mm: memcg/slab: use a single set of kmem_caches for all allocations

Instead of having two sets of kmem_caches: one for system-wide and
non-accounted allocations and the second one shared by all accounted
allocations, we can use just one.

The idea is simple: space for obj_cgroup metadata can be allocated on
demand and filled only for accounted allocations.

It allows to remove a bunch of code which is required to handle kmem_cache
clones for accounted allocations.  There is no more need to create them,
accumulate statistics, propagate attributes, etc.  It's a quite
significant simplification.

Also, because the total number of slab_caches is reduced almost twice (not
all kmem_caches have a memcg clone), some additional memory savings are
expected.  On my devvm it additionally saves about 3.5% of slab memory.

[guro@fb.com: fix build on MIPS]
  Link: http://lkml.kernel.org/r/20200717214810.3733082-1-guro@fb.com

Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Naresh Kamboju <naresh.kamboju@linaro.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-18-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 42 insertions, 152 deletions

diff --git a/mm/slab.h b/mm/slab.h
index 7500a707121b..ec8e22ee6544 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -30,28 +30,6 @@ struct kmem_cache {
 	struct list_head list;	/* List of all slab caches on the system */
 };
 
-#else /* !CONFIG_SLOB */
-
-/*
- * This is the main placeholder for memcg-related information in kmem caches.
- * Both the root cache and the child cache will have it. Some fields are used
- * in both cases, other are specific to root caches.
- *
- * @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_cache: pointer to memcg kmem cache, used by all non-root memory
- *		cgroups.
- * @work: work struct used to create the non-root cache.
- */
-struct memcg_cache_params {
-	struct kmem_cache *root_cache;
-
-	struct kmem_cache *memcg_cache;
-	struct work_struct work;
-};
 #endif /* CONFIG_SLOB */
 
 #ifdef CONFIG_SLAB
@@ -196,7 +174,6 @@ int __kmem_cache_shutdown(struct kmem_cache *);
 void __kmem_cache_release(struct kmem_cache *);
 int __kmem_cache_shrink(struct kmem_cache *);
 void slab_kmem_cache_release(struct kmem_cache *);
-void kmem_cache_shrink_all(struct kmem_cache *s);
 
 struct seq_file;
 struct file;
@@ -263,43 +240,6 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla
 }
 
 #ifdef CONFIG_MEMCG_KMEM
-static inline bool is_root_cache(struct kmem_cache *s)
-{
-	return !s->memcg_params.root_cache;
-}
-
-static inline bool slab_equal_or_root(struct kmem_cache *s,
-				      struct kmem_cache *p)
-{
-	return p == s || p == s->memcg_params.root_cache;
-}
-
-/*
- * 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)
-{
-	if (!is_root_cache(s))
-		s = s->memcg_params.root_cache;
-	return s->name;
-}
-
-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;
-}
-
-static inline struct kmem_cache *memcg_cache(struct kmem_cache *s)
-{
-	if (is_root_cache(s))
-		return s->memcg_params.memcg_cache;
-	return NULL;
-}
-
 static inline struct obj_cgroup **page_obj_cgroups(struct page *page)
 {
 	/*
@@ -317,21 +257,8 @@ static inline bool page_has_obj_cgroups(struct page *page)
 	return ((unsigned long)page->obj_cgroups & 0x1UL);
 }
 
-static inline 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;
-
-	kmemleak_not_leak(vec);
-	page->obj_cgroups = (struct obj_cgroup **) ((unsigned long)vec | 0x1UL);
-	return 0;
-}
+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)
 {
@@ -348,38 +275,25 @@ static inline size_t obj_full_size(struct kmem_cache *s)
 	return s->size + sizeof(struct obj_cgroup *);
 }
 
-static inline struct kmem_cache *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
-						struct obj_cgroup **objcgp,
-						size_t objects, gfp_t flags)
+static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
+							   size_t objects,
+							   gfp_t flags)
 {
-	struct kmem_cache *cachep;
 	struct obj_cgroup *objcg;
 
 	if (memcg_kmem_bypass())
-		return s;
-
-	cachep = READ_ONCE(s->memcg_params.memcg_cache);
-	if (unlikely(!cachep)) {
-		/*
-		 * If memcg cache does not exist yet, we schedule it's
-		 * asynchronous creation and let the current allocation
-		 * go through with the root cache.
-		 */
-		queue_work(system_wq, &s->memcg_params.work);
-		return s;
-	}
+		return NULL;
 
 	objcg = get_obj_cgroup_from_current();
 	if (!objcg)
-		return s;
+		return NULL;
 
 	if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) {
 		obj_cgroup_put(objcg);
-		cachep = NULL;
+		return NULL;
 	}
 
-	*objcgp = objcg;
-	return cachep;
+	return objcg;
 }
 
 static inline void mod_objcg_state(struct obj_cgroup *objcg,
@@ -398,15 +312,27 @@ static inline void mod_objcg_state(struct obj_cgroup *objcg,
 
 static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 					      struct obj_cgroup *objcg,
-					      size_t size, void **p)
+					      gfp_t flags, size_t size,
+					      void **p)
 {
 	struct page *page;
 	unsigned long off;
 	size_t i;
 
+	if (!objcg)
+		return;
+
+	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;
@@ -425,13 +351,19 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
 	struct obj_cgroup *objcg;
 	unsigned int off;
 
-	if (!memcg_kmem_enabled() || is_root_cache(s))
+	if (!memcg_kmem_enabled())
+		return;
+
+	if (!page_has_obj_cgroups(page))
 		return;
 
 	off = obj_to_index(s, page, p);
 	objcg = page_obj_cgroups(page)[off];
 	page_obj_cgroups(page)[off] = NULL;
 
+	if (!objcg)
+		return;
+
 	obj_cgroup_uncharge(objcg, obj_full_size(s));
 	mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
 			-obj_full_size(s));
@@ -439,35 +371,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
 	obj_cgroup_put(objcg);
 }
 
-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;
-}
-
-static inline bool slab_equal_or_root(struct kmem_cache *s,
-				      struct kmem_cache *p)
-{
-	return s == p;
-}
-
-static inline const char *cache_name(struct kmem_cache *s)
-{
-	return s->name;
-}
-
-static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
-{
-	return s;
-}
-
-static inline struct kmem_cache *memcg_cache(struct kmem_cache *s)
-{
-	return NULL;
-}
-
 static inline bool page_has_obj_cgroups(struct page *page)
 {
 	return false;
@@ -488,16 +392,17 @@ static inline void memcg_free_page_obj_cgroups(struct page *page)
 {
 }
 
-static inline struct kmem_cache *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
-						struct obj_cgroup **objcgp,
-						size_t objects, gfp_t flags)
+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_slab_post_alloc_hook(struct kmem_cache *s,
 					      struct obj_cgroup *objcg,
-					      size_t size, void **p)
+					      gfp_t flags, size_t size,
+					      void **p)
 {
 }
 
@@ -505,11 +410,6 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s, struct page *page,
 					void *p)
 {
 }
-
-static inline void slab_init_memcg_params(struct kmem_cache *s)
-{
-}
-
 #endif /* CONFIG_MEMCG_KMEM */
 
 static inline struct kmem_cache *virt_to_cache(const void *obj)
@@ -523,27 +423,18 @@ 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 charge_slab_page(struct page *page,
+					     gfp_t gfp, int order,
+					     struct kmem_cache *s)
 {
-	if (memcg_kmem_enabled() && !is_root_cache(s)) {
-		int ret;
-
-		ret = memcg_alloc_page_obj_cgroups(page, s, gfp);
-		if (ret)
-			return ret;
-	}
-
 	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
 			    PAGE_SIZE << order);
-	return 0;
 }
 
 static __always_inline void uncharge_slab_page(struct page *page, int order,
 					       struct kmem_cache *s)
 {
-	if (memcg_kmem_enabled() && !is_root_cache(s))
+	if (memcg_kmem_enabled())
 		memcg_free_page_obj_cgroups(page);
 
 	mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
@@ -555,12 +446,11 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 	struct kmem_cache *cachep;
 
 	if (!IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
-	    !memcg_kmem_enabled() &&
 	    !kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS))
 		return s;
 
 	cachep = virt_to_cache(x);
-	if (WARN(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))
 		print_tracking(cachep, x);
@@ -613,7 +503,7 @@ 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_slab_pre_alloc_hook(s, objcgp, size, flags);
+		*objcgp = memcg_slab_pre_alloc_hook(s, size, flags);
 
 	return s;
 }
@@ -632,8 +522,8 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s,
 					 s->flags, flags);
 	}
 
-	if (memcg_kmem_enabled() && !is_root_cache(s))
-		memcg_slab_post_alloc_hook(s, objcg, size, p);
+	if (memcg_kmem_enabled())
+		memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
 }
 
 #ifndef CONFIG_SLOB