From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id A4FCEC433F5 for ; Thu, 20 Jan 2022 12:05:01 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232012AbiATMFB (ORCPT ); Thu, 20 Jan 2022 07:05:01 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:55326 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232001AbiATMFA (ORCPT ); Thu, 20 Jan 2022 07:05:00 -0500 Received: from Chamillionaire.breakpoint.cc (Chamillionaire.breakpoint.cc [IPv6:2a0a:51c0:0:12e:520::1]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 637E1C061574 for ; Thu, 20 Jan 2022 04:05:00 -0800 (PST) Received: from fw by Chamillionaire.breakpoint.cc with local (Exim 4.92) (envelope-from ) id 1nAWBW-0002jQ-7j; Thu, 20 Jan 2022 13:04:58 +0100 Date: Thu, 20 Jan 2022 13:04:58 +0100 From: Florian Westphal To: Pablo Neira Ayuso , Florian Westphal , Netfilter Development Subject: Re: [PATCH libnetfilter_queue v3 1-5/5] src: Speed-up Message-ID: <20220120120458.GF31905@breakpoint.cc> References: <20220109031653.23835-1-duncan_roe@optusnet.com.au> <20220109031653.23835-6-duncan_roe@optusnet.com.au> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.10.1 (2018-07-13) Precedence: bulk List-ID: X-Mailing-List: netfilter-devel@vger.kernel.org Duncan Roe wrote: > On Tue, Jan 18, 2022 at 02:11:43AM +0100, Pablo Neira Ayuso wrote: > > > > This patch have a number of showstoppers such as exposing structure > > layout on the header files. > > > That's only in patch 5. You could apply 1-4. There are actually no other > showstoppers, right? Regarding patch 5, I think its ok except the pkt_buff layout freeze. >From a quick glance, there is no assumption that the data area resides after the pktbuff head, so it should be possible to keep pkt_buff private, allocate an empty packet and then associate a new buffer with it. I agree the memcpy needs to go, nfqueue uses should use F_GSO feature flag and memcpy'ing 60k big packets isn't ideal.