accel/rocket: Add IOCTLs for synchronizing memory accesses

The NPU cores have their own access to the memory bus, and this isn't
cache coherent with the CPUs.

Add IOCTLs so userspace can mark when the caches need to be flushed, and
also when a writer job needs to be waited for before the buffer can be
accessed from the CPU.

Initially based on the same IOCTLs from the Etnaviv driver.

v2:
- Don't break UABI by reordering the IOCTL IDs (Jeffrey Hugo)

Signed-off-by: Tomeu Vizoso <tomeu@tomeuvizoso.net>

drivers/accel/rocket/rocket_drv.c

@@ -58,6 +58,8 @@ static const struct drm_ioctl_desc rocket_drm_driver_ioctls[] = {
 
 	ROCKET_IOCTL(CREATE_BO, create_bo),
 	ROCKET_IOCTL(SUBMIT, submit),
+	ROCKET_IOCTL(PREP_BO, prep_bo),
+	ROCKET_IOCTL(FINI_BO, fini_bo),
 };
 
 DEFINE_DRM_ACCEL_FOPS(rocket_accel_driver_fops);

drivers/accel/rocket/rocket_gem.c

@@ -138,4 +138,79 @@ int rocket_ioctl_create_bo(struct drm_device *dev, void *data, struct drm_file *
 	drm_gem_shmem_object_free(gem_obj);
 
 	return ret;
-}
\ No newline at end of file
+}
+
+static inline enum dma_data_direction rocket_op_to_dma_dir(u32 op)
+{
+	if (op & ROCKET_PREP_READ)
+		return DMA_FROM_DEVICE;
+	else if (op & ROCKET_PREP_WRITE)
+		return DMA_TO_DEVICE;
+	else
+		return DMA_BIDIRECTIONAL;
+}
+
+int rocket_ioctl_prep_bo(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_rocket_prep_bo *args = data;
+	unsigned long timeout = drm_timeout_abs_to_jiffies(args->timeout_ns);
+	struct rocket_device *rdev = to_rocket_device(dev);
+	struct drm_gem_object *gem_obj;
+	struct drm_gem_shmem_object *shmem_obj;
+	bool write = !!(args->op & ROCKET_PREP_WRITE);
+	long ret = 0;
+
+	if (args->op & ~(ROCKET_PREP_READ | ROCKET_PREP_WRITE))
+		return -EINVAL;
+
+	gem_obj = drm_gem_object_lookup(file, args->handle);
+	if (!gem_obj)
+		return -ENOENT;
+
+	ret = dma_resv_wait_timeout(gem_obj->resv, dma_resv_usage_rw(write),
+				    true, timeout);
+	if (!ret)
+		ret = timeout ? -ETIMEDOUT : -EBUSY;
+
+	shmem_obj = &to_rocket_bo(gem_obj)->base;
+
+	for (unsigned int core = 1; core < rdev->num_cores; core++) {
+		dma_sync_sgtable_for_cpu(rdev->cores[core].dev, shmem_obj->sgt,
+					 rocket_op_to_dma_dir(args->op));
+	}
+
+	to_rocket_bo(gem_obj)->last_cpu_prep_op = args->op;
+
+	drm_gem_object_put(gem_obj);
+
+	return ret;
+}
+
+int rocket_ioctl_fini_bo(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_rocket_fini_bo *args = data;
+	struct drm_gem_object *gem_obj;
+	struct rocket_gem_object *rkt_obj;
+	struct drm_gem_shmem_object *shmem_obj;
+	struct rocket_device *rdev = to_rocket_device(dev);
+
+	gem_obj = drm_gem_object_lookup(file, args->handle);
+	if (!gem_obj)
+		return -ENOENT;
+
+	rkt_obj = to_rocket_bo(gem_obj);
+	shmem_obj = &rkt_obj->base;
+
+	WARN_ON(rkt_obj->last_cpu_prep_op == 0);
+
+	for (unsigned int core = 1; core < rdev->num_cores; core++) {
+		dma_sync_sgtable_for_device(rdev->cores[core].dev, shmem_obj->sgt,
+					    rocket_op_to_dma_dir(rkt_obj->last_cpu_prep_op));
+	}
+
+	rkt_obj->last_cpu_prep_op = 0;
+
+	drm_gem_object_put(gem_obj);
+
+	return 0;
+}

drivers/accel/rocket/rocket_gem.h

@@ -12,16 +12,21 @@ struct rocket_gem_object {
 	struct mutex mutex;
 	size_t size;
 	u32 offset;
+	u32 last_cpu_prep_op;
 };
 
 struct drm_gem_object *rocket_gem_create_object(struct drm_device *dev, size_t size);
 
 int rocket_ioctl_create_bo(struct drm_device *dev, void *data, struct drm_file *file);
 
+int rocket_ioctl_prep_bo(struct drm_device *dev, void *data, struct drm_file *file);
+
+int rocket_ioctl_fini_bo(struct drm_device *dev, void *data, struct drm_file *file);
+
 static inline
 struct  rocket_gem_object *to_rocket_bo(struct drm_gem_object *obj)
 {
 	return container_of(to_drm_gem_shmem_obj(obj), struct rocket_gem_object, base);
 }
 
-#endif
\ No newline at end of file
+#endif

include/uapi/drm/rocket_accel.h

@@ -13,9 +13,13 @@ extern "C" {
 
 #define DRM_ROCKET_CREATE_BO			0x00
 #define DRM_ROCKET_SUBMIT			0x01
+#define DRM_ROCKET_PREP_BO			0x02
+#define DRM_ROCKET_FINI_BO			0x03
 
 #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)
+#define DRM_IOCTL_ROCKET_PREP_BO		DRM_IOW(DRM_COMMAND_BASE + DRM_ROCKET_PREP_BO, struct drm_rocket_prep_bo)
+#define DRM_IOCTL_ROCKET_FINI_BO		DRM_IOW(DRM_COMMAND_BASE + DRM_ROCKET_FINI_BO, struct drm_rocket_fini_bo)
 
 /**
  * struct drm_rocket_create_bo - ioctl argument for creating Rocket BOs.
@@ -38,6 +42,20 @@ struct drm_rocket_create_bo {
 	__u64 offset;
 };
 
+#define ROCKET_PREP_READ        0x01
+#define ROCKET_PREP_WRITE       0x02
+
+struct drm_rocket_prep_bo {
+	__u32 handle;		/* in */
+	__u32 op;		/* in, mask of ROCKET_PREP_x */
+	__s64 timeout_ns;	/* in */
+};
+
+struct drm_rocket_fini_bo {
+	__u32 handle;		/* in */
+	__u32 flags;		/* in, placeholder for now, no defined values */
+};
+
 /**
  * struct drm_rocket_task - A task to be run on the NPU
  *