Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755110Ab3I3BvO (ORCPT ); Sun, 29 Sep 2013 21:51:14 -0400 Received: from ozlabs.org ([203.10.76.45]:44647 "EHLO ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755018Ab3I3BvM (ORCPT ); Sun, 29 Sep 2013 21:51:12 -0400 From: Rusty Russell To: Jason Wang , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org Cc: Jason Wang , "Michael S. Tsirkin" Subject: Re: [PATCH net-next] virtio-net: switch to use XPS to choose txq In-Reply-To: <1380261444-40918-1-git-send-email-jasowang@redhat.com> References: <1380261444-40918-1-git-send-email-jasowang@redhat.com> User-Agent: Notmuch/0.15.2+81~gd2c8818 (http://notmuchmail.org) Emacs/23.4.1 (i686-pc-linux-gnu) Date: Mon, 30 Sep 2013 09:05:59 +0930 Message-ID: <874n932obk.fsf@rustcorp.com.au> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2907 Lines: 93 Jason Wang writes: > We used to use a percpu structure vq_index to record the cpu to queue > mapping, this is suboptimal since it duplicates the work of XPS and > loses all other XPS functionality such as allowing use to configure > their own transmission steering strategy. > > So this patch switches to use XPS and suggest a default mapping when > the number of cpus is equal to the number of queues. With XPS support, > there's no need for keeping per-cpu vq_index and .ndo_select_queue(), > so they were removed also. > > Cc: Rusty Russell > Cc: Michael S. Tsirkin > Signed-off-by: Jason Wang > --- > drivers/net/virtio_net.c | 55 +++++++-------------------------------------- > 1 files changed, 9 insertions(+), 46 deletions(-) > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c > index defec2b..4102c1b 100644 > --- a/drivers/net/virtio_net.c > +++ b/drivers/net/virtio_net.c > @@ -127,9 +127,6 @@ struct virtnet_info { > /* Does the affinity hint is set for virtqueues? */ > bool affinity_hint_set; > > - /* Per-cpu variable to show the mapping from CPU to virtqueue */ > - int __percpu *vq_index; > - > /* CPU hot plug notifier */ > struct notifier_block nb; > }; > @@ -1063,7 +1060,6 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev, > static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu) > { > int i; > - int cpu; > > if (vi->affinity_hint_set) { > for (i = 0; i < vi->max_queue_pairs; i++) { > @@ -1073,20 +1069,11 @@ static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu) > > vi->affinity_hint_set = false; > } > - > - i = 0; > - for_each_online_cpu(cpu) { > - if (cpu == hcpu) { > - *per_cpu_ptr(vi->vq_index, cpu) = -1; > - } else { > - *per_cpu_ptr(vi->vq_index, cpu) = > - ++i % vi->curr_queue_pairs; > - } > - } > } > > static void virtnet_set_affinity(struct virtnet_info *vi) > { > + cpumask_var_t cpumask; > int i; > int cpu; > > @@ -1100,15 +1087,21 @@ static void virtnet_set_affinity(struct virtnet_info *vi) > return; > } > > + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) > + return; > + > i = 0; > for_each_online_cpu(cpu) { > virtqueue_set_affinity(vi->rq[i].vq, cpu); > virtqueue_set_affinity(vi->sq[i].vq, cpu); > - *per_cpu_ptr(vi->vq_index, cpu) = i; > + cpumask_clear(cpumask); > + cpumask_set_cpu(cpu, cpumask); > + netif_set_xps_queue(vi->dev, cpumask, i); > i++; > } > > vi->affinity_hint_set = true; > + free_cpumask_var(cpumask); > } Um, isn't this just cpumask_of(cpu)? Cheers, Rusty. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/