From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jesper Dangaard Brouer Subject: Re: [bpf-next V2 PATCH 3/8] ixgbe: implement flush flag for ndo_xdp_xmit Date: Mon, 4 Jun 2018 15:53:24 +0200 Message-ID: <20180604155324.45e10eb7@redhat.com> References: <152775714013.24817.5067576840614810786.stgit@firesoul> <152775719796.24817.11035788244128769860.stgit@firesoul> <156d6d45-8557-0303-edeb-10d04c2be474@iogearbox.net> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, Daniel Borkmann , Alexei Starovoitov , liu.song.a23@gmail.com, songliubraving@fb.com, John Fastabend , brouer@redhat.com To: Daniel Borkmann Return-path: Received: from mx3-rdu2.redhat.com ([66.187.233.73]:48442 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1753063AbeFDNxb (ORCPT ); Mon, 4 Jun 2018 09:53:31 -0400 In-Reply-To: <156d6d45-8557-0303-edeb-10d04c2be474@iogearbox.net> Sender: netdev-owner@vger.kernel.org List-ID: On Mon, 4 Jun 2018 15:19:05 +0200 Daniel Borkmann wrote: > > +static void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring) > > +{ > > + /* Force memory writes to complete before letting h/w know there > > + * are new descriptors to fetch. > > + */ > > + wmb(); > > + writel(ring->next_to_use, ring->tail); > > +} > > Did you double check that this doesn't become a function call? Should this > get an __always_inline attribute? I did check this doesn't become a function call. The same kind of code happens other places in the driver, but I choose not to generalize this, exactly to avoid this becoming a function call ;-) -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat LinkedIn: http://www.linkedin.com/in/brouer