From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Nikita V. Shirokov" Subject: Re: [PATCH bpf-next v2 02/11] bpf: make generic xdp compatible w/ bpf_xdp_adjust_tail Date: Tue, 17 Apr 2018 21:48:30 -0700 Message-ID: <20180418044830.GB17737@maindev> References: <20180418042951.17183-1-tehnerd@tehnerd.com> <20180418042951.17183-3-tehnerd@tehnerd.com> <20180418144818.0bcba1f9@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Alexei Starovoitov , Daniel Borkmann , "David S. Miller " , netdev@vger.kernel.org To: Jesper Dangaard Brouer Return-path: Received: from mail-pf0-f194.google.com ([209.85.192.194]:41990 "EHLO mail-pf0-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753170AbeDRN2J (ORCPT ); Wed, 18 Apr 2018 09:28:09 -0400 Received: by mail-pf0-f194.google.com with SMTP id o16so912285pfk.9 for ; Wed, 18 Apr 2018 06:28:09 -0700 (PDT) Content-Disposition: inline In-Reply-To: <20180418144818.0bcba1f9@redhat.com> Sender: netdev-owner@vger.kernel.org List-ID: On Wed, Apr 18, 2018 at 02:48:18PM +0200, Jesper Dangaard Brouer wrote: > On Tue, 17 Apr 2018 21:29:42 -0700 > "Nikita V. Shirokov" wrote: > > > w/ bpf_xdp_adjust_tail helper xdp's data_end pointer could be changed as > > well (only "decrease" of pointer's location is going to be supported). > > changing of this pointer will change packet's size. > > for generic XDP we need to reflect this packet's length change by > > adjusting skb's tail pointer > > > > Acked-by: Alexei Starovoitov > > You are missing your own Signed-off-by: line on all of the patches. > yeah, somehow lost it between v1 and v2 :) thanks ! > BTW, thank you for working on this! It have been on my todo-list for a > while now! > > _After_ this patchset, I would like to see adding support for > "increasing" the data_end location to create a larger packet. For that > we should likely add a data_hard_end pointer. This, would also be > helpful in cpu_map_build_skb() to know the data_hard_end, to determine > the frame size (as some driver doesn't use PAGE_SIZE frames, ixgbe). > yeah, increasing the size would be nice to have, but will require more thinking / rework on drivers side (as you pointed out it's not as easy as "every driver have at least PAGE_SIZE of data available for xdp".). will add to my TODO > > -- > Best regards, > Jesper Dangaard Brouer > MSc.CS, Principal Kernel Engineer at Red Hat > LinkedIn: http://www.linkedin.com/in/brouer