From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756792Ab3CRVNM (ORCPT ); Mon, 18 Mar 2013 17:13:12 -0400 Received: from mail.linuxfoundation.org ([140.211.169.12]:46154 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932488Ab3CRVK2 (ORCPT ); Mon, 18 Mar 2013 17:10:28 -0400 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Neal Cardwell , Eric Dumazet , "David S. Miller" Subject: [ 34/40] tcp: fix double-counted receiver RTT when leaving receiver fast path Date: Mon, 18 Mar 2013 14:11:12 -0700 Message-Id: <20130318211018.715345150@linuxfoundation.org> X-Mailer: git-send-email 1.8.1.2.434.g9a6c84e.dirty In-Reply-To: <20130318211016.254453918@linuxfoundation.org> References: <20130318211016.254453918@linuxfoundation.org> User-Agent: quilt/0.60-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 3.0-stable review patch. If anyone has any objections, please let me know. ------------------ From: Neal Cardwell [ 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: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5419,6 +5419,9 @@ int tcp_rcv_established(struct sock *sk, 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: @@ -5430,9 +5433,6 @@ int tcp_rcv_established(struct sock *sk, 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 */