5 files changed, 17 insertions, 20 deletions

diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index a043ac3aae98..f32ac8c98f37 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -25,7 +25,6 @@ struct v3d_queue_state {
 
 	u64 fence_context;
 	u64 emit_seqno;
-	u64 finished_seqno;
 };
 
 struct v3d_dev {
@@ -85,6 +84,11 @@ struct v3d_dev {
 	 */
 	struct mutex reset_lock;
 
+	/* Lock taken when creating and pushing the GPU scheduler
+	 * jobs, to keep the sched-fence seqnos in order.
+	 */
+	struct mutex sched_lock;
+
 	struct {
 		u32 num_allocated;
 		u32 pages_allocated;
diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c
index 087d49c8cb12..bfe31a89668b 100644
--- a/drivers/gpu/drm/v3d/v3d_fence.c
+++ b/drivers/gpu/drm/v3d/v3d_fence.c
@@ -40,19 +40,14 @@ static bool v3d_fence_enable_signaling(struct dma_fence *fence)
 	return true;
 }
 
-static bool v3d_fence_signaled(struct dma_fence *fence)
-{
-	struct v3d_fence *f = to_v3d_fence(fence);
-	struct v3d_dev *v3d = to_v3d_dev(f->dev);
-
-	return v3d->queue[f->queue].finished_seqno >= f->seqno;
-}
-
 const struct dma_fence_ops v3d_fence_ops = {
 	.get_driver_name = v3d_fence_get_driver_name,
 	.get_timeline_name = v3d_fence_get_timeline_name,
 	.enable_signaling = v3d_fence_enable_signaling,
-	.signaled = v3d_fence_signaled,
+	/* Each of our fences gets signaled as complete by the IRQ
+	 * handler, so we rely on the core's tracking of signaling.
+	 */
+	.signaled = NULL,
 	.wait = dma_fence_default_wait,
 	.release = dma_fence_free,
 };
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index b513f9189caf..e1fcbb4cd0ae 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -550,6 +550,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto fail;
 
+	mutex_lock(&v3d->sched_lock);
 	if (exec->bin.start != exec->bin.end) {
 		ret = drm_sched_job_init(&exec->bin.base,
 					 &v3d->queue[V3D_BIN].sched,
@@ -576,6 +577,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	kref_get(&exec->refcount); /* put by scheduler job completion */
 	drm_sched_entity_push_job(&exec->render.base,
 				  &v3d_priv->sched_entity[V3D_RENDER]);
+	mutex_unlock(&v3d->sched_lock);
 
 	v3d_attach_object_fences(exec);
 
@@ -594,6 +596,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	return 0;
 
 fail_unreserve:
+	mutex_unlock(&v3d->sched_lock);
 	v3d_unlock_bo_reservations(dev, exec, &acquire_ctx);
 fail:
 	v3d_exec_put(exec);
@@ -615,6 +618,7 @@ v3d_gem_init(struct drm_device *dev)
 	spin_lock_init(&v3d->job_lock);
 	mutex_init(&v3d->bo_lock);
 	mutex_init(&v3d->reset_lock);
+	mutex_init(&v3d->sched_lock);
 
 	/* Note: We don't allocate address 0.  Various bits of HW
 	 * treat 0 as special, such as the occlusion query counters
@@ -650,17 +654,14 @@ void
 v3d_gem_destroy(struct drm_device *dev)
 {
 	struct v3d_dev *v3d = to_v3d_dev(dev);
-	enum v3d_queue q;
 
 	v3d_sched_fini(v3d);
 
 	/* Waiting for exec to finish would need to be done before
 	 * unregistering V3D.
 	 */
-	for (q = 0; q < V3D_MAX_QUEUES; q++) {
-		WARN_ON(v3d->queue[q].emit_seqno !=
-			v3d->queue[q].finished_seqno);
-	}
+	WARN_ON(v3d->bin_job);
+	WARN_ON(v3d->render_job);
 
 	drm_mm_takedown(&v3d->mm);
 
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index 77e1fa046c10..e07514eb11b5 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -87,15 +87,12 @@ v3d_irq(int irq, void *arg)
 	}
 
 	if (intsts & V3D_INT_FLDONE) {
-		v3d->queue[V3D_BIN].finished_seqno++;
 		dma_fence_signal(v3d->bin_job->bin.done_fence);
 		status = IRQ_HANDLED;
 	}
 
 	if (intsts & V3D_INT_FRDONE) {
-		v3d->queue[V3D_RENDER].finished_seqno++;
 		dma_fence_signal(v3d->render_job->render.done_fence);
-
 		status = IRQ_HANDLED;
 	}
 
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index b07bece9417d..808bc901f567 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -114,8 +114,8 @@ static struct dma_fence *v3d_job_run(struct drm_sched_job *sched_job)
 	v3d_invalidate_caches(v3d);
 
 	fence = v3d_fence_create(v3d, q);
-	if (!fence)
-		return fence;
+	if (IS_ERR(fence))
+		return NULL;
 
 	if (job->done_fence)
 		dma_fence_put(job->done_fence);