From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.linuxfoundation.org ([140.211.169.12]:57292 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S966379AbcIVRp3 (ORCPT ); Thu, 22 Sep 2016 13:45:29 -0400 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Artem Germanov , Dmitry Adamushko , "David S. Miller" Subject: [PATCH 4.7 035/184] tcp: cwnd does not increase in TCP YeAH Date: Thu, 22 Sep 2016 19:39:29 +0200 Message-Id: <20160922174050.218977274@linuxfoundation.org> In-Reply-To: <20160922174048.653794923@linuxfoundation.org> References: <20160922174048.653794923@linuxfoundation.org> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: stable-owner@vger.kernel.org List-ID: 4.7-stable review patch. If anyone has any objections, please let me know. ------------------ From: Artem Germanov [ Upstream commit db7196a0d0984b933ccf2cd6a60e26abf466e8a3 ] Commit 76174004a0f19785a328f40388e87e982bbf69b9 (tcp: do not slow start when cwnd equals ssthresh ) introduced regression in TCP YeAH. Using 100ms delay 1% loss virtual ethernet link kernel 4.2 shows bandwidth ~500KB/s for single TCP connection and kernel 4.3 and above (including 4.8-rc4) shows bandwidth ~100KB/s. That is caused by stalled cwnd when cwnd equals ssthresh. This patch fixes it by proper increasing cwnd in this case. Signed-off-by: Artem Germanov Acked-by: Dmitry Adamushko Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_yeah.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -76,7 +76,7 @@ static void tcp_yeah_cong_avoid(struct s if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else if (!yeah->doing_reno_now) {