Re: [PATCH 2/6] vduse: add vq group support

[Jason Wang <jasowang@redhat.com>]

On Mon, Sep 1, 2025 at 4:40 PM Eugenio Perez Martin <eperezma@redhat.com> wrote:
>
> On Mon, Sep 1, 2025 at 3:59 AM Jason Wang <jasowang@redhat.com> wrote:
> >
> > On Tue, Aug 26, 2025 at 7:27 PM Eugenio Pérez <eperezma@redhat.com> wrote:
> > >
> > > This allows sepparate the different virtqueues in groups that shares the
> > > same address space.  Asking the VDUSE device for the groups of the vq at
> > > the beginning as they're needed for the DMA API.
> > >
> > > Allocating 3 vq groups as net is the device that need the most groups:
> > > * Dataplane (guest passthrough)
> > > * CVQ
> > > * Shadowed vrings.
> > >
> > > Future versions of the series can include dynamic allocation of the
> > > groups array so VDUSE can declare more groups.
> > >
> > > Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
> > > ---
> > > v1: Fix: Remove BIT_ULL(VIRTIO_S_*), as _S_ is already the bit (Maxime)
> > >
> > > RFC v3:
> > > * Increase VDUSE_MAX_VQ_GROUPS to 0xffff (Jason). It was set to a lower
> > >   value to reduce memory consumption, but vqs are already limited to
> > >   that value and userspace VDUSE is able to allocate that many vqs.
> > > * Remove the descs vq group capability as it will not be used and we can
> > >   add it on top.
> > > * Do not ask for vq groups in number of vq groups < 2.
> > > * Move the valid vq groups range check to vduse_validate_config.
> > >
> > > RFC v2:
> > > * Cache group information in kernel, as we need to provide the vq map
> > >   tokens properly.
> > > * Add descs vq group to optimize SVQ forwarding and support indirect
> > >   descriptors out of the box.
> > > ---
> > >  drivers/vdpa/vdpa_user/vduse_dev.c | 51 ++++++++++++++++++++++++++++--
> > >  include/uapi/linux/vduse.h         | 21 +++++++++++-
> > >  2 files changed, 68 insertions(+), 4 deletions(-)
> > >
> > > diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
> > > index e7bced0b5542..0f4e36dd167e 100644
> > > --- a/drivers/vdpa/vdpa_user/vduse_dev.c
> > > +++ b/drivers/vdpa/vdpa_user/vduse_dev.c
> > > @@ -58,6 +58,7 @@ struct vduse_virtqueue {
> > >         struct vdpa_vq_state state;
> > >         bool ready;
> > >         bool kicked;
> > > +       u32 vq_group;
> > >         spinlock_t kick_lock;
> > >         spinlock_t irq_lock;
> > >         struct eventfd_ctx *kickfd;
> > > @@ -114,6 +115,7 @@ struct vduse_dev {
> > >         u8 status;
> > >         u32 vq_num;
> > >         u32 vq_align;
> > > +       u32 ngroups;
> > >         struct vduse_umem *umem;
> > >         struct mutex mem_lock;
> > >         unsigned int bounce_size;
> > > @@ -592,6 +594,13 @@ static int vduse_vdpa_set_vq_state(struct vdpa_device *vdpa, u16 idx,
> > >         return 0;
> > >  }
> > >
> > > +static u32 vduse_get_vq_group(struct vdpa_device *vdpa, u16 idx)
> > > +{
> > > +       struct vduse_dev *dev = vdpa_to_vduse(vdpa);
> > > +
> > > +       return dev->vqs[idx]->vq_group;
> > > +}
> > > +
> > >  static int vduse_vdpa_get_vq_state(struct vdpa_device *vdpa, u16 idx,
> > >                                 struct vdpa_vq_state *state)
> > >  {
> > > @@ -678,6 +687,28 @@ static u8 vduse_vdpa_get_status(struct vdpa_device *vdpa)
> > >         return dev->status;
> > >  }
> > >
> > > +static int vduse_fill_vq_groups(struct vduse_dev *dev)
> > > +{
> > > +       /* All vqs and descs must be in vq group 0 if ngroups < 2 */
> > > +       if (dev->ngroups < 2)
> > > +               return 0;
> > > +
> > > +       for (int i = 0; i < dev->vdev->vdpa.nvqs; ++i) {
> > > +               struct vduse_dev_msg msg = { 0 };
> > > +               int ret;
> > > +
> > > +               msg.req.type = VDUSE_GET_VQ_GROUP;
> > > +               msg.req.vq_group.index = i;
> > > +               ret = vduse_dev_msg_sync(dev, &msg);
> > > +               if (ret)
> > > +                       return ret;
> > > +
> > > +               dev->vqs[i]->vq_group = msg.resp.vq_group.group;
> > > +       }
> > > +
> > > +       return 0;
> > > +}
> > > +
> > >  static void vduse_vdpa_set_status(struct vdpa_device *vdpa, u8 status)
> > >  {
> > >         struct vduse_dev *dev = vdpa_to_vduse(vdpa);
> > > @@ -685,6 +716,11 @@ static void vduse_vdpa_set_status(struct vdpa_device *vdpa, u8 status)
> > >         if (vduse_dev_set_status(dev, status))
> > >                 return;
> > >
> > > +       if (((dev->status ^ status) & VIRTIO_CONFIG_S_FEATURES_OK) &&
> > > +           (status & VIRTIO_CONFIG_S_FEATURES_OK))
> > > +               if (vduse_fill_vq_groups(dev))
> > > +                       return;
> >
> > I may lose some context but I think we've agreed that we need to
> > extend the status response for this instead of having multiple
> > indepdent response.
> >
>
> My understanding was it is ok to start with this version by [1]. We
> can even make it asynchronous on top if we find this is a bottleneck
> and the VDUSE device would need no change, would that work?
>
> > > +
> > >         dev->status = status;
> > >  }
> > >
> > > @@ -789,6 +825,7 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = {
> > >         .set_vq_cb              = vduse_vdpa_set_vq_cb,
> > >         .set_vq_num             = vduse_vdpa_set_vq_num,
> > >         .get_vq_size            = vduse_vdpa_get_vq_size,
> > > +       .get_vq_group           = vduse_get_vq_group,
> > >         .set_vq_ready           = vduse_vdpa_set_vq_ready,
> > >         .get_vq_ready           = vduse_vdpa_get_vq_ready,
> > >         .set_vq_state           = vduse_vdpa_set_vq_state,
> > > @@ -1737,12 +1774,19 @@ static bool features_is_valid(struct vduse_dev_config *config)
> > >         return true;
> > >  }
> > >
> > > -static bool vduse_validate_config(struct vduse_dev_config *config)
> > > +static bool vduse_validate_config(struct vduse_dev_config *config,
> > > +                                 u64 api_version)
> > >  {
> > >         if (!is_mem_zero((const char *)config->reserved,
> > >                          sizeof(config->reserved)))
> > >                 return false;
> > >
> > > +       if (api_version < VDUSE_API_VERSION_1 && config->ngroups)
> > > +               return false;
> > > +
> > > +       if (api_version >= VDUSE_API_VERSION_1 && config->ngroups > 0xffff)
> > > +               return false;
> >
> > Let's use a macro instead of magic number.
> >
>
> The rest of the limits are hardcoded, but I'm ok with changing this.
> Is UINT16_MAX ok here, or do you prefer something like MAX_NGROUPS and
> MAX_ASID?

MAX_NGROUPS and MAX_ASID seem to be better.

Thanks

>
> [...]
>
> [1] https://patchew.org/linux/20250807115752.1663383-1-eperezma@redhat.com/20250807115752.1663383-3-eperezma@redhat.com/#CACGkMEuVngGjgPZXnajiPC+pcbt+dr6jqKRQr8OcX7HK1W3WNQ@mail.gmail.com
>