Re: [PATCH v3 5/7] drm/amdgpu: Set/Reset GPU workload profile

[Christian König]

Am 28.08.23 um 14:26 schrieb Arvind Yadav:
> This patch is to switch the GPU workload profile based
> on the submitted job. The workload profile is reset to
> default when the job is done.
>
> v3:
> - Addressed the review comment about changing the function
>    name from *_set() to *_get().

That looks like a really bad idea in general. This are the high level 
functions, but what you want to use are the low level functions for each 
ring.

Take a look at amdgpu_ring_begin_use()/_end_use() instead.

Christian.

> Cc: Christian Koenig <christian.koenig@xxxxxxx>
> Cc: Alex Deucher <alexander.deucher@xxxxxxx>
> Reviewed-by: Shashank Sharma <shashank.sharma@xxxxxxx>
> Signed-off-by: Arvind Yadav <Arvind.Yadav@xxxxxxx>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 5 +++++
>   1 file changed, 5 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> index c3d9d75143f4..c5032762d497 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> @@ -176,6 +176,9 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
>   static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
>   {
>   	struct amdgpu_job *job = to_amdgpu_job(s_job);
> +	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
> +
> +	amdgpu_workload_profile_put(ring->adev, ring->funcs->type);
>   
>   	drm_sched_job_cleanup(s_job);
>   
> @@ -295,6 +298,8 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
>   			DRM_ERROR("Error scheduling IBs (%d)\n", r);
>   	}
>   
> +	amdgpu_workload_profile_get(adev, ring->funcs->type);
> +
>   	job->job_run_counter++;
>   	amdgpu_job_free_resources(job);
>