[Intel-gfx] [PATCH 04/11] drm/i915: Try harder to finish the idle-worker

[Chris Wilson]

If a worker requeues itself, it may switch to a different kworker pool,
which flush_work() considers as complete. To be strict, we then need to
keep flushing the work until it is no longer pending.

References: https://bugs.freedesktop.org/show_bug.cgi?id=102456
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c |  3 +--
 drivers/gpu/drm/i915/i915_gem.c     |  3 +--
 drivers/gpu/drm/i915/i915_utils.h   | 13 +++++++++++++
 3 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 6338018f655d..d65558f650d6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -4256,8 +4256,7 @@ fault_irq_set(struct drm_i915_private *i915,
 	mutex_unlock(&i915->drm.struct_mutex);
 
 	/* Flush idle worker to disarm irq */
-	while (flush_delayed_work(&i915->gt.idle_work))
-		;
+	drain_delayed_work(&i915->gt.idle_work);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index f445587c1a4b..d98f7b25d395 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4583,8 +4583,7 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 	/* As the idle_work is rearming if it detects a race, play safe and
 	 * repeat the flush until it is definitely idle.
 	 */
-	while (flush_delayed_work(&dev_priv->gt.idle_work))
-		;
+	drain_delayed_work(&dev_priv->gt.idle_work);
 
 	/* Assert that we sucessfully flushed all the work and
 	 * reset the GPU back to its idle, low power state.
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index 12fc250b47b9..4f7ffa0976b1 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -119,4 +119,17 @@ static inline void __list_del_many(struct list_head *head,
 	WRITE_ONCE(head->next, first);
 }
 
+/*
+ * Wait until the work is finally complete, even if it tries to postpone
+ * by requeueing itself. Note, that if the worker never cancels itself,
+ * we will spin forever.
+ */
+static inline void drain_delayed_work(struct delayed_work *dw)
+{
+	do {
+		while (flush_delayed_work(dw))
+			;
+	} while (delayed_work_pending(dw));
+}
+
 #endif /* !__I915_UTILS_H */
-- 
2.14.1