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

1 files changed, 64 insertions, 0 deletions

diff --git a/include/uapi/drm/rocket_accel.h b/include/uapi/drm/rocket_accel.h
index 95720702b7c4..374f8370ac9d 100644
--- a/include/uapi/drm/rocket_accel.h
+++ b/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