From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH net] tcp: minimize false-positives on TCP/GRO check Date: Mon, 03 Apr 2017 18:44:56 -0700 (PDT) Message-ID: <20170403.184456.724166144761742945.davem@davemloft.net> References: <47c94077ffa8988118a19514389b42fccdc2f6ef.1491054871.git.marcelo.leitner@gmail.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, eric.dumazet@gmail.com, jmaxwell37@gmail.com, markus@trippelsdorf.de To: marcelo.leitner@gmail.com Return-path: Received: from shards.monkeyblade.net ([184.105.139.130]:53036 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751536AbdDDBpA (ORCPT ); Mon, 3 Apr 2017 21:45:00 -0400 In-Reply-To: <47c94077ffa8988118a19514389b42fccdc2f6ef.1491054871.git.marcelo.leitner@gmail.com> Sender: netdev-owner@vger.kernel.org List-ID: From: Marcelo Ricardo Leitner Date: Sat, 1 Apr 2017 11:00:21 -0300 > Markus Trippelsdorf reported that after commit dcb17d22e1c2 ("tcp: warn > on bogus MSS and try to amend it") the kernel started logging the > warning for a NIC driver that doesn't even support GRO. > > It was diagnosed that it was possibly caused on connections that were > using TCP Timestamps but some packets lacked the Timestamps option. As > we reduce rcv_mss when timestamps are used, the lack of them would cause > the packets to be bigger than expected, although this is a valid case. > > As this warning is more as a hint, getting a clean-cut on the > threshold is probably not worth the execution time spent on it. This > patch thus alleviates the false-positives with 2 quick checks: by > accounting for the entire TCP option space and also checking against the > interface MTU if it's available. > > These changes, specially the MTU one, might mask some real positives, > though if they are really happening, it's possible that sooner or later > it will be triggered anyway. > > Reported-by: Markus Trippelsdorf > Cc: Eric Dumazet > Signed-off-by: Marcelo Ricardo Leitner Applied, thanks Marcelo.