1 files changed, 247 insertions, 78 deletions

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 2f15e0e33903..046b6ba31197 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -37,8 +37,8 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 	 * for zapping and thus puts the TDP MMU's reference to each root, i.e.
 	 * ultimately frees all roots.
 	 */
-	kvm_tdp_mmu_invalidate_all_roots(kvm);
-	kvm_tdp_mmu_zap_invalidated_roots(kvm);
+	kvm_tdp_mmu_invalidate_roots(kvm, KVM_VALID_ROOTS);
+	kvm_tdp_mmu_zap_invalidated_roots(kvm, false);
 
 	WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
@@ -53,6 +53,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 
 static void tdp_mmu_free_sp(struct kvm_mmu_page *sp)
 {
+	free_page((unsigned long)sp->external_spt);
 	free_page((unsigned long)sp->spt);
 	kmem_cache_free(mmu_page_header_cache, sp);
 }
@@ -91,19 +92,33 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
 	call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback);
 }
 
+static bool tdp_mmu_root_match(struct kvm_mmu_page *root,
+			       enum kvm_tdp_mmu_root_types types)
+{
+	if (WARN_ON_ONCE(!(types & KVM_VALID_ROOTS)))
+		return false;
+
+	if (root->role.invalid && !(types & KVM_INVALID_ROOTS))
+		return false;
+
+	if (likely(!is_mirror_sp(root)))
+		return types & KVM_DIRECT_ROOTS;
+	return types & KVM_MIRROR_ROOTS;
+}
+
 /*
  * Returns the next root after @prev_root (or the first root if @prev_root is
- * NULL).  A reference to the returned root is acquired, and the reference to
- * @prev_root is released (the caller obviously must hold a reference to
- * @prev_root if it's non-NULL).
+ * NULL) that matches with @types.  A reference to the returned root is
+ * acquired, and the reference to @prev_root is released (the caller obviously
+ * must hold a reference to @prev_root if it's non-NULL).
  *
- * If @only_valid is true, invalid roots are skipped.
+ * Roots that doesn't match with @types are skipped.
  *
  * Returns NULL if the end of tdp_mmu_roots was reached.
  */
 static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 					      struct kvm_mmu_page *prev_root,
-					      bool only_valid)
+					      enum kvm_tdp_mmu_root_types types)
 {
 	struct kvm_mmu_page *next_root;
 
@@ -124,7 +139,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 						   typeof(*next_root), link);
 
 	while (next_root) {
-		if ((!only_valid || !next_root->role.invalid) &&
+		if (tdp_mmu_root_match(next_root, types) &&
 		    kvm_tdp_mmu_get_root(next_root))
 			break;
 
@@ -149,20 +164,20 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
  * If shared is set, this function is operating under the MMU lock in read
  * mode.
  */
-#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid)	\
-	for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid);		\
+#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _types)	\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, _types);		\
 	     ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root;		\
-	     _root = tdp_mmu_next_root(_kvm, _root, _only_valid))		\
+	     _root = tdp_mmu_next_root(_kvm, _root, _types))		\
 		if (_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) {	\
 		} else
 
 #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id)	\
-	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, true)
+	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, KVM_VALID_ROOTS)
 
 #define for_each_tdp_mmu_root_yield_safe(_kvm, _root)			\
-	for (_root = tdp_mmu_next_root(_kvm, NULL, false);		\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, KVM_ALL_ROOTS);		\
 	     ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root;	\
-	     _root = tdp_mmu_next_root(_kvm, _root, false))
+	     _root = tdp_mmu_next_root(_kvm, _root, KVM_ALL_ROOTS))
 
 /*
  * Iterate over all TDP MMU roots.  Requires that mmu_lock be held for write,
@@ -171,18 +186,15 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
  * Holding mmu_lock for write obviates the need for RCU protection as the list
  * is guaranteed to be stable.
  */
-#define __for_each_tdp_mmu_root(_kvm, _root, _as_id, _only_valid)		\
+#define __for_each_tdp_mmu_root(_kvm, _root, _as_id, _types)			\
 	list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link)		\
 		if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) &&		\
 		    ((_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) ||	\
-		     ((_only_valid) && (_root)->role.invalid))) {		\
+		     !tdp_mmu_root_match((_root), (_types)))) {			\
 		} else
 
-#define for_each_tdp_mmu_root(_kvm, _root, _as_id)			\
-	__for_each_tdp_mmu_root(_kvm, _root, _as_id, false)
-
 #define for_each_valid_tdp_mmu_root(_kvm, _root, _as_id)		\
-	__for_each_tdp_mmu_root(_kvm, _root, _as_id, true)
+	__for_each_tdp_mmu_root(_kvm, _root, _as_id, KVM_VALID_ROOTS)
 
 static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu)
 {
@@ -223,7 +235,7 @@ static void tdp_mmu_init_child_sp(struct kvm_mmu_page *child_sp,
 	tdp_mmu_init_sp(child_sp, iter->sptep, iter->gfn, role);
 }
 
-int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu)
+void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu, bool mirror)
 {
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
 	union kvm_mmu_page_role role = mmu->root_role;
@@ -231,6 +243,9 @@ int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_page *root;
 
+	if (mirror)
+		role.is_mirror = true;
+
 	/*
 	 * Check for an existing root before acquiring the pages lock to avoid
 	 * unnecessary serialization if multiple vCPUs are loading a new root.
@@ -282,9 +297,12 @@ out_read_unlock:
 	 * and actually consuming the root if it's invalidated after dropping
 	 * mmu_lock, and the root can't be freed as this vCPU holds a reference.
 	 */
-	mmu->root.hpa = __pa(root->spt);
-	mmu->root.pgd = 0;
-	return 0;
+	if (mirror) {
+		mmu->mirror_root_hpa = __pa(root->spt);
+	} else {
+		mmu->root.hpa = __pa(root->spt);
+		mmu->root.pgd = 0;
+	}
 }
 
 static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
@@ -322,6 +340,29 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 	spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
 }
 
+static void remove_external_spte(struct kvm *kvm, gfn_t gfn, u64 old_spte,
+				 int level)
+{
+	kvm_pfn_t old_pfn = spte_to_pfn(old_spte);
+	int ret;
+
+	/*
+	 * External (TDX) SPTEs are limited to PG_LEVEL_4K, and external
+	 * PTs are removed in a special order, involving free_external_spt().
+	 * But remove_external_spte() will be called on non-leaf PTEs via
+	 * __tdp_mmu_zap_root(), so avoid the error the former would return
+	 * in this case.
+	 */
+	if (!is_last_spte(old_spte, level))
+		return;
+
+	/* Zapping leaf spte is allowed only when write lock is held. */
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	/* Because write lock is held, operation should success. */
+	ret = static_call(kvm_x86_remove_external_spte)(kvm, gfn, level, old_pfn);
+	KVM_BUG_ON(ret, kvm);
+}
+
 /**
  * handle_removed_pt() - handle a page table removed from the TDP structure
  *
@@ -417,11 +458,81 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared)
 		}
 		handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn,
 				    old_spte, FROZEN_SPTE, level, shared);
+
+		if (is_mirror_sp(sp)) {
+			KVM_BUG_ON(shared, kvm);
+			remove_external_spte(kvm, gfn, old_spte, level);
+		}
+	}
+
+	if (is_mirror_sp(sp) &&
+	    WARN_ON(static_call(kvm_x86_free_external_spt)(kvm, base_gfn, sp->role.level,
+							  sp->external_spt))) {
+		/*
+		 * Failed to free page table page in mirror page table and
+		 * there is nothing to do further.
+		 * Intentionally leak the page to prevent the kernel from
+		 * accessing the encrypted page.
+		 */
+		sp->external_spt = NULL;
 	}
 
 	call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
 }
 
+static void *get_external_spt(gfn_t gfn, u64 new_spte, int level)
+{
+	if (is_shadow_present_pte(new_spte) && !is_last_spte(new_spte, level)) {
+		struct kvm_mmu_page *sp = spte_to_child_sp(new_spte);
+
+		WARN_ON_ONCE(sp->role.level + 1 != level);
+		WARN_ON_ONCE(sp->gfn != gfn);
+		return sp->external_spt;
+	}
+
+	return NULL;
+}
+
+static int __must_check set_external_spte_present(struct kvm *kvm, tdp_ptep_t sptep,
+						 gfn_t gfn, u64 old_spte,
+						 u64 new_spte, int level)
+{
+	bool was_present = is_shadow_present_pte(old_spte);
+	bool is_present = is_shadow_present_pte(new_spte);
+	bool is_leaf = is_present && is_last_spte(new_spte, level);
+	kvm_pfn_t new_pfn = spte_to_pfn(new_spte);
+	int ret = 0;
+
+	KVM_BUG_ON(was_present, kvm);
+
+	lockdep_assert_held(&kvm->mmu_lock);
+	/*
+	 * We need to lock out other updates to the SPTE until the external
+	 * page table has been modified. Use FROZEN_SPTE similar to
+	 * the zapping case.
+	 */
+	if (!try_cmpxchg64(rcu_dereference(sptep), &old_spte, FROZEN_SPTE))
+		return -EBUSY;
+
+	/*
+	 * Use different call to either set up middle level
+	 * external page table, or leaf.
+	 */
+	if (is_leaf) {
+		ret = static_call(kvm_x86_set_external_spte)(kvm, gfn, level, new_pfn);
+	} else {
+		void *external_spt = get_external_spt(gfn, new_spte, level);
+
+		KVM_BUG_ON(!external_spt, kvm);
+		ret = static_call(kvm_x86_link_external_spt)(kvm, gfn, level, external_spt);
+	}
+	if (ret)
+		__kvm_tdp_mmu_write_spte(sptep, old_spte);
+	else
+		__kvm_tdp_mmu_write_spte(sptep, new_spte);
+	return ret;
+}
+
 /**
  * handle_changed_spte - handle bookkeeping associated with an SPTE change
  * @kvm: kvm instance
@@ -522,11 +633,10 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 		handle_removed_pt(kvm, spte_to_child_pt(old_spte, level), shared);
 }
 
-static inline int __must_check __tdp_mmu_set_spte_atomic(struct tdp_iter *iter,
+static inline int __must_check __tdp_mmu_set_spte_atomic(struct kvm *kvm,
+							 struct tdp_iter *iter,
 							 u64 new_spte)
 {
-	u64 *sptep = rcu_dereference(iter->sptep);
-
 	/*
 	 * The caller is responsible for ensuring the old SPTE is not a FROZEN
 	 * SPTE.  KVM should never attempt to zap or manipulate a FROZEN SPTE,
@@ -535,15 +645,34 @@ static inline int __must_check __tdp_mmu_set_spte_atomic(struct tdp_iter *iter,
 	 */
 	WARN_ON_ONCE(iter->yielded || is_frozen_spte(iter->old_spte));
 
-	/*
-	 * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and
-	 * does not hold the mmu_lock.  On failure, i.e. if a different logical
-	 * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with
-	 * the current value, so the caller operates on fresh data, e.g. if it
-	 * retries tdp_mmu_set_spte_atomic()
-	 */
-	if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte))
-		return -EBUSY;
+	if (is_mirror_sptep(iter->sptep) && !is_frozen_spte(new_spte)) {
+		int ret;
+
+		/*
+		 * Users of atomic zapping don't operate on mirror roots,
+		 * so don't handle it and bug the VM if it's seen.
+		 */
+		if (KVM_BUG_ON(!is_shadow_present_pte(new_spte), kvm))
+			return -EBUSY;
+
+		ret = set_external_spte_present(kvm, iter->sptep, iter->gfn,
+						iter->old_spte, new_spte, iter->level);
+		if (ret)
+			return ret;
+	} else {
+		u64 *sptep = rcu_dereference(iter->sptep);
+
+		/*
+		 * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs
+		 * and does not hold the mmu_lock.  On failure, i.e. if a
+		 * different logical CPU modified the SPTE, try_cmpxchg64()
+		 * updates iter->old_spte with the current value, so the caller
+		 * operates on fresh data, e.g. if it retries
+		 * tdp_mmu_set_spte_atomic()
+		 */
+		if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte))
+			return -EBUSY;
+	}
 
 	return 0;
 }
@@ -573,7 +702,7 @@ static inline int __must_check tdp_mmu_set_spte_atomic(struct kvm *kvm,
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
-	ret = __tdp_mmu_set_spte_atomic(iter, new_spte);
+	ret = __tdp_mmu_set_spte_atomic(kvm, iter, new_spte);
 	if (ret)
 		return ret;
 
@@ -613,6 +742,16 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep,
 	old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level);
 
 	handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false);
+
+	/*
+	 * Users that do non-atomic setting of PTEs don't operate on mirror
+	 * roots, so don't handle it and bug the VM if it's seen.
+	 */
+	if (is_mirror_sptep(sptep)) {
+		KVM_BUG_ON(is_shadow_present_pte(new_spte), kvm);
+		remove_external_spte(kvm, gfn, old_spte, level);
+	}
+
 	return old_spte;
 }
 
@@ -625,18 +764,18 @@ static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 					  iter->gfn, iter->level);
 }
 
-#define tdp_root_for_each_pte(_iter, _root, _start, _end) \
-	for_each_tdp_pte(_iter, _root, _start, _end)
+#define tdp_root_for_each_pte(_iter, _kvm, _root, _start, _end)	\
+	for_each_tdp_pte(_iter, _kvm, _root, _start, _end)
 
-#define tdp_root_for_each_leaf_pte(_iter, _root, _start, _end)	\
-	tdp_root_for_each_pte(_iter, _root, _start, _end)		\
+#define tdp_root_for_each_leaf_pte(_iter, _kvm, _root, _start, _end)	\
+	tdp_root_for_each_pte(_iter, _kvm, _root, _start, _end)		\
 		if (!is_shadow_present_pte(_iter.old_spte) ||		\
 		    !is_last_spte(_iter.old_spte, _iter.level))		\
 			continue;					\
 		else
 
-#define tdp_mmu_for_each_pte(_iter, _mmu, _start, _end)		\
-	for_each_tdp_pte(_iter, root_to_sp(_mmu->root.hpa), _start, _end)
+#define tdp_mmu_for_each_pte(_iter, _kvm, _root, _start, _end)	\
+	for_each_tdp_pte(_iter, _kvm, _root, _start, _end)
 
 static inline bool __must_check tdp_mmu_iter_need_resched(struct kvm *kvm,
 							  struct tdp_iter *iter)
@@ -705,10 +844,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
 {
 	struct tdp_iter iter;
 
-	gfn_t end = tdp_mmu_max_gfn_exclusive();
-	gfn_t start = 0;
-
-	for_each_tdp_pte_min_level(iter, root, zap_level, start, end) {
+	for_each_tdp_pte_min_level_all(iter, root, zap_level) {
 retry:
 		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared))
 			continue;
@@ -812,7 +948,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
 
 	rcu_read_lock();
 
-	for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) {
+	for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_4K, start, end) {
 		if (can_yield &&
 		    tdp_mmu_iter_cond_resched(kvm, &iter, flush, false)) {
 			flush = false;
@@ -863,19 +999,21 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 	struct kvm_mmu_page *root;
 
 	/*
-	 * Zap all roots, including invalid roots, as all SPTEs must be dropped
-	 * before returning to the caller.  Zap directly even if the root is
-	 * also being zapped by a worker.  Walking zapped top-level SPTEs isn't
-	 * all that expensive and mmu_lock is already held, which means the
-	 * worker has yielded, i.e. flushing the work instead of zapping here
-	 * isn't guaranteed to be any faster.
+	 * Zap all direct roots, including invalid direct roots, as all direct
+	 * SPTEs must be dropped before returning to the caller. For TDX, mirror
+	 * roots don't need handling in response to the mmu notifier (the caller).
+	 *
+	 * Zap directly even if the root is also being zapped by a concurrent
+	 * "fast zap".  Walking zapped top-level SPTEs isn't all that expensive
+	 * and mmu_lock is already held, which means the other thread has yielded.
 	 *
 	 * A TLB flush is unnecessary, KVM zaps everything if and only the VM
 	 * is being destroyed or the userspace VMM has exited.  In both cases,
 	 * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request.
 	 */
 	lockdep_assert_held_write(&kvm->mmu_lock);
-	for_each_tdp_mmu_root_yield_safe(kvm, root)
+	__for_each_tdp_mmu_root_yield_safe(kvm, root, -1,
+					   KVM_DIRECT_ROOTS | KVM_INVALID_ROOTS)
 		tdp_mmu_zap_root(kvm, root, false);
 }
 
@@ -883,11 +1021,14 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
  * Zap all invalidated roots to ensure all SPTEs are dropped before the "fast
  * zap" completes.
  */
-void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
+void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared)
 {
 	struct kvm_mmu_page *root;
 
-	read_lock(&kvm->mmu_lock);
+	if (shared)
+		read_lock(&kvm->mmu_lock);
+	else
+		write_lock(&kvm->mmu_lock);
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root) {
 		if (!root->tdp_mmu_scheduled_root_to_zap)
@@ -905,7 +1046,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 		 * that may be zapped, as such entries are associated with the
 		 * ASID on both VMX and SVM.
 		 */
-		tdp_mmu_zap_root(kvm, root, true);
+		tdp_mmu_zap_root(kvm, root, shared);
 
 		/*
 		 * The referenced needs to be put *after* zapping the root, as
@@ -915,7 +1056,10 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 		kvm_tdp_mmu_put_root(kvm, root);
 	}
 
-	read_unlock(&kvm->mmu_lock);
+	if (shared)
+		read_unlock(&kvm->mmu_lock);
+	else
+		write_unlock(&kvm->mmu_lock);
 }
 
 /*
@@ -928,11 +1072,19 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
  * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference.
  * See kvm_tdp_mmu_alloc_root().
  */
-void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
+void kvm_tdp_mmu_invalidate_roots(struct kvm *kvm,
+				  enum kvm_tdp_mmu_root_types root_types)
 {
 	struct kvm_mmu_page *root;
 
 	/*
+	 * Invalidating invalid roots doesn't make sense, prevent developers from
+	 * having to think about it.
+	 */
+	if (WARN_ON_ONCE(root_types & KVM_INVALID_ROOTS))
+		root_types &= ~KVM_INVALID_ROOTS;
+
+	/*
 	 * mmu_lock must be held for write to ensure that a root doesn't become
 	 * invalid while there are active readers (invalidating a root while
 	 * there are active readers may or may not be problematic in practice,
@@ -953,6 +1105,9 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
 	 * or get/put references to roots.
 	 */
 	list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) {
+		if (!tdp_mmu_root_match(root, root_types))
+			continue;
+
 		/*
 		 * Note, invalid roots can outlive a memslot update!  Invalid
 		 * roots must be *zapped* before the memslot update completes,
@@ -1068,7 +1223,7 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
  */
 int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
-	struct kvm_mmu *mmu = vcpu->arch.mmu;
+	struct kvm_mmu_page *root = tdp_mmu_get_root_for_fault(vcpu, fault);
 	struct kvm *kvm = vcpu->kvm;
 	struct tdp_iter iter;
 	struct kvm_mmu_page *sp;
@@ -1080,7 +1235,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 
 	rcu_read_lock();
 
-	tdp_mmu_for_each_pte(iter, mmu, fault->gfn, fault->gfn + 1) {
+	tdp_mmu_for_each_pte(iter, kvm, root, fault->gfn, fault->gfn + 1) {
 		int r;
 
 		if (fault->nx_huge_page_workaround_enabled)
@@ -1107,13 +1262,18 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 		 */
 		sp = tdp_mmu_alloc_sp(vcpu);
 		tdp_mmu_init_child_sp(sp, &iter);
+		if (is_mirror_sp(sp))
+			kvm_mmu_alloc_external_spt(vcpu, sp);
 
 		sp->nx_huge_page_disallowed = fault->huge_page_disallowed;
 
-		if (is_shadow_present_pte(iter.old_spte))
+		if (is_shadow_present_pte(iter.old_spte)) {
+			/* Don't support large page for mirrored roots (TDX) */
+			KVM_BUG_ON(is_mirror_sptep(iter.sptep), vcpu->kvm);
 			r = tdp_mmu_split_huge_page(kvm, &iter, sp, true);
-		else
+		} else {
 			r = tdp_mmu_link_sp(kvm, &iter, sp, true);
+		}
 
 		/*
 		 * Force the guest to retry if installing an upper level SPTE
@@ -1148,12 +1308,16 @@ retry:
 	return ret;
 }
 
+/* Used by mmu notifier via kvm_unmap_gfn_range() */
 bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 				 bool flush)
 {
+	enum kvm_tdp_mmu_root_types types;
 	struct kvm_mmu_page *root;
 
-	__for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false)
+	types = kvm_gfn_range_filter_to_root_types(kvm, range->attr_filter) | KVM_INVALID_ROOTS;
+
+	__for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, types)
 		flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end,
 					  range->may_block, flush);
 
@@ -1193,20 +1357,24 @@ static bool __kvm_tdp_mmu_age_gfn_range(struct kvm *kvm,
 					struct kvm_gfn_range *range,
 					bool test_only)
 {
+	enum kvm_tdp_mmu_root_types types;
 	struct kvm_mmu_page *root;
 	struct tdp_iter iter;
 	bool ret = false;
 
+	types = kvm_gfn_range_filter_to_root_types(kvm, range->attr_filter);
+
 	/*
 	 * Don't support rescheduling, none of the MMU notifiers that funnel
 	 * into this helper allow blocking; it'd be dead, wasteful code.  Note,
 	 * this helper must NOT be used to unmap GFNs, as it processes only
 	 * valid roots!
 	 */
-	for_each_valid_tdp_mmu_root(kvm, root, range->slot->as_id) {
+	WARN_ON(types & ~KVM_VALID_ROOTS);
+	__for_each_tdp_mmu_root(kvm, root, range->slot->as_id, types) {
 		guard(rcu)();
 
-		tdp_root_for_each_leaf_pte(iter, root, range->start, range->end) {
+		tdp_root_for_each_leaf_pte(iter, kvm, root, range->start, range->end) {
 			if (!is_accessed_spte(iter.old_spte))
 				continue;
 
@@ -1247,7 +1415,7 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 
 	BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL);
 
-	for_each_tdp_pte_min_level(iter, root, min_level, start, end) {
+	for_each_tdp_pte_min_level(iter, kvm, root, min_level, start, end) {
 retry:
 		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
 			continue;
@@ -1366,7 +1534,7 @@ static int tdp_mmu_split_huge_pages_root(struct kvm *kvm,
 	 * level above the target level (e.g. splitting a 1GB to 512 2MB pages,
 	 * and then splitting each of those to 512 4KB pages).
 	 */
-	for_each_tdp_pte_min_level(iter, root, target_level + 1, start, end) {
+	for_each_tdp_pte_min_level(iter, kvm, root, target_level + 1, start, end) {
 retry:
 		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared))
 			continue;
@@ -1464,7 +1632,7 @@ static void clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 
 	rcu_read_lock();
 
-	tdp_root_for_each_pte(iter, root, start, end) {
+	tdp_root_for_each_pte(iter, kvm, root, start, end) {
 retry:
 		if (!is_shadow_present_pte(iter.old_spte) ||
 		    !is_last_spte(iter.old_spte, iter.level))
@@ -1512,7 +1680,7 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
 
 	rcu_read_lock();
 
-	tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask),
+	tdp_root_for_each_leaf_pte(iter, kvm, root, gfn + __ffs(mask),
 				    gfn + BITS_PER_LONG) {
 		if (!mask)
 			break;
@@ -1566,7 +1734,7 @@ static int tdp_mmu_make_huge_spte(struct kvm *kvm,
 	gfn_t end = start + KVM_PAGES_PER_HPAGE(parent->level);
 	struct tdp_iter iter;
 
-	tdp_root_for_each_leaf_pte(iter, root, start, end) {
+	tdp_root_for_each_leaf_pte(iter, kvm, root, start, end) {
 		/*
 		 * Use the parent iterator when checking for forward progress so
 		 * that KVM doesn't get stuck continuously trying to yield (i.e.
@@ -1600,7 +1768,7 @@ static void recover_huge_pages_range(struct kvm *kvm,
 
 	rcu_read_lock();
 
-	for_each_tdp_pte_min_level(iter, root, PG_LEVEL_2M, start, end) {
+	for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_2M, start, end) {
 retry:
 		if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) {
 			flush = false;
@@ -1681,7 +1849,7 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root,
 
 	rcu_read_lock();
 
-	for_each_tdp_pte_min_level(iter, root, min_level, gfn, gfn + 1) {
+	for_each_tdp_pte_min_level(iter, kvm, root, min_level, gfn, gfn + 1) {
 		if (!is_shadow_present_pte(iter.old_spte) ||
 		    !is_last_spte(iter.old_spte, iter.level))
 			continue;
@@ -1729,14 +1897,14 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
 			 int *root_level)
 {
+	struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa);
 	struct tdp_iter iter;
-	struct kvm_mmu *mmu = vcpu->arch.mmu;
 	gfn_t gfn = addr >> PAGE_SHIFT;
 	int leaf = -1;
 
 	*root_level = vcpu->arch.mmu->root_role.level;
 
-	tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
+	tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) {
 		leaf = iter.level;
 		sptes[leaf] = iter.old_spte;
 	}
@@ -1758,11 +1926,12 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
 u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn,
 					u64 *spte)
 {
+	/* Fast pf is not supported for mirrored roots  */
+	struct kvm_mmu_page *root = tdp_mmu_get_root(vcpu, KVM_DIRECT_ROOTS);
 	struct tdp_iter iter;
-	struct kvm_mmu *mmu = vcpu->arch.mmu;
 	tdp_ptep_t sptep = NULL;
 
-	tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
+	tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) {
 		*spte = iter.old_spte;
 		sptep = iter.sptep;
 	}