slab.c 94.2 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
/*
 * linux/mm/slab.c
 * Written by Mark Hemment, 1996/97.
 * (markhe@nextd.demon.co.uk)
 *
 * kmem_cache_destroy() + some cleanup - 1999 Andrea Arcangeli
 *
 * Major cleanup, different bufctl logic, per-cpu arrays
 *	(c) 2000 Manfred Spraul
 *
 * Cleanup, make the head arrays unconditional, preparation for NUMA
 * 	(c) 2002 Manfred Spraul
 *
 * An implementation of the Slab Allocator as described in outline in;
 *	UNIX Internals: The New Frontiers by Uresh Vahalia
 *	Pub: Prentice Hall	ISBN 0-13-101908-2
 * or with a little more detail in;
 *	The Slab Allocator: An Object-Caching Kernel Memory Allocator
 *	Jeff Bonwick (Sun Microsystems).
 *	Presented at: USENIX Summer 1994 Technical Conference
 *
 * The memory is organized in caches, one cache for each object type.
 * (e.g. inode_cache, dentry_cache, buffer_head, vm_area_struct)
 * Each cache consists out of many slabs (they are small (usually one
 * page long) and always contiguous), and each slab contains multiple
 * initialized objects.
 *
 * This means, that your constructor is used only for newly allocated
 * slabs and you must pass objects with the same intializations to
 * kmem_cache_free.
 *
 * Each cache can only support one memory type (GFP_DMA, GFP_HIGHMEM,
 * normal). If you need a special memory type, then must create a new
 * cache for that memory type.
 *
 * In order to reduce fragmentation, the slabs are sorted in 3 groups:
 *   full slabs with 0 free objects
 *   partial slabs
 *   empty slabs with no allocated objects
 *
 * If partial slabs exist, then new allocations come from these slabs,
 * otherwise from empty slabs or new slabs are allocated.
 *
 * kmem_cache_destroy() CAN CRASH if you try to allocate from the cache
 * during kmem_cache_destroy(). The caller must prevent concurrent allocs.
 *
 * Each cache has a short per-cpu head array, most allocs
 * and frees go into that array, and if that array overflows, then 1/2
 * of the entries in the array are given back into the global cache.
 * The head array is strictly LIFO and should improve the cache hit rates.
 * On SMP, it additionally reduces the spinlock operations.
 *
 * The c_cpuarray may not be read with enabled local interrupts - 
 * it's changed with a smp_call_function().
 *
 * SMP synchronization:
 *  constructors and destructors are called without any locking.
 *  Several members in kmem_cache_t and struct slab never change, they
 *	are accessed without any locking.
 *  The per-cpu arrays are never accessed from the wrong cpu, no locking,
 *  	and local interrupts are disabled so slab code is preempt-safe.
 *  The non-constant members are protected with a per-cache irq spinlock.
 *
 * Many thanks to Mark Hemment, who wrote another per-cpu slab patch
 * in 2000 - many ideas in the current implementation are derived from
 * his patch.
 *
 * Further notes from the original documentation:
 *
 * 11 April '97.  Started multi-threading - markhe
 *	The global cache-chain is protected by the semaphore 'cache_chain_sem'.
 *	The sem is only needed when accessing/extending the cache-chain, which
 *	can never happen inside an interrupt (kmem_cache_create(),
 *	kmem_cache_shrink() and kmem_cache_reap()).
 *
 *	At present, each engine can be growing a cache.  This should be blocked.
 *
78
79
80
81
82
83
84
85
86
 * 15 March 2005. NUMA slab allocator.
 *	Shai Fultheim <shai@scalex86.org>.
 *	Shobhit Dayal <shobhit@calsoftinc.com>
 *	Alok N Kataria <alokk@calsoftinc.com>
 *	Christoph Lameter <christoph@lameter.com>
 *
 *	Modified the slab allocator to be node aware on NUMA systems.
 *	Each node has its own list of partial, free and full slabs.
 *	All object allocations for a node occur from node specific slab lists.
Linus Torvalds's avatar
Linus Torvalds committed
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
 */

#include	<linux/config.h>
#include	<linux/slab.h>
#include	<linux/mm.h>
#include	<linux/swap.h>
#include	<linux/cache.h>
#include	<linux/interrupt.h>
#include	<linux/init.h>
#include	<linux/compiler.h>
#include	<linux/seq_file.h>
#include	<linux/notifier.h>
#include	<linux/kallsyms.h>
#include	<linux/cpu.h>
#include	<linux/sysctl.h>
#include	<linux/module.h>
#include	<linux/rcupdate.h>
104
#include	<linux/string.h>
105
#include	<linux/nodemask.h>
Linus Torvalds's avatar
Linus Torvalds committed
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
201

#include	<asm/uaccess.h>
#include	<asm/cacheflush.h>
#include	<asm/tlbflush.h>
#include	<asm/page.h>

/*
 * DEBUG	- 1 for kmem_cache_create() to honour; SLAB_DEBUG_INITIAL,
 *		  SLAB_RED_ZONE & SLAB_POISON.
 *		  0 for faster, smaller code (especially in the critical paths).
 *
 * STATS	- 1 to collect stats for /proc/slabinfo.
 *		  0 for faster, smaller code (especially in the critical paths).
 *
 * FORCED_DEBUG	- 1 enables SLAB_RED_ZONE and SLAB_POISON (if possible)
 */

#ifdef CONFIG_DEBUG_SLAB
#define	DEBUG		1
#define	STATS		1
#define	FORCED_DEBUG	1
#else
#define	DEBUG		0
#define	STATS		0
#define	FORCED_DEBUG	0
#endif


/* Shouldn't this be in a header file somewhere? */
#define	BYTES_PER_WORD		sizeof(void *)

#ifndef cache_line_size
#define cache_line_size()	L1_CACHE_BYTES
#endif

#ifndef ARCH_KMALLOC_MINALIGN
/*
 * Enforce a minimum alignment for the kmalloc caches.
 * Usually, the kmalloc caches are cache_line_size() aligned, except when
 * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned.
 * Some archs want to perform DMA into kmalloc caches and need a guaranteed
 * alignment larger than BYTES_PER_WORD. ARCH_KMALLOC_MINALIGN allows that.
 * Note that this flag disables some debug features.
 */
#define ARCH_KMALLOC_MINALIGN 0
#endif

#ifndef ARCH_SLAB_MINALIGN
/*
 * Enforce a minimum alignment for all caches.
 * Intended for archs that get misalignment faults even for BYTES_PER_WORD
 * aligned buffers. Includes ARCH_KMALLOC_MINALIGN.
 * If possible: Do not enable this flag for CONFIG_DEBUG_SLAB, it disables
 * some debug features.
 */
#define ARCH_SLAB_MINALIGN 0
#endif

#ifndef ARCH_KMALLOC_FLAGS
#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
#endif

/* Legal flag mask for kmem_cache_create(). */
#if DEBUG
# define CREATE_MASK	(SLAB_DEBUG_INITIAL | SLAB_RED_ZONE | \
			 SLAB_POISON | SLAB_HWCACHE_ALIGN | \
			 SLAB_NO_REAP | SLAB_CACHE_DMA | \
			 SLAB_MUST_HWCACHE_ALIGN | SLAB_STORE_USER | \
			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
			 SLAB_DESTROY_BY_RCU)
#else
# define CREATE_MASK	(SLAB_HWCACHE_ALIGN | SLAB_NO_REAP | \
			 SLAB_CACHE_DMA | SLAB_MUST_HWCACHE_ALIGN | \
			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
			 SLAB_DESTROY_BY_RCU)
#endif

/*
 * kmem_bufctl_t:
 *
 * Bufctl's are used for linking objs within a slab
 * linked offsets.
 *
 * This implementation relies on "struct page" for locating the cache &
 * slab an object belongs to.
 * This allows the bufctl structure to be small (one int), but limits
 * the number of objects a slab (not a cache) can contain when off-slab
 * bufctls are used. The limit is the size of the largest general cache
 * that does not use off-slab slabs.
 * For 32bit archs with 4 kB pages, is this 56.
 * This is not serious, as it is only for large objects, when it is unwise
 * to have too many per slab.
 * Note: This limit can be raised by introducing a general cache whose size
 * is less than 512 (PAGE_SIZE<<3), but greater than 256.
 */

202
typedef unsigned int kmem_bufctl_t;
Linus Torvalds's avatar
Linus Torvalds committed
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
#define BUFCTL_END	(((kmem_bufctl_t)(~0U))-0)
#define BUFCTL_FREE	(((kmem_bufctl_t)(~0U))-1)
#define	SLAB_LIMIT	(((kmem_bufctl_t)(~0U))-2)

/* Max number of objs-per-slab for caches which use off-slab slabs.
 * Needed to avoid a possible looping condition in cache_grow().
 */
static unsigned long offslab_limit;

/*
 * struct slab
 *
 * Manages the objs in a slab. Placed either at the beginning of mem allocated
 * for a slab, or allocated from an general cache.
 * Slabs are chained into three list: fully used, partial, fully free slabs.
 */
struct slab {
	struct list_head	list;
	unsigned long		colouroff;
	void			*s_mem;		/* including colour offset */
	unsigned int		inuse;		/* num of objs active in slab */
	kmem_bufctl_t		free;
225
	unsigned short          nodeid;
Linus Torvalds's avatar
Linus Torvalds committed
226
227
228
229
230
231
232
233
234
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
263
264
265
266
};

/*
 * struct slab_rcu
 *
 * slab_destroy on a SLAB_DESTROY_BY_RCU cache uses this structure to
 * arrange for kmem_freepages to be called via RCU.  This is useful if
 * we need to approach a kernel structure obliquely, from its address
 * obtained without the usual locking.  We can lock the structure to
 * stabilize it and check it's still at the given address, only if we
 * can be sure that the memory has not been meanwhile reused for some
 * other kind of object (which our subsystem's lock might corrupt).
 *
 * rcu_read_lock before reading the address, then rcu_read_unlock after
 * taking the spinlock within the structure expected at that address.
 *
 * We assume struct slab_rcu can overlay struct slab when destroying.
 */
struct slab_rcu {
	struct rcu_head		head;
	kmem_cache_t		*cachep;
	void			*addr;
};

/*
 * struct array_cache
 *
 * Purpose:
 * - LIFO ordering, to hand out cache-warm objects from _alloc
 * - reduce the number of linked list operations
 * - reduce spinlock operations
 *
 * The limit is stored in the per-cpu structure to reduce the data cache
 * footprint.
 *
 */
struct array_cache {
	unsigned int avail;
	unsigned int limit;
	unsigned int batchcount;
	unsigned int touched;
267
268
269
270
271
272
273
	spinlock_t lock;
	void *entry[0];		/*
				 * Must have this definition in here for the proper
				 * alignment of array_cache. Also simplifies accessing
				 * the entries.
				 * [0] is for gcc 2.95. It should really be [].
				 */
Linus Torvalds's avatar
Linus Torvalds committed
274
275
276
277
278
279
280
281
282
283
284
285
};

/* bootstrap: The caches do not work without cpuarrays anymore,
 * but the cpuarrays are allocated from the generic caches...
 */
#define BOOT_CPUCACHE_ENTRIES	1
struct arraycache_init {
	struct array_cache cache;
	void * entries[BOOT_CPUCACHE_ENTRIES];
};

/*
286
 * The slab lists for all objects.
Linus Torvalds's avatar
Linus Torvalds committed
287
288
289
290
291
292
293
 */
struct kmem_list3 {
	struct list_head	slabs_partial;	/* partial list first, better asm code */
	struct list_head	slabs_full;
	struct list_head	slabs_free;
	unsigned long	free_objects;
	unsigned long	next_reap;
294
295
296
297
298
	int		free_touched;
	unsigned int 	free_limit;
	spinlock_t      list_lock;
	struct array_cache	*shared;	/* shared per node */
	struct array_cache	**alien;	/* on other nodes */
Linus Torvalds's avatar
Linus Torvalds committed
299
300
};

301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
/*
 * Need this for bootstrapping a per node allocator.
 */
#define NUM_INIT_LISTS (2 * MAX_NUMNODES + 1)
struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
#define	CACHE_CACHE 0
#define	SIZE_AC 1
#define	SIZE_L3 (1 + MAX_NUMNODES)

/*
 * This function may be completely optimized away if
 * a constant is passed to it. Mostly the same as
 * what is in linux/slab.h except it returns an
 * index.
 */
static inline int index_of(const size_t size)
{
	if (__builtin_constant_p(size)) {
		int i = 0;

#define CACHE(x) \
	if (size <=x) \
		return i; \
	else \
		i++;
#include "linux/kmalloc_sizes.h"
#undef CACHE
		{
			extern void __bad_size(void);
			__bad_size();
		}
Linus Torvalds's avatar
Linus Torvalds committed
332
	}
333
334
335
336
337
	return 0;
}

#define INDEX_AC index_of(sizeof(struct arraycache_init))
#define INDEX_L3 index_of(sizeof(struct kmem_list3))
Linus Torvalds's avatar
Linus Torvalds committed
338

339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
static inline void kmem_list3_init(struct kmem_list3 *parent)
{
	INIT_LIST_HEAD(&parent->slabs_full);
	INIT_LIST_HEAD(&parent->slabs_partial);
	INIT_LIST_HEAD(&parent->slabs_free);
	parent->shared = NULL;
	parent->alien = NULL;
	spin_lock_init(&parent->list_lock);
	parent->free_objects = 0;
	parent->free_touched = 0;
}

#define MAKE_LIST(cachep, listp, slab, nodeid)	\
	do {	\
		INIT_LIST_HEAD(listp);		\
		list_splice(&(cachep->nodelists[nodeid]->slab), listp); \
	} while (0)

#define	MAKE_ALL_LISTS(cachep, ptr, nodeid)			\
	do {					\
	MAKE_LIST((cachep), (&(ptr)->slabs_full), slabs_full, nodeid);	\
	MAKE_LIST((cachep), (&(ptr)->slabs_partial), slabs_partial, nodeid); \
	MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid);	\
	} while (0)
Linus Torvalds's avatar
Linus Torvalds committed
363
364
365
366
367
368
369
370
371
372
373
374

/*
 * kmem_cache_t
 *
 * manages a cache.
 */
	
struct kmem_cache_s {
/* 1) per-cpu data, touched during every alloc/free */
	struct array_cache	*array[NR_CPUS];
	unsigned int		batchcount;
	unsigned int		limit;
375
	unsigned int 		shared;
Linus Torvalds's avatar
Linus Torvalds committed
376
	unsigned int		objsize;
377
378
/* 2) touched by every alloc & free from the backend */
	struct kmem_list3	*nodelists[MAX_NUMNODES];
Linus Torvalds's avatar
Linus Torvalds committed
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
	unsigned int	 	flags;	/* constant flags */
	unsigned int		num;	/* # of objs per slab */
	spinlock_t		spinlock;

/* 3) cache_grow/shrink */
	/* order of pgs per slab (2^n) */
	unsigned int		gfporder;

	/* force GFP flags, e.g. GFP_DMA */
	unsigned int		gfpflags;

	size_t			colour;		/* cache colouring range */
	unsigned int		colour_off;	/* colour offset */
	unsigned int		colour_next;	/* cache colouring */
	kmem_cache_t		*slabp_cache;
	unsigned int		slab_size;
	unsigned int		dflags;		/* dynamic flags */

	/* constructor func */
	void (*ctor)(void *, kmem_cache_t *, unsigned long);

	/* de-constructor func */
	void (*dtor)(void *, kmem_cache_t *, unsigned long);

/* 4) cache creation/removal */
	const char		*name;
	struct list_head	next;

/* 5) statistics */
#if STATS
	unsigned long		num_active;
	unsigned long		num_allocations;
	unsigned long		high_mark;
	unsigned long		grown;
	unsigned long		reaped;
	unsigned long 		errors;
	unsigned long		max_freeable;
	unsigned long		node_allocs;
417
	unsigned long		node_frees;
Linus Torvalds's avatar
Linus Torvalds committed
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
	atomic_t		allochit;
	atomic_t		allocmiss;
	atomic_t		freehit;
	atomic_t		freemiss;
#endif
#if DEBUG
	int			dbghead;
	int			reallen;
#endif
};

#define CFLGS_OFF_SLAB		(0x80000000UL)
#define	OFF_SLAB(x)	((x)->flags & CFLGS_OFF_SLAB)

#define BATCHREFILL_LIMIT	16
/* Optimization question: fewer reaps means less 
 * probability for unnessary cpucache drain/refill cycles.
 *
 * OTHO the cpuarrays can contain lots of objects,
 * which could lock up otherwise freeable slabs.
 */
#define REAPTIMEOUT_CPUC	(2*HZ)
#define REAPTIMEOUT_LIST3	(4*HZ)

#if STATS
#define	STATS_INC_ACTIVE(x)	((x)->num_active++)
#define	STATS_DEC_ACTIVE(x)	((x)->num_active--)
#define	STATS_INC_ALLOCED(x)	((x)->num_allocations++)
#define	STATS_INC_GROWN(x)	((x)->grown++)
#define	STATS_INC_REAPED(x)	((x)->reaped++)
#define	STATS_SET_HIGH(x)	do { if ((x)->num_active > (x)->high_mark) \
					(x)->high_mark = (x)->num_active; \
				} while (0)
#define	STATS_INC_ERR(x)	((x)->errors++)
#define	STATS_INC_NODEALLOCS(x)	((x)->node_allocs++)
453
#define	STATS_INC_NODEFREES(x)	((x)->node_frees++)
Linus Torvalds's avatar
Linus Torvalds committed
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
#define	STATS_SET_FREEABLE(x, i) \
				do { if ((x)->max_freeable < i) \
					(x)->max_freeable = i; \
				} while (0)

#define STATS_INC_ALLOCHIT(x)	atomic_inc(&(x)->allochit)
#define STATS_INC_ALLOCMISS(x)	atomic_inc(&(x)->allocmiss)
#define STATS_INC_FREEHIT(x)	atomic_inc(&(x)->freehit)
#define STATS_INC_FREEMISS(x)	atomic_inc(&(x)->freemiss)
#else
#define	STATS_INC_ACTIVE(x)	do { } while (0)
#define	STATS_DEC_ACTIVE(x)	do { } while (0)
#define	STATS_INC_ALLOCED(x)	do { } while (0)
#define	STATS_INC_GROWN(x)	do { } while (0)
#define	STATS_INC_REAPED(x)	do { } while (0)
#define	STATS_SET_HIGH(x)	do { } while (0)
#define	STATS_INC_ERR(x)	do { } while (0)
#define	STATS_INC_NODEALLOCS(x)	do { } while (0)
472
#define	STATS_INC_NODEFREES(x)	do { } while (0)
Linus Torvalds's avatar
Linus Torvalds committed
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
#define	STATS_SET_FREEABLE(x, i) \
				do { } while (0)

#define STATS_INC_ALLOCHIT(x)	do { } while (0)
#define STATS_INC_ALLOCMISS(x)	do { } while (0)
#define STATS_INC_FREEHIT(x)	do { } while (0)
#define STATS_INC_FREEMISS(x)	do { } while (0)
#endif

#if DEBUG
/* Magic nums for obj red zoning.
 * Placed in the first word before and the first word after an obj.
 */
#define	RED_INACTIVE	0x5A2CF071UL	/* when obj is inactive */
#define	RED_ACTIVE	0x170FC2A5UL	/* when obj is active */

/* ...and for poisoning */
#define	POISON_INUSE	0x5a	/* for use-uninitialised poisoning */
#define POISON_FREE	0x6b	/* for use-after-free poisoning */
#define	POISON_END	0xa5	/* end-byte of poisoning */

/* memory layout of objects:
 * 0		: objp
 * 0 .. cachep->dbghead - BYTES_PER_WORD - 1: padding. This ensures that
 * 		the end of an object is aligned with the end of the real
 * 		allocation. Catches writes behind the end of the allocation.
 * cachep->dbghead - BYTES_PER_WORD .. cachep->dbghead - 1:
 * 		redzone word.
 * cachep->dbghead: The real object.
 * cachep->objsize - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long]
 * cachep->objsize - 1* BYTES_PER_WORD: last caller address [BYTES_PER_WORD long]
 */
static int obj_dbghead(kmem_cache_t *cachep)
{
	return cachep->dbghead;
}

static int obj_reallen(kmem_cache_t *cachep)
{
	return cachep->reallen;
}

static unsigned long *dbg_redzone1(kmem_cache_t *cachep, void *objp)
{
	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
	return (unsigned long*) (objp+obj_dbghead(cachep)-BYTES_PER_WORD);
}

static unsigned long *dbg_redzone2(kmem_cache_t *cachep, void *objp)
{
	BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
	if (cachep->flags & SLAB_STORE_USER)
		return (unsigned long*) (objp+cachep->objsize-2*BYTES_PER_WORD);
	return (unsigned long*) (objp+cachep->objsize-BYTES_PER_WORD);
}

static void **dbg_userword(kmem_cache_t *cachep, void *objp)
{
	BUG_ON(!(cachep->flags & SLAB_STORE_USER));
	return (void**)(objp+cachep->objsize-BYTES_PER_WORD);
}

#else

#define obj_dbghead(x)			0
#define obj_reallen(cachep)		(cachep->objsize)
#define dbg_redzone1(cachep, objp)	({BUG(); (unsigned long *)NULL;})
#define dbg_redzone2(cachep, objp)	({BUG(); (unsigned long *)NULL;})
#define dbg_userword(cachep, objp)	({BUG(); (void **)NULL;})

#endif

/*
 * Maximum size of an obj (in 2^order pages)
 * and absolute limit for the gfp order.
 */
#if defined(CONFIG_LARGE_ALLOCS)
#define	MAX_OBJ_ORDER	13	/* up to 32Mb */
#define	MAX_GFP_ORDER	13	/* up to 32Mb */
#elif defined(CONFIG_MMU)
#define	MAX_OBJ_ORDER	5	/* 32 pages */
#define	MAX_GFP_ORDER	5	/* 32 pages */
#else
#define	MAX_OBJ_ORDER	8	/* up to 1Mb */
#define	MAX_GFP_ORDER	8	/* up to 1Mb */
#endif

/*
 * Do not go above this order unless 0 objects fit into the slab.
 */
#define	BREAK_GFP_ORDER_HI	1
#define	BREAK_GFP_ORDER_LO	0
static int slab_break_gfp_order = BREAK_GFP_ORDER_LO;

/* Macros for storing/retrieving the cachep and or slab from the
 * global 'mem_map'. These are used to find the slab an obj belongs to.
 * With kfree(), these are used to find the cache which an obj belongs to.
 */
#define	SET_PAGE_CACHE(pg,x)  ((pg)->lru.next = (struct list_head *)(x))
#define	GET_PAGE_CACHE(pg)    ((kmem_cache_t *)(pg)->lru.next)
#define	SET_PAGE_SLAB(pg,x)   ((pg)->lru.prev = (struct list_head *)(x))
#define	GET_PAGE_SLAB(pg)     ((struct slab *)(pg)->lru.prev)

/* These are the default caches for kmalloc. Custom caches can have other sizes. */
struct cache_sizes malloc_sizes[] = {
#define CACHE(x) { .cs_size = (x) },
#include <linux/kmalloc_sizes.h>
	CACHE(ULONG_MAX)
#undef CACHE
};
EXPORT_SYMBOL(malloc_sizes);

/* Must match cache_sizes above. Out of line to keep cache footprint low. */
struct cache_names {
	char *name;
	char *name_dma;
};

static struct cache_names __initdata cache_names[] = {
#define CACHE(x) { .name = "size-" #x, .name_dma = "size-" #x "(DMA)" },
#include <linux/kmalloc_sizes.h>
	{ NULL, }
#undef CACHE
};

static struct arraycache_init initarray_cache __initdata =
	{ { 0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
static struct arraycache_init initarray_generic =
	{ { 0, BOOT_CPUCACHE_ENTRIES, 1, 0} };

/* internal cache of cache description objs */
static kmem_cache_t cache_cache = {
	.batchcount	= 1,
	.limit		= BOOT_CPUCACHE_ENTRIES,
607
	.shared		= 1,
Linus Torvalds's avatar
Linus Torvalds committed
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
	.objsize	= sizeof(kmem_cache_t),
	.flags		= SLAB_NO_REAP,
	.spinlock	= SPIN_LOCK_UNLOCKED,
	.name		= "kmem_cache",
#if DEBUG
	.reallen	= sizeof(kmem_cache_t),
#endif
};

/* Guard access to the cache-chain. */
static struct semaphore	cache_chain_sem;
static struct list_head cache_chain;

/*
 * vm_enough_memory() looks at this to determine how many
 * slab-allocated pages are possibly freeable under pressure
 *
 * SLAB_RECLAIM_ACCOUNT turns this on per-slab
 */
atomic_t slab_reclaim_pages;

/*
 * chicken and egg problem: delay the per-cpu array allocation
 * until the general caches are up.
 */
static enum {
	NONE,
635
636
	PARTIAL_AC,
	PARTIAL_L3,
Linus Torvalds's avatar
Linus Torvalds committed
637
638
639
640
641
642
643
644
	FULL
} g_cpucache_up;

static DEFINE_PER_CPU(struct work_struct, reap_work);

static void free_block(kmem_cache_t* cachep, void** objpp, int len);
static void enable_cpucache (kmem_cache_t *cachep);
static void cache_reap (void *unused);
645
static int __node_shrink(kmem_cache_t *cachep, int node);
Linus Torvalds's avatar
Linus Torvalds committed
646
647
648
649
650
651

static inline struct array_cache *ac_data(kmem_cache_t *cachep)
{
	return cachep->array[smp_processor_id()];
}

652
653
static inline kmem_cache_t *__find_general_cachep(size_t size,
						unsigned int __nocast gfpflags)
Linus Torvalds's avatar
Linus Torvalds committed
654
655
656
657
658
659
660
661
{
	struct cache_sizes *csizep = malloc_sizes;

#if DEBUG
	/* This happens if someone tries to call
 	* kmem_cache_create(), or __kmalloc(), before
 	* the generic caches are initialized.
 	*/
662
	BUG_ON(malloc_sizes[INDEX_AC].cs_cachep == NULL);
Linus Torvalds's avatar
Linus Torvalds committed
663
664
665
666
667
#endif
	while (size > csizep->cs_size)
		csizep++;

	/*
668
	 * Really subtle: The last entry with cs->cs_size==ULONG_MAX
Linus Torvalds's avatar
Linus Torvalds committed
669
670
671
672
673
674
675
676
	 * has cs_{dma,}cachep==NULL. Thus no special case
	 * for large kmalloc calls required.
	 */
	if (unlikely(gfpflags & GFP_DMA))
		return csizep->cs_dmacachep;
	return csizep->cs_cachep;
}

677
678
kmem_cache_t *kmem_find_general_cachep(size_t size,
		unsigned int __nocast gfpflags)
679
680
681
682
683
{
	return __find_general_cachep(size, gfpflags);
}
EXPORT_SYMBOL(kmem_find_general_cachep);

Linus Torvalds's avatar
Linus Torvalds committed
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
/* Cal the num objs, wastage, and bytes left over for a given slab size. */
static void cache_estimate(unsigned long gfporder, size_t size, size_t align,
		 int flags, size_t *left_over, unsigned int *num)
{
	int i;
	size_t wastage = PAGE_SIZE<<gfporder;
	size_t extra = 0;
	size_t base = 0;

	if (!(flags & CFLGS_OFF_SLAB)) {
		base = sizeof(struct slab);
		extra = sizeof(kmem_bufctl_t);
	}
	i = 0;
	while (i*size + ALIGN(base+i*extra, align) <= wastage)
		i++;
	if (i > 0)
		i--;

	if (i > SLAB_LIMIT)
		i = SLAB_LIMIT;

	*num = i;
	wastage -= i*size;
	wastage -= ALIGN(base+i*extra, align);
	*left_over = wastage;
}

#define slab_error(cachep, msg) __slab_error(__FUNCTION__, cachep, msg)

static void __slab_error(const char *function, kmem_cache_t *cachep, char *msg)
{
	printk(KERN_ERR "slab error in %s(): cache `%s': %s\n",
		function, cachep->name, msg);
	dump_stack();
}

/*
 * Initiate the reap timer running on the target CPU.  We run at around 1 to 2Hz
 * via the workqueue/eventd.
 * Add the CPU number into the expiration time to minimize the possibility of
 * the CPUs getting into lockstep and contending for the global cache chain
 * lock.
 */
static void __devinit start_cpu_timer(int cpu)
{
	struct work_struct *reap_work = &per_cpu(reap_work, cpu);

	/*
	 * When this gets called from do_initcalls via cpucache_init(),
	 * init_workqueues() has already run, so keventd will be setup
	 * at that time.
	 */
	if (keventd_up() && reap_work->func == NULL) {
		INIT_WORK(reap_work, cache_reap, NULL);
		schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu);
	}
}

743
static struct array_cache *alloc_arraycache(int node, int entries,
Linus Torvalds's avatar
Linus Torvalds committed
744
745
746
747
748
						int batchcount)
{
	int memsize = sizeof(void*)*entries+sizeof(struct array_cache);
	struct array_cache *nc = NULL;

749
	nc = kmalloc_node(memsize, GFP_KERNEL, node);
Linus Torvalds's avatar
Linus Torvalds committed
750
751
752
753
754
	if (nc) {
		nc->avail = 0;
		nc->limit = entries;
		nc->batchcount = batchcount;
		nc->touched = 0;
755
		spin_lock_init(&nc->lock);
Linus Torvalds's avatar
Linus Torvalds committed
756
757
758
759
	}
	return nc;
}

760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
#ifdef CONFIG_NUMA
static inline struct array_cache **alloc_alien_cache(int node, int limit)
{
	struct array_cache **ac_ptr;
	int memsize = sizeof(void*)*MAX_NUMNODES;
	int i;

	if (limit > 1)
		limit = 12;
	ac_ptr = kmalloc_node(memsize, GFP_KERNEL, node);
	if (ac_ptr) {
		for_each_node(i) {
			if (i == node || !node_online(i)) {
				ac_ptr[i] = NULL;
				continue;
			}
			ac_ptr[i] = alloc_arraycache(node, limit, 0xbaadf00d);
			if (!ac_ptr[i]) {
				for (i--; i <=0; i--)
					kfree(ac_ptr[i]);
				kfree(ac_ptr);
				return NULL;
			}
		}
	}
	return ac_ptr;
}

static inline void free_alien_cache(struct array_cache **ac_ptr)
{
	int i;

	if (!ac_ptr)
		return;

	for_each_node(i)
		kfree(ac_ptr[i]);

	kfree(ac_ptr);
}

static inline void __drain_alien_cache(kmem_cache_t *cachep, struct array_cache *ac, int node)
{
	struct kmem_list3 *rl3 = cachep->nodelists[node];

	if (ac->avail) {
		spin_lock(&rl3->list_lock);
		free_block(cachep, ac->entry, ac->avail);
		ac->avail = 0;
		spin_unlock(&rl3->list_lock);
	}
}

static void drain_alien_cache(kmem_cache_t *cachep, struct kmem_list3 *l3)
{
	int i=0;
	struct array_cache *ac;
	unsigned long flags;

	for_each_online_node(i) {
		ac = l3->alien[i];
		if (ac) {
			spin_lock_irqsave(&ac->lock, flags);
			__drain_alien_cache(cachep, ac, i);
			spin_unlock_irqrestore(&ac->lock, flags);
		}
	}
}
#else
#define alloc_alien_cache(node, limit) do { } while (0)
#define free_alien_cache(ac_ptr) do { } while (0)
#define drain_alien_cache(cachep, l3) do { } while (0)
#endif

Linus Torvalds's avatar
Linus Torvalds committed
834
835
836
837
838
static int __devinit cpuup_callback(struct notifier_block *nfb,
				  unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;
	kmem_cache_t* cachep;
839
840
841
842
	struct kmem_list3 *l3 = NULL;
	int node = cpu_to_node(cpu);
	int memsize = sizeof(struct kmem_list3);
	struct array_cache *nc = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
843
844
845
846

	switch (action) {
	case CPU_UP_PREPARE:
		down(&cache_chain_sem);
847
848
849
850
851
852
		/* we need to do this right in the beginning since
		 * alloc_arraycache's are going to use this list.
		 * kmalloc_node allows us to add the slab to the right
		 * kmem_list3 and not this cpu's kmem_list3
		 */

Linus Torvalds's avatar
Linus Torvalds committed
853
		list_for_each_entry(cachep, &cache_chain, next) {
854
855
856
857
858
859
860
861
862
863
864
865
866
867
			/* setup the size64 kmemlist for cpu before we can
			 * begin anything. Make sure some other cpu on this
			 * node has not already allocated this
			 */
			if (!cachep->nodelists[node]) {
				if (!(l3 = kmalloc_node(memsize,
						GFP_KERNEL, node)))
					goto bad;
				kmem_list3_init(l3);
				l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
				  ((unsigned long)cachep)%REAPTIMEOUT_LIST3;

				cachep->nodelists[node] = l3;
			}
Linus Torvalds's avatar
Linus Torvalds committed
868

869
870
871
872
873
874
875
876
877
878
879
880
			spin_lock_irq(&cachep->nodelists[node]->list_lock);
			cachep->nodelists[node]->free_limit =
				(1 + nr_cpus_node(node)) *
				cachep->batchcount + cachep->num;
			spin_unlock_irq(&cachep->nodelists[node]->list_lock);
		}

		/* Now we can go ahead with allocating the shared array's
		  & array cache's */
		list_for_each_entry(cachep, &cache_chain, next) {
			nc = alloc_arraycache(node, cachep->limit,
					cachep->batchcount);
Linus Torvalds's avatar
Linus Torvalds committed
881
882
883
884
			if (!nc)
				goto bad;
			cachep->array[cpu] = nc;

885
886
887
888
889
890
891
892
893
894
895
896
			l3 = cachep->nodelists[node];
			BUG_ON(!l3);
			if (!l3->shared) {
				if (!(nc = alloc_arraycache(node,
					cachep->shared*cachep->batchcount,
					0xbaadf00d)))
					goto  bad;

				/* we are serialised from CPU_DEAD or
				  CPU_UP_CANCELLED by the cpucontrol lock */
				l3->shared = nc;
			}
Linus Torvalds's avatar
Linus Torvalds committed
897
898
899
900
901
902
903
904
905
906
907
908
909
910
		}
		up(&cache_chain_sem);
		break;
	case CPU_ONLINE:
		start_cpu_timer(cpu);
		break;
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_DEAD:
		/* fall thru */
	case CPU_UP_CANCELED:
		down(&cache_chain_sem);

		list_for_each_entry(cachep, &cache_chain, next) {
			struct array_cache *nc;
911
			cpumask_t mask;
Linus Torvalds's avatar
Linus Torvalds committed
912

913
			mask = node_to_cpumask(node);
Linus Torvalds's avatar
Linus Torvalds committed
914
915
916
917
			spin_lock_irq(&cachep->spinlock);
			/* cpu is dead; no one can alloc from it. */
			nc = cachep->array[cpu];
			cachep->array[cpu] = NULL;
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
			l3 = cachep->nodelists[node];

			if (!l3)
				goto unlock_cache;

			spin_lock(&l3->list_lock);

			/* Free limit for this kmem_list3 */
			l3->free_limit -= cachep->batchcount;
			if (nc)
				free_block(cachep, nc->entry, nc->avail);

			if (!cpus_empty(mask)) {
                                spin_unlock(&l3->list_lock);
                                goto unlock_cache;
                        }

			if (l3->shared) {
				free_block(cachep, l3->shared->entry,
						l3->shared->avail);
				kfree(l3->shared);
				l3->shared = NULL;
			}
			if (l3->alien) {
				drain_alien_cache(cachep, l3);
				free_alien_cache(l3->alien);
				l3->alien = NULL;
			}

			/* free slabs belonging to this node */
			if (__node_shrink(cachep, node)) {
				cachep->nodelists[node] = NULL;
				spin_unlock(&l3->list_lock);
				kfree(l3);
			} else {
				spin_unlock(&l3->list_lock);
			}
unlock_cache:
Linus Torvalds's avatar
Linus Torvalds committed
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
			spin_unlock_irq(&cachep->spinlock);
			kfree(nc);
		}
		up(&cache_chain_sem);
		break;
#endif
	}
	return NOTIFY_OK;
bad:
	up(&cache_chain_sem);
	return NOTIFY_BAD;
}

static struct notifier_block cpucache_notifier = { &cpuup_callback, NULL, 0 };

971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
/*
 * swap the static kmem_list3 with kmalloced memory
 */
static void init_list(kmem_cache_t *cachep, struct kmem_list3 *list,
		int nodeid)
{
	struct kmem_list3 *ptr;

	BUG_ON(cachep->nodelists[nodeid] != list);
	ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, nodeid);
	BUG_ON(!ptr);

	local_irq_disable();
	memcpy(ptr, list, sizeof(struct kmem_list3));
	MAKE_ALL_LISTS(cachep, ptr, nodeid);
	cachep->nodelists[nodeid] = ptr;
	local_irq_enable();
}

Linus Torvalds's avatar
Linus Torvalds committed
990
991
992
993
994
995
996
997
/* Initialisation.
 * Called after the gfp() functions have been enabled, and before smp_init().
 */
void __init kmem_cache_init(void)
{
	size_t left_over;
	struct cache_sizes *sizes;
	struct cache_names *names;
998
999
1000
	int i;

	for (i = 0; i < NUM_INIT_LISTS; i++) {