[PATCH v2 17/17] media: rockchip: rga: schedule jobs to multiple cores

[Sven Püschel]

Schedule jobs to multiple cores to utilize all RGA cores. To avoid race
conditions when selecting the next free core a dedicated spinlock is added.

Note that this doesn't increase the max frame rate of a single
stream, as a context will wait for the job to finish before starting
the next device_run call.

Signed-off-by: Sven Püschel <s.pueschel at pengutronix.de>

---
v2
- Set core->curr to null first in pm_runtime_resume_and_get error path
  (https://sashiko.dev/#/patchset/20260606-spu-rga3multicore-v1-0-3ec2b15675f7%40pengutronix.de?part=15)
- Also protect adding/removing cores with the spinlock in bind/unbind
---
 drivers/media/platform/rockchip/rga/rga.c | 30 +++++++++++++++++++++++++++---
 drivers/media/platform/rockchip/rga/rga.h |  1 +
 2 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c
index b2eeae0a61771..6294825eaacfd 100644
--- a/drivers/media/platform/rockchip/rga/rga.c
+++ b/drivers/media/platform/rockchip/rga/rga.c
@@ -38,13 +38,29 @@ static void device_run(void *prv)
 {
 	struct rga_ctx *ctx = prv;
 	struct rockchip_rga *rga = ctx->rga;
-	struct rga_core *core = rga->cores[0];
+	struct rga_core *core = NULL;
 	struct vb2_v4l2_buffer *src, *dst;
 	unsigned long flags;
 	int ret;
+	unsigned int i;
+
+	spin_lock_irqsave(&rga->cores_lock, flags);
+	for (i = 0; i < rga->num_cores; i++) {
+		if (!rga->cores[i]->curr) {
+			core = rga->cores[i];
+			core->curr = ctx;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&rga->cores_lock, flags);
+
+	WARN_ONCE(!core, "No free core although max parallel jobs matches the core count!\n");
+	if (!core)
+		return;
 
 	ret = pm_runtime_resume_and_get(core->dev);
 	if (ret < 0) {
+		core->curr = NULL;
 		v4l2_m2m_buf_done_and_job_finish(rga->m2m_dev, ctx->fh.m2m_ctx,
 						 VB2_BUF_STATE_ERROR);
 		return;
@@ -58,8 +74,6 @@ static void device_run(void *prv)
 	}
 	spin_unlock_irqrestore(&rga->ctrl_lock, flags);
 
-	core->curr = ctx;
-
 	src = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
 	src->sequence = ctx->osequence++;
 
@@ -748,6 +762,7 @@ static int rga_core_bind(struct device *dev, struct device *master, void *data)
 	struct rockchip_rga *rga = data;
 	struct rga_core *core = dev_get_drvdata(dev);
 	struct rockchip_rga_version version;
+	unsigned long flags;
 	int ret = 0;
 
 	core->rga = rga;
@@ -785,7 +800,9 @@ static int rga_core_bind(struct device *dev, struct device *master, void *data)
 
 	pm_runtime_put(core->dev);
 
+	spin_lock_irqsave(&rga->cores_lock, flags);
 	rga->cores[rga->num_cores++] = core;
+	spin_unlock_irqrestore(&rga->cores_lock, flags);
 
 	return 0;
 }
@@ -796,6 +813,7 @@ static void rga_core_unbind(struct device *dev, struct device *master,
 	struct rga_core *core = dev_get_drvdata(dev);
 	struct rockchip_rga *rga = core->rga;
 	u8 i;
+	unsigned long flags;
 
 	/* Remove our core from the list */
 	for (i = 0; i < rga->num_cores; i++) {
@@ -810,8 +828,10 @@ static void rga_core_unbind(struct device *dev, struct device *master,
 				iommu_detach_device(domain, core->dev);
 		}
 
+		spin_lock_irqsave(&rga->cores_lock, flags);
 		rga->cores[i] = rga->cores[rga->num_cores - 1];
 		rga->num_cores--;
+		spin_unlock_irqrestore(&rga->cores_lock, flags);
 		break;
 	}
 
@@ -977,6 +997,9 @@ static int rga_bind(struct device *dev)
 		goto rel_m2m;
 	}
 
+	/* after binding all cores num_cores has the proper number of cores */
+	v4l2_m2m_set_max_parallel_jobs(rga->m2m_dev, rga->num_cores);
+
 	v4l2_info(&rga->v4l2_dev, "Registered %s as /dev/%s\n",
 		  vfd->name, video_device_node_name(vfd));
 
@@ -1047,6 +1070,7 @@ static int rga_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, -ENODEV, "failed to get match data\n");
 
 	spin_lock_init(&rga->ctrl_lock);
+	spin_lock_init(&rga->cores_lock);
 	mutex_init(&rga->mutex);
 
 	dev_set_drvdata(dev, rga);
diff --git a/drivers/media/platform/rockchip/rga/rga.h b/drivers/media/platform/rockchip/rga/rga.h
index 522021c3e0249..b046083244bf6 100644
--- a/drivers/media/platform/rockchip/rga/rga.h
+++ b/drivers/media/platform/rockchip/rga/rga.h
@@ -86,6 +86,7 @@ struct rockchip_rga {
 	struct mutex mutex;
 	/* ctrl parm lock */
 	spinlock_t ctrl_lock;
+	spinlock_t cores_lock;
 
 	const struct rga_hw *hw;
 

-- 
2.55.0