1 files changed, 186 insertions, 149 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);