From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: Re: Re: Re: Re: [bisected regression] e1000e: "Detected Hardware Unit Hang" Date: Thu, 15 Jan 2015 10:24:49 -0800 Message-ID: <1421346289.11734.82.camel@edumazet-glaptop2.roam.corp.google.com> References: <1719052.SGOfRAJhfQ@storm> <1837410.pEGIH05mML@storm> <1421342437.11734.79.camel@edumazet-glaptop2.roam.corp.google.com> <1951915.1kCMSXLj6g@storm> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Cc: 'Linux Netdev List' , Eric Dumazet , Jeff Kirsher , e1000-devel To: Thomas Jarosch Return-path: Received: from mail-ig0-f169.google.com ([209.85.213.169]:60055 "EHLO mail-ig0-f169.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751448AbbAOSYz (ORCPT ); Thu, 15 Jan 2015 13:24:55 -0500 Received: by mail-ig0-f169.google.com with SMTP id z20so4530818igj.0 for ; Thu, 15 Jan 2015 10:24:54 -0800 (PST) In-Reply-To: <1951915.1kCMSXLj6g@storm> Sender: netdev-owner@vger.kernel.org List-ID: On Thu, 2015-01-15 at 18:37 +0100, Thomas Jarosch wrote: > On Thursday, 15. January 2015 09:20:37 Eric Dumazet wrote: > > > for the sake of completeness: > > > 1: hang > > > > This is weird : This should have same effect then GRO off (at most one > > segment per packet) > > I thought so, too. OTOH the code path was changed from > "goto merge" to "return -E2BIG". I didn't look at the code > what happens at the "merge" label. If you leave the "goto merge", then GRO still builds big GRO packets, using a linked list of packets. Then because drivers do not generally support NETIF_F_FRAGLIST, core networking code linearizes such GRO packets before reaching ndo_start_xmit() Check 8a29111c7ca68d928dfab58636f3f6acf0ac04f7 "net: gro: allow to build full sized skb" for details about this.