On Wed, Apr 07, 2021 at 01:16:12PM +0300, Eli Cohen wrote:
> On Wed, Apr 07, 2021 at 03:25:00PM +0800, Jason Wang wrote:
> >
> > 在 2021/4/7 上午1:04, Parav Pandit 写道:
> > > From: Eli Cohen <elic@xxxxxxxxxx>
> > >
> > > When we suspend the VM, the VDPA interface will be reset. When the VM is
> > > resumed again, clear_virtqueues() will clear the available and used
> > > indices resulting in hardware virqtqueue objects becoming out of sync.
> > > We can avoid this function alltogether since qemu will clear them if
> > > required, e.g. when the VM went through a reboot.
> > >
> > > Moreover, since the hw available and used indices should always be
> > > identical on query and should be restored to the same value same value
> > > for virtqueues that complete in order, we set the single value provided
> > > by set_vq_state(). In get_vq_state() we return the value of hardware
> > > used index.
> > >
> > > Fixes: b35ccebe3ef7 ("vdpa/mlx5: Restore the hardware used index after change map")
> > > Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
> > > Signed-off-by: Eli Cohen <elic@xxxxxxxxxx>
> > > ---
> > > drivers/vdpa/mlx5/net/mlx5_vnet.c | 17 ++++-------------
> > > 1 file changed, 4 insertions(+), 13 deletions(-)
> > >
> > > diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > index 56d463d2be85..a6e6d44b9ca5 100644
> > > --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > @@ -1170,6 +1170,7 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m
> > > return;
> > > }
> > > mvq->avail_idx = attr.available_index;
> > > + mvq->used_idx = attr.used_index;
> > > }
> > > static void suspend_vqs(struct mlx5_vdpa_net *ndev)
> > > @@ -1466,6 +1467,7 @@ static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx,
> > > return -EINVAL;
> > > }
> > > + mvq->used_idx = state->avail_index;
> > > mvq->avail_idx = state->avail_index;
> > > return 0;
> > > }
> > > @@ -1483,7 +1485,7 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
> > > * that cares about emulating the index after vq is stopped.
> > > */
> > > if (!mvq->initialized) {
> > > - state->avail_index = mvq->avail_idx;
> > > + state->avail_index = mvq->used_idx;
> >
> >
> > Even if the hardware avail idx is always equal to used idx. I would still
> > keep using the avail_idx, this makes it easier to be reviewed since it is
> > consistent to e.g kernel vhost bakcend implementations. (The last_avail_idx
> > in vhost_virtqueue).
> >
>
> The problem is that there is a bug in the firmware such that for RX
> virtqueues firmware returns a wrong value in the avail_idx. The correct
> value is reported in used_idx. That's why we need to take the value from
> used_idx.
Maybe add a code comment here so people can figure it out?
> > Thanks
> >
> >
> > > return 0;
> > > }
> > > @@ -1492,7 +1494,7 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
> > > mlx5_vdpa_warn(mvdev, "failed to query virtqueue\n");
> > > return err;
> > > }
> > > - state->avail_index = attr.available_index;
> > > + state->avail_index = attr.used_index;
> > > return 0;
> > > }
> > > @@ -1572,16 +1574,6 @@ static void teardown_virtqueues(struct mlx5_vdpa_net *ndev)
> > > }
> > > }
> > > -static void clear_virtqueues(struct mlx5_vdpa_net *ndev)
> > > -{
> > > - int i;
> > > -
> > > - for (i = ndev->mvdev.max_vqs - 1; i >= 0; i--) {
> > > - ndev->vqs[i].avail_idx = 0;
> > > - ndev->vqs[i].used_idx = 0;
> > > - }
> > > -}
> > > -
> > > /* TODO: cross-endian support */
> > > static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev)
> > > {
> > > @@ -1822,7 +1814,6 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
> > > if (!status) {
> > > mlx5_vdpa_info(mvdev, "performing device reset\n");
> > > teardown_driver(ndev);
> > > - clear_virtqueues(ndev);
> > > mlx5_vdpa_destroy_mr(&ndev->mvdev);
> > > ndev->mvdev.status = 0;
> > > ++mvdev->generation;
> >
_______________________________________________
Virtualization mailing list
Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
