| Message ID | 20240617-stage-vdpa-vq-precreate-v1-23-8c0483f0ca2a@nvidia.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | vdpa/mlx5: Pre-create HW VQs to reduce LM downtime | expand |
| Context | Check | Description |
|---|---|---|
| netdev/tree_selection | success | Not a local patch |
On Mon, Jun 17, 2024 at 5:09 PM Dragos Tatulea <dtatulea@nvidia.com> wrote: > > VQ indices in the range [cur_num_qps, max_vqs) represent queues that > have not yet been activated. .set_vq_ready should not activate these > VQs. > > Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com> > Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com> Acked-by: Eugenio Pérez <eperezma@redhat.com> > --- > drivers/vdpa/mlx5/net/mlx5_vnet.c | 3 +++ > 1 file changed, 3 insertions(+) > > diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c > index 1a5ee0d2b47f..a969a7f105a6 100644 > --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c > +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c > @@ -1575,6 +1575,9 @@ static int resume_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq > if (!mvq->initialized) > return 0; > > + if (mvq->index >= ndev->cur_num_vqs) > + return 0; > + > switch (mvq->fw_state) { > case MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT: > /* Due to a FW quirk we need to modify the VQ fields first then change state. > > -- > 2.45.1 >
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 1a5ee0d2b47f..a969a7f105a6 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1575,6 +1575,9 @@ static int resume_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq if (!mvq->initialized) return 0; + if (mvq->index >= ndev->cur_num_vqs) + return 0; + switch (mvq->fw_state) { case MLX5_VIRTIO_NET_Q_OBJECT_STATE_INIT: /* Due to a FW quirk we need to modify the VQ fields first then change state.