xfs: concurrent readdir hangs on data buffer locks (9f541801) · Commits · 戴 / test

There's a three-process deadlock involving shared/exclusive barriers and inverted lock orders in the directory readdir implementation. It's a pre-existing problem with lock ordering, exposed by the VFS parallelisation code. process 1 process 2 process 3 --------- --------- --------- readdir iolock(shared) get_leaf_dents iterate entries ilock(shared) map, lock and read buffer iunlock(shared) process entries in buffer ..... readdir iolock(shared) get_leaf_dents iterate entries ilock(shared) map, lock buffer <blocks> finish ->iterate_shared file_accessed() ->update_time start transaction ilock(excl) <blocks> ..... finishes processing buffer get next buffer ilock(shared) <blocks> And that's the deadlock. Fix this by dropping the current buffer lock in process 1 before trying to map the next buffer. This means we keep the lock order of ilock -> buffer lock intact and hence will allow process 3 to make progress and drop it's ilock(shared) once it is done. Reported-by:

Xiong Zhou <xzhou@redhat.com> Signed-off-by:

Dave Chinner <dchinner@redhat.com> Signed-off-by:

Al Viro <viro@zeniv.linux.org.uk>

fs/xfs/xfs_dir2_readdir.c

+14 −9

Original line number	Diff line number	Diff line
		@@ -273,10 +273,11 @@ xfs_dir2_leaf_readbuf(
		size_t bufsize,
		struct xfs_dir2_leaf_map_info *mip,
		xfs_dir2_off_t *curoff,
		struct xfs_buf **bpp)
		struct xfs_buf **bpp,
		bool trim_map)
		{
		struct xfs_inode *dp = args->dp;
		struct xfs_buf bp = bpp;
		struct xfs_buf *bp = NULL;
		struct xfs_bmbt_irec *map = mip->map;
		struct blk_plug plug;
		int error = 0;
		@@ -286,13 +287,10 @@ xfs_dir2_leaf_readbuf(
		struct xfs_da_geometry *geo = args->geo;

		/*
		* If we have a buffer, we need to release it and
		* take it out of the mapping.
		* If the caller just finished processing a buffer, it will tell us
		* we need to trim that block out of the mapping now it is done.
		*/

		if (bp) {
		xfs_trans_brelse(NULL, bp);
		bp = NULL;
		if (trim_map) {
		mip->map_blocks -= geo->fsbcount;
		/*
		* Loop to get rid of the extents for the
		@@ -533,10 +531,17 @@ xfs_dir2_leaf_getdents(
		*/
		if (!bp \|\| ptr >= (char *)bp->b_addr + geo->blksize) {
		int lock_mode;
		bool trim_map = false;

		if (bp) {
		xfs_trans_brelse(NULL, bp);
		bp = NULL;
		trim_map = true;
		}

		lock_mode = xfs_ilock_data_map_shared(dp);
		error = xfs_dir2_leaf_readbuf(args, bufsize, map_info,
		&curoff, &bp);
		&curoff, &bp, trim_map);
		xfs_iunlock(dp, lock_mode);
		if (error \|\| !map_info->map_valid)
		break;

Admin message