libceph: WARN, don't BUG on unexpected connection states

A number of assertions in the ceph messenger are implemented with
BUG_ON(), killing the system if connection's state doesn't match
what's expected.  At this point our state model is (evidently) not
well understood enough for these assertions to trigger a BUG().
Convert all BUG_ON(con->state...) calls to be WARN_ON(con->state...)
so we learn about these issues without killing the machine.

We now recognize that a connection fault can occur due to a socket
closure at any time, regardless of the state of the connection.  So
there is really nothing we can assert about the state of the
connection at that point so eliminate that assertion.

Reported-by: Ugis <ugis22@gmail.com>
Tested-by: Ugis <ugis22@gmail.com>
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>

1 files changed, 5 insertions, 6 deletions

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 4d111fd2b492..3b386674e34c 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -561,7 +561,7 @@ void ceph_con_open(struct ceph_connection *con,
         mutex_lock(&con->mutex);
         dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
 
-        BUG_ON(con->state != CON_STATE_CLOSED);
+        WARN_ON(con->state != CON_STATE_CLOSED);
         con->state = CON_STATE_PREOPEN;
 
         con->peer_name.type = (__u8) entity_type;
@@ -1509,7 +1509,7 @@ static int process_banner(struct ceph_connection *con)
 static void fail_protocol(struct ceph_connection *con)
 {
         reset_connection(con);
-        BUG_ON(con->state != CON_STATE_NEGOTIATING);
+        WARN_ON(con->state != CON_STATE_NEGOTIATING);
         con->state = CON_STATE_CLOSED;
 }
 
@@ -1635,7 +1635,7 @@ static int process_connect(struct ceph_connection *con)
                         return -1;
                 }
 
-                BUG_ON(con->state != CON_STATE_NEGOTIATING);
+                WARN_ON(con->state != CON_STATE_NEGOTIATING);
                 con->state = CON_STATE_OPEN;
 
                 con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
@@ -2132,7 +2132,6 @@ more:
                 if (ret < 0)
                         goto out;
 
-                BUG_ON(con->state != CON_STATE_CONNECTING);
                 con->state = CON_STATE_NEGOTIATING;
 
                 /*
@@ -2160,7 +2159,7 @@ more:
                 goto more;
         }
 
-        BUG_ON(con->state != CON_STATE_OPEN);
+        WARN_ON(con->state != CON_STATE_OPEN);
 
         if (con->in_base_pos < 0) {
                 /*
@@ -2382,7 +2381,7 @@ static void ceph_fault(struct ceph_connection *con)
         dout("fault %p state %lu to peer %s\n",
              con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));
 
-        BUG_ON(con->state != CON_STATE_CONNECTING &&
+        WARN_ON(con->state != CON_STATE_CONNECTING &&
                con->state != CON_STATE_NEGOTIATING &&
                con->state != CON_STATE_OPEN);