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, 4 insertions, 159 deletions

diff --git a/mm/slub.c b/mm/slub.c
index 9cd724fe37d8..eba8f57d5734 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -218,14 +218,10 @@ enum track_item { TRACK_ALLOC, TRACK_FREE };
 #ifdef CONFIG_SYSFS
 static int sysfs_slab_add(struct kmem_cache *);
 static int sysfs_slab_alias(struct kmem_cache *, const char *);
-static void memcg_propagate_slab_attrs(struct kmem_cache *s);
-static void sysfs_slab_remove(struct kmem_cache *s);
 #else
 static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
 static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
 							{ return 0; }
-static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
-static inline void sysfs_slab_remove(struct kmem_cache *s) { }
 #endif
 
 static inline void stat(const struct kmem_cache *s, enum stat_item si)
@@ -1624,10 +1620,8 @@ static inline struct page *alloc_slab_page(struct kmem_cache *s,
 	else
 		page = __alloc_pages_node(node, flags, order);
 
-	if (page && charge_slab_page(page, flags, order, s)) {
-		__free_pages(page, order);
-		page = NULL;
-	}
+	if (page)
+		charge_slab_page(page, flags, order, s);
 
 	return page;
 }
@@ -3920,7 +3914,6 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
 		if (n->nr_partial || slabs_node(s, node))
 			return 1;
 	}
-	sysfs_slab_remove(s);
 	return 0;
 }
 
@@ -4358,7 +4351,6 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
 			p->slab_cache = s;
 #endif
 	}
-	slab_init_memcg_params(s);
 	list_add(&s->list, &slab_caches);
 	return s;
 }
@@ -4414,7 +4406,7 @@ struct kmem_cache *
 __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 		   slab_flags_t flags, void (*ctor)(void *))
 {
-	struct kmem_cache *s, *c;
+	struct kmem_cache *s;
 
 	s = find_mergeable(size, align, flags, name, ctor);
 	if (s) {
@@ -4427,12 +4419,6 @@ __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 		s->object_size = max(s->object_size, size);
 		s->inuse = max(s->inuse, ALIGN(size, sizeof(void *)));
 
-		c = memcg_cache(s);
-		if (c) {
-			c->object_size = s->object_size;
-			c->inuse = max(c->inuse, ALIGN(size, sizeof(void *)));
-		}
-
 		if (sysfs_slab_alias(s, name)) {
 			s->refcount--;
 			s = NULL;
@@ -4454,7 +4440,6 @@ int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags)
 	if (slab_state <= UP)
 		return 0;
 
-	memcg_propagate_slab_attrs(s);
 	err = sysfs_slab_add(s);
 	if (err)
 		__kmem_cache_release(s);
@@ -5312,7 +5297,7 @@ static ssize_t shrink_store(struct kmem_cache *s,
 			const char *buf, size_t length)
 {
 	if (buf[0] == '1')
-		kmem_cache_shrink_all(s);
+		kmem_cache_shrink(s);
 	else
 		return -EINVAL;
 	return length;
@@ -5536,99 +5521,9 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 		return -EIO;
 
 	err = attribute->store(s, buf, len);
-#ifdef CONFIG_MEMCG
-	if (slab_state >= FULL && err >= 0 && is_root_cache(s)) {
-		struct kmem_cache *c;
-
-		mutex_lock(&slab_mutex);
-		if (s->max_attr_size < len)
-			s->max_attr_size = len;
-
-		/*
-		 * This is a best effort propagation, so this function's return
-		 * value will be determined by the parent cache only. This is
-		 * basically because not all attributes will have a well
-		 * defined semantics for rollbacks - most of the actions will
-		 * have permanent effects.
-		 *
-		 * Returning the error value of any of the children that fail
-		 * is not 100 % defined, in the sense that users seeing the
-		 * error code won't be able to know anything about the state of
-		 * the cache.
-		 *
-		 * Only returning the error code for the parent cache at least
-		 * has well defined semantics. The cache being written to
-		 * directly either failed or succeeded, in which case we loop
-		 * through the descendants with best-effort propagation.
-		 */
-		c = memcg_cache(s);
-		if (c)
-			attribute->store(c, buf, len);
-		mutex_unlock(&slab_mutex);
-	}
-#endif
 	return err;
 }
 
-static void memcg_propagate_slab_attrs(struct kmem_cache *s)
-{
-#ifdef CONFIG_MEMCG
-	int i;
-	char *buffer = NULL;
-	struct kmem_cache *root_cache;
-
-	if (is_root_cache(s))
-		return;
-
-	root_cache = s->memcg_params.root_cache;
-
-	/*
-	 * This mean this cache had no attribute written. Therefore, no point
-	 * in copying default values around
-	 */
-	if (!root_cache->max_attr_size)
-		return;
-
-	for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) {
-		char mbuf[64];
-		char *buf;
-		struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
-		ssize_t len;
-
-		if (!attr || !attr->store || !attr->show)
-			continue;
-
-		/*
-		 * It is really bad that we have to allocate here, so we will
-		 * do it only as a fallback. If we actually allocate, though,
-		 * we can just use the allocated buffer until the end.
-		 *
-		 * Most of the slub attributes will tend to be very small in
-		 * size, but sysfs allows buffers up to a page, so they can
-		 * theoretically happen.
-		 */
-		if (buffer)
-			buf = buffer;
-		else if (root_cache->max_attr_size < ARRAY_SIZE(mbuf) &&
-			 !IS_ENABLED(CONFIG_SLUB_STATS))
-			buf = mbuf;
-		else {
-			buffer = (char *) get_zeroed_page(GFP_KERNEL);
-			if (WARN_ON(!buffer))
-				continue;
-			buf = buffer;
-		}
-
-		len = attr->show(root_cache, buf);
-		if (len > 0)
-			attr->store(s, buf, len);
-	}
-
-	if (buffer)
-		free_page((unsigned long)buffer);
-#endif	/* CONFIG_MEMCG */
-}
-
 static void kmem_cache_release(struct kobject *k)
 {
 	slab_kmem_cache_release(to_slab(k));
@@ -5648,10 +5543,6 @@ static struct kset *slab_kset;
 
 static inline struct kset *cache_kset(struct kmem_cache *s)
 {
-#ifdef CONFIG_MEMCG
-	if (!is_root_cache(s))
-		return s->memcg_params.root_cache->memcg_kset;
-#endif
 	return slab_kset;
 }
 
@@ -5694,27 +5585,6 @@ static char *create_unique_id(struct kmem_cache *s)
 	return name;
 }
 
-static void sysfs_slab_remove_workfn(struct work_struct *work)
-{
-	struct kmem_cache *s =
-		container_of(work, struct kmem_cache, kobj_remove_work);
-
-	if (!s->kobj.state_in_sysfs)
-		/*
-		 * For a memcg cache, this may be called during
-		 * deactivation and again on shutdown.  Remove only once.
-		 * A cache is never shut down before deactivation is
-		 * complete, so no need to worry about synchronization.
-		 */
-		goto out;
-
-#ifdef CONFIG_MEMCG
-	kset_unregister(s->memcg_kset);
-#endif
-out:
-	kobject_put(&s->kobj);
-}
-
 static int sysfs_slab_add(struct kmem_cache *s)
 {
 	int err;
@@ -5722,8 +5592,6 @@ static int sysfs_slab_add(struct kmem_cache *s)
 	struct kset *kset = cache_kset(s);
 	int unmergeable = slab_unmergeable(s);
 
-	INIT_WORK(&s->kobj_remove_work, sysfs_slab_remove_workfn);
-
 	if (!kset) {
 		kobject_init(&s->kobj, &slab_ktype);
 		return 0;
@@ -5760,16 +5628,6 @@ static int sysfs_slab_add(struct kmem_cache *s)
 	if (err)
 		goto out_del_kobj;
 
-#ifdef CONFIG_MEMCG
-	if (is_root_cache(s) && memcg_sysfs_enabled) {
-		s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj);
-		if (!s->memcg_kset) {
-			err = -ENOMEM;
-			goto out_del_kobj;
-		}
-	}
-#endif
-
 	if (!unmergeable) {
 		/* Setup first alias */
 		sysfs_slab_alias(s, s->name);
@@ -5783,19 +5641,6 @@ out_del_kobj:
 	goto out;
 }
 
-static void sysfs_slab_remove(struct kmem_cache *s)
-{
-	if (slab_state < FULL)
-		/*
-		 * Sysfs has not been setup yet so no need to remove the
-		 * cache from sysfs.
-		 */
-		return;
-
-	kobject_get(&s->kobj);
-	schedule_work(&s->kobj_remove_work);
-}
-
 void sysfs_slab_unlink(struct kmem_cache *s)
 {
 	if (slab_state >= FULL)