[Intel-gfx] [PATCH 2/5] drm/i915: Include bound and active pages in the count of shrinkable objects

[Chris Wilson]

When the machine is under a lot of memory pressure and being stressed by
multiple GPU threads, we quite often report fewer than shrinker->batch
(i.e. SHRINK_BATCH) pages to be freed. This causes the shrink_control to
skip calling into i915.ko to release pages, despite the GPU holding onto
most of the physical pages in its active lists.

References: https://bugs.freedesktop.org/show_bug.cgi?id=72742
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Reviewed-by: Rafael Barbalho <rafael.barbalho at intel.com>
---
 drivers/gpu/drm/i915/i915_dma.c |  8 ++++----
 drivers/gpu/drm/i915/i915_drv.h |  2 +-
 drivers/gpu/drm/i915/i915_gem.c | 42 +++++++++++++++++++++++------------------
 3 files changed, 29 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index dea455bd889a..bf813967728a 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1741,8 +1741,8 @@ out_power_well:
 	intel_power_domains_remove(dev_priv);
 	drm_vblank_cleanup(dev);
 out_gem_unload:
-	if (dev_priv->mm.inactive_shrinker.scan_objects)
-		unregister_shrinker(&dev_priv->mm.inactive_shrinker);
+	if (dev_priv->mm.shrinker.scan_objects)
+		unregister_shrinker(&dev_priv->mm.shrinker);
 
 	if (dev->pdev->msi_enabled)
 		pci_disable_msi(dev->pdev);
@@ -1793,8 +1793,8 @@ int i915_driver_unload(struct drm_device *dev)
 
 	i915_teardown_sysfs(dev);
 
-	if (dev_priv->mm.inactive_shrinker.scan_objects)
-		unregister_shrinker(&dev_priv->mm.inactive_shrinker);
+	if (dev_priv->mm.shrinker.scan_objects)
+		unregister_shrinker(&dev_priv->mm.shrinker);
 
 	io_mapping_free(dev_priv->gtt.mappable);
 	arch_phys_wc_del(dev_priv->gtt.mtrr);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 5d5e57dc4201..e69cb51de738 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1057,7 +1057,7 @@ struct i915_gem_mm {
 	/** PPGTT used for aliasing the PPGTT with the GTT */
 	struct i915_hw_ppgtt *aliasing_ppgtt;
 
-	struct shrinker inactive_shrinker;
+	struct shrinker shrinker;
 	bool shrinker_no_lock_stealing;
 
 	/** LRU list of objects with fence regs on them. */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index f0e4c5609adb..fa46d987cd3a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -57,9 +57,9 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
 					 struct drm_i915_fence_reg *fence,
 					 bool enable);
 
-static unsigned long i915_gem_inactive_count(struct shrinker *shrinker,
+static unsigned long i915_gem_shrinker_count(struct shrinker *shrinker,
 					     struct shrink_control *sc);
-static unsigned long i915_gem_inactive_scan(struct shrinker *shrinker,
+static unsigned long i915_gem_shrinker_scan(struct shrinker *shrinker,
 					    struct shrink_control *sc);
 static unsigned long i915_gem_purge(struct drm_i915_private *dev_priv, long target);
 static unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
@@ -4739,10 +4739,10 @@ i915_gem_load(struct drm_device *dev)
 
 	dev_priv->mm.interruptible = true;
 
-	dev_priv->mm.inactive_shrinker.scan_objects = i915_gem_inactive_scan;
-	dev_priv->mm.inactive_shrinker.count_objects = i915_gem_inactive_count;
-	dev_priv->mm.inactive_shrinker.seeks = DEFAULT_SEEKS;
-	register_shrinker(&dev_priv->mm.inactive_shrinker);
+	dev_priv->mm.shrinker.scan_objects = i915_gem_shrinker_scan;
+	dev_priv->mm.shrinker.count_objects = i915_gem_shrinker_count;
+	dev_priv->mm.shrinker.seeks = DEFAULT_SEEKS;
+	register_shrinker(&dev_priv->mm.shrinker);
 }
 
 /*
@@ -5001,13 +5001,23 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
 #endif
 }
 
+static int num_vma_bound(struct drm_i915_gem_object *obj)
+{
+	struct i915_vma *vma;
+	int count = 0;
+
+	list_for_each_entry(vma, &obj->vma_list, vma_link)
+		if (drm_mm_node_allocated(&vma->node))
+			count++;
+
+	return count;
+}
+
 static unsigned long
-i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc)
+i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 {
 	struct drm_i915_private *dev_priv =
-		container_of(shrinker,
-			     struct drm_i915_private,
-			     mm.inactive_shrinker);
+		container_of(shrinker, struct drm_i915_private, mm.shrinker);
 	struct drm_device *dev = dev_priv->dev;
 	struct drm_i915_gem_object *obj;
 	bool unlock = true;
@@ -5029,10 +5039,8 @@ i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc)
 			count += obj->base.size >> PAGE_SHIFT;
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if (obj->active)
-			continue;
-
-		if (!i915_gem_obj_is_pinned(obj) && obj->pages_pin_count == 0)
+		if (!i915_gem_obj_is_pinned(obj) &&
+		    obj->pages_pin_count == num_vma_bound(obj))
 			count += obj->base.size >> PAGE_SHIFT;
 	}
 
@@ -5105,12 +5113,10 @@ unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
 }
 
 static unsigned long
-i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc)
+i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 {
 	struct drm_i915_private *dev_priv =
-		container_of(shrinker,
-			     struct drm_i915_private,
-			     mm.inactive_shrinker);
+		container_of(shrinker, struct drm_i915_private, mm.shrinker);
 	struct drm_device *dev = dev_priv->dev;
 	unsigned long freed;
 	bool unlock = true;
-- 
2.0.0.rc2