KVM: x86/mmu: Rename NX huge pages fields/functions for consistency

Rename most of the variables/functions involved in the NX huge page
mitigation to provide consistency, e.g. lpage vs huge page, and NX huge
vs huge NX, and also to provide clarity, e.g. to make it obvious the flag
applies only to the NX huge page mitigation, not to any condition that
prevents creating a huge page.

Add a comment explaining what the newly named "possible_nx_huge_pages"
tracks.

Leave the nx_lpage_splits stat alone as the name is ABI and thus set in
stone.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Mingwei Zhang <mizhang@google.com>
Message-Id: <20221019165618.927057-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -1159,7 +1159,18 @@ struct kvm_arch {
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	struct list_head active_mmu_pages;
 	struct list_head zapped_obsolete_pages;
-	struct list_head lpage_disallowed_mmu_pages;
+	/*
+	 * A list of kvm_mmu_page structs that, if zapped, could possibly be
+	 * replaced by an NX huge page.  A shadow page is on this list if its
+	 * existence disallows an NX huge page (nx_huge_page_disallowed is set)
+	 * and there are no other conditions that prevent a huge page, e.g.
+	 * the backing host page is huge, dirtly logging is not enabled for its
+	 * memslot, etc...  Note, zapping shadow pages on this list doesn't
+	 * guarantee an NX huge page will be created in its stead, e.g. if the
+	 * guest attempts to execute from the region then KVM obviously can't
+	 * create an NX huge page (without hanging the guest).
+	 */
+	struct list_head possible_nx_huge_pages;
 	struct kvm_page_track_notifier_node mmu_sp_tracker;
 	struct kvm_page_track_notifier_head track_notifier_head;
 	/*
@@ -1275,7 +1286,7 @@ struct kvm_arch {
 	bool sgx_provisioning_allowed;
 
 	struct kvm_pmu_event_filter __rcu *pmu_event_filter;
-	struct task_struct *nx_lpage_recovery_thread;
+	struct task_struct *nx_huge_page_recovery_thread;
 
 #ifdef CONFIG_X86_64
 	/*
@@ -1320,8 +1331,8 @@ struct kvm_arch {
 	 *  - tdp_mmu_roots (above)
 	 *  - tdp_mmu_pages (above)
 	 *  - the link field of kvm_mmu_page structs used by the TDP MMU
-	 *  - lpage_disallowed_mmu_pages
-	 *  - the lpage_disallowed_link field of kvm_mmu_page structs used
+	 *  - possible_nx_huge_pages;
+	 *  - the possible_nx_huge_page_link field of kvm_mmu_page structs used
 	 *    by the TDP MMU
 	 * It is acceptable, but not necessary, to acquire this lock when
 	 * the thread holds the MMU lock in write mode.

arch/x86/kvm/mmu/mmu.c

@@ -803,10 +803,10 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 		kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
 }
 
-void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 			  bool nx_huge_page_possible)
 {
-	sp->lpage_disallowed = true;
+	sp->nx_huge_page_disallowed = true;
 
 	/*
 	 * If it's possible to replace the shadow page with an NX huge page,
@@ -816,12 +816,13 @@ void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 	 * on the list if KVM is reusing an existing shadow page, i.e. if KVM
 	 * links a shadow page at multiple points.
 	 */
-	if (!nx_huge_page_possible || !list_empty(&sp->lpage_disallowed_link))
+	if (!nx_huge_page_possible ||
+	    !list_empty(&sp->possible_nx_huge_page_link))
 		return;
 
 	++kvm->stat.nx_lpage_splits;
-	list_add_tail(&sp->lpage_disallowed_link,
-		      &kvm->arch.lpage_disallowed_mmu_pages);
+	list_add_tail(&sp->possible_nx_huge_page_link,
+		      &kvm->arch.possible_nx_huge_pages);
 }
 
 static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
@@ -841,15 +842,15 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm_mmu_gfn_allow_lpage(slot, gfn);
 }
 
-void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	sp->lpage_disallowed = false;
+	sp->nx_huge_page_disallowed = false;
 
-	if (list_empty(&sp->lpage_disallowed_link))
+	if (list_empty(&sp->possible_nx_huge_page_link))
 		return;
 
 	--kvm->stat.nx_lpage_splits;
-	list_del_init(&sp->lpage_disallowed_link);
+	list_del_init(&sp->possible_nx_huge_page_link);
 }
 
 static struct kvm_memory_slot *
@@ -2144,7 +2145,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm,
 
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 
-	INIT_LIST_HEAD(&sp->lpage_disallowed_link);
+	INIT_LIST_HEAD(&sp->possible_nx_huge_page_link);
 
 	/*
 	 * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages()
@@ -2503,8 +2504,8 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 		zapped_root = !is_obsolete_sp(kvm, sp);
 	}
 
-	if (sp->lpage_disallowed)
-		unaccount_huge_nx_page(kvm, sp);
+	if (sp->nx_huge_page_disallowed)
+		unaccount_nx_huge_page(kvm, sp);
 
 	sp->role.invalid = 1;
 
@@ -3144,7 +3145,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 
 		link_shadow_page(vcpu, it.sptep, sp);
 		if (fault->is_tdp && fault->huge_page_disallowed)
-			account_huge_nx_page(vcpu->kvm, sp,
+			account_nx_huge_page(vcpu->kvm, sp,
 					     fault->req_level >= it.level);
 	}
 
@@ -5998,7 +5999,7 @@ int kvm_mmu_init_vm(struct kvm *kvm)
 
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
-	INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
+	INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
 	spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
 
 	r = kvm_mmu_init_tdp_mmu(kvm);
@@ -6683,7 +6684,7 @@ 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);
 
-			wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+			wake_up_process(kvm->arch.nx_huge_page_recovery_thread);
 		}
 		mutex_unlock(&kvm_lock);
 	}
@@ -6815,7 +6816,7 @@ 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)
-			wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+			wake_up_process(kvm->arch.nx_huge_page_recovery_thread);
 
 		mutex_unlock(&kvm_lock);
 	}
@@ -6823,7 +6824,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel
 	return err;
 }
 
-static void kvm_recover_nx_lpages(struct kvm *kvm)
+static void kvm_recover_nx_huge_pages(struct kvm *kvm)
 {
 	unsigned long nx_lpage_splits = kvm->stat.nx_lpage_splits;
 	int rcu_idx;
@@ -6846,23 +6847,25 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 	ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
 	to_zap = ratio ? DIV_ROUND_UP(nx_lpage_splits, ratio) : 0;
 	for ( ; to_zap; --to_zap) {
-		if (list_empty(&kvm->arch.lpage_disallowed_mmu_pages))
+		if (list_empty(&kvm->arch.possible_nx_huge_pages))
 			break;
 
 		/*
 		 * We use a separate list instead of just using active_mmu_pages
-		 * because the number of lpage_disallowed pages is expected to
-		 * be relatively small compared to the total.
+		 * because the number of shadow pages that be replaced with an
+		 * NX huge page is expected to be relatively small compared to
+		 * the total number of shadow pages.  And because the TDP MMU
+		 * doesn't use active_mmu_pages.
 		 */
-		sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages,
+		sp = list_first_entry(&kvm->arch.possible_nx_huge_pages,
 				      struct kvm_mmu_page,
-				      lpage_disallowed_link);
-		WARN_ON_ONCE(!sp->lpage_disallowed);
+				      possible_nx_huge_page_link);
+		WARN_ON_ONCE(!sp->nx_huge_page_disallowed);
 		if (is_tdp_mmu_page(sp)) {
 			flush |= kvm_tdp_mmu_zap_sp(kvm, sp);
 		} else {
 			kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
-			WARN_ON_ONCE(sp->lpage_disallowed);
+			WARN_ON_ONCE(sp->nx_huge_page_disallowed);
 		}
 
 		if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
@@ -6883,7 +6886,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 	srcu_read_unlock(&kvm->srcu, rcu_idx);
 }
 
-static long get_nx_lpage_recovery_timeout(u64 start_time)
+static long get_nx_huge_page_recovery_timeout(u64 start_time)
 {
 	bool enabled;
 	uint period;
@@ -6894,19 +6897,19 @@ static long get_nx_lpage_recovery_timeout(u64 start_time)
 		       : MAX_SCHEDULE_TIMEOUT;
 }
 
-static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
+static int kvm_nx_huge_page_recovery_worker(struct kvm *kvm, uintptr_t data)
 {
 	u64 start_time;
 	long remaining_time;
 
 	while (true) {
 		start_time = get_jiffies_64();
-		remaining_time = get_nx_lpage_recovery_timeout(start_time);
+		remaining_time = get_nx_huge_page_recovery_timeout(start_time);
 
 		set_current_state(TASK_INTERRUPTIBLE);
 		while (!kthread_should_stop() && remaining_time > 0) {
 			schedule_timeout(remaining_time);
-			remaining_time = get_nx_lpage_recovery_timeout(start_time);
+			remaining_time = get_nx_huge_page_recovery_timeout(start_time);
 			set_current_state(TASK_INTERRUPTIBLE);
 		}
 
@@ -6915,7 +6918,7 @@ static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
 		if (kthread_should_stop())
 			return 0;
 
-		kvm_recover_nx_lpages(kvm);
+		kvm_recover_nx_huge_pages(kvm);
 	}
 }
 
@@ -6923,17 +6926,17 @@ int kvm_mmu_post_init_vm(struct kvm *kvm)
 {
 	int err;
 
-	err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0,
+	err = kvm_vm_create_worker_thread(kvm, kvm_nx_huge_page_recovery_worker, 0,
 					  "kvm-nx-lpage-recovery",
-					  &kvm->arch.nx_lpage_recovery_thread);
+					  &kvm->arch.nx_huge_page_recovery_thread);
 	if (!err)
-		kthread_unpark(kvm->arch.nx_lpage_recovery_thread);
+		kthread_unpark(kvm->arch.nx_huge_page_recovery_thread);
 
 	return err;
 }
 
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 {
-	if (kvm->arch.nx_lpage_recovery_thread)
-		kthread_stop(kvm->arch.nx_lpage_recovery_thread);
+	if (kvm->arch.nx_huge_page_recovery_thread)
+		kthread_stop(kvm->arch.nx_huge_page_recovery_thread);
 }

arch/x86/kvm/mmu/mmu_internal.h

@@ -57,7 +57,13 @@ struct kvm_mmu_page {
 	bool tdp_mmu_page;
 	bool unsync;
 	u8 mmu_valid_gen;
-	bool lpage_disallowed; /* Can't be replaced by an equiv large page */
+
+	 /*
+	  * The shadow page can't be replaced by an equivalent huge page
+	  * because it is being used to map an executable page in the guest
+	  * and the NX huge page mitigation is enabled.
+	  */
+	bool nx_huge_page_disallowed;
 
 	/*
 	 * The following two entries are used to key the shadow page in the
@@ -102,12 +108,12 @@ struct kvm_mmu_page {
 
 	/*
 	 * Tracks shadow pages that, if zapped, would allow KVM to create an NX
-	 * huge page.  A shadow page will have lpage_disallowed set but not be
-	 * on the list if a huge page is disallowed for other reasons, e.g.
-	 * because KVM is shadowing a PTE at the same gfn, the memslot isn't
-	 * properly aligned, etc...
+	 * huge page.  A shadow page will have nx_huge_page_disallowed set but
+	 * not be on the list if a huge page is disallowed for other reasons,
+	 * e.g. because KVM is shadowing a PTE at the same gfn, the memslot
+	 * isn't properly aligned, etc...
 	 */
-	struct list_head lpage_disallowed_link;
+	struct list_head possible_nx_huge_page_link;
 #ifdef CONFIG_X86_32
 	/*
 	 * Used out of the mmu-lock to avoid reading spte values while an
@@ -322,8 +328,8 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
 
 void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 
-void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 			  bool nx_huge_page_possible);
-void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
+void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp);
 
 #endif /* __KVM_X86_MMU_INTERNAL_H */

arch/x86/kvm/mmu/paging_tmpl.h

@@ -714,7 +714,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 
 		link_shadow_page(vcpu, it.sptep, sp);
 		if (fault->huge_page_disallowed)
-			account_huge_nx_page(vcpu->kvm, sp,
+			account_nx_huge_page(vcpu->kvm, sp,
 					     fault->req_level >= it.level);
 	}
 

arch/x86/kvm/mmu/tdp_mmu.c

@@ -284,7 +284,7 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu)
 static void tdp_mmu_init_sp(struct kvm_mmu_page *sp, tdp_ptep_t sptep,
 			    gfn_t gfn, union kvm_mmu_page_role role)
 {
-	INIT_LIST_HEAD(&sp->lpage_disallowed_link);
+	INIT_LIST_HEAD(&sp->possible_nx_huge_page_link);
 
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 
@@ -403,8 +403,8 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp,
 		lockdep_assert_held_write(&kvm->mmu_lock);
 
 	list_del(&sp->link);
-	if (sp->lpage_disallowed)
-		unaccount_huge_nx_page(kvm, sp);
+	if (sp->nx_huge_page_disallowed)
+		unaccount_nx_huge_page(kvm, sp);
 
 	if (shared)
 		spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
@@ -1143,7 +1143,7 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
 	spin_lock(&kvm->arch.tdp_mmu_pages_lock);
 	list_add(&sp->link, &kvm->arch.tdp_mmu_pages);
 	if (account_nx)
-		account_huge_nx_page(kvm, sp, true);
+		account_nx_huge_page(kvm, sp, true);
 	spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
 	tdp_account_mmu_page(kvm, sp);