Re: [PATCH v1 1/2] drm/amdgpu: move debug_vm handling to amdgpu_cs_parser_fini

[Christian König]

On 6/22/26 11:28, Pierre-Eric Pelloux-Prayer wrote:
> The commit referenced below restarts the CS if the validation is
> still in progress. When debug_vm is enabled, all BOs from the CS
> are invalidated so we will hit an infinite loop.
> 
> To avoid that, defer BO invalidation to amdgpu_cs_parser_fini.
> 
> Fixes: 83ac717d7837 ("drm/amdgpu: restart the CS if some parts of the VM are still invalidated")
> Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@xxxxxxx>

Reviewed-by: Christian König <christian.koenig@xxxxxxx> for both patches.

> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 30 ++++++++++++++------------
>  1 file changed, 16 insertions(+), 14 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> index d63fbc7c568d..7e75c536dab3 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
> @@ -1180,19 +1180,6 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
>  		job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.bo);
>  	}
>  
> -	if (adev->debug_vm) {
> -		/* Invalidate all BOs to test for userspace bugs */
> -		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
> -			struct amdgpu_bo *bo = e->bo;
> -
> -			/* ignore duplicates */
> -			if (!bo)
> -				continue;
> -
> -			amdgpu_vm_bo_invalidate(bo, false);
> -		}
> -	}
> -
>  	return 0;
>  }
>  
> @@ -1382,6 +1369,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
>  /* Cleanup the parser structure */
>  static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser)
>  {
> +	struct amdgpu_device *adev = parser->adev;
> +	struct amdgpu_bo_list_entry *e;
>  	unsigned int i;
>  
>  	amdgpu_sync_free(&parser->sync);
> @@ -1397,8 +1386,21 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser)
>  
>  	if (parser->ctx)
>  		amdgpu_ctx_put(parser->ctx);
> -	if (parser->bo_list)
> +	if (parser->bo_list) {
> +		if (adev->debug_vm) {
> +			/* Invalidate all BOs to test for userspace bugs */
> +			amdgpu_bo_list_for_each_entry(e, parser->bo_list) {
> +				struct amdgpu_bo *bo = e->bo;
> +
> +				/* ignore duplicates */
> +				if (!bo)
> +					continue;
> +
> +				amdgpu_vm_bo_invalidate(bo, false);
> +			}
> +		}
>  		amdgpu_bo_list_put(parser->bo_list);
> +	}
>  
>  	for (i = 0; i < parser->nchunks; i++)
>  		kvfree(parser->chunks[i].kdata);