1 files changed, 97 insertions, 27 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1b4438e24814..8edfb4e4a73d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5591,7 +5591,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0,
 	union kvm_mmu_page_role root_role;
 
 	/* NPT requires CR0.PG=1. */
-	WARN_ON_ONCE(cpu_role.base.direct);
+	WARN_ON_ONCE(cpu_role.base.direct || !cpu_role.base.guest_mode);
 
 	root_role = cpu_role.base;
 	root_role.level = kvm_mmu_get_tdp_level(vcpu);
@@ -6234,7 +6234,7 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	/* It's actually a GPA for vcpu->arch.guest_mmu.  */
 	if (mmu != &vcpu->arch.guest_mmu) {
 		/* INVLPG on a non-canonical address is a NOP according to the SDM.  */
-		if (is_noncanonical_address(addr, vcpu))
+		if (is_noncanonical_invlpg_address(addr, vcpu))
 			return;
 
 		kvm_x86_call(flush_tlb_gva)(vcpu, addr);
@@ -7227,6 +7227,19 @@ static void mmu_destroy_caches(void)
 	kmem_cache_destroy(mmu_page_header_cache);
 }
 
+static void kvm_wake_nx_recovery_thread(struct kvm *kvm)
+{
+	/*
+	 * The NX recovery thread is spawned on-demand at the first KVM_RUN and
+	 * may not be valid even though the VM is globally visible.  Do nothing,
+	 * as such a VM can't have any possible NX huge pages.
+	 */
+	struct vhost_task *nx_thread = READ_ONCE(kvm->arch.nx_huge_page_recovery_thread);
+
+	if (nx_thread)
+		vhost_task_wake(nx_thread);
+}
+
 static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp)
 {
 	if (nx_hugepage_mitigation_hard_disabled)
@@ -7287,7 +7300,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
 			kvm_mmu_zap_all_fast(kvm);
 			mutex_unlock(&kvm->slots_lock);
 
-			vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread);
+			kvm_wake_nx_recovery_thread(kvm);
 		}
 		mutex_unlock(&kvm_lock);
 	}
@@ -7433,7 +7446,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel
 		mutex_lock(&kvm_lock);
 
 		list_for_each_entry(kvm, &vm_list, vm_list)
-			vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread);
+			kvm_wake_nx_recovery_thread(kvm);
 
 		mutex_unlock(&kvm_lock);
 	}
@@ -7565,20 +7578,34 @@ static bool kvm_nx_huge_page_recovery_worker(void *data)
 	return true;
 }
 
+static void kvm_mmu_start_lpage_recovery(struct once *once)
+{
+	struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once);
+	struct kvm *kvm = container_of(ka, struct kvm, arch);
+	struct vhost_task *nx_thread;
+
+	kvm->arch.nx_huge_page_last = get_jiffies_64();
+	nx_thread = vhost_task_create(kvm_nx_huge_page_recovery_worker,
+				      kvm_nx_huge_page_recovery_worker_kill,
+				      kvm, "kvm-nx-lpage-recovery");
+
+	if (IS_ERR(nx_thread))
+		return;
+
+	vhost_task_start(nx_thread);
+
+	/* Make the task visible only once it is fully started. */
+	WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread);
+}
+
 int kvm_mmu_post_init_vm(struct kvm *kvm)
 {
 	if (nx_hugepage_mitigation_hard_disabled)
 		return 0;
 
-	kvm->arch.nx_huge_page_last = get_jiffies_64();
-	kvm->arch.nx_huge_page_recovery_thread = vhost_task_create(
-		kvm_nx_huge_page_recovery_worker, kvm_nx_huge_page_recovery_worker_kill,
-		kvm, "kvm-nx-lpage-recovery");
-
+	call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
 	if (!kvm->arch.nx_huge_page_recovery_thread)
 		return -ENOMEM;
-
-	vhost_task_start(kvm->arch.nx_huge_page_recovery_thread);
 	return 0;
 }
 
@@ -7589,9 +7616,30 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 }
 
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+				int level)
+{
+	return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+				 int level)
+{
+	lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
+}
+
+static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
+			       int level)
+{
+	lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
+}
+
 bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 					struct kvm_gfn_range *range)
 {
+	struct kvm_memory_slot *slot = range->slot;
+	int level;
+
 	/*
 	 * Zap SPTEs even if the slot can't be mapped PRIVATE.  KVM x86 only
 	 * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
@@ -7606,27 +7654,49 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 	if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
 		return false;
 
-	return kvm_unmap_gfn_range(kvm, range);
-}
+	if (WARN_ON_ONCE(range->end <= range->start))
+		return false;
 
-static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
-				int level)
-{
-	return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG;
-}
+	/*
+	 * If the head and tail pages of the range currently allow a hugepage,
+	 * i.e. reside fully in the slot and don't have mixed attributes, then
+	 * add each corresponding hugepage range to the ongoing invalidation,
+	 * e.g. to prevent KVM from creating a hugepage in response to a fault
+	 * for a gfn whose attributes aren't changing.  Note, only the range
+	 * of gfns whose attributes are being modified needs to be explicitly
+	 * unmapped, as that will unmap any existing hugepages.
+	 */
+	for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+		gfn_t start = gfn_round_for_level(range->start, level);
+		gfn_t end = gfn_round_for_level(range->end - 1, level);
+		gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level);
 
-static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
-				 int level)
-{
-	lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG;
-}
+		if ((start != range->start || start + nr_pages > range->end) &&
+		    start >= slot->base_gfn &&
+		    start + nr_pages <= slot->base_gfn + slot->npages &&
+		    !hugepage_test_mixed(slot, start, level))
+			kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages);
 
-static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn,
-			       int level)
-{
-	lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG;
+		if (end == start)
+			continue;
+
+		if ((end + nr_pages) > range->end &&
+		    (end + nr_pages) <= (slot->base_gfn + slot->npages) &&
+		    !hugepage_test_mixed(slot, end, level))
+			kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages);
+	}
+
+	/* Unmap the old attribute page. */
+	if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE)
+		range->attr_filter = KVM_FILTER_SHARED;
+	else
+		range->attr_filter = KVM_FILTER_PRIVATE;
+
+	return kvm_unmap_gfn_range(kvm, range);
 }
 
+
+
 static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot,
 			       gfn_t gfn, int level, unsigned long attrs)
 {