tipc: update a binding service via broadcast

Currently, updating binding table (add service binding to
name table/withdraw a service binding) is being sent over replicast.
However, if we are scaling up clusters to > 100 nodes/containers this
method is less affection because of looping through nodes in a cluster one
by one.

It is worth to use broadcast to update a binding service. This way, the
binding table can be updated on all peer nodes in one shot.

Broadcast is used when all peer nodes, as indicated by a new capability
flag TIPC_NAMED_BCAST, support reception of this message type.

Four problems need to be considered when introducing this feature.
1) When establishing a link to a new peer node we still update this by a
unicast 'bulk' update. This may lead to race conditions, where a later
broadcast publication/withdrawal bypass the 'bulk', resulting in
disordered publications, or even that a withdrawal may arrive before the
corresponding publication. We solve this by adding an 'is_last_bulk' bit
in the last bulk messages so that it can be distinguished from all other
messages. Only when this message has arrived do we open up for reception
of broadcast publications/withdrawals.

2) When a first legacy node is added to the cluster all distribution
will switch over to use the legacy 'replicast' method, while the
opposite happens when the last legacy node leaves the cluster. This
entails another risk of message disordering that has to be handled. We
solve this by adding a sequence number to the broadcast/replicast
messages, so that disordering can be discovered and corrected. Note
however that we don't need to consider potential message loss or
duplication at this protocol level.

3) Bulk messages don't contain any sequence numbers, and will always
arrive in order. Hence we must exempt those from the sequence number
control and deliver them unconditionally. We solve this by adding a new
'is_bulk' bit in those messages so that they can be recognized.

4) Legacy messages, which don't contain any new bits or sequence
numbers, but neither can arrive out of order, also need to be exempt
from the initial synchronization and sequence number check, and
delivered unconditionally. Therefore, we add another 'is_not_legacy' bit
to all new messages so that those can be distinguished from legacy
messages and the latter delivered directly.

v1->v2:
 - fix warning issue reported by kbuild test robot <lkp@intel.com>
 - add santiy check to drop the publication message with a sequence
number that is lower than the agreed synch point

Signed-off-by: kernel test robot <lkp@intel.com>
Signed-off-by: Hoang Huu Le <hoang.h.le@dektech.com.au>
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 23 insertions, 6 deletions

diff --git a/net/tipc/node.c b/net/tipc/node.c
index a4c2816c3746..030a51c4d1fa 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -75,6 +75,8 @@ struct tipc_bclink_entry {
 	struct sk_buff_head arrvq;
 	struct sk_buff_head inputq2;
 	struct sk_buff_head namedq;
+	u16 named_rcv_nxt;
+	bool named_open;
 };
 
 /**
@@ -396,10 +398,10 @@ static void tipc_node_write_unlock(struct tipc_node *n)
 	write_unlock_bh(&n->lock);
 
 	if (flags & TIPC_NOTIFY_NODE_DOWN)
-		tipc_publ_notify(net, publ_list, addr);
+		tipc_publ_notify(net, publ_list, addr, n->capabilities);
 
 	if (flags & TIPC_NOTIFY_NODE_UP)
-		tipc_named_node_up(net, addr);
+		tipc_named_node_up(net, addr, n->capabilities);
 
 	if (flags & TIPC_NOTIFY_LINK_UP) {
 		tipc_mon_peer_up(net, addr, bearer_id);
@@ -1483,6 +1485,7 @@ static void node_lost_contact(struct tipc_node *n,
 
 	/* Clean up broadcast state */
 	tipc_bcast_remove_peer(n->net, n->bc_entry.link);
+	__skb_queue_purge(&n->bc_entry.namedq);
 
 	/* Abort any ongoing link failover */
 	for (i = 0; i < MAX_BEARERS; i++) {
@@ -1729,12 +1732,23 @@ int tipc_node_distr_xmit(struct net *net, struct sk_buff_head *xmitq)
 	return 0;
 }
 
-void tipc_node_broadcast(struct net *net, struct sk_buff *skb)
+void tipc_node_broadcast(struct net *net, struct sk_buff *skb, int rc_dests)
 {
+	struct sk_buff_head xmitq;
 	struct sk_buff *txskb;
 	struct tipc_node *n;
+	u16 dummy;
 	u32 dst;
 
+	/* Use broadcast if all nodes support it */
+	if (!rc_dests && tipc_bcast_get_mode(net) != BCLINK_MODE_RCAST) {
+		__skb_queue_head_init(&xmitq);
+		__skb_queue_tail(&xmitq, skb);
+		tipc_bcast_xmit(net, &xmitq, &dummy);
+		return;
+	}
+
+	/* Otherwise use legacy replicast method */
 	rcu_read_lock();
 	list_for_each_entry_rcu(n, tipc_nodes(net), list) {
 		dst = n->addr;
@@ -1749,7 +1763,6 @@ void tipc_node_broadcast(struct net *net, struct sk_buff *skb)
 		tipc_node_xmit_skb(net, txskb, dst, 0);
 	}
 	rcu_read_unlock();
-
 	kfree_skb(skb);
 }
 
@@ -1844,7 +1857,9 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id
 
 	/* Handle NAME_DISTRIBUTOR messages sent from 1.7 nodes */
 	if (!skb_queue_empty(&n->bc_entry.namedq))
-		tipc_named_rcv(net, &n->bc_entry.namedq);
+		tipc_named_rcv(net, &n->bc_entry.namedq,
+			       &n->bc_entry.named_rcv_nxt,
+			       &n->bc_entry.named_open);
 
 	/* If reassembly or retransmission failure => reset all links to peer */
 	if (rc & TIPC_LINK_DOWN_EVT)
@@ -2114,7 +2129,9 @@ rcv:
 		tipc_node_link_down(n, bearer_id, false);
 
 	if (unlikely(!skb_queue_empty(&n->bc_entry.namedq)))
-		tipc_named_rcv(net, &n->bc_entry.namedq);
+		tipc_named_rcv(net, &n->bc_entry.namedq,
+			       &n->bc_entry.named_rcv_nxt,
+			       &n->bc_entry.named_open);
 
 	if (unlikely(!skb_queue_empty(&n->bc_entry.inputq1)))
 		tipc_node_mcast_rcv(n);