slub.c 80.5 KB
Newer Older
Christoph Lameter's avatar
Christoph Lameter 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
/*
 * 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 and only
 * uses a centralized lock to manage a pool of partial slabs.
 *
 * (C) 2007 SGI, Christoph Lameter <clameter@sgi.com>
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/bit_spinlock.h>
#include <linux/interrupt.h>
#include <linux/bitops.h>
#include <linux/slab.h>
#include <linux/seq_file.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/mempolicy.h>
#include <linux/ctype.h>
#include <linux/kallsyms.h>

/*
 * Lock order:
 *   1. slab_lock(page)
 *   2. slab->list_lock
 *
 *   The slab_lock protects operations on the object of a particular
 *   slab and its metadata in the page struct. If the slab lock
 *   has been taken then no allocations nor frees can be performed
 *   on the objects in the slab nor can the slab be added or removed
 *   from the partial or full lists since this would mean modifying
 *   the page_struct of the slab.
 *
 *   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.
 *
 *   The lock order is sometimes inverted when we are trying to get a slab
 *   off a list. We take the list_lock and then look for a page on the list
 *   to use. While we do that objects in the slabs may be freed. We can
 *   only operate on the slab if we have also taken the slab_lock. So we use
 *   a slab_trylock() on the slab. If trylock was successful then no frees
 *   can occur anymore and we can use the slab for allocations etc. If the
 *   slab_trylock() does not succeed then frees are in progress in the slab and
 *   we must stay away from it for a while since we may cause a bouncing
 *   cacheline if we try to acquire the lock. So go onto the next slab.
 *   If all pages are busy then we may allocate a new slab instead of reusing
 *   a partial slab. A new slab has noone operating on it and thus there is
 *   no danger of cacheline contention.
 *
 *   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.
 *
Christoph Lameter's avatar
Christoph Lameter committed
69
70
 * 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
Christoph Lameter's avatar
Christoph Lameter committed
71
 * freed then the slab will show up again on the partial lists.
Christoph Lameter's avatar
Christoph Lameter committed
72
73
 * We track full slabs for debugging purposes though because otherwise we
 * cannot scan all objects.
Christoph Lameter's avatar
Christoph Lameter committed
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
 *
 * 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 used as a cpu cache. Allocations
 * 			may be performed from the slab. The slab is not
 * 			on any slab list and cannot be moved onto one.
 *
 * PageError		Slab requires special handling due to debug
 * 			options set. This moves	slab handling out of
 * 			the fast path.
 */

/*
 * Issues still to be resolved:
 *
 * - The per cpu array is updated for each new slab and and is a remote
 *   cacheline for most nodes. This could become a bouncing cacheline given
Christoph Lameter's avatar
Christoph Lameter committed
95
96
 *   enough frequent updates. There are 16 pointers in a cacheline, so at
 *   max 16 cpus could compete for the cacheline which may be okay.
Christoph Lameter's avatar
Christoph Lameter committed
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
 *
 * - 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

#if PAGE_SHIFT <= 12

/*
 * Small page size. Make sure that we do not fragment memory
 */
#define DEFAULT_MAX_ORDER 1
#define DEFAULT_MIN_OBJECTS 4

#else

/*
 * Large page machines are customarily able to handle larger
 * page orders.
 */
#define DEFAULT_MAX_ORDER 2
#define DEFAULT_MIN_OBJECTS 8

#endif

125
126
127
128
/*
 * Mininum number of partial slabs. These will be left on the partial
 * lists even if they are empty. kmem_cache_shrink may reclaim them.
 */
Christoph Lameter's avatar
Christoph Lameter committed
129
130
#define MIN_PARTIAL 2

131
132
133
134
135
136
137
/*
 * 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 the.
 */
#define MAX_PARTIAL 10

Christoph Lameter's avatar
Christoph Lameter committed
138
139
#define DEBUG_DEFAULT_FLAGS (SLAB_DEBUG_FREE | SLAB_RED_ZONE | \
				SLAB_POISON | SLAB_STORE_USER)
Christoph Lameter's avatar
Christoph Lameter committed
140

Christoph Lameter's avatar
Christoph Lameter committed
141
142
143
144
145
146
147
148
149
150
/*
 * Set of flags that will prevent slab merging
 */
#define SLUB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
		SLAB_TRACE | SLAB_DESTROY_BY_RCU)

#define SLUB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
		SLAB_CACHE_DMA)

#ifndef ARCH_KMALLOC_MINALIGN
151
#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
Christoph Lameter's avatar
Christoph Lameter committed
152
153
154
#endif

#ifndef ARCH_SLAB_MINALIGN
155
#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
Christoph Lameter's avatar
Christoph Lameter committed
156
157
158
159
160
#endif

/* Internal SLUB flags */
#define __OBJECT_POISON 0x80000000	/* Poison object */

161
162
163
164
165
/* Not all arches define cache_line_size */
#ifndef cache_line_size
#define cache_line_size()	L1_CACHE_BYTES
#endif

Christoph Lameter's avatar
Christoph Lameter committed
166
167
168
169
170
171
172
173
174
static int kmem_size = sizeof(struct kmem_cache);

#ifdef CONFIG_SMP
static struct notifier_block slab_notifier;
#endif

static enum {
	DOWN,		/* No slab functionality available */
	PARTIAL,	/* kmem_cache_open() works but kmalloc does not */
Christoph Lameter's avatar
Christoph Lameter committed
175
	UP,		/* Everything works but does not show up in sysfs */
Christoph Lameter's avatar
Christoph Lameter committed
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
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
	SYSFS		/* Sysfs up */
} slab_state = DOWN;

/* A list of all slab caches on the system */
static DECLARE_RWSEM(slub_lock);
LIST_HEAD(slab_caches);

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

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

int slab_is_available(void)
{
	return slab_state >= UP;
}

static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
{
#ifdef CONFIG_NUMA
	return s->node[node];
#else
	return &s->local_node;
#endif
}

/*
 * Object debugging
 */
static void print_section(char *text, u8 *addr, unsigned int length)
{
	int i, offset;
	int newline = 1;
	char ascii[17];

	ascii[16] = 0;

	for (i = 0; i < length; i++) {
		if (newline) {
			printk(KERN_ERR "%10s 0x%p: ", text, addr + i);
			newline = 0;
		}
		printk(" %02x", addr[i]);
		offset = i % 16;
		ascii[offset] = isgraph(addr[i]) ? addr[i] : '.';
		if (offset == 15) {
			printk(" %s\n",ascii);
			newline = 1;
		}
	}
	if (!newline) {
		i %= 16;
		while (i < 16) {
			printk("   ");
			ascii[i] = ' ';
			i++;
		}
		printk(" %s\n", ascii);
	}
}

/*
 * Slow version of get and set free pointer.
 *
Christoph Lameter's avatar
Christoph Lameter committed
249
250
251
 * This version requires touching the cache lines of kmem_cache which
 * we avoid to do in the fast alloc free paths. There we obtain the offset
 * from the page struct.
Christoph Lameter's avatar
Christoph Lameter committed
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
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
332
333
334
335
336
337
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
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
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
 */
static void *get_freepointer(struct kmem_cache *s, void *object)
{
	return *(void **)(object + s->offset);
}

static void set_freepointer(struct kmem_cache *s, void *object, void *fp)
{
	*(void **)(object + s->offset) = fp;
}

/*
 * Tracking user of a slab.
 */
struct track {
	void *addr;		/* Called from address */
	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 };

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, void *addr)
{
	struct track *p;

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

	p += alloc;
	if (addr) {
		p->addr = addr;
		p->cpu = smp_processor_id();
		p->pid = current ? current->pid : -1;
		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) {
		set_track(s, object, TRACK_FREE, NULL);
		set_track(s, object, TRACK_ALLOC, NULL);
	}
}

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

	printk(KERN_ERR "%s: ", s);
	__print_symbol("%s", (unsigned long)t->addr);
	printk(" jiffies_ago=%lu cpu=%u pid=%d\n", jiffies - t->when, t->cpu, t->pid);
}

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

	if (s->flags & SLAB_RED_ZONE)
		print_section("Redzone", p + s->objsize,
			s->inuse - s->objsize);

	printk(KERN_ERR "FreePointer 0x%p -> 0x%p\n",
			p + s->offset,
			get_freepointer(s, p));

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

	if (s->flags & SLAB_STORE_USER) {
		print_track("Last alloc", get_track(s, p, TRACK_ALLOC));
		print_track("Last free ", get_track(s, p, TRACK_FREE));
		off += 2 * sizeof(struct track);
	}

	if (off != s->size)
		/* Beginning of the filler is the free pointer */
		print_section("Filler", p + off, s->size - off);
}

static void object_err(struct kmem_cache *s, struct page *page,
			u8 *object, char *reason)
{
	u8 *addr = page_address(page);

	printk(KERN_ERR "*** SLUB %s: %s@0x%p slab 0x%p\n",
			s->name, reason, object, page);
	printk(KERN_ERR "    offset=%tu flags=0x%04lx inuse=%u freelist=0x%p\n",
		object - addr, page->flags, page->inuse, page->freelist);
	if (object > addr + 16)
		print_section("Bytes b4", object - 16, 16);
	print_section("Object", object, min(s->objsize, 128));
	print_trailer(s, object);
	dump_stack();
}

static void slab_err(struct kmem_cache *s, struct page *page, char *reason, ...)
{
	va_list args;
	char buf[100];

	va_start(args, reason);
	vsnprintf(buf, sizeof(buf), reason, args);
	va_end(args);
	printk(KERN_ERR "*** SLUB %s: %s in slab @0x%p\n", s->name, buf,
		page);
	dump_stack();
}

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

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

	if (s->flags & SLAB_RED_ZONE)
		memset(p + s->objsize,
			active ? SLUB_RED_ACTIVE : SLUB_RED_INACTIVE,
			s->inuse - s->objsize);
}

static int check_bytes(u8 *start, unsigned int value, unsigned int bytes)
{
	while (bytes) {
		if (*start != (u8)value)
			return 0;
		start++;
		bytes--;
	}
	return 1;
}

409
410
static inline int check_valid_pointer(struct kmem_cache *s,
				struct page *page, const void *object)
Christoph Lameter's avatar
Christoph Lameter committed
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
{
	void *base;

	if (!object)
		return 1;

	base = page_address(page);
	if (object < base || object >= base + s->objects * s->size ||
		(object - base) % s->size) {
		return 0;
	}

	return 1;
}

/*
 * 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.
Christoph Lameter's avatar
Christoph Lameter committed
433
 *
Christoph Lameter's avatar
Christoph Lameter committed
434
435
436
437
438
 * 	Poisoning uses 0x6b (POISON_FREE) and the last byte is
 * 	0xa5 (POISON_END)
 *
 * object + s->objsize
 * 	Padding to reach word boundary. This is also used for Redzoning.
Christoph Lameter's avatar
Christoph Lameter committed
439
440
441
 * 	Padding is extended by another word if Redzoning is enabled and
 * 	objsize == inuse.
 *
Christoph Lameter's avatar
Christoph Lameter committed
442
443
444
445
 * 	We fill with 0xbb (RED_INACTIVE) for inactive objects and with
 * 	0xcc (RED_ACTIVE) for objects in use.
 *
 * object + s->inuse
Christoph Lameter's avatar
Christoph Lameter committed
446
447
 * 	Meta data starts here.
 *
Christoph Lameter's avatar
Christoph Lameter committed
448
449
 * 	A. Free pointer (if we cannot overwrite object on free)
 * 	B. Tracking data for SLAB_STORE_USER
Christoph Lameter's avatar
Christoph Lameter committed
450
451
452
453
454
 * 	C. Padding to reach required alignment boundary or at mininum
 * 		one word if debuggin is on to be able to detect writes
 * 		before the word boundary.
 *
 *	Padding is done using 0x5a (POISON_INUSE)
Christoph Lameter's avatar
Christoph Lameter committed
455
456
 *
 * object + s->size
Christoph Lameter's avatar
Christoph Lameter committed
457
 * 	Nothing is used beyond s->size.
Christoph Lameter's avatar
Christoph Lameter committed
458
 *
Christoph Lameter's avatar
Christoph Lameter committed
459
460
 * If slabcaches are merged then the objsize and inuse boundaries are mostly
 * ignored. And therefore no slab options that rely on these boundaries
Christoph Lameter's avatar
Christoph Lameter committed
461
462
463
464
465
466
 * may be used with merged slabcaches.
 */

static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
						void *from, void *to)
{
467
	printk(KERN_ERR "@@@ SLUB %s: Restoring %s (0x%x) from 0x%p-0x%p\n",
Christoph Lameter's avatar
Christoph Lameter committed
468
469
470
471
472
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
		s->name, message, data, from, to - 1);
	memset(from, data, to - from);
}

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);

	if (s->size == off)
		return 1;

	if (check_bytes(p + off, POISON_INUSE, s->size - off))
		return 1;

	object_err(s, page, p, "Object padding check fails");

	/*
	 * Restore padding
	 */
	restore_bytes(s, "object padding", POISON_INUSE, p + off, p + s->size);
	return 0;
}

static int slab_pad_check(struct kmem_cache *s, struct page *page)
{
	u8 *p;
	int length, remainder;

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

	p = page_address(page);
	length = s->objects * s->size;
	remainder = (PAGE_SIZE << s->order) - length;
	if (!remainder)
		return 1;

	if (!check_bytes(p + length, POISON_INUSE, remainder)) {
514
		slab_err(s, page, "Padding check failed");
Christoph Lameter's avatar
Christoph Lameter committed
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
		restore_bytes(s, "slab padding", POISON_INUSE, p + length,
			p + length + remainder);
		return 0;
	}
	return 1;
}

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

	if (s->flags & SLAB_RED_ZONE) {
		unsigned int red =
			active ? SLUB_RED_ACTIVE : SLUB_RED_INACTIVE;

		if (!check_bytes(endobject, red, s->inuse - s->objsize)) {
			object_err(s, page, object,
			active ? "Redzone Active" : "Redzone Inactive");
			restore_bytes(s, "redzone", red,
				endobject, object + s->inuse);
			return 0;
		}
	} else {
		if ((s->flags & SLAB_POISON) && s->objsize < s->inuse &&
			!check_bytes(endobject, POISON_INUSE,
					s->inuse - s->objsize)) {
		object_err(s, page, p, "Alignment padding check fails");
		/*
		 * Fix it so that there will not be another report.
		 *
		 * Hmmm... We may be corrupting an object that now expects
		 * to be longer than allowed.
		 */
		restore_bytes(s, "alignment padding", POISON_INUSE,
			endobject, object + s->inuse);
		}
	}

	if (s->flags & SLAB_POISON) {
		if (!active && (s->flags & __OBJECT_POISON) &&
			(!check_bytes(p, POISON_FREE, s->objsize - 1) ||
				p[s->objsize - 1] != POISON_END)) {

			object_err(s, page, p, "Poison check failed");
			restore_bytes(s, "Poison", POISON_FREE,
						p, p + s->objsize -1);
			restore_bytes(s, "Poison", POISON_END,
					p + s->objsize - 1, p + s->objsize);
			return 0;
		}
		/*
		 * check_pad_bytes cleans up on its own.
		 */
		check_pad_bytes(s, page, p);
	}

	if (!s->offset && 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 loose the remainder
		 * of the free objects in this slab. May cause
Christoph Lameter's avatar
Christoph Lameter committed
586
		 * another error because the object count is now wrong.
Christoph Lameter's avatar
Christoph Lameter committed
587
588
589
590
591
592
593
594
595
596
597
598
		 */
		set_freepointer(s, p, NULL);
		return 0;
	}
	return 1;
}

static int check_slab(struct kmem_cache *s, struct page *page)
{
	VM_BUG_ON(!irqs_disabled());

	if (!PageSlab(page)) {
599
600
		slab_err(s, page, "Not a valid slab page flags=%lx "
			"mapping=0x%p count=%d", page->flags, page->mapping,
Christoph Lameter's avatar
Christoph Lameter committed
601
602
603
604
			page_count(page));
		return 0;
	}
	if (page->offset * sizeof(void *) != s->offset) {
605
606
		slab_err(s, page, "Corrupted offset %lu flags=0x%lx "
			"mapping=0x%p count=%d",
Christoph Lameter's avatar
Christoph Lameter committed
607
608
609
610
611
612
613
			(unsigned long)(page->offset * sizeof(void *)),
			page->flags,
			page->mapping,
			page_count(page));
		return 0;
	}
	if (page->inuse > s->objects) {
614
615
616
		slab_err(s, page, "inuse %u > max %u @0x%p flags=%lx "
			"mapping=0x%p count=%d",
			s->name, page->inuse, s->objects, page->flags,
Christoph Lameter's avatar
Christoph Lameter committed
617
618
619
620
621
622
623
624
625
			page->mapping, page_count(page));
		return 0;
	}
	/* Slab_pad_check fixes things up after itself */
	slab_pad_check(s, page);
	return 1;
}

/*
Christoph Lameter's avatar
Christoph Lameter committed
626
627
 * 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.
Christoph Lameter's avatar
Christoph Lameter committed
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
 */
static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
{
	int nr = 0;
	void *fp = page->freelist;
	void *object = NULL;

	while (fp && nr <= s->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);
				break;
			} else {
645
646
				slab_err(s, page, "Freepointer 0x%p corrupt",
									fp);
Christoph Lameter's avatar
Christoph Lameter committed
647
648
				page->freelist = NULL;
				page->inuse = s->objects;
649
650
651
				printk(KERN_ERR "@@@ SLUB %s: Freelist "
					"cleared. Slab 0x%p\n",
					s->name, page);
Christoph Lameter's avatar
Christoph Lameter committed
652
653
654
655
656
657
658
659
660
661
				return 0;
			}
			break;
		}
		object = fp;
		fp = get_freepointer(s, object);
		nr++;
	}

	if (page->inuse != s->objects - nr) {
662
663
664
		slab_err(s, page, "Wrong object count. Counter is %d but "
			"counted were %d", s, page, page->inuse,
							s->objects - nr);
Christoph Lameter's avatar
Christoph Lameter committed
665
		page->inuse = s->objects - nr;
666
667
		printk(KERN_ERR "@@@ SLUB %s: Object count adjusted. "
			"Slab @0x%p\n", s->name, page);
Christoph Lameter's avatar
Christoph Lameter committed
668
669
670
671
	}
	return search == NULL;
}

672
/*
Christoph Lameter's avatar
Christoph Lameter committed
673
 * Tracking of fully allocated slabs for debugging purposes.
674
 */
Christoph Lameter's avatar
Christoph Lameter committed
675
static void add_full(struct kmem_cache_node *n, struct page *page)
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
{
	spin_lock(&n->list_lock);
	list_add(&page->lru, &n->full);
	spin_unlock(&n->list_lock);
}

static void remove_full(struct kmem_cache *s, struct page *page)
{
	struct kmem_cache_node *n;

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

	n = get_node(s, page_to_nid(page));

	spin_lock(&n->list_lock);
	list_del(&page->lru);
	spin_unlock(&n->list_lock);
}

Christoph Lameter's avatar
Christoph Lameter committed
696
697
698
699
700
701
702
static int alloc_object_checks(struct kmem_cache *s, struct page *page,
							void *object)
{
	if (!check_slab(s, page))
		goto bad;

	if (object && !on_freelist(s, page, object)) {
703
704
		slab_err(s, page, "Object 0x%p already allocated", object);
		goto bad;
Christoph Lameter's avatar
Christoph Lameter committed
705
706
707
708
	}

	if (!check_valid_pointer(s, page, object)) {
		object_err(s, page, object, "Freelist Pointer check fails");
709
		goto bad;
Christoph Lameter's avatar
Christoph Lameter committed
710
711
712
713
714
715
716
717
718
719
720
721
722
723
	}

	if (!object)
		return 1;

	if (!check_object(s, page, object, 0))
		goto bad;

	return 1;
bad:
	if (PageSlab(page)) {
		/*
		 * If this is a slab page then lets do the best we can
		 * to avoid issues in the future. Marking all objects
Christoph Lameter's avatar
Christoph Lameter committed
724
		 * as used avoids touching the remaining objects.
Christoph Lameter's avatar
Christoph Lameter committed
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
		 */
		printk(KERN_ERR "@@@ SLUB: %s slab 0x%p. Marking all objects used.\n",
			s->name, page);
		page->inuse = s->objects;
		page->freelist = NULL;
		/* Fix up fields that may be corrupted */
		page->offset = s->offset / sizeof(void *);
	}
	return 0;
}

static int free_object_checks(struct kmem_cache *s, struct page *page,
							void *object)
{
	if (!check_slab(s, page))
		goto fail;

	if (!check_valid_pointer(s, page, object)) {
743
		slab_err(s, page, "Invalid object pointer 0x%p", object);
Christoph Lameter's avatar
Christoph Lameter committed
744
745
746
747
		goto fail;
	}

	if (on_freelist(s, page, object)) {
748
		slab_err(s, page, "Object 0x%p already free", object);
Christoph Lameter's avatar
Christoph Lameter committed
749
750
751
752
753
754
755
756
		goto fail;
	}

	if (!check_object(s, page, object, 1))
		return 0;

	if (unlikely(s != page->slab)) {
		if (!PageSlab(page))
757
758
			slab_err(s, page, "Attempt to free object(0x%p) "
				"outside of slab", object);
Christoph Lameter's avatar
Christoph Lameter committed
759
		else
760
		if (!page->slab) {
Christoph Lameter's avatar
Christoph Lameter committed
761
			printk(KERN_ERR
762
				"SLUB <none>: no slab for object 0x%p.\n",
Christoph Lameter's avatar
Christoph Lameter committed
763
						object);
764
765
			dump_stack();
		}
Christoph Lameter's avatar
Christoph Lameter committed
766
		else
767
768
			slab_err(s, page, "object at 0x%p belongs "
				"to slab %s", object, page->slab->name);
Christoph Lameter's avatar
Christoph Lameter committed
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
		goto fail;
	}
	return 1;
fail:
	printk(KERN_ERR "@@@ SLUB: %s slab 0x%p object at 0x%p not freed.\n",
		s->name, page, object);
	return 0;
}

/*
 * Slab allocation and freeing
 */
static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
{
	struct page * page;
	int pages = 1 << s->order;

	if (s->order)
		flags |= __GFP_COMP;

	if (s->flags & SLAB_CACHE_DMA)
		flags |= SLUB_DMA;

	if (node == -1)
		page = alloc_pages(flags, s->order);
	else
		page = alloc_pages_node(node, flags, s->order);

	if (!page)
		return NULL;

	mod_zone_page_state(page_zone(page),
		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
		pages);

	return page;
}

static void setup_object(struct kmem_cache *s, struct page *page,
				void *object)
{
	if (PageError(page)) {
		init_object(s, object, 0);
		init_tracking(s, object);
	}

816
817
	if (unlikely(s->ctor))
		s->ctor(object, s, SLAB_CTOR_CONSTRUCTOR);
Christoph Lameter's avatar
Christoph Lameter committed
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
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
}

static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
{
	struct page *page;
	struct kmem_cache_node *n;
	void *start;
	void *end;
	void *last;
	void *p;

	BUG_ON(flags & ~(GFP_DMA | GFP_LEVEL_MASK));

	if (flags & __GFP_WAIT)
		local_irq_enable();

	page = allocate_slab(s, flags & GFP_LEVEL_MASK, node);
	if (!page)
		goto out;

	n = get_node(s, page_to_nid(page));
	if (n)
		atomic_long_inc(&n->nr_slabs);
	page->offset = s->offset / sizeof(void *);
	page->slab = s;
	page->flags |= 1 << PG_slab;
	if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
			SLAB_STORE_USER | SLAB_TRACE))
		page->flags |= 1 << PG_error;

	start = page_address(page);
	end = start + s->objects * s->size;

	if (unlikely(s->flags & SLAB_POISON))
		memset(start, POISON_INUSE, PAGE_SIZE << s->order);

	last = start;
	for (p = start + s->size; p < end; p += s->size) {
		setup_object(s, page, last);
		set_freepointer(s, last, p);
		last = p;
	}
	setup_object(s, page, last);
	set_freepointer(s, last, NULL);

	page->freelist = start;
	page->inuse = 0;
out:
	if (flags & __GFP_WAIT)
		local_irq_disable();
	return page;
}

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

	if (unlikely(PageError(page) || s->dtor)) {
		void *start = page_address(page);
		void *end = start + (pages << PAGE_SHIFT);
		void *p;

		slab_pad_check(s, page);
		for (p = start; p <= end - s->size; p += s->size) {
			if (s->dtor)
				s->dtor(p, s, 0);
			check_object(s, page, p, 0);
		}
	}

	mod_zone_page_state(page_zone(page),
		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
		- pages);

	page->mapping = NULL;
	__free_pages(page, s->order);
}

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

	page = container_of((struct list_head *)h, struct page, lru);
	__free_slab(page->slab, page);
}

static void free_slab(struct kmem_cache *s, struct page *page)
{
	if (unlikely(s->flags & SLAB_DESTROY_BY_RCU)) {
		/*
		 * RCU free overloads the RCU head over the LRU
		 */
		struct rcu_head *head = (void *)&page->lru;

		call_rcu(head, rcu_free_slab);
	} else
		__free_slab(s, page);
}

static void discard_slab(struct kmem_cache *s, struct page *page)
{
	struct kmem_cache_node *n = get_node(s, page_to_nid(page));

	atomic_long_dec(&n->nr_slabs);
	reset_page_mapcount(page);
	page->flags &= ~(1 << PG_slab | 1 << PG_error);
	free_slab(s, page);
}

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

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

static __always_inline int slab_trylock(struct page *page)
{
	int rc = 1;

	rc = bit_spin_trylock(PG_locked, &page->flags);
	return rc;
}

/*
 * Management of partially allocated slabs
 */
Christoph Lameter's avatar
Christoph Lameter committed
952
static void add_partial_tail(struct kmem_cache_node *n, struct page *page)
Christoph Lameter's avatar
Christoph Lameter committed
953
{
Christoph Lameter's avatar
Christoph Lameter committed
954
955
956
957
958
	spin_lock(&n->list_lock);
	n->nr_partial++;
	list_add_tail(&page->lru, &n->partial);
	spin_unlock(&n->list_lock);
}
Christoph Lameter's avatar
Christoph Lameter committed
959

Christoph Lameter's avatar
Christoph Lameter committed
960
961
static void add_partial(struct kmem_cache_node *n, struct page *page)
{
Christoph Lameter's avatar
Christoph Lameter committed
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
	spin_lock(&n->list_lock);
	n->nr_partial++;
	list_add(&page->lru, &n->partial);
	spin_unlock(&n->list_lock);
}

static void remove_partial(struct kmem_cache *s,
						struct page *page)
{
	struct kmem_cache_node *n = get_node(s, page_to_nid(page));

	spin_lock(&n->list_lock);
	list_del(&page->lru);
	n->nr_partial--;
	spin_unlock(&n->list_lock);
}

/*
Christoph Lameter's avatar
Christoph Lameter committed
980
 * Lock slab and remove from the partial list.
Christoph Lameter's avatar
Christoph Lameter committed
981
 *
Christoph Lameter's avatar
Christoph Lameter committed
982
 * Must hold list_lock.
Christoph Lameter's avatar
Christoph Lameter committed
983
984
985
986
987
988
989
990
991
992
993
994
 */
static int lock_and_del_slab(struct kmem_cache_node *n, struct page *page)
{
	if (slab_trylock(page)) {
		list_del(&page->lru);
		n->nr_partial--;
		return 1;
	}
	return 0;
}

/*
Christoph Lameter's avatar
Christoph Lameter committed
995
 * Try to allocate a partial slab from a specific node.
Christoph Lameter's avatar
Christoph Lameter committed
996
997
998
999
1000
1001
1002
1003
 */
static struct page *get_partial_node(struct kmem_cache_node *n)
{
	struct page *page;

	/*
	 * Racy check. If we mistakenly see no partial slabs then we
	 * just allocate an empty slab. If we mistakenly try to get a
Christoph Lameter's avatar
Christoph Lameter committed
1004
1005
	 * partial slab and there is none available then get_partials()
	 * will return NULL.
Christoph Lameter's avatar
Christoph Lameter committed
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
	 */
	if (!n || !n->nr_partial)
		return NULL;

	spin_lock(&n->list_lock);
	list_for_each_entry(page, &n->partial, lru)
		if (lock_and_del_slab(n, page))
			goto out;
	page = NULL;
out:
	spin_unlock(&n->list_lock);
	return page;
}

/*
Christoph Lameter's avatar
Christoph Lameter committed
1021
 * Get a page from somewhere. Search in increasing NUMA distances.
Christoph Lameter's avatar
Christoph Lameter committed
1022
1023
1024
1025
1026
1027
1028
1029
1030
 */
static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
{
#ifdef CONFIG_NUMA
	struct zonelist *zonelist;
	struct zone **z;
	struct page *page;

	/*
Christoph Lameter's avatar
Christoph Lameter committed
1031
1032
1033
1034
	 * The defrag ratio allows a configuration of the tradeoffs between
	 * inter node defragmentation and node local allocations. A lower
	 * defrag_ratio increases the tendency to do local allocations
	 * instead of attempting to obtain partial slabs from other nodes.
Christoph Lameter's avatar
Christoph Lameter committed
1035
	 *
Christoph Lameter's avatar
Christoph Lameter committed
1036
1037
1038
1039
	 * If the defrag_ratio is set to 0 then kmalloc() always
	 * returns node local objects. If the ratio is higher then kmalloc()
	 * may return off node objects because partial slabs are obtained
	 * from other nodes and filled up.
Christoph Lameter's avatar
Christoph Lameter committed
1040
1041
	 *
	 * If /sys/slab/xx/defrag_ratio is set to 100 (which makes
Christoph Lameter's avatar
Christoph Lameter committed
1042
1043
1044
1045
1046
	 * defrag_ratio = 1000) then every (well almost) allocation will
	 * first attempt to defrag slab caches on other nodes. This means
	 * scanning over all nodes to look for partial slabs which may be
	 * expensive if we do it every time we are trying to find a slab
	 * with available objects.
Christoph Lameter's avatar
Christoph Lameter committed
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
	 */
	if (!s->defrag_ratio || get_cycles() % 1024 > s->defrag_ratio)
		return NULL;

	zonelist = &NODE_DATA(slab_node(current->mempolicy))
					->node_zonelists[gfp_zone(flags)];
	for (z = zonelist->zones; *z; z++) {
		struct kmem_cache_node *n;

		n = get_node(s, zone_to_nid(*z));

		if (n && cpuset_zone_allowed_hardwall(*z, flags) &&
Christoph Lameter's avatar
Christoph Lameter committed
1059
				n->nr_partial > MIN_PARTIAL) {
Christoph Lameter's avatar
Christoph Lameter committed
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
			page = get_partial_node(n);
			if (page)
				return page;
		}
	}
#endif
	return NULL;
}

/*
 * Get a partial page, lock it and return it.
 */
static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node)
{
	struct page *page;
	int searchnode = (node == -1) ? numa_node_id() : node;

	page = get_partial_node(get_node(s, searchnode));
	if (page || (flags & __GFP_THISNODE))
		return page;

	return get_any_partial(s, flags);
}

/*
 * Move a page back to the lists.
 *
 * Must be called with the slab lock held.
 *
 * On exit the slab lock will have been dropped.
 */
static void putback_slab(struct kmem_cache *s, struct page *page)
{
Christoph Lameter's avatar
Christoph Lameter committed
1093
1094
	struct kmem_cache_node *n = get_node(s, page_to_nid(page));

Christoph Lameter's avatar
Christoph Lameter committed
1095
	if (page->inuse) {
Christoph Lameter's avatar
Christoph Lameter committed
1096

Christoph Lameter's avatar
Christoph Lameter committed
1097
		if (page->freelist)
Christoph Lameter's avatar
Christoph Lameter committed
1098
1099
1100
			add_partial(n, page);
		else if (PageError(page) && (s->flags & SLAB_STORE_USER))
			add_full(n, page);
Christoph Lameter's avatar
Christoph Lameter committed
1101
		slab_unlock(page);
Christoph Lameter's avatar
Christoph Lameter committed
1102

Christoph Lameter's avatar
Christoph Lameter committed
1103
	} else {
Christoph Lameter's avatar
Christoph Lameter committed
1104
1105
		if (n->nr_partial < MIN_PARTIAL) {
			/*
Christoph Lameter's avatar
Christoph Lameter committed
1106
1107
1108
1109
1110
1111
			 * Adding an empty slab to the partial slabs in order
			 * to avoid page allocator overhead. This slab needs
			 * to come after the other slabs with objects in
			 * order to fill them up. That way the size of the
			 * partial list stays small. kmem_cache_shrink can
			 * reclaim empty slabs from the partial list.
Christoph Lameter's avatar
Christoph Lameter committed
1112
1113
1114
1115
1116
1117
1118
			 */
			add_partial_tail(n, page);
			slab_unlock(page);
		} else {
			slab_unlock(page);
			discard_slab(s, page);
		}
Christoph Lameter's avatar
Christoph Lameter committed
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
	}
}

/*
 * Remove the cpu slab
 */
static void deactivate_slab(struct kmem_cache *s, struct page *page, int cpu)
{
	s->cpu_slab[cpu] = NULL;
	ClearPageActive(page);

	putback_slab(s, page);
}

static void flush_slab(struct kmem_cache *s, struct page *page, int cpu)
{
	slab_lock(page);
	deactivate_slab(s, page, cpu);
}

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

	if (likely(page))
		flush_slab(s, page, cpu);
}

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

	__flush_cpu_slab(s, cpu);
}

static void flush_all(struct kmem_cache *s)
{
#ifdef CONFIG_SMP
	on_each_cpu(flush_cpu_slab, s, 1, 1);
#else
	unsigned long flags;

	local_irq_save(flags);
	flush_cpu_slab(s);
	local_irq_restore(flags);
#endif
}

/*
 * slab_alloc is optimized to only modify two cachelines on the fast path
 * (aside from the stack):
 *
 * 1. The page struct
 * 2. The first cacheline of the object to be allocated.
 *
Christoph Lameter's avatar
Christoph Lameter committed
1179
 * The only other cache lines that are read (apart from code) is the
Christoph Lameter's avatar
Christoph Lameter committed
1180
1181
1182
1183
1184
 * per cpu array in the kmem_cache struct.
 *
 * Fastpath is not possible if we need to get a new slab or have
 * debugging enabled (which means all slabs are marked with PageError)
 */
Christoph Lameter's avatar
Christoph Lameter committed
1185
1186
static void *slab_alloc(struct kmem_cache *s,
				gfp_t gfpflags, int node, void *addr)
Christoph Lameter's avatar
Christoph Lameter committed
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
{
	struct page *page;
	void **object;
	unsigned long flags;
	int cpu;

	local_irq_save(flags);
	cpu = smp_processor_id();
	page = s->cpu_slab[cpu];
	if (!page)
		goto new_slab;

	slab_lock(page);
	if (unlikely(node != -1 && page_to_nid(page) != node))
		goto another_slab;
redo:
	object = page->freelist;
	if (unlikely(!object))
		goto another_slab;
	if (unlikely(PageError(page)))
		goto debug;

have_object:
	page->inuse++;
	page->freelist = object[page->offset];
	slab_unlock(page);
	local_irq_restore(flags);
	return object;

another_slab:
	deactivate_slab(s, page, cpu);

new_slab:
	page = get_partial(s, gfpflags, node);
	if (likely(page)) {
have_slab:
		s->cpu_slab[cpu] = page;
		SetPageActive(page);
		goto redo;
	}

	page = new_slab(s, gfpflags, node);
	if (page) {
		cpu = smp_processor_id();
		if (s->cpu_slab[cpu]) {
			/*
Christoph Lameter's avatar
Christoph Lameter committed
1233
1234
1235
1236
1237
			 * Someone else populated the cpu_slab while we
			 * enabled interrupts, or we have gotten scheduled
			 * on another cpu. The page may not be on the
			 * requested node even if __GFP_THISNODE was
			 * specified. So we need to recheck.
Christoph Lameter's avatar
Christoph Lameter committed
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
			 */
			if (node == -1 ||
				page_to_nid(s->cpu_slab[cpu]) == node) {
				/*
				 * Current cpuslab is acceptable and we
				 * want the current one since its cache hot
				 */
				discard_slab(s, page);
				page = s->cpu_slab[cpu];
				slab_lock(page);
				goto redo;
			}
Christoph Lameter's avatar
Christoph Lameter committed
1250
			/* New slab does not fit our expectations */
Christoph Lameter's avatar
Christoph Lameter committed
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
			flush_slab(s, s->cpu_slab[cpu], cpu);
		}
		slab_lock(page);
		goto have_slab;
	}
	local_irq_restore(flags);
	return NULL;
debug:
	if (!alloc_object_checks(s, page, object))
		goto another_slab;
	if (s->flags & SLAB_STORE_USER)
Christoph Lameter's avatar
Christoph Lameter committed
1262
		set_track(s, object, TRACK_ALLOC, addr);
1263
1264
1265
1266
1267
1268
1269
	if (s->flags & SLAB_TRACE) {
		printk(KERN_INFO "TRACE %s alloc 0x%p inuse=%d fp=0x%p\n",
			s->name, object, page->inuse,
			page->freelist);
		dump_stack();
	}
	init_object(s, object, 1);
Christoph Lameter's avatar
Christoph Lameter committed
1270
1271
1272
1273
1274
	goto have_object;
}

void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
{
Christoph Lameter's avatar
Christoph Lameter committed
1275
	return slab_alloc(s, gfpflags, -1, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
1276
1277
1278
1279
1280
1281
}
EXPORT_SYMBOL(kmem_cache_alloc);

#ifdef CONFIG_NUMA
void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
{
Christoph Lameter's avatar
Christoph Lameter committed
1282
	return slab_alloc(s, gfpflags, node, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
1283
1284
1285
1286
1287
1288
1289
1290
}
EXPORT_SYMBOL(kmem_cache_alloc_node);
#endif

/*
 * The fastpath only writes the cacheline of the page struct and the first
 * cacheline of the object.
 *
Christoph Lameter's avatar
Christoph Lameter committed
1291
1292
 * We read the cpu_slab cacheline to check if the slab is the per cpu
 * slab for this processor.
Christoph Lameter's avatar
Christoph Lameter committed
1293
 */
Christoph Lameter's avatar
Christoph Lameter committed
1294
1295
static void slab_free(struct kmem_cache *s, struct page *page,
					void *x, void *addr)
Christoph Lameter's avatar
Christoph Lameter committed
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
{
	void *prior;
	void **object = (void *)x;
	unsigned long flags;

	local_irq_save(flags);
	slab_lock(page);

	if (unlikely(PageError(page)))
		goto debug;
checks_ok:
	prior = object[page->offset] = page->freelist;
	page->freelist = object;
	page->inuse--;

	if (unlikely(PageActive(page)))
		/*
		 * Cpu slabs are never on partial lists and are
		 * never freed.
		 */
		goto out_unlock;

	if (unlikely(!page->inuse))
		goto slab_empty;

	/*
	 * Objects left in the slab. If it
	 * was not on the partial list before
	 * then add it.
	 */
	if (unlikely(!prior))
Christoph Lameter's avatar
Christoph Lameter committed
1327
		add_partial(get_node(s, page_to_nid(page)), page);
Christoph Lameter's avatar
Christoph Lameter committed
1328
1329
1330
1331
1332
1333
1334
1335
1336

out_unlock:
	slab_unlock(page);
	local_irq_restore(flags);
	return;

slab_empty:
	if (prior)
		/*
Christoph Lameter's avatar
Christoph Lameter committed
1337
		 * Slab still on the partial list.
Christoph Lameter's avatar
Christoph Lameter committed
1338
1339
1340
1341
1342
1343
1344
1345
1346
		 */
		remove_partial(s, page);

	slab_unlock(page);
	discard_slab(s, page);
	local_irq_restore(flags);
	return;

debug:
Christoph Lameter's avatar
Christoph Lameter committed
1347
1348
	if (!free_object_checks(s, page, x))
		goto out_unlock;
1349
1350
	if (!PageActive(page) && !page->freelist)
		remove_full(s, page);
Christoph Lameter's avatar
Christoph Lameter committed
1351
1352
	if (s->flags & SLAB_STORE_USER)
		set_track(s, x, TRACK_FREE, addr);
1353
1354
1355
1356
1357
1358
1359
1360
	if (s->flags & SLAB_TRACE) {
		printk(KERN_INFO "TRACE %s free 0x%p inuse=%d fp=0x%p\n",
			s->name, object, page->inuse,
			page->freelist);
		print_section("Object", (void *)object, s->objsize);
		dump_stack();
	}
	init_object(s, object, 0);
Christoph Lameter's avatar
Christoph Lameter committed
1361
	goto checks_ok;
Christoph Lameter's avatar
Christoph Lameter committed
1362
1363
1364
1365
}

void kmem_cache_free(struct kmem_cache *s, void *x)
{
Christoph Lameter's avatar
Christoph Lameter committed
1366
	struct page *page;
Christoph Lameter's avatar
Christoph Lameter committed
1367

1368
	page = virt_to_head_page(x);
Christoph Lameter's avatar
Christoph Lameter committed
1369

Christoph Lameter's avatar
Christoph Lameter committed
1370
	slab_free(s, page, x, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
1371
1372
1373
1374
1375
1376
}
EXPORT_SYMBOL(kmem_cache_free);

/* Figure out on which slab object the object resides */
static struct page *get_object_page(const void *x)
{
1377
	struct page *page = virt_to_head_page(x);
Christoph Lameter's avatar
Christoph Lameter committed
1378
1379
1380
1381
1382
1383
1384
1385

	if (!PageSlab(page))
		return NULL;

	return page;
}

/*
Christoph Lameter's avatar
Christoph Lameter committed
1386
1387
1388
1389
 * Object placement in a slab is made very easy because we always start at
 * offset 0. If we tune the size of the object to the alignment then we can
 * get the required alignment by putting one properly sized object after
 * another.
Christoph Lameter's avatar
Christoph Lameter committed
1390
1391
1392
1393
 *
 * Notice that the allocation order determines the sizes of the per cpu
 * caches. Each processor has always one slab available for allocations.
 * Increasing the allocation order reduces the number of times that slabs
Christoph Lameter's avatar
Christoph Lameter committed
1394
 * must be moved on and off the partial lists and is therefore a factor in
Christoph Lameter's avatar
Christoph Lameter committed
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
 * locking overhead.
 */

/*
 * Mininum / Maximum order of slab pages. This influences locking overhead
 * and slab fragmentation. A higher order reduces the number of partial slabs
 * and increases the number of allocations possible without having to
 * take the list_lock.
 */
static int slub_min_order;
static int slub_max_order = DEFAULT_MAX_ORDER;
static int slub_min_objects = DEFAULT_MIN_OBJECTS;

/*
 * Merge control. If this is set then no merging of slab caches will occur.
Christoph Lameter's avatar
Christoph Lameter committed
1410
 * (Could be removed. This was introduced to pacify the merge skeptics.)
Christoph Lameter's avatar
Christoph Lameter committed
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
 */
static int slub_nomerge;

/*
 * Debug settings:
 */
static int slub_debug;

static char *slub_debug_slabs;

/*
 * Calculate the order of allocation given an slab object size.
 *
Christoph Lameter's avatar
Christoph Lameter committed
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
 * The order of allocation has significant impact on performance and other
 * system components. Generally order 0 allocations should be preferred since
 * order 0 does not cause fragmentation in the page allocator. Larger objects
 * be problematic to put into order 0 slabs because there may be too much
 * unused space left. We go to a higher order if more than 1/8th of the slab
 * would be wasted.
 *
 * In order to reach satisfactory performance we must ensure that a minimum
 * number of objects is in one slab. Otherwise we may generate too much
 * activity on the partial lists which requires taking the list_lock. This is
 * less a concern for large slabs though which are rarely used.
Christoph Lameter's avatar
Christoph Lameter committed
1435
 *
Christoph Lameter's avatar
Christoph Lameter committed
1436
1437
1438
1439
 * slub_max_order specifies the order where we begin to stop considering the
 * number of objects in a slab as critical. If we reach slub_max_order then
 * we try to keep the page order as low as possible. So we accept more waste
 * of space in favor of a small page order.
Christoph Lameter's avatar
Christoph Lameter committed
1440
 *
Christoph Lameter's avatar
Christoph Lameter committed
1441
1442
1443
1444
 * Higher order allocations also allow the placement of more objects in a
 * slab and thereby reduce object handling overhead. If the user has
 * requested a higher mininum order then we start with that one instead of
 * the smallest order which will fit the object.
Christoph Lameter's avatar
Christoph Lameter committed
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
 */
static int calculate_order(int size)
{
	int order;
	int rem;

	for (order = max(slub_min_order, fls(size - 1) - PAGE_SHIFT);
			order < MAX_ORDER; order++) {
		unsigned long slab_size = PAGE_SIZE << order;

		if (slub_max_order > order &&
				slab_size < slub_min_objects * size)
			continue;

		if (slab_size < size)
			continue;

		rem = slab_size % size;

Christoph Lameter's avatar
Christoph Lameter committed
1464
		if (rem <= slab_size / 8)
Christoph Lameter's avatar
Christoph Lameter committed
1465
1466
1467
1468
1469
			break;

	}
	if (order >= MAX_ORDER)
		return -E2BIG;
Christoph Lameter's avatar
Christoph Lameter committed
1470

Christoph Lameter's avatar
Christoph Lameter committed
1471
1472
1473
1474
	return order;
}

/*
Christoph Lameter's avatar
Christoph Lameter committed
1475
 * Figure out what the alignment of the objects will be.
Christoph Lameter's avatar
Christoph Lameter committed
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
 */
static unsigned long calculate_alignment(unsigned long flags,
		unsigned long align, unsigned long size)
{
	/*
	 * If the user wants hardware cache aligned objects then
	 * follow that suggestion if the object is sufficiently
	 * large.
	 *
	 * The hardware cache alignment cannot override the
	 * specified alignment though. If that is greater
	 * then use it.
	 */
1489
	if ((flags & SLAB_HWCACHE_ALIGN) &&
1490
1491
			size > cache_line_size() / 2)
		return max_t(unsigned long, align, cache_line_size());
Christoph Lameter's avatar
Christoph Lameter committed
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504

	if (align < ARCH_SLAB_MINALIGN)
		return ARCH_SLAB_MINALIGN;

	return ALIGN(align, sizeof(void *));
}

static void init_kmem_cache_node(struct kmem_cache_node *n)
{
	n->nr_partial = 0;
	atomic_long_set(&n->nr_slabs, 0);
	spin_lock_init(&n->list_lock);
	INIT_LIST_HEAD(&n->partial);
1505
	INIT_LIST_HEAD(&n->full);
Christoph Lameter's avatar
Christoph Lameter committed
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
}

#ifdef CONFIG_NUMA
/*
 * No kmalloc_node yet so do it by hand. We know that this is the first
 * slab on the node for this slabcache. There are no concurrent accesses
 * possible.
 *
 * Note that this function only works on the kmalloc_node_cache
 * when allocating for the kmalloc_node_cache.
 */
static struct kmem_cache_node * __init early_kmem_cache_node_alloc(gfp_t gfpflags,
								int node)
{
	struct page *page;
	struct kmem_cache_node *n;

	BUG_ON(kmalloc_caches->size < sizeof(struct kmem_cache_node));

	page = new_slab(kmalloc_caches, gfpflags | GFP_THISNODE, node);
	/* new_slab() disables interupts */
	local_irq_enable();

	BUG_ON(!page);
	n = page->freelist;
	BUG_ON(!n);
	page->freelist = get_freepointer(kmalloc_caches, n);
	page->inuse++;
	kmalloc_caches->node[node] = n;
	init_object(kmalloc_caches, n, 1);
	init_kmem_cache_node(n);
	atomic_long_inc(&n->nr_slabs);
Christoph Lameter's avatar
Christoph Lameter committed
1538
	add_partial(n, page);
Christoph Lameter's avatar
Christoph Lameter committed
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
	return n;
}

static void free_kmem_cache_nodes(struct kmem_cache *s)
{
	int node;

	for_each_online_node(node) {
		struct kmem_cache_node *n = s->node[node];
		if (n && n != &s->local_node)
			kmem_cache_free(kmalloc_caches, n);
		s->node[node] = NULL;
	}
}

static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
{
	int node;
	int local_node;

	if (slab_state >= UP)
		local_node = page_to_nid(virt_to_page(s));
	else
		local_node = 0;

	for_each_online_node(node) {
		struct kmem_cache_node *n;

		if (local_node == node)
			n = &s->local_node;
		else {
			if (slab_state == DOWN) {
				n = early_kmem_cache_node_alloc(gfpflags,
								node);
				continue;
			}
			n = kmem_cache_alloc_node(kmalloc_caches,
							gfpflags, node);

			if (!n) {
				free_kmem_cache_nodes(s);
				return 0;
			}

		}
		s->node[node] = n;
		init_kmem_cache_node(n);
	}
	return 1;
}
#else
static void free_kmem_cache_nodes(struct kmem_cache *s)
{
}

static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
{
	init_kmem_cache_node(&s->local_node);
	return 1;
}
#endif

/*
 * calculate_sizes() determines the order and the distribution of data within
 * a slab object.
 */
static int calculate_sizes(struct kmem_cache *s)
{
	unsigned long flags = s->flags;
	unsigned long size = s->objsize;
	unsigned long align = s->align;

	/*
	 * Determine if we can poison the object itself. If the user of
	 * the slab may touch the object after free or before allocation
	 * then we should never poison the object itself.
	 */
	if ((flags & SLAB_POISON) && !(flags & SLAB_DESTROY_BY_RCU) &&
			!s->ctor && !s->dtor)
		s->flags |= __OBJECT_POISON;
	else
		s->flags &= ~__OBJECT_POISON;

	/*
	 * Round up object size to the next word boundary. We can only
	 * place the free pointer at word boundaries and this determines
	 * the possible location of the free pointer.
	 */
	size = ALIGN(size, sizeof(void *));

	/*
Christoph Lameter's avatar
Christoph Lameter committed
1630
	 * If we are Redzoning then check if there is some space between the
Christoph Lameter's avatar
Christoph Lameter committed
1631
	 * end of the object and the free pointer. If not then add an
Christoph Lameter's avatar
Christoph Lameter committed
1632
	 * additional word to have some bytes to store Redzone information.
Christoph Lameter's avatar
Christoph Lameter committed
1633
1634
1635
1636
1637
	 */
	if ((flags & SLAB_RED_ZONE) && size == s->objsize)
		size += sizeof(void *);

	/*
Christoph Lameter's avatar
Christoph Lameter committed
1638
1639
	 * With that we have determined the number of bytes in actual use
	 * by the object. This is the potential offset to the free pointer.
Christoph Lameter's avatar
Christoph Lameter committed
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
	 */
	s->inuse = size;

	if (((flags & (SLAB_DESTROY_BY_RCU | SLAB_POISON)) ||
		s->ctor || s->dtor)) {
		/*
		 * Relocate free pointer after the object if it is not
		 * permitted to overwrite the first word of the object on
		 * kmem_cache_free.
		 *
		 * This is the case if we do RCU, have a constructor or
		 * destructor or are poisoning the objects.
		 */
		s->offset = size;
		size += sizeof(void *);
	}

	if (flags & SLAB_STORE_USER)
		/*
		 * Need to store information about allocs and frees after
		 * the object.
		 */
		size += 2 * sizeof(struct track);

1664
	if (flags & SLAB_RED_ZONE)
Christoph Lameter's avatar
Christoph Lameter committed
1665
1666
1667
1668
1669
1670
1671
1672
		/*
		 * Add some empty padding so that we can catch
		 * overwrites from earlier objects rather than let
		 * tracking information or the free pointer be
		 * corrupted if an user writes before the start
		 * of the object.
		 */
		size += sizeof(void *);
Christoph Lameter's avatar
Christoph Lameter committed
1673

Christoph Lameter's avatar
Christoph Lameter committed
1674
1675
	/*
	 * Determine the alignment based on various parameters that the
1676
1677
	 * user specified and the dynamic determination of cache line size
	 * on bootup.
Christoph Lameter's avatar
Christoph Lameter committed
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
	 */
	align = calculate_alignment(flags, align, s->objsize);

	/*
	 * SLUB stores one object immediately after another beginning from
	 * offset 0. In order to align the objects we have to simply size
	 * each object to conform to the alignment.
	 */
	size = ALIGN(size, align);
	s->size = size;

	s->order = calculate_order(size);
	if (s->order < 0)
		return 0;

	/*
	 * Determine the number of objects per slab
	 */
	s->objects = (PAGE_SIZE << s->order) / size;

	/*
	 * Verify that the number of objects is within permitted limits.
	 * The page->inuse field is only 16 bit wide! So we cannot have
	 * more than 64k objects per slab.
	 */
	if (!s->objects || s->objects > 65535)
		return 0;
	return 1;

}

static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
		const char *name, size_t size,
		size_t align, unsigned long flags,
		void (*ctor)(void *, struct kmem_cache *, unsigned long),
		void (*dtor)(void *, struct kmem_cache *, unsigned long))
{
	memset(s, 0, kmem_size);
	s->name = name;
	s->ctor = ctor;
	s->dtor = dtor;
	s->objsize = size;
	s->flags = flags;
	s->align = align;

	/*
	 * The page->offset field is only 16 bit wide. This is an offset
	 * in units of words from the beginning of an object. If the slab
	 * size is bigger then we cannot move the free pointer behind the
	 * object anymore.
	 *
	 * On 32 bit platforms the limit is 256k. On 64bit platforms
	 * the limit is 512k.
	 *
	 * Debugging or ctor/dtors may create a need to move the free
	 * pointer. Fail if this happens.
	 */
	if (s->size >= 65535 * sizeof(void *)) {
		BUG_ON(flags & (SLAB_RED_ZONE | SLAB_POISON |
				SLAB_STORE_USER | SLAB_DESTROY_BY_RCU));
		BUG_ON(ctor || dtor);
	}
	else
		/*
		 * Enable debugging if selected on the kernel commandline.
		 */
		if (slub_debug && (!slub_debug_slabs ||
		    strncmp(slub_debug_slabs, name,
		    	strlen(slub_debug_slabs)) == 0))
				s->flags |= slub_debug;

	if (!calculate_sizes(s))
		goto error;

	s->refcount = 1;
#ifdef CONFIG_NUMA
	s->defrag_ratio = 100;
#endif

	if (init_kmem_cache_nodes(s, gfpflags & ~SLUB_DMA))
		return 1;
error:
	if (flags & SLAB_PANIC)
		panic("Cannot create slab %s size=%lu realsize=%u "
			"order=%u offset=%u flags=%lx\n",
			s->name, (unsigned long)size, s->size, s->order,
			s->offset, flags);
	return 0;
}
EXPORT_SYMBOL(kmem_cache_open);

/*
 * Check if a given pointer is valid
 */
int kmem_ptr_validate(struct kmem_cache *s, const void *object)
{
	struct page * page;

	page = get_object_page(object);

	if (!page || s != page->slab)
		/* No slab or wrong slab */
		return 0;

1782
	if (!check_valid_pointer(s, page, object))
Christoph Lameter's avatar
Christoph Lameter committed
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
		return 0;

	/*
	 * We could also check if the object is on the slabs freelist.
	 * But this would be too expensive and it seems that the main
	 * purpose of kmem_ptr_valid is to check if the object belongs
	 * to a certain slab.
	 */
	return 1;
}
EXPORT_SYMBOL(kmem_ptr_validate);

/*
 * Determine the size of a slab object
 */
unsigned int kmem_cache_size(struct kmem_cache *s)
{
	return s->objsize;
}
EXPORT_SYMBOL(kmem_cache_size);

const char *kmem_cache_name(struct kmem_cache *s)
{
	return s->name;
}
EXPORT_SYMBOL(kmem_cache_name);

/*
Christoph Lameter's avatar
Christoph Lameter committed
1811
1812
 * Attempt to free all slabs on a node. Return the number of slabs we
 * were unable to free.
Christoph Lameter's avatar
Christoph Lameter committed
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
 */
static int free_list(struct kmem_cache *s, struct kmem_cache_node *n,
			struct list_head *list)
{
	int slabs_inuse = 0;
	unsigned long flags;
	struct page *page, *h;

	spin_lock_irqsave(&n->list_lock, flags);
	list_for_each_entry_safe(page, h, list, lru)
		if (!page->inuse) {
			list_del(&page->lru);
			discard_slab(s, page);
		} else
			slabs_inuse++;
	spin_unlock_irqrestore(&n->list_lock, flags);
	return slabs_inuse;
}

/*
Christoph Lameter's avatar
Christoph Lameter committed
1833
 * Release all resources used by a slab cache.
Christoph Lameter's avatar
Christoph Lameter committed
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
 */
static int kmem_cache_close(struct kmem_cache *s)
{
	int node;

	flush_all(s);

	/* Attempt to free all objects */
	for_each_online_node(node) {
		struct kmem_cache_node *n = get_node(s, node);

1845
		n->nr_partial -= free_list(s, n, &n->partial);
Christoph Lameter's avatar
Christoph Lameter committed
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
		if (atomic_long_read(&n->nr_slabs))
			return 1;
	}
	free_kmem_cache_nodes(s);
	return 0;
}

/*
 * Close a cache and release the kmem_cache structure
 * (must be used for caches created using kmem_cache_create)
 */
void kmem_cache_destroy(struct kmem_cache *s)
{
	down_write(&slub_lock);
	s->refcount--;
	if (!s->refcount) {
		list_del(&s->list);
		if (kmem_cache_close(s))
			WARN_ON(1);
		sysfs_slab_remove(s);
		kfree(s);
	}
	up_write(&slub_lock);
}
EXPORT_SYMBOL(kmem_cache_destroy);

/********************************************************************
 *		Kmalloc subsystem
 *******************************************************************/

struct kmem_cache kmalloc_caches[KMALLOC_SHIFT_HIGH + 1] __cacheline_aligned;
EXPORT_SYMBOL(kmalloc_caches);

#ifdef CONFIG_ZONE_DMA
static struct kmem_cache *kmalloc_caches_dma[KMALLOC_SHIFT_HIGH + 1];
#endif

static int __init setup_slub_min_order(char *str)
{
	get_option (&str, &slub_min_order);

	return 1;
}

__setup("slub_min_order=", setup_slub_min_order);

static int __init setup_slub_max_order(char *str)
{
	get_option (&str, &slub_max_order);

	return 1;
}

__setup("slub_max_order=", setup_slub_max_order);

static int __init setup_slub_min_objects(char *str)
{
	get_option (&str, &slub_min_objects);

	return 1;
}

__setup("slub_min_objects=", setup_slub_min_objects);

static int __init setup_slub_nomerge(char *str)
{
	slub_nomerge = 1;
	return 1;
}

__setup("slub_nomerge", setup_slub_nomerge);

static int __init setup_slub_debug(char *str)
{
	if (!str || *str != '=')
		slub_debug = DEBUG_DEFAULT_FLAGS;
	else {
		str++;
		if (*str == 0 || *str == ',')
			slub_debug = DEBUG_DEFAULT_FLAGS;
		else
		for( ;*str && *str != ','; str++)
			switch (*str) {
			case 'f' : case 'F' :
				slub_debug |= SLAB_DEBUG_FREE;
				break;
			case 'z' : case 'Z' :
				slub_debug |= SLAB_RED_ZONE;
				break;
			case 'p' : case 'P' :
				slub_debug |= SLAB_POISON;
				break;
			case 'u' : case 'U' :
				slub_debug |= SLAB_STORE_USER;
				break;
			case 't' : case 'T' :
				slub_debug |= SLAB_TRACE;
				break;
			default:
				printk(KERN_ERR "slub_debug option '%c' "
					"unknown. skipped\n",*str);
			}
	}

	if (*str == ',')
		slub_debug_slabs = str + 1;
	return 1;
}

__setup("slub_debug", setup_slub_debug);

static struct kmem_cache *create_kmalloc_cache(struct kmem_cache *s,
		const char *name, int size, gfp_t gfp_flags)
{
	unsigned int flags = 0;

	if (gfp_flags & SLUB_DMA)
		flags = SLAB_CACHE_DMA;

	down_write(&slub_lock);
	if (!kmem_cache_open(s, gfp_flags, name, size, ARCH_KMALLOC_MINALIGN,
			flags, NULL, NULL))
		goto panic;

	list_add(&s->list, &slab_caches);
	up_write(&slub_lock);
	if (sysfs_slab_add(s))
		goto panic;
	return s;

panic:
	panic("Creation of kmalloc slab %s size=%d failed.\n", name, size);
}

static struct kmem_cache *get_slab(size_t size, gfp_t flags)
{
	int index = kmalloc_index(size);

1984
	if (!index)
Christoph Lameter's avatar
Christoph Lameter committed
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
		return NULL;

	/* Allocation too large? */
	BUG_ON(index < 0);

#ifdef CONFIG_ZONE_DMA
	if ((flags & SLUB_DMA)) {
		struct kmem_cache *s;
		struct kmem_cache *x;
		char *text;
		size_t realsize;

		s = kmalloc_caches_dma[index];
		if (s)
			return s;

		/* Dynamically create dma cache */
		x = kmalloc(kmem_size, flags & ~SLUB_DMA);
		if (!x)
			panic("Unable to allocate memory for dma cache\n");

		if (index <= KMALLOC_SHIFT_HIGH)
			realsize = 1 << index;
		else {
			if (index == 1)
				realsize = 96;
			else
				realsize = 192;
		}

		text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d",
				(unsigned int)realsize);
		s = create_kmalloc_cache(x, text, realsize, flags);
		kmalloc_caches_dma[index] = s;
		return s;
	}
#endif
	return &kmalloc_caches[index];
}

void *__kmalloc(size_t size, gfp_t flags)
{
	struct kmem_cache *s = get_slab(size, flags);

	if (s)
Christoph Lameter's avatar
Christoph Lameter committed
2030
		return slab_alloc(s, flags, -1, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
	return NULL;
}
EXPORT_SYMBOL(__kmalloc);

#ifdef CONFIG_NUMA
void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
	struct kmem_cache *s = get_slab(size, flags);

	if (s)
Christoph Lameter's avatar
Christoph Lameter committed
2041
		return slab_alloc(s, flags, node, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
	return NULL;
}
EXPORT_SYMBOL(__kmalloc_node);
#endif

size_t ksize(const void *object)
{
	struct page *page = get_object_page(object);
	struct kmem_cache *s;

	BUG_ON(!page);
	s = page->slab;
	BUG_ON(!s);

	/*
	 * Debugging requires use of the padding between object
	 * and whatever may come after it.
	 */
	if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
		return s->objsize;

	/*
	 * 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.
	 */
	if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
		return s->inuse;

	/*
	 * Else we can use all the padding etc for the allocation
	 */
	return s->size;
}
EXPORT_SYMBOL(ksize);

void kfree(const void *x)
{
	struct kmem_cache *s;
	struct page *page;

	if (!x)
		return;

2086
	page = virt_to_head_page(x);
Christoph Lameter's avatar
Christoph Lameter committed
2087
2088
	s = page->slab;

Christoph Lameter's avatar
Christoph Lameter committed
2089
	slab_free(s, page, (void *)x, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
2090
2091
2092
}
EXPORT_SYMBOL(kfree);

2093
/*
Christoph Lameter's avatar
Christoph Lameter committed
2094
2095
2096
2097
2098
2099
2100
2101
 * kmem_cache_shrink removes empty slabs from the partial lists and sorts
 * the remaining slabs by the number of items in use. The slabs with the
 * most items in use come first. New allocations will then fill those up
 * and thus they can be removed from the partial lists.
 *
 * The slabs with the least items are placed last. This results in them
 * being allocated from last increasing the chance that the last objects
 * are freed in them.
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
 */
int kmem_cache_shrink(struct kmem_cache *s)
{
	int node;
	int i;
	struct kmem_cache_node *n;
	struct page *page;
	struct page *t;
	struct list_head *slabs_by_inuse =
		kmalloc(sizeof(struct list_head) * s->objects, GFP_KERNEL);
	unsigned long flags;

	if (!slabs_by_inuse)
		return -ENOMEM;

	flush_all(s);
	for_each_online_node(node) {
		n = get_node(s, node);

		if (!n->nr_partial)
			continue;

		for (i = 0; i < s->objects; i++)
			INIT_LIST_HEAD(slabs_by_inuse + i);

		spin_lock_irqsave(&n->list_lock, flags);

		/*
Christoph Lameter's avatar
Christoph Lameter committed
2130
		 * Build lists indexed by the items in use in each slab.
2131
		 *
Christoph Lameter's avatar
Christoph Lameter committed
2132
2133
		 * Note that concurrent frees may occur while we hold the
		 * list_lock. page->inuse here is the upper limit.