drm/i915: Try harder to finish the idle-worker

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@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006104038.22337-1-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/i915_debugfs.c

@@ -4259,8 +4259,7 @@ 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;
 

drivers/gpu/drm/i915/i915_gem.c

@@ -4547,8 +4547,7 @@ 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.

drivers/gpu/drm/i915/i915_utils.h

@@ -124,4 +124,17 @@ 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 */