accel/rocket: Add a new driver for Rockchip's NPU

This initial version supports the NPU as shipped in the RK3588 SoC and
described in the first part of its TRM, in Chapter 36.

This NPU contains 3 independent cores that the driver can submit jobs
to.

This commit adds just hardware initialization and power management.

v2:
- Split cores and IOMMUs as independent devices (Sebastian Reichel)
- Add some documentation (Jeffrey Hugo)
- Be more explicit in the Kconfig documentation (Jeffrey Hugo)
- Remove resets, as these haven't been found useful so far (Zenghui Yu)
- Repack structs (Jeffrey Hugo)
- Use DEFINE_DRM_ACCEL_FOPS (Jeffrey Hugo)
- Use devm_drm_dev_alloc (Jeffrey Hugo)
- Use probe log helper (Jeffrey Hugo)
- Introduce UABI header in a later patch (Jeffrey Hugo)

v3:
- Adapt to a split of the register block in the DT bindings (Nicolas
  Frattaroli)
- Move registers header to its own commit (Thomas Zimmermann)
- Misc. cleanups (Thomas Zimmermann and Jeff Hugo)
- Make use of GPL-2.0-only for the copyright notice (Jeff Hugo)
- PM improvements (Nicolas Frattaroli)

v4:
- Use bulk clk API (Krzysztof Kozlowski)

v6:
- Remove mention to NVDLA, as the hardware is only incidentally related
  (Kever Yang)
- Use calloc instead of GFP_ZERO (Jeff Hugo)
- Explicitly include linux/container_of.h (Jeff Hugo)
- pclk and npu clocks are now needed by all cores (Rob Herring)

v7:
- Assign its own IOMMU domain to each client, for isolation (Daniel
  Stone and Robin Murphy)

v8:
- Kconfig: fix depends to be more explicit about Rockchip, and remove
  superfluous selects (Robin Murphy)
- Use reset lines to reset the cores (Robin Murphy)
- Reference count the module
- Set dma_set_max_seg_size
- Correctly acquire a reference to the IOMMU (Robin Murphy)
- Remove notion of top core (Robin Murphy)

Reviewed-by: Robert Foss <rfoss@kernel.org>
Tested-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com>
Signed-off-by: Tomeu Vizoso <tomeu@tomeuvizoso.net>
Signed-off-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250721-6-10-rocket-v9-2-77ebd484941e@tomeuvizoso.net

1 files changed, 261 insertions, 0 deletions

diff --git a/drivers/accel/rocket/rocket_drv.c b/drivers/accel/rocket/rocket_drv.c
new file mode 100644
index 000000000000..a5df94f6b125
--- /dev/null
+++ b/drivers/accel/rocket/rocket_drv.c
@@ -0,0 +1,261 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#include <drm/drm_accel.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_ioctl.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/iommu.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#include "rocket_drv.h"
+
+/*
+ * Facade device, used to expose a single DRM device to userspace, that
+ * schedules jobs to any RKNN cores in the system.
+ */
+static struct platform_device *drm_dev;
+static struct rocket_device *rdev;
+
+static void
+rocket_iommu_domain_destroy(struct kref *kref)
+{
+	struct rocket_iommu_domain *domain = container_of(kref, struct rocket_iommu_domain, kref);
+
+	iommu_domain_free(domain->domain);
+	domain->domain = NULL;
+	kfree(domain);
+}
+
+static struct rocket_iommu_domain*
+rocket_iommu_domain_create(struct device *dev)
+{
+	struct rocket_iommu_domain *domain = kmalloc(sizeof(*domain), GFP_KERNEL);
+	void *err;
+
+	if (!domain)
+		return ERR_PTR(-ENOMEM);
+
+	domain->domain = iommu_paging_domain_alloc(dev);
+	if (IS_ERR(domain->domain)) {
+		err = ERR_CAST(domain->domain);
+		kfree(domain);
+		return err;
+	}
+	kref_init(&domain->kref);
+
+	return domain;
+}
+
+struct rocket_iommu_domain *
+rocket_iommu_domain_get(struct rocket_file_priv *rocket_priv)
+{
+	kref_get(&rocket_priv->domain->kref);
+	return rocket_priv->domain;
+}
+
+void
+rocket_iommu_domain_put(struct rocket_iommu_domain *domain)
+{
+	kref_put(&domain->kref, rocket_iommu_domain_destroy);
+}
+
+static int
+rocket_open(struct drm_device *dev, struct drm_file *file)
+{
+	struct rocket_device *rdev = to_rocket_device(dev);
+	struct rocket_file_priv *rocket_priv;
+	int ret;
+
+	if (!try_module_get(THIS_MODULE))
+		return -EINVAL;
+
+	rocket_priv = kzalloc(sizeof(*rocket_priv), GFP_KERNEL);
+	if (!rocket_priv) {
+		ret = -ENOMEM;
+		goto err_put_mod;
+	}
+
+	rocket_priv->rdev = rdev;
+	rocket_priv->domain = rocket_iommu_domain_create(rdev->cores[0].dev);
+	if (IS_ERR(rocket_priv->domain)) {
+		ret = PTR_ERR(rocket_priv->domain);
+		goto err_free;
+	}
+
+	file->driver_priv = rocket_priv;
+
+	return 0;
+
+err_free:
+	kfree(rocket_priv);
+err_put_mod:
+	module_put(THIS_MODULE);
+	return ret;
+}
+
+static void
+rocket_postclose(struct drm_device *dev, struct drm_file *file)
+{
+	struct rocket_file_priv *rocket_priv = file->driver_priv;
+
+	rocket_iommu_domain_put(rocket_priv->domain);
+	kfree(rocket_priv);
+	module_put(THIS_MODULE);
+}
+
+static const struct drm_ioctl_desc rocket_drm_driver_ioctls[] = {
+#define ROCKET_IOCTL(n, func) \
+	DRM_IOCTL_DEF_DRV(ROCKET_##n, rocket_ioctl_##func, 0)
+};
+
+DEFINE_DRM_ACCEL_FOPS(rocket_accel_driver_fops);
+
+/*
+ * Rocket driver version:
+ * - 1.0 - initial interface
+ */
+static const struct drm_driver rocket_drm_driver = {
+	.driver_features	= DRIVER_COMPUTE_ACCEL,
+	.open			= rocket_open,
+	.postclose		= rocket_postclose,
+	.ioctls			= rocket_drm_driver_ioctls,
+	.num_ioctls		= ARRAY_SIZE(rocket_drm_driver_ioctls),
+	.fops			= &rocket_accel_driver_fops,
+	.name			= "rocket",
+	.desc			= "rocket DRM",
+};
+
+static int rocket_probe(struct platform_device *pdev)
+{
+	if (rdev == NULL) {
+		/* First core probing, initialize DRM device. */
+		rdev = rocket_device_init(drm_dev, &rocket_drm_driver);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev, "failed to initialize rocket device\n");
+			return PTR_ERR(rdev);
+		}
+	}
+
+	unsigned int core = rdev->num_cores;
+
+	dev_set_drvdata(&pdev->dev, rdev);
+
+	rdev->cores[core].rdev = rdev;
+	rdev->cores[core].dev = &pdev->dev;
+	rdev->cores[core].index = core;
+
+	rdev->num_cores++;
+
+	return rocket_core_init(&rdev->cores[core]);
+}
+
+static void rocket_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+
+	for (unsigned int core = 0; core < rdev->num_cores; core++) {
+		if (rdev->cores[core].dev == dev) {
+			rocket_core_fini(&rdev->cores[core]);
+			rdev->num_cores--;
+			break;
+		}
+	}
+
+	if (rdev->num_cores == 0) {
+		/* Last core removed, deinitialize DRM device. */
+		rocket_device_fini(rdev);
+		rdev = NULL;
+	}
+}
+
+static const struct of_device_id dt_match[] = {
+	{ .compatible = "rockchip,rk3588-rknn-core" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, dt_match);
+
+static int find_core_for_dev(struct device *dev)
+{
+	struct rocket_device *rdev = dev_get_drvdata(dev);
+
+	for (unsigned int core = 0; core < rdev->num_cores; core++) {
+		if (dev == rdev->cores[core].dev)
+			return core;
+	}
+
+	return -1;
+}
+
+static int rocket_device_runtime_resume(struct device *dev)
+{
+	struct rocket_device *rdev = dev_get_drvdata(dev);
+	int core = find_core_for_dev(dev);
+	int err = 0;
+
+	if (core < 0)
+		return -ENODEV;
+
+	err = clk_bulk_prepare_enable(ARRAY_SIZE(rdev->cores[core].clks), rdev->cores[core].clks);
+	if (err) {
+		dev_err(dev, "failed to enable (%d) clocks for core %d\n", err, core);
+		return err;
+	}
+
+	return 0;
+}
+
+static int rocket_device_runtime_suspend(struct device *dev)
+{
+	struct rocket_device *rdev = dev_get_drvdata(dev);
+	int core = find_core_for_dev(dev);
+
+	if (core < 0)
+		return -ENODEV;
+
+	clk_bulk_disable_unprepare(ARRAY_SIZE(rdev->cores[core].clks), rdev->cores[core].clks);
+
+	return 0;
+}
+
+EXPORT_GPL_DEV_PM_OPS(rocket_pm_ops) = {
+	RUNTIME_PM_OPS(rocket_device_runtime_suspend, rocket_device_runtime_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+};
+
+static struct platform_driver rocket_driver = {
+	.probe = rocket_probe,
+	.remove = rocket_remove,
+	.driver	 = {
+		.name = "rocket",
+		.pm = pm_ptr(&rocket_pm_ops),
+		.of_match_table = dt_match,
+	},
+};
+
+static int __init rocket_register(void)
+{
+	drm_dev = platform_device_register_simple("rknn", -1, NULL, 0);
+	if (IS_ERR(drm_dev))
+		return PTR_ERR(drm_dev);
+
+	return platform_driver_register(&rocket_driver);
+}
+
+static void __exit rocket_unregister(void)
+{
+	platform_driver_unregister(&rocket_driver);
+
+	platform_device_unregister(drm_dev);
+}
+
+module_init(rocket_register);
+module_exit(rocket_unregister);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("DRM driver for the Rockchip NPU IP");
+MODULE_AUTHOR("Tomeu Vizoso");