1 files changed, 190 insertions, 193 deletions

diff --git a/mm/list_lru.c b/mm/list_lru.c
index 9b7ff06e9d32..f93ada6a207b 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -59,6 +59,53 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
 	}
 	return &lru->node[nid].lru;
 }
+
+static inline struct list_lru_one *
+lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
+		       bool irq, bool skip_empty)
+{
+	struct list_lru_one *l;
+	long nr_items;
+
+	rcu_read_lock();
+again:
+	l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
+	if (likely(l)) {
+		if (irq)
+			spin_lock_irq(&l->lock);
+		else
+			spin_lock(&l->lock);
+		nr_items = READ_ONCE(l->nr_items);
+		if (likely(nr_items != LONG_MIN)) {
+			WARN_ON(nr_items < 0);
+			rcu_read_unlock();
+			return l;
+		}
+		if (irq)
+			spin_unlock_irq(&l->lock);
+		else
+			spin_unlock(&l->lock);
+	}
+	/*
+	 * Caller may simply bail out if raced with reparenting or
+	 * may iterate through the list_lru and expect empty slots.
+	 */
+	if (skip_empty) {
+		rcu_read_unlock();
+		return NULL;
+	}
+	VM_WARN_ON(!css_is_dying(&memcg->css));
+	memcg = parent_mem_cgroup(memcg);
+	goto again;
+}
+
+static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off)
+{
+	if (irq_off)
+		spin_unlock_irq(&l->lock);
+	else
+		spin_unlock(&l->lock);
+}
 #else
 static void list_lru_register(struct list_lru *lru)
 {
@@ -83,30 +130,52 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
 {
 	return &lru->node[nid].lru;
 }
+
+static inline struct list_lru_one *
+lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
+		       bool irq, bool skip_empty)
+{
+	struct list_lru_one *l = &lru->node[nid].lru;
+
+	if (irq)
+		spin_lock_irq(&l->lock);
+	else
+		spin_lock(&l->lock);
+
+	return l;
+}
+
+static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off)
+{
+	if (irq_off)
+		spin_unlock_irq(&l->lock);
+	else
+		spin_unlock(&l->lock);
+}
 #endif /* CONFIG_MEMCG */
 
 /* The caller must ensure the memcg lifetime. */
 bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
-		    struct mem_cgroup *memcg)
+		  struct mem_cgroup *memcg)
 {
 	struct list_lru_node *nlru = &lru->node[nid];
 	struct list_lru_one *l;
 
-	spin_lock(&nlru->lock);
+	l = lock_list_lru_of_memcg(lru, nid, memcg, false, false);
+	if (!l)
+		return false;
 	if (list_empty(item)) {
-		l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
 		list_add_tail(item, &l->list);
 		/* Set shrinker bit if the first element was added */
 		if (!l->nr_items++)
 			set_shrinker_bit(memcg, nid, lru_shrinker_id(lru));
-		nlru->nr_items++;
-		spin_unlock(&nlru->lock);
+		unlock_list_lru(l, false);
+		atomic_long_inc(&nlru->nr_items);
 		return true;
 	}
-	spin_unlock(&nlru->lock);
+	unlock_list_lru(l, false);
 	return false;
 }
-EXPORT_SYMBOL_GPL(list_lru_add);
 
 bool list_lru_add_obj(struct list_lru *lru, struct list_head *item)
 {
@@ -127,24 +196,23 @@ EXPORT_SYMBOL_GPL(list_lru_add_obj);
 
 /* The caller must ensure the memcg lifetime. */
 bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid,
-		    struct mem_cgroup *memcg)
+		  struct mem_cgroup *memcg)
 {
 	struct list_lru_node *nlru = &lru->node[nid];
 	struct list_lru_one *l;
-
-	spin_lock(&nlru->lock);
+	l = lock_list_lru_of_memcg(lru, nid, memcg, false, false);
+	if (!l)
+		return false;
 	if (!list_empty(item)) {
-		l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
 		list_del_init(item);
 		l->nr_items--;
-		nlru->nr_items--;
-		spin_unlock(&nlru->lock);
+		unlock_list_lru(l, false);
+		atomic_long_dec(&nlru->nr_items);
 		return true;
 	}
-	spin_unlock(&nlru->lock);
+	unlock_list_lru(l, false);
 	return false;
 }
-EXPORT_SYMBOL_GPL(list_lru_del);
 
 bool list_lru_del_obj(struct list_lru *lru, struct list_head *item)
 {
@@ -201,25 +269,24 @@ unsigned long list_lru_count_node(struct list_lru *lru, int nid)
 	struct list_lru_node *nlru;
 
 	nlru = &lru->node[nid];
-	return nlru->nr_items;
+	return atomic_long_read(&nlru->nr_items);
 }
 EXPORT_SYMBOL_GPL(list_lru_count_node);
 
 static unsigned long
-__list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx,
+__list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
 		    list_lru_walk_cb isolate, void *cb_arg,
-		    unsigned long *nr_to_walk)
+		    unsigned long *nr_to_walk, bool irq_off)
 {
 	struct list_lru_node *nlru = &lru->node[nid];
-	struct list_lru_one *l;
+	struct list_lru_one *l = NULL;
 	struct list_head *item, *n;
 	unsigned long isolated = 0;
 
 restart:
-	l = list_lru_from_memcg_idx(lru, nid, memcg_idx);
+	l = lock_list_lru_of_memcg(lru, nid, memcg, irq_off, true);
 	if (!l)
-		goto out;
-
+		return isolated;
 	list_for_each_safe(item, n, &l->list) {
 		enum lru_status ret;
 
@@ -231,19 +298,19 @@ restart:
 			break;
 		--*nr_to_walk;
 
-		ret = isolate(item, l, &nlru->lock, cb_arg);
+		ret = isolate(item, l, cb_arg);
 		switch (ret) {
+		/*
+		 * LRU_RETRY, LRU_REMOVED_RETRY and LRU_STOP will drop the lru
+		 * lock. List traversal will have to restart from scratch.
+		 */
+		case LRU_RETRY:
+			goto restart;
 		case LRU_REMOVED_RETRY:
-			assert_spin_locked(&nlru->lock);
 			fallthrough;
 		case LRU_REMOVED:
 			isolated++;
-			nlru->nr_items--;
-			/*
-			 * If the lru lock has been dropped, our list
-			 * traversal is now invalid and so we have to
-			 * restart from scratch.
-			 */
+			atomic_long_dec(&nlru->nr_items);
 			if (ret == LRU_REMOVED_RETRY)
 				goto restart;
 			break;
@@ -252,20 +319,13 @@ restart:
 			break;
 		case LRU_SKIP:
 			break;
-		case LRU_RETRY:
-			/*
-			 * The lru lock has been dropped, our list traversal is
-			 * now invalid and so we have to restart from scratch.
-			 */
-			assert_spin_locked(&nlru->lock);
-			goto restart;
 		case LRU_STOP:
-			assert_spin_locked(&nlru->lock);
 			goto out;
 		default:
 			BUG();
 		}
 	}
+	unlock_list_lru(l, irq_off);
 out:
 	return isolated;
 }
@@ -275,14 +335,8 @@ list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
 		  list_lru_walk_cb isolate, void *cb_arg,
 		  unsigned long *nr_to_walk)
 {
-	struct list_lru_node *nlru = &lru->node[nid];
-	unsigned long ret;
-
-	spin_lock(&nlru->lock);
-	ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate,
-				  cb_arg, nr_to_walk);
-	spin_unlock(&nlru->lock);
-	return ret;
+	return __list_lru_walk_one(lru, nid, memcg, isolate,
+				   cb_arg, nr_to_walk, false);
 }
 EXPORT_SYMBOL_GPL(list_lru_walk_one);
 
@@ -291,14 +345,8 @@ list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
 		      list_lru_walk_cb isolate, void *cb_arg,
 		      unsigned long *nr_to_walk)
 {
-	struct list_lru_node *nlru = &lru->node[nid];
-	unsigned long ret;
-
-	spin_lock_irq(&nlru->lock);
-	ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate,
-				  cb_arg, nr_to_walk);
-	spin_unlock_irq(&nlru->lock);
-	return ret;
+	return __list_lru_walk_one(lru, nid, memcg, isolate,
+				   cb_arg, nr_to_walk, true);
 }
 
 unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
@@ -313,16 +361,21 @@ unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
 #ifdef CONFIG_MEMCG
 	if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) {
 		struct list_lru_memcg *mlru;
+		struct mem_cgroup *memcg;
 		unsigned long index;
 
 		xa_for_each(&lru->xa, index, mlru) {
-			struct list_lru_node *nlru = &lru->node[nid];
-
-			spin_lock(&nlru->lock);
-			isolated += __list_lru_walk_one(lru, nid, index,
+			rcu_read_lock();
+			memcg = mem_cgroup_from_id(index);
+			if (!mem_cgroup_tryget(memcg)) {
+				rcu_read_unlock();
+				continue;
+			}
+			rcu_read_unlock();
+			isolated += __list_lru_walk_one(lru, nid, memcg,
 							isolate, cb_arg,
-							nr_to_walk);
-			spin_unlock(&nlru->lock);
+							nr_to_walk, false);
+			mem_cgroup_put(memcg);
 
 			if (*nr_to_walk <= 0)
 				break;
@@ -334,14 +387,19 @@ unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
 }
 EXPORT_SYMBOL_GPL(list_lru_walk_node);
 
-static void init_one_lru(struct list_lru_one *l)
+static void init_one_lru(struct list_lru *lru, struct list_lru_one *l)
 {
 	INIT_LIST_HEAD(&l->list);
+	spin_lock_init(&l->lock);
 	l->nr_items = 0;
+#ifdef CONFIG_LOCKDEP
+	if (lru->key)
+		lockdep_set_class(&l->lock, lru->key);
+#endif
 }
 
 #ifdef CONFIG_MEMCG
-static struct list_lru_memcg *memcg_init_list_lru_one(gfp_t gfp)
+static struct list_lru_memcg *memcg_init_list_lru_one(struct list_lru *lru, gfp_t gfp)
 {
 	int nid;
 	struct list_lru_memcg *mlru;
@@ -351,25 +409,11 @@ static struct list_lru_memcg *memcg_init_list_lru_one(gfp_t gfp)
 		return NULL;
 
 	for_each_node(nid)
-		init_one_lru(&mlru->node[nid]);
+		init_one_lru(lru, &mlru->node[nid]);
 
 	return mlru;
 }
 
-static void memcg_list_lru_free(struct list_lru *lru, int src_idx)
-{
-	struct list_lru_memcg *mlru = xa_erase_irq(&lru->xa, src_idx);
-
-	/*
-	 * The __list_lru_walk_one() can walk the list of this node.
-	 * We need kvfree_rcu() here. And the walking of the list
-	 * is under lru->node[nid]->lock, which can serve as a RCU
-	 * read-side critical section.
-	 */
-	if (mlru)
-		kvfree_rcu(mlru, rcu);
-}
-
 static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
 {
 	if (memcg_aware)
@@ -393,77 +437,64 @@ static void memcg_destroy_list_lru(struct list_lru *lru)
 	xas_unlock_irq(&xas);
 }
 
-static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid,
-					 int src_idx, struct mem_cgroup *dst_memcg)
+static void memcg_reparent_list_lru_one(struct list_lru *lru, int nid,
+					struct list_lru_one *src,
+					struct mem_cgroup *dst_memcg)
 {
-	struct list_lru_node *nlru = &lru->node[nid];
 	int dst_idx = dst_memcg->kmemcg_id;
-	struct list_lru_one *src, *dst;
-
-	/*
-	 * Since list_lru_{add,del} may be called under an IRQ-safe lock,
-	 * we have to use IRQ-safe primitives here to avoid deadlock.
-	 */
-	spin_lock_irq(&nlru->lock);
+	struct list_lru_one *dst;
 
-	src = list_lru_from_memcg_idx(lru, nid, src_idx);
-	if (!src)
-		goto out;
+	spin_lock_irq(&src->lock);
 	dst = list_lru_from_memcg_idx(lru, nid, dst_idx);
+	spin_lock_nested(&dst->lock, SINGLE_DEPTH_NESTING);
 
 	list_splice_init(&src->list, &dst->list);
-
 	if (src->nr_items) {
 		dst->nr_items += src->nr_items;
 		set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru));
-		src->nr_items = 0;
 	}
-out:
-	spin_unlock_irq(&nlru->lock);
-}
-
-static void memcg_reparent_list_lru(struct list_lru *lru,
-				    int src_idx, struct mem_cgroup *dst_memcg)
-{
-	int i;
+	/* Mark the list_lru_one dead */
+	src->nr_items = LONG_MIN;
 
-	for_each_node(i)
-		memcg_reparent_list_lru_node(lru, i, src_idx, dst_memcg);
-
-	memcg_list_lru_free(lru, src_idx);
+	spin_unlock(&dst->lock);
+	spin_unlock_irq(&src->lock);
 }
 
 void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent)
 {
-	struct cgroup_subsys_state *css;
 	struct list_lru *lru;
-	int src_idx = memcg->kmemcg_id;
+	int i;
 
-	/*
-	 * Change kmemcg_id of this cgroup and all its descendants to the
-	 * parent's id, and then move all entries from this cgroup's list_lrus
-	 * to ones of the parent.
-	 *
-	 * After we have finished, all list_lrus corresponding to this cgroup
-	 * are guaranteed to remain empty. So we can safely free this cgroup's
-	 * list lrus in memcg_list_lru_free().
-	 *
-	 * Changing ->kmemcg_id to the parent can prevent memcg_list_lru_alloc()
-	 * from allocating list lrus for this cgroup after memcg_list_lru_free()
-	 * call.
-	 */
-	rcu_read_lock();
-	css_for_each_descendant_pre(css, &memcg->css) {
-		struct mem_cgroup *child;
+	mutex_lock(&list_lrus_mutex);
+	list_for_each_entry(lru, &memcg_list_lrus, list) {
+		struct list_lru_memcg *mlru;
+		XA_STATE(xas, &lru->xa, memcg->kmemcg_id);
 
-		child = mem_cgroup_from_css(css);
-		WRITE_ONCE(child->kmemcg_id, parent->kmemcg_id);
-	}
-	rcu_read_unlock();
+		/*
+		 * Lock the Xarray to ensure no on going list_lru_memcg
+		 * allocation and further allocation will see css_is_dying().
+		 */
+		xas_lock_irq(&xas);
+		mlru = xas_store(&xas, NULL);
+		xas_unlock_irq(&xas);
+		if (!mlru)
+			continue;
 
-	mutex_lock(&list_lrus_mutex);
-	list_for_each_entry(lru, &memcg_list_lrus, list)
-		memcg_reparent_list_lru(lru, src_idx, parent);
+		/*
+		 * With Xarray value set to NULL, holding the lru lock below
+		 * prevents list_lru_{add,del,isolate} from touching the lru,
+		 * safe to reparent.
+		 */
+		for_each_node(i)
+			memcg_reparent_list_lru_one(lru, i, &mlru->node[i], parent);
+
+		/*
+		 * Here all list_lrus corresponding to the cgroup are guaranteed
+		 * to remain empty, we can safely free this lru, any further
+		 * memcg_list_lru_alloc() call will simply bail out.
+		 */
+		kvfree_rcu(mlru, rcu);
+	}
 	mutex_unlock(&list_lrus_mutex);
 }
 
@@ -478,77 +509,48 @@ static inline bool memcg_list_lru_allocated(struct mem_cgroup *memcg,
 int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru,
 			 gfp_t gfp)
 {
-	int i;
 	unsigned long flags;
-	struct list_lru_memcg_table {
-		struct list_lru_memcg *mlru;
-		struct mem_cgroup *memcg;
-	} *table;
+	struct list_lru_memcg *mlru;
+	struct mem_cgroup *pos, *parent;
 	XA_STATE(xas, &lru->xa, 0);
 
 	if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru))
 		return 0;
 
 	gfp &= GFP_RECLAIM_MASK;
-	table = kmalloc_array(memcg->css.cgroup->level, sizeof(*table), gfp);
-	if (!table)
-		return -ENOMEM;
-
 	/*
 	 * Because the list_lru can be reparented to the parent cgroup's
 	 * list_lru, we should make sure that this cgroup and all its
 	 * ancestors have allocated list_lru_memcg.
 	 */
-	for (i = 0; memcg; memcg = parent_mem_cgroup(memcg), i++) {
-		if (memcg_list_lru_allocated(memcg, lru))
-			break;
-
-		table[i].memcg = memcg;
-		table[i].mlru = memcg_init_list_lru_one(gfp);
-		if (!table[i].mlru) {
-			while (i--)
-				kfree(table[i].mlru);
-			kfree(table);
-			return -ENOMEM;
+	do {
+		/*
+		 * Keep finding the farest parent that wasn't populated
+		 * until found memcg itself.
+		 */
+		pos = memcg;
+		parent = parent_mem_cgroup(pos);
+		while (!memcg_list_lru_allocated(parent, lru)) {
+			pos = parent;
+			parent = parent_mem_cgroup(pos);
 		}
-	}
-
-	xas_lock_irqsave(&xas, flags);
-	while (i--) {
-		int index = READ_ONCE(table[i].memcg->kmemcg_id);
-		struct list_lru_memcg *mlru = table[i].mlru;
 
-		xas_set(&xas, index);
-retry:
-		if (unlikely(index < 0 || xas_error(&xas) || xas_load(&xas))) {
-			kfree(mlru);
-		} else {
-			xas_store(&xas, mlru);
-			if (xas_error(&xas) == -ENOMEM) {
-				xas_unlock_irqrestore(&xas, flags);
-				if (xas_nomem(&xas, gfp))
-					xas_set_err(&xas, 0);
-				xas_lock_irqsave(&xas, flags);
-				/*
-				 * The xas lock has been released, this memcg
-				 * can be reparented before us. So reload
-				 * memcg id. More details see the comments
-				 * in memcg_reparent_list_lrus().
-				 */
-				index = READ_ONCE(table[i].memcg->kmemcg_id);
-				if (index < 0)
-					xas_set_err(&xas, 0);
-				else if (!xas_error(&xas) && index != xas.xa_index)
-					xas_set(&xas, index);
-				goto retry;
+		mlru = memcg_init_list_lru_one(lru, gfp);
+		if (!mlru)
+			return -ENOMEM;
+		xas_set(&xas, pos->kmemcg_id);
+		do {
+			xas_lock_irqsave(&xas, flags);
+			if (!xas_load(&xas) && !css_is_dying(&pos->css)) {
+				xas_store(&xas, mlru);
+				if (!xas_error(&xas))
+					mlru = NULL;
 			}
-		}
-	}
-	/* xas_nomem() is used to free memory instead of memory allocation. */
-	if (xas.xa_alloc)
-		xas_nomem(&xas, gfp);
-	xas_unlock_irqrestore(&xas, flags);
-	kfree(table);
+			xas_unlock_irqrestore(&xas, flags);
+		} while (xas_nomem(&xas, gfp));
+		if (mlru)
+			kfree(mlru);
+	} while (pos != memcg && !css_is_dying(&pos->css));
 
 	return xas_error(&xas);
 }
@@ -562,8 +564,7 @@ static void memcg_destroy_list_lru(struct list_lru *lru)
 }
 #endif /* CONFIG_MEMCG */
 
-int __list_lru_init(struct list_lru *lru, bool memcg_aware,
-		    struct lock_class_key *key, struct shrinker *shrinker)
+int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct shrinker *shrinker)
 {
 	int i;
 
@@ -581,12 +582,8 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware,
 	if (!lru->node)
 		return -ENOMEM;
 
-	for_each_node(i) {
-		spin_lock_init(&lru->node[i].lock);
-		if (key)
-			lockdep_set_class(&lru->node[i].lock, key);
-		init_one_lru(&lru->node[i].lru);
-	}
+	for_each_node(i)
+		init_one_lru(lru, &lru->node[i].lru);
 
 	memcg_init_list_lru(lru, memcg_aware);
 	list_lru_register(lru);