cifs: only set ops for inodes in I_NEW state

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.

Cc: <stable@vger.kernel.org>
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: Steve French <sfrench@us.ibm.com>

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index fc3025199cb336f6c07c8172d19e501601a3f1f7..20efd81266c643338bcd81b434edfe9fbcacc0ac 100644 (file)
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -171,7 +171,8 @@ 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