[PATCH v2 1/2] drm/msm: Move hangcheck timer restart

[Rob Clark <robdclark@xxxxxxxxx>]

From: Rob Clark <robdclark@xxxxxxxxxxxx>

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.

v2: Keep the hangcheck timer restart in the timer handler in the case
    where we aren't scheduling recover_worker

Signed-off-by: Rob Clark <robdclark@xxxxxxxxxxxx>
---
 drivers/gpu/drm/msm/msm_gpu.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index fba85f894314..6762001d9945 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -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);
@@ -498,6 +506,7 @@ static void hangcheck_handler(struct timer_list *t)
 	struct drm_device *dev = gpu->dev;
 	struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu);
 	uint32_t fence = ring->memptrs->fence;
+	bool restart_hangcheck = true;
 
 	if (fence != ring->hangcheck_fence) {
 		/* some progress has been made.. ya! */
@@ -513,10 +522,16 @@ static void hangcheck_handler(struct timer_list *t)
 				gpu->name, ring->fctx->last_fence);
 
 		kthread_queue_work(gpu->worker, &gpu->recover_work);
+
+		/* If we do recovery, we want to defer restarting the hangcheck
+		 * timer until recovery completes and the remaining non-guilty
+		 * jobs are re-played.
+		 */
+		restart_hangcheck = false;
 	}
 
 	/* if still more pending work, reset the hangcheck timer: */
-	if (fence_after(ring->fctx->last_fence, ring->hangcheck_fence))
+	if (restart_hangcheck && fence_after(ring->fctx->last_fence, ring->hangcheck_fence))
 		hangcheck_timer_reset(gpu);
 
 	/* workaround for missing irq: */
-- 
2.36.1