diff options
| author |   Wei Wang <weiwan@google.com> | 2020-09-09 17:50:48 -0700 |
|---|---|---|
| committer |   David S. Miller <davem@davemloft.net> | 2020-09-10 13:15:40 -0700 |
| commit | ac8f1710c12bb4c3626280ce03f05459ba8feef6 (patch) | |
| tree | f9db7718210545aa9708155babb2b1df39fb0fce /net/ipv4/tcp_ipv4.c | |
| parent | ip: pass tos into ip_build_and_send_pkt() (diff) | |
| download | linux-dev-ac8f1710c12bb4c3626280ce03f05459ba8feef6.tar.xz linux-dev-ac8f1710c12bb4c3626280ce03f05459ba8feef6.zip | |
tcp: reflect tos value received in SYN to the socket
This commit adds a new TCP feature to reflect the tos value received in
SYN, and send it out on the SYN-ACK, and eventually set the tos value of
the established socket with this reflected tos value. This provides a
way to set the traffic class/QoS level for all traffic in the same
connection to be the same as the incoming SYN request. It could be
useful in data centers to provide equivalent QoS according to the
incoming request.
This feature is guarded by /proc/sys/net/ipv4/tcp_reflect_tos, and is by
default turned off.
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp_ipv4.c')
| -rw-r--r-- | net/ipv4/tcp_ipv4.c | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c4c7ad4c8b5a..ace48b2790ff 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -972,6 +972,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi4 fl4; int err = -1; struct sk_buff *skb; + u8 tos; /* First, grab a route. */ if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) @@ -979,6 +980,9 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); + tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + tcp_rsk(req)->syn_tos : inet_sk(sk)->tos; + if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); @@ -986,7 +990,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, rcu_dereference(ireq->ireq_opt), - inet_sk(sk)->tos); + tos & ~INET_ECN_MASK); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -1531,6 +1535,10 @@ 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. */ + if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) + newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; + if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); if (!dst) |