[PATCH 1/3] drm/amdkfd: support concurrent userptr update for HMM v2

[Kuehling, Felix]

On 2019-03-06 9:42 p.m., Yang, Philip wrote:
> Userptr restore may have concurrent userptr invalidation after
> hmm_vma_fault adds the range to the hmm->ranges list, needs call
> hmm_vma_range_done to remove the range from hmm->ranges list first,
> then reschedule the restore worker. Otherwise hmm_vma_fault will add
> same range to the list, this will cause loop in the list because
> range->next point to range itself.
>
> Add function untrack_invalid_user_pages to reduce code duplication.
>
> Change-Id: I31407739dc10554f8e418c7a0e0415d3d95552f1
> Signed-off-by: Philip Yang <Philip.Yang at amd.com>

This patch is Reviewed-by: Felix Kuehling <Felix.Kuehling at amd.com>


> ---
>   .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c  | 25 ++++++++++++++-----
>   1 file changed, 19 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> index d2e315f42dad..60d53b0b497a 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> @@ -1935,6 +1935,23 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
>   	return 0;
>   }
>   
> +/* Remove invalid userptr BOs from hmm track list
> + *
> + * Stop HMM track the userptr update
> + */
> +static void untrack_invalid_user_pages(struct amdkfd_process_info *process_info)
> +{
> +	struct kgd_mem *mem, *tmp_mem;
> +	struct amdgpu_bo *bo;
> +
> +	list_for_each_entry_safe(mem, tmp_mem,
> +				 &process_info->userptr_inval_list,
> +				 validate_list.head) {
> +		bo = mem->bo;
> +		amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
> +	}
> +}
> +
>   /* Validate invalid userptr BOs
>    *
>    * Validates BOs on the userptr_inval_list, and moves them back to the
> @@ -2052,12 +2069,6 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
>   out_free:
>   	kfree(pd_bo_list_entries);
>   out_no_mem:
> -	list_for_each_entry_safe(mem, tmp_mem,
> -				 &process_info->userptr_inval_list,
> -				 validate_list.head) {
> -		bo = mem->bo;
> -		amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
> -	}
>   
>   	return ret;
>   }
> @@ -2122,7 +2133,9 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work)
>   		 * hanging. No point trying again.
>   		 */
>   	}
> +
>   unlock_out:
> +	untrack_invalid_user_pages(process_info);
>   	mutex_unlock(&process_info->lock);
>   	mmput(mm);
>   	put_task_struct(usertask);