slab.h 14.4 KB
Newer Older
L
Linus Torvalds 已提交
1
/*
2 3
 * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk).
 *
C
Christoph Lameter 已提交
4
 * (C) SGI 2006, Christoph Lameter
5 6
 * 	Cleaned up and restructured to ease the addition of alternative
 * 	implementations of SLAB allocators.
L
Linus Torvalds 已提交
7 8 9 10 11
 */

#ifndef _LINUX_SLAB_H
#define	_LINUX_SLAB_H

12 13
#include <linux/gfp.h>
#include <linux/types.h>
G
Glauber Costa 已提交
14 15
#include <linux/workqueue.h>

L
Linus Torvalds 已提交
16

17 18 19
/*
 * Flags to pass to kmem_cache_create().
 * The ones marked DEBUG are only valid if CONFIG_SLAB_DEBUG is set.
L
Linus Torvalds 已提交
20
 */
C
Christoph Lameter 已提交
21 22 23 24
#define SLAB_DEBUG_FREE		0x00000100UL	/* DEBUG: Perform (expensive) checks on free */
#define SLAB_RED_ZONE		0x00000400UL	/* DEBUG: Red zone objs in a cache */
#define SLAB_POISON		0x00000800UL	/* DEBUG: Poison objects */
#define SLAB_HWCACHE_ALIGN	0x00002000UL	/* Align objs on cache lines */
25 26 27
#define SLAB_CACHE_DMA		0x00004000UL	/* Use GFP_DMA memory */
#define SLAB_STORE_USER		0x00010000UL	/* DEBUG: Store the last owner for bug hunting */
#define SLAB_PANIC		0x00040000UL	/* Panic if kmem_cache_create() fails */
28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55
/*
 * SLAB_DESTROY_BY_RCU - **WARNING** READ THIS!
 *
 * This delays freeing the SLAB page by a grace period, it does _NOT_
 * delay object freeing. This means that if you do kmem_cache_free()
 * that memory location is free to be reused at any time. Thus it may
 * be possible to see another object there in the same RCU grace period.
 *
 * This feature only ensures the memory location backing the object
 * stays valid, the trick to using this is relying on an independent
 * object validation pass. Something like:
 *
 *  rcu_read_lock()
 * again:
 *  obj = lockless_lookup(key);
 *  if (obj) {
 *    if (!try_get_ref(obj)) // might fail for free objects
 *      goto again;
 *
 *    if (obj->key != key) { // not the object we expected
 *      put_ref(obj);
 *      goto again;
 *    }
 *  }
 *  rcu_read_unlock();
 *
 * See also the comment on struct slab_rcu in mm/slab.c.
 */
56
#define SLAB_DESTROY_BY_RCU	0x00080000UL	/* Defer freeing slabs to RCU */
57
#define SLAB_MEM_SPREAD		0x00100000UL	/* Spread some memory over cpuset */
C
Christoph Lameter 已提交
58
#define SLAB_TRACE		0x00200000UL	/* Trace allocations and frees */
L
Linus Torvalds 已提交
59

60 61 62 63 64 65 66
/* Flag to prevent checks on free */
#ifdef CONFIG_DEBUG_OBJECTS
# define SLAB_DEBUG_OBJECTS	0x00400000UL
#else
# define SLAB_DEBUG_OBJECTS	0x00000000UL
#endif

67 68
#define SLAB_NOLEAKTRACE	0x00800000UL	/* Avoid kmemleak tracing */

V
Vegard Nossum 已提交
69 70 71 72 73 74
/* Don't track use of uninitialized memory */
#ifdef CONFIG_KMEMCHECK
# define SLAB_NOTRACK		0x01000000UL
#else
# define SLAB_NOTRACK		0x00000000UL
#endif
75 76 77 78 79
#ifdef CONFIG_FAILSLAB
# define SLAB_FAILSLAB		0x02000000UL	/* Fault injection mark */
#else
# define SLAB_FAILSLAB		0x00000000UL
#endif
V
Vegard Nossum 已提交
80

81 82 83
/* The following flags affect the page allocator grouping pages by mobility */
#define SLAB_RECLAIM_ACCOUNT	0x00020000UL		/* Objects are reclaimable */
#define SLAB_TEMPORARY		SLAB_RECLAIM_ACCOUNT	/* Objects are short-lived */
84 85 86 87 88 89 90 91 92 93
/*
 * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests.
 *
 * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault.
 *
 * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can.
 * Both make kfree a no-op.
 */
#define ZERO_SIZE_PTR ((void *)16)

94
#define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \
95 96
				(unsigned long)ZERO_SIZE_PTR)

97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120
/*
 * 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.
 */
#ifdef CONFIG_SLOB
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 */
	unsigned long flags;	/* Active flags on the slab */
	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

121
struct mem_cgroup;
122 123 124 125
/*
 * struct kmem_cache related prototypes
 */
void __init kmem_cache_init(void);
C
Christoph Lameter 已提交
126
int slab_is_available(void);
L
Linus Torvalds 已提交
127

128
struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
129
			unsigned long,
130
			void (*)(void *));
131 132
struct kmem_cache *
kmem_cache_create_memcg(struct mem_cgroup *, const char *, size_t, size_t,
G
Glauber Costa 已提交
133
			unsigned long, void (*)(void *), struct kmem_cache *);
134 135 136 137
void kmem_cache_destroy(struct kmem_cache *);
int kmem_cache_shrink(struct kmem_cache *);
void kmem_cache_free(struct kmem_cache *, void *);

138 139 140 141 142 143 144 145 146 147
/*
 * Please use this macro to create slab caches. Simply specify the
 * name of the structure and maybe some flags that are listed above.
 *
 * The alignment of the struct determines object alignment. If you
 * f.e. add ____cacheline_aligned_in_smp to the struct declaration
 * then the objects will be properly aligned in SMP configurations.
 */
#define KMEM_CACHE(__struct, __flags) kmem_cache_create(#__struct,\
		sizeof(struct __struct), __alignof__(struct __struct),\
148
		(__flags), NULL)
149

150 151 152 153 154 155 156 157 158
/*
 * The largest kmalloc size supported by the slab allocators is
 * 32 megabyte (2^25) or the maximum allocatable page order if that is
 * less than 32 MB.
 *
 * WARNING: Its not easy to increase this value since the allocators have
 * to do various tricks to work around compiler limitations in order to
 * ensure proper constant folding.
 */
159 160
#define KMALLOC_SHIFT_HIGH	((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \
				(MAX_ORDER + PAGE_SHIFT - 1) : 25)
161 162 163 164

#define KMALLOC_MAX_SIZE	(1UL << KMALLOC_SHIFT_HIGH)
#define KMALLOC_MAX_ORDER	(KMALLOC_SHIFT_HIGH - PAGE_SHIFT)

165 166 167 168 169
/*
 * Some archs want to perform DMA into kmalloc caches and need a guaranteed
 * alignment larger than the alignment of a 64-bit integer.
 * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that.
 */
170 171 172 173 174 175
#ifdef ARCH_DMA_MINALIGN
#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN
#else
#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
#endif

176 177 178 179 180
/*
 * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment.
 * Intended for arches that get misalignment faults even for 64 bit integer
 * aligned buffers.
 */
181 182 183
#ifndef ARCH_SLAB_MINALIGN
#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
#endif
G
Glauber Costa 已提交
184 185 186 187 188 189 190 191 192 193 194 195 196 197 198
/*
 * This is the main placeholder for memcg-related information in kmem caches.
 * struct kmem_cache will hold a pointer to it, so the memory cost while
 * disabled is 1 pointer. The runtime cost while enabled, gets bigger than it
 * would otherwise be if that would be bundled in kmem_cache: we'll need an
 * extra pointer chase. But the trade off clearly lays in favor of not
 * penalizing non-users.
 *
 * Both the root cache and the child caches will have it. For the root cache,
 * this will hold a dynamically allocated array large enough to hold
 * information about the currently limited memcgs in the system.
 *
 * Child caches will hold extra metadata needed for its operation. Fields are:
 *
 * @memcg: pointer to the memcg this cache belongs to
199 200
 * @list: list_head for the list of all caches in this memcg
 * @root_cache: pointer to the global, root cache, this cache was derived from
G
Glauber Costa 已提交
201 202 203 204
 * @dead: set to true after the memcg dies; the cache may still be around.
 * @nr_pages: number of pages that belongs to this cache.
 * @destroy: worker to be called whenever we are ready, or believe we may be
 *           ready, to destroy this cache.
G
Glauber Costa 已提交
205 206 207 208 209
 */
struct memcg_cache_params {
	bool is_root_cache;
	union {
		struct kmem_cache *memcg_caches[0];
210 211 212 213
		struct {
			struct mem_cgroup *memcg;
			struct list_head list;
			struct kmem_cache *root_cache;
G
Glauber Costa 已提交
214 215 216
			bool dead;
			atomic_t nr_pages;
			struct work_struct destroy;
217
		};
G
Glauber Costa 已提交
218 219 220
	};
};

221 222
int memcg_update_all_caches(int num_memcgs);

223 224 225 226
struct seq_file;
int cache_show(struct kmem_cache *s, struct seq_file *m);
void print_slabinfo_header(struct seq_file *m);

227 228 229
/*
 * Common kmalloc functions provided by all allocators
 */
230
void * __must_check __krealloc(const void *, size_t, gfp_t);
P
Pekka Enberg 已提交
231
void * __must_check krealloc(const void *, size_t, gfp_t);
232
void kfree(const void *);
J
Johannes Weiner 已提交
233
void kzfree(const void *);
P
Pekka Enberg 已提交
234
size_t ksize(const void *);
235

236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262
/*
 * Allocator specific definitions. These are mainly used to establish optimized
 * ways to convert kmalloc() calls to kmem_cache_alloc() invocations by
 * selecting the appropriate general cache at compile time.
 *
 * Allocators must define at least:
 *
 *	kmem_cache_alloc()
 *	__kmalloc()
 *	kmalloc()
 *
 * Those wishing to support NUMA must also define:
 *
 *	kmem_cache_alloc_node()
 *	kmalloc_node()
 *
 * See each allocator definition file for additional comments and
 * implementation notes.
 */
#ifdef CONFIG_SLUB
#include <linux/slub_def.h>
#elif defined(CONFIG_SLOB)
#include <linux/slob_def.h>
#else
#include <linux/slab_def.h>
#endif

263
/**
X
Xi Wang 已提交
264
 * kmalloc_array - allocate memory for an array.
265 266 267
 * @n: number of elements.
 * @size: element size.
 * @flags: the type of memory to allocate.
268 269 270 271 272 273 274
 *
 * The @flags argument may be one of:
 *
 * %GFP_USER - Allocate memory on behalf of user.  May sleep.
 *
 * %GFP_KERNEL - Allocate normal kernel ram.  May sleep.
 *
P
Paul Mundt 已提交
275
 * %GFP_ATOMIC - Allocation will not sleep.  May use emergency pools.
276 277 278 279 280 281 282 283
 *   For example, use this inside interrupt handlers.
 *
 * %GFP_HIGHUSER - Allocate pages from high memory.
 *
 * %GFP_NOIO - Do not do any I/O at all while trying to get memory.
 *
 * %GFP_NOFS - Do not make any fs calls while trying to get memory.
 *
P
Paul Mundt 已提交
284 285 286 287 288 289 290 291
 * %GFP_NOWAIT - Allocation will not sleep.
 *
 * %GFP_THISNODE - Allocate node-local memory only.
 *
 * %GFP_DMA - Allocation suitable for DMA.
 *   Should only be used for kmalloc() caches. Otherwise, use a
 *   slab created with SLAB_DMA.
 *
292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308
 * Also it is possible to set different flags by OR'ing
 * in one or more of the following additional @flags:
 *
 * %__GFP_COLD - Request cache-cold pages instead of
 *   trying to return cache-warm pages.
 *
 * %__GFP_HIGH - This allocation has high priority and may use emergency pools.
 *
 * %__GFP_NOFAIL - Indicate that this allocation is in no way allowed to fail
 *   (think twice before using).
 *
 * %__GFP_NORETRY - If memory is not immediately available,
 *   then give up at once.
 *
 * %__GFP_NOWARN - If allocation fails, don't issue any warnings.
 *
 * %__GFP_REPEAT - If allocation fails initially, try once more before failing.
P
Paul Mundt 已提交
309 310 311 312
 *
 * There are other flags available as well, but these are not intended
 * for general use, and so are not documented here. For a full list of
 * potential flags, always refer to linux/gfp.h.
313
 */
X
Xi Wang 已提交
314
static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags)
L
Linus Torvalds 已提交
315
{
X
Xi Wang 已提交
316
	if (size != 0 && n > SIZE_MAX / size)
P
Paul Mundt 已提交
317
		return NULL;
X
Xi Wang 已提交
318 319 320 321 322 323 324 325 326 327 328 329
	return __kmalloc(n * size, flags);
}

/**
 * kcalloc - allocate memory for an array. The memory is set to zero.
 * @n: number of elements.
 * @size: element size.
 * @flags: the type of memory to allocate (see kmalloc).
 */
static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
{
	return kmalloc_array(n, size, flags | __GFP_ZERO);
L
Linus Torvalds 已提交
330 331
}

P
Paul Mundt 已提交
332 333 334 335 336 337 338 339 340 341 342
#if !defined(CONFIG_NUMA) && !defined(CONFIG_SLOB)
/**
 * kmalloc_node - allocate memory from a specific node
 * @size: how many bytes of memory are required.
 * @flags: the type of memory to allocate (see kcalloc).
 * @node: node to allocate from.
 *
 * kmalloc() for non-local nodes, used to allocate from a specific node
 * if available. Equivalent to kmalloc() in the non-NUMA single-node
 * case.
 */
C
Christoph Lameter 已提交
343 344 345 346 347 348 349 350 351
static inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
	return kmalloc(size, flags);
}

static inline void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
	return __kmalloc(size, flags);
}
P
Paul Mundt 已提交
352 353 354 355 356 357 358 359 360

void *kmem_cache_alloc(struct kmem_cache *, gfp_t);

static inline void *kmem_cache_alloc_node(struct kmem_cache *cachep,
					gfp_t flags, int node)
{
	return kmem_cache_alloc(cachep, flags);
}
#endif /* !CONFIG_NUMA && !CONFIG_SLOB */
C
Christoph Lameter 已提交
361

362 363 364 365 366 367 368 369
/*
 * kmalloc_track_caller is a special version of kmalloc that records the
 * calling function of the routine calling it for slab leak tracking instead
 * of just the calling function (confusing, eh?).
 * It's useful when the call to kmalloc comes from a widely-used standard
 * allocator where we care about the real place the memory allocation
 * request comes from.
 */
370
#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \
371 372
	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING)) || \
	(defined(CONFIG_SLOB) && defined(CONFIG_TRACING))
373
extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
374
#define kmalloc_track_caller(size, flags) \
375
	__kmalloc_track_caller(size, flags, _RET_IP_)
376 377 378 379
#else
#define kmalloc_track_caller(size, flags) \
	__kmalloc(size, flags)
#endif /* DEBUG_SLAB */
L
Linus Torvalds 已提交
380

381
#ifdef CONFIG_NUMA
382 383 384 385 386 387 388 389
/*
 * kmalloc_node_track_caller is a special version of kmalloc_node that
 * records the calling function of the routine calling it for slab leak
 * tracking instead of just the calling function (confusing, eh?).
 * It's useful when the call to kmalloc_node comes from a widely-used
 * standard allocator where we care about the real place the memory
 * allocation request comes from.
 */
390
#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_SLUB) || \
391 392
	(defined(CONFIG_SLAB) && defined(CONFIG_TRACING)) || \
	(defined(CONFIG_SLOB) && defined(CONFIG_TRACING))
393
extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long);
394 395
#define kmalloc_node_track_caller(size, flags, node) \
	__kmalloc_node_track_caller(size, flags, node, \
396
			_RET_IP_)
397 398 399
#else
#define kmalloc_node_track_caller(size, flags, node) \
	__kmalloc_node(size, flags, node)
400
#endif
401

402 403 404 405
#else /* CONFIG_NUMA */

#define kmalloc_node_track_caller(size, flags, node) \
	kmalloc_track_caller(size, flags)
406

P
Pascal Terjan 已提交
407
#endif /* CONFIG_NUMA */
408

409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426
/*
 * Shortcuts
 */
static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags)
{
	return kmem_cache_alloc(k, flags | __GFP_ZERO);
}

/**
 * kzalloc - allocate memory. The memory is set to zero.
 * @size: how many bytes of memory are required.
 * @flags: the type of memory to allocate (see kmalloc).
 */
static inline void *kzalloc(size_t size, gfp_t flags)
{
	return kmalloc(size, flags | __GFP_ZERO);
}

J
Jeff Layton 已提交
427 428 429 430 431 432 433 434 435 436 437
/**
 * kzalloc_node - allocate zeroed memory from a particular memory node.
 * @size: how many bytes of memory are required.
 * @flags: the type of memory to allocate (see kmalloc).
 * @node: memory node from which to allocate
 */
static inline void *kzalloc_node(size_t size, gfp_t flags, int node)
{
	return kmalloc_node(size, flags | __GFP_ZERO, node);
}

438 439 440 441 442 443 444 445
/*
 * Determine the size of a slab object
 */
static inline unsigned int kmem_cache_size(struct kmem_cache *s)
{
	return s->object_size;
}

446 447
void __init kmem_cache_init_late(void);

L
Linus Torvalds 已提交
448
#endif	/* _LINUX_SLAB_H */