1 files changed, 125 insertions, 51 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b6f96d47e596..835426254e76 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -22,6 +22,7 @@
 #include "tdp_mmu.h"
 #include "x86.h"
 #include "kvm_cache_regs.h"
+#include "smm.h"
 #include "kvm_emulate.h"
 #include "cpuid.h"
 #include "spte.h"
@@ -802,15 +803,31 @@ 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 track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	if (sp->lpage_disallowed)
+	/*
+	 * If it's possible to replace the shadow page with an NX huge page,
+	 * i.e. if the shadow page is the only thing currently preventing KVM
+	 * from using a huge page, add the shadow page to the list of "to be
+	 * zapped for NX recovery" pages.  Note, the shadow page can already be
+	 * on the list if KVM is reusing an existing shadow page, i.e. if KVM
+	 * links a shadow page at multiple points.
+	 */
+	if (!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);
-	sp->lpage_disallowed = true;
+	list_add_tail(&sp->possible_nx_huge_page_link,
+		      &kvm->arch.possible_nx_huge_pages);
+}
+
+static void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+				 bool nx_huge_page_possible)
+{
+	sp->nx_huge_page_disallowed = true;
+
+	if (nx_huge_page_possible)
+		track_possible_nx_huge_page(kvm, sp);
 }
 
 static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
@@ -830,11 +847,20 @@ 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 untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
+	if (list_empty(&sp->possible_nx_huge_page_link))
+		return;
+
 	--kvm->stat.nx_lpage_splits;
-	sp->lpage_disallowed = false;
-	list_del(&sp->lpage_disallowed_link);
+	list_del_init(&sp->possible_nx_huge_page_link);
+}
+
+static void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	sp->nx_huge_page_disallowed = false;
+
+	untrack_possible_nx_huge_page(kvm, sp);
 }
 
 static struct kvm_memory_slot *
@@ -1645,7 +1671,7 @@ static int is_empty_shadow_page(u64 *spt)
 	u64 *pos;
 	u64 *end;
 
-	for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
+	for (pos = spt, end = pos + SPTE_ENT_PER_PAGE; pos != end; pos++)
 		if (is_shadow_present_pte(*pos)) {
 			printk(KERN_ERR "%s: %p %llx\n", __func__,
 			       pos, *pos);
@@ -1793,7 +1819,7 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
 			continue;
 		}
 
-		child = to_shadow_page(ent & SPTE_BASE_ADDR_MASK);
+		child = spte_to_child_sp(ent);
 
 		if (child->unsync_children) {
 			if (mmu_pages_add(pvec, child, i))
@@ -1894,7 +1920,7 @@ static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 	if (sp->role.invalid)
 		return true;
 
-	/* TDP MMU pages due not use the MMU generation. */
+	/* TDP MMU pages do not use the MMU generation. */
 	return !sp->tdp_mmu_page &&
 	       unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
 }
@@ -2129,6 +2155,8 @@ 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->possible_nx_huge_page_link);
+
 	/*
 	 * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages()
 	 * depends on valid pages being added to the head of the list.  See
@@ -2350,7 +2378,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		 * so we should update the spte at this point to get
 		 * a new sp with the correct access.
 		 */
-		child = to_shadow_page(*sptep & SPTE_BASE_ADDR_MASK);
+		child = spte_to_child_sp(*sptep);
 		if (child->role.access == direct_access)
 			return;
 
@@ -2371,7 +2399,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 		if (is_last_spte(pte, sp->role.level)) {
 			drop_spte(kvm, spte);
 		} else {
-			child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK);
+			child = spte_to_child_sp(pte);
 			drop_parent_pte(child, spte);
 
 			/*
@@ -2487,8 +2515,8 @@ 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;
 
@@ -2811,7 +2839,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 			struct kvm_mmu_page *child;
 			u64 pte = *sptep;
 
-			child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK);
+			child = spte_to_child_sp(pte);
 			drop_parent_pte(child, sptep);
 			flush = true;
 		} else if (pfn != spte_to_pfn(*sptep)) {
@@ -3085,7 +3113,8 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
 	if (cur_level > PG_LEVEL_4K &&
 	    cur_level == fault->goal_level &&
 	    is_shadow_present_pte(spte) &&
-	    !is_large_pte(spte)) {
+	    !is_large_pte(spte) &&
+	    spte_to_child_sp(spte)->nx_huge_page_disallowed) {
 		/*
 		 * A small SPTE exists for this pfn, but FNAME(fetch)
 		 * and __direct_map would like to create a large PTE
@@ -3127,9 +3156,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 			continue;
 
 		link_shadow_page(vcpu, it.sptep, sp);
-		if (fault->is_tdp && fault->huge_page_disallowed &&
-		    fault->req_level >= it.level)
-			account_huge_nx_page(vcpu->kvm, sp);
+		if (fault->huge_page_disallowed)
+			account_nx_huge_page(vcpu->kvm, sp,
+					     fault->req_level >= it.level);
 	}
 
 	if (WARN_ON_ONCE(it.level != fault->goal_level))
@@ -3149,8 +3178,13 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *
 	send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk);
 }
 
-static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
+static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
 {
+	if (is_sigpending_pfn(pfn)) {
+		kvm_handle_signal_exit(vcpu);
+		return -EINTR;
+	}
+
 	/*
 	 * Do not cache the mmio info caused by writing the readonly gfn
 	 * into the spte otherwise read access on readonly gfn also can
@@ -3172,7 +3206,7 @@ static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fau
 {
 	/* The pfn is invalid, report the error! */
 	if (unlikely(is_error_pfn(fault->pfn)))
-		return kvm_handle_bad_page(vcpu, fault->gfn, fault->pfn);
+		return kvm_handle_error_pfn(vcpu, fault->gfn, fault->pfn);
 
 	if (unlikely(!fault->slot)) {
 		gva_t gva = fault->is_tdp ? 0 : fault->addr;
@@ -3423,7 +3457,11 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
 	if (!VALID_PAGE(*root_hpa))
 		return;
 
-	sp = to_shadow_page(*root_hpa & SPTE_BASE_ADDR_MASK);
+	/*
+	 * The "root" may be a special root, e.g. a PAE entry, treat it as a
+	 * SPTE to ensure any non-PA bits are dropped.
+	 */
+	sp = spte_to_child_sp(*root_hpa);
 	if (WARN_ON(!sp))
 		return;
 
@@ -3908,8 +3946,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 		hpa_t root = vcpu->arch.mmu->pae_root[i];
 
 		if (IS_VALID_PAE_ROOT(root)) {
-			root &= SPTE_BASE_ADDR_MASK;
-			sp = to_shadow_page(root);
+			sp = spte_to_child_sp(root);
 			mmu_sync_children(vcpu, sp, true);
 		}
 	}
@@ -4170,7 +4207,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 	}
 
 	async = false;
-	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
+	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
 					  fault->write, &fault->map_writable,
 					  &fault->hva);
 	if (!async)
@@ -4187,7 +4224,12 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 		}
 	}
 
-	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, NULL,
+	/*
+	 * Allow gup to bail on pending non-fatal signals when it's also allowed
+	 * to wait for IO.  Note, gup always bails if it is unable to quickly
+	 * get a page and a fatal signal, i.e. SIGKILL, is pending.
+	 */
+	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL,
 					  fault->write, &fault->map_writable,
 					  &fault->hva);
 	return RET_PF_CONTINUE;
@@ -5972,7 +6014,7 @@ 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);
@@ -6657,7 +6699,7 @@ 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);
 	}
@@ -6789,7 +6831,7 @@ 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);
 	}
@@ -6797,9 +6839,10 @@ 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;
+	struct kvm_memory_slot *slot;
 	int rcu_idx;
 	struct kvm_mmu_page *sp;
 	unsigned int ratio;
@@ -6820,24 +6863,55 @@ 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);
-		if (is_tdp_mmu_page(sp)) {
+				      possible_nx_huge_page_link);
+		WARN_ON_ONCE(!sp->nx_huge_page_disallowed);
+		WARN_ON_ONCE(!sp->role.direct);
+
+		/*
+		 * Unaccount and do not attempt to recover any NX Huge Pages
+		 * that are being dirty tracked, as they would just be faulted
+		 * back in as 4KiB pages. The NX Huge Pages in this slot will be
+		 * recovered, along with all the other huge pages in the slot,
+		 * when dirty logging is disabled.
+		 *
+		 * Since gfn_to_memslot() is relatively expensive, it helps to
+		 * skip it if it the test cannot possibly return true.  On the
+		 * other hand, if any memslot has logging enabled, chances are
+		 * good that all of them do, in which case unaccount_nx_huge_page()
+		 * is much cheaper than zapping the page.
+		 *
+		 * If a memslot update is in progress, reading an incorrect value
+		 * of kvm->nr_memslots_dirty_logging is not a problem: if it is
+		 * becoming zero, gfn_to_memslot() will be done unnecessarily; if
+		 * it is becoming nonzero, the page will be zapped unnecessarily.
+		 * Either way, this only affects efficiency in racy situations,
+		 * and not correctness.
+		 */
+		slot = NULL;
+		if (atomic_read(&kvm->nr_memslots_dirty_logging)) {
+			slot = gfn_to_memslot(kvm, sp->gfn);
+			WARN_ON_ONCE(!slot);
+		}
+
+		if (slot && kvm_slot_dirty_track_enabled(slot))
+			unaccount_nx_huge_page(kvm, sp);
+		else if (is_tdp_mmu_page(sp))
 			flush |= kvm_tdp_mmu_zap_sp(kvm, sp);
-		} else {
+		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)) {
 			kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
@@ -6857,7 +6931,7 @@ 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;
@@ -6868,19 +6942,19 @@ 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);
 		}
 
@@ -6889,7 +6963,7 @@ 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);
 	}
 }
 
@@ -6897,17 +6971,17 @@ 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);
 }