1 files changed, 202 insertions, 196 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3a24e3b619f5..e3c7ca7dc174 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -20,6 +20,9 @@
  * Lockless page tracking & accounting
  * Unified hierarchy configuration model
  * Copyright (C) 2015 Red Hat, Inc., Johannes Weiner
+ *
+ * Per memcg lru locking
+ * Copyright (C) 2020 Alibaba, Inc, Alex Shi
  */
 
 #include <linux/page_counter.h>
@@ -533,7 +536,7 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
 {
 	struct mem_cgroup *memcg;
 
-	memcg = page->mem_cgroup;
+	memcg = page_memcg(page);
 
 	if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		memcg = root_mem_cgroup;
@@ -560,16 +563,7 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
-	memcg = page->mem_cgroup;
-
-	/*
-	 * The lowest bit set means that memcg isn't a valid
-	 * memcg pointer, but a obj_cgroups pointer.
-	 * In this case the page is shared and doesn't belong
-	 * to any specific memory cgroup.
-	 */
-	if ((unsigned long) memcg & 0x1UL)
-		memcg = NULL;
+	memcg = page_memcg_check(page);
 
 	while (memcg && !(memcg->css.flags & CSS_ONLINE))
 		memcg = parent_mem_cgroup(memcg);
@@ -623,14 +617,9 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
 		if (mz->usage_in_excess < mz_node->usage_in_excess) {
 			p = &(*p)->rb_left;
 			rightmost = false;
-		}
-
-		/*
-		 * We can't avoid mem cgroups that are over their soft
-		 * limit by the same amount
-		 */
-		else if (mz->usage_in_excess >= mz_node->usage_in_excess)
+		} else {
 			p = &(*p)->rb_right;
+		}
 	}
 
 	if (rightmost)
@@ -858,33 +847,46 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 		__mod_memcg_lruvec_state(lruvec, idx, val);
 }
 
-void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
+void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx,
+			     int val)
 {
-	pg_data_t *pgdat = page_pgdat(virt_to_page(p));
-	struct mem_cgroup *memcg;
+	struct page *head = compound_head(page); /* rmap on tail pages */
+	struct mem_cgroup *memcg = page_memcg(head);
+	pg_data_t *pgdat = page_pgdat(page);
 	struct lruvec *lruvec;
 
-	rcu_read_lock();
-	memcg = mem_cgroup_from_obj(p);
-
 	/* Untracked pages have no memcg, no lruvec. Update only the node */
-	if (!memcg || memcg == root_mem_cgroup) {
+	if (!memcg) {
 		__mod_node_page_state(pgdat, idx, val);
-	} else {
-		lruvec = mem_cgroup_lruvec(memcg, pgdat);
-		__mod_lruvec_state(lruvec, idx, val);
+		return;
 	}
-	rcu_read_unlock();
+
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
+	__mod_lruvec_state(lruvec, idx, val);
 }
+EXPORT_SYMBOL(__mod_lruvec_page_state);
 
-void mod_memcg_obj_state(void *p, int idx, int val)
+void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
 {
+	pg_data_t *pgdat = page_pgdat(virt_to_page(p));
 	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
 
 	rcu_read_lock();
 	memcg = mem_cgroup_from_obj(p);
-	if (memcg)
-		mod_memcg_state(memcg, idx, val);
+
+	/*
+	 * Untracked pages have no memcg, no lruvec. Update only the
+	 * node. If we reparent the slab objects to the root memcg,
+	 * when we free the slab object, we need to update the per-memcg
+	 * vmstats to keep it correct for the root memcg.
+	 */
+	if (!memcg) {
+		__mod_node_page_state(pgdat, idx, val);
+	} else {
+		lruvec = mem_cgroup_lruvec(memcg, pgdat);
+		__mod_lruvec_state(lruvec, idx, val);
+	}
 	rcu_read_unlock();
 }
 
@@ -1050,7 +1052,7 @@ EXPORT_SYMBOL(get_mem_cgroup_from_mm);
  */
 struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
 {
-	struct mem_cgroup *memcg = page->mem_cgroup;
+	struct mem_cgroup *memcg = page_memcg(page);
 
 	if (mem_cgroup_disabled())
 		return NULL;
@@ -1152,12 +1154,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 	if (prev && !reclaim)
 		pos = prev;
 
-	if (!root->use_hierarchy && root != root_mem_cgroup) {
-		if (prev)
-			goto out;
-		return root;
-	}
-
 	rcu_read_lock();
 
 	if (reclaim) {
@@ -1237,7 +1233,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 
 out_unlock:
 	rcu_read_unlock();
-out:
 	if (prev && prev != root)
 		css_put(&prev->css);
 
@@ -1330,12 +1325,29 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 	return ret;
 }
 
+#ifdef CONFIG_DEBUG_VM
+void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+{
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	memcg = page_memcg(page);
+
+	if (!memcg)
+		VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != root_mem_cgroup, page);
+	else
+		VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != memcg, page);
+}
+#endif
+
 /**
  * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
  * @page: the page
  * @pgdat: pgdat of the page
  *
- * This function relies on page->mem_cgroup being stable - see the
+ * This function relies on page's memcg being stable - see the
  * access rules in commit_charge().
  */
 struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat)
@@ -1349,7 +1361,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd
 		goto out;
 	}
 
-	memcg = page->mem_cgroup;
+	memcg = page_memcg(page);
 	/*
 	 * Swapcache readahead pages are added to the LRU - and
 	 * possibly migrated - before they are charged.
@@ -1371,6 +1383,60 @@ out:
 }
 
 /**
+ * lock_page_lruvec - lock and return lruvec for a given page.
+ * @page: the page
+ *
+ * This series functions should be used in either conditions:
+ * PageLRU is cleared or unset
+ * or page->_refcount is zero
+ * or page is locked.
+ */
+struct lruvec *lock_page_lruvec(struct page *page)
+{
+	struct lruvec *lruvec;
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	rcu_read_lock();
+	lruvec = mem_cgroup_page_lruvec(page, pgdat);
+	spin_lock(&lruvec->lru_lock);
+	rcu_read_unlock();
+
+	lruvec_memcg_debug(lruvec, page);
+
+	return lruvec;
+}
+
+struct lruvec *lock_page_lruvec_irq(struct page *page)
+{
+	struct lruvec *lruvec;
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	rcu_read_lock();
+	lruvec = mem_cgroup_page_lruvec(page, pgdat);
+	spin_lock_irq(&lruvec->lru_lock);
+	rcu_read_unlock();
+
+	lruvec_memcg_debug(lruvec, page);
+
+	return lruvec;
+}
+
+struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags)
+{
+	struct lruvec *lruvec;
+	struct pglist_data *pgdat = page_pgdat(page);
+
+	rcu_read_lock();
+	lruvec = mem_cgroup_page_lruvec(page, pgdat);
+	spin_lock_irqsave(&lruvec->lru_lock, *flags);
+	rcu_read_unlock();
+
+	lruvec_memcg_debug(lruvec, page);
+
+	return lruvec;
+}
+
+/**
  * mem_cgroup_update_lru_size - account for adding or removing an lru page
  * @lruvec: mem_cgroup per zone lru vector
  * @lru: index of lru list the page is sitting on
@@ -1494,6 +1560,7 @@ static struct memory_stat memory_stats[] = {
 	{ "anon", PAGE_SIZE, NR_ANON_MAPPED },
 	{ "file", PAGE_SIZE, NR_FILE_PAGES },
 	{ "kernel_stack", 1024, NR_KERNEL_STACK_KB },
+	{ "pagetables", PAGE_SIZE, NR_PAGETABLE },
 	{ "percpu", 1, MEMCG_PERCPU_B },
 	{ "sock", PAGE_SIZE, MEMCG_SOCK },
 	{ "shmem", PAGE_SIZE, NR_SHMEM },
@@ -1507,6 +1574,8 @@ static struct memory_stat memory_stats[] = {
 	 * constant(e.g. powerpc).
 	 */
 	{ "anon_thp", 0, NR_ANON_THPS },
+	{ "file_thp", 0, NR_FILE_THPS },
+	{ "shmem_thp", 0, NR_SHMEM_THPS },
 #endif
 	{ "inactive_anon", PAGE_SIZE, NR_INACTIVE_ANON },
 	{ "active_anon", PAGE_SIZE, NR_ACTIVE_ANON },
@@ -1537,7 +1606,9 @@ static int __init memory_stats_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		if (memory_stats[i].idx == NR_ANON_THPS)
+		if (memory_stats[i].idx == NR_ANON_THPS ||
+		    memory_stats[i].idx == NR_FILE_THPS ||
+		    memory_stats[i].idx == NR_SHMEM_THPS)
 			memory_stats[i].ratio = HPAGE_PMD_SIZE;
 #endif
 		VM_BUG_ON(!memory_stats[i].ratio);
@@ -2109,7 +2180,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
 }
 
 /**
- * lock_page_memcg - lock a page->mem_cgroup binding
+ * lock_page_memcg - lock a page and memcg binding
  * @page: the page
  *
  * This function protects unlocked LRU pages from being moved to
@@ -2141,15 +2212,21 @@ struct mem_cgroup *lock_page_memcg(struct page *page)
 	if (mem_cgroup_disabled())
 		return NULL;
 again:
-	memcg = head->mem_cgroup;
+	memcg = page_memcg(head);
 	if (unlikely(!memcg))
 		return NULL;
 
+#ifdef CONFIG_PROVE_LOCKING
+	local_irq_save(flags);
+	might_lock(&memcg->move_lock);
+	local_irq_restore(flags);
+#endif
+
 	if (atomic_read(&memcg->moving_account) <= 0)
 		return memcg;
 
 	spin_lock_irqsave(&memcg->move_lock, flags);
-	if (memcg != head->mem_cgroup) {
+	if (memcg != page_memcg(head)) {
 		spin_unlock_irqrestore(&memcg->move_lock, flags);
 		goto again;
 	}
@@ -2187,14 +2264,14 @@ void __unlock_page_memcg(struct mem_cgroup *memcg)
 }
 
 /**
- * unlock_page_memcg - unlock a page->mem_cgroup binding
+ * unlock_page_memcg - unlock a page and memcg binding
  * @page: the page
  */
 void unlock_page_memcg(struct page *page)
 {
 	struct page *head = compound_head(page);
 
-	__unlock_page_memcg(head->mem_cgroup);
+	__unlock_page_memcg(page_memcg(head));
 }
 EXPORT_SYMBOL(unlock_page_memcg);
 
@@ -2884,16 +2961,16 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 
 static void commit_charge(struct page *page, struct mem_cgroup *memcg)
 {
-	VM_BUG_ON_PAGE(page->mem_cgroup, page);
+	VM_BUG_ON_PAGE(page_memcg(page), page);
 	/*
-	 * Any of the following ensures page->mem_cgroup stability:
+	 * Any of the following ensures page's memcg stability:
 	 *
 	 * - the page lock
 	 * - LRU isolation
 	 * - lock_page_memcg()
 	 * - exclusive reference
 	 */
-	page->mem_cgroup = memcg;
+	page->memcg_data = (unsigned long)memcg;
 }
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -2908,8 +2985,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 	if (!vec)
 		return -ENOMEM;
 
-	if (cmpxchg(&page->obj_cgroups, NULL,
-		    (struct obj_cgroup **) ((unsigned long)vec | 0x1UL)))
+	if (!set_page_objcgs(page, vec))
 		kfree(vec);
 	else
 		kmemleak_not_leak(vec);
@@ -2920,6 +2996,12 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 /*
  * Returns a pointer to the memory cgroup to which the kernel object is charged.
  *
+ * A passed kernel object can be a slab object or a generic kernel page, so
+ * different mechanisms for getting the memory cgroup pointer should be used.
+ * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller
+ * can not know for sure how the kernel object is implemented.
+ * mem_cgroup_from_obj() can be safely used in such cases.
+ *
  * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
  * cgroup_mutex, etc.
  */
@@ -2933,35 +3015,30 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
 	page = virt_to_head_page(p);
 
 	/*
-	 * If page->mem_cgroup is set, it's either a simple mem_cgroup pointer
-	 * or a pointer to obj_cgroup vector. In the latter case the lowest
-	 * bit of the pointer is set.
-	 * The page->mem_cgroup pointer can be asynchronously changed
-	 * from NULL to (obj_cgroup_vec | 0x1UL), but can't be changed
-	 * from a valid memcg pointer to objcg vector or back.
-	 */
-	if (!page->mem_cgroup)
-		return NULL;
-
-	/*
 	 * Slab objects are accounted individually, not per-page.
 	 * Memcg membership data for each individual object is saved in
 	 * the page->obj_cgroups.
 	 */
-	if (page_has_obj_cgroups(page)) {
+	if (page_objcgs_check(page)) {
 		struct obj_cgroup *objcg;
 		unsigned int off;
 
 		off = obj_to_index(page->slab_cache, page, p);
-		objcg = page_obj_cgroups(page)[off];
+		objcg = page_objcgs(page)[off];
 		if (objcg)
 			return obj_cgroup_memcg(objcg);
 
 		return NULL;
 	}
 
-	/* All other pages use page->mem_cgroup */
-	return page->mem_cgroup;
+	/*
+	 * page_memcg_check() is used here, because page_has_obj_cgroups()
+	 * check above could fail because the object cgroups vector wasn't set
+	 * at that moment, but it can be set concurrently.
+	 * page_memcg_check(page) will guarantee that a proper memory
+	 * cgroup pointer or NULL will be returned.
+	 */
+	return page_memcg_check(page);
 }
 
 __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
@@ -2982,6 +3059,7 @@ __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
 		objcg = rcu_dereference(memcg->objcg);
 		if (objcg && obj_cgroup_tryget(objcg))
 			break;
+		objcg = NULL;
 	}
 	rcu_read_unlock();
 
@@ -3099,8 +3177,8 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
 	if (memcg && !mem_cgroup_is_root(memcg)) {
 		ret = __memcg_kmem_charge(memcg, gfp, 1 << order);
 		if (!ret) {
-			page->mem_cgroup = memcg;
-			__SetPageKmemcg(page);
+			page->memcg_data = (unsigned long)memcg |
+				MEMCG_DATA_KMEM;
 			return 0;
 		}
 		css_put(&memcg->css);
@@ -3115,7 +3193,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
  */
 void __memcg_kmem_uncharge_page(struct page *page, int order)
 {
-	struct mem_cgroup *memcg = page->mem_cgroup;
+	struct mem_cgroup *memcg = page_memcg(page);
 	unsigned int nr_pages = 1 << order;
 
 	if (!memcg)
@@ -3123,12 +3201,8 @@ void __memcg_kmem_uncharge_page(struct page *page, int order)
 
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
 	__memcg_kmem_uncharge(memcg, nr_pages);
-	page->mem_cgroup = NULL;
+	page->memcg_data = 0;
 	css_put(&memcg->css);
-
-	/* slab pages do not have PageKmemcg flag set */
-	if (PageKmemcg(page))
-		__ClearPageKmemcg(page);
 }
 
 static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
@@ -3241,8 +3315,10 @@ int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size)
 	 * independently later.
 	 */
 	rcu_read_lock();
+retry:
 	memcg = obj_cgroup_memcg(objcg);
-	css_get(&memcg->css);
+	if (unlikely(!css_tryget(&memcg->css)))
+		goto retry;
 	rcu_read_unlock();
 
 	nr_pages = size >> PAGE_SHIFT;
@@ -3267,14 +3343,12 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
 #endif /* CONFIG_MEMCG_KMEM */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-
 /*
- * Because tail pages are not marked as "used", set it. We're under
- * pgdat->lru_lock and migration entries setup in all page mappings.
+ * Because page_memcg(head) is not set on compound tails, set it now.
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
-	struct mem_cgroup *memcg = head->mem_cgroup;
+	struct mem_cgroup *memcg = page_memcg(head);
 	int i;
 
 	if (mem_cgroup_disabled())
@@ -3282,7 +3356,7 @@ void mem_cgroup_split_huge_fixup(struct page *head)
 
 	for (i = 1; i < HPAGE_PMD_NR; i++) {
 		css_get(&memcg->css);
-		head[i].mem_cgroup = memcg;
+		head[i].memcg_data = (unsigned long)memcg;
 	}
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -3465,22 +3539,6 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 }
 
 /*
- * Test whether @memcg has children, dead or alive.  Note that this
- * function doesn't care whether @memcg has use_hierarchy enabled and
- * returns %true if there are child csses according to the cgroup
- * hierarchy.  Testing use_hierarchy is the caller's responsibility.
- */
-static inline bool memcg_has_children(struct mem_cgroup *memcg)
-{
-	bool ret;
-
-	rcu_read_lock();
-	ret = css_next_child(NULL, &memcg->css);
-	rcu_read_unlock();
-	return ret;
-}
-
-/*
  * Reclaims as many pages from the given memcg as possible.
  *
  * Caller is responsible for holding css reference for memcg.
@@ -3528,37 +3586,20 @@ static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of,
 static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
 				     struct cftype *cft)
 {
-	return mem_cgroup_from_css(css)->use_hierarchy;
+	return 1;
 }
 
 static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
 				      struct cftype *cft, u64 val)
 {
-	int retval = 0;
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent);
-
-	if (memcg->use_hierarchy == val)
+	if (val == 1)
 		return 0;
 
-	/*
-	 * If parent's use_hierarchy is set, we can't make any modifications
-	 * in the child subtrees. If it is unset, then the change can
-	 * occur, provided the current cgroup has no children.
-	 *
-	 * For the root cgroup, parent_mem is NULL, we allow value to be
-	 * set if there are no children.
-	 */
-	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
-				(val == 1 || val == 0)) {
-		if (!memcg_has_children(memcg))
-			memcg->use_hierarchy = val;
-		else
-			retval = -EBUSY;
-	} else
-		retval = -EINVAL;
+	pr_warn_once("Non-hierarchical mode is deprecated. "
+		     "Please report your usecase to linux-mm@kvack.org if you "
+		     "depend on this functionality.\n");
 
-	return retval;
+	return -EINVAL;
 }
 
 static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
@@ -3707,12 +3748,6 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
 
 	static_branch_enable(&memcg_kmem_enabled_key);
 
-	/*
-	 * A memory cgroup is considered kmem-online as soon as it gets
-	 * kmemcg_id. Setting the id after enabling static branching will
-	 * guarantee no one starts accounting before all call sites are
-	 * patched.
-	 */
 	memcg->kmemcg_id = memcg_id;
 	memcg->kmem_state = KMEM_ONLINE;
 
@@ -3752,8 +3787,6 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 		child = mem_cgroup_from_css(css);
 		BUG_ON(child->kmemcg_id != kmemcg_id);
 		child->kmemcg_id = parent->kmemcg_id;
-		if (!memcg->use_hierarchy)
-			break;
 	}
 	rcu_read_unlock();
 
@@ -4110,11 +4143,17 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 			   (u64)memsw * PAGE_SIZE);
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
+		unsigned long nr;
+
 		if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
 			continue;
+		nr = memcg_page_state(memcg, memcg1_stats[i]);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		if (memcg1_stats[i] == NR_ANON_THPS)
+			nr *= HPAGE_PMD_NR;
+#endif
 		seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i],
-			   (u64)memcg_page_state(memcg, memcg1_stats[i]) *
-			   PAGE_SIZE);
+						(u64)nr * PAGE_SIZE);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
@@ -4658,7 +4697,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
 					     struct bdi_writeback *wb)
 {
-	struct mem_cgroup *memcg = page->mem_cgroup;
+	struct mem_cgroup *memcg = page_memcg(page);
 	struct memcg_cgwb_frn *frn;
 	u64 now = get_jiffies_64();
 	u64 oldest_at = now;
@@ -5338,9 +5377,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	if (parent) {
 		memcg->swappiness = mem_cgroup_swappiness(parent);
 		memcg->oom_kill_disable = parent->oom_kill_disable;
-	}
-	if (parent && parent->use_hierarchy) {
-		memcg->use_hierarchy = true;
+
 		page_counter_init(&memcg->memory, &parent->memory);
 		page_counter_init(&memcg->swap, &parent->swap);
 		page_counter_init(&memcg->kmem, &parent->kmem);
@@ -5350,21 +5387,12 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 		page_counter_init(&memcg->swap, NULL);
 		page_counter_init(&memcg->kmem, NULL);
 		page_counter_init(&memcg->tcpmem, NULL);
-		/*
-		 * Deeper hierachy with use_hierarchy == false doesn't make
-		 * much sense so let cgroup subsystem know about this
-		 * unfortunate state in our controller.
-		 */
-		if (parent != root_mem_cgroup)
-			memory_cgrp_subsys.broken_hierarchy = true;
-	}
 
-	/* The following stuff does not apply to the root */
-	if (!parent) {
 		root_mem_cgroup = memcg;
 		return &memcg->css;
 	}
 
+	/* The following stuff does not apply to the root */
 	error = memcg_online_kmem(memcg);
 	if (error)
 		goto fail;
@@ -5630,14 +5658,14 @@ static int mem_cgroup_move_account(struct page *page,
 
 	/*
 	 * Prevent mem_cgroup_migrate() from looking at
-	 * page->mem_cgroup of its source page while we change it.
+	 * page's memory cgroup of its source page while we change it.
 	 */
 	ret = -EBUSY;
 	if (!trylock_page(page))
 		goto out;
 
 	ret = -EINVAL;
-	if (page->mem_cgroup != from)
+	if (page_memcg(page) != from)
 		goto out_unlock;
 
 	pgdat = page_pgdat(page);
@@ -5692,13 +5720,13 @@ static int mem_cgroup_move_account(struct page *page,
 	/*
 	 * All state has been migrated, let's switch to the new memcg.
 	 *
-	 * It is safe to change page->mem_cgroup here because the page
+	 * It is safe to change page's memcg here because the page
 	 * is referenced, charged, isolated, and locked: we can't race
 	 * with (un)charging, migration, LRU putback, or anything else
-	 * that would rely on a stable page->mem_cgroup.
+	 * that would rely on a stable page's memory cgroup.
 	 *
 	 * Note that lock_page_memcg is a memcg lock, not a page lock,
-	 * to save space. As soon as we switch page->mem_cgroup to a
+	 * to save space. As soon as we switch page's memory cgroup to a
 	 * new memcg that isn't locked, the above state can change
 	 * concurrently again. Make sure we're truly done with it.
 	 */
@@ -5707,7 +5735,7 @@ static int mem_cgroup_move_account(struct page *page,
 	css_get(&to->css);
 	css_put(&from->css);
 
-	page->mem_cgroup = to;
+	page->memcg_data = (unsigned long)to;
 
 	__unlock_page_memcg(from);
 
@@ -5773,7 +5801,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		 * mem_cgroup_move_account() checks the page is valid or
 		 * not under LRU exclusion.
 		 */
-		if (page->mem_cgroup == mc.from) {
+		if (page_memcg(page) == mc.from) {
 			ret = MC_TARGET_PAGE;
 			if (is_device_private_page(page))
 				ret = MC_TARGET_DEVICE;
@@ -5817,7 +5845,7 @@ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
 	VM_BUG_ON_PAGE(!page || !PageHead(page), page);
 	if (!(mc.flags & MOVE_ANON))
 		return ret;
-	if (page->mem_cgroup == mc.from) {
+	if (page_memcg(page) == mc.from) {
 		ret = MC_TARGET_PAGE;
 		if (target) {
 			get_page(page);
@@ -6201,24 +6229,6 @@ static void mem_cgroup_move_task(void)
 }
 #endif
 
-/*
- * Cgroup retains root cgroups across [un]mount cycles making it necessary
- * to verify whether we're attached to the default hierarchy on each mount
- * attempt.
- */
-static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
-{
-	/*
-	 * use_hierarchy is forced on the default hierarchy.  cgroup core
-	 * guarantees that @root doesn't have any children, so turning it
-	 * on for the root memcg is enough.
-	 */
-	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
-		root_mem_cgroup->use_hierarchy = true;
-	else
-		root_mem_cgroup->use_hierarchy = false;
-}
-
 static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value)
 {
 	if (value == PAGE_COUNTER_MAX)
@@ -6556,7 +6566,6 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.post_attach = mem_cgroup_move_task,
-	.bind = mem_cgroup_bind,
 	.dfl_cftypes = memory_files,
 	.legacy_cftypes = mem_cgroup_legacy_files,
 	.early_init = 0,
@@ -6763,12 +6772,12 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
 		/*
 		 * Every swap fault against a single page tries to charge the
 		 * page, bail as early as possible.  shmem_unuse() encounters
-		 * already charged pages, too.  page->mem_cgroup is protected
-		 * by the page lock, which serializes swap cache removal, which
-		 * in turn serializes uncharging.
+		 * already charged pages, too.  page and memcg binding is
+		 * protected by the page lock, which serializes swap cache
+		 * removal, which in turn serializes uncharging.
 		 */
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
-		if (compound_head(page)->mem_cgroup)
+		if (page_memcg(compound_head(page)))
 			goto out;
 
 		id = lookup_swap_cgroup_id(ent);
@@ -6852,21 +6861,21 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 
-	if (!page->mem_cgroup)
+	if (!page_memcg(page))
 		return;
 
 	/*
 	 * Nobody should be changing or seriously looking at
-	 * page->mem_cgroup at this point, we have fully
+	 * page_memcg(page) at this point, we have fully
 	 * exclusive access to the page.
 	 */
 
-	if (ug->memcg != page->mem_cgroup) {
+	if (ug->memcg != page_memcg(page)) {
 		if (ug->memcg) {
 			uncharge_batch(ug);
 			uncharge_gather_clear(ug);
 		}
-		ug->memcg = page->mem_cgroup;
+		ug->memcg = page_memcg(page);
 
 		/* pairs with css_put in uncharge_batch */
 		css_get(&ug->memcg->css);
@@ -6875,15 +6884,13 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 	nr_pages = compound_nr(page);
 	ug->nr_pages += nr_pages;
 
-	if (!PageKmemcg(page)) {
-		ug->pgpgout++;
-	} else {
+	if (PageMemcgKmem(page))
 		ug->nr_kmem += nr_pages;
-		__ClearPageKmemcg(page);
-	}
+	else
+		ug->pgpgout++;
 
 	ug->dummy_page = page;
-	page->mem_cgroup = NULL;
+	page->memcg_data = 0;
 	css_put(&ug->memcg->css);
 }
 
@@ -6926,7 +6933,7 @@ void mem_cgroup_uncharge(struct page *page)
 		return;
 
 	/* Don't touch page->lru of any random page, pre-check: */
-	if (!page->mem_cgroup)
+	if (!page_memcg(page))
 		return;
 
 	uncharge_gather_clear(&ug);
@@ -6976,11 +6983,10 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 		return;
 
 	/* Page cache replacement: new page already charged? */
-	if (newpage->mem_cgroup)
+	if (page_memcg(newpage))
 		return;
 
-	/* Swapcache readahead pages can get replaced before being charged */
-	memcg = oldpage->mem_cgroup;
+	memcg = page_memcg(oldpage);
 	if (!memcg)
 		return;
 
@@ -7175,7 +7181,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return;
 
-	memcg = page->mem_cgroup;
+	memcg = page_memcg(page);
 
 	/* Readahead page, never charged */
 	if (!memcg)
@@ -7196,7 +7202,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	VM_BUG_ON_PAGE(oldid, page);
 	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
 
-	page->mem_cgroup = NULL;
+	page->memcg_data = 0;
 
 	if (!mem_cgroup_is_root(memcg))
 		page_counter_uncharge(&memcg->memory, nr_entries);
@@ -7239,7 +7245,7 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return 0;
 
-	memcg = page->mem_cgroup;
+	memcg = page_memcg(page);
 
 	/* Readahead page, never charged */
 	if (!memcg)
@@ -7320,7 +7326,7 @@ bool mem_cgroup_swap_full(struct page *page)
 	if (cgroup_memory_noswap || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return false;
 
-	memcg = page->mem_cgroup;
+	memcg = page_memcg(page);
 	if (!memcg)
 		return false;
 
@@ -7338,9 +7344,9 @@ bool mem_cgroup_swap_full(struct page *page)
 static int __init setup_swap_account(char *s)
 {
 	if (!strcmp(s, "1"))
-		cgroup_memory_noswap = 0;
+		cgroup_memory_noswap = false;
 	else if (!strcmp(s, "0"))
-		cgroup_memory_noswap = 1;
+		cgroup_memory_noswap = true;
 	return 1;
 }
 __setup("swapaccount=", setup_swap_account);