1 files changed, 422 insertions, 132 deletions

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index b56d604809b8..71e100a5670f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -7,32 +7,23 @@
 #include "tdp_mmu.h"
 #include "spte.h"
 
+#include <asm/cmpxchg.h>
 #include <trace/events/kvm.h>
 
-#ifdef CONFIG_X86_64
 static bool __read_mostly tdp_mmu_enabled = false;
 module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644);
-#endif
-
-static bool is_tdp_mmu_enabled(void)
-{
-#ifdef CONFIG_X86_64
-	return tdp_enabled && READ_ONCE(tdp_mmu_enabled);
-#else
-	return false;
-#endif /* CONFIG_X86_64 */
-}
 
 /* Initializes the TDP MMU for the VM, if enabled. */
 void kvm_mmu_init_tdp_mmu(struct kvm *kvm)
 {
-	if (!is_tdp_mmu_enabled())
+	if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled))
 		return;
 
 	/* This should not be changed for the lifetime of the VM. */
 	kvm->arch.tdp_mmu_enabled = true;
 
 	INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
+	spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
 	INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages);
 }
 
@@ -42,6 +33,12 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 		return;
 
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
+
+	/*
+	 * Ensure that all the outstanding RCU callbacks to free shadow pages
+	 * can run before the VM is torn down.
+	 */
+	rcu_barrier();
 }
 
 static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
@@ -53,7 +50,7 @@ static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
 static inline bool tdp_mmu_next_root_valid(struct kvm *kvm,
 					   struct kvm_mmu_page *root)
 {
-	lockdep_assert_held(&kvm->mmu_lock);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	if (list_entry_is_head(root, &kvm->arch.tdp_mmu_roots, link))
 		return false;
@@ -88,22 +85,6 @@ static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 #define for_each_tdp_mmu_root(_kvm, _root)				\
 	list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link)
 
-bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa)
-{
-	struct kvm_mmu_page *sp;
-
-	if (!kvm->arch.tdp_mmu_enabled)
-		return false;
-	if (WARN_ON(!VALID_PAGE(hpa)))
-		return false;
-
-	sp = to_shadow_page(hpa);
-	if (WARN_ON(!sp))
-		return false;
-
-	return sp->tdp_mmu_page && sp->root_count;
-}
-
 static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 			  gfn_t start, gfn_t end, bool can_yield);
 
@@ -111,7 +92,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
 	gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
 
-	lockdep_assert_held(&kvm->mmu_lock);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	WARN_ON(root->root_count);
 	WARN_ON(!root->tdp_mmu_page);
@@ -164,13 +145,13 @@ static struct kvm_mmu_page *get_tdp_mmu_vcpu_root(struct kvm_vcpu *vcpu)
 
 	role = page_role_for_level(vcpu, vcpu->arch.mmu->shadow_root_level);
 
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 
 	/* Check for an existing root before allocating a new one. */
 	for_each_tdp_mmu_root(kvm, root) {
 		if (root->role.word == role.word) {
 			kvm_mmu_get_root(kvm, root);
-			spin_unlock(&kvm->mmu_lock);
+			write_unlock(&kvm->mmu_lock);
 			return root;
 		}
 	}
@@ -180,7 +161,7 @@ static struct kvm_mmu_page *get_tdp_mmu_vcpu_root(struct kvm_vcpu *vcpu)
 
 	list_add(&root->link, &kvm->arch.tdp_mmu_roots);
 
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 
 	return root;
 }
@@ -196,8 +177,31 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
 	return __pa(root->spt);
 }
 
+static void tdp_mmu_free_sp(struct kvm_mmu_page *sp)
+{
+	free_page((unsigned long)sp->spt);
+	kmem_cache_free(mmu_page_header_cache, sp);
+}
+
+/*
+ * This is called through call_rcu in order to free TDP page table memory
+ * safely with respect to other kernel threads that may be operating on
+ * the memory.
+ * By only accessing TDP MMU page table memory in an RCU read critical
+ * section, and freeing it after a grace period, lockless access to that
+ * memory won't use it after it is freed.
+ */
+static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
+{
+	struct kvm_mmu_page *sp = container_of(head, struct kvm_mmu_page,
+					       rcu_head);
+
+	tdp_mmu_free_sp(sp);
+}
+
 static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
-				u64 old_spte, u64 new_spte, int level);
+				u64 old_spte, u64 new_spte, int level,
+				bool shared);
 
 static int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
 {
@@ -235,6 +239,128 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
 }
 
 /**
+ * tdp_mmu_link_page - Add a new page to the list of pages used by the TDP MMU
+ *
+ * @kvm: kvm instance
+ * @sp: the new page
+ * @shared: This operation may not be running under the exclusive use of
+ *	    the MMU lock and the operation must synchronize with other
+ *	    threads that might be adding or removing pages.
+ * @account_nx: This page replaces a NX large page and should be marked for
+ *		eventual reclaim.
+ */
+static void tdp_mmu_link_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+			      bool shared, bool account_nx)
+{
+	if (shared)
+		spin_lock(&kvm->arch.tdp_mmu_pages_lock);
+	else
+		lockdep_assert_held_write(&kvm->mmu_lock);
+
+	list_add(&sp->link, &kvm->arch.tdp_mmu_pages);
+	if (account_nx)
+		account_huge_nx_page(kvm, sp);
+
+	if (shared)
+		spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+}
+
+/**
+ * tdp_mmu_unlink_page - Remove page from the list of pages used by the TDP MMU
+ *
+ * @kvm: kvm instance
+ * @sp: the page to be removed
+ * @shared: This operation may not be running under the exclusive use of
+ *	    the MMU lock and the operation must synchronize with other
+ *	    threads that might be adding or removing pages.
+ */
+static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+				bool shared)
+{
+	if (shared)
+		spin_lock(&kvm->arch.tdp_mmu_pages_lock);
+	else
+		lockdep_assert_held_write(&kvm->mmu_lock);
+
+	list_del(&sp->link);
+	if (sp->lpage_disallowed)
+		unaccount_huge_nx_page(kvm, sp);
+
+	if (shared)
+		spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+}
+
+/**
+ * handle_removed_tdp_mmu_page - handle a pt removed from the TDP structure
+ *
+ * @kvm: kvm instance
+ * @pt: the page removed from the paging structure
+ * @shared: This operation may not be running under the exclusive use
+ *	    of the MMU lock and the operation must synchronize with other
+ *	    threads that might be modifying SPTEs.
+ *
+ * Given a page table that has been removed from the TDP paging structure,
+ * iterates through the page table to clear SPTEs and free child page tables.
+ */
+static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
+					bool shared)
+{
+	struct kvm_mmu_page *sp = sptep_to_sp(pt);
+	int level = sp->role.level;
+	gfn_t base_gfn = sp->gfn;
+	u64 old_child_spte;
+	u64 *sptep;
+	gfn_t gfn;
+	int i;
+
+	trace_kvm_mmu_prepare_zap_page(sp);
+
+	tdp_mmu_unlink_page(kvm, sp, shared);
+
+	for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
+		sptep = pt + i;
+		gfn = base_gfn + (i * KVM_PAGES_PER_HPAGE(level - 1));
+
+		if (shared) {
+			/*
+			 * Set the SPTE to a nonpresent value that other
+			 * threads will not overwrite. If the SPTE was
+			 * already marked as removed then another thread
+			 * handling a page fault could overwrite it, so
+			 * set the SPTE until it is set from some other
+			 * value to the removed SPTE value.
+			 */
+			for (;;) {
+				old_child_spte = xchg(sptep, REMOVED_SPTE);
+				if (!is_removed_spte(old_child_spte))
+					break;
+				cpu_relax();
+			}
+		} else {
+			old_child_spte = READ_ONCE(*sptep);
+
+			/*
+			 * Marking the SPTE as a removed SPTE is not
+			 * strictly necessary here as the MMU lock will
+			 * stop other threads from concurrently modifying
+			 * this SPTE. Using the removed SPTE value keeps
+			 * the two branches consistent and simplifies
+			 * the function.
+			 */
+			WRITE_ONCE(*sptep, REMOVED_SPTE);
+		}
+		handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn,
+				    old_child_spte, REMOVED_SPTE, level - 1,
+				    shared);
+	}
+
+	kvm_flush_remote_tlbs_with_address(kvm, gfn,
+					   KVM_PAGES_PER_HPAGE(level));
+
+	call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
+}
+
+/**
  * handle_changed_spte - handle bookkeeping associated with an SPTE change
  * @kvm: kvm instance
  * @as_id: the address space of the paging structure the SPTE was a part of
@@ -242,22 +368,22 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
  * @old_spte: The value of the SPTE before the change
  * @new_spte: The value of the SPTE after the change
  * @level: the level of the PT the SPTE is part of in the paging structure
+ * @shared: This operation may not be running under the exclusive use of
+ *	    the MMU lock and the operation must synchronize with other
+ *	    threads that might be modifying SPTEs.
  *
  * Handle bookkeeping that might result from the modification of a SPTE.
  * This function must be called for all TDP SPTE modifications.
  */
 static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
-				u64 old_spte, u64 new_spte, int level)
+				  u64 old_spte, u64 new_spte, int level,
+				  bool shared)
 {
 	bool was_present = is_shadow_present_pte(old_spte);
 	bool is_present = is_shadow_present_pte(new_spte);
 	bool was_leaf = was_present && is_last_spte(old_spte, level);
 	bool is_leaf = is_present && is_last_spte(new_spte, level);
 	bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
-	u64 *pt;
-	struct kvm_mmu_page *sp;
-	u64 old_child_spte;
-	int i;
 
 	WARN_ON(level > PT64_ROOT_MAX_LEVEL);
 	WARN_ON(level < PG_LEVEL_4K);
@@ -298,15 +424,19 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 	 */
 	if (!was_present && !is_present) {
 		/*
-		 * If this change does not involve a MMIO SPTE, it is
-		 * unexpected. Log the change, though it should not impact the
-		 * guest since both the former and current SPTEs are nonpresent.
+		 * If this change does not involve a MMIO SPTE or removed SPTE,
+		 * it is unexpected. Log the change, though it should not
+		 * impact the guest since both the former and current SPTEs
+		 * are nonpresent.
 		 */
-		if (WARN_ON(!is_mmio_spte(old_spte) && !is_mmio_spte(new_spte)))
+		if (WARN_ON(!is_mmio_spte(old_spte) &&
+			    !is_mmio_spte(new_spte) &&
+			    !is_removed_spte(new_spte)))
 			pr_err("Unexpected SPTE change! Nonpresent SPTEs\n"
 			       "should not be replaced with another,\n"
 			       "different nonpresent SPTE, unless one or both\n"
-			       "are MMIO SPTEs.\n"
+			       "are MMIO SPTEs, or the new SPTE is\n"
+			       "a temporary removed SPTE.\n"
 			       "as_id: %d gfn: %llx old_spte: %llx new_spte: %llx level: %d",
 			       as_id, gfn, old_spte, new_spte, level);
 		return;
@@ -321,54 +451,127 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 	 * Recursively handle child PTs if the change removed a subtree from
 	 * the paging structure.
 	 */
-	if (was_present && !was_leaf && (pfn_changed || !is_present)) {
-		pt = spte_to_child_pt(old_spte, level);
-		sp = sptep_to_sp(pt);
+	if (was_present && !was_leaf && (pfn_changed || !is_present))
+		handle_removed_tdp_mmu_page(kvm,
+				spte_to_child_pt(old_spte, level), shared);
+}
 
-		trace_kvm_mmu_prepare_zap_page(sp);
+static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
+				u64 old_spte, u64 new_spte, int level,
+				bool shared)
+{
+	__handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level,
+			      shared);
+	handle_changed_spte_acc_track(old_spte, new_spte, level);
+	handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte,
+				      new_spte, level);
+}
 
-		list_del(&sp->link);
+/*
+ * tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically and handle the
+ * associated bookkeeping
+ *
+ * @kvm: kvm instance
+ * @iter: a tdp_iter instance currently on the SPTE that should be set
+ * @new_spte: The value the SPTE should be set to
+ * Returns: true if the SPTE was set, false if it was not. If false is returned,
+ *	    this function will have no side-effects.
+ */
+static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
+					   struct tdp_iter *iter,
+					   u64 new_spte)
+{
+	u64 *root_pt = tdp_iter_root_pt(iter);
+	struct kvm_mmu_page *root = sptep_to_sp(root_pt);
+	int as_id = kvm_mmu_page_as_id(root);
 
-		if (sp->lpage_disallowed)
-			unaccount_huge_nx_page(kvm, sp);
+	lockdep_assert_held_read(&kvm->mmu_lock);
 
-		for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
-			old_child_spte = READ_ONCE(*(pt + i));
-			WRITE_ONCE(*(pt + i), 0);
-			handle_changed_spte(kvm, as_id,
-				gfn + (i * KVM_PAGES_PER_HPAGE(level - 1)),
-				old_child_spte, 0, level - 1);
-		}
+	/*
+	 * Do not change removed SPTEs. Only the thread that froze the SPTE
+	 * may modify it.
+	 */
+	if (iter->old_spte == REMOVED_SPTE)
+		return false;
 
-		kvm_flush_remote_tlbs_with_address(kvm, gfn,
-						   KVM_PAGES_PER_HPAGE(level));
+	if (cmpxchg64(rcu_dereference(iter->sptep), iter->old_spte,
+		      new_spte) != iter->old_spte)
+		return false;
 
-		free_page((unsigned long)pt);
-		kmem_cache_free(mmu_page_header_cache, sp);
-	}
+	handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
+			    iter->level, true);
+
+	return true;
 }
 
-static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
-				u64 old_spte, u64 new_spte, int level)
+static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm,
+					   struct tdp_iter *iter)
 {
-	__handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level);
-	handle_changed_spte_acc_track(old_spte, new_spte, level);
-	handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte,
-				      new_spte, level);
+	/*
+	 * Freeze the SPTE by setting it to a special,
+	 * non-present value. This will stop other threads from
+	 * immediately installing a present entry in its place
+	 * before the TLBs are flushed.
+	 */
+	if (!tdp_mmu_set_spte_atomic(kvm, iter, REMOVED_SPTE))
+		return false;
+
+	kvm_flush_remote_tlbs_with_address(kvm, iter->gfn,
+					   KVM_PAGES_PER_HPAGE(iter->level));
+
+	/*
+	 * No other thread can overwrite the removed SPTE as they
+	 * must either wait on the MMU lock or use
+	 * tdp_mmu_set_spte_atomic which will not overrite the
+	 * special removed SPTE value. No bookkeeping is needed
+	 * here since the SPTE is going from non-present
+	 * to non-present.
+	 */
+	WRITE_ONCE(*iter->sptep, 0);
+
+	return true;
 }
 
+
+/*
+ * __tdp_mmu_set_spte - Set a TDP MMU SPTE and handle the associated bookkeeping
+ * @kvm: kvm instance
+ * @iter: a tdp_iter instance currently on the SPTE that should be set
+ * @new_spte: The value the SPTE should be set to
+ * @record_acc_track: Notify the MM subsystem of changes to the accessed state
+ *		      of the page. Should be set unless handling an MMU
+ *		      notifier for access tracking. Leaving record_acc_track
+ *		      unset in that case prevents page accesses from being
+ *		      double counted.
+ * @record_dirty_log: Record the page as dirty in the dirty bitmap if
+ *		      appropriate for the change being made. Should be set
+ *		      unless performing certain dirty logging operations.
+ *		      Leaving record_dirty_log unset in that case prevents page
+ *		      writes from being double counted.
+ */
 static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 				      u64 new_spte, bool record_acc_track,
 				      bool record_dirty_log)
 {
-	u64 *root_pt = tdp_iter_root_pt(iter);
+	tdp_ptep_t root_pt = tdp_iter_root_pt(iter);
 	struct kvm_mmu_page *root = sptep_to_sp(root_pt);
 	int as_id = kvm_mmu_page_as_id(root);
 
-	WRITE_ONCE(*iter->sptep, new_spte);
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	/*
+	 * No thread should be using this function to set SPTEs to the
+	 * temporary removed SPTE value.
+	 * If operating under the MMU lock in read mode, tdp_mmu_set_spte_atomic
+	 * should be used. If operating under the MMU lock in write mode, the
+	 * use of the removed SPTE should not be necessary.
+	 */
+	WARN_ON(iter->old_spte == REMOVED_SPTE);
+
+	WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte);
 
 	__handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
-			      iter->level);
+			      iter->level, false);
 	if (record_acc_track)
 		handle_changed_spte_acc_track(iter->old_spte, new_spte,
 					      iter->level);
@@ -413,27 +616,46 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
 			 _mmu->shadow_root_level, _start, _end)
 
 /*
- * Flush the TLB if the process should drop kvm->mmu_lock.
- * Return whether the caller still needs to flush the tlb.
+ * Yield if the MMU lock is contended or this thread needs to return control
+ * to the scheduler.
+ *
+ * If this function should yield and flush is set, it will perform a remote
+ * TLB flush before yielding.
+ *
+ * If this function yields, it will also reset the tdp_iter's walk over the
+ * paging structure and the calling function should skip to the next
+ * iteration to allow the iterator to continue its traversal from the
+ * paging structure root.
+ *
+ * Return true if this function yielded and the iterator's traversal was reset.
+ * Return false if a yield was not needed.
  */
-static bool tdp_mmu_iter_flush_cond_resched(struct kvm *kvm, struct tdp_iter *iter)
+static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
+					     struct tdp_iter *iter, bool flush)
 {
-	if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
-		kvm_flush_remote_tlbs(kvm);
-		cond_resched_lock(&kvm->mmu_lock);
-		tdp_iter_refresh_walk(iter);
+	/* Ensure forward progress has been made before yielding. */
+	if (iter->next_last_level_gfn == iter->yielded_gfn)
 		return false;
-	} else {
+
+	if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
+		rcu_read_unlock();
+
+		if (flush)
+			kvm_flush_remote_tlbs(kvm);
+
+		cond_resched_rwlock_write(&kvm->mmu_lock);
+		rcu_read_lock();
+
+		WARN_ON(iter->gfn > iter->next_last_level_gfn);
+
+		tdp_iter_start(iter, iter->pt_path[iter->root_level - 1],
+			       iter->root_level, iter->min_level,
+			       iter->next_last_level_gfn);
+
 		return true;
 	}
-}
 
-static void tdp_mmu_iter_cond_resched(struct kvm *kvm, struct tdp_iter *iter)
-{
-	if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
-		cond_resched_lock(&kvm->mmu_lock);
-		tdp_iter_refresh_walk(iter);
-	}
+	return false;
 }
 
 /*
@@ -453,7 +675,15 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 	struct tdp_iter iter;
 	bool flush_needed = false;
 
+	rcu_read_lock();
+
 	tdp_root_for_each_pte(iter, root, start, end) {
+		if (can_yield &&
+		    tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) {
+			flush_needed = false;
+			continue;
+		}
+
 		if (!is_shadow_present_pte(iter.old_spte))
 			continue;
 
@@ -468,12 +698,10 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 			continue;
 
 		tdp_mmu_set_spte(kvm, &iter, 0);
-
-		if (can_yield)
-			flush_needed = tdp_mmu_iter_flush_cond_resched(kvm, &iter);
-		else
-			flush_needed = true;
+		flush_needed = true;
 	}
+
+	rcu_read_unlock();
 	return flush_needed;
 }
 
@@ -517,21 +745,18 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write,
 	int ret = 0;
 	int make_spte_ret = 0;
 
-	if (unlikely(is_noslot_pfn(pfn))) {
+	if (unlikely(is_noslot_pfn(pfn)))
 		new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
-		trace_mark_mmio_spte(iter->sptep, iter->gfn, new_spte);
-	} else {
+	else
 		make_spte_ret = make_spte(vcpu, ACC_ALL, iter->level, iter->gfn,
 					 pfn, iter->old_spte, prefault, true,
 					 map_writable, !shadow_accessed_mask,
 					 &new_spte);
-		trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep);
-	}
 
 	if (new_spte == iter->old_spte)
 		ret = RET_PF_SPURIOUS;
-	else
-		tdp_mmu_set_spte(vcpu->kvm, iter, new_spte);
+	else if (!tdp_mmu_set_spte_atomic(vcpu->kvm, iter, new_spte))
+		return RET_PF_RETRY;
 
 	/*
 	 * If the page fault was caused by a write but the page is write
@@ -545,10 +770,16 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write,
 	}
 
 	/* If a MMIO SPTE is installed, the MMIO will need to be emulated. */
-	if (unlikely(is_mmio_spte(new_spte)))
+	if (unlikely(is_mmio_spte(new_spte))) {
+		trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn,
+				     new_spte);
 		ret = RET_PF_EMULATE;
+	} else
+		trace_kvm_mmu_set_spte(iter->level, iter->gfn,
+				       rcu_dereference(iter->sptep));
 
-	trace_kvm_mmu_set_spte(iter->level, iter->gfn, iter->sptep);
+	trace_kvm_mmu_set_spte(iter->level, iter->gfn,
+			       rcu_dereference(iter->sptep));
 	if (!prefault)
 		vcpu->stat.pf_fixed++;
 
@@ -586,6 +817,9 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 					huge_page_disallowed, &req_level);
 
 	trace_kvm_mmu_spte_requested(gpa, level, pfn);
+
+	rcu_read_lock();
+
 	tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
 		if (nx_huge_page_workaround_enabled)
 			disallowed_hugepage_adjust(iter.old_spte, gfn,
@@ -601,49 +835,61 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 		 */
 		if (is_shadow_present_pte(iter.old_spte) &&
 		    is_large_pte(iter.old_spte)) {
-			tdp_mmu_set_spte(vcpu->kvm, &iter, 0);
-
-			kvm_flush_remote_tlbs_with_address(vcpu->kvm, iter.gfn,
-					KVM_PAGES_PER_HPAGE(iter.level));
+			if (!tdp_mmu_zap_spte_atomic(vcpu->kvm, &iter))
+				break;
 
 			/*
 			 * The iter must explicitly re-read the spte here
 			 * because the new value informs the !present
 			 * path below.
 			 */
-			iter.old_spte = READ_ONCE(*iter.sptep);
+			iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
 		}
 
 		if (!is_shadow_present_pte(iter.old_spte)) {
 			sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level);
-			list_add(&sp->link, &vcpu->kvm->arch.tdp_mmu_pages);
 			child_pt = sp->spt;
-			clear_page(child_pt);
+
 			new_spte = make_nonleaf_spte(child_pt,
 						     !shadow_accessed_mask);
 
-			trace_kvm_mmu_get_page(sp, true);
-			if (huge_page_disallowed && req_level >= iter.level)
-				account_huge_nx_page(vcpu->kvm, sp);
-
-			tdp_mmu_set_spte(vcpu->kvm, &iter, new_spte);
+			if (tdp_mmu_set_spte_atomic(vcpu->kvm, &iter,
+						    new_spte)) {
+				tdp_mmu_link_page(vcpu->kvm, sp, true,
+						  huge_page_disallowed &&
+						  req_level >= iter.level);
+
+				trace_kvm_mmu_get_page(sp, true);
+			} else {
+				tdp_mmu_free_sp(sp);
+				break;
+			}
 		}
 	}
 
-	if (WARN_ON(iter.level != level))
+	if (iter.level != level) {
+		rcu_read_unlock();
 		return RET_PF_RETRY;
+	}
 
 	ret = tdp_mmu_map_handle_target_level(vcpu, write, map_writable, &iter,
 					      pfn, prefault);
+	rcu_read_unlock();
 
 	return ret;
 }
 
-static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start,
-		unsigned long end, unsigned long data,
-		int (*handler)(struct kvm *kvm, struct kvm_memory_slot *slot,
-			       struct kvm_mmu_page *root, gfn_t start,
-			       gfn_t end, unsigned long data))
+static __always_inline int
+kvm_tdp_mmu_handle_hva_range(struct kvm *kvm,
+			     unsigned long start,
+			     unsigned long end,
+			     unsigned long data,
+			     int (*handler)(struct kvm *kvm,
+					    struct kvm_memory_slot *slot,
+					    struct kvm_mmu_page *root,
+					    gfn_t start,
+					    gfn_t end,
+					    unsigned long data))
 {
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
@@ -705,6 +951,8 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot,
 	int young = 0;
 	u64 new_spte = 0;
 
+	rcu_read_lock();
+
 	tdp_root_for_each_leaf_pte(iter, root, start, end) {
 		/*
 		 * If we have a non-accessed entry we don't need to change the
@@ -736,6 +984,8 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot,
 		trace_kvm_age_page(iter.gfn, iter.level, slot, young);
 	}
 
+	rcu_read_unlock();
+
 	return young;
 }
 
@@ -781,6 +1031,8 @@ static int set_tdp_spte(struct kvm *kvm, struct kvm_memory_slot *slot,
 	u64 new_spte;
 	int need_flush = 0;
 
+	rcu_read_lock();
+
 	WARN_ON(pte_huge(*ptep));
 
 	new_pfn = pte_pfn(*ptep);
@@ -809,6 +1061,8 @@ static int set_tdp_spte(struct kvm *kvm, struct kvm_memory_slot *slot,
 	if (need_flush)
 		kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
 
+	rcu_read_unlock();
+
 	return 0;
 }
 
@@ -832,21 +1086,27 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 	u64 new_spte;
 	bool spte_set = false;
 
+	rcu_read_lock();
+
 	BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL);
 
 	for_each_tdp_pte_min_level(iter, root->spt, root->role.level,
 				   min_level, start, end) {
+		if (tdp_mmu_iter_cond_resched(kvm, &iter, false))
+			continue;
+
 		if (!is_shadow_present_pte(iter.old_spte) ||
-		    !is_last_spte(iter.old_spte, iter.level))
+		    !is_last_spte(iter.old_spte, iter.level) ||
+		    !(iter.old_spte & PT_WRITABLE_MASK))
 			continue;
 
 		new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
 
 		tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
 		spte_set = true;
-
-		tdp_mmu_iter_cond_resched(kvm, &iter);
 	}
+
+	rcu_read_unlock();
 	return spte_set;
 }
 
@@ -888,7 +1148,12 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 	u64 new_spte;
 	bool spte_set = false;
 
+	rcu_read_lock();
+
 	tdp_root_for_each_leaf_pte(iter, root, start, end) {
+		if (tdp_mmu_iter_cond_resched(kvm, &iter, false))
+			continue;
+
 		if (spte_ad_need_write_protect(iter.old_spte)) {
 			if (is_writable_pte(iter.old_spte))
 				new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
@@ -903,9 +1168,9 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 
 		tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
 		spte_set = true;
-
-		tdp_mmu_iter_cond_resched(kvm, &iter);
 	}
+
+	rcu_read_unlock();
 	return spte_set;
 }
 
@@ -947,6 +1212,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
 	struct tdp_iter iter;
 	u64 new_spte;
 
+	rcu_read_lock();
+
 	tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask),
 				    gfn + BITS_PER_LONG) {
 		if (!mask)
@@ -956,6 +1223,8 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
 		    !(mask & (1UL << (iter.gfn - gfn))))
 			continue;
 
+		mask &= ~(1UL << (iter.gfn - gfn));
+
 		if (wrprot || spte_ad_need_write_protect(iter.old_spte)) {
 			if (is_writable_pte(iter.old_spte))
 				new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
@@ -969,9 +1238,9 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
 		}
 
 		tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
-
-		mask &= ~(1UL << (iter.gfn - gfn));
 	}
+
+	rcu_read_unlock();
 }
 
 /*
@@ -989,7 +1258,7 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 	struct kvm_mmu_page *root;
 	int root_as_id;
 
-	lockdep_assert_held(&kvm->mmu_lock);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	for_each_tdp_mmu_root(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
@@ -1011,18 +1280,23 @@ static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 	u64 new_spte;
 	bool spte_set = false;
 
+	rcu_read_lock();
+
 	tdp_root_for_each_pte(iter, root, start, end) {
-		if (!is_shadow_present_pte(iter.old_spte))
+		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;
-
-		tdp_mmu_iter_cond_resched(kvm, &iter);
 	}
 
+	rcu_read_unlock();
 	return spte_set;
 }
 
@@ -1060,7 +1334,14 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
 	kvm_pfn_t pfn;
 	bool spte_set = false;
 
+	rcu_read_lock();
+
 	tdp_root_for_each_pte(iter, root, start, end) {
+		if (tdp_mmu_iter_cond_resched(kvm, &iter, spte_set)) {
+			spte_set = false;
+			continue;
+		}
+
 		if (!is_shadow_present_pte(iter.old_spte) ||
 		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
@@ -1072,9 +1353,10 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
 
 		tdp_mmu_set_spte(kvm, &iter, 0);
 
-		spte_set = tdp_mmu_iter_flush_cond_resched(kvm, &iter);
+		spte_set = true;
 	}
 
+	rcu_read_unlock();
 	if (spte_set)
 		kvm_flush_remote_tlbs(kvm);
 }
@@ -1111,6 +1393,8 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root,
 	u64 new_spte;
 	bool spte_set = false;
 
+	rcu_read_lock();
+
 	tdp_root_for_each_leaf_pte(iter, root, gfn, gfn + 1) {
 		if (!is_writable_pte(iter.old_spte))
 			break;
@@ -1122,6 +1406,8 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root,
 		spte_set = true;
 	}
 
+	rcu_read_unlock();
+
 	return spte_set;
 }
 
@@ -1137,7 +1423,7 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 	int root_as_id;
 	bool spte_set = false;
 
-	lockdep_assert_held(&kvm->mmu_lock);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	for_each_tdp_mmu_root(kvm, root) {
 		root_as_id = kvm_mmu_page_as_id(root);
 		if (root_as_id != slot->as_id)
@@ -1162,10 +1448,14 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
 
 	*root_level = vcpu->arch.mmu->shadow_root_level;
 
+	rcu_read_lock();
+
 	tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
 		leaf = iter.level;
 		sptes[leaf] = iter.old_spte;
 	}
 
+	rcu_read_unlock();
+
 	return leaf;
 }