drm/msm/shrinker: Only iterate dontneed objs

In situations where the GPU is mostly idle, all or nearly all buffer
objects will be in the inactive list.  But if the system is under memory
pressure (from something other than GPU), we could still get a lot of
shrinker calls.  Which results in traversing a list of thousands of objs
and in the end finding nothing to shrink.  Which isn't so efficient.

Instead split the inactive_list into two lists, one inactive objs which
are shrinkable, and a second one for those that are not.  This way we
can avoid traversing objs which we know are not shrinker candidates.

v2: Fix inverted logic think-o
Signed-off-by: Rob Clark <robdclark@chromium.org>

drivers/gpu/drm/msm/msm_debugfs.c

@@ -124,7 +124,8 @@ static int msm_gem_show(struct drm_device *dev, struct seq_file *m)
 	}
 
 	seq_printf(m, "Inactive Objects:\n");
-	msm_gem_describe_objects(&priv->inactive_list, m);
+	msm_gem_describe_objects(&priv->inactive_dontneed, m);
+	msm_gem_describe_objects(&priv->inactive_willneed, m);
 
 	mutex_unlock(&priv->mm_lock);
 

drivers/gpu/drm/msm/msm_drv.c

@@ -438,7 +438,8 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
 	priv->wq = alloc_ordered_workqueue("msm", 0);
 
-	INIT_LIST_HEAD(&priv->inactive_list);
+	INIT_LIST_HEAD(&priv->inactive_willneed);
+	INIT_LIST_HEAD(&priv->inactive_dontneed);
 	mutex_init(&priv->mm_lock);
 
 	/* Teach lockdep about lock ordering wrt. shrinker: */

drivers/gpu/drm/msm/msm_drv.h

@@ -175,8 +175,9 @@ struct msm_drm_private {
 	struct msm_perf_state *perf;
 
 	/*
-	 * List of inactive GEM objects.  Every bo is either in the inactive_list
-	 * or gpu->active_list (for the gpu it is active on[1])
+	 * Lists of inactive GEM objects.  Every bo is either in one of the
+	 * inactive lists (depending on whether or not it is shrinkable) or
+	 * gpu->active_list (for the gpu it is active on[1])
 	 *
 	 * These lists are protected by mm_lock.  If struct_mutex is involved, it
 	 * should be aquired prior to mm_lock.  One should *not* hold mm_lock in
@@ -185,7 +186,8 @@ struct msm_drm_private {
 	 * [1] if someone ever added support for the old 2d cores, there could be
 	 *     more than one gpu object
 	 */
-	struct list_head inactive_list;
+	struct list_head inactive_willneed;  /* inactive + !shrinkable */
+	struct list_head inactive_dontneed;  /* inactive +  shrinkable */
 	struct mutex mm_lock;
 
 	struct workqueue_struct *wq;

drivers/gpu/drm/msm/msm_gem.c

@@ -18,6 +18,7 @@
 #include "msm_gpu.h"
 #include "msm_mmu.h"
 
+static void update_inactive(struct msm_gem_object *msm_obj);
 
 static dma_addr_t physaddr(struct drm_gem_object *obj)
 {
@@ -677,6 +678,12 @@ int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv)
 
 	madv = msm_obj->madv;
 
+	/* If the obj is inactive, we might need to move it
+	 * between inactive lists
+	 */
+	if (msm_obj->active_count == 0)
+		update_inactive(msm_obj);
+
 	msm_gem_unlock(obj);
 
 	return (madv != __MSM_MADV_PURGED);
@@ -780,19 +787,31 @@ void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu)
 void msm_gem_active_put(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-	struct msm_drm_private *priv = obj->dev->dev_private;
 
 	might_sleep();
 	WARN_ON(!msm_gem_is_locked(obj));
 
 	if (--msm_obj->active_count == 0) {
-		mutex_lock(&priv->mm_lock);
-		list_del_init(&msm_obj->mm_list);
-		list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
-		mutex_unlock(&priv->mm_lock);
+		update_inactive(msm_obj);
 	}
 }
 
+static void update_inactive(struct msm_gem_object *msm_obj)
+{
+	struct msm_drm_private *priv = msm_obj->base.dev->dev_private;
+
+	mutex_lock(&priv->mm_lock);
+	WARN_ON(msm_obj->active_count != 0);
+
+	list_del_init(&msm_obj->mm_list);
+	if (msm_obj->madv == MSM_MADV_WILLNEED)
+		list_add_tail(&msm_obj->mm_list, &priv->inactive_willneed);
+	else
+		list_add_tail(&msm_obj->mm_list, &priv->inactive_dontneed);
+
+	mutex_unlock(&priv->mm_lock);
+}
+
 int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout)
 {
 	bool write = !!(op & MSM_PREP_WRITE);
@@ -1098,7 +1117,8 @@ static struct drm_gem_object *_msm_gem_new(struct drm_device *dev,
 	}
 
 	mutex_lock(&priv->mm_lock);
-	list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+	/* Initially obj is idle, obj->madv == WILLNEED: */
+	list_add_tail(&msm_obj->mm_list, &priv->inactive_willneed);
 	mutex_unlock(&priv->mm_lock);
 
 	return obj;
@@ -1168,7 +1188,7 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev,
 	msm_gem_unlock(obj);
 
 	mutex_lock(&priv->mm_lock);
-	list_add_tail(&msm_obj->mm_list, &priv->inactive_list);
+	list_add_tail(&msm_obj->mm_list, &priv->inactive_willneed);
 	mutex_unlock(&priv->mm_lock);
 
 	return obj;

drivers/gpu/drm/msm/msm_gem_shrinker.c

@@ -19,7 +19,7 @@ msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 
 	mutex_lock(&priv->mm_lock);
 
-	list_for_each_entry(msm_obj, &priv->inactive_list, mm_list) {
+	list_for_each_entry(msm_obj, &priv->inactive_dontneed, mm_list) {
 		if (!msm_gem_trylock(&msm_obj->base))
 			continue;
 		if (is_purgeable(msm_obj))
@@ -42,7 +42,7 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 
 	mutex_lock(&priv->mm_lock);
 
-	list_for_each_entry(msm_obj, &priv->inactive_list, mm_list) {
+	list_for_each_entry(msm_obj, &priv->inactive_dontneed, mm_list) {
 		if (freed >= sc->nr_to_scan)
 			break;
 		if (!msm_gem_trylock(&msm_obj->base))
@@ -96,7 +96,8 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr)
 	struct msm_drm_private *priv =
 		container_of(nb, struct msm_drm_private, vmap_notifier);
 	struct list_head *mm_lists[] = {
-		&priv->inactive_list,
+		&priv->inactive_dontneed,
+		&priv->inactive_willneed,
 		priv->gpu ? &priv->gpu->active_list : NULL,
 		NULL,
 	};