Thank you for your contribution! Sashiko AI review found 1 potential
issue to consider:
- [Medium] drm/panfrost: runtime suspend race in panfrost_job_timedout()
  before reset
--

commit 3b989ea77e83f04bf915c182d8dabfa8f214f4fc
Author: Arun Iyengar <[email protected]>

drm/panfrost: Soft-stop and resume a job that outlives the timeout

This commit updates the Panfrost job timeout handler to soft-stop and resume
slots whose jobs are still active, falling back to a hard-stop after 5 seconds
and a full GPU reset only if the hard-stop fails or another reset is
requested.

> diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c 
> b/drivers/gpu/drm/panfrost/panfrost_job.c
> index 8235d182d8114..6757d0fbf63c9 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_job.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_job.c
[ ... ]
> @@ -664,18 +677,35 @@ static bool panfrost_slots_idle(struct panfrost_device 
> *pfdev)
[ ... ]
>  static void
>  panfrost_reset(struct panfrost_device *pfdev,
> -            struct drm_sched_job *bad)
> +            struct drm_sched_job *bad, bool job_active)
>  {
>       struct panfrost_job *evicted[NUM_JOB_SLOTS] = {};
> +     struct panfrost_job *hung[NUM_JOB_SLOTS] = {};
> +     bool cookie, idle, stop_failed = false, reset_gpu;
>       unsigned int i, j;
> -     bool cookie, idle;
>       int ret;
>  
>       if (!atomic_read(&pfdev->reset.pending))
>               return;
>  
> +     /* The stopped jobs drop their runtime PM references before they are
> +      * resubmitted: keep the GPU powered in between.
> +      */
> +     pm_runtime_get_noresume(pfdev->base.dev);
[ ... ]
> @@ -816,18 +920,46 @@ static enum drm_gpu_sched_stat 
> panfrost_job_timedout(struct drm_sched_job
>               return DRM_GPU_SCHED_STAT_NO_HANG;
>       }
>  
> -     dev_err(pfdev->base.dev, "gpu sched timeout, js=%d, config=0x%x, 
> status=0x%x, head=0x%x, tail=0x%x, sched_job=%p",
> -             js,
> -             job_read(pfdev, JS_CONFIG(js)),
> -             job_read(pfdev, JS_STATUS(js)),
> -             job_read(pfdev, JS_HEAD_LO(js)),
> -             job_read(pfdev, JS_TAIL_LO(js)),
> -             sched_job);
> +     /*
> +      * A slot that is still ACTIVE runs a long job, not a hung one:
> +      * soft-stop and resume it instead of resetting the GPU.
> +      */
> +     js_status = job_read(pfdev, JS_STATUS(js));
> +     job_active = js_status == DRM_PANFROST_EXCEPTION_ACTIVE;
> +
> +     /* The job may have completed since the fence check above. */
> +     if (!job_active) {
> +             if (job_read(pfdev, JOB_INT_RAWSTAT) & JOB_INT_MASK_DONE(js))
> +                     return DRM_GPU_SCHED_STAT_NO_HANG;
> +
> +             synchronize_irq(pfdev->js->irq);
> +             if (dma_fence_is_signaled(job->done_fence))
> +                     return DRM_GPU_SCHED_STAT_NO_HANG;
> +     }
>  
> -     panfrost_core_dump(job);
> +     if (job_active) {
> +             dev_dbg(pfdev->base.dev, "job still active after %u ms, js=%d, 
> head=0x%x, sched_job=%p: soft-stopping it to resume",
> +                     JOB_TIMEOUT_MS, js, job_read(pfdev, JS_HEAD_LO(js)),
> +                     sched_job);
> +     } else {
> +             dev_err(pfdev->base.dev, "gpu sched timeout, js=%d, 
> config=0x%x, status=0x%x, head=0x%x, tail=0x%x, sched_job=%p",
> +                     js,
> +                     job_read(pfdev, JS_CONFIG(js)),
> +                     js_status,
> +                     job_read(pfdev, JS_HEAD_LO(js)),
> +                     job_read(pfdev, JS_TAIL_LO(js)),
> +                     sched_job);
>  
> -     atomic_set(&pfdev->reset.pending, 1);
> -     panfrost_reset(pfdev, sched_job);
> +             panfrost_core_dump(job);
> +     }
> +
> +     /* Ask for a reset, or only for the stop if no reset is pending. */
> +     if (job_active)
> +             atomic_cmpxchg(&pfdev->reset.pending, 0,
> +                            PANFROST_RESET_STOP_ONLY);
> +     else
> +             atomic_set(&pfdev->reset.pending, 1);
> +     panfrost_reset(pfdev, sched_job, job_active);

[Severity: Medium]
Can the GPU runtime-autosuspend in panfrost_job_timedout() before
panfrost_reset() calls pm_runtime_get_noresume(), causing MMIO accesses on
a powered-off GPU?

CPU0 (timeout worker)             CPU1 (IRQ thread / PM worker)
panfrost_job_timedout()
  js_status = job_read(JS_STATUS)
  // reads ACTIVE
                                  panfrost_jm_irq_handler_thread()
                                    panfrost_jm_handle_done()
                                      dma_fence_signal_locked(done_fence)
                                        drm_sched_job_done_cb()
                                          // credit_count -> 0
                                      pm_runtime_put_autosuspend()
                                  ...
                                  // 50 ms autosuspend expires
                                  panfrost_device_runtime_suspend()
                                    panfrost_gpu_power_off()
  panfrost_reset()
    pm_runtime_get_noresume()
    job_write(JOB_INT_MASK, 0)    <-- external abort (GPU powered off)

Job interrupts remain enabled until panfrost_reset() masks JOB_INT_MASK,
and the completion callback on job->done_fence remains attached until
drm_sched_stop().  If the only in-flight job completes right after
JS_STATUS(js) is read as DRM_PANFROST_EXCEPTION_ACTIVE (or faults just
before, setting JOB_INT_MASK_ERR(js) rather than JOB_INT_MASK_DONE(js),
and the IRQ thread finishes while panfrost_core_dump() is copying BOs),
the IRQ handler drops sched->credit_count to 0 and releases the job's
runtime PM reference.  With panfrost_jm_is_idle() now true, runtime
autosuspend can power off the GPU and disable its clocks before
panfrost_reset() is reached, and pm_runtime_get_noresume() only increments
usage_count without resuming the device.

Acquiring the runtime PM reference at the start of panfrost_job_timedout()
(or using pm_runtime_resume_and_get()) before checking the fences and
reading registers would keep the GPU powered throughout the timeout and
reset path.

-- 
Sashiko AI review ยท 
https://sashiko.dev/#/patchset/[email protected]?part=13

Reply via email to