kybaaz/linux-xiaomi-chiron
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Revert "drm/scheduler: improve job distribution with multiple queues"

Browse source 
It needs to revert this patch to avoid amdgpu_test compute hang problem
on picasso.

This reverts commit 56822db194.

Signed-off-by: changzhu <Changfeng.Zhu@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
changzhu 2020-03-11 19:12:52 +08:00 • committed by Alex Deucher
parent 9015d60c9e
commit d164bebb95
3 changed files with 10 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

6
include/drm/gpu_scheduler.h
View file

@ -262,7 +262,7 @@ struct drm_sched_backend_ops {
* @job_list_lock: lock to protect the ring_mirror_list.
* @hang_limit: once the hangs by a job crosses this limit then it is marked
* guilty and it will be considered for scheduling further.
* @score: score to help loadbalancer pick a idle sched
* @num_jobs: the number of jobs in queue in the scheduler
* @ready: marks if the underlying HW is ready to work
* @free_guilty: A hit to time out handler to free the guilty job.
*
@ -283,8 +283,8 @@ struct drm_gpu_scheduler {
struct list_head ring_mirror_list;
spinlock_t job_list_lock;
int hang_limit;
atomic_t score;
bool ready;
atomic_t num_jobs;
bool ready;
bool free_guilty;
};