Re: [PATCH v2 10/12] drm/panfrost: Kill in-flight jobs on FD close

On 21/06/2021 14:39, Boris Brezillon wrote:

If the process who submitted these jobs decided to close the FD before the jobs are done it probably means it doesn't care about the result.

Signed-off-by: Boris Brezillon boris.brezillon@collabora.com

drivers/gpu/drm/panfrost/panfrost_job.c | 33 +++++++++++++++++++++---- 1 file changed, 28 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index aedc604d331c..a51fa0a81367 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -494,14 +494,22 @@ static irqreturn_t panfrost_job_irq_handler(int irq, void *data) if (status & JOB_INT_MASK_ERR(j)) { enum panfrost_queue_status old_status; u32 js_status = job_read(pfdev, JS_STATUS(j));

• 	int error = panfrost_exception_to_error(js_status);
  

• 	const char *exception_name = panfrost_exception_name(js_status);
  

NIT: I'm not sure if it's worth it, but it feels like a function which returns both the name and error-code would make sense. E.g. making struct panfrost_exception_info public.

	job_write(pfdev, JS_COMMAND_NEXT(j), JS_COMMAND_NOP);

• 	dev_err(pfdev->dev, "js fault, js=%d, status=%s, head=0x%x, tail=0x%x",
  

• 		j,
  

• 		panfrost_exception_name(js_status),
  

• 		job_read(pfdev, JS_HEAD_LO(j)),
  

• 		job_read(pfdev, JS_TAIL_LO(j)));
  

• 	if (!error) {
  

• 		dev_dbg(pfdev->dev, "js interrupt, js=%d, status=%s, head=0x%x, tail=0x%x",
  

• 			j, exception_name,
  

• 			job_read(pfdev, JS_HEAD_LO(j)),
  

• 			job_read(pfdev, JS_TAIL_LO(j)));
  

• 	} else {
  

• 		dev_err(pfdev->dev, "js fault, js=%d, status=%s, head=0x%x, tail=0x%x",
  

• 			j, exception_name,
  

• 			job_read(pfdev, JS_HEAD_LO(j)),
  

• 			job_read(pfdev, JS_TAIL_LO(j)));
  

• 	}
  

Again here you're going to have issues with TERMINATED - dev_err() is probably too chatty, so just changing panfrost_exception_to_error() to return an error value is going to cause problems here.

Steve

	/* If we need a reset, signal it to the reset handler,
	 * otherwise, update the fence error field and signal

@@ -688,10 +696,25 @@ int panfrost_job_open(struct panfrost_file_priv *panfrost_priv)

void panfrost_job_close(struct panfrost_file_priv *panfrost_priv) {

• struct panfrost_device *pfdev = panfrost_priv->pfdev;

• unsigned long flags; int i;

  for (i = 0; i < NUM_JOB_SLOTS; i++) drm_sched_entity_destroy(&panfrost_priv->sched_entity[i]);

• /* Kill in-flight jobs */

• spin_lock_irqsave(&pfdev->js->job_lock, flags);

• for (i = 0; i < NUM_JOB_SLOTS; i++) {

• struct drm_sched_entity *entity = &panfrost_priv->sched_entity[i];
  

• struct panfrost_job *job = pfdev->jobs[i];
  

• if (!job || job->base.entity != entity)
  

• 	continue;
  

• job_write(pfdev, JS_COMMAND(i), JS_COMMAND_HARD_STOP);
  

• }

• spin_unlock_irqrestore(&pfdev->js->job_lock, flags);

}

int panfrost_job_is_idle(struct panfrost_device *pfdev)