supported */
+	if (ghcb->ghcb_usage) {
+		reason = GHCB_ERR_INVALID_USAGE;
+		goto vmgexit_err;
+	}
+
+	reason = GHCB_ERR_MISSING_INPUT;
+
 	if (!ghcb_sw_exit_code_is_valid(ghcb) ||
 	    !ghcb_sw_exit_info_1_is_valid(ghcb) ||
 	    !ghcb_sw_exit_info_2_is_valid(ghcb))
@@ -2437,30 +2453,34 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		break;
 	default:
+		reason = GHCB_ERR_INVALID_EVENT;
 		goto vmgexit_err;
 	}
 
-	return 0;
+	return true;
 
 vmgexit_err:
 	vcpu = &svm->vcpu;
 
-	if (ghcb->ghcb_usage) {
+	if (reason == GHCB_ERR_INVALID_USAGE) {
 		vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n",
 			    ghcb->ghcb_usage);
+	} else if (reason == GHCB_ERR_INVALID_EVENT) {
+		vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n",
+			    exit_code);
 	} else {
-		vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n",
+		vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n",
 			    exit_code);
 		dump_ghcb(svm);
 	}
 
-	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
-	vcpu->run->internal.ndata = 2;
-	vcpu->run->internal.data[0] = exit_code;
-	vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
+	/* Clear the valid entries fields */
+	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
+
+	ghcb_set_sw_exit_info_1(ghcb, 2);
+	ghcb_set_sw_exit_info_2(ghcb, reason);
 
-	return -EINVAL;
+	return false;
 }
 
 void sev_es_unmap_ghcb(struct vcpu_svm *svm)
@@ -2482,7 +2502,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm)
 			svm->sev_es.ghcb_sa_sync = false;
 		}
 
-		kfree(svm->sev_es.ghcb_sa);
+		kvfree(svm->sev_es.ghcb_sa);
 		svm->sev_es.ghcb_sa = NULL;
 		svm->sev_es.ghcb_sa_free = false;
 	}
@@ -2530,14 +2550,14 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 	scratch_gpa_beg = ghcb_get_sw_scratch(ghcb);
 	if (!scratch_gpa_beg) {
 		pr_err("vmgexit: scratch gpa not provided\n");
-		return false;
+		goto e_scratch;
 	}
 
 	scratch_gpa_end = scratch_gpa_beg + len;
 	if (scratch_gpa_end < scratch_gpa_beg) {
 		pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n",
 		       len, scratch_gpa_beg);
-		return false;
+		goto e_scratch;
 	}
 
 	if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) {
@@ -2555,7 +2575,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		    scratch_gpa_end > ghcb_scratch_end) {
 			pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n",
 			       scratch_gpa_beg, scratch_gpa_end);
-			return false;
+			goto e_scratch;
 		}
 
 		scratch_va = (void *)svm->sev_es.ghcb;
@@ -2568,18 +2588,18 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		if (len > GHCB_SCRATCH_AREA_LIMIT) {
 			pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n",
 			       len, GHCB_SCRATCH_AREA_LIMIT);
-			return false;
+			goto e_scratch;
 		}
-		scratch_va = kzalloc(len, GFP_KERNEL_ACCOUNT);
+		scratch_va = kvzalloc(len, GFP_KERNEL_ACCOUNT);
 		if (!scratch_va)
-			return false;
+			goto e_scratch;
 
 		if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) {
 			/* Unable to copy scratch area from guest */
 			pr_err("vmgexit: kvm_read_guest for scratch area failed\n");
 
-			kfree(scratch_va);
-			return false;
+			kvfree(scratch_va);
+			goto e_scratch;
 		}
 
 		/*
@@ -2596,6 +2616,12 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 	svm->sev_es.ghcb_sa_len = len;
 
 	return true;
+
+e_scratch:
+	ghcb_set_sw_exit_info_1(ghcb, 2);
+	ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA);
+
+	return false;
 }
 
 static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask,
@@ -2646,7 +2672,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 
 		ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_CPUID);
 		if (!ret) {
-			ret = -EINVAL;
+			/* Error, keep GHCB MSR value as-is */
 			break;
 		}
 
@@ -2682,10 +2708,13 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 						GHCB_MSR_TERM_REASON_POS);
 		pr_info("SEV-ES guest requested termination: %#llx:%#llx\n",
 			reason_set, reason_code);
-		fallthrough;
+
+		ret = -EINVAL;
+		break;
 	}
 	default:
-		ret = -EINVAL;
+		/* Error, keep GHCB MSR value as-is */
+		break;
 	}
 
 	trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id,
@@ -2709,14 +2738,18 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 
 	if (!ghcb_gpa) {
 		vcpu_unimpl(vcpu, "vmgexit: GHCB gpa is not set\n");
-		return -EINVAL;
+
+		/* Without a GHCB, just return right back to the guest */
+		return 1;
 	}
 
 	if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) {
 		/* Unable to map GHCB from guest */
 		vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n",
 			    ghcb_gpa);
-		return -EINVAL;
+
+		/* Without a GHCB, just return right back to the guest */
+		return 1;
 	}
 
 	svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva;
@@ -2726,15 +2759,14 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 
 	exit_code = ghcb_get_sw_exit_code(ghcb);
 
-	ret = sev_es_validate_vmgexit(svm);
-	if (ret)
-		return ret;
+	if (!sev_es_validate_vmgexit(svm))
+		return 1;
 
 	sev_es_sync_from_ghcb(svm);
 	ghcb_set_sw_exit_info_1(ghcb, 0);
 	ghcb_set_sw_exit_info_2(ghcb, 0);
 
-	ret = -EINVAL;
+	ret = 1;
 	switch (exit_code) {
 	case SVM_VMGEXIT_MMIO_READ:
 		if (!setup_vmgexit_scratch(svm, true, control->exit_info_2))
@@ -2775,20 +2807,17 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		default:
 			pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n",
 			       control->exit_info_1);
-			ghcb_set_sw_exit_info_1(ghcb, 1);
-			ghcb_set_sw_exit_info_2(ghcb,
-						X86_TRAP_UD |
-						SVM_EVTINJ_TYPE_EXEPT |
-						SVM_EVTINJ_VALID);
+			ghcb_set_sw_exit_info_1(ghcb, 2);
+			ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT);
 		}
 
-		ret = 1;
 		break;
 	}
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		vcpu_unimpl(vcpu,
 			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
 			    control->exit_info_1, control->exit_info_2);
+		ret = -EINVAL;
 		break;
 	default:
 		ret = svm_invoke_exit_handler(vcpu, exit_code);
@@ -2810,7 +2839,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 		return -EINVAL;
 
 	if (!setup_vmgexit_scratch(svm, in, bytes))
-		return -EINVAL;
+		return 1;
 
 	return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa,
 				    count, in);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 5630c241d5f6..5151efa424ac 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1585,6 +1585,15 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	to_svm(vcpu)->vmcb->save.rflags = rflags;
 }
 
+static bool svm_get_if_flag(struct kvm_vcpu *vcpu)
+{
+	struct vmcb *vmcb = to_svm(vcpu)->vmcb;
+
+	return sev_es_guest(vcpu->kvm)
+		? vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK
+		: kvm_get_rflags(vcpu) & X86_EFLAGS_IF;
+}
+
 static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 {
 	switch (reg) {
@@ -3568,14 +3577,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu)
 	if (!gif_set(svm))
 		return true;
 
-	if (sev_es_guest(vcpu->kvm)) {
-		/*
-		 * SEV-ES guests to not expose RFLAGS. Use the VMCB interrupt mask
-		 * bit to determine the state of the IF flag.
-		 */
-		if (!(vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK))
-			return true;
-	} else if (is_guest_mode(vcpu)) {
+	if (is_guest_mode(vcpu)) {
 		/* As long as interrupts are being delivered...  */
 		if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK)
 		    ? !(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF)
@@ -3586,7 +3588,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu)
 		if (nested_exit_on_intr(svm))
 			return false;
 	} else {
-		if (!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF))
+		if (!svm_get_if_flag(vcpu))
 			return true;
 	}
 
@@ -4621,6 +4623,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.cache_reg = svm_cache_reg,
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
+	.get_if_flag = svm_get_if_flag,
 
 	.tlb_flush_all = svm_flush_tlb,
 	.tlb_flush_current = svm_flush_tlb,
@@ -4651,7 +4654,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
 	.hwapic_irr_update = svm_hwapic_irr_update,
 	.hwapic_isr_update = svm_hwapic_isr_update,
-	.sync_pir_to_irr = kvm_lapic_find_highest_irr,
 	.apicv_post_state_restore = avic_post_state_restore,
 
 	.set_tss_addr = svm_set_tss_addr,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 5faad3dc10e2..1c7306c370fa 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -79,6 +79,7 @@ struct kvm_sev_info {
 	struct list_head regions_list;  /* List of registered regions */
 	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */
 	struct kvm *enc_context_owner; /* Owner of copied encryption context */
+	unsigned long num_mirrored_vms; /* Number of VMs sharing this ASID */
 	struct misc_cg *misc_cg; /* For misc cgroup accounting */
 	atomic_t migration_in_progress;
 };
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 1e2f66951566..9c941535f78c 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1162,29 +1162,26 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 	WARN_ON(!enable_vpid);
 
 	/*
-	 * If VPID is enabled and used by vmc12, but L2 does not have a unique
-	 * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate
-	 * a VPID for L2, flush the current context as the effective ASID is
-	 * common to both L1 and L2.
-	 *
-	 * Defer the flush so that it runs after vmcs02.EPTP has been set by
-	 * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid
-	 * redundant flushes further down the nested pipeline.
-	 *
-	 * If a TLB flush isn't required due to any of the above, and vpid12 is
-	 * changing then the new "virtual" VPID (vpid12) will reuse the same
-	 * "real" VPID (vpid02), and so needs to be flushed.  There's no direct
-	 * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for
-	 * all nested vCPUs.  Remember, a flush on VM-Enter does not invalidate
-	 * guest-physical mappings, so there is no need to sync the nEPT MMU.
+	 * VPID is enabled and in use by vmcs12.  If vpid12 is changing, then
+	 * emulate a guest TLB flush as KVM does not track vpid12 history nor
+	 * is the VPID incorporated into the MMU context.  I.e. KVM must assume
+	 * that the new vpid12 has never been used and thus represents a new
+	 * guest ASID that cannot have entries in the TLB.
 	 */
-	if (!nested_has_guest_tlb_tag(vcpu)) {
-		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
-	} else if (is_vmenter &&
-		   vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
+	if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
 		vmx->nested.last_vpid = vmcs12->virtual_processor_id;
-		vpid_sync_context(nested_get_vpid02(vcpu));
+		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
+		return;
 	}
+
+	/*
+	 * If VPID is enabled, used by vmc12, and vpid12 is not changing but
+	 * does not have a unique TLB tag (ASID), i.e. EPT is disabled and
+	 * KVM was unable to allocate a VPID for L2, flush the current context
+	 * as the effective ASID is common to both L1 and L2.
+	 */
+	if (!nested_has_guest_tlb_tag(vcpu))
+		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 }
 
 static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
@@ -2594,8 +2591,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
 	    WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
-				     vmcs12->guest_ia32_perf_global_ctrl)))
+				     vmcs12->guest_ia32_perf_global_ctrl))) {
+		*entry_failure_code = ENTRY_FAIL_DEFAULT;
 		return -EINVAL;
+	}
 
 	kvm_rsp_write(vcpu, vmcs12->guest_rsp);
 	kvm_rip_write(vcpu, vmcs12->guest_rip);
@@ -3344,8 +3343,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	};
 	u32 failed_index;
 
-	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-		kvm_vcpu_flush_tlb_current(vcpu);
+	kvm_service_local_tlb_flush_requests(vcpu);
 
 	evaluate_pending_interrupts = exec_controls_get(vmx) &
 		(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING);
@@ -4502,9 +4500,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		(void)nested_get_evmcs_page(vcpu);
 	}
 
-	/* Service the TLB flush request for L2 before switching to L1. */
-	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-		kvm_vcpu_flush_tlb_current(vcpu);
+	/* Service pending TLB flush requests for L2 before switching to L1. */
+	kvm_service_local_tlb_flush_requests(vcpu);
 
 	/*
 	 * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between
@@ -4857,6 +4854,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 	if (!vmx->nested.cached_vmcs12)
 		goto out_cached_vmcs12;
 
+	vmx->nested.shadow_vmcs12_cache.gpa = INVALID_GPA;
 	vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT);
 	if (!vmx->nested.cached_shadow_vmcs12)
 		goto out_cached_shadow_vmcs12;
@@ -5289,8 +5287,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache;
 		struct vmcs_hdr hdr;
 
-		if (ghc->gpa != vmptr &&
-		    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) {
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) {
 			/*
 			 * Reads from an unbacked page return all 1s,
 			 * which means that the 32 bits located at the
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 5f81ef092bd4..1c94783b5a54 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -5,6 +5,7 @@
 #include <asm/cpu.h>
 
 #include "lapic.h"
+#include "irq.h"
 #include "posted_intr.h"
 #include "trace.h"
 #include "vmx.h"
@@ -77,13 +78,18 @@ after_clear_sn:
 		pi_set_on(pi_desc);
 }
 
+static bool vmx_can_use_vtd_pi(struct kvm *kvm)
+{
+	return irqchip_in_kernel(kvm) && enable_apicv &&
+		kvm_arch_has_assigned_device(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 (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
 		return;
 
 	/* Set SN when the vCPU is preempted */
@@ -141,9 +147,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu)
 	struct pi_desc old, new;
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
 		return 0;
 
 	WARN_ON(irqs_disabled());
@@ -270,9 +274,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq,
 	struct vcpu_data vcpu_info;
 	int idx, ret = 0;
 
-	if (!kvm_arch_has_assigned_device(kvm) ||
-	    !irq_remapping_cap(IRQ_POSTING_CAP) ||
-	    !kvm_vcpu_apicv_active(kvm->vcpus[0]))
+	if (!vmx_can_use_vtd_pi(kvm))
 		return 0;
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ba66c171d951..0dbf94eb954f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1363,6 +1363,11 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 		vmx->emulation_required = vmx_emulation_required(vcpu);
 }
 
+static bool vmx_get_if_flag(struct kvm_vcpu *vcpu)
+{
+	return vmx_get_rflags(vcpu) & X86_EFLAGS_IF;
+}
+
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
 {
 	u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
@@ -2646,15 +2651,6 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
 		if (!loaded_vmcs->msr_bitmap)
 			goto out_vmcs;
 		memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
-
-		if (IS_ENABLED(CONFIG_HYPERV) &&
-		    static_branch_unlikely(&enable_evmcs) &&
-		    (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
-			struct hv_enlightened_vmcs *evmcs =
-				(struct hv_enlightened_vmcs *)loaded_vmcs->vmcs;
-
-			evmcs->hv_enlightenments_control.msr_bitmap = 1;
-		}
 	}
 
 	memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state));
@@ -2918,6 +2914,13 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu)
 	}
 }
 
+static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu)
+{
+	if (is_guest_mode(vcpu))
+		return nested_get_vpid02(vcpu);
+	return to_vmx(vcpu)->vpid;
+}
+
 static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
@@ -2930,31 +2933,29 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 	if (enable_ept)
 		ept_sync_context(construct_eptp(vcpu, root_hpa,
 						mmu->shadow_root_level));
-	else if (!is_guest_mode(vcpu))
-		vpid_sync_context(to_vmx(vcpu)->vpid);
 	else
-		vpid_sync_context(nested_get_vpid02(vcpu));
+		vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
 
 static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
 {
 	/*
-	 * vpid_sync_vcpu_addr() is a nop if vmx->vpid==0, see the comment in
+	 * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in
 	 * vmx_flush_tlb_guest() for an explanation of why this is ok.
 	 */
-	vpid_sync_vcpu_addr(to_vmx(vcpu)->vpid, addr);
+	vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr);
 }
 
 static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu)
 {
 	/*
-	 * vpid_sync_context() is a nop if vmx->vpid==0, e.g. if enable_vpid==0
-	 * or a vpid couldn't be allocated for this vCPU.  VM-Enter and VM-Exit
-	 * are required to flush GVA->{G,H}PA mappings from the TLB if vpid is
+	 * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a
+	 * vpid couldn't be allocated for this vCPU.  VM-Enter and VM-Exit are
+	 * required to flush GVA->{G,H}PA mappings from the TLB if vpid is
 	 * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed),
 	 * i.e. no explicit INVVPID is necessary.
 	 */
-	vpid_sync_context(to_vmx(vcpu)->vpid);
+	vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
 
 void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu)
@@ -3963,8 +3964,7 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 	if (pi_test_and_set_on(&vmx->pi_desc))
 		return 0;
 
-	if (vcpu != kvm_get_running_vcpu() &&
-	    !kvm_vcpu_trigger_posted_interrupt(vcpu, false))
+	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
 		kvm_vcpu_kick(vcpu);
 
 	return 0;
@@ -5881,18 +5881,14 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		vmx_flush_pml_buffer(vcpu);
 
 	/*
-	 * We should never reach this point with a pending nested VM-Enter, and
-	 * more specifically emulation of L2 due to invalid guest state (see
-	 * below) should never happen as that means we incorrectly allowed a
-	 * nested VM-Enter with an invalid vmcs12.
+	 * KVM should never reach this point with a pending nested VM-Enter.
+	 * More specifically, short-circuiting VM-Entry to emulate L2 due to
+	 * invalid guest state should never happen as that means KVM knowingly
+	 * allowed a nested VM-Enter with an invalid vmcs12.  More below.
 	 */
 	if (KVM_BUG_ON(vmx->nested.nested_run_pending, vcpu->kvm))
 		return -EIO;
 
-	/* If guest state is invalid, start emulating */
-	if (vmx->emulation_required)
-		return handle_invalid_guest_state(vcpu);
-
 	if (is_guest_mode(vcpu)) {
 		/*
 		 * PML is never enabled when running L2, bail immediately if a
@@ -5914,10 +5910,30 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		 */
 		nested_mark_vmcs12_pages_dirty(vcpu);
 
+		/*
+		 * Synthesize a triple fault if L2 state is invalid.  In normal
+		 * operation, nested VM-Enter rejects any attempt to enter L2
+		 * with invalid state.  However, those checks are skipped if
+		 * state is being stuffed via RSM or KVM_SET_NESTED_STATE.  If
+		 * L2 state is invalid, it means either L1 modified SMRAM state
+		 * or userspace provided bad state.  Synthesize TRIPLE_FAULT as
+		 * doing so is architecturally allowed in the RSM case, and is
+		 * the least awful solution for the userspace case without
+		 * risking false positives.
+		 */
+		if (vmx->emulation_required) {
+			nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0);
+			return 1;
+		}
+
 		if (nested_vmx_reflect_vmexit(vcpu))
 			return 1;
 	}
 
+	/* If guest state is invalid, start emulating.  L2 is handled above. */
+	if (vmx->emulation_required)
+		return handle_invalid_guest_state(vcpu);
+
 	if (exit_reason.failed_vmentry) {
 		dump_vmcs(vcpu);
 		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
@@ -6262,9 +6278,9 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int max_irr;
-	bool max_irr_updated;
+	bool got_posted_interrupt;
 
-	if (KVM_BUG_ON(!vcpu->arch.apicv_active, vcpu->kvm))
+	if (KVM_BUG_ON(!enable_apicv, vcpu->kvm))
 		return -EIO;
 
 	if (pi_test_on(&vmx->pi_desc)) {
@@ -6274,22 +6290,33 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 		 * But on x86 this is just a compiler barrier anyway.
 		 */
 		smp_mb__after_atomic();
-		max_irr_updated =
+		got_posted_interrupt =
 			kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);
-
-		/*
-		 * If we are running L2 and L1 has a new pending interrupt
-		 * which can be injected, this may cause a vmexit or it may
-		 * be injected into L2.  Either way, this interrupt will be
-		 * processed via KVM_REQ_EVENT, not RVI, because we do not use
-		 * virtual interrupt delivery to inject L1 interrupts into L2.
-		 */
-		if (is_guest_mode(vcpu) && max_irr_updated)
-			kvm_make_request(KVM_REQ_EVENT, vcpu);
 	} else {
 		max_irr = kvm_lapic_find_highest_irr(vcpu);
+		got_posted_interrupt = false;
 	}
-	vmx_hwapic_irr_update(vcpu, max_irr);
+
+	/*
+	 * Newly recognized interrupts are injected via either virtual interrupt
+	 * delivery (RVI) or KVM_REQ_EVENT.  Virtual interrupt delivery is
+	 * disabled in two cases:
+	 *
+	 * 1) If L2 is running and the vCPU has a new pending interrupt.  If L1
+	 * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a
+	 * VM-Exit to L1.  If L1 doesn't want to exit, the interrupt is injected
+	 * into L2, but KVM doesn't use virtual interrupt delivery to inject
+	 * interrupts into L2, and so KVM_REQ_EVENT is again needed.
+	 *
+	 * 2) If APICv is disabled for this vCPU, assigned devices may still
+	 * attempt to post interrupts.  The posted interrupt vector will cause
+	 * a VM-Exit and the subsequent entry will call sync_pir_to_irr.
+	 */
+	if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu))
+		vmx_set_rvi(max_irr);
+	else if (got_posted_interrupt)
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
 	return max_irr;
 }
 
@@ -6601,9 +6628,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * consistency check VM-Exit due to invalid guest state and bail.
 	 */
 	if (unlikely(vmx->emulation_required)) {
-
-		/* We don't emulate invalid state of a nested guest */
-		vmx->fail = is_guest_mode(vcpu);
+		vmx->fail = 0;
 
 		vmx->exit_reason.full = EXIT_REASON_INVALID_STATE;
 		vmx->exit_reason.failed_vmentry = 1;
@@ -6826,6 +6851,19 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 	if (err < 0)
 		goto free_pml;
 
+	/*
+	 * Use Hyper-V 'Enlightened MSR Bitmap' feature when KVM runs as a
+	 * nested (L1) hypervisor and Hyper-V in L0 supports it. Enable the
+	 * feature only for vmcs01, KVM currently isn't equipped to realize any
+	 * performance benefits from enabling it for vmcs02.
+	 */
+	if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs) &&
+	    (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
+		struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs;
+
+		evmcs->hv_enlightenments_control.msr_bitmap = 1;
+	}
+
 	/* The MSR bitmap starts with all ones */
 	bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
 	bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
@@ -7509,6 +7547,7 @@ static void hardware_unsetup(void)
 static bool vmx_check_apicv_inhibit_reasons(ulong bit)
 {
 	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
+			  BIT(APICV_INHIBIT_REASON_ABSENT) |
 			  BIT(APICV_INHIBIT_REASON_HYPERV) |
 			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
 
@@ -7558,6 +7597,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.cache_reg = vmx_cache_reg,
 	.get_rflags = vmx_get_rflags,
 	.set_rflags = vmx_set_rflags,
+	.get_if_flag = vmx_get_if_flag,
 
 	.tlb_flush_all = vmx_flush_tlb_all,
 	.tlb_flush_current = vmx_flush_tlb_current,
@@ -7761,10 +7801,10 @@ static __init int hardware_setup(void)
 		ple_window_shrink = 0;
 	}
 
-	if (!cpu_has_vmx_apicv()) {
+	if (!cpu_has_vmx_apicv())
 		enable_apicv = 0;
+	if (!enable_apicv)
 		vmx_x86_ops.sync_pir_to_irr = NULL;
-	}
 
 	if (cpu_has_vmx_tsc_scaling()) {
 		kvm_has_tsc_control = true;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5a403d92833f..e50e97ac4408 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -890,7 +890,8 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	    !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)))
 		return 1;
 
-	if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))
+	if (!(cr0 & X86_CR0_PG) &&
+	    (is_64_bit_mode(vcpu) || kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)))
 		return 1;
 
 	static_call(kvm_x86_set_cr0)(vcpu, cr0);
@@ -1330,7 +1331,7 @@ static const u32 msrs_to_save_all[] = {
 	MSR_IA32_UMWAIT_CONTROL,
 
 	MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
-	MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3,
+	MSR_ARCH_PERFMON_FIXED_CTR0 + 2,
 	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
 	MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
 	MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1,
@@ -3258,6 +3259,29 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
 	static_call(kvm_x86_tlb_flush_guest)(vcpu);
 }
 
+
+static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+	++vcpu->stat.tlb_flush;
+	static_call(kvm_x86_tlb_flush_current)(vcpu);
+}
+
+/*
+ * Service "local" TLB flush requests, which are specific to the current MMU
+ * context.  In addition to the generic event handling in vcpu_enter_guest(),
+ * TLB flushes that are targeted at an MMU context also need to be serviced
+ * prior before nested VM-Enter/VM-Exit.
+ */
+void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu)
+{
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+		kvm_vcpu_flush_tlb_current(vcpu);
+
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
+		kvm_vcpu_flush_tlb_guest(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests);
+
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
 	struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache;
@@ -3389,7 +3413,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 		if (!msr_info->host_initiated)
 			return 1;
-		if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM) && kvm_get_msr_feature(&msr_ent))
+		if (kvm_get_msr_feature(&msr_ent))
 			return 1;
 		if (data & ~msr_ent.data)
 			return 1;
@@ -4133,6 +4157,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SGX_ATTRIBUTE:
 #endif
 	case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM:
+	case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM:
 	case KVM_CAP_SREGS2:
 	case KVM_CAP_EXIT_ON_EMULATION_FAILURE:
 	case KVM_CAP_VCPU_ATTRIBUTES:
@@ -4448,8 +4473,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
 				    struct kvm_lapic_state *s)
 {
-	if (vcpu->arch.apicv_active)
-		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+	static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 	return kvm_apic_get_state(vcpu, s);
 }
@@ -5124,6 +5148,17 @@ 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;
@@ -5134,6 +5169,14 @@ 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;
@@ -5698,6 +5741,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		smp_wmb();
 		kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT;
 		kvm->arch.nr_reserved_ioapic_pins = cap->args[0];
+		kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT);
 		r = 0;
 split_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
@@ -6078,6 +6122,7 @@ set_identity_unlock:
 		/* Write kvm->irq_routing before enabling irqchip_in_kernel. */
 		smp_wmb();
 		kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL;
+		kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT);
 	create_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
 		break;
@@ -7077,7 +7122,13 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
 			   unsigned short port, void *val, unsigned int count)
 {
 	if (vcpu->arch.pio.count) {
-		/* Complete previous iteration.  */
+		/*
+		 * Complete a previous iteration that required userspace I/O.
+		 * Note, @count isn't guaranteed to match pio.count as userspace
+		 * can modify ECX before rerunning the vCPU.  Ignore any such
+		 * shenanigans as KVM doesn't support modifying the rep count,
+		 * and the emulator ensures @count doesn't overflow the buffer.
+		 */
 	} else {
 		int r = __emulator_pio_in(vcpu, size, port, count);
 		if (!r)
@@ -7086,7 +7137,6 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
 		/* Results already available, fall through.  */
 	}
 
-	WARN_ON(count != vcpu->arch.pio.count);
 	complete_emulator_pio_in(vcpu, val);
 	return 1;
 }
@@ -8776,10 +8826,9 @@ static void kvm_apicv_init(struct kvm *kvm)
 {
 	init_rwsem(&kvm->arch.apicv_update_lock);
 
-	if (enable_apicv)
-		clear_bit(APICV_INHIBIT_REASON_DISABLE,
-			  &kvm->arch.apicv_inhibit_reasons);
-	else
+	set_bit(APICV_INHIBIT_REASON_ABSENT,
+		&kvm->arch.apicv_inhibit_reasons);
+	if (!enable_apicv)
 		set_bit(APICV_INHIBIT_REASON_DISABLE,
 			&kvm->arch.apicv_inhibit_reasons);
 }
@@ -8952,14 +9001,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *kvm_run = vcpu->run;
 
-	/*
-	 * if_flag is obsolete and useless, so do not bother
-	 * setting it for SEV-ES guests.  Userspace can just
-	 * use kvm_run->ready_for_interrupt_injection.
-	 */
-	kvm_run->if_flag = !vcpu->arch.guest_state_protected
-		&& (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
-
+	kvm_run->if_flag = static_call(kvm_x86_get_if_flag)(vcpu);
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
 
@@ -9528,8 +9570,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	if (irqchip_split(vcpu->kvm))
 		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
 	else {
-		if (vcpu->arch.apicv_active)
-			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 		if (ioapic_in_kernel(vcpu->kvm))
 			kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
 	}
@@ -9648,10 +9689,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			/* Flushing all ASIDs flushes the current ASID... */
 			kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 		}
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-			kvm_vcpu_flush_tlb_current(vcpu);
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
-			kvm_vcpu_flush_tlb_guest(vcpu);
+		kvm_service_local_tlb_flush_requests(vcpu);
 
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
@@ -9802,10 +9840,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	/*
 	 * This handles the case where a posted interrupt was
-	 * notified with kvm_vcpu_kick.
+	 * 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.
 	 */
-	if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active)
-		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+	if (kvm_lapic_enabled(vcpu))
+		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 	if (kvm_vcpu_exit_request(vcpu)) {
 		vcpu->mode = OUTSIDE_GUEST_MODE;
@@ -9849,8 +9889,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
 			break;
 
-		if (vcpu->arch.apicv_active)
-			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+		if (kvm_lapic_enabled(vcpu))
+			static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 		if (unlikely(kvm_vcpu_exit_request(vcpu))) {
 			exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 997669ae9caa..4abcd8d9836d 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -103,6 +103,7 @@ static inline unsigned int __shrink_ple_window(unsigned int val,
 
 #define MSR_IA32_CR_PAT_DEFAULT  0x0007040600070406ULL
 
+void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu);
 int kvm_check_nested_events(struct kvm_vcpu *vcpu);
 
 static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
@@ -185,12 +186,6 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
 	return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
 }
 
-static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
-{
-	++vcpu->stat.tlb_flush;
-	static_call(kvm_x86_tlb_flush_current)(vcpu);
-}
-
 static inline int is_pae(struct kvm_vcpu *vcpu)
 {
 	return kvm_read_cr4_bits(vcpu, X86_CR4_PAE);