From ac89b2ef9b55924bcf922251f043ba73a32d05bb Mon Sep 17 00:00:00 2001 From: Eryu Guan Date: Thu, 5 Apr 2018 16:19:49 -0700 Subject: [PATCH] 9p: don't maintain dir i_nlink if the exported fs doesn't either If the exported filesystem dir on 9p server doesn't maintain accurate i_nlink count, e.g. always reports i_nlink as 1, then 9p should not maintain nlink count either, otherwise drop_link would report warning with i_nlink being zero. For example: - overlayfs sets nlink to 1 for merged dir - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more than EXT4_LINK_MAX (65000) links. In this case, everytime a stat(2) call (getattr) on such exported dirs on 9p client side, the i_nlink gets reset to 1, then operations like rmdir(2), unlink(2) and rename(2) would cause the dir nlink to go to zero (then negative), which results in warnings in drop_nlink() and/or inc_nlink() calls. This can be reproduced easily as the following steps: - export a merged overlayfs dir via qemu virtfs to guest - mount the exported virtfs in guest - create two sub-directories in the root dir of the mounted 9pfs - stat the root dir of 9pfs, this resets nlink to 1 - remove all subdirs, the second unlink/rmdir would trigger warning ------------[ cut here ]------------ WARNING: CPU: 3 PID: 1284 at fs/inode.c:282 drop_nlink+0x3e/0x50 ... Call Trace: dump_stack+0x63/0x81 __warn+0xcb/0xf0 warn_slowpath_null+0x1d/0x20 drop_nlink+0x3e/0x50 v9fs_remove+0xaa/0x130 [9p] v9fs_vfs_rmdir+0x13/0x20 [9p] vfs_rmdir+0xb7/0x130 do_rmdir+0x1b8/0x230 SyS_unlinkat+0x22/0x30 do_syscall_64+0x67/0x180 ---[ end trace 43758d8ba91e603b ]--- Fix it by leaving i_nlink to be 1 and don't drop nlink if a directory has nlink <= 2, which indicates that the underlying exported fs doesn't maintain nlink count accurately. This follows what ext4 does in ext4_dec_count(). Link: http://lkml.kernel.org/r/20180312053829.4367-1-eguan@linux.alibaba.com Signed-off-by: Eryu Guan Reviewed-by: Yiwen Jiang Tested-by: Roman Kapl Cc: Caspar Zhang Cc: Eric Van Hensbergen Cc: Ron Minnich Cc: Latchesar Ionkov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/9p/vfs_inode.c | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index bdabb27..9ee5341 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -579,6 +579,24 @@ static int v9fs_at_to_dotl_flags(int flags) } /** + * v9fs_dec_count - helper functon to drop i_nlink. + * + * If a directory had nlink <= 2 (including . and ..), then we should not drop + * the link count, which indicates the underlying exported fs doesn't maintain + * nlink accurately. e.g. + * - overlayfs sets nlink to 1 for merged dir + * - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more + * than EXT4_LINK_MAX (65000) links. + * + * @inode: inode whose nlink is being dropped + */ +static void v9fs_dec_count(struct inode *inode) +{ + if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2) + drop_nlink(inode); +} + +/** * v9fs_remove - helper function to remove files and directories * @dir: directory inode that is being deleted * @dentry: dentry that is being deleted @@ -621,9 +639,9 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags) */ if (flags & AT_REMOVEDIR) { clear_nlink(inode); - drop_nlink(dir); + v9fs_dec_count(dir); } else - drop_nlink(inode); + v9fs_dec_count(inode); v9fs_invalidate_inode_attr(inode); v9fs_invalidate_inode_attr(dir); @@ -1024,12 +1042,12 @@ clunk_newdir: if (S_ISDIR(new_inode->i_mode)) clear_nlink(new_inode); else - drop_nlink(new_inode); + v9fs_dec_count(new_inode); } if (S_ISDIR(old_inode->i_mode)) { if (!new_inode) inc_nlink(new_dir); - drop_nlink(old_dir); + v9fs_dec_count(old_dir); } v9fs_invalidate_inode_attr(old_inode); v9fs_invalidate_inode_attr(old_dir); -- 2.7.4