1 files changed, 162 insertions, 233 deletions

diff --git a/mm/slab.h b/mm/slab.h
index 74f7e09a7cfd..6cc323f1313a 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -30,69 +30,6 @@ struct kmem_cache {
 	struct list_head list;	/* List of all slab caches on the system */
 };
 
-#else /* !CONFIG_SLOB */
-
-struct memcg_cache_array {
-	struct rcu_head rcu;
-	struct kmem_cache *entries[0];
-};
-
-/*
- * This is the main placeholder for memcg-related information in kmem caches.
- * Both the root cache and the child caches will have it. For the root cache,
- * this will hold a dynamically allocated array large enough to hold
- * information about the currently limited memcgs in the system. To allow the
- * array to be accessed without taking any locks, on relocation we free the old
- * version only after a grace period.
- *
- * Root and child caches hold different metadata.
- *
- * @root_cache:	Common to root and child caches.  NULL for root, pointer to
- *		the root cache for children.
- *
- * The following fields are specific to root caches.
- *
- * @memcg_caches: kmemcg ID indexed table of child caches.  This table is
- *		used to index child cachces during allocation and cleared
- *		early during shutdown.
- *
- * @root_caches_node: List node for slab_root_caches list.
- *
- * @children:	List of all child caches.  While the child caches are also
- *		reachable through @memcg_caches, a child cache remains on
- *		this list until it is actually destroyed.
- *
- * The following fields are specific to child caches.
- *
- * @memcg:	Pointer to the memcg this cache belongs to.
- *
- * @children_node: List node for @root_cache->children list.
- *
- * @kmem_caches_node: List node for @memcg->kmem_caches list.
- */
-struct memcg_cache_params {
-	struct kmem_cache *root_cache;
-	union {
-		struct {
-			struct memcg_cache_array __rcu *memcg_caches;
-			struct list_head __root_caches_node;
-			struct list_head children;
-			bool dying;
-		};
-		struct {
-			struct mem_cgroup *memcg;
-			struct list_head children_node;
-			struct list_head kmem_caches_node;
-			struct percpu_ref refcnt;
-
-			void (*work_fn)(struct kmem_cache *);
-			union {
-				struct rcu_head rcu_head;
-				struct work_struct work;
-			};
-		};
-	};
-};
 #endif /* CONFIG_SLOB */
 
 #ifdef CONFIG_SLAB
@@ -109,6 +46,7 @@ struct memcg_cache_params {
 #include <linux/kmemleak.h>
 #include <linux/random.h>
 #include <linux/sched/mm.h>
+#include <linux/kmemleak.h>
 
 /*
  * State of the slab allocator.
@@ -152,6 +90,7 @@ void create_kmalloc_caches(slab_flags_t);
 struct kmem_cache *kmalloc_slab(size_t, gfp_t);
 #endif
 
+gfp_t kmalloc_fix_flags(gfp_t flags);
 
 /* Functions provided by the slab allocators */
 int __kmem_cache_create(struct kmem_cache *, slab_flags_t flags);
@@ -234,10 +173,7 @@ bool __kmem_cache_empty(struct kmem_cache *);
 int __kmem_cache_shutdown(struct kmem_cache *);
 void __kmem_cache_release(struct kmem_cache *);
 int __kmem_cache_shrink(struct kmem_cache *);
-void __kmemcg_cache_deactivate(struct kmem_cache *s);
-void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s);
 void slab_kmem_cache_release(struct kmem_cache *);
-void kmem_cache_shrink_all(struct kmem_cache *s);
 
 struct seq_file;
 struct file;
@@ -272,199 +208,208 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
 static inline int cache_vmstat_idx(struct kmem_cache *s)
 {
 	return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
-		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE;
+		NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
 }
 
-#ifdef CONFIG_MEMCG_KMEM
-
-/* List of all root caches. */
-extern struct list_head		slab_root_caches;
-#define root_caches_node	memcg_params.__root_caches_node
+#ifdef CONFIG_SLUB_DEBUG
+#ifdef CONFIG_SLUB_DEBUG_ON
+DECLARE_STATIC_KEY_TRUE(slub_debug_enabled);
+#else
+DECLARE_STATIC_KEY_FALSE(slub_debug_enabled);
+#endif
+extern void print_tracking(struct kmem_cache *s, void *object);
+#else
+static inline void print_tracking(struct kmem_cache *s, void *object)
+{
+}
+#endif
 
 /*
- * Iterate over all memcg caches of the given root cache. The caller must hold
- * slab_mutex.
+ * Returns true if any of the specified slub_debug flags is enabled for the
+ * cache. Use only for flags parsed by setup_slub_debug() as it also enables
+ * the static key.
  */
-#define for_each_memcg_cache(iter, root) \
-	list_for_each_entry(iter, &(root)->memcg_params.children, \
-			    memcg_params.children_node)
-
-static inline bool is_root_cache(struct kmem_cache *s)
+static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags)
 {
-	return !s->memcg_params.root_cache;
+#ifdef CONFIG_SLUB_DEBUG
+	VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS));
+	if (static_branch_unlikely(&slub_debug_enabled))
+		return s->flags & flags;
+#endif
+	return false;
 }
 
-static inline bool slab_equal_or_root(struct kmem_cache *s,
-				      struct kmem_cache *p)
+#ifdef CONFIG_MEMCG_KMEM
+static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
 {
-	return p == s || p == s->memcg_params.root_cache;
+	/*
+	 * page->mem_cgroup and page->obj_cgroups are sharing the same
+	 * space. To distinguish between them in case we don't know for sure
+	 * that the page is a slab page (e.g. page_cgroup_ino()), let's
+	 * always set the lowest bit of obj_cgroups.
+	 */
+	return (struct obj_cgroup **)
+		((unsigned long)page->obj_cgroups & ~0x1UL);
 }
 
-/*
- * We use suffixes to the name in memcg because we can't have caches
- * created in the system with the same name. But when we print them
- * locally, better refer to them with the base name
- */
-static inline const char *cache_name(struct kmem_cache *s)
+static inline bool page_has_obj_cgroups(struct page *page)
 {
-	if (!is_root_cache(s))
-		s = s->memcg_params.root_cache;
-	return s->name;
+	return ((unsigned long)page->obj_cgroups & 0x1UL);
 }
 
-static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
+int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
+				 gfp_t gfp);
+
+static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
-	if (is_root_cache(s))
-		return s;
-	return s->memcg_params.root_cache;
+	kfree(page_obj_cgroups(page));
+	page->obj_cgroups = NULL;
 }
 
-/*
- * Expects a pointer to a slab page. Please note, that PageSlab() check
- * isn't sufficient, as it returns true also for tail compound slab pages,
- * which do not have slab_cache pointer set.
- * So this function assumes that the page can pass PageSlab() && !PageTail()
- * check.
- *
- * The kmem_cache can be reparented asynchronously. The caller must ensure
- * the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex.
- */
-static inline struct mem_cgroup *memcg_from_slab_page(struct page *page)
+static inline size_t obj_full_size(struct kmem_cache *s)
 {
-	struct kmem_cache *s;
-
-	s = READ_ONCE(page->slab_cache);
-	if (s && !is_root_cache(s))
-		return READ_ONCE(s->memcg_params.memcg);
-
-	return NULL;
+	/*
+	 * For each accounted object there is an extra space which is used
+	 * to store obj_cgroup membership. Charge it too.
+	 */
+	return s->size + sizeof(struct obj_cgroup *);
 }
 
-/*
- * Charge the slab page belonging to the non-root kmem_cache.
- * Can be called for non-root kmem_caches only.
- */
-static __always_inline int memcg_charge_slab(struct page *page,
-					     gfp_t gfp, int order,
-					     struct kmem_cache *s)
+static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
+							   size_t objects,
+							   gfp_t flags)
 {
-	int nr_pages = 1 << order;
-	struct mem_cgroup *memcg;
-	struct lruvec *lruvec;
-	int ret;
-
-	rcu_read_lock();
-	memcg = READ_ONCE(s->memcg_params.memcg);
-	while (memcg && !css_tryget_online(&memcg->css))
-		memcg = parent_mem_cgroup(memcg);
-	rcu_read_unlock();
+	struct obj_cgroup *objcg;
 
-	if (unlikely(!memcg || mem_cgroup_is_root(memcg))) {
-		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    nr_pages);
-		percpu_ref_get_many(&s->memcg_params.refcnt, nr_pages);
-		return 0;
-	}
+	if (memcg_kmem_bypass())
+		return NULL;
 
-	ret = memcg_kmem_charge(memcg, gfp, nr_pages);
-	if (ret)
-		goto out;
+	objcg = get_obj_cgroup_from_current();
+	if (!objcg)
+		return NULL;
 
-	lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
-	mod_lruvec_state(lruvec, cache_vmstat_idx(s), nr_pages);
+	if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) {
+		obj_cgroup_put(objcg);
+		return NULL;
+	}
 
-	/* transer try_charge() page references to kmem_cache */
-	percpu_ref_get_many(&s->memcg_params.refcnt, nr_pages);
-	css_put_many(&memcg->css, nr_pages);
-out:
-	css_put(&memcg->css);
-	return ret;
+	return objcg;
 }
 
-/*
- * Uncharge a slab page belonging to a non-root kmem_cache.
- * Can be called for non-root kmem_caches only.
- */
-static __always_inline void memcg_uncharge_slab(struct page *page, int order,
-						struct kmem_cache *s)
+static inline void mod_objcg_state(struct obj_cgroup *objcg,
+				   struct pglist_data *pgdat,
+				   int idx, int nr)
 {
-	int nr_pages = 1 << order;
 	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
 
 	rcu_read_lock();
-	memcg = READ_ONCE(s->memcg_params.memcg);
-	if (likely(!mem_cgroup_is_root(memcg))) {
-		lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
-		mod_lruvec_state(lruvec, cache_vmstat_idx(s), -nr_pages);
-		memcg_kmem_uncharge(memcg, nr_pages);
-	} else {
-		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    -nr_pages);
-	}
+	memcg = obj_cgroup_memcg(objcg);
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
+	mod_memcg_lruvec_state(lruvec, idx, nr);
 	rcu_read_unlock();
+}
+
+static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
+					      struct obj_cgroup *objcg,
+					      gfp_t flags, size_t size,
+					      void **p)
+{
+	struct page *page;
+	unsigned long off;
+	size_t i;
+
+	if (!objcg)
+		return;
 
-	percpu_ref_put_many(&s->memcg_params.refcnt, nr_pages);
+	flags &= ~__GFP_ACCOUNT;
+	for (i = 0; i < size; i++) {
+		if (likely(p[i])) {
+			page = virt_to_head_page(p[i]);
+
+			if (!page_has_obj_cgroups(page) &&
+			    memcg_alloc_page_obj_cgroups(page, s, flags)) {
+				obj_cgroup_uncharge(objcg, obj_full_size(s));
+				continue;
+			}
+
+			off = obj_to_index(s, page, p[i]);
+			obj_cgroup_get(objcg);
+			page_obj_cgroups(page)[off] = objcg;
+			mod_objcg_state(objcg, page_pgdat(page),
+					cache_vmstat_idx(s), obj_full_size(s));
+		} else {
+			obj_cgroup_uncharge(objcg, obj_full_size(s));
+		}
+	}
+	obj_cgroup_put(objcg);
 }
 
-extern void slab_init_memcg_params(struct kmem_cache *);
-extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
+static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
+					void *p)
+{
+	struct obj_cgroup *objcg;
+	unsigned int off;
 
-#else /* CONFIG_MEMCG_KMEM */
+	if (!memcg_kmem_enabled())
+		return;
 
-/* If !memcg, all caches are root. */
-#define slab_root_caches	slab_caches
-#define root_caches_node	list
+	if (!page_has_obj_cgroups(page))
+		return;
 
-#define for_each_memcg_cache(iter, root) \
-	for ((void)(iter), (void)(root); 0; )
+	off = obj_to_index(s, page, p);
+	objcg = page_obj_cgroups(page)[off];
+	page_obj_cgroups(page)[off] = NULL;
 
-static inline bool is_root_cache(struct kmem_cache *s)
-{
-	return true;
-}
+	if (!objcg)
+		return;
 
-static inline bool slab_equal_or_root(struct kmem_cache *s,
-				      struct kmem_cache *p)
-{
-	return s == p;
-}
+	obj_cgroup_uncharge(objcg, obj_full_size(s));
+	mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
+			-obj_full_size(s));
 
-static inline const char *cache_name(struct kmem_cache *s)
-{
-	return s->name;
+	obj_cgroup_put(objcg);
 }
 
-static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
+#else /* CONFIG_MEMCG_KMEM */
+static inline bool page_has_obj_cgroups(struct page *page)
 {
-	return s;
+	return false;
 }
 
-static inline struct mem_cgroup *memcg_from_slab_page(struct page *page)
+static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
 {
 	return NULL;
 }
 
-static inline int memcg_charge_slab(struct page *page, gfp_t gfp, int order,
-				    struct kmem_cache *s)
+static inline int memcg_alloc_page_obj_cgroups(struct page *page,
+					       struct kmem_cache *s, gfp_t gfp)
 {
 	return 0;
 }
 
-static inline void memcg_uncharge_slab(struct page *page, int order,
-				       struct kmem_cache *s)
+static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
 }
 
-static inline void slab_init_memcg_params(struct kmem_cache *s)
+static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
+							   size_t objects,
+							   gfp_t flags)
 {
+	return NULL;
 }
 
-static inline void memcg_link_cache(struct kmem_cache *s,
-				    struct mem_cgroup *memcg)
+static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
+					      struct obj_cgroup *objcg,
+					      gfp_t flags, size_t size,
+					      void **p)
 {
 }
 
+static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
+					void *p)
+{
+}
 #endif /* CONFIG_MEMCG_KMEM */
 
 static inline struct kmem_cache *virt_to_cache(const void *obj)
@@ -478,51 +423,36 @@ static inline struct kmem_cache *virt_to_cache(const void *obj)
 	return page->slab_cache;
 }
 
-static __always_inline int charge_slab_page(struct page *page,
-					    gfp_t gfp, int order,
-					    struct kmem_cache *s)
+static __always_inline void account_slab_page(struct page *page, int order,
+					      struct kmem_cache *s)
 {
-	if (is_root_cache(s)) {
-		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    1 << order);
-		return 0;
-	}
-
-	return memcg_charge_slab(page, gfp, order, s);
+	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+			    PAGE_SIZE << order);
 }
 
-static __always_inline void uncharge_slab_page(struct page *page, int order,
-					       struct kmem_cache *s)
+static __always_inline void unaccount_slab_page(struct page *page, int order,
+						struct kmem_cache *s)
 {
-	if (is_root_cache(s)) {
-		mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
-				    -(1 << order));
-		return;
-	}
+	if (memcg_kmem_enabled())
+		memcg_free_page_obj_cgroups(page);
 
-	memcg_uncharge_slab(page, order, s);
+	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+			    -(PAGE_SIZE << order));
 }
 
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 {
 	struct kmem_cache *cachep;
 
-	/*
-	 * When kmemcg is not being used, both assignments should return the
-	 * same value. but we don't want to pay the assignment price in that
-	 * case. If it is not compiled in, the compiler should be smart enough
-	 * to not do even the assignment. In that case, slab_equal_or_root
-	 * will also be a constant.
-	 */
-	if (!memcg_kmem_enabled() &&
-	    !IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
-	    !unlikely(s->flags & SLAB_CONSISTENCY_CHECKS))
+	if (!IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
+	    !kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS))
 		return s;
 
 	cachep = virt_to_cache(x);
-	WARN_ONCE(cachep && !slab_equal_or_root(cachep, s),
+	if (WARN(cachep && cachep != s,
 		  "%s: Wrong slab cache. %s but object is from %s\n",
-		  __func__, s->name, cachep->name);
+		  __func__, s->name, cachep->name))
+		print_tracking(cachep, x);
 	return cachep;
 }
 
@@ -557,7 +487,8 @@ static inline size_t slab_ksize(const struct kmem_cache *s)
 }
 
 static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
-						     gfp_t flags)
+						     struct obj_cgroup **objcgp,
+						     size_t size, gfp_t flags)
 {
 	flags &= gfp_allowed_mask;
 
@@ -571,13 +502,14 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
 
 	if (memcg_kmem_enabled() &&
 	    ((flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)))
-		return memcg_kmem_get_cache(s);
+		*objcgp = memcg_slab_pre_alloc_hook(s, size, flags);
 
 	return s;
 }
 
-static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
-					size_t size, void **p)
+static inline void slab_post_alloc_hook(struct kmem_cache *s,
+					struct obj_cgroup *objcg,
+					gfp_t flags, size_t size, void **p)
 {
 	size_t i;
 
@@ -590,7 +522,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
 	}
 
 	if (memcg_kmem_enabled())
-		memcg_kmem_put_cache(s);
+		memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
 }
 
 #ifndef CONFIG_SLOB
@@ -645,9 +577,6 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 void *slab_start(struct seq_file *m, loff_t *pos);
 void *slab_next(struct seq_file *m, void *p, loff_t *pos);
 void slab_stop(struct seq_file *m, void *p);
-void *memcg_slab_start(struct seq_file *m, loff_t *pos);
-void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos);
-void memcg_slab_stop(struct seq_file *m, void *p);
 int memcg_slab_show(struct seq_file *m, void *p);
 
 #if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)