1 files changed, 473 insertions, 279 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8cc617ede7e2..8d9ceea7fe4d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -73,8 +73,6 @@ EXPORT_SYMBOL(memory_cgrp_subsys);
 
 struct mem_cgroup *root_mem_cgroup __read_mostly;
 
-#define MEM_CGROUP_RECLAIM_RETRIES	5
-
 /* Socket memory accounting disabled? */
 static bool cgroup_memory_nosocket;
 
@@ -257,8 +255,100 @@ struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr)
 }
 
 #ifdef CONFIG_MEMCG_KMEM
+extern spinlock_t css_set_lock;
+
+static void obj_cgroup_release(struct percpu_ref *ref)
+{
+	struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt);
+	struct mem_cgroup *memcg;
+	unsigned int nr_bytes;
+	unsigned int nr_pages;
+	unsigned long flags;
+
+	/*
+	 * At this point all allocated objects are freed, and
+	 * objcg->nr_charged_bytes can't have an arbitrary byte value.
+	 * However, it can be PAGE_SIZE or (x * PAGE_SIZE).
+	 *
+	 * The following sequence can lead to it:
+	 * 1) CPU0: objcg == stock->cached_objcg
+	 * 2) CPU1: we do a small allocation (e.g. 92 bytes),
+	 *          PAGE_SIZE bytes are charged
+	 * 3) CPU1: a process from another memcg is allocating something,
+	 *          the stock if flushed,
+	 *          objcg->nr_charged_bytes = PAGE_SIZE - 92
+	 * 5) CPU0: we do release this object,
+	 *          92 bytes are added to stock->nr_bytes
+	 * 6) CPU0: stock is flushed,
+	 *          92 bytes are added to objcg->nr_charged_bytes
+	 *
+	 * In the result, nr_charged_bytes == PAGE_SIZE.
+	 * This page will be uncharged in obj_cgroup_release().
+	 */
+	nr_bytes = atomic_read(&objcg->nr_charged_bytes);
+	WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1));
+	nr_pages = nr_bytes >> PAGE_SHIFT;
+
+	spin_lock_irqsave(&css_set_lock, flags);
+	memcg = obj_cgroup_memcg(objcg);
+	if (nr_pages)
+		__memcg_kmem_uncharge(memcg, nr_pages);
+	list_del(&objcg->list);
+	mem_cgroup_put(memcg);
+	spin_unlock_irqrestore(&css_set_lock, flags);
+
+	percpu_ref_exit(ref);
+	kfree_rcu(objcg, rcu);
+}
+
+static struct obj_cgroup *obj_cgroup_alloc(void)
+{
+	struct obj_cgroup *objcg;
+	int ret;
+
+	objcg = kzalloc(sizeof(struct obj_cgroup), GFP_KERNEL);
+	if (!objcg)
+		return NULL;
+
+	ret = percpu_ref_init(&objcg->refcnt, obj_cgroup_release, 0,
+			      GFP_KERNEL);
+	if (ret) {
+		kfree(objcg);
+		return NULL;
+	}
+	INIT_LIST_HEAD(&objcg->list);
+	return objcg;
+}
+
+static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
+				  struct mem_cgroup *parent)
+{
+	struct obj_cgroup *objcg, *iter;
+
+	objcg = rcu_replace_pointer(memcg->objcg, NULL, true);
+
+	spin_lock_irq(&css_set_lock);
+
+	/* Move active objcg to the parent's list */
+	xchg(&objcg->memcg, parent);
+	css_get(&parent->css);
+	list_add(&objcg->list, &parent->objcg_list);
+
+	/* Move already reparented objcgs to the parent's list */
+	list_for_each_entry(iter, &memcg->objcg_list, list) {
+		css_get(&parent->css);
+		xchg(&iter->memcg, parent);
+		css_put(&memcg->css);
+	}
+	list_splice(&memcg->objcg_list, &parent->objcg_list);
+
+	spin_unlock_irq(&css_set_lock);
+
+	percpu_ref_kill(&objcg->refcnt);
+}
+
 /*
- * This will be the memcg's index in each cache's ->memcg_params.memcg_caches.
+ * This will be used as a shrinker list's index.
  * The main reason for not using cgroup id for this:
  *  this works better in sparse environments, where we have a lot of memcgs,
  *  but only a few kmem-limited. Or also, if we have, for instance, 200
@@ -301,14 +391,12 @@ void memcg_put_cache_ids(void)
 
 /*
  * A lot of the calls to the cache allocation functions are expected to be
- * inlined by the compiler. Since the calls to memcg_kmem_get_cache are
+ * inlined by the compiler. Since the calls to memcg_slab_pre_alloc_hook() are
  * conditional to this static branch, we'll have to allow modules that does
  * kmem_cache_alloc and the such to see this symbol as well
  */
 DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key);
 EXPORT_SYMBOL(memcg_kmem_enabled_key);
-
-struct workqueue_struct *memcg_kmem_cache_wq;
 #endif
 
 static int memcg_shrinker_map_size;
@@ -477,10 +565,17 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
-	if (PageSlab(page) && !PageTail(page))
-		memcg = memcg_from_slab_page(page);
-	else
-		memcg = READ_ONCE(page->mem_cgroup);
+	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;
+
 	while (memcg && !(memcg->css.flags & CSS_ONLINE))
 		memcg = parent_mem_cgroup(memcg);
 	if (memcg)
@@ -681,13 +776,16 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
  */
 void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 {
-	long x;
+	long x, threshold = MEMCG_CHARGE_BATCH;
 
 	if (mem_cgroup_disabled())
 		return;
 
+	if (vmstat_item_in_bytes(idx))
+		threshold <<= PAGE_SHIFT;
+
 	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
-	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+	if (unlikely(abs(x) > threshold)) {
 		struct mem_cgroup *mi;
 
 		/*
@@ -713,29 +811,12 @@ parent_nodeinfo(struct mem_cgroup_per_node *pn, int nid)
 	return mem_cgroup_nodeinfo(parent, nid);
 }
 
-/**
- * __mod_lruvec_state - update lruvec memory statistics
- * @lruvec: the lruvec
- * @idx: the stat item
- * @val: delta to add to the counter, can be negative
- *
- * The lruvec is the intersection of the NUMA node and a cgroup. This
- * function updates the all three counters that are affected by a
- * change of state at this level: per-node, per-cgroup, per-lruvec.
- */
-void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
-			int val)
+void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+			      int val)
 {
-	pg_data_t *pgdat = lruvec_pgdat(lruvec);
 	struct mem_cgroup_per_node *pn;
 	struct mem_cgroup *memcg;
-	long x;
-
-	/* Update node */
-	__mod_node_page_state(pgdat, idx, val);
-
-	if (mem_cgroup_disabled())
-		return;
+	long x, threshold = MEMCG_CHARGE_BATCH;
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	memcg = pn->memcg;
@@ -746,8 +827,12 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	/* Update lruvec */
 	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);
 
+	if (vmstat_item_in_bytes(idx))
+		threshold <<= PAGE_SHIFT;
+
 	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
-	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+	if (unlikely(abs(x) > threshold)) {
+		pg_data_t *pgdat = lruvec_pgdat(lruvec);
 		struct mem_cgroup_per_node *pi;
 
 		for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
@@ -757,6 +842,27 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
 }
 
+/**
+ * __mod_lruvec_state - update lruvec memory statistics
+ * @lruvec: the lruvec
+ * @idx: the stat item
+ * @val: delta to add to the counter, can be negative
+ *
+ * The lruvec is the intersection of the NUMA node and a cgroup. This
+ * function updates the all three counters that are affected by a
+ * change of state at this level: per-node, per-cgroup, per-lruvec.
+ */
+void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+			int val)
+{
+	/* Update node */
+	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+
+	/* Update memcg and lruvec */
+	if (!mem_cgroup_disabled())
+		__mod_memcg_lruvec_state(lruvec, idx, val);
+}
+
 void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
 {
 	pg_data_t *pgdat = page_pgdat(virt_to_page(p));
@@ -1377,12 +1483,11 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 		       (u64)memcg_page_state(memcg, NR_FILE_PAGES) *
 		       PAGE_SIZE);
 	seq_buf_printf(&s, "kernel_stack %llu\n",
-		       (u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) *
+		       (u64)memcg_page_state(memcg, NR_KERNEL_STACK_KB) *
 		       1024);
 	seq_buf_printf(&s, "slab %llu\n",
-		       (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) +
-			     memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE)) *
-		       PAGE_SIZE);
+		       (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B) +
+			     memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE_B)));
 	seq_buf_printf(&s, "sock %llu\n",
 		       (u64)memcg_page_state(memcg, MEMCG_SOCK) *
 		       PAGE_SIZE);
@@ -1412,11 +1517,9 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 			       PAGE_SIZE);
 
 	seq_buf_printf(&s, "slab_reclaimable %llu\n",
-		       (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) *
-		       PAGE_SIZE);
+		       (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B));
 	seq_buf_printf(&s, "slab_unreclaimable %llu\n",
-		       (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE) *
-		       PAGE_SIZE);
+		       (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE_B));
 
 	/* Accumulated memory events */
 
@@ -1560,15 +1663,21 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		.gfp_mask = gfp_mask,
 		.order = order,
 	};
-	bool ret;
+	bool ret = true;
 
 	if (mutex_lock_killable(&oom_lock))
 		return true;
+
+	if (mem_cgroup_margin(memcg) >= (1 << order))
+		goto unlock;
+
 	/*
 	 * A few threads which were not waiting at mutex_lock_killable() can
 	 * fail to bail out. Therefore, check again after holding oom_lock.
 	 */
 	ret = should_force_charge() || out_of_memory(&oc);
+
+unlock:
 	mutex_unlock(&oom_lock);
 	return ret;
 }
@@ -2039,6 +2148,12 @@ EXPORT_SYMBOL(unlock_page_memcg);
 struct memcg_stock_pcp {
 	struct mem_cgroup *cached; /* this never be root cgroup */
 	unsigned int nr_pages;
+
+#ifdef CONFIG_MEMCG_KMEM
+	struct obj_cgroup *cached_objcg;
+	unsigned int nr_bytes;
+#endif
+
 	struct work_struct work;
 	unsigned long flags;
 #define FLUSHING_CACHED_CHARGE	0
@@ -2046,6 +2161,22 @@ struct memcg_stock_pcp {
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
 static DEFINE_MUTEX(percpu_charge_mutex);
 
+#ifdef CONFIG_MEMCG_KMEM
+static void drain_obj_stock(struct memcg_stock_pcp *stock);
+static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
+				     struct mem_cgroup *root_memcg);
+
+#else
+static inline void drain_obj_stock(struct memcg_stock_pcp *stock)
+{
+}
+static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
+				     struct mem_cgroup *root_memcg)
+{
+	return false;
+}
+#endif
+
 /**
  * consume_stock: Try to consume stocked charge on this cpu.
  * @memcg: memcg to consume from.
@@ -2086,13 +2217,17 @@ static void drain_stock(struct memcg_stock_pcp *stock)
 {
 	struct mem_cgroup *old = stock->cached;
 
+	if (!old)
+		return;
+
 	if (stock->nr_pages) {
 		page_counter_uncharge(&old->memory, stock->nr_pages);
 		if (do_memsw_account())
 			page_counter_uncharge(&old->memsw, stock->nr_pages);
-		css_put_many(&old->css, stock->nr_pages);
 		stock->nr_pages = 0;
 	}
+
+	css_put(&old->css);
 	stock->cached = NULL;
 }
 
@@ -2108,6 +2243,7 @@ static void drain_local_stock(struct work_struct *dummy)
 	local_irq_save(flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
+	drain_obj_stock(stock);
 	drain_stock(stock);
 	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
 
@@ -2128,6 +2264,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 	stock = this_cpu_ptr(&memcg_stock);
 	if (stock->cached != memcg) { /* reset if necessary */
 		drain_stock(stock);
+		css_get(&memcg->css);
 		stock->cached = memcg;
 	}
 	stock->nr_pages += nr_pages;
@@ -2166,6 +2303,8 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 		if (memcg && stock->nr_pages &&
 		    mem_cgroup_is_descendant(memcg, root_memcg))
 			flush = true;
+		if (obj_stock_flush_required(stock, root_memcg))
+			flush = true;
 		rcu_read_unlock();
 
 		if (flush &&
@@ -2228,18 +2367,29 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu)
 	return 0;
 }
 
-static void reclaim_high(struct mem_cgroup *memcg,
-			 unsigned int nr_pages,
-			 gfp_t gfp_mask)
+static unsigned long reclaim_high(struct mem_cgroup *memcg,
+				  unsigned int nr_pages,
+				  gfp_t gfp_mask)
 {
+	unsigned long nr_reclaimed = 0;
+
 	do {
+		unsigned long pflags;
+
 		if (page_counter_read(&memcg->memory) <=
 		    READ_ONCE(memcg->memory.high))
 			continue;
+
 		memcg_memory_event(memcg, MEMCG_HIGH);
-		try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true);
+
+		psi_memstall_enter(&pflags);
+		nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages,
+							     gfp_mask, true);
+		psi_memstall_leave(&pflags);
 	} while ((memcg = parent_mem_cgroup(memcg)) &&
 		 !mem_cgroup_is_root(memcg));
+
+	return nr_reclaimed;
 }
 
 static void high_work_func(struct work_struct *work)
@@ -2395,16 +2545,32 @@ void mem_cgroup_handle_over_high(void)
 {
 	unsigned long penalty_jiffies;
 	unsigned long pflags;
+	unsigned long nr_reclaimed;
 	unsigned int nr_pages = current->memcg_nr_pages_over_high;
+	int nr_retries = MAX_RECLAIM_RETRIES;
 	struct mem_cgroup *memcg;
+	bool in_retry = false;
 
 	if (likely(!nr_pages))
 		return;
 
 	memcg = get_mem_cgroup_from_mm(current->mm);
-	reclaim_high(memcg, nr_pages, GFP_KERNEL);
 	current->memcg_nr_pages_over_high = 0;
 
+retry_reclaim:
+	/*
+	 * The allocating task should reclaim at least the batch size, but for
+	 * subsequent retries we only want to do what's necessary to prevent oom
+	 * or breaching resource isolation.
+	 *
+	 * This is distinct from memory.max or page allocator behaviour because
+	 * memory.high is currently batched, whereas memory.max and the page
+	 * allocator run every time an allocation is made.
+	 */
+	nr_reclaimed = reclaim_high(memcg,
+				    in_retry ? SWAP_CLUSTER_MAX : nr_pages,
+				    GFP_KERNEL);
+
 	/*
 	 * memory.high is breached and reclaim is unable to keep up. Throttle
 	 * allocators proactively to slow down excessive growth.
@@ -2432,6 +2598,16 @@ void mem_cgroup_handle_over_high(void)
 		goto out;
 
 	/*
+	 * If reclaim is making forward progress but we're still over
+	 * memory.high, we want to encourage that rather than doing allocator
+	 * throttling.
+	 */
+	if (nr_reclaimed || nr_retries--) {
+		in_retry = true;
+		goto retry_reclaim;
+	}
+
+	/*
 	 * If we exit early, we're guaranteed to die (since
 	 * schedule_timeout_killable sets TASK_KILLABLE). This means we don't
 	 * need to account for any ill-begotten jiffies to pay them off later.
@@ -2448,13 +2624,14 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		      unsigned int nr_pages)
 {
 	unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages);
-	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+	int nr_retries = MAX_RECLAIM_RETRIES;
 	struct mem_cgroup *mem_over_limit;
 	struct page_counter *counter;
+	enum oom_status oom_status;
 	unsigned long nr_reclaimed;
 	bool may_swap = true;
 	bool drained = false;
-	enum oom_status oom_status;
+	unsigned long pflags;
 
 	if (mem_cgroup_is_root(memcg))
 		return 0;
@@ -2514,8 +2691,10 @@ retry:
 
 	memcg_memory_event(mem_over_limit, MEMCG_MAX);
 
+	psi_memstall_enter(&pflags);
 	nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
 						    gfp_mask, may_swap);
+	psi_memstall_leave(&pflags);
 
 	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
 		goto retry;
@@ -2567,7 +2746,7 @@ retry:
 		       get_order(nr_pages * PAGE_SIZE));
 	switch (oom_status) {
 	case OOM_SUCCESS:
-		nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+		nr_retries = MAX_RECLAIM_RETRIES;
 		goto retry;
 	case OOM_FAILED:
 		goto force;
@@ -2586,12 +2765,10 @@ force:
 	page_counter_charge(&memcg->memory, nr_pages);
 	if (do_memsw_account())
 		page_counter_charge(&memcg->memsw, nr_pages);
-	css_get_many(&memcg->css, nr_pages);
 
 	return 0;
 
 done_restock:
-	css_get_many(&memcg->css, batch);
 	if (batch > nr_pages)
 		refill_stock(memcg, batch - nr_pages);
 
@@ -2649,8 +2826,6 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 	page_counter_uncharge(&memcg->memory, nr_pages);
 	if (do_memsw_account())
 		page_counter_uncharge(&memcg->memsw, nr_pages);
-
-	css_put_many(&memcg->css, nr_pages);
 }
 #endif
 
@@ -2669,6 +2844,26 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
 }
 
 #ifdef CONFIG_MEMCG_KMEM
+int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
+				 gfp_t gfp)
+{
+	unsigned int objects = objs_per_slab_page(s, page);
+	void *vec;
+
+	vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
+			   page_to_nid(page));
+	if (!vec)
+		return -ENOMEM;
+
+	if (cmpxchg(&page->obj_cgroups, NULL,
+		    (struct obj_cgroup **) ((unsigned long)vec | 0x1UL)))
+		kfree(vec);
+	else
+		kmemleak_not_leak(vec);
+
+	return 0;
+}
+
 /*
  * Returns a pointer to the memory cgroup to which the kernel object is charged.
  *
@@ -2685,17 +2880,50 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p)
 	page = virt_to_head_page(p);
 
 	/*
-	 * Slab pages don't have page->mem_cgroup set because corresponding
-	 * kmem caches can be reparented during the lifetime. That's why
-	 * memcg_from_slab_page() should be used instead.
+	 * Slab objects are accounted individually, not per-page.
+	 * Memcg membership data for each individual object is saved in
+	 * the page->obj_cgroups.
 	 */
-	if (PageSlab(page))
-		return memcg_from_slab_page(page);
+	if (page_has_obj_cgroups(page)) {
+		struct obj_cgroup *objcg;
+		unsigned int off;
+
+		off = obj_to_index(page->slab_cache, page, p);
+		objcg = page_obj_cgroups(page)[off];
+		if (objcg)
+			return obj_cgroup_memcg(objcg);
+
+		return NULL;
+	}
 
 	/* All other pages use page->mem_cgroup */
 	return page->mem_cgroup;
 }
 
+__always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
+{
+	struct obj_cgroup *objcg = NULL;
+	struct mem_cgroup *memcg;
+
+	if (unlikely(!current->mm && !current->active_memcg))
+		return NULL;
+
+	rcu_read_lock();
+	if (unlikely(current->active_memcg))
+		memcg = rcu_dereference(current->active_memcg);
+	else
+		memcg = mem_cgroup_from_task(current);
+
+	for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) {
+		objcg = rcu_dereference(memcg->objcg);
+		if (objcg && obj_cgroup_tryget(objcg))
+			break;
+	}
+	rcu_read_unlock();
+
+	return objcg;
+}
+
 static int memcg_alloc_cache_id(void)
 {
 	int id, size;
@@ -2721,9 +2949,7 @@ static int memcg_alloc_cache_id(void)
 	else if (size > MEMCG_CACHES_MAX_SIZE)
 		size = MEMCG_CACHES_MAX_SIZE;
 
-	err = memcg_update_all_caches(size);
-	if (!err)
-		err = memcg_update_all_list_lrus(size);
+	err = memcg_update_all_list_lrus(size);
 	if (!err)
 		memcg_nr_cache_ids = size;
 
@@ -2741,150 +2967,6 @@ static void memcg_free_cache_id(int id)
 	ida_simple_remove(&memcg_cache_ida, id);
 }
 
-struct memcg_kmem_cache_create_work {
-	struct mem_cgroup *memcg;
-	struct kmem_cache *cachep;
-	struct work_struct work;
-};
-
-static void memcg_kmem_cache_create_func(struct work_struct *w)
-{
-	struct memcg_kmem_cache_create_work *cw =
-		container_of(w, struct memcg_kmem_cache_create_work, work);
-	struct mem_cgroup *memcg = cw->memcg;
-	struct kmem_cache *cachep = cw->cachep;
-
-	memcg_create_kmem_cache(memcg, cachep);
-
-	css_put(&memcg->css);
-	kfree(cw);
-}
-
-/*
- * Enqueue the creation of a per-memcg kmem_cache.
- */
-static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
-					       struct kmem_cache *cachep)
-{
-	struct memcg_kmem_cache_create_work *cw;
-
-	if (!css_tryget_online(&memcg->css))
-		return;
-
-	cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN);
-	if (!cw) {
-		css_put(&memcg->css);
-		return;
-	}
-
-	cw->memcg = memcg;
-	cw->cachep = cachep;
-	INIT_WORK(&cw->work, memcg_kmem_cache_create_func);
-
-	queue_work(memcg_kmem_cache_wq, &cw->work);
-}
-
-static inline bool memcg_kmem_bypass(void)
-{
-	if (in_interrupt())
-		return true;
-
-	/* Allow remote memcg charging in kthread contexts. */
-	if ((!current->mm || (current->flags & PF_KTHREAD)) &&
-	     !current->active_memcg)
-		return true;
-	return false;
-}
-
-/**
- * memcg_kmem_get_cache: select the correct per-memcg cache for allocation
- * @cachep: the original global kmem cache
- *
- * Return the kmem_cache we're supposed to use for a slab allocation.
- * We try to use the current memcg's version of the cache.
- *
- * If the cache does not exist yet, if we are the first user of it, we
- * create it asynchronously in a workqueue and let the current allocation
- * go through with the original cache.
- *
- * This function takes a reference to the cache it returns to assure it
- * won't get destroyed while we are working with it. Once the caller is
- * done with it, memcg_kmem_put_cache() must be called to release the
- * reference.
- */
-struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
-{
-	struct mem_cgroup *memcg;
-	struct kmem_cache *memcg_cachep;
-	struct memcg_cache_array *arr;
-	int kmemcg_id;
-
-	VM_BUG_ON(!is_root_cache(cachep));
-
-	if (memcg_kmem_bypass())
-		return cachep;
-
-	rcu_read_lock();
-
-	if (unlikely(current->active_memcg))
-		memcg = current->active_memcg;
-	else
-		memcg = mem_cgroup_from_task(current);
-
-	if (!memcg || memcg == root_mem_cgroup)
-		goto out_unlock;
-
-	kmemcg_id = READ_ONCE(memcg->kmemcg_id);
-	if (kmemcg_id < 0)
-		goto out_unlock;
-
-	arr = rcu_dereference(cachep->memcg_params.memcg_caches);
-
-	/*
-	 * Make sure we will access the up-to-date value. The code updating
-	 * memcg_caches issues a write barrier to match the data dependency
-	 * barrier inside READ_ONCE() (see memcg_create_kmem_cache()).
-	 */
-	memcg_cachep = READ_ONCE(arr->entries[kmemcg_id]);
-
-	/*
-	 * If we are in a safe context (can wait, and not in interrupt
-	 * context), we could be be predictable and return right away.
-	 * This would guarantee that the allocation being performed
-	 * already belongs in the new cache.
-	 *
-	 * However, there are some clashes that can arrive from locking.
-	 * For instance, because we acquire the slab_mutex while doing
-	 * memcg_create_kmem_cache, this means no further allocation
-	 * could happen with the slab_mutex held. So it's better to
-	 * defer everything.
-	 *
-	 * If the memcg is dying or memcg_cache is about to be released,
-	 * don't bother creating new kmem_caches. Because memcg_cachep
-	 * is ZEROed as the fist step of kmem offlining, we don't need
-	 * percpu_ref_tryget_live() here. css_tryget_online() check in
-	 * memcg_schedule_kmem_cache_create() will prevent us from
-	 * creation of a new kmem_cache.
-	 */
-	if (unlikely(!memcg_cachep))
-		memcg_schedule_kmem_cache_create(memcg, cachep);
-	else if (percpu_ref_tryget(&memcg_cachep->memcg_params.refcnt))
-		cachep = memcg_cachep;
-out_unlock:
-	rcu_read_unlock();
-	return cachep;
-}
-
-/**
- * memcg_kmem_put_cache: drop reference taken by memcg_kmem_get_cache
- * @cachep: the cache returned by memcg_kmem_get_cache
- */
-void memcg_kmem_put_cache(struct kmem_cache *cachep)
-{
-	if (!is_root_cache(cachep))
-		percpu_ref_put(&cachep->memcg_params.refcnt);
-}
-
 /**
  * __memcg_kmem_charge: charge a number of kernel pages to a memcg
  * @memcg: memory cgroup to charge
@@ -2958,6 +3040,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
 		if (!ret) {
 			page->mem_cgroup = memcg;
 			__SetPageKmemcg(page);
+			return 0;
 		}
 	}
 	css_put(&memcg->css);
@@ -2980,13 +3063,146 @@ 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;
+	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)
+{
+	struct memcg_stock_pcp *stock;
+	unsigned long flags;
+	bool ret = false;
+
+	local_irq_save(flags);
+
+	stock = this_cpu_ptr(&memcg_stock);
+	if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) {
+		stock->nr_bytes -= nr_bytes;
+		ret = true;
+	}
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static void drain_obj_stock(struct memcg_stock_pcp *stock)
+{
+	struct obj_cgroup *old = stock->cached_objcg;
+
+	if (!old)
+		return;
+
+	if (stock->nr_bytes) {
+		unsigned int nr_pages = stock->nr_bytes >> PAGE_SHIFT;
+		unsigned int nr_bytes = stock->nr_bytes & (PAGE_SIZE - 1);
+
+		if (nr_pages) {
+			rcu_read_lock();
+			__memcg_kmem_uncharge(obj_cgroup_memcg(old), nr_pages);
+			rcu_read_unlock();
+		}
+
+		/*
+		 * The leftover is flushed to the centralized per-memcg value.
+		 * On the next attempt to refill obj stock it will be moved
+		 * to a per-cpu stock (probably, on an other CPU), see
+		 * refill_obj_stock().
+		 *
+		 * How often it's flushed is a trade-off between the memory
+		 * limit enforcement accuracy and potential CPU contention,
+		 * so it might be changed in the future.
+		 */
+		atomic_add(nr_bytes, &old->nr_charged_bytes);
+		stock->nr_bytes = 0;
+	}
+
+	obj_cgroup_put(old);
+	stock->cached_objcg = NULL;
+}
+
+static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
+				     struct mem_cgroup *root_memcg)
+{
+	struct mem_cgroup *memcg;
+
+	if (stock->cached_objcg) {
+		memcg = obj_cgroup_memcg(stock->cached_objcg);
+		if (memcg && mem_cgroup_is_descendant(memcg, root_memcg))
+			return true;
+	}
+
+	return false;
+}
+
+static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
+{
+	struct memcg_stock_pcp *stock;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	stock = this_cpu_ptr(&memcg_stock);
+	if (stock->cached_objcg != objcg) { /* reset if necessary */
+		drain_obj_stock(stock);
+		obj_cgroup_get(objcg);
+		stock->cached_objcg = objcg;
+		stock->nr_bytes = atomic_xchg(&objcg->nr_charged_bytes, 0);
+	}
+	stock->nr_bytes += nr_bytes;
+
+	if (stock->nr_bytes > PAGE_SIZE)
+		drain_obj_stock(stock);
+
+	local_irq_restore(flags);
+}
+
+int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size)
+{
+	struct mem_cgroup *memcg;
+	unsigned int nr_pages, nr_bytes;
+	int ret;
+
+	if (consume_obj_stock(objcg, size))
+		return 0;
+
+	/*
+	 * In theory, memcg->nr_charged_bytes can have enough
+	 * pre-charged bytes to satisfy the allocation. However,
+	 * flushing memcg->nr_charged_bytes requires two atomic
+	 * operations, and memcg->nr_charged_bytes can't be big,
+	 * so it's better to ignore it and try grab some new pages.
+	 * memcg->nr_charged_bytes will be flushed in
+	 * refill_obj_stock(), called from this function or
+	 * independently later.
+	 */
+	rcu_read_lock();
+	memcg = obj_cgroup_memcg(objcg);
+	css_get(&memcg->css);
+	rcu_read_unlock();
+
+	nr_pages = size >> PAGE_SHIFT;
+	nr_bytes = size & (PAGE_SIZE - 1);
+
+	if (nr_bytes)
+		nr_pages += 1;
 
-	css_put_many(&memcg->css, nr_pages);
+	ret = __memcg_kmem_charge(memcg, gfp, nr_pages);
+	if (!ret && nr_bytes)
+		refill_obj_stock(objcg, PAGE_SIZE - nr_bytes);
+
+	css_put(&memcg->css);
+	return ret;
 }
+
+void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
+{
+	refill_obj_stock(objcg, size);
+}
+
 #endif /* CONFIG_MEMCG_KMEM */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -2997,13 +3213,16 @@ void __memcg_kmem_uncharge_page(struct page *page, int order)
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
+	struct mem_cgroup *memcg = head->mem_cgroup;
 	int i;
 
 	if (mem_cgroup_disabled())
 		return;
 
-	for (i = 1; i < HPAGE_PMD_NR; i++)
-		head[i].mem_cgroup = head->mem_cgroup;
+	for (i = 1; i < HPAGE_PMD_NR; i++) {
+		css_get(&memcg->css);
+		head[i].mem_cgroup = memcg;
+	}
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
@@ -3207,7 +3426,7 @@ static inline bool memcg_has_children(struct mem_cgroup *memcg)
  */
 static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 {
-	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+	int nr_retries = MAX_RECLAIM_RETRIES;
 
 	/* we call try-to-free pages for make this cgroup empty */
 	lru_add_drain_all();
@@ -3404,6 +3623,7 @@ static void memcg_flush_percpu_vmevents(struct mem_cgroup *memcg)
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_online_kmem(struct mem_cgroup *memcg)
 {
+	struct obj_cgroup *objcg;
 	int memcg_id;
 
 	if (cgroup_memory_nokmem)
@@ -3416,7 +3636,16 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
 	if (memcg_id < 0)
 		return memcg_id;
 
-	static_branch_inc(&memcg_kmem_enabled_key);
+	objcg = obj_cgroup_alloc();
+	if (!objcg) {
+		memcg_free_cache_id(memcg_id);
+		return -ENOMEM;
+	}
+	objcg->memcg = memcg;
+	rcu_assign_pointer(memcg->objcg, objcg);
+
+	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
@@ -3425,7 +3654,6 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
 	 */
 	memcg->kmemcg_id = memcg_id;
 	memcg->kmem_state = KMEM_ONLINE;
-	INIT_LIST_HEAD(&memcg->kmem_caches);
 
 	return 0;
 }
@@ -3438,22 +3666,14 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 
 	if (memcg->kmem_state != KMEM_ONLINE)
 		return;
-	/*
-	 * Clear the online state before clearing memcg_caches array
-	 * entries. The slab_mutex in memcg_deactivate_kmem_caches()
-	 * guarantees that no cache will be created for this cgroup
-	 * after we are done (see memcg_create_kmem_cache()).
-	 */
+
 	memcg->kmem_state = KMEM_ALLOCATED;
 
 	parent = parent_mem_cgroup(memcg);
 	if (!parent)
 		parent = root_mem_cgroup;
 
-	/*
-	 * Deactivate and reparent kmem_caches.
-	 */
-	memcg_deactivate_kmem_caches(memcg, parent);
+	memcg_reparent_objcgs(memcg, parent);
 
 	kmemcg_id = memcg->kmemcg_id;
 	BUG_ON(kmemcg_id < 0);
@@ -3486,11 +3706,6 @@ static void memcg_free_kmem(struct mem_cgroup *memcg)
 	/* css_alloc() failed, offlining didn't happen */
 	if (unlikely(memcg->kmem_state == KMEM_ONLINE))
 		memcg_offline_kmem(memcg);
-
-	if (memcg->kmem_state == KMEM_ALLOCATED) {
-		WARN_ON(!list_empty(&memcg->kmem_caches));
-		static_branch_dec(&memcg_kmem_enabled_key);
-	}
 }
 #else
 static int memcg_online_kmem(struct mem_cgroup *memcg)
@@ -4800,9 +5015,6 @@ static struct cftype mem_cgroup_legacy_files[] = {
 	(defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG))
 	{
 		.name = "kmem.slabinfo",
-		.seq_start = memcg_slab_start,
-		.seq_next = memcg_slab_next,
-		.seq_stop = memcg_slab_stop,
 		.seq_show = memcg_slab_show,
 	},
 #endif
@@ -5022,6 +5234,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	memcg->socket_pressure = jiffies;
 #ifdef CONFIG_MEMCG_KMEM
 	memcg->kmemcg_id = -1;
+	INIT_LIST_HEAD(&memcg->objcg_list);
 #endif
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&memcg->cgwb_list);
@@ -5084,9 +5297,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	/* The following stuff does not apply to the root */
 	if (!parent) {
-#ifdef CONFIG_MEMCG_KMEM
-		INIT_LIST_HEAD(&memcg->kmem_caches);
-#endif
 		root_mem_cgroup = memcg;
 		return &memcg->css;
 	}
@@ -5448,7 +5658,10 @@ static int mem_cgroup_move_account(struct page *page,
 	 */
 	smp_mb();
 
-	page->mem_cgroup = to; 	/* caller should have done css_get */
+	css_get(&to->css);
+	css_put(&from->css);
+
+	page->mem_cgroup = to;
 
 	__unlock_page_memcg(from);
 
@@ -5669,8 +5882,6 @@ static void __mem_cgroup_clear_mc(void)
 		if (!mem_cgroup_is_root(mc.to))
 			page_counter_uncharge(&mc.to->memory, mc.moved_swap);
 
-		css_put_many(&mc.to->css, mc.moved_swap);
-
 		mc.moved_swap = 0;
 	}
 	memcg_oom_recover(from);
@@ -6036,7 +6247,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 				 char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	unsigned int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+	unsigned int nr_retries = MAX_RECLAIM_RETRIES;
 	bool drained = false;
 	unsigned long high;
 	int err;
@@ -6046,8 +6257,6 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 	if (err)
 		return err;
 
-	page_counter_set_high(&memcg->memory, high);
-
 	for (;;) {
 		unsigned long nr_pages = page_counter_read(&memcg->memory);
 		unsigned long reclaimed;
@@ -6071,6 +6280,10 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 			break;
 	}
 
+	page_counter_set_high(&memcg->memory, high);
+
+	memcg_wb_domain_size_changed(memcg);
+
 	return nbytes;
 }
 
@@ -6084,7 +6297,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	unsigned int nr_reclaims = MEM_CGROUP_RECLAIM_RETRIES;
+	unsigned int nr_reclaims = MAX_RECLAIM_RETRIES;
 	bool drained = false;
 	unsigned long max;
 	int err;
@@ -6391,40 +6604,42 @@ static unsigned long effective_protection(unsigned long usage,
  *
  * WARNING: This function is not stateless! It can only be used as part
  *          of a top-down tree iteration, not for isolated queries.
- *
- * Returns one of the following:
- *   MEMCG_PROT_NONE: cgroup memory is not protected
- *   MEMCG_PROT_LOW: cgroup memory is protected as long there is
- *     an unprotected supply of reclaimable memory from other cgroups.
- *   MEMCG_PROT_MIN: cgroup memory is protected
  */
-enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
-						struct mem_cgroup *memcg)
+void mem_cgroup_calculate_protection(struct mem_cgroup *root,
+				     struct mem_cgroup *memcg)
 {
 	unsigned long usage, parent_usage;
 	struct mem_cgroup *parent;
 
 	if (mem_cgroup_disabled())
-		return MEMCG_PROT_NONE;
+		return;
 
 	if (!root)
 		root = root_mem_cgroup;
+
+	/*
+	 * Effective values of the reclaim targets are ignored so they
+	 * can be stale. Have a look at mem_cgroup_protection for more
+	 * details.
+	 * TODO: calculation should be more robust so that we do not need
+	 * that special casing.
+	 */
 	if (memcg == root)
-		return MEMCG_PROT_NONE;
+		return;
 
 	usage = page_counter_read(&memcg->memory);
 	if (!usage)
-		return MEMCG_PROT_NONE;
+		return;
 
 	parent = parent_mem_cgroup(memcg);
 	/* No parent means a non-hierarchical mode on v1 memcg */
 	if (!parent)
-		return MEMCG_PROT_NONE;
+		return;
 
 	if (parent == root) {
 		memcg->memory.emin = READ_ONCE(memcg->memory.min);
 		memcg->memory.elow = READ_ONCE(memcg->memory.low);
-		goto out;
+		return;
 	}
 
 	parent_usage = page_counter_read(&parent->memory);
@@ -6438,14 +6653,6 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 			READ_ONCE(memcg->memory.low),
 			READ_ONCE(parent->memory.elow),
 			atomic_long_read(&parent->memory.children_low_usage)));
-
-out:
-	if (usage <= memcg->memory.emin)
-		return MEMCG_PROT_MIN;
-	else if (usage <= memcg->memory.elow)
-		return MEMCG_PROT_LOW;
-	else
-		return MEMCG_PROT_NONE;
 }
 
 /**
@@ -6498,6 +6705,7 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
 	if (ret)
 		goto out_put;
 
+	css_get(&memcg->css);
 	commit_charge(page, memcg);
 
 	local_irq_disable();
@@ -6552,9 +6760,6 @@ static void uncharge_batch(const struct uncharge_gather *ug)
 	__this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages);
 	memcg_check_events(ug->memcg, ug->dummy_page);
 	local_irq_restore(flags);
-
-	if (!mem_cgroup_is_root(ug->memcg))
-		css_put_many(&ug->memcg->css, ug->nr_pages);
 }
 
 static void uncharge_page(struct page *page, struct uncharge_gather *ug)
@@ -6592,6 +6797,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 
 	ug->dummy_page = page;
 	page->mem_cgroup = NULL;
+	css_put(&ug->memcg->css);
 }
 
 static void uncharge_list(struct list_head *page_list)
@@ -6697,8 +6903,8 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 	page_counter_charge(&memcg->memory, nr_pages);
 	if (do_memsw_account())
 		page_counter_charge(&memcg->memsw, nr_pages);
-	css_get_many(&memcg->css, nr_pages);
 
+	css_get(&memcg->css);
 	commit_charge(newpage, memcg);
 
 	local_irq_save(flags);
@@ -6821,17 +7027,6 @@ static int __init mem_cgroup_init(void)
 {
 	int cpu, node;
 
-#ifdef CONFIG_MEMCG_KMEM
-	/*
-	 * Kmem cache creation is mostly done with the slab_mutex held,
-	 * so use a workqueue with limited concurrency to avoid stalling
-	 * all worker threads in case lots of cgroups are created and
-	 * destroyed simultaneously.
-	 */
-	memcg_kmem_cache_wq = alloc_workqueue("memcg_kmem_cache", 0, 1);
-	BUG_ON(!memcg_kmem_cache_wq);
-#endif
-
 	cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
 				  memcg_hotplug_cpu_dead);
 
@@ -6935,8 +7130,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	mem_cgroup_charge_statistics(memcg, page, -nr_entries);
 	memcg_check_events(memcg, page);
 
-	if (!mem_cgroup_is_root(memcg))
-		css_put_many(&memcg->css, nr_entries);
+	css_put(&memcg->css);
 }
 
 /**