drm/panfrost: Add cycle counter job requirement

Extend the uAPI with a new job requirement flag for cycle
counters. This requirement is used by userland to indicate that a job
requires cycle counters or system timestamp to be propagated. (for use
with write value timestamp jobs)

We cannot enable cycle counters unconditionally as this would result in
an increase of GPU power consumption. As a result, they should be left
off unless required by the application.

If a job requires cycle counters or system timestamps propagation, we
must enable cycle counting before issuing a job and disable it right
after the job completes.

Since this extends the uAPI and because userland needs a way to advertise
features like VK_KHR_shader_clock conditionally, we bumps the driver
minor version.

v2:
- Rework commit message
- Squash uAPI changes and implementation in this commit
- Simplify changes based on Steven Price comments

v3:
- Add Steven Price r-b
- Fix a codestyle issue

Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Tested-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Steven Price <steven.price@arm.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240819080224.24914-3-mary.guillemard@collabora.com

1 files changed, 17 insertions, 11 deletions

diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index df49d37d0e7e..3ad131eb6657 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -159,16 +159,17 @@ panfrost_dequeue_job(struct panfrost_device *pfdev, int slot)
 	struct panfrost_job *job = pfdev->jobs[slot][0];
 
 	WARN_ON(!job);
-	if (job->is_profiled) {
-		if (job->engine_usage) {
-			job->engine_usage->elapsed_ns[slot] +=
-				ktime_to_ns(ktime_sub(ktime_get(), job->start_time));
-			job->engine_usage->cycles[slot] +=
-				panfrost_cycle_counter_read(pfdev) - job->start_cycles;
-		}
-		panfrost_cycle_counter_put(job->pfdev);
+
+	if (job->is_profiled && job->engine_usage) {
+		job->engine_usage->elapsed_ns[slot] +=
+			ktime_to_ns(ktime_sub(ktime_get(), job->start_time));
+		job->engine_usage->cycles[slot] +=
+			panfrost_cycle_counter_read(pfdev) - job->start_cycles;
 	}
 
+	if (job->requirements & PANFROST_JD_REQ_CYCLE_COUNT || job->is_profiled)
+		panfrost_cycle_counter_put(pfdev);
+
 	pfdev->jobs[slot][0] = pfdev->jobs[slot][1];
 	pfdev->jobs[slot][1] = NULL;
 
@@ -243,9 +244,13 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 	subslot = panfrost_enqueue_job(pfdev, js, job);
 	/* Don't queue the job if a reset is in progress */
 	if (!atomic_read(&pfdev->reset.pending)) {
-		if (pfdev->profile_mode) {
+		job->is_profiled = pfdev->profile_mode;
+
+		if (job->requirements & PANFROST_JD_REQ_CYCLE_COUNT ||
+		    job->is_profiled)
 			panfrost_cycle_counter_get(pfdev);
-			job->is_profiled = true;
+
+		if (job->is_profiled) {
 			job->start_time = ktime_get();
 			job->start_cycles = panfrost_cycle_counter_read(pfdev);
 		}
@@ -693,7 +698,8 @@ panfrost_reset(struct panfrost_device *pfdev,
 	spin_lock(&pfdev->js->job_lock);
 	for (i = 0; i < NUM_JOB_SLOTS; i++) {
 		for (j = 0; j < ARRAY_SIZE(pfdev->jobs[0]) && pfdev->jobs[i][j]; j++) {
-			if (pfdev->jobs[i][j]->is_profiled)
+			if (pfdev->jobs[i][j]->requirements & PANFROST_JD_REQ_CYCLE_COUNT ||
+			    pfdev->jobs[i][j]->is_profiled)
 				panfrost_cycle_counter_put(pfdev->jobs[i][j]->pfdev);
 			pm_runtime_put_noidle(pfdev->dev);
 			panfrost_devfreq_record_idle(&pfdev->pfdevfreq);