Re: [PATCH v6 14/16] drm/panfrost: Kill in-flight jobs on FD close

On 30/06/2021 07:27, 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.

v5:

• Add a panfrost_exception_is_fault() helper and the DRM_PANFROST_EXCEPTION_MAX_NON_FAULT value

v4:

• Don't disable/restore irqs when taking the job_lock (not needed since this lock is never taken from an interrupt context)

v3:

• Set fence error to ECANCELED when a TERMINATED exception is received

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

drivers/gpu/drm/panfrost/panfrost_device.h | 7 ++++ drivers/gpu/drm/panfrost/panfrost_job.c | 42 ++++++++++++++++++---- 2 files changed, 43 insertions(+), 6 deletions(-)

The panfrost_exception_is_fault() makes the code much more readable - thanks!

Reviewed-by: Steven Price steven.price@arm.com

diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h index 68e93b7e5b61..193cd87f643c 100644 --- a/drivers/gpu/drm/panfrost/panfrost_device.h +++ b/drivers/gpu/drm/panfrost/panfrost_device.h @@ -184,6 +184,7 @@ enum drm_panfrost_exception_type { DRM_PANFROST_EXCEPTION_KABOOM = 0x05, DRM_PANFROST_EXCEPTION_EUREKA = 0x06, DRM_PANFROST_EXCEPTION_ACTIVE = 0x08,

• DRM_PANFROST_EXCEPTION_MAX_NON_FAULT = 0x3f, DRM_PANFROST_EXCEPTION_JOB_CONFIG_FAULT = 0x40, DRM_PANFROST_EXCEPTION_JOB_POWER_FAULT = 0x41, DRM_PANFROST_EXCEPTION_JOB_READ_FAULT = 0x42,

@@ -244,6 +245,12 @@ enum drm_panfrost_exception_type { DRM_PANFROST_EXCEPTION_MEM_ATTR_NONCACHE_3 = 0xef, };

+static inline bool +panfrost_exception_is_fault(u32 exception_code) +{

• return exception_code > DRM_PANFROST_EXCEPTION_MAX_NON_FAULT;

+}

const char *panfrost_exception_name(u32 exception_code); bool panfrost_exception_needs_reset(const struct panfrost_device *pfdev, u32 exception_code); diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index cf5f9e8b2a27..8a0db9571bfd 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -483,14 +483,21 @@ static void panfrost_job_handle_irq(struct panfrost_device *pfdev, u32 status)

if (status & JOB_INT_MASK_ERR(j)) {
	u32 js_status = job_read(pfdev, JS_STATUS(j));

• 	const char *exception_name = panfrost_exception_name(js_status);
  
  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 (!panfrost_exception_is_fault(js_status)) {
  

• 		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)));
  

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

@@ -499,7 +506,16 @@ static void panfrost_job_handle_irq(struct panfrost_device *pfdev, u32 status) if (panfrost_exception_needs_reset(pfdev, js_status)) { drm_sched_fault(&pfdev->js->queue[j].sched); } else {

• 		dma_fence_set_error(pfdev->jobs[j]->done_fence, -EINVAL);
  

• 		int error = 0;
  

• 		if (js_status == DRM_PANFROST_EXCEPTION_TERMINATED)
  

• 			error = -ECANCELED;
  

• 		else if (panfrost_exception_is_fault(js_status))
  

• 			error = -EINVAL;
  

• 		if (error)
  

• 			dma_fence_set_error(pfdev->jobs[j]->done_fence, error);
  

• 	status |= JOB_INT_MASK_DONE(j);
  }
  

  }

@@ -665,10 +681,24 @@ 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; 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(&pfdev->js->job_lock);

• 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(&pfdev->js->job_lock);

}

int panfrost_job_is_idle(struct panfrost_device *pfdev)