btrfs: track refs in a rb_tree instead of a list

If we get a significant amount of delayed refs for a single block (think
modifying multiple snapshots) we can end up spending an ungodly amount
of time looping through all of the entries trying to see if they can be
merged.  This is because we only add them to a list, so we have O(2n)
for every ref head.  This doesn't make any sense as we likely have refs
for different roots, and so they cannot be merged.  Tracking in a tree
will allow us to break as soon as we hit an entry that doesn't match,
making our worst case O(n).

With this we can also merge entries more easily.  Before we had to hope
that matching refs were on the ends of our list, but with the tree we
can search down to exact matches and merge them at insert time.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/backref.c

@@ -773,6 +773,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
 	struct btrfs_key key;
 	struct btrfs_key tmp_op_key;
 	struct btrfs_key *op_key = NULL;
+	struct rb_node *n;
 	int count;
 	int ret = 0;
 
@@ -782,7 +783,9 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
 	}
 
 	spin_lock(&head->lock);
-	list_for_each_entry(node, &head->ref_list, list) {
+	for (n = rb_first(&head->ref_tree); n; n = rb_next(n)) {
+		node = rb_entry(n, struct btrfs_delayed_ref_node,
+				ref_node);
 		if (node->seq > seq)
 			continue;
 

fs/btrfs/delayed-ref.c

@@ -143,6 +143,34 @@ static struct btrfs_delayed_ref_head *htree_insert(struct rb_root *root,
 	return NULL;
 }
 
+static struct btrfs_delayed_ref_node* tree_insert(struct rb_root *root,
+		struct btrfs_delayed_ref_node *ins)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *node = &ins->ref_node;
+	struct rb_node *parent_node = NULL;
+	struct btrfs_delayed_ref_node *entry;
+
+	while (*p) {
+		int comp;
+
+		parent_node = *p;
+		entry = rb_entry(parent_node, struct btrfs_delayed_ref_node,
+				 ref_node);
+		comp = comp_refs(ins, entry, true);
+		if (comp < 0)
+			p = &(*p)->rb_left;
+		else if (comp > 0)
+			p = &(*p)->rb_right;
+		else
+			return entry;
+	}
+
+	rb_link_node(node, parent_node, p);
+	rb_insert_color(node, root);
+	return NULL;
+}
+
 /*
  * find an head entry based on bytenr. This returns the delayed ref
  * head if it was able to find one, or NULL if nothing was in that spot.
@@ -212,7 +240,8 @@ static inline void drop_delayed_ref(struct btrfs_trans_handle *trans,
 				    struct btrfs_delayed_ref_node *ref)
 {
 	assert_spin_locked(&head->lock);
-	list_del(&ref->list);
+	rb_erase(&ref->ref_node, &head->ref_tree);
+	RB_CLEAR_NODE(&ref->ref_node);
 	if (!list_empty(&ref->add_list))
 		list_del(&ref->add_list);
 	ref->in_tree = 0;
@@ -229,24 +258,18 @@ static bool merge_ref(struct btrfs_trans_handle *trans,
 		      u64 seq)
 {
 	struct btrfs_delayed_ref_node *next;
+	struct rb_node *node = rb_next(&ref->ref_node);
 	bool done = false;
 
-	next = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node,
-				list);
-	while (!done && &next->list != &head->ref_list) {
+	while (!done && node) {
 		int mod;
-		struct btrfs_delayed_ref_node *next2;
-
-		next2 = list_next_entry(next, list);
-
-		if (next == ref)
-			goto next;
 
+		next = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
+		node = rb_next(node);
 		if (seq && next->seq >= seq)
-			goto next;
-
+			break;
 		if (comp_refs(ref, next, false))
-			goto next;
+			break;
 
 		if (ref->action == next->action) {
 			mod = next->ref_mod;
@@ -270,8 +293,6 @@ static bool merge_ref(struct btrfs_trans_handle *trans,
 			WARN_ON(ref->type == BTRFS_TREE_BLOCK_REF_KEY ||
 				ref->type == BTRFS_SHARED_BLOCK_REF_KEY);
 		}
-next:
-		next = next2;
 	}
 
 	return done;
@@ -283,11 +304,12 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
 			      struct btrfs_delayed_ref_head *head)
 {
 	struct btrfs_delayed_ref_node *ref;
+	struct rb_node *node;
 	u64 seq = 0;
 
 	assert_spin_locked(&head->lock);
 
-	if (list_empty(&head->ref_list))
+	if (RB_EMPTY_ROOT(&head->ref_tree))
 		return;
 
 	/* We don't have too many refs to merge for data. */
@@ -304,22 +326,13 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
 	}
 	spin_unlock(&fs_info->tree_mod_seq_lock);
 
-	ref = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node,
-			       list);
-	while (&ref->list != &head->ref_list) {
+again:
+	for (node = rb_first(&head->ref_tree); node; node = rb_next(node)) {
+		ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
 		if (seq && ref->seq >= seq)
-			goto next;
-
-		if (merge_ref(trans, delayed_refs, head, ref, seq)) {
-			if (list_empty(&head->ref_list))
-				break;
-			ref = list_first_entry(&head->ref_list,
-					       struct btrfs_delayed_ref_node,
-					       list);
 			continue;
-		}
-next:
-		ref = list_next_entry(ref, list);
+		if (merge_ref(trans, delayed_refs, head, ref, seq))
+			goto again;
 	}
 }
 
@@ -402,8 +415,7 @@ btrfs_select_ref_head(struct btrfs_trans_handle *trans)
  * Return 0 for insert.
  * Return >0 for merge.
  */
-static int
-add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans,
+static int insert_delayed_ref(struct btrfs_trans_handle *trans,
 			      struct btrfs_delayed_ref_root *root,
 			      struct btrfs_delayed_ref_head *href,
 			      struct btrfs_delayed_ref_node *ref)
@@ -413,14 +425,9 @@ add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans,
 	int ret = 0;
 
 	spin_lock(&href->lock);
-	/* Check whether we can merge the tail node with ref */
-	if (list_empty(&href->ref_list))
-		goto add_tail;
-	exist = list_entry(href->ref_list.prev, struct btrfs_delayed_ref_node,
-			   list);
-	/* No need to compare bytenr nor is_head */
-	if (comp_refs(exist, ref, true))
-		goto add_tail;
+	exist = tree_insert(&href->ref_tree, ref);
+	if (!exist)
+		goto inserted;
 
 	/* Now we are sure we can merge */
 	ret = 1;
@@ -451,9 +458,7 @@ add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans,
 		drop_delayed_ref(trans, root, href, exist);
 	spin_unlock(&href->lock);
 	return ret;
-
-add_tail:
-	list_add_tail(&ref->list, &href->ref_list);
+inserted:
 	if (ref->action == BTRFS_ADD_DELAYED_REF)
 		list_add_tail(&ref->add_list, &href->ref_add_list);
 	atomic_inc(&root->num_entries);
@@ -593,7 +598,7 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	head_ref->ref_mod = count_mod;
 	head_ref->must_insert_reserved = must_insert_reserved;
 	head_ref->is_data = is_data;
-	INIT_LIST_HEAD(&head_ref->ref_list);
+	head_ref->ref_tree = RB_ROOT;
 	INIT_LIST_HEAD(&head_ref->ref_add_list);
 	RB_CLEAR_NODE(&head_ref->href_node);
 	head_ref->processing = 0;
@@ -685,7 +690,7 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	ref->is_head = 0;
 	ref->in_tree = 1;
 	ref->seq = seq;
-	INIT_LIST_HEAD(&ref->list);
+	RB_CLEAR_NODE(&ref->ref_node);
 	INIT_LIST_HEAD(&ref->add_list);
 
 	full_ref = btrfs_delayed_node_to_tree_ref(ref);
@@ -699,7 +704,7 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 
 	trace_add_delayed_tree_ref(fs_info, ref, full_ref, action);
 
-	ret = add_delayed_ref_tail_merge(trans, delayed_refs, head_ref, ref);
+	ret = insert_delayed_ref(trans, delayed_refs, head_ref, ref);
 
 	/*
 	 * XXX: memory should be freed at the same level allocated.
@@ -742,7 +747,7 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 	ref->is_head = 0;
 	ref->in_tree = 1;
 	ref->seq = seq;
-	INIT_LIST_HEAD(&ref->list);
+	RB_CLEAR_NODE(&ref->ref_node);
 	INIT_LIST_HEAD(&ref->add_list);
 
 	full_ref = btrfs_delayed_node_to_data_ref(ref);
@@ -758,8 +763,7 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 
 	trace_add_delayed_data_ref(fs_info, ref, full_ref, action);
 
-	ret = add_delayed_ref_tail_merge(trans, delayed_refs, head_ref, ref);
-
+	ret = insert_delayed_ref(trans, delayed_refs, head_ref, ref);
 	if (ret > 0)
 		kmem_cache_free(btrfs_delayed_data_ref_cachep, full_ref);
 }

fs/btrfs/delayed-ref.h

@@ -27,8 +27,7 @@
 #define BTRFS_UPDATE_DELAYED_HEAD 4 /* not changing ref count on head ref */
 
 struct btrfs_delayed_ref_node {
-	/*data/tree ref use list, stored in ref_head->ref_list. */
-	struct list_head list;
+	struct rb_node ref_node;
 	/*
 	 * If action is BTRFS_ADD_DELAYED_REF, also link this node to
 	 * ref_head->ref_add_list, then we do not need to iterate the
@@ -92,7 +91,7 @@ struct btrfs_delayed_ref_head {
 	struct mutex mutex;
 
 	spinlock_t lock;
-	struct list_head ref_list;
+	struct rb_root ref_tree;
 	/* accumulate add BTRFS_ADD_DELAYED_REF nodes to this ref_add_list. */
 	struct list_head ref_add_list;
 

fs/btrfs/disk-io.c

@@ -4113,7 +4113,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 
 	while ((node = rb_first(&delayed_refs->href_root)) != NULL) {
 		struct btrfs_delayed_ref_head *head;
-		struct btrfs_delayed_ref_node *tmp;
+		struct rb_node *n;
 		bool pin_bytes = false;
 
 		head = rb_entry(node, struct btrfs_delayed_ref_head,
@@ -4129,10 +4129,12 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 			continue;
 		}
 		spin_lock(&head->lock);
-		list_for_each_entry_safe_reverse(ref, tmp, &head->ref_list,
-						 list) {
+		while ((n = rb_first(&head->ref_tree)) != NULL) {
+			ref = rb_entry(n, struct btrfs_delayed_ref_node,
+				       ref_node);
 			ref->in_tree = 0;
-			list_del(&ref->list);
+			rb_erase(&ref->ref_node, &head->ref_tree);
+			RB_CLEAR_NODE(&ref->ref_node);
 			if (!list_empty(&ref->add_list))
 				list_del(&ref->add_list);
 			atomic_dec(&delayed_refs->num_entries);

fs/btrfs/extent-tree.c

@@ -2519,7 +2519,7 @@ select_delayed_ref(struct btrfs_delayed_ref_head *head)
 {
 	struct btrfs_delayed_ref_node *ref;
 
-	if (list_empty(&head->ref_list))
+	if (RB_EMPTY_ROOT(&head->ref_tree))
 		return NULL;
 
 	/*
@@ -2532,8 +2532,8 @@ select_delayed_ref(struct btrfs_delayed_ref_head *head)
 		return list_first_entry(&head->ref_add_list,
 				struct btrfs_delayed_ref_node, add_list);
 
-	ref = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node,
-			       list);
+	ref = rb_entry(rb_first(&head->ref_tree),
+		       struct btrfs_delayed_ref_node, ref_node);
 	ASSERT(list_empty(&ref->add_list));
 	return ref;
 }
@@ -2593,7 +2593,7 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
 	spin_unlock(&head->lock);
 	spin_lock(&delayed_refs->lock);
 	spin_lock(&head->lock);
-	if (!list_empty(&head->ref_list) || head->extent_op) {
+	if (!RB_EMPTY_ROOT(&head->ref_tree) || head->extent_op) {
 		spin_unlock(&head->lock);
 		spin_unlock(&delayed_refs->lock);
 		return 1;
@@ -2740,7 +2740,8 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 
 		actual_count++;
 		ref->in_tree = 0;
-		list_del(&ref->list);
+		rb_erase(&ref->ref_node, &locked_ref->ref_tree);
+		RB_CLEAR_NODE(&ref->ref_node);
 		if (!list_empty(&ref->add_list))
 			list_del(&ref->add_list);
 		/*
@@ -3138,6 +3139,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 	struct btrfs_delayed_data_ref *data_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_transaction *cur_trans;
+	struct rb_node *node;
 	int ret = 0;
 
 	cur_trans = root->fs_info->running_transaction;
@@ -3170,7 +3172,12 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
 	spin_unlock(&delayed_refs->lock);
 
 	spin_lock(&head->lock);
-	list_for_each_entry(ref, &head->ref_list, list) {
+	/*
+	 * XXX: We should replace this with a proper search function in the
+	 * future.
+	 */
+	for (node = rb_first(&head->ref_tree); node; node = rb_next(node)) {
+		ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
 		/* If it's a shared ref we know a cross reference exists */
 		if (ref->type != BTRFS_EXTENT_DATA_REF_KEY) {
 			ret = 1;
@@ -7141,7 +7148,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
 		goto out_delayed_unlock;
 
 	spin_lock(&head->lock);
-	if (!list_empty(&head->ref_list))
+	if (!RB_EMPTY_ROOT(&head->ref_tree))
 		goto out;
 
 	if (head->extent_op) {