Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 2ce9da5..d3877dd 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -343,6 +343,8 @@
 {
 	BUG_ON((u64)(unsigned)access_mask != access_mask);
 	BUG_ON((mmio_mask & mmio_value) != mmio_value);
+	WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len));
+	WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);
 	shadow_mmio_value = mmio_value | SPTE_MMIO_MASK;
 	shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK;
 	shadow_mmio_access_mask = access_mask;
@@ -405,11 +407,11 @@
 }
 
 /*
- * Due to limited space in PTEs, the MMIO generation is a 19 bit subset of
+ * Due to limited space in PTEs, the MMIO generation is a 18 bit subset of
  * the memslots generation and is derived as follows:
  *
  * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11
- * Bits 9-18 of the MMIO generation are propagated to spte bits 52-61
+ * Bits 9-17 of the MMIO generation are propagated to spte bits 54-62
  *
  * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in
  * the MMIO generation number, as doing so would require stealing a bit from
@@ -418,25 +420,38 @@
  * requires a full MMU zap).  The flag is instead explicitly queried when
  * checking for MMIO spte cache hits.
  */
-#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(18, 0)
 
 #define MMIO_SPTE_GEN_LOW_START		3
 #define MMIO_SPTE_GEN_LOW_END		11
+
+#define MMIO_SPTE_GEN_HIGH_START	PT64_SECOND_AVAIL_BITS_SHIFT
+#define MMIO_SPTE_GEN_HIGH_END		62
+
 #define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
 						    MMIO_SPTE_GEN_LOW_START)
-
-#define MMIO_SPTE_GEN_HIGH_START	52
-#define MMIO_SPTE_GEN_HIGH_END		61
 #define MMIO_SPTE_GEN_HIGH_MASK		GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \
 						    MMIO_SPTE_GEN_HIGH_START)
+
+#define MMIO_SPTE_GEN_LOW_BITS		(MMIO_SPTE_GEN_LOW_END - MMIO_SPTE_GEN_LOW_START + 1)
+#define MMIO_SPTE_GEN_HIGH_BITS		(MMIO_SPTE_GEN_HIGH_END - MMIO_SPTE_GEN_HIGH_START + 1)
+
+/* remember to adjust the comment above as well if you change these */
+static_assert(MMIO_SPTE_GEN_LOW_BITS == 9 && MMIO_SPTE_GEN_HIGH_BITS == 9);
+
+#define MMIO_SPTE_GEN_LOW_SHIFT		(MMIO_SPTE_GEN_LOW_START - 0)
+#define MMIO_SPTE_GEN_HIGH_SHIFT	(MMIO_SPTE_GEN_HIGH_START - MMIO_SPTE_GEN_LOW_BITS)
+
+#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)
+
 static u64 generation_mmio_spte_mask(u64 gen)
 {
 	u64 mask;
 
 	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
+	BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK);
 
-	mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK;
-	mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK;
+	mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK;
+	mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK;
 	return mask;
 }
 
@@ -444,10 +459,8 @@
 {
 	u64 gen;
 
-	spte &= ~shadow_mmio_mask;
-
-	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START;
-	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START;
+	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_SHIFT;
+	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_SHIFT;
 	return gen;
 }
 
@@ -538,16 +551,20 @@
 static u8 kvm_get_shadow_phys_bits(void)
 {
 	/*
-	 * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected
-	 * in CPU detection code, but MKTME treats those reduced bits as
-	 * 'keyID' thus they are not reserved bits. Therefore for MKTME
-	 * we should still return physical address bits reported by CPUID.
+	 * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected
+	 * in CPU detection code, but the processor treats those reduced bits as
+	 * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at
+	 * the physical address bits reported by CPUID.
 	 */
-	if (!boot_cpu_has(X86_FEATURE_TME) ||
-	    WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008))
-		return boot_cpu_data.x86_phys_bits;
+	if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008))
+		return cpuid_eax(0x80000008) & 0xff;
 
-	return cpuid_eax(0x80000008) & 0xff;
+	/*
+	 * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with
+	 * custom CPUID.  Proceed with whatever the kernel found since these features
+	 * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008).
+	 */
+	return boot_cpu_data.x86_phys_bits;
 }
 
 static void kvm_mmu_reset_all_pte_masks(void)
@@ -576,16 +593,15 @@
 	 * the most significant bits of legal physical address space.
 	 */
 	shadow_nonpresent_or_rsvd_mask = 0;
-	low_phys_bits = boot_cpu_data.x86_cache_bits;
-	if (boot_cpu_data.x86_cache_bits <
-	    52 - shadow_nonpresent_or_rsvd_mask_len) {
+	low_phys_bits = boot_cpu_data.x86_phys_bits;
+	if (boot_cpu_has_bug(X86_BUG_L1TF) &&
+	    !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >=
+			  52 - shadow_nonpresent_or_rsvd_mask_len)) {
+		low_phys_bits = boot_cpu_data.x86_cache_bits
+			- shadow_nonpresent_or_rsvd_mask_len;
 		shadow_nonpresent_or_rsvd_mask =
-			rsvd_bits(boot_cpu_data.x86_cache_bits -
-				  shadow_nonpresent_or_rsvd_mask_len,
-				  boot_cpu_data.x86_cache_bits - 1);
-		low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
-	} else
-		WARN_ON_ONCE(boot_cpu_has_bug(X86_BUG_L1TF));
+			rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1);
+	}
 
 	shadow_nonpresent_or_rsvd_lower_gfn_mask =
 		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
@@ -1282,12 +1298,12 @@
 	return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
 }
 
-static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
+static int host_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	unsigned long page_size;
 	int i, ret = 0;
 
-	page_size = kvm_host_page_size(kvm, gfn);
+	page_size = kvm_host_page_size(vcpu, gfn);
 
 	for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
 		if (page_size >= KVM_HPAGE_SIZE(i))
@@ -1337,7 +1353,7 @@
 	if (unlikely(*force_pt_level))
 		return PT_PAGE_TABLE_LEVEL;
 
-	host_level = host_mapping_level(vcpu->kvm, large_gfn);
+	host_level = host_mapping_level(vcpu, large_gfn);
 
 	if (host_level == PT_PAGE_TABLE_LEVEL)
 		return host_level;
@@ -1814,10 +1830,10 @@
  * Emulate arch specific page modification logging for the
  * nested hypervisor
  */
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa)
 {
 	if (kvm_x86_ops->write_log_dirty)
-		return kvm_x86_ops->write_log_dirty(vcpu);
+		return kvm_x86_ops->write_log_dirty(vcpu, l2_gpa);
 
 	return 0;
 }
@@ -2040,7 +2056,8 @@
 	return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
 }
 
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
+			unsigned flags)
 {
 	return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
 }
@@ -2126,7 +2143,7 @@
  * aggregate version in order to make the slab shrinker
  * faster
  */
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
 {
 	kvm->arch.n_used_mmu_pages += nr;
 	percpu_counter_add(&kvm_total_used_mmu_pages, nr);
@@ -2226,13 +2243,6 @@
 {
 }
 
-static void nonpaging_update_pte(struct kvm_vcpu *vcpu,
-				 struct kvm_mmu_page *sp, u64 *spte,
-				 const void *pte)
-{
-	WARN_ON(1);
-}
-
 #define KVM_PAGE_ARRAY_NR 16
 
 struct kvm_mmu_pages {
@@ -3528,7 +3538,7 @@
  * - true: let the vcpu to access on the same address again.
  * - false: let the real page fault path to fix it.
  */
-static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
+static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int level,
 			    u32 error_code)
 {
 	struct kvm_shadow_walk_iterator iterator;
@@ -3548,7 +3558,7 @@
 	do {
 		u64 new_spte;
 
-		for_each_shadow_entry_lockless(vcpu, gva, iterator, spte)
+		for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte)
 			if (!is_shadow_present_pte(spte) ||
 			    iterator.level < level)
 				break;
@@ -3626,7 +3636,7 @@
 
 	} while (true);
 
-	trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep,
+	trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep,
 			      spte, fault_handled);
 	walk_shadow_page_lockless_end(vcpu);
 
@@ -3634,10 +3644,11 @@
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable);
+			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
+			 bool *writable);
 static int make_mmu_pages_available(struct kvm_vcpu *vcpu);
 
-static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
+static int nonpaging_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			 gfn_t gfn, bool prefault)
 {
 	int r;
@@ -3663,16 +3674,16 @@
 		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
 	}
 
-	if (fast_page_fault(vcpu, v, level, error_code))
+	if (fast_page_fault(vcpu, gpa, level, error_code))
 		return RET_PF_RETRY;
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
-	if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable))
+	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
 		return RET_PF_RETRY;
 
-	if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r))
+	if (handle_abnormal_pfn(vcpu, gpa, gfn, pfn, ACC_ALL, &r))
 		return r;
 
 	r = RET_PF_RETRY;
@@ -3683,7 +3694,7 @@
 		goto out_unlock;
 	if (likely(!force_pt_level))
 		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
-	r = __direct_map(vcpu, v, write, map_writable, level, pfn,
+	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
 			 prefault, false);
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
@@ -3981,7 +3992,7 @@
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);
 
-static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				  u32 access, struct x86_exception *exception)
 {
 	if (exception)
@@ -3989,7 +4000,7 @@
 	return vaddr;
 }
 
-static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr,
 					 u32 access,
 					 struct x86_exception *exception)
 {
@@ -4149,13 +4160,14 @@
 	walk_shadow_page_lockless_end(vcpu);
 }
 
-static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
+static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa,
 				u32 error_code, bool prefault)
 {
-	gfn_t gfn = gva >> PAGE_SHIFT;
+	gfn_t gfn = gpa >> PAGE_SHIFT;
 	int r;
 
-	pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
+	/* Note, paging is disabled, ergo gva == gpa. */
+	pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code);
 
 	if (page_fault_handle_page_track(vcpu, error_code, gfn))
 		return RET_PF_EMULATE;
@@ -4167,11 +4179,12 @@
 	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
 
 
-	return nonpaging_map(vcpu, gva & PAGE_MASK,
+	return nonpaging_map(vcpu, gpa & PAGE_MASK,
 			     error_code, gfn, prefault);
 }
 
-static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
+static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+				   gfn_t gfn)
 {
 	struct kvm_arch_async_pf arch;
 
@@ -4180,11 +4193,13 @@
 	arch.direct_map = vcpu->arch.mmu->direct_map;
 	arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu);
 
-	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
+	return kvm_setup_async_pf(vcpu, cr2_or_gpa,
+				  kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable)
+			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
+			 bool *writable)
 {
 	struct kvm_memory_slot *slot;
 	bool async;
@@ -4204,12 +4219,12 @@
 		return false; /* *pfn has correct page already */
 
 	if (!prefault && kvm_can_do_async_pf(vcpu)) {
-		trace_kvm_try_async_get_page(gva, gfn);
+		trace_kvm_try_async_get_page(cr2_or_gpa, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
-			trace_kvm_async_pf_doublefault(gva, gfn);
+			trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn);
 			kvm_make_request(KVM_REQ_APF_HALT, vcpu);
 			return true;
-		} else if (kvm_arch_setup_async_pf(vcpu, gva, gfn))
+		} else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn))
 			return true;
 	}
 
@@ -4222,6 +4237,12 @@
 {
 	int r = 1;
 
+#ifndef CONFIG_X86_64
+	/* A 64-bit CR2 should be impossible on 32-bit KVM. */
+	if (WARN_ON_ONCE(fault_address >> 32))
+		return -EFAULT;
+#endif
+
 	vcpu->arch.l1tf_flush_l1d = true;
 	switch (vcpu->arch.apf.host_apf_reason) {
 	default:
@@ -4259,7 +4280,7 @@
 	return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num);
 }
 
-static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
+static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			  bool prefault)
 {
 	kvm_pfn_t pfn;
@@ -4328,7 +4349,6 @@
 	context->gva_to_gpa = nonpaging_gva_to_gpa;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
-	context->update_pte = nonpaging_update_pte;
 	context->root_level = 0;
 	context->shadow_root_level = PT32E_ROOT_LEVEL;
 	context->direct_map = true;
@@ -4564,7 +4584,7 @@
 			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | gbpages_bit_rsvd |
+			gbpages_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
@@ -4646,7 +4666,15 @@
 void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 {
-	bool uses_nx = context->nx ||
+	/*
+	 * KVM uses NX when TDP is disabled to handle a variety of scenarios,
+	 * notably for huge SPTEs if iTLB multi-hit mitigation is enabled and
+	 * to generate correct permissions for CR0.WP=0/CR4.SMEP=1/EFER.NX=0.
+	 * The iTLB multi-hit workaround can be toggled at any time, so assume
+	 * NX can be used by any non-nested shadow MMU to avoid having to reset
+	 * MMU contexts.  Note, KVM forces EFER.NX=1 when TDP is disabled.
+	 */
+	bool uses_nx = context->nx || !tdp_enabled ||
 		context->mmu_role.base.smep_andnot_wp;
 	struct rsvd_bits_validate *shadow_zero_check;
 	int i;
@@ -4907,7 +4935,6 @@
 	context->gva_to_gpa = paging64_gva_to_gpa;
 	context->sync_page = paging64_sync_page;
 	context->invlpg = paging64_invlpg;
-	context->update_pte = paging64_update_pte;
 	context->shadow_root_level = level;
 	context->direct_map = false;
 }
@@ -4936,7 +4963,6 @@
 	context->gva_to_gpa = paging32_gva_to_gpa;
 	context->sync_page = paging32_sync_page;
 	context->invlpg = paging32_invlpg;
-	context->update_pte = paging32_update_pte;
 	context->shadow_root_level = PT32E_ROOT_LEVEL;
 	context->direct_map = false;
 }
@@ -5011,7 +5037,6 @@
 	context->page_fault = tdp_page_fault;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
-	context->update_pte = nonpaging_update_pte;
 	context->shadow_root_level = kvm_x86_ops->get_tdp_level(vcpu);
 	context->direct_map = true;
 	context->set_cr3 = kvm_x86_ops->set_tdp_cr3;
@@ -5144,7 +5169,6 @@
 	context->gva_to_gpa = ept_gva_to_gpa;
 	context->sync_page = ept_sync_page;
 	context->invlpg = ept_invlpg;
-	context->update_pte = ept_update_pte;
 	context->root_level = PT64_ROOT_4LEVEL;
 	context->direct_map = false;
 	context->mmu_role.as_u64 = new_role.as_u64;
@@ -5284,19 +5308,6 @@
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unload);
 
-static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
-				  struct kvm_mmu_page *sp, u64 *spte,
-				  const void *new)
-{
-	if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
-		++vcpu->kvm->stat.mmu_pde_zapped;
-		return;
-        }
-
-	++vcpu->kvm->stat.mmu_pte_updated;
-	vcpu->arch.mmu->update_pte(vcpu, sp, spte, new);
-}
-
 static bool need_remote_flush(u64 old, u64 new)
 {
 	if (!is_shadow_present_pte(old))
@@ -5462,14 +5473,10 @@
 
 		local_flush = true;
 		while (npte--) {
-			u32 base_role = vcpu->arch.mmu->mmu_role.base.word;
-
 			entry = *spte;
 			mmu_page_zap_pte(vcpu->kvm, sp, spte);
-			if (gentry &&
-			      !((sp->role.word ^ base_role)
-			      & mmu_base_role_mask.word) && rmap_can_add(vcpu))
-				mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
+			if (gentry && sp->role.level != PG_LEVEL_4K)
+				++vcpu->kvm->stat.mmu_pde_zapped;
 			if (need_remote_flush(entry, *spte))
 				remote_flush = true;
 			++spte;
@@ -5516,7 +5523,7 @@
 	return 0;
 }
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len)
 {
 	int r, emulation_type = 0;
@@ -5525,18 +5532,18 @@
 	/* With shadow page tables, fault_address contains a GVA or nGPA.  */
 	if (vcpu->arch.mmu->direct_map) {
 		vcpu->arch.gpa_available = true;
-		vcpu->arch.gpa_val = cr2;
+		vcpu->arch.gpa_val = cr2_or_gpa;
 	}
 
 	r = RET_PF_INVALID;
 	if (unlikely(error_code & PFERR_RSVD_MASK)) {
-		r = handle_mmio_page_fault(vcpu, cr2, direct);
+		r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct);
 		if (r == RET_PF_EMULATE)
 			goto emulate;
 	}
 
 	if (r == RET_PF_INVALID) {
-		r = vcpu->arch.mmu->page_fault(vcpu, cr2,
+		r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa,
 					       lower_32_bits(error_code),
 					       false);
 		WARN_ON(r == RET_PF_INVALID);
@@ -5556,7 +5563,7 @@
 	 */
 	if (vcpu->arch.mmu->direct_map &&
 	    (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
-		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
+		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa));
 		return 1;
 	}
 
@@ -5571,7 +5578,7 @@
 	 * explicitly shadowing L1's page tables, i.e. unprotecting something
 	 * for L1 isn't going to magically fix whatever issue cause L2 to fail.
 	 */
-	if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu))
+	if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu))
 		emulation_type = EMULTYPE_ALLOW_RETRY;
 emulate:
 	/*
@@ -5586,7 +5593,7 @@
 			return 1;
 	}
 
-	return x86_emulate_instruction(vcpu, cr2, emulation_type, insn,
+	return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn,
 				       insn_len);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
@@ -6232,25 +6239,16 @@
 	u64 mask;
 
 	/*
-	 * Set the reserved bits and the present bit of an paging-structure
-	 * entry to generate page fault with PFER.RSV = 1.
+	 * Set a reserved PA bit in MMIO SPTEs to generate page faults with
+	 * PFEC.RSVD=1 on MMIO accesses.  64-bit PTEs (PAE, x86-64, and EPT
+	 * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports
+	 * 52-bit physical addresses then there are no reserved PA bits in the
+	 * PTEs and so the reserved PA approach must be disabled.
 	 */
-
-	/*
-	 * Mask the uppermost physical address bit, which would be reserved as
-	 * long as the supported physical address width is less than 52.
-	 */
-	mask = 1ull << 51;
-
-	/* Set the present bit. */
-	mask |= 1ull;
-
-	/*
-	 * If reserved bit is not supported, clear the present bit to disable
-	 * mmio page fault.
-	 */
-	if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52)
-		mask &= ~1ull;
+	if (shadow_phys_bits < 52)
+		mask = BIT_ULL(51) | PT_PRESENT_MASK;
+	else
+		mask = 0;
 
 	kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);
 }
@@ -6445,6 +6443,7 @@
 				cond_resched_lock(&kvm->mmu_lock);
 		}
 	}
+	kvm_mmu_commit_zap_page(kvm, &invalid_list);
 
 	spin_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, rcu_idx);