2005-06-01 Paul Jakma <paul.jakma@sun.com>

	* bgpd/(general) refcount struct peer and bgp_info, hence allowing us
	  add work_queues for bgp_process.
	* bgpd/bgp_route.h: (struct bgp_info) Add 'lock' field for refcount.
	  Add bgp_info_{lock,unlock} helper functions.
	  Add bgp_info_{add,delete} helpers, to remove need for
	  users managing locking/freeing of bgp_info and bgp_node's.
	* bgpd/bgp_table.h: (struct bgp_node) Add a flags field, and
	  BGP_NODE_PROCESS_SCHEDULED to merge redundant processing of
	  nodes.
	* bgpd/bgp_fsm.h: Make the ON/OFF/ADD/REMOVE macros lock and unlock
	  peer reference as appropriate.
	* bgpd/bgp_damp.c: Remove its internal prototypes for
	  bgp_info_delete/free. Just use bgp_info_delete.
	* bgpd/bgpd.h: (struct bgp_master) Add work_queue pointers.
	  (struct peer) Add reference count 'lock'
	  (peer_lock,peer_unlock) New helpers to take/release reference
	  on struct peer.
	* bgpd/bgp_advertise.c: (general) Add peer and bgp_info refcounting
	  and balance how references are taken and released.
	  (bgp_advertise_free) release bgp_info reference, if appropriate
	  (bgp_adj_out_free) unlock peer
	  (bgp_advertise_clean) leave the adv references alone, or else
	  call bgp_advertise_free cant unlock them.
	  (bgp_adj_out_set) lock the peer on new adj's, leave the reference
	  alone otherwise. lock the new bgp_info reference.
	  (bgp_adj_in_set) lock the peer reference
	  (bgp_adj_in_remove) and unlock it here
	  (bgp_sync_delete) make hash_free on peer conditional, just in
	  case.
	* bgpd/bgp_fsm.c: (general) document that the timers depend on
	  bgp_event to release a peer reference.
	  (bgp_fsm_change_status) moved up the file, unchanged.
	  (bgp_stop) Decrement peer lock as many times as cancel_event
	  canceled - shouldnt be needed but just in case.
	  stream_fifo_clean of obuf made conditional, just in case.
	  (bgp_event) always unlock the peer, regardless of return value
	  of bgp_fsm_change_status.
	* bgpd/bgp_packet.c: (general) change several bgp_stop's to BGP_EVENT's.
	  (bgp_read) Add a mysterious extra peer_unlock for ACCEPT_PEERs
	  along with a comment on it.
	* bgpd/bgp_route.c: (general) Add refcounting of bgp_info, cleanup
	  some of the resource management around bgp_info. Refcount peer.
	  Add workqueues for bgp_process and clear_table.
	  (bgp_info_new) make static
	  (bgp_info_free) Ditto, and unlock the peer reference.
	  (bgp_info_lock,bgp_info_unlock) new exported functions
	  (bgp_info_add) Add a bgp_info to a bgp_node in correct fashion,
	  taking care of reference counts.
	  (bgp_info_delete) do the opposite of bgp_info_add.
	  (bgp_process_rsclient) Converted into a work_queue work function.
	  (bgp_process_main) ditto.
	  (bgp_processq_del) process work queue item deconstructor
	  (bgp_process_queue_init) process work queue init
	  (bgp_process) call init function if required, set up queue item
	  and add to queue, rather than calling process functions directly.
	  (bgp_rib_remove) let bgp_info_delete manage bgp_info refcounts
	  (bgp_rib_withdraw) ditto
	  (bgp_update_rsclient) let bgp_info_add manage refcounts
	  (bgp_update_main) ditto
	  (bgp_clear_route_node) clear_node_queue work function, does
	  per-node aspects of what bgp_clear_route_table did previously
	  (bgp_clear_node_queue_del) clear_node_queue item delete function
	  (bgp_clear_node_complete) clear_node_queue completion function,
	  it unplugs the process queues, which have to be blocked while
	  clear_node_queue is being processed to prevent a race.
	  (bgp_clear_node_queue_init) init function for clear_node_queue
	  work queues
	  (bgp_clear_route_table) Sets up items onto a workqueue now, rather
	  than clearing each node directly. Plugs both process queues to
	  avoid potential race.
	  (bgp_static_withdraw_rsclient) let bgp_info_{add,delete} manage
	  bgp_info refcounts.
	  (bgp_static_update_rsclient) ditto
	  (bgp_static_update_main) ditto
	  (bgp_static_update_vpnv4) ditto, remove unneeded cast.
	  (bgp_static_withdraw) see bgp_static_withdraw_rsclient
	  (bgp_static_withdraw_vpnv4) ditto
	  (bgp_aggregate_{route,add,delete}) ditto
	  (bgp_redistribute_{add,delete,withdraw}) ditto
	* bgpd/bgp_vty.c: (peer_rsclient_set_vty) lock rsclient list peer
	  reference
	  (peer_rsclient_unset_vty) ditto, but unlock same reference
	* bgpd/bgpd.c: (peer_free) handle frees of info to be kept for lifetime
	  of struct peer.
	  (peer_lock,peer_unlock) peer refcount helpers
	  (peer_new) add initial refcounts
	  (peer_create,peer_create_accept) lock peer as appropriate
	  (peer_delete) unlock as appropriate, move out some free's to
	  peer_free.
	  (peer_group_bind,peer_group_unbind) peer refcounting as
	  appropriate.
	  (bgp_create) check CALLOC return value.
	  (bgp_terminate) free workqueues too.
	* lib/memtypes.c: Add MTYPE_BGP_PROCESS_QUEUE and
	  MTYPE_BGP_CLEAR_NODE_QUEUE

1 files changed, 41 insertions, 36 deletions

diff --git a/bgpd/bgp_fsm.c b/bgpd/bgp_fsm.c
index 6368ff47..fc7654f0 100644
--- a/bgpd/bgp_fsm.c
+++ b/bgpd/bgp_fsm.c
@@ -214,7 +214,7 @@ bgp_start_timer (struct thread *thread)
 	  "%s [FSM] Timer (start timer expire).", peer->host);
 
   THREAD_VAL (thread) = BGP_Start;
-  bgp_event (thread);
+  bgp_event (thread);  /* bgp_event unlocks peer */
 
   return 0;
 }
@@ -233,7 +233,7 @@ bgp_connect_timer (struct thread *thread)
 	  peer->host);
 
   THREAD_VAL (thread) = ConnectRetry_timer_expired;
-  bgp_event (thread);
+  bgp_event (thread); /* bgp_event unlocks peer */
 
   return 0;
 }
@@ -253,7 +253,7 @@ bgp_holdtime_timer (struct thread *thread)
 	  peer->host);
 
   THREAD_VAL (thread) = Hold_Timer_expired;
-  bgp_event (thread);
+  bgp_event (thread); /* bgp_event unlocks peer */
 
   return 0;
 }
@@ -273,7 +273,7 @@ bgp_keepalive_timer (struct thread *thread)
 	  peer->host);
 
   THREAD_VAL (thread) = KeepAlive_timer_expired;
-  bgp_event (thread);
+  bgp_event (thread); /* bgp_event unlocks peer */
 
   return 0;
 }
@@ -388,12 +388,31 @@ bgp_graceful_stale_timer_expire (struct thread *thread)
   return 0;
 }
 
+/* Called after event occured, this function change status and reset
+   read/write and timer thread. */
+void
+bgp_fsm_change_status (struct peer *peer, int status)
+{
+  bgp_dump_state (peer, peer->status, status);
+
+  /* Preserve old status and change into new status. */
+  peer->ostatus = peer->status;
+  peer->status = status;
+
+  if (BGP_DEBUG (normal, NORMAL))
+    zlog_debug ("%s went from %s to %s",
+		peer->host,
+		LOOKUP (bgp_status_msg, peer->ostatus),
+		LOOKUP (bgp_status_msg, peer->status));
+}
+
 /* Administrative BGP peer stop event. */
 int
 bgp_stop (struct peer *peer)
 {
   afi_t afi;
   safi_t safi;
+  unsigned int i;
   char orf_name[BUFSIZ];
 
   /* Increment Dropped count. */
@@ -468,9 +487,11 @@ bgp_stop (struct peer *peer)
   BGP_TIMER_OFF (peer->t_asorig);
   BGP_TIMER_OFF (peer->t_routeadv);
 
-  /* Delete all existing events of the peer. */
-  BGP_EVENT_DELETE (peer);
-
+  /* Delete all existing events of the peer,
+     and corresponding peer ref-count */
+  for (i = thread_cancel_event (master, peer); i > 0; i--)
+    peer_unlock (peer); /* thread event reference */
+  
   /* Stream reset. */
   peer->packet_size = 0;
 
@@ -479,7 +500,8 @@ bgp_stop (struct peer *peer)
     stream_reset (peer->ibuf);
   if (peer->work)
     stream_reset (peer->work);
-  stream_fifo_clean (peer->obuf);
+  if (peer->obuf)
+    stream_fifo_clean (peer->obuf);
 
   /* Close of file descriptor. */
   if (peer->fd >= 0)
@@ -683,24 +705,6 @@ bgp_fsm_open (struct peer *peer)
   return 0;
 }
 
-/* Called after event occured, this function change status and reset
-   read/write and timer thread. */
-void
-bgp_fsm_change_status (struct peer *peer, int status)
-{
-  bgp_dump_state (peer, peer->status, status);
-
-  /* Preserve old status and change into new status. */
-  peer->ostatus = peer->status;
-  peer->status = status;
-
-  if (BGP_DEBUG (normal, NORMAL))
-    zlog_debug ("%s went from %s to %s",
-		peer->host,
-		LOOKUP (bgp_status_msg, peer->ostatus),
-		LOOKUP (bgp_status_msg, peer->status));
-}
-
 /* Keepalive send to peer. */
 int
 bgp_fsm_keepalive_expire (struct peer *peer)
@@ -1021,15 +1025,16 @@ bgp_event (struct thread *thread)
   ret = (*(FSM [peer->status - 1][event - 1].func))(peer);
 
   /* When function do not want proceed next job return -1. */
-  if (ret < 0)
-    return ret;
-    
-  /* If status is changed. */
-  if (next != peer->status)
-    bgp_fsm_change_status (peer, next);
-
-  /* Make sure timer is set. */
-  bgp_timer_set (peer);
+  if (ret >= 0)
+    {
+      /* If status is changed. */
+      if (next != peer->status)
+        bgp_fsm_change_status (peer, next);
 
-  return 0;
+      /* Make sure timer is set. */
+      bgp_timer_set (peer);
+    }
+  
+  peer_unlock (peer); /* bgp-event peer reference */
+  return ret;
 }