From: "Darrick J. Wong" darrick.wong@oracle.com
commit 6da1b4b1ab36d80a3994fd4811c8381de10af604 upstream.
When overlayfs is running on top of xfs and the user unlinks a file in the overlay, overlayfs will create a whiteout inode and ask xfs to "rename" the whiteout file atop the one being unlinked. If the file being unlinked loses its one nlink, we then have to put the inode on the unlinked list.
This requires us to grab the AGI buffer of the whiteout inode to take it off the unlinked list (which is where whiteouts are created) and to grab the AGI buffer of the file being deleted. If the whiteout was created in a higher numbered AG than the file being deleted, we'll lock the AGIs in the wrong order and deadlock.
Therefore, grab all the AGI locks we think we'll need ahead of time, and in order of increasing AG number per the locking rules.
Reported-by: wenli xie wlxie7296@gmail.com Fixes: 93597ae8dac0 ("xfs: Fix deadlock between AGI and AGF when target_ip exists in xfs_rename()") Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by: Brian Foster bfoster@redhat.com Acked-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandan.babu@oracle.com --- fs/xfs/libxfs/xfs_dir2.h | 2 -- fs/xfs/libxfs/xfs_dir2_sf.c | 2 +- fs/xfs/xfs_inode.c | 42 ++++++++++++++++++++++--------------- 3 files changed, 26 insertions(+), 20 deletions(-)
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index 01b1722333a9..f54244779492 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -124,8 +124,6 @@ extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp, extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_name *name, xfs_ino_t ino, xfs_extlen_t tot); -extern bool xfs_dir2_sf_replace_needblock(struct xfs_inode *dp, - xfs_ino_t inum); extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_name *name, xfs_ino_t inum, xfs_extlen_t tot); diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 90eff6c2de7e..f980c3f3d2f6 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -947,7 +947,7 @@ xfs_dir2_sf_removename( /* * Check whether the sf dir replace operation need more blocks. */ -bool +static bool xfs_dir2_sf_replace_needblock( struct xfs_inode *dp, xfs_ino_t inum) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 70c5050463a6..7b72c189cff0 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3224,7 +3224,7 @@ xfs_rename( struct xfs_trans *tp; struct xfs_inode *wip = NULL; /* whiteout inode */ struct xfs_inode *inodes[__XFS_SORT_INODES]; - struct xfs_buf *agibp; + int i; int num_inodes = __XFS_SORT_INODES; bool new_parent = (src_dp != target_dp); bool src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode); @@ -3336,6 +3336,30 @@ xfs_rename( } }
+ /* + * Lock the AGI buffers we need to handle bumping the nlink of the + * whiteout inode off the unlinked list and to handle dropping the + * nlink of the target inode. Per locking order rules, do this in + * increasing AG order and before directory block allocation tries to + * grab AGFs because we grab AGIs before AGFs. + * + * The (vfs) caller must ensure that if src is a directory then + * target_ip is either null or an empty directory. + */ + for (i = 0; i < num_inodes && inodes[i] != NULL; i++) { + if (inodes[i] == wip || + (inodes[i] == target_ip && + (VFS_I(target_ip)->i_nlink == 1 || src_is_directory))) { + struct xfs_buf *bp; + xfs_agnumber_t agno; + + agno = XFS_INO_TO_AGNO(mp, inodes[i]->i_ino); + error = xfs_read_agi(mp, tp, agno, &bp); + if (error) + goto out_trans_cancel; + } + } + /* * Directory entry creation below may acquire the AGF. Remove * the whiteout from the unlinked list first to preserve correct @@ -3389,22 +3413,6 @@ xfs_rename( * In case there is already an entry with the same * name at the destination directory, remove it first. */ - - /* - * Check whether the replace operation will need to allocate - * blocks. This happens when the shortform directory lacks - * space and we have to convert it to a block format directory. - * When more blocks are necessary, we must lock the AGI first - * to preserve locking order (AGI -> AGF). - */ - if (xfs_dir2_sf_replace_needblock(target_dp, src_ip->i_ino)) { - error = xfs_read_agi(mp, tp, - XFS_INO_TO_AGNO(mp, target_ip->i_ino), - &agibp); - if (error) - goto out_trans_cancel; - } - error = xfs_dir_replace(tp, target_dp, target_name, src_ip->i_ino, spaceres); if (error)