On Mon, Jul 18, 2022 at 10:53 AM Jason Wang <jasow...@redhat.com> wrote:
>
>
> 在 2022/7/16 19:34, Eugenio Pérez 写道:
> > So we can reuse to inject state messages.
> >
> > Signed-off-by: Eugenio Pérez <epere...@redhat.com>
> > ---
> > net/vhost-vdpa.c | 89 +++++++++++++++++++++++++++---------------------
> > 1 file changed, 51 insertions(+), 38 deletions(-)
> >
> > diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
> > index 211bd0468b..aaae51a778 100644
> > --- a/net/vhost-vdpa.c
> > +++ b/net/vhost-vdpa.c
> > @@ -334,6 +334,54 @@ static bool vhost_vdpa_net_cvq_map_elem(VhostVDPAState
> > *s,
> > return true;
> > }
> >
> > +static virtio_net_ctrl_ack vhost_vdpa_net_svq_add(VhostShadowVirtqueue
> > *svq,
> > + const struct iovec
> > *dev_buffers)
>
>
> The name should be tweaked since it is used only for cvq.
>
Right, I'll change.
>
> > +{
> > + /* in buffer used for device model */
> > + virtio_net_ctrl_ack status;
> > + const struct iovec in = {
> > + .iov_base = &status,
> > + .iov_len = sizeof(status),
> > + };
> > + size_t dev_written;
> > + int r;
> > + void *unused = (void *)1;
> > +
> > + r = vhost_svq_add(svq, &dev_buffers[0], 1, &dev_buffers[1], 1, unused);
> > + if (unlikely(r != 0)) {
> > + if (unlikely(r == -ENOSPC)) {
> > + qemu_log_mask(LOG_GUEST_ERROR, "%s: No space on device
> > queue\n",
> > + __func__);
> > + }
> > + return VIRTIO_NET_ERR;
> > + }
> > +
> > + /*
> > + * We can poll here since we've had BQL from the time we sent the
> > + * descriptor. Also, we need to take the answer before SVQ pulls by
> > itself,
> > + * when BQL is released
> > + */
>
>
> This reminds me that, do we need a upper limit of the time on the
> polling here. (Avoid taking BQL for too long time).
>
Sending a new version of rx filters here.
But we have other parts where we can have BQL forever because we trust
the device, like vring enable syscalls for example.
Thanks!
