diff options
author | Jeff Layton <jlayton@redhat.com> | 2013-07-30 11:38:44 -0400 |
---|---|---|
committer | Steve French <smfrench@gmail.com> | 2013-07-31 13:45:02 -0500 |
commit | 66ffd113f5d81e951b0379acfd0a1df0771d8828 (patch) | |
tree | 0256de4f8e9b68b8d3db0309db37e0aa2232792c /fs/cifs/cifsacl.c | |
parent | ba48202932de455566868a065874279688c9241f (diff) | |
download | lwn-66ffd113f5d81e951b0379acfd0a1df0771d8828.tar.gz lwn-66ffd113f5d81e951b0379acfd0a1df0771d8828.zip |
cifs: set sb->s_d_op before calling d_make_root()
Currently, the s_root dentry doesn't get its d_op pointer set to
anything. This breaks lookups in the root of case-insensitive mounts
since that relies on having d_hash and d_compare routines that know to
treat the filename as case-insensitive.
cifs.ko has been broken this way for a long time, but commit 1c929cfe6
("switch cifs"), added a cryptic comment which is removed in the patch
below, which makes me wonder if this was done deliberately for some
reason. It's not clear to me why we'd want the s_root not to have d_op
set properly.
It may have something to do with d_automount or d_revalidate on the
root, but my suspicion in looking over the code is that Al was just
trying to preserve the existing behavior when changing this code over to
use s_d_op.
This patch changes it so that we set s_d_op before calling d_make_root
and removes the comment. I tested mounting, accessing and unmounting
several types of shares (including DFS referrals) and everything still
seemed to work OK afterward. I could be missing something however, so
please do let me know if I am.
Reported-by: Jan-Marek Glogowski <glogow@fbihome.de>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Ian Kent <raven@themaw.net>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <smfrench@gmail.com>
Diffstat (limited to 'fs/cifs/cifsacl.c')
0 files changed, 0 insertions, 0 deletions