tcp: provide skb->hash to synack packets
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.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Acked-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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 @@
}
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 @@
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 @@
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 @@
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 @@
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...
