[RFC v2 2/2] drm/panthor: Create per queue priority workqueues

[Tvrtko Ursulin <tvrtko.ursulin@igalia.com>]

Split the single workqueue shared between the driver internal logic and
DRM scheduler use into separate ones, where the DRM scheduler one is
created per GPU priority level using the appropriate mapping to
workqueue priorities.

Low and medium GPU priority are served by a normal workqueue,
high is server by a WQ_HIGHPRI instance, while realtime GPU priority is
using the newly added WQ_RTPRI flag for lowest possible latency.

These workqueues are device global and for all three we set the maximum
concurrency to two in order to keep the GPU optimally fed with work.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Cc: Boris Brezillon <boris.brezillon@collabora.com>
Cc: Chia-I Wu <olv@google.com>
Cc: Liviu Dudau <liviu.dudau@arm.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Steven Price <steven.price@arm.com>
Cc: Tejun Heo <tj@kernel.org>
---
 drivers/gpu/drm/panthor/panthor_sched.c | 38 +++++++++++++++++++++----
 1 file changed, 33 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
index 2bee1c92fb9e..f01adc8c024c 100644
--- a/drivers/gpu/drm/panthor/panthor_sched.c
+++ b/drivers/gpu/drm/panthor/panthor_sched.c
@@ -152,11 +152,18 @@ struct panthor_scheduler {
 	 *
 	 * Used for the scheduler tick, group update or other kind of FW
 	 * event processing that can't be handled in the threaded interrupt
-	 * path. Also passed to the drm_gpu_scheduler instances embedded
-	 * in panthor_queue.
+	 * path.
 	 */
 	struct workqueue_struct *wq;
 
+	/**
+	 * @submit_wq: Per priority workqueues for the DRM scheduler
+	 *
+	 * Passed to the drm_gpu_scheduler instances embedded
+	 * in panthor_queue based on the queue priority.
+	 */
+	struct workqueue_struct *submit_wq[PANTHOR_CSG_PRIORITY_COUNT];
+
 	/**
 	 * @heap_alloc_wq: Workqueue used to schedule tiler_oom works.
 	 *
@@ -3488,7 +3495,6 @@ group_create_queue(struct panthor_group *group,
 {
 	struct drm_sched_init_args sched_args = {
 		.ops = &panthor_queue_sched_ops,
-		.submit_wq = group->ptdev->scheduler->wq,
 		/*
 		 * The credit limit argument tells us the total number of
 		 * instructions across all CS slots in the ringbuffer, with
@@ -3581,8 +3587,14 @@ group_create_queue(struct panthor_group *group,
 		goto err_free_queue;
 	}
 
+	if (group->priority >= ARRAY_SIZE(group->ptdev->scheduler->submit_wq) ||
+	    !group->ptdev->scheduler->submit_wq[group->priority]) {
+		ret = -EINVAL;
+		goto err_free_queue;
+	}
+
 	sched_args.name = queue->name;
-
+	sched_args.submit_wq = group->ptdev->scheduler->submit_wq[group->priority];
 	ret = drm_sched_init(&queue->scheduler, &sched_args);
 	if (ret)
 		goto err_free_queue;
@@ -4072,6 +4084,15 @@ static void panthor_sched_fini(struct drm_device *ddev, void *res)
 	if (!sched || !sched->csg_slot_count)
 		return;
 
+	if (sched->submit_wq[PANTHOR_CSG_PRIORITY_MEDIUM])
+		destroy_workqueue(sched->submit_wq[PANTHOR_CSG_PRIORITY_MEDIUM]);
+
+	if (sched->submit_wq[PANTHOR_CSG_PRIORITY_HIGH])
+		destroy_workqueue(sched->submit_wq[PANTHOR_CSG_PRIORITY_HIGH]);
+
+	if (sched->submit_wq[PANTHOR_CSG_PRIORITY_RT])
+		destroy_workqueue(sched->submit_wq[PANTHOR_CSG_PRIORITY_RT]);
+
 	if (sched->wq)
 		destroy_workqueue(sched->wq);
 
@@ -4173,7 +4194,14 @@ int panthor_sched_init(struct panthor_device *ptdev)
 	 */
 	sched->heap_alloc_wq = alloc_workqueue("panthor-heap-alloc", WQ_UNBOUND, 0);
 	sched->wq = alloc_workqueue("panthor-csf-sched", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
-	if (!sched->wq || !sched->heap_alloc_wq) {
+	sched->submit_wq[PANTHOR_CSG_PRIORITY_MEDIUM] = alloc_workqueue("panthor-drm", WQ_MEM_RECLAIM | WQ_UNBOUND, 2);
+	sched->submit_wq[PANTHOR_CSG_PRIORITY_LOW] = sched->submit_wq[PANTHOR_CSG_PRIORITY_MEDIUM];
+	sched->submit_wq[PANTHOR_CSG_PRIORITY_HIGH] = alloc_workqueue("panthor-drm-high", WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_UNBOUND, 2);
+	sched->submit_wq[PANTHOR_CSG_PRIORITY_RT] = alloc_workqueue("panthor-drm-rt", WQ_RTPRI | WQ_MEM_RECLAIM | WQ_UNBOUND, 2);
+	if (!sched->wq || !sched->heap_alloc_wq ||
+	    !sched->submit_wq[PANTHOR_CSG_PRIORITY_MEDIUM] ||
+	    !sched->submit_wq[PANTHOR_CSG_PRIORITY_HIGH] ||
+	    !sched->submit_wq[PANTHOR_CSG_PRIORITY_RT]) {
 		panthor_sched_fini(&ptdev->base, sched);
 		drm_err(&ptdev->base, "Failed to allocate the workqueues");
 		return -ENOMEM;
-- 
2.54.0