Re: [PATCH v2] drm/amdkfd: fix svm_bo release invalid wait context warning

[Felix Kuehling <felix.kuehling@xxxxxxx>]

On 2021-12-09 4:18 p.m., Philip Yang wrote:
> Add svm_range_bo_unref_async to schedule work to wait for svm_bo
> eviction work done and then free svm_bo. __do_munmap put_page
> is atomic context, call svm_range_bo_unref_async to avoid warning
> invalid wait context. Other non atomic context call svm_range_bo_unref.
>
> Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>

Reviewed-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>


> ---
>   drivers/gpu/drm/amd/amdkfd/kfd_migrate.c |  2 +-
>   drivers/gpu/drm/amd/amdkfd/kfd_svm.c     | 31 +++++++++++++++++++++---
>   drivers/gpu/drm/amd/amdkfd/kfd_svm.h     |  3 ++-
>   3 files changed, 30 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> index 9731151b67d6..d5d2cf2ee788 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> @@ -550,7 +550,7 @@ static void svm_migrate_page_free(struct page *page)
>   
>   	if (svm_bo) {
>   		pr_debug_ratelimited("ref: %d\n", kref_read(&svm_bo->kref));
> -		svm_range_bo_unref(svm_bo);
> +		svm_range_bo_unref_async(svm_bo);
>   	}
>   }
>   
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> index c178d56361d6..b216842b5fe2 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> @@ -332,6 +332,8 @@ static void svm_range_bo_release(struct kref *kref)
>   	struct svm_range_bo *svm_bo;
>   
>   	svm_bo = container_of(kref, struct svm_range_bo, kref);
> +	pr_debug("svm_bo 0x%p\n", svm_bo);
> +
>   	spin_lock(&svm_bo->list_lock);
>   	while (!list_empty(&svm_bo->range_list)) {
>   		struct svm_range *prange =
> @@ -365,12 +367,33 @@ static void svm_range_bo_release(struct kref *kref)
>   	kfree(svm_bo);
>   }
>   
> -void svm_range_bo_unref(struct svm_range_bo *svm_bo)
> +static void svm_range_bo_wq_release(struct work_struct *work)
>   {
> -	if (!svm_bo)
> -		return;
> +	struct svm_range_bo *svm_bo;
> +
> +	svm_bo = container_of(work, struct svm_range_bo, release_work);
> +	svm_range_bo_release(&svm_bo->kref);
> +}
> +
> +static void svm_range_bo_release_async(struct kref *kref)
> +{
> +	struct svm_range_bo *svm_bo;
> +
> +	svm_bo = container_of(kref, struct svm_range_bo, kref);
> +	pr_debug("svm_bo 0x%p\n", svm_bo);
> +	INIT_WORK(&svm_bo->release_work, svm_range_bo_wq_release);
> +	schedule_work(&svm_bo->release_work);
> +}
>   
> -	kref_put(&svm_bo->kref, svm_range_bo_release);
> +void svm_range_bo_unref_async(struct svm_range_bo *svm_bo)
> +{
> +	kref_put(&svm_bo->kref, svm_range_bo_release_async);
> +}
> +
> +static void svm_range_bo_unref(struct svm_range_bo *svm_bo)
> +{
> +	if (svm_bo)
> +		kref_put(&svm_bo->kref, svm_range_bo_release);
>   }
>   
>   static bool
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
> index 6dc91c33e80f..2f8a95e86dcb 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
> @@ -48,6 +48,7 @@ struct svm_range_bo {
>   	struct work_struct		eviction_work;
>   	struct svm_range_list		*svms;
>   	uint32_t			evicting;
> +	struct work_struct		release_work;
>   };
>   
>   enum svm_work_list_ops {
> @@ -195,7 +196,7 @@ void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_s
>    */
>   #define KFD_IS_SVM_API_SUPPORTED(dev) ((dev)->pgmap.type != 0)
>   
> -void svm_range_bo_unref(struct svm_range_bo *svm_bo);
> +void svm_range_bo_unref_async(struct svm_range_bo *svm_bo);
>   #else
>   
>   struct kfd_process;