From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH net-next] tcp: gso: fix truesize tracking Date: Tue, 29 Oct 2013 00:05:36 -0400 (EDT) Message-ID: <20131029.000536.2072554973179658458.davem@davemloft.net> References: <1382743502.4032.6.camel@edumazet-glaptop.roam.corp.google.com> <1382747177.4032.21.camel@edumazet-glaptop.roam.corp.google.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: ast@plumgrid.com, edumazet@google.com, stephen@networkplumber.org, netdev@vger.kernel.org To: eric.dumazet@gmail.com Return-path: Received: from shards.monkeyblade.net ([149.20.54.216]:40336 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750719Ab3J2EFh (ORCPT ); Tue, 29 Oct 2013 00:05:37 -0400 In-Reply-To: <1382747177.4032.21.camel@edumazet-glaptop.roam.corp.google.com> Sender: netdev-owner@vger.kernel.org List-ID: From: Eric Dumazet Date: Fri, 25 Oct 2013 17:26:17 -0700 > From: Eric Dumazet > > commit 6ff50cd55545 ("tcp: gso: do not generate out of order packets") > had an heuristic that can trigger a warning in skb_try_coalesce(), > because skb->truesize of the gso segments were exactly set to mss. > > This breaks the requirement that > > skb->truesize >= skb->len + truesizeof(struct sk_buff); > > It can trivially be reproduced by : > > ifconfig lo mtu 1500 > ethtool -K lo tso off > netperf > > As the skbs are looped into the TCP networking stack, skb_try_coalesce() > warns us of these skb under-estimating their truesize. > > Signed-off-by: Eric Dumazet > Reported-by: Alexei Starovoitov I decided to apply this to 'net' and queue it up for -stable, thanks Eric!