1 files changed, 300 insertions, 111 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 562e87cbd7a1..5199b9696bab 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -185,39 +185,181 @@ static LIST_HEAD(shrinker_list);
 static DECLARE_RWSEM(shrinker_rwsem);
 
 #ifdef CONFIG_MEMCG
-/*
- * We allow subsystems to populate their shrinker-related
- * LRU lists before register_shrinker_prepared() is called
- * for the shrinker, since we don't want to impose
- * restrictions on their internal registration order.
- * In this case shrink_slab_memcg() may find corresponding
- * bit is set in the shrinkers map.
- *
- * This value is used by the function to detect registering
- * shrinkers and to skip do_shrink_slab() calls for them.
- */
-#define SHRINKER_REGISTERING ((struct shrinker *)~0UL)
+static int shrinker_nr_max;
+
+/* The shrinker_info is expanded in a batch of BITS_PER_LONG */
+static inline int shrinker_map_size(int nr_items)
+{
+	return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long));
+}
+
+static inline int shrinker_defer_size(int nr_items)
+{
+	return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t));
+}
+
+static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg,
+						     int nid)
+{
+	return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info,
+					 lockdep_is_held(&shrinker_rwsem));
+}
+
+static int expand_one_shrinker_info(struct mem_cgroup *memcg,
+				    int map_size, int defer_size,
+				    int old_map_size, int old_defer_size)
+{
+	struct shrinker_info *new, *old;
+	struct mem_cgroup_per_node *pn;
+	int nid;
+	int size = map_size + defer_size;
+
+	for_each_node(nid) {
+		pn = memcg->nodeinfo[nid];
+		old = shrinker_info_protected(memcg, nid);
+		/* Not yet online memcg */
+		if (!old)
+			return 0;
+
+		new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid);
+		if (!new)
+			return -ENOMEM;
+
+		new->nr_deferred = (atomic_long_t *)(new + 1);
+		new->map = (void *)new->nr_deferred + defer_size;
+
+		/* map: set all old bits, clear all new bits */
+		memset(new->map, (int)0xff, old_map_size);
+		memset((void *)new->map + old_map_size, 0, map_size - old_map_size);
+		/* nr_deferred: copy old values, clear all new values */
+		memcpy(new->nr_deferred, old->nr_deferred, old_defer_size);
+		memset((void *)new->nr_deferred + old_defer_size, 0,
+		       defer_size - old_defer_size);
+
+		rcu_assign_pointer(pn->shrinker_info, new);
+		kvfree_rcu(old, rcu);
+	}
+
+	return 0;
+}
+
+void free_shrinker_info(struct mem_cgroup *memcg)
+{
+	struct mem_cgroup_per_node *pn;
+	struct shrinker_info *info;
+	int nid;
+
+	for_each_node(nid) {
+		pn = memcg->nodeinfo[nid];
+		info = rcu_dereference_protected(pn->shrinker_info, true);
+		kvfree(info);
+		rcu_assign_pointer(pn->shrinker_info, NULL);
+	}
+}
+
+int alloc_shrinker_info(struct mem_cgroup *memcg)
+{
+	struct shrinker_info *info;
+	int nid, size, ret = 0;
+	int map_size, defer_size = 0;
+
+	down_write(&shrinker_rwsem);
+	map_size = shrinker_map_size(shrinker_nr_max);
+	defer_size = shrinker_defer_size(shrinker_nr_max);
+	size = map_size + defer_size;
+	for_each_node(nid) {
+		info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid);
+		if (!info) {
+			free_shrinker_info(memcg);
+			ret = -ENOMEM;
+			break;
+		}
+		info->nr_deferred = (atomic_long_t *)(info + 1);
+		info->map = (void *)info->nr_deferred + defer_size;
+		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info);
+	}
+	up_write(&shrinker_rwsem);
+
+	return ret;
+}
+
+static inline bool need_expand(int nr_max)
+{
+	return round_up(nr_max, BITS_PER_LONG) >
+	       round_up(shrinker_nr_max, BITS_PER_LONG);
+}
+
+static int expand_shrinker_info(int new_id)
+{
+	int ret = 0;
+	int new_nr_max = new_id + 1;
+	int map_size, defer_size = 0;
+	int old_map_size, old_defer_size = 0;
+	struct mem_cgroup *memcg;
+
+	if (!need_expand(new_nr_max))
+		goto out;
+
+	if (!root_mem_cgroup)
+		goto out;
+
+	lockdep_assert_held(&shrinker_rwsem);
+
+	map_size = shrinker_map_size(new_nr_max);
+	defer_size = shrinker_defer_size(new_nr_max);
+	old_map_size = shrinker_map_size(shrinker_nr_max);
+	old_defer_size = shrinker_defer_size(shrinker_nr_max);
+
+	memcg = mem_cgroup_iter(NULL, NULL, NULL);
+	do {
+		ret = expand_one_shrinker_info(memcg, map_size, defer_size,
+					       old_map_size, old_defer_size);
+		if (ret) {
+			mem_cgroup_iter_break(NULL, memcg);
+			goto out;
+		}
+	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
+out:
+	if (!ret)
+		shrinker_nr_max = new_nr_max;
+
+	return ret;
+}
+
+void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
+{
+	if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) {
+		struct shrinker_info *info;
+
+		rcu_read_lock();
+		info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info);
+		/* Pairs with smp mb in shrink_slab() */
+		smp_mb__before_atomic();
+		set_bit(shrinker_id, info->map);
+		rcu_read_unlock();
+	}
+}
 
 static DEFINE_IDR(shrinker_idr);
-static int shrinker_nr_max;
 
 static int prealloc_memcg_shrinker(struct shrinker *shrinker)
 {
 	int id, ret = -ENOMEM;
 
+	if (mem_cgroup_disabled())
+		return -ENOSYS;
+
 	down_write(&shrinker_rwsem);
 	/* This may call shrinker, so it must use down_read_trylock() */
-	id = idr_alloc(&shrinker_idr, SHRINKER_REGISTERING, 0, 0, GFP_KERNEL);
+	id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL);
 	if (id < 0)
 		goto unlock;
 
 	if (id >= shrinker_nr_max) {
-		if (memcg_expand_shrinker_maps(id)) {
+		if (expand_shrinker_info(id)) {
 			idr_remove(&shrinker_idr, id);
 			goto unlock;
 		}
-
-		shrinker_nr_max = id + 1;
 	}
 	shrinker->id = id;
 	ret = 0;
@@ -232,9 +374,51 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker)
 
 	BUG_ON(id < 0);
 
-	down_write(&shrinker_rwsem);
+	lockdep_assert_held(&shrinker_rwsem);
+
 	idr_remove(&shrinker_idr, id);
-	up_write(&shrinker_rwsem);
+}
+
+static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker,
+				   struct mem_cgroup *memcg)
+{
+	struct shrinker_info *info;
+
+	info = shrinker_info_protected(memcg, nid);
+	return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0);
+}
+
+static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker,
+				  struct mem_cgroup *memcg)
+{
+	struct shrinker_info *info;
+
+	info = shrinker_info_protected(memcg, nid);
+	return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]);
+}
+
+void reparent_shrinker_deferred(struct mem_cgroup *memcg)
+{
+	int i, nid;
+	long nr;
+	struct mem_cgroup *parent;
+	struct shrinker_info *child_info, *parent_info;
+
+	parent = parent_mem_cgroup(memcg);
+	if (!parent)
+		parent = root_mem_cgroup;
+
+	/* Prevent from concurrent shrinker_info expand */
+	down_read(&shrinker_rwsem);
+	for_each_node(nid) {
+		child_info = shrinker_info_protected(memcg, nid);
+		parent_info = shrinker_info_protected(parent, nid);
+		for (i = 0; i < shrinker_nr_max; i++) {
+			nr = atomic_long_read(&child_info->nr_deferred[i]);
+			atomic_long_add(nr, &parent_info->nr_deferred[i]);
+		}
+	}
+	up_read(&shrinker_rwsem);
 }
 
 static bool cgroup_reclaim(struct scan_control *sc)
@@ -268,13 +452,25 @@ static bool writeback_throttling_sane(struct scan_control *sc)
 #else
 static int prealloc_memcg_shrinker(struct shrinker *shrinker)
 {
-	return 0;
+	return -ENOSYS;
 }
 
 static void unregister_memcg_shrinker(struct shrinker *shrinker)
 {
 }
 
+static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker,
+				   struct mem_cgroup *memcg)
+{
+	return 0;
+}
+
+static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker,
+				  struct mem_cgroup *memcg)
+{
+	return 0;
+}
+
 static bool cgroup_reclaim(struct scan_control *sc)
 {
 	return false;
@@ -286,6 +482,39 @@ static bool writeback_throttling_sane(struct scan_control *sc)
 }
 #endif
 
+static long xchg_nr_deferred(struct shrinker *shrinker,
+			     struct shrink_control *sc)
+{
+	int nid = sc->nid;
+
+	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
+		nid = 0;
+
+	if (sc->memcg &&
+	    (shrinker->flags & SHRINKER_MEMCG_AWARE))
+		return xchg_nr_deferred_memcg(nid, shrinker,
+					      sc->memcg);
+
+	return atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
+}
+
+
+static long add_nr_deferred(long nr, struct shrinker *shrinker,
+			    struct shrink_control *sc)
+{
+	int nid = sc->nid;
+
+	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
+		nid = 0;
+
+	if (sc->memcg &&
+	    (shrinker->flags & SHRINKER_MEMCG_AWARE))
+		return add_nr_deferred_memcg(nr, nid, shrinker,
+					     sc->memcg);
+
+	return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]);
+}
+
 /*
  * This misses isolated pages which are not accounted for to save counters.
  * As the data only determines if reclaim or compaction continues, it is
@@ -335,8 +564,18 @@ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru,
  */
 int prealloc_shrinker(struct shrinker *shrinker)
 {
-	unsigned int size = sizeof(*shrinker->nr_deferred);
+	unsigned int size;
+	int err;
+
+	if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
+		err = prealloc_memcg_shrinker(shrinker);
+		if (err != -ENOSYS)
+			return err;
+
+		shrinker->flags &= ~SHRINKER_MEMCG_AWARE;
+	}
 
+	size = sizeof(*shrinker->nr_deferred);
 	if (shrinker->flags & SHRINKER_NUMA_AWARE)
 		size *= nr_node_ids;
 
@@ -344,26 +583,17 @@ int prealloc_shrinker(struct shrinker *shrinker)
 	if (!shrinker->nr_deferred)
 		return -ENOMEM;
 
-	if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
-		if (prealloc_memcg_shrinker(shrinker))
-			goto free_deferred;
-	}
-
 	return 0;
-
-free_deferred:
-	kfree(shrinker->nr_deferred);
-	shrinker->nr_deferred = NULL;
-	return -ENOMEM;
 }
 
 void free_prealloced_shrinker(struct shrinker *shrinker)
 {
-	if (!shrinker->nr_deferred)
-		return;
-
-	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
+	if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
+		down_write(&shrinker_rwsem);
 		unregister_memcg_shrinker(shrinker);
+		up_write(&shrinker_rwsem);
+		return;
+	}
 
 	kfree(shrinker->nr_deferred);
 	shrinker->nr_deferred = NULL;
@@ -373,10 +603,7 @@ void register_shrinker_prepared(struct shrinker *shrinker)
 {
 	down_write(&shrinker_rwsem);
 	list_add_tail(&shrinker->list, &shrinker_list);
-#ifdef CONFIG_MEMCG
-	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
-		idr_replace(&shrinker_idr, shrinker, shrinker->id);
-#endif
+	shrinker->flags |= SHRINKER_REGISTERED;
 	up_write(&shrinker_rwsem);
 }
 
@@ -396,13 +623,16 @@ EXPORT_SYMBOL(register_shrinker);
  */
 void unregister_shrinker(struct shrinker *shrinker)
 {
-	if (!shrinker->nr_deferred)
+	if (!(shrinker->flags & SHRINKER_REGISTERED))
 		return;
-	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
-		unregister_memcg_shrinker(shrinker);
+
 	down_write(&shrinker_rwsem);
 	list_del(&shrinker->list);
+	shrinker->flags &= ~SHRINKER_REGISTERED;
+	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
+		unregister_memcg_shrinker(shrinker);
 	up_write(&shrinker_rwsem);
+
 	kfree(shrinker->nr_deferred);
 	shrinker->nr_deferred = NULL;
 }
@@ -419,14 +649,10 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	long freeable;
 	long nr;
 	long new_nr;
-	int nid = shrinkctl->nid;
 	long batch_size = shrinker->batch ? shrinker->batch
 					  : SHRINK_BATCH;
 	long scanned = 0, next_deferred;
 
-	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
-		nid = 0;
-
 	freeable = shrinker->count_objects(shrinker, shrinkctl);
 	if (freeable == 0 || freeable == SHRINK_EMPTY)
 		return freeable;
@@ -436,9 +662,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	 * and zero it so that other concurrent shrinker invocations
 	 * don't also do this scanning work.
 	 */
-	nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
+	nr = xchg_nr_deferred(shrinker, shrinkctl);
 
-	total_scan = nr;
 	if (shrinker->seeks) {
 		delta = freeable >> priority;
 		delta *= 4;
@@ -452,37 +677,9 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 		delta = freeable / 2;
 	}
 
+	total_scan = nr >> priority;
 	total_scan += delta;
-	if (total_scan < 0) {
-		pr_err("shrink_slab: %pS negative objects to delete nr=%ld\n",
-		       shrinker->scan_objects, total_scan);
-		total_scan = freeable;
-		next_deferred = nr;
-	} else
-		next_deferred = total_scan;
-
-	/*
-	 * We need to avoid excessive windup on filesystem shrinkers
-	 * due to large numbers of GFP_NOFS allocations causing the
-	 * shrinkers to return -1 all the time. This results in a large
-	 * nr being built up so when a shrink that can do some work
-	 * comes along it empties the entire cache due to nr >>>
-	 * freeable. This is bad for sustaining a working set in
-	 * memory.
-	 *
-	 * Hence only allow the shrinker to scan the entire cache when
-	 * a large delta change is calculated directly.
-	 */
-	if (delta < freeable / 4)
-		total_scan = min(total_scan, freeable / 2);
-
-	/*
-	 * Avoid risking looping forever due to too large nr value:
-	 * never try to free more than twice the estimate number of
-	 * freeable entries.
-	 */
-	if (total_scan > freeable * 2)
-		total_scan = freeable * 2;
+	total_scan = min(total_scan, (2 * freeable));
 
 	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
 				   freeable, delta, total_scan, priority);
@@ -521,22 +718,22 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 		cond_resched();
 	}
 
-	if (next_deferred >= scanned)
-		next_deferred -= scanned;
-	else
-		next_deferred = 0;
+	/*
+	 * The deferred work is increased by any new work (delta) that wasn't
+	 * done, decreased by old deferred work that was done now.
+	 *
+	 * And it is capped to two times of the freeable items.
+	 */
+	next_deferred = max_t(long, (nr + delta - scanned), 0);
+	next_deferred = min(next_deferred, (2 * freeable));
+
 	/*
 	 * move the unused scan count back into the shrinker in a
-	 * manner that handles concurrent updates. If we exhausted the
-	 * scan, there is no need to do an update.
+	 * manner that handles concurrent updates.
 	 */
-	if (next_deferred > 0)
-		new_nr = atomic_long_add_return(next_deferred,
-						&shrinker->nr_deferred[nid]);
-	else
-		new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);
+	new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl);
 
-	trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan);
+	trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan);
 	return freed;
 }
 
@@ -544,7 +741,7 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
 			struct mem_cgroup *memcg, int priority)
 {
-	struct memcg_shrinker_map *map;
+	struct shrinker_info *info;
 	unsigned long ret, freed = 0;
 	int i;
 
@@ -554,12 +751,11 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
 	if (!down_read_trylock(&shrinker_rwsem))
 		return 0;
 
-	map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map,
-					true);
-	if (unlikely(!map))
+	info = shrinker_info_protected(memcg, nid);
+	if (unlikely(!info))
 		goto unlock;
 
-	for_each_set_bit(i, map->map, shrinker_nr_max) {
+	for_each_set_bit(i, info->map, shrinker_nr_max) {
 		struct shrink_control sc = {
 			.gfp_mask = gfp_mask,
 			.nid = nid,
@@ -568,9 +764,9 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
 		struct shrinker *shrinker;
 
 		shrinker = idr_find(&shrinker_idr, i);
-		if (unlikely(!shrinker || shrinker == SHRINKER_REGISTERING)) {
+		if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) {
 			if (!shrinker)
-				clear_bit(i, map->map);
+				clear_bit(i, info->map);
 			continue;
 		}
 
@@ -581,7 +777,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
 
 		ret = do_shrink_slab(&sc, shrinker, priority);
 		if (ret == SHRINK_EMPTY) {
-			clear_bit(i, map->map);
+			clear_bit(i, info->map);
 			/*
 			 * After the shrinker reported that it had no objects to
 			 * free, but before we cleared the corresponding bit in
@@ -590,7 +786,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
 			 * case, we invoke the shrinker one more time and reset
 			 * the bit if it reports that it is not empty anymore.
 			 * The memory barrier here pairs with the barrier in
-			 * memcg_set_shrinker_bit():
+			 * set_shrinker_bit():
 			 *
 			 * list_lru_add()     shrink_slab_memcg()
 			 *   list_add_tail()    clear_bit()
@@ -602,7 +798,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
 			if (ret == SHRINK_EMPTY)
 				ret = 0;
 			else
-				memcg_set_shrinker_bit(memcg, nid, i);
+				set_shrinker_bit(memcg, nid, i);
 		}
 		freed += ret;
 
@@ -1507,8 +1703,9 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 	LIST_HEAD(clean_pages);
 
 	list_for_each_entry_safe(page, next, page_list, lru) {
-		if (page_is_file_lru(page) && !PageDirty(page) &&
-		    !__PageMovable(page) && !PageUnevictable(page)) {
+		if (!PageHuge(page) && page_is_file_lru(page) &&
+		    !PageDirty(page) && !__PageMovable(page) &&
+		    !PageUnevictable(page)) {
 			ClearPageActive(page);
 			list_move(&page->lru, &clean_pages);
 		}
@@ -3862,7 +4059,7 @@ static int kswapd(void *p)
 {
 	unsigned int alloc_order, reclaim_order;
 	unsigned int highest_zoneidx = MAX_NR_ZONES - 1;
-	pg_data_t *pgdat = (pg_data_t*)p;
+	pg_data_t *pgdat = (pg_data_t *)p;
 	struct task_struct *tsk = current;
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
@@ -4086,14 +4283,6 @@ module_init(kswapd_init)
 int node_reclaim_mode __read_mostly;
 
 /*
- * These bit locations are exposed in the vm.zone_reclaim_mode sysctl
- * ABI.  New bits are OK, but existing bits can never change.
- */
-#define RECLAIM_ZONE  (1<<0)   /* Run shrink_inactive_list on the zone */
-#define RECLAIM_WRITE (1<<1)   /* Writeout pages during reclaim */
-#define RECLAIM_UNMAP (1<<2)   /* Unmap pages during reclaim */
-
-/*
  * Priority for NODE_RECLAIM. This determines the fraction of pages
  * of a node considered for each zone_reclaim. 4 scans 1/16th of
  * a zone.