tcp: reflect SYN queue_mapping into SYNACK packets

While testing how linux behaves on SYNFLOOD attack on multiqueue device
(ixgbe), I found that SYNACK messages were dropped at Qdisc level
because we send them all on a single queue.

Obvious choice is to reflect incoming SYN packet @queue_mapping to
SYNACK packet.

Under stress, my machine could only send 25.000 SYNACK per second (for
200.000 incoming SYN per second). NIC : ixgbe with 16 rx/tx queues.

After patch, not a single SYNACK is dropped.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Hans Schillstrom <hans.schillstrom@ericsson.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 12 insertions, 6 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a43b87d..c8d28c4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -824,7 +824,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
  */
 static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 			      struct request_sock *req,
-			      struct request_values *rvp)
+			      struct request_values *rvp,
+			      u16 queue_mapping)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct flowi4 fl4;
@@ -840,6 +841,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr);
 
+		skb_set_queue_mapping(skb, queue_mapping);
 		err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
 					    ireq->rmt_addr,
 					    ireq->opt);
@@ -854,7 +856,7 @@ static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req,
 			      struct request_values *rvp)
 {
 	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
-	return tcp_v4_send_synack(sk, NULL, req, rvp);
+	return tcp_v4_send_synack(sk, NULL, req, rvp, 0);
 }
 
 /*
@@ -1422,7 +1424,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_rsk(req)->snt_synack = tcp_time_stamp;
 
 	if (tcp_v4_send_synack(sk, dst, req,
-			       (struct request_values *)&tmp_ext) ||
+			       (struct request_values *)&tmp_ext,
+			       skb_get_queue_mapping(skb)) ||
 	    want_cookie)
 		goto drop_and_free;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 554d599..3a9aec2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -476,7 +476,8 @@ out:
 
 
 static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
-			      struct request_values *rvp)
+			      struct request_values *rvp,
+			      u16 queue_mapping)
 {
 	struct inet6_request_sock *treq = inet6_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -513,6 +514,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 		__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
 
 		fl6.daddr = treq->rmt_addr;
+		skb_set_queue_mapping(skb, queue_mapping);
 		err = ip6_xmit(sk, skb, &fl6, opt, np->tclass);
 		err = net_xmit_eval(err);
 	}
@@ -528,7 +530,7 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req,
 			     struct request_values *rvp)
 {
 	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
-	return tcp_v6_send_synack(sk, req, rvp);
+	return tcp_v6_send_synack(sk, req, rvp, 0);
 }
 
 static void tcp_v6_reqsk_destructor(struct request_sock *req)
@@ -1213,7 +1215,8 @@ have_isn:
 	security_inet_conn_request(sk, skb, req);
 
 	if (tcp_v6_send_synack(sk, req,
-			       (struct request_values *)&tmp_ext) ||
+			       (struct request_values *)&tmp_ext,
+			       skb_get_queue_mapping(skb)) ||
 	    want_cookie)
 		goto drop_and_free;