accel/rocket: Add job submission IOCTL

Using the DRM GPU scheduler infrastructure, with a scheduler for each
core.

Userspace can decide for a series of tasks to be executed sequentially
in the same core, so SRAM locality can be taken advantage of.

The job submission code was initially based on Panfrost.

v2:
- Remove hardcoded number of cores
- Misc. style fixes (Jeffrey Hugo)
- Repack IOCTL struct (Jeffrey Hugo)

v3:
- Adapt to a split of the register block in the DT bindings (Nicolas
  Frattaroli)
- Make use of GPL-2.0-only for the copyright notice (Jeff Hugo)
- Use drm_* logging functions (Thomas Zimmermann)
- Rename reg i/o macros (Thomas Zimmermann)
- Add padding to ioctls and check for zero (Jeff Hugo)
- Improve error handling (Nicolas Frattaroli)

v6:
- Use mutexes guard (Markus Elfring)
- Use u64_to_user_ptr (Jeff Hugo)
- Drop rocket_fence (Rob Herring)

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

v8:
- Use reset lines to reset the cores (Robin Murphy)
- Use the macros to compute the values for the bitfields (Robin Murphy)
- More descriptive name for the IRQ (Robin Murphy)
- Simplify job interrupt handing (Robin Murphy)
- Correctly acquire a reference to the IOMMU (Robin Murphy)
- Specify the size of the embedded structs in the IOCTLs for future
  extensibility (Rob Herring)
- Expose only 32 bits for the address of the regcmd BO (Robin Murphy)

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-v9-4-77ebd484941e@tomeuvizoso.net

drivers/accel/rocket/Makefile

@@ -6,4 +6,5 @@ rocket-y := \
 	rocket_core.o \
 	rocket_device.o \
 	rocket_drv.o \
-	rocket_gem.o
+	rocket_gem.o \
+	rocket_job.o

drivers/accel/rocket/rocket_core.c

@@ -12,6 +12,7 @@
 #include <linux/reset.h>
 
 #include "rocket_core.h"
+#include "rocket_job.h"
 
 int rocket_core_init(struct rocket_core *core)
 {
@@ -57,6 +58,10 @@ int rocket_core_init(struct rocket_core *core)
 
 	core->iommu_group = iommu_group_get(dev);
 
+	err = rocket_job_init(core);
+	if (err)
+		return err;
+
 	pm_runtime_use_autosuspend(dev);
 
 	/*
@@ -70,6 +75,10 @@ int rocket_core_init(struct rocket_core *core)
 	pm_runtime_enable(dev);
 
 	err = pm_runtime_get_sync(dev);
+	if (err) {
+		rocket_job_fini(core);
+		return err;
+	}
 
 	version = rocket_pc_readl(core, VERSION);
 	version += rocket_pc_readl(core, VERSION_NUM) & 0xffff;
@@ -88,6 +97,7 @@ void rocket_core_fini(struct rocket_core *core)
 	pm_runtime_disable(core->dev);
 	iommu_group_put(core->iommu_group);
 	core->iommu_group = NULL;
+	rocket_job_fini(core);
 }
 
 void rocket_core_reset(struct rocket_core *core)

drivers/accel/rocket/rocket_core.h

@@ -40,6 +40,21 @@ struct rocket_core {
 	struct reset_control_bulk_data resets[2];
 
 	struct iommu_group *iommu_group;
+
+	struct mutex job_lock;
+	struct rocket_job *in_flight_job;
+
+	spinlock_t fence_lock;
+
+	struct {
+		struct workqueue_struct *wq;
+		struct work_struct work;
+		atomic_t pending;
+	} reset;
+
+	struct drm_gpu_scheduler sched;
+	u64 fence_context;
+	u64 emit_seqno;
 };
 
 int rocket_core_init(struct rocket_core *core);

drivers/accel/rocket/rocket_device.c

@@ -41,6 +41,10 @@ struct rocket_device *rocket_device_init(struct platform_device *pdev,
 	if (err)
 		return ERR_PTR(err);
 
+	err = devm_mutex_init(dev, &rdev->sched_lock);
+	if (err)
+		return ERR_PTR(-ENOMEM);
+
 	err = drm_dev_register(ddev, 0);
 	if (err)
 		return ERR_PTR(err);

drivers/accel/rocket/rocket_device.h

@@ -15,6 +15,8 @@
 struct rocket_device {
 	struct drm_device ddev;
 
+	struct mutex sched_lock;
+
 	struct rocket_core *cores;
 	unsigned int num_cores;
 };

drivers/accel/rocket/rocket_drv.c

@@ -15,6 +15,7 @@
 
 #include "rocket_drv.h"
 #include "rocket_gem.h"
+#include "rocket_job.h"
 
 /*
  * Facade device, used to expose a single DRM device to userspace, that
@@ -97,8 +98,16 @@ rocket_open(struct drm_device *dev, struct drm_file *file)
 	drm_mm_init(&rocket_priv->mm, start, end - start + 1);
 	mutex_init(&rocket_priv->mm_lock);
 
+	ret = rocket_job_open(rocket_priv);
+	if (ret)
+		goto err_mm_takedown;
+
 	return 0;
 
+err_mm_takedown:
+	mutex_destroy(&rocket_priv->mm_lock);
+	drm_mm_takedown(&rocket_priv->mm);
+	rocket_iommu_domain_put(rocket_priv->domain);
 err_free:
 	kfree(rocket_priv);
 err_put_mod:
@@ -111,6 +120,7 @@ rocket_postclose(struct drm_device *dev, struct drm_file *file)
 {
 	struct rocket_file_priv *rocket_priv = file->driver_priv;
 
+	rocket_job_close(rocket_priv);
 	mutex_destroy(&rocket_priv->mm_lock);
 	drm_mm_takedown(&rocket_priv->mm);
 	rocket_iommu_domain_put(rocket_priv->domain);
@@ -123,6 +133,7 @@ static const struct drm_ioctl_desc rocket_drm_driver_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(ROCKET_##n, rocket_ioctl_##func, 0)
 
 	ROCKET_IOCTL(CREATE_BO, create_bo),
+	ROCKET_IOCTL(SUBMIT, submit),
 };
 
 DEFINE_DRM_ACCEL_FOPS(rocket_accel_driver_fops);
@@ -230,6 +241,9 @@ static int rocket_device_runtime_suspend(struct device *dev)
 	if (core < 0)
 		return -ENODEV;
 
+	if (!rocket_job_is_idle(&rdev->cores[core]))
+		return -EBUSY;
+
 	clk_bulk_disable_unprepare(ARRAY_SIZE(rdev->cores[core].clks), rdev->cores[core].clks);
 
 	return 0;

drivers/accel/rocket/rocket_drv.h

@@ -5,6 +5,7 @@
 #define __ROCKET_DRV_H__
 
 #include <drm/drm_mm.h>
+#include <drm/gpu_scheduler.h>
 
 #include "rocket_device.h"
 
@@ -19,6 +20,8 @@ struct rocket_file_priv {
 	struct rocket_iommu_domain *domain;
 	struct drm_mm mm;
 	struct mutex mm_lock;
+
+	struct drm_sched_entity sched_entity;
 };
 
 struct rocket_iommu_domain *rocket_iommu_domain_get(struct rocket_file_priv *rocket_priv);

drivers/accel/rocket/rocket_job.h

@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
+
+#ifndef __ROCKET_JOB_H__
+#define __ROCKET_JOB_H__
+
+#include <drm/drm_drv.h>
+#include <drm/gpu_scheduler.h>
+
+#include "rocket_core.h"
+#include "rocket_drv.h"
+
+struct rocket_task {
+	u64 regcmd;
+	u32 regcmd_count;
+};
+
+struct rocket_job {
+	struct drm_sched_job base;
+
+	struct rocket_device *rdev;
+
+	struct drm_gem_object **in_bos;
+	struct drm_gem_object **out_bos;
+
+	u32 in_bo_count;
+	u32 out_bo_count;
+
+	struct rocket_task *tasks;
+	u32 task_count;
+	u32 next_task_idx;
+
+	/* Fence to be signaled by drm-sched once its done with the job */
+	struct dma_fence *inference_done_fence;
+
+	/* Fence to be signaled by IRQ handler when the job is complete. */
+	struct dma_fence *done_fence;
+
+	struct rocket_iommu_domain *domain;
+
+	struct kref refcount;
+};
+
+int rocket_ioctl_submit(struct drm_device *dev, void *data, struct drm_file *file);
+
+int rocket_job_init(struct rocket_core *core);
+void rocket_job_fini(struct rocket_core *core);
+int rocket_job_open(struct rocket_file_priv *rocket_priv);
+void rocket_job_close(struct rocket_file_priv *rocket_priv);
+int rocket_job_is_idle(struct rocket_core *core);
+
+#endif

include/uapi/drm/rocket_accel.h

@@ -12,8 +12,10 @@ extern "C" {
 #endif
 
 #define DRM_ROCKET_CREATE_BO			0x00
+#define DRM_ROCKET_SUBMIT			0x01
 
 #define DRM_IOCTL_ROCKET_CREATE_BO		DRM_IOWR(DRM_COMMAND_BASE + DRM_ROCKET_CREATE_BO, struct drm_rocket_create_bo)
+#define DRM_IOCTL_ROCKET_SUBMIT			DRM_IOW(DRM_COMMAND_BASE + DRM_ROCKET_SUBMIT, struct drm_rocket_submit)
 
 /**
  * struct drm_rocket_create_bo - ioctl argument for creating Rocket BOs.
@@ -37,6 +39,68 @@ struct drm_rocket_create_bo {
 	__u64 offset;
 };
 
+/**
+ * struct drm_rocket_task - A task to be run on the NPU
+ *
+ * A task is the smallest unit of work that can be run on the NPU.
+ */
+struct drm_rocket_task {
+	/** Input: DMA address to NPU mapping of register command buffer */
+	__u32 regcmd;
+
+	/** Input: Number of commands in the register command buffer */
+	__u32 regcmd_count;
+};
+
+/**
+ * struct drm_rocket_job - A job to be run on the NPU
+ *
+ * The kernel will schedule the execution of this job taking into account its
+ * dependencies with other jobs. All tasks in the same job will be executed
+ * sequentially on the same core, to benefit from memory residency in SRAM.
+ */
+struct drm_rocket_job {
+	/** Input: Pointer to an array of struct drm_rocket_task. */
+	__u64 tasks;
+
+	/** Input: Pointer to a u32 array of the BOs that are read by the job. */
+	__u64 in_bo_handles;
+
+	/** Input: Pointer to a u32 array of the BOs that are written to by the job. */
+	__u64 out_bo_handles;
+
+	/** Input: Number of tasks passed in. */
+	__u32 task_count;
+
+	/** Input: Size in bytes of the structs in the @tasks field. */
+	__u32 task_struct_size;
+
+	/** Input: Number of input BO handles passed in (size is that times 4). */
+	__u32 in_bo_handle_count;
+
+	/** Input: Number of output BO handles passed in (size is that times 4). */
+	__u32 out_bo_handle_count;
+};
+
+/**
+ * struct drm_rocket_submit - ioctl argument for submitting commands to the NPU.
+ *
+ * The kernel will schedule the execution of these jobs in dependency order.
+ */
+struct drm_rocket_submit {
+	/** Input: Pointer to an array of struct drm_rocket_job. */
+	__u64 jobs;
+
+	/** Input: Number of jobs passed in. */
+	__u32 job_count;
+
+	/** Input: Size in bytes of the structs in the @jobs field. */
+	__u32 job_struct_size;
+
+	/** Reserved, must be zero. */
+	__u64 reserved;
+};
+
 #if defined(__cplusplus)
 }
 #endif