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

@@ -325,7 +325,7 @@ void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
 	int i;
 
 	/* Signal all jobs not yet scheduled */
-	for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_LOW; i--) {
+	for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++) {
 		struct drm_sched_rq *rq = sched->sched_rq[i];
 		spin_lock(&rq->lock);
 		list_for_each_entry(s_entity, &rq->entities, list) {

drivers/gpu/drm/msm/msm_gpu.h

@@ -347,7 +347,7 @@ struct msm_gpu_perfcntr {
  * DRM_SCHED_PRIORITY_KERNEL priority level is treated specially in some
  * cases, so we don't use it (no need for kernel generated jobs).
  */
-#define NR_SCHED_PRIORITIES (1 + DRM_SCHED_PRIORITY_HIGH - DRM_SCHED_PRIORITY_LOW)
+#define NR_SCHED_PRIORITIES (1 + DRM_SCHED_PRIORITY_LOW - DRM_SCHED_PRIORITY_HIGH)
 
 /**
  * struct msm_file_private - per-drm_file context

drivers/gpu/drm/scheduler/sched_entity.c

@@ -82,13 +82,14 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
 		pr_warn("%s: called with uninitialized scheduler\n", __func__);
 	} else if (num_sched_list) {
 		/* The "priority" of an entity cannot exceed the number of run-queues of a
-		 * scheduler. Protect against num_rqs being 0, by converting to signed.
+		 * scheduler. Protect against num_rqs being 0, by converting to signed. Choose
+		 * the lowest priority available.
 		 */
 		if (entity->priority >= sched_list[0]->num_rqs) {
 			drm_err(sched_list[0], "entity with out-of-bounds priority:%u num_rqs:%u\n",
 				entity->priority, sched_list[0]->num_rqs);
 			entity->priority = max_t(s32, (s32) sched_list[0]->num_rqs - 1,
-						 (s32) DRM_SCHED_PRIORITY_LOW);
+						 (s32) DRM_SCHED_PRIORITY_KERNEL);
 		}
 		entity->rq = sched_list[0]->sched_rq[entity->priority];
 	}

drivers/gpu/drm/scheduler/sched_main.c

@@ -1051,8 +1051,9 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 	struct drm_sched_entity *entity;
 	int i;
 
-	/* Kernel run queue has higher priority than normal run queue*/
+	/* Start with the highest priority.
-	for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_LOW; i--) {
+	 */
+	for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++) {
 		entity = drm_sched_policy == DRM_SCHED_POLICY_FIFO ?
 			drm_sched_rq_select_entity_fifo(sched, sched->sched_rq[i]) :
 			drm_sched_rq_select_entity_rr(sched, sched->sched_rq[i]);
@@ -1291,7 +1292,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	if (!sched->sched_rq)
 		goto Out_free;
 	sched->num_rqs = num_rqs;
-	for (i = DRM_SCHED_PRIORITY_LOW; i < sched->num_rqs; i++) {
+	for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++) {
 		sched->sched_rq[i] = kzalloc(sizeof(*sched->sched_rq[i]), GFP_KERNEL);
 		if (!sched->sched_rq[i])
 			goto Out_unroll;
@@ -1312,7 +1313,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	sched->ready = true;
 	return 0;
 Out_unroll:
-	for (--i ; i >= DRM_SCHED_PRIORITY_LOW; i--)
+	for (--i ; i >= DRM_SCHED_PRIORITY_KERNEL; i--)
 		kfree(sched->sched_rq[i]);
 Out_free:
 	kfree(sched->sched_rq);
@@ -1338,7 +1339,7 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched)
 
 	drm_sched_wqueue_stop(sched);
 
-	for (i = sched->num_rqs - 1; i >= DRM_SCHED_PRIORITY_LOW; i--) {
+	for (i = DRM_SCHED_PRIORITY_KERNEL; i < sched->num_rqs; i++) {
 		struct drm_sched_rq *rq = sched->sched_rq[i];
 
 		spin_lock(&rq->lock);
@@ -1390,9 +1391,7 @@ void drm_sched_increase_karma(struct drm_sched_job *bad)
 	if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
 		atomic_inc(&bad->karma);
 
-		for (i = DRM_SCHED_PRIORITY_LOW;
+		for (i = DRM_SCHED_PRIORITY_HIGH; i < sched->num_rqs; i++) {
-		     i < min_t(typeof(sched->num_rqs), sched->num_rqs, DRM_SCHED_PRIORITY_KERNEL);
-		     i++) {
 			struct drm_sched_rq *rq = sched->sched_rq[i];
 
 			spin_lock(&rq->lock);

include/drm/gpu_scheduler.h

@@ -63,10 +63,10 @@ struct drm_file;
  * to an array, and as such should start at 0.
  */
 enum drm_sched_priority {
-	DRM_SCHED_PRIORITY_LOW,
-	DRM_SCHED_PRIORITY_NORMAL,
-	DRM_SCHED_PRIORITY_HIGH,
 	DRM_SCHED_PRIORITY_KERNEL,
+	DRM_SCHED_PRIORITY_HIGH,
+	DRM_SCHED_PRIORITY_NORMAL,
+	DRM_SCHED_PRIORITY_LOW,
 
 	DRM_SCHED_PRIORITY_COUNT
 };