drm/sched: Reverse run-queue priority enumeration
authorLuben Tuikov <ltuikov89@gmail.com>
Thu, 23 Nov 2023 03:08:48 +0000 (22:08 -0500)
committerLuben Tuikov <ltuikov89@gmail.com>
Sat, 25 Nov 2023 04:03:53 +0000 (23:03 -0500)
commit38f922a563aac3148ac73e73689805917f034cb5
tree7e8ace1adc9c50e5aaaf60f1b207433894d9d217
parentfe375c74806dbd30b00ec038a80a5b7bf4653ab7
drm/sched: Reverse run-queue priority enumeration

Reverse run-queue priority enumeration such that the higest priority is now 0,
and for each consecutive integer the prioirty diminishes.

Run-queues correspond to priorities. To an external observer a scheduler
created with a single run-queue, and another created with
DRM_SCHED_PRIORITY_COUNT number of run-queues, should always schedule
sched->sched_rq[0] with the same "priority", as that index run-queue exists in
both schedulers, i.e. a scheduler with one run-queue or many. This patch makes
it so.

In other words, the "priority" of sched->sched_rq[n], n >= 0, is the same for
any scheduler created with any allowable number of run-queues (priorities), 0
to DRM_SCHED_PRIORITY_COUNT.

Cc: Rob Clark <robdclark@gmail.com>
Cc: Abhinav Kumar <quic_abhinavk@quicinc.com>
Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Cc: Danilo Krummrich <dakr@redhat.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: linux-arm-msm@vger.kernel.org
Cc: freedreno@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Luben Tuikov <ltuikov89@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231124052752.6915-6-ltuikov89@gmail.com
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
drivers/gpu/drm/msm/msm_gpu.h
drivers/gpu/drm/scheduler/sched_entity.c
drivers/gpu/drm/scheduler/sched_main.c
include/drm/gpu_scheduler.h