summaryrefslogtreecommitdiffstats
path: root/mm/slob.c
blob: 0111e0dece9309e167bbea1918127c4ec155ae89 (plain)
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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
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
/*
 * SLOB Allocator: Simple List Of Blocks
 *
 * Matt Mackall <mpm@selenic.com> 12/30/03
 *
 * NUMA support by Paul Mundt, 2007.
 *
 * How SLOB works:
 *
 * The core of SLOB is a traditional K&R style heap allocator, with
 * support for returning aligned objects. The granularity of this
 * allocator is as little as 2 bytes, however typically most architectures
 * will require 4 bytes on 32-bit and 8 bytes on 64-bit.
 *
 * The slob heap is a set of linked list of pages from alloc_pages(),
 * and within each page, there is a singly-linked list of free blocks
 * (slob_t). The heap is grown on demand. To reduce fragmentation,
 * heap pages are segregated into three lists, with objects less than
 * 256 bytes, objects less than 1024 bytes, and all other objects.
 *
 * Allocation from heap involves first searching for a page with
 * sufficient free blocks (using a next-fit-like approach) followed by
 * a first-fit scan of the page. Deallocation inserts objects back
 * into the free list in address order, so this is effectively an
 * address-ordered first fit.
 *
 * Above this is an implementation of kmalloc/kfree. Blocks returned
 * from kmalloc are prepended with a 4-byte header with the kmalloc size.
 * If kmalloc is asked for objects of PAGE_SIZE or larger, it calls
 * alloc_pages() directly, allocating compound pages so the page order
 * does not have to be separately tracked, and also stores the exact
 * allocation size in page->private so that it can be used to accurately
 * provide ksize(). These objects are detected in kfree() because slob_page()
 * is false for them.
 *
 * SLAB is emulated on top of SLOB by simply calling constructors and
 * destructors for every SLAB allocation. Objects are returned with the
 * 4-byte alignment unless the SLAB_HWCACHE_ALIGN flag is set, in which
 * case the low-level allocator will fragment blocks to create the proper
 * alignment. Again, objects of page-size or greater are allocated by
 * calling alloc_pages(). As SLAB objects know their size, no separate
 * size bookkeeping is necessary and there is essentially no allocation
 * space overhead, and compound pages aren't needed for multi-page
 * allocations.
 *
 * NUMA support in SLOB is fairly simplistic, pushing most of the real
 * logic down to the page allocator, and simply doing the node accounting
 * on the upper levels. In the event that a node id is explicitly
 * provided, alloc_pages_exact_node() with the specified node id is used
 * instead. The common case (or when the node id isn't explicitly provided)
 * will default to the current node, as per numa_node_id().
 *
 * Node aware pages are still inserted in to the global freelist, and
 * these are scanned for by matching against the node id encoded in the
 * page flags. As a result, block allocations that can be satisfied from
 * the freelist will only be done so on pages residing on the same node,
 * in order to prevent random node placement.
 */

#include <linux/kernel.h>
#include <linux/slab.h>
#include "slab.h"

#include <linux/mm.h>
#include <linux/swap.h> /* struct reclaim_state */
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/rcupdate.h>
#include <linux/list.h>
#include <linux/kmemleak.h>

#include <trace/events/kmem.h>

#include <linux/atomic.h>

/*
 * slob_block has a field 'units', which indicates size of block if +ve,
 * or offset of next block if -ve (in SLOB_UNITs).
 *
 * Free blocks of size 1 unit simply contain the offset of the next block.
 * Those with larger size contain their size in the first SLOB_UNIT of
 * memory, and the offset of the next free block in the second SLOB_UNIT.
 */
#if PAGE_SIZE <= (32767 * 2)
typedef s16 slobidx_t;
#else
typedef s32 slobidx_t;
#endif

struct slob_block {
	slobidx_t units;
};
typedef struct slob_block slob_t;

/*
 * All partially free slob pages go on these lists.
 */
#define SLOB_BREAK1 256
#define SLOB_BREAK2 1024
static LIST_HEAD(free_slob_small);
static LIST_HEAD(free_slob_medium);
static LIST_HEAD(free_slob_large);

/*
 * slob_page_free: true for pages on free_slob_pages list.
 */
static inline int slob_page_free(struct page *sp)
{
	return PageSlobFree(sp);
}

static void set_slob_page_free(struct page *sp, struct list_head *list)
{
	list_add(&sp->list, list);
	__SetPageSlobFree(sp);
}

static inline void clear_slob_page_free(struct page *sp)
{
	list_del(&sp->list);
	__ClearPageSlobFree(sp);
}

#define SLOB_UNIT sizeof(slob_t)
#define SLOB_UNITS(size) (((size) + SLOB_UNIT - 1)/SLOB_UNIT)
#define SLOB_ALIGN L1_CACHE_BYTES

/*
 * struct slob_rcu is inserted at the tail of allocated slob blocks, which
 * were created with a SLAB_DESTROY_BY_RCU slab. slob_rcu is used to free
 * the block using call_rcu.
 */
struct slob_rcu {
	struct rcu_head head;
	int size;
};

/*
 * slob_lock protects all slob allocator structures.
 */
static DEFINE_SPINLOCK(slob_lock);

/*
 * Encode the given size and next info into a free slob block s.
 */
static void set_slob(slob_t *s, slobidx_t size, slob_t *next)
{
	slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK);
	slobidx_t offset = next - base;

	if (size > 1) {
		s[0].units = size;
		s[1].units = offset;
	} else
		s[0].units = -offset;
}

/*
 * Return the size of a slob block.
 */
static slobidx_t slob_units(slob_t *s)
{
	if (s->units > 0)
		return s->units;
	return 1;
}

/*
 * Return the next free slob block pointer after this one.
 */
static slob_t *slob_next(slob_t *s)
{
	slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK);
	slobidx_t next;

	if (s[0].units < 0)
		next = -s[0].units;
	else
		next = s[1].units;
	return base+next;
}

/*
 * Returns true if s is the last free block in its page.
 */
static int slob_last(slob_t *s)
{
	return !((unsigned long)slob_next(s) & ~PAGE_MASK);
}

static void *slob_new_pages(gfp_t gfp, int order, int node)
{
	void *page;

#ifdef CONFIG_NUMA
	if (node != -1)
		page = alloc_pages_exact_node(node, gfp, order);
	else
#endif
		page = alloc_pages(gfp, order);

	if (!page)
		return NULL;

	return page_address(page);
}

static void slob_free_pages(void *b, int order)
{
	if (current->reclaim_state)
		current->reclaim_state->reclaimed_slab += 1 << order;
	free_pages((unsigned long)b, order);
}

/*
 * Allocate a slob block within a given slob_page sp.
 */
static void *slob_page_alloc(struct page *sp, size_t size, int align)
{
	slob_t *prev, *cur, *aligned = NULL;
	int delta = 0, units = SLOB_UNITS(size);

	for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) {
		slobidx_t avail = slob_units(cur);

		if (align) {
			aligned = (slob_t *)ALIGN((unsigned long)cur, align);
			delta = aligned - cur;
		}
		if (avail >= units + delta) { /* room enough? */
			slob_t *next;

			if (delta) { /* need to fragment head to align? */
				next = slob_next(cur);
				set_slob(aligned, avail - delta, next);
				set_slob(cur, delta, aligned);
				prev = cur;
				cur = aligned;
				avail = slob_units(cur);
			}

			next = slob_next(cur);
			if (avail == units) { /* exact fit? unlink. */
				if (prev)
					set_slob(prev, slob_units(prev), next);
				else
					sp->freelist = next;
			} else { /* fragment */
				if (prev)
					set_slob(prev, slob_units(prev), cur + units);
				else
					sp->freelist = cur + units;
				set_slob(cur + units, avail - units, next);
			}

			sp->units -= units;
			if (!sp->units)
				clear_slob_page_free(sp);
			return cur;
		}
		if (slob_last(cur))
			return NULL;
	}
}

/*
 * slob_alloc: entry point into the slob allocator.
 */
static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
{
	struct page *sp;
	struct list_head *prev;
	struct list_head *slob_list;
	slob_t *b = NULL;
	unsigned long flags;

	if (size < SLOB_BREAK1)
		slob_list = &free_slob_small;
	else if (size < SLOB_BREAK2)
		slob_list = &free_slob_medium;
	else
		slob_list = &free_slob_large;

	spin_lock_irqsave(&slob_lock, flags);
	/* Iterate through each partially free page, try to find room */
	list_for_each_entry(sp, slob_list, list) {
#ifdef CONFIG_NUMA
		/*
		 * If there's a node specification, search for a partial
		 * page with a matching node id in the freelist.
		 */
		if (node != -1 && page_to_nid(sp) != node)
			continue;
#endif
		/* Enough room on this page? */
		if (sp->units < SLOB_UNITS(size))
			continue;

		/* Attempt to alloc */
		prev = sp->list.prev;
		b = slob_page_alloc(sp, size, align);
		if (!b)
			continue;

		/* Improve fragment distribution and reduce our average
		 * search time by starting our next search here. (see
		 * Knuth vol 1, sec 2.5, pg 449) */
		if (prev != slob_list->prev &&
				slob_list->next != prev->next)
			list_move_tail(slob_list, prev->next);
		break;
	}
	spin_unlock_irqrestore(&slob_lock, flags);

	/* Not enough space: must allocate a new page */
	if (!b) {
		b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node);
		if (!b)
			return NULL;
		sp = virt_to_page(b);
		__SetPageSlab(sp);

		spin_lock_irqsave(&slob_lock, flags);
		sp->units = SLOB_UNITS(PAGE_SIZE);
		sp->freelist = b;
		INIT_LIST_HEAD(&sp->list);
		set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
		set_slob_page_free(sp, slob_list);
		b = slob_page_alloc(sp, size, align);
		BUG_ON(!b);
		spin_unlock_irqrestore(&slob_lock, flags);
	}
	if (unlikely((gfp & __GFP_ZERO) && b))
		memset(b, 0, size);
	return b;
}

/*
 * slob_free: entry point into the slob allocator.
 */
static void slob_free(void *block, int size)
{
	struct page *sp;
	slob_t *prev, *next, *b = (slob_t *)block;
	slobidx_t units;
	unsigned long flags;
	struct list_head *slob_list;

	if (unlikely(ZERO_OR_NULL_PTR(block)))
		return;
	BUG_ON(!size);

	sp = virt_to_page(block);
	units = SLOB_UNITS(size);

	spin_lock_irqsave(&slob_lock, flags);

	if (sp->units + units == SLOB_UNITS(PAGE_SIZE)) {
		/* Go directly to page allocator. Do not pass slob allocator */
		if (slob_page_free(sp))
			clear_slob_page_free(sp);
		spin_unlock_irqrestore(&slob_lock, flags);
		__ClearPageSlab(sp);
		reset_page_mapcount(sp);
		slob_free_pages(b, 0);
		return;
	}

	if (!slob_page_free(sp)) {
		/* This slob page is about to become partially free. Easy! */
		sp->units = units;
		sp->freelist = b;
		set_slob(b, units,
			(void *)((unsigned long)(b +
					SLOB_UNITS(PAGE_SIZE)) & PAGE_MASK));
		if (size < SLOB_BREAK1)
			slob_list = &free_slob_small;
		else if (size < SLOB_BREAK2)
			slob_list = &free_slob_medium;
		else
			slob_list = &free_slob_large;
		set_slob_page_free(sp, slob_list);
		goto out;
	}

	/*
	 * Otherwise the page is already partially free, so find reinsertion
	 * point.
	 */
	sp->units += units;

	if (b < (slob_t *)sp->freelist) {
		if (b + units == sp->freelist) {
			units += slob_units(sp->freelist);
			sp->freelist = slob_next(sp->freelist);
		}
		set_slob(b, units, sp->freelist);
		sp->freelist = b;
	} else {
		prev = sp->freelist;
		next = slob_next(prev);
		while (b > next) {
			prev = next;
			next = slob_next(prev);
		}

		if (!slob_last(prev) && b + units == next) {
			units += slob_units(next);
			set_slob(b, units, slob_next(next));
		} else
			set_slob(b, units, next);

		if (prev + slob_units(prev) == b) {
			units = slob_units(b) + slob_units(prev);
			set_slob(prev, units, slob_next(b));
		} else
			set_slob(prev, slob_units(prev), b);
	}
out:
	spin_unlock_irqrestore(&slob_lock, flags);
}

/*
 * End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend.
 */

void *__kmalloc_node(size_t size, gfp_t gfp, int node)
{
	unsigned int *m;
	int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
	void *ret;

	gfp &= gfp_allowed_mask;

	lockdep_trace_alloc(gfp);

	if (size < PAGE_SIZE - align) {
		if (!size)
			return ZERO_SIZE_PTR;

		m = slob_alloc(size + align, gfp, align, node);

		if (!m)
			return NULL;
		*m = size;
		ret = (void *)m + align;

		trace_kmalloc_node(_RET_IP_, ret,
				   size, size + align, gfp, node);
	} else {
		unsigned int order = get_order(size);

		if (likely(order))
			gfp |= __GFP_COMP;
		ret = slob_new_pages(gfp, order, node);
		if (ret) {
			struct page *page;
			page = virt_to_page(ret);
			page->private = size;
		}

		trace_kmalloc_node(_RET_IP_, ret,
				   size, PAGE_SIZE << order, gfp, node);
	}

	kmemleak_alloc(ret, size, 1, gfp);
	return ret;
}
EXPORT_SYMBOL(__kmalloc_node);

void kfree(const void *block)
{
	struct page *sp;

	trace_kfree(_RET_IP_, block);

	if (unlikely(ZERO_OR_NULL_PTR(block)))
		return;
	kmemleak_free(block);

	sp = virt_to_page(block);
	if (PageSlab(sp)) {
		int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
		unsigned int *m = (unsigned int *)(block - align);
		slob_free(m, *m + align);
	} else
		put_page(sp);
}
EXPORT_SYMBOL(kfree);

/* can't use ksize for kmem_cache_alloc memory, only kmalloc */
size_t ksize(const void *block)
{
	struct page *sp;

	BUG_ON(!block);
	if (unlikely(block == ZERO_SIZE_PTR))
		return 0;

	sp = virt_to_page(block);
	if (PageSlab(sp)) {
		int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
		unsigned int *m = (unsigned int *)(block - align);
		return SLOB_UNITS(*m) * SLOB_UNIT;
	} else
		return sp->private;
}
EXPORT_SYMBOL(ksize);

struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
	size_t align, unsigned long flags, void (*ctor)(void *))
{
	struct kmem_cache *c;

	c = slob_alloc(sizeof(struct kmem_cache),
		GFP_KERNEL, ARCH_KMALLOC_MINALIGN, -1);

	if (c) {
		c->name = name;
		c->size = c->object_size;
		if (flags & SLAB_DESTROY_BY_RCU) {
			/* leave room for rcu footer at the end of object */
			c->size += sizeof(struct slob_rcu);
		}
		c->flags = flags;
		c->ctor = ctor;
		/* ignore alignment unless it's forced */
		c->align = (flags & SLAB_HWCACHE_ALIGN) ? SLOB_ALIGN : 0;
		if (c->align < ARCH_SLAB_MINALIGN)
			c->align = ARCH_SLAB_MINALIGN;
		if (c->align < align)
			c->align = align;

		kmemleak_alloc(c, sizeof(struct kmem_cache), 1, GFP_KERNEL);
		c->refcount = 1;
	}
	return c;
}

void kmem_cache_destroy(struct kmem_cache *c)
{
	kmemleak_free(c);
	if (c->flags & SLAB_DESTROY_BY_RCU)
		rcu_barrier();
	slob_free(c, sizeof(struct kmem_cache));
}
EXPORT_SYMBOL(kmem_cache_destroy);

void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
{
	void *b;

	flags &= gfp_allowed_mask;

	lockdep_trace_alloc(flags);

	if (c->size < PAGE_SIZE) {
		b = slob_alloc(c->size, flags, c->align, node);
		trace_kmem_cache_alloc_node(_RET_IP_, b, c->size,
					    SLOB_UNITS(c->size) * SLOB_UNIT,
					    flags, node);
	} else {
		b = slob_new_pages(flags, get_order(c->size), node);
		trace_kmem_cache_alloc_node(_RET_IP_, b, c->size,
					    PAGE_SIZE << get_order(c->size),
					    flags, node);
	}

	if (c->ctor)
		c->ctor(b);

	kmemleak_alloc_recursive(b, c->size, 1, c->flags, flags);
	return b;
}
EXPORT_SYMBOL(kmem_cache_alloc_node);

static void __kmem_cache_free(void *b, int size)
{
	if (size < PAGE_SIZE)
		slob_free(b, size);
	else
		slob_free_pages(b, get_order(size));
}

static void kmem_rcu_free(struct rcu_head *head)
{
	struct slob_rcu *slob_rcu = (struct slob_rcu *)head;
	void *b = (void *)slob_rcu - (slob_rcu->size - sizeof(struct slob_rcu));

	__kmem_cache_free(b, slob_rcu->size);
}

void kmem_cache_free(struct kmem_cache *c, void *b)
{
	kmemleak_free_recursive(b, c->flags);
	if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) {
		struct slob_rcu *slob_rcu;
		slob_rcu = b + (c->size - sizeof(struct slob_rcu));
		slob_rcu->size = c->size;
		call_rcu(&slob_rcu->head, kmem_rcu_free);
	} else {
		__kmem_cache_free(b, c->size);
	}

	trace_kmem_cache_free(_RET_IP_, b);
}
EXPORT_SYMBOL(kmem_cache_free);

unsigned int kmem_cache_size(struct kmem_cache *c)
{
	return c->size;
}
EXPORT_SYMBOL(kmem_cache_size);

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

void __init kmem_cache_init(void)
{
	slab_state = UP;
}

void __init kmem_cache_init_late(void)
{
	slab_state = FULL;
}