From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH v2] tcp: fix infinite cwnd in tcp_complete_cwr() Date: Mon, 30 Apr 2012 13:45:40 -0400 (EDT) Message-ID: <20120430.134540.610433288172120407.davem@davemloft.net> References: <1335801618-31498-1-git-send-email-ycheng@google.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: ycheng@google.com, ilpo.jarvinen@helsinki.fi, nanditad@google.com, netdev@vger.kernel.org To: ncardwell@google.com Return-path: Received: from shards.monkeyblade.net ([198.137.202.13]:41035 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752968Ab2D3Rpx convert rfc822-to-8bit (ORCPT ); Mon, 30 Apr 2012 13:45:53 -0400 In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: =46rom: Neal Cardwell Date: Mon, 30 Apr 2012 12:25:56 -0400 > On Mon, Apr 30, 2012 at 12:00 PM, Yuchung Cheng w= rote: >> When the cwnd reduction is done, ssthresh may be infinite >> if TCP enters CWR via ECN or F-RTO. If cwnd is not undone, i.e., >> undo_marker is set, tcp_complete_cwr() falsely set cwnd to the >> infinite ssthresh value. The correct operation is to keep cwnd >> intact because it has been updated in ECN or F-RTO. >> >> Signed-off-by: Yuchung Cheng >> --- >> ChangeLog since v1: >> =A0- Add snd_cwnd_stamp timestamping in CWR mode >> >> =A0net/ipv4/tcp_input.c | =A0 =A09 ++++++--- >> =A01 files changed, 6 insertions(+), 3 deletions(-) >=20 > Acked-by: Neal Cardwell Applied and queued up for -stable, thanks.