tcp: be more strict before accepting ECN negociation

commit bd14b1b2e29bd6812597f896dde06eaf7c6d2f24 upstream.

It appears some networks play bad games with the two bits reserved for
ECN. This can trigger false congestion notifications and very slow
transferts.

Since RFC 3168 (6.1.1) forbids SYN packets to carry CT bits, we can
disable TCP ECN negociation if it happens we receive mangled CT bits in
the SYN packet.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Perry Lorier <perryl@google.com>
Cc: Matt Mathis <mattmathis@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Wilmer van der Gaast <wilmer@google.com>
Cc: Ankur Jain <jankur@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Dave Täht <dave.taht@bufferbloat.net>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Cc: Florian Westphal <fw@strlen.de>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index fe46019..238255b 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -358,13 +358,6 @@ static inline void tcp_dec_quickack_mode(struct sock *sk,
 #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)
-{
-       if (sysctl_tcp_ecn && th->ece && th->cwr)
-               inet_rsk(req)->ecn_ok = 1;
-}
-
 enum tcp_tw_status {
        TCP_TW_SUCCESS = 0,
        TCP_TW_RST = 1,
@@ -652,6 +645,22 @@ struct tcp_skb_cb {
 
 #define TCP_SKB_CB(__skb)      ((struct tcp_skb_cb *)&((__skb)->cb[0]))
 
+/* RFC3168 : 6.1.1 SYN packets must not have ECT/ECN bits set
+ *
+ * If we receive a SYN packet with these bits set, it means a network is
+ * playing bad games with TOS bits. In order to avoid possible false congestion
+ * notifications, we disable TCP ECN negociation.
+ */
+static inline void
+TCP_ECN_create_request(struct request_sock *req, const struct sk_buff *skb)
+{
+       const struct tcphdr *th = tcp_hdr(skb);
+
+       if (sysctl_tcp_ecn && th->ece && th->cwr &&
+           INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield))
+               inet_rsk(req)->ecn_ok = 1;
+}
+
 /* Due to TSO, an SKB can be composed of multiple actual
  * packets.  To keep these tracked properly, we use this.
  */

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 92d7138..26eb8e2 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1352,7 +1352,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
                goto drop_and_free;
 
        if (!want_cookie || tmp_opt.tstamp_ok)
-               TCP_ECN_create_request(req, tcp_hdr(skb));
+               TCP_ECN_create_request(req, skb);
 
        if (want_cookie) {
                isn = cookie_v4_init_sequence(sk, skb, &req->mss);

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c69358c..057a9d2 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1254,7 +1254,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
        ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr);
        ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr);
        if (!want_cookie || tmp_opt.tstamp_ok)
-               TCP_ECN_create_request(req, tcp_hdr(skb));
+               TCP_ECN_create_request(req, skb);
 
        treq->iif = sk->sk_bound_dev_if;