3 files changed, 96 insertions, 8 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 7a4ce885bd21..13a0524cc048 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1012,6 +1012,8 @@ enum {
 	BTRFS_ROOT_DEAD_TREE,
 	/* The root has a log tree. Used only for subvolume roots. */
 	BTRFS_ROOT_HAS_LOG_TREE,
+	/* Qgroup flushing is in progress */
+	BTRFS_ROOT_QGROUP_FLUSHING,
 };
 
 /*
@@ -1164,6 +1166,7 @@ struct btrfs_root {
 	spinlock_t qgroup_meta_rsv_lock;
 	u64 qgroup_meta_rsv_pertrans;
 	u64 qgroup_meta_rsv_prealloc;
+	wait_queue_head_t qgroup_flush_wait;
 
 	/* Number of active swapfiles */
 	atomic_t nr_swapfiles;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9b307034d32c..4360937acc2f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1116,6 +1116,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	mutex_init(&root->log_mutex);
 	mutex_init(&root->ordered_extent_mutex);
 	mutex_init(&root->delalloc_mutex);
+	init_waitqueue_head(&root->qgroup_flush_wait);
 	init_waitqueue_head(&root->log_writer_wait);
 	init_waitqueue_head(&root->log_commit_wait[0]);
 	init_waitqueue_head(&root->log_commit_wait[1]);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 054f36df60cf..23579dc39fa6 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -3515,17 +3515,58 @@ static int qgroup_unreserve_range(struct btrfs_inode *inode,
 }
 
 /*
- * Reserve qgroup space for range [start, start + len).
+ * Try to free some space for qgroup.
  *
- * This function will either reserve space from related qgroups or doing
- * nothing if the range is already reserved.
+ * For qgroup, there are only 3 ways to free qgroup space:
+ * - Flush nodatacow write
+ *   Any nodatacow write will free its reserved data space at run_delalloc_range().
+ *   In theory, we should only flush nodatacow inodes, but it's not yet
+ *   possible, so we need to flush the whole root.
  *
- * Return 0 for successful reserve
- * Return <0 for error (including -EQUOT)
+ * - Wait for ordered extents
+ *   When ordered extents are finished, their reserved metadata is finally
+ *   converted to per_trans status, which can be freed by later commit
+ *   transaction.
  *
- * NOTE: this function may sleep for memory allocation.
+ * - Commit transaction
+ *   This would free the meta_per_trans space.
+ *   In theory this shouldn't provide much space, but any more qgroup space
+ *   is needed.
  */
-int btrfs_qgroup_reserve_data(struct btrfs_inode *inode,
+static int try_flush_qgroup(struct btrfs_root *root)
+{
+	struct btrfs_trans_handle *trans;
+	int ret;
+
+	/*
+	 * We don't want to run flush again and again, so if there is a running
+	 * one, we won't try to start a new flush, but exit directly.
+	 */
+	if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) {
+		wait_event(root->qgroup_flush_wait,
+			!test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state));
+		return 0;
+	}
+
+	ret = btrfs_start_delalloc_snapshot(root);
+	if (ret < 0)
+		goto out;
+	btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1);
+
+	trans = btrfs_join_transaction(root);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto out;
+	}
+
+	ret = btrfs_commit_transaction(trans);
+out:
+	clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state);
+	wake_up(&root->qgroup_flush_wait);
+	return ret;
+}
+
+static int qgroup_reserve_data(struct btrfs_inode *inode,
 			struct extent_changeset **reserved_ret, u64 start,
 			u64 len)
 {
@@ -3578,6 +3619,34 @@ out:
 	return ret;
 }
 
+/*
+ * Reserve qgroup space for range [start, start + len).
+ *
+ * This function will either reserve space from related qgroups or do nothing
+ * if the range is already reserved.
+ *
+ * Return 0 for successful reservation
+ * Return <0 for error (including -EQUOT)
+ *
+ * NOTE: This function may sleep for memory allocation, dirty page flushing and
+ *	 commit transaction. So caller should not hold any dirty page locked.
+ */
+int btrfs_qgroup_reserve_data(struct btrfs_inode *inode,
+			struct extent_changeset **reserved_ret, u64 start,
+			u64 len)
+{
+	int ret;
+
+	ret = qgroup_reserve_data(inode, reserved_ret, start, len);
+	if (ret <= 0 && ret != -EDQUOT)
+		return ret;
+
+	ret = try_flush_qgroup(inode->root);
+	if (ret < 0)
+		return ret;
+	return qgroup_reserve_data(inode, reserved_ret, start, len);
+}
+
 /* Free ranges specified by @reserved, normally in error path */
 static int qgroup_free_reserved_data(struct btrfs_inode *inode,
 			struct extent_changeset *reserved, u64 start, u64 len)
@@ -3746,7 +3815,7 @@ static int sub_root_meta_rsv(struct btrfs_root *root, int num_bytes,
 	return num_bytes;
 }
 
-int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
+static int qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 				enum btrfs_qgroup_rsv_type type, bool enforce)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -3773,6 +3842,21 @@ int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 	return ret;
 }
 
+int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
+				enum btrfs_qgroup_rsv_type type, bool enforce)
+{
+	int ret;
+
+	ret = qgroup_reserve_meta(root, num_bytes, type, enforce);
+	if (ret <= 0 && ret != -EDQUOT)
+		return ret;
+
+	ret = try_flush_qgroup(root);
+	if (ret < 0)
+		return ret;
+	return qgroup_reserve_meta(root, num_bytes, type, enforce);
+}
+
 void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;