From mboxrd@z Thu Jan 1 00:00:00 1970 From: Markus Trippelsdorf Subject: Re: "TCP: eth0: Driver has suspect GRO implementation, TCP performance may be compromised." message with "ethtool -K eth0 gro off" Date: Fri, 3 Feb 2017 13:06:07 +0100 Message-ID: <20170203120607.GA289@x4> References: <20170202115240.GH17590@x4> <1486038733.13103.21.camel@edumazet-glaptop3.roam.corp.google.com> <20170202123427.GA7212@x4> <1486042270.13103.26.camel@edumazet-glaptop3.roam.corp.google.com> <1486043964.13103.33.camel@edumazet-glaptop3.roam.corp.google.com> <20170203115457.GA5296@localhost.localdomain> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Eric Dumazet , netdev@vger.kernel.org To: Marcelo Ricardo Leitner Return-path: Received: from ud10.udmedia.de ([194.117.254.50]:51632 "EHLO mail.ud10.udmedia.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751944AbdBCMGQ (ORCPT ); Fri, 3 Feb 2017 07:06:16 -0500 Content-Disposition: inline In-Reply-To: <20170203115457.GA5296@localhost.localdomain> Sender: netdev-owner@vger.kernel.org List-ID: On 2017.02.03 at 09:54 -0200, Marcelo Ricardo Leitner wrote: > On Thu, Feb 02, 2017 at 05:59:24AM -0800, Eric Dumazet wrote: > > On Thu, 2017-02-02 at 05:31 -0800, Eric Dumazet wrote: > > > > > Anyway, I suspect the test is simply buggy ;) > > > > > > diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c > > > index 41dcbd568cbe2403f2a9e659669afe462a42e228..5394a39fcce964a7fe7075b1531a8a1e05550a54 100644 > > > --- a/net/ipv4/tcp_input.c > > > +++ b/net/ipv4/tcp_input.c > > > @@ -164,7 +164,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) > > > if (len >= icsk->icsk_ack.rcv_mss) { > > > icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, > > > tcp_sk(sk)->advmss); > > > - if (unlikely(icsk->icsk_ack.rcv_mss != len)) > > > + if (unlikely(icsk->icsk_ack.rcv_mss != len && skb_is_gso(skb))) > > > tcp_gro_dev_warn(sk, skb); > > > } else { > > > /* Otherwise, we make more careful check taking into account, > > > > This wont really help. > > > > Our tcp_sk(sk)->advmss can be lower than the MSS used by the remote > > peer. > > > > ip ro add .... advmss 512 > > I don't follow. With a good driver, how can advmss be smaller than the > MSS used by the remote peer? Even with the route entry above, I get > segments just up to advmss, and no warning. > > Though yeah, interesting that this driver doesn't even support GRO. FCS > perhaps? > > Markus, do you have other interfaces in your system? Which MTU do you > use, and please try the (untested) patch below, to gather more debug > info: No, eth0 is the only interface. MTU = 1500. Sure, I will try your patch. But I don't know how to reproduce the issue, so you will have to wait until it triggers again. -- Markus