On Thu, Dec 2, 2021 at 3:58 AM Eli Cohen <e...@nvidia.com> wrote:
>
> Report back in get_vq_num_max() the correct number of virtqueues queried
> from the device instead of using a constant value.
>
> Signed-off-by: Eli Cohen <e...@nvidia.com>
> ---
> drivers/vdpa/mlx5/net/mlx5_vnet.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> index 62aba5dbd8fa..336eda3dcf41 100644
> --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> @@ -1992,10 +1992,10 @@ static void mlx5_vdpa_set_config_cb(struct
> vdpa_device *vdev, struct vdpa_callba
> ndev->config_cb = *cb;
> }
>
> -#define MLX5_VDPA_MAX_VQ_ENTRIES 256
> static u16 mlx5_vdpa_get_vq_num_max(struct vdpa_device *vdev)
> {
> - return MLX5_VDPA_MAX_VQ_ENTRIES;
> + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
> + return MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev,
> max_num_virtio_queues);
> }
I may miss something but I guess it should not be the hardware
limitation but the one that is set from netlink.
Thanks
>
> static u32 mlx5_vdpa_get_device_id(struct vdpa_device *vdev)
> --
> 2.33.1
>
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
