Commit da3208e8 authored by Daniel Vetter's avatar Daniel Vetter
Browse files

drm/v3d: Use scheduler dependency handling 



With the prep work out of the way this isn't tricky anymore.

Aside: The chaining of the various jobs is a bit awkward, with the
possibility of failure in bad places. I think with the
drm_sched_job_init/arm split and maybe preloading the
job->dependencies xarray this should be fixable.

v2: Rebase over renamed function names for adding dependencies.

Reviewed-by: Melissa Wen <mwen@igalia.com> (v1)
Acked-by: default avatarEmma Anholt <emma@anholt.net>
Cc: Melissa Wen <melissa.srw@gmail.com>
Signed-off-by: default avatarDaniel Vetter <daniel.vetter@intel.com>
Cc: Emma Anholt <emma@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20210805104705.862416-11-daniel.vetter@ffwll.ch
parent 916044fa

drivers/gpu/drm/v3d/v3d_drv.h

+0 −5
Original line number Diff line number Diff line
@@ -234,11 +234,6 @@ struct v3d_job { 
	struct drm_gem_object **bo;

	u32 bo_count;



	/* Array of struct dma_fence * to block on before submitting this job.

	 */

	struct xarray deps;

	unsigned long last_dep;



	/* v3d fence to be signaled by IRQ handler when the job is complete. */

	struct dma_fence *irq_fence;

drivers/gpu/drm/v3d/v3d_gem.c

+9 −17
Original line number Diff line number Diff line
@@ -259,7 +259,7 @@ v3d_lock_bo_reservations(struct v3d_job *job, 
		return ret;



	for (i = 0; i < job->bo_count; i++) {

		ret = drm_gem_fence_array_add_implicit(&job->deps,

		ret = drm_sched_job_add_implicit_dependencies(&job->base,

							      job->bo[i], true);

		if (ret) {

			drm_gem_unlock_reservations(job->bo, job->bo_count,
@@ -356,8 +356,6 @@ static void 
v3d_job_free(struct kref *ref)

{

	struct v3d_job *job = container_of(ref, struct v3d_job, refcount);

	unsigned long index;

	struct dma_fence *fence;

	int i;



	for (i = 0; i < job->bo_count; i++) {
@@ -366,11 +364,6 @@ v3d_job_free(struct kref *ref) 
	}

	kvfree(job->bo);



	xa_for_each(&job->deps, index, fence) {

		dma_fence_put(fence);

	}

	xa_destroy(&job->deps);



	dma_fence_put(job->irq_fence);

	dma_fence_put(job->done_fence);
@@ -457,7 +450,6 @@ v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, 
	if (ret < 0)

		return ret;



	xa_init_flags(&job->deps, XA_FLAGS_ALLOC);

	ret = drm_sched_job_init(&job->base, &v3d_priv->sched_entity[queue],

				 v3d_priv);

	if (ret)
@@ -467,7 +459,7 @@ v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, 
	if (ret == -EINVAL)

		goto fail_job;



	ret = drm_gem_fence_array_add(&job->deps, in_fence);

	ret = drm_sched_job_add_dependency(&job->base, in_fence);

	if (ret)

		goto fail_job;
@@ -477,7 +469,6 @@ v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv, 
fail_job:

	drm_sched_job_cleanup(&job->base);

fail:

	xa_destroy(&job->deps);

	pm_runtime_put_autosuspend(v3d->drm.dev);

	return ret;

}
@@ -640,7 +631,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, 
		v3d_perfmon_get(bin->base.perfmon);

		v3d_push_job(&bin->base);



		ret = drm_gem_fence_array_add(&render->base.deps,

		ret = drm_sched_job_add_dependency(&render->base.base,

						   dma_fence_get(bin->base.done_fence));

		if (ret)

			goto fail_unreserve;
@@ -651,7 +642,8 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, 
	if (clean_job) {

		struct dma_fence *render_fence =

			dma_fence_get(render->base.done_fence);

		ret = drm_gem_fence_array_add(&clean_job->deps, render_fence);

		ret = drm_sched_job_add_dependency(&clean_job->base,

						   render_fence);

		if (ret)

			goto fail_unreserve;

		clean_job->perfmon = render->base.perfmon;
@@ -853,7 +845,7 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data, 
	mutex_lock(&v3d->sched_lock);

	v3d_push_job(&job->base);



	ret = drm_gem_fence_array_add(&clean_job->deps,

	ret = drm_sched_job_add_dependency(&clean_job->base,

					   dma_fence_get(job->base.done_fence));

	if (ret)

		goto fail_unreserve;

drivers/gpu/drm/v3d/v3d_sched.c

+1 −28
Original line number Diff line number Diff line
@@ -13,7 +13,7 @@ 
 * jobs when bulk background jobs are queued up, we submit a new job

 * to the HW only when it has completed the last one, instead of

 * filling up the CT[01]Q FIFOs with jobs.  Similarly, we use

 * v3d_job_dependency() to manage the dependency between bin and

 * drm_sched_job_add_dependency() to manage the dependency between bin and

 * render, instead of having the clients submit jobs using the HW's

 * semaphores to interlock between them.

 */
@@ -72,28 +72,6 @@ v3d_switch_perfmon(struct v3d_dev *v3d, struct v3d_job *job) 
		v3d_perfmon_start(v3d, job->perfmon);

}



/*

 * Returns the fences that the job depends on, one by one.

 *

 * If placed in the scheduler's .dependency method, the corresponding

 * .run_job won't be called until all of them have been signaled.

 */

static struct dma_fence *

v3d_job_dependency(struct drm_sched_job *sched_job,

		   struct drm_sched_entity *s_entity)

{

	struct v3d_job *job = to_v3d_job(sched_job);



	/* XXX: Wait on a fence for switching the GMP if necessary,

	 * and then do so.

	 */



	if (!xa_empty(&job->deps))

		return xa_erase(&job->deps, job->last_dep++);



	return NULL;

}



static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)

{

	struct v3d_bin_job *job = to_bin_job(sched_job);
@@ -372,35 +350,30 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job) 
}



static const struct drm_sched_backend_ops v3d_bin_sched_ops = {

	.dependency = v3d_job_dependency,

	.run_job = v3d_bin_job_run,

	.timedout_job = v3d_bin_job_timedout,

	.free_job = v3d_sched_job_free,

};



static const struct drm_sched_backend_ops v3d_render_sched_ops = {

	.dependency = v3d_job_dependency,

	.run_job = v3d_render_job_run,

	.timedout_job = v3d_render_job_timedout,

	.free_job = v3d_sched_job_free,

};



static const struct drm_sched_backend_ops v3d_tfu_sched_ops = {

	.dependency = v3d_job_dependency,

	.run_job = v3d_tfu_job_run,

	.timedout_job = v3d_generic_job_timedout,

	.free_job = v3d_sched_job_free,

};



static const struct drm_sched_backend_ops v3d_csd_sched_ops = {

	.dependency = v3d_job_dependency,

	.run_job = v3d_csd_job_run,

	.timedout_job = v3d_csd_job_timedout,

	.free_job = v3d_sched_job_free

};



static const struct drm_sched_backend_ops v3d_cache_clean_sched_ops = {

	.dependency = v3d_job_dependency,

	.run_job = v3d_cache_clean_job_run,

	.timedout_job = v3d_generic_job_timedout,

	.free_job = v3d_sched_job_free