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);
