slab: embed memcg_cache_params to kmem_cache

Currently, kmem_cache stores a pointer to struct memcg_cache_params
instead of embedding it.  The rationale is to save memory when kmem
accounting is disabled.  However, the memcg_cache_params has shrivelled
drastically since it was first introduced:

* Initially:

struct memcg_cache_params {
	bool is_root_cache;
	union {
		struct kmem_cache *memcg_caches[0];
		struct {
			struct mem_cgroup *memcg;
			struct list_head list;
			struct kmem_cache *root_cache;
			bool dead;
			atomic_t nr_pages;
			struct work_struct destroy;
		};
	};
};

* Now:

struct memcg_cache_params {
	bool is_root_cache;
	union {
		struct {
			struct rcu_head rcu_head;
			struct kmem_cache *memcg_caches[0];
		};
		struct {
			struct mem_cgroup *memcg;
			struct kmem_cache *root_cache;
		};
	};
};

So the memory saving does not seem to be a clear win anymore.

OTOH, keeping a pointer to memcg_cache_params struct instead of embedding
it results in touching one more cache line on kmem alloc/free hot paths.
Besides, it makes linking kmem caches in a list chained by a field of
struct memcg_cache_params really painful due to a level of indirection,
while I want to make them linked in the following patch.  That said, let
us embed it.

Signed-off-by: Vladimir Davydov <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Christoph Lameter <[email protected]>
Cc: Pekka Enberg <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: Joonsoo Kim <[email protected]>
Cc: Dave Chinner <[email protected]>
Cc: Dan Carpenter <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/slab.h

@@ -473,14 +473,14 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 #ifndef ARCH_SLAB_MINALIGN
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
 #endif
+
+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.
- * struct kmem_cache will hold a pointer to it, so the memory cost while
- * disabled is 1 pointer. The runtime cost while enabled, gets bigger than it
- * would otherwise be if that would be bundled in kmem_cache: we'll need an
- * extra pointer chase. But the trade off clearly lays in favor of not
- * penalizing non-users.
- *
  * 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
@@ -495,10 +495,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 struct memcg_cache_params {
 	bool is_root_cache;
 	union {
-		struct {
-			struct rcu_head rcu_head;
-			struct kmem_cache *memcg_caches[0];
-		};
+		struct memcg_cache_array __rcu *memcg_caches;
 		struct {
 			struct mem_cgroup *memcg;
 			struct kmem_cache *root_cache;

include/linux/slab_def.h

@@ -70,7 +70,7 @@ struct kmem_cache {
 	int obj_offset;
 #endif /* CONFIG_DEBUG_SLAB */
 #ifdef CONFIG_MEMCG_KMEM
-	struct memcg_cache_params *memcg_params;
+	struct memcg_cache_params memcg_params;
 #endif
 
 	struct kmem_cache_node *node[MAX_NUMNODES];

include/linux/slub_def.h

@@ -85,7 +85,7 @@ struct kmem_cache {
 	struct kobject kobj;	/* For sysfs */
 #endif
 #ifdef CONFIG_MEMCG_KMEM
-	struct memcg_cache_params *memcg_params;
+	struct memcg_cache_params memcg_params;
 	int max_attr_size; /* for propagation, maximum size of a stored attr */
 #ifdef CONFIG_SYSFS
 	struct kset *memcg_kset;

mm/memcontrol.c

@@ -332,7 +332,7 @@ struct mem_cgroup {
 	struct cg_proto tcp_mem;
 #endif
 #if defined(CONFIG_MEMCG_KMEM)
-        /* Index in the kmem_cache->memcg_params->memcg_caches array */
+        /* Index in the kmem_cache->memcg_params.memcg_caches array */
 	int kmemcg_id;
 #endif
 
@@ -531,7 +531,7 @@ static void disarm_sock_keys(struct mem_cgroup *memcg)
 
 #ifdef CONFIG_MEMCG_KMEM
 /*
- * This will be the memcg's index in each cache's ->memcg_params->memcg_caches.
+ * This will be the memcg's index in each cache's ->memcg_params.memcg_caches.
  * 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
@@ -2667,8 +2667,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep)
 	struct mem_cgroup *memcg;
 	struct kmem_cache *memcg_cachep;
 
-	VM_BUG_ON(!cachep->memcg_params);
-	VM_BUG_ON(!cachep->memcg_params->is_root_cache);
+	VM_BUG_ON(!is_root_cache(cachep));
 
 	if (current->memcg_kmem_skip_account)
 		return cachep;
@@ -2702,7 +2701,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep)
 void __memcg_kmem_put_cache(struct kmem_cache *cachep)
 {
 	if (!is_root_cache(cachep))
-		css_put(&cachep->memcg_params->memcg->css);
+		css_put(&cachep->memcg_params.memcg->css);
 }
 
 /*
@@ -2778,7 +2777,7 @@ struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr)
 	if (PageSlab(page)) {
 		cachep = page->slab_cache;
 		if (!is_root_cache(cachep))
-			memcg = cachep->memcg_params->memcg;
+			memcg = cachep->memcg_params.memcg;
 	} else
 		/* page allocated by alloc_kmem_pages */
 		memcg = page->mem_cgroup;

mm/slab.h

@@ -86,8 +86,6 @@ extern struct kmem_cache *create_kmalloc_cache(const char *name, size_t size,
 extern void create_boot_cache(struct kmem_cache *, const char *name,
 			size_t size, unsigned long flags);
 
-struct mem_cgroup;
-
 int slab_unmergeable(struct kmem_cache *s);
 struct kmem_cache *find_mergeable(size_t size, size_t align,
 		unsigned long flags, const char *name, void (*ctor)(void *));
@@ -167,14 +165,13 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 #ifdef CONFIG_MEMCG_KMEM
 static inline bool is_root_cache(struct kmem_cache *s)
 {
-	return !s->memcg_params || s->memcg_params->is_root_cache;
+	return s->memcg_params.is_root_cache;
 }
 
 static inline bool slab_equal_or_root(struct kmem_cache *s,
-					struct kmem_cache *p)
+				      struct kmem_cache *p)
 {
-	return (p == s) ||
-		(s->memcg_params && (p == s->memcg_params->root_cache));
+	return p == s || p == s->memcg_params.root_cache;
 }
 
 /*
@@ -185,37 +182,30 @@ static inline bool slab_equal_or_root(struct kmem_cache *s,
 static inline const char *cache_name(struct kmem_cache *s)
 {
 	if (!is_root_cache(s))
-		return s->memcg_params->root_cache->name;
+		s = s->memcg_params.root_cache;
 	return s->name;
 }
 
 /*
  * Note, we protect with RCU only the memcg_caches array, not per-memcg caches.
- * That said the caller must assure the memcg's cache won't go away. Since once
- * created a memcg's cache is destroyed only along with the root cache, it is
- * true if we are going to allocate from the cache or hold a reference to the
- * root cache by other means. Otherwise, we should hold either the slab_mutex
- * or the memcg's slab_caches_mutex while calling this function and accessing
- * the returned value.
+ * That said the caller must assure the memcg's cache won't go away by either
+ * taking a css reference to the owner cgroup, or holding the slab_mutex.
  */
 static inline struct kmem_cache *
 cache_from_memcg_idx(struct kmem_cache *s, int idx)
 {
 	struct kmem_cache *cachep;
-	struct memcg_cache_params *params;
-
-	if (!s->memcg_params)
-		return NULL;
+	struct memcg_cache_array *arr;
 
 	rcu_read_lock();
-	params = rcu_dereference(s->memcg_params);
+	arr = rcu_dereference(s->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 this (see
-	 * memcg_register_cache()).
+	 * memcg_create_kmem_cache()).
 	 */
-	cachep = lockless_dereference(params->memcg_caches[idx]);
+	cachep = lockless_dereference(arr->entries[idx]);
 	rcu_read_unlock();
 
 	return cachep;
@@ -225,7 +215,7 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 {
 	if (is_root_cache(s))
 		return s;
-	return s->memcg_params->root_cache;
+	return s->memcg_params.root_cache;
 }
 
 static __always_inline int memcg_charge_slab(struct kmem_cache *s,
@@ -235,7 +225,7 @@ static __always_inline int memcg_charge_slab(struct kmem_cache *s,
 		return 0;
 	if (is_root_cache(s))
 		return 0;
-	return memcg_charge_kmem(s->memcg_params->memcg, gfp, 1 << order);
+	return memcg_charge_kmem(s->memcg_params.memcg, gfp, 1 << order);
 }
 
 static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
@@ -244,9 +234,13 @@ static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
 		return;
 	if (is_root_cache(s))
 		return;
-	memcg_uncharge_kmem(s->memcg_params->memcg, 1 << order);
+	memcg_uncharge_kmem(s->memcg_params.memcg, 1 << order);
 }
-#else
+
+extern void slab_init_memcg_params(struct kmem_cache *);
+
+#else /* !CONFIG_MEMCG_KMEM */
+
 static inline bool is_root_cache(struct kmem_cache *s)
 {
 	return true;
@@ -282,7 +276,11 @@ static inline int memcg_charge_slab(struct kmem_cache *s, gfp_t gfp, int order)
 static inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
 {
 }
-#endif
+
+static inline void slab_init_memcg_params(struct kmem_cache *s)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
 
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 {