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 operatios
 * 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> /* struct reclaim_state */
#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/cpu.h>
#include <linux/cpuset.h>
#include <linux/mempolicy.h>
#include <linux/ctype.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/stacktrace.h>
#include <linux/prefetch.h>
#include <linux/memcontrol.h>
#include <linux/random.h>

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

#include "internal.h"

/*
 * Lock order:
 *   1. slab_mutex (Global Mutex)
 *   2. node->list_lock
 *   3. slab_lock(page) (Only on some arches and 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.
 *
 *   The slab_lock is only used for debugging and on arches that do not
 *   have the ability to do a cmpxchg_double. It only protects:
 *	A. page->freelist	-> List of object free in a page
 *	B. page->inuse		-> Number of objects in use
 *	C. page->objects	-> Number of objects in page
 *	D. page->frozen		-> frozen state
 *
 *   If a slab is frozen then it is exempt from list management. It is not
 *   on any list except per cpu partial list. The processor that froze the
 *   slab is the one who can perform list operations on the page. 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
 *   page's freelist.
 *
 *   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.
 *   Interrupts are disabled during allocation and deallocation in order to
 *   make the slab allocator safe to use in the context of an irq. In addition
 *   interrupts are disabled to ensure that the processor does not change
 *   while handling per_cpu slabs, due to kernel preemption.
 *
 * 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.
 *
 * page->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.
 */

#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

static inline bool kmem_cache_debug(struct kmem_cache *s)
{
	return kmem_cache_debug_flags(s, SLAB_DEBUG_FLAGS);
}

void *fixup_red_left(struct kmem_cache *s, void *p)
{
	if (kmem_cache_debug_flags(s, SLAB_RED_ZONE))
		p += s->red_left_pad;

	return p;
}

static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
{
#ifdef CONFIG_SLUB_CPU_PARTIAL
	return !kmem_cache_debug(s);
#else
	return false;
#endif
}

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

/* Enable to test recovery from slab corruption on boot */
#undef SLUB_RESILIENCY_TEST

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

/*
 * Mininum 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 5

/*
 * 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 10

#define DEBUG_DEFAULT_FLAGS (SLAB_CONSISTENCY_CHECKS | SLAB_RED_ZONE | \
				SLAB_POISON | SLAB_STORE_USER)

/*
 * These debug flags cannot use CMPXCHG because there might be consistency
 * issues when checking or reading debug information
 */
#define SLAB_NO_CMPXCHG (SLAB_CONSISTENCY_CHECKS | SLAB_STORE_USER | \
				SLAB_TRACE)


/*
 * Debugging flags that require metadata to be stored in the slab.  These get
 * disabled when slub_debug=O is used and a cache's min order increases with
 * metadata.
 */
#define DEBUG_METADATA_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)

#define OO_SHIFT	16
#define OO_MASK		((1 << OO_SHIFT) - 1)
#define MAX_OBJS_PER_PAGE	32767 /* since page.objects is u15 */

/* Internal SLUB flags */
/* Poison object */
#define __OBJECT_POISON		((slab_flags_t __force)0x80000000U)
/* Use cmpxchg_double */
#define __CMPXCHG_DOUBLE	((slab_flags_t __force)0x40000000U)

#ifdef CONFIG_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) { return 0; }
static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
							{ return 0; }
#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

static inline void stat(const struct kmem_cache *s, enum stat_item si)
{
#ifdef CONFIG_SLUB_STATS
	/*
	 * The rmw is racy on a preemptible kernel but this is acceptable, so
	 * avoid this_cpu_add()'s irq-disable overhead.
	 */
	raw_cpu_inc(s->cpu_slab->stat[si]);
#endif
}

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

/*
 * 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 void *freelist_ptr(const struct kmem_cache *s, void *ptr,
				 unsigned long ptr_addr)
{
#ifdef CONFIG_SLAB_FREELIST_HARDENED
	/*
	 * When CONFIG_KASAN_SW/HW_TAGS is enabled, ptr_addr might be tagged.
	 * Normally, this doesn't cause any issues, as both set_freepointer()
	 * and get_freepointer() are called with a pointer with the same tag.
	 * However, there are some issues with CONFIG_SLUB_DEBUG code. For
	 * example, when __free_slub() iterates over objects in a cache, it
	 * passes untagged pointers to check_object(). check_object() in turns
	 * calls get_freepointer() with an untagged pointer, which causes the
	 * freepointer to be restored incorrectly.
	 */
	return (void *)((unsigned long)ptr ^ s->random ^
			swab((unsigned long)kasan_reset_tag((void *)ptr_addr)));
#else
	return ptr;
#endif
}

/* Returns the freelist pointer recorded at location ptr_addr. */
static inline void *freelist_dereference(const struct kmem_cache *s,
					 void *ptr_addr)
{
	return freelist_ptr(s, (void *)*(unsigned long *)(ptr_addr),
			    (unsigned long)ptr_addr);
}

static inline void *get_freepointer(struct kmem_cache *s, void *object)
{
	object = kasan_reset_tag(object);
	return freelist_dereference(s, object + s->offset);
}

static void prefetch_freepointer(const struct kmem_cache *s, void *object)
{
	prefetch(object + s->offset);
}

static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)
{
	unsigned long freepointer_addr;
	void *p;

	if (!debug_pagealloc_enabled_static())
		return get_freepointer(s, object);

	object = kasan_reset_tag(object);
	freepointer_addr = (unsigned long)object + s->offset;
	copy_from_kernel_nofault(&p, (void **)freepointer_addr, sizeof(p));
	return freelist_ptr(s, p, freepointer_addr);
}

static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
{
	unsigned long freeptr_addr = (unsigned long)object + s->offset;

#ifdef CONFIG_SLAB_FREELIST_HARDENED
	BUG_ON(object == fp); /* naive detection of double free or corruption */
#endif

	freeptr_addr = (unsigned long)kasan_reset_tag((void *)freeptr_addr);
	*(void **)freeptr_addr = freelist_ptr(s, fp, freeptr_addr);
}

/* Loop over all objects in a slab */
#define for_each_object(__p, __s, __addr, __objects) \
	for (__p = fixup_red_left(__s, __addr); \
		__p < (__addr) + (__objects) * (__s)->size; \
		__p += (__s)->size)

static inline unsigned int order_objects(unsigned int order, unsigned int size)
{
	return ((unsigned int)PAGE_SIZE << order) / size;
}

static inline struct kmem_cache_order_objects oo_make(unsigned int order,
		unsigned int size)
{
	struct kmem_cache_order_objects x = {
		(order << OO_SHIFT) + order_objects(order, size)
	};

	return x;
}

static inline unsigned int oo_order(struct kmem_cache_order_objects x)
{
	return x.x >> OO_SHIFT;
}

static inline unsigned int oo_objects(struct kmem_cache_order_objects x)
{
	return x.x & OO_MASK;
}

/*
 * Per slab locking using the pagelock
 */
static __always_inline void slab_lock(struct page *page)
{
	VM_BUG_ON_PAGE(PageTail(page), page);
	bit_spin_lock(PG_locked, &page->flags);
}

static __always_inline void slab_unlock(struct page *page)
{
	VM_BUG_ON_PAGE(PageTail(page), page);
	__bit_spin_unlock(PG_locked, &page->flags);
}

/* Interrupts must be disabled (for the fallback code to work right) */
static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
		void *freelist_old, unsigned long counters_old,
		void *freelist_new, unsigned long counters_new,
		const char *n)
{
	VM_BUG_ON(!irqs_disabled());
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
    defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
	if (s->flags & __CMPXCHG_DOUBLE) {
		if (cmpxchg_double(&page->freelist, &page->counters,
				   freelist_old, counters_old,
				   freelist_new, counters_new))
			return true;
	} else
#endif
	{
		slab_lock(page);
		if (page->freelist == freelist_old &&
					page->counters == counters_old) {
			page->freelist = freelist_new;
			page->counters = counters_new;
			slab_unlock(page);
			return true;
		}
		slab_unlock(page);
	}

	cpu_relax();
	stat(s, CMPXCHG_DOUBLE_FAIL);

#ifdef SLUB_DEBUG_CMPXCHG
	pr_info("%s %s: cmpxchg double redo ", n, s->name);
#endif

	return false;
}

static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
		void *freelist_old, unsigned long counters_old,
		void *freelist_new, unsigned long counters_new,
		const char *n)
{
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
    defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
	if (s->flags & __CMPXCHG_DOUBLE) {
		if (cmpxchg_double(&page->freelist, &page->counters,
				   freelist_old, counters_old,
				   freelist_new, counters_new))
			return true;
	} else
#endif
	{
		unsigned long flags;

		local_irq_save(flags);
		slab_lock(page);
		if (page->freelist == freelist_old &&
					page->counters == counters_old) {
			page->freelist = freelist_new;
			page->counters = counters_new;
			slab_unlock(page);
			local_irq_restore(flags);
			return true;
		}
		slab_unlock(page);
		local_irq_restore(flags);
	}

	cpu_relax();
	stat(s, CMPXCHG_DOUBLE_FAIL);

#ifdef SLUB_DEBUG_CMPXCHG
	pr_info("%s %s: cmpxchg double redo ", n, s->name);
#endif

	return false;
}

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

/*
 * Determine a map of object in use on a page.
 *
 * Node listlock must be held to guarantee that the page does
 * not vanish from under us.
 */
static unsigned long *get_map(struct kmem_cache *s, struct page *page)
	__acquires(&object_map_lock)
{
	void *p;
	void *addr = page_address(page);

	VM_BUG_ON(!irqs_disabled());

	spin_lock(&object_map_lock);

	bitmap_zero(object_map, page->objects);

	for (p = page->freelist; p; p = get_freepointer(s, p))
		set_bit(__obj_to_index(s, addr, p), object_map);

	return object_map;
}

static void put_map(unsigned long *map) __releases(&object_map_lock)
{
	VM_BUG_ON(map != object_map);
	spin_unlock(&object_map_lock);
}

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)
slab_flags_t slub_debug = DEBUG_DEFAULT_FLAGS;
#else
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();
}

static inline void metadata_access_disable(void)
{
	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 page *page, void *object)
{
	void *base;

	if (!object)
		return 1;

	base = page_address(page);
	object = kasan_reset_tag(object);
	object = restore_red_left(s, object);
	if (object < base || object >= base + page->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();
}

/*
 * See comment in calculate_sizes().
 */
static inline bool freeptr_outside_object(struct kmem_cache *s)
{
	return s->offset >= s->inuse;
}

/*
 * 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)
{
	if (freeptr_outside_object(s))
		return s->inuse + sizeof(void *);
	else
		return s->inuse;
}

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);
}

/*
 * This function will be used to loop through all the slab objects in
 * a page to give track structure for each object, the function fn will
 * be using this track structure and extract required info into its private
 * data, the return value will be the number of track structures that are
 * processed.
 */
unsigned long get_each_object_track(struct kmem_cache *s,
		struct page *page, enum track_item alloc,
		int (*fn)(const struct kmem_cache *, const void *,
		const struct track *, void *), void *private)
{
	void *p;
	struct track *t;
	int ret;
	unsigned long num_track = 0;

	if (!slub_debug || !(s->flags & SLAB_STORE_USER))
		return 0;

	slab_lock(page);
	for_each_object(p, s, page_address(page), page->objects) {
		t = get_track(s, p, alloc);
		ret = fn(s, p, t, private);
		if (ret < 0)
			break;
		num_track += 1;
	}
	slab_unlock(page);
	return num_track;
}
EXPORT_SYMBOL_GPL(get_each_object_track);

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

	if (addr) {
#ifdef CONFIG_STACKTRACE
		unsigned int nr_entries;

		metadata_access_enable();
		nr_entries = stack_trace_save(kasan_reset_tag(p->addrs),
					      TRACK_ADDRS_COUNT, 3);
		metadata_access_disable();

		if (nr_entries < TRACK_ADDRS_COUNT)
			p->addrs[nr_entries] = 0;
		trace_android_vh_save_track_hash(alloc == TRACK_ALLOC,
						(unsigned long)p);
#endif
		p->addr = addr;
		p->cpu = smp_processor_id();
		p->pid = current->pid;
		p->when = jiffies;
	} else {
		memset(p, 0, sizeof(struct track));
	}
}

static void init_tracking(struct kmem_cache *s, void *object)
{
	if (!(s->flags & SLAB_STORE_USER))
		return;

	set_track(s, object, TRACK_FREE, 0UL);
	set_track(s, object, TRACK_ALLOC, 0UL);
}

static void print_track(const char *s, struct track *t, unsigned long pr_time)
{
	if (!t->addr)
		return;

	pr_err("INFO: %s in %pS age=%lu cpu=%u pid=%d\n",
	       s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid);
#ifdef CONFIG_STACKTRACE
	{
		int i;
		for (i = 0; i < TRACK_ADDRS_COUNT; i++)
			if (t->addrs[i])
				pr_err("\t%pS\n", (void *)t->addrs[i]);
			else
				break;
	}
#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_page_info(struct page *page)
{
	pr_err("INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n",
	       page, page->objects, page->inuse, page->freelist, page->flags);

}

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);
}

static void slab_fix(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("FIX %s: %pV\n", s->name, &vaf);
	va_end(args);
}

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

	return false;
}

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

	print_tracking(s, p);

	print_page_info(page);

	pr_err("INFO: 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);

	off += kasan_metadata_size(s);

	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();
}

void object_err(struct kmem_cache *s, struct page *page,
			u8 *object, char *reason)
{
	slab_bug(s, "%s", reason);
	print_trailer(s, page, object);
	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}

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

	va_start(args, fmt);
	vsnprintf(buf, sizeof(buf), fmt, args);
	va_end(args);
	slab_bug(s, "%s", buf);
	print_page_info(page);
	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);

	if (s->flags & SLAB_RED_ZONE)
		memset(p - s->red_left_pad, val, s->red_left_pad);

	if (s->flags & __OBJECT_POISON) {
		memset(p, POISON_FREE, s->object_size - 1);
		p[s->object_size - 1] = POISON_END;
	}

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

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

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

	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--;

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

	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 (RED_INACTIVE) for inactive objects and with
 * 	0xcc (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. Padding to reach required alignment boundary or at mininum
 * 		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 page *page, 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);

	off += kasan_metadata_size(s);

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

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

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

	if (!(s->flags & SLAB_POISON))
		return 1;

	start = page_address(page);
	length = page_size(page);
	end = start + length;
	remainder = length % s->size;
	if (!remainder)
		return 1;

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

	slab_err(s, page, "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);
	return 0;
}

static int check_object(struct kmem_cache *s, struct page *page,
					void *object, u8 val)
{
	u8 *p = object;
	u8 *endobject = object + s->object_size;

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

		if (!check_bytes_and_report(s, page, object, "Right Redzone",
			endobject, val, s->inuse - s->object_size))
			return 0;
	} else {
		if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) {
			check_bytes_and_report(s, page, p, "Alignment padding",
				endobject, POISON_INUSE,
				s->inuse - s->object_size);
		}
	}

	if (s->flags & SLAB_POISON) {
		if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) &&
			(!check_bytes_and_report(s, page, p, "Poison", p,
					POISON_FREE, s->object_size - 1) ||
			 !check_bytes_and_report(s, page, p, "End Poison",
				p + s->object_size - 1, POISON_END, 1)))
			return 0;
		/*
		 * check_pad_bytes cleans up on its own.
		 */
		check_pad_bytes(s, page, p);
	}

	if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE)
		/*
		 * Object and freepointer overlap. Cannot check
		 * freepointer while object is allocated.
		 */
		return 1;

	/* Check free pointer validity */
	if (!check_valid_pointer(s, page, get_freepointer(s, p))) {
		object_err(s, page, 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);
		return 0;
	}
	return 1;
}

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

	VM_BUG_ON(!irqs_disabled());

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

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

/*
 * Determine if a certain object on a page 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 page *page, void *search)
{
	int nr = 0;
	void *fp;
	void *object = NULL;
	int max_objects;

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

	max_objects = order_objects(compound_order(page), s->size);
	if (max_objects > MAX_OBJS_PER_PAGE)
		max_objects = MAX_OBJS_PER_PAGE;

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

static void trace(struct kmem_cache *s, struct page *page, 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, page->inuse,
			page->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 page *page)
{
	if (!(s->flags & SLAB_STORE_USER))
		return;

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

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

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

/* Tracking of the number of slabs for debugging purposes */
static inline unsigned long slabs_node(struct kmem_cache *s, int node)
{
	struct kmem_cache_node *n = get_node(s, node);

	return atomic_long_read(&n->nr_slabs);
}

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);

	/*
	 * May be called early in order to allocate a slab for the
	 * kmem_cache_node structure. Solve the chicken-egg
	 * dilemma by deferring the increment of the count during
	 * bootstrap (see early_kmem_cache_node_alloc).
	 */
	if (likely(n)) {
		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, struct page *page,
								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_page_debug(struct kmem_cache *s, struct page *page, void *addr)
{
	if (!kmem_cache_debug_flags(s, SLAB_POISON))
		return;

	metadata_access_enable();
	memset(kasan_reset_tag(addr), POISON_INUSE, page_size(page));
	metadata_access_disable();
}

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

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

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

	return 1;
}

static noinline int alloc_debug_processing(struct kmem_cache *s,
					struct page *page,
					void *object, unsigned long addr)
{
	if (s->flags & SLAB_CONSISTENCY_CHECKS) {
		if (!alloc_consistency_checks(s, page, object))
			goto bad;
	}

	/* Success perform special debug activities for allocs */
	if (s->flags & SLAB_STORE_USER)
		set_track(s, object, TRACK_ALLOC, addr);
	trace(s, page, object, 1);
	init_object(s, object, SLUB_RED_ACTIVE);
	return 1;

bad:
	if (PageSlab(page)) {
		/*
		 * 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");
		page->inuse = page->objects;
		page->freelist = NULL;
	}
	return 0;
}

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

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

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

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

/* Supports checking bulk free of a constructed freelist */
static noinline int free_debug_processing(
	struct kmem_cache *s, struct page *page,
	void *head, void *tail, int bulk_cnt,
	unsigned long addr)
{
	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
	void *object = head;
	int cnt = 0;
	unsigned long flags;
	int ret = 0;

	spin_lock_irqsave(&n->list_lock, flags);
	slab_lock(page);

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

next_object:
	cnt++;

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

	if (s->flags & SLAB_STORE_USER)
		set_track(s, object, TRACK_FREE, addr);
	trace(s, page, 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;
	}
	ret = 1;

out:
	if (cnt != bulk_cnt)
		slab_err(s, page, "Bulk freelist count(%d) invalid(%d)\n",
			 bulk_cnt, cnt);

	slab_unlock(page);
	spin_unlock_irqrestore(&n->list_lock, flags);
	if (!ret)
		slab_fix(s, "Object at 0x%p not freed", object);
	return ret;
}

/*
 * Parse a block of slub_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("slub_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;
		}
	}

	/*
	 * For backwards compatibility, a single list of flags with list of
	 * slabs means debugging is only changed for those slabs, so the global
	 * slub_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 != 0 || slub_debug_string)
		static_branch_enable(&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("slub_debug", setup_slub_debug);

/*
 * kmem_cache_flags - apply debugging options to the cache
 * @object_size:	the size of an object without meta data
 * @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.
 * slub_debug=<Debug-Options>,<slab name1>,<slab name2> ...
 * then only the select slabs will receive the debug option(s).
 */
slab_flags_t kmem_cache_flags(unsigned int object_size,
	slab_flags_t flags, const char *name)
{
	char *iter;
	size_t len;
	char *next_block;
	slab_flags_t block_flags;

	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;
}
#else /* !CONFIG_SLUB_DEBUG */
static inline void setup_object_debug(struct kmem_cache *s,
			struct page *page, void *object) {}
static inline
void setup_page_debug(struct kmem_cache *s, struct page *page, void *addr) {}

static inline int alloc_debug_processing(struct kmem_cache *s,
	struct page *page, void *object, unsigned long addr) { return 0; }

static inline int free_debug_processing(
	struct kmem_cache *s, struct page *page,
	void *head, void *tail, int bulk_cnt,
	unsigned long addr) { return 0; }

static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
			{ return 1; }
static inline int check_object(struct kmem_cache *s, struct page *page,
			void *object, u8 val) { return 1; }
static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
					struct page *page) {}
static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
					struct page *page) {}
slab_flags_t kmem_cache_flags(unsigned int object_size,
	slab_flags_t flags, const char *name)
{
	return flags;
}
#define slub_debug 0

#define disable_higher_order_debug 0

static inline unsigned long slabs_node(struct kmem_cache *s, int node)
							{ return 0; }
static inline unsigned long node_nr_slabs(struct kmem_cache_node *n)
							{ return 0; }
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) {}

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

/*
 * Hooks for other subsystems that check memory allocations. In a typical
 * production configuration these hooks all should produce no code at all.
 */
static inline void *kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
{
	ptr = kasan_kmalloc_large(ptr, size, flags);
	/* As ptr might get tagged, call kmemleak hook after KASAN. */
	kmemleak_alloc(ptr, size, 1, flags);
	return ptr;
}

static __always_inline void kfree_hook(void *x)
{
	kmemleak_free(x);
	kasan_kfree_large(x);
}

static __always_inline bool slab_free_hook(struct kmem_cache *s,
						void *x, bool init)
{
	kmemleak_free_recursive(x, s->flags);

	/*
	 * Trouble is that we may no longer disable interrupts in the fast path
	 * So in order to make the debug calls that expect irqs to be
	 * disabled we need to disable interrupts temporarily.
	 */
#ifdef CONFIG_LOCKDEP
	{
		unsigned long flags;

		local_irq_save(flags);
		debug_check_no_locks_freed(x, s->object_size);
		local_irq_restore(flags);
	}
#endif
	if (!(s->flags & SLAB_DEBUG_OBJECTS))
		debug_check_no_obj_freed(x, s->object_size);

	/* Use KCSAN to help debug racy use-after-free. */
	if (!(s->flags & SLAB_TYPESAFE_BY_RCU))
		__kcsan_check_access(x, s->object_size,
				     KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT);

	/*
	 * As memory initialization might be integrated into KASAN,
	 * kasan_slab_free and initialization memset's must be
	 * kept together to avoid discrepancies in behavior.
	 *
	 * The initialization memset's clear the object and the metadata,
	 * but don't touch the SLAB redzone.
	 */
	if (init) {
		int rsize;

		if (!kasan_has_integrated_init())
			memset(kasan_reset_tag(x), 0, s->object_size);
		rsize = (s->flags & SLAB_RED_ZONE) ? s->red_left_pad : 0;
		memset((char *)kasan_reset_tag(x) + s->inuse, 0,
		       s->size - s->inuse - rsize);
	}
	/* KASAN might put x into memory quarantine, delaying its reuse. */
	return kasan_slab_free(s, x, init);
}

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

	void *object;
	void *next = *head;
	void *old_tail = *tail ? *tail : *head;

	if (is_kfence_address(next)) {
		slab_free_hook(s, next, false);
		return true;
	}

	/* Head and tail of the reconstructed freelist */
	*head = NULL;
	*tail = NULL;

	do {
		object = next;
		next = get_freepointer(s, object);

		/* If object's reuse doesn't have to be delayed */
		if (!slab_free_hook(s, object, slab_want_init_on_free(s))) {
			/* Move object to the new freelist */
			set_freepointer(s, object, *head);
			*head = object;
			if (!*tail)
				*tail = object;
		} else {
			/*
			 * Adjust the reconstructed freelist depth
			 * accordingly if object's reuse is delayed.
			 */
			--(*cnt);
		}
	} while (object != old_tail);

	if (*head == *tail)
		*tail = NULL;

	return *head != NULL;
}

static void *setup_object(struct kmem_cache *s, struct page *page,
				void *object)
{
	setup_object_debug(s, page, object);
	object = kasan_init_slab_obj(s, object);
	if (unlikely(s->ctor)) {
		kasan_unpoison_object_data(s, object);
		s->ctor(object);
		kasan_poison_object_data(s, object);
	}
	return object;
}

/*
 * Slab allocation and freeing
 */
static inline struct page *alloc_slab_page(struct kmem_cache *s,
		gfp_t flags, int node, struct kmem_cache_order_objects oo)
{
	struct page *page;
	unsigned int order = oo_order(oo);

	if (node == NUMA_NO_NODE)
		page = alloc_pages(flags, order);
	else
		page = __alloc_pages_node(node, flags, order);

	if (page)
		account_slab_page(page, order, s);

	return page;
}

#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, struct page *page,
				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 page *page)
{
	void *start;
	void *cur;
	void *next;
	unsigned long idx, pos, page_limit, freelist_count;

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

	freelist_count = oo_objects(s->oo);
	pos = get_random_int() % freelist_count;

	page_limit = page->objects * s->size;
	start = fixup_red_left(s, page_address(page));

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

	for (idx = 1; idx < page->objects; idx++) {
		next = next_freelist_entry(s, page, &pos, start, page_limit,
			freelist_count);
		next = setup_object(s, page, 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)
{
	return 0;
}
static inline void init_freelist_randomization(void) { }
static inline bool shuffle_freelist(struct kmem_cache *s, struct page *page)
{
	return false;
}
#endif /* CONFIG_SLAB_FREELIST_RANDOM */

static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
{
	struct page *page;
	struct kmem_cache_order_objects oo = s->oo;
	gfp_t alloc_gfp;
	void *start, *p, *next;
	int idx;
	bool shuffle;

	flags &= gfp_allowed_mask;

	if (gfpflags_allow_blocking(flags))
		local_irq_enable();

	flags |= s->allocflags;

	/*
	 * Let the initial higher-order allocation fail under memory pressure
	 * so we fall-back to the minimum order allocation.
	 */
	alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL;
	if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min))
		alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~(__GFP_RECLAIM|__GFP_NOFAIL);

	page = alloc_slab_page(s, alloc_gfp, node, oo);
	if (unlikely(!page)) {
		oo = s->min;
		alloc_gfp = flags;
		/*
		 * Allocation may have failed due to fragmentation.
		 * Try a lower order alloc if possible
		 */
		page = alloc_slab_page(s, alloc_gfp, node, oo);
		if (unlikely(!page))
			goto out;
		stat(s, ORDER_FALLBACK);
	}

	page->objects = oo_objects(oo);

	page->slab_cache = s;
	__SetPageSlab(page);
	if (page_is_pfmemalloc(page))
		SetPageSlabPfmemalloc(page);

	kasan_poison_slab(page);

	start = page_address(page);

	setup_page_debug(s, page, start);

	shuffle = shuffle_freelist(s, page);

	if (!shuffle) {
		start = fixup_red_left(s, start);
		start = setup_object(s, page, start);
		page->freelist = start;
		for (idx = 0, p = start; idx < page->objects - 1; idx++) {
			next = p + s->size;
			next = setup_object(s, page, next);
			set_freepointer(s, p, next);
			p = next;
		}
		set_freepointer(s, p, NULL);
	}

	page->inuse = page->objects;
	page->frozen = 1;

out:
	if (gfpflags_allow_blocking(flags))
		local_irq_disable();
	if (!page)
		return NULL;

	inc_slabs_node(s, page_to_nid(page), page->objects);

	return page;
}

static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
{
	if (unlikely(flags & GFP_SLAB_BUG_MASK))
		flags = kmalloc_fix_flags(flags);

	return allocate_slab(s,
		flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
}

static void __free_slab(struct kmem_cache *s, struct page *page)
{
	int order = compound_order(page);
	int pages = 1 << order;

	if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) {
		void *p;

		slab_pad_check(s, page);
		for_each_object(p, s, page_address(page),
						page->objects)
			check_object(s, page, p, SLUB_RED_INACTIVE);
	}

	__ClearPageSlabPfmemalloc(page);
	__ClearPageSlab(page);

	page->mapping = NULL;
	if (current->reclaim_state)
		current->reclaim_state->reclaimed_slab += pages;
	unaccount_slab_page(page, order, s);
	__free_pages(page, order);
}

static void rcu_free_slab(struct rcu_head *h)
{
	struct page *page = container_of(h, struct page, rcu_head);

	__free_slab(page->slab_cache, page);
}

static void free_slab(struct kmem_cache *s, struct page *page)
{
	if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) {
		call_rcu(&page->rcu_head, rcu_free_slab);
	} else
		__free_slab(s, page);
}

static void discard_slab(struct kmem_cache *s, struct page *page)
{
	dec_slabs_node(s, page_to_nid(page), page->objects);
	free_slab(s, page);
}

/*
 * Management of partially allocated slabs.
 */
static inline void
__add_partial(struct kmem_cache_node *n, struct page *page, int tail)
{
	n->nr_partial++;
	if (tail == DEACTIVATE_TO_TAIL)
		list_add_tail(&page->slab_list, &n->partial);
	else
		list_add(&page->slab_list, &n->partial);
}

static inline void add_partial(struct kmem_cache_node *n,
				struct page *page, int tail)
{
	lockdep_assert_held(&n->list_lock);
	__add_partial(n, page, tail);
}

static inline void remove_partial(struct kmem_cache_node *n,
					struct page *page)
{
	lockdep_assert_held(&n->list_lock);
	list_del(&page->slab_list);
	n->nr_partial--;
}

/*
 * Remove slab from the partial list, freeze it and
 * return the pointer to the freelist.
 *
 * Returns a list of objects or NULL if it fails.
 */
static inline void *acquire_slab(struct kmem_cache *s,
		struct kmem_cache_node *n, struct page *page,
		int mode, int *objects)
{
	void *freelist;
	unsigned long counters;
	struct page new;

	lockdep_assert_held(&n->list_lock);

	/*
	 * Zap the freelist and set the frozen bit.
	 * The old freelist is the list of objects for the
	 * per cpu allocation list.
	 */
	freelist = page->freelist;
	counters = page->counters;
	new.counters = counters;
	*objects = new.objects - new.inuse;
	if (mode) {
		new.inuse = page->objects;
		new.freelist = NULL;
	} else {
		new.freelist = freelist;
	}

	VM_BUG_ON(new.frozen);
	new.frozen = 1;

	if (!__cmpxchg_double_slab(s, page,
			freelist, counters,
			new.freelist, new.counters,
			"acquire_slab"))
		return NULL;

	remove_partial(n, page);
	WARN_ON(!freelist);
	return freelist;
}

static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);

/*
 * Try to allocate a partial slab from a specific node.
 */
static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
				struct kmem_cache_cpu *c, gfp_t flags)
{
	struct page *page, *page2;
	void *object = NULL;
	unsigned int available = 0;
	int objects;

	/*
	 * Racy check. If we mistakenly see no partial slabs then we
	 * just allocate an empty slab. If we mistakenly try to get a
	 * partial slab and there is none available then get_partial()
	 * will return NULL.
	 */
	if (!n || !n->nr_partial)
		return NULL;

	spin_lock(&n->list_lock);
	list_for_each_entry_safe(page, page2, &n->partial, slab_list) {
		void *t;

		if (!pfmemalloc_match(page, flags))
			continue;

		t = acquire_slab(s, n, page, object == NULL, &objects);
		if (!t)
			break;

		available += objects;
		if (!object) {
			c->page = page;
			stat(s, ALLOC_FROM_PARTIAL);
			object = t;
		} else {
			put_cpu_partial(s, page, 0);
			stat(s, CPU_PARTIAL_NODE);
		}
		if (!kmem_cache_has_cpu_partial(s)
			|| available > slub_cpu_partial(s) / 2)
			break;

	}
	spin_unlock(&n->list_lock);
	return object;
}

/*
 * Get a page from somewhere. Search in increasing NUMA distances.
 */
static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
		struct kmem_cache_cpu *c)
{
#ifdef CONFIG_NUMA
	struct zonelist *zonelist;
	struct zoneref *z;
	struct zone *zone;
	enum zone_type highest_zoneidx = gfp_zone(flags);
	void *object;
	unsigned int cpuset_mems_cookie;

	/*
	 * The defrag ratio allows a configuration of the tradeoffs between
	 * inter node defragmentation and node local allocations. A lower
	 * defrag_ratio increases the tendency to do local allocations
	 * instead of attempting to obtain partial slabs from other nodes.
	 *
	 * If the defrag_ratio is set to 0 then kmalloc() always
	 * returns node local objects. If the ratio is higher then kmalloc()
	 * may return off node objects because partial slabs are obtained
	 * from other nodes and filled up.
	 *
	 * If /sys/kernel/slab/xx/remote_node_defrag_ratio is set to 100
	 * (which makes defrag_ratio = 1000) then every (well almost)
	 * allocation will first attempt to defrag slab caches on other nodes.
	 * This means scanning over all nodes to look for partial slabs which
	 * may be expensive if we do it every time we are trying to find a slab
	 * with available objects.
	 */
	if (!s->remote_node_defrag_ratio ||
			get_cycles() % 1024 > s->remote_node_defrag_ratio)
		return NULL;

	do {
		cpuset_mems_cookie = read_mems_allowed_begin();
		zonelist = node_zonelist(mempolicy_slab_node(), flags);
		for_each_zone_zonelist(zone, z, zonelist, highest_zoneidx) {
			struct kmem_cache_node *n;

			n = get_node(s, zone_to_nid(zone));

			if (n && cpuset_zone_allowed(zone, flags) &&
					n->nr_partial > s->min_partial) {
				object = get_partial_node(s, n, c, flags);
				if (object) {
					/*
					 * Don't check read_mems_allowed_retry()
					 * here - if mems_allowed was updated in
					 * parallel, that was a harmless race
					 * between allocation and the cpuset
					 * update
					 */
					return object;
				}
			}
		}
	} while (read_mems_allowed_retry(cpuset_mems_cookie));
#endif	/* CONFIG_NUMA */
	return NULL;
}

/*
 * Get a partial page, lock it and return it.
 */
static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
		struct kmem_cache_cpu *c)
{
	void *object;
	int searchnode = node;

	if (node == NUMA_NO_NODE)
		searchnode = numa_mem_id();

	object = get_partial_node(s, get_node(s, searchnode), c, flags);
	if (object || node != NUMA_NO_NODE)
		return object;

	return get_any_partial(s, flags, c);
}

#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  roundup_pow_of_two(CONFIG_NR_CPUS)
#else
/*
 * No preemption supported therefore also no need to check for
 * different cpus.
 */
#define TID_STEP 1
#endif

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;

	for_each_possible_cpu(cpu)
		per_cpu_ptr(s->cpu_slab, cpu)->tid = init_tid(cpu);
}

/*
 * Remove the cpu slab
 */
static void deactivate_slab(struct kmem_cache *s, struct page *page,
				void *freelist, struct kmem_cache_cpu *c)
{
	enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
	int lock = 0;
	enum slab_modes l = M_NONE, m = M_NONE;
	void *nextfree;
	int tail = DEACTIVATE_TO_HEAD;
	struct page new;
	struct page old;

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

	/*
	 * Stage one: Free all available per cpu objects back
	 * to the page freelist while it is still frozen. Leave the
	 * last one.
	 *
	 * There is no need to take the list->lock because the page
	 * is still frozen.
	 */
	while (freelist && (nextfree = get_freepointer(s, freelist))) {
		void *prior;
		unsigned long counters;

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

		do {
			prior = page->freelist;
			counters = page->counters;
			set_freepointer(s, freelist, prior);
			new.counters = counters;
			new.inuse--;
			VM_BUG_ON(!new.frozen);

		} while (!__cmpxchg_double_slab(s, page,
			prior, counters,
			freelist, new.counters,
			"drain percpu freelist"));

		freelist = nextfree;
	}

	/*
	 * Stage two: Ensure that the page is unfrozen while the
	 * list presence reflects the actual number of objects
	 * during unfreeze.
	 *
	 * We setup the list membership and then perform a cmpxchg
	 * with the count. If there is a mismatch then the page
	 * is not unfrozen but the page is on the wrong list.
	 *
	 * Then we restart the process which may have to remove
	 * the page from the list that we just put it on again
	 * because the number of objects in the slab may have
	 * changed.
	 */
redo:

	old.freelist = page->freelist;
	old.counters = page->counters;
	VM_BUG_ON(!old.frozen);

	/* Determine target state of the slab */
	new.counters = old.counters;
	if (freelist) {
		new.inuse--;
		set_freepointer(s, freelist, old.freelist);
		new.freelist = freelist;
	} else
		new.freelist = old.freelist;

	new.frozen = 0;

	if (!new.inuse && n->nr_partial >= s->min_partial)
		m = M_FREE;
	else if (new.freelist) {
		m = M_PARTIAL;
		if (!lock) {
			lock = 1;
			/*
			 * Taking the spinlock removes the possibility
			 * that acquire_slab() will see a slab page that
			 * is frozen
			 */
			spin_lock(&n->list_lock);
		}
	} else {
		m = M_FULL;
#ifdef CONFIG_SLUB_DEBUG
		if ((s->flags & SLAB_STORE_USER) && !lock) {
			lock = 1;
			/*
			 * This also ensures that the scanning of full
			 * slabs from diagnostic functions will not see
			 * any frozen slabs.
			 */
			spin_lock(&n->list_lock);
		}
#endif
	}

	if (l != m) {
		if (l == M_PARTIAL)
			remove_partial(n, page);
		else if (l == M_FULL)
			remove_full(s, n, page);

		if (m == M_PARTIAL)
			add_partial(n, page, tail);
		else if (m == M_FULL)
			add_full(s, n, page);
	}

	l = m;
	if (!__cmpxchg_double_slab(s, page,
				old.freelist, old.counters,
				new.freelist, new.counters,
				"unfreezing slab"))
		goto redo;

	if (lock)
		spin_unlock(&n->list_lock);

	if (m == M_PARTIAL)
		stat(s, tail);
	else if (m == M_FULL)
		stat(s, DEACTIVATE_FULL);
	else if (m == M_FREE) {
		stat(s, DEACTIVATE_EMPTY);
		discard_slab(s, page);
		stat(s, FREE_SLAB);
	}

	c->page = NULL;
	c->freelist = NULL;
}

/*
 * Unfreeze all the cpu partial slabs.
 *
 * This function must be called with interrupts disabled
 * for the cpu using c (or some other guarantee must be there
 * to guarantee no concurrent accesses).
 */
static void unfreeze_partials(struct kmem_cache *s,
		struct kmem_cache_cpu *c)
{
#ifdef CONFIG_SLUB_CPU_PARTIAL
	struct kmem_cache_node *n = NULL, *n2 = NULL;
	struct page *page, *discard_page = NULL;

	while ((page = slub_percpu_partial(c))) {
		struct page new;
		struct page old;

		slub_set_percpu_partial(c, page);

		n2 = get_node(s, page_to_nid(page));
		if (n != n2) {
			if (n)
				spin_unlock(&n->list_lock);

			n = n2;
			spin_lock(&n->list_lock);
		}

		do {

			old.freelist = page->freelist;
			old.counters = page->counters;
			VM_BUG_ON(!old.frozen);

			new.counters = old.counters;
			new.freelist = old.freelist;

			new.frozen = 0;

		} while (!__cmpxchg_double_slab(s, page,
				old.freelist, old.counters,
				new.freelist, new.counters,
				"unfreezing slab"));

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

	if (n)
		spin_unlock(&n->list_lock);

	while (discard_page) {
		page = discard_page;
		discard_page = discard_page->next;

		stat(s, DEACTIVATE_EMPTY);
		discard_slab(s, page);
		stat(s, FREE_SLAB);
	}
#endif	/* CONFIG_SLUB_CPU_PARTIAL */
}

/*
 * Put a page that was just frozen (in __slab_free|get_partial_node) into a
 * partial page 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 page *page, int drain)
{
#ifdef CONFIG_SLUB_CPU_PARTIAL
	struct page *oldpage;
	int pages;
	int pobjects;

	preempt_disable();
	do {
		pages = 0;
		pobjects = 0;
		oldpage = this_cpu_read(s->cpu_slab->partial);

		if (oldpage) {
			pobjects = oldpage->pobjects;
			pages = oldpage->pages;
			if (drain && pobjects > slub_cpu_partial(s)) {
				unsigned long flags;
				/*
				 * partial array is full. Move the existing
				 * set to the per node partial list.
				 */
				local_irq_save(flags);
				unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
				local_irq_restore(flags);
				oldpage = NULL;
				pobjects = 0;
				pages = 0;
				stat(s, CPU_PARTIAL_DRAIN);
			}
		}

		pages++;
		pobjects += page->objects - page->inuse;

		page->pages = pages;
		page->pobjects = pobjects;
		page->next = oldpage;

	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page)
								!= oldpage);
	if (unlikely(!slub_cpu_partial(s))) {
		unsigned long flags;

		local_irq_save(flags);
		unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
		local_irq_restore(flags);
	}
	preempt_enable();
#endif	/* CONFIG_SLUB_CPU_PARTIAL */
}

static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
{
	stat(s, CPUSLAB_FLUSH);
	deactivate_slab(s, c->page, c->freelist, c);

	c->tid = next_tid(c->tid);
}

/*
 * Flush cpu slab.
 *
 * Called from IPI handler with interrupts disabled.
 */
static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
{
	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);

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

	unfreeze_partials(s, c);
}

static void flush_cpu_slab(void *d)
{
	struct kmem_cache *s = d;

	__flush_cpu_slab(s, smp_processor_id());
}

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

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

static void flush_all(struct kmem_cache *s)
{
	on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1);
}

/*
 * 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;
	unsigned long flags;

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

/*
 * Check if the objects in a per cpu structure fit numa
 * locality expectations.
 */
static inline int node_match(struct page *page, int node)
{
#ifdef CONFIG_NUMA
	if (node != NUMA_NO_NODE && page_to_nid(page) != node)
		return 0;
#endif
	return 1;
}

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

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

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

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

static noinline void
slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
{
#ifdef CONFIG_SLUB_DEBUG
	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 slub_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(n, count_free);
		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);
	}
#endif
}

static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
			int node, struct kmem_cache_cpu **pc)
{
	void *freelist;
	struct kmem_cache_cpu *c = *pc;
	struct page *page;

	WARN_ON_ONCE(s->ctor && (flags & __GFP_ZERO));

	freelist = get_partial(s, flags, node, c);

	if (freelist)
		return freelist;

	page = new_slab(s, flags, node);
	if (page) {
		c = raw_cpu_ptr(s->cpu_slab);
		if (c->page)
			flush_slab(s, c);

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

		stat(s, ALLOC_SLAB);
		c->page = page;
		*pc = c;
	}

	return freelist;
}

static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags)
{
	if (unlikely(PageSlabPfmemalloc(page)))
		return gfp_pfmemalloc_allowed(gfpflags);

	return true;
}

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

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

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

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

	} while (!__cmpxchg_double_slab(s, page,
		freelist, counters,
		NULL, new.counters,
		"get_freelist"));

	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 interrupts are
 * 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)
{
	void *freelist;
	struct page *page;

	stat(s, ALLOC_SLOWPATH);

	page = c->page;
	if (!page) {
		/*
		 * if the node is not online or has no normal memory, just
		 * ignore the node constraint
		 */
		if (unlikely(node != NUMA_NO_NODE &&
			     !node_state(node, N_NORMAL_MEMORY)))
			node = NUMA_NO_NODE;
		goto new_slab;
	}
redo:

	if (unlikely(!node_match(page, node))) {
		/*
		 * same as above but node_match() being false already
		 * implies node != NUMA_NO_NODE
		 */
		if (!node_state(node, N_NORMAL_MEMORY)) {
			node = NUMA_NO_NODE;
			goto redo;
		} else {
			stat(s, ALLOC_NODE_MISMATCH);
			deactivate_slab(s, page, c->freelist, c);
			goto new_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(page, gfpflags))) {
		deactivate_slab(s, page, c->freelist, c);
		goto new_slab;
	}

	/* must check again c->freelist in case of cpu migration or IRQ */
	freelist = c->freelist;
	if (freelist)
		goto load_freelist;

	freelist = get_freelist(s, page);

	if (!freelist) {
		c->page = NULL;
		stat(s, DEACTIVATE_BYPASS);
		goto new_slab;
	}

	stat(s, ALLOC_REFILL);

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

new_slab:

	if (slub_percpu_partial(c)) {
		page = c->page = slub_percpu_partial(c);
		slub_set_percpu_partial(c, page);
		stat(s, CPU_PARTIAL_ALLOC);
		goto redo;
	}

	freelist = new_slab_objects(s, gfpflags, node, &c);

	if (unlikely(!freelist)) {
		slab_out_of_memory(s, gfpflags, node);
		return NULL;
	}

	page = c->page;
	if (likely(!kmem_cache_debug(s) && pfmemalloc_match(page, gfpflags)))
		goto load_freelist;

	/* Only entered in the debug case */
	if (kmem_cache_debug(s) &&
			!alloc_debug_processing(s, page, freelist, addr))
		goto new_slab;	/* Slab failed checks. Next slab needed */

	deactivate_slab(s, page, get_freepointer(s, freelist), c);
	return freelist;
}

/*
 * Another one that disabled interrupt and 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)
{
	void *p;
	unsigned long flags;

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

	p = ___slab_alloc(s, gfpflags, node, addr, c);
	local_irq_restore(flags);
	return p;
}

/*
 * 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)
{
	if (unlikely(slab_want_init_on_free(s)) && obj)
		memset((void *)((char *)kasan_reset_tag(obj) + s->offset),
			0, sizeof(void *));
}

/*
 * 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 __always_inline void *slab_alloc_node(struct kmem_cache *s,
		gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)
{
	void *object;
	struct kmem_cache_cpu *c;
	struct page *page;
	unsigned long tid;
	struct obj_cgroup *objcg = NULL;
	bool init = false;

	s = slab_pre_alloc_hook(s, &objcg, 1, gfpflags);
	if (!s)
		return NULL;

	object = kfence_alloc(s, orig_size, gfpflags);
	if (unlikely(object))
		goto out;

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 should guarantee that tid and kmem_cache are retrieved on
	 * the same cpu. It could be different if CONFIG_PREEMPTION so we need
	 * to check if it is matched or not.
	 */
	do {
		tid = this_cpu_read(s->cpu_slab->tid);
		c = raw_cpu_ptr(s->cpu_slab);
	} while (IS_ENABLED(CONFIG_PREEMPTION) &&
		 unlikely(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 page associated with previous tid
	 * won't be used with current tid. If we fetch tid first, object and
	 * page 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;
	page = c->page;
	if (unlikely(!object || !page || !node_match(page, node))) {
		object = __slab_alloc(s, gfpflags, node, addr, c);
	} 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(!this_cpu_cmpxchg_double(
				s->cpu_slab->freelist, s->cpu_slab->tid,
				object, tid,
				next_object, next_tid(tid)))) {

			note_cmpxchg_failure("slab_alloc", s, tid);
			goto redo;
		}
		prefetch_freepointer(s, next_object);
		stat(s, ALLOC_FASTPATH);
	}

	maybe_wipe_obj_freeptr(s, object);
	init = slab_want_init_on_alloc(gfpflags, s);

out:
	slab_post_alloc_hook(s, objcg, gfpflags, 1, &object, init);

	return object;
}

static __always_inline void *slab_alloc(struct kmem_cache *s,
		gfp_t gfpflags, unsigned long addr, size_t orig_size)
{
	return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr, orig_size);
}

void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
{
	void *ret = slab_alloc(s, gfpflags, _RET_IP_, s->object_size);

	trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size,
				s->size, gfpflags);

	return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc);

#ifdef CONFIG_TRACING
void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
{
	void *ret = slab_alloc(s, gfpflags, _RET_IP_, size);
	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
	ret = kasan_kmalloc(s, ret, size, gfpflags);
	return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_trace);
#endif

#ifdef CONFIG_NUMA
void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
{
	void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_, s->object_size);

	trace_kmem_cache_alloc_node(_RET_IP_, ret,
				    s->object_size, s->size, gfpflags, node);

	return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node);

#ifdef CONFIG_TRACING
void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
				    gfp_t gfpflags,
				    int node, size_t size)
{
	void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_, size);

	trace_kmalloc_node(_RET_IP_, ret,
			   size, s->size, gfpflags, node);

	ret = kasan_kmalloc(s, ret, size, gfpflags);
	return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
#endif
#endif	/* CONFIG_NUMA */

/*
 * 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 page
 * handling required then we can return immediately.
 */
static void __slab_free(struct kmem_cache *s, struct page *page,
			void *head, void *tail, int cnt,
			unsigned long addr)

{
	void *prior;
	int was_frozen;
	struct page new;
	unsigned long counters;
	struct kmem_cache_node *n = NULL;
	unsigned long flags;

	stat(s, FREE_SLOWPATH);

	if (kfence_free(head))
		return;

	if (kmem_cache_debug(s) &&
	    !free_debug_processing(s, page, head, tail, cnt, addr))
		return;

	do {
		if (unlikely(n)) {
			spin_unlock_irqrestore(&n->list_lock, flags);
			n = NULL;
		}
		prior = page->freelist;
		counters = page->counters;
		set_freepointer(s, tail, prior);
		new.counters = counters;
		was_frozen = new.frozen;
		new.inuse -= cnt;
		if ((!new.inuse || !prior) && !was_frozen) {

			if (kmem_cache_has_cpu_partial(s) && !prior) {

				/*
				 * Slab was on no list before and will be
				 * partially empty
				 * We can defer the list move and instead
				 * freeze it.
				 */
				new.frozen = 1;

			} else { /* Needs to be taken off a list */

				n = get_node(s, page_to_nid(page));
				/*
				 * Speculatively acquire the list_lock.
				 * If the cmpxchg does not succeed then we may
				 * drop the list_lock without any processing.
				 *
				 * Otherwise the list_lock will synchronize with
				 * other processors updating the list of slabs.
				 */
				spin_lock_irqsave(&n->list_lock, flags);

			}
		}

	} while (!cmpxchg_double_slab(s, page,
		prior, counters,
		head, new.counters,
		"__slab_free"));

	if (likely(!n)) {

		if (likely(was_frozen)) {
			/*
			 * The list lock was not taken therefore no list
			 * activity can be necessary.
			 */
			stat(s, FREE_FROZEN);
		} else if (new.frozen) {
			/*
			 * If we just froze the page then put it onto the
			 * per cpu partial list.
			 */
			put_cpu_partial(s, page, 1);
			stat(s, CPU_PARTIAL_FREE);
		}

		return;
	}

	if (unlikely(!new.inuse && n->nr_partial >= s->min_partial))
		goto slab_empty;

	/*
	 * Objects left in the slab. If it was not on the partial list before
	 * then add it.
	 */
	if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) {
		remove_full(s, n, page);
		add_partial(n, page, DEACTIVATE_TO_TAIL);
		stat(s, FREE_ADD_PARTIAL);
	}
	spin_unlock_irqrestore(&n->list_lock, flags);
	return;

slab_empty:
	if (prior) {
		/*
		 * Slab on the partial list.
		 */
		remove_partial(n, page);
		stat(s, FREE_REMOVE_PARTIAL);
	} else {
		/* Slab must be on the full list */
		remove_full(s, n, page);
	}

	spin_unlock_irqrestore(&n->list_lock, flags);
	stat(s, FREE_SLAB);
	discard_slab(s, page);
}

/*
 * 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 page) 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 page *page, void *head, void *tail,
				int cnt, unsigned long addr)
{
	void *tail_obj = tail ? : head;
	struct kmem_cache_cpu *c;
	unsigned long tid;

	/* memcg_slab_free_hook() is already called for bulk free. */
	if (!tail)
		memcg_slab_free_hook(s, &head, 1);
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.