tipc: transfer broadcast nacks in link state messages

When we send broadcasts in clusters of more 70-80 nodes, we sometimes
see the broadcast link resetting because of an excessive number of
retransmissions. This is caused by a combination of two factors:

1) A 'NACK crunch", where loss of broadcast packets is discovered
   and NACK'ed by several nodes simultaneously, leading to multiple
   redundant broadcast retransmissions.

2) The fact that the NACKS as such also are sent as broadcast, leading
   to excessive load and packet loss on the transmitting switch/bridge.

This commit deals with the latter problem, by moving sending of
broadcast nacks from the dedicated BCAST_PROTOCOL/NACK message type
to regular unicast LINK_PROTOCOL/STATE messages. We allocate 10 unused
bits in word 8 of the said message for this purpose, and introduce a
new capability bit, TIPC_BCAST_STATE_NACK in order to keep the change
backwards compatible.

Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 30 insertions, 2 deletions

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 7e8b75fd1a02..7ef14e2d2356 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1262,6 +1262,34 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb)
         kfree_skb(skb);
 }
 
+static void tipc_node_bc_sync_rcv(struct tipc_node *n, struct tipc_msg *hdr,
+                                  int bearer_id, struct sk_buff_head *xmitq)
+{
+        struct tipc_link *ucl;
+        int rc;
+
+        rc = tipc_bcast_sync_rcv(n->net, n->bc_entry.link, hdr);
+
+        if (rc & TIPC_LINK_DOWN_EVT) {
+                tipc_bearer_reset_all(n->net);
+                return;
+        }
+
+        if (!(rc & TIPC_LINK_SND_STATE))
+                return;
+
+        /* If probe message, a STATE response will be sent anyway */
+        if (msg_probe(hdr))
+                return;
+
+        /* Produce a STATE message carrying broadcast NACK */
+        tipc_node_read_lock(n);
+        ucl = n->links[bearer_id].link;
+        if (ucl)
+                tipc_link_build_state_msg(ucl, xmitq);
+        tipc_node_read_unlock(n);
+}
+
 /**
  * tipc_node_bc_rcv - process TIPC broadcast packet arriving from off-node
  * @net: the applicable net namespace
@@ -1298,7 +1326,7 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id
         rc = tipc_bcast_rcv(net, be->link, skb);
 
         /* Broadcast ACKs are sent on a unicast link */
-        if (rc & TIPC_LINK_SND_BC_ACK) {
+        if (rc & TIPC_LINK_SND_STATE) {
                 tipc_node_read_lock(n);
                 tipc_link_build_state_msg(le->link, &xmitq);
                 tipc_node_read_unlock(n);
@@ -1505,7 +1533,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
 
         /* Ensure broadcast reception is in synch with peer's send state */
         if (unlikely(usr == LINK_PROTOCOL))
-                tipc_bcast_sync_rcv(net, n->bc_entry.link, hdr);
+                tipc_node_bc_sync_rcv(n, hdr, bearer_id, &xmitq);
         else if (unlikely(tipc_link_acked(n->bc_entry.link) != bc_ack))
                 tipc_bcast_ack_rcv(net, n->bc_entry.link, bc_ack);