From: Xiubo Li <xiubli@redhat.com>
Date: Wed, 30 Mar 2022 06:39:33 +0000 (+0800)
Subject: ceph: stop retrying the request when exceeding 256 times
X-Git-Url: http://git.apps.os.sepia.ceph.com/?a=commitdiff_plain;h=7a219f16cc2283d837759126788814f39d2ccd25;p=ceph-client.git

ceph: stop retrying the request when exceeding 256 times

The type of 'r_attempts' in kernel 'ceph_mds_request' is 'int',
while in 'ceph_mds_request_head' the type of 'num_retry' is '__u8'.
So in case the request retries exceeding 256 times, the MDS will
receive a incorrect retry seq.

In this case it's ususally a bug in MDS and continue retrying the
request makes no sense. For now let's limit it to 256. In future
this could be fixed in ceph code, so avoid using the hardcode here.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Xiubo Li <xiubli@redhat.com>
---

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index be57067314d5a..5b48bdb3c2b3e 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2680,7 +2680,28 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 	struct ceph_mds_client *mdsc = session->s_mdsc;
 	struct ceph_mds_request_head_old *rhead;
 	struct ceph_msg *msg;
-	int flags = 0;
+	int flags = 0, max_retry;
+
+	/*
+	 * The type of 'r_attempts' in kernel 'ceph_mds_request'
+	 * is 'int', while in 'ceph_mds_request_head' the type of
+	 * 'num_retry' is '__u8'. So in case the request retries
+	 *  exceeding 256 times, the MDS will receive a incorrect
+	 *  retry seq.
+	 *
+	 * In this case it's ususally a bug in MDS and continue
+	 * retrying the request makes no sense.
+	 *
+	 * In future this could be fixed in ceph code, so avoid
+	 * using the hardcode here.
+	 */
+	max_retry = sizeof_field(struct ceph_mds_request_head, num_retry);
+	max_retry = 1 << (max_retry * BITS_PER_BYTE);
+	if (req->r_attempts >= max_retry) {
+		pr_warn_ratelimited("%s request tid %llu seq overflow\n",
+				    __func__, req->r_tid);
+		return -EMULTIHOP;
+	}
 
 	req->r_attempts++;
 	if (req->r_inode) {
@@ -2692,7 +2713,7 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 		else
 			req->r_sent_on_mseq = -1;
 	}
-	dout("prepare_send_request %p tid %lld %s (attempt %d)\n", req,
+	dout("%s %p tid %lld %s (attempt %d)\n", __func__, req,
 	     req->r_tid, ceph_mds_op_name(req->r_op), req->r_attempts);
 
 	if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) {