btrfs: disable strict file flushes for renames and truncates

Truncates and renames are often used to replace old versions of a file
with new versions.  Applications often expect this to be an atomic
replacement, even if they haven't done anything to make sure the new
version is fully on disk.

Btrfs has strict flushing in place to make sure that renaming over an
old file with a new file will fully flush out the new file before
allowing the transaction commit with the rename to complete.

This ordering means the commit code needs to be able to lock file pages,
and there are a few paths in the filesystem where we will try to end a
transaction with the page lock held.  It's rare, but these things can
deadlock.

This patch removes the ordered flushes and switches to a best effort
filemap_flush like ext4 uses. It's not perfect, but it should fix the
deadlocks.

Signed-off-by: Chris Mason <clm@fb.com>

1 files changed, 2 insertions, 31 deletions

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 5f379affdf23..d89c6d3542ca 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -218,7 +218,6 @@ loop:
 	spin_lock_init(&cur_trans->delayed_refs.lock);
 
 	INIT_LIST_HEAD(&cur_trans->pending_snapshots);
-	INIT_LIST_HEAD(&cur_trans->ordered_operations);
 	INIT_LIST_HEAD(&cur_trans->pending_chunks);
 	INIT_LIST_HEAD(&cur_trans->switch_commits);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
@@ -1612,27 +1611,6 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans,
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 }
 
-static int btrfs_flush_all_pending_stuffs(struct btrfs_trans_handle *trans,
-					  struct btrfs_root *root)
-{
-	int ret;
-
-	ret = btrfs_run_delayed_items(trans, root);
-	if (ret)
-		return ret;
-
-	/*
-	 * rename don't use btrfs_join_transaction, so, once we
-	 * set the transaction to blocked above, we aren't going
-	 * to get any new ordered operations.  We can safely run
-	 * it here and no for sure that nothing new will be added
-	 * to the list
-	 */
-	ret = btrfs_run_ordered_operations(trans, root, 1);
-
-	return ret;
-}
-
 static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
 {
 	if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT))
@@ -1653,13 +1631,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	struct btrfs_transaction *prev_trans = NULL;
 	int ret;
 
-	ret = btrfs_run_ordered_operations(trans, root, 0);
-	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
-		btrfs_end_transaction(trans, root);
-		return ret;
-	}
-
 	/* Stop the commit early if ->aborted is set */
 	if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;
@@ -1740,7 +1711,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto cleanup_transaction;
 
-	ret = btrfs_flush_all_pending_stuffs(trans, root);
+	ret = btrfs_run_delayed_items(trans, root);
 	if (ret)
 		goto cleanup_transaction;
 
@@ -1748,7 +1719,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 		   extwriter_counter_read(cur_trans) == 0);
 
 	/* some pending stuffs might be added after the previous flush. */
-	ret = btrfs_flush_all_pending_stuffs(trans, root);
+	ret = btrfs_run_delayed_items(trans, root);
 	if (ret)
 		goto cleanup_transaction;