From: Arun Iyengar <[email protected]>

panfrost_job_hw_submit() puts a job in pfdev->jobs[] but, while a reset
is pending, does not start it and takes no cycle counter reference.
panfrost_reset() drops one for every job in pfdev->jobs[] that wants the
counter, so use_count goes below zero. The same happens for a job that
was stopped (reference dropped at dequeue) and resubmitted while a reset
was pending: is_profiled is still set from its first run.

Today the GPU reset that follows WARNs in panfrost_gpu_soft_reset() and
sets use_count back to 0. Without a reset ("Soft-stop and resume a job
that outlives the timeout") the count stays wrong and
panfrost_cycle_counter_get() no longer starts the counter.

Record in the job whether it holds a reference, and drop it only then.

Found by code review (Sashiko). Not reproduced.

Fixes: f11b0417eec2 ("drm/panfrost: Add fdinfo support GPU load metrics")
Cc: [email protected]
Reported-by: Sashiko <[email protected]>
Closes: https://lore.kernel.org/all/[email protected]/
Signed-off-by: Arun Iyengar <[email protected]>
---
 drivers/gpu/drm/panfrost/panfrost_job.c | 19 +++++++++++++------
 drivers/gpu/drm/panfrost/panfrost_job.h |  2 ++
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c 
b/drivers/gpu/drm/panfrost/panfrost_job.c
index 897743cb8..df7fcc436 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -160,6 +160,14 @@ panfrost_get_job_chain_flag(const struct panfrost_job *job)
        return (f->seqno & 1) ? JS_CONFIG_JOB_CHAIN_FLAG : 0;
 }
 
+static void panfrost_job_put_cycle_counter(struct panfrost_job *job)
+{
+       if (job->cycle_counter_ref) {
+               panfrost_cycle_counter_put(job->pfdev);
+               job->cycle_counter_ref = false;
+       }
+}
+
 static struct panfrost_job *
 panfrost_dequeue_job(struct panfrost_device *pfdev, int slot)
 {
@@ -174,8 +182,7 @@ panfrost_dequeue_job(struct panfrost_device *pfdev, int 
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);
+       panfrost_job_put_cycle_counter(job);
 
        pfdev->jobs[slot][0] = pfdev->jobs[slot][1];
        pfdev->jobs[slot][1] = NULL;
@@ -259,8 +266,10 @@ static int panfrost_job_hw_submit(struct panfrost_job 
*job, int js)
                job->is_profiled = pfdev->profile_mode;
 
                if (job->requirements & PANFROST_JD_REQ_CYCLE_COUNT ||
-                   job->is_profiled)
+                   job->is_profiled) {
                        panfrost_cycle_counter_get(pfdev);
+                       job->cycle_counter_ref = true;
+               }
 
                if (job->is_profiled) {
                        job->start_time = ktime_get();
@@ -740,9 +749,7 @@ panfrost_reset(struct panfrost_device *pfdev,
                        pfdev->jobs[i][pfdev->jobs[i][0] ? 1 : 0] = evicted[i];
 
                for (j = 0; j < ARRAY_SIZE(pfdev->jobs[0]) && 
pfdev->jobs[i][j]; j++) {
-                       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);
+                       panfrost_job_put_cycle_counter(pfdev->jobs[i][j]);
                        pm_runtime_put_noidle(pfdev->base.dev);
                        panfrost_devfreq_record_idle(&pfdev->pfdevfreq);
                }
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.h 
b/drivers/gpu/drm/panfrost/panfrost_job.h
index 3e3b97178..cd82d7930 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.h
+++ b/drivers/gpu/drm/panfrost/panfrost_job.h
@@ -36,6 +36,8 @@ struct panfrost_job {
 
        struct panfrost_engine_usage *engine_usage;
        bool is_profiled;
+       /* Holds a reference on the cycle counter */
+       bool cycle_counter_ref;
        ktime_t start_time;
        u64 start_cycles;
 };

-- 
2.55.0


Reply via email to