[RFC PATCH 7/9] accel/rocket: add RK3576 NPU (RKNN) support

[Jiaxing Hu <gahing@gahingwoo.com>]

Add RK3576 support to the rocket DRM accelerator driver (used with the
Mesa Teflon TFLite delegate).

  - match rockchip,rk3576-rknn-core; iterate its nodes at probe
  - add named clock IDs (aclk/hclk/npu/pclk) and the CBUF clock domain
    (ACLK/HCLK_RKNN_CBUF); the CNA fills the CBUF and CORE reads from it,
    so the compute path stalls if those clocks are not held for a job
  - guard rocket_job_timedout() MMIO behind pm_runtime_active()
  - hrtimer completion poll: OP_EN never clears on RK3576 (unlike
    RK3588), so poll INTERRUPT_RAW_STATUS PC_DONE bits instead
  - map the DPU (0x4000) and DPU_RDMA (0x5000) blocks and pre-arm them
  - attach both NPU power domains (PD_NPU0 + PD_NPU1): the CBUF->CMAC
    read path is only fully powered with NPU1 up

Tested on a Radxa ROCK 4D: the NPU probes, powers on, brings up its
IOMMUs and runs submitted jobs to completion. Full multi-layer inference
is not yet correct on this SoC (only the first operation per power
session produces valid output); see the cover letter.

Signed-off-by: Jiaxing Hu <gahing@gahingwoo.com>
---
 drivers/accel/rocket/rocket_core.c   |  43 +++++++-
 drivers/accel/rocket/rocket_core.h   |  22 +++-
 drivers/accel/rocket/rocket_device.c |   4 +
 drivers/accel/rocket/rocket_drv.c    |   1 +
 drivers/accel/rocket/rocket_job.c    | 154 +++++++++++++++++++++------
 5 files changed, 187 insertions(+), 37 deletions(-)

diff --git a/drivers/accel/rocket/rocket_core.c b/drivers/accel/rocket/rocket_core.c
index b3b2fa9ba..7b0c48e4d 100644
--- a/drivers/accel/rocket/rocket_core.c
+++ b/drivers/accel/rocket/rocket_core.c
@@ -8,6 +8,7 @@
 #include <linux/err.h>
 #include <linux/iommu.h>
 #include <linux/platform_device.h>
+#include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
@@ -22,12 +23,23 @@ int rocket_core_init(struct rocket_core *core)
 	int err = 0;
 
 	core->resets[0].id = "srst_a";
-	core->resets[1].id = "srst_h";
 	err = devm_reset_control_bulk_get_exclusive(&pdev->dev, ARRAY_SIZE(core->resets),
 						    core->resets);
 	if (err)
 		return dev_err_probe(dev, err, "failed to get resets for core %d\n", core->index);
 
+	core->clks[0].id = "aclk";
+	core->clks[1].id = "hclk";
+	core->clks[2].id = "npu";
+	core->clks[3].id = "pclk";
+	/*
+	 * RK3576: the CBUF (convolution buffer) has its own clock domain. The CNA
+	 * fills the CBUF and CORE reads from it; without these the compute path
+	 * stalls after loading one slice (RDMA, which bypasses the CBUF, still
+	 * runs). The vendor keeps all NPU clocks on whenever powered.
+	 */
+	core->clks[4].id = "aclk_cbuf";
+	core->clks[5].id = "hclk_cbuf";
 	err = devm_clk_bulk_get(dev, ARRAY_SIZE(core->clks), core->clks);
 	if (err)
 		return dev_err_probe(dev, err, "failed to get clocks for core %d\n", core->index);
@@ -50,6 +62,18 @@ int rocket_core_init(struct rocket_core *core)
 		return PTR_ERR(core->core_iomem);
 	}
 
+	core->dpu_iomem = devm_platform_ioremap_resource_byname(pdev, "dpu");
+	if (IS_ERR(core->dpu_iomem)) {
+		dev_warn(dev, "no DPU registers; DPU S_POINTER won't be pre-armed\n");
+		core->dpu_iomem = NULL;
+	}
+
+	core->dpu_rdma_iomem = devm_platform_ioremap_resource_byname(pdev, "dpu_rdma");
+	if (IS_ERR(core->dpu_rdma_iomem)) {
+		dev_warn(dev, "no DPU_RDMA registers; DPU_RDMA S_POINTER won't be pre-armed\n");
+		core->dpu_rdma_iomem = NULL;
+	}
+
 	dma_set_max_seg_size(dev, UINT_MAX);
 
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40));
@@ -65,6 +89,23 @@ int rocket_core_init(struct rocket_core *core)
 		return err;
 	}
 
+	/*
+	 * RK3576: the NPU spans TWO power domains (PD_NPU0 + PD_NPU1). The vendor
+	 * powers BOTH from its single NPU node even when computing on one core --
+	 * the CBUF->CMAC read path only works fully with NPU1 powered. The board DT
+	 * lists both power-domains on rknn_core_0; a multi-PD device skips the
+	 * driver-core single-PD auto-attach, so attach the list explicitly. With
+	 * one PD in DT this is a no-op (returns 1) and behaves as before.
+	 */
+	{
+		struct dev_pm_domain_list *pd_list;
+
+		err = devm_pm_domain_attach_list(dev, NULL, &pd_list);
+		if (err < 0)
+			return dev_err_probe(dev, err,
+					     "failed to attach NPU power domains\n");
+	}
+
 	pm_runtime_use_autosuspend(dev);
 
 	/*
diff --git a/drivers/accel/rocket/rocket_core.h b/drivers/accel/rocket/rocket_core.h
index f6d738285..e959b26dd 100644
--- a/drivers/accel/rocket/rocket_core.h
+++ b/drivers/accel/rocket/rocket_core.h
@@ -6,6 +6,7 @@
 
 #include <drm/gpu_scheduler.h>
 #include <linux/clk.h>
+#include <linux/hrtimer.h>
 #include <linux/io.h>
 #include <linux/mutex_types.h>
 #include <linux/reset.h>
@@ -27,6 +28,16 @@
 #define rocket_core_writel(core, reg, value) \
 	writel(value, (core)->core_iomem + (REG_CORE_##reg) - REG_CORE_S_STATUS)
 
+#define rocket_dpu_readl(core, reg) \
+	readl((core)->dpu_iomem + (REG_DPU_##reg) - REG_DPU_S_STATUS)
+#define rocket_dpu_writel(core, reg, value) \
+	writel(value, (core)->dpu_iomem + (REG_DPU_##reg) - REG_DPU_S_STATUS)
+
+#define rocket_dpu_rdma_readl(core, reg) \
+	readl((core)->dpu_rdma_iomem + (REG_DPU_RDMA_##reg) - REG_DPU_RDMA_RDMA_S_STATUS)
+#define rocket_dpu_rdma_writel(core, reg, value) \
+	writel(value, (core)->dpu_rdma_iomem + (REG_DPU_RDMA_##reg) - REG_DPU_RDMA_RDMA_S_STATUS)
+
 struct rocket_core {
 	struct device *dev;
 	struct rocket_device *rdev;
@@ -36,8 +47,10 @@ struct rocket_core {
 	void __iomem *pc_iomem;
 	void __iomem *cna_iomem;
 	void __iomem *core_iomem;
-	struct clk_bulk_data clks[4];
-	struct reset_control_bulk_data resets[2];
+	void __iomem *dpu_iomem;
+	void __iomem *dpu_rdma_iomem;
+	struct clk_bulk_data clks[6];
+	struct reset_control_bulk_data resets[1];
 
 	struct iommu_group *iommu_group;
 
@@ -52,6 +65,11 @@ struct rocket_core {
 		atomic_t pending;
 	} reset;
 
+	/* RK3576 has no completion IRQ; poll for PC_DONE via hrtimer. */
+	struct hrtimer poll_timer;
+	struct work_struct poll_work;
+	atomic_t poll_active;
+
 	struct drm_gpu_scheduler sched;
 	u64 fence_context;
 	u64 emit_seqno;
diff --git a/drivers/accel/rocket/rocket_device.c b/drivers/accel/rocket/rocket_device.c
index 46e6ee1e7..bfb00f967 100644
--- a/drivers/accel/rocket/rocket_device.c
+++ b/drivers/accel/rocket/rocket_device.c
@@ -31,6 +31,10 @@ struct rocket_device *rocket_device_init(struct platform_device *pdev,
 		if (of_device_is_available(core_node))
 			num_cores++;
 
+	for_each_compatible_node(core_node, NULL, "rockchip,rk3576-rknn-core")
+		if (of_device_is_available(core_node))
+			num_cores++;
+
 	rdev->cores = devm_kcalloc(dev, num_cores, sizeof(*rdev->cores), GFP_KERNEL);
 	if (!rdev->cores)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/accel/rocket/rocket_drv.c b/drivers/accel/rocket/rocket_drv.c
index 8bbbce594..8f6a02d50 100644
--- a/drivers/accel/rocket/rocket_drv.c
+++ b/drivers/accel/rocket/rocket_drv.c
@@ -215,6 +215,7 @@ static void rocket_remove(struct platform_device *pdev)
 
 static const struct of_device_id dt_match[] = {
 	{ .compatible = "rockchip,rk3588-rknn-core" },
+	{ .compatible = "rockchip,rk3576-rknn-core" },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dt_match);
diff --git a/drivers/accel/rocket/rocket_job.c b/drivers/accel/rocket/rocket_job.c
index 2f1861f96..94461bf71 100644
--- a/drivers/accel/rocket/rocket_job.c
+++ b/drivers/accel/rocket/rocket_job.c
@@ -7,6 +7,7 @@
 #include <drm/drm_file.h>
 #include <drm/drm_gem.h>
 #include <drm/rocket_accel.h>
+#include <linux/hrtimer.h>
 #include <linux/interrupt.h>
 #include <linux/iommu.h>
 #include <linux/platform_device.h>
@@ -20,6 +21,16 @@
 
 #define JOB_TIMEOUT_MS 500
 
+/*
+ * RK3576: INTERRUPT_MASK bits 28-29 are read-only (hardware rejects the write),
+ * so the PC_DONE completion signal cannot be routed to the GIC via the normal
+ * interrupt-mask path.  We poll OPERATION_ENABLE every RK3576_POLL_INTERVAL_NS
+ * instead of waiting for a completion IRQ.
+ */
+#define PC_INTERRUPT_MASK_RK3576_PC_DONE_0  0x10000000u
+#define PC_INTERRUPT_MASK_RK3576_PC_DONE_1  0x20000000u
+#define RK3576_POLL_INTERVAL_NS  1000000LL  /* 1 ms */
+
 static struct rocket_job *
 to_rocket_job(struct drm_sched_job *sched_job)
 {
@@ -137,8 +148,21 @@ static void rocket_job_hw_submit(struct rocket_core *core, struct rocket_job *jo
 	rocket_pc_writel(core, REGISTER_AMOUNTS,
 			 PC_REGISTER_AMOUNTS_PC_DATA_AMOUNT((task->regcmd_count + 1) / 2 - 1));
 
-	rocket_pc_writel(core, INTERRUPT_MASK, PC_INTERRUPT_MASK_DPU_0 | PC_INTERRUPT_MASK_DPU_1);
-	rocket_pc_writel(core, INTERRUPT_CLEAR, PC_INTERRUPT_CLEAR_DPU_0 | PC_INTERRUPT_CLEAR_DPU_1);
+	/* Enable DMA-error interrupts; PC_DONE (bits 28-29) is polled, see above. */
+	rocket_pc_writel(core, INTERRUPT_MASK,
+			 PC_INTERRUPT_MASK_DPU_0    | PC_INTERRUPT_MASK_DPU_1    |
+			 PC_INTERRUPT_MASK_CORE_0   | PC_INTERRUPT_MASK_CORE_1   |
+			 PC_INTERRUPT_MASK_PPU_0    | PC_INTERRUPT_MASK_PPU_1    |
+			 PC_INTERRUPT_MASK_CNA_CSC_0 | PC_INTERRUPT_MASK_CNA_CSC_1 |
+			 PC_INTERRUPT_MASK_DMA_READ_ERROR |
+			 PC_INTERRUPT_MASK_DMA_WRITE_ERROR);
+	rocket_pc_writel(core, INTERRUPT_CLEAR,
+			 PC_INTERRUPT_CLEAR_DPU_0    | PC_INTERRUPT_CLEAR_DPU_1    |
+			 PC_INTERRUPT_CLEAR_CORE_0   | PC_INTERRUPT_CLEAR_CORE_1   |
+			 PC_INTERRUPT_CLEAR_PPU_0    | PC_INTERRUPT_CLEAR_PPU_1    |
+			 PC_INTERRUPT_CLEAR_CNA_CSC_0 | PC_INTERRUPT_CLEAR_CNA_CSC_1 |
+			 PC_INTERRUPT_MASK_RK3576_PC_DONE_0 |
+			 PC_INTERRUPT_MASK_RK3576_PC_DONE_1);
 
 	rocket_pc_writel(core, TASK_CON, PC_TASK_CON_RESERVED_0(1) |
 					 PC_TASK_CON_TASK_COUNT_CLEAR(1) |
@@ -149,7 +173,9 @@ static void rocket_job_hw_submit(struct rocket_core *core, struct rocket_job *jo
 
 	rocket_pc_writel(core, OPERATION_ENABLE, PC_OPERATION_ENABLE_OP_EN(1));
 
-	dev_dbg(core->dev, "Submitted regcmd at 0x%llx to core %d", task->regcmd, core->index);
+	atomic_set(&core->poll_active, 1);
+	hrtimer_start(&core->poll_timer, ns_to_ktime(RK3576_POLL_INTERVAL_NS),
+		      HRTIMER_MODE_REL);
 }
 
 static int rocket_acquire_object_fences(struct drm_gem_object **bos,
@@ -326,56 +352,99 @@ static struct dma_fence *rocket_job_run(struct drm_sched_job *sched_job)
 	return fence;
 }
 
+static void rocket_job_handle_irq(struct rocket_core *core);
+
+static enum hrtimer_restart rocket_poll_timer_fn(struct hrtimer *timer)
+{
+	struct rocket_core *core = container_of(timer, struct rocket_core, poll_timer);
+
+	if (!atomic_read(&core->poll_active))
+		return HRTIMER_NORESTART;
+
+	/*
+	 * On RK3576, OPERATION_ENABLE is not cleared by hardware on completion;
+	 * check INTERRUPT_RAW_STATUS bits 28-29 (PC_DONE_0/1) instead.
+	 */
+	if (rocket_pc_readl(core, OPERATION_ENABLE) == 0 ||
+	    (rocket_pc_readl(core, INTERRUPT_RAW_STATUS) &
+	     (PC_INTERRUPT_MASK_RK3576_PC_DONE_0 |
+	      PC_INTERRUPT_MASK_RK3576_PC_DONE_1))) {
+		atomic_set(&core->poll_active, 0);
+		schedule_work(&core->poll_work);
+		return HRTIMER_NORESTART;
+	}
+
+	hrtimer_forward_now(timer, ns_to_ktime(RK3576_POLL_INTERVAL_NS));
+	return HRTIMER_RESTART;
+}
+
+static void rocket_poll_work_fn(struct work_struct *work)
+{
+	struct rocket_core *core = container_of(work, struct rocket_core, poll_work);
+
+	rocket_job_handle_irq(core);
+}
+
 static void rocket_job_handle_irq(struct rocket_core *core)
 {
+	struct rocket_job *job;
+
+	/* Stop the completion poll — we're handling it now. */
+	atomic_set(&core->poll_active, 0);
+	hrtimer_cancel(&core->poll_timer);
+
 	pm_runtime_mark_last_busy(core->dev);
 
 	rocket_pc_writel(core, OPERATION_ENABLE, 0x0);
-	rocket_pc_writel(core, INTERRUPT_CLEAR, 0x1ffff);
-
-	scoped_guard(mutex, &core->job_lock)
-		if (core->in_flight_job) {
-			if (core->in_flight_job->next_task_idx < core->in_flight_job->task_count) {
-				rocket_job_hw_submit(core, core->in_flight_job);
-				return;
-			}
-
-			iommu_detach_group(NULL, iommu_group_get(core->dev));
-			dma_fence_signal(core->in_flight_job->done_fence);
-			pm_runtime_put_autosuspend(core->dev);
-			core->in_flight_job = NULL;
+	rocket_pc_writel(core, INTERRUPT_CLEAR,
+			 0x1ffff |
+			 PC_INTERRUPT_MASK_RK3576_PC_DONE_0 |
+			 PC_INTERRUPT_MASK_RK3576_PC_DONE_1);
+
+	scoped_guard(mutex, &core->job_lock) {
+		job = core->in_flight_job;
+		if (!job)
+			return;
+
+		if (job->next_task_idx < job->task_count) {
+			rocket_job_hw_submit(core, job);
+			return;
 		}
+
+		iommu_detach_group(job->domain->domain, core->iommu_group);
+		dma_fence_signal(job->done_fence);
+		pm_runtime_put_autosuspend(core->dev);
+		core->in_flight_job = NULL;
+	}
 }
 
 static void
 rocket_reset(struct rocket_core *core, struct drm_sched_job *bad)
 {
+	struct rocket_job *job;
+
 	if (!atomic_read(&core->reset.pending))
 		return;
 
+	atomic_set(&core->poll_active, 0);
+	hrtimer_cancel(&core->poll_timer);
+	cancel_work(&core->poll_work);
+
 	drm_sched_stop(&core->sched, bad);
 
-	/*
-	 * Remaining interrupts have been handled, but we might still have
-	 * stuck jobs. Let's make sure the PM counters stay balanced by
-	 * manually calling pm_runtime_put_noidle().
-	 */
 	scoped_guard(mutex, &core->job_lock) {
-		if (core->in_flight_job)
+		job = core->in_flight_job;
+		if (job) {
 			pm_runtime_put_noidle(core->dev);
-
-		iommu_detach_group(NULL, core->iommu_group);
-
-		core->in_flight_job = NULL;
+			iommu_detach_group(job->domain->domain, core->iommu_group);
+			core->in_flight_job = NULL;
+		}
 	}
 
-	/* Proceed with reset now. */
 	rocket_core_reset(core);
 
-	/* NPU has been reset, we can clear the reset pending bit. */
 	atomic_set(&core->reset.pending, 0);
 
-	/* Restart the scheduler */
 	drm_sched_start(&core->sched, 0);
 }
 
@@ -385,7 +454,14 @@ static enum drm_gpu_sched_stat rocket_job_timedout(struct drm_sched_job *sched_j
 	struct rocket_device *rdev = job->rdev;
 	struct rocket_core *core = sched_to_core(rdev, sched_job->sched);
 
-	dev_err(core->dev, "NPU job timed out");
+	if (pm_runtime_active(core->dev))
+		dev_err(core->dev,
+			"NPU job timed out: RAW_STATUS=0x%08x MASK=0x%08x OP_EN=0x%08x\n",
+			rocket_pc_readl(core, INTERRUPT_RAW_STATUS),
+			rocket_pc_readl(core, INTERRUPT_MASK),
+			rocket_pc_readl(core, OPERATION_ENABLE));
+	else
+		dev_err(core->dev, "NPU job timed out (device not active)\n");
 
 	atomic_set(&core->reset.pending, 1);
 	rocket_reset(core, sched_job);
@@ -420,14 +496,16 @@ static irqreturn_t rocket_job_irq_handler(int irq, void *data)
 {
 	struct rocket_core *core = data;
 	u32 raw_status = rocket_pc_readl(core, INTERRUPT_RAW_STATUS);
+	/* Only bits 0-13 (DMA errors) can raise this IRQ; PC_DONE is polled. */
+	u32 active = raw_status & 0x3fff;
+
+	if (!active)
+		return IRQ_NONE;
 
 	WARN_ON(raw_status & PC_INTERRUPT_RAW_STATUS_DMA_READ_ERROR);
 	WARN_ON(raw_status & PC_INTERRUPT_RAW_STATUS_DMA_WRITE_ERROR);
 
-	if (!(raw_status & PC_INTERRUPT_RAW_STATUS_DPU_0 ||
-	      raw_status & PC_INTERRUPT_RAW_STATUS_DPU_1))
-		return IRQ_NONE;
-
+	rocket_pc_writel(core, INTERRUPT_CLEAR, active);
 	rocket_pc_writel(core, INTERRUPT_MASK, 0x0);
 
 	return IRQ_WAKE_THREAD;
@@ -445,6 +523,10 @@ int rocket_job_init(struct rocket_core *core)
 	int ret;
 
 	INIT_WORK(&core->reset.work, rocket_reset_work);
+	INIT_WORK(&core->poll_work, rocket_poll_work_fn);
+	hrtimer_setup(&core->poll_timer, rocket_poll_timer_fn, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
+	atomic_set(&core->poll_active, 0);
 	spin_lock_init(&core->fence_lock);
 	mutex_init(&core->job_lock);
 
@@ -486,6 +568,10 @@ int rocket_job_init(struct rocket_core *core)
 
 void rocket_job_fini(struct rocket_core *core)
 {
+	atomic_set(&core->poll_active, 0);
+	hrtimer_cancel(&core->poll_timer);
+	cancel_work_sync(&core->poll_work);
+
 	drm_sched_fini(&core->sched);
 
 	cancel_work_sync(&core->reset.work);
-- 
2.43.0