[PATCH 12/12] drm/amdgpu: put old hw fence of job if gpu reset

Christian König deathsimple at vodafone.de
Fri Jul 1 09:33:22 UTC 2016


Am 30.06.2016 um 11:34 schrieb Chunming Zhou:
> Change-Id: I15593e08ab79db77912797790ed59019b8686306
> Signed-off-by: Chunming Zhou <David1.Zhou at amd.com>

Might be a good idea to move this patch up in the set.

Anyway it is Reviewed-by: Christian König <christian.koenig at amd.com>.

Additional to that feel free to push the patches already reviewed to our 
branch, no need to send them out over and over again.

Regards,
Christian.

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 ++
>   1 file changed, 2 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> index 327f4df..0b55025 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> @@ -178,6 +178,8 @@ static struct fence *amdgpu_job_run(struct amd_sched_job *sched_job)
>   	}
>   
>   err:
> +	/* if gpu reset, hw fence will be replaced here */
> +	fence_put(job->fence);
>   	job->fence = fence;
>   	return fence;
>   }



More information about the amd-gfx mailing list