[PATCH v2] drm/amdkfd: Don't clear PT after process killed

[PATCH v2] drm/amdkfd: Don't clear PT after process killed

[Philip Yang]

If process is killed. the vm entity is stopped, submit pt update job
will trigger the error message "*ERROR* Trying to push to a killed
entity", job will not execute.

Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 96ccd5ade031..b1c24c8fa686 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1274,6 +1274,10 @@ static int unmap_bo_from_gpuvm(struct kgd_mem *mem,
 
 	(void)amdgpu_vm_bo_unmap(adev, bo_va, entry->va);
 
+	/* VM entity stopped if process killed, don't clear freed pt bo */
+	if (!amdgpu_vm_ready(vm))
+		return 0;
+
 	(void)amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
 
 	(void)amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);
-- 
2.49.0

Re: [PATCH v2] drm/amdkfd: Don't clear PT after process killed

[Christian König]

On 10/31/25 16:14, Philip Yang wrote:
> If process is killed. the vm entity is stopped, submit pt update job
> will trigger the error message "*ERROR* Trying to push to a killed
> entity", job will not execute.
> 
> Suggested-by: Christian König <christian.koenig@amd.com>
> Signed-off-by: Philip Yang <Philip.Yang@amd.com>

Reviewed-by: Christian König <christian.koenig@amd.com>

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 4 ++++
>  1 file changed, 4 insertions(+)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> index 96ccd5ade031..b1c24c8fa686 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> @@ -1274,6 +1274,10 @@ static int unmap_bo_from_gpuvm(struct kgd_mem *mem,
>  
>  	(void)amdgpu_vm_bo_unmap(adev, bo_va, entry->va);
>  
> +	/* VM entity stopped if process killed, don't clear freed pt bo */
> +	if (!amdgpu_vm_ready(vm))
> +		return 0;
> +
>  	(void)amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
>  
>  	(void)amdgpu_sync_fence(sync, bo_va->last_pt_update, GFP_KERNEL);