[bgpd] Fix 0.99 shutdown regression, introduce Clearing and Deleted states

2006-09-14 Paul Jakma <paul.jakma@sun.com>

	* (general) Fix some niggly issues around 'shutdown' and clearing
	  by adding a Clearing FSM wait-state and a hidden 'Deleted'
	  FSM state, to allow deleted peers to 'cool off' and hit 0
	  references. This introduces a slow memory leak of struct peer,
	  however that's more a testament to the fragility of the
	  reference counting than a bug in this patch, cleanup of
	  reference counting to fix this is to follow.
	* bgpd.h: Add Clearing, Deleted states and Clearing_Completed
	  and event.
	* bgp_debug.c: (bgp_status_msg[]) Add strings for Clearing and
	  Deleted.
	* bgp_fsm.h: Don't allow timer/event threads to set anything
	  for Deleted peers.
	* bgp_fsm.c: (bgp_timer_set) Add Clearing and Deleted. Deleted
	  needs to stop everything.
	  (bgp_stop) Remove explicit fsm_change_status call, the
	  general framework handles the transition.
	  (bgp_start) Log a warning if a start is attempted on a peer
	  that should stay down, trying to start a peer.
	  (struct .. FSM) Add Clearing_Completed
	  events, has little influence except when in state
	  Clearing to signal wait-state can end.
	  Add Clearing and Deleted states, former is a wait-state,
	  latter is a placeholder state to allow peers to disappear
	  quietly once refcounts settle.
	  (bgp_event) Try reduce verbosity of FSM state-change debug,
	  changes to same state are not interesting (Established->Established)
	  Allow NULL action functions in FSM.
	* bgp_packet.c: (bgp_write) Use FSM events, rather than trying
	  to twiddle directly with FSM state behind the back of FSM.
	  (bgp_write_notify) ditto.
	  (bgp_read) Remove the vague ACCEPT_PEER peer_unlock, or else
	  this patch crashes, now it leaks instead.
	* bgp_route.c: (bgp_clear_node_complete) Clearing_Completed
	  event, to end clearing.
	  (bgp_clear_route) See extensive comments.
	* bgpd.c: (peer_free) should only be called while in Deleted,
	  peer refcounting controls when peer_free is called.
	  bgp_sync_delete should be here, not in peer_delete.
	  (peer_delete) Initiate delete.
	  Transition to Deleted state manually.
	  When removing peer from indices that provide visibility of it,
	  take great care to be idempotent wrt the reference counting
	  of struct peer through those indices.
	  Use bgp_timer_set, rather than replicating.
	  Call to bgp_sync_delete isn't appropriate here, sync can be
	  referenced while shutting down and finishing deletion.
	  (peer_group_bind) Take care to be idempotent wrt list references
	  indexing peers.

1 files changed, 5 insertions, 22 deletions

diff --git a/bgpd/bgp_packet.c b/bgpd/bgp_packet.c
index 8b024a1c..da59d329 100644
--- a/bgpd/bgp_packet.c
+++ b/bgpd/bgp_packet.c
@@ -637,9 +637,7 @@ bgp_write (struct thread *thread)
 	  if (write_errno == EWOULDBLOCK || write_errno == EAGAIN)
 	      break;
 
-	  BGP_EVENT_ADD (peer, BGP_Stop);
-	  peer->status = Idle;
-	  bgp_timer_set (peer);
+	  BGP_EVENT_FLUSH_ADD (peer, TCP_fatal_error);
 	  return 0;
 	}
       if (num != writenum)
@@ -673,10 +671,8 @@ bgp_write (struct thread *thread)
 	  if (peer->v_start >= (60 * 2))
 	    peer->v_start = (60 * 2);
 
-	  BGP_EVENT_ADD (peer, BGP_Stop);
-	  /*bgp_stop (peer);*/
-	  peer->status = Idle;
-	  bgp_timer_set (peer);
+	  /* Flush any existing events */
+	  BGP_EVENT_FLUSH_ADD (peer, BGP_Stop);
 	  return 0;
 	case BGP_MSG_KEEPALIVE:
 	  peer->keepalive_out++;
@@ -721,9 +717,7 @@ bgp_write_notify (struct peer *peer)
   ret = writen (peer->fd, STREAM_DATA (s), stream_get_endp (s));
   if (ret <= 0)
     {
-      BGP_EVENT_ADD (peer, BGP_Stop);
-      peer->status = Idle;
-      bgp_timer_set (peer);
+      BGP_EVENT_FLUSH_ADD (peer, TCP_fatal_error);
       return 0;
     }
 
@@ -743,10 +737,7 @@ bgp_write_notify (struct peer *peer)
   if (peer->v_start >= (60 * 2))
     peer->v_start = (60 * 2);
 
-  /* We don't call event manager at here for avoiding other events. */
-  bgp_stop (peer);
-  peer->status = Idle;
-  bgp_timer_set (peer);
+  BGP_EVENT_FLUSH_ADD (peer, BGP_Stop);
 
   return 0;
 }
@@ -2375,14 +2366,6 @@ bgp_read (struct thread *thread)
       if (BGP_DEBUG (events, EVENTS))
 	zlog_debug ("%s [Event] Accepting BGP peer delete", peer->host);
       peer_delete (peer);
-      /* we've lost track of a reference to ACCEPT_PEER somehow.  It doesnt
-       * _seem_ to be the 'update realpeer with accept peer' hack, yet it
-       * *must* be.. Very very odd, but I give up trying to
-       * root cause this - ACCEPT_PEER is a dirty hack, it should be fixed
-       * instead, which would make root-causing this a moot point..
-       * A hack because of a hack, appropriate.
-       */
-      peer_unlock (peer); /* god knows what reference... ACCEPT_PEER sucks */
     }
   return 0;
 }