Commit bd14b1b2 authored by Eric Dumazet's avatar Eric Dumazet Committed by David S. Miller

tcp: be more strict before accepting ECN negociation

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: default avatarEric 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: default avatarNeal Cardwell <ncardwell@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent f45ebf3a
...@@ -367,13 +367,6 @@ static inline void tcp_dec_quickack_mode(struct sock *sk, ...@@ -367,13 +367,6 @@ static inline void tcp_dec_quickack_mode(struct sock *sk,
#define TCP_ECN_DEMAND_CWR 4 #define TCP_ECN_DEMAND_CWR 4
#define TCP_ECN_SEEN 8 #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 { enum tcp_tw_status {
TCP_TW_SUCCESS = 0, TCP_TW_SUCCESS = 0,
TCP_TW_RST = 1, TCP_TW_RST = 1,
...@@ -671,6 +664,22 @@ struct tcp_skb_cb { ...@@ -671,6 +664,22 @@ struct tcp_skb_cb {
#define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) #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 /* Due to TSO, an SKB can be composed of multiple actual
* packets. To keep these tracked properly, we use this. * packets. To keep these tracked properly, we use this.
*/ */
......
...@@ -1368,7 +1368,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ...@@ -1368,7 +1368,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
goto drop_and_free; goto drop_and_free;
if (!want_cookie || tmp_opt.tstamp_ok) if (!want_cookie || tmp_opt.tstamp_ok)
TCP_ECN_create_request(req, tcp_hdr(skb)); TCP_ECN_create_request(req, skb);
if (want_cookie) { if (want_cookie) {
isn = cookie_v4_init_sequence(sk, skb, &req->mss); isn = cookie_v4_init_sequence(sk, skb, &req->mss);
......
...@@ -1140,7 +1140,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ...@@ -1140,7 +1140,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
treq->rmt_addr = ipv6_hdr(skb)->saddr; treq->rmt_addr = ipv6_hdr(skb)->saddr;
treq->loc_addr = ipv6_hdr(skb)->daddr; treq->loc_addr = ipv6_hdr(skb)->daddr;
if (!want_cookie || tmp_opt.tstamp_ok) 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; treq->iif = sk->sk_bound_dev_if;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment