1 files changed, 60 insertions, 39 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2ed5f2a0879d..09d342c7cbd0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -84,7 +84,7 @@ EXPORT_PER_CPU_SYMBOL_GPL(int_active_memcg);
 static bool cgroup_memory_nosocket __ro_after_init;
 
 /* Kernel memory accounting disabled? */
-bool cgroup_memory_nokmem __ro_after_init;
+static bool cgroup_memory_nokmem __ro_after_init;
 
 /* Whether the swap controller is active */
 #ifdef CONFIG_MEMCG_SWAP
@@ -629,11 +629,17 @@ static DEFINE_SPINLOCK(stats_flush_lock);
 static DEFINE_PER_CPU(unsigned int, stats_updates);
 static atomic_t stats_flush_threshold = ATOMIC_INIT(0);
 
-static inline void memcg_rstat_updated(struct mem_cgroup *memcg)
+static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 {
+	unsigned int x;
+
 	cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id());
-	if (!(__this_cpu_inc_return(stats_updates) % MEMCG_CHARGE_BATCH))
-		atomic_inc(&stats_flush_threshold);
+
+	x = __this_cpu_add_return(stats_updates, abs(val));
+	if (x > MEMCG_CHARGE_BATCH) {
+		atomic_add(x / MEMCG_CHARGE_BATCH, &stats_flush_threshold);
+		__this_cpu_write(stats_updates, 0);
+	}
 }
 
 static void __mem_cgroup_flush_stats(void)
@@ -656,7 +662,7 @@ void mem_cgroup_flush_stats(void)
 
 static void flush_memcg_stats_dwork(struct work_struct *w)
 {
-	mem_cgroup_flush_stats();
+	__mem_cgroup_flush_stats();
 	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ);
 }
 
@@ -672,7 +678,7 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 		return;
 
 	__this_cpu_add(memcg->vmstats_percpu->state[idx], val);
-	memcg_rstat_updated(memcg);
+	memcg_rstat_updated(memcg, val);
 }
 
 /* idx can be of type enum memcg_stat_item or node_stat_item. */
@@ -705,7 +711,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	/* Update lruvec */
 	__this_cpu_add(pn->lruvec_stats_percpu->state[idx], val);
 
-	memcg_rstat_updated(memcg);
+	memcg_rstat_updated(memcg, val);
 }
 
 /**
@@ -789,7 +795,7 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
 		return;
 
 	__this_cpu_add(memcg->vmstats_percpu->events[idx], count);
-	memcg_rstat_updated(memcg);
+	memcg_rstat_updated(memcg, count);
 }
 
 static unsigned long memcg_events(struct mem_cgroup *memcg, int event)
@@ -1369,6 +1375,7 @@ static const struct memory_stat memory_stats[] = {
 	{ "pagetables",			NR_PAGETABLE			},
 	{ "percpu",			MEMCG_PERCPU_B			},
 	{ "sock",			MEMCG_SOCK			},
+	{ "vmalloc",			MEMCG_VMALLOC			},
 	{ "shmem",			NR_SHMEM			},
 	{ "file_mapped",		NR_FILE_MAPPED			},
 	{ "file_dirty",			NR_FILE_DIRTY			},
@@ -2816,31 +2823,31 @@ static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
 	rcu_read_unlock();
 }
 
-int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
-				 gfp_t gfp, bool new_page)
+int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s,
+				 gfp_t gfp, bool new_slab)
 {
-	unsigned int objects = objs_per_slab_page(s, page);
+	unsigned int objects = objs_per_slab(s, slab);
 	unsigned long memcg_data;
 	void *vec;
 
 	gfp &= ~OBJCGS_CLEAR_MASK;
 	vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
-			   page_to_nid(page));
+			   slab_nid(slab));
 	if (!vec)
 		return -ENOMEM;
 
 	memcg_data = (unsigned long) vec | MEMCG_DATA_OBJCGS;
-	if (new_page) {
+	if (new_slab) {
 		/*
-		 * If the slab page is brand new and nobody can yet access
-		 * it's memcg_data, no synchronization is required and
-		 * memcg_data can be simply assigned.
+		 * If the slab is brand new and nobody can yet access its
+		 * memcg_data, no synchronization is required and memcg_data can
+		 * be simply assigned.
 		 */
-		page->memcg_data = memcg_data;
-	} else if (cmpxchg(&page->memcg_data, 0, memcg_data)) {
+		slab->memcg_data = memcg_data;
+	} else if (cmpxchg(&slab->memcg_data, 0, memcg_data)) {
 		/*
-		 * If the slab page is already in use, somebody can allocate
-		 * and assign obj_cgroups in parallel. In this case the existing
+		 * If the slab is already in use, somebody can allocate and
+		 * assign obj_cgroups in parallel. In this case the existing
 		 * objcg vector should be reused.
 		 */
 		kfree(vec);
@@ -2865,38 +2872,43 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
  */
 struct mem_cgroup *mem_cgroup_from_obj(void *p)
 {
-	struct page *page;
+	struct folio *folio;
 
 	if (mem_cgroup_disabled())
 		return NULL;
 
-	page = virt_to_head_page(p);
+	folio = virt_to_folio(p);
 
 	/*
 	 * Slab objects are accounted individually, not per-page.
 	 * Memcg membership data for each individual object is saved in
-	 * the page->obj_cgroups.
+	 * slab->memcg_data.
 	 */
-	if (page_objcgs_check(page)) {
-		struct obj_cgroup *objcg;
+	if (folio_test_slab(folio)) {
+		struct obj_cgroup **objcgs;
+		struct slab *slab;
 		unsigned int off;
 
-		off = obj_to_index(page->slab_cache, page, p);
-		objcg = page_objcgs(page)[off];
-		if (objcg)
-			return obj_cgroup_memcg(objcg);
+		slab = folio_slab(folio);
+		objcgs = slab_objcgs(slab);
+		if (!objcgs)
+			return NULL;
+
+		off = obj_to_index(slab->slab_cache, slab, p);
+		if (objcgs[off])
+			return obj_cgroup_memcg(objcgs[off]);
 
 		return NULL;
 	}
 
 	/*
-	 * 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() is used here, because in theory we can encounter
+	 * a folio where the slab flag has been cleared already, but
+	 * slab->memcg_data has not been freed yet
 	 * page_memcg_check(page) will guarantee that a proper memory
 	 * cgroup pointer or NULL will be returned.
 	 */
-	return page_memcg_check(page);
+	return page_memcg_check(folio_page(folio, 0));
 }
 
 __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
@@ -4845,6 +4857,17 @@ out_kfree:
 	return ret;
 }
 
+#if defined(CONFIG_MEMCG_KMEM) && (defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG))
+static int mem_cgroup_slab_show(struct seq_file *m, void *p)
+{
+	/*
+	 * Deprecated.
+	 * Please, take a look at tools/cgroup/slabinfo.py .
+	 */
+	return 0;
+}
+#endif
+
 static struct cftype mem_cgroup_legacy_files[] = {
 	{
 		.name = "usage_in_bytes",
@@ -4945,7 +4968,7 @@ static struct cftype mem_cgroup_legacy_files[] = {
 	(defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG))
 	{
 		.name = "kmem.slabinfo",
-		.seq_show = memcg_slab_show,
+		.seq_show = mem_cgroup_slab_show,
 	},
 #endif
 	{
@@ -5105,15 +5128,11 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *memcg;
-	unsigned int size;
 	int node;
 	int __maybe_unused i;
 	long error = -ENOMEM;
 
-	size = sizeof(struct mem_cgroup);
-	size += nr_node_ids * sizeof(struct mem_cgroup_per_node *);
-
-	memcg = kzalloc(size, GFP_KERNEL);
+	memcg = kzalloc(struct_size(memcg, nodeinfo, nr_node_ids), GFP_KERNEL);
 	if (!memcg)
 		return ERR_PTR(error);
 
@@ -6307,6 +6326,8 @@ static void __memory_events_show(struct seq_file *m, atomic_long_t *events)
 	seq_printf(m, "oom %lu\n", atomic_long_read(&events[MEMCG_OOM]));
 	seq_printf(m, "oom_kill %lu\n",
 		   atomic_long_read(&events[MEMCG_OOM_KILL]));
+	seq_printf(m, "oom_group_kill %lu\n",
+		   atomic_long_read(&events[MEMCG_OOM_GROUP_KILL]));
 }
 
 static int memory_events_show(struct seq_file *m, void *v)