From: "Michael S. Tsirkin" <mst@redhat•com>
To: John Fastabend <john.fastabend@gmail•com>
Cc: daniel@iogearbox•net, shm@cumulusnetworks•com,
davem@davemloft•net, tgraf@suug•ch, alexei.starovoitov@gmail•com,
john.r.fastabend@intel•com, netdev@vger•kernel.org,
brouer@redhat•com
Subject: Re: [net-next PATCH v5 1/6] net: virtio dynamically disable/enable LRO
Date: Thu, 15 Dec 2016 18:35:14 +0200 [thread overview]
Message-ID: <20161215183341-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <58517AE7.5090104@gmail.com>
On Wed, Dec 14, 2016 at 09:01:27AM -0800, John Fastabend wrote:
> On 16-12-14 05:31 AM, Michael S. Tsirkin wrote:
> > On Thu, Dec 08, 2016 at 04:04:58PM -0800, John Fastabend wrote:
> >> On 16-12-08 01:36 PM, Michael S. Tsirkin wrote:
> >>> On Wed, Dec 07, 2016 at 12:11:11PM -0800, John Fastabend wrote:
> >>>> This adds support for dynamically setting the LRO feature flag. The
> >>>> message to control guest features in the backend uses the
> >>>> CTRL_GUEST_OFFLOADS msg type.
> >>>>
> >>>> Signed-off-by: John Fastabend <john.r.fastabend@intel•com>
> >>>> ---
>
> [...]
>
> >>>>
> >>>> static void virtnet_config_changed_work(struct work_struct *work)
> >>>> @@ -1815,6 +1846,12 @@ static int virtnet_probe(struct virtio_device *vdev)
> >>>> if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
> >>>> dev->features |= NETIF_F_RXCSUM;
> >>>>
> >>>> + if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) &&
> >>>> + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6)) {
> >>>> + dev->features |= NETIF_F_LRO;
> >>>> + dev->hw_features |= NETIF_F_LRO;
> >>>
> >>> So the issue is I think that the virtio "LRO" isn't really
> >>> LRO, it's typically just GRO forwarded to guests.
> >>> So these are easily re-split along MTU boundaries,
> >>> which makes it ok to forward these across bridges.
> >>>
> >>> It's not nice that we don't document this in the spec,
> >>> but it's the reality and people rely on this.
> >>>
> >>> For now, how about doing a custom thing and just disable/enable
> >>> it as XDP is attached/detached?
> >>
> >> The annoying part about doing this is ethtool will say that it is fixed
> >> yet it will be changed by seemingly unrelated operation. I'm not sure I
> >> like the idea to start automatically configuring the link via xdp_set.
> >
> > I really don't like the idea of dropping performance
> > by a factor of 3 for people bridging two virtio net
> > interfaces.
> >
> > So how about a simple approach for now, just disable
> > XDP if GUEST_TSO is enabled?
> >
> > We can discuss better approaches in next version.
> >
>
> So the proposal is to add a check in XDP setup so that
>
> if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO{4|6})
> return -ENOPSUPP;
>
> Or whatever is the most appropriate return code? Then we can
> disable TSO via qemu-system with guest_tso4=off,guest_tso6=off for
> XDP use cases.
Right. It's a start.
> Sounds like a reasonable start to me. I'll make the change should this
> go through DaveMs net-next tree or do you want it on virtio tree? Either
> is fine with me.
>
> Thanks,
> John
I think I'll merge it because I'm tweaking RX processing too,
and this will likely conflict.
--
MST
next prev parent reply other threads:[~2016-12-15 16:35 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-07 20:10 [net-next PATCH v5 0/6] XDP for virtio_net John Fastabend
2016-12-07 20:11 ` [net-next PATCH v5 1/6] net: virtio dynamically disable/enable LRO John Fastabend
2016-12-08 21:36 ` Michael S. Tsirkin
2016-12-09 0:04 ` John Fastabend
2016-12-09 3:05 ` Michael S. Tsirkin
2016-12-14 13:31 ` Michael S. Tsirkin
2016-12-14 17:01 ` John Fastabend
2016-12-15 16:35 ` Michael S. Tsirkin [this message]
2016-12-07 20:11 ` [net-next PATCH v5 2/6] net: xdp: add invalid buffer warning John Fastabend
2016-12-07 20:11 ` [net-next PATCH v5 3/6] virtio_net: Add XDP support John Fastabend
2016-12-08 4:48 ` Michael S. Tsirkin
2016-12-08 5:14 ` John Fastabend
2016-12-08 5:54 ` Michael S. Tsirkin
2016-12-07 20:12 ` [net-next PATCH v5 4/6] virtio_net: add dedicated XDP transmit queues John Fastabend
2016-12-08 5:59 ` Michael S. Tsirkin
2016-12-08 17:10 ` John Fastabend
2016-12-07 20:12 ` [net-next PATCH v5 5/6] virtio_net: add XDP_TX support John Fastabend
2016-12-08 6:11 ` Michael S. Tsirkin
2016-12-08 18:18 ` John Fastabend
2016-12-08 21:08 ` Michael S. Tsirkin
2016-12-08 21:18 ` Michael S. Tsirkin
2016-12-08 21:25 ` John Fastabend
2016-12-08 21:45 ` Michael S. Tsirkin
2016-12-08 21:51 ` John Fastabend
2016-12-07 20:13 ` [net-next PATCH v5 6/6] virtio_net: xdp, add slowpath case for non contiguous buffers John Fastabend
2016-12-08 19:17 ` [net-next PATCH v5 0/6] XDP for virtio_net David Miller
2016-12-08 19:38 ` Alexei Starovoitov
2016-12-08 20:46 ` John Fastabend
2016-12-08 20:58 ` Michael S. Tsirkin
2016-12-08 21:10 ` Michael S. Tsirkin
2016-12-08 21:08 ` Alexei Starovoitov
2016-12-08 22:16 ` David Miller
2016-12-09 3:01 ` Michael S. Tsirkin
2016-12-13 8:46 ` XDP_DROP and XDP_TX (Was: Re: [net-next PATCH v5 0/6] XDP for virtio_net) Jesper Dangaard Brouer
2016-12-08 21:16 ` [net-next PATCH v5 0/6] XDP for virtio_net Michael S. Tsirkin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20161215183341-mutt-send-email-mst@kernel.org \
--to=mst@redhat$(echo .)com \
--cc=alexei.starovoitov@gmail$(echo .)com \
--cc=brouer@redhat$(echo .)com \
--cc=daniel@iogearbox$(echo .)net \
--cc=davem@davemloft$(echo .)net \
--cc=john.fastabend@gmail$(echo .)com \
--cc=john.r.fastabend@intel$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=shm@cumulusnetworks$(echo .)com \
--cc=tgraf@suug$(echo .)ch \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox