From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752808AbaEWPbg (ORCPT ); Fri, 23 May 2014 11:31:36 -0400 Received: from mx0.aculab.com ([213.249.233.131]:59422 "HELO mx0.aculab.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751387AbaEWPbV (ORCPT ); Fri, 23 May 2014 11:31:21 -0400 From: David Laight To: "'Eric Dumazet'" , Jim Baxter CC: =?utf-8?B?J0Jqw7hybiBNb3JrJw==?= , "linux-usb@vger.kernel.org" , "linux-kernel@vger.kernel.org" , "netdev@vger.kernel.org" , "David S. Miller" , "kamal@canonical.com" , "edumazet@google.com" , "mszeredi@suse.cz" , "fw@strlen.de" Subject: RE: skbuff truesize incorrect. Thread-Topic: skbuff truesize incorrect. Thread-Index: AQHPdmwmL2lnKeimqUeV55a8ET8tq5tN+mog///3/4CAACsHgIAAJ6iA Date: Fri, 23 May 2014 15:30:37 +0000 Message-ID: <063D6719AE5E284EB5DD2968C1650D6D1724CACF@AcuExch.aculab.com> References: <537E4AFD.20304@mentor.com> <1400792295.5367.174.camel@edumazet-glaptop2.roam.corp.google.com> <063D6719AE5E284EB5DD2968C1650D6D1724C490@AcuExch.aculab.com> <87r43k4yhe.fsf@nemi.mork.no> <063D6719AE5E284EB5DD2968C1650D6D1724C7A1@AcuExch.aculab.com> <537F2D53.5020408@mentor.com> <1400852843.5367.191.camel@edumazet-glaptop2.roam.corp.google.com> In-Reply-To: <1400852843.5367.191.camel@edumazet-glaptop2.roam.corp.google.com> Accept-Language: en-GB, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.202.99.200] Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Transfer-Encoding: 8bit X-MIME-Autoconverted: from base64 to 8bit by mail.home.local id s4NFVqAv004052 From: Eric Dumazet ... > TCP stack uses fast clones, and current stack gives them a truesize of > 2048 + sizeof(sk_buff), while it really should be 2048 + > 2*sizeof(sk_buff) > > Luckily, GSO/TSO tends to reduce the error, as skbs overhead is lower. Doesn't that affect the tx side - where the truesize doesn't matter as much? David {.n++%ݶw{.n+{G{ayʇڙ,jfhz_(階ݢj"mG?&~iOzv^m ?I