From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1030904AbeCANk2 (ORCPT ); Thu, 1 Mar 2018 08:40:28 -0500 Received: from mx3-rdu2.redhat.com ([66.187.233.73]:37604 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1030701AbeCANk1 (ORCPT ); Thu, 1 Mar 2018 08:40:27 -0500 Date: Thu, 1 Mar 2018 15:40:26 +0200 From: "Michael S. Tsirkin" To: Jesper Dangaard Brouer Cc: Jason Wang , virtualization@lists.linux-foundation.org, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, john.fastabend@gmail.com, Alexei Starovoitov Subject: Re: [PATCH net-next 0/2] virtio-net: re enable XDP_REDIRECT for mergeable buffer Message-ID: <20180301153900-mutt-send-email-mst@kernel.org> References: <1519874345-10235-1-git-send-email-jasowang@redhat.com> <20180301101038.4253424d@redhat.com> <20180301113531.7b25e2df@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <20180301113531.7b25e2df@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Mar 01, 2018 at 11:35:31AM +0100, Jesper Dangaard Brouer wrote: > On Thu, 1 Mar 2018 17:23:37 +0800 > Jason Wang wrote: > > > On 2018年03月01日 17:10, Jesper Dangaard Brouer wrote: > > > On Thu, 1 Mar 2018 11:19:03 +0800 > > > Jason Wang wrote: > > > > > >> This series tries to re-enable XDP_REDIRECT for mergeable buffer which > > >> was removed since commit 7324f5399b06 ("virtio_net: disable > > >> XDP_REDIRECT in receive_mergeable() case"). Main concerns are: > > >> > > >> - not enough tailroom was reserved which breaks cpumap > > > > > To address this at a more fundamental level, I would suggest that we/you > > > instead extend XDP to know it's buffers "frame" size/end. (The > > > assumption use to be, xdp_buff->data_hard_start + PAGE_SIZE, but > > > ixgbe+virtio_net broke that assumption). > > > > > > It should actually be fairly easy to implement: > > > * Simply extend xdp_buff with a "data_hard_end" pointer. > > > > Right, and then cpumap can warn and drop packets with insufficient > > tailroom. > > > > But it should be a patch on top of this I think. > > Hmmm, not really. If we/you instead fix the issue of XDP doesn't know > the end/size of the frame, then we don't need this mixed XDP > generic/native code path mixing. > > You could re-enable native redirect, and push the responsibility to > cpumap for detecting this too-small frame "missing tailroom" (and avoid > crashing...). (If we really want to support this, cpumap could fallback > to dev_alloc_skb, and handle it gracefully). Yea, we probably should. However it's not nice that redirect is now gone in net. IMHO a smaller version of patch 1/2 (without using generic code) should go into net. tailroom tracking and fallback to dev_alloc_skb can go into net-next. > -- > Best regards, > Jesper Dangaard Brouer > MSc.CS, Principal Kernel Engineer at Red Hat > LinkedIn: http://www.linkedin.com/in/brouer