slub.c

/*
 * 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/bitops.h>
#include <linux/slab.h>
#include "slab.h"
#include <linux/proc_fs.h>
#include <linux/notifier.h>
#include <linux/seq_file.h>
#include <linux/kasan.h>
#include <linux/kmemcheck.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/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 <trace/events/kmem.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 the second
 *   double word in the page struct. Meaning
 *	A. page->freelist	-> List of object free in a page
 *	B. page->counters	-> Counters of objects
 *	C. page->frozen		-> frozen state
 *
 *   If a slab is frozen then it is exempt from list management. It is not
 *   on any 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.
 *
 * Overloading of page flags that are otherwise used for LRU management.
 *
 * PageActive 		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.
 *
 * PageError		Slab requires special handling due to debug
 * 			options set. This moves	slab handling out of
 * 			the fast path and disables lockless freelists.
 */

static inline int kmem_cache_debug(struct kmem_cache *s)
{
#ifdef CONFIG_SLUB_DEBUG
	return unlikely(s->flags & SLAB_DEBUG_FLAGS);
#else
	return 0;
#endif
}

void *fixup_red_left(struct kmem_cache *s, void *p)
{
	if (kmem_cache_debug(s) && s->flags & 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 */
#define __OBJECT_POISON		0x80000000UL /* Poison object */
#define __CMPXCHG_DOUBLE	0x40000000UL /* Use cmpxchg_double */

/*
 * Tracking user of a slab.
 */
#define TRACK_ADDRS_COUNT 16
struct track {
	unsigned long addr;	/* Called from address */
#ifdef CONFIG_STACKTRACE
	unsigned long addrs[TRACK_ADDRS_COUNT];	/* Called from address */
#endif
	int cpu;		/* Was running on cpu */
	int pid;		/* Pid context */
	unsigned long when;	/* When did the operation occur */
};

enum track_item { TRACK_ALLOC, TRACK_FREE };

#ifdef CONFIG_SYSFS
static int sysfs_slab_add(struct kmem_cache *);
static int sysfs_slab_alias(struct kmem_cache *, const char *);
static void memcg_propagate_slab_attrs(struct kmem_cache *s);
static void sysfs_slab_remove(struct kmem_cache *s);
#else
static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
							{ return 0; }
static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
static inline void sysfs_slab_remove(struct kmem_cache *s) { }
#endif

static inline void stat(const struct kmem_cache *s, enum stat_item si)
{
#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
	return (void *)((unsigned long)ptr ^ s->random ^ 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)
{
	return freelist_dereference(s, object + s->offset);
}

static void prefetch_freepointer(const struct kmem_cache *s, void *object)
{
	if (object)
		prefetch(freelist_dereference(s, 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())
		return get_freepointer(s, object);

	freepointer_addr = (unsigned long)object + s->offset;
	probe_kernel_read(&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

	*(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)

#define for_each_object_idx(__p, __idx, __s, __addr, __objects) \
	for (__p = fixup_red_left(__s, __addr), __idx = 1; \
		__idx <= __objects; \
		__p += (__s)->size, __idx++)

/* Determine object index from a given position */
static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
{
	return (p - addr) / s->size;
}

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

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

	return x;
}

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

static inline 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);
}

static inline void set_page_slub_counters(struct page *page, unsigned long counters_new)
{
	struct page tmp;
	tmp.counters = counters_new;
	/*
	 * page->counters can cover frozen/inuse/objects as well
	 * as page->_refcount.  If we assign to ->counters directly
	 * we run the risk of losing updates to page->_refcount, so
	 * be careful and only assign to the fields we need.
	 */
	page->frozen  = tmp.frozen;
	page->inuse   = tmp.inuse;
	page->objects = tmp.objects;
}

/* 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;
			set_page_slub_counters(page, 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;
			set_page_slub_counters(page, 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
/*
 * 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 void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
{
	void *p;
	void *addr = page_address(page);

	for (p = page->freelist; p; p = get_freepointer(s, p))
		set_bit(slab_index(p, s, addr), map);
}

static inline 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 int slub_debug = DEBUG_DEFAULT_FLAGS;
#else
static int slub_debug;
#endif

static char *slub_debug_slabs;
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 = 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, addr,
			length, 1);
	metadata_access_disable();
}

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

	if (s->offset)
		p = object + s->offset + sizeof(void *);
	else
		p = object + s->inuse;

	return p + alloc;
}

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
		struct stack_trace trace;
		int i;

		trace.nr_entries = 0;
		trace.max_entries = TRACK_ADDRS_COUNT;
		trace.entries = p->addrs;
		trace.skip = 3;
		metadata_access_enable();
		save_stack_trace(&trace);
		metadata_access_disable();

		/* See rant in lockdep.c */
		if (trace.nr_entries != 0 &&
		    trace.entries[trace.nr_entries - 1] == ULONG_MAX)
			trace.nr_entries--;

		for (i = trace.nr_entries; i < TRACK_ADDRS_COUNT; i++)
			p->addrs[i] = 0;
#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)
{
	if (!t->addr)
		return;

	pr_err("INFO: %s in %pS age=%lu cpu=%u pid=%d\n",
	       s, (void *)t->addr, jiffies - 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
}

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

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

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");

	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
	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 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 long, 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);

	if (s->offset)
		off = s->offset + sizeof(void *);
	else
		off = s->inuse;

	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);
}

static 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();
}

static void init_object(struct kmem_cache *s, void *object, u8 val)
{
	u8 *p = 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;

	metadata_access_enable();
	fault = memchr_inv(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. First byte 0x%x instead of 0x%x\n",
					fault, end - 1, fault[0], value);
	print_trailer(s, page, object);

	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 the first word 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 = s->inuse;	/* The end of info */

	if (s->offset)
		/* Freepointer is placed after the object. */
		off += sizeof(void *);

	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;
	int length;
	int remainder;

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

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

	metadata_access_enable();
	fault = memchr_inv(end - remainder, 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", fault, end - 1);
	print_section(KERN_ERR, "Padding ", end - remainder, remainder);

	restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, 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, "Redzone",
			object - s->red_left_pad, val, s->red_left_pad))
			return 0;

		if (!check_bytes_and_report(s, page, object, "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, "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 (!s->offset && 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, s->reserved);
	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, s->reserved);
	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->lru, &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->lru);
}

/* 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 */