KVM: x86/mmu: Tear down roots before kvm_mmu_zap_all_fast returns

To avoid saddling a vCPU thread with the work of tearing down an entire
paging structure, take a reference on each root before they become
obsolete, so that the thread initiating the fast invalidation can tear
down the paging structure and (most likely) release the last reference.
As a bonus, this teardown can happen under the MMU lock in read mode so
as not to block the progress of vCPU threads.
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210401233736.638171-14-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/mmu/mmu.c

@@ -5443,6 +5443,12 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
 	kvm_zap_obsolete_pages(kvm);
 
 	write_unlock(&kvm->mmu_lock);
+
+	if (is_tdp_mmu_enabled(kvm)) {
+		read_lock(&kvm->mmu_lock);
+		kvm_tdp_mmu_zap_invalidated_roots(kvm);
+		read_unlock(&kvm->mmu_lock);
+	}
 }
 
 static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)

arch/x86/kvm/mmu/tdp_mmu.c

@@ -797,11 +797,91 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 		kvm_flush_remote_tlbs(kvm);
 }
 
+static struct kvm_mmu_page *next_invalidated_root(struct kvm *kvm,
+						  struct kvm_mmu_page *prev_root)
+{
+	struct kvm_mmu_page *next_root;
+
+	if (prev_root)
+		next_root = list_next_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+						  &prev_root->link,
+						  typeof(*prev_root), link);
+	else
+		next_root = list_first_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+						   typeof(*next_root), link);
+
+	while (next_root && !(next_root->role.invalid &&
+			      refcount_read(&next_root->tdp_mmu_root_count)))
+		next_root = list_next_or_null_rcu(&kvm->arch.tdp_mmu_roots,
+						  &next_root->link,
+						  typeof(*next_root), link);
+
+	return next_root;
+}
+
+/*
+ * Since kvm_tdp_mmu_zap_all_fast has acquired a reference to each
+ * invalidated root, they will not be freed until this function drops the
+ * reference. Before dropping that reference, tear down the paging
+ * structure so that whichever thread does drop the last reference
+ * only has to do a trivial amount of work. Since the roots are invalid,
+ * no new SPTEs should be created under them.
+ */
+void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
+{
+	gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
+	struct kvm_mmu_page *next_root;
+	struct kvm_mmu_page *root;
+	bool flush = false;
+
+	lockdep_assert_held_read(&kvm->mmu_lock);
+
+	rcu_read_lock();
+
+	root = next_invalidated_root(kvm, NULL);
+
+	while (root) {
+		next_root = next_invalidated_root(kvm, root);
+
+		rcu_read_unlock();
+
+		flush = zap_gfn_range(kvm, root, 0, max_gfn, true, flush,
+				      true);
+
+		/*
+		 * Put the reference acquired in
+		 * kvm_tdp_mmu_invalidate_roots
+		 */
+		kvm_tdp_mmu_put_root(kvm, root, true);
+
+		root = next_root;
+
+		rcu_read_lock();
+	}
+
+	rcu_read_unlock();
+
+	if (flush)
+		kvm_flush_remote_tlbs(kvm);
+}
+
 /*
  * Mark each TDP MMU root as invalid so that other threads
  * will drop their references and allow the root count to
  * go to 0.
  *
+ * Also take a reference on all roots so that this thread
+ * can do the bulk of the work required to free the roots
+ * once they are invalidated. Without this reference, a
+ * vCPU thread might drop the last reference to a root and
+ * get stuck with tearing down the entire paging structure.
+ *
+ * Roots which have a zero refcount should be skipped as
+ * they're already being torn down.
+ * Already invalid roots should be referenced again so that
+ * they aren't freed before kvm_tdp_mmu_zap_all_fast is
+ * done with them.
+ *
  * This has essentially the same effect for the TDP MMU
  * as updating mmu_valid_gen does for the shadow MMU.
  */
@@ -811,7 +891,8 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 	list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link)
-		root->role.invalid = true;
+		if (refcount_inc_not_zero(&root->tdp_mmu_root_count))
+			root->role.invalid = true;
 }
 
 /*

arch/x86/kvm/mmu/tdp_mmu.h

@@ -49,6 +49,7 @@ static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 void kvm_tdp_mmu_zap_all(struct kvm *kvm);
 void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
+void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm);
 
 int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 		    int map_writable, int max_level, kvm_pfn_t pfn,