diff options
| author | Eric Dumazet <edumazet@google.com> | 2015-10-16 13:00:01 -0700 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2015-10-18 22:26:02 -0700 |
| commit | dc6ef6be52154490c5c03f742e28bc781cc751b2 (patch) | |
| tree | 8e297dd00c9cef73f67424b72a5669d6a97d13f7 /net/ipv4/tcp_input.c | |
| parent | 951b5d959f1da4bae8910085a2d8d6a3d374c72d (diff) | |
| download | op-kernel-dev-dc6ef6be52154490c5c03f742e28bc781cc751b2.zip op-kernel-dev-dc6ef6be52154490c5c03f742e28bc781cc751b2.tar.gz | |
tcp: do not set queue_mapping on SYNACK
At the time of commit fff326990789 ("tcp: reflect SYN queue_mapping into
SYNACK packets") we had little ways to cope with SYN floods.
We no longer need to reflect incoming skb queue mappings, and instead
can pick a TX queue based on cpu cooking the SYNACK, with normal XPS
affinities.
Note that all SYNACK retransmits were picking TX queue 0, this no longer
is a win given that SYNACK rtx are now distributed on all cpus.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp_input.c')
| -rw-r--r-- | net/ipv4/tcp_input.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3b35c3f..944eaca 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6236,7 +6236,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, } if (fastopen_sk) { af_ops->send_synack(fastopen_sk, dst, &fl, req, - skb_get_queue_mapping(skb), &foc, false); + &foc, false); /* Add the child socket directly into the accept queue */ inet_csk_reqsk_queue_add(sk, req, fastopen_sk); sk->sk_data_ready(sk); @@ -6247,7 +6247,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (!want_cookie) inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); af_ops->send_synack(sk, dst, &fl, req, - skb_get_queue_mapping(skb), &foc, !want_cookie); + &foc, !want_cookie); if (want_cookie) goto drop_and_free; } |
