slab.h 23.0 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 */
2 3 4 5 6 7
#ifndef MM_SLAB_H
#define MM_SLAB_H
/*
 * Internal slab definitions
 */

8 9 10
/* Reuses the bits in struct page */
struct slab {
	unsigned long __page_flags;
11 12 13

#if defined(CONFIG_SLAB)

14 15
	union {
		struct list_head slab_list;
16 17 18 19 20 21 22 23 24 25 26 27 28
		struct rcu_head rcu_head;
	};
	struct kmem_cache *slab_cache;
	void *freelist;	/* array of free object indexes */
	void *s_mem;	/* first object */
	unsigned int active;

#elif defined(CONFIG_SLUB)

	union {
		struct list_head slab_list;
		struct rcu_head rcu_head;
		struct {
29 30 31 32 33 34 35 36
			struct slab *next;
#ifdef CONFIG_64BIT
			int slabs;	/* Nr of slabs left */
#else
			short int slabs;
#endif
		};
	};
37
	struct kmem_cache *slab_cache;
38 39 40
	/* Double-word boundary */
	void *freelist;		/* first free object */
	union {
41 42
		unsigned long counters;
		struct {
43 44 45 46 47
			unsigned inuse:16;
			unsigned objects:15;
			unsigned frozen:1;
		};
	};
48 49 50 51 52 53 54 55 56 57 58 59 60
	unsigned int __unused;

#elif defined(CONFIG_SLOB)

	struct list_head slab_list;
	void *__unused_1;
	void *freelist;		/* first free block */
	void *__unused_2;
	int units;

#else
#error "Unexpected slab allocator configured"
#endif
61 62 63 64 65 66 67 68 69 70 71 72

	atomic_t __page_refcount;
#ifdef CONFIG_MEMCG
	unsigned long memcg_data;
#endif
};

#define SLAB_MATCH(pg, sl)						\
	static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl))
SLAB_MATCH(flags, __page_flags);
SLAB_MATCH(compound_head, slab_list);	/* Ensure bit 0 is clear */
SLAB_MATCH(slab_list, slab_list);
73
#ifndef CONFIG_SLOB
74 75
SLAB_MATCH(rcu_head, rcu_head);
SLAB_MATCH(slab_cache, slab_cache);
76 77
#endif
#ifdef CONFIG_SLAB
78 79
SLAB_MATCH(s_mem, s_mem);
SLAB_MATCH(active, active);
80
#endif
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
SLAB_MATCH(_refcount, __page_refcount);
#ifdef CONFIG_MEMCG
SLAB_MATCH(memcg_data, memcg_data);
#endif
#undef SLAB_MATCH
static_assert(sizeof(struct slab) <= sizeof(struct page));

/**
 * folio_slab - Converts from folio to slab.
 * @folio: The folio.
 *
 * Currently struct slab is a different representation of a folio where
 * folio_test_slab() is true.
 *
 * Return: The slab which contains this folio.
 */
#define folio_slab(folio)	(_Generic((folio),			\
	const struct folio *:	(const struct slab *)(folio),		\
	struct folio *:		(struct slab *)(folio)))

/**
 * slab_folio - The folio allocated for a slab
 * @slab: The slab.
 *
 * Slabs are allocated as folios that contain the individual objects and are
 * using some fields in the first struct page of the folio - those fields are
 * now accessed by struct slab. It is occasionally necessary to convert back to
 * a folio in order to communicate with the rest of the mm.  Please use this
 * helper function instead of casting yourself, as the implementation may change
 * in the future.
 */
#define slab_folio(s)		(_Generic((s),				\
	const struct slab *:	(const struct folio *)s,		\
	struct slab *:		(struct folio *)s))

/**
 * page_slab - Converts from first struct page to slab.
 * @p: The first (either head of compound or single) page of slab.
 *
 * A temporary wrapper to convert struct page to struct slab in situations where
 * we know the page is the compound head, or single order-0 page.
 *
 * Long-term ideally everything would work with struct slab directly or go
 * through folio to struct slab.
 *
 * Return: The slab which contains this page
 */
#define page_slab(p)		(_Generic((p),				\
	const struct page *:	(const struct slab *)(p),		\
	struct page *:		(struct slab *)(p)))

/**
 * slab_page - The first struct page allocated for a slab
 * @slab: The slab.
 *
 * A convenience wrapper for converting slab to the first struct page of the
 * underlying folio, to communicate with code not yet converted to folio or
 * struct slab.
 */
#define slab_page(s) folio_page(slab_folio(s), 0)

/*
 * If network-based swap is enabled, sl*b must keep track of whether pages
 * were allocated from pfmemalloc reserves.
 */
static inline bool slab_test_pfmemalloc(const struct slab *slab)
{
	return folio_test_active((struct folio *)slab_folio(slab));
}

static inline void slab_set_pfmemalloc(struct slab *slab)
{
	folio_set_active(slab_folio(slab));
}

static inline void slab_clear_pfmemalloc(struct slab *slab)
{
	folio_clear_active(slab_folio(slab));
}

static inline void __slab_clear_pfmemalloc(struct slab *slab)
{
	__folio_clear_active(slab_folio(slab));
}

static inline void *slab_address(const struct slab *slab)
{
	return folio_address(slab_folio(slab));
}

static inline int slab_nid(const struct slab *slab)
{
	return folio_nid(slab_folio(slab));
}

static inline pg_data_t *slab_pgdat(const struct slab *slab)
{
	return folio_pgdat(slab_folio(slab));
}

static inline struct slab *virt_to_slab(const void *addr)
{
	struct folio *folio = virt_to_folio(addr);

	if (!folio_test_slab(folio))
		return NULL;

	return folio_slab(folio);
}

static inline int slab_order(const struct slab *slab)
{
	return folio_order((struct folio *)slab_folio(slab));
}

static inline size_t slab_size(const struct slab *slab)
{
	return PAGE_SIZE << slab_order(slab);
}

201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216
#ifdef CONFIG_SLOB
/*
 * Common fields provided in kmem_cache by all slab allocators
 * This struct is either used directly by the allocator (SLOB)
 * or the allocator must include definitions for all fields
 * provided in kmem_cache_common in their definition of kmem_cache.
 *
 * Once we can do anonymous structs (C11 standard) we could put a
 * anonymous struct definition in these allocators so that the
 * separate allocations in the kmem_cache structure of SLAB and
 * SLUB is no longer needed.
 */
struct kmem_cache {
	unsigned int object_size;/* The original size of the object */
	unsigned int size;	/* The aligned/padded/added on size  */
	unsigned int align;	/* Alignment as calculated */
217
	slab_flags_t flags;	/* Active flags on the slab */
218 219
	unsigned int useroffset;/* Usercopy region offset */
	unsigned int usersize;	/* Usercopy region size */
220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236
	const char *name;	/* Slab name for sysfs */
	int refcount;		/* Use counter */
	void (*ctor)(void *);	/* Called on object slot creation */
	struct list_head list;	/* List of all slab caches on the system */
};

#endif /* CONFIG_SLOB */

#ifdef CONFIG_SLAB
#include <linux/slab_def.h>
#endif

#ifdef CONFIG_SLUB
#include <linux/slub_def.h>
#endif

#include <linux/memcontrol.h>
237 238 239
#include <linux/fault-inject.h>
#include <linux/kasan.h>
#include <linux/kmemleak.h>
240
#include <linux/random.h>
241
#include <linux/sched/mm.h>
242

243 244 245 246 247 248 249 250 251 252 253
/*
 * State of the slab allocator.
 *
 * This is used to describe the states of the allocator during bootup.
 * Allocators use this to gradually bootstrap themselves. Most allocators
 * have the problem that the structures used for managing slab caches are
 * allocated from slab caches themselves.
 */
enum slab_state {
	DOWN,			/* No slab functionality yet */
	PARTIAL,		/* SLUB: kmem_cache_node available */
254
	PARTIAL_NODE,		/* SLAB: kmalloc size for node struct available */
255 256 257 258 259 260
	UP,			/* Slab caches usable but not all extras yet */
	FULL			/* Everything is working */
};

extern enum slab_state slab_state;

261 262
/* The slab cache mutex protects the management structures during changes */
extern struct mutex slab_mutex;
263 264

/* The list of all slab caches on the system */
265 266
extern struct list_head slab_caches;

267 268 269
/* The slab cache that manages slab cache information */
extern struct kmem_cache *kmem_cache;

270 271
/* A table of kmalloc cache names and sizes */
extern const struct kmalloc_info_struct {
272
	const char *name[NR_KMALLOC_TYPES];
273
	unsigned int size;
274 275
} kmalloc_info[];

276 277
#ifndef CONFIG_SLOB
/* Kmalloc array related functions */
278
void setup_kmalloc_cache_index_table(void);
279
void create_kmalloc_caches(slab_flags_t);
280 281 282

/* Find the kmalloc slab corresponding for a certain size */
struct kmem_cache *kmalloc_slab(size_t, gfp_t);
283 284
#endif

285
gfp_t kmalloc_fix_flags(gfp_t flags);
286

287
/* Functions provided by the slab allocators */
288
int __kmem_cache_create(struct kmem_cache *, slab_flags_t flags);
289

290 291 292
struct kmem_cache *create_kmalloc_cache(const char *name, unsigned int size,
			slab_flags_t flags, unsigned int useroffset,
			unsigned int usersize);
293
extern void create_boot_cache(struct kmem_cache *, const char *name,
294 295
			unsigned int size, slab_flags_t flags,
			unsigned int useroffset, unsigned int usersize);
296

297
int slab_unmergeable(struct kmem_cache *s);
298
struct kmem_cache *find_mergeable(unsigned size, unsigned align,
299
		slab_flags_t flags, const char *name, void (*ctor)(void *));
J
Joonsoo Kim 已提交
300
#ifndef CONFIG_SLOB
301
struct kmem_cache *
302
__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
303
		   slab_flags_t flags, void (*ctor)(void *));
304

305
slab_flags_t kmem_cache_flags(unsigned int object_size,
306
	slab_flags_t flags, const char *name);
307
#else
308
static inline struct kmem_cache *
309
__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
310
		   slab_flags_t flags, void (*ctor)(void *))
311
{ return NULL; }
312

313
static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
314
	slab_flags_t flags, const char *name)
315 316 317
{
	return flags;
}
318 319 320
#endif


321
/* Legal flag mask for kmem_cache_create(), for various configurations */
322 323
#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \
			 SLAB_CACHE_DMA32 | SLAB_PANIC | \
324
			 SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS )
325 326 327 328 329

#if defined(CONFIG_DEBUG_SLAB)
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
#elif defined(CONFIG_SLUB_DEBUG)
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
330
			  SLAB_TRACE | SLAB_CONSISTENCY_CHECKS)
331 332 333 334 335 336
#else
#define SLAB_DEBUG_FLAGS (0)
#endif

#if defined(CONFIG_SLAB)
#define SLAB_CACHE_FLAGS (SLAB_MEM_SPREAD | SLAB_NOLEAKTRACE | \
V
Vladimir Davydov 已提交
337
			  SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | \
338
			  SLAB_ACCOUNT)
339 340
#elif defined(CONFIG_SLUB)
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
341
			  SLAB_TEMPORARY | SLAB_ACCOUNT)
342
#else
343
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE)
344 345
#endif

346
/* Common flags available with current configuration */
347 348
#define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)

349 350 351 352 353 354 355 356 357 358 359 360 361
/* Common flags permitted for kmem_cache_create */
#define SLAB_FLAGS_PERMITTED (SLAB_CORE_FLAGS | \
			      SLAB_RED_ZONE | \
			      SLAB_POISON | \
			      SLAB_STORE_USER | \
			      SLAB_TRACE | \
			      SLAB_CONSISTENCY_CHECKS | \
			      SLAB_MEM_SPREAD | \
			      SLAB_NOLEAKTRACE | \
			      SLAB_RECLAIM_ACCOUNT | \
			      SLAB_TEMPORARY | \
			      SLAB_ACCOUNT)

362
bool __kmem_cache_empty(struct kmem_cache *);
363
int __kmem_cache_shutdown(struct kmem_cache *);
364
void __kmem_cache_release(struct kmem_cache *);
365
int __kmem_cache_shrink(struct kmem_cache *);
366
void slab_kmem_cache_release(struct kmem_cache *);
367

368 369 370
struct seq_file;
struct file;

371 372 373 374 375 376 377 378 379 380 381 382 383 384 385
struct slabinfo {
	unsigned long active_objs;
	unsigned long num_objs;
	unsigned long active_slabs;
	unsigned long num_slabs;
	unsigned long shared_avail;
	unsigned int limit;
	unsigned int batchcount;
	unsigned int shared;
	unsigned int objects_per_slab;
	unsigned int cache_order;
};

void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s);
386 387
ssize_t slabinfo_write(struct file *file, const char __user *buffer,
		       size_t count, loff_t *ppos);
G
Glauber Costa 已提交
388

389 390 391
/*
 * Generic implementation of bulk operations
 * These are useful for situations in which the allocator cannot
J
Jesper Dangaard Brouer 已提交
392
 * perform optimizations. In that case segments of the object listed
393 394 395
 * may be allocated or freed using these operations.
 */
void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
396
int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
397

398
static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s)
399 400
{
	return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
401
		NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
402 403
}

404 405 406 407 408 409 410
#ifdef CONFIG_SLUB_DEBUG
#ifdef CONFIG_SLUB_DEBUG_ON
DECLARE_STATIC_KEY_TRUE(slub_debug_enabled);
#else
DECLARE_STATIC_KEY_FALSE(slub_debug_enabled);
#endif
extern void print_tracking(struct kmem_cache *s, void *object);
411
long validate_slab_cache(struct kmem_cache *s);
412 413 414 415
static inline bool __slub_debug_enabled(void)
{
	return static_branch_unlikely(&slub_debug_enabled);
}
416 417 418 419
#else
static inline void print_tracking(struct kmem_cache *s, void *object)
{
}
420 421 422 423
static inline bool __slub_debug_enabled(void)
{
	return false;
}
424 425 426 427 428 429 430 431 432
#endif

/*
 * Returns true if any of the specified slub_debug flags is enabled for the
 * cache. Use only for flags parsed by setup_slub_debug() as it also enables
 * the static key.
 */
static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags)
{
433 434 435
	if (IS_ENABLED(CONFIG_SLUB_DEBUG))
		VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS));
	if (__slub_debug_enabled())
436 437 438 439
		return s->flags & flags;
	return false;
}

440
#ifdef CONFIG_MEMCG_KMEM
441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460
/*
 * slab_objcgs - get the object cgroups vector associated with a slab
 * @slab: a pointer to the slab struct
 *
 * Returns a pointer to the object cgroups vector associated with the slab,
 * or NULL if no such vector has been associated yet.
 */
static inline struct obj_cgroup **slab_objcgs(struct slab *slab)
{
	unsigned long memcg_data = READ_ONCE(slab->memcg_data);

	VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS),
							slab_page(slab));
	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, slab_page(slab));

	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
}

int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s,
				 gfp_t gfp, bool new_slab);
461 462
void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
		     enum node_stat_item idx, int nr);
463

464
static inline void memcg_free_slab_cgroups(struct slab *slab)
465
{
466 467
	kfree(slab_objcgs(slab));
	slab->memcg_data = 0;
468 469
}

470 471 472 473 474 475 476 477 478
static inline size_t obj_full_size(struct kmem_cache *s)
{
	/*
	 * For each accounted object there is an extra space which is used
	 * to store obj_cgroup membership. Charge it too.
	 */
	return s->size + sizeof(struct obj_cgroup *);
}

479 480 481 482 483 484
/*
 * Returns false if the allocation should fail.
 */
static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
					     struct obj_cgroup **objcgp,
					     size_t objects, gfp_t flags)
485
{
486 487
	struct obj_cgroup *objcg;

488 489 490 491 492 493
	if (!memcg_kmem_enabled())
		return true;

	if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT))
		return true;

494 495
	objcg = get_obj_cgroup_from_current();
	if (!objcg)
496
		return true;
497 498 499

	if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) {
		obj_cgroup_put(objcg);
500
		return false;
501 502
	}

503 504
	*objcgp = objcg;
	return true;
505 506
}

507 508
static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
					      struct obj_cgroup *objcg,
509 510
					      gfp_t flags, size_t size,
					      void **p)
511
{
512
	struct slab *slab;
513 514 515
	unsigned long off;
	size_t i;

516
	if (!memcg_kmem_enabled() || !objcg)
517 518
		return;

519 520
	for (i = 0; i < size; i++) {
		if (likely(p[i])) {
521
			slab = virt_to_slab(p[i]);
522

523 524
			if (!slab_objcgs(slab) &&
			    memcg_alloc_slab_cgroups(slab, s, flags,
525
							 false)) {
526 527 528 529
				obj_cgroup_uncharge(objcg, obj_full_size(s));
				continue;
			}

530
			off = obj_to_index(s, slab, p[i]);
531
			obj_cgroup_get(objcg);
532 533
			slab_objcgs(slab)[off] = objcg;
			mod_objcg_state(objcg, slab_pgdat(slab),
534 535 536
					cache_vmstat_idx(s), obj_full_size(s));
		} else {
			obj_cgroup_uncharge(objcg, obj_full_size(s));
537 538 539 540 541
		}
	}
	obj_cgroup_put(objcg);
}

542 543
static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
					void **p, int objects)
544
{
545
	struct kmem_cache *s;
546
	struct obj_cgroup **objcgs;
547
	struct obj_cgroup *objcg;
548
	struct slab *slab;
549
	unsigned int off;
550
	int i;
551

552 553 554
	if (!memcg_kmem_enabled())
		return;

555 556 557
	for (i = 0; i < objects; i++) {
		if (unlikely(!p[i]))
			continue;
558

559 560 561 562 563 564
		slab = virt_to_slab(p[i]);
		/* we could be given a kmalloc_large() object, skip those */
		if (!slab)
			continue;

		objcgs = slab_objcgs(slab);
565
		if (!objcgs)
566
			continue;
567

568
		if (!s_orig)
569
			s = slab->slab_cache;
570 571
		else
			s = s_orig;
572

573
		off = obj_to_index(s, slab, p[i]);
574
		objcg = objcgs[off];
575 576
		if (!objcg)
			continue;
577

578
		objcgs[off] = NULL;
579
		obj_cgroup_uncharge(objcg, obj_full_size(s));
580
		mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s),
581 582 583
				-obj_full_size(s));
		obj_cgroup_put(objcg);
	}
584 585
}

586
#else /* CONFIG_MEMCG_KMEM */
587 588 589 590 591
static inline struct obj_cgroup **slab_objcgs(struct slab *slab)
{
	return NULL;
}

592
static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
593 594 595 596
{
	return NULL;
}

597
static inline int memcg_alloc_slab_cgroups(struct slab *slab,
598
					       struct kmem_cache *s, gfp_t gfp,
599
					       bool new_slab)
600 601 602 603
{
	return 0;
}

604
static inline void memcg_free_slab_cgroups(struct slab *slab)
605 606 607
{
}

608 609 610
static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
					     struct obj_cgroup **objcgp,
					     size_t objects, gfp_t flags)
611
{
612
	return true;
613 614
}

615 616
static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
					      struct obj_cgroup *objcg,
617 618
					      gfp_t flags, size_t size,
					      void **p)
619 620 621
{
}

622 623
static inline void memcg_slab_free_hook(struct kmem_cache *s,
					void **p, int objects)
624 625
{
}
626
#endif /* CONFIG_MEMCG_KMEM */
627

628
#ifndef CONFIG_SLOB
629 630
static inline struct kmem_cache *virt_to_cache(const void *obj)
{
631
	struct slab *slab;
632

633 634
	slab = virt_to_slab(obj);
	if (WARN_ONCE(!slab, "%s: Object is not a Slab page!\n",
635 636
					__func__))
		return NULL;
637
	return slab->slab_cache;
638 639
}

640 641
static __always_inline void account_slab(struct slab *slab, int order,
					 struct kmem_cache *s, gfp_t gfp)
642
{
643
	if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
644
		memcg_alloc_slab_cgroups(slab, s, gfp, true);
645

646
	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
647
			    PAGE_SIZE << order);
648 649
}

650 651
static __always_inline void unaccount_slab(struct slab *slab, int order,
					   struct kmem_cache *s)
652
{
653
	if (memcg_kmem_enabled())
654
		memcg_free_slab_cgroups(slab);
655

656
	mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
657
			    -(PAGE_SIZE << order));
658 659
}

660 661 662 663 664 665 666 667 668
static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
{
	struct kmem_cache *cachep;

	if (!IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
	    !kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS))
		return s;

	cachep = virt_to_cache(x);
669
	if (WARN(cachep && cachep != s,
670 671 672 673 674
		  "%s: Wrong slab cache. %s but object is from %s\n",
		  __func__, s->name, cachep->name))
		print_tracking(cachep, x);
	return cachep;
}
675
#endif /* CONFIG_SLOB */
676

677 678 679 680 681 682 683 684 685 686 687 688 689 690
static inline size_t slab_ksize(const struct kmem_cache *s)
{
#ifndef CONFIG_SLUB
	return s->object_size;

#else /* CONFIG_SLUB */
# ifdef CONFIG_SLUB_DEBUG
	/*
	 * Debugging requires use of the padding between object
	 * and whatever may come after it.
	 */
	if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
		return s->object_size;
# endif
691 692
	if (s->flags & SLAB_KASAN)
		return s->object_size;
693 694 695 696 697
	/*
	 * If we have the need to store the freelist pointer
	 * back there or track user information then we can
	 * only use the space before that information.
	 */
698
	if (s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER))
699 700 701 702 703 704 705 706 707
		return s->inuse;
	/*
	 * Else we can use all the padding etc for the allocation
	 */
	return s->size;
#endif
}

static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
708 709
						     struct obj_cgroup **objcgp,
						     size_t size, gfp_t flags)
710 711
{
	flags &= gfp_allowed_mask;
712

713
	might_alloc(flags);
714

715
	if (should_failslab(s, flags))
716 717
		return NULL;

718 719
	if (!memcg_slab_pre_alloc_hook(s, objcgp, size, flags))
		return NULL;
720 721

	return s;
722 723
}

724
static inline void slab_post_alloc_hook(struct kmem_cache *s,
725 726
					struct obj_cgroup *objcg, gfp_t flags,
					size_t size, void **p, bool init)
727 728 729 730
{
	size_t i;

	flags &= gfp_allowed_mask;
731 732 733 734 735 736 737 738

	/*
	 * As memory initialization might be integrated into KASAN,
	 * kasan_slab_alloc and initialization memset must be
	 * kept together to avoid discrepancies in behavior.
	 *
	 * As p[i] might get tagged, memset and kmemleak hook come after KASAN.
	 */
739
	for (i = 0; i < size; i++) {
740 741 742
		p[i] = kasan_slab_alloc(s, p[i], flags, init);
		if (p[i] && init && !kasan_has_integrated_init())
			memset(p[i], 0, s->object_size);
743
		kmemleak_alloc_recursive(p[i], s->object_size, 1,
744 745
					 s->flags, flags);
	}
746

747
	memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
748 749
}

750
#ifndef CONFIG_SLOB
751 752 753 754 755 756 757 758 759 760
/*
 * The slab lists for all objects.
 */
struct kmem_cache_node {
	spinlock_t list_lock;

#ifdef CONFIG_SLAB
	struct list_head slabs_partial;	/* partial list first, better asm code */
	struct list_head slabs_full;
	struct list_head slabs_free;
761 762
	unsigned long total_slabs;	/* length of all slab lists */
	unsigned long free_slabs;	/* length of free slab list only */
763 764 765 766
	unsigned long free_objects;
	unsigned int free_limit;
	unsigned int colour_next;	/* Per-node cache coloring */
	struct array_cache *shared;	/* shared per node */
J
Joonsoo Kim 已提交
767
	struct alien_cache **alien;	/* on other nodes */
768 769 770 771 772 773 774 775 776 777 778 779 780 781 782
	unsigned long next_reap;	/* updated without locking */
	int free_touched;		/* updated without locking */
#endif

#ifdef CONFIG_SLUB
	unsigned long nr_partial;
	struct list_head partial;
#ifdef CONFIG_SLUB_DEBUG
	atomic_long_t nr_slabs;
	atomic_long_t total_objects;
	struct list_head full;
#endif
#endif

};
783

784 785 786 787 788 789 790 791 792 793
static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
{
	return s->node[node];
}

/*
 * Iterator over all nodes. The body will be executed for each node that has
 * a kmem_cache_node structure allocated (which is true for all online nodes)
 */
#define for_each_kmem_cache_node(__s, __node, __n) \
794 795
	for (__node = 0; __node < nr_node_ids; __node++) \
		 if ((__n = get_node(__s, __node)))
796 797 798

#endif

799
void *slab_start(struct seq_file *m, loff_t *pos);
800 801
void *slab_next(struct seq_file *m, void *p, loff_t *pos);
void slab_stop(struct seq_file *m, void *p);
802
int memcg_slab_show(struct seq_file *m, void *p);
803

804 805 806 807 808 809 810 811
#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
void dump_unreclaimable_slab(void);
#else
static inline void dump_unreclaimable_slab(void)
{
}
#endif

812 813
void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);

814 815 816 817 818 819 820 821 822 823 824 825 826
#ifdef CONFIG_SLAB_FREELIST_RANDOM
int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count,
			gfp_t gfp);
void cache_random_seq_destroy(struct kmem_cache *cachep);
#else
static inline int cache_random_seq_create(struct kmem_cache *cachep,
					unsigned int count, gfp_t gfp)
{
	return 0;
}
static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { }
#endif /* CONFIG_SLAB_FREELIST_RANDOM */

827 828
static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c)
{
829 830
	if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
				&init_on_alloc)) {
831 832 833 834 835 836 837 838 839 840 841
		if (c->ctor)
			return false;
		if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))
			return flags & __GFP_ZERO;
		return true;
	}
	return flags & __GFP_ZERO;
}

static inline bool slab_want_init_on_free(struct kmem_cache *c)
{
842 843
	if (static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON,
				&init_on_free))
844 845 846 847 848
		return !(c->ctor ||
			 (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)));
	return false;
}

849 850 851 852 853 854
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG)
void debugfs_slab_release(struct kmem_cache *);
#else
static inline void debugfs_slab_release(struct kmem_cache *s) { }
#endif

855
#ifdef CONFIG_PRINTK
856 857 858
#define KS_ADDRS_COUNT 16
struct kmem_obj_info {
	void *kp_ptr;
859
	struct slab *kp_slab;
860 861 862 863 864
	void *kp_objp;
	unsigned long kp_data_offset;
	struct kmem_cache *kp_slab_cache;
	void *kp_ret;
	void *kp_stack[KS_ADDRS_COUNT];
865
	void *kp_free_stack[KS_ADDRS_COUNT];
866
};
867
void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab);
868
#endif
869

870 871 872 873 874 875 876 877 878 879 880
#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
void __check_heap_object(const void *ptr, unsigned long n,
			 const struct slab *slab, bool to_user);
#else
static inline
void __check_heap_object(const void *ptr, unsigned long n,
			 const struct slab *slab, bool to_user)
{
}
#endif

881
#endif /* MM_SLAB_H */