ceph: fix authenticator timeout

We were failing to reconnect to services due to an old authenticator, even
though we had the new ticket, because we weren't properly retrying the
connect handshake, because we were calling an old/incorrect helper that
left in_base_pos incorrect.  The result was a failure to reconnect to the
OSD or MDS (with an authentication error) if the MDS restarted after the
service had been up a few hours (long enough for the original authenticator
to be invalid).  This was only a problem if the AUTH_X authentication was
enabled.

Now that the 'negotiate' and 'connect' stages are fully separated, we
should use the prepare_read_connect() helper instead, and remove the
obsolete one.

Signed-off-by: Sage Weil <sage@newdream.net>

diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c
index 781656a49bf87d101444139cb0483c055df802fb..203c4359b549a21071e3800f119aaae5c42184a0 100644 (file)
--- a/fs/ceph/messenger.c
+++ b/fs/ceph/messenger.c
@@ -830,13 +830,6 @@ static void prepare_read_connect(struct ceph_connection *con)
        con->in_base_pos = 0;
 }
 
-static void prepare_read_connect_retry(struct ceph_connection *con)
-{
-       dout("prepare_read_connect_retry %p\n", con);
-       con->in_base_pos = strlen(CEPH_BANNER) + sizeof(con->actual_peer_addr)
-               + sizeof(con->peer_addr_for_me);
-}
-
 static void prepare_read_ack(struct ceph_connection *con)
 {
        dout("prepare_read_ack %p\n", con);
@@ -1146,7 +1139,7 @@ static int process_connect(struct ceph_connection *con)
                }
                con->auth_retry = 1;
                prepare_write_connect(con->msgr, con, 0);
-               prepare_read_connect_retry(con);
+               prepare_read_connect(con);
                break;
 
        case CEPH_MSGR_TAG_RESETSESSION: