From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: GRO/GSO hiding PMTU? Date: Thu, 10 Feb 2011 23:07:12 -0800 (PST) Message-ID: <20110210.230712.183040908.davem@davemloft.net> References: <20110210235022.GA25293@gondor.apana.org.au> <20110210.222216.104050992.davem@davemloft.net> <20110211063753.GA29940@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, netfilter-devel@vger.kernel.org To: herbert@gondor.apana.org.au Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:56140 "EHLO sunset.davemloft.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753459Ab1BKHGg (ORCPT ); Fri, 11 Feb 2011 02:06:36 -0500 In-Reply-To: <20110211063753.GA29940@gondor.apana.org.au> Sender: netfilter-devel-owner@vger.kernel.org List-ID: From: Herbert Xu Date: Fri, 11 Feb 2011 17:37:53 +1100 > What I wanted to do if I ever get enough time to work on this is > to record the transport header length in a gso_hlen field so we > can fix this properly. > > We currently have a useless gso_segs field that only has one or > two users that don't even need it. We could easily get rid of it > and use that space for gso_hlen instead. > > The gso_hlen field only needs to be filled in at the few spots > that generate GSO packets, i.e., > > 1) TCP > 2) Virt backends like tun.c > 3) GRO Yep, that's good idea. And even if we needed to add one more u32 to skb_shared_info() that's still sort-of "free" because of SLAB slack space. I'll look into doing this. Thanks!