KVM: x86/mmu: Ensure MMU pages are available when allocating roots

Hold the mmu_lock for write for the entire duration of allocating and
initializing an MMU's roots.  This ensures there are MMU pages available
and thus prevents root allocations from failing.  That in turn fixes a
bug where KVM would fail to free valid PAE roots if a one of the later
roots failed to allocate.

Add a comment to make_mmu_pages_available() to call out that the limit
is a soft limit, e.g. KVM will temporarily exceed the threshold if a
page fault allocates multiple shadow pages and there was only one page
"available".

Note, KVM _still_ leaks the PAE roots if the guest PDPTR checks fail.
This will be addressed in a future commit.

Cc: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210305011101.3597423-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/mmu/mmu.c

@@ -2421,6 +2421,15 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
 
 	kvm_mmu_zap_oldest_mmu_pages(vcpu->kvm, KVM_REFILL_PAGES - avail);
 
+	/*
+	 * Note, this check is intentionally soft, it only guarantees that one
+	 * page is available, while the caller may end up allocating as many as
+	 * four pages, e.g. for PAE roots or for 5-level paging.  Temporarily
+	 * exceeding the (arbitrary by default) limit will not harm the host,
+	 * being too agressive may unnecessarily kill the guest, and getting an
+	 * exact count is far more trouble than it's worth, especially in the
+	 * page fault paths.
+	 */
 	if (!kvm_mmu_available_pages(vcpu->kvm))
 		return -ENOSPC;
 	return 0;
@@ -3226,16 +3235,9 @@ static hpa_t mmu_alloc_root(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gva,
 {
 	struct kvm_mmu_page *sp;
 
-	write_lock(&vcpu->kvm->mmu_lock);
-
-	if (make_mmu_pages_available(vcpu)) {
-		write_unlock(&vcpu->kvm->mmu_lock);
-		return INVALID_PAGE;
-	}
 	sp = kvm_mmu_get_page(vcpu, gfn, gva, level, direct, ACC_ALL);
 	++sp->root_count;
 
-	write_unlock(&vcpu->kvm->mmu_lock);
 	return __pa(sp->spt);
 }
 
@@ -3248,16 +3250,9 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 
 	if (is_tdp_mmu_enabled(vcpu->kvm)) {
 		root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu);
-
-		if (!VALID_PAGE(root))
-			return -ENOSPC;
 		mmu->root_hpa = root;
 	} else if (shadow_root_level >= PT64_ROOT_4LEVEL) {
-		root = mmu_alloc_root(vcpu, 0, 0, shadow_root_level,
-				      true);
-
-		if (!VALID_PAGE(root))
-			return -ENOSPC;
+		root = mmu_alloc_root(vcpu, 0, 0, shadow_root_level, true);
 		mmu->root_hpa = root;
 	} else if (shadow_root_level == PT32E_ROOT_LEVEL) {
 		for (i = 0; i < 4; ++i) {
@@ -3265,8 +3260,6 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 
 			root = mmu_alloc_root(vcpu, i << (30 - PAGE_SHIFT),
 					      i << 30, PT32_ROOT_LEVEL, true);
-			if (!VALID_PAGE(root))
-				return -ENOSPC;
 			mmu->pae_root[i] = root | PT_PRESENT_MASK;
 		}
 		mmu->root_hpa = __pa(mmu->pae_root);
@@ -3302,8 +3295,6 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 
 		root = mmu_alloc_root(vcpu, root_gfn, 0,
 				      mmu->shadow_root_level, false);
-		if (!VALID_PAGE(root))
-			return -ENOSPC;
 		mmu->root_hpa = root;
 		goto set_root_pgd;
 	}
@@ -3322,6 +3313,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 
 	for (i = 0; i < 4; ++i) {
 		MMU_WARN_ON(VALID_PAGE(mmu->pae_root[i]));
+
 		if (mmu->root_level == PT32E_ROOT_LEVEL) {
 			pdptr = mmu->get_pdptr(vcpu, i);
 			if (!(pdptr & PT_PRESENT_MASK)) {
@@ -3335,8 +3327,6 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 
 		root = mmu_alloc_root(vcpu, root_gfn, i << 30,
 				      PT32_ROOT_LEVEL, false);
-		if (!VALID_PAGE(root))
-			return -ENOSPC;
 		mmu->pae_root[i] = root | pm_mask;
 	}
 
@@ -3400,14 +3390,6 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
-{
-	if (vcpu->arch.mmu->direct_map)
-		return mmu_alloc_direct_roots(vcpu);
-	else
-		return mmu_alloc_shadow_roots(vcpu);
-}
-
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 {
 	int i;
@@ -4838,7 +4820,15 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
 	r = mmu_alloc_special_roots(vcpu);
 	if (r)
 		goto out;
-	r = mmu_alloc_roots(vcpu);
+	write_lock(&vcpu->kvm->mmu_lock);
+	if (make_mmu_pages_available(vcpu))
+		r = -ENOSPC;
+	else if (vcpu->arch.mmu->direct_map)
+		r = mmu_alloc_direct_roots(vcpu);
+	else
+		r = mmu_alloc_shadow_roots(vcpu);
+	write_unlock(&vcpu->kvm->mmu_lock);
+
 	kvm_mmu_sync_roots(vcpu);
 	if (r)
 		goto out;

arch/x86/kvm/mmu/tdp_mmu.c

@@ -137,22 +137,21 @@ static struct kvm_mmu_page *alloc_tdp_mmu_page(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return sp;
 }
 
-static struct kvm_mmu_page *get_tdp_mmu_vcpu_root(struct kvm_vcpu *vcpu)
+hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
 {
 	union kvm_mmu_page_role role;
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_page *root;
 
-	role = page_role_for_level(vcpu, vcpu->arch.mmu->shadow_root_level);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 
-	write_lock(&kvm->mmu_lock);
+	role = page_role_for_level(vcpu, vcpu->arch.mmu->shadow_root_level);
 
 	/* 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);
-			write_unlock(&kvm->mmu_lock);
-			return root;
+			goto out;
 		}
 	}
 
@@ -161,19 +160,7 @@ static struct kvm_mmu_page *get_tdp_mmu_vcpu_root(struct kvm_vcpu *vcpu)
 
 	list_add(&root->link, &kvm->arch.tdp_mmu_roots);
 
-	write_unlock(&kvm->mmu_lock);
-
-	return root;
-}
-
-hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
-{
-	struct kvm_mmu_page *root;
-
-	root = get_tdp_mmu_vcpu_root(vcpu);
-	if (!root)
-		return INVALID_PAGE;
-
+out:
 	return __pa(root->spt);
 }