similar to: Re: Linux router performance (fwd)

On Thu, 1 Mar 2018 21:15:36 +0800 Jason Wang <jasowang at redhat.com> wrote: > On 2018?03?01? 18:35, Jesper Dangaard Brouer wrote: > > On Thu, 1 Mar 2018 17:23:37 +0800 > > Jason Wang <jasowang at redhat.com> wrote: > > > >> On 2018?03?01? 17:10, Jesper Dangaard Brouer wrote: > >>> On Thu, 1 Mar 2018 11:19:03 +0800 > >>> Jason

We don't disable VIRTIO_NET_F_GUEST_CSUM if XDP was set. This means we can receive partial csumed packets with metadata kept in the vnet_hdr. This may have several side effects: - It could be overridden by header adjustment, thus is might be not correct after XDP processing. - There's no way to pass such metadata information through XDP_REDIRECT to another driver. - XDP does not

We don't disable VIRTIO_NET_F_GUEST_CSUM if XDP was set. This means we can receive partial csumed packets with metadata kept in the vnet_hdr. This may have several side effects: - It could be overridden by header adjustment, thus is might be not correct after XDP processing. - There's no way to pass such metadata information through XDP_REDIRECT to another driver. - XDP does not

On Fri, 2 Mar 2018 17:29:14 +0800 Jason Wang <jasowang at redhat.com> wrote: > XDP_REDIRECT support for mergeable buffer was removed since commit > 7324f5399b06 ("virtio_net: disable XDP_REDIRECT in receive_mergeable() > case"). This is because we don't reserve enough tailroom for struct > skb_shared_info which breaks XDP assumption. So this patch fixes this >

We don't support partial csumed packet since its metadata will be lost or incorrect during XDP processing. So fail the XDP set if guest_csum feature is negotiated. Fixes: f600b6905015 ("virtio_net: Add XDP support") Reported-by: Jesper Dangaard Brouer <brouer at redhat.com> Cc: Jesper Dangaard Brouer <brouer at redhat.com> Cc: Pavel Popa <pashinho1990 at gmail.com>

From: Jason Wang <jasowang at redhat.com> Date: Thu, 22 Nov 2018 14:36:30 +0800 > We don't disable VIRTIO_NET_F_GUEST_CSUM if XDP was set. This means we > can receive partial csumed packets with metadata kept in the > vnet_hdr. This may have several side effects: > > - It could be overridden by header adjustment, thus is might be not > correct after XDP processing.

On Sat, 2 Feb 2019 14:27:26 -0700 David Ahern <dsahern at gmail.com> wrote: > On 1/31/19 1:15 PM, Jesper Dangaard Brouer wrote: > >> > >> David, Jesper, care to chime in where we ended up in that last thread > >> discussion this? > > > > IHMO packets RX and TX on a device need to be accounted, in standard > > counters, regardless of XDP.

On Wed, 6 May 2020 14:16:32 +0800 Jason Wang <jasowang at redhat.com> wrote: > We tried to reserve space for vnet header before > xdp.data_hard_start. But this is useless since the packet could be > modified by XDP which may invalidate the information stored in the > header and IMHO above statements are wrong. XDP cannot access memory before xdp.data_hard_start. Thus, it is

On Thu, 1 Mar 2018 17:23:37 +0800 Jason Wang <jasowang at redhat.com> wrote: > On 2018?03?01? 17:10, Jesper Dangaard Brouer wrote: > > On Thu, 1 Mar 2018 11:19:03 +0800 > > Jason Wang <jasowang at redhat.com> wrote: > > > >> This series tries to re-enable XDP_REDIRECT for mergeable buffer which > >> was removed since commit 7324f5399b06

On Wed, May 06, 2020 at 04:34:36PM +0800, Jason Wang wrote: > > On 2020/5/6 ??4:21, Jesper Dangaard Brouer wrote: > > On Wed, 6 May 2020 14:16:32 +0800 > > Jason Wang <jasowang at redhat.com> wrote: > > > > > We tried to reserve space for vnet header before > > > xdp.data_hard_start. But this is useless since the packet could be > > >

On Thu, 1 Mar 2018 11:19:04 +0800 Jason Wang <jasowang at redhat.com> wrote: > XDP_REDIRECT support for mergeable buffer was removed since commit > 7324f5399b06 ("virtio_net: disable XDP_REDIRECT in receive_mergeable() > case"). This is because we don't reserve enough tailroom for struct > skb_shared_info which breaks XDP assumption. Other complaints are, the >

On 2020/5/6 ??4:21, Jesper Dangaard Brouer wrote: > On Wed, 6 May 2020 14:16:32 +0800 > Jason Wang <jasowang at redhat.com> wrote: > >> We tried to reserve space for vnet header before >> xdp.data_hard_start. But this is useless since the packet could be >> modified by XDP which may invalidate the information stored in the >> header and > IMHO above

On 2020/5/6 ??4:21, Jesper Dangaard Brouer wrote: > On Wed, 6 May 2020 14:16:32 +0800 > Jason Wang <jasowang at redhat.com> wrote: > >> We tried to reserve space for vnet header before >> xdp.data_hard_start. But this is useless since the packet could be >> modified by XDP which may invalidate the information stored in the >> header and > IMHO above

On 2018?03?01? 18:35, Jesper Dangaard Brouer wrote: > On Thu, 1 Mar 2018 17:23:37 +0800 > Jason Wang <jasowang at redhat.com> wrote: > >> On 2018?03?01? 17:10, Jesper Dangaard Brouer wrote: >>> On Thu, 1 Mar 2018 11:19:03 +0800 >>> Jason Wang <jasowang at redhat.com> wrote: >>> >>>> This series tries to re-enable XDP_REDIRECT

On 2018?03?01? 18:35, Jesper Dangaard Brouer wrote: > On Thu, 1 Mar 2018 17:23:37 +0800 > Jason Wang <jasowang at redhat.com> wrote: > >> On 2018?03?01? 17:10, Jesper Dangaard Brouer wrote: >>> On Thu, 1 Mar 2018 11:19:03 +0800 >>> Jason Wang <jasowang at redhat.com> wrote: >>> >>>> This series tries to re-enable XDP_REDIRECT

The virtio_net driver doesn't dynamically change the RX-ring queue layout and backing pages, but instead reject XDP setup if all the conditions for XDP is not meet. Thus, the xdp_rxq_info also remains fairly static. This allow us to simply add the reg/unreg to net_device open/close functions. Driver hook points for xdp_rxq_info: * reg : virtnet_open * unreg: virtnet_close Cc:

David Ahern <dsahern at gmail.com> writes: > On 2/4/19 3:53 AM, Jesper Dangaard Brouer wrote: >> On Sat, 2 Feb 2019 14:27:26 -0700 >> David Ahern <dsahern at gmail.com> wrote: >> >>> On 1/31/19 1:15 PM, Jesper Dangaard Brouer wrote: >>>>> >>>>> David, Jesper, care to chime in where we ended up in that last thread

On Fri, 29 Jun 2018 23:33:58 -0700 xiangxia.m.yue at gmail.com wrote: > From: Tonghao Zhang <xiangxia.m.yue at gmail.com> > > This patch improves the guest receive and transmit performance. > On the handle_tx side, we poll the sock receive queue at the > same time. handle_rx do that in the same way. > > We set the poll-us=100us and use the iperf3 to test Where/how do

On Wed, May 06, 2020 at 02:16:33PM +0800, Jason Wang wrote: > We should not exclude headroom and tailroom when XDP is set. So this > patch fixes this by initializing the truesize from PAGE_SIZE when XDP > is set. > > Cc: Jesper Dangaard Brouer <brouer at redhat.com> > Signed-off-by: Jason Wang <jasowang at redhat.com> Seems too aggressive, we do not use up the whole

On Wed, May 06, 2020 at 02:16:33PM +0800, Jason Wang wrote: > We should not exclude headroom and tailroom when XDP is set. So this > patch fixes this by initializing the truesize from PAGE_SIZE when XDP > is set. > > Cc: Jesper Dangaard Brouer <brouer at redhat.com> > Signed-off-by: Jason Wang <jasowang at redhat.com> Seems too aggressive, we do not use up the whole