linux/mm/slub.c

// SPDX-License-Identifier: GPL-2.0
/*
 * SLUB: A slab allocator that limits cache line use instead of queuing
 * objects in per cpu and per node lists.
 *
 * The allocator synchronizes using per slab locks or atomic operations
 * and only uses a centralized lock to manage a pool of partial slabs.
 *
 * (C) 2007 SGI, Christoph Lameter
 * (C) 2011 Linux Foundation, Christoph Lameter
 */

#include <linux/mm.h>
#include <linux/swap.h> /* mm_account_reclaimed_pages() */
#include <linux/module.h>
#include <linux/bit_spinlock.h>
#include <linux/interrupt.h>
#include <linux/swab.h>
#include <linux/bitops.h>
#include <linux/slab.h>
#include "slab.h"
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/kasan.h>
#include <linux/kmsan.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/mempolicy.h>
#include <linux/ctype.h>
#include <linux/stackdepot.h>
#include <linux/debugobjects.h>
#include <linux/kallsyms.h>
#include <linux/kfence.h>
#include <linux/memory.h>
#include <linux/math64.h>
#include <linux/fault-inject.h>
#include <linux/kmemleak.h>
#include <linux/stacktrace.h>
#include <linux/prefetch.h>
#include <linux/memcontrol.h>
#include <linux/random.h>
#include <kunit/test.h>
#include <kunit/test-bug.h>
#include <linux/sort.h>

#include <linux/debugfs.h>
#include <trace/events/kmem.h>

#include "internal.h"

/*
 * Lock order:
 *   1. slab_mutex (Global Mutex)
 *   2. node->list_lock (Spinlock)
 *   3. kmem_cache->cpu_slab->lock (Local lock)
 *   4. slab_lock(slab) (Only on some arches)
 *   5. object_map_lock (Only for debugging)
 *
 *   slab_mutex
 *
 *   The role of the slab_mutex is to protect the list of all the slabs
 *   and to synchronize major metadata changes to slab cache structures.
 *   Also synchronizes memory hotplug callbacks.
 *
 *   slab_lock
 *
 *   The slab_lock is a wrapper around the page lock, thus it is a bit
 *   spinlock.
 *
 *   The slab_lock is only used on arches that do not have the ability
 *   to do a cmpxchg_double. It only protects:
 *
 *	A. slab->freelist	-> List of free objects in a slab
 *	B. slab->inuse		-> Number of objects in use
 *	C. slab->objects	-> Number of objects in slab
 *	D. slab->frozen		-> frozen state
 *
 *   Frozen slabs
 *
 *   If a slab is frozen then it is exempt from list management. It is
 *   the cpu slab which is actively allocated from by the processor that
 *   froze it and it is not on any list. The processor that froze the
 *   slab is the one who can perform list operations on the slab. Other
 *   processors may put objects onto the freelist but the processor that
 *   froze the slab is the only one that can retrieve the objects from the
 *   slab's freelist.
 *
 *   CPU partial slabs
 *
 *   The partially empty slabs cached on the CPU partial list are used
 *   for performance reasons, which speeds up the allocation process.
 *   These slabs are not frozen, but are also exempt from list management,
 *   by clearing the PG_workingset flag when moving out of the node
 *   partial list. Please see __slab_free() for more details.
 *
 *   To sum up, the current scheme is:
 *   - node partial slab: PG_Workingset && !frozen
 *   - cpu partial slab: !PG_Workingset && !frozen
 *   - cpu slab: !PG_Workingset && frozen
 *   - full slab: !PG_Workingset && !frozen
 *
 *   list_lock
 *
 *   The list_lock protects the partial and full list on each node and
 *   the partial slab counter. If taken then no new slabs may be added or
 *   removed from the lists nor make the number of partial slabs be modified.
 *   (Note that the total number of slabs is an atomic value that may be
 *   modified without taking the list lock).
 *
 *   The list_lock is a centralized lock and thus we avoid taking it as
 *   much as possible. As long as SLUB does not have to handle partial
 *   slabs, operations can continue without any centralized lock. F.e.
 *   allocating a long series of objects that fill up slabs does not require
 *   the list lock.
 *
 *   For debug caches, all allocations are forced to go through a list_lock
 *   protected region to serialize against concurrent validation.
 *
 *   cpu_slab->lock local lock
 *
 *   This locks protect slowpath manipulation of all kmem_cache_cpu fields
 *   except the stat counters. This is a percpu structure manipulated only by
 *   the local cpu, so the lock protects against being preempted or interrupted
 *   by an irq. Fast path operations rely on lockless operations instead.
 *
 *   On PREEMPT_RT, the local lock neither disables interrupts nor preemption
 *   which means the lockless fastpath cannot be used as it might interfere with
 *   an in-progress slow path operations. In this case the local lock is always
 *   taken but it still utilizes the freelist for the common operations.
 *
 *   lockless fastpaths
 *
 *   The fast path allocation (slab_alloc_node()) and freeing (do_slab_free())
 *   are fully lockless when satisfied from the percpu slab (and when
 *   cmpxchg_double is possible to use, otherwise slab_lock is taken).
 *   They also don't disable preemption or migration or irqs. They rely on
 *   the transaction id (tid) field to detect being preempted or moved to
 *   another cpu.
 *
 *   irq, preemption, migration considerations
 *
 *   Interrupts are disabled as part of list_lock or local_lock operations, or
 *   around the slab_lock operation, in order to make the slab allocator safe
 *   to use in the context of an irq.
 *
 *   In addition, preemption (or migration on PREEMPT_RT) is disabled in the
 *   allocation slowpath, bulk allocation, and put_cpu_partial(), so that the
 *   local cpu doesn't change in the process and e.g. the kmem_cache_cpu pointer
 *   doesn't have to be revalidated in each section protected by the local lock.
 *
 * SLUB assigns one slab for allocation to each processor.
 * Allocations only occur from these slabs called cpu slabs.
 *
 * Slabs with free elements are kept on a partial list and during regular
 * operations no list for full slabs is used. If an object in a full slab is
 * freed then the slab will show up again on the partial lists.
 * We track full slabs for debugging purposes though because otherwise we
 * cannot scan all objects.
 *
 * Slabs are freed when they become empty. Teardown and setup is
 * minimal so we rely on the page allocators per cpu caches for
 * fast frees and allocs.
 *
 * slab->frozen		The slab is frozen and exempt from list processing.
 * 			This means that the slab is dedicated to a purpose
 * 			such as satisfying allocations for a specific
 * 			processor. Objects may be freed in the slab while
 * 			it is frozen but slab_free will then skip the usual
 * 			list operations. It is up to the processor holding
 * 			the slab to integrate the slab into the slab lists
 * 			when the slab is no longer needed.
 *
 * 			One use of this flag is to mark slabs that are
 * 			used for allocations. Then such a slab becomes a cpu
 * 			slab. The cpu slab may be equipped with an additional
 * 			freelist that allows lockless access to
 * 			free objects in addition to the regular freelist
 * 			that requires the slab lock.
 *
 * SLAB_DEBUG_FLAGS	Slab requires special handling due to debug
 * 			options set. This moves	slab handling out of
 * 			the fast path and disables lockless freelists.
 */

/*
 * We could simply use migrate_disable()/enable() but as long as it's a
 * function call even on !PREEMPT_RT, use inline preempt_disable() there.
 */
#ifndef CONFIG_PREEMPT_RT
#define slub_get_cpu_ptr(var) …
#define slub_put_cpu_ptr(var) …
#define USE_LOCKLESS_FAST_PATH() …
#else
#define slub_get_cpu_ptr …
#define slub_put_cpu_ptr …
#define USE_LOCKLESS_FAST_PATH …
#endif

#ifndef CONFIG_SLUB_TINY
#define __fastpath_inline …
#else
#define __fastpath_inline
#endif

#ifdef CONFIG_SLUB_DEBUG
#ifdef CONFIG_SLUB_DEBUG_ON
DEFINE_STATIC_KEY_TRUE(slub_debug_enabled);
#else
DEFINE_STATIC_KEY_FALSE(slub_debug_enabled);
#endif
#endif		/* CONFIG_SLUB_DEBUG */

/* Structure holding parameters for get_partial() call chain */
struct partial_context { … };

static inline bool kmem_cache_debug(struct kmem_cache *s)
{ … }

static inline bool slub_debug_orig_size(struct kmem_cache *s)
{ … }

void *fixup_red_left(struct kmem_cache *s, void *p)
{ … }

static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
{ … }

/*
 * Issues still to be resolved:
 *
 * - Support PAGE_ALLOC_DEBUG. Should be easy to do.
 *
 * - Variable sizing of the per node arrays
 */

/* Enable to log cmpxchg failures */
#undef SLUB_DEBUG_CMPXCHG

#ifndef CONFIG_SLUB_TINY
/*
 * Minimum number of partial slabs. These will be left on the partial
 * lists even if they are empty. kmem_cache_shrink may reclaim them.
 */
#define MIN_PARTIAL …

/*
 * Maximum number of desirable partial slabs.
 * The existence of more partial slabs makes kmem_cache_shrink
 * sort the partial list by the number of objects in use.
 */
#define MAX_PARTIAL …
#else
#define MIN_PARTIAL …
#define MAX_PARTIAL …
#endif

#define DEBUG_DEFAULT_FLAGS …

/*
 * These debug flags cannot use CMPXCHG because there might be consistency
 * issues when checking or reading debug information
 */
#define SLAB_NO_CMPXCHG …


/*
 * Debugging flags that require metadata to be stored in the slab.  These get
 * disabled when slab_debug=O is used and a cache's min order increases with
 * metadata.
 */
#define DEBUG_METADATA_FLAGS …

#define OO_SHIFT …
#define OO_MASK …
#define MAX_OBJS_PER_PAGE …

/* Internal SLUB flags */
/* Poison object */
#define __OBJECT_POISON …
/* Use cmpxchg_double */

#ifdef system_has_freelist_aba
#define __CMPXCHG_DOUBLE …
#else
#define __CMPXCHG_DOUBLE …
#endif

/*
 * Tracking user of a slab.
 */
#define TRACK_ADDRS_COUNT …
struct track { … };

enum track_item { … };

#ifdef SLAB_SUPPORTS_SYSFS
static int sysfs_slab_add(struct kmem_cache *);
static int sysfs_slab_alias(struct kmem_cache *, const char *);
#else
static inline int sysfs_slab_add(struct kmem_cache *s) { … }
static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
							{ … }
#endif

#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG)
static void debugfs_slab_add(struct kmem_cache *);
#else
static inline void debugfs_slab_add(struct kmem_cache *s) { … }
#endif

enum stat_item { … };

#ifndef CONFIG_SLUB_TINY
/*
 * When changing the layout, make sure freelist and tid are still compatible
 * with this_cpu_cmpxchg_double() alignment requirements.
 */
struct kmem_cache_cpu {
	union {
		struct {
			void **freelist;	/* Pointer to next available object */
			unsigned long tid;	/* Globally unique transaction id */
		};
		freelist_aba_t freelist_tid;
	};
	struct slab *slab;	/* The slab from which we are allocating */
#ifdef CONFIG_SLUB_CPU_PARTIAL
	struct slab *partial;	/* Partially allocated slabs */
#endif
	local_lock_t lock;	/* Protects the fields above */
#ifdef CONFIG_SLUB_STATS
	unsigned int stat[NR_SLUB_STAT_ITEMS];
#endif
};
#endif /* CONFIG_SLUB_TINY */

static inline void stat(const struct kmem_cache *s, enum stat_item si)
{ … }

static inline
void stat_add(const struct kmem_cache *s, enum stat_item si, int v)
{ … }

/*
 * The slab lists for all objects.
 */
struct kmem_cache_node { … };

static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
{ … }

/*
 * Iterator over all nodes. The body will be executed for each node that has
 * a kmem_cache_node structure allocated (which is true for all online nodes)
 */
#define for_each_kmem_cache_node(__s, __node, __n) …

/*
 * Tracks for which NUMA nodes we have kmem_cache_nodes allocated.
 * Corresponds to node_state[N_NORMAL_MEMORY], but can temporarily
 * differ during memory hotplug/hotremove operations.
 * Protected by slab_mutex.
 */
static nodemask_t slab_nodes;

#ifndef CONFIG_SLUB_TINY
/*
 * Workqueue used for flush_cpu_slab().
 */
static struct workqueue_struct *flushwq;
#endif

/********************************************************************
 * 			Core slab cache functions
 *******************************************************************/

/*
 * freeptr_t represents a SLUB freelist pointer, which might be encoded
 * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled.
 */
freeptr_t;

/*
 * Returns freelist pointer (ptr). With hardening, this is obfuscated
 * with an XOR of the address where the pointer is held and a per-cache
 * random number.
 */
static inline freeptr_t freelist_ptr_encode(const struct kmem_cache *s,
					    void *ptr, unsigned long ptr_addr)
{ … }

static inline void *freelist_ptr_decode(const struct kmem_cache *s,
					freeptr_t ptr, unsigned long ptr_addr)
{ … }

static inline void *get_freepointer(struct kmem_cache *s, void *object)
{ … }

#ifndef CONFIG_SLUB_TINY
static void prefetch_freepointer(const struct kmem_cache *s, void *object)
{
	prefetchw(object + s->offset);
}
#endif

/*
 * When running under KMSAN, get_freepointer_safe() may return an uninitialized
 * pointer value in the case the current thread loses the race for the next
 * memory chunk in the freelist. In that case this_cpu_cmpxchg_double() in
 * slab_alloc_node() will fail, so the uninitialized value won't be used, but
 * KMSAN will still check all arguments of cmpxchg because of imperfect
 * handling of inline assembly.
 * To work around this problem, we apply __no_kmsan_checks to ensure that
 * get_freepointer_safe() returns initialized memory.
 */
__no_kmsan_checks
static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
{ … }

static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
{ … }

/*
 * See comment in calculate_sizes().
 */
static inline bool freeptr_outside_object(struct kmem_cache *s)
{ … }

/*
 * Return offset of the end of info block which is inuse + free pointer if
 * not overlapping with object.
 */
static inline unsigned int get_info_end(struct kmem_cache *s)
{ … }

/* Loop over all objects in a slab */
#define for_each_object(__p, __s, __addr, __objects) …

static inline unsigned int order_objects(unsigned int order, unsigned int size)
{ … }

static inline struct kmem_cache_order_objects oo_make(unsigned int order,
		unsigned int size)
{ … }

static inline unsigned int oo_order(struct kmem_cache_order_objects x)
{ … }

static inline unsigned int oo_objects(struct kmem_cache_order_objects x)
{ … }

#ifdef CONFIG_SLUB_CPU_PARTIAL
static void slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects)
{
	unsigned int nr_slabs;

	s->cpu_partial = nr_objects;

	/*
	 * We take the number of objects but actually limit the number of
	 * slabs on the per cpu partial list, in order to limit excessive
	 * growth of the list. For simplicity we assume that the slabs will
	 * be half-full.
	 */
	nr_slabs = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo));
	s->cpu_partial_slabs = nr_slabs;
}

static inline unsigned int slub_get_cpu_partial(struct kmem_cache *s)
{
	return s->cpu_partial_slabs;
}
#else
static inline void
slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects)
{ … }

static inline unsigned int slub_get_cpu_partial(struct kmem_cache *s)
{ … }
#endif /* CONFIG_SLUB_CPU_PARTIAL */

/*
 * Per slab locking using the pagelock
 */
static __always_inline void slab_lock(struct slab *slab)
{ … }

static __always_inline void slab_unlock(struct slab *slab)
{ … }

static inline bool
__update_freelist_fast(struct slab *slab,
		      void *freelist_old, unsigned long counters_old,
		      void *freelist_new, unsigned long counters_new)
{ … }

static inline bool
__update_freelist_slow(struct slab *slab,
		      void *freelist_old, unsigned long counters_old,
		      void *freelist_new, unsigned long counters_new)
{ … }

/*
 * Interrupts must be disabled (for the fallback code to work right), typically
 * by an _irqsave() lock variant. On PREEMPT_RT the preempt_disable(), which is
 * part of bit_spin_lock(), is sufficient because the policy is not to allow any
 * allocation/ free operation in hardirq context. Therefore nothing can
 * interrupt the operation.
 */
static inline bool __slab_update_freelist(struct kmem_cache *s, struct slab *slab,
		void *freelist_old, unsigned long counters_old,
		void *freelist_new, unsigned long counters_new,
		const char *n)
{ … }

static inline bool slab_update_freelist(struct kmem_cache *s, struct slab *slab,
		void *freelist_old, unsigned long counters_old,
		void *freelist_new, unsigned long counters_new,
		const char *n)
{ … }

#ifdef CONFIG_SLUB_DEBUG
static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)];
static DEFINE_SPINLOCK(object_map_lock);

static void __fill_map(unsigned long *obj_map, struct kmem_cache *s,
		       struct slab *slab)
{
	void *addr = slab_address(slab);
	void *p;

	bitmap_zero(obj_map, slab->objects);

	for (p = slab->freelist; p; p = get_freepointer(s, p))
		set_bit(__obj_to_index(s, addr, p), obj_map);
}

#if IS_ENABLED(CONFIG_KUNIT)
static bool slab_add_kunit_errors(void)
{
	struct kunit_resource *resource;

	if (!kunit_get_current_test())
		return false;

	resource = kunit_find_named_resource(current->kunit_test, "slab_errors");
	if (!resource)
		return false;

	(*(int *)resource->data)++;
	kunit_put_resource(resource);
	return true;
}

static bool slab_in_kunit_test(void)
{
	struct kunit_resource *resource;

	if (!kunit_get_current_test())
		return false;

	resource = kunit_find_named_resource(current->kunit_test, "slab_errors");
	if (!resource)
		return false;

	kunit_put_resource(resource);
	return true;
}
#else
static inline bool slab_add_kunit_errors(void) { return false; }
static inline bool slab_in_kunit_test(void) { return false; }
#endif

static inline unsigned int size_from_object(struct kmem_cache *s)
{
	if (s->flags & SLAB_RED_ZONE)
		return s->size - s->red_left_pad;

	return s->size;
}

static inline void *restore_red_left(struct kmem_cache *s, void *p)
{
	if (s->flags & SLAB_RED_ZONE)
		p -= s->red_left_pad;

	return p;
}

/*
 * Debug settings:
 */
#if defined(CONFIG_SLUB_DEBUG_ON)
static slab_flags_t slub_debug = DEBUG_DEFAULT_FLAGS;
#else
static slab_flags_t slub_debug;
#endif

static char *slub_debug_string;
static int disable_higher_order_debug;

/*
 * slub is about to manipulate internal object metadata.  This memory lies
 * outside the range of the allocated object, so accessing it would normally
 * be reported by kasan as a bounds error.  metadata_access_enable() is used
 * to tell kasan that these accesses are OK.
 */
static inline void metadata_access_enable(void)
{
	kasan_disable_current();
	kmsan_disable_current();
}

static inline void metadata_access_disable(void)
{
	kmsan_enable_current();
	kasan_enable_current();
}

/*
 * Object debugging
 */

/* Verify that a pointer has an address that is valid within a slab page */
static inline int check_valid_pointer(struct kmem_cache *s,
				struct slab *slab, void *object)
{
	void *base;

	if (!object)
		return 1;

	base = slab_address(slab);
	object = kasan_reset_tag(object);
	object = restore_red_left(s, object);
	if (object < base || object >= base + slab->objects * s->size ||
		(object - base) % s->size) {
		return 0;
	}

	return 1;
}

static void print_section(char *level, char *text, u8 *addr,
			  unsigned int length)
{
	metadata_access_enable();
	print_hex_dump(level, text, DUMP_PREFIX_ADDRESS,
			16, 1, kasan_reset_tag((void *)addr), length, 1);
	metadata_access_disable();
}

static struct track *get_track(struct kmem_cache *s, void *object,
	enum track_item alloc)
{
	struct track *p;

	p = object + get_info_end(s);

	return kasan_reset_tag(p + alloc);
}

#ifdef CONFIG_STACKDEPOT
static noinline depot_stack_handle_t set_track_prepare(void)
{
	depot_stack_handle_t handle;
	unsigned long entries[TRACK_ADDRS_COUNT];
	unsigned int nr_entries;

	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3);
	handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT);

	return handle;
}
#else
static inline depot_stack_handle_t set_track_prepare(void)
{
	return 0;
}
#endif

static void set_track_update(struct kmem_cache *s, void *object,
			     enum track_item alloc, unsigned long addr,
			     depot_stack_handle_t handle)
{
	struct track *p = get_track(s, object, alloc);

#ifdef CONFIG_STACKDEPOT
	p->handle = handle;
#endif
	p->addr = addr;
	p->cpu = smp_processor_id();
	p->pid = current->pid;
	p->when = jiffies;
}

static __always_inline void set_track(struct kmem_cache *s, void *object,
				      enum track_item alloc, unsigned long addr)
{
	depot_stack_handle_t handle = set_track_prepare();

	set_track_update(s, object, alloc, addr, handle);
}

static void init_tracking(struct kmem_cache *s, void *object)
{
	struct track *p;

	if (!(s->flags & SLAB_STORE_USER))
		return;

	p = get_track(s, object, TRACK_ALLOC);
	memset(p, 0, 2*sizeof(struct track));
}

static void print_track(const char *s, struct track *t, unsigned long pr_time)
{
	depot_stack_handle_t handle __maybe_unused;

	if (!t->addr)
		return;

	pr_err("%s in %pS age=%lu cpu=%u pid=%d\n",
	       s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid);
#ifdef CONFIG_STACKDEPOT
	handle = READ_ONCE(t->handle);
	if (handle)
		stack_depot_print(handle);
	else
		pr_err("object allocation/free stack trace missing\n");
#endif
}

void print_tracking(struct kmem_cache *s, void *object)
{
	unsigned long pr_time = jiffies;
	if (!(s->flags & SLAB_STORE_USER))
		return;

	print_track("Allocated", get_track(s, object, TRACK_ALLOC), pr_time);
	print_track("Freed", get_track(s, object, TRACK_FREE), pr_time);
}

static void print_slab_info(const struct slab *slab)
{
	pr_err("Slab 0x%p objects=%u used=%u fp=0x%p flags=%pGp\n",
	       slab, slab->objects, slab->inuse, slab->freelist,
	       &slab->__page_flags);
}

/*
 * kmalloc caches has fixed sizes (mostly power of 2), and kmalloc() API
 * family will round up the real request size to these fixed ones, so
 * there could be an extra area than what is requested. Save the original
 * request size in the meta data area, for better debug and sanity check.
 */
static inline void set_orig_size(struct kmem_cache *s,
				void *object, unsigned int orig_size)
{
	void *p = kasan_reset_tag(object);
	unsigned int kasan_meta_size;

	if (!slub_debug_orig_size(s))
		return;

	/*
	 * KASAN can save its free meta data inside of the object at offset 0.
	 * If this meta data size is larger than 'orig_size', it will overlap
	 * the data redzone in [orig_size+1, object_size]. Thus, we adjust
	 * 'orig_size' to be as at least as big as KASAN's meta data.
	 */
	kasan_meta_size = kasan_metadata_size(s, true);
	if (kasan_meta_size > orig_size)
		orig_size = kasan_meta_size;

	p += get_info_end(s);
	p += sizeof(struct track) * 2;

	*(unsigned int *)p = orig_size;
}

static inline unsigned int get_orig_size(struct kmem_cache *s, void *object)
{
	void *p = kasan_reset_tag(object);

	if (!slub_debug_orig_size(s))
		return s->object_size;

	p += get_info_end(s);
	p += sizeof(struct track) * 2;

	return *(unsigned int *)p;
}

void skip_orig_size_check(struct kmem_cache *s, const void *object)
{
	set_orig_size(s, (void *)object, s->object_size);
}

static void slab_bug(struct kmem_cache *s, char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;
	pr_err("=============================================================================\n");
	pr_err("BUG %s (%s): %pV\n", s->name, print_tainted(), &vaf);
	pr_err("-----------------------------------------------------------------------------\n\n");
	va_end(args);
}

__printf(2, 3)
static void slab_fix(struct kmem_cache *s, char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	if (slab_add_kunit_errors())
		return;

	va_start(args, fmt);
	vaf.fmt = fmt;
	vaf.va = &args;
	pr_err("FIX %s: %pV\n", s->name, &vaf);
	va_end(args);
}

static void print_trailer(struct kmem_cache *s, struct slab *slab, u8 *p)
{
	unsigned int off;	/* Offset of last byte */
	u8 *addr = slab_address(slab);

	print_tracking(s, p);

	print_slab_info(slab);

	pr_err("Object 0x%p @offset=%tu fp=0x%p\n\n",
	       p, p - addr, get_freepointer(s, p));

	if (s->flags & SLAB_RED_ZONE)
		print_section(KERN_ERR, "Redzone  ", p - s->red_left_pad,
			      s->red_left_pad);
	else if (p > addr + 16)
		print_section(KERN_ERR, "Bytes b4 ", p - 16, 16);

	print_section(KERN_ERR,         "Object   ", p,
		      min_t(unsigned int, s->object_size, PAGE_SIZE));
	if (s->flags & SLAB_RED_ZONE)
		print_section(KERN_ERR, "Redzone  ", p + s->object_size,
			s->inuse - s->object_size);

	off = get_info_end(s);

	if (s->flags & SLAB_STORE_USER)
		off += 2 * sizeof(struct track);

	if (slub_debug_orig_size(s))
		off += sizeof(unsigned int);

	off += kasan_metadata_size(s, false);

	if (off != size_from_object(s))
		/* Beginning of the filler is the free pointer */
		print_section(KERN_ERR, "Padding  ", p + off,
			      size_from_object(s) - off);

	dump_stack();
}

static void object_err(struct kmem_cache *s, struct slab *slab,
			u8 *object, char *reason)
{
	if (slab_add_kunit_errors())
		return;

	slab_bug(s, "%s", reason);
	print_trailer(s, slab, object);
	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}

static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
			       void **freelist, void *nextfree)
{
	if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
	    !check_valid_pointer(s, slab, nextfree) && freelist) {
		object_err(s, slab, *freelist, "Freechain corrupt");
		*freelist = NULL;
		slab_fix(s, "Isolate corrupted freechain");
		return true;
	}

	return false;
}

static __printf(3, 4) void slab_err(struct kmem_cache *s, struct slab *slab,
			const char *fmt, ...)
{
	va_list args;
	char buf[100];

	if (slab_add_kunit_errors())
		return;

	va_start(args, fmt);
	vsnprintf(buf, sizeof(buf), fmt, args);
	va_end(args);
	slab_bug(s, "%s", buf);
	print_slab_info(slab);
	dump_stack();
	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}

static void init_object(struct kmem_cache *s, void *object, u8 val)
{
	u8 *p = kasan_reset_tag(object);
	unsigned int poison_size = s->object_size;

	if (s->flags & SLAB_RED_ZONE) {
		/*
		 * Here and below, avoid overwriting the KMSAN shadow. Keeping
		 * the shadow makes it possible to distinguish uninit-value
		 * from use-after-free.
		 */
		memset_no_sanitize_memory(p - s->red_left_pad, val,
					  s->red_left_pad);

		if (slub_debug_orig_size(s) && val == SLUB_RED_ACTIVE) {
			/*
			 * Redzone the extra allocated space by kmalloc than
			 * requested, and the poison size will be limited to
			 * the original request size accordingly.
			 */
			poison_size = get_orig_size(s, object);
		}
	}

	if (s->flags & __OBJECT_POISON) {
		memset_no_sanitize_memory(p, POISON_FREE, poison_size - 1);
		memset_no_sanitize_memory(p + poison_size - 1, POISON_END, 1);
	}

	if (s->flags & SLAB_RED_ZONE)
		memset_no_sanitize_memory(p + poison_size, val,
					  s->inuse - poison_size);
}

static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
						void *from, void *to)
{
	slab_fix(s, "Restoring %s 0x%p-0x%p=0x%x", message, from, to - 1, data);
	memset(from, data, to - from);
}

#ifdef CONFIG_KMSAN
#define pad_check_attributes …
#else
#define pad_check_attributes
#endif

static pad_check_attributes int
check_bytes_and_report(struct kmem_cache *s, struct slab *slab,
		       u8 *object, char *what,
		       u8 *start, unsigned int value, unsigned int bytes)
{
	u8 *fault;
	u8 *end;
	u8 *addr = slab_address(slab);

	metadata_access_enable();
	fault = memchr_inv(kasan_reset_tag(start), value, bytes);
	metadata_access_disable();
	if (!fault)
		return 1;

	end = start + bytes;
	while (end > fault && end[-1] == value)
		end--;

	if (slab_add_kunit_errors())
		goto skip_bug_print;

	slab_bug(s, "%s overwritten", what);
	pr_err("0x%p-0x%p @offset=%tu. First byte 0x%x instead of 0x%x\n",
					fault, end - 1, fault - addr,
					fault[0], value);

skip_bug_print:
	restore_bytes(s, what, value, fault, end);
	return 0;
}

/*
 * Object layout:
 *
 * object address
 * 	Bytes of the object to be managed.
 * 	If the freepointer may overlay the object then the free
 *	pointer is at the middle of the object.
 *
 * 	Poisoning uses 0x6b (POISON_FREE) and the last byte is
 * 	0xa5 (POISON_END)
 *
 * object + s->object_size
 * 	Padding to reach word boundary. This is also used for Redzoning.
 * 	Padding is extended by another word if Redzoning is enabled and
 * 	object_size == inuse.
 *
 * 	We fill with 0xbb (SLUB_RED_INACTIVE) for inactive objects and with
 * 	0xcc (SLUB_RED_ACTIVE) for objects in use.
 *
 * object + s->inuse
 * 	Meta data starts here.
 *
 * 	A. Free pointer (if we cannot overwrite object on free)
 * 	B. Tracking data for SLAB_STORE_USER
 *	C. Original request size for kmalloc object (SLAB_STORE_USER enabled)
 *	D. Padding to reach required alignment boundary or at minimum
 * 		one word if debugging is on to be able to detect writes
 * 		before the word boundary.
 *
 *	Padding is done using 0x5a (POISON_INUSE)
 *
 * object + s->size
 * 	Nothing is used beyond s->size.
 *
 * If slabcaches are merged then the object_size and inuse boundaries are mostly
 * ignored. And therefore no slab options that rely on these boundaries
 * may be used with merged slabcaches.
 */

static int check_pad_bytes(struct kmem_cache *s, struct slab *slab, u8 *p)
{
	unsigned long off = get_info_end(s);	/* The end of info */

	if (s->flags & SLAB_STORE_USER) {
		/* We also have user information there */
		off += 2 * sizeof(struct track);

		if (s->flags & SLAB_KMALLOC)
			off += sizeof(unsigned int);
	}

	off += kasan_metadata_size(s, false);

	if (size_from_object(s) == off)
		return 1;

	return check_bytes_and_report(s, slab, p, "Object padding",
			p + off, POISON_INUSE, size_from_object(s) - off);
}

/* Check the pad bytes at the end of a slab page */
static pad_check_attributes void
slab_pad_check(struct kmem_cache *s, struct slab *slab)
{
	u8 *start;
	u8 *fault;
	u8 *end;
	u8 *pad;
	int length;
	int remainder;

	if (!(s->flags & SLAB_POISON))
		return;

	start = slab_address(slab);
	length = slab_size(slab);
	end = start + length;
	remainder = length % s->size;
	if (!remainder)
		return;

	pad = end - remainder;
	metadata_access_enable();
	fault = memchr_inv(kasan_reset_tag(pad), POISON_INUSE, remainder);
	metadata_access_disable();
	if (!fault)
		return;
	while (end > fault && end[-1] == POISON_INUSE)
		end--;

	slab_err(s, slab, "Padding overwritten. 0x%p-0x%p @offset=%tu",
			fault, end - 1, fault - start);
	print_section(KERN_ERR, "Padding ", pad, remainder);

	restore_bytes(s, "slab padding", POISON_INUSE, fault, end);
}

static int check_object(struct kmem_cache *s, struct slab *slab,
					void *object, u8 val)
{
	u8 *p = object;
	u8 *endobject = object + s->object_size;
	unsigned int orig_size, kasan_meta_size;
	int ret = 1;

	if (s->flags & SLAB_RED_ZONE) {
		if (!check_bytes_and_report(s, slab, object, "Left Redzone",
			object - s->red_left_pad, val, s->red_left_pad))
			ret = 0;

		if (!check_bytes_and_report(s, slab, object, "Right Redzone",
			endobject, val, s->inuse - s->object_size))
			ret = 0;

		if (slub_debug_orig_size(s) && val == SLUB_RED_ACTIVE) {
			orig_size = get_orig_size(s, object);

			if (s->object_size > orig_size  &&
				!check_bytes_and_report(s, slab, object,
					"kmalloc Redzone", p + orig_size,
					val, s->object_size - orig_size)) {
				ret = 0;
			}
		}
	} else {
		if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) {
			if (!check_bytes_and_report(s, slab, p, "Alignment padding",
				endobject, POISON_INUSE,
				s->inuse - s->object_size))
				ret = 0;
		}
	}

	if (s->flags & SLAB_POISON) {
		if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON)) {
			/*
			 * KASAN can save its free meta data inside of the
			 * object at offset 0. Thus, skip checking the part of
			 * the redzone that overlaps with the meta data.
			 */
			kasan_meta_size = kasan_metadata_size(s, true);
			if (kasan_meta_size < s->object_size - 1 &&
			    !check_bytes_and_report(s, slab, p, "Poison",
					p + kasan_meta_size, POISON_FREE,
					s->object_size - kasan_meta_size - 1))
				ret = 0;
			if (kasan_meta_size < s->object_size &&
			    !check_bytes_and_report(s, slab, p, "End Poison",
					p + s->object_size - 1, POISON_END, 1))
				ret = 0;
		}
		/*
		 * check_pad_bytes cleans up on its own.
		 */
		if (!check_pad_bytes(s, slab, p))
			ret = 0;
	}

	/*
	 * Cannot check freepointer while object is allocated if
	 * object and freepointer overlap.
	 */
	if ((freeptr_outside_object(s) || val != SLUB_RED_ACTIVE) &&
	    !check_valid_pointer(s, slab, get_freepointer(s, p))) {
		object_err(s, slab, p, "Freepointer corrupt");
		/*
		 * No choice but to zap it and thus lose the remainder
		 * of the free objects in this slab. May cause
		 * another error because the object count is now wrong.
		 */
		set_freepointer(s, p, NULL);
		ret = 0;
	}

	if (!ret && !slab_in_kunit_test()) {
		print_trailer(s, slab, object);
		add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
	}

	return ret;
}

static int check_slab(struct kmem_cache *s, struct slab *slab)
{
	int maxobj;

	if (!folio_test_slab(slab_folio(slab))) {
		slab_err(s, slab, "Not a valid slab page");
		return 0;
	}

	maxobj = order_objects(slab_order(slab), s->size);
	if (slab->objects > maxobj) {
		slab_err(s, slab, "objects %u > max %u",
			slab->objects, maxobj);
		return 0;
	}
	if (slab->inuse > slab->objects) {
		slab_err(s, slab, "inuse %u > max %u",
			slab->inuse, slab->objects);
		return 0;
	}
	/* Slab_pad_check fixes things up after itself */
	slab_pad_check(s, slab);
	return 1;
}

/*
 * Determine if a certain object in a slab is on the freelist. Must hold the
 * slab lock to guarantee that the chains are in a consistent state.
 */
static int on_freelist(struct kmem_cache *s, struct slab *slab, void *search)
{
	int nr = 0;
	void *fp;
	void *object = NULL;
	int max_objects;

	fp = slab->freelist;
	while (fp && nr <= slab->objects) {
		if (fp == search)
			return 1;
		if (!check_valid_pointer(s, slab, fp)) {
			if (object) {
				object_err(s, slab, object,
					"Freechain corrupt");
				set_freepointer(s, object, NULL);
			} else {
				slab_err(s, slab, "Freepointer corrupt");
				slab->freelist = NULL;
				slab->inuse = slab->objects;
				slab_fix(s, "Freelist cleared");
				return 0;
			}
			break;
		}
		object = fp;
		fp = get_freepointer(s, object);
		nr++;
	}

	max_objects = order_objects(slab_order(slab), s->size);
	if (max_objects > MAX_OBJS_PER_PAGE)
		max_objects = MAX_OBJS_PER_PAGE;

	if (slab->objects != max_objects) {
		slab_err(s, slab, "Wrong number of objects. Found %d but should be %d",
			 slab->objects, max_objects);
		slab->objects = max_objects;
		slab_fix(s, "Number of objects adjusted");
	}
	if (slab->inuse != slab->objects - nr) {
		slab_err(s, slab, "Wrong object count. Counter is %d but counted were %d",
			 slab->inuse, slab->objects - nr);
		slab->inuse = slab->objects - nr;
		slab_fix(s, "Object count adjusted");
	}
	return search == NULL;
}

static void trace(struct kmem_cache *s, struct slab *slab, void *object,
								int alloc)
{
	if (s->flags & SLAB_TRACE) {
		pr_info("TRACE %s %s 0x%p inuse=%d fp=0x%p\n",
			s->name,
			alloc ? "alloc" : "free",
			object, slab->inuse,
			slab->freelist);

		if (!alloc)
			print_section(KERN_INFO, "Object ", (void *)object,
					s->object_size);

		dump_stack();
	}
}

/*
 * Tracking of fully allocated slabs for debugging purposes.
 */
static void add_full(struct kmem_cache *s,
	struct kmem_cache_node *n, struct slab *slab)
{
	if (!(s->flags & SLAB_STORE_USER))
		return;

	lockdep_assert_held(&n->list_lock);
	list_add(&slab->slab_list, &n->full);
}

static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct slab *slab)
{
	if (!(s->flags & SLAB_STORE_USER))
		return;

	lockdep_assert_held(&n->list_lock);
	list_del(&slab->slab_list);
}

static inline unsigned long node_nr_slabs(struct kmem_cache_node *n)
{
	return atomic_long_read(&n->nr_slabs);
}

static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
{
	struct kmem_cache_node *n = get_node(s, node);

	atomic_long_inc(&n->nr_slabs);
	atomic_long_add(objects, &n->total_objects);
}
static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects)
{
	struct kmem_cache_node *n = get_node(s, node);

	atomic_long_dec(&n->nr_slabs);
	atomic_long_sub(objects, &n->total_objects);
}

/* Object debug checks for alloc/free paths */
static void setup_object_debug(struct kmem_cache *s, void *object)
{
	if (!kmem_cache_debug_flags(s, SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON))
		return;

	init_object(s, object, SLUB_RED_INACTIVE);
	init_tracking(s, object);
}

static
void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr)
{
	if (!kmem_cache_debug_flags(s, SLAB_POISON))
		return;

	metadata_access_enable();
	memset(kasan_reset_tag(addr), POISON_INUSE, slab_size(slab));
	metadata_access_disable();
}

static inline int alloc_consistency_checks(struct kmem_cache *s,
					struct slab *slab, void *object)
{
	if (!check_slab(s, slab))
		return 0;

	if (!check_valid_pointer(s, slab, object)) {
		object_err(s, slab, object, "Freelist Pointer check fails");
		return 0;
	}

	if (!check_object(s, slab, object, SLUB_RED_INACTIVE))
		return 0;

	return 1;
}

static noinline bool alloc_debug_processing(struct kmem_cache *s,
			struct slab *slab, void *object, int orig_size)
{
	if (s->flags & SLAB_CONSISTENCY_CHECKS) {
		if (!alloc_consistency_checks(s, slab, object))
			goto bad;
	}

	/* Success. Perform special debug activities for allocs */
	trace(s, slab, object, 1);
	set_orig_size(s, object, orig_size);
	init_object(s, object, SLUB_RED_ACTIVE);
	return true;

bad:
	if (folio_test_slab(slab_folio(slab))) {
		/*
		 * If this is a slab page then lets do the best we can
		 * to avoid issues in the future. Marking all objects
		 * as used avoids touching the remaining objects.
		 */
		slab_fix(s, "Marking all objects used");
		slab->inuse = slab->objects;
		slab->freelist = NULL;
	}
	return false;
}

static inline int free_consistency_checks(struct kmem_cache *s,
		struct slab *slab, void *object, unsigned long addr)
{
	if (!check_valid_pointer(s, slab, object)) {
		slab_err(s, slab, "Invalid object pointer 0x%p", object);
		return 0;
	}

	if (on_freelist(s, slab, object)) {
		object_err(s, slab, object, "Object already free");
		return 0;
	}

	if (!check_object(s, slab, object, SLUB_RED_ACTIVE))
		return 0;

	if (unlikely(s != slab->slab_cache)) {
		if (!folio_test_slab(slab_folio(slab))) {
			slab_err(s, slab, "Attempt to free object(0x%p) outside of slab",
				 object);
		} else if (!slab->slab_cache) {
			pr_err("SLUB <none>: no slab for object 0x%p.\n",
			       object);
			dump_stack();
		} else
			object_err(s, slab, object,
					"page slab pointer corrupt.");
		return 0;
	}
	return 1;
}

/*
 * Parse a block of slab_debug options. Blocks are delimited by ';'
 *
 * @str:    start of block
 * @flags:  returns parsed flags, or DEBUG_DEFAULT_FLAGS if none specified
 * @slabs:  return start of list of slabs, or NULL when there's no list
 * @init:   assume this is initial parsing and not per-kmem-create parsing
 *
 * returns the start of next block if there's any, or NULL
 */
static char *
parse_slub_debug_flags(char *str, slab_flags_t *flags, char **slabs, bool init)
{
	bool higher_order_disable = false;

	/* Skip any completely empty blocks */
	while (*str && *str == ';')
		str++;

	if (*str == ',') {
		/*
		 * No options but restriction on slabs. This means full
		 * debugging for slabs matching a pattern.
		 */
		*flags = DEBUG_DEFAULT_FLAGS;
		goto check_slabs;
	}
	*flags = 0;

	/* Determine which debug features should be switched on */
	for (; *str && *str != ',' && *str != ';'; str++) {
		switch (tolower(*str)) {
		case '-':
			*flags = 0;
			break;
		case 'f':
			*flags |= SLAB_CONSISTENCY_CHECKS;
			break;
		case 'z':
			*flags |= SLAB_RED_ZONE;
			break;
		case 'p':
			*flags |= SLAB_POISON;
			break;
		case 'u':
			*flags |= SLAB_STORE_USER;
			break;
		case 't':
			*flags |= SLAB_TRACE;
			break;
		case 'a':
			*flags |= SLAB_FAILSLAB;
			break;
		case 'o':
			/*
			 * Avoid enabling debugging on caches if its minimum
			 * order would increase as a result.
			 */
			higher_order_disable = true;
			break;
		default:
			if (init)
				pr_err("slab_debug option '%c' unknown. skipped\n", *str);
		}
	}
check_slabs:
	if (*str == ',')
		*slabs = ++str;
	else
		*slabs = NULL;

	/* Skip over the slab list */
	while (*str && *str != ';')
		str++;

	/* Skip any completely empty blocks */
	while (*str && *str == ';')
		str++;

	if (init && higher_order_disable)
		disable_higher_order_debug = 1;

	if (*str)
		return str;
	else
		return NULL;
}

static int __init setup_slub_debug(char *str)
{
	slab_flags_t flags;
	slab_flags_t global_flags;
	char *saved_str;
	char *slab_list;
	bool global_slub_debug_changed = false;
	bool slab_list_specified = false;

	global_flags = DEBUG_DEFAULT_FLAGS;
	if (*str++ != '=' || !*str)
		/*
		 * No options specified. Switch on full debugging.
		 */
		goto out;

	saved_str = str;
	while (str) {
		str = parse_slub_debug_flags(str, &flags, &slab_list, true);

		if (!slab_list) {
			global_flags = flags;
			global_slub_debug_changed = true;
		} else {
			slab_list_specified = true;
			if (flags & SLAB_STORE_USER)
				stack_depot_request_early_init();
		}
	}

	/*
	 * For backwards compatibility, a single list of flags with list of
	 * slabs means debugging is only changed for those slabs, so the global
	 * slab_debug should be unchanged (0 or DEBUG_DEFAULT_FLAGS, depending
	 * on CONFIG_SLUB_DEBUG_ON). We can extended that to multiple lists as
	 * long as there is no option specifying flags without a slab list.
	 */
	if (slab_list_specified) {
		if (!global_slub_debug_changed)
			global_flags = slub_debug;
		slub_debug_string = saved_str;
	}
out:
	slub_debug = global_flags;
	if (slub_debug & SLAB_STORE_USER)
		stack_depot_request_early_init();
	if (slub_debug != 0 || slub_debug_string)
		static_branch_enable(&slub_debug_enabled);
	else
		static_branch_disable(&slub_debug_enabled);
	if ((static_branch_unlikely(&init_on_alloc) ||
	     static_branch_unlikely(&init_on_free)) &&
	    (slub_debug & SLAB_POISON))
		pr_info("mem auto-init: SLAB_POISON will take precedence over init_on_alloc/init_on_free\n");
	return 1;
}

__setup("slab_debug", setup_slub_debug);
__setup_param("slub_debug", slub_debug, setup_slub_debug, 0);

/*
 * kmem_cache_flags - apply debugging options to the cache
 * @flags:		flags to set
 * @name:		name of the cache
 *
 * Debug option(s) are applied to @flags. In addition to the debug
 * option(s), if a slab name (or multiple) is specified i.e.
 * slab_debug=<Debug-Options>,<slab name1>,<slab name2> ...
 * then only the select slabs will receive the debug option(s).
 */
slab_flags_t kmem_cache_flags(slab_flags_t flags, const char *name)
{
	char *iter;
	size_t len;
	char *next_block;
	slab_flags_t block_flags;
	slab_flags_t slub_debug_local = slub_debug;

	if (flags & SLAB_NO_USER_FLAGS)
		return flags;

	/*
	 * If the slab cache is for debugging (e.g. kmemleak) then
	 * don't store user (stack trace) information by default,
	 * but let the user enable it via the command line below.
	 */
	if (flags & SLAB_NOLEAKTRACE)
		slub_debug_local &= ~SLAB_STORE_USER;

	len = strlen(name);
	next_block = slub_debug_string;
	/* Go through all blocks of debug options, see if any matches our slab's name */
	while (next_block) {
		next_block = parse_slub_debug_flags(next_block, &block_flags, &iter, false);
		if (!iter)
			continue;
		/* Found a block that has a slab list, search it */
		while (*iter) {
			char *end, *glob;
			size_t cmplen;

			end = strchrnul(iter, ',');
			if (next_block && next_block < end)
				end = next_block - 1;

			glob = strnchr(iter, end - iter, '*');
			if (glob)
				cmplen = glob - iter;
			else
				cmplen = max_t(size_t, len, (end - iter));

			if (!strncmp(name, iter, cmplen)) {
				flags |= block_flags;
				return flags;
			}

			if (!*end || *end == ';')
				break;
			iter = end + 1;
		}
	}

	return flags | slub_debug_local;
}
#else /* !CONFIG_SLUB_DEBUG */
static inline void setup_object_debug(struct kmem_cache *s, void *object) { … }
static inline
void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr) { … }

static inline bool alloc_debug_processing(struct kmem_cache *s,
	struct slab *slab, void *object, int orig_size) { … }

static inline bool free_debug_processing(struct kmem_cache *s,
	struct slab *slab, void *head, void *tail, int *bulk_cnt,
	unsigned long addr, depot_stack_handle_t handle) { … }

static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) { … }
static inline int check_object(struct kmem_cache *s, struct slab *slab,
			void *object, u8 val) { … }
static inline depot_stack_handle_t set_track_prepare(void) { … }
static inline void set_track(struct kmem_cache *s, void *object,
			     enum track_item alloc, unsigned long addr) { … }
static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
					struct slab *slab) { … }
static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
					struct slab *slab) { … }
slab_flags_t kmem_cache_flags(slab_flags_t flags, const char *name)
{ … }
#define slub_debug …

#define disable_higher_order_debug …

static inline unsigned long node_nr_slabs(struct kmem_cache_node *n)
							{ … }
static inline void inc_slabs_node(struct kmem_cache *s, int node,
							int objects) { … }
static inline void dec_slabs_node(struct kmem_cache *s, int node,
							int objects) { … }

#ifndef CONFIG_SLUB_TINY
static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
			       void **freelist, void *nextfree)
{
	return false;
}
#endif
#endif /* CONFIG_SLUB_DEBUG */

#ifdef CONFIG_SLAB_OBJ_EXT

#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG

static inline void mark_objexts_empty(struct slabobj_ext *obj_exts)
{
	struct slabobj_ext *slab_exts;
	struct slab *obj_exts_slab;

	obj_exts_slab = virt_to_slab(obj_exts);
	slab_exts = slab_obj_exts(obj_exts_slab);
	if (slab_exts) {
		unsigned int offs = obj_to_index(obj_exts_slab->slab_cache,
						 obj_exts_slab, obj_exts);
		/* codetag should be NULL */
		WARN_ON(slab_exts[offs].ref.ct);
		set_codetag_empty(&slab_exts[offs].ref);
	}
}

static inline void mark_failed_objexts_alloc(struct slab *slab)
{
	slab->obj_exts = OBJEXTS_ALLOC_FAIL;
}

static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
			struct slabobj_ext *vec, unsigned int objects)
{
	/*
	 * If vector previously failed to allocate then we have live
	 * objects with no tag reference. Mark all references in this
	 * vector as empty to avoid warnings later on.
	 */
	if (obj_exts & OBJEXTS_ALLOC_FAIL) {
		unsigned int i;

		for (i = 0; i < objects; i++)
			set_codetag_empty(&vec[i].ref);
	}
}

#else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */

static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) { … }
static inline void mark_failed_objexts_alloc(struct slab *slab) { … }
static inline void handle_failed_objexts_alloc(unsigned long obj_exts,
			struct slabobj_ext *vec, unsigned int objects) { … }

#endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */

/*
 * The allocated objcg pointers array is not accounted directly.
 * Moreover, it should not come from DMA buffer and is not readily
 * reclaimable. So those GFP bits should be masked off.
 */
#define OBJCGS_CLEAR_MASK …

int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
		        gfp_t gfp, bool new_slab)
{ … }

static inline void free_slab_obj_exts(struct slab *slab)
{ … }

static inline bool need_slab_obj_ext(void)
{ … }

#else /* CONFIG_SLAB_OBJ_EXT */

static int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s,
			       gfp_t gfp, bool new_slab)
{
	return 0;
}

static inline void free_slab_obj_exts(struct slab *slab)
{
}

static inline bool need_slab_obj_ext(void)
{
	return false;
}

#endif /* CONFIG_SLAB_OBJ_EXT */

#ifdef CONFIG_MEM_ALLOC_PROFILING

static inline struct slabobj_ext *
prepare_slab_obj_exts_hook(struct kmem_cache *s, gfp_t flags, void *p)
{
	struct slab *slab;

	if (!p)
		return NULL;

	if (s->flags & (SLAB_NO_OBJ_EXT | SLAB_NOLEAKTRACE))
		return NULL;

	if (flags & __GFP_NO_OBJ_EXT)
		return NULL;

	slab = virt_to_slab(p);
	if (!slab_obj_exts(slab) &&
	    WARN(alloc_slab_obj_exts(slab, s, flags, false),
		 "%s, %s: Failed to create slab extension vector!\n",
		 __func__, s->name))
		return NULL;

	return slab_obj_exts(slab) + obj_to_index(s, slab, p);
}

static inline void
alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
{
	if (need_slab_obj_ext()) {
		struct slabobj_ext *obj_exts;

		obj_exts = prepare_slab_obj_exts_hook(s, flags, object);
		/*
		 * Currently obj_exts is used only for allocation profiling.
		 * If other users appear then mem_alloc_profiling_enabled()
		 * check should be added before alloc_tag_add().
		 */
		if (likely(obj_exts))
			alloc_tag_add(&obj_exts->ref, current->alloc_tag, s->size);
	}
}

static inline void
alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
			     int objects)
{
	struct slabobj_ext *obj_exts;
	int i;

	if (!mem_alloc_profiling_enabled())
		return;

	obj_exts = slab_obj_exts(slab);
	if (!obj_exts)
		return;

	for (i = 0; i < objects; i++) {
		unsigned int off = obj_to_index(s, slab, p[i]);

		alloc_tag_sub(&obj_exts[off].ref, s->size);
	}
}

#else /* CONFIG_MEM_ALLOC_PROFILING */

static inline void
alloc_tagging_slab_alloc_hook(struct kmem_cache *s, void *object, gfp_t flags)
{ … }

static inline void
alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
			     int objects)
{ … }

#endif /* CONFIG_MEM_ALLOC_PROFILING */


#ifdef CONFIG_MEMCG

static void memcg_alloc_abort_single(struct kmem_cache *s, void *object);

static __fastpath_inline
bool memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru,
				gfp_t flags, size_t size, void **p)
{ … }

static __fastpath_inline
void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
			  int objects)
{ … }
#else /* CONFIG_MEMCG */
static inline bool memcg_slab_post_alloc_hook(struct kmem_cache *s,
					      struct list_lru *lru,
					      gfp_t flags, size_t size,
					      void **p)
{
	return true;
}

static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
					void **p, int objects)
{
}
#endif /* CONFIG_MEMCG */

/*
 * Hooks for other subsystems that check memory allocations. In a typical
 * production configuration these hooks all should produce no code at all.
 *
 * Returns true if freeing of the object can proceed, false if its reuse
 * was delayed by KASAN quarantine, or it was returned to KFENCE.
 */
static __always_inline
bool slab_free_hook(struct kmem_cache *s, void *x, bool init)
{ … }

static __fastpath_inline
bool slab_free_freelist_hook(struct kmem_cache *s, void **head, void **tail,
			     int *cnt)
{ … }

static void *setup_object(struct kmem_cache *s, void *object)
{ … }

/*
 * Slab allocation and freeing
 */
static inline struct slab *alloc_slab_page(gfp_t flags, int node,
		struct kmem_cache_order_objects oo)
{ … }

#ifdef CONFIG_SLAB_FREELIST_RANDOM
/* Pre-initialize the random sequence cache */
static int init_cache_random_seq(struct kmem_cache *s)
{
	unsigned int count = oo_objects(s->oo);
	int err;

	/* Bailout if already initialised */
	if (s->random_seq)
		return 0;

	err = cache_random_seq_create(s, count, GFP_KERNEL);
	if (err) {
		pr_err("SLUB: Unable to initialize free list for %s\n",
			s->name);
		return err;
	}

	/* Transform to an offset on the set of pages */
	if (s->random_seq) {
		unsigned int i;

		for (i = 0; i < count; i++)
			s->random_seq[i] *= s->size;
	}
	return 0;
}

/* Initialize each random sequence freelist per cache */
static void __init init_freelist_randomization(void)
{
	struct kmem_cache *s;

	mutex_lock(&slab_mutex);

	list_for_each_entry(s, &slab_caches, list)
		init_cache_random_seq(s);

	mutex_unlock(&slab_mutex);
}

/* Get the next entry on the pre-computed freelist randomized */
static void *next_freelist_entry(struct kmem_cache *s,
				unsigned long *pos, void *start,
				unsigned long page_limit,
				unsigned long freelist_count)
{
	unsigned int idx;

	/*
	 * If the target page allocation failed, the number of objects on the
	 * page might be smaller than the usual size defined by the cache.
	 */
	do {
		idx = s->random_seq[*pos];
		*pos += 1;
		if (*pos >= freelist_count)
			*pos = 0;
	} while (unlikely(idx >= page_limit));

	return (char *)start + idx;
}

/* Shuffle the single linked freelist based on a random pre-computed sequence */
static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
{
	void *start;
	void *cur;
	void *next;
	unsigned long idx, pos, page_limit, freelist_count;

	if (slab->objects < 2 || !s->random_seq)
		return false;

	freelist_count = oo_objects(s->oo);
	pos = get_random_u32_below(freelist_count);

	page_limit = slab->objects * s->size;
	start = fixup_red_left(s, slab_address(slab));

	/* First entry is used as the base of the freelist */
	cur = next_freelist_entry(s, &pos, start, page_limit, freelist_count);
	cur = setup_object(s, cur);
	slab->freelist = cur;

	for (idx = 1; idx < slab->objects; idx++) {
		next = next_freelist_entry(s, &pos, start, page_limit,
			freelist_count);
		next = setup_object(s, next);
		set_freepointer(s, cur, next);
		cur = next;
	}
	set_freepointer(s, cur, NULL);

	return true;
}
#else
static inline int init_cache_random_seq(struct kmem_cache *s)
{ … }
static inline void init_freelist_randomization(void) { … }
static inline bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
{ … }
#endif /* CONFIG_SLAB_FREELIST_RANDOM */

static __always_inline void account_slab(struct slab *slab, int order,
					 struct kmem_cache *s, gfp_t gfp)
{ … }

static __always_inline void unaccount_slab(struct slab *slab, int order,
					   struct kmem_cache *s)
{ … }

static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
{ … }

static struct slab *new_slab(struct kmem_cache *s, gfp_t flags, int node)
{ … }

static void __free_slab(struct kmem_cache *s, struct slab *slab)
{ … }

static void rcu_free_slab(struct rcu_head *h)
{ … }

static void free_slab(struct kmem_cache *s, struct slab *slab)
{ … }

static void discard_slab(struct kmem_cache *s, struct slab *slab)
{ … }

/*
 * SLUB reuses PG_workingset bit to keep track of whether it's on
 * the per-node partial list.
 */
static inline bool slab_test_node_partial(const struct slab *slab)
{ … }

static inline void slab_set_node_partial(struct slab *slab)
{ … }

static inline void slab_clear_node_partial(struct slab *slab)
{ … }

/*
 * Management of partially allocated slabs.
 */
static inline void
__add_partial(struct kmem_cache_node *n, struct slab *slab, int tail)
{ … }

static inline void add_partial(struct kmem_cache_node *n,
				struct slab *slab, int tail)
{ … }

static inline void remove_partial(struct kmem_cache_node *n,
					struct slab *slab)
{ … }

/*
 * Called only for kmem_cache_debug() caches instead of remove_partial(), with a
 * slab from the n->partial list. Remove only a single object from the slab, do
 * the alloc_debug_processing() checks and leave the slab on the list, or move
 * it to full list if it was the last free object.
 */
static void *alloc_single_from_partial(struct kmem_cache *s,
		struct kmem_cache_node *n, struct slab *slab, int orig_size)
{ … }

/*
 * Called only for kmem_cache_debug() caches to allocate from a freshly
 * allocated slab. Allocate a single object instead of whole freelist
 * and put the slab to the partial (or full) list.
 */
static void *alloc_single_from_new_slab(struct kmem_cache *s,
					struct slab *slab, int orig_size)
{ … }

#ifdef CONFIG_SLUB_CPU_PARTIAL
static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain);
#else
static inline void put_cpu_partial(struct kmem_cache *s, struct slab *slab,
				   int drain) { … }
#endif
static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags);

/*
 * Try to allocate a partial slab from a specific node.
 */
static struct slab *get_partial_node(struct kmem_cache *s,
				     struct kmem_cache_node *n,
				     struct partial_context *pc)
{ … }

/*
 * Get a slab from somewhere. Search in increasing NUMA distances.
 */
static struct slab *get_any_partial(struct kmem_cache *s,
				    struct partial_context *pc)
{ … }

/*
 * Get a partial slab, lock it and return it.
 */
static struct slab *get_partial(struct kmem_cache *s, int node,
				struct partial_context *pc)
{ … }

#ifndef CONFIG_SLUB_TINY

#ifdef CONFIG_PREEMPTION
/*
 * Calculate the next globally unique transaction for disambiguation
 * during cmpxchg. The transactions start with the cpu number and are then
 * incremented by CONFIG_NR_CPUS.
 */
#define TID_STEP …
#else
/*
 * No preemption supported therefore also no need to check for
 * different cpus.
 */
#define TID_STEP …
#endif /* CONFIG_PREEMPTION */

static inline unsigned long next_tid(unsigned long tid)
{
	return tid + TID_STEP;
}

#ifdef SLUB_DEBUG_CMPXCHG
static inline unsigned int tid_to_cpu(unsigned long tid)
{
	return tid % TID_STEP;
}

static inline unsigned long tid_to_event(unsigned long tid)
{
	return tid / TID_STEP;
}
#endif

static inline unsigned int init_tid(int cpu)
{
	return cpu;
}

static inline void note_cmpxchg_failure(const char *n,
		const struct kmem_cache *s, unsigned long tid)
{
#ifdef SLUB_DEBUG_CMPXCHG
	unsigned long actual_tid = __this_cpu_read(s->cpu_slab->tid);

	pr_info("%s %s: cmpxchg redo ", n, s->name);

#ifdef CONFIG_PREEMPTION
	if (tid_to_cpu(tid) != tid_to_cpu(actual_tid))
		pr_warn("due to cpu change %d -> %d\n",
			tid_to_cpu(tid), tid_to_cpu(actual_tid));
	else
#endif
	if (tid_to_event(tid) != tid_to_event(actual_tid))
		pr_warn("due to cpu running other code. Event %ld->%ld\n",
			tid_to_event(tid), tid_to_event(actual_tid));
	else
		pr_warn("for unknown reason: actual=%lx was=%lx target=%lx\n",
			actual_tid, tid, next_tid(tid));
#endif
	stat(s, CMPXCHG_DOUBLE_CPU_FAIL);
}

static void init_kmem_cache_cpus(struct kmem_cache *s)
{
	int cpu;
	struct kmem_cache_cpu *c;

	for_each_possible_cpu(cpu) {
		c = per_cpu_ptr(s->cpu_slab, cpu);
		local_lock_init(&c->lock);
		c->tid = init_tid(cpu);
	}
}

/*
 * Finishes removing the cpu slab. Merges cpu's freelist with slab's freelist,
 * unfreezes the slabs and puts it on the proper list.
 * Assumes the slab has been already safely taken away from kmem_cache_cpu
 * by the caller.
 */
static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
			    void *freelist)
{
	struct kmem_cache_node *n = get_node(s, slab_nid(slab));
	int free_delta = 0;
	void *nextfree, *freelist_iter, *freelist_tail;
	int tail = DEACTIVATE_TO_HEAD;
	unsigned long flags = 0;
	struct slab new;
	struct slab old;

	if (READ_ONCE(slab->freelist)) {
		stat(s, DEACTIVATE_REMOTE_FREES);
		tail = DEACTIVATE_TO_TAIL;
	}

	/*
	 * Stage one: Count the objects on cpu's freelist as free_delta and
	 * remember the last object in freelist_tail for later splicing.
	 */
	freelist_tail = NULL;
	freelist_iter = freelist;
	while (freelist_iter) {
		nextfree = get_freepointer(s, freelist_iter);

		/*
		 * If 'nextfree' is invalid, it is possible that the object at
		 * 'freelist_iter' is already corrupted.  So isolate all objects
		 * starting at 'freelist_iter' by skipping them.
		 */
		if (freelist_corrupted(s, slab, &freelist_iter, nextfree))
			break;

		freelist_tail = freelist_iter;
		free_delta++;

		freelist_iter = nextfree;
	}

	/*
	 * Stage two: Unfreeze the slab while splicing the per-cpu
	 * freelist to the head of slab's freelist.
	 */
	do {
		old.freelist = READ_ONCE(slab->freelist);
		old.counters = READ_ONCE(slab->counters);
		VM_BUG_ON(!old.frozen);

		/* Determine target state of the slab */
		new.counters = old.counters;
		new.frozen = 0;
		if (freelist_tail) {
			new.inuse -= free_delta;
			set_freepointer(s, freelist_tail, old.freelist);
			new.freelist = freelist;
		} else {
			new.freelist = old.freelist;
		}
	} while (!slab_update_freelist(s, slab,
		old.freelist, old.counters,
		new.freelist, new.counters,
		"unfreezing slab"));

	/*
	 * Stage three: Manipulate the slab list based on the updated state.
	 */
	if (!new.inuse && n->nr_partial >= s->min_partial) {
		stat(s, DEACTIVATE_EMPTY);
		discard_slab(s, slab);
		stat(s, FREE_SLAB);
	} else if (new.freelist) {
		spin_lock_irqsave(&n->list_lock, flags);
		add_partial(n, slab, tail);
		spin_unlock_irqrestore(&n->list_lock, flags);
		stat(s, tail);
	} else {
		stat(s, DEACTIVATE_FULL);
	}
}

#ifdef CONFIG_SLUB_CPU_PARTIAL
static void __put_partials(struct kmem_cache *s, struct slab *partial_slab)
{
	struct kmem_cache_node *n = NULL, *n2 = NULL;
	struct slab *slab, *slab_to_discard = NULL;
	unsigned long flags = 0;

	while (partial_slab) {
		slab = partial_slab;
		partial_slab = slab->next;

		n2 = get_node(s, slab_nid(slab));
		if (n != n2) {
			if (n)
				spin_unlock_irqrestore(&n->list_lock, flags);

			n = n2;
			spin_lock_irqsave(&n->list_lock, flags);
		}

		if (unlikely(!slab->inuse && n->nr_partial >= s->min_partial)) {
			slab->next = slab_to_discard;
			slab_to_discard = slab;
		} else {
			add_partial(n, slab, DEACTIVATE_TO_TAIL);
			stat(s, FREE_ADD_PARTIAL);
		}
	}

	if (n)
		spin_unlock_irqrestore(&n->list_lock, flags);

	while (slab_to_discard) {
		slab = slab_to_discard;
		slab_to_discard = slab_to_discard->next;

		stat(s, DEACTIVATE_EMPTY);
		discard_slab(s, slab);
		stat(s, FREE_SLAB);
	}
}

/*
 * Put all the cpu partial slabs to the node partial list.
 */
static void put_partials(struct kmem_cache *s)
{
	struct slab *partial_slab;
	unsigned long flags;

	local_lock_irqsave(&s->cpu_slab->lock, flags);
	partial_slab = this_cpu_read(s->cpu_slab->partial);
	this_cpu_write(s->cpu_slab->partial, NULL);
	local_unlock_irqrestore(&s->cpu_slab->lock, flags);

	if (partial_slab)
		__put_partials(s, partial_slab);
}

static void put_partials_cpu(struct kmem_cache *s,
			     struct kmem_cache_cpu *c)
{
	struct slab *partial_slab;

	partial_slab = slub_percpu_partial(c);
	c->partial = NULL;

	if (partial_slab)
		__put_partials(s, partial_slab);
}

/*
 * Put a slab into a partial slab slot if available.
 *
 * If we did not find a slot then simply move all the partials to the
 * per node partial list.
 */
static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain)
{
	struct slab *oldslab;
	struct slab *slab_to_put = NULL;
	unsigned long flags;
	int slabs = 0;

	local_lock_irqsave(&s->cpu_slab->lock, flags);

	oldslab = this_cpu_read(s->cpu_slab->partial);

	if (oldslab) {
		if (drain && oldslab->slabs >= s->cpu_partial_slabs) {
			/*
			 * Partial array is full. Move the existing set to the
			 * per node partial list. Postpone the actual unfreezing
			 * outside of the critical section.
			 */
			slab_to_put = oldslab;
			oldslab = NULL;
		} else {
			slabs = oldslab->slabs;
		}
	}

	slabs++;

	slab->slabs = slabs;
	slab->next = oldslab;

	this_cpu_write(s->cpu_slab->partial, slab);

	local_unlock_irqrestore(&s->cpu_slab->lock, flags);

	if (slab_to_put) {
		__put_partials(s, slab_to_put);
		stat(s, CPU_PARTIAL_DRAIN);
	}
}

#else	/* CONFIG_SLUB_CPU_PARTIAL */

static inline void put_partials(struct kmem_cache *s) { }
static inline void put_partials_cpu(struct kmem_cache *s,
				    struct kmem_cache_cpu *c) { }

#endif	/* CONFIG_SLUB_CPU_PARTIAL */

static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
{
	unsigned long flags;
	struct slab *slab;
	void *freelist;

	local_lock_irqsave(&s->cpu_slab->lock, flags);

	slab = c->slab;
	freelist = c->freelist;

	c->slab = NULL;
	c->freelist = NULL;
	c->tid = next_tid(c->tid);

	local_unlock_irqrestore(&s->cpu_slab->lock, flags);

	if (slab) {
		deactivate_slab(s, slab, freelist);
		stat(s, CPUSLAB_FLUSH);
	}
}

static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
{
	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
	void *freelist = c->freelist;
	struct slab *slab = c->slab;

	c->slab = NULL;
	c->freelist = NULL;
	c->tid = next_tid(c->tid);

	if (slab) {
		deactivate_slab(s, slab, freelist);
		stat(s, CPUSLAB_FLUSH);
	}

	put_partials_cpu(s, c);
}

struct slub_flush_work {
	struct work_struct work;
	struct kmem_cache *s;
	bool skip;
};

/*
 * Flush cpu slab.
 *
 * Called from CPU work handler with migration disabled.
 */
static void flush_cpu_slab(struct work_struct *w)
{
	struct kmem_cache *s;
	struct kmem_cache_cpu *c;
	struct slub_flush_work *sfw;

	sfw = container_of(w, struct slub_flush_work, work);

	s = sfw->s;
	c = this_cpu_ptr(s->cpu_slab);

	if (c->slab)
		flush_slab(s, c);

	put_partials(s);
}

static bool has_cpu_slab(int cpu, struct kmem_cache *s)
{
	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);

	return c->slab || slub_percpu_partial(c);
}

static DEFINE_MUTEX(flush_lock);
static DEFINE_PER_CPU(struct slub_flush_work, slub_flush);

static void flush_all_cpus_locked(struct kmem_cache *s)
{
	struct slub_flush_work *sfw;
	unsigned int cpu;

	lockdep_assert_cpus_held();
	mutex_lock(&flush_lock);

	for_each_online_cpu(cpu) {
		sfw = &per_cpu(slub_flush, cpu);
		if (!has_cpu_slab(cpu, s)) {
			sfw->skip = true;
			continue;
		}
		INIT_WORK(&sfw->work, flush_cpu_slab);
		sfw->skip = false;
		sfw->s = s;
		queue_work_on(cpu, flushwq, &sfw->work);
	}

	for_each_online_cpu(cpu) {
		sfw = &per_cpu(slub_flush, cpu);
		if (sfw->skip)
			continue;
		flush_work(&sfw->work);
	}

	mutex_unlock(&flush_lock);
}

static void flush_all(struct kmem_cache *s)
{
	cpus_read_lock();
	flush_all_cpus_locked(s);
	cpus_read_unlock();
}

/*
 * Use the cpu notifier to insure that the cpu slabs are flushed when
 * necessary.
 */
static int slub_cpu_dead(unsigned int cpu)
{
	struct kmem_cache *s;

	mutex_lock(&slab_mutex);
	list_for_each_entry(s, &slab_caches, list)
		__flush_cpu_slab(s, cpu);
	mutex_unlock(&slab_mutex);
	return 0;
}

#else /* CONFIG_SLUB_TINY */
static inline void flush_all_cpus_locked(struct kmem_cache *s) { … }
static inline void flush_all(struct kmem_cache *s) { … }
static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) { … }
static inline int slub_cpu_dead(unsigned int cpu) { … }
#endif /* CONFIG_SLUB_TINY */

/*
 * Check if the objects in a per cpu structure fit numa
 * locality expectations.
 */
static inline int node_match(struct slab *slab, int node)
{ … }

#ifdef CONFIG_SLUB_DEBUG
static int count_free(struct slab *slab)
{
	return slab->objects - slab->inuse;
}

static inline unsigned long node_nr_objs(struct kmem_cache_node *n)
{
	return atomic_long_read(&n->total_objects);
}

/* Supports checking bulk free of a constructed freelist */
static inline bool free_debug_processing(struct kmem_cache *s,
	struct slab *slab, void *head, void *tail, int *bulk_cnt,
	unsigned long addr, depot_stack_handle_t handle)
{
	bool checks_ok = false;
	void *object = head;
	int cnt = 0;

	if (s->flags & SLAB_CONSISTENCY_CHECKS) {
		if (!check_slab(s, slab))
			goto out;
	}

	if (slab->inuse < *bulk_cnt) {
		slab_err(s, slab, "Slab has %d allocated objects but %d are to be freed\n",
			 slab->inuse, *bulk_cnt);
		goto out;
	}

next_object:

	if (++cnt > *bulk_cnt)
		goto out_cnt;

	if (s->flags & SLAB_CONSISTENCY_CHECKS) {
		if (!free_consistency_checks(s, slab, object, addr))
			goto out;
	}

	if (s->flags & SLAB_STORE_USER)
		set_track_update(s, object, TRACK_FREE, addr, handle);
	trace(s, slab, object, 0);
	/* Freepointer not overwritten by init_object(), SLAB_POISON moved it */
	init_object(s, object, SLUB_RED_INACTIVE);

	/* Reached end of constructed freelist yet? */
	if (object != tail) {
		object = get_freepointer(s, object);
		goto next_object;
	}
	checks_ok = true;

out_cnt:
	if (cnt != *bulk_cnt) {
		slab_err(s, slab, "Bulk free expected %d objects but found %d\n",
			 *bulk_cnt, cnt);
		*bulk_cnt = cnt;
	}

out:

	if (!checks_ok)
		slab_fix(s, "Object at 0x%p not freed", object);

	return checks_ok;
}
#endif /* CONFIG_SLUB_DEBUG */

#if defined(CONFIG_SLUB_DEBUG) || defined(SLAB_SUPPORTS_SYSFS)
static unsigned long count_partial(struct kmem_cache_node *n,
					int (*get_count)(struct slab *))
{
	unsigned long flags;
	unsigned long x = 0;
	struct slab *slab;

	spin_lock_irqsave(&n->list_lock, flags);
	list_for_each_entry(slab, &n->partial, slab_list)
		x += get_count(slab);
	spin_unlock_irqrestore(&n->list_lock, flags);
	return x;
}
#endif /* CONFIG_SLUB_DEBUG || SLAB_SUPPORTS_SYSFS */

#ifdef CONFIG_SLUB_DEBUG
#define MAX_PARTIAL_TO_SCAN …

static unsigned long count_partial_free_approx(struct kmem_cache_node *n)
{
	unsigned long flags;
	unsigned long x = 0;
	struct slab *slab;

	spin_lock_irqsave(&n->list_lock, flags);
	if (n->nr_partial <= MAX_PARTIAL_TO_SCAN) {
		list_for_each_entry(slab, &n->partial, slab_list)
			x += slab->objects - slab->inuse;
	} else {
		/*
		 * For a long list, approximate the total count of objects in
		 * it to meet the limit on the number of slabs to scan.
		 * Scan from both the list's head and tail for better accuracy.
		 */
		unsigned long scanned = 0;

		list_for_each_entry(slab, &n->partial, slab_list) {
			x += slab->objects - slab->inuse;
			if (++scanned == MAX_PARTIAL_TO_SCAN / 2)
				break;
		}
		list_for_each_entry_reverse(slab, &n->partial, slab_list) {
			x += slab->objects - slab->inuse;
			if (++scanned == MAX_PARTIAL_TO_SCAN)
				break;
		}
		x = mult_frac(x, n->nr_partial, scanned);
		x = min(x, node_nr_objs(n));
	}
	spin_unlock_irqrestore(&n->list_lock, flags);
	return x;
}

static noinline void
slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
{
	static DEFINE_RATELIMIT_STATE(slub_oom_rs, DEFAULT_RATELIMIT_INTERVAL,
				      DEFAULT_RATELIMIT_BURST);
	int node;
	struct kmem_cache_node *n;

	if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slub_oom_rs))
		return;

	pr_warn("SLUB: Unable to allocate memory on node %d, gfp=%#x(%pGg)\n",
		nid, gfpflags, &gfpflags);
	pr_warn("  cache: %s, object size: %u, buffer size: %u, default order: %u, min order: %u\n",
		s->name, s->object_size, s->size, oo_order(s->oo),
		oo_order(s->min));

	if (oo_order(s->min) > get_order(s->object_size))
		pr_warn("  %s debugging increased min order, use slab_debug=O to disable.\n",
			s->name);

	for_each_kmem_cache_node(s, node, n) {
		unsigned long nr_slabs;
		unsigned long nr_objs;
		unsigned long nr_free;

		nr_free  = count_partial_free_approx(n);
		nr_slabs = node_nr_slabs(n);
		nr_objs  = node_nr_objs(n);

		pr_warn("  node %d: slabs: %ld, objs: %ld, free: %ld\n",
			node, nr_slabs, nr_objs, nr_free);
	}
}
#else /* CONFIG_SLUB_DEBUG */
static inline void
slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid) { … }
#endif

static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags)
{ … }

#ifndef CONFIG_SLUB_TINY
static inline bool
__update_cpu_freelist_fast(struct kmem_cache *s,
			   void *freelist_old, void *freelist_new,
			   unsigned long tid)
{
	freelist_aba_t old = { .freelist = freelist_old, .counter = tid };
	freelist_aba_t new = { .freelist = freelist_new, .counter = next_tid(tid) };

	return this_cpu_try_cmpxchg_freelist(s->cpu_slab->freelist_tid.full,
					     &old.full, new.full);
}

/*
 * Check the slab->freelist and either transfer the freelist to the
 * per cpu freelist or deactivate the slab.
 *
 * The slab is still frozen if the return value is not NULL.
 *
 * If this function returns NULL then the slab has been unfrozen.
 */
static inline void *get_freelist(struct kmem_cache *s, struct slab *slab)
{
	struct slab new;
	unsigned long counters;
	void *freelist;

	lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock));

	do {
		freelist = slab->freelist;
		counters = slab->counters;

		new.counters = counters;

		new.inuse = slab->objects;
		new.frozen = freelist != NULL;

	} while (!__slab_update_freelist(s, slab,
		freelist, counters,
		NULL, new.counters,
		"get_freelist"));

	return freelist;
}

/*
 * Freeze the partial slab and return the pointer to the freelist.
 */
static inline void *freeze_slab(struct kmem_cache *s, struct slab *slab)
{
	struct slab new;
	unsigned long counters;
	void *freelist;

	do {
		freelist = slab->freelist;
		counters = slab->counters;

		new.counters = counters;
		VM_BUG_ON(new.frozen);

		new.inuse = slab->objects;
		new.frozen = 1;

	} while (!slab_update_freelist(s, slab,
		freelist, counters,
		NULL, new.counters,
		"freeze_slab"));

	return freelist;
}

/*
 * Slow path. The lockless freelist is empty or we need to perform
 * debugging duties.
 *
 * Processing is still very fast if new objects have been freed to the
 * regular freelist. In that case we simply take over the regular freelist
 * as the lockless freelist and zap the regular freelist.
 *
 * If that is not working then we fall back to the partial lists. We take the
 * first element of the freelist as the object to allocate now and move the
 * rest of the freelist to the lockless freelist.
 *
 * And if we were unable to get a new slab from the partial slab lists then
 * we need to allocate a new slab. This is the slowest path since it involves
 * a call to the page allocator and the setup of a new slab.
 *
 * Version of __slab_alloc to use when we know that preemption is
 * already disabled (which is the case for bulk allocation).
 */
static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
			  unsigned long addr, struct kmem_cache_cpu *c, unsigned int orig_size)
{
	void *freelist;
	struct slab *slab;
	unsigned long flags;
	struct partial_context pc;
	bool try_thisnode = true;

	stat(s, ALLOC_SLOWPATH);

reread_slab:

	slab = READ_ONCE(c->slab);
	if (!slab) {
		/*
		 * if the node is not online or has no normal memory, just
		 * ignore the node constraint
		 */
		if (unlikely(node != NUMA_NO_NODE &&
			     !node_isset(node, slab_nodes)))
			node = NUMA_NO_NODE;
		goto new_slab;
	}

	if (unlikely(!node_match(slab, node))) {
		/*
		 * same as above but node_match() being false already
		 * implies node != NUMA_NO_NODE
		 */
		if (!node_isset(node, slab_nodes)) {
			node = NUMA_NO_NODE;
		} else {
			stat(s, ALLOC_NODE_MISMATCH);
			goto deactivate_slab;
		}
	}

	/*
	 * By rights, we should be searching for a slab page that was
	 * PFMEMALLOC but right now, we are losing the pfmemalloc
	 * information when the page leaves the per-cpu allocator
	 */
	if (unlikely(!pfmemalloc_match(slab, gfpflags)))
		goto deactivate_slab;

	/* must check again c->slab in case we got preempted and it changed */
	local_lock_irqsave(&s->cpu_slab->lock, flags);
	if (unlikely(slab != c->slab)) {
		local_unlock_irqrestore(&s->cpu_slab->lock, flags);
		goto reread_slab;
	}
	freelist = c->freelist;
	if (freelist)
		goto load_freelist;

	freelist = get_freelist(s, slab);

	if (!freelist) {
		c->slab = NULL;
		c->tid = next_tid(c->tid);
		local_unlock_irqrestore(&s->cpu_slab->lock, flags);
		stat(s, DEACTIVATE_BYPASS);
		goto new_slab;
	}

	stat(s, ALLOC_REFILL);

load_freelist:

	lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock));

	/*
	 * freelist is pointing to the list of objects to be used.
	 * slab is pointing to the slab from which the objects are obtained.
	 * That slab must be frozen for per cpu allocations to work.
	 */
	VM_BUG_ON(!c->slab->frozen);
	c->freelist = get_freepointer(s, freelist);
	c->tid = next_tid(c->tid);
	local_unlock_irqrestore(&s->cpu_slab->lock, flags);
	return freelist;

deactivate_slab:

	local_lock_irqsave(&s->cpu_slab->lock, flags);
	if (slab != c->slab) {
		local_unlock_irqrestore(&s->cpu_slab->lock, flags);
		goto reread_slab;
	}
	freelist = c->freelist;
	c->slab = NULL;
	c->freelist = NULL;
	c->tid = next_tid(c->tid);
	local_unlock_irqrestore(&s->cpu_slab->lock, flags);
	deactivate_slab(s, slab, freelist);

new_slab:

#ifdef CONFIG_SLUB_CPU_PARTIAL
	while (slub_percpu_partial(c)) {
		local_lock_irqsave(&s->cpu_slab->lock, flags);
		if (unlikely(c->slab)) {
			local_unlock_irqrestore(&s->cpu_slab->lock, flags);
			goto reread_slab;
		}
		if (unlikely(!slub_percpu_partial(c))) {
			local_unlock_irqrestore(&s->cpu_slab->lock, flags);
			/* we were preempted and partial list got empty */
			goto new_objects;
		}

		slab = slub_percpu_partial(c);
		slub_set_percpu_partial(c, slab);

		if (likely(node_match(slab, node) &&
			   pfmemalloc_match(slab, gfpflags))) {
			c->slab = slab;
			freelist = get_freelist(s, slab);
			VM_BUG_ON(!freelist);
			stat(s, CPU_PARTIAL_ALLOC);
			goto load_freelist;
		}

		local_unlock_irqrestore(&s->cpu_slab->lock, flags);

		slab->next = NULL;
		__put_partials(s, slab);
	}
#endif

new_objects:

	pc.flags = gfpflags;
	/*
	 * When a preferred node is indicated but no __GFP_THISNODE
	 *
	 * 1) try to get a partial slab from target node only by having
	 *    __GFP_THISNODE in pc.flags for get_partial()
	 * 2) if 1) failed, try to allocate a new slab from target node with
	 *    GPF_NOWAIT | __GFP_THISNODE opportunistically
	 * 3) if 2) failed, retry with original gfpflags which will allow
	 *    get_partial() try partial lists of other nodes before potentially
	 *    allocating new page from other nodes
	 */
	if (unlikely(node != NUMA_NO_NODE && !(gfpflags & __GFP_THISNODE)
		     && try_thisnode))
		pc.flags = GFP_NOWAIT | __GFP_THISNODE;

	pc.orig_size = orig_size;
	slab = get_partial(s, node, &pc);
	if (slab) {
		if (kmem_cache_debug(s)) {
			freelist = pc.object;
			/*
			 * For debug caches here we had to go through
			 * alloc_single_from_partial() so just store the
			 * tracking info and return the object.
			 */
			if (s->flags & SLAB_STORE_USER)
				set_track(s, freelist, TRACK_ALLOC, addr);

			return freelist;
		}

		freelist = freeze_slab(s, slab);
		goto retry_load_slab;
	}

	slub_put_cpu_ptr(s->cpu_slab);
	slab = new_slab(s, pc.flags, node);
	c = slub_get_cpu_ptr(s->cpu_slab);

	if (unlikely(!slab)) {
		if (node != NUMA_NO_NODE && !(gfpflags & __GFP_THISNODE)
		    && try_thisnode) {
			try_thisnode = false;
			goto new_objects;
		}
		slab_out_of_memory(s, gfpflags, node);
		return NULL;
	}

	stat(s, ALLOC_SLAB);

	if (kmem_cache_debug(s)) {
		freelist = alloc_single_from_new_slab(s, slab, orig_size);

		if (unlikely(!freelist))
			goto new_objects;

		if (s->flags & SLAB_STORE_USER)
			set_track(s, freelist, TRACK_ALLOC, addr);

		return freelist;
	}

	/*
	 * No other reference to the slab yet so we can
	 * muck around with it freely without cmpxchg
	 */
	freelist = slab->freelist;
	slab->freelist = NULL;
	slab->inuse = slab->objects;
	slab->frozen = 1;

	inc_slabs_node(s, slab_nid(slab), slab->objects);

	if (unlikely(!pfmemalloc_match(slab, gfpflags))) {
		/*
		 * For !pfmemalloc_match() case we don't load freelist so that
		 * we don't make further mismatched allocations easier.
		 */
		deactivate_slab(s, slab, get_freepointer(s, freelist));
		return freelist;
	}

retry_load_slab:

	local_lock_irqsave(&s->cpu_slab->lock, flags);
	if (unlikely(c->slab)) {
		void *flush_freelist = c->freelist;
		struct slab *flush_slab = c->slab;

		c->slab = NULL;
		c->freelist = NULL;
		c->tid = next_tid(c->tid);

		local_unlock_irqrestore(&s->cpu_slab->lock, flags);

		deactivate_slab(s, flush_slab, flush_freelist);

		stat(s, CPUSLAB_FLUSH);

		goto retry_load_slab;
	}
	c->slab = slab;

	goto load_freelist;
}

/*
 * A wrapper for ___slab_alloc() for contexts where preemption is not yet
 * disabled. Compensates for possible cpu changes by refetching the per cpu area
 * pointer.
 */
static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
			  unsigned long addr, struct kmem_cache_cpu *c, unsigned int orig_size)
{
	void *p;

#ifdef CONFIG_PREEMPT_COUNT
	/*
	 * We may have been preempted and rescheduled on a different
	 * cpu before disabling preemption. Need to reload cpu area
	 * pointer.
	 */
	c = slub_get_cpu_ptr(s->cpu_slab);
#endif

	p = ___slab_alloc(s, gfpflags, node, addr, c, orig_size);
#ifdef CONFIG_PREEMPT_COUNT
	slub_put_cpu_ptr(s->cpu_slab);
#endif
	return p;
}

static __always_inline void *__slab_alloc_node(struct kmem_cache *s,
		gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
{
	struct kmem_cache_cpu *c;
	struct slab *slab;
	unsigned long tid;
	void *object;

redo:
	/*
	 * Must read kmem_cache cpu data via this cpu ptr. Preemption is
	 * enabled. We may switch back and forth between cpus while
	 * reading from one cpu area. That does not matter as long
	 * as we end up on the original cpu again when doing the cmpxchg.
	 *
	 * We must guarantee that tid and kmem_cache_cpu are retrieved on the
	 * same cpu. We read first the kmem_cache_cpu pointer and use it to read
	 * the tid. If we are preempted and switched to another cpu between the
	 * two reads, it's OK as the two are still associated with the same cpu
	 * and cmpxchg later will validate the cpu.
	 */
	c = raw_cpu_ptr(s->cpu_slab);
	tid = READ_ONCE(c->tid);

	/*
	 * Irqless object alloc/free algorithm used here depends on sequence
	 * of fetching cpu_slab's data. tid should be fetched before anything
	 * on c to guarantee that object and slab associated with previous tid
	 * won't be used with current tid. If we fetch tid first, object and
	 * slab could be one associated with next tid and our alloc/free
	 * request will be failed. In this case, we will retry. So, no problem.
	 */
	barrier();

	/*
	 * The transaction ids are globally unique per cpu and per operation on
	 * a per cpu queue. Thus they can be guarantee that the cmpxchg_double
	 * occurs on the right processor and that there was no operation on the
	 * linked list in between.
	 */

	object = c->freelist;
	slab = c->slab;

	if (!USE_LOCKLESS_FAST_PATH() ||
	    unlikely(!object || !slab || !node_match(slab, node))) {
		object = __slab_alloc(s, gfpflags, node, addr, c, orig_size);
	} else {
		void *next_object = get_freepointer_safe(s, object);

		/*
		 * The cmpxchg will only match if there was no additional
		 * operation and if we are on the right processor.
		 *
		 * The cmpxchg does the following atomically (without lock
		 * semantics!)
		 * 1. Relocate first pointer to the current per cpu area.
		 * 2. Verify that tid and freelist have not been changed
		 * 3. If they were not changed replace tid and freelist
		 *
		 * Since this is without lock semantics the protection is only
		 * against code executing on this cpu *not* from access by
		 * other cpus.
		 */
		if (unlikely(!__update_cpu_freelist_fast(s, object, next_object, tid))) {
			note_cmpxchg_failure("slab_alloc", s, tid);
			goto redo;
		}
		prefetch_freepointer(s, next_object);
		stat(s, ALLOC_FASTPATH);
	}

	return object;
}
#else /* CONFIG_SLUB_TINY */
static void *__slab_alloc_node(struct kmem_cache *s,
		gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
{ … }
#endif /* CONFIG_SLUB_TINY */

/*
 * If the object has been wiped upon free, make sure it's fully initialized by
 * zeroing out freelist pointer.
 */
static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
						   void *obj)
{ … }

static __fastpath_inline
struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
{ … }

static __fastpath_inline
bool slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru,
			  gfp_t flags, size_t size, void **p, bool init,
			  unsigned int orig_size)
{ … }

/*
 * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
 * have the fastpath folded into their functions. So no function call
 * overhead for requests that can be satisfied on the fastpath.
 *
 * The fastpath works by first checking if the lockless freelist can be used.
 * If not then __slab_alloc is called for slow processing.
 *
 * Otherwise we can simply pick the next object from the lockless free list.
 */
static __fastpath_inline void *slab_alloc_node(struct kmem_cache *s, struct list_lru *lru,
		gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
{ … }

void *kmem_cache_alloc_noprof(struct kmem_cache *s, gfp_t gfpflags)
{ … }
EXPORT_SYMBOL(…);

void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru,
			   gfp_t gfpflags)
{ … }
EXPORT_SYMBOL(…);

/**
 * kmem_cache_alloc_node - Allocate an object on the specified node
 * @s: The cache to allocate from.
 * @gfpflags: See kmalloc().
 * @node: node number of the target node.
 *
 * Identical to kmem_cache_alloc but it will allocate memory on the given
 * node, which can improve the performance for cpu bound structures.
 *
 * Fallback to other node is possible if __GFP_THISNODE is not set.
 *
 * Return: pointer to the new object or %NULL in case of error
 */
void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t gfpflags, int node)
{ … }
EXPORT_SYMBOL(…);

/*
 * To avoid unnecessary overhead, we pass through large allocation requests
 * directly to the page allocator. We use __GFP_COMP, because we will need to
 * know the allocation order to free the pages properly in kfree.
 */
static void *___kmalloc_large_node(size_t size, gfp_t flags, int node)
{ … }

void *__kmalloc_large_noprof(size_t size, gfp_t flags)
{ … }
EXPORT_SYMBOL(…);

void *__kmalloc_large_node_noprof(size_t size, gfp_t flags, int node)
{ … }
EXPORT_SYMBOL(…);

static __always_inline
void *__do_kmalloc_node(size_t size, kmem_buckets *b, gfp_t flags, int node,
			unsigned long caller)
{ … }
void *__kmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node)
{ … }
EXPORT_SYMBOL(…);

void *__kmalloc_noprof(size_t size, gfp_t flags)
{ … }
EXPORT_SYMBOL(…);

void *__kmalloc_node_track_caller_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags,
					 int node, unsigned long caller)
{ … }
EXPORT_SYMBOL(…);

void *__kmalloc_cache_noprof(struct kmem_cache *s, gfp_t gfpflags, size_t size)
{ … }
EXPORT_SYMBOL(…);

void *__kmalloc_cache_node_noprof(struct kmem_cache *s, gfp_t gfpflags,
				  int node, size_t size)
{ … }
EXPORT_SYMBOL(…);

static noinline void free_to_partial_list(
	struct kmem_cache *s, struct slab *slab,
	void *head, void *tail, int bulk_cnt,
	unsigned long addr)
{ … }

/*
 * Slow path handling. This may still be called frequently since objects
 * have a longer lifetime than the cpu slabs in most processing loads.
 *
 * So we still attempt to reduce cache line usage. Just take the slab
 * lock and free the item. If there is no additional partial slab
 * handling required then we can return immediately.
 */
static void __slab_free(struct kmem_cache *s, struct slab *slab,
			void *head, void *tail, int cnt,
			unsigned long addr)

{ … }

#ifndef CONFIG_SLUB_TINY
/*
 * Fastpath with forced inlining to produce a kfree and kmem_cache_free that
 * can perform fastpath freeing without additional function calls.
 *
 * The fastpath is only possible if we are freeing to the current cpu slab
 * of this processor. This typically the case if we have just allocated
 * the item before.
 *
 * If fastpath is not possible then fall back to __slab_free where we deal
 * with all sorts of special processing.
 *
 * Bulk free of a freelist with several objects (all pointing to the
 * same slab) possible by specifying head and tail ptr, plus objects
 * count (cnt). Bulk free indicated by tail pointer being set.
 */
static __always_inline void do_slab_free(struct kmem_cache *s,
				struct slab *slab, void *head, void *tail,
				int cnt, unsigned long addr)
{
	struct kmem_cache_cpu *c;
	unsigned long tid;
	void **freelist;

redo:
	/*
	 * Determine the currently cpus per cpu slab.
	 * The cpu may change afterward. However that does not matter since
	 * data is retrieved via this pointer. If we are on the same cpu
	 * during the cmpxchg then the free will succeed.
	 */
	c = raw_cpu_ptr(s->cpu_slab);
	tid = READ_ONCE(c->tid);

	/* Same with comment on barrier() in __slab_alloc_node() */
	barrier();

	if (unlikely(slab != c->slab)) {
		__slab_free(s, slab, head, tail, cnt, addr);
		return;
	}

	if (USE_LOCKLESS_FAST_PATH()) {
		freelist = READ_ONCE(c->freelist);

		set_freepointer(s, tail, freelist);

		if (unlikely(!__update_cpu_freelist_fast(s, freelist, head, tid))) {
			note_cmpxchg_failure("slab_free", s, tid);
			goto redo;
		}
	} else {
		/* Update the free list under the local lock */
		local_lock(&s->cpu_slab->lock);
		c = this_cpu_ptr(s->cpu_slab);
		if (unlikely(slab != c->slab)) {
			local_unlock(&s->cpu_slab->lock);
			goto redo;
		}
		tid = c->tid;
		freelist = c->freelist;

		set_freepointer(s, tail, freelist);
		c->freelist = head;
		c->tid = next_tid(tid);

		local_unlock(&s->cpu_slab->lock);
	}
	stat_add(s, FREE_FASTPATH, cnt);
}
#else /* CONFIG_SLUB_TINY */
static void do_slab_free(struct kmem_cache *s,
				struct slab *slab, void *head, void *tail,
				int cnt, unsigned long addr)
{ … }
#endif /* CONFIG_SLUB_TINY */

static __fastpath_inline
void slab_free(struct kmem_cache *s, struct slab *slab, void *object,
	       unsigned long addr)
{ … }

#ifdef CONFIG_MEMCG
/* Do not inline the rare memcg charging failed path into the allocation path */
static noinline
void memcg_alloc_abort_single(struct kmem_cache *s, void *object)
{ … }
#endif

static __fastpath_inline
void slab_free_bulk(struct kmem_cache *s, struct slab *slab, void *head,
		    void *tail, void **p, int cnt, unsigned long addr)
{ … }

#ifdef CONFIG_KASAN_GENERIC
void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr)
{
	do_slab_free(cache, virt_to_slab(x), x, x, 1, addr);
}
#endif

static inline struct kmem_cache *virt_to_cache(const void *obj)
{ … }

static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
{ … }

/**
 * kmem_cache_free - Deallocate an object
 * @s: The cache the allocation was from.
 * @x: The previously allocated object.
 *
 * Free an object which was previously allocated from this
 * cache.
 */
void kmem_cache_free(struct kmem_cache *s, void *x)
{ … }
EXPORT_SYMBOL(…);

static void free_large_kmalloc(struct folio *folio, void *object)
{ … }

/**
 * kfree - free previously allocated memory
 * @object: pointer returned by kmalloc() or kmem_cache_alloc()
 *
 * If @object is NULL, no operation is performed.
 */
void kfree(const void *object)
{ … }
EXPORT_SYMBOL(…);

struct detached_freelist { … };

/*
 * This function progressively scans the array with free objects (with
 * a limited look ahead) and extract objects belonging to the same
 * slab.  It builds a detached freelist directly within the given
 * slab/objects.  This can happen without any need for
 * synchronization, because the objects are owned by running process.
 * The freelist is build up as a single linked list in the objects.
 * The idea is, that this detached freelist can then be bulk
 * transferred to the real freelist(s), but only requiring a single
 * synchronization primitive.  Look ahead in the array is limited due
 * to performance reasons.
 */
static inline
int build_detached_freelist(struct kmem_cache *s, size_t size,
			    void **p, struct detached_freelist *df)
{ … }

/*
 * Internal bulk free of objects that were not initialised by the post alloc
 * hooks and thus should not be processed by the free hooks
 */
static void __kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
{ … }

/* Note that interrupts must be enabled when calling this function. */
void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
{ … }
EXPORT_SYMBOL(…);

#ifndef CONFIG_SLUB_TINY
static inline
int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
			    void **p)
{
	struct kmem_cache_cpu *c;
	unsigned long irqflags;
	int i;

	/*
	 * Drain objects in the per cpu slab, while disabling local
	 * IRQs, which protects against PREEMPT and interrupts
	 * handlers invoking normal fastpath.
	 */
	c = slub_get_cpu_ptr(s->cpu_slab);
	local_lock_irqsave(&s->cpu_slab->lock, irqflags);

	for (i = 0; i < size; i++) {
		void *object = kfence_alloc(s, s->object_size, flags);

		if (unlikely(object)) {
			p[i] = object;
			continue;
		}

		object = c->freelist;
		if (unlikely(!object)) {
			/*
			 * We may have removed an object from c->freelist using
			 * the fastpath in the previous iteration; in that case,
			 * c->tid has not been bumped yet.
			 * Since ___slab_alloc() may reenable interrupts while
			 * allocating memory, we should bump c->tid now.
			 */
			c->tid = next_tid(c->tid);

			local_unlock_irqrestore(&s->cpu_slab->lock, irqflags);

			/*
			 * Invoking slow path likely have side-effect
			 * of re-populating per CPU c->freelist
			 */
			p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE,
					    _RET_IP_, c, s->object_size);
			if (unlikely(!p[i]))
				goto error;

			c = this_cpu_ptr(s->cpu_slab);
			maybe_wipe_obj_freeptr(s, p[i]);

			local_lock_irqsave(&s->cpu_slab->lock, irqflags);

			continue; /* goto for-loop */
		}
		c->freelist = get_freepointer(s, object);
		p[i] = object;
		maybe_wipe_obj_freeptr(s, p[i]);
		stat(s, ALLOC_FASTPATH);
	}
	c->tid = next_tid(c->tid);
	local_unlock_irqrestore(&s->cpu_slab->lock, irqflags);
	slub_put_cpu_ptr(s->cpu_slab);

	return i;

error:
	slub_put_cpu_ptr(s->cpu_slab);
	__kmem_cache_free_bulk(s, i, p);
	return 0;

}
#else /* CONFIG_SLUB_TINY */
static int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags,
				   size_t size, void **p)
{ … }
#endif /* CONFIG_SLUB_TINY */

/* Note that interrupts must be enabled when calling this function. */
int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size,
				 void **p)
{ … }
EXPORT_SYMBOL(…);


/*
 * Object placement in a slab is made very easy because we always start at
 * offset 0. If we tune the size of the object to the alignment then we can
 * get the required alignment by putting one properly sized object after
 * another.
 *
 * Notice that the allocation order determines the sizes of the per cpu
 * caches. Each processor has always one slab available for allocations.
 * Increasing the allocation order reduces the number of times that slabs
 * must be moved on and off the partial lists and is therefore a factor in
 * locking overhead.
 */

/*
 * Minimum / Maximum order of slab pages. This influences locking overhead
 * and slab fragmentation. A higher order reduces the number of partial slabs
 * and increases the number of allocations possible without having to
 * take the list_lock.
 */
static unsigned int slub_min_order;
static unsigned int slub_max_order = …;
static unsigned int slub_min_objects;

/*
 * Calculate the order of allocation given an slab object size.
 *
 * The order of allocation has significant impact on performance and other
 * system components. Generally order 0 allocations should be preferred since
 * order 0 does not cause fragmentation in the page allocator. Larger objects
 * be problematic to put into order 0 slabs because there may be too much
 * unused space left. We go to a higher order if more than 1/16th of the slab
 * would be wasted.
 *
 * In order to reach satisfactory performance we must ensure that a minimum
 * number of objects is in one slab. Otherwise we may generate too much
 * activity on the partial lists which requires taking the list_lock. This is
 * less a concern for large slabs though which are rarely used.
 *
 * slab_max_order specifies the order where we begin to stop considering the
 * number of objects in a slab as critical. If we reach slab_max_order then
 * we try to keep the page order as low as possible. So we accept more waste
 * of space in favor of a small page order.
 *
 * Higher order allocations also allow the placement of more objects in a
 * slab and thereby reduce object handling overhead. If the user has
 * requested a higher minimum order then we start with that one instead of
 * the smallest order which will fit the object.
 */
static inline unsigned int calc_slab_order(unsigned int size,
		unsigned int min_order, unsigned int max_order,
		unsigned int fract_leftover)
{ … }

static inline int calculate_order(unsigned int size)
{ … }

static void
init_kmem_cache_node(struct kmem_cache_node *n)
{ … }

#ifndef CONFIG_SLUB_TINY
static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
{
	BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
			NR_KMALLOC_TYPES * KMALLOC_SHIFT_HIGH *
			sizeof(struct kmem_cache_cpu));

	/*
	 * Must align to double word boundary for the double cmpxchg
	 * instructions to work; see __pcpu_double_call_return_bool().
	 */
	s->cpu_slab = __alloc_percpu(sizeof(struct kmem_cache_cpu),
				     2 * sizeof(void *));

	if (!s->cpu_slab)
		return 0;

	init_kmem_cache_cpus(s);

	return 1;
}
#else
static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
{ … }
#endif /* CONFIG_SLUB_TINY */

static struct kmem_cache *kmem_cache_node;

/*
 * No kmalloc_node yet so do it by hand. We know that this is the first
 * slab on the node for this slabcache. There are no concurrent accesses
 * possible.
 *
 * Note that this function only works on the kmem_cache_node
 * when allocating for the kmem_cache_node. This is used for bootstrapping
 * memory on a fresh node that has no slab structures yet.
 */
static void early_kmem_cache_node_alloc(int node)
{ … }

static void free_kmem_cache_nodes(struct kmem_cache *s)
{ … }

void __kmem_cache_release(struct kmem_cache *s)
{ … }

static int init_kmem_cache_nodes(struct kmem_cache *s)
{ … }

static void set_cpu_partial(struct kmem_cache *s)
{ … }

/*
 * calculate_sizes() determines the order and the distribution of data within
 * a slab object.
 */
static int calculate_sizes(struct kmem_cache *s)
{ … }

static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags)
{ … }

static void list_slab_objects(struct kmem_cache *s, struct slab *slab,
			      const char *text)
{ … }

/*
 * Attempt to free all partial slabs on a node.
 * This is called from __kmem_cache_shutdown(). We must take list_lock
 * because sysfs file might still access partial list after the shutdowning.
 */
static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
{ … }

bool __kmem_cache_empty(struct kmem_cache *s)
{ … }

/*
 * Release all resources used by a slab cache.
 */
int __kmem_cache_shutdown(struct kmem_cache *s)
{ … }

#ifdef CONFIG_PRINTK
void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
{ … }
#endif

/********************************************************************
 *		Kmalloc subsystem
 *******************************************************************/

static int __init setup_slub_min_order(char *str)
{ … }

__setup(…);
__setup_param(…);


static int __init setup_slub_max_order(char *str)
{ … }

__setup(…);
__setup_param(…);

static int __init setup_slub_min_objects(char *str)
{ … }

__setup(…);
__setup_param(…);

#ifdef CONFIG_HARDENED_USERCOPY
/*
 * Rejects incorrectly sized objects and objects that are to be copied
 * to/from userspace but do not fall entirely within the containing slab
 * cache's usercopy region.
 *
 * Returns NULL if check passes, otherwise const char * to name of cache
 * to indicate an error.
 */
void __check_heap_object(const void *ptr, unsigned long n,
			 const struct slab *slab, bool to_user)
{ … }
#endif /* CONFIG_HARDENED_USERCOPY */

#define SHRINK_PROMOTE_MAX …

/*
 * kmem_cache_shrink discards empty slabs and promotes the slabs filled
 * up most to the head of the partial lists. New allocations will then
 * fill those up and thus they can be removed from the partial lists.
 *
 * The slabs with the least items are placed last. This results in them
 * being allocated from last increasing the chance that the last objects
 * are freed in them.
 */
static int __kmem_cache_do_shrink(struct kmem_cache *s)
{ … }

int __kmem_cache_shrink(struct kmem_cache *s)
{ … }

static int slab_mem_going_offline_callback(void *arg)
{ … }

static void slab_mem_offline_callback(void *arg)
{ … }

static int slab_mem_going_online_callback(void *arg)
{ … }

static int slab_memory_callback(struct notifier_block *self,
				unsigned long action, void *arg)
{ … }

/********************************************************************
 *			Basic setup of slabs
 *******************************************************************/

/*
 * Used for early kmem_cache structures that were allocated using
 * the page allocator. Allocate them properly then fix up the pointers
 * that may be pointing to the wrong kmem_cache structure.
 */

static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache)
{ … }

void __init kmem_cache_init(void)
{ … }

void __init kmem_cache_init_late(void)
{ … }

struct kmem_cache *
__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
		   slab_flags_t flags, void (*ctor)(void *))
{ … }

int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags)
{ … }

#ifdef SLAB_SUPPORTS_SYSFS
static int count_inuse(struct slab *slab)
{
	return slab->inuse;
}

static int count_total(struct slab *slab)
{
	return slab->objects;
}
#endif

#ifdef CONFIG_SLUB_DEBUG
static void validate_slab(struct kmem_cache *s, struct slab *slab,
			  unsigned long *obj_map)
{
	void *p;
	void *addr = slab_address(slab);

	if (!check_slab(s, slab) || !on_freelist(s, slab, NULL))
		return;

	/* Now we know that a valid freelist exists */
	__fill_map(obj_map, s, slab);
	for_each_object(p, s, addr, slab->objects) {
		u8 val = test_bit(__obj_to_index(s, addr, p), obj_map) ?
			 SLUB_RED_INACTIVE : SLUB_RED_ACTIVE;

		if (!check_object(s, slab, p, val))
			break;
	}
}

static int validate_slab_node(struct kmem_cache *s,
		struct kmem_cache_node *n, unsigned long *obj_map)
{
	unsigned long count = 0;
	struct slab *slab;
	unsigned long flags;

	spin_lock_irqsave(&n->list_lock, flags);

	list_for_each_entry(slab, &n->partial, slab_list) {
		validate_slab(s, slab, obj_map);
		count++;
	}
	if (count != n->nr_partial) {
		pr_err("SLUB %s: %ld partial slabs counted but counter=%ld\n",
		       s->name, count, n->nr_partial);
		slab_add_kunit_errors();
	}

	if (!(s->flags & SLAB_STORE_USER))
		goto out;

	list_for_each_entry(slab, &n->full, slab_list) {
		validate_slab(s, slab, obj_map);
		count++;
	}
	if (count != node_nr_slabs(n)) {
		pr_err("SLUB: %s %ld slabs counted but counter=%ld\n",
		       s->name, count, node_nr_slabs(n));
		slab_add_kunit_errors();
	}

out:
	spin_unlock_irqrestore(&n->list_lock, flags);
	return count;
}

long validate_slab_cache(struct kmem_cache *s)
{
	int node;
	unsigned long count = 0;
	struct kmem_cache_node *n;
	unsigned long *obj_map;

	obj_map = bitmap_alloc(oo_objects(s->oo), GFP_KERNEL);
	if (!obj_map)
		return -ENOMEM;

	flush_all(s);
	for_each_kmem_cache_node(s, node, n)
		count += validate_slab_node(s, n, obj_map);

	bitmap_free(obj_map);

	return count;
}
EXPORT_SYMBOL(validate_slab_cache);

#ifdef CONFIG_DEBUG_FS
/*
 * Generate lists of code addresses where slabcache objects are allocated
 * and freed.
 */

struct location {
	depot_stack_handle_t handle;
	unsigned long count;
	unsigned long addr;
	unsigned long waste;
	long long sum_time;
	long min_time;
	long max_time;
	long min_pid;
	long max_pid;
	DECLARE_BITMAP(cpus, NR_CPUS);
	nodemask_t nodes;
};

struct loc_track {
	unsigned long max;
	unsigned long count;
	struct location *loc;
	loff_t idx;
};

static struct dentry *slab_debugfs_root;

static void free_loc_track(struct loc_track *t)
{
	if (t->max)
		free_pages((unsigned long)t->loc,
			get_order(sizeof(struct location) * t->max));
}

static int alloc_loc_track(struct loc_track *t, unsigned long max, gfp_t flags)
{
	struct location *l;
	int order;

	order = get_order(sizeof(struct location) * max);

	l = (void *)__get_free_pages(flags, order);
	if (!l)
		return 0;

	if (t->count) {
		memcpy(l, t->loc, sizeof(struct location) * t->count);
		free_loc_track(t);
	}
	t->max = max;
	t->loc = l;
	return 1;
}

static int add_location(struct loc_track *t, struct kmem_cache *s,
				const struct track *track,
				unsigned int orig_size)
{
	long start, end, pos;
	struct location *l;
	unsigned long caddr, chandle, cwaste;
	unsigned long age = jiffies - track->when;
	depot_stack_handle_t handle = 0;
	unsigned int waste = s->object_size - orig_size;

#ifdef CONFIG_STACKDEPOT
	handle = READ_ONCE(track->handle);
#endif
	start = -1;
	end = t->count;

	for ( ; ; ) {
		pos = start + (end - start + 1) / 2;

		/*
		 * There is nothing at "end". If we end up there
		 * we need to add something to before end.
		 */
		if (pos == end)
			break;

		l = &t->loc[pos];
		caddr = l->addr;
		chandle = l->handle;
		cwaste = l->waste;
		if ((track->addr == caddr) && (handle == chandle) &&
			(waste == cwaste)) {

			l->count++;
			if (track->when) {
				l->sum_time += age;
				if (age < l->min_time)
					l->min_time = age;
				if (age > l->max_time)
					l->max_time = age;

				if (track->pid < l->min_pid)
					l->min_pid = track->pid;
				if (track->pid > l->max_pid)
					l->max_pid = track->pid;

				cpumask_set_cpu(track->cpu,
						to_cpumask(l->cpus));
			}
			node_set(page_to_nid(virt_to_page(track)), l->nodes);
			return 1;
		}

		if (track->addr < caddr)
			end = pos;
		else if (track->addr == caddr && handle < chandle)
			end = pos;
		else if (track->addr == caddr && handle == chandle &&
				waste < cwaste)
			end = pos;
		else
			start = pos;
	}

	/*
	 * Not found. Insert new tracking element.
	 */
	if (t->count >= t->max && !alloc_loc_track(t, 2 * t->max, GFP_ATOMIC))
		return 0;

	l = t->loc + pos;
	if (pos < t->count)
		memmove(l + 1, l,
			(t->count - pos) * sizeof(struct location));
	t->count++;
	l->count = 1;
	l->addr = track->addr;
	l->sum_time = age;
	l->min_time = age;
	l->max_time = age;
	l->min_pid = track->pid;
	l->max_pid = track->pid;
	l->handle = handle;
	l->waste = waste;
	cpumask_clear(to_cpumask(l->cpus));
	cpumask_set_cpu(track->cpu, to_cpumask(l->cpus));
	nodes_clear(l->nodes);
	node_set(page_to_nid(virt_to_page(track)), l->nodes);
	return 1;
}

static void process_slab(struct loc_track *t, struct kmem_cache *s,
		struct slab *slab, enum track_item alloc,
		unsigned long *obj_map)
{
	void *addr = slab_address(slab);
	bool is_alloc = (alloc == TRACK_ALLOC);
	void *p;

	__fill_map(obj_map, s, slab);

	for_each_object(p, s, addr, slab->objects)
		if (!test_bit(__obj_to_index(s, addr, p), obj_map))
			add_location(t, s, get_track(s, p, alloc),
				     is_alloc ? get_orig_size(s, p) :
						s->object_size);
}
#endif  /* CONFIG_DEBUG_FS   */
#endif	/* CONFIG_SLUB_DEBUG */

#ifdef SLAB_SUPPORTS_SYSFS
enum slab_stat_type {
	SL_ALL,			/* All slabs */
	SL_PARTIAL,		/* Only partially allocated slabs */
	SL_CPU,			/* Only slabs used for cpu caches */
	SL_OBJECTS,		/* Determine allocated objects not slabs */
	SL_TOTAL		/* Determine object capacity not slabs */
};

#define SO_ALL …
#define SO_PARTIAL …
#define SO_CPU …
#define SO_OBJECTS …
#define SO_TOTAL …

static ssize_t show_slab_objects(struct kmem_cache *s,
				 char *buf, unsigned long flags)
{
	unsigned long total = 0;
	int node;
	int x;
	unsigned long *nodes;
	int len = 0;

	nodes = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL);
	if (!nodes)
		return -ENOMEM;

	if (flags & SO_CPU) {
		int cpu;

		for_each_possible_cpu(cpu) {
			struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab,
							       cpu);
			int node;
			struct slab *slab;

			slab = READ_ONCE(c->slab);
			if (!slab)
				continue;

			node = slab_nid(slab);
			if (flags & SO_TOTAL)
				x = slab->objects;
			else if (flags & SO_OBJECTS)
				x = slab->inuse;
			else
				x = 1;

			total += x;
			nodes[node] += x;

#ifdef CONFIG_SLUB_CPU_PARTIAL
			slab = slub_percpu_partial_read_once(c);
			if (slab) {
				node = slab_nid(slab);
				if (flags & SO_TOTAL)
					WARN_ON_ONCE(1);
				else if (flags & SO_OBJECTS)
					WARN_ON_ONCE(1);
				else
					x = data_race(slab->slabs);
				total += x;
				nodes[node] += x;
			}
#endif
		}
	}

	/*
	 * It is impossible to take "mem_hotplug_lock" here with "kernfs_mutex"
	 * already held which will conflict with an existing lock order:
	 *
	 * mem_hotplug_lock->slab_mutex->kernfs_mutex
	 *
	 * We don't really need mem_hotplug_lock (to hold off
	 * slab_mem_going_offline_callback) here because slab's memory hot
	 * unplug code doesn't destroy the kmem_cache->node[] data.
	 */

#ifdef CONFIG_SLUB_DEBUG
	if (flags & SO_ALL) {
		struct kmem_cache_node *n;

		for_each_kmem_cache_node(s, node, n) {

			if (flags & SO_TOTAL)
				x = node_nr_objs(n);
			else if (flags & SO_OBJECTS)
				x = node_nr_objs(n) - count_partial(n, count_free);
			else
				x = node_nr_slabs(n);
			total += x;
			nodes[node] += x;
		}

	} else
#endif
	if (flags & SO_PARTIAL) {
		struct kmem_cache_node *n;

		for_each_kmem_cache_node(s, node, n) {
			if (flags & SO_TOTAL)
				x = count_partial(n, count_total);
			else if (flags & SO_OBJECTS)
				x = count_partial(n, count_inuse);
			else
				x = n->nr_partial;
			total += x;
			nodes[node] += x;
		}
	}

	len += sysfs_emit_at(buf, len, "%lu", total);
#ifdef CONFIG_NUMA
	for (node = 0; node < nr_node_ids; node++) {
		if (nodes[node])
			len += sysfs_emit_at(buf, len, " N%d=%lu",
					     node, nodes[node]);
	}
#endif
	len += sysfs_emit_at(buf, len, "\n");
	kfree(nodes);

	return len;
}

#define to_slab_attr …
#define to_slab …

struct slab_attribute {
	struct attribute attr;
	ssize_t (*show)(struct kmem_cache *s, char *buf);
	ssize_t (*store)(struct kmem_cache *s, const char *x, size_t count);
};

#define SLAB_ATTR_RO …

#define SLAB_ATTR …

static ssize_t slab_size_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%u\n", s->size);
}
SLAB_ATTR_RO(slab_size);

static ssize_t align_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%u\n", s->align);
}
SLAB_ATTR_RO(align);

static ssize_t object_size_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%u\n", s->object_size);
}
SLAB_ATTR_RO(object_size);

static ssize_t objs_per_slab_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%u\n", oo_objects(s->oo));
}
SLAB_ATTR_RO(objs_per_slab);

static ssize_t order_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%u\n", oo_order(s->oo));
}
SLAB_ATTR_RO(order);

static ssize_t min_partial_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%lu\n", s->min_partial);
}

static ssize_t min_partial_store(struct kmem_cache *s, const char *buf,
				 size_t length)
{
	unsigned long min;
	int err;

	err = kstrtoul(buf, 10, &min);
	if (err)
		return err;

	s->min_partial = min;
	return length;
}
SLAB_ATTR(min_partial);

static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf)
{
	unsigned int nr_partial = 0;
#ifdef CONFIG_SLUB_CPU_PARTIAL
	nr_partial = s->cpu_partial;
#endif

	return sysfs_emit(buf, "%u\n", nr_partial);
}

static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf,
				 size_t length)
{
	unsigned int objects;
	int err;

	err = kstrtouint(buf, 10, &objects);
	if (err)
		return err;
	if (objects && !kmem_cache_has_cpu_partial(s))
		return -EINVAL;

	slub_set_cpu_partial(s, objects);
	flush_all(s);
	return length;
}
SLAB_ATTR(cpu_partial);

static ssize_t ctor_show(struct kmem_cache *s, char *buf)
{
	if (!s->ctor)
		return 0;
	return sysfs_emit(buf, "%pS\n", s->ctor);
}
SLAB_ATTR_RO(ctor);

static ssize_t aliases_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", s->refcount < 0 ? 0 : s->refcount - 1);
}
SLAB_ATTR_RO(aliases);

static ssize_t partial_show(struct kmem_cache *s, char *buf)
{
	return show_slab_objects(s, buf, SO_PARTIAL);
}
SLAB_ATTR_RO(partial);

static ssize_t cpu_slabs_show(struct kmem_cache *s, char *buf)
{
	return show_slab_objects(s, buf, SO_CPU);
}
SLAB_ATTR_RO(cpu_slabs);

static ssize_t objects_partial_show(struct kmem_cache *s, char *buf)
{
	return show_slab_objects(s, buf, SO_PARTIAL|SO_OBJECTS);
}
SLAB_ATTR_RO(objects_partial);

static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf)
{
	int objects = 0;
	int slabs = 0;
	int cpu __maybe_unused;
	int len = 0;

#ifdef CONFIG_SLUB_CPU_PARTIAL
	for_each_online_cpu(cpu) {
		struct slab *slab;

		slab = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu));

		if (slab)
			slabs += data_race(slab->slabs);
	}
#endif

	/* Approximate half-full slabs, see slub_set_cpu_partial() */
	objects = (slabs * oo_objects(s->oo)) / 2;
	len += sysfs_emit_at(buf, len, "%d(%d)", objects, slabs);

#ifdef CONFIG_SLUB_CPU_PARTIAL
	for_each_online_cpu(cpu) {
		struct slab *slab;

		slab = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu));
		if (slab) {
			slabs = data_race(slab->slabs);
			objects = (slabs * oo_objects(s->oo)) / 2;
			len += sysfs_emit_at(buf, len, " C%d=%d(%d)",
					     cpu, objects, slabs);
		}
	}
#endif
	len += sysfs_emit_at(buf, len, "\n");

	return len;
}
SLAB_ATTR_RO(slabs_cpu_partial);

static ssize_t reclaim_account_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_RECLAIM_ACCOUNT));
}
SLAB_ATTR_RO(reclaim_account);

static ssize_t hwcache_align_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_HWCACHE_ALIGN));
}
SLAB_ATTR_RO(hwcache_align);

#ifdef CONFIG_ZONE_DMA
static ssize_t cache_dma_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_CACHE_DMA));
}
SLAB_ATTR_RO(cache_dma);
#endif

#ifdef CONFIG_HARDENED_USERCOPY
static ssize_t usersize_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%u\n", s->usersize);
}
SLAB_ATTR_RO(usersize);
#endif

static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_TYPESAFE_BY_RCU));
}
SLAB_ATTR_RO(destroy_by_rcu);

#ifdef CONFIG_SLUB_DEBUG
static ssize_t slabs_show(struct kmem_cache *s, char *buf)
{
	return show_slab_objects(s, buf, SO_ALL);
}
SLAB_ATTR_RO(slabs);

static ssize_t total_objects_show(struct kmem_cache *s, char *buf)
{
	return show_slab_objects(s, buf, SO_ALL|SO_TOTAL);
}
SLAB_ATTR_RO(total_objects);

static ssize_t objects_show(struct kmem_cache *s, char *buf)
{
	return show_slab_objects(s, buf, SO_ALL|SO_OBJECTS);
}
SLAB_ATTR_RO(objects);

static ssize_t sanity_checks_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_CONSISTENCY_CHECKS));
}
SLAB_ATTR_RO(sanity_checks);

static ssize_t trace_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_TRACE));
}
SLAB_ATTR_RO(trace);

static ssize_t red_zone_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_RED_ZONE));
}

SLAB_ATTR_RO(red_zone);

static ssize_t poison_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_POISON));
}

SLAB_ATTR_RO(poison);

static ssize_t store_user_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_STORE_USER));
}

SLAB_ATTR_RO(store_user);

static ssize_t validate_show(struct kmem_cache *s, char *buf)
{
	return 0;
}

static ssize_t validate_store(struct kmem_cache *s,
			const char *buf, size_t length)
{
	int ret = -EINVAL;

	if (buf[0] == '1' && kmem_cache_debug(s)) {
		ret = validate_slab_cache(s);
		if (ret >= 0)
			ret = length;
	}
	return ret;
}
SLAB_ATTR(validate);

#endif /* CONFIG_SLUB_DEBUG */

#ifdef CONFIG_FAILSLAB
static ssize_t failslab_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_FAILSLAB));
}

static ssize_t failslab_store(struct kmem_cache *s, const char *buf,
				size_t length)
{
	if (s->refcount > 1)
		return -EINVAL;

	if (buf[0] == '1')
		WRITE_ONCE(s->flags, s->flags | SLAB_FAILSLAB);
	else
		WRITE_ONCE(s->flags, s->flags & ~SLAB_FAILSLAB);

	return length;
}
SLAB_ATTR(failslab);
#endif

static ssize_t shrink_show(struct kmem_cache *s, char *buf)
{
	return 0;
}

static ssize_t shrink_store(struct kmem_cache *s,
			const char *buf, size_t length)
{
	if (buf[0] == '1')
		kmem_cache_shrink(s);
	else
		return -EINVAL;
	return length;
}
SLAB_ATTR(shrink);

#ifdef CONFIG_NUMA
static ssize_t remote_node_defrag_ratio_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%u\n", s->remote_node_defrag_ratio / 10);
}

static ssize_t remote_node_defrag_ratio_store(struct kmem_cache *s,
				const char *buf, size_t length)
{
	unsigned int ratio;
	int err;

	err = kstrtouint(buf, 10, &ratio);
	if (err)
		return err;
	if (ratio > 100)
		return -ERANGE;

	s->remote_node_defrag_ratio = ratio * 10;

	return length;
}
SLAB_ATTR(remote_node_defrag_ratio);
#endif

#ifdef CONFIG_SLUB_STATS
static int show_stat(struct kmem_cache *s, char *buf, enum stat_item si)
{
	unsigned long sum  = 0;
	int cpu;
	int len = 0;
	int *data = kmalloc_array(nr_cpu_ids, sizeof(int), GFP_KERNEL);

	if (!data)
		return -ENOMEM;

	for_each_online_cpu(cpu) {
		unsigned x = per_cpu_ptr(s->cpu_slab, cpu)->stat[si];

		data[cpu] = x;
		sum += x;
	}

	len += sysfs_emit_at(buf, len, "%lu", sum);

#ifdef CONFIG_SMP
	for_each_online_cpu(cpu) {
		if (data[cpu])
			len += sysfs_emit_at(buf, len, " C%d=%u",
					     cpu, data[cpu]);
	}
#endif
	kfree(data);
	len += sysfs_emit_at(buf, len, "\n");

	return len;
}

static void clear_stat(struct kmem_cache *s, enum stat_item si)
{
	int cpu;

	for_each_online_cpu(cpu)
		per_cpu_ptr(s->cpu_slab, cpu)->stat[si] = 0;
}

#define STAT_ATTR …						\

STAT_ATTR(ALLOC_FASTPATH, alloc_fastpath);
STAT_ATTR(ALLOC_SLOWPATH, alloc_slowpath);
STAT_ATTR(FREE_FASTPATH, free_fastpath);
STAT_ATTR(FREE_SLOWPATH, free_slowpath);
STAT_ATTR(FREE_FROZEN, free_frozen);
STAT_ATTR(FREE_ADD_PARTIAL, free_add_partial);
STAT_ATTR(FREE_REMOVE_PARTIAL, free_remove_partial);
STAT_ATTR(ALLOC_FROM_PARTIAL, alloc_from_partial);
STAT_ATTR(ALLOC_SLAB, alloc_slab);
STAT_ATTR(ALLOC_REFILL, alloc_refill);
STAT_ATTR(ALLOC_NODE_MISMATCH, alloc_node_mismatch);
STAT_ATTR(FREE_SLAB, free_slab);
STAT_ATTR(CPUSLAB_FLUSH, cpuslab_flush);
STAT_ATTR(DEACTIVATE_FULL, deactivate_full);
STAT_ATTR(DEACTIVATE_EMPTY, deactivate_empty);
STAT_ATTR(DEACTIVATE_TO_HEAD, deactivate_to_head);
STAT_ATTR(DEACTIVATE_TO_TAIL, deactivate_to_tail);
STAT_ATTR(DEACTIVATE_REMOTE_FREES, deactivate_remote_frees);
STAT_ATTR(DEACTIVATE_BYPASS, deactivate_bypass);
STAT_ATTR(ORDER_FALLBACK, order_fallback);
STAT_ATTR(CMPXCHG_DOUBLE_CPU_FAIL, cmpxchg_double_cpu_fail);
STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail);
STAT_ATTR(CPU_PARTIAL_ALLOC, cpu_partial_alloc);
STAT_ATTR(CPU_PARTIAL_FREE, cpu_partial_free);
STAT_ATTR(CPU_PARTIAL_NODE, cpu_partial_node);
STAT_ATTR(CPU_PARTIAL_DRAIN, cpu_partial_drain);
#endif	/* CONFIG_SLUB_STATS */

#ifdef CONFIG_KFENCE
static ssize_t skip_kfence_show(struct kmem_cache *s, char *buf)
{
	return sysfs_emit(buf, "%d\n", !!(s->flags & SLAB_SKIP_KFENCE));
}

static ssize_t skip_kfence_store(struct kmem_cache *s,
			const char *buf, size_t length)
{
	int ret = length;

	if (buf[0] == '0')
		s->flags &= ~SLAB_SKIP_KFENCE;
	else if (buf[0] == '1')
		s->flags |= SLAB_SKIP_KFENCE;
	else
		ret = -EINVAL;

	return ret;
}
SLAB_ATTR(skip_kfence);
#endif

static struct attribute *slab_attrs[] = {
	&slab_size_attr.attr,
	&object_size_attr.attr,
	&objs_per_slab_attr.attr,
	&order_attr.attr,
	&min_partial_attr.attr,
	&cpu_partial_attr.attr,
	&objects_partial_attr.attr,
	&partial_attr.attr,
	&cpu_slabs_attr.attr,
	&ctor_attr.attr,
	&aliases_attr.attr,
	&align_attr.attr,
	&hwcache_align_attr.attr,
	&reclaim_account_attr.attr,
	&destroy_by_rcu_attr.attr,
	&shrink_attr.attr,
	&slabs_cpu_partial_attr.attr,
#ifdef CONFIG_SLUB_DEBUG
	&total_objects_attr.attr,
	&objects_attr.attr,
	&slabs_attr.attr,
	&sanity_checks_attr.attr,
	&trace_attr.attr,
	&red_zone_attr.attr,
	&poison_attr.attr,
	&store_user_attr.attr,
	&validate_attr.attr,
#endif
#ifdef CONFIG_ZONE_DMA
	&cache_dma_attr.attr,
#endif
#ifdef CONFIG_NUMA
	&remote_node_defrag_ratio_attr.attr,
#endif
#ifdef CONFIG_SLUB_STATS
	&alloc_fastpath_attr.attr,
	&alloc_slowpath_attr.attr,
	&free_fastpath_attr.attr,
	&free_slowpath_attr.attr,
	&free_frozen_attr.attr,
	&free_add_partial_attr.attr,
	&free_remove_partial_attr.attr,
	&alloc_from_partial_attr.attr,
	&alloc_slab_attr.attr,
	&alloc_refill_attr.attr,
	&alloc_node_mismatch_attr.attr,
	&free_slab_attr.attr,
	&cpuslab_flush_attr.attr,
	&deactivate_full_attr.attr,
	&deactivate_empty_attr.attr,
	&deactivate_to_head_attr.attr,
	&deactivate_to_tail_attr.attr,
	&deactivate_remote_frees_attr.attr,
	&deactivate_bypass_attr.attr,
	&order_fallback_attr.attr,
	&cmpxchg_double_fail_attr.attr,
	&cmpxchg_double_cpu_fail_attr.attr,
	&cpu_partial_alloc_attr.attr,
	&cpu_partial_free_attr.attr,
	&cpu_partial_node_attr.attr,
	&cpu_partial_drain_attr.attr,
#endif
#ifdef CONFIG_FAILSLAB
	&failslab_attr.attr,
#endif
#ifdef CONFIG_HARDENED_USERCOPY
	&usersize_attr.attr,
#endif
#ifdef CONFIG_KFENCE
	&skip_kfence_attr.attr,
#endif

	NULL
};

static const struct attribute_group slab_attr_group = {
	.attrs = slab_attrs,
};

static ssize_t slab_attr_show(struct kobject *kobj,
				struct attribute *attr,
				char *buf)
{
	struct slab_attribute *attribute;
	struct kmem_cache *s;

	attribute = to_slab_attr(attr);
	s = to_slab(kobj);

	if (!attribute->show)
		return -EIO;

	return attribute->show(s, buf);
}

static ssize_t slab_attr_store(struct kobject *kobj,
				struct attribute *attr,
				const char *buf, size_t len)
{
	struct slab_attribute *attribute;
	struct kmem_cache *s;

	attribute = to_slab_attr(attr);
	s = to_slab(kobj);

	if (!attribute->store)
		return -EIO;

	return attribute->store(s, buf, len);
}

static void kmem_cache_release(struct kobject *k)
{
	slab_kmem_cache_release(to_slab(k));
}

static const struct sysfs_ops slab_sysfs_ops = {
	.show = slab_attr_show,
	.store = slab_attr_store,
};

static const struct kobj_type slab_ktype = {
	.sysfs_ops = &slab_sysfs_ops,
	.release = kmem_cache_release,
};

static struct kset *slab_kset;

static inline struct kset *cache_kset(struct kmem_cache *s)
{
	return slab_kset;
}

#define ID_STR_LENGTH …

/* Create a unique string id for a slab cache:
 *
 * Format	:[flags-]size
 */
static char *create_unique_id(struct kmem_cache *s)
{
	char *name = kmalloc(ID_STR_LENGTH, GFP_KERNEL);
	char *p = name;

	if (!name)
		return ERR_PTR(-ENOMEM);

	*p++ = ':';
	/*
	 * First flags affecting slabcache operations. We will only
	 * get here for aliasable slabs so we do not need to support
	 * too many flags. The flags here must cover all flags that
	 * are matched during merging to guarantee that the id is
	 * unique.
	 */
	if (s->flags & SLAB_CACHE_DMA)
		*p++ = 'd';
	if (s->flags & SLAB_CACHE_DMA32)
		*p++ = 'D';
	if (s->flags & SLAB_RECLAIM_ACCOUNT)
		*p++ = 'a';
	if (s->flags & SLAB_CONSISTENCY_CHECKS)
		*p++ = 'F';
	if (s->flags & SLAB_ACCOUNT)
		*p++ = 'A';
	if (p != name + 1)
		*p++ = '-';
	p += snprintf(p, ID_STR_LENGTH - (p - name), "%07u", s->size);

	if (WARN_ON(p > name + ID_STR_LENGTH - 1)) {
		kfree(name);
		return ERR_PTR(-EINVAL);
	}
	kmsan_unpoison_memory(name, p - name);
	return name;
}

static int sysfs_slab_add(struct kmem_cache *s)
{
	int err;
	const char *name;
	struct kset *kset = cache_kset(s);
	int unmergeable = slab_unmergeable(s);

	if (!unmergeable && disable_higher_order_debug &&
			(slub_debug & DEBUG_METADATA_FLAGS))
		unmergeable = 1;

	if (unmergeable) {
		/*
		 * Slabcache can never be merged so we can use the name proper.
		 * This is typically the case for debug situations. In that
		 * case we can catch duplicate names easily.
		 */
		sysfs_remove_link(&slab_kset->kobj, s->name);
		name = s->name;
	} else {
		/*
		 * Create a unique name for the slab as a target
		 * for the symlinks.
		 */
		name = create_unique_id(s);
		if (IS_ERR(name))
			return PTR_ERR(name);
	}

	s->kobj.kset = kset;
	err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
	if (err)
		goto out;

	err = sysfs_create_group(&s->kobj, &slab_attr_group);
	if (err)
		goto out_del_kobj;

	if (!unmergeable) {
		/* Setup first alias */
		sysfs_slab_alias(s, s->name);
	}
out:
	if (!unmergeable)
		kfree(name);
	return err;
out_del_kobj:
	kobject_del(&s->kobj);
	goto out;
}

void sysfs_slab_unlink(struct kmem_cache *s)
{
	kobject_del(&s->kobj);
}

void sysfs_slab_release(struct kmem_cache *s)
{
	kobject_put(&s->kobj);
}

/*
 * Need to buffer aliases during bootup until sysfs becomes
 * available lest we lose that information.
 */
struct saved_alias {
	struct kmem_cache *s;
	const char *name;
	struct saved_alias *next;
};

static struct saved_alias *alias_list;

static int sysfs_slab_alias(struct kmem_cache *s, const char *name)
{
	struct saved_alias *al;

	if (slab_state == FULL) {
		/*
		 * If we have a leftover link then remove it.
		 */
		sysfs_remove_link(&slab_kset->kobj, name);
		return sysfs_create_link(&slab_kset->kobj, &s->kobj, name);
	}

	al = kmalloc(sizeof(struct saved_alias), GFP_KERNEL);
	if (!al)
		return -ENOMEM;

	al->s = s;
	al->name = name;
	al->next = alias_list;
	alias_list = al;
	kmsan_unpoison_memory(al, sizeof(*al));
	return 0;
}

static int __init slab_sysfs_init(void)
{
	struct kmem_cache *s;
	int err;

	mutex_lock(&slab_mutex);

	slab_kset = kset_create_and_add("slab", NULL, kernel_kobj);
	if (!slab_kset) {
		mutex_unlock(&slab_mutex);
		pr_err("Cannot register slab subsystem.\n");
		return -ENOMEM;
	}

	slab_state = FULL;

	list_for_each_entry(s, &slab_caches, list) {
		err = sysfs_slab_add(s);
		if (err)
			pr_err("SLUB: Unable to add boot slab %s to sysfs\n",
			       s->name);
	}

	while (alias_list) {
		struct saved_alias *al = alias_list;

		alias_list = alias_list->next;
		err = sysfs_slab_alias(al->s, al->name);
		if (err)
			pr_err("SLUB: Unable to add boot slab alias %s to sysfs\n",
			       al->name);
		kfree(al);
	}

	mutex_unlock(&slab_mutex);
	return 0;
}
late_initcall(slab_sysfs_init);
#endif /* SLAB_SUPPORTS_SYSFS */

#if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS)
static int slab_debugfs_show(struct seq_file *seq, void *v)
{
	struct loc_track *t = seq->private;
	struct location *l;
	unsigned long idx;

	idx = (unsigned long) t->idx;
	if (idx < t->count) {
		l = &t->loc[idx];

		seq_printf(seq, "%7ld ", l->count);

		if (l->addr)
			seq_printf(seq, "%pS", (void *)l->addr);
		else
			seq_puts(seq, "<not-available>");

		if (l->waste)
			seq_printf(seq, " waste=%lu/%lu",
				l->count * l->waste, l->waste);

		if (l->sum_time != l->min_time) {
			seq_printf(seq, " age=%ld/%llu/%ld",
				l->min_time, div_u64(l->sum_time, l->count),
				l->max_time);
		} else
			seq_printf(seq, " age=%ld", l->min_time);

		if (l->min_pid != l->max_pid)
			seq_printf(seq, " pid=%ld-%ld", l->min_pid, l->max_pid);
		else
			seq_printf(seq, " pid=%ld",
				l->min_pid);

		if (num_online_cpus() > 1 && !cpumask_empty(to_cpumask(l->cpus)))
			seq_printf(seq, " cpus=%*pbl",
				 cpumask_pr_args(to_cpumask(l->cpus)));

		if (nr_online_nodes > 1 && !nodes_empty(l->nodes))
			seq_printf(seq, " nodes=%*pbl",
				 nodemask_pr_args(&l->nodes));

#ifdef CONFIG_STACKDEPOT
		{
			depot_stack_handle_t handle;
			unsigned long *entries;
			unsigned int nr_entries, j;

			handle = READ_ONCE(l->handle);
			if (handle) {
				nr_entries = stack_depot_fetch(handle, &entries);
				seq_puts(seq, "\n");
				for (j = 0; j < nr_entries; j++)
					seq_printf(seq, "        %pS\n", (void *)entries[j]);
			}
		}
#endif
		seq_puts(seq, "\n");
	}

	if (!idx && !t->count)
		seq_puts(seq, "No data\n");

	return 0;
}

static void slab_debugfs_stop(struct seq_file *seq, void *v)
{
}

static void *slab_debugfs_next(struct seq_file *seq, void *v, loff_t *ppos)
{
	struct loc_track *t = seq->private;

	t->idx = ++(*ppos);
	if (*ppos <= t->count)
		return ppos;

	return NULL;
}

static int cmp_loc_by_count(const void *a, const void *b, const void *data)
{
	struct location *loc1 = (struct location *)a;
	struct location *loc2 = (struct location *)b;

	if (loc1->count > loc2->count)
		return -1;
	else
		return 1;
}

static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos)
{
	struct loc_track *t = seq->private;

	t->idx = *ppos;
	return ppos;
}

static const struct seq_operations slab_debugfs_sops = {
	.start  = slab_debugfs_start,
	.next   = slab_debugfs_next,
	.stop   = slab_debugfs_stop,
	.show   = slab_debugfs_show,
};

static int slab_debug_trace_open(struct inode *inode, struct file *filep)
{

	struct kmem_cache_node *n;
	enum track_item alloc;
	int node;
	struct loc_track *t = __seq_open_private(filep, &slab_debugfs_sops,
						sizeof(struct loc_track));
	struct kmem_cache *s = file_inode(filep)->i_private;
	unsigned long *obj_map;

	if (!t)
		return -ENOMEM;

	obj_map = bitmap_alloc(oo_objects(s->oo), GFP_KERNEL);
	if (!obj_map) {
		seq_release_private(inode, filep);
		return -ENOMEM;
	}

	if (strcmp(filep->f_path.dentry->d_name.name, "alloc_traces") == 0)
		alloc = TRACK_ALLOC;
	else
		alloc = TRACK_FREE;

	if (!alloc_loc_track(t, PAGE_SIZE / sizeof(struct location), GFP_KERNEL)) {
		bitmap_free(obj_map);
		seq_release_private(inode, filep);
		return -ENOMEM;
	}

	for_each_kmem_cache_node(s, node, n) {
		unsigned long flags;
		struct slab *slab;

		if (!node_nr_slabs(n))
			continue;

		spin_lock_irqsave(&n->list_lock, flags);
		list_for_each_entry(slab, &n->partial, slab_list)
			process_slab(t, s, slab, alloc, obj_map);
		list_for_each_entry(slab, &n->full, slab_list)
			process_slab(t, s, slab, alloc, obj_map);
		spin_unlock_irqrestore(&n->list_lock, flags);
	}

	/* Sort locations by count */
	sort_r(t->loc, t->count, sizeof(struct location),
		cmp_loc_by_count, NULL, NULL);

	bitmap_free(obj_map);
	return 0;
}

static int slab_debug_trace_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	struct loc_track *t = seq->private;

	free_loc_track(t);
	return seq_release_private(inode, file);
}

static const struct file_operations slab_debugfs_fops = {
	.open    = slab_debug_trace_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = slab_debug_trace_release,
};

static void debugfs_slab_add(struct kmem_cache *s)
{
	struct dentry *slab_cache_dir;

	if (unlikely(!slab_debugfs_root))
		return;

	slab_cache_dir = debugfs_create_dir(s->name, slab_debugfs_root);

	debugfs_create_file("alloc_traces", 0400,
		slab_cache_dir, s, &slab_debugfs_fops);

	debugfs_create_file("free_traces", 0400,
		slab_cache_dir, s, &slab_debugfs_fops);
}

void debugfs_slab_release(struct kmem_cache *s)
{
	debugfs_lookup_and_remove(s->name, slab_debugfs_root);
}

static int __init slab_debugfs_init(void)
{
	struct kmem_cache *s;

	slab_debugfs_root = debugfs_create_dir("slab", NULL);

	list_for_each_entry(s, &slab_caches, list)
		if (s->flags & SLAB_STORE_USER)
			debugfs_slab_add(s);

	return 0;

}
__initcall(slab_debugfs_init);
#endif
/*
 * The /proc/slabinfo ABI
 */
#ifdef CONFIG_SLUB_DEBUG
void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
{
	unsigned long nr_slabs = 0;
	unsigned long nr_objs = 0;
	unsigned long nr_free = 0;
	int node;
	struct kmem_cache_node *n;

	for_each_kmem_cache_node(s, node, n) {
		nr_slabs += node_nr_slabs(n);
		nr_objs += node_nr_objs(n);
		nr_free += count_partial_free_approx(n);
	}

	sinfo->active_objs = nr_objs - nr_free;
	sinfo->num_objs = nr_objs;
	sinfo->active_slabs = nr_slabs;
	sinfo->num_slabs = nr_slabs;
	sinfo->objects_per_slab = oo_objects(s->oo);
	sinfo->cache_order = oo_order(s->oo);
}
#endif /* CONFIG_SLUB_DEBUG */