On Tue, Sep 15, 2015 at 3:24 PM, Eric Dumazet <eric.duma...@gmail.com> wrote:
> From: Eric Dumazet <eduma...@google.com>
>
> In commit b73c3d0e4f0e ("net: Save TX flow hash in sock and set in skbuf
> on xmit"), Tom provided a l4 hash to most outgoing TCP packets.
>
> We'd like to provide one as well for SYNACK packets, so that all packets
> of a given flow share same txhash, to later enable bonding driver to
> also use skb->hash to perform slave selection.
>
> Note that a SYNACK retransmit shuffles the tx hash, as Tom did
> in commit 265f94ff54d62 ("net: Recompute sk_txhash on negative routing
> advice") for established sockets.
>
> This has nice effect making TCP flows resilient to some kind of black
> holes, even at connection establish phase.
>
Acked-by: Tom Herbert <t...@herbertland.com>
> Signed-off-by: Eric Dumazet <eduma...@google.com>
> Cc: Tom Herbert <t...@herbertland.com>
> Cc: Mahesh Bandewar <mahe...@google.com>
> ---
> include/linux/tcp.h | 1 +
> include/net/sock.h | 12 ++++++++----
> net/ipv4/tcp_input.c | 1 +
> net/ipv4/tcp_ipv4.c | 2 +-
> net/ipv4/tcp_output.c | 2 ++
> net/ipv6/tcp_ipv6.c | 2 +-
> 6 files changed, 14 insertions(+), 6 deletions(-)
>
> diff --git a/include/linux/tcp.h b/include/linux/tcp.h
> index 48c3696..937b978 100644
> --- a/include/linux/tcp.h
> +++ b/include/linux/tcp.h
> @@ -113,6 +113,7 @@ struct tcp_request_sock {
> struct inet_request_sock req;
> const struct tcp_request_sock_ops *af_specific;
> bool tfo_listener;
> + u32 txhash;
> u32 rcv_isn;
> u32 snt_isn;
> u32 snt_synack; /* synack sent time */
> diff --git a/include/net/sock.h b/include/net/sock.h
> index 7aa7844..94dff7f 100644
> --- a/include/net/sock.h
> +++ b/include/net/sock.h
> @@ -1654,12 +1654,16 @@ static inline void sock_graft(struct sock *sk, struct
> socket *parent)
> kuid_t sock_i_uid(struct sock *sk);
> unsigned long sock_i_ino(struct sock *sk);
>
> -static inline void sk_set_txhash(struct sock *sk)
> +static inline u32 net_tx_rndhash(void)
> {
> - sk->sk_txhash = prandom_u32();
> + u32 v = prandom_u32();
> +
> + return v ?: 1;
> +}
>
> - if (unlikely(!sk->sk_txhash))
> - sk->sk_txhash = 1;
> +static inline void sk_set_txhash(struct sock *sk)
> +{
> + sk->sk_txhash = net_tx_rndhash();
> }
>
> static inline void sk_rethink_txhash(struct sock *sk)
> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> index a8f515b..a62e9c7 100644
> --- a/net/ipv4/tcp_input.c
> +++ b/net/ipv4/tcp_input.c
> @@ -6228,6 +6228,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
> }
>
> tcp_rsk(req)->snt_isn = isn;
> + tcp_rsk(req)->txhash = net_tx_rndhash();
> tcp_openreq_init_rwin(req, sk, dst);
> fastopen = !want_cookie &&
> tcp_try_fastopen(sk, skb, req, &foc, dst);
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index 93898e0..d671d74 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -1276,8 +1276,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk,
> struct sk_buff *skb,
> newinet->mc_index = inet_iif(skb);
> newinet->mc_ttl = ip_hdr(skb)->ttl;
> newinet->rcv_tos = ip_hdr(skb)->tos;
> + newsk->sk_txhash = tcp_rsk(req)->txhash;
> inet_csk(newsk)->icsk_ext_hdr_len = 0;
> - sk_set_txhash(newsk);
> if (inet_opt)
> inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
> newinet->inet_id = newtp->write_seq ^ jiffies;
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index f9a8a12..d0ad355 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -2987,6 +2987,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct
> dst_entry *dst,
> rcu_read_lock();
> md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
> #endif
> + skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
> tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
> foc) + sizeof(*th);
>
> @@ -3505,6 +3506,7 @@ int tcp_rtx_synack(struct sock *sk, struct request_sock
> *req)
> struct flowi fl;
> int res;
>
> + tcp_rsk(req)->txhash = net_tx_rndhash();
> res = af_ops->send_synack(sk, NULL, &fl, req, 0, NULL);
> if (!res) {
> TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> index 97d9314..f9c0e26 100644
> --- a/net/ipv6/tcp_ipv6.c
> +++ b/net/ipv6/tcp_ipv6.c
> @@ -1090,7 +1090,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock
> *sk, struct sk_buff *skb,
> newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
> newsk->sk_bound_dev_if = ireq->ir_iif;
>
> - sk_set_txhash(newsk);
> + newsk->sk_txhash = tcp_rsk(req)->txhash;
>
> /* Now IPv6 options...
>
>
>
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
