[Intel-gfx] [PATCH 3/4] drm/i915: Cancel retire_worker on parking

[Chris Wilson]

Replace the racy continuation check within retire_work with a definite
kill-switch on idling. The race was being exposed by gem_concurrent_blit
where the retire_worker would be terminated too early leaving us
spinning in debugfs/i915_drop_caches with nothing flushing the
retirement queue.

Although that the igt is trying to idle from one child while submitting
from another may be a contributing factor as to why  it runs so slowly...

v2: Use the non-sync version of cancel_delayed_work(), we only need to
stop it from being scheduled as we independently check whether now is
the right time to be parking.

Testcase: igt/gem_concurrent_blit
Fixes: 79ffac8599c4 ("drm/i915: Invert the GEM wakeref hierarchy")
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_gem_pm.c             | 18 ++++++++++++------
 .../gpu/drm/i915/selftests/mock_gem_device.c   |  1 -
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_pm.c b/drivers/gpu/drm/i915/i915_gem_pm.c
index ae91ad7cb31e..fa9c2ebd966a 100644
--- a/drivers/gpu/drm/i915/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/i915_gem_pm.c
@@ -30,15 +30,23 @@ static void idle_work_handler(struct work_struct *work)
 {
 	struct drm_i915_private *i915 =
 		container_of(work, typeof(*i915), gem.idle_work);
+	bool restart = true;
 
+	cancel_delayed_work(&i915->gem.retire_work);
 	mutex_lock(&i915->drm.struct_mutex);
 
 	intel_wakeref_lock(&i915->gt.wakeref);
-	if (!intel_wakeref_active(&i915->gt.wakeref) && !work_pending(work))
+	if (!intel_wakeref_active(&i915->gt.wakeref) && !work_pending(work)) {
 		i915_gem_park(i915);
+		restart = false;
+	}
 	intel_wakeref_unlock(&i915->gt.wakeref);
 
 	mutex_unlock(&i915->drm.struct_mutex);
+	if (restart)
+		queue_delayed_work(i915->wq,
+				   &i915->gem.retire_work,
+				   round_jiffies_up_relative(HZ));
 }
 
 static void retire_work_handler(struct work_struct *work)
@@ -52,10 +60,9 @@ static void retire_work_handler(struct work_struct *work)
 		mutex_unlock(&i915->drm.struct_mutex);
 	}
 
-	if (intel_wakeref_active(&i915->gt.wakeref))
-		queue_delayed_work(i915->wq,
-				   &i915->gem.retire_work,
-				   round_jiffies_up_relative(HZ));
+	queue_delayed_work(i915->wq,
+			   &i915->gem.retire_work,
+			   round_jiffies_up_relative(HZ));
 }
 
 static int pm_notifier(struct notifier_block *nb,
@@ -140,7 +147,6 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	 * Assert that we successfully flushed all the work and
 	 * reset the GPU back to its idle, low power state.
 	 */
-	drain_delayed_work(&i915->gem.retire_work);
 	GEM_BUG_ON(i915->gt.awake);
 	flush_work(&i915->gem.idle_work);
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index d919f512042c..9fd02025d382 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -58,7 +58,6 @@ static void mock_device_release(struct drm_device *dev)
 	i915_gem_contexts_lost(i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
-	drain_delayed_work(&i915->gem.retire_work);
 	flush_work(&i915->gem.idle_work);
 	i915_gem_drain_workqueue(i915);
 
-- 
2.20.1