Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

10 files changed, 329 insertions, 283 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index db007a4dff..8d74bdef68 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -336,16 +336,19 @@ static int is_cpuid_PSE36(void)
 #ifdef CONFIG_X86_64
 static void __set_spte(u64 *sptep, u64 spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
 	WRITE_ONCE(*sptep, spte);
 }
 
 static void __update_clear_spte_fast(u64 *sptep, u64 spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
 	WRITE_ONCE(*sptep, spte);
 }
 
 static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(spte));
 	return xchg(sptep, spte);
 }
 
@@ -432,8 +435,8 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
  * The idea using the light way get the spte on x86_32 guest is from
  * gup_get_pte (mm/gup.c).
  *
- * An spte tlb flush may be pending, because kvm_set_pte_rmap
- * coalesces them and we are running out of the MMU lock.  Therefore
+ * An spte tlb flush may be pending, because they are coalesced and
+ * we are running out of the MMU lock.  Therefore
  * we need to protect against in-progress updates of the spte.
  *
  * Reading the spte while an update is in progress may get the old value
@@ -567,9 +570,9 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
 
 	if (!is_shadow_present_pte(old_spte) ||
 	    !spte_has_volatile_bits(old_spte))
-		__update_clear_spte_fast(sptep, 0ull);
+		__update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE);
 	else
-		old_spte = __update_clear_spte_slow(sptep, 0ull);
+		old_spte = __update_clear_spte_slow(sptep, SHADOW_NONPRESENT_VALUE);
 
 	if (!is_shadow_present_pte(old_spte))
 		return old_spte;
@@ -603,7 +606,7 @@ static u64 mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
  */
 static void mmu_spte_clear_no_track(u64 *sptep)
 {
-	__update_clear_spte_fast(sptep, 0ull);
+	__update_clear_spte_fast(sptep, SHADOW_NONPRESENT_VALUE);
 }
 
 static u64 mmu_spte_get_lockless(u64 *sptep)
@@ -831,6 +834,15 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	gfn_t gfn;
 
 	kvm->arch.indirect_shadow_pages++;
+	/*
+	 * Ensure indirect_shadow_pages is elevated prior to re-reading guest
+	 * child PTEs in FNAME(gpte_changed), i.e. guarantee either in-flight
+	 * emulated writes are visible before re-reading guest PTEs, or that
+	 * an emulated write will see the elevated count and acquire mmu_lock
+	 * to update SPTEs.  Pairs with the smp_mb() in kvm_mmu_track_write().
+	 */
+	smp_mb();
+
 	gfn = sp->gfn;
 	slots = kvm_memslots_for_spte_role(kvm, sp->role);
 	slot = __gfn_to_memslot(slots, gfn);
@@ -1448,49 +1460,11 @@ static bool __kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 }
 
 static bool kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
-			 struct kvm_memory_slot *slot, gfn_t gfn, int level,
-			 pte_t unused)
+			 struct kvm_memory_slot *slot, gfn_t gfn, int level)
 {
 	return __kvm_zap_rmap(kvm, rmap_head, slot);
 }
 
-static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
-			     struct kvm_memory_slot *slot, gfn_t gfn, int level,
-			     pte_t pte)
-{
-	u64 *sptep;
-	struct rmap_iterator iter;
-	bool need_flush = false;
-	u64 new_spte;
-	kvm_pfn_t new_pfn;
-
-	WARN_ON_ONCE(pte_huge(pte));
-	new_pfn = pte_pfn(pte);
-
-restart:
-	for_each_rmap_spte(rmap_head, &iter, sptep) {
-		need_flush = true;
-
-		if (pte_write(pte)) {
-			kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
-			goto restart;
-		} else {
-			new_spte = kvm_mmu_changed_pte_notifier_make_spte(
-					*sptep, new_pfn);
-
-			mmu_spte_clear_track_bits(kvm, sptep);
-			mmu_spte_set(sptep, new_spte);
-		}
-	}
-
-	if (need_flush && kvm_available_flush_remote_tlbs_range()) {
-		kvm_flush_remote_tlbs_gfn(kvm, gfn, level);
-		return false;
-	}
-
-	return need_flush;
-}
-
 struct slot_rmap_walk_iterator {
 	/* input fields. */
 	const struct kvm_memory_slot *slot;
@@ -1562,7 +1536,7 @@ static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator)
 
 typedef bool (*rmap_handler_t)(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 			       struct kvm_memory_slot *slot, gfn_t gfn,
-			       int level, pte_t pte);
+			       int level);
 
 static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm,
 						 struct kvm_gfn_range *range,
@@ -1574,7 +1548,7 @@ static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm,
 	for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL,
 				 range->start, range->end - 1, &iterator)
 		ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn,
-			       iterator.level, range->arg.pte);
+			       iterator.level);
 
 	return ret;
 }
@@ -1596,22 +1570,8 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 	return flush;
 }
 
-bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	bool flush = false;
-
-	if (kvm_memslots_have_rmaps(kvm))
-		flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmap);
-
-	if (tdp_mmu_enabled)
-		flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range);
-
-	return flush;
-}
-
 static bool kvm_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
-			 struct kvm_memory_slot *slot, gfn_t gfn, int level,
-			 pte_t unused)
+			 struct kvm_memory_slot *slot, gfn_t gfn, int level)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1624,8 +1584,7 @@ static bool kvm_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 }
 
 static bool kvm_test_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
-			      struct kvm_memory_slot *slot, gfn_t gfn,
-			      int level, pte_t unused)
+			      struct kvm_memory_slot *slot, gfn_t gfn, int level)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1950,7 +1909,8 @@ static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 static int kvm_sync_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i)
 {
-	if (!sp->spt[i])
+	/* sp->spt[i] has initial value of shadow page table allocation */
+	if (sp->spt[i] == SHADOW_NONPRESENT_VALUE)
 		return 0;
 
 	return vcpu->arch.mmu->sync_spte(vcpu, sp, i);
@@ -2514,7 +2474,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 				return kvm_mmu_prepare_zap_page(kvm, child,
 								invalid_list);
 		}
-	} else if (is_mmio_spte(pte)) {
+	} else if (is_mmio_spte(kvm, pte)) {
 		mmu_spte_clear_no_track(spte);
 	}
 	return 0;
@@ -3314,9 +3274,19 @@ static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu,
 {
 	gva_t gva = fault->is_tdp ? 0 : fault->addr;
 
+	if (fault->is_private) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
 	vcpu_cache_mmio_info(vcpu, gva, fault->gfn,
 			     access & shadow_mmio_access_mask);
 
+	fault->slot = NULL;
+	fault->pfn = KVM_PFN_NOSLOT;
+	fault->map_writable = false;
+	fault->hva = KVM_HVA_ERR_BAD;
+
 	/*
 	 * If MMIO caching is disabled, emulate immediately without
 	 * touching the shadow page tables as attempting to install an
@@ -4134,23 +4104,31 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level
 	return leaf;
 }
 
-/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
-static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
+static int get_sptes_lockless(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			      int *root_level)
 {
-	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
-	struct rsvd_bits_validate *rsvd_check;
-	int root, leaf, level;
-	bool reserved = false;
+	int leaf;
 
 	walk_shadow_page_lockless_begin(vcpu);
 
 	if (is_tdp_mmu_active(vcpu))
-		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
+		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, root_level);
 	else
-		leaf = get_walk(vcpu, addr, sptes, &root);
+		leaf = get_walk(vcpu, addr, sptes, root_level);
 
 	walk_shadow_page_lockless_end(vcpu);
+	return leaf;
+}
 
+/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
+static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
+{
+	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
+	struct rsvd_bits_validate *rsvd_check;
+	int root, leaf, level;
+	bool reserved = false;
+
+	leaf = get_sptes_lockless(vcpu, addr, sptes, &root);
 	if (unlikely(leaf < 0)) {
 		*sptep = 0ull;
 		return reserved;
@@ -4196,7 +4174,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 	if (WARN_ON_ONCE(reserved))
 		return -EINVAL;
 
-	if (is_mmio_spte(spte)) {
+	if (is_mmio_spte(vcpu->kvm, spte)) {
 		gfn_t gfn = get_mmio_spte_gfn(spte);
 		unsigned int access = get_mmio_spte_access(spte);
 
@@ -4259,24 +4237,28 @@ static u32 alloc_apf_token(struct kvm_vcpu *vcpu)
 	return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
 }
 
-static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
-				    gfn_t gfn)
+static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu,
+				    struct kvm_page_fault *fault)
 {
 	struct kvm_arch_async_pf arch;
 
 	arch.token = alloc_apf_token(vcpu);
-	arch.gfn = gfn;
+	arch.gfn = fault->gfn;
+	arch.error_code = fault->error_code;
 	arch.direct_map = vcpu->arch.mmu->root_role.direct;
 	arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu);
 
-	return kvm_setup_async_pf(vcpu, cr2_or_gpa,
-				  kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
+	return kvm_setup_async_pf(vcpu, fault->addr,
+				  kvm_vcpu_gfn_to_hva(vcpu, fault->gfn), &arch);
 }
 
 void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 {
 	int r;
 
+	if (WARN_ON_ONCE(work->arch.error_code & PFERR_PRIVATE_ACCESS))
+		return;
+
 	if ((vcpu->arch.mmu->root_role.direct != work->arch.direct_map) ||
 	      work->wakeup_all)
 		return;
@@ -4289,7 +4271,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	      work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu))
 		return;
 
-	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL);
+	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, work->arch.error_code, true, NULL);
 }
 
 static inline u8 kvm_max_level_for_order(int order)
@@ -4309,14 +4291,6 @@ static inline u8 kvm_max_level_for_order(int order)
 	return PG_LEVEL_4K;
 }
 
-static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
-					      struct kvm_page_fault *fault)
-{
-	kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
-				      PAGE_SIZE, fault->write, fault->exec,
-				      fault->is_private);
-}
-
 static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 				   struct kvm_page_fault *fault)
 {
@@ -4343,48 +4317,15 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 
 static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
-	struct kvm_memory_slot *slot = fault->slot;
 	bool async;
 
-	/*
-	 * Retry the page fault if the gfn hit a memslot that is being deleted
-	 * or moved.  This ensures any existing SPTEs for the old memslot will
-	 * be zapped before KVM inserts a new MMIO SPTE for the gfn.
-	 */
-	if (slot && (slot->flags & KVM_MEMSLOT_INVALID))
-		return RET_PF_RETRY;
-
-	if (!kvm_is_visible_memslot(slot)) {
-		/* Don't expose private memslots to L2. */
-		if (is_guest_mode(vcpu)) {
-			fault->slot = NULL;
-			fault->pfn = KVM_PFN_NOSLOT;
-			fault->map_writable = false;
-			return RET_PF_CONTINUE;
-		}
-		/*
-		 * If the APIC access page exists but is disabled, go directly
-		 * to emulation without caching the MMIO access or creating a
-		 * MMIO SPTE.  That way the cache doesn't need to be purged
-		 * when the AVIC is re-enabled.
-		 */
-		if (slot && slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT &&
-		    !kvm_apicv_activated(vcpu->kvm))
-			return RET_PF_EMULATE;
-	}
-
-	if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
-		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
-		return -EFAULT;
-	}
-
 	if (fault->is_private)
 		return kvm_faultin_pfn_private(vcpu, fault);
 
 	async = false;
-	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
-					  fault->write, &fault->map_writable,
-					  &fault->hva);
+	fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, false,
+					  &async, fault->write,
+					  &fault->map_writable, &fault->hva);
 	if (!async)
 		return RET_PF_CONTINUE; /* *pfn has correct page already */
 
@@ -4394,7 +4335,7 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 			trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn);
 			kvm_make_request(KVM_REQ_APF_HALT, vcpu);
 			return RET_PF_RETRY;
-		} else if (kvm_arch_setup_async_pf(vcpu, fault->addr, fault->gfn)) {
+		} else if (kvm_arch_setup_async_pf(vcpu, fault)) {
 			return RET_PF_RETRY;
 		}
 	}
@@ -4404,21 +4345,73 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * to wait for IO.  Note, gup always bails if it is unable to quickly
 	 * get a page and a fatal signal, i.e. SIGKILL, is pending.
 	 */
-	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL,
-					  fault->write, &fault->map_writable,
-					  &fault->hva);
+	fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, true,
+					  NULL, fault->write,
+					  &fault->map_writable, &fault->hva);
 	return RET_PF_CONTINUE;
 }
 
 static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 			   unsigned int access)
 {
+	struct kvm_memory_slot *slot = fault->slot;
 	int ret;
 
+	/*
+	 * Note that the mmu_invalidate_seq also serves to detect a concurrent
+	 * change in attributes.  is_page_fault_stale() will detect an
+	 * invalidation relate to fault->fn and resume the guest without
+	 * installing a mapping in the page tables.
+	 */
 	fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/*
+	 * Now that we have a snapshot of mmu_invalidate_seq we can check for a
+	 * private vs. shared mismatch.
+	 */
+	if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
+		kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+		return -EFAULT;
+	}
+
+	if (unlikely(!slot))
+		return kvm_handle_noslot_fault(vcpu, fault, access);
+
+	/*
+	 * Retry the page fault if the gfn hit a memslot that is being deleted
+	 * or moved.  This ensures any existing SPTEs for the old memslot will
+	 * be zapped before KVM inserts a new MMIO SPTE for the gfn.
+	 */
+	if (slot->flags & KVM_MEMSLOT_INVALID)
+		return RET_PF_RETRY;
+
+	if (slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) {
+		/*
+		 * Don't map L1's APIC access page into L2, KVM doesn't support
+		 * using APICv/AVIC to accelerate L2 accesses to L1's APIC,
+		 * i.e. the access needs to be emulated.  Emulating access to
+		 * L1's APIC is also correct if L1 is accelerating L2's own
+		 * virtual APIC, but for some reason L1 also maps _L1's_ APIC
+		 * into L2.  Note, vcpu_is_mmio_gpa() always treats access to
+		 * the APIC as MMIO.  Allow an MMIO SPTE to be created, as KVM
+		 * uses different roots for L1 vs. L2, i.e. there is no danger
+		 * of breaking APICv/AVIC for L1.
+		 */
+		if (is_guest_mode(vcpu))
+			return kvm_handle_noslot_fault(vcpu, fault, access);
+
+		/*
+		 * If the APIC access page exists but is disabled, go directly
+		 * to emulation without caching the MMIO access or creating a
+		 * MMIO SPTE.  That way the cache doesn't need to be purged
+		 * when the AVIC is re-enabled.
+		 */
+		if (!kvm_apicv_activated(vcpu->kvm))
+			return RET_PF_EMULATE;
+	}
+
+	/*
 	 * Check for a relevant mmu_notifier invalidation event before getting
 	 * the pfn from the primary MMU, and before acquiring mmu_lock.
 	 *
@@ -4439,8 +4432,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	 * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held
 	 * to detect retry guarantees the worst case latency for the vCPU.
 	 */
-	if (fault->slot &&
-	    mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn))
+	if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn))
 		return RET_PF_RETRY;
 
 	ret = __kvm_faultin_pfn(vcpu, fault);
@@ -4450,7 +4442,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 	if (unlikely(is_error_pfn(fault->pfn)))
 		return kvm_handle_error_pfn(vcpu, fault);
 
-	if (unlikely(!fault->slot))
+	if (WARN_ON_ONCE(!fault->slot || is_noslot_pfn(fault->pfn)))
 		return kvm_handle_noslot_fault(vcpu, fault, access);
 
 	/*
@@ -4561,6 +4553,16 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 	if (WARN_ON_ONCE(fault_address >> 32))
 		return -EFAULT;
 #endif
+	/*
+	 * Legacy #PF exception only have a 32-bit error code.  Simply drop the
+	 * upper bits as KVM doesn't use them for #PF (because they are never
+	 * set), and to ensure there are no collisions with KVM-defined bits.
+	 */
+	if (WARN_ON_ONCE(error_code >> 32))
+		error_code = lower_32_bits(error_code);
+
+	/* Ensure the above sanity check also covers KVM-defined flags. */
+	BUILD_BUG_ON(lower_32_bits(PFERR_SYNTHETIC_MASK));
 
 	vcpu->arch.l1tf_flush_l1d = true;
 	if (!flags) {
@@ -4812,7 +4814,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd);
 static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
 			   unsigned int access)
 {
-	if (unlikely(is_mmio_spte(*sptep))) {
+	if (unlikely(is_mmio_spte(vcpu->kvm, *sptep))) {
 		if (gfn != get_mmio_spte_gfn(*sptep)) {
 			mmu_spte_clear_no_track(sptep);
 			return true;
@@ -5322,6 +5324,11 @@ static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu)
 	return max_tdp_level;
 }
 
+u8 kvm_mmu_get_max_tdp_level(void)
+{
+	return tdp_root_level ? tdp_root_level : max_tdp_level;
+}
+
 static union kvm_mmu_page_role
 kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu,
 				union kvm_cpu_role cpu_role)
@@ -5802,10 +5809,15 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
 	bool flush = false;
 
 	/*
-	 * If we don't have indirect shadow pages, it means no page is
-	 * write-protected, so we can exit simply.
+	 * When emulating guest writes, ensure the written value is visible to
+	 * any task that is handling page faults before checking whether or not
+	 * KVM is shadowing a guest PTE.  This ensures either KVM will create
+	 * the correct SPTE in the page fault handler, or this task will see
+	 * a non-zero indirect_shadow_pages.  Pairs with the smp_mb() in
+	 * account_shadowed().
 	 */
-	if (!READ_ONCE(vcpu->kvm->arch.indirect_shadow_pages))
+	smp_mb();
+	if (!vcpu->kvm->arch.indirect_shadow_pages)
 		return;
 
 	write_lock(&vcpu->kvm->mmu_lock);
@@ -5846,30 +5858,35 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
 	int r, emulation_type = EMULTYPE_PF;
 	bool direct = vcpu->arch.mmu->root_role.direct;
 
-	/*
-	 * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP
-	 * checks when emulating instructions that triggers implicit access.
-	 * WARN if hardware generates a fault with an error code that collides
-	 * with the KVM-defined value.  Clear the flag and continue on, i.e.
-	 * don't terminate the VM, as KVM can't possibly be relying on a flag
-	 * that KVM doesn't know about.
-	 */
-	if (WARN_ON_ONCE(error_code & PFERR_IMPLICIT_ACCESS))
-		error_code &= ~PFERR_IMPLICIT_ACCESS;
-
 	if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa)))
 		return RET_PF_RETRY;
 
+	/*
+	 * Except for reserved faults (emulated MMIO is shared-only), set the
+	 * PFERR_PRIVATE_ACCESS flag for software-protected VMs based on the gfn's
+	 * current attributes, which are the source of truth for such VMs.  Note,
+	 * this wrong for nested MMUs as the GPA is an L2 GPA, but KVM doesn't
+	 * currently supported nested virtualization (among many other things)
+	 * for software-protected VMs.
+	 */
+	if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) &&
+	    !(error_code & PFERR_RSVD_MASK) &&
+	    vcpu->kvm->arch.vm_type == KVM_X86_SW_PROTECTED_VM &&
+	    kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)))
+		error_code |= PFERR_PRIVATE_ACCESS;
+
 	r = RET_PF_INVALID;
 	if (unlikely(error_code & PFERR_RSVD_MASK)) {
+		if (WARN_ON_ONCE(error_code & PFERR_PRIVATE_ACCESS))
+			return -EFAULT;
+
 		r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct);
 		if (r == RET_PF_EMULATE)
 			goto emulate;
 	}
 
 	if (r == RET_PF_INVALID) {
-		r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa,
-					  lower_32_bits(error_code), false,
+		r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, error_code, false,
 					  &emulation_type);
 		if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm))
 			return -EIO;
@@ -5912,6 +5929,22 @@ emulate:
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
 
+void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg)
+{
+	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
+	int root_level, leaf, level;
+
+	leaf = get_sptes_lockless(vcpu, gpa, sptes, &root_level);
+	if (unlikely(leaf < 0))
+		return;
+
+	pr_err("%s %llx", msg, gpa);
+	for (level = root_level; level >= leaf; level--)
+		pr_cont(", spte[%d] = 0x%llx", level, sptes[level]);
+	pr_cont("\n");
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_print_sptes);
+
 static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 				      u64 addr, hpa_t root_hpa)
 {
@@ -6173,7 +6206,10 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache;
 	vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO;
 
-	vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
+	vcpu->arch.mmu_shadow_page_cache.init_value =
+		SHADOW_NONPRESENT_VALUE;
+	if (!vcpu->arch.mmu_shadow_page_cache.init_value)
+		vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
 
 	vcpu->arch.mmu = &vcpu->arch.root_mmu;
 	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
@@ -6316,6 +6352,7 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
 
 void kvm_mmu_init_vm(struct kvm *kvm)
 {
+	kvm->arch.shadow_mmio_value = shadow_mmio_value;
 	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);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 5390a591a5..ce2fcd19ba 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -190,7 +190,7 @@ static inline bool is_nx_huge_page_enabled(struct kvm *kvm)
 struct kvm_page_fault {
 	/* arguments to kvm_mmu_do_page_fault.  */
 	const gpa_t addr;
-	const u32 error_code;
+	const u64 error_code;
 	const bool prefetch;
 
 	/* Derived from error_code.  */
@@ -279,8 +279,16 @@ enum {
 	RET_PF_SPURIOUS,
 };
 
+static inline void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+						     struct kvm_page_fault *fault)
+{
+	kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT,
+				      PAGE_SIZE, fault->write, fault->exec,
+				      fault->is_private);
+}
+
 static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
-					u32 err, bool prefetch, int *emulation_type)
+					u64 err, bool prefetch, int *emulation_type)
 {
 	struct kvm_page_fault fault = {
 		.addr = cr2_or_gpa,
@@ -298,7 +306,10 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 		.max_level = KVM_MAX_HUGEPAGE_LEVEL,
 		.req_level = PG_LEVEL_4K,
 		.goal_level = PG_LEVEL_4K,
-		.is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT),
+		.is_private = err & PFERR_PRIVATE_ACCESS,
+
+		.pfn = KVM_PFN_ERR_FAULT,
+		.hva = KVM_HVA_ERR_BAD,
 	};
 	int r;
 
@@ -320,6 +331,17 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	else
 		r = vcpu->arch.mmu->page_fault(vcpu, &fault);
 
+	/*
+	 * Not sure what's happening, but punt to userspace and hope that
+	 * they can fix it by changing memory to shared, or they can
+	 * provide a better error.
+	 */
+	if (r == RET_PF_EMULATE && fault.is_private) {
+		pr_warn_ratelimited("kvm: unexpected emulation request on private memory\n");
+		kvm_mmu_prepare_memory_fault_exit(vcpu, &fault);
+		return -EFAULT;
+	}
+
 	if (fault.write_fault_to_shadow_pgtable && emulation_type)
 		*emulation_type |= EMULTYPE_WRITE_PF_TO_SP;
 
diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
index ae86820cef..195d98bc8d 100644
--- a/arch/x86/kvm/mmu/mmutrace.h
+++ b/arch/x86/kvm/mmu/mmutrace.h
@@ -260,7 +260,7 @@ TRACE_EVENT(
 	TP_STRUCT__entry(
 		__field(int, vcpu_id)
 		__field(gpa_t, cr2_or_gpa)
-		__field(u32, error_code)
+		__field(u64, error_code)
 		__field(u64 *, sptep)
 		__field(u64, old_spte)
 		__field(u64, new_spte)
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index f6448284c1..561c331fd6 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -41,7 +41,7 @@ bool kvm_page_track_write_tracking_enabled(struct kvm *kvm)
 
 void kvm_page_track_free_memslot(struct kvm_memory_slot *slot)
 {
-	kvfree(slot->arch.gfn_write_track);
+	vfree(slot->arch.gfn_write_track);
 	slot->arch.gfn_write_track = NULL;
 }
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 4d4e98fe4f..d3dbcf382e 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -497,21 +497,21 @@ error:
 	 * The other bits are set to 0.
 	 */
 	if (!(errcode & PFERR_RSVD_MASK)) {
-		vcpu->arch.exit_qualification &= (EPT_VIOLATION_GVA_IS_VALID |
-						  EPT_VIOLATION_GVA_TRANSLATED);
+		walker->fault.exit_qualification = 0;
+
 		if (write_fault)
-			vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_WRITE;
+			walker->fault.exit_qualification |= EPT_VIOLATION_ACC_WRITE;
 		if (user_fault)
-			vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_READ;
+			walker->fault.exit_qualification |= EPT_VIOLATION_ACC_READ;
 		if (fetch_fault)
-			vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_INSTR;
+			walker->fault.exit_qualification |= EPT_VIOLATION_ACC_INSTR;
 
 		/*
 		 * Note, pte_access holds the raw RWX bits from the EPTE, not
 		 * ACC_*_MASK flags!
 		 */
-		vcpu->arch.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) <<
-						 EPT_VIOLATION_RWX_SHIFT;
+		walker->fault.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) <<
+						     EPT_VIOLATION_RWX_SHIFT;
 	}
 #endif
 	walker->fault.address = addr;
@@ -911,7 +911,7 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int
 	gpa_t pte_gpa;
 	gfn_t gfn;
 
-	if (WARN_ON_ONCE(!sp->spt[i]))
+	if (WARN_ON_ONCE(sp->spt[i] == SHADOW_NONPRESENT_VALUE))
 		return 0;
 
 	first_pte_gpa = FNAME(get_level1_sp_gpa)(sp);
@@ -933,13 +933,13 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int
 		return 0;
 
 	/*
-	 * Drop the SPTE if the new protections would result in a RWX=0
-	 * SPTE or if the gfn is changing.  The RWX=0 case only affects
-	 * EPT with execute-only support, i.e. EPT without an effective
-	 * "present" bit, as all other paging modes will create a
-	 * read-only SPTE if pte_access is zero.
+	 * Drop the SPTE if the new protections result in no effective
+	 * "present" bit or if the gfn is changing.  The former case
+	 * only affects EPT with execute-only support with pte_access==0;
+	 * all other paging modes will create a read-only SPTE if
+	 * pte_access is zero.
 	 */
-	if ((!pte_access && !shadow_present_mask) ||
+	if ((pte_access | shadow_present_mask) == SHADOW_NONPRESENT_VALUE ||
 	    gfn != kvm_mmu_page_get_gfn(sp, i)) {
 		drop_spte(vcpu->kvm, &sp->spt[i]);
 		return 1;
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 4a599130e9..a5e014d7bc 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -74,10 +74,10 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access)
 	u64 spte = generation_mmio_spte_mask(gen);
 	u64 gpa = gfn << PAGE_SHIFT;
 
-	WARN_ON_ONCE(!shadow_mmio_value);
+	WARN_ON_ONCE(!vcpu->kvm->arch.shadow_mmio_value);
 
 	access &= shadow_mmio_access_mask;
-	spte |= shadow_mmio_value | access;
+	spte |= vcpu->kvm->arch.shadow_mmio_value | access;
 	spte |= gpa | shadow_nonpresent_or_rsvd_mask;
 	spte |= (gpa & shadow_nonpresent_or_rsvd_mask)
 		<< SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
@@ -144,19 +144,19 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	u64 spte = SPTE_MMU_PRESENT_MASK;
 	bool wrprot = false;
 
-	WARN_ON_ONCE(!pte_access && !shadow_present_mask);
+	/*
+	 * For the EPT case, shadow_present_mask has no RWX bits set if
+	 * exec-only page table entries are supported.  In that case,
+	 * ACC_USER_MASK and shadow_user_mask are used to represent
+	 * read access.  See FNAME(gpte_access) in paging_tmpl.h.
+	 */
+	WARN_ON_ONCE((pte_access | shadow_present_mask) == SHADOW_NONPRESENT_VALUE);
 
 	if (sp->role.ad_disabled)
 		spte |= SPTE_TDP_AD_DISABLED;
 	else if (kvm_mmu_page_ad_need_write_protect(sp))
 		spte |= SPTE_TDP_AD_WRPROT_ONLY;
 
-	/*
-	 * For the EPT case, shadow_present_mask is 0 if hardware
-	 * supports exec-only page table entries.  In that case,
-	 * ACC_USER_MASK and shadow_user_mask are used to represent
-	 * read access.  See FNAME(gpte_access) in paging_tmpl.h.
-	 */
 	spte |= shadow_present_mask;
 	if (!prefetch)
 		spte |= spte_shadow_accessed_mask(spte);
@@ -322,22 +322,6 @@ u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled)
 	return spte;
 }
 
-u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn)
-{
-	u64 new_spte;
-
-	new_spte = old_spte & ~SPTE_BASE_ADDR_MASK;
-	new_spte |= (u64)new_pfn << PAGE_SHIFT;
-
-	new_spte &= ~PT_WRITABLE_MASK;
-	new_spte &= ~shadow_host_writable_mask;
-	new_spte &= ~shadow_mmu_writable_mask;
-
-	new_spte = mark_spte_for_access_track(new_spte);
-
-	return new_spte;
-}
-
 u64 mark_spte_for_access_track(u64 spte)
 {
 	if (spte_ad_enabled(spte))
@@ -429,7 +413,9 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
 	shadow_dirty_mask	= has_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull;
 	shadow_nx_mask		= 0ull;
 	shadow_x_mask		= VMX_EPT_EXECUTABLE_MASK;
-	shadow_present_mask	= has_exec_only ? 0ull : VMX_EPT_READABLE_MASK;
+	/* VMX_EPT_SUPPRESS_VE_BIT is needed for W or X violation. */
+	shadow_present_mask	=
+		(has_exec_only ? 0ull : VMX_EPT_READABLE_MASK) | VMX_EPT_SUPPRESS_VE_BIT;
 	/*
 	 * EPT overrides the host MTRRs, and so KVM must program the desired
 	 * memtype directly into the SPTEs.  Note, this mask is just the mask
@@ -446,7 +432,7 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
 	 * of an EPT paging-structure entry is 110b (write/execute).
 	 */
 	kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE,
-				   VMX_EPT_RWX_MASK, 0);
+				   VMX_EPT_RWX_MASK | VMX_EPT_SUPPRESS_VE_BIT, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_ept_masks);
 
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index a129951c9a..52fa004a1f 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -3,6 +3,8 @@
 #ifndef KVM_X86_MMU_SPTE_H
 #define KVM_X86_MMU_SPTE_H
 
+#include <asm/vmx.h>
+
 #include "mmu.h"
 #include "mmu_internal.h"
 
@@ -149,6 +151,22 @@ static_assert(MMIO_SPTE_GEN_LOW_BITS == 8 && MMIO_SPTE_GEN_HIGH_BITS == 11);
 
 #define MMIO_SPTE_GEN_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)
 
+/*
+ * Non-present SPTE value needs to set bit 63 for TDX, in order to suppress
+ * #VE and get EPT violations on non-present PTEs.  We can use the
+ * same value also without TDX for both VMX and SVM:
+ *
+ * For SVM NPT, for non-present spte (bit 0 = 0), other bits are ignored.
+ * For VMX EPT, bit 63 is ignored if #VE is disabled. (EPT_VIOLATION_VE=0)
+ *              bit 63 is #VE suppress if #VE is enabled. (EPT_VIOLATION_VE=1)
+ */
+#ifdef CONFIG_X86_64
+#define SHADOW_NONPRESENT_VALUE	BIT_ULL(63)
+static_assert(!(SHADOW_NONPRESENT_VALUE & SPTE_MMU_PRESENT_MASK));
+#else
+#define SHADOW_NONPRESENT_VALUE	0ULL
+#endif
+
 extern u64 __read_mostly shadow_host_writable_mask;
 extern u64 __read_mostly shadow_mmu_writable_mask;
 extern u64 __read_mostly shadow_nx_mask;
@@ -190,11 +208,11 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
  *
  * Use a semi-arbitrary value that doesn't set RWX bits, i.e. is not-present on
  * both AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF
- * vulnerability.  Use only low bits to avoid 64-bit immediates.
+ * vulnerability.
  *
  * Only used by the TDP MMU.
  */
-#define REMOVED_SPTE	0x5a0ULL
+#define REMOVED_SPTE	(SHADOW_NONPRESENT_VALUE | 0x5a0ULL)
 
 /* Removed SPTEs must not be misconstrued as shadow present PTEs. */
 static_assert(!(REMOVED_SPTE & SPTE_MMU_PRESENT_MASK));
@@ -249,9 +267,9 @@ static inline struct kvm_mmu_page *root_to_sp(hpa_t root)
 	return spte_to_child_sp(root);
 }
 
-static inline bool is_mmio_spte(u64 spte)
+static inline bool is_mmio_spte(struct kvm *kvm, u64 spte)
 {
-	return (spte & shadow_mmio_mask) == shadow_mmio_value &&
+	return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value &&
 	       likely(enable_mmio_caching);
 }
 
@@ -260,6 +278,13 @@ static inline bool is_shadow_present_pte(u64 pte)
 	return !!(pte & SPTE_MMU_PRESENT_MASK);
 }
 
+static inline bool is_ept_ve_possible(u64 spte)
+{
+	return (shadow_present_mask & VMX_EPT_SUPPRESS_VE_BIT) &&
+	       !(spte & VMX_EPT_SUPPRESS_VE_BIT) &&
+	       (spte & VMX_EPT_RWX_MASK) != VMX_EPT_MISCONFIG_WX_VALUE;
+}
+
 /*
  * Returns true if A/D bits are supported in hardware and are enabled by KVM.
  * When enabled, KVM uses A/D bits for all non-nested MMUs.  Because L1 can
@@ -496,8 +521,6 @@ static inline u64 restore_acc_track_spte(u64 spte)
 	return spte;
 }
 
-u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte, kvm_pfn_t new_pfn);
-
 void __init kvm_mmu_spte_module_init(void);
 void kvm_mmu_reset_all_pte_masks(void);
 
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index fae559559a..2880fd392e 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -21,11 +21,13 @@ static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep)
 
 static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
 	return xchg(rcu_dereference(sptep), new_spte);
 }
 
 static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
 {
+	KVM_MMU_WARN_ON(is_ept_ve_possible(new_spte));
 	WRITE_ONCE(*rcu_dereference(sptep), new_spte);
 }
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 04c1f0957f..36539c1b36 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -495,8 +495,8 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 		 * impact the guest since both the former and current SPTEs
 		 * are nonpresent.
 		 */
-		if (WARN_ON_ONCE(!is_mmio_spte(old_spte) &&
-				 !is_mmio_spte(new_spte) &&
+		if (WARN_ON_ONCE(!is_mmio_spte(kvm, old_spte) &&
+				 !is_mmio_spte(kvm, new_spte) &&
 				 !is_removed_spte(new_spte)))
 			pr_err("Unexpected SPTE change! Nonpresent SPTEs\n"
 			       "should not be replaced with another,\n"
@@ -530,6 +530,31 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 		kvm_set_pfn_accessed(spte_to_pfn(old_spte));
 }
 
+static inline int __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, u64 new_spte)
+{
+	u64 *sptep = rcu_dereference(iter->sptep);
+
+	/*
+	 * The caller is responsible for ensuring the old SPTE is not a REMOVED
+	 * SPTE.  KVM should never attempt to zap or manipulate a REMOVED SPTE,
+	 * and pre-checking before inserting a new SPTE is advantageous as it
+	 * avoids unnecessary work.
+	 */
+	WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte));
+
+	/*
+	 * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and
+	 * does not hold the mmu_lock.  On failure, i.e. if a different logical
+	 * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with
+	 * the current value, so the caller operates on fresh data, e.g. if it
+	 * retries tdp_mmu_set_spte_atomic()
+	 */
+	if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte))
+		return -EBUSY;
+
+	return 0;
+}
+
 /*
  * tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically
  * and handle the associated bookkeeping.  Do not mark the page dirty
@@ -551,27 +576,13 @@ static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm,
 					  struct tdp_iter *iter,
 					  u64 new_spte)
 {
-	u64 *sptep = rcu_dereference(iter->sptep);
-
-	/*
-	 * The caller is responsible for ensuring the old SPTE is not a REMOVED
-	 * SPTE.  KVM should never attempt to zap or manipulate a REMOVED SPTE,
-	 * and pre-checking before inserting a new SPTE is advantageous as it
-	 * avoids unnecessary work.
-	 */
-	WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte));
+	int ret;
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
-	/*
-	 * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and
-	 * does not hold the mmu_lock.  On failure, i.e. if a different logical
-	 * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with
-	 * the current value, so the caller operates on fresh data, e.g. if it
-	 * retries tdp_mmu_set_spte_atomic()
-	 */
-	if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte))
-		return -EBUSY;
+	ret = __tdp_mmu_set_spte_atomic(iter, new_spte);
+	if (ret)
+		return ret;
 
 	handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
 			    new_spte, iter->level, true);
@@ -584,13 +595,17 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
 {
 	int ret;
 
+	lockdep_assert_held_read(&kvm->mmu_lock);
+
 	/*
-	 * Freeze the SPTE by setting it to a special,
-	 * non-present value. This will stop other threads from
-	 * immediately installing a present entry in its place
-	 * before the TLBs are flushed.
+	 * Freeze the SPTE by setting it to a special, non-present value. This
+	 * will stop other threads from immediately installing a present entry
+	 * in its place before the TLBs are flushed.
+	 *
+	 * Delay processing of the zapped SPTE until after TLBs are flushed and
+	 * the REMOVED_SPTE is replaced (see below).
 	 */
-	ret = tdp_mmu_set_spte_atomic(kvm, iter, REMOVED_SPTE);
+	ret = __tdp_mmu_set_spte_atomic(iter, REMOVED_SPTE);
 	if (ret)
 		return ret;
 
@@ -599,11 +614,19 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm,
 	/*
 	 * No other thread can overwrite the removed SPTE as they must either
 	 * wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not
-	 * overwrite the special removed SPTE value. No bookkeeping is needed
-	 * here since the SPTE is going from non-present to non-present.  Use
-	 * the raw write helper to avoid an unnecessary check on volatile bits.
+	 * overwrite the special removed SPTE value. Use the raw write helper to
+	 * avoid an unnecessary check on volatile bits.
 	 */
-	__kvm_tdp_mmu_write_spte(iter->sptep, 0);
+	__kvm_tdp_mmu_write_spte(iter->sptep, SHADOW_NONPRESENT_VALUE);
+
+	/*
+	 * Process the zapped SPTE after flushing TLBs, and after replacing
+	 * REMOVED_SPTE with 0. This minimizes the amount of time vCPUs are
+	 * blocked by the REMOVED_SPTE and reduces contention on the child
+	 * SPTEs.
+	 */
+	handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+			    SHADOW_NONPRESENT_VALUE, iter->level, true);
 
 	return 0;
 }
@@ -740,8 +763,8 @@ retry:
 			continue;
 
 		if (!shared)
-			tdp_mmu_iter_set_spte(kvm, &iter, 0);
-		else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0))
+			tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
+		else if (tdp_mmu_set_spte_atomic(kvm, &iter, SHADOW_NONPRESENT_VALUE))
 			goto retry;
 	}
 }
@@ -808,8 +831,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 	if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte)))
 		return false;
 
-	tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0,
-			 sp->gfn, sp->role.level + 1);
+	tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte,
+			 SHADOW_NONPRESENT_VALUE, sp->gfn, sp->role.level + 1);
 
 	return true;
 }
@@ -843,7 +866,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
 		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
 
-		tdp_mmu_iter_set_spte(kvm, &iter, 0);
+		tdp_mmu_iter_set_spte(kvm, &iter, SHADOW_NONPRESENT_VALUE);
 
 		/*
 		 * Zappings SPTEs in invalid roots doesn't require a TLB flush,
@@ -1028,7 +1051,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
 	}
 
 	/* If a MMIO SPTE is installed, the MMIO will need to be emulated. */
-	if (unlikely(is_mmio_spte(new_spte))) {
+	if (unlikely(is_mmio_spte(vcpu->kvm, new_spte))) {
 		vcpu->stat.pf_mmio_spte_created++;
 		trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn,
 				     new_spte);
@@ -1258,52 +1281,6 @@ bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	return kvm_tdp_mmu_handle_gfn(kvm, range, test_age_gfn);
 }
 
-static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter,
-			 struct kvm_gfn_range *range)
-{
-	u64 new_spte;
-
-	/* Huge pages aren't expected to be modified without first being zapped. */
-	WARN_ON_ONCE(pte_huge(range->arg.pte) || range->start + 1 != range->end);
-
-	if (iter->level != PG_LEVEL_4K ||
-	    !is_shadow_present_pte(iter->old_spte))
-		return false;
-
-	/*
-	 * Note, when changing a read-only SPTE, it's not strictly necessary to
-	 * zero the SPTE before setting the new PFN, but doing so preserves the
-	 * invariant that the PFN of a present * leaf SPTE can never change.
-	 * See handle_changed_spte().
-	 */
-	tdp_mmu_iter_set_spte(kvm, iter, 0);
-
-	if (!pte_write(range->arg.pte)) {
-		new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte,
-								  pte_pfn(range->arg.pte));
-
-		tdp_mmu_iter_set_spte(kvm, iter, new_spte);
-	}
-
-	return true;
-}
-
-/*
- * Handle the changed_pte MMU notifier for the TDP MMU.
- * data is a pointer to the new pte_t mapping the HVA specified by the MMU
- * notifier.
- * Returns non-zero if a flush is needed before releasing the MMU lock.
- */
-bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
-{
-	/*
-	 * No need to handle the remote TLB flush under RCU protection, the
-	 * target SPTE _must_ be a leaf SPTE, i.e. cannot result in freeing a
-	 * shadow page. See the WARN on pfn_changed in handle_changed_spte().
-	 */
-	return kvm_tdp_mmu_handle_gfn(kvm, range, set_spte_gfn);
-}
-
 /*
  * Remove write access from all SPTEs at or above min_level that map GFNs
  * [start, end). Returns true if an SPTE has been changed and the TLBs need to
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 6e1ea04ca8..58b55e61bd 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -31,7 +31,6 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 				 bool flush);
 bool kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
-bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
 
 bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm,
 			     const struct kvm_memory_slot *slot, int min_level);