Commit 8ef44b6f authored by Wei Wang's avatar Wei Wang Committed by David S. Miller
Browse files

tcp: Retain ECT bits for tos reflection 



For DCTCP, we have to retain the ECT bits set by the congestion control
algorithm on the socket when reflecting syn TOS in syn-ack, in order to
make ECN work properly.

Fixes: ac8f1710 ("tcp: reflect tos value received in SYN to the socket")
Reported-by: default avatarAlexander Duyck <alexanderduyck@fb.com>
Signed-off-by: default avatarWei Wang <weiwan@google.com>
Reviewed-by: default avatarEric Dumazet <edumazet@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent a770bf51

net/ipv4/tcp_ipv4.c

+5 −2
Original line number Diff line number Diff line
@@ -984,7 +984,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, 
		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);



		tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?

				tcp_rsk(req)->syn_tos & ~INET_ECN_MASK :

				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |

				(inet_sk(sk)->tos & INET_ECN_MASK) :

				inet_sk(sk)->tos;



		if (!INET_ECN_is_capable(tos) &&
@@ -1541,7 +1542,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, 
		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;

	newinet->inet_id = prandom_u32();



	/* Set ToS of the new socket based upon the value of incoming SYN. */

	/* Set ToS of the new socket based upon the value of incoming SYN.

	 * ECT bits are set later in tcp_init_transfer().

	 */

	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)

		newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;

net/ipv6/tcp_ipv6.c

+5 −2
Original line number Diff line number Diff line
@@ -528,7 +528,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, 
			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));



		tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?

				tcp_rsk(req)->syn_tos & ~INET_ECN_MASK :

				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |

				(np->tclass & INET_ECN_MASK) :

				np->tclass;



		if (!INET_ECN_is_capable(tclass) &&
@@ -1320,7 +1321,9 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * 
	if (np->repflow)

		newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));



	/* Set ToS of the new socket based upon the value of incoming SYN. */

	/* Set ToS of the new socket based upon the value of incoming SYN.

	 * ECT bits are set later in tcp_init_transfer().

	 */

	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)

		newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;