drm/v3d: Expose performance counters to userspace

The V3D engine has several hardware performance counters that can of
interest for userspace performance analysis tools.

This exposes new ioctls to create and destroy performance monitor
objects, as well as to query the counter values.

Each created performance monitor object has an ID that can be attached
to CL/CSD submissions, so the driver enables the requested counters when
the job is submitted, and updates the performance monitor values when
the job is done.

It is up to the user to ensure all the jobs have been finished before
getting the performance monitor values. It is also up to the user to
properly synchronize BCL jobs when submitting jobs with different
performance monitors attached.

Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: Emma Anholt <emma@anholt.net>
To: dri-devel@lists.freedesktop.org
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Acked-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210608111541.461991-1-jasuarez@igalia.com

1 files changed, 31 insertions, 0 deletions

diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 4eb354226972..5689da118197 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -126,6 +126,8 @@ v3d_reset(struct v3d_dev *v3d)
 	v3d_mmu_set_page_table(v3d);
 	v3d_irq_reset(v3d);
 
+	v3d_perfmon_stop(v3d, v3d->active_perfmon, false);
+
 	trace_v3d_reset_end(dev);
 }
 
@@ -375,6 +377,9 @@ v3d_job_free(struct kref *ref)
 	pm_runtime_mark_last_busy(job->v3d->drm.dev);
 	pm_runtime_put_autosuspend(job->v3d->drm.dev);
 
+	if (job->perfmon)
+		v3d_perfmon_put(job->perfmon);
+
 	kfree(job);
 }
 
@@ -539,6 +544,9 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 	trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end);
 
+	if (args->pad != 0)
+		return -EINVAL;
+
 	if (args->flags != 0 &&
 	    args->flags != DRM_V3D_SUBMIT_CL_FLUSH_CACHE) {
 		DRM_INFO("invalid flags: %d\n", args->flags);
@@ -611,8 +619,20 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto fail;
 
+	if (args->perfmon_id) {
+		render->base.perfmon = v3d_perfmon_find(v3d_priv,
+							args->perfmon_id);
+
+		if (!render->base.perfmon) {
+			ret = -ENOENT;
+			goto fail;
+		}
+	}
+
 	mutex_lock(&v3d->sched_lock);
 	if (bin) {
+		bin->base.perfmon = render->base.perfmon;
+		v3d_perfmon_get(bin->base.perfmon);
 		ret = v3d_push_job(v3d_priv, &bin->base, V3D_BIN);
 		if (ret)
 			goto fail_unreserve;
@@ -633,6 +653,8 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 		ret = drm_gem_fence_array_add(&clean_job->deps, render_fence);
 		if (ret)
 			goto fail_unreserve;
+		clean_job->perfmon = render->base.perfmon;
+		v3d_perfmon_get(clean_job->perfmon);
 		ret = v3d_push_job(v3d_priv, clean_job, V3D_CACHE_CLEAN);
 		if (ret)
 			goto fail_unreserve;
@@ -827,6 +849,15 @@ v3d_submit_csd_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto fail;
 
+	if (args->perfmon_id) {
+		job->base.perfmon = v3d_perfmon_find(v3d_priv,
+						     args->perfmon_id);
+		if (!job->base.perfmon) {
+			ret = -ENOENT;
+			goto fail;
+		}
+	}
+
 	mutex_lock(&v3d->sched_lock);
 	ret = v3d_push_job(v3d_priv, &job->base, V3D_CSD);
 	if (ret)