Re: [PATCH vhost 4/7] vdpa/mlx5: Introduce per vq and device resume

[Eugenio Perez Martin]

On Fri, Dec 1, 2023 at 11:50 AM Dragos Tatulea <dtatulea@xxxxxxxxxx> wrote:
>
> Implement vdpa vq and device resume if capability detected. Add support
> for suspend -> ready state change.
>
> Signed-off-by: Dragos Tatulea <dtatulea@xxxxxxxxxx>

Acked-by: Eugenio Pérez <eperezma@xxxxxxxxxx>

> ---
>  drivers/vdpa/mlx5/net/mlx5_vnet.c | 67 +++++++++++++++++++++++++++----
>  1 file changed, 60 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> index d06285e46fe2..68e534cb57e2 100644
> --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> @@ -1170,7 +1170,12 @@ static int query_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueu
>         return err;
>  }
>
> -static bool is_valid_state_change(int oldstate, int newstate)
> +static bool is_resumable(struct mlx5_vdpa_net *ndev)
> +{
> +       return ndev->mvdev.vdev.config->resume;
> +}
> +
> +static bool is_valid_state_change(int oldstate, int newstate, bool resumable)
>  {
>         switch (oldstate) {
>         case MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT:
> @@ -1178,6 +1183,7 @@ static bool is_valid_state_change(int oldstate, int newstate)
>         case MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY:
>                 return newstate == MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND;
>         case MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND:
> +               return resumable ? newstate == MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY : false;
>         case MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR:
>         default:
>                 return false;
> @@ -1200,6 +1206,7 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
>  {
>         int inlen = MLX5_ST_SZ_BYTES(modify_virtio_net_q_in);
>         u32 out[MLX5_ST_SZ_DW(modify_virtio_net_q_out)] = {};
> +       bool state_change = false;
>         void *obj_context;
>         void *cmd_hdr;
>         void *in;
> @@ -1211,9 +1218,6 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
>         if (!modifiable_virtqueue_fields(mvq))
>                 return -EINVAL;
>
> -       if (!is_valid_state_change(mvq->fw_state, state))
> -               return -EINVAL;
> -
>         in = kzalloc(inlen, GFP_KERNEL);
>         if (!in)
>                 return -ENOMEM;
> @@ -1226,17 +1230,29 @@ static int modify_virtqueue(struct mlx5_vdpa_net *ndev,
>         MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, uid, ndev->mvdev.res.uid);
>
>         obj_context = MLX5_ADDR_OF(modify_virtio_net_q_in, in, obj_context);
> -       if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_STATE)
> +
> +       if (mvq->modified_fields & MLX5_VIRTQ_MODIFY_MASK_STATE) {
> +               if (!is_valid_state_change(mvq->fw_state, state, is_resumable(ndev))) {
> +                       err = -EINVAL;
> +                       goto done;
> +               }
> +
>                 MLX5_SET(virtio_net_q_object, obj_context, state, state);
> +               state_change = true;
> +       }
>
>         MLX5_SET64(virtio_net_q_object, obj_context, modify_field_select, mvq->modified_fields);
>         err = mlx5_cmd_exec(ndev->mvdev.mdev, in, inlen, out, sizeof(out));
> -       kfree(in);
> -       if (!err)
> +       if (err)
> +               goto done;
> +
> +       if (state_change)
>                 mvq->fw_state = state;
>
>         mvq->modified_fields = 0;
>
> +done:
> +       kfree(in);
>         return err;
>  }
>
> @@ -1430,6 +1446,24 @@ static void suspend_vqs(struct mlx5_vdpa_net *ndev)
>                 suspend_vq(ndev, &ndev->vqs[i]);
>  }
>
> +static void resume_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
> +{
> +       if (!mvq->initialized || !is_resumable(ndev))
> +               return;
> +
> +       if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND)
> +               return;
> +
> +       if (modify_virtqueue_state(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY))
> +               mlx5_vdpa_warn(&ndev->mvdev, "modify to resume failed\n");
> +}
> +
> +static void resume_vqs(struct mlx5_vdpa_net *ndev)
> +{
> +       for (int i = 0; i < ndev->mvdev.max_vqs; i++)
> +               resume_vq(ndev, &ndev->vqs[i]);
> +}
> +
>  static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
>  {
>         if (!mvq->initialized)
> @@ -3256,6 +3290,21 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev)
>         return 0;
>  }
>
> +static int mlx5_vdpa_resume(struct vdpa_device *vdev)
> +{
> +       struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
> +       struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
> +
> +       mlx5_vdpa_info(mvdev, "resuming device\n");
> +
> +       down_write(&ndev->reslock);
> +       mvdev->suspended = false;
> +       resume_vqs(ndev);
> +       register_link_notifier(ndev);
> +       up_write(&ndev->reslock);
> +       return 0;
> +}
> +
>  static int mlx5_set_group_asid(struct vdpa_device *vdev, u32 group,
>                                unsigned int asid)
>  {
> @@ -3312,6 +3361,7 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = {
>         .get_vq_dma_dev = mlx5_get_vq_dma_dev,
>         .free = mlx5_vdpa_free,
>         .suspend = mlx5_vdpa_suspend,
> +       .resume = mlx5_vdpa_resume, /* Op disabled if not supported. */
>  };
>
>  static int query_mtu(struct mlx5_core_dev *mdev, u16 *mtu)
> @@ -3683,6 +3733,9 @@ static int mlx5v_probe(struct auxiliary_device *adev,
>         if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, desc_group_mkey_supported))
>                 mgtdev->vdpa_ops.get_vq_desc_group = NULL;
>
> +       if (!MLX5_CAP_DEV_VDPA_EMULATION(mdev, freeze_to_rdy_supported))
> +               mgtdev->vdpa_ops.resume = NULL;
> +
>         err = vdpa_mgmtdev_register(&mgtdev->mgtdev);
>         if (err)
>                 goto reg_err;
> --
> 2.42.0
>