Jason Wang
2022-Sep-14 04:44 UTC
[PATCH] vdpa/mlx5: Fix MQ to support non power of two num queues
On Mon, Sep 12, 2022 at 8:50 PM Eli Cohen <elic at nvidia.com> wrote:> > RQT objects require that a power of two value be configured for both > rqt_max_size and rqt_actual size. > > For create_rqt, make sure to round up to the power of two the value of > given by the user who created the vdpa device and given by > ndev->rqt_size. The actual size is also rounded up to the power of two > using the current number of VQs given by ndev->cur_num_vqs. > > Same goes with modify_rqt where we need to make sure act size is power > of two based on the new number of QPs. > > Without this patch, attempt to create a device with non power of two QPs > would result in error from firmware. > > Fixes: 52893733f2c5 ("vdpa/mlx5: Add multiqueue support") > Signed-off-by: Eli Cohen <elic at nvidia.com>Acked-by: Jason Wang <jasowang at redhat.com>> --- > drivers/vdpa/mlx5/net/mlx5_vnet.c | 17 ++++++++++------- > 1 file changed, 10 insertions(+), 7 deletions(-) > > diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c > index ed100a35e596..90913365def4 100644 > --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c > +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c > @@ -1320,6 +1320,8 @@ static void teardown_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue * > > static int create_rqt(struct mlx5_vdpa_net *ndev) > { > + int rqt_table_size = roundup_pow_of_two(ndev->rqt_size); > + int act_sz = roundup_pow_of_two(ndev->cur_num_vqs / 2); > __be32 *list; > void *rqtc; > int inlen; > @@ -1327,7 +1329,7 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) > int i, j; > int err; > > - inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + ndev->rqt_size * MLX5_ST_SZ_BYTES(rq_num); > + inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + rqt_table_size * MLX5_ST_SZ_BYTES(rq_num); > in = kzalloc(inlen, GFP_KERNEL); > if (!in) > return -ENOMEM; > @@ -1336,12 +1338,12 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) > rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); > > MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q); > - MLX5_SET(rqtc, rqtc, rqt_max_size, ndev->rqt_size); > + MLX5_SET(rqtc, rqtc, rqt_max_size, rqt_table_size); > list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]); > - for (i = 0, j = 0; i < ndev->rqt_size; i++, j += 2) > + for (i = 0, j = 0; i < act_sz; i++, j += 2) > list[i] = cpu_to_be32(ndev->vqs[j % ndev->cur_num_vqs].virtq_id); > > - MLX5_SET(rqtc, rqtc, rqt_actual_size, ndev->rqt_size); > + MLX5_SET(rqtc, rqtc, rqt_actual_size, act_sz); > err = mlx5_vdpa_create_rqt(&ndev->mvdev, in, inlen, &ndev->res.rqtn); > kfree(in); > if (err) > @@ -1354,6 +1356,7 @@ static int create_rqt(struct mlx5_vdpa_net *ndev) > > static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) > { > + int act_sz = roundup_pow_of_two(num / 2); > __be32 *list; > void *rqtc; > int inlen; > @@ -1361,7 +1364,7 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) > int i, j; > int err; > > - inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + ndev->rqt_size * MLX5_ST_SZ_BYTES(rq_num); > + inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + act_sz * MLX5_ST_SZ_BYTES(rq_num); > in = kzalloc(inlen, GFP_KERNEL); > if (!in) > return -ENOMEM; > @@ -1372,10 +1375,10 @@ static int modify_rqt(struct mlx5_vdpa_net *ndev, int num) > MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q); > > list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]); > - for (i = 0, j = 0; i < ndev->rqt_size; i++, j += 2) > + for (i = 0, j = 0; i < act_sz; i++, j = j + 2) > list[i] = cpu_to_be32(ndev->vqs[j % num].virtq_id); > > - MLX5_SET(rqtc, rqtc, rqt_actual_size, ndev->rqt_size); > + MLX5_SET(rqtc, rqtc, rqt_actual_size, act_sz); > err = mlx5_vdpa_modify_rqt(&ndev->mvdev, in, inlen, ndev->res.rqtn); > kfree(in); > if (err) > -- > 2.35.1 >