From: Neal Cardwell Date: Mon, 4 Mar 2013 06:23:05 +0000 (+0000) Subject: tcp: fix double-counted receiver RTT when leaving receiver fast path X-Git-Tag: v3.2.42~84 X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=fc1b43e0fb47bdf0bfe9549e26b433bd4b340fbd;p=thirdparty%2Fkernel%2Fstable.git tcp: fix double-counted receiver RTT when leaving receiver fast path [ Upstream commit aab2b4bf224ef8358d262f95b568b8ad0cecf0a0 ] We should not update ts_recent and call tcp_rcv_rtt_measure_ts() both before and after going to step5. That wastes CPU and double-counts the receiver-side RTT sample. Signed-off-by: Neal Cardwell Acked-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Ben Hutchings --- diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e865ed17ba3a3..1b1f7af17d6a6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5494,6 +5494,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, if (tcp_checksum_complete_user(sk, skb)) goto csum_error; + if ((int)skb->truesize > sk->sk_forward_alloc) + goto step5; + /* Predicted packet is in window by definition. * seq == rcv_nxt and rcv_wup <= rcv_nxt. * Hence, check seq<=rcv_wup reduces to: @@ -5505,9 +5508,6 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_rcv_rtt_measure_ts(sk, skb); - if ((int)skb->truesize > sk->sk_forward_alloc) - goto step5; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */