ceph: fail the request directly if handle_reply gets an ESTALE

If MDS return ESTALE, that means the MDS has already iterated all the
possible active MDSes including the auth MDS or the inode is under
purging. No need to retry in auth MDS and will just return ESTALE
directly. Retrying in this situation will cause an infinite loop.

Also, retrying like this would prevent the kernel VFS layer ESTALE
handling from working properly. An ESTALE error is usually an indication
that the dcache is wrong, so we want to allow the VFS to redo the lookup
and revalidate it properly.

URL: https://tracker.ceph.com/issues/53504
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Acked-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

fs/ceph/mds_client.c

@@ -3098,35 +3098,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
 	result = le32_to_cpu(head->result);
 
-	/*
-	 * Handle an ESTALE
-	 * if we're not talking to the authority, send to them
-	 * if the authority has changed while we weren't looking,
-	 * send to new authority
-	 * Otherwise we just have to return an ESTALE
-	 */
-	if (result == -ESTALE) {
-		dout("got ESTALE on request %llu\n", req->r_tid);
-		req->r_resend_mds = -1;
-		if (req->r_direct_mode != USE_AUTH_MDS) {
-			dout("not using auth, setting for that now\n");
-			req->r_direct_mode = USE_AUTH_MDS;
-			__do_request(mdsc, req);
-			mutex_unlock(&mdsc->mutex);
-			goto out;
-		} else  {
-			int mds = __choose_mds(mdsc, req, NULL);
-			if (mds >= 0 && mds != req->r_session->s_mds) {
-				dout("but auth changed, so resending\n");
-				__do_request(mdsc, req);
-				mutex_unlock(&mdsc->mutex);
-				goto out;
-			}
-		}
-		dout("have to return ESTALE on request %llu\n", req->r_tid);
-	}
-
-
 	if (head->safe) {
 		set_bit(CEPH_MDS_R_GOT_SAFE, &req->r_req_flags);
 		__unregister_request(mdsc, req);