tcp: ECN blackhole should not force quickack mode

While playing with a new ADSL box at home, I discovered that ECN
blackhole can trigger suboptimal quickack mode on linux : We send one
ACK for each incoming data frame, without any delay and eventual
piggyback.

This is because TCP_ECN_check_ce() considers that if no ECT is seen on a
segment, this is because this segment was a retransmit.

Refine this heuristic and apply it only if we seen ECT in a previous
segment, to detect ECN blackhole at IP level.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Jamal Hadi Salim <jhs@mojatatu.com>
CC: Jerry Chu <hkchu@google.com>
CC: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
CC: Jim Gettys <jg@freedesktop.org>
CC: Dave Taht <dave.taht@gmail.com>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index f357befaaa01873eab5143f94a8cbe1960866a94..702aefc8d43da5bc9093bdb0fdd783825c842472 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -356,6 +356,7 @@ static inline void tcp_dec_quickack_mode(struct sock *sk,
 #define        TCP_ECN_OK              1
 #define        TCP_ECN_QUEUE_CWR       2
 #define        TCP_ECN_DEMAND_CWR      4
+#define        TCP_ECN_SEEN            8
 
 static __inline__ void
 TCP_ECN_create_request(struct request_sock *req, struct tcphdr *th)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a5d01b183cf71ad5a20ee9370568911473825987..5a4408c55155c22841f978e8c0125a6f3a3e6a7f 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -217,16 +217,25 @@ static inline void TCP_ECN_withdraw_cwr(struct tcp_sock *tp)
        tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
 }
 
-static inline void TCP_ECN_check_ce(struct tcp_sock *tp, struct sk_buff *skb)
+static inline void TCP_ECN_check_ce(struct tcp_sock *tp, const struct sk_buff *skb)
 {
-       if (tp->ecn_flags & TCP_ECN_OK) {
-               if (INET_ECN_is_ce(TCP_SKB_CB(skb)->flags))
-                       tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+       if (!(tp->ecn_flags & TCP_ECN_OK))
+               return;
+
+       switch (TCP_SKB_CB(skb)->flags & INET_ECN_MASK) {
+       case INET_ECN_NOT_ECT:
                /* Funny extension: if ECT is not set on a segment,
-                * it is surely retransmit. It is not in ECN RFC,
-                * but Linux follows this rule. */
-               else if (INET_ECN_is_not_ect((TCP_SKB_CB(skb)->flags)))
+                * and we already seen ECT on a previous segment,
+                * it is probably a retransmit.
+                */
+               if (tp->ecn_flags & TCP_ECN_SEEN)
                        tcp_enter_quickack_mode((struct sock *)tp);
+               break;
+       case INET_ECN_CE:
+               tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
+               /* fallinto */
+       default:
+               tp->ecn_flags |= TCP_ECN_SEEN;
        }
 }