On 5/26/2020 07:34, Leon Romanovsky wrote:
> From: Mark Zhang <markz@xxxxxxxxxxxx>
>
> The mlx5 VF driver doesn't set QP tx port affinity because it doesn't
> know if the lag is active or not, since the "lag_active" works only for
> PF interfaces. In this case for VF interfaces only one lag is used
> which brings performance issue.
>
> Add a lag_tx_port_affinity CAP bit; When it is enabled and
> "num_lag_ports > 1", then driver always set QP tx affinity, regardless
> of lag state.
>
> Signed-off-by: Mark Zhang <markz@xxxxxxxxxxxx>
> Reviewed-by: Maor Gottlieb <maorg@xxxxxxxxxxxx>
> Signed-off-by: Leon Romanovsky <leonro@xxxxxxxxxxxx>
> ---
> drivers/infiniband/hw/mlx5/main.c | 2 +-
> drivers/infiniband/hw/mlx5/mlx5_ib.h | 7 +++++++
> drivers/infiniband/hw/mlx5/qp.c | 3 ++-
> 3 files changed, 10 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
> index 570c519ca530..4719da201382 100644
> --- a/drivers/infiniband/hw/mlx5/main.c
> +++ b/drivers/infiniband/hw/mlx5/main.c
> @@ -1984,7 +1984,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx,
> context->lib_caps = req.lib_caps;
> print_lib_caps(dev, context->lib_caps);
>
> - if (dev->lag_active) {
> + if (mlx5_ib_lag_should_assign_affinity(dev)) {
> u8 port = mlx5_core_native_port_num(dev->mdev) - 1;
>
> atomic_set(&context->tx_port_affinity,
> diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
> index b486139b08ce..0f5a713ac2a9 100644
> --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
> +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
> @@ -1553,4 +1553,11 @@ static inline bool mlx5_ib_can_use_umr(struct mlx5_ib_dev *dev,
>
> int mlx5_ib_enable_driver(struct ib_device *dev);
> int mlx5_ib_test_wc(struct mlx5_ib_dev *dev);
> +
> +static inline bool mlx5_ib_lag_should_assign_affinity(struct mlx5_ib_dev *dev)
> +{
> + return dev->lag_active ||
> + (MLX5_CAP_GEN(dev->mdev, num_lag_ports) &&
> + MLX5_CAP_GEN(dev->mdev, lag_tx_port_affinity));
first of all in the commit message you write:
"When it is enabled and > "num_lag_ports > 1""
which isn't the case here as even num_lag_ports == 1 will pass.
In addition, even on a system without lag this cap can be 2 (on a 2 port NIC
where the FW supports lag).
I assume/hope/think that somewhere in the FW there is a check that says:
"If user has set port_affinity but lag isn't active use the native port affinity"
either way I think it needs to be documented in the commit message.
Mark
> +}
> #endif /* MLX5_IB_H */
> diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
> index 1988a0375696..9364a7a76ac2 100644
> --- a/drivers/infiniband/hw/mlx5/qp.c
> +++ b/drivers/infiniband/hw/mlx5/qp.c
> @@ -3653,7 +3653,8 @@ static unsigned int get_tx_affinity(struct ib_qp *qp,
> struct mlx5_ib_qp_base *qp_base;
> unsigned int tx_affinity;
>
> - if (!(dev->lag_active && qp_supports_affinity(qp)))
> + if (!(mlx5_ib_lag_should_assign_affinity(dev) &&
> + qp_supports_affinity(qp)))
> return 0;
>
> if (mqp->flags & MLX5_IB_QP_CREATE_SQPN_QP1)
>
