From 169073db442cb9e5aa2b70a2e4158d4f35a3b810 Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Thu, 7 Apr 2011 13:05:25 -0400 Subject: [PATCH] tipc: Prevent broadcast link stalling when another node fails Ensure that broadcast link messages that have not been acknowledged by a newly failed node do not get an implied acknowledgement until the failed node is removed from the broadcast link's map of reachable nodes. Previously, a race condition allowed a new broadcast link message to be sent after the implicit acknowledgement processing was completed, but before the map of reachable nodes was updated, resulting in the message having an expected acknowledgement count that required the failed node to explicitly acknowledge the message. Since this would never occur the new message would remain in the broadcast link's transmit queue forever, eventually causing the link to become congested and "stall". Delaying the implicit acknowledgement processing until after the update of the map of reachable nodes eliminates this race condition and prevents stalling. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker --- net/tipc/node.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/node.c b/net/tipc/node.c index 810b39545264..d75432f5e726 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -349,9 +349,9 @@ static void node_lost_contact(struct tipc_node *n_ptr) n_ptr->bclink.defragm = NULL; } + tipc_nmap_remove(&tipc_bcast_nmap, n_ptr->addr); tipc_bclink_acknowledge(n_ptr, mod(n_ptr->bclink.acked + 10000)); - tipc_nmap_remove(&tipc_bcast_nmap, n_ptr->addr); if (n_ptr->addr < tipc_own_addr) tipc_own_tag--; -- 2.39.5