3 files changed, 24 insertions, 1 deletions
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index c3852a7ff3c7..841de32f1fee 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -821,6 +821,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
+		.procname	= "tcp_ecn_fallback",
+		.data		= &init_net.ipv4.sysctl_tcp_ecn_fallback,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
 		.procname	= "ip_local_port_range",
 		.maxlen		= sizeof(init_net.ipv4.ip_local_ports.range),
 		.data		= &init_net.ipv4.ip_local_ports.range,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 91cb4768a860..0cc4b5a630cd 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2411,12 +2411,15 @@ static int __net_init tcp_sk_init(struct net *net)
 			goto fail;
 		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
 	}
+
 	net->ipv4.sysctl_tcp_ecn = 2;
+	net->ipv4.sysctl_tcp_ecn_fallback = 1;
+
 	net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
 	net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD;
 	net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL;
-	return 0;
 
+	return 0;
 fail:
 	tcp_sk_exit(net);
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 08c2cc40b26d..e29d43b5a0bb 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -350,6 +350,15 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 	}
 }
 
+static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
+{
+	if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)
+		/* tp->ecn_flags are cleared at a later point in time when
+		 * SYN ACK is ultimatively being received.
+		 */
+		TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR);
+}
+
 static void
 tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th,
 		    struct sock *sk)
@@ -2615,6 +2624,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		}
 	}
 
+	/* RFC3168, section 6.1.1.1. ECN fallback */
+	if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN)
+		tcp_ecn_clear_syn(sk, skb);
+
 	tcp_retrans_try_collapse(sk, skb, cur_mss);
 
 	/* Make a copy, if the first transmission SKB clone we made