slab_common.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Slab allocator functions that are independent of the allocator strategy
 *
 * (C) 2012 Christoph Lameter <cl@linux.com>
 */
#include <linux/slab.h>

#include <linux/mm.h>
#include <linux/poison.h>
#include <linux/interrupt.h>
#include <linux/memory.h>
#include <linux/cache.h>
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/cpu.h>
#include <linux/uaccess.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
#include <linux/memcontrol.h>

#define CREATE_TRACE_POINTS
#include <trace/events/kmem.h>

#include "slab.h"

enum slab_state slab_state;
LIST_HEAD(slab_caches);
DEFINE_MUTEX(slab_mutex);
struct kmem_cache *kmem_cache;

#ifdef CONFIG_HARDENED_USERCOPY
bool usercopy_fallback __ro_after_init =
		IS_ENABLED(CONFIG_HARDENED_USERCOPY_FALLBACK);
module_param(usercopy_fallback, bool, 0400);
MODULE_PARM_DESC(usercopy_fallback,
		"WARN instead of reject usercopy whitelist violations");
#endif

static LIST_HEAD(slab_caches_to_rcu_destroy);
static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work);
static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
		    slab_caches_to_rcu_destroy_workfn);

/*
 * Set of flags that will prevent slab merging
 */
#define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
		SLAB_TRACE | SLAB_TYPESAFE_BY_RCU | SLAB_NOLEAKTRACE | \
		SLAB_FAILSLAB | SLAB_KASAN)

#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \
			 SLAB_ACCOUNT)

/*
 * Merge control. If this is set then no merging of slab caches will occur.
 */
static bool slab_nomerge = !IS_ENABLED(CONFIG_SLAB_MERGE_DEFAULT);

static int __init setup_slab_nomerge(char *str)
{
	slab_nomerge = true;
	return 1;
}

#ifdef CONFIG_SLUB
__setup_param("slub_nomerge", slub_nomerge, setup_slab_nomerge, 0);
#endif

__setup("slab_nomerge", setup_slab_nomerge);

/*
 * Determine the size of a slab object
 */
unsigned int kmem_cache_size(struct kmem_cache *s)
{
	return s->object_size;
}
EXPORT_SYMBOL(kmem_cache_size);

#ifdef CONFIG_DEBUG_VM
static int kmem_cache_sanity_check(const char *name, unsigned int size)
{
	if (!name || in_interrupt() || size < sizeof(void *) ||
		size > KMALLOC_MAX_SIZE) {
		pr_err("kmem_cache_create(%s) integrity check failed\n", name);
		return -EINVAL;
	}

	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
	return 0;
}
#else
static inline int kmem_cache_sanity_check(const char *name, unsigned int size)
{
	return 0;
}
#endif

void __kmem_cache_free_bulk(struct kmem_cache *s, size_t nr, void **p)
{
	size_t i;

	for (i = 0; i < nr; i++) {
		if (s)
			kmem_cache_free(s, p[i]);
		else
			kfree(p[i]);
	}
}

int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
								void **p)
{
	size_t i;

	for (i = 0; i < nr; i++) {
		void *x = p[i] = kmem_cache_alloc(s, flags);
		if (!x) {
			__kmem_cache_free_bulk(s, i, p);
			return 0;
		}
	}
	return i;
}

#ifdef CONFIG_MEMCG_KMEM

LIST_HEAD(slab_root_caches);

void slab_init_memcg_params(struct kmem_cache *s)
{
	s->memcg_params.root_cache = NULL;
	RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
	INIT_LIST_HEAD(&s->memcg_params.children);
	s->memcg_params.dying = false;
}

static int init_memcg_params(struct kmem_cache *s,
		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
{
	struct memcg_cache_array *arr;

	if (root_cache) {
		s->memcg_params.root_cache = root_cache;
		s->memcg_params.memcg = memcg;
		INIT_LIST_HEAD(&s->memcg_params.children_node);
		INIT_LIST_HEAD(&s->memcg_params.kmem_caches_node);
		return 0;
	}

	slab_init_memcg_params(s);

	if (!memcg_nr_cache_ids)
		return 0;

	arr = kvzalloc(sizeof(struct memcg_cache_array) +
		       memcg_nr_cache_ids * sizeof(void *),
		       GFP_KERNEL);
	if (!arr)
		return -ENOMEM;

	RCU_INIT_POINTER(s->memcg_params.memcg_caches, arr);
	return 0;
}

static void destroy_memcg_params(struct kmem_cache *s)
{
	if (is_root_cache(s))
		kvfree(rcu_access_pointer(s->memcg_params.memcg_caches));
}

static void free_memcg_params(struct rcu_head *rcu)
{
	struct memcg_cache_array *old;

	old = container_of(rcu, struct memcg_cache_array, rcu);
	kvfree(old);
}

static int update_memcg_params(struct kmem_cache *s, int new_array_size)
{
	struct memcg_cache_array *old, *new;

	new = kvzalloc(sizeof(struct memcg_cache_array) +
		       new_array_size * sizeof(void *), GFP_KERNEL);
	if (!new)
		return -ENOMEM;

	old = rcu_dereference_protected(s->memcg_params.memcg_caches,
					lockdep_is_held(&slab_mutex));
	if (old)
		memcpy(new->entries, old->entries,
		       memcg_nr_cache_ids * sizeof(void *));

	rcu_assign_pointer(s->memcg_params.memcg_caches, new);
	if (old)
		call_rcu(&old->rcu, free_memcg_params);
	return 0;
}

int memcg_update_all_caches(int num_memcgs)
{
	struct kmem_cache *s;
	int ret = 0;

	mutex_lock(&slab_mutex);
	list_for_each_entry(s, &slab_root_caches, root_caches_node) {
		ret = update_memcg_params(s, num_memcgs);
		/*
		 * Instead of freeing the memory, we'll just leave the caches
		 * up to this point in an updated state.
		 */
		if (ret)
			break;
	}
	mutex_unlock(&slab_mutex);
	return ret;
}

void memcg_link_cache(struct kmem_cache *s)
{
	if (is_root_cache(s)) {
		list_add(&s->root_caches_node, &slab_root_caches);
	} else {
		list_add(&s->memcg_params.children_node,
			 &s->memcg_params.root_cache->memcg_params.children);
		list_add(&s->memcg_params.kmem_caches_node,
			 &s->memcg_params.memcg->kmem_caches);
	}
}

static void memcg_unlink_cache(struct kmem_cache *s)
{
	if (is_root_cache(s)) {
		list_del(&s->root_caches_node);
	} else {
		list_del(&s->memcg_params.children_node);
		list_del(&s->memcg_params.kmem_caches_node);
	}
}
#else
static inline int init_memcg_params(struct kmem_cache *s,
		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
{
	return 0;
}

static inline void destroy_memcg_params(struct kmem_cache *s)
{
}

static inline void memcg_unlink_cache(struct kmem_cache *s)
{
}
#endif /* CONFIG_MEMCG_KMEM */

/*
 * Figure out what the alignment of the objects will be given a set of
 * flags, a user specified alignment and the size of the objects.
 */
static unsigned int calculate_alignment(slab_flags_t flags,
		unsigned int align, unsigned int size)
{
	/*
	 * If the user wants hardware cache aligned objects then follow that
	 * suggestion if the object is sufficiently large.
	 *
	 * The hardware cache alignment cannot override the specified
	 * alignment though. If that is greater then use it.
	 */
	if (flags & SLAB_HWCACHE_ALIGN) {
		unsigned int ralign;

		ralign = cache_line_size();
		while (size <= ralign / 2)
			ralign /= 2;
		align = max(align, ralign);
	}

	if (align < ARCH_SLAB_MINALIGN)
		align = ARCH_SLAB_MINALIGN;

	return ALIGN(align, sizeof(void *));
}

/*
 * Find a mergeable slab cache
 */
int slab_unmergeable(struct kmem_cache *s)
{
	if (slab_nomerge || (s->flags & SLAB_NEVER_MERGE))
		return 1;

	if (!is_root_cache(s))
		return 1;

	if (s->ctor)
		return 1;

	if (s->usersize)
		return 1;

	/*
	 * We may have set a slab to be unmergeable during bootstrap.
	 */
	if (s->refcount < 0)
		return 1;

	return 0;
}

struct kmem_cache *find_mergeable(unsigned int size, unsigned int align,
		slab_flags_t flags, const char *name, void (*ctor)(void *))
{
	struct kmem_cache *s;

	if (slab_nomerge)
		return NULL;

	if (ctor)
		return NULL;

	size = ALIGN(size, sizeof(void *));
	align = calculate_alignment(flags, align, size);
	size = ALIGN(size, align);
	flags = kmem_cache_flags(size, flags, name, NULL);

	if (flags & SLAB_NEVER_MERGE)
		return NULL;

	list_for_each_entry_reverse(s, &slab_root_caches, root_caches_node) {
		if (slab_unmergeable(s))
			continue;

		if (size > s->size)
			continue;

		if ((flags & SLAB_MERGE_SAME) != (s->flags & SLAB_MERGE_SAME))
			continue;
		/*
		 * Check if alignment is compatible.
		 * Courtesy of Adrian Drzewiecki
		 */
		if ((s->size & ~(align - 1)) != s->size)
			continue;

		if (s->size - size >= sizeof(void *))
			continue;

		if (IS_ENABLED(CONFIG_SLAB) && align &&
			(align > s->align || s->align % align))
			continue;

		return s;
	}
	return NULL;
}

static struct kmem_cache *create_cache(const char *name,
		unsigned int object_size, unsigned int align,
		slab_flags_t flags, unsigned int useroffset,
		unsigned int usersize, void (*ctor)(void *),
		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
{
	struct kmem_cache *s;
	int err;

	if (WARN_ON(useroffset + usersize > object_size))
		useroffset = usersize = 0;

	err = -ENOMEM;
	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
	if (!s)
		goto out;

	s->name = name;
	s->size = s->object_size = object_size;
	s->align = align;
	s->ctor = ctor;
	s->useroffset = useroffset;
	s->usersize = usersize;

	err = init_memcg_params(s, memcg, root_cache);
	if (err)
		goto out_free_cache;

	err = __kmem_cache_create(s, flags);
	if (err)
		goto out_free_cache;

	s->refcount = 1;
	list_add(&s->list, &slab_caches);
	memcg_link_cache(s);
out:
	if (err)
		return ERR_PTR(err);
	return s;

out_free_cache:
	destroy_memcg_params(s);
	kmem_cache_free(kmem_cache, s);
	goto out;
}

/**
 * kmem_cache_create_usercopy - Create a cache with a region suitable
 * for copying to userspace
 * @name: A string which is used in /proc/slabinfo to identify this cache.
 * @size: The size of objects to be created in this cache.
 * @align: The required alignment for the objects.
 * @flags: SLAB flags
 * @useroffset: Usercopy region offset
 * @usersize: Usercopy region size
 * @ctor: A constructor for the objects.
 *
 * Cannot be called within a interrupt, but can be interrupted.
 * The @ctor is run when new pages are allocated by the cache.
 *
 * The flags are
 *
 * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
 * to catch references to uninitialised memory.
 *
 * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check
 * for buffer overruns.
 *
 * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
 * cacheline.  This can be beneficial if you're counting cycles as closely
 * as davem.
 *
 * Return: a pointer to the cache on success, NULL on failure.
 */
struct kmem_cache *
kmem_cache_create_usercopy(const char *name,
		  unsigned int size, unsigned int align,
		  slab_flags_t flags,
		  unsigned int useroffset, unsigned int usersize,
		  void (*ctor)(void *))
{
	struct kmem_cache *s = NULL;
	const char *cache_name;
	int err;

	get_online_cpus();
	get_online_mems();
	memcg_get_cache_ids();

	mutex_lock(&slab_mutex);

	err = kmem_cache_sanity_check(name, size);
	if (err) {
		goto out_unlock;
	}

	/* Refuse requests with allocator specific flags */
	if (flags & ~SLAB_FLAGS_PERMITTED) {
		err = -EINVAL;
		goto out_unlock;
	}

	/*
	 * Some allocators will constraint the set of valid flags to a subset
	 * of all flags. We expect them to define CACHE_CREATE_MASK in this
	 * case, and we'll just provide them with a sanitized version of the
	 * passed flags.
	 */
	flags &= CACHE_CREATE_MASK;

	/* Fail closed on bad usersize of useroffset values. */
	if (WARN_ON(!usersize && useroffset) ||
	    WARN_ON(size < usersize || size - usersize < useroffset))
		usersize = useroffset = 0;

	if (!usersize)
		s = __kmem_cache_alias(name, size, align, flags, ctor);
	if (s)
		goto out_unlock;

	cache_name = kstrdup_const(name, GFP_KERNEL);
	if (!cache_name) {
		err = -ENOMEM;
		goto out_unlock;
	}

	s = create_cache(cache_name, size,
			 calculate_alignment(flags, align, size),
			 flags, useroffset, usersize, ctor, NULL, NULL);
	if (IS_ERR(s)) {
		err = PTR_ERR(s);
		kfree_const(cache_name);
	}

out_unlock:
	mutex_unlock(&slab_mutex);

	memcg_put_cache_ids();
	put_online_mems();
	put_online_cpus();

	if (err) {
		if (flags & SLAB_PANIC)
			panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
				name, err);
		else {
			pr_warn("kmem_cache_create(%s) failed with error %d\n",
				name, err);
			dump_stack();
		}
		return NULL;
	}
	return s;
}
EXPORT_SYMBOL(kmem_cache_create_usercopy);

/**
 * kmem_cache_create - Create a cache.
 * @name: A string which is used in /proc/slabinfo to identify this cache.
 * @size: The size of objects to be created in this cache.
 * @align: The required alignment for the objects.
 * @flags: SLAB flags
 * @ctor: A constructor for the objects.
 *
 * Cannot be called within a interrupt, but can be interrupted.
 * The @ctor is run when new pages are allocated by the cache.
 *
 * The flags are
 *
 * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
 * to catch references to uninitialised memory.
 *
 * %SLAB_RED_ZONE - Insert `Red` zones around the allocated memory to check
 * for buffer overruns.
 *
 * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
 * cacheline.  This can be beneficial if you're counting cycles as closely
 * as davem.
 *
 * Return: a pointer to the cache on success, NULL on failure.
 */
struct kmem_cache *
kmem_cache_create(const char *name, unsigned int size, unsigned int align,
		slab_flags_t flags, void (*ctor)(void *))
{
	return kmem_cache_create_usercopy(name, size, align, flags, 0, 0,
					  ctor);
}
EXPORT_SYMBOL(kmem_cache_create);

static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
{
	LIST_HEAD(to_destroy);
	struct kmem_cache *s, *s2;

	/*
	 * On destruction, SLAB_TYPESAFE_BY_RCU kmem_caches are put on the
	 * @slab_caches_to_rcu_destroy list.  The slab pages are freed
	 * through RCU and and the associated kmem_cache are dereferenced
	 * while freeing the pages, so the kmem_caches should be freed only
	 * after the pending RCU operations are finished.  As rcu_barrier()
	 * is a pretty slow operation, we batch all pending destructions
	 * asynchronously.
	 */
	mutex_lock(&slab_mutex);
	list_splice_init(&slab_caches_to_rcu_destroy, &to_destroy);
	mutex_unlock(&slab_mutex);

	if (list_empty(&to_destroy))
		return;

	rcu_barrier();

	list_for_each_entry_safe(s, s2, &to_destroy, list) {
#ifdef SLAB_SUPPORTS_SYSFS
		sysfs_slab_release(s);
#else
		slab_kmem_cache_release(s);
#endif
	}
}

static int shutdown_cache(struct kmem_cache *s)
{
	/* free asan quarantined objects */
	kasan_cache_shutdown(s);

	if (__kmem_cache_shutdown(s) != 0)
		return -EBUSY;

	memcg_unlink_cache(s);
	list_del(&s->list);

	if (s->flags & SLAB_TYPESAFE_BY_RCU) {
#ifdef SLAB_SUPPORTS_SYSFS
		sysfs_slab_unlink(s);
#endif
		list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
		schedule_work(&slab_caches_to_rcu_destroy_work);
	} else {
#ifdef SLAB_SUPPORTS_SYSFS
		sysfs_slab_unlink(s);
		sysfs_slab_release(s);
#else
		slab_kmem_cache_release(s);
#endif
	}

	return 0;
}

#ifdef CONFIG_MEMCG_KMEM
/*
 * memcg_create_kmem_cache - Create a cache for a memory cgroup.
 * @memcg: The memory cgroup the new cache is for.
 * @root_cache: The parent of the new cache.
 *
 * This function attempts to create a kmem cache that will serve allocation
 * requests going from @memcg to @root_cache. The new cache inherits properties
 * from its parent.
 */
void memcg_create_kmem_cache(struct mem_cgroup *memcg,
			     struct kmem_cache *root_cache)
{
	static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */
	struct cgroup_subsys_state *css = &memcg->css;
	struct memcg_cache_array *arr;
	struct kmem_cache *s = NULL;
	char *cache_name;
	int idx;

	get_online_cpus();
	get_online_mems();

	mutex_lock(&slab_mutex);

	/*
	 * The memory cgroup could have been offlined while the cache
	 * creation work was pending.
	 */
	if (memcg->kmem_state != KMEM_ONLINE || root_cache->memcg_params.dying)
		goto out_unlock;

	idx = memcg_cache_id(memcg);
	arr = rcu_dereference_protected(root_cache->memcg_params.memcg_caches,
					lockdep_is_held(&slab_mutex));

	/*
	 * Since per-memcg caches are created asynchronously on first
	 * allocation (see memcg_kmem_get_cache()), several threads can try to
	 * create the same cache, but only one of them may succeed.
	 */
	if (arr->entries[idx])
		goto out_unlock;

	cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf));
	cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name,
			       css->serial_nr, memcg_name_buf);
	if (!cache_name)
		goto out_unlock;

	s = create_cache(cache_name, root_cache->object_size,
			 root_cache->align,
			 root_cache->flags & CACHE_CREATE_MASK,
			 root_cache->useroffset, root_cache->usersize,
			 root_cache->ctor, memcg, root_cache);
	/*
	 * If we could not create a memcg cache, do not complain, because
	 * that's not critical at all as we can always proceed with the root
	 * cache.
	 */
	if (IS_ERR(s)) {
		kfree(cache_name);
		goto out_unlock;
	}

	/*
	 * Since readers won't lock (see cache_from_memcg_idx()), we need a
	 * barrier here to ensure nobody will see the kmem_cache partially
	 * initialized.
	 */
	smp_wmb();
	arr->entries[idx] = s;

out_unlock:
	mutex_unlock(&slab_mutex);

	put_online_mems();
	put_online_cpus();
}

static void kmemcg_deactivate_workfn(struct work_struct *work)
{
	struct kmem_cache *s = container_of(work, struct kmem_cache,
					    memcg_params.deact_work);

	get_online_cpus();
	get_online_mems();

	mutex_lock(&slab_mutex);

	s->memcg_params.deact_fn(s);

	mutex_unlock(&slab_mutex);

	put_online_mems();
	put_online_cpus();

	/* done, put the ref from slab_deactivate_memcg_cache_rcu_sched() */
	css_put(&s->memcg_params.memcg->css);
}

static void kmemcg_deactivate_rcufn(struct rcu_head *head)
{
	struct kmem_cache *s = container_of(head, struct kmem_cache,
					    memcg_params.deact_rcu_head);

	/*
	 * We need to grab blocking locks.  Bounce to ->deact_work.  The
	 * work item shares the space with the RCU head and can't be
	 * initialized eariler.
	 */
	INIT_WORK(&s->memcg_params.deact_work, kmemcg_deactivate_workfn);
	queue_work(memcg_kmem_cache_wq, &s->memcg_params.deact_work);
}

/**
 * slab_deactivate_memcg_cache_rcu_sched - schedule deactivation after a
 *					   sched RCU grace period
 * @s: target kmem_cache
 * @deact_fn: deactivation function to call
 *
 * Schedule @deact_fn to be invoked with online cpus, mems and slab_mutex
 * held after a sched RCU grace period.  The slab is guaranteed to stay
 * alive until @deact_fn is finished.  This is to be used from
 * __kmemcg_cache_deactivate().
 */
void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
					   void (*deact_fn)(struct kmem_cache *))
{
	if (WARN_ON_ONCE(is_root_cache(s)) ||
	    WARN_ON_ONCE(s->memcg_params.deact_fn))
		return;

	if (s->memcg_params.root_cache->memcg_params.dying)
		return;

	/* pin memcg so that @s doesn't get destroyed in the middle */
	css_get(&s->memcg_params.memcg->css);

	s->memcg_params.deact_fn = deact_fn;
	call_rcu(&s->memcg_params.deact_rcu_head, kmemcg_deactivate_rcufn);
}

void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
{
	int idx;
	struct memcg_cache_array *arr;
	struct kmem_cache *s, *c;

	idx = memcg_cache_id(memcg);

	get_online_cpus();
	get_online_mems();

	mutex_lock(&slab_mutex);
	list_for_each_entry(s, &slab_root_caches, root_caches_node) {
		arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
						lockdep_is_held(&slab_mutex));
		c = arr->entries[idx];
		if (!c)
			continue;

		__kmemcg_cache_deactivate(c);
		arr->entries[idx] = NULL;
	}
	mutex_unlock(&slab_mutex);

	put_online_mems();
	put_online_cpus();
}

void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
{
	struct kmem_cache *s, *s2;

	get_online_cpus();
	get_online_mems();

	mutex_lock(&slab_mutex);
	list_for_each_entry_safe(s, s2, &memcg->kmem_caches,
				 memcg_params.kmem_caches_node) {
		/*
		 * The cgroup is about to be freed and therefore has no charges
		 * left. Hence, all its caches must be empty by now.
		 */
		BUG_ON(shutdown_cache(s));
	}
	mutex_unlock(&slab_mutex);

	put_online_mems();
	put_online_cpus();
}

static int shutdown_memcg_caches(struct kmem_cache *s)
{
	struct memcg_cache_array *arr;
	struct kmem_cache *c, *c2;
	LIST_HEAD(busy);
	int i;

	BUG_ON(!is_root_cache(s));

	/*
	 * First, shutdown active caches, i.e. caches that belong to online
	 * memory cgroups.
	 */
	arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
					lockdep_is_held(&slab_mutex));
	for_each_memcg_cache_index(i) {
		c = arr->entries[i];
		if (!c)
			continue;
		if (shutdown_cache(c))
			/*
			 * The cache still has objects. Move it to a temporary
			 * list so as not to try to destroy it for a second
			 * time while iterating over inactive caches below.
			 */
			list_move(&c->memcg_params.children_node, &busy);
		else
			/*
			 * The cache is empty and will be destroyed soon. Clear
			 * the pointer to it in the memcg_caches array so that
			 * it will never be accessed even if the root cache
			 * stays alive.
			 */
			arr->entries[i] = NULL;
	}

	/*
	 * Second, shutdown all caches left from memory cgroups that are now
	 * offline.
	 */
	list_for_each_entry_safe(c, c2, &s->memcg_params.children,
				 memcg_params.children_node)
		shutdown_cache(c);

	list_splice(&busy, &s->memcg_params.children);

	/*
	 * A cache being destroyed must be empty. In particular, this means
	 * that all per memcg caches attached to it must be empty too.
	 */
	if (!list_empty(&s->memcg_params.children))
		return -EBUSY;
	return 0;
}

static void flush_memcg_workqueue(struct kmem_cache *s)
{
	mutex_lock(&slab_mutex);
	s->memcg_params.dying = true;
	mutex_unlock(&slab_mutex);

	/*
	 * SLUB deactivates the kmem_caches through call_rcu. Make
	 * sure all registered rcu callbacks have been invoked.
	 */
	if (IS_ENABLED(CONFIG_SLUB))
		rcu_barrier();

	/*
	 * SLAB and SLUB create memcg kmem_caches through workqueue and SLUB
	 * deactivates the memcg kmem_caches through workqueue. Make sure all
	 * previous workitems on workqueue are processed.
	 */
	flush_workqueue(memcg_kmem_cache_wq);
}
#else
static inline int shutdown_memcg_caches(struct kmem_cache *s)
{
	return 0;
}

static inline void flush_memcg_workqueue(struct kmem_cache *s)
{
}
#endif /* CONFIG_MEMCG_KMEM */

void slab_kmem_cache_release(struct kmem_cache *s)
{
	__kmem_cache_release(s);
	destroy_memcg_params(s);
	kfree_const(s->name);
	kmem_cache_free(kmem_cache, s);
}

void kmem_cache_destroy(struct kmem_cache *s)
{
	int err;

	if (unlikely(!s))
		return;

	flush_memcg_workqueue(s);

	get_online_cpus();
	get_online_mems();

	mutex_lock(&slab_mutex);

	s->refcount--;
	if (s->refcount)
		goto out_unlock;

	err = shutdown_memcg_caches(s);
	if (!err)
		err = shutdown_cache(s);

	if (err) {
		pr_err("kmem_cache_destroy %s: Slab cache still has objects\n",
		       s->name);
		dump_stack();
	}
out_unlock:
	mutex_unlock(&slab_mutex);

	put_online_mems();
	put_online_cpus();
}
EXPORT_SYMBOL(kmem_cache_destroy);

/**
 * kmem_cache_shrink - Shrink a cache.
 * @cachep: The cache to shrink.
 *
 * Releases as many slabs as possible for a cache.
 * To help debugging, a zero exit status indicates all slabs were released.
 *
 * Return: %0 if all slabs were released, non-zero otherwise
 */
int kmem_cache_shrink(struct kmem_cache *cachep)
{
	int ret;

	get_online_cpus();
	get_online_mems();
	kasan_cache_shrink(cachep);
	ret = __kmem_cache_shrink(cachep);
	put_online_mems();
	put_online_cpus();
	return ret;
}
EXPORT_SYMBOL(kmem_cache_shrink);

bool slab_is_available(void)
{
	return slab_state >= UP;
}

#ifndef CONFIG_SLOB
/* Create a cache during boot when no slab services are available yet */
void __init create_boot_cache(struct kmem_cache *s, const char *name,
		unsigned int size, slab_flags_t flags,
		unsigned int useroffset, unsigned int usersize)
{
	int err;

	s->name = name;
	s->size = s->object_size = size;
	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
	s->useroffset = useroffset;
	s->usersize = usersize;

	slab_init_memcg_params(s);

	err = __kmem_cache_create(s, flags);

	if (err)
		panic("Creation of kmalloc slab %s size=%u failed. Reason %d\n",
					name, size, err);

	s->refcount = -1;	/* Exempt from merging for now */
}

struct kmem_cache *__init create_kmalloc_cache(const char *name,
		unsigned int size, slab_flags_t flags,
		unsigned int useroffset, unsigned int usersize)
{
	struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);

	if (!s)
		panic("Out of memory when creating slab %s\n", name);

	create_boot_cache(s, name, size, flags, useroffset, usersize);
	list_add(&s->list, &slab_caches);
	memcg_link_cache(s);