Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull more KVM updates from Paolo Bonzini:
 "x86:

   - take into account HVA before retrying on MMU notifier race

   - fixes for nested AMD guests without NPT

   - allow INVPCID in guest without PCID

   - disable PML in hardware when not in use

   - MMU code cleanups:

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (28 commits)
  KVM: SVM: Fix nested VM-Exit on #GP interception handling
  KVM: vmx/pmu: Fix dummy check if lbr_desc->event is created
  KVM: x86/mmu: Consider the hva in mmu_notifier retry
  KVM: x86/mmu: Skip mmu_notifier check when handling MMIO page fault
  KVM: Documentation: rectify rst markup in KVM_GET_SUPPORTED_HV_CPUID
  KVM: nSVM: prepare guest save area while is_guest_mode is true
  KVM: x86/mmu: Remove a variety of unnecessary exports
  KVM: x86: Fold "write-protect large" use case into generic write-protect
  KVM: x86/mmu: Don't set dirty bits when disabling dirty logging w/ PML
  KVM: VMX: Dynamically enable/disable PML based on memslot dirty logging
  KVM: x86: Further clarify the logic and comments for toggling log dirty
  KVM: x86: Move MMU's PML logic to common code
  KVM: x86/mmu: Make dirty log size hook (PML) a value, not a function
  KVM: x86/mmu: Expand on the comment in kvm_vcpu_ad_need_write_protect()
  KVM: nVMX: Disable PML in hardware when running L2
  KVM: x86/mmu: Consult max mapping level when zapping collapsible SPTEs
  KVM: x86/mmu: Pass the memslot to the rmap callbacks
  KVM: x86/mmu: Split out max mapping level calculation to helper
  KVM: x86/mmu: Expand collapsible SPTE zap for TDP MMU to ZONE_DEVICE and HugeTLB pages
  KVM: nVMX: no need to undo inject_page_fault change on nested vmexit
  ...

Documentation/virt/kvm/api.rst

@@ -4519,6 +4519,7 @@ KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature
 leaves (0x40000000, 0x40000001).
 
 Currently, the following list of CPUID leaves are returned:
+
  - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS
  - HYPERV_CPUID_INTERFACE
  - HYPERV_CPUID_VERSION
@@ -4543,6 +4544,7 @@ userspace should not expect to get any particular value there.
 Note, vcpu version of KVM_GET_SUPPORTED_HV_CPUID is currently deprecated. Unlike
 system ioctl which exposes all supported feature bits unconditionally, vcpu
 version has the following quirks:
+
 - HYPERV_CPUID_NESTED_FEATURES leaf and HV_X64_ENLIGHTENED_VMCS_RECOMMENDED
   feature bit are only exposed when Enlightened VMCS was previously enabled
   on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -591,7 +591,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
 	} else {
 		/* Call KVM generic code to do the slow-path check */
 		pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
-					   writing, &write_ok);
+					   writing, &write_ok, NULL);
 		if (is_error_noslot_pfn(pfn))
 			return -EFAULT;
 		page = NULL;

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -822,7 +822,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 
 		/* Call KVM generic code to do the slow-path check */
 		pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
-					   writing, upgrade_p);
+					   writing, upgrade_p, NULL);
 		if (is_error_noslot_pfn(pfn))
 			return -EFAULT;
 		page = NULL;

arch/x86/include/asm/kvm-x86-ops.h

@@ -93,11 +93,7 @@ KVM_X86_OP(check_intercept)
 KVM_X86_OP(handle_exit_irqoff)
 KVM_X86_OP_NULL(request_immediate_exit)
 KVM_X86_OP(sched_in)
-KVM_X86_OP_NULL(slot_enable_log_dirty)
-KVM_X86_OP_NULL(slot_disable_log_dirty)
-KVM_X86_OP_NULL(flush_log_dirty)
-KVM_X86_OP_NULL(enable_log_dirty_pt_masked)
-KVM_X86_OP_NULL(cpu_dirty_log_size)
+KVM_X86_OP_NULL(update_cpu_dirty_logging)
 KVM_X86_OP_NULL(pre_block)
 KVM_X86_OP_NULL(post_block)
 KVM_X86_OP_NULL(vcpu_blocking)

arch/x86/include/asm/kvm_host.h

@@ -89,6 +89,8 @@
 	KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_APF_READY		KVM_ARCH_REQ(28)
 #define KVM_REQ_MSR_FILTER_CHANGED	KVM_ARCH_REQ(29)
+#define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \
+	KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -1007,6 +1009,7 @@ struct kvm_arch {
 	u32 bsp_vcpu_id;
 
 	u64 disabled_quirks;
+	int cpu_dirty_logging_count;
 
 	enum kvm_irqchip_mode irqchip_mode;
 	u8 nr_reserved_ioapic_pins;
@@ -1271,30 +1274,11 @@ struct kvm_x86_ops {
 	void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
 
 	/*
-	 * Arch-specific dirty logging hooks. These hooks are only supposed to
-	 * be valid if the specific arch has hardware-accelerated dirty logging
-	 * mechanism. Currently only for PML on VMX.
-	 *
-	 *  - slot_enable_log_dirty:
-	 *	called when enabling log dirty mode for the slot.
-	 *  - slot_disable_log_dirty:
-	 *	called when disabling log dirty mode for the slot.
-	 *	also called when slot is created with log dirty disabled.
-	 *  - flush_log_dirty:
-	 *	called before reporting dirty_bitmap to userspace.
-	 *  - enable_log_dirty_pt_masked:
-	 *	called when reenabling log dirty for the GFNs in the mask after
-	 *	corresponding bits are cleared in slot->dirty_bitmap.
+	 * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer.  A zero
+	 * value indicates CPU dirty logging is unsupported or disabled.
 	 */
-	void (*slot_enable_log_dirty)(struct kvm *kvm,
-				      struct kvm_memory_slot *slot);
-	void (*slot_disable_log_dirty)(struct kvm *kvm,
-				       struct kvm_memory_slot *slot);
-	void (*flush_log_dirty)(struct kvm *kvm);
-	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
-					   struct kvm_memory_slot *slot,
-					   gfn_t offset, unsigned long mask);
-	int (*cpu_dirty_log_size)(void);
+	int cpu_dirty_log_size;
+	void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
@@ -1437,11 +1421,6 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot);
 void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
 					struct kvm_memory_slot *memslot);
-void kvm_mmu_slot_set_dirty(struct kvm *kvm,
-			    struct kvm_memory_slot *memslot);
-void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
-				   struct kvm_memory_slot *slot,
-				   gfn_t gfn_offset, unsigned long mask);
 void kvm_mmu_zap_all(struct kvm *kvm);
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
 unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
@@ -1613,7 +1592,6 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 void kvm_update_dr7(struct kvm_vcpu *vcpu);
 
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
-int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);

arch/x86/kvm/cpuid.c

@@ -408,7 +408,7 @@ void kvm_set_cpu_caps(void)
 
 	kvm_cpu_cap_mask(CPUID_7_0_EBX,
 		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
-		F(BMI2) | F(ERMS) | 0 /*INVPCID*/ | F(RTM) | 0 /*MPX*/ | F(RDSEED) |
+		F(BMI2) | F(ERMS) | F(INVPCID) | F(RTM) | 0 /*MPX*/ | F(RDSEED) |
 		F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) |
 		F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) |
 		F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/

arch/x86/kvm/mmu/mmu.c

@@ -1165,7 +1165,8 @@ static bool spte_wrprot_for_clear_dirty(u64 *sptep)
  *	- W bit on ad-disabled SPTEs.
  * Returns true iff any D or W bits were cleared.
  */
-static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
+static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
+			       struct kvm_memory_slot *slot)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1180,35 +1181,6 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
 	return flush;
 }
 
-static bool spte_set_dirty(u64 *sptep)
-{
-	u64 spte = *sptep;
-
-	rmap_printk("spte %p %llx\n", sptep, *sptep);
-
-	/*
-	 * Similar to the !kvm_x86_ops.slot_disable_log_dirty case,
-	 * do not bother adding back write access to pages marked
-	 * SPTE_AD_WRPROT_ONLY_MASK.
-	 */
-	spte |= shadow_dirty_mask;
-
-	return mmu_spte_update(sptep, spte);
-}
-
-static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
-{
-	u64 *sptep;
-	struct rmap_iterator iter;
-	bool flush = false;
-
-	for_each_rmap_spte(rmap_head, &iter, sptep)
-		if (spte_ad_enabled(*sptep))
-			flush |= spte_set_dirty(sptep);
-
-	return flush;
-}
-
 /**
  * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages
  * @kvm: kvm instance
@@ -1248,9 +1220,9 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
  *
  * Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap.
  */
-void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
-				     struct kvm_memory_slot *slot,
-				     gfn_t gfn_offset, unsigned long mask)
+static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
+					 struct kvm_memory_slot *slot,
+					 gfn_t gfn_offset, unsigned long mask)
 {
 	struct kvm_rmap_head *rmap_head;
 
@@ -1260,13 +1232,12 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 	while (mask) {
 		rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
 					  PG_LEVEL_4K, slot);
-		__rmap_clear_dirty(kvm, rmap_head);
+		__rmap_clear_dirty(kvm, rmap_head, slot);
 
 		/* clear the first set bit */
 		mask &= mask - 1;
 	}
 }
-EXPORT_SYMBOL_GPL(kvm_mmu_clear_dirty_pt_masked);
 
 /**
  * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected
@@ -1282,20 +1253,15 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 				struct kvm_memory_slot *slot,
 				gfn_t gfn_offset, unsigned long mask)
 {
-	if (kvm_x86_ops.enable_log_dirty_pt_masked)
-		static_call(kvm_x86_enable_log_dirty_pt_masked)(kvm, slot,
-								gfn_offset,
-								mask);
+	if (kvm_x86_ops.cpu_dirty_log_size)
+		kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask);
 	else
 		kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
 }
 
 int kvm_cpu_dirty_log_size(void)
 {
-	if (kvm_x86_ops.cpu_dirty_log_size)
-		return static_call(kvm_x86_cpu_dirty_log_size)();
-
-	return 0;
+	return kvm_x86_ops.cpu_dirty_log_size;
 }
 
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
@@ -1325,7 +1291,8 @@ static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
 	return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn);
 }
 
-static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
+static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
+			  struct kvm_memory_slot *slot)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1345,7 +1312,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 			   struct kvm_memory_slot *slot, gfn_t gfn, int level,
 			   unsigned long data)
 {
-	return kvm_zap_rmapp(kvm, rmap_head);
+	return kvm_zap_rmapp(kvm, rmap_head, slot);
 }
 
 static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
@@ -2499,7 +2466,21 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 
 	return r;
 }
-EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
+
+static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
+{
+	gpa_t gpa;
+	int r;
+
+	if (vcpu->arch.mmu->direct_map)
+		return 0;
+
+	gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
+
+	r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+
+	return r;
+}
 
 static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
@@ -2753,11 +2734,18 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 	if (sp->role.level > PG_LEVEL_4K)
 		return;
 
+	/*
+	 * If addresses are being invalidated, skip prefetching to avoid
+	 * accidentally prefetching those addresses.
+	 */
+	if (unlikely(vcpu->kvm->mmu_notifier_count))
+		return;
+
 	__direct_pte_prefetch(vcpu, sp, sptep);
 }
 
-static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn,
-				  kvm_pfn_t pfn, struct kvm_memory_slot *slot)
+static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
+				  struct kvm_memory_slot *slot)
 {
 	unsigned long hva;
 	pte_t *pte;
@@ -2776,19 +2764,36 @@ static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn,
 	 */
 	hva = __gfn_to_hva_memslot(slot, gfn);
 
-	pte = lookup_address_in_mm(vcpu->kvm->mm, hva, &level);
+	pte = lookup_address_in_mm(kvm->mm, hva, &level);
 	if (unlikely(!pte))
 		return PG_LEVEL_4K;
 
 	return level;
 }
 
+int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_memory_slot *slot,
+			      gfn_t gfn, kvm_pfn_t pfn, int max_level)
+{
+	struct kvm_lpage_info *linfo;
+
+	max_level = min(max_level, max_huge_page_level);
+	for ( ; max_level > PG_LEVEL_4K; max_level--) {
+		linfo = lpage_info_slot(gfn, slot, max_level);
+		if (!linfo->disallow_lpage)
+			break;
+	}
+
+	if (max_level == PG_LEVEL_4K)
+		return PG_LEVEL_4K;
+
+	return host_pfn_mapping_level(kvm, gfn, pfn, slot);
+}
+
 int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
 			    int max_level, kvm_pfn_t *pfnp,
 			    bool huge_page_disallowed, int *req_level)
 {
 	struct kvm_memory_slot *slot;
-	struct kvm_lpage_info *linfo;
 	kvm_pfn_t pfn = *pfnp;
 	kvm_pfn_t mask;
 	int level;
@@ -2805,17 +2810,7 @@ int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
 	if (!slot)
 		return PG_LEVEL_4K;
 
-	max_level = min(max_level, max_huge_page_level);
-	for ( ; max_level > PG_LEVEL_4K; max_level--) {
-		linfo = lpage_info_slot(gfn, slot, max_level);
-		if (!linfo->disallow_lpage)
-			break;
-	}
-
-	if (max_level == PG_LEVEL_4K)
-		return PG_LEVEL_4K;
-
-	level = host_pfn_mapping_level(vcpu, gfn, pfn, slot);
+	level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, gfn, pfn, max_level);
 	if (level == PG_LEVEL_4K)
 		return level;
 
@@ -3437,7 +3432,6 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 	kvm_mmu_audit(vcpu, AUDIT_POST_SYNC);
 	write_unlock(&vcpu->kvm->mmu_lock);
 }
-EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);
 
 static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				  u32 access, struct x86_exception *exception)
@@ -3653,8 +3647,8 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
-			 bool *writable)
+			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, hva_t *hva,
+			 bool write, bool *writable)
 {
 	struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 	bool async;
@@ -3667,7 +3661,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	}
 
 	async = false;
-	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable);
+	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async,
+				    write, writable, hva);
 	if (!async)
 		return false; /* *pfn has correct page already */
 
@@ -3681,7 +3676,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 			return true;
 	}
 
-	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable);
+	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL,
+				    write, writable, hva);
 	return false;
 }
 
@@ -3694,6 +3690,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	unsigned long mmu_seq;
 	kvm_pfn_t pfn;
+	hva_t hva;
 	int r;
 
 	if (page_fault_handle_page_track(vcpu, error_code, gfn))
@@ -3712,7 +3709,8 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
-	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
+	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, &hva,
+			 write, &map_writable))
 		return RET_PF_RETRY;
 
 	if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r))
@@ -3725,7 +3723,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	else
 		write_lock(&vcpu->kvm->mmu_lock);
 
-	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
+	if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva))
 		goto out_unlock;
 	r = make_mmu_pages_available(vcpu);
 	if (r)
@@ -5003,22 +5001,6 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	write_unlock(&vcpu->kvm->mmu_lock);
 }
 
-int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
-{
-	gpa_t gpa;
-	int r;
-
-	if (vcpu->arch.mmu->direct_map)
-		return 0;
-
-	gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
-
-	r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
-
-	return r;
-}
-EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt);
-
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len)
 {
@@ -5117,7 +5099,6 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		mmu->invlpg(vcpu, gva, root_hpa);
 	}
 }
-EXPORT_SYMBOL_GPL(kvm_mmu_invalidate_gva);
 
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
 {
@@ -5157,7 +5138,6 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid)
 	 * for them.
 	 */
 }
-EXPORT_SYMBOL_GPL(kvm_mmu_invpcid_gva);
 
 void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level,
 		       int tdp_huge_page_level)
@@ -5182,7 +5162,8 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level,
 EXPORT_SYMBOL_GPL(kvm_configure_mmu);
 
 /* The return value indicates if tlb flush on all vcpus is needed. */
-typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);
+typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head,
+				    struct kvm_memory_slot *slot);
 
 /* The caller should hold mmu-lock before calling this function. */
 static __always_inline bool
@@ -5196,7 +5177,7 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn,
 			end_gfn, &iterator) {
 		if (iterator.rmap)
-			flush |= fn(kvm, iterator.rmap);
+			flush |= fn(kvm, iterator.rmap, memslot);
 
 		if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
 			if (flush && lock_flush_tlb) {
@@ -5229,22 +5210,6 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			lock_flush_tlb);
 }
 
-static __always_inline bool
-slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
-		      slot_level_handler fn, bool lock_flush_tlb)
-{
-	return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K,
-				 KVM_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
-}
-
-static __always_inline bool
-slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
-			slot_level_handler fn, bool lock_flush_tlb)
-{
-	return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K + 1,
-				 KVM_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
-}
-
 static __always_inline bool
 slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		 slot_level_handler fn, bool lock_flush_tlb)
@@ -5485,7 +5450,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 }
 
 static bool slot_rmap_write_protect(struct kvm *kvm,
-				    struct kvm_rmap_head *rmap_head)
+				    struct kvm_rmap_head *rmap_head,
+				    struct kvm_memory_slot *slot)
 {
 	return __rmap_write_protect(kvm, rmap_head, false);
 }
@@ -5519,7 +5485,8 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
 }
 
 static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
-					 struct kvm_rmap_head *rmap_head)
+					 struct kvm_rmap_head *rmap_head,
+					 struct kvm_memory_slot *slot)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -5540,8 +5507,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 		 * mapping if the indirect sp has level = 1.
 		 */
 		if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
-		    (kvm_is_zone_device_pfn(pfn) ||
-		     PageCompound(pfn_to_page(pfn)))) {
+		    sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
+							       pfn, PG_LEVEL_NUM)) {
 			pte_list_remove(rmap_head, sptep);
 
 			if (kvm_available_flush_tlb_with_range())
@@ -5561,12 +5528,13 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 				   const struct kvm_memory_slot *memslot)
 {
 	/* FIXME: const-ify all uses of struct kvm_memory_slot.  */
+	struct kvm_memory_slot *slot = (struct kvm_memory_slot *)memslot;
+
 	write_lock(&kvm->mmu_lock);
-	slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot,
-			 kvm_mmu_zap_collapsible_spte, true);
+	slot_handle_leaf(kvm, slot, kvm_mmu_zap_collapsible_spte, true);
 
 	if (is_tdp_mmu_enabled(kvm))
-		kvm_tdp_mmu_zap_collapsible_sptes(kvm, memslot);
+		kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot);
 	write_unlock(&kvm->mmu_lock);
 }
 
@@ -5605,40 +5573,6 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 	if (flush)
 		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
 }
-EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty);
-
-void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
-					struct kvm_memory_slot *memslot)
-{
-	bool flush;
-
-	write_lock(&kvm->mmu_lock);
-	flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect,
-					false);
-	if (is_tdp_mmu_enabled(kvm))
-		flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_2M);
-	write_unlock(&kvm->mmu_lock);
-
-	if (flush)
-		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
-}
-EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access);
-
-void kvm_mmu_slot_set_dirty(struct kvm *kvm,
-			    struct kvm_memory_slot *memslot)
-{
-	bool flush;
-
-	write_lock(&kvm->mmu_lock);
-	flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false);
-	if (is_tdp_mmu_enabled(kvm))
-		flush |= kvm_tdp_mmu_slot_set_dirty(kvm, memslot);
-	write_unlock(&kvm->mmu_lock);
-
-	if (flush)
-		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
-}
-EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty);
 
 void kvm_mmu_zap_all(struct kvm *kvm)
 {

arch/x86/kvm/mmu/mmu_internal.h

@@ -84,7 +84,10 @@ static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
 	 * When using the EPT page-modification log, the GPAs in the log
 	 * would come from L2 rather than L1.  Therefore, we need to rely
 	 * on write protection to record dirty pages.  This also bypasses
-	 * PML, since writes now result in a vmexit.
+	 * PML, since writes now result in a vmexit.  Note, this helper will
+	 * tag SPTEs as needing write-protection even if PML is disabled or
+	 * unsupported, but that's ok because the tag is consumed if and only
+	 * if PML is enabled.  Omit the PML check to save a few uops.
 	 */
 	return vcpu->arch.mmu == &vcpu->arch.guest_mmu;
 }
@@ -138,6 +141,8 @@ enum {
 #define SET_SPTE_NEED_REMOTE_TLB_FLUSH	BIT(1)
 #define SET_SPTE_SPURIOUS		BIT(2)
 
+int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_memory_slot *slot,
+			      gfn_t gfn, kvm_pfn_t pfn, int max_level);
 int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
 			    int max_level, kvm_pfn_t *pfnp,
 			    bool huge_page_disallowed, int *req_level);

arch/x86/kvm/mmu/paging_tmpl.h

@@ -601,6 +601,13 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 	if (sp->role.level > PG_LEVEL_4K)
 		return;
 
+	/*
+	 * If addresses are being invalidated, skip prefetching to avoid
+	 * accidentally prefetching those addresses.
+	 */
+	if (unlikely(vcpu->kvm->mmu_notifier_count))
+		return;
+
 	if (sp->role.direct)
 		return __direct_pte_prefetch(vcpu, sp, sptep);
 
@@ -790,6 +797,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 	struct guest_walker walker;
 	int r;
 	kvm_pfn_t pfn;
+	hva_t hva;
 	unsigned long mmu_seq;
 	bool map_writable, is_self_change_mapping;
 	int max_level;
@@ -840,8 +848,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
-	if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, write_fault,
-			 &map_writable))
+	if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, &hva,
+			 write_fault, &map_writable))
 		return RET_PF_RETRY;
 
 	if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r))
@@ -869,7 +877,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 
 	r = RET_PF_RETRY;
 	write_lock(&vcpu->kvm->mmu_lock);
-	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
+	if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva))
 		goto out_unlock;
 
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);

arch/x86/kvm/mmu/tdp_mmu.c

@@ -1268,68 +1268,16 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 	}
 }
 
-/*
- * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is
- * only used for PML, and so will involve setting the dirty bit on each SPTE.
- * Returns true if an SPTE has been changed and the TLBs need to be flushed.
- */
-static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
-				gfn_t start, gfn_t end)
-{
-	struct tdp_iter iter;
-	u64 new_spte;
-	bool spte_set = false;
-
-	rcu_read_lock();
-
-	tdp_root_for_each_pte(iter, root, start, end) {
-		if (tdp_mmu_iter_cond_resched(kvm, &iter, false))
-			continue;
-
-		if (!is_shadow_present_pte(iter.old_spte) ||
-		    iter.old_spte & shadow_dirty_mask)
-			continue;
-
-		new_spte = iter.old_spte | shadow_dirty_mask;
-
-		tdp_mmu_set_spte(kvm, &iter, new_spte);
-		spte_set = true;
-	}
-
-	rcu_read_unlock();
-	return spte_set;
-}
-
-/*
- * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is
- * only used for PML, and so will involve setting the dirty bit on each SPTE.
- * Returns true if an SPTE has been changed and the TLBs need to be flushed.
- */
-bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot)
-{
-	struct kvm_mmu_page *root;
-	int root_as_id;
-	bool spte_set = false;
-
-	for_each_tdp_mmu_root_yield_safe(kvm, root) {
-		root_as_id = kvm_mmu_page_as_id(root);
-		if (root_as_id != slot->as_id)
-			continue;
-
-		spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn,
-				slot->base_gfn + slot->npages);
-	}
-	return spte_set;
-}
-
 /*
  * Clear leaf entries which could be replaced by large mappings, for
  * GFNs within the slot.
  */
 static void zap_collapsible_spte_range(struct kvm *kvm,
 				       struct kvm_mmu_page *root,
-				       gfn_t start, gfn_t end)
+				       struct kvm_memory_slot *slot)
 {
+	gfn_t start = slot->base_gfn;
+	gfn_t end = start + slot->npages;
 	struct tdp_iter iter;
 	kvm_pfn_t pfn;
 	bool spte_set = false;
@@ -1348,7 +1296,8 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
 
 		pfn = spte_to_pfn(iter.old_spte);
 		if (kvm_is_reserved_pfn(pfn) ||
-		    !PageTransCompoundMap(pfn_to_page(pfn)))
+		    iter.level >= kvm_mmu_max_mapping_level(kvm, slot, iter.gfn,
+							    pfn, PG_LEVEL_NUM))
 			continue;
 
 		tdp_mmu_set_spte(kvm, &iter, 0);
@@ -1366,7 +1315,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
  * be replaced by large mappings, for GFNs within the slot.
  */
 void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot)
+				       struct kvm_memory_slot *slot)
 {
 	struct kvm_mmu_page *root;
 	int root_as_id;
@@ -1376,8 +1325,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
 		if (root_as_id != slot->as_id)
 			continue;
 
-		zap_collapsible_spte_range(kvm, root, slot->base_gfn,
-					   slot->base_gfn + slot->npages);
+		zap_collapsible_spte_range(kvm, root, slot);
 	}
 }
 

arch/x86/kvm/mmu/tdp_mmu.h

@@ -33,9 +33,8 @@ 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_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot);
+				       struct kvm_memory_slot *slot);
 
 bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn);

arch/x86/kvm/svm/nested.c

@@ -51,6 +51,23 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
 	nested_svm_vmexit(svm);
 }
 
+static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_exception *fault)
+{
+       struct vcpu_svm *svm = to_svm(vcpu);
+       WARN_ON(!is_guest_mode(vcpu));
+
+       if (vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) &&
+	   !svm->nested.nested_run_pending) {
+               svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR;
+               svm->vmcb->control.exit_code_hi = 0;
+               svm->vmcb->control.exit_info_1 = fault->error_code;
+               svm->vmcb->control.exit_info_2 = fault->address;
+               nested_svm_vmexit(svm);
+       } else {
+               kvm_inject_page_fault(vcpu, fault);
+       }
+}
+
 static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -436,16 +453,33 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa,
 {
 	int ret;
 
+	trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb12_gpa,
+			       vmcb12->save.rip,
+			       vmcb12->control.int_ctl,
+			       vmcb12->control.event_inj,
+			       vmcb12->control.nested_ctl);
+
+	trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff,
+				    vmcb12->control.intercepts[INTERCEPT_CR] >> 16,
+				    vmcb12->control.intercepts[INTERCEPT_EXCEPTION],
+				    vmcb12->control.intercepts[INTERCEPT_WORD3],
+				    vmcb12->control.intercepts[INTERCEPT_WORD4],
+				    vmcb12->control.intercepts[INTERCEPT_WORD5]);
+
+
 	svm->nested.vmcb12_gpa = vmcb12_gpa;
 	load_nested_vmcb_control(svm, &vmcb12->control);
-	nested_prepare_vmcb_save(svm, vmcb12);
 	nested_prepare_vmcb_control(svm);
+	nested_prepare_vmcb_save(svm, vmcb12);
 
 	ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3,
 				  nested_npt_enabled(svm));
 	if (ret)
 		return ret;
 
+	if (!npt_enabled)
+		svm->vcpu.arch.mmu->inject_page_fault = svm_inject_page_fault_nested;
+
 	svm_set_gif(svm, true);
 
 	return 0;
@@ -489,18 +523,6 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
 		goto out;
 	}
 
-	trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb12_gpa,
-			       vmcb12->save.rip,
-			       vmcb12->control.int_ctl,
-			       vmcb12->control.event_inj,
-			       vmcb12->control.nested_ctl);
-
-	trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff,
-				    vmcb12->control.intercepts[INTERCEPT_CR] >> 16,
-				    vmcb12->control.intercepts[INTERCEPT_EXCEPTION],
-				    vmcb12->control.intercepts[INTERCEPT_WORD3],
-				    vmcb12->control.intercepts[INTERCEPT_WORD4],
-				    vmcb12->control.intercepts[INTERCEPT_WORD5]);
 
 	/* Clear internal status */
 	kvm_clear_exception_queue(&svm->vcpu);

arch/x86/kvm/svm/svm.c

@@ -926,9 +926,6 @@ static __init void svm_set_cpu_caps(void)
 	if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
 	    boot_cpu_has(X86_FEATURE_AMD_SSBD))
 		kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD);
-
-	/* Enable INVPCID feature */
-	kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID);
 }
 
 static __init int svm_hardware_setup(void)
@@ -1103,12 +1100,12 @@ static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 static void svm_check_invpcid(struct vcpu_svm *svm)
 {
 	/*
-	 * Intercept INVPCID instruction only if shadow page table is
-	 * enabled. Interception is not required with nested page table
-	 * enabled.
+	 * Intercept INVPCID if shadow paging is enabled to sync/free shadow
+	 * roots, or if INVPCID is disabled in the guest to inject #UD.
 	 */
 	if (kvm_cpu_cap_has(X86_FEATURE_INVPCID)) {
-		if (!npt_enabled)
+		if (!npt_enabled ||
+		    !guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID))
 			svm_set_intercept(svm, INTERCEPT_INVPCID);
 		else
 			svm_clr_intercept(svm, INTERCEPT_INVPCID);
@@ -2214,15 +2211,20 @@ static int emulate_svm_instr(struct kvm_vcpu *vcpu, int opcode)
 		[SVM_INSTR_VMSAVE] = vmsave_interception,
 	};
 	struct vcpu_svm *svm = to_svm(vcpu);
+	int ret;
 
 	if (is_guest_mode(vcpu)) {
 		svm->vmcb->control.exit_code = guest_mode_exit_codes[opcode];
 		svm->vmcb->control.exit_info_1 = 0;
 		svm->vmcb->control.exit_info_2 = 0;
 
-		return nested_svm_vmexit(svm);
-	} else
-		return svm_instr_handlers[opcode](svm);
+		/* Returns '1' or -errno on failure, '0' on success. */
+		ret = nested_svm_vmexit(svm);
+		if (ret)
+			return ret;
+		return 1;
+	}
+	return svm_instr_handlers[opcode](svm);
 }
 
 /*

arch/x86/kvm/vmx/nested.c

@@ -2167,15 +2167,13 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
 		vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
 
 	/*
-	 * The PML address never changes, so it is constant in vmcs02.
-	 * Conceptually we want to copy the PML index from vmcs01 here,
-	 * and then back to vmcs01 on nested vmexit.  But since we flush
-	 * the log and reset GUEST_PML_INDEX on each vmexit, the PML
-	 * index is also effectively constant in vmcs02.
+	 * PML is emulated for L2, but never enabled in hardware as the MMU
+	 * handles A/D emulation.  Disabling PML for L2 also avoids having to
+	 * deal with filtering out L2 GPAs from the buffer.
 	 */
 	if (enable_pml) {
-		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
-		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+		vmcs_write64(PML_ADDRESS, 0);
+		vmcs_write16(GUEST_PML_INDEX, -1);
 	}
 
 	if (cpu_has_vmx_encls_vmexit())
@@ -2210,7 +2208,7 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx,
 
 static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 {
-	u32 exec_control, vmcs12_exec_ctrl;
+	u32 exec_control;
 	u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12);
 
 	if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs)
@@ -2284,11 +2282,11 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 				  SECONDARY_EXEC_APIC_REGISTER_VIRT |
 				  SECONDARY_EXEC_ENABLE_VMFUNC);
 		if (nested_cpu_has(vmcs12,
-				   CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) {
-			vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control &
-				~SECONDARY_EXEC_ENABLE_PML;
-			exec_control |= vmcs12_exec_ctrl;
-		}
+				   CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
+			exec_control |= vmcs12->secondary_vm_exec_control;
+
+		/* PML is emulated and never enabled in hardware for L2. */
+		exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
 
 		/* VMCS shadowing for L2 is emulated for now */
 		exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;
@@ -4200,9 +4198,6 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &ignored))
 		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
 
-	if (!enable_ept)
-		vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
-
 	nested_vmx_transition_tlb_flush(vcpu, vmcs12, false);
 
 	vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
@@ -4495,6 +4490,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		vmx_set_virtual_apic_mode(vcpu);
 	}
 
+	if (vmx->nested.update_vmcs01_cpu_dirty_logging) {
+		vmx->nested.update_vmcs01_cpu_dirty_logging = false;
+		vmx_update_cpu_dirty_logging(vcpu);
+	}
+
 	/* Unpin physical memory we referred to in vmcs02 */
 	if (vmx->nested.apic_access_page) {
 		kvm_release_page_clean(vmx->nested.apic_access_page);
@@ -5793,7 +5793,10 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 	case EXIT_REASON_PREEMPTION_TIMER:
 		return true;
 	case EXIT_REASON_PML_FULL:
-		/* We emulate PML support to L1. */
+		/*
+		 * PML is emulated for an L1 VMM and should never be enabled in
+		 * vmcs02, always "handle" PML_FULL by exiting to userspace.
+		 */
 		return true;
 	case EXIT_REASON_VMFUNC:
 		/* VM functions are emulated through L2->L0 vmexits. */

arch/x86/kvm/vmx/pmu_intel.c

@@ -298,7 +298,7 @@ int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu)
 	if (IS_ERR(event)) {
 		pr_debug_ratelimited("%s: failed %ld\n",
 					__func__, PTR_ERR(event));
-		return -ENOENT;
+		return PTR_ERR(event);
 	}
 	lbr_desc->event = event;
 	pmu->event_count++;
@@ -320,7 +320,7 @@ static bool intel_pmu_handle_lbr_msrs_access(struct kvm_vcpu *vcpu,
 	if (!intel_pmu_is_valid_lbr_msr(vcpu, index))
 		return false;
 
-	if (!lbr_desc->event && !intel_pmu_create_guest_lbr_event(vcpu))
+	if (!lbr_desc->event && intel_pmu_create_guest_lbr_event(vcpu) < 0)
 		goto dummy;
 
 	/*

arch/x86/kvm/vmx/vmx.c

@@ -4277,7 +4277,12 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 	*/
 	exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;
 
-	if (!enable_pml)
+	/*
+	 * PML is enabled/disabled when dirty logging of memsmlots changes, but
+	 * it needs to be set here when dirty logging is already active, e.g.
+	 * if this vCPU was created after dirty logging was enabled.
+	 */
+	if (!vcpu->kvm->arch.cpu_dirty_logging_count)
 		exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
 
 	if (cpu_has_vmx_xsaves()) {
@@ -4295,18 +4300,8 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 	}
 
 	vmx_adjust_sec_exec_feature(vmx, &exec_control, rdtscp, RDTSCP);
-
-	/*
-	 * Expose INVPCID if and only if PCID is also exposed to the guest.
-	 * INVPCID takes a #UD when it's disabled in the VMCS, but a #GP or #PF
-	 * if CR4.PCIDE=0.  Enumerating CPUID.INVPCID=1 would lead to incorrect
-	 * behavior from the guest perspective (it would expect #GP or #PF).
-	 */
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID))
-		guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID);
 	vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID);
 
-
 	vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND);
 	vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdseed, RDSEED);
 
@@ -5776,24 +5771,6 @@ static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu)
 	vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
 }
 
-/*
- * Flush all vcpus' PML buffer and update logged GPAs to dirty_bitmap.
- * Called before reporting dirty_bitmap to userspace.
- */
-static void kvm_flush_pml_buffers(struct kvm *kvm)
-{
-	int i;
-	struct kvm_vcpu *vcpu;
-	/*
-	 * We only need to kick vcpu out of guest mode here, as PML buffer
-	 * is flushed at beginning of all VMEXITs, and it's obvious that only
-	 * vcpus running in guest are possible to have unflushed GPAs in PML
-	 * buffer.
-	 */
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_vcpu_kick(vcpu);
-}
-
 static void vmx_dump_sel(char *name, uint32_t sel)
 {
 	pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n",
@@ -5976,9 +5953,10 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	 * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before
 	 * querying dirty_bitmap, we only need to kick all vcpus out of guest
 	 * mode as if vcpus is in root mode, the PML buffer must has been
-	 * flushed already.
+	 * flushed already.  Note, PML is never enabled in hardware while
+	 * running L2.
 	 */
-	if (enable_pml)
+	if (enable_pml && !is_guest_mode(vcpu))
 		vmx_flush_pml_buffer(vcpu);
 
 	/*
@@ -5994,6 +5972,13 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		return handle_invalid_guest_state(vcpu);
 
 	if (is_guest_mode(vcpu)) {
+		/*
+		 * PML is never enabled when running L2, bail immediately if a
+		 * PML full exit occurs as something is horribly wrong.
+		 */
+		if (exit_reason.basic == EXIT_REASON_PML_FULL)
+			goto unexpected_vmexit;
+
 		/*
 		 * The host physical addresses of some pages of guest memory
 		 * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC
@@ -6851,13 +6836,15 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY))
 		kvm_machine_check();
 
+	if (likely(!vmx->exit_reason.failed_vmentry))
+		vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
+
 	trace_kvm_exit(vmx->exit_reason.full, vcpu, KVM_ISA_VMX);
 
 	if (unlikely(vmx->exit_reason.failed_vmentry))
 		return EXIT_FASTPATH_NONE;
 
 	vmx->loaded_vmcs->launched = 1;
-	vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
 
 	vmx_recover_nmi_blocking(vmx);
 	vmx_complete_interrupts(vmx);
@@ -7330,8 +7317,8 @@ static __init void vmx_set_cpu_caps(void)
 	/* CPUID 0x7 */
 	if (kvm_mpx_supported())
 		kvm_cpu_cap_check_and_set(X86_FEATURE_MPX);
-	if (cpu_has_vmx_invpcid())
-		kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID);
+	if (!cpu_has_vmx_invpcid())
+		kvm_cpu_cap_clear(X86_FEATURE_INVPCID);
 	if (vmx_pt_mode_is_host_guest())
 		kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT);
 
@@ -7509,30 +7496,24 @@ static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
 		shrink_ple_window(vcpu);
 }
 
-static void vmx_slot_enable_log_dirty(struct kvm *kvm,
-				     struct kvm_memory_slot *slot)
+void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
 {
-	if (!kvm_dirty_log_manual_protect_and_init_set(kvm))
-		kvm_mmu_slot_leaf_clear_dirty(kvm, slot);
-	kvm_mmu_slot_largepage_remove_write_access(kvm, slot);
-}
-
-static void vmx_slot_disable_log_dirty(struct kvm *kvm,
-				       struct kvm_memory_slot *slot)
-{
-	kvm_mmu_slot_set_dirty(kvm, slot);
-}
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-static void vmx_flush_log_dirty(struct kvm *kvm)
-{
-	kvm_flush_pml_buffers(kvm);
-}
+	if (is_guest_mode(vcpu)) {
+		vmx->nested.update_vmcs01_cpu_dirty_logging = true;
+		return;
+	}
 
-static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
-					   struct kvm_memory_slot *memslot,
-					   gfn_t offset, unsigned long mask)
-{
-	kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
+	/*
+	 * Note, cpu_dirty_logging_count can be changed concurrent with this
+	 * code, but in that case another update request will be made and so
+	 * the guest will never run with a stale PML value.
+	 */
+	if (vcpu->kvm->arch.cpu_dirty_logging_count)
+		secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_ENABLE_PML);
+	else
+		secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML);
 }
 
 static int vmx_pre_block(struct kvm_vcpu *vcpu)
@@ -7642,11 +7623,6 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit)
 	return supported & BIT(bit);
 }
 
-static int vmx_cpu_dirty_log_size(void)
-{
-	return enable_pml ? PML_ENTITY_NUM : 0;
-}
-
 static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.hardware_unsetup = hardware_unsetup,
 
@@ -7746,10 +7722,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 
 	.sched_in = vmx_sched_in,
 
-	.slot_enable_log_dirty = vmx_slot_enable_log_dirty,
-	.slot_disable_log_dirty = vmx_slot_disable_log_dirty,
-	.flush_log_dirty = vmx_flush_log_dirty,
-	.enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked,
+	.cpu_dirty_log_size = PML_ENTITY_NUM,
+	.update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
 
 	.pre_block = vmx_pre_block,
 	.post_block = vmx_post_block,
@@ -7777,7 +7751,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 
 	.msr_filter_changed = vmx_msr_filter_changed,
 	.complete_emulated_msr = kvm_complete_insn_gp,
-	.cpu_dirty_log_size = vmx_cpu_dirty_log_size,
 
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
 };
@@ -7894,13 +7867,8 @@ static __init int hardware_setup(void)
 	if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml())
 		enable_pml = 0;
 
-	if (!enable_pml) {
-		vmx_x86_ops.slot_enable_log_dirty = NULL;
-		vmx_x86_ops.slot_disable_log_dirty = NULL;
-		vmx_x86_ops.flush_log_dirty = NULL;
-		vmx_x86_ops.enable_log_dirty_pt_masked = NULL;
-		vmx_x86_ops.cpu_dirty_log_size = NULL;
-	}
+	if (!enable_pml)
+		vmx_x86_ops.cpu_dirty_log_size = 0;
 
 	if (!cpu_has_vmx_preemption_timer())
 		enable_preemption_timer = false;

arch/x86/kvm/vmx/vmx.h

@@ -165,6 +165,7 @@ struct nested_vmx {
 
 	bool change_vmcs01_virtual_apic_mode;
 	bool reload_vmcs01_apic_access_page;
+	bool update_vmcs01_cpu_dirty_logging;
 
 	/*
 	 * Enlightened VMCS has been enabled. It does not mean that L1 has to
@@ -393,6 +394,7 @@ int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr);
 void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);
 void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu,
 	u32 msr, int type, bool value);
+void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
 
 static inline u8 vmx_get_rvi(void)
 {

arch/x86/kvm/x86.c

@@ -5215,10 +5215,18 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 
 void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
+
 	/*
-	 * Flush potentially hardware-cached dirty pages to dirty_bitmap.
+	 * Flush all CPUs' dirty log buffers to the  dirty_bitmap.  Called
+	 * before reporting dirty_bitmap to userspace.  KVM flushes the buffers
+	 * on all VM-Exits, thus we only need to kick running vCPUs to force a
+	 * VM-Exit.
 	 */
-	static_call_cond(kvm_x86_flush_log_dirty)(kvm);
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_vcpu_kick(vcpu);
 }
 
 int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
@@ -8980,6 +8988,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_check_async_pf_completion(vcpu);
 		if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu))
 			static_call(kvm_x86_msr_filter_changed)(vcpu);
+
+		if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu))
+			static_call(kvm_x86_update_cpu_dirty_logging)(vcpu);
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win ||
@@ -10748,75 +10759,96 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+
+static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable)
+{
+	struct kvm_arch *ka = &kvm->arch;
+
+	if (!kvm_x86_ops.cpu_dirty_log_size)
+		return;
+
+	if ((enable && ++ka->cpu_dirty_logging_count == 1) ||
+	    (!enable && --ka->cpu_dirty_logging_count == 0))
+		kvm_make_all_cpus_request(kvm, KVM_REQ_UPDATE_CPU_DIRTY_LOGGING);
+
+	WARN_ON_ONCE(ka->cpu_dirty_logging_count < 0);
+}
+
 static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
 				     struct kvm_memory_slot *old,
 				     struct kvm_memory_slot *new,
 				     enum kvm_mr_change change)
 {
+	bool log_dirty_pages = new->flags & KVM_MEM_LOG_DIRTY_PAGES;
+
 	/*
-	 * Nothing to do for RO slots or CREATE/MOVE/DELETE of a slot.
-	 * See comments below.
+	 * Update CPU dirty logging if dirty logging is being toggled.  This
+	 * applies to all operations.
 	 */
-	if ((change != KVM_MR_FLAGS_ONLY) || (new->flags & KVM_MEM_READONLY))
-		return;
+	if ((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES)
+		kvm_mmu_update_cpu_dirty_logging(kvm, log_dirty_pages);
 
 	/*
-	 * Dirty logging tracks sptes in 4k granularity, meaning that large
-	 * sptes have to be split.  If live migration is successful, the guest
-	 * in the source machine will be destroyed and large sptes will be
-	 * created in the destination. However, if the guest continues to run
-	 * in the source machine (for example if live migration fails), small
-	 * sptes will remain around and cause bad performance.
-	 *
-	 * Scan sptes if dirty logging has been stopped, dropping those
-	 * which can be collapsed into a single large-page spte.  Later
-	 * page faults will create the large-page sptes.
+	 * Nothing more to do for RO slots (which can't be dirtied and can't be
+	 * made writable) or CREATE/MOVE/DELETE of a slot.
 	 *
-	 * There is no need to do this in any of the following cases:
+	 * For a memslot with dirty logging disabled:
 	 * CREATE:      No dirty mappings will already exist.
 	 * MOVE/DELETE: The old mappings will already have been cleaned up by
 	 *		kvm_arch_flush_shadow_memslot()
+	 *
+	 * For a memslot with dirty logging enabled:
+	 * CREATE:      No shadow pages exist, thus nothing to write-protect
+	 *		and no dirty bits to clear.
+	 * MOVE/DELETE: The old mappings will already have been cleaned up by
+	 *		kvm_arch_flush_shadow_memslot().
 	 */
-	if ((old->flags & KVM_MEM_LOG_DIRTY_PAGES) &&
-	    !(new->flags & KVM_MEM_LOG_DIRTY_PAGES))
-		kvm_mmu_zap_collapsible_sptes(kvm, new);
+	if ((change != KVM_MR_FLAGS_ONLY) || (new->flags & KVM_MEM_READONLY))
+		return;
 
 	/*
-	 * Enable or disable dirty logging for the slot.
-	 *
-	 * For KVM_MR_DELETE and KVM_MR_MOVE, the shadow pages of the old
-	 * slot have been zapped so no dirty logging updates are needed for
-	 * the old slot.
-	 * For KVM_MR_CREATE and KVM_MR_MOVE, once the new slot is visible
-	 * any mappings that might be created in it will consume the
-	 * properties of the new slot and do not need to be updated here.
-	 *
-	 * When PML is enabled, the kvm_x86_ops dirty logging hooks are
-	 * called to enable/disable dirty logging.
-	 *
-	 * When disabling dirty logging with PML enabled, the D-bit is set
-	 * for sptes in the slot in order to prevent unnecessary GPA
-	 * logging in the PML buffer (and potential PML buffer full VMEXIT).
-	 * This guarantees leaving PML enabled for the guest's lifetime
-	 * won't have any additional overhead from PML when the guest is
-	 * running with dirty logging disabled.
-	 *
-	 * When enabling dirty logging, large sptes are write-protected
-	 * so they can be split on first write.  New large sptes cannot
-	 * be created for this slot until the end of the logging.
-	 * See the comments in fast_page_fault().
-	 * For small sptes, nothing is done if the dirty log is in the
-	 * initial-all-set state.  Otherwise, depending on whether pml
-	 * is enabled the D-bit or the W-bit will be cleared.
+	 * READONLY and non-flags changes were filtered out above, and the only
+	 * other flag is LOG_DIRTY_PAGES, i.e. something is wrong if dirty
+	 * logging isn't being toggled on or off.
 	 */
-	if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
-		if (kvm_x86_ops.slot_enable_log_dirty) {
-			static_call(kvm_x86_slot_enable_log_dirty)(kvm, new);
-		} else {
-			int level =
-				kvm_dirty_log_manual_protect_and_init_set(kvm) ?
-				PG_LEVEL_2M : PG_LEVEL_4K;
+	if (WARN_ON_ONCE(!((old->flags ^ new->flags) & KVM_MEM_LOG_DIRTY_PAGES)))
+		return;
+
+	if (!log_dirty_pages) {
+		/*
+		 * Dirty logging tracks sptes in 4k granularity, meaning that
+		 * large sptes have to be split.  If live migration succeeds,
+		 * the guest in the source machine will be destroyed and large
+		 * sptes will be created in the destination.  However, if the
+		 * guest continues to run in the source machine (for example if
+		 * live migration fails), small sptes will remain around and
+		 * cause bad performance.
+		 *
+		 * Scan sptes if dirty logging has been stopped, dropping those
+		 * which can be collapsed into a single large-page spte.  Later
+		 * page faults will create the large-page sptes.
+		 */
+		kvm_mmu_zap_collapsible_sptes(kvm, new);
+	} else {
+		/* By default, write-protect everything to log writes. */
+		int level = PG_LEVEL_4K;
+
+		if (kvm_x86_ops.cpu_dirty_log_size) {
+			/*
+			 * Clear all dirty bits, unless pages are treated as
+			 * dirty from the get-go.
+			 */
+			if (!kvm_dirty_log_manual_protect_and_init_set(kvm))
+				kvm_mmu_slot_leaf_clear_dirty(kvm, new);
 
+			/*
+			 * Write-protect large pages on write so that dirty
+			 * logging happens at 4k granularity.  No need to
+			 * write-protect small SPTEs since write accesses are
+			 * logged by the CPU via dirty bits.
+			 */
+			level = PG_LEVEL_2M;
+		} else if (kvm_dirty_log_manual_protect_and_init_set(kvm)) {
 			/*
 			 * If we're with initial-all-set, we don't need
 			 * to write protect any small page because
@@ -10825,10 +10857,9 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
 			 * so that the page split can happen lazily on
 			 * the first write to the huge page.
 			 */
-			kvm_mmu_slot_remove_write_access(kvm, new, level);
+			level = PG_LEVEL_2M;
 		}
-	} else {
-		static_call_cond(kvm_x86_slot_disable_log_dirty)(kvm, new);
+		kvm_mmu_slot_remove_write_access(kvm, new, level);
 	}
 }
 

include/linux/kvm_host.h

@@ -11,6 +11,7 @@
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/bug.h>
+#include <linux/minmax.h>
 #include <linux/mm.h>
 #include <linux/mmu_notifier.h>
 #include <linux/preempt.h>
@@ -506,6 +507,8 @@ struct kvm {
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_notifier_seq;
 	long mmu_notifier_count;
+	unsigned long mmu_notifier_range_start;
+	unsigned long mmu_notifier_range_end;
 #endif
 	long tlbs_dirty;
 	struct list_head devices;
@@ -733,7 +736,7 @@ kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
 kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn);
 kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
 			       bool atomic, bool *async, bool write_fault,
-			       bool *writable);
+			       bool *writable, hva_t *hva);
 
 void kvm_release_pfn_clean(kvm_pfn_t pfn);
 void kvm_release_pfn_dirty(kvm_pfn_t pfn);
@@ -1207,6 +1210,26 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
 		return 1;
 	return 0;
 }
+
+static inline int mmu_notifier_retry_hva(struct kvm *kvm,
+					 unsigned long mmu_seq,
+					 unsigned long hva)
+{
+	lockdep_assert_held(&kvm->mmu_lock);
+	/*
+	 * If mmu_notifier_count is non-zero, then the range maintained by
+	 * kvm_mmu_notifier_invalidate_range_start contains all addresses that
+	 * might be being invalidated. Note that it may include some false
+	 * positives, due to shortcuts when handing concurrent invalidations.
+	 */
+	if (unlikely(kvm->mmu_notifier_count) &&
+	    hva >= kvm->mmu_notifier_range_start &&
+	    hva < kvm->mmu_notifier_range_end)
+		return 1;
+	if (kvm->mmu_notifier_seq != mmu_seq)
+		return 1;
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING

tools/testing/selftests/kvm/.gitignore

@@ -33,6 +33,7 @@
 /demand_paging_test
 /dirty_log_test
 /dirty_log_perf_test
+/hardware_disable_test
 /kvm_create_max_vcpus
 /memslot_modification_stress_test
 /set_memory_region_test

tools/testing/selftests/kvm/Makefile

@@ -67,6 +67,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
+TEST_GEN_PROGS_x86_64 += hardware_disable_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test
 TEST_GEN_PROGS_x86_64 += set_memory_region_test

tools/testing/selftests/kvm/hardware_disable_test.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This test is intended to reproduce a crash that happens when
+ * kvm_arch_hardware_disable is called and it attempts to unregister the user
+ * return notifiers.
+ */
+
+#define _GNU_SOURCE
+
+#include <fcntl.h>
+#include <pthread.h>
+#include <semaphore.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/wait.h>
+
+#include <test_util.h>
+
+#include "kvm_util.h"
+
+#define VCPU_NUM 4
+#define SLEEPING_THREAD_NUM (1 << 4)
+#define FORK_NUM (1ULL << 9)
+#define DELAY_US_MAX 2000
+#define GUEST_CODE_PIO_PORT 4
+
+sem_t *sem;
+
+/* Arguments for the pthreads */
+struct payload {
+	struct kvm_vm *vm;
+	uint32_t index;
+};
+
+static void guest_code(void)
+{
+	for (;;)
+		;  /* Some busy work */
+	printf("Should not be reached.\n");
+}
+
+static void *run_vcpu(void *arg)
+{
+	struct payload *payload = (struct payload *)arg;
+	struct kvm_run *state = vcpu_state(payload->vm, payload->index);
+
+	vcpu_run(payload->vm, payload->index);
+
+	TEST_ASSERT(false, "%s: exited with reason %d: %s\n",
+		    __func__, state->exit_reason,
+		    exit_reason_str(state->exit_reason));
+	pthread_exit(NULL);
+}
+
+static void *sleeping_thread(void *arg)
+{
+	int fd;
+
+	while (true) {
+		fd = open("/dev/null", O_RDWR);
+		close(fd);
+	}
+	TEST_ASSERT(false, "%s: exited\n", __func__);
+	pthread_exit(NULL);
+}
+
+static inline void check_create_thread(pthread_t *thread, pthread_attr_t *attr,
+				       void *(*f)(void *), void *arg)
+{
+	int r;
+
+	r = pthread_create(thread, attr, f, arg);
+	TEST_ASSERT(r == 0, "%s: failed to create thread", __func__);
+}
+
+static inline void check_set_affinity(pthread_t thread, cpu_set_t *cpu_set)
+{
+	int r;
+
+	r = pthread_setaffinity_np(thread, sizeof(cpu_set_t), cpu_set);
+	TEST_ASSERT(r == 0, "%s: failed set affinity", __func__);
+}
+
+static inline void check_join(pthread_t thread, void **retval)
+{
+	int r;
+
+	r = pthread_join(thread, retval);
+	TEST_ASSERT(r == 0, "%s: failed to join thread", __func__);
+}
+
+static void run_test(uint32_t run)
+{
+	struct kvm_vm *vm;
+	cpu_set_t cpu_set;
+	pthread_t threads[VCPU_NUM];
+	pthread_t throw_away;
+	struct payload payloads[VCPU_NUM];
+	void *b;
+	uint32_t i, j;
+
+	CPU_ZERO(&cpu_set);
+	for (i = 0; i < VCPU_NUM; i++)
+		CPU_SET(i, &cpu_set);
+
+	vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+	vm_create_irqchip(vm);
+
+	fprintf(stderr, "%s: [%d] start vcpus\n", __func__, run);
+	for (i = 0; i < VCPU_NUM; ++i) {
+		vm_vcpu_add_default(vm, i, guest_code);
+		payloads[i].vm = vm;
+		payloads[i].index = i;
+
+		check_create_thread(&threads[i], NULL, run_vcpu,
+				    (void *)&payloads[i]);
+		check_set_affinity(threads[i], &cpu_set);
+
+		for (j = 0; j < SLEEPING_THREAD_NUM; ++j) {
+			check_create_thread(&throw_away, NULL, sleeping_thread,
+					    (void *)NULL);
+			check_set_affinity(throw_away, &cpu_set);
+		}
+	}
+	fprintf(stderr, "%s: [%d] all threads launched\n", __func__, run);
+	sem_post(sem);
+	for (i = 0; i < VCPU_NUM; ++i)
+		check_join(threads[i], &b);
+	/* Should not be reached */
+	TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run);
+}
+
+int main(int argc, char **argv)
+{
+	uint32_t i;
+	int s, r;
+	pid_t pid;
+
+	sem = sem_open("vm_sem", O_CREAT | O_EXCL, 0644, 0);
+	sem_unlink("vm_sem");
+
+	for (i = 0; i < FORK_NUM; ++i) {
+		pid = fork();
+		TEST_ASSERT(pid >= 0, "%s: unable to fork", __func__);
+		if (pid == 0)
+			run_test(i); /* This function always exits */
+
+		fprintf(stderr, "%s: [%d] waiting semaphore\n", __func__, i);
+		sem_wait(sem);
+		r = (rand() % DELAY_US_MAX) + 1;
+		fprintf(stderr, "%s: [%d] waiting %dus\n", __func__, i, r);
+		usleep(r);
+		r = waitpid(pid, &s, WNOHANG);
+		TEST_ASSERT(r != pid,
+			    "%s: [%d] child exited unexpectedly status: [%d]",
+			    __func__, i, s);
+		fprintf(stderr, "%s: [%d] killing child\n", __func__, i);
+		kill(pid, SIGKILL);
+	}
+
+	sem_destroy(sem);
+	exit(0);
+}

tools/testing/selftests/kvm/lib/x86_64/processor.c

@@ -720,7 +720,8 @@ struct kvm_cpuid2 *vcpu_get_cpuid(struct kvm_vm *vm, uint32_t vcpuid)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	struct kvm_cpuid2 *cpuid;
-	int rc, max_ent;
+	int max_ent;
+	int rc = -1;
 
 	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
 

virt/kvm/kvm_main.c

@@ -486,6 +486,24 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 * count is also read inside the mmu_lock critical section.
 	 */
 	kvm->mmu_notifier_count++;
+	if (likely(kvm->mmu_notifier_count == 1)) {
+		kvm->mmu_notifier_range_start = range->start;
+		kvm->mmu_notifier_range_end = range->end;
+	} else {
+		/*
+		 * Fully tracking multiple concurrent ranges has dimishing
+		 * returns. Keep things simple and just find the minimal range
+		 * which includes the current and new ranges. As there won't be
+		 * enough information to subtract a range after its invalidate
+		 * completes, any ranges invalidated concurrently will
+		 * accumulate and persist until all outstanding invalidates
+		 * complete.
+		 */
+		kvm->mmu_notifier_range_start =
+			min(kvm->mmu_notifier_range_start, range->start);
+		kvm->mmu_notifier_range_end =
+			max(kvm->mmu_notifier_range_end, range->end);
+	}
 	need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end,
 					     range->flags);
 	/* we've to flush the tlb before the pages can be freed */
@@ -2023,10 +2041,13 @@ static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
 
 kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
 			       bool atomic, bool *async, bool write_fault,
-			       bool *writable)
+			       bool *writable, hva_t *hva)
 {
 	unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
 
+	if (hva)
+		*hva = addr;
+
 	if (addr == KVM_HVA_ERR_RO_BAD) {
 		if (writable)
 			*writable = false;
@@ -2054,19 +2075,19 @@ kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
 		      bool *writable)
 {
 	return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL,
-				    write_fault, writable);
+				    write_fault, writable, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
 
 kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL);
+	return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);
 
 kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL);
+	return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);