slub.c 79.1 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
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
/*
 * 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.
 *
 * Slabs with free elements are kept on a partial list.
 * There is no list for full slabs. If an object in a full slab is
 * freed then the slab will show up again on the partial lists.
 * Otherwise there is no need to track full slabs unless we have to
 * track full slabs for debugging purposes.
 *
 * 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
 *   enough frequent updates. There are 16 pointers in a cacheline.so at
 *   max 16 cpus could compete. Likely okay.
 *
 * - Support PAGE_ALLOC_DEBUG. Should be easy to do.
 *
 * - SLAB_DEBUG_INITIAL is not supported but I have never seen a use of
 *   it.
 *
 * - 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

/*
 * Flags from the regular SLAB that SLUB does not support:
 */
#define SLUB_UNIMPLEMENTED (SLAB_DEBUG_INITIAL)

Christoph Lameter's avatar
Christoph Lameter committed
133
134
135
/* Mininum number of partial slabs */
#define MIN_PARTIAL 2

Christoph Lameter's avatar
Christoph Lameter committed
136
137
138
139
140
141
142
143
144
145
146
147
#define DEBUG_DEFAULT_FLAGS (SLAB_DEBUG_FREE | SLAB_RED_ZONE | \
				SLAB_POISON | SLAB_STORE_USER)
/*
 * 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
148
#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
Christoph Lameter's avatar
Christoph Lameter committed
149
150
151
#endif

#ifndef ARCH_SLAB_MINALIGN
152
#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
Christoph Lameter's avatar
Christoph Lameter committed
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
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
249
250
251
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
409
410
411
412
413
414
415
416
417
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
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
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
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
607
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
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
#endif

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

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 */
	UP,		/* Everything works */
	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.
 *
 * This requires touching the cache lines of kmem_cache.
 * The offset can also be obtained from the page. In that
 * case it is in the cacheline that we already need to touch.
 */
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;
}


static int check_valid_pointer(struct kmem_cache *s, struct page *page,
					 void *object)
{
	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.
 * 	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.
 * 	Padding is extended to word size if Redzoning is enabled
 * 	and objsize == inuse.
 * 	We fill with 0xbb (RED_INACTIVE) for inactive objects and with
 * 	0xcc (RED_ACTIVE) for objects in use.
 *
 * object + s->inuse
 * 	A. Free pointer (if we cannot overwrite object on free)
 * 	B. Tracking data for SLAB_STORE_USER
 * 	C. Padding to reach required alignment boundary
 * 		Padding is done using 0x5a (POISON_INUSE)
 *
 * object + s->size
 *
 * If slabcaches are merged then the objsize and inuse boundaries are to
 * be ignored. And therefore no slab options that rely on these boundaries
 * may be used with merged slabcaches.
 */

static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
						void *from, void *to)
{
	printk(KERN_ERR "@@@ SLUB: %s Restoring %s (0x%x) from 0x%p-0x%p\n",
		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)) {
		printk(KERN_ERR "SLUB: %s slab 0x%p: Padding fails check\n",
			s->name, p);
		dump_stack();
		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
		 * another error because the object count maybe
		 * wrong now.
		 */
		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)) {
		printk(KERN_ERR "SLUB: %s Not a valid slab page @0x%p "
			"flags=%lx mapping=0x%p count=%d \n",
			s->name, page, page->flags, page->mapping,
			page_count(page));
		return 0;
	}
	if (page->offset * sizeof(void *) != s->offset) {
		printk(KERN_ERR "SLUB: %s Corrupted offset %lu in slab @0x%p"
			" flags=0x%lx mapping=0x%p count=%d\n",
			s->name,
			(unsigned long)(page->offset * sizeof(void *)),
			page,
			page->flags,
			page->mapping,
			page_count(page));
		dump_stack();
		return 0;
	}
	if (page->inuse > s->objects) {
		printk(KERN_ERR "SLUB: %s Inuse %u > max %u in slab "
			"page @0x%p flags=%lx mapping=0x%p count=%d\n",
			s->name, page->inuse, s->objects, page, page->flags,
			page->mapping, page_count(page));
		dump_stack();
		return 0;
	}
	/* Slab_pad_check fixes things up after itself */
	slab_pad_check(s, page);
	return 1;
}

/*
 * Determine if a certain object on a page is on the freelist and
 * therefore free. Must hold the slab lock for cpu slabs to
 * guarantee that the chains are consistent.
 */
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 {
				printk(KERN_ERR "SLUB: %s slab 0x%p "
					"freepointer 0x%p corrupted.\n",
					s->name, page, fp);
				dump_stack();
				page->freelist = NULL;
				page->inuse = s->objects;
				return 0;
			}
			break;
		}
		object = fp;
		fp = get_freepointer(s, object);
		nr++;
	}

	if (page->inuse != s->objects - nr) {
		printk(KERN_ERR "slab %s: page 0x%p wrong object count."
			" counter is %d but counted were %d\n",
			s->name, page, page->inuse,
			s->objects - nr);
		page->inuse = s->objects - nr;
	}
	return search == NULL;
}

664
665
666
/*
 * Tracking of fully allocated slabs for debugging
 */
Christoph Lameter's avatar
Christoph Lameter committed
667
static void add_full(struct kmem_cache_node *n, struct page *page)
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
{
	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
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
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
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
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
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
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)) {
		printk(KERN_ERR "SLUB: %s Object 0x%p@0x%p "
			"already allocated.\n",
			s->name, object, page);
		goto dump;
	}

	if (!check_valid_pointer(s, page, object)) {
		object_err(s, page, object, "Freelist Pointer check fails");
		goto dump;
	}

	if (!object)
		return 1;

	if (!check_object(s, page, object, 0))
		goto bad;
	init_object(s, object, 1);

	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();
	}
	return 1;
dump:
	dump_stack();
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
		 * as used avoids touching the remainder.
		 */
		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)) {
		printk(KERN_ERR "SLUB: %s slab 0x%p invalid "
			"object pointer 0x%p\n",
			s->name, page, object);
		goto fail;
	}

	if (on_freelist(s, page, object)) {
		printk(KERN_ERR "SLUB: %s slab 0x%p object "
			"0x%p already free.\n", s->name, page, object);
		goto fail;
	}

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

	if (unlikely(s != page->slab)) {
		if (!PageSlab(page))
			printk(KERN_ERR "slab_free %s size %d: attempt to"
				"free object(0x%p) outside of slab.\n",
				s->name, s->size, object);
		else
		if (!page->slab)
			printk(KERN_ERR
				"slab_free : no slab(NULL) for object 0x%p.\n",
						object);
		else
		printk(KERN_ERR "slab_free %s(%d): object at 0x%p"
				" belongs to slab %s(%d)\n",
				s->name, s->size, object,
				page->slab->name, page->slab->size);
		goto fail;
	}
	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", object, s->objsize);
		dump_stack();
	}
	init_object(s, object, 0);
	return 1;
fail:
	dump_stack();
	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);
	}

	if (unlikely(s->ctor)) {
		int mode = SLAB_CTOR_CONSTRUCTOR;

		if (!(s->flags & __GFP_WAIT))
			mode |= SLAB_CTOR_ATOMIC;

		s->ctor(object, s, mode);
	}
}

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;

	if (flags & __GFP_NO_GROW)
		return NULL;

	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
977
static void add_partial_tail(struct kmem_cache_node *n, struct page *page)
Christoph Lameter's avatar
Christoph Lameter committed
978
{
Christoph Lameter's avatar
Christoph Lameter committed
979
980
981
982
983
	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
984

Christoph Lameter's avatar
Christoph Lameter committed
985
986
static void add_partial(struct kmem_cache_node *n, struct page *page)
{
Christoph Lameter's avatar
Christoph Lameter committed
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
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
	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);
}

/*
 * Lock page and remove it from the partial list
 *
 * Must hold list_lock
 */
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;
}

/*
 * Try to get a partial slab from a specific node
 */
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
	 * partial slab then get_partials() will return NULL.
	 */
	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;
}

/*
 * Get a page from somewhere. Search in increasing NUMA
 * distances.
 */
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;

	/*
	 * The defrag ratio allows to configure the tradeoffs between
	 * inter node defragmentation and node local allocations.
	 * A lower defrag_ratio increases the tendency to do local
	 * allocations instead of scanning throught the partial
	 * lists on other nodes.
	 *
	 * If defrag_ratio is set to 0 then kmalloc() always
	 * returns node local objects. If its higher then kmalloc()
	 * may return off node objects in order to avoid fragmentation.
	 *
	 * A higher ratio means slabs may be taken from other nodes
	 * thus reducing the number of partial slabs on those nodes.
	 *
	 * If /sys/slab/xx/defrag_ratio is set to 100 (which makes
	 * 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 a bit expensive to do on every slab allocation.
	 */
	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
1086
				n->nr_partial > MIN_PARTIAL) {
Christoph Lameter's avatar
Christoph Lameter committed
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
			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
1120
1121
	struct kmem_cache_node *n = get_node(s, page_to_nid(page));

Christoph Lameter's avatar
Christoph Lameter committed
1122
	if (page->inuse) {
Christoph Lameter's avatar
Christoph Lameter committed
1123

Christoph Lameter's avatar
Christoph Lameter committed
1124
		if (page->freelist)
Christoph Lameter's avatar
Christoph Lameter committed
1125
1126
1127
			add_partial(n, page);
		else if (PageError(page) && (s->flags & SLAB_STORE_USER))
			add_full(n, page);
Christoph Lameter's avatar
Christoph Lameter committed
1128
		slab_unlock(page);
Christoph Lameter's avatar
Christoph Lameter committed
1129

Christoph Lameter's avatar
Christoph Lameter committed
1130
	} else {
Christoph Lameter's avatar
Christoph Lameter committed
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
		if (n->nr_partial < MIN_PARTIAL) {
			/*
			 * Adding an empty page to the partial slabs in order
			 * to avoid page allocator overhead. This page needs to
			 * come after all the others that are not fully empty
			 * in order to make sure that we do maximum
			 * defragmentation.
			 */
			add_partial_tail(n, page);
			slab_unlock(page);
		} else {
			slab_unlock(page);
			discard_slab(s, page);
		}
Christoph Lameter's avatar
Christoph Lameter committed
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
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
	}
}

/*
 * 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.
 *
 * The only cache lines that are read (apart from code) is the
 * 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
1211
1212
static void *slab_alloc(struct kmem_cache *s,
				gfp_t gfpflags, int node, void *addr)
Christoph Lameter's avatar
Christoph Lameter committed
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
{
	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]) {
			/*
			 * Someone else populated the cpu_slab while we enabled
			 * interrupts, or we have got scheduled on another cpu.
			 * The page may not be on the requested node.
			 */
			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;
			}
			/* Dump the current slab */
			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
1286
		set_track(s, object, TRACK_ALLOC, addr);
Christoph Lameter's avatar
Christoph Lameter committed
1287
1288
1289
1290
1291
	goto have_object;
}

void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
{
Christoph Lameter's avatar
Christoph Lameter committed
1292
	return slab_alloc(s, gfpflags, -1, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
1293
1294
1295
1296
1297
1298
}
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
1299
	return slab_alloc(s, gfpflags, node, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
}
EXPORT_SYMBOL(kmem_cache_alloc_node);
#endif

/*
 * The fastpath only writes the cacheline of the page struct and the first
 * cacheline of the object.
 *
 * No special cachelines need to be read
 */
Christoph Lameter's avatar
Christoph Lameter committed
1310
1311
static void slab_free(struct kmem_cache *s, struct page *page,
					void *x, void *addr)
Christoph Lameter's avatar
Christoph Lameter committed
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
{
	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
1343
		add_partial(get_node(s, page_to_nid(page)), page);
Christoph Lameter's avatar
Christoph Lameter committed
1344
1345
1346
1347
1348
1349
1350
1351
1352

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

slab_empty:
	if (prior)
		/*
1353
		 * Slab on the partial list.
Christoph Lameter's avatar
Christoph Lameter committed
1354
1355
1356
1357
1358
1359
1360
1361
1362
		 */
		remove_partial(s, page);

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

debug:
Christoph Lameter's avatar
Christoph Lameter committed
1363
1364
	if (!free_object_checks(s, page, x))
		goto out_unlock;
1365
1366
	if (!PageActive(page) && !page->freelist)
		remove_full(s, page);
Christoph Lameter's avatar
Christoph Lameter committed
1367
1368
1369
	if (s->flags & SLAB_STORE_USER)
		set_track(s, x, TRACK_FREE, addr);
	goto checks_ok;
Christoph Lameter's avatar
Christoph Lameter committed
1370
1371
1372
1373
}

void kmem_cache_free(struct kmem_cache *s, void *x)
{
Christoph Lameter's avatar
Christoph Lameter committed
1374
	struct page *page;
Christoph Lameter's avatar
Christoph Lameter committed
1375

1376
	page = virt_to_head_page(x);
Christoph Lameter's avatar
Christoph Lameter committed
1377

Christoph Lameter's avatar
Christoph Lameter committed
1378
	slab_free(s, page, x, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
1379
1380
1381
1382
1383
1384
}
EXPORT_SYMBOL(kmem_cache_free);

/* Figure out on which slab object the object resides */
static struct page *get_object_page(const void *x)
{
1385
	struct page *page = virt_to_head_page(x);
Christoph Lameter's avatar
Christoph Lameter committed
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518

	if (!PageSlab(page))
		return NULL;

	return page;
}

/*
 * kmem_cache_open produces objects aligned at "size" and the first object
 * is placed at offset 0 in the slab (We have no metainformation on the
 * slab, all slabs are in essence "off slab").
 *
 * In order to get the desired alignment one just needs to align the
 * size.
 *
 * 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
 * must be moved on and off the partial lists and therefore may influence
 * locking overhead.
 *
 * The offset is used to relocate the free list link in each object. It is
 * therefore possible to move the free list link behind the object. This
 * is necessary for RCU to work properly and also useful for debugging.
 */

/*
 * 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;

/*
 * Minimum number of objects per slab. This is necessary in order to
 * reduce locking overhead. Similar to the queue size in SLAB.
 */
static int slub_min_objects = DEFAULT_MIN_OBJECTS;

/*
 * Merge control. If this is set then no merging of slab caches will occur.
 */
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.
 *
 * The order of allocation has significant impact on other elements
 * of the system. Generally order 0 allocations should be preferred
 * since they do not cause fragmentation in the page allocator. Larger
 * objects may have problems with order 0 because there may be too much
 * space left unused in a slab. 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. This is less a
 * concern for large slabs though. slub_max_order specifies the order
 * where we begin to stop considering the number of objects in a slab.
 *
 * 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 zero.
 */
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;

		if (rem <= (PAGE_SIZE << order) / 8)
			break;

	}
	if (order >= MAX_ORDER)
		return -E2BIG;
	return order;
}

/*
 * Function to figure out which alignment to use from the
 * various ways of specifying it.
 */
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.
	 */
	if ((flags & (SLAB_MUST_HWCACHE_ALIGN | SLAB_HWCACHE_ALIGN)) &&
			size > L1_CACHE_BYTES / 2)
		return max_t(unsigned long, align, L1_CACHE_BYTES);

	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);
1519
	INIT_LIST_HEAD(&n->full);
Christoph Lameter's avatar
Christoph Lameter committed
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
}

#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
1552
	add_partial(n, page);
Christoph Lameter's avatar
Christoph Lameter committed
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
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
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
1782
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
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
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
1984
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
	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 *));

	/*
	 * If we are redzoning then check if there is some space between the
	 * end of the object and the free pointer. If not then add an
	 * additional word, so that we can establish a redzone between
	 * the object and the freepointer to be able to check for overwrites.
	 */
	if ((flags & SLAB_RED_ZONE) && size == s->objsize)
		size += sizeof(void *);

	/*
	 * With that we have determined how much of the slab is in actual
	 * use by the object. This is the potential offset to the free
	 * pointer.
	 */
	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);

	if (flags & DEBUG_DEFAULT_FLAGS)
		/*
		 * 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 *);
	/*
	 * Determine the alignment based on various parameters that the
	 * user specified (this is unecessarily complex due to the attempt
	 * to be compatible with SLAB. Should be cleaned up some day).
	 */
	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 __init finish_bootstrap(void)
{
	struct list_head *h;
	int err;

	slab_state = SYSFS;

	list_for_each(h, &slab_caches) {
		struct kmem_cache *s =
			container_of(h, struct kmem_cache, list);

		err = sysfs_slab_add(s);
		BUG_ON(err);
	}
	return 0;
}

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;

	BUG_ON(flags & SLUB_UNIMPLEMENTED);

	/*
	 * 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;
	void *addr;

	page = get_object_page(object);

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

	addr = page_address(page);
	if (object < addr || object >= addr + s->objects * s->size)
		/* Out of bounds */
		return 0;

	if ((object - addr) % s->size)
		/* Improperly aligned */
		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);

/*
 * Attempt to free all slabs on a node
 */
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;
}

/*
 * Release all resources used by slab cache
 */
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);

		free_list(s, n, &n->partial);
		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);

2024
	if (!index)
Christoph Lameter's avatar
Christoph Lameter committed
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
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
		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
2070
		return slab_alloc(s, flags, -1, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
	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
2081
		return slab_alloc(s, flags, node, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
	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;

2126
	page = virt_to_head_page(x);
Christoph Lameter's avatar
Christoph Lameter committed
2127
2128
	s = page->slab;

Christoph Lameter's avatar
Christoph Lameter committed
2129
	slab_free(s, page, (void *)x, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
}
EXPORT_SYMBOL(kfree);

/**
 * krealloc - reallocate memory. The contents will remain unchanged.
 *
 * @p: object to reallocate memory for.
 * @new_size: how many bytes of memory are required.
 * @flags: the type of memory to allocate.
 *
 * The contents of the object pointed to are preserved up to the
 * lesser of the new and old sizes.  If @p is %NULL, krealloc()
 * behaves exactly like kmalloc().  If @size is 0 and @p is not a
 * %NULL pointer, the object pointed to is freed.
 */
void *krealloc(const void *p, size_t new_size, gfp_t flags)
{
	struct kmem_cache *new_cache;
	void *ret;
	struct page *page;

	if (unlikely(!p))
		return kmalloc(new_size, flags);

	if (unlikely(!new_size)) {
		kfree(p);
		return NULL;
	}

2159
	page = virt_to_head_page(p);
Christoph Lameter's avatar
Christoph Lameter committed
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337

	new_cache = get_slab(new_size, flags);

	/*
 	 * If new size fits in the current cache, bail out.
 	 */
	if (likely(page->slab == new_cache))
		return (void *)p;

	ret = kmalloc(new_size, flags);
	if (ret) {
		memcpy(ret, p, min(new_size, ksize(p)));
		kfree(p);
	}
	return ret;
}
EXPORT_SYMBOL(krealloc);

/********************************************************************
 *			Basic setup of slabs
 *******************************************************************/

void __init kmem_cache_init(void)
{
	int i;

#ifdef CONFIG_NUMA
	/*
	 * Must first have the slab cache available for the allocations of the
	 * struct kmalloc_cache_node's. There is special bootstrap code in
	 * kmem_cache_open for slab_state == DOWN.
	 */
	create_kmalloc_cache(&kmalloc_caches[0], "kmem_cache_node",
		sizeof(struct kmem_cache_node), GFP_KERNEL);
#endif

	/* Able to allocate the per node structures */
	slab_state = PARTIAL;

	/* Caches that are not of the two-to-the-power-of size */
	create_kmalloc_cache(&kmalloc_caches[1],
				"kmalloc-96", 96, GFP_KERNEL);
	create_kmalloc_cache(&kmalloc_caches[2],
				"kmalloc-192", 192, GFP_KERNEL);

	for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++)
		create_kmalloc_cache(&kmalloc_caches[i],
			"kmalloc", 1 << i, GFP_KERNEL);

	slab_state = UP;

	/* Provide the correct kmalloc names now that the caches are up */
	for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++)
		kmalloc_caches[i]. name =
			kasprintf(GFP_KERNEL, "kmalloc-%d", 1 << i);

#ifdef CONFIG_SMP
	register_cpu_notifier(&slab_notifier);
#endif

	if (nr_cpu_ids)	/* Remove when nr_cpu_ids is fixed upstream ! */
		kmem_size = offsetof(struct kmem_cache, cpu_slab)
			 + nr_cpu_ids * sizeof(struct page *);

	printk(KERN_INFO "SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d,"
		" Processors=%d, Nodes=%d\n",
		KMALLOC_SHIFT_HIGH, L1_CACHE_BYTES,
		slub_min_order, slub_max_order, slub_min_objects,
		nr_cpu_ids, nr_node_ids);
}

/*
 * Find a mergeable slab cache
 */
static int slab_unmergeable(struct kmem_cache *s)
{
	if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE))
		return 1;

	if (s->ctor || s->dtor)
		return 1;

	return 0;
}

static struct kmem_cache *find_mergeable(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))
{
	struct list_head *h;

	if (slub_nomerge || (flags & SLUB_NEVER_MERGE))
		return NULL;

	if (ctor || dtor)
		return NULL;

	size = ALIGN(size, sizeof(void *));
	align = calculate_alignment(flags, align, size);
	size = ALIGN(size, align);

	list_for_each(h, &slab_caches) {
		struct kmem_cache *s =
			container_of(h, struct kmem_cache, list);

		if (slab_unmergeable(s))
			continue;

		if (size > s->size)
			continue;

		if (((flags | slub_debug) & SLUB_MERGE_SAME) !=
			(s->flags & SLUB_MERGE_SAME))
				continue;
		/*
		 * Check if alignment is compatible.
		 * Courtesy of Adrian Drzewiecki
		 */
		if ((s->size & ~(align -1)) != s->size)
			continue;

		if (s->size - size >= sizeof(void *))
			continue;

		return s;
	}
	return NULL;
}

struct kmem_cache *kmem_cache_create(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))
{
	struct kmem_cache *s;

	down_write(&slub_lock);
	s = find_mergeable(size, align, flags, dtor, ctor);
	if (s) {
		s->refcount++;
		/*
		 * Adjust the object sizes so that we clear
		 * the complete object on kzalloc.
		 */
		s->objsize = max(s->objsize, (int)size);
		s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
		if (sysfs_slab_alias(s, name))
			goto err;
	} else {
		s = kmalloc(kmem_size, GFP_KERNEL);
		if (s && kmem_cache_open(s, GFP_KERNEL, name,
				size, align, flags, ctor, dtor)) {
			if (sysfs_slab_add(s)) {
				kfree(s);
				goto err;
			}
			list_add(&s->list, &slab_caches);
		} else
			kfree(s);
	}
	up_write(&slub_lock);
	return s;

err:
	up_write(&slub_lock);
	if (flags & SLAB_PANIC)
		panic("Cannot create slabcache %s\n", name);
	else
		s = NULL;
	return s;
}
EXPORT_SYMBOL(kmem_cache_create);

void *kmem_cache_zalloc(struct kmem_cache *s, gfp_t flags)
{
	void *x;

Christoph Lameter's avatar
Christoph Lameter committed
2338
	x = slab_alloc(s, flags, -1, __builtin_return_address(0));
Christoph Lameter's avatar
Christoph Lameter committed
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
	if (x)
		memset(x, 0, s->objsize);
	return x;
}
EXPORT_SYMBOL(kmem_cache_zalloc);

#ifdef CONFIG_SMP
static void for_all_slabs(void (*func)(struct kmem_cache *, int), int cpu)
{
	struct list_head *h;

	down_read(&slub_lock);
	list_for_each(h, &slab_caches) {
		struct kmem_cache *s =
			container_of(h, struct kmem_cache, list);

		func(s, cpu);
	}
	up_read(&slub_lock);
}

/*
 * Use the cpu notifier to insure that the slab are flushed
 * when necessary.
 */
static int __cpuinit slab_cpuup_callback(struct notifier_block *nfb,
		unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;

	switch (action) {
	case CPU_UP_CANCELED:
	case CPU_DEAD:
		for_all_slabs(__flush_cpu_slab, cpu);
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata slab_notifier =
	{ &slab_cpuup_callback, NULL, 0 };

#endif

/***************************************************************
 *	Compatiblility definitions
 **************************************************************/

int kmem_cache_shrink(struct kmem_cache *s)
{
	flush_all(s);
	return 0;
}
EXPORT_SYMBOL(kmem_cache_shrink);

#ifdef CONFIG_NUMA

/*****************************************************************
 * Generic reaper used to support the page allocator
 * (the cpu slabs are reaped by a per slab workqueue).
 *
 * Maybe move this to the page allocator?
 ****************************************************************/

static DEFINE_PER_CPU(unsigned long, reap_node);

static void init_reap_node(int cpu)
{
	int node;

	node = next_node(cpu_to_node(cpu), node_online_map);
	if (node == MAX_NUMNODES)
		node = first_node(node_online_map);

	__get_cpu_var(reap_node) = node;
}

static void next_reap_node(void)
{
	int node = __get_cpu_var(reap_node);

	/*
	 * Also drain per cpu pages on remote zones
	 */
	if (node != numa_node_id())
		drain_node_pages(node);

	node = next_node(node, node_online_map);
	if (unlikely(node >= MAX_NUMNODES))
		node = first_node(node_online_map);
	__get_cpu_var(reap_node) = node;
}
#else
#define init_reap_node(cpu) do { } while (0)
#define next_reap_node(void) do { } while (0)
#endif

#define REAPTIMEOUT_CPUC	(2*HZ)

#ifdef CONFIG_SMP
static DEFINE_PER_CPU(struct delayed_work, reap_work);

static void cache_reap(struct work_struct *unused)
{
	next_reap_node();
	refresh_cpu_vm_stats(smp_processor_id());
	schedule_delayed_work(&__get_cpu_var(reap_work),
				      REAPTIMEOUT_CPUC);
}

static void __devinit start_cpu_timer(int cpu)
{
	struct delayed_work *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->work.func == NULL) {
		init_reap_node(cpu);
		INIT_DELAYED_WORK(reap_work, cache_reap);
		schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu);
	}
}

static int __init cpucache_init(void)
{
	int cpu;

	/*
	 * Register the timers that drain pcp pages and update vm statistics
	 */
	for_each_online_cpu(cpu)
		start_cpu_timer(cpu);
	return 0;
}
__initcall(cpucache_init);
#endif

#ifdef SLUB_RESILIENCY_TEST
static unsigned long validate_slab_cache(struct kmem_cache *s);

static void resiliency_test(void)
{
	u8 *p;

	printk(KERN_ERR "SLUB resiliency testing\n");
	printk(KERN_ERR "-----------------------\n");
	printk(KERN_ERR "A. Corruption after allocation\n");

	p = kzalloc(16, GFP_KERNEL);
	p[16] = 0x12;
	printk(KERN_ERR "\n1. kmalloc-16: Clobber Redzone/next pointer"
			" 0x12->0x%p\n\n", p + 16);

	validate_slab_cache(kmalloc_caches + 4);

	/* Hmmm... The next two are dangerous */
	p = kzalloc(32, GFP_KERNEL);
	p[32 + sizeof(void *)] = 0x34;
	printk(KERN_ERR "\n2. kmalloc-32: Clobber next pointer/next slab"
		 	" 0x34 -> -0x%p\n", p);
	printk(KERN_ERR "If allocated object is overwritten then not detectable\n\n");

	validate_slab_cache(kmalloc_caches + 5);
	p = kzalloc(64, GFP_KERNEL);
	p += 64 + (get_cycles() & 0xff) * sizeof(void *);
	*p = 0x56;
	printk(KERN_ERR "\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n",
									p);
	printk(KERN_ERR "If allocated object is overwritten then not detectable\n\n");
	validate_slab_cache(kmalloc_caches + 6);

	printk(KERN_ERR "\nB. Corruption after free\n");
	p = kzalloc(128, GFP_KERNEL);
	kfree(p);
	*p = 0x78;
	printk(KERN_ERR "1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p);
	validate_slab_cache(kmalloc_caches + 7);

	p = kzalloc(256, GFP_KERNEL);
	kfree(p);
	p[50] = 0x9a;
	printk(KERN_ERR "\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p);
	validate_slab_cache(kmalloc_caches + 8);

	p = kzalloc(512, GFP_KERNEL);
	kfree(p);
	p[512] = 0xab;
	printk(KERN_ERR "\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p);
	validate_slab_cache(kmalloc_caches + 9);
}
#else
static void resiliency_test(void) {};
#endif

/*
 * These are not as efficient as kmalloc for the non debug case.
 * We do not have the page struct available so we have to touch one
 * cacheline in struct kmem_cache to check slab flags.
 */
void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, void *caller)
{
	struct kmem_cache *s = get_slab(size, gfpflags);

	if (!s)
		return NULL;

Christoph Lameter's avatar
Christoph Lameter committed
2550
	return slab_alloc(s, gfpflags, -1, caller);
Christoph Lameter's avatar
Christoph Lameter committed
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
}

void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
					int node, void *caller)
{
	struct kmem_cache *s = get_slab(size, gfpflags);

	if (!s)
		return NULL;

Christoph Lameter's avatar
Christoph Lameter committed
2561
	return slab_alloc(s, gfpflags, node, caller);
Christoph Lameter's avatar
Christoph Lameter committed
2562
2563
2564
2565
}

#ifdef CONFIG_SYSFS

2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
static int validate_slab(struct kmem_cache *s, struct page *page)
{
	void *p;
	void *addr = page_address(page);
	unsigned long map[BITS_TO_LONGS(s->objects)];

	if (!check_slab(s, page) ||
			!on_freelist(s, page, NULL))
		return 0;

	/* Now we know that a valid freelist exists */
	bitmap_zero(map, s->objects);

	for(p = page->freelist; p; p = get_freepointer(s, p)) {
		set_bit((p - addr) / s->size, map);
		if (!check_object(s, page, p, 0))
			return 0;
	}

	for(p = addr; p < addr + s->objects * s->size; p += s->size)
		if (!test_bit((p - addr) / s->size, map))
			if (!check_object(s, page, p, 1))
				return 0;
	return 1;
}

static void validate_slab_slab(struct kmem_cache *s, struct page *page)
{
	if (slab_trylock(page)) {
		validate_slab(s, page);
		slab_unlock(page);
	} else
		printk(KERN_INFO "SLUB %s: Skipped busy slab 0x%p\n",
			s->name, page);

	if (s->flags & DEBUG_DEFAULT_FLAGS) {
		if (!PageError(page))
			printk(KERN_ERR "SLUB %s: PageError not set "
				"on slab 0x%p\n", s->name, page);
	} else {
		if (PageError(page))
			printk(KERN_ERR "SLUB %s: PageError set on "
				"slab 0x%p\n", s->name, page);
	}
}

static int validate_slab_node(struct kmem_cache *s, struct kmem_cache_node *n)
{
	unsigned long count = 0;
	struct page *page;
	unsigned long flags;

	spin_lock_irqsave(&n->list_lock, flags);

	list_for_each_entry(page, &n->partial, lru) {
		validate_slab_slab(s, page);
		count++;
	}
	if (count != n->nr_partial)
		printk(KERN_ERR "SLUB %s: %ld partial slabs counted but "
			"counter=%ld\n", s->name, count, n->nr_partial);

	if (!(s->flags & SLAB_STORE_USER))
		goto out;

	list_for_each_entry(page, &n->full, lru) {
		validate_slab_slab(s, page);
		count++;
	}
	if (count != atomic_long_read(&n->nr_slabs))
		printk(KERN_ERR "SLUB: %s %ld slabs counted but "
			"counter=%ld\n", s->name, count,
			atomic_long_read(&n->nr_slabs));

out:
	spin_unlock_irqrestore(&n->list_lock, flags);
	return count;
}

static unsigned long validate_slab_cache(struct kmem_cache *s)
{
	int node;
	unsigned long count = 0;

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

		count += validate_slab_node(s, n);
	}
	return count;
}

2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748