From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [bisected] xfrm: TCP connection initiating PMTU discovery stalls on v3. Date: Fri, 12 Dec 2014 09:27:05 -0800 Message-ID: <1418405225.13491.19.camel@edumazet-glaptop2.roam.corp.google.com> References: <1709726.jUgUSQI9sl@pikkukde.a.i2n> <6700748.kZ07xrNvHX@h2o.as.studentenwerk.mhn.de> <1418238603.27198.37.camel@edumazet-glaptop2.roam.corp.google.com> <2630078.LdJXSsPB40@h2o.as.studentenwerk.mhn.de> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Cc: Thomas Jarosch , netdev@vger.kernel.org, Eric Dumazet , Herbert Xu , Steffen Klassert To: Wolfgang Walter Return-path: Received: from mail-ie0-f182.google.com ([209.85.223.182]:59394 "EHLO mail-ie0-f182.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1030876AbaLLR1I (ORCPT ); Fri, 12 Dec 2014 12:27:08 -0500 Received: by mail-ie0-f182.google.com with SMTP id x19so7402840ier.13 for ; Fri, 12 Dec 2014 09:27:07 -0800 (PST) In-Reply-To: <2630078.LdJXSsPB40@h2o.as.studentenwerk.mhn.de> Sender: netdev-owner@vger.kernel.org List-ID: On Fri, 2014-12-12 at 17:58 +0100, Wolfgang Walter wrote: > This fixes hangs of local tcp connections over ipsec tunnels where > pmtu is lower than the mtu of the interface. Again this is a work around, the one liner patch is not a clean patch. Something is wrong, we should fix GSO path instead. Why ? Because we can queue a GSO packet in a qdisc, then later call sk_setup_caps() (too late)