similar to: performance bug in virtio net xdp

Hi: This series tries to re-enable XDP_REDIRECT for mergeable buffer which was removed since commit 7324f5399b06 ("virtio_net: disable XDP_REDIRECT in receive_mergeable() case"). Main concerns are: - not enough tailroom was reserved which breaks cpumap - complex logic like EWMA and linearizing during XDP processing Fix those by: - reserve enough tailroom during refill - disable EWMA

Hi: This series tries to re-enable XDP_REDIRECT for mergeable buffer which was removed since commit 7324f5399b06 ("virtio_net: disable XDP_REDIRECT in receive_mergeable() case"). Main concerns are: - not enough tailroom was reserved which breaks cpumap - complex logic like EWMA and linearizing during XDP processing Fix those by: - reserve enough tailroom during refill - disable EWMA

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

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 there's no way for XDP to know the existence of the vnet header currently. So let's just not reserve space for vnet header in this case. Cc: Jesper Dangaard Brouer <brouer at redhat.com>

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 there's no way for XDP to know the existence of the vnet header currently. So let's just not reserve space for vnet header in this case. Cc: Jesper Dangaard Brouer <brouer at redhat.com>

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 by reserving enough tailroom and using fixed size of rx buffer. Signed-off-by: Jason Wang <jasowang at

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 by reserving enough tailroom and using fixed size of rx buffer. Signed-off-by: Jason Wang <jasowang at

On Wed, May 06, 2020 at 04:21:15PM +0800, Jason Wang wrote: > > On 2020/5/6 ??3:37, Michael S. Tsirkin wrote: > > 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. > > > >

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 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 Thu, 1 Mar 2018 11:19:05 +0800 Jason Wang <jasowang at redhat.com> wrote: > We used to do data copy through xdp_linearize_page() for the buffer > without sufficient headroom, it brings extra complexity without > helping for the performance. So this patch remove it and switch to use > generic XDP routine to handle this case. I don't like where this is going. I don't

On Thu, 1 Mar 2018 11:19:05 +0800 Jason Wang <jasowang at redhat.com> wrote: > We used to do data copy through xdp_linearize_page() for the buffer > without sufficient headroom, it brings extra complexity without > helping for the performance. So this patch remove it and switch to use > generic XDP routine to handle this case. I don't like where this is going. I don't

On Wed, 6 May 2020 04:08:27 -0400 "Michael S. Tsirkin" <mst at redhat.com> wrote: > So for mergeable bufs, we use ewma machinery to guess the correct buffer > size. If we don't guess correctly, XDP has to do aggressive copies. > > Problem is, xdp paths do not update the ewma at all, except > sometimes with XDP_PASS. So whatever we happen to have > before we

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

On 2020/5/6 ??3:53, Michael S. Tsirkin wrote: > On Wed, May 06, 2020 at 02:16:32PM +0800, Jason Wang 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 there's no way for XDP to know the existence of the

On 2020/5/6 ??3:53, Michael S. Tsirkin wrote: > On Wed, May 06, 2020 at 02:16:32PM +0800, Jason Wang 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 there's no way for XDP to know the existence of the

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 ("virtio_net: disable >> XDP_REDIRECT in receive_mergeable() case"). Main concerns are: >> >>