btrfs: implement a nowait option for tree searches

For NOWAIT IOCBs we'll need a way to tell search to not wait on locks
or anything.  Accomplish this by adding a path->nowait flag that will
use trylocks and skip reading of metadata, returning -EAGAIN in either
of these cases.  For now we only need this for reads, so only the read
side is handled.  Add an ASSERT() to catch anybody trying to use this
for writes so they know they'll have to implement the write side.

Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Stefan Roesch <shr@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/ctree.c

@@ -1447,6 +1447,11 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 			return 0;
 		}
 
+		if (p->nowait) {
+			free_extent_buffer(tmp);
+			return -EAGAIN;
+		}
+
 		if (unlock_up)
 			btrfs_unlock_up_safe(p, level + 1);
 
@@ -1467,6 +1472,8 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 			ret = -EAGAIN;
 
 		goto out;
+	} else if (p->nowait) {
+		return -EAGAIN;
 	}
 
 	if (unlock_up) {
@@ -1634,7 +1641,13 @@ static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
 		 * We don't know the level of the root node until we actually
 		 * have it read locked
 		 */
-		b = btrfs_read_lock_root_node(root);
+		if (p->nowait) {
+			b = btrfs_try_read_lock_root_node(root);
+			if (IS_ERR(b))
+				return b;
+		} else {
+			b = btrfs_read_lock_root_node(root);
+		}
 		level = btrfs_header_level(b);
 		if (level > write_lock_level)
 			goto out;
@@ -1910,6 +1923,13 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	WARN_ON(p->nodes[0] != NULL);
 	BUG_ON(!cow && ins_len);
 
+	/*
+	 * For now only allow nowait for read only operations.  There's no
+	 * strict reason why we can't, we just only need it for reads so it's
+	 * only implemented for reads.
+	 */
+	ASSERT(!p->nowait || !cow);
+
 	if (ins_len < 0) {
 		lowest_unlock = 2;
 
@@ -1936,7 +1956,12 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 
 	if (p->need_commit_sem) {
 		ASSERT(p->search_commit_root);
-		down_read(&fs_info->commit_root_sem);
+		if (p->nowait) {
+			if (!down_read_trylock(&fs_info->commit_root_sem))
+				return -EAGAIN;
+		} else {
+			down_read(&fs_info->commit_root_sem);
+		}
 	}
 
 again:
@@ -2082,7 +2107,15 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 				btrfs_tree_lock(b);
 				p->locks[level] = BTRFS_WRITE_LOCK;
 			} else {
-				btrfs_tree_read_lock(b);
+				if (p->nowait) {
+					if (!btrfs_try_tree_read_lock(b)) {
+						free_extent_buffer(b);
+						ret = -EAGAIN;
+						goto done;
+					}
+				} else {
+					btrfs_tree_read_lock(b);
+				}
 				p->locks[level] = BTRFS_READ_LOCK;
 			}
 			p->nodes[level] = b;

fs/btrfs/ctree.h

@@ -443,6 +443,8 @@ struct btrfs_path {
 	 * header (ie. sizeof(struct btrfs_item) is not included).
 	 */
 	unsigned int search_for_extension:1;
+	/* Stop search if any locks need to be taken (for read) */
+	unsigned int nowait:1;
 };
 
 struct btrfs_dev_replace {

fs/btrfs/locking.c

@@ -285,6 +285,31 @@ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
 	return eb;
 }
 
+/*
+ * Loop around taking references on and locking the root node of the tree in
+ * nowait mode until we end up with a lock on the root node or returning to
+ * avoid blocking.
+ *
+ * Return: root extent buffer with read lock held or -EAGAIN.
+ */
+struct extent_buffer *btrfs_try_read_lock_root_node(struct btrfs_root *root)
+{
+	struct extent_buffer *eb;
+
+	while (1) {
+		eb = btrfs_root_node(root);
+		if (!btrfs_try_tree_read_lock(eb)) {
+			free_extent_buffer(eb);
+			return ERR_PTR(-EAGAIN);
+		}
+		if (eb == root->node)
+			break;
+		btrfs_tree_read_unlock(eb);
+		free_extent_buffer(eb);
+	}
+	return eb;
+}
+
 /*
  * DREW locks
  * ==========

fs/btrfs/locking.h

@@ -94,6 +94,7 @@ int btrfs_try_tree_read_lock(struct extent_buffer *eb);
 int btrfs_try_tree_write_lock(struct extent_buffer *eb);
 struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
 struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root);
+struct extent_buffer *btrfs_try_read_lock_root_node(struct btrfs_root *root);
 
 #ifdef CONFIG_BTRFS_DEBUG
 static inline void btrfs_assert_tree_write_locked(struct extent_buffer *eb)