From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jesper Dangaard Brouer Subject: Re: [bpf-next V1 PATCH 2/8] i40e: implement flush flag for ndo_xdp_xmit Date: Thu, 31 May 2018 10:47:39 +0200 Message-ID: <20180531104739.3c3f6e26@redhat.com> References: <152770312703.20510.5854417568847239931.stgit@firesoul> <152770324304.20510.3553783983496502887.stgit@firesoul> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Networking , Daniel Borkmann , Alexei Starovoitov , John Fastabend , makita.toshiaki@lab.ntt.co.jp, brouer@redhat.com To: Song Liu Return-path: Received: from mx3-rdu2.redhat.com ([66.187.233.73]:52072 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1754040AbeEaIrp (ORCPT ); Thu, 31 May 2018 04:47:45 -0400 In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: On Wed, 30 May 2018 14:58:16 -0700 Song Liu wrote: > > @@ -3699,6 +3699,9 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, > > } > > } > > > > + if (unlikely(flags & XDP_XMIT_FLUSH)) > > + i40e_xdp_ring_update_tail(vsi->xdp_rings[queue_index]); > > + > > return n - drops; > > Do we still flush when drops > 0? Yes, just as before. Even if all frames are dropped, then it's allowed to update the tail. -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat LinkedIn: http://www.linkedin.com/in/brouer