From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752259AbdGRUHr (ORCPT ); Tue, 18 Jul 2017 16:07:47 -0400 Received: from mx1.redhat.com ([209.132.183.28]:54910 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751513AbdGRUHo (ORCPT ); Tue, 18 Jul 2017 16:07:44 -0400 DMARC-Filter: OpenDMARC Filter v1.3.2 mx1.redhat.com 009BEC0587C6 Authentication-Results: ext-mx08.extmail.prod.ext.phx2.redhat.com; dmarc=none (p=none dis=none) header.from=redhat.com Authentication-Results: ext-mx08.extmail.prod.ext.phx2.redhat.com; spf=pass smtp.mailfrom=mst@redhat.com DKIM-Filter: OpenDKIM Filter v2.11.0 mx1.redhat.com 009BEC0587C6 Date: Tue, 18 Jul 2017 23:07:42 +0300 From: "Michael S. Tsirkin" To: Jason Wang Cc: virtualization@lists.linux-foundation.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org Subject: Re: [PATCH net-next 5/5] virtio-net: switch off offloads on demand if possible on XDP set Message-ID: <20170718225011-mutt-send-email-mst@kernel.org> References: <1500295441-19339-1-git-send-email-jasowang@redhat.com> <1500295441-19339-6-git-send-email-jasowang@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1500295441-19339-6-git-send-email-jasowang@redhat.com> X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.32]); Tue, 18 Jul 2017 20:07:44 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Jul 17, 2017 at 08:44:01PM +0800, Jason Wang wrote: > Current XDP implementation want guest offloads feature to be disabled s/want/wants/ > on qemu cli. on the device. > This is inconvenient and means guest can't benefit from > offloads if XDP is not used. This patch tries to address this > limitation by disable disabling > the offloads on demand through control guest > offloads. Guest offloads will be disabled and enabled on demand on XDP > set. > > Signed-off-by: Jason Wang In fact, since we no longer reset when XDP is set, here device might have offloads enabled, buffers are used but not consumed, then XDP is set. This can result in - packet scattered across multiple buffers (handled correctly but need to update the comment) - packet may have VIRTIO_NET_HDR_F_NEEDS_CSUM, in that case the spec says "The checksum on the packet is incomplete". (probably needs to be handled by calculating the checksum). Ideas for follow-up patches: - skip looking at packet data completely won't work if you play with checksums dynamically but can be done if disabled on device - allow ethtools to tweak offloads from userspace as well > --- > drivers/net/virtio_net.c | 70 ++++++++++++++++++++++++++++++++++++++++++++---- > 1 file changed, 65 insertions(+), 5 deletions(-) > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c > index e732bd6..d970c2d 100644 > --- a/drivers/net/virtio_net.c > +++ b/drivers/net/virtio_net.c > @@ -57,6 +57,11 @@ DECLARE_EWMA(pkt_len, 0, 64) > > #define VIRTNET_DRIVER_VERSION "1.0.0" > > +const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO4, > + VIRTIO_NET_F_GUEST_TSO6, > + VIRTIO_NET_F_GUEST_ECN, > + VIRTIO_NET_F_GUEST_UFO }; > + > struct virtnet_stats { > struct u64_stats_sync tx_syncp; > struct u64_stats_sync rx_syncp; > @@ -164,10 +169,13 @@ struct virtnet_info { > u8 ctrl_promisc; > u8 ctrl_allmulti; > u16 ctrl_vid; > + u64 ctrl_offloads; > > /* Ethtool settings */ > u8 duplex; > u32 speed; > + > + unsigned long guest_offloads; > }; > > struct padded_vnet_hdr { > @@ -1889,6 +1897,47 @@ static int virtnet_restore_up(struct virtio_device *vdev) > return err; > } > > +static int virtnet_set_guest_offloads(struct virtnet_info *vi, u64 offloads) > +{ > + struct scatterlist sg; > + vi->ctrl_offloads = cpu_to_virtio64(vi->vdev, offloads); > + > + sg_init_one(&sg, &vi->ctrl_offloads, sizeof(vi->ctrl_offloads)); > + > + if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS, > + VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) { > + dev_warn(&vi->dev->dev, "Fail to set guest offload. \n"); > + return -EINVAL; > + } > + > + return 0; > +} > + > +static int virtnet_clear_guest_offloads(struct virtnet_info *vi) > +{ > + u64 offloads = 0; > + > + if (!vi->guest_offloads) > + return 0; > + > + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM)) > + offloads = 1ULL << VIRTIO_NET_F_GUEST_CSUM; > + > + return virtnet_set_guest_offloads(vi, offloads); > +} > + > +static int virtnet_restore_guest_offloads(struct virtnet_info *vi) > +{ > + u64 offloads = vi->guest_offloads; > + > + if (!vi->guest_offloads) > + return 0; > + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM)) > + offloads |= 1ULL << VIRTIO_NET_F_GUEST_CSUM; > + > + return virtnet_set_guest_offloads(vi, offloads); > +} > + > static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, > struct netlink_ext_ack *extack) > { > @@ -1898,10 +1947,11 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, > u16 xdp_qp = 0, curr_qp; > int i, err; > > - if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) || > - virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) || > - virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) || > - virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO)) { > + if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS) > + && (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) || > + virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) || > + virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) || > + virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO))) { > NL_SET_ERR_MSG_MOD(extack, "Can't set XDP while host is implementing LRO, disable LRO first"); > return -EOPNOTSUPP; > } > @@ -1950,6 +2000,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, > for (i = 0; i < vi->max_queue_pairs; i++) { > old_prog = rtnl_dereference(vi->rq[i].xdp_prog); > rcu_assign_pointer(vi->rq[i].xdp_prog, prog); > + if (i == 0) { > + if (!old_prog) > + virtnet_clear_guest_offloads(vi); > + if (!prog) > + virtnet_restore_guest_offloads(vi); > + } > if (old_prog) > bpf_prog_put(old_prog); > napi_enable(&vi->rq[i].napi); > @@ -2583,6 +2639,10 @@ static int virtnet_probe(struct virtio_device *vdev) > netif_carrier_on(dev); > } > > + for (i = 0; i < ARRAY_SIZE(guest_offloads); i++) > + if (virtio_has_feature(vi->vdev, guest_offloads[i])) > + set_bit(guest_offloads[i], &vi->guest_offloads); > + > pr_debug("virtnet: registered device %s with %d RX and TX vq's\n", > dev->name, max_queue_pairs); > > @@ -2679,7 +2739,7 @@ static struct virtio_device_id id_table[] = { > VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, \ > VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \ > VIRTIO_NET_F_CTRL_MAC_ADDR, \ > - VIRTIO_NET_F_MTU > + VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS > > static unsigned int features[] = { > VIRTNET_FEATURES, > -- > 2.7.4