drm/v3d: Replace a global spinlock with a per-queue spinlock

Each V3D queue works independently and all the dependencies between the
jobs are handled through the DRM scheduler. Therefore, there is no need
to use one single lock for all queues. Using it, creates unnecessary
contention between different queues that can operate independently.

Replace the global spinlock with per-queue locks to improve parallelism
and reduce contention between different V3D queues (BIN, RENDER, TFU,
CSD). This allows independent queues to operate concurrently while
maintaining proper synchronization within each queue.

Signed-off-by: Maíra Canal <mcanal@igalia.com>

Author: mairacanal

drivers/gpu/drm/v3d/v3d_drv.h

@@ -61,6 +61,7 @@ struct v3d_queue_state {
 
 	/* Currently active job for this queue */
 	struct v3d_job *active_job;
+	spinlock_t queue_lock;
 };
 
 /* Performance monitor object. The perform lifetime is controlled by userspace
@@ -170,11 +171,6 @@ struct v3d_dev {
 
 	struct v3d_queue_state queue[V3D_MAX_QUEUES];
 
-	/* Spinlock used to synchronize the overflow memory
-	 * management against bin job submission.
-	 */
-	spinlock_t job_lock;
-
 	/* Used to track the active perfmon if any. */
 	struct v3d_perfmon *active_perfmon;
 
@@ -563,7 +559,7 @@ void v3d_get_stats(const struct v3d_stats *stats, u64 timestamp,
 
 /* v3d_fence.c */
 extern const struct dma_fence_ops v3d_fence_ops;
-struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue queue);
+struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue q);
 
 /* v3d_gem.c */
 int v3d_gem_init(struct drm_device *dev);

drivers/gpu/drm/v3d/v3d_fence.c

@@ -3,19 +3,20 @@
 
 #include "v3d_drv.h"
 
-struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue queue)
+struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue q)
 {
+	struct v3d_queue_state *queue = &v3d->queue[q];
 	struct v3d_fence *fence;
 
 	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
 	if (!fence)
 		return ERR_PTR(-ENOMEM);
 
 	fence->dev = &v3d->drm;
-	fence->queue = queue;
-	fence->seqno = ++v3d->queue[queue].emit_seqno;
-	dma_fence_init(&fence->base, &v3d_fence_ops, &v3d->job_lock,
-		       v3d->queue[queue].fence_context, fence->seqno);
+	fence->queue = q;
+	fence->seqno = ++queue->emit_seqno;
+	dma_fence_init(&fence->base, &v3d_fence_ops, &queue->queue_lock,
+		       queue->fence_context, fence->seqno);
 
 	return &fence->base;
 }

drivers/gpu/drm/v3d/v3d_gem.c

@@ -272,10 +272,11 @@ v3d_gem_init(struct drm_device *dev)
 		queue->fence_context = dma_fence_context_alloc(1);
 		memset(&queue->stats, 0, sizeof(queue->stats));
 		seqcount_init(&queue->stats.lock);
+
+		spin_lock_init(&queue->queue_lock);
 	}
 
 	spin_lock_init(&v3d->mm_lock);
-	spin_lock_init(&v3d->job_lock);
 	ret = drmm_mutex_init(dev, &v3d->bo_lock);
 	if (ret)
 		return ret;

drivers/gpu/drm/v3d/v3d_irq.c

@@ -62,17 +62,17 @@ v3d_overflow_mem_work(struct work_struct *work)
 	 * bin job got scheduled, that's fine.  We'll just give them
 	 * some binner pool anyway.
 	 */
-	spin_lock_irqsave(&v3d->job_lock, irqflags);
+	spin_lock_irqsave(&queue->queue_lock, irqflags);
 	bin_job = (struct v3d_bin_job *)queue->active_job;
 
 	if (!bin_job) {
-		spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+		spin_unlock_irqrestore(&queue->queue_lock, irqflags);
 		goto out;
 	}
 
 	drm_gem_object_get(obj);
 	list_add_tail(&bo->unref_head, &bin_job->render->unref_list);
-	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+	spin_unlock_irqrestore(&queue->queue_lock, irqflags);
 
 	v3d_mmu_flush_all(v3d);
 

drivers/gpu/drm/v3d/v3d_sched.c

@@ -226,27 +226,28 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
 {
 	struct v3d_bin_job *job = to_bin_job(sched_job);
 	struct v3d_dev *v3d = job->base.v3d;
+	struct v3d_queue_state *queue = &v3d->queue[V3D_BIN];
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 	unsigned long irqflags;
 
 	if (unlikely(job->base.base.s_fence->finished.error)) {
-		spin_lock_irqsave(&v3d->job_lock, irqflags);
-		v3d->queue[V3D_BIN].active_job = NULL;
-		spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+		spin_lock_irqsave(&queue->queue_lock, irqflags);
+		queue->active_job = NULL;
+		spin_unlock_irqrestore(&queue->queue_lock, irqflags);
 		return NULL;
 	}
 
 	/* Lock required around bin_job update vs
 	 * v3d_overflow_mem_work().
 	 */
-	spin_lock_irqsave(&v3d->job_lock, irqflags);
-	v3d->queue[V3D_BIN].active_job = &job->base;
+	spin_lock_irqsave(&queue->queue_lock, irqflags);
+	queue->active_job = &job->base;
 	/* Clear out the overflow allocation, so we don't
 	 * reuse the overflow attached to a previous job.
 	 */
 	V3D_CORE_WRITE(0, V3D_PTB_BPOS, 0);
-	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+	spin_unlock_irqrestore(&queue->queue_lock, irqflags);
 
 	v3d_invalidate_caches(v3d);