Re: [PATCH 5/6] vdpa: add get_vq_num_unchangeable callback in vdpa_config_ops

From: Wu Zongyong
Date: Thu Sep 09 2021 - 05:57:30 EST


On Thu, Sep 09, 2021 at 05:28:26PM +0800, Jason Wang wrote:
> On Thu, Sep 9, 2021 at 4:02 PM Wu Zongyong <wuzongyong@xxxxxxxxxxxxxxxxx> wrote:
> >
> > On Thu, Sep 09, 2021 at 10:55:03AM +0800, Jason Wang wrote:
> > > On Wed, Sep 8, 2021 at 8:23 PM Wu Zongyong <wuzongyong@xxxxxxxxxxxxxxxxx> wrote:
> > > >
> > > > This new callback is used to indicate whether the vring size can be
> > > > change or not. It is useful when we have a legacy virtio pci device as
> > > > the vdpa device for there is no way to negotiate the vring num by the
> > > > specification.
> > >
> > > So I'm not sure it's worth bothering. E.g what if we just fail
> > > VHOST_SET_VRING_NUM it the value doesn't match what hardware has?
> > >
> > > Thanks
> > >
> > I think we should not call VHOST_SET_VRING_NUM in that case.
> >
> > If the hardware reports that the virtqueue size cannot be changed, we
> > should call VHOST_GET_VRING_NUM to get the static virtqueue size
> > firstly, then allocate the same size memory for the virtqueues and write
> > the address to hardware finally.
> >
> > For QEMU, we will ignore the properties rx/tx_queue_size and just get it
> > from the hardware if this new callback return true.
>
> This will break live migration. My understanding is that we can
> advertise those capability/limitation via the netlink management
> protocol then management layer can choose to use the correct queue
> size.
>
> Thanks
I agree, it is a good idea.
BTW, can we also advertise mac address of network device? I found the
mac address generated by libvirt or qemu will break the network datapath
down if I don't specify the right mac explicitly in the XML or qemu
commandline.
>
> >
> > What do you think?
> > > >
> > > > Signed-off-by: Wu Zongyong <wuzongyong@xxxxxxxxxxxxxxxxx>
> > > > ---
> > > > drivers/vhost/vdpa.c | 19 +++++++++++++++++++
> > > > drivers/virtio/virtio_vdpa.c | 5 ++++-
> > > > include/linux/vdpa.h | 4 ++++
> > > > include/uapi/linux/vhost.h | 2 ++
> > > > 4 files changed, 29 insertions(+), 1 deletion(-)
> > > >
> > > > diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
> > > > index 9479f7f79217..2204d27d1e5d 100644
> > > > --- a/drivers/vhost/vdpa.c
> > > > +++ b/drivers/vhost/vdpa.c
> > > > @@ -350,6 +350,22 @@ static long vhost_vdpa_get_iova_range(struct vhost_vdpa *v, u32 __user *argp)
> > > > return 0;
> > > > }
> > > >
> > > > +static long vhost_vdpa_get_vring_num_unchangeable(struct vhost_vdpa *v,
> > > > + u32 __user *argp)
> > > > +{
> > > > + struct vdpa_device *vdpa = v->vdpa;
> > > > + const struct vdpa_config_ops *ops = vdpa->config;
> > > > + bool unchangeable = false;
> > > > +
> > > > + if (ops->get_vq_num_unchangeable)
> > > > + unchangeable = ops->get_vq_num_unchangeable(vdpa);
> > > > +
> > > > + if (copy_to_user(argp, &unchangeable, sizeof(unchangeable)))
> > > > + return -EFAULT;
> > > > +
> > > > + return 0;
> > > > +}
> > > > +
> > > > static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
> > > > void __user *argp)
> > > > {
> > > > @@ -487,6 +503,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
> > > > case VHOST_VDPA_GET_IOVA_RANGE:
> > > > r = vhost_vdpa_get_iova_range(v, argp);
> > > > break;
> > > > + case VHOST_VDPA_GET_VRING_NUM_UNCHANGEABLE:
> > > > + r = vhost_vdpa_get_vring_num_unchangeable(v, argp);
> > > > + break;
> > > > default:
> > > > r = vhost_dev_ioctl(&v->vdev, cmd, argp);
> > > > if (r == -ENOIOCTLCMD)
> > > > diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
> > > > index 72eaef2caeb1..afb47465307a 100644
> > > > --- a/drivers/virtio/virtio_vdpa.c
> > > > +++ b/drivers/virtio/virtio_vdpa.c
> > > > @@ -146,6 +146,7 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
> > > > struct vdpa_vq_state state = {0};
> > > > unsigned long flags;
> > > > u32 align, num;
> > > > + bool may_reduce_num = true;
> > > > int err;
> > > >
> > > > if (!name)
> > > > @@ -171,8 +172,10 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
> > > >
> > > > /* Create the vring */
> > > > align = ops->get_vq_align(vdpa);
> > > > + if (ops->get_vq_num_unchangeable)
> > > > + may_reduce_num = !ops->get_vq_num_unchangeable(vdpa);
> > > > vq = vring_create_virtqueue(index, num, align, vdev,
> > > > - true, true, ctx,
> > > > + true, may_reduce_num, ctx,
> > > > virtio_vdpa_notify, callback, name);
> > > > if (!vq) {
> > > > err = -ENOMEM;
> > > > diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
> > > > index 35648c11e312..f809b7ada00d 100644
> > > > --- a/include/linux/vdpa.h
> > > > +++ b/include/linux/vdpa.h
> > > > @@ -195,6 +195,9 @@ struct vdpa_iova_range {
> > > > * @vdev: vdpa device
> > > > * Returns the iova range supported by
> > > > * the device.
> > > > + * @get_vq_num_unchangeable Check if size of virtqueue is unchangeable (optional)
> > > > + * @vdev: vdpa device
> > > > + * Returns boolean: unchangeable (true) or not (false)
> > > > * @set_map: Set device memory mapping (optional)
> > > > * Needed for device that using device
> > > > * specific DMA translation (on-chip IOMMU)
> > > > @@ -262,6 +265,7 @@ struct vdpa_config_ops {
> > > > const void *buf, unsigned int len);
> > > > u32 (*get_generation)(struct vdpa_device *vdev);
> > > > struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev);
> > > > + bool (*get_vq_num_unchangeable)(struct vdpa_device *vdev);
> > > >
> > > > /* DMA ops */
> > > > int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb);
> > > > diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
> > > > index c998860d7bbc..184f1f7f8498 100644
> > > > --- a/include/uapi/linux/vhost.h
> > > > +++ b/include/uapi/linux/vhost.h
> > > > @@ -150,4 +150,6 @@
> > > > /* Get the valid iova range */
> > > > #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \
> > > > struct vhost_vdpa_iova_range)
> > > > +/* Check if the vring size can be change */
> > > > +#define VHOST_VDPA_GET_VRING_NUM_UNCHANGEABLE _IOR(VHOST_VIRTIO, 0X79, bool)
> > > > #endif
> > > > --
> > > > 2.31.1
> > > >
> >