[Intel-gfx] [PATCH v2] drm/i915: Repeat flush of idle work during suspend

[Chris Wilson]

The idle work handler is self-arming - if it detects that it needs to
run again it will queue itself from its work handler. Take greater care
when trying to drain the idle work, and double check that it is flushed.

The free worker has a similar issue where it is armed by an RCU task
which may be running concurrently with us.

This should hopefully help with the sporadic WARN_ON(dev_priv->gt.awake)
from i915_gem_suspend.

v2: Reuse drain_freed_objects.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.c          | 3 +--
 drivers/gpu/drm/i915/i915_drv.h          | 7 +++++++
 drivers/gpu/drm/i915/i915_gem.c          | 6 ++++--
 drivers/gpu/drm/i915/i915_gem_shrinker.c | 4 +++-
 4 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 6428588518aa..2c020eafada6 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -545,8 +545,7 @@ static void i915_gem_fini(struct drm_i915_private *dev_priv)
 	i915_gem_context_fini(dev_priv);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
-	rcu_barrier();
-	flush_work(&dev_priv->mm.free_work);
+	i915_gem_drain_freed_objects(dev_priv);
 
 	WARN_ON(!list_empty(&dev_priv->context_list));
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 77d7a079c51b..37ea557d3cd4 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3207,6 +3207,13 @@ i915_gem_object_create_from_data(struct drm_i915_private *dev_priv,
 void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file);
 void i915_gem_free_object(struct drm_gem_object *obj);
 
+static inline void i915_gem_drain_freed_objects(struct drm_i915_private *i915)
+{
+	rcu_barrier();
+	while (flush_work(&i915->mm.free_work))
+		rcu_barrier();
+}
+
 struct i915_vma * __must_check
 i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			 const struct i915_ggtt_view *view,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5275f6248ce3..6f131d463322 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4264,8 +4264,10 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 
 	cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
 	cancel_delayed_work_sync(&dev_priv->gt.retire_work);
-	flush_delayed_work(&dev_priv->gt.idle_work);
-	flush_work(&dev_priv->mm.free_work);
+	while (flush_delayed_work(&dev_priv->gt.idle_work))
+		;
+
+	i915_gem_drain_freed_objects(dev_priv);
 
 	/* 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_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index a6fc1bdc48af..2034047ab8e1 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -272,7 +272,9 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 				I915_SHRINK_BOUND |
 				I915_SHRINK_UNBOUND |
 				I915_SHRINK_ACTIVE);
-	rcu_barrier(); /* wait until our RCU delayed slab frees are completed */
+
+	/* wait until our RCU delayed slab frees are completed */
+	i915_gem_drain_freed_objects(dev_priv);
 
 	return freed;
 }
-- 
2.11.0