On Thu, Nov 08, 2018 at 09:10:15PM +0200, Leon Romanovsky wrote:
> From: Moni Shoua <monis@xxxxxxxxxxxx>
>
> Telling the HCA that page fault handling is done and QP can resume
> its flow is done in the context of the page fault handler. This blocks
> the handling of the next work in queue without a need.
> Call the PAGE_FAULT_RESUME command in an asynchronous manner and free
> the workqueue to pick the next work item for handling. All tasks that
> were executed after PAGE_FAULT_RESUME need to be done now
> in the callback of the asynchronous command mechanism.
>
> Signed-off-by: Moni Shoua <monis@xxxxxxxxxxxx>
> Signed-off-by: Leon Romanovsky <leonro@xxxxxxxxxxxx>
> drivers/infiniband/hw/mlx5/odp.c | 110 +++++++++++++++++++++++++------
> include/linux/mlx5/driver.h | 3 +
> 2 files changed, 94 insertions(+), 19 deletions(-)
>
> diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
> index abce55b8b9ba..0c4f469cdd5b 100644
> +++ b/drivers/infiniband/hw/mlx5/odp.c
> @@ -298,20 +298,78 @@ void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
> return;
> }
>
> +struct pfault_resume_cb_ctx {
> + struct mlx5_ib_dev *dev;
> + struct mlx5_core_rsc_common *res;
> + struct mlx5_pagefault *pfault;
> +};
> +
> +static void page_fault_resume_callback(int status, void *context)
> +{
> + struct pfault_resume_cb_ctx *ctx = context;
> + struct mlx5_pagefault *pfault = ctx->pfault;
> +
> + if (status)
> + mlx5_ib_err(ctx->dev, "Resolve the page fault failed with status %d\n",
> + status);
> +
> + if (ctx->res)
> + mlx5_core_res_put(ctx->res);
> + kfree(pfault);
> + kfree(ctx);
> +}
> +
> static void mlx5_ib_page_fault_resume(struct mlx5_ib_dev *dev,
> + struct mlx5_core_rsc_common *res,
> struct mlx5_pagefault *pfault,
> - int error)
> + int error,
> + bool async)
> {
> + int ret = 0;
> + u32 *out = pfault->out_pf_resume;
> + u32 *in = pfault->in_pf_resume;
> + u32 token = pfault->token;
> int wq_num = pfault->event_subtype == MLX5_PFAULT_SUBTYPE_WQE ?
> - pfault->wqe.wq_num : pfault->token;
> - int ret = mlx5_core_page_fault_resume(dev->mdev,
> - pfault->token,
> - wq_num,
> - pfault->type,
> - error);
> - if (ret)
> - mlx5_ib_err(dev, "Failed to resolve the page fault on WQ 0x%x\n",
> - wq_num);
> + pfault->wqe.wq_num : pfault->token;
> + u8 type = pfault->type;
> + struct pfault_resume_cb_ctx *ctx = NULL;
> +
> + if (async)
> + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
Why not allocate this ctx ast part of the mlx5_pagefault and avoid
this allocation failure strategy?
Jason
