summaryrefslogtreecommitdiff
path: root/fs/cifs/cifsacl.c
diff options
context:
space:
mode:
authorJeff Layton <jlayton@redhat.com>2013-07-30 11:38:44 -0400
committerSteve French <smfrench@gmail.com>2013-07-31 13:45:02 -0500
commit66ffd113f5d81e951b0379acfd0a1df0771d8828 (patch)
tree0256de4f8e9b68b8d3db0309db37e0aa2232792c /fs/cifs/cifsacl.c
parentba48202932de455566868a065874279688c9241f (diff)
downloadlwn-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