sctp: add dst_pending_confirm flag

Add new transport flag to allow sockets to confirm neighbour.
When same struct dst_entry can be used for many different
neighbours we can not use it for pending confirmations.
The flag is propagated from transport to every packet.
It is reset when cached dst is reset.

Reported-by: YueHaibing <yuehaibing@huawei.com>
Fixes: 5110effee8fd ("net: Do delayed neigh confirmation.")
Fixes: f2bb4bedf35d ("ipv4: Cache output routes in fib_info nexthops.")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 31 insertions, 12 deletions

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index e50dc6d7543f..2a6835b4562b 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -832,8 +832,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 		if (transport->state != SCTP_UNCONFIRMED)
 			transport->state = SCTP_INACTIVE;
 		else {
-			dst_release(transport->dst);
-			transport->dst = NULL;
+			sctp_transport_dst_release(transport);
 			ulp_notify = false;
 		}
 
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 07ab5062e541..814eac047467 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -546,6 +546,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	struct sctp_association *asoc = tp->asoc;
 	struct sctp_chunk *chunk, *tmp;
 	int pkt_count, gso = 0;
+	int confirm;
 	struct dst_entry *dst;
 	struct sk_buff *head;
 	struct sctphdr *sh;
@@ -624,7 +625,14 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 			asoc->peer.last_sent_to = tp;
 	}
 	head->ignore_df = packet->ipfragok;
-	tp->af_specific->sctp_xmit(head, tp);
+	confirm = tp->dst_pending_confirm;
+	if (confirm)
+		skb_set_dst_pending_confirm(head, 1);
+	/* neighbour should be confirmed on successful transmission or
+	 * positive error
+	 */
+	if (tp->af_specific->sctp_xmit(head, tp) >= 0 && confirm)
+		tp->dst_pending_confirm = 0;
 
 out:
 	list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 65abe22d8691..db352e5d61f8 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -1654,7 +1654,7 @@ static void sctp_check_transmitted(struct sctp_outq *q,
 
 		if (forward_progress) {
 			if (transport->dst)
-				dst_confirm(transport->dst);
+				sctp_transport_dst_confirm(transport);
 		}
 	}
 
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index ad3445b3408e..c7d3249f88ec 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -3333,8 +3333,7 @@ static void sctp_asconf_param_success(struct sctp_association *asoc,
 		local_bh_enable();
 		list_for_each_entry(transport, &asoc->peer.transport_addr_list,
 				transports) {
-			dst_release(transport->dst);
-			transport->dst = NULL;
+			sctp_transport_dst_release(transport);
 		}
 		break;
 	case SCTP_PARAM_DEL_IP:
@@ -3348,8 +3347,7 @@ static void sctp_asconf_param_success(struct sctp_association *asoc,
 		local_bh_enable();
 		list_for_each_entry(transport, &asoc->peer.transport_addr_list,
 				transports) {
-			dst_release(transport->dst);
-			transport->dst = NULL;
+			sctp_transport_dst_release(transport);
 		}
 		break;
 	default:
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index a4552712b882..51abcc90fe75 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -755,7 +755,7 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds,
 	 * forward progress.
 	 */
 	if (t->dst)
-		dst_confirm(t->dst);
+		sctp_transport_dst_confirm(t);
 
 	/* The receiver of the HEARTBEAT ACK should also perform an
 	 * RTT measurement for that destination transport address
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 5fc7122c76de..a4609a0be76d 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -592,7 +592,7 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
 			list_for_each_entry(trans,
 			    &asoc->peer.transport_addr_list, transports) {
 				/* Clear the source and route cache */
-				dst_release(trans->dst);
+				sctp_transport_dst_release(trans);
 				trans->cwnd = min(4*asoc->pathmtu, max_t(__u32,
 				    2*asoc->pathmtu, 4380));
 				trans->ssthresh = asoc->peer.i.a_rwnd;
@@ -843,7 +843,7 @@ skip_mkasconf:
 		 */
 		list_for_each_entry(transport, &asoc->peer.transport_addr_list,
 					transports) {
-			dst_release(transport->dst);
+			sctp_transport_dst_release(transport);
 			sctp_transport_route(transport, NULL,
 					     sctp_sk(asoc->base.sk));
 		}
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index baa1ac00d7b5..5b63ceb3bf37 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -240,7 +240,7 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
 {
 	/* If we don't have a fresh route, look one up */
 	if (!transport->dst || transport->dst->obsolete) {
-		dst_release(transport->dst);
+		sctp_transport_dst_release(transport);
 		transport->af_specific->get_dst(transport, &transport->saddr,
 						&transport->fl, sk);
 	}
@@ -672,3 +672,17 @@ void sctp_transport_immediate_rtx(struct sctp_transport *t)
 			sctp_transport_hold(t);
 	}
 }
+
+/* Drop dst */
+void sctp_transport_dst_release(struct sctp_transport *t)
+{
+	dst_release(t->dst);
+	t->dst = NULL;
+	t->dst_pending_confirm = 0;
+}
+
+/* Schedule neighbour confirm */
+void sctp_transport_dst_confirm(struct sctp_transport *t)
+{
+	t->dst_pending_confirm = 1;
+}