1 files changed, 248 insertions, 213 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index e2e2e5cc7dc6..4e03841f053d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -18,6 +18,7 @@
 #include "irq.h"
 #include "ioapic.h"
 #include "mmu.h"
+#include "mmu_internal.h"
 #include "x86.h"
 #include "kvm_cache_regs.h"
 #include "kvm_emulate.h"
@@ -91,7 +92,8 @@ module_param_named(flush_on_reuse, force_flush_and_sync_on_reuse, bool, 0644);
  */
 bool tdp_enabled = false;
 
-static int max_page_level __read_mostly;
+static int max_huge_page_level __read_mostly;
+static int max_tdp_level __read_mostly;
 
 enum {
 	AUDIT_PRE_PAGE_FAULT,
@@ -515,6 +517,18 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
 	return likely(kvm_gen == spte_gen);
 }
 
+static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+                                  struct x86_exception *exception)
+{
+	/* Check if guest physical address doesn't exceed guest maximum */
+	if (kvm_mmu_is_illegal_gpa(vcpu, gpa)) {
+		exception->error_code |= PFERR_RSVD_MASK;
+		return UNMAPPED_GVA;
+	}
+
+        return gpa;
+}
+
 /*
  * Sets the shadow PTE masks used by the MMU.
  *
@@ -676,7 +690,7 @@ union split_spte {
 
 static void count_spte_clear(u64 *sptep, u64 spte)
 {
-	struct kvm_mmu_page *sp =  page_header(__pa(sptep));
+	struct kvm_mmu_page *sp =  sptep_to_sp(sptep);
 
 	if (is_shadow_present_pte(spte))
 		return;
@@ -760,7 +774,7 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
  */
 static u64 __get_spte_lockless(u64 *sptep)
 {
-	struct kvm_mmu_page *sp =  page_header(__pa(sptep));
+	struct kvm_mmu_page *sp =  sptep_to_sp(sptep);
 	union split_spte spte, *orig = (union split_spte *)sptep;
 	int count;
 
@@ -1060,94 +1074,40 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 }
 
-static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
-				  struct kmem_cache *base_cache, int min)
-{
-	void *obj;
-
-	if (cache->nobjs >= min)
-		return 0;
-	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
-		obj = kmem_cache_zalloc(base_cache, GFP_KERNEL_ACCOUNT);
-		if (!obj)
-			return cache->nobjs >= min ? 0 : -ENOMEM;
-		cache->objects[cache->nobjs++] = obj;
-	}
-	return 0;
-}
-
-static int mmu_memory_cache_free_objects(struct kvm_mmu_memory_cache *cache)
-{
-	return cache->nobjs;
-}
-
-static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc,
-				  struct kmem_cache *cache)
-{
-	while (mc->nobjs)
-		kmem_cache_free(cache, mc->objects[--mc->nobjs]);
-}
-
-static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
-				       int min)
-{
-	void *page;
-
-	if (cache->nobjs >= min)
-		return 0;
-	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
-		page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
-		if (!page)
-			return cache->nobjs >= min ? 0 : -ENOMEM;
-		cache->objects[cache->nobjs++] = page;
-	}
-	return 0;
-}
-
-static void mmu_free_memory_cache_page(struct kvm_mmu_memory_cache *mc)
-{
-	while (mc->nobjs)
-		free_page((unsigned long)mc->objects[--mc->nobjs]);
-}
-
-static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu)
+static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect)
 {
 	int r;
 
-	r = mmu_topup_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache,
-				   pte_list_desc_cache, 8 + PTE_PREFETCH_NUM);
+	/* 1 rmap, 1 parent PTE per level, and the prefetched rmaps. */
+	r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache,
+				       1 + PT64_ROOT_MAX_LEVEL + PTE_PREFETCH_NUM);
 	if (r)
-		goto out;
-	r = mmu_topup_memory_cache_page(&vcpu->arch.mmu_page_cache, 8);
+		return r;
+	r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache,
+				       PT64_ROOT_MAX_LEVEL);
 	if (r)
-		goto out;
-	r = mmu_topup_memory_cache(&vcpu->arch.mmu_page_header_cache,
-				   mmu_page_header_cache, 4);
-out:
-	return r;
+		return r;
+	if (maybe_indirect) {
+		r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_gfn_array_cache,
+					       PT64_ROOT_MAX_LEVEL);
+		if (r)
+			return r;
+	}
+	return kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_page_header_cache,
+					  PT64_ROOT_MAX_LEVEL);
 }
 
 static void mmu_free_memory_caches(struct kvm_vcpu *vcpu)
 {
-	mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache,
-				pte_list_desc_cache);
-	mmu_free_memory_cache_page(&vcpu->arch.mmu_page_cache);
-	mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache,
-				mmu_page_header_cache);
-}
-
-static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
-{
-	void *p;
-
-	BUG_ON(!mc->nobjs);
-	p = mc->objects[--mc->nobjs];
-	return p;
+	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache);
+	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadow_page_cache);
+	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_gfn_array_cache);
+	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache);
 }
 
 static struct pte_list_desc *mmu_alloc_pte_list_desc(struct kvm_vcpu *vcpu)
 {
-	return mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache);
+	return kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_pte_list_desc_cache);
 }
 
 static void mmu_free_pte_list_desc(struct pte_list_desc *pte_list_desc)
@@ -1415,10 +1375,10 @@ static struct kvm_rmap_head *gfn_to_rmap(struct kvm *kvm, gfn_t gfn,
 
 static bool rmap_can_add(struct kvm_vcpu *vcpu)
 {
-	struct kvm_mmu_memory_cache *cache;
+	struct kvm_mmu_memory_cache *mc;
 
-	cache = &vcpu->arch.mmu_pte_list_desc_cache;
-	return mmu_memory_cache_free_objects(cache);
+	mc = &vcpu->arch.mmu_pte_list_desc_cache;
+	return kvm_mmu_memory_cache_nr_free_objects(mc);
 }
 
 static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
@@ -1426,7 +1386,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 	struct kvm_mmu_page *sp;
 	struct kvm_rmap_head *rmap_head;
 
-	sp = page_header(__pa(spte));
+	sp = sptep_to_sp(spte);
 	kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn);
 	rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp);
 	return pte_list_add(vcpu, spte, rmap_head);
@@ -1438,7 +1398,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
 	gfn_t gfn;
 	struct kvm_rmap_head *rmap_head;
 
-	sp = page_header(__pa(spte));
+	sp = sptep_to_sp(spte);
 	gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
 	rmap_head = gfn_to_rmap(kvm, gfn, sp);
 	__pte_list_remove(spte, rmap_head);
@@ -1530,7 +1490,7 @@ static void drop_spte(struct kvm *kvm, u64 *sptep)
 static bool __drop_large_spte(struct kvm *kvm, u64 *sptep)
 {
 	if (is_large_pte(*sptep)) {
-		WARN_ON(page_header(__pa(sptep))->role.level == PG_LEVEL_4K);
+		WARN_ON(sptep_to_sp(sptep)->role.level == PG_LEVEL_4K);
 		drop_spte(kvm, sptep);
 		--kvm->stat.lpages;
 		return true;
@@ -1542,7 +1502,7 @@ static bool __drop_large_spte(struct kvm *kvm, u64 *sptep)
 static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
 {
 	if (__drop_large_spte(vcpu->kvm, sptep)) {
-		struct kvm_mmu_page *sp = page_header(__pa(sptep));
+		struct kvm_mmu_page *sp = sptep_to_sp(sptep);
 
 		kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn,
 			KVM_PAGES_PER_HPAGE(sp->role.level));
@@ -1738,21 +1698,6 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
 }
 
-/**
- * kvm_arch_write_log_dirty - emulate dirty page logging
- * @vcpu: Guest mode vcpu
- *
- * Emulate arch specific page modification logging for the
- * nested hypervisor
- */
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa)
-{
-	if (kvm_x86_ops.write_log_dirty)
-		return kvm_x86_ops.write_log_dirty(vcpu, l2_gpa);
-
-	return 0;
-}
-
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn)
 {
@@ -2016,7 +1961,7 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 	struct kvm_rmap_head *rmap_head;
 	struct kvm_mmu_page *sp;
 
-	sp = page_header(__pa(spte));
+	sp = sptep_to_sp(spte);
 
 	rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp);
 
@@ -2105,10 +2050,10 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct
 {
 	struct kvm_mmu_page *sp;
 
-	sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache);
-	sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
+	sp = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache);
+	sp->spt = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_shadow_page_cache);
 	if (!direct)
-		sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
+		sp->gfns = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_gfn_array_cache);
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 
 	/*
@@ -2138,7 +2083,7 @@ static void mark_unsync(u64 *spte)
 	struct kvm_mmu_page *sp;
 	unsigned int index;
 
-	sp = page_header(__pa(spte));
+	sp = sptep_to_sp(spte);
 	index = spte - sp->spt;
 	if (__test_and_set_bit(index, sp->unsync_child_bitmap))
 		return;
@@ -2207,7 +2152,7 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
 			continue;
 		}
 
-		child = page_header(ent & PT64_BASE_ADDR_MASK);
+		child = to_shadow_page(ent & PT64_BASE_ADDR_MASK);
 
 		if (child->unsync_children) {
 			if (mmu_pages_add(pvec, child, i))
@@ -2258,15 +2203,14 @@ static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 				    struct list_head *invalid_list);
 
-
-#define for_each_valid_sp(_kvm, _sp, _gfn)				\
-	hlist_for_each_entry(_sp,					\
-	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
+#define for_each_valid_sp(_kvm, _sp, _list)				\
+	hlist_for_each_entry(_sp, _list, hash_link)			\
 		if (is_obsolete_sp((_kvm), (_sp))) {			\
 		} else
 
 #define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn)			\
-	for_each_valid_sp(_kvm, _sp, _gfn)				\
+	for_each_valid_sp(_kvm, _sp,					\
+	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)])	\
 		if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else
 
 static inline bool is_ept_sp(struct kvm_mmu_page *sp)
@@ -2464,9 +2408,7 @@ static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp)
 
 static void clear_sp_write_flooding_count(u64 *spte)
 {
-	struct kvm_mmu_page *sp =  page_header(__pa(spte));
-
-	__clear_sp_write_flooding_count(sp);
+	__clear_sp_write_flooding_count(sptep_to_sp(spte));
 }
 
 static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
@@ -2476,7 +2418,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 					     int direct,
 					     unsigned int access)
 {
+	bool direct_mmu = vcpu->arch.mmu->direct_map;
 	union kvm_mmu_page_role role;
+	struct hlist_head *sp_list;
 	unsigned quadrant;
 	struct kvm_mmu_page *sp;
 	bool need_sync = false;
@@ -2490,13 +2434,14 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	if (role.direct)
 		role.gpte_is_8_bytes = true;
 	role.access = access;
-	if (!vcpu->arch.mmu->direct_map
-	    && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
+	if (!direct_mmu && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
 		quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
 		quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
 		role.quadrant = quadrant;
 	}
-	for_each_valid_sp(vcpu->kvm, sp, gfn) {
+
+	sp_list = &vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)];
+	for_each_valid_sp(vcpu->kvm, sp, sp_list) {
 		if (sp->gfn != gfn) {
 			collisions++;
 			continue;
@@ -2508,6 +2453,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		if (sp->role.word != role.word)
 			continue;
 
+		if (direct_mmu)
+			goto trace_get_page;
+
 		if (sp->unsync) {
 			/* The page is good, but __kvm_sync_page might still end
 			 * up zapping it.  If so, break in order to rebuild it.
@@ -2523,6 +2471,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 
 		__clear_sp_write_flooding_count(sp);
+
+trace_get_page:
 		trace_kvm_mmu_get_page(sp, false);
 		goto out;
 	}
@@ -2533,8 +2483,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 
 	sp->gfn = gfn;
 	sp->role = role;
-	hlist_add_head(&sp->hash_link,
-		&vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]);
+	hlist_add_head(&sp->hash_link, sp_list);
 	if (!direct) {
 		/*
 		 * we should do write protection before syncing pages
@@ -2548,7 +2497,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		if (level > PG_LEVEL_4K && need_sync)
 			flush |= kvm_sync_pages(vcpu, gfn, &invalid_list);
 	}
-	clear_page(sp->spt);
 	trace_kvm_mmu_get_page(sp, true);
 
 	kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush);
@@ -2657,7 +2605,7 @@ 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 = page_header(*sptep & PT64_BASE_ADDR_MASK);
+		child = to_shadow_page(*sptep & PT64_BASE_ADDR_MASK);
 		if (child->role.access == direct_access)
 			return;
 
@@ -2679,7 +2627,7 @@ static bool mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 			if (is_large_pte(pte))
 				--kvm->stat.lpages;
 		} else {
-			child = page_header(pte & PT64_BASE_ADDR_MASK);
+			child = to_shadow_page(pte & PT64_BASE_ADDR_MASK);
 			drop_parent_pte(child, spte);
 		}
 		return true;
@@ -2757,10 +2705,23 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 	if (!sp->root_count) {
 		/* Count self */
 		(*nr_zapped)++;
-		list_move(&sp->link, invalid_list);
+
+		/*
+		 * Already invalid pages (previously active roots) are not on
+		 * the active page list.  See list_del() in the "else" case of
+		 * !sp->root_count.
+		 */
+		if (sp->role.invalid)
+			list_add(&sp->link, invalid_list);
+		else
+			list_move(&sp->link, invalid_list);
 		kvm_mod_used_mmu_pages(kvm, -1);
 	} else {
-		list_move(&sp->link, &kvm->arch.active_mmu_pages);
+		/*
+		 * Remove the active root from the active page list, the root
+		 * will be explicitly freed when the root_count hits zero.
+		 */
+		list_del(&sp->link);
 
 		/*
 		 * Obsolete pages cannot be used on any vCPUs, see the comment
@@ -2812,33 +2773,60 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 	}
 }
 
-static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
-					struct list_head *invalid_list)
+static unsigned long kvm_mmu_zap_oldest_mmu_pages(struct kvm *kvm,
+						  unsigned long nr_to_zap)
 {
-	struct kvm_mmu_page *sp;
+	unsigned long total_zapped = 0;
+	struct kvm_mmu_page *sp, *tmp;
+	LIST_HEAD(invalid_list);
+	bool unstable;
+	int nr_zapped;
 
 	if (list_empty(&kvm->arch.active_mmu_pages))
-		return false;
+		return 0;
+
+restart:
+	list_for_each_entry_safe(sp, tmp, &kvm->arch.active_mmu_pages, link) {
+		/*
+		 * Don't zap active root pages, the page itself can't be freed
+		 * and zapping it will just force vCPUs to realloc and reload.
+		 */
+		if (sp->root_count)
+			continue;
+
+		unstable = __kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list,
+						      &nr_zapped);
+		total_zapped += nr_zapped;
+		if (total_zapped >= nr_to_zap)
+			break;
+
+		if (unstable)
+			goto restart;
+	}
 
-	sp = list_last_entry(&kvm->arch.active_mmu_pages,
-			     struct kvm_mmu_page, link);
-	return kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
+	kvm_mmu_commit_zap_page(kvm, &invalid_list);
+
+	kvm->stat.mmu_recycled += total_zapped;
+	return total_zapped;
+}
+
+static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
+{
+	if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
+		return kvm->arch.n_max_mmu_pages -
+			kvm->arch.n_used_mmu_pages;
+
+	return 0;
 }
 
 static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
 {
-	LIST_HEAD(invalid_list);
+	unsigned long avail = kvm_mmu_available_pages(vcpu->kvm);
 
-	if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES))
+	if (likely(avail >= KVM_MIN_FREE_MMU_PAGES))
 		return 0;
 
-	while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) {
-		if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list))
-			break;
-
-		++vcpu->kvm->stat.mmu_recycled;
-	}
-	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
+	kvm_mmu_zap_oldest_mmu_pages(vcpu->kvm, KVM_REFILL_PAGES - avail);
 
 	if (!kvm_mmu_available_pages(vcpu->kvm))
 		return -ENOSPC;
@@ -2851,17 +2839,12 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
  */
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
 {
-	LIST_HEAD(invalid_list);
-
 	spin_lock(&kvm->mmu_lock);
 
 	if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) {
-		/* Need to free some mmu pages to achieve the goal. */
-		while (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages)
-			if (!prepare_zap_oldest_mmu_page(kvm, &invalid_list))
-				break;
+		kvm_mmu_zap_oldest_mmu_pages(kvm, kvm->arch.n_used_mmu_pages -
+						  goal_nr_mmu_pages);
 
-		kvm_mmu_commit_zap_page(kvm, &invalid_list);
 		goal_nr_mmu_pages = kvm->arch.n_used_mmu_pages;
 	}
 
@@ -2999,7 +2982,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access))
 		return 0;
 
-	sp = page_header(__pa(sptep));
+	sp = sptep_to_sp(sptep);
 	if (sp_ad_disabled(sp))
 		spte |= SPTE_AD_DISABLED_MASK;
 	else if (kvm_vcpu_ad_need_write_protect(vcpu))
@@ -3102,7 +3085,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			struct kvm_mmu_page *child;
 			u64 pte = *sptep;
 
-			child = page_header(pte & PT64_BASE_ADDR_MASK);
+			child = to_shadow_page(pte & PT64_BASE_ADDR_MASK);
 			drop_parent_pte(child, sptep);
 			flush = true;
 		} else if (pfn != spte_to_pfn(*sptep)) {
@@ -3212,7 +3195,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 {
 	struct kvm_mmu_page *sp;
 
-	sp = page_header(__pa(sptep));
+	sp = sptep_to_sp(sptep);
 
 	/*
 	 * Without accessed bits, there's no way to distinguish between
@@ -3274,7 +3257,7 @@ static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
 	if (!slot)
 		return PG_LEVEL_4K;
 
-	max_level = min(max_level, max_page_level);
+	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)
@@ -3520,7 +3503,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			if (!is_shadow_present_pte(spte))
 				break;
 
-		sp = page_header(__pa(iterator.sptep));
+		sp = sptep_to_sp(iterator.sptep);
 		if (!is_last_spte(spte, sp->role.level))
 			break;
 
@@ -3607,7 +3590,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
 	if (!VALID_PAGE(*root_hpa))
 		return;
 
-	sp = page_header(*root_hpa & PT64_BASE_ADDR_MASK);
+	sp = to_shadow_page(*root_hpa & PT64_BASE_ADDR_MASK);
 	--sp->root_count;
 	if (!sp->root_count && sp->role.invalid)
 		kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
@@ -3668,7 +3651,7 @@ static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn)
 {
 	int ret = 0;
 
-	if (!kvm_is_visible_gfn(vcpu->kvm, root_gfn)) {
+	if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) {
 		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 		ret = 1;
 	}
@@ -3837,7 +3820,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 
 	if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
 		hpa_t root = vcpu->arch.mmu->root_hpa;
-		sp = page_header(root);
+		sp = to_shadow_page(root);
 
 		/*
 		 * Even if another CPU was marking the SP as unsync-ed
@@ -3871,7 +3854,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 
 		if (root && VALID_PAGE(root)) {
 			root &= PT64_BASE_ADDR_MASK;
-			sp = page_header(root);
+			sp = to_shadow_page(root);
 			mmu_sync_children(vcpu, sp);
 		}
 	}
@@ -4045,8 +4028,8 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
 	walk_shadow_page_lockless_end(vcpu);
 }
 
-static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
-				   gfn_t gfn)
+static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+				    gfn_t gfn)
 {
 	struct kvm_arch_async_pf arch;
 
@@ -4108,16 +4091,16 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	if (page_fault_handle_page_track(vcpu, error_code, gfn))
 		return RET_PF_EMULATE;
 
-	r = mmu_topup_memory_caches(vcpu);
+	if (fast_page_fault(vcpu, gpa, error_code))
+		return RET_PF_RETRY;
+
+	r = mmu_topup_memory_caches(vcpu, false);
 	if (r)
 		return r;
 
 	if (lpage_disallowed)
 		max_level = PG_LEVEL_4K;
 
-	if (fast_page_fault(vcpu, gpa, error_code))
-		return RET_PF_RETRY;
-
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
@@ -4131,7 +4114,8 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	spin_lock(&vcpu->kvm->mmu_lock);
 	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
-	if (make_mmu_pages_available(vcpu) < 0)
+	r = make_mmu_pages_available(vcpu);
+	if (r)
 		goto out_unlock;
 	r = __direct_map(vcpu, gpa, write, map_writable, max_level, pfn,
 			 prefault, is_tdp && lpage_disallowed);
@@ -4156,6 +4140,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 				u64 fault_address, char *insn, int insn_len)
 {
 	int r = 1;
+	u32 flags = vcpu->arch.apf.host_apf_flags;
 
 #ifndef CONFIG_X86_64
 	/* A 64-bit CR2 should be impossible on 32-bit KVM. */
@@ -4164,28 +4149,22 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 #endif
 
 	vcpu->arch.l1tf_flush_l1d = true;
-	switch (vcpu->arch.apf.host_apf_flags) {
-	default:
+	if (!flags) {
 		trace_kvm_page_fault(fault_address, error_code);
 
 		if (kvm_event_needs_reinjection(vcpu))
 			kvm_mmu_unprotect_page_virt(vcpu, fault_address);
 		r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn,
 				insn_len);
-		break;
-	case KVM_PV_REASON_PAGE_NOT_PRESENT:
+	} else if (flags & KVM_PV_REASON_PAGE_NOT_PRESENT) {
 		vcpu->arch.apf.host_apf_flags = 0;
 		local_irq_disable();
 		kvm_async_pf_task_wait_schedule(fault_address);
 		local_irq_enable();
-		break;
-	case KVM_PV_REASON_PAGE_READY:
-		vcpu->arch.apf.host_apf_flags = 0;
-		local_irq_disable();
-		kvm_async_pf_task_wake(fault_address);
-		local_irq_enable();
-		break;
+	} else {
+		WARN_ONCE(1, "Unexpected host async PF flags: %x\n", flags);
 	}
+
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_handle_page_fault);
@@ -4227,8 +4206,8 @@ static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd,
 				  union kvm_mmu_page_role role)
 {
 	return (role.direct || pgd == root->pgd) &&
-	       VALID_PAGE(root->hpa) && page_header(root->hpa) &&
-	       role.word == page_header(root->hpa)->role.word;
+	       VALID_PAGE(root->hpa) && to_shadow_page(root->hpa) &&
+	       role.word == to_shadow_page(root->hpa)->role.word;
 }
 
 /*
@@ -4277,8 +4256,7 @@ static bool fast_pgd_switch(struct kvm_vcpu *vcpu, gpa_t new_pgd,
 	 */
 	if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL &&
 	    mmu->root_level >= PT64_ROOT_4LEVEL)
-		return !mmu_check_root(vcpu, new_pgd >> PAGE_SHIFT) &&
-		       cached_root_available(vcpu, new_pgd, new_role);
+		return cached_root_available(vcpu, new_pgd, new_role);
 
 	return false;
 }
@@ -4313,7 +4291,7 @@ static void __kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd,
 	 */
 	vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
 
-	__clear_sp_write_flooding_count(page_header(vcpu->arch.mmu->root_hpa));
+	__clear_sp_write_flooding_count(to_shadow_page(vcpu->arch.mmu->root_hpa));
 }
 
 void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush,
@@ -4869,13 +4847,22 @@ static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu,
 	return role;
 }
 
+static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu)
+{
+	/* Use 5-level TDP if and only if it's useful/necessary. */
+	if (max_tdp_level == 5 && cpuid_maxphyaddr(vcpu) <= 48)
+		return 4;
+
+	return max_tdp_level;
+}
+
 static union kvm_mmu_role
 kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
 {
 	union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only);
 
 	role.base.ad_disabled = (shadow_accessed_mask == 0);
-	role.base.level = vcpu->arch.tdp_level;
+	role.base.level = kvm_mmu_get_tdp_level(vcpu);
 	role.base.direct = true;
 	role.base.gpte_is_8_bytes = true;
 
@@ -4884,7 +4871,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
 
 static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 {
-	struct kvm_mmu *context = vcpu->arch.mmu;
+	struct kvm_mmu *context = &vcpu->arch.root_mmu;
 	union kvm_mmu_role new_role =
 		kvm_calc_tdp_mmu_root_page_role(vcpu, false);
 
@@ -4896,7 +4883,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = NULL;
 	context->update_pte = nonpaging_update_pte;
-	context->shadow_root_level = vcpu->arch.tdp_level;
+	context->shadow_root_level = kvm_mmu_get_tdp_level(vcpu);
 	context->direct_map = true;
 	context->get_guest_pgd = get_cr3;
 	context->get_pdptr = kvm_pdptr_read;
@@ -4931,7 +4918,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 }
 
 static union kvm_mmu_role
-kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
+kvm_calc_shadow_root_page_role_common(struct kvm_vcpu *vcpu, bool base_only)
 {
 	union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only);
 
@@ -4939,9 +4926,19 @@ kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
 		!is_write_protection(vcpu);
 	role.base.smap_andnot_wp = role.ext.cr4_smap &&
 		!is_write_protection(vcpu);
-	role.base.direct = !is_paging(vcpu);
 	role.base.gpte_is_8_bytes = !!is_pae(vcpu);
 
+	return role;
+}
+
+static union kvm_mmu_role
+kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
+{
+	union kvm_mmu_role role =
+		kvm_calc_shadow_root_page_role_common(vcpu, base_only);
+
+	role.base.direct = !is_paging(vcpu);
+
 	if (!is_long_mode(vcpu))
 		role.base.level = PT32E_ROOT_LEVEL;
 	else if (is_la57_mode(vcpu))
@@ -4952,15 +4949,10 @@ kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
 	return role;
 }
 
-void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer)
+static void shadow_mmu_init_context(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
+				    u32 cr0, u32 cr4, u32 efer,
+				    union kvm_mmu_role new_role)
 {
-	struct kvm_mmu *context = vcpu->arch.mmu;
-	union kvm_mmu_role new_role =
-		kvm_calc_shadow_mmu_root_page_role(vcpu, false);
-
-	if (new_role.as_u64 == context->mmu_role.as_u64)
-		return;
-
 	if (!(cr0 & X86_CR0_PG))
 		nonpaging_init_context(vcpu, context);
 	else if (efer & EFER_LMA)
@@ -4973,7 +4965,43 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer)
 	context->mmu_role.as_u64 = new_role.as_u64;
 	reset_shadow_zero_bits_mask(vcpu, context);
 }
-EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
+
+static void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer)
+{
+	struct kvm_mmu *context = &vcpu->arch.root_mmu;
+	union kvm_mmu_role new_role =
+		kvm_calc_shadow_mmu_root_page_role(vcpu, false);
+
+	if (new_role.as_u64 != context->mmu_role.as_u64)
+		shadow_mmu_init_context(vcpu, context, cr0, cr4, efer, new_role);
+}
+
+static union kvm_mmu_role
+kvm_calc_shadow_npt_root_page_role(struct kvm_vcpu *vcpu)
+{
+	union kvm_mmu_role role =
+		kvm_calc_shadow_root_page_role_common(vcpu, false);
+
+	role.base.direct = false;
+	role.base.level = kvm_mmu_get_tdp_level(vcpu);
+
+	return role;
+}
+
+void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, u32 cr0, u32 cr4, u32 efer,
+			     gpa_t nested_cr3)
+{
+	struct kvm_mmu *context = &vcpu->arch.guest_mmu;
+	union kvm_mmu_role new_role = kvm_calc_shadow_npt_root_page_role(vcpu);
+
+	context->shadow_root_level = new_role.base.level;
+
+	__kvm_mmu_new_pgd(vcpu, nested_cr3, new_role.base, false, false);
+
+	if (new_role.as_u64 != context->mmu_role.as_u64)
+		shadow_mmu_init_context(vcpu, context, cr0, cr4, efer, new_role);
+}
+EXPORT_SYMBOL_GPL(kvm_init_shadow_npt_mmu);
 
 static union kvm_mmu_role
 kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
@@ -5007,7 +5035,7 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 			     bool accessed_dirty, gpa_t new_eptp)
 {
-	struct kvm_mmu *context = vcpu->arch.mmu;
+	struct kvm_mmu *context = &vcpu->arch.guest_mmu;
 	u8 level = vmx_eptp_page_walk_level(new_eptp);
 	union kvm_mmu_role new_role =
 		kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty,
@@ -5041,7 +5069,7 @@ EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
 
 static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
 {
-	struct kvm_mmu *context = vcpu->arch.mmu;
+	struct kvm_mmu *context = &vcpu->arch.root_mmu;
 
 	kvm_init_shadow_mmu(vcpu,
 			    kvm_read_cr0_bits(vcpu, X86_CR0_PG),
@@ -5151,7 +5179,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
 {
 	int r;
 
-	r = mmu_topup_memory_caches(vcpu);
+	r = mmu_topup_memory_caches(vcpu, !vcpu->arch.mmu->direct_map);
 	if (r)
 		goto out;
 	r = mmu_alloc_roots(vcpu);
@@ -5345,7 +5373,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	 * or not since pte prefetch is skiped if it does not have
 	 * enough objects in the cache.
 	 */
-	mmu_topup_memory_caches(vcpu);
+	mmu_topup_memory_caches(vcpu, true);
 
 	spin_lock(&vcpu->kvm->mmu_lock);
 
@@ -5553,23 +5581,25 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_invpcid_gva);
 
-void kvm_configure_mmu(bool enable_tdp, int tdp_page_level)
+void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level,
+		       int tdp_huge_page_level)
 {
 	tdp_enabled = enable_tdp;
+	max_tdp_level = tdp_max_root_level;
 
 	/*
-	 * max_page_level reflects the capabilities of KVM's MMU irrespective
+	 * max_huge_page_level reflects KVM's MMU capabilities irrespective
 	 * of kernel support, e.g. KVM may be capable of using 1GB pages when
 	 * the kernel is not.  But, KVM never creates a page size greater than
 	 * what is used by the kernel for any given HVA, i.e. the kernel's
 	 * capabilities are ultimately consulted by kvm_mmu_hugepage_adjust().
 	 */
 	if (tdp_enabled)
-		max_page_level = tdp_page_level;
+		max_huge_page_level = tdp_huge_page_level;
 	else if (boot_cpu_has(X86_FEATURE_GBPAGES))
-		max_page_level = PG_LEVEL_1G;
+		max_huge_page_level = PG_LEVEL_1G;
 	else
-		max_page_level = PG_LEVEL_2M;
+		max_huge_page_level = PG_LEVEL_2M;
 }
 EXPORT_SYMBOL_GPL(kvm_configure_mmu);
 
@@ -5665,7 +5695,7 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
 	 * SVM's 32-bit NPT support, TDP paging doesn't use PAE paging and can
 	 * skip allocating the PDP table.
 	 */
-	if (tdp_enabled && vcpu->arch.tdp_level > PT32E_ROOT_LEVEL)
+	if (tdp_enabled && kvm_mmu_get_tdp_level(vcpu) > PT32E_ROOT_LEVEL)
 		return 0;
 
 	page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_DMA32);
@@ -5684,6 +5714,14 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 	uint i;
 	int ret;
 
+	vcpu->arch.mmu_pte_list_desc_cache.kmem_cache = pte_list_desc_cache;
+	vcpu->arch.mmu_pte_list_desc_cache.gfp_zero = __GFP_ZERO;
+
+	vcpu->arch.mmu_page_header_cache.kmem_cache = mmu_page_header_cache;
+	vcpu->arch.mmu_page_header_cache.gfp_zero = __GFP_ZERO;
+
+	vcpu->arch.mmu_shadow_page_cache.gfp_zero = __GFP_ZERO;
+
 	vcpu->arch.mmu = &vcpu->arch.root_mmu;
 	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
 
@@ -5732,12 +5770,11 @@ restart:
 			break;
 
 		/*
-		 * Skip invalid pages with a non-zero root count, zapping pages
-		 * with a non-zero root count will never succeed, i.e. the page
-		 * will get thrown back on active_mmu_pages and we'll get stuck
-		 * in an infinite loop.
+		 * Invalid pages should never land back on the list of active
+		 * pages.  Skip the bogus page, otherwise we'll get stuck in an
+		 * infinite loop if the page gets put back on the list (again).
 		 */
-		if (sp->role.invalid && sp->root_count)
+		if (WARN_ON(sp->role.invalid))
 			continue;
 
 		/*
@@ -5904,7 +5941,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 
 restart:
 	for_each_rmap_spte(rmap_head, &iter, sptep) {
-		sp = page_header(__pa(sptep));
+		sp = sptep_to_sp(sptep);
 		pfn = spte_to_pfn(*sptep);
 
 		/*
@@ -6015,7 +6052,7 @@ void kvm_mmu_zap_all(struct kvm *kvm)
 	spin_lock(&kvm->mmu_lock);
 restart:
 	list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) {
-		if (sp->role.invalid && sp->root_count)
+		if (WARN_ON(sp->role.invalid))
 			continue;
 		if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign))
 			goto restart;
@@ -6092,9 +6129,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 			goto unlock;
 		}
 
-		if (prepare_zap_oldest_mmu_page(kvm, &invalid_list))
-			freed++;
-		kvm_mmu_commit_zap_page(kvm, &invalid_list);
+		freed = kvm_mmu_zap_oldest_mmu_pages(kvm, sc->nr_to_scan);
 
 unlock:
 		spin_unlock(&kvm->mmu_lock);