1 files changed, 214 insertions, 281 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 36e9f38c919d..f5ad1a680494 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -348,48 +348,6 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
 }
 
 /*
- * 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
- *  memcgs, and none but the 200th is kmem-limited, we'd have to have a
- *  200 entry array for that.
- *
- * The current size of the caches array is stored in memcg_nr_cache_ids. It
- * will double each time we have to increase it.
- */
-static DEFINE_IDA(memcg_cache_ida);
-int memcg_nr_cache_ids;
-
-/* Protects memcg_nr_cache_ids */
-static DECLARE_RWSEM(memcg_cache_ids_sem);
-
-void memcg_get_cache_ids(void)
-{
-	down_read(&memcg_cache_ids_sem);
-}
-
-void memcg_put_cache_ids(void)
-{
-	up_read(&memcg_cache_ids_sem);
-}
-
-/*
- * MIN_SIZE is different than 1, because we would like to avoid going through
- * the alloc/free process all the time. In a small machine, 4 kmem-limited
- * cgroups is a reasonable guess. In the future, it could be a parameter or
- * tunable, but that is strictly not necessary.
- *
- * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get
- * this constant directly from cgroup, but it is understandable that this is
- * better kept as an internal representation in cgroup.c. In any case, the
- * cgrp_id space is not getting any smaller, and we don't have to necessarily
- * increase ours as well if it increases.
- */
-#define MEMCG_CACHES_MIN_SIZE 4
-#define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX
-
-/*
  * A lot of the calls to the cache allocation functions are expected to be
  * 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
@@ -629,6 +587,35 @@ static DEFINE_SPINLOCK(stats_flush_lock);
 static DEFINE_PER_CPU(unsigned int, stats_updates);
 static atomic_t stats_flush_threshold = ATOMIC_INIT(0);
 
+/*
+ * Accessors to ensure that preemption is disabled on PREEMPT_RT because it can
+ * not rely on this as part of an acquired spinlock_t lock. These functions are
+ * never used in hardirq context on PREEMPT_RT and therefore disabling preemtion
+ * is sufficient.
+ */
+static void memcg_stats_lock(void)
+{
+#ifdef CONFIG_PREEMPT_RT
+      preempt_disable();
+#else
+      VM_BUG_ON(!irqs_disabled());
+#endif
+}
+
+static void __memcg_stats_lock(void)
+{
+#ifdef CONFIG_PREEMPT_RT
+      preempt_disable();
+#endif
+}
+
+static void memcg_stats_unlock(void)
+{
+#ifdef CONFIG_PREEMPT_RT
+      preempt_enable();
+#endif
+}
+
 static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 {
 	unsigned int x;
@@ -705,6 +692,27 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	memcg = pn->memcg;
 
+	/*
+	 * The caller from rmap relay on disabled preemption becase they never
+	 * update their counter from in-interrupt context. For these two
+	 * counters we check that the update is never performed from an
+	 * interrupt context while other caller need to have disabled interrupt.
+	 */
+	__memcg_stats_lock();
+	if (IS_ENABLED(CONFIG_DEBUG_VM) && !IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		switch (idx) {
+		case NR_ANON_MAPPED:
+		case NR_FILE_MAPPED:
+		case NR_ANON_THPS:
+		case NR_SHMEM_PMDMAPPED:
+		case NR_FILE_PMDMAPPED:
+			WARN_ON_ONCE(!in_task());
+			break;
+		default:
+			WARN_ON_ONCE(!irqs_disabled());
+		}
+	}
+
 	/* Update memcg */
 	__this_cpu_add(memcg->vmstats_percpu->state[idx], val);
 
@@ -712,6 +720,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	__this_cpu_add(pn->lruvec_stats_percpu->state[idx], val);
 
 	memcg_rstat_updated(memcg, val);
+	memcg_stats_unlock();
 }
 
 /**
@@ -794,8 +803,10 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
 	if (mem_cgroup_disabled())
 		return;
 
+	memcg_stats_lock();
 	__this_cpu_add(memcg->vmstats_percpu->events[idx], count);
 	memcg_rstat_updated(memcg, count);
+	memcg_stats_unlock();
 }
 
 static unsigned long memcg_events(struct mem_cgroup *memcg, int event)
@@ -858,6 +869,9 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
  */
 static void memcg_check_events(struct mem_cgroup *memcg, int nid)
 {
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		return;
+
 	/* threshold event is triggered in finer grain than soft limit */
 	if (unlikely(mem_cgroup_event_ratelimit(memcg,
 						MEM_CGROUP_TARGET_THRESH))) {
@@ -1371,6 +1385,7 @@ struct memory_stat {
 static const struct memory_stat memory_stats[] = {
 	{ "anon",			NR_ANON_MAPPED			},
 	{ "file",			NR_FILE_PAGES			},
+	{ "kernel",			MEMCG_KMEM			},
 	{ "kernel_stack",		NR_KERNEL_STACK_KB		},
 	{ "pagetables",			NR_PAGETABLE			},
 	{ "percpu",			MEMCG_PERCPU_B			},
@@ -1795,20 +1810,16 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 		__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
 }
 
-enum oom_status {
-	OOM_SUCCESS,
-	OOM_FAILED,
-	OOM_ASYNC,
-	OOM_SKIPPED
-};
-
-static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
+/*
+ * Returns true if successfully killed one or more processes. Though in some
+ * corner cases it can return true even without killing any process.
+ */
+static bool mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
-	enum oom_status ret;
-	bool locked;
+	bool locked, ret;
 
 	if (order > PAGE_ALLOC_COSTLY_ORDER)
-		return OOM_SKIPPED;
+		return false;
 
 	memcg_memory_event(memcg, MEMCG_OOM);
 
@@ -1831,14 +1842,13 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int
 	 * victim and then we have to bail out from the charge path.
 	 */
 	if (memcg->oom_kill_disable) {
-		if (!current->in_user_fault)
-			return OOM_SKIPPED;
-		css_get(&memcg->css);
-		current->memcg_in_oom = memcg;
-		current->memcg_oom_gfp_mask = mask;
-		current->memcg_oom_order = order;
-
-		return OOM_ASYNC;
+		if (current->in_user_fault) {
+			css_get(&memcg->css);
+			current->memcg_in_oom = memcg;
+			current->memcg_oom_gfp_mask = mask;
+			current->memcg_oom_order = order;
+		}
+		return false;
 	}
 
 	mem_cgroup_mark_under_oom(memcg);
@@ -1849,10 +1859,7 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int
 		mem_cgroup_oom_notify(memcg);
 
 	mem_cgroup_unmark_under_oom(memcg);
-	if (mem_cgroup_out_of_memory(memcg, mask, order))
-		ret = OOM_SUCCESS;
-	else
-		ret = OOM_FAILED;
+	ret = mem_cgroup_out_of_memory(memcg, mask, order);
 
 	if (locked)
 		mem_cgroup_oom_unlock(memcg);
@@ -2085,45 +2092,47 @@ void unlock_page_memcg(struct page *page)
 	folio_memcg_unlock(page_folio(page));
 }
 
-struct obj_stock {
+struct memcg_stock_pcp {
+	local_lock_t stock_lock;
+	struct mem_cgroup *cached; /* this never be root cgroup */
+	unsigned int nr_pages;
+
 #ifdef CONFIG_MEMCG_KMEM
 	struct obj_cgroup *cached_objcg;
 	struct pglist_data *cached_pgdat;
 	unsigned int nr_bytes;
 	int nr_slab_reclaimable_b;
 	int nr_slab_unreclaimable_b;
-#else
-	int dummy[0];
 #endif
-};
-
-struct memcg_stock_pcp {
-	struct mem_cgroup *cached; /* this never be root cgroup */
-	unsigned int nr_pages;
-	struct obj_stock task_obj;
-	struct obj_stock irq_obj;
 
 	struct work_struct work;
 	unsigned long flags;
 #define FLUSHING_CACHED_CHARGE	0
 };
-static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
+static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock) = {
+	.stock_lock = INIT_LOCAL_LOCK(stock_lock),
+};
 static DEFINE_MUTEX(percpu_charge_mutex);
 
 #ifdef CONFIG_MEMCG_KMEM
-static void drain_obj_stock(struct obj_stock *stock);
+static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock);
 static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
 				     struct mem_cgroup *root_memcg);
+static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages);
 
 #else
-static inline void drain_obj_stock(struct obj_stock *stock)
+static inline struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock)
 {
+	return NULL;
 }
 static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
 				     struct mem_cgroup *root_memcg)
 {
 	return false;
 }
+static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages)
+{
+}
 #endif
 
 /**
@@ -2146,7 +2155,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 	if (nr_pages > MEMCG_CHARGE_BATCH)
 		return ret;
 
-	local_irq_save(flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
@@ -2154,7 +2163,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 		ret = true;
 	}
 
-	local_irq_restore(flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	return ret;
 }
@@ -2183,6 +2192,7 @@ static void drain_stock(struct memcg_stock_pcp *stock)
 static void drain_local_stock(struct work_struct *dummy)
 {
 	struct memcg_stock_pcp *stock;
+	struct obj_cgroup *old = NULL;
 	unsigned long flags;
 
 	/*
@@ -2190,28 +2200,25 @@ static void drain_local_stock(struct work_struct *dummy)
 	 * drain_stock races is that we always operate on local CPU stock
 	 * here with IRQ disabled
 	 */
-	local_irq_save(flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
-	drain_obj_stock(&stock->irq_obj);
-	if (in_task())
-		drain_obj_stock(&stock->task_obj);
+	old = drain_obj_stock(stock);
 	drain_stock(stock);
 	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
 
-	local_irq_restore(flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	if (old)
+		obj_cgroup_put(old);
 }
 
 /*
  * Cache charges(val) to local per_cpu area.
  * This will be consumed by consume_stock() function, later.
  */
-static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
+static void __refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	struct memcg_stock_pcp *stock;
-	unsigned long flags;
-
-	local_irq_save(flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	if (stock->cached != memcg) { /* reset if necessary */
@@ -2223,8 +2230,15 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 
 	if (stock->nr_pages > MEMCG_CHARGE_BATCH)
 		drain_stock(stock);
+}
 
-	local_irq_restore(flags);
+static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
+{
+	unsigned long flags;
+
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	__refill_stock(memcg, nr_pages);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 }
 
 /*
@@ -2244,7 +2258,8 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 	 * as well as workers from this path always operate on the local
 	 * per-cpu data. CPU up doesn't touch memcg_stock at all.
 	 */
-	curcpu = get_cpu();
+	migrate_disable();
+	curcpu = smp_processor_id();
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
 		struct mem_cgroup *memcg;
@@ -2267,7 +2282,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 				schedule_work_on(cpu, &stock->work);
 		}
 	}
-	put_cpu();
+	migrate_enable();
 	mutex_unlock(&percpu_charge_mutex);
 }
 
@@ -2541,7 +2556,6 @@ static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	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 passed_oom = false;
 	bool may_swap = true;
@@ -2570,15 +2584,6 @@ retry:
 	}
 
 	/*
-	 * Memcg doesn't have a dedicated reserve for atomic
-	 * allocations. But like the global atomic pool, we need to
-	 * put the burden of reclaim on regular allocation requests
-	 * and let these go through as privileged allocations.
-	 */
-	if (gfp_mask & __GFP_ATOMIC)
-		goto force;
-
-	/*
 	 * Prevent unbounded recursion when reclaim operations need to
 	 * allocate memory. This might exceed the limits temporarily,
 	 * but we prefer facilitating memory reclaim and getting back
@@ -2644,15 +2649,20 @@ retry:
 	 * a forward progress or bypass the charge if the oom killer
 	 * couldn't make any progress.
 	 */
-	oom_status = mem_cgroup_oom(mem_over_limit, gfp_mask,
-		       get_order(nr_pages * PAGE_SIZE));
-	if (oom_status == OOM_SUCCESS) {
+	if (mem_cgroup_oom(mem_over_limit, gfp_mask,
+			   get_order(nr_pages * PAGE_SIZE))) {
 		passed_oom = true;
 		nr_retries = MAX_RECLAIM_RETRIES;
 		goto retry;
 	}
 nomem:
-	if (!(gfp_mask & __GFP_NOFAIL))
+	/*
+	 * Memcg doesn't have a dedicated reserve for atomic
+	 * allocations. But like the global atomic pool, we need to
+	 * put the burden of reclaim on regular allocation requests
+	 * and let these go through as privileged allocations.
+	 */
+	if (!(gfp_mask & (__GFP_NOFAIL | __GFP_HIGH)))
 		return -ENOMEM;
 force:
 	/*
@@ -2688,7 +2698,7 @@ done_restock:
 			READ_ONCE(memcg->swap.high);
 
 		/* Don't bother a random interrupted task */
-		if (in_interrupt()) {
+		if (!in_task()) {
 			if (mem_high) {
 				schedule_work(&memcg->high_work);
 				break;
@@ -2712,6 +2722,11 @@ done_restock:
 		}
 	} while ((memcg = parent_mem_cgroup(memcg)));
 
+	if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH &&
+	    !(current->flags & PF_MEMALLOC) &&
+	    gfpflags_allow_blocking(gfp_mask)) {
+		mem_cgroup_handle_over_high();
+	}
 	return 0;
 }
 
@@ -2748,20 +2763,6 @@ static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
 	folio->memcg_data = (unsigned long)memcg;
 }
 
-static struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
-{
-	struct mem_cgroup *memcg;
-
-	rcu_read_lock();
-retry:
-	memcg = obj_cgroup_memcg(objcg);
-	if (unlikely(!css_tryget(&memcg->css)))
-		goto retry;
-	rcu_read_unlock();
-
-	return memcg;
-}
-
 #ifdef CONFIG_MEMCG_KMEM
 /*
  * The allocated objcg pointers array is not accounted directly.
@@ -2771,41 +2772,6 @@ retry:
 #define OBJCGS_CLEAR_MASK	(__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT)
 
 /*
- * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
- * sequence used in this case to access content from object stock is slow.
- * To optimize for user context access, there are now two object stocks for
- * task context and interrupt context access respectively.
- *
- * The task context object stock can be accessed by disabling preemption only
- * which is cheap in non-preempt kernel. The interrupt context object stock
- * can only be accessed after disabling interrupt. User context code can
- * access interrupt object stock, but not vice versa.
- */
-static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
-{
-	struct memcg_stock_pcp *stock;
-
-	if (likely(in_task())) {
-		*pflags = 0UL;
-		preempt_disable();
-		stock = this_cpu_ptr(&memcg_stock);
-		return &stock->task_obj;
-	}
-
-	local_irq_save(*pflags);
-	stock = this_cpu_ptr(&memcg_stock);
-	return &stock->irq_obj;
-}
-
-static inline void put_obj_stock(unsigned long flags)
-{
-	if (likely(in_task()))
-		preempt_enable();
-	else
-		local_irq_restore(flags);
-}
-
-/*
  * mod_objcg_mlstate() may be called with irq enabled, so
  * mod_memcg_lruvec_state() should be used.
  */
@@ -2936,48 +2902,17 @@ __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
 	return objcg;
 }
 
-static int memcg_alloc_cache_id(void)
+static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages)
 {
-	int id, size;
-	int err;
-
-	id = ida_simple_get(&memcg_cache_ida,
-			    0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
-	if (id < 0)
-		return id;
-
-	if (id < memcg_nr_cache_ids)
-		return id;
-
-	/*
-	 * There's no space for the new id in memcg_caches arrays,
-	 * so we have to grow them.
-	 */
-	down_write(&memcg_cache_ids_sem);
-
-	size = 2 * (id + 1);
-	if (size < MEMCG_CACHES_MIN_SIZE)
-		size = MEMCG_CACHES_MIN_SIZE;
-	else if (size > MEMCG_CACHES_MAX_SIZE)
-		size = MEMCG_CACHES_MAX_SIZE;
-
-	err = memcg_update_all_list_lrus(size);
-	if (!err)
-		memcg_nr_cache_ids = size;
-
-	up_write(&memcg_cache_ids_sem);
-
-	if (err) {
-		ida_simple_remove(&memcg_cache_ida, id);
-		return err;
+	mod_memcg_state(memcg, MEMCG_KMEM, nr_pages);
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) {
+		if (nr_pages > 0)
+			page_counter_charge(&memcg->kmem, nr_pages);
+		else
+			page_counter_uncharge(&memcg->kmem, -nr_pages);
 	}
-	return id;
 }
 
-static void memcg_free_cache_id(int id)
-{
-	ida_simple_remove(&memcg_cache_ida, id);
-}
 
 /*
  * obj_cgroup_uncharge_pages: uncharge a number of kernel pages from a objcg
@@ -2991,8 +2926,7 @@ static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
 
 	memcg = get_mem_cgroup_from_objcg(objcg);
 
-	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
-		page_counter_uncharge(&memcg->kmem, nr_pages);
+	memcg_account_kmem(memcg, -nr_pages);
 	refill_stock(memcg, nr_pages);
 
 	css_put(&memcg->css);
@@ -3018,8 +2952,7 @@ static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp,
 	if (ret)
 		goto out;
 
-	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
-		page_counter_charge(&memcg->kmem, nr_pages);
+	memcg_account_kmem(memcg, nr_pages);
 out:
 	css_put(&memcg->css);
 
@@ -3075,17 +3008,21 @@ void __memcg_kmem_uncharge_page(struct page *page, int order)
 void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 		     enum node_stat_item idx, int nr)
 {
+	struct memcg_stock_pcp *stock;
+	struct obj_cgroup *old = NULL;
 	unsigned long flags;
-	struct obj_stock *stock = get_obj_stock(&flags);
 	int *bytes;
 
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	stock = this_cpu_ptr(&memcg_stock);
+
 	/*
 	 * Save vmstat data in stock and skip vmstat array update unless
 	 * accumulating over a page of vmstat data or when pgdat or idx
 	 * changes.
 	 */
 	if (stock->cached_objcg != objcg) {
-		drain_obj_stock(stock);
+		old = drain_obj_stock(stock);
 		obj_cgroup_get(objcg);
 		stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
 				? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0;
@@ -3129,38 +3066,51 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 	if (nr)
 		mod_objcg_mlstate(objcg, pgdat, idx, nr);
 
-	put_obj_stock(flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	if (old)
+		obj_cgroup_put(old);
 }
 
 static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
 {
+	struct memcg_stock_pcp *stock;
 	unsigned long flags;
-	struct obj_stock *stock = get_obj_stock(&flags);
 	bool ret = false;
 
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+
+	stock = this_cpu_ptr(&memcg_stock);
 	if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) {
 		stock->nr_bytes -= nr_bytes;
 		ret = true;
 	}
 
-	put_obj_stock(flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	return ret;
 }
 
-static void drain_obj_stock(struct obj_stock *stock)
+static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock)
 {
 	struct obj_cgroup *old = stock->cached_objcg;
 
 	if (!old)
-		return;
+		return NULL;
 
 	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)
-			obj_cgroup_uncharge_pages(old, nr_pages);
+		if (nr_pages) {
+			struct mem_cgroup *memcg;
+
+			memcg = get_mem_cgroup_from_objcg(old);
+
+			memcg_account_kmem(memcg, -nr_pages);
+			__refill_stock(memcg, nr_pages);
+
+			css_put(&memcg->css);
+		}
 
 		/*
 		 * The leftover is flushed to the centralized per-memcg value.
@@ -3195,8 +3145,12 @@ static void drain_obj_stock(struct obj_stock *stock)
 		stock->cached_pgdat = NULL;
 	}
 
-	obj_cgroup_put(old);
 	stock->cached_objcg = NULL;
+	/*
+	 * The `old' objects needs to be released by the caller via
+	 * obj_cgroup_put() outside of memcg_stock_pcp::stock_lock.
+	 */
+	return old;
 }
 
 static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
@@ -3204,13 +3158,8 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
 {
 	struct mem_cgroup *memcg;
 
-	if (in_task() && stock->task_obj.cached_objcg) {
-		memcg = obj_cgroup_memcg(stock->task_obj.cached_objcg);
-		if (memcg && mem_cgroup_is_descendant(memcg, root_memcg))
-			return true;
-	}
-	if (stock->irq_obj.cached_objcg) {
-		memcg = obj_cgroup_memcg(stock->irq_obj.cached_objcg);
+	if (stock->cached_objcg) {
+		memcg = obj_cgroup_memcg(stock->cached_objcg);
 		if (memcg && mem_cgroup_is_descendant(memcg, root_memcg))
 			return true;
 	}
@@ -3221,12 +3170,16 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
 static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 			     bool allow_uncharge)
 {
+	struct memcg_stock_pcp *stock;
+	struct obj_cgroup *old = NULL;
 	unsigned long flags;
-	struct obj_stock *stock = get_obj_stock(&flags);
 	unsigned int nr_pages = 0;
 
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+
+	stock = this_cpu_ptr(&memcg_stock);
 	if (stock->cached_objcg != objcg) { /* reset if necessary */
-		drain_obj_stock(stock);
+		old = drain_obj_stock(stock);
 		obj_cgroup_get(objcg);
 		stock->cached_objcg = objcg;
 		stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
@@ -3240,7 +3193,9 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 		stock->nr_bytes &= (PAGE_SIZE - 1);
 	}
 
-	put_obj_stock(flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	if (old)
+		obj_cgroup_put(old);
 
 	if (nr_pages)
 		obj_cgroup_uncharge_pages(objcg, nr_pages);
@@ -3625,28 +3580,23 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 static int memcg_online_kmem(struct mem_cgroup *memcg)
 {
 	struct obj_cgroup *objcg;
-	int memcg_id;
 
 	if (cgroup_memory_nokmem)
 		return 0;
 
-	BUG_ON(memcg->kmemcg_id >= 0);
-
-	memcg_id = memcg_alloc_cache_id();
-	if (memcg_id < 0)
-		return memcg_id;
+	if (unlikely(mem_cgroup_is_root(memcg)))
+		return 0;
 
 	objcg = obj_cgroup_alloc();
-	if (!objcg) {
-		memcg_free_cache_id(memcg_id);
+	if (!objcg)
 		return -ENOMEM;
-	}
+
 	objcg->memcg = memcg;
 	rcu_assign_pointer(memcg->objcg, objcg);
 
 	static_branch_enable(&memcg_kmem_enabled_key);
 
-	memcg->kmemcg_id = memcg_id;
+	memcg->kmemcg_id = memcg->id.id;
 
 	return 0;
 }
@@ -3654,9 +3604,11 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
 static void memcg_offline_kmem(struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *parent;
-	int kmemcg_id;
 
-	if (memcg->kmemcg_id == -1)
+	if (cgroup_memory_nokmem)
+		return;
+
+	if (unlikely(mem_cgroup_is_root(memcg)))
 		return;
 
 	parent = parent_mem_cgroup(memcg);
@@ -3665,19 +3617,13 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 
 	memcg_reparent_objcgs(memcg, parent);
 
-	kmemcg_id = memcg->kmemcg_id;
-	BUG_ON(kmemcg_id < 0);
-
 	/*
 	 * After we have finished memcg_reparent_objcgs(), all list_lrus
 	 * corresponding to this cgroup are guaranteed to remain empty.
 	 * The ordering is imposed by list_lru_node->lock taken by
-	 * memcg_drain_all_list_lrus().
+	 * memcg_reparent_list_lrus().
 	 */
-	memcg_drain_all_list_lrus(kmemcg_id, parent);
-
-	memcg_free_cache_id(kmemcg_id);
-	memcg->kmemcg_id = -1;
+	memcg_reparent_list_lrus(memcg, parent);
 }
 #else
 static int memcg_online_kmem(struct mem_cgroup *memcg)
@@ -3763,8 +3709,12 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
 		}
 		break;
 	case RES_SOFT_LIMIT:
-		memcg->soft_limit = nr_pages;
-		ret = 0;
+		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+			ret = -EOPNOTSUPP;
+		} else {
+			memcg->soft_limit = nr_pages;
+			ret = 0;
+		}
 		break;
 	}
 	return ret ?: nbytes;
@@ -4740,6 +4690,9 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	char *endp;
 	int ret;
 
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		return -EOPNOTSUPP;
+
 	buf = strstrip(buf);
 
 	efd = simple_strtoul(buf, &endp, 10);
@@ -5067,18 +5020,8 @@ struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
 static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 {
 	struct mem_cgroup_per_node *pn;
-	int tmp = node;
-	/*
-	 * This routine is called against possible nodes.
-	 * But it's BUG to call kmalloc() against offline node.
-	 *
-	 * TODO: this routine can waste much memory for nodes which will
-	 *       never be onlined. It's better to use memory hotplug callback
-	 *       function.
-	 */
-	if (!node_state(node, N_NORMAL_MEMORY))
-		tmp = -1;
-	pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp);
+
+	pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, node);
 	if (!pn)
 		return 1;
 
@@ -5090,8 +5033,6 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	}
 
 	lruvec_init(&pn->lruvec);
-	pn->usage_in_excess = 0;
-	pn->on_tree = false;
 	pn->memcg = memcg;
 
 	memcg->nodeinfo[node] = pn;
@@ -5137,8 +5078,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 		return ERR_PTR(error);
 
 	memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL,
-				 1, MEM_CGROUP_ID_MAX,
-				 GFP_KERNEL);
+				 1, MEM_CGROUP_ID_MAX + 1, GFP_KERNEL);
 	if (memcg->id.id < 0) {
 		error = memcg->id.id;
 		goto fail;
@@ -5192,7 +5132,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	struct mem_cgroup *parent = mem_cgroup_from_css(parent_css);
 	struct mem_cgroup *memcg, *old_memcg;
-	long error = -ENOMEM;
 
 	old_memcg = set_active_memcg(parent);
 	memcg = mem_cgroup_alloc();
@@ -5221,34 +5160,26 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 		return &memcg->css;
 	}
 
-	/* The following stuff does not apply to the root */
-	error = memcg_online_kmem(memcg);
-	if (error)
-		goto fail;
-
 	if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket)
 		static_branch_inc(&memcg_sockets_enabled_key);
 
 	return &memcg->css;
-fail:
-	mem_cgroup_id_remove(memcg);
-	mem_cgroup_free(memcg);
-	return ERR_PTR(error);
 }
 
 static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 
+	if (memcg_online_kmem(memcg))
+		goto remove_id;
+
 	/*
 	 * A memcg must be visible for expand_shrinker_info()
 	 * by the time the maps are allocated. So, we allocate maps
 	 * here, when for_each_mem_cgroup() can't skip it.
 	 */
-	if (alloc_shrinker_info(memcg)) {
-		mem_cgroup_id_remove(memcg);
-		return -ENOMEM;
-	}
+	if (alloc_shrinker_info(memcg))
+		goto offline_kmem;
 
 	/* Online state pins memcg ID, memcg ID pins CSS */
 	refcount_set(&memcg->id.ref, 1);
@@ -5258,6 +5189,11 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
 		queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
 				   2UL*HZ);
 	return 0;
+offline_kmem:
+	memcg_offline_kmem(memcg);
+remove_id:
+	mem_cgroup_id_remove(memcg);
+	return -ENOMEM;
 }
 
 static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
@@ -5315,9 +5251,6 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 	cancel_work_sync(&memcg->high_work);
 	mem_cgroup_remove_from_trees(memcg);
 	free_shrinker_info(memcg);
-
-	/* Need to offline kmem if online_css() fails */
-	memcg_offline_kmem(memcg);
 	mem_cgroup_free(memcg);
 }
 
@@ -6801,8 +6734,8 @@ static void uncharge_batch(const struct uncharge_gather *ug)
 		page_counter_uncharge(&ug->memcg->memory, ug->nr_memory);
 		if (do_memsw_account())
 			page_counter_uncharge(&ug->memcg->memsw, ug->nr_memory);
-		if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && ug->nr_kmem)
-			page_counter_uncharge(&ug->memcg->kmem, ug->nr_kmem);
+		if (ug->nr_kmem)
+			memcg_account_kmem(ug->memcg, -ug->nr_kmem);
 		memcg_oom_recover(ug->memcg);
 	}
 
@@ -6821,7 +6754,6 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug)
 	long nr_pages;
 	struct mem_cgroup *memcg;
 	struct obj_cgroup *objcg;
-	bool use_objcg = folio_memcg_kmem(folio);
 
 	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
 
@@ -6830,7 +6762,7 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug)
 	 * folio memcg or objcg at this point, we have fully
 	 * exclusive access to the folio.
 	 */
-	if (use_objcg) {
+	if (folio_memcg_kmem(folio)) {
 		objcg = __folio_objcg(folio);
 		/*
 		 * This get matches the put at the end of the function and
@@ -6858,7 +6790,7 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug)
 
 	nr_pages = folio_nr_pages(folio);
 
-	if (use_objcg) {
+	if (folio_memcg_kmem(folio)) {
 		ug->nr_memory += nr_pages;
 		ug->nr_kmem += nr_pages;
 
@@ -6968,7 +6900,7 @@ void mem_cgroup_sk_alloc(struct sock *sk)
 		return;
 
 	/* Do not associate the sock with unrelated interrupted task's memcg. */
-	if (in_interrupt())
+	if (!in_task())
 		return;
 
 	rcu_read_lock();
@@ -7053,7 +6985,7 @@ static int __init cgroup_memory(char *s)
 		if (!strcmp(token, "nokmem"))
 			cgroup_memory_nokmem = true;
 	}
-	return 0;
+	return 1;
 }
 __setup("cgroup.memory=", cgroup_memory);
 
@@ -7179,8 +7111,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	 * important here to have the interrupts disabled because it is the
 	 * only synchronisation we have for updating the per-CPU variables.
 	 */
-	VM_BUG_ON(!irqs_disabled());
+	memcg_stats_lock();
 	mem_cgroup_charge_statistics(memcg, -nr_entries);
+	memcg_stats_unlock();
 	memcg_check_events(memcg, page_to_nid(page));
 
 	css_put(&memcg->css);