drm/msm: Move hangcheck timer restart

From: Rob Clark <[email protected]>

Don't directly restart the hangcheck timer from the timer handler, but instead start it after the recover_worker replays remaining jobs.

If the kthread is blocked for other reasons, there is no point to immediately restart the timer. Fixes a random symptom of the problem fixed in the next patch.

Signed-off-by Rob Clark <[email protected]>

---
  drivers/gpu/drm/msm/msm_gpu.c | 14 +++++++++-----
  1 file changed, 9 insertions(+), 5 deletions(-)

drivers/gpu/drm/msm/msm_gpu.c +9 -1

index fba85f894314..8f9c48eabf7d 100644
@@ -328,6 +328,7 @@ find_submit(struct msm_ringbuffer *ring, uint32_t fence)
  }
 
  static void retire_submits(struct msm_gpu *gpu);
+static void hangcheck_timer_reset(struct msm_gpu *gpu);
 
  static void get_comm_cmdline(struct msm_gem_submit *submit, char **comm, char **cmd)
  {

@@ -420,6 +421,8 @@ static void recover_worker(struct kthread_work *work)
  	}
 
  	if (msm_gpu_active(gpu)) {
+		bool restart_hangcheck = false;
+
  		/* retire completed submits, plus the one that hung: */
  		retire_submits(gpu);
 

@@ -436,10 +439,15 @@ static void recover_worker(struct kthread_work *work)
  			unsigned long flags;
 
  			spin_lock_irqsave(&ring->submit_lock, flags);
-			list_for_each_entry(submit, &ring->submits, node)
+			list_for_each_entry(submit, &ring->submits, node) {
  				gpu->funcs->submit(gpu, submit);
+				restart_hangcheck = true;
+			}
  			spin_unlock_irqrestore(&ring->submit_lock, flags);
  		}
+
+		if (restart_hangcheck)
+			hangcheck_timer_reset(gpu);
  	}
 
  	mutex_unlock(&gpu->lock);

drivers/gpu/drm/msm/msm_gpu.c +0 -3

-	if (fence_after(ring->fctx->last_fence, ring->hangcheck_fence))
-		hangcheck_timer_reset(gpu);
-
  	/* workaround for missing irq: */
  	msm_gpu_retire(gpu);
  }

Quoted 51 lines · Rob Clark

From: Rob Clark <[email protected]>

Don't directly restart the hangcheck timer from the timer handler, but instead start it after the recover_worker replays remaining jobs.

If the kthread is blocked for other reasons, there is no point to immediately restart the timer. Fixes a random symptom of the problem fixed in the next patch.

Signed-off-by Rob Clark <[email protected]>

---
  drivers/gpu/drm/msm/msm_gpu.c | 14 +++++++++-----
  1 file changed, 9 insertions(+), 5 deletions(-)

drivers/gpu/drm/msm/msm_gpu.c +9 -1

index fba85f894314..8f9c48eabf7d 100644
@@ -328,6 +328,7 @@ find_submit(struct msm_ringbuffer *ring, uint32_t fence)
  }
 
  static void retire_submits(struct msm_gpu *gpu);
+static void hangcheck_timer_reset(struct msm_gpu *gpu);
 
  static void get_comm_cmdline(struct msm_gem_submit *submit, char **comm, char **cmd)
  {

@@ -420,6 +421,8 @@ static void recover_worker(struct kthread_work *work)
      }
 
      if (msm_gpu_active(gpu)) {
+             bool restart_hangcheck = false;
+
              /* retire completed submits, plus the one that hung: */
              retire_submits(gpu);
 

@@ -436,10 +439,15 @@ static void recover_worker(struct kthread_work *work)
                      unsigned long flags;
 
                      spin_lock_irqsave(&ring->submit_lock, flags);
-                     list_for_each_entry(submit, &ring->submits, node)
+                     list_for_each_entry(submit, &ring->submits, node) {
                              gpu->funcs->submit(gpu, submit);
+                             restart_hangcheck = true;
+                     }
                      spin_unlock_irqrestore(&ring->submit_lock, flags);
              }
+
+             if (restart_hangcheck)
+                     hangcheck_timer_reset(gpu);
      }
 

drivers/gpu/drm/msm/msm_gpu.c static void hangcheck_handler(struct timer_list *t) · line 518

Quoted 6 lines

drivers/gpu/drm/msm/msm_gpu.c +0 -1

      mutex_unlock(&gpu->lock);

@@ -515,10 +523,6 @@ static void hangcheck_handler(struct timer_list *t)
              kthread_queue_work(gpu->worker, &gpu->recover_work);
      }
 
-     /* if still more pending work, reset the hangcheck timer: */

In the scenario mentioned here, shouldn't we restart the timer?

-Akhil.

Quoted 7 lines

drivers/gpu/drm/msm/msm_gpu.c +0 -3

-     if (fence_after(ring->fctx->last_fence, ring->hangcheck_fence))
-             hangcheck_timer_reset(gpu);
-
      /* workaround for missing irq: */
      msm_gpu_retire(gpu);
  }

Quoted 57 lines · Akhil P Oommen

Quoted 56 lines · Rob Clark

From: Rob Clark <[email protected]>

Don't directly restart the hangcheck timer from the timer handler, but instead start it after the recover_worker replays remaining jobs.

If the kthread is blocked for other reasons, there is no point to immediately restart the timer. Fixes a random symptom of the problem fixed in the next patch.

Signed-off-by Rob Clark <[email protected]>

---
   drivers/gpu/drm/msm/msm_gpu.c | 14 +++++++++-----
   1 file changed, 9 insertions(+), 5 deletions(-)

drivers/gpu/drm/msm/msm_gpu.c +9 -1

index fba85f894314..8f9c48eabf7d 100644
@@ -328,6 +328,7 @@ find_submit(struct msm_ringbuffer *ring, uint32_t fence)
   }
 
   static void retire_submits(struct msm_gpu *gpu);
+static void hangcheck_timer_reset(struct msm_gpu *gpu);
 
   static void get_comm_cmdline(struct msm_gem_submit *submit, char **comm, char **cmd)
   {

@@ -420,6 +421,8 @@ static void recover_worker(struct kthread_work *work)
       }
 
       if (msm_gpu_active(gpu)) {
+             bool restart_hangcheck = false;
+
               /* retire completed submits, plus the one that hung: */
               retire_submits(gpu);
 

@@ -436,10 +439,15 @@ static void recover_worker(struct kthread_work *work)
                       unsigned long flags;
 
                       spin_lock_irqsave(&ring->submit_lock, flags);
-                     list_for_each_entry(submit, &ring->submits, node)
+                     list_for_each_entry(submit, &ring->submits, node) {
                               gpu->funcs->submit(gpu, submit);
+                             restart_hangcheck = true;
+                     }
                       spin_unlock_irqrestore(&ring->submit_lock, flags);
               }
+
+             if (restart_hangcheck)
+                     hangcheck_timer_reset(gpu);
       }
 
       mutex_unlock(&gpu->lock);

@@ -515,10 +523,6 @@ static void hangcheck_handler(struct timer_list *t)
               kthread_queue_work(gpu->worker, &gpu->recover_work);
       }
 

Quoted 2 lines

drivers/gpu/drm/msm/msm_gpu.c static void hangcheck_handler(struct timer_list *t) · line 518

Quoted 1 line

drivers/gpu/drm/msm/msm_gpu.c +0 -1

-     /* if still more pending work, reset the hangcheck timer: */

In the scenario mentioned here, shouldn't we restart the timer?

yeah, actually the case where we don't want to restart the timer is *only* when we schedule recover_work..

BR,
-R

Quoted 9 lines

-Akhil.

Quoted 7 lines

drivers/gpu/drm/msm/msm_gpu.c +0 -3

-     if (fence_after(ring->fctx->last_fence, ring->hangcheck_fence))
-             hangcheck_timer_reset(gpu);
-
       /* workaround for missing irq: */
       msm_gpu_retire(gpu);
   }

Quoted 63 lines · Rob Clark

Quoted 52 lines · Akhil P Oommen

Quoted 51 lines · Rob Clark

From: Rob Clark <[email protected]>

Don't directly restart the hangcheck timer from the timer handler, but instead start it after the recover_worker replays remaining jobs.

If the kthread is blocked for other reasons, there is no point to immediately restart the timer. Fixes a random symptom of the problem fixed in the next patch.

Signed-off-by Rob Clark <[email protected]>

---
   drivers/gpu/drm/msm/msm_gpu.c | 14 +++++++++-----
   1 file changed, 9 insertions(+), 5 deletions(-)

drivers/gpu/drm/msm/msm_gpu.c +9 -1

index fba85f894314..8f9c48eabf7d 100644
@@ -328,6 +328,7 @@ find_submit(struct msm_ringbuffer *ring, uint32_t fence)
   }
 
   static void retire_submits(struct msm_gpu *gpu);
+static void hangcheck_timer_reset(struct msm_gpu *gpu);
 
   static void get_comm_cmdline(struct msm_gem_submit *submit, char **comm, char **cmd)
   {

@@ -420,6 +421,8 @@ static void recover_worker(struct kthread_work *work)
       }
 
       if (msm_gpu_active(gpu)) {
+             bool restart_hangcheck = false;
+
               /* retire completed submits, plus the one that hung: */
               retire_submits(gpu);
 

@@ -436,10 +439,15 @@ static void recover_worker(struct kthread_work *work)
                       unsigned long flags;
 
                       spin_lock_irqsave(&ring->submit_lock, flags);
-                     list_for_each_entry(submit, &ring->submits, node)
+                     list_for_each_entry(submit, &ring->submits, node) {
                               gpu->funcs->submit(gpu, submit);
+                             restart_hangcheck = true;
+                     }
                       spin_unlock_irqrestore(&ring->submit_lock, flags);
               }
+
+             if (restart_hangcheck)
+                     hangcheck_timer_reset(gpu);
       }
 

Quoted 7 lines

drivers/gpu/drm/msm/msm_gpu.c static void hangcheck_handler(struct timer_list *t) · line 518

Quoted 6 lines

drivers/gpu/drm/msm/msm_gpu.c +0 -1

       mutex_unlock(&gpu->lock);

@@ -515,10 +523,6 @@ static void hangcheck_handler(struct timer_list *t)
               kthread_queue_work(gpu->worker, &gpu->recover_work);
       }
 
-     /* if still more pending work, reset the hangcheck timer: */

In the scenario mentioned here, shouldn't we restart the timer?

yeah, actually the case where we don't want to restart the timer is *only* when we schedule recover_work..

Quoted 2 lines

BR,
-R

Not sure if your codebase is different but based on msm-next branch, when "if (fence != ring->hangcheck_fence)" is true, we now skip rescheduling the timer. I don't think that is what we want. There should be a hangcheck timer running as long as there is an active submit, unless we have scheduled a recover_work here.

-Akhil.

Quoted 9 lines

Quoted 9 lines

-Akhil.

Quoted 7 lines

drivers/gpu/drm/msm/msm_gpu.c +0 -3

-     if (fence_after(ring->fctx->last_fence, ring->hangcheck_fence))
-             hangcheck_timer_reset(gpu);
-
       /* workaround for missing irq: */
       msm_gpu_retire(gpu);
   }