From mboxrd@z Thu Jan 1 00:00:00 1970 From: William Allen Simpson Subject: Re: [PATCH v4] tcp: harmonize tcp_vx_rcv header length assumptions Date: Thu, 14 Jan 2010 10:02:03 -0500 Message-ID: <4B4F31EB.1000004@gmail.com> References: <4B49D001.4000302@gmail.com> <4B4DA4F4.6060007@gmail.com> <20100113115617.GA24818@basil.fritz.box> <4B4DE887.6030602@gmail.com> <20100113155323.GB24818@basil.fritz.box> <4B4E23E0.4000007@gmail.com> <4B4E378A.7040506@gmail.com> <1263430990.1966.12.camel@Joe-Laptop.home> <4B4ED830.4040407@trash.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15; format=flowed Content-Transfer-Encoding: 7bit Cc: Joe Perches , Andi Kleen , Linux Kernel Developers , Linux Kernel Network Developers , =?ISO-8859-15?Q?Ilpo_J=E4rvinen?= , Eric Dumazet To: Patrick McHardy Return-path: Received: from mail-iw0-f194.google.com ([209.85.223.194]:56322 "EHLO mail-iw0-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756837Ab0ANPCG (ORCPT ); Thu, 14 Jan 2010 10:02:06 -0500 In-Reply-To: <4B4ED830.4040407@trash.net> Sender: netdev-owner@vger.kernel.org List-ID: Patrick McHardy wrote: > In IPv6 it is released in ip6_input.c before the packet is handed to > the protocol handler. > Thanks, I made a note of it. Thanks to Andi, I've been using his suggestion to compare the IPv4 and IPv6 generated code. Another minor difference between them was IPv4 stored *iph. So, I added *ip6h, and discovered that it made the code longer. Later inline function invocations had also calculated it, so adding it merely calculated it earlier and stored it. The code thrashes registers making room for the additional variable. I'm guessing that the IPv6 folks had already looked at the issue.... Good work! So, I tried removing *iph, and that shrunk the IPv4 code some, too. Thanks to everybody for their comments and review.