cifs: only set ops for inodes in I_NEW state

commit c2b93e0699723700f886ce17bb65ffd771195a6d upstream.

It's generally not safe to reset the inode ops once they've been set. In
the case where the inode was originally thought to be a directory and
then later found to be a DFS referral, this can lead to an oops when we
try to trigger an inode op on it after changing the ops to the blank
referral operations.

Reported-and-Tested-by: Sachin Prabhu <sprabhu@redhat.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <smfrench@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 745e5cdca8f7f75b27b2d56d631051c11733f9e4..6f37228c3c3446f5dc3d29798e6be1fcac45229c 100644 (file)
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -173,7 +173,8 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 
        if (fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL)
                inode->i_flags |= S_AUTOMOUNT;
-       cifs_set_ops(inode);
+       if (inode->i_state & I_NEW)
+               cifs_set_ops(inode);
 }
 
 void