summaryrefslogtreecommitdiffstats
path: root/mm/zbud.c
blob: f3bf6f7627d8d103bb674a99ed504092f15499a9 (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
631
632
633
634
635
636
637
638
639
/*
 * zbud.c
 *
 * Copyright (C) 2013, Seth Jennings, IBM
 *
 * Concepts based on zcache internal zbud allocator by Dan Magenheimer.
 *
 * zbud is an special purpose allocator for storing compressed pages.  Contrary
 * to what its name may suggest, zbud is not a buddy allocator, but rather an
 * allocator that "buddies" two compressed pages together in a single memory
 * page.
 *
 * While this design limits storage density, it has simple and deterministic
 * reclaim properties that make it preferable to a higher density approach when
 * reclaim will be used.
 *
 * zbud works by storing compressed pages, or "zpages", together in pairs in a
 * single memory page called a "zbud page".  The first buddy is "left
 * justified" at the beginning of the zbud page, and the last buddy is "right
 * justified" at the end of the zbud page.  The benefit is that if either
 * buddy is freed, the freed buddy space, coalesced with whatever slack space
 * that existed between the buddies, results in the largest possible free region
 * within the zbud page.
 *
 * zbud also provides an attractive lower bound on density. The ratio of zpages
 * to zbud pages can not be less than 1.  This ensures that zbud can never "do
 * harm" by using more pages to store zpages than the uncompressed zpages would
 * have used on their own.
 *
 * zbud pages are divided into "chunks".  The size of the chunks is fixed at
 * compile time and determined by NCHUNKS_ORDER below.  Dividing zbud pages
 * into chunks allows organizing unbuddied zbud pages into a manageable number
 * of unbuddied lists according to the number of free chunks available in the
 * zbud page.
 *
 * The zbud API differs from that of conventional allocators in that the
 * allocation function, zbud_alloc(), returns an opaque handle to the user,
 * not a dereferenceable pointer.  The user must map the handle using
 * zbud_map() in order to get a usable pointer by which to access the
 * allocation data and unmap the handle with zbud_unmap() when operations
 * on the allocation data are complete.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/atomic.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/preempt.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/zbud.h>
#include <linux/zpool.h>

/*****************
 * Structures
*****************/
/*
 * NCHUNKS_ORDER determines the internal allocation granularity, effectively
 * adjusting internal fragmentation.  It also determines the number of
 * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the
 * allocation granularity will be in chunks of size PAGE_SIZE/64. As one chunk
 * in allocated page is occupied by zbud header, NCHUNKS will be calculated to
 * 63 which shows the max number of free chunks in zbud page, also there will be
 * 63 freelists per pool.
 */
#define NCHUNKS_ORDER	6

#define CHUNK_SHIFT	(PAGE_SHIFT - NCHUNKS_ORDER)
#define CHUNK_SIZE	(1 << CHUNK_SHIFT)
#define ZHDR_SIZE_ALIGNED CHUNK_SIZE
#define NCHUNKS		((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT)

/**
 * struct zbud_pool - stores metadata for each zbud pool
 * @lock:	protects all pool fields and first|last_chunk fields of any
 *		zbud page in the pool
 * @unbuddied:	array of lists tracking zbud pages that only contain one buddy;
 *		the lists each zbud page is added to depends on the size of
 *		its free region.
 * @buddied:	list tracking the zbud pages that contain two buddies;
 *		these zbud pages are full
 * @lru:	list tracking the zbud pages in LRU order by most recently
 *		added buddy.
 * @pages_nr:	number of zbud pages in the pool.
 * @ops:	pointer to a structure of user defined operations specified at
 *		pool creation time.
 *
 * This structure is allocated at pool creation time and maintains metadata
 * pertaining to a particular zbud pool.
 */
struct zbud_pool {
	spinlock_t lock;
	struct list_head unbuddied[NCHUNKS];
	struct list_head buddied;
	struct list_head lru;
	u64 pages_nr;
	struct zbud_ops *ops;
#ifdef CONFIG_ZPOOL
	struct zpool *zpool;
	struct zpool_ops *zpool_ops;
#endif
};

/*
 * struct zbud_header - zbud page metadata occupying the first chunk of each
 *			zbud page.
 * @buddy:	links the zbud page into the unbuddied/buddied lists in the pool
 * @lru:	links the zbud page into the lru list in the pool
 * @first_chunks:	the size of the first buddy in chunks, 0 if free
 * @last_chunks:	the size of the last buddy in chunks, 0 if free
 */
struct zbud_header {
	struct list_head buddy;
	struct list_head lru;
	unsigned int first_chunks;
	unsigned int last_chunks;
	bool under_reclaim;
};

/*****************
 * zpool
 ****************/

#ifdef CONFIG_ZPOOL

static int zbud_zpool_evict(struct zbud_pool *pool, unsigned long handle)
{
	if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict)
		return pool->zpool_ops->evict(pool->zpool, handle);
	else
		return -ENOENT;
}

static struct zbud_ops zbud_zpool_ops = {
	.evict =	zbud_zpool_evict
};

static void *zbud_zpool_create(char *name, gfp_t gfp,
			       struct zpool_ops *zpool_ops,
			       struct zpool *zpool)
{
	struct zbud_pool *pool;

	pool = zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL);
	if (pool) {
		pool->zpool = zpool;
		pool->zpool_ops = zpool_ops;
	}
	return pool;
}

static void zbud_zpool_destroy(void *pool)
{
	zbud_destroy_pool(pool);
}

static int zbud_zpool_malloc(void *pool, size_t size, gfp_t gfp,
			unsigned long *handle)
{
	return zbud_alloc(pool, size, gfp, handle);
}
static void zbud_zpool_free(void *pool, unsigned long handle)
{
	zbud_free(pool, handle);
}

static int zbud_zpool_shrink(void *pool, unsigned int pages,
			unsigned int *reclaimed)
{
	unsigned int total = 0;
	int ret = -EINVAL;

	while (total < pages) {
		ret = zbud_reclaim_page(pool, 8);
		if (ret < 0)
			break;
		total++;
	}

	if (reclaimed)
		*reclaimed = total;

	return ret;
}

static void *zbud_zpool_map(void *pool, unsigned long handle,
			enum zpool_mapmode mm)
{
	return zbud_map(pool, handle);
}
static void zbud_zpool_unmap(void *pool, unsigned long handle)
{
	zbud_unmap(pool, handle);
}

static u64 zbud_zpool_total_size(void *pool)
{
	return zbud_get_pool_size(pool) * PAGE_SIZE;
}

static struct zpool_driver zbud_zpool_driver = {
	.type =		"zbud",
	.owner =	THIS_MODULE,
	.create =	zbud_zpool_create,
	.destroy =	zbud_zpool_destroy,
	.malloc =	zbud_zpool_malloc,
	.free =		zbud_zpool_free,
	.shrink =	zbud_zpool_shrink,
	.map =		zbud_zpool_map,
	.unmap =	zbud_zpool_unmap,
	.total_size =	zbud_zpool_total_size,
};

MODULE_ALIAS("zpool-zbud");
#endif /* CONFIG_ZPOOL */

/*****************
 * Helpers
*****************/
/* Just to make the code easier to read */
enum buddy {
	FIRST,
	LAST
};

/* Converts an allocation size in bytes to size in zbud chunks */
static int size_to_chunks(size_t size)
{
	return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT;
}

#define for_each_unbuddied_list(_iter, _begin) \
	for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++)

/* Initializes the zbud header of a newly allocated zbud page */
static struct zbud_header *init_zbud_page(struct page *page)
{
	struct zbud_header *zhdr = page_address(page);
	zhdr->first_chunks = 0;
	zhdr->last_chunks = 0;
	INIT_LIST_HEAD(&zhdr->buddy);
	INIT_LIST_HEAD(&zhdr->lru);
	zhdr->under_reclaim = 0;
	return zhdr;
}

/* Resets the struct page fields and frees the page */
static void free_zbud_page(struct zbud_header *zhdr)
{
	__free_page(virt_to_page(zhdr));
}

/*
 * Encodes the handle of a particular buddy within a zbud page
 * Pool lock should be held as this function accesses first|last_chunks
 */
static unsigned long encode_handle(struct zbud_header *zhdr, enum buddy bud)
{
	unsigned long handle;

	/*
	 * For now, the encoded handle is actually just the pointer to the data
	 * but this might not always be the case.  A little information hiding.
	 * Add CHUNK_SIZE to the handle if it is the first allocation to jump
	 * over the zbud header in the first chunk.
	 */
	handle = (unsigned long)zhdr;
	if (bud == FIRST)
		/* skip over zbud header */
		handle += ZHDR_SIZE_ALIGNED;
	else /* bud == LAST */
		handle += PAGE_SIZE - (zhdr->last_chunks  << CHUNK_SHIFT);
	return handle;
}

/* Returns the zbud page where a given handle is stored */
static struct zbud_header *handle_to_zbud_header(unsigned long handle)
{
	return (struct zbud_header *)(handle & PAGE_MASK);
}

/* Returns the number of free chunks in a zbud page */
static int num_free_chunks(struct zbud_header *zhdr)
{
	/*
	 * Rather than branch for different situations, just use the fact that
	 * free buddies have a length of zero to simplify everything.
	 */
	return NCHUNKS - zhdr->first_chunks - zhdr->last_chunks;
}

/*****************
 * API Functions
*****************/
/**
 * zbud_create_pool() - create a new zbud pool
 * @gfp:	gfp flags when allocating the zbud pool structure
 * @ops:	user-defined operations for the zbud pool
 *
 * Return: pointer to the new zbud pool or NULL if the metadata allocation
 * failed.
 */
struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops)
{
	struct zbud_pool *pool;
	int i;

	pool = kzalloc(sizeof(struct zbud_pool), gfp);
	if (!pool)
		return NULL;
	spin_lock_init(&pool->lock);
	for_each_unbuddied_list(i, 0)
		INIT_LIST_HEAD(&pool->unbuddied[i]);
	INIT_LIST_HEAD(&pool->buddied);
	INIT_LIST_HEAD(&pool->lru);
	pool->pages_nr = 0;
	pool->ops = ops;
	return pool;
}

/**
 * zbud_destroy_pool() - destroys an existing zbud pool
 * @pool:	the zbud pool to be destroyed
 *
 * The pool should be emptied before this function is called.
 */
void zbud_destroy_pool(struct zbud_pool *pool)
{
	kfree(pool);
}

/**
 * zbud_alloc() - allocates a region of a given size
 * @pool:	zbud pool from which to allocate
 * @size:	size in bytes of the desired allocation
 * @gfp:	gfp flags used if the pool needs to grow
 * @handle:	handle of the new allocation
 *
 * This function will attempt to find a free region in the pool large enough to
 * satisfy the allocation request.  A search of the unbuddied lists is
 * performed first. If no suitable free region is found, then a new page is
 * allocated and added to the pool to satisfy the request.
 *
 * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used
 * as zbud pool pages.
 *
 * Return: 0 if success and handle is set, otherwise -EINVAL if the size or
 * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate
 * a new page.
 */
int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp,
			unsigned long *handle)
{
	int chunks, i, freechunks;
	struct zbud_header *zhdr = NULL;
	enum buddy bud;
	struct page *page;

	if (!size || (gfp & __GFP_HIGHMEM))
		return -EINVAL;
	if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE)
		return -ENOSPC;
	chunks = size_to_chunks(size);
	spin_lock(&pool->lock);

	/* First, try to find an unbuddied zbud page. */
	zhdr = NULL;
	for_each_unbuddied_list(i, chunks) {
		if (!list_empty(&pool->unbuddied[i])) {
			zhdr = list_first_entry(&pool->unbuddied[i],
					struct zbud_header, buddy);
			list_del(&zhdr->buddy);
			if (zhdr->first_chunks == 0)
				bud = FIRST;
			else
				bud = LAST;
			goto found;
		}
	}

	/* Couldn't find unbuddied zbud page, create new one */
	spin_unlock(&pool->lock);
	page = alloc_page(gfp);
	if (!page)
		return -ENOMEM;
	spin_lock(&pool->lock);
	pool->pages_nr++;
	zhdr = init_zbud_page(page);
	bud = FIRST;

found:
	if (bud == FIRST)
		zhdr->first_chunks = chunks;
	else
		zhdr->last_chunks = chunks;

	if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0) {
		/* Add to unbuddied list */
		freechunks = num_free_chunks(zhdr);
		list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
	} else {
		/* Add to buddied list */
		list_add(&zhdr->buddy, &pool->buddied);
	}

	/* Add/move zbud page to beginning of LRU */
	if (!list_empty(&zhdr->lru))
		list_del(&zhdr->lru);
	list_add(&zhdr->lru, &pool->lru);

	*handle = encode_handle(zhdr, bud);
	spin_unlock(&pool->lock);

	return 0;
}

/**
 * zbud_free() - frees the allocation associated with the given handle
 * @pool:	pool in which the allocation resided
 * @handle:	handle associated with the allocation returned by zbud_alloc()
 *
 * In the case that the zbud page in which the allocation resides is under
 * reclaim, as indicated by the PG_reclaim flag being set, this function
 * only sets the first|last_chunks to 0.  The page is actually freed
 * once both buddies are evicted (see zbud_reclaim_page() below).
 */
void zbud_free(struct zbud_pool *pool, unsigned long handle)
{
	struct zbud_header *zhdr;
	int freechunks;

	spin_lock(&pool->lock);
	zhdr = handle_to_zbud_header(handle);

	/* If first buddy, handle will be page aligned */
	if ((handle - ZHDR_SIZE_ALIGNED) & ~PAGE_MASK)
		zhdr->last_chunks = 0;
	else
		zhdr->first_chunks = 0;

	if (zhdr->under_reclaim) {
		/* zbud page is under reclaim, reclaim will free */
		spin_unlock(&pool->lock);
		return;
	}

	/* Remove from existing buddy list */
	list_del(&zhdr->buddy);

	if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) {
		/* zbud page is empty, free */
		list_del(&zhdr->lru);
		free_zbud_page(zhdr);
		pool->pages_nr--;
	} else {
		/* Add to unbuddied list */
		freechunks = num_free_chunks(zhdr);
		list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
	}

	spin_unlock(&pool->lock);
}

#define list_tail_entry(ptr, type, member) \
	list_entry((ptr)->prev, type, member)

/**
 * zbud_reclaim_page() - evicts allocations from a pool page and frees it
 * @pool:	pool from which a page will attempt to be evicted
 * @retires:	number of pages on the LRU list for which eviction will
 *		be attempted before failing
 *
 * zbud reclaim is different from normal system reclaim in that the reclaim is
 * done from the bottom, up.  This is because only the bottom layer, zbud, has
 * information on how the allocations are organized within each zbud page. This
 * has the potential to create interesting locking situations between zbud and
 * the user, however.
 *
 * To avoid these, this is how zbud_reclaim_page() should be called:

 * The user detects a page should be reclaimed and calls zbud_reclaim_page().
 * zbud_reclaim_page() will remove a zbud page from the pool LRU list and call
 * the user-defined eviction handler with the pool and handle as arguments.
 *
 * If the handle can not be evicted, the eviction handler should return
 * non-zero. zbud_reclaim_page() will add the zbud page back to the
 * appropriate list and try the next zbud page on the LRU up to
 * a user defined number of retries.
 *
 * If the handle is successfully evicted, the eviction handler should
 * return 0 _and_ should have called zbud_free() on the handle. zbud_free()
 * contains logic to delay freeing the page if the page is under reclaim,
 * as indicated by the setting of the PG_reclaim flag on the underlying page.
 *
 * If all buddies in the zbud page are successfully evicted, then the
 * zbud page can be freed.
 *
 * Returns: 0 if page is successfully freed, otherwise -EINVAL if there are
 * no pages to evict or an eviction handler is not registered, -EAGAIN if
 * the retry limit was hit.
 */
int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries)
{
	int i, ret, freechunks;
	struct zbud_header *zhdr;
	unsigned long first_handle = 0, last_handle = 0;

	spin_lock(&pool->lock);
	if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) ||
			retries == 0) {
		spin_unlock(&pool->lock);
		return -EINVAL;
	}
	for (i = 0; i < retries; i++) {
		zhdr = list_tail_entry(&pool->lru, struct zbud_header, lru);
		list_del(&zhdr->lru);
		list_del(&zhdr->buddy);
		/* Protect zbud page against free */
		zhdr->under_reclaim = true;
		/*
		 * We need encode the handles before unlocking, since we can
		 * race with free that will set (first|last)_chunks to 0
		 */
		first_handle = 0;
		last_handle = 0;
		if (zhdr->first_chunks)
			first_handle = encode_handle(zhdr, FIRST);
		if (zhdr->last_chunks)
			last_handle = encode_handle(zhdr, LAST);
		spin_unlock(&pool->lock);

		/* Issue the eviction callback(s) */
		if (first_handle) {
			ret = pool->ops->evict(pool, first_handle);
			if (ret)
				goto next;
		}
		if (last_handle) {
			ret = pool->ops->evict(pool, last_handle);
			if (ret)
				goto next;
		}
next:
		spin_lock(&pool->lock);
		zhdr->under_reclaim = false;
		if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) {
			/*
			 * Both buddies are now free, free the zbud page and
			 * return success.
			 */
			free_zbud_page(zhdr);
			pool->pages_nr--;
			spin_unlock(&pool->lock);
			return 0;
		} else if (zhdr->first_chunks == 0 ||
				zhdr->last_chunks == 0) {
			/* add to unbuddied list */
			freechunks = num_free_chunks(zhdr);
			list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
		} else {
			/* add to buddied list */
			list_add(&zhdr->buddy, &pool->buddied);
		}

		/* add to beginning of LRU */
		list_add(&zhdr->lru, &pool->lru);
	}
	spin_unlock(&pool->lock);
	return -EAGAIN;
}

/**
 * zbud_map() - maps the allocation associated with the given handle
 * @pool:	pool in which the allocation resides
 * @handle:	handle associated with the allocation to be mapped
 *
 * While trivial for zbud, the mapping functions for others allocators
 * implementing this allocation API could have more complex information encoded
 * in the handle and could create temporary mappings to make the data
 * accessible to the user.
 *
 * Returns: a pointer to the mapped allocation
 */
void *zbud_map(struct zbud_pool *pool, unsigned long handle)
{
	return (void *)(handle);
}

/**
 * zbud_unmap() - maps the allocation associated with the given handle
 * @pool:	pool in which the allocation resides
 * @handle:	handle associated with the allocation to be unmapped
 */
void zbud_unmap(struct zbud_pool *pool, unsigned long handle)
{
}

/**
 * zbud_get_pool_size() - gets the zbud pool size in pages
 * @pool:	pool whose size is being queried
 *
 * Returns: size in pages of the given pool.  The pool lock need not be
 * taken to access pages_nr.
 */
u64 zbud_get_pool_size(struct zbud_pool *pool)
{
	return pool->pages_nr;
}

static int __init init_zbud(void)
{
	/* Make sure the zbud header will fit in one chunk */
	BUILD_BUG_ON(sizeof(struct zbud_header) > ZHDR_SIZE_ALIGNED);
	pr_info("loaded\n");

#ifdef CONFIG_ZPOOL
	zpool_register_driver(&zbud_zpool_driver);
#endif

	return 0;
}

static void __exit exit_zbud(void)
{
#ifdef CONFIG_ZPOOL
	zpool_unregister_driver(&zbud_zpool_driver);
#endif

	pr_info("unloaded\n");
}

module_init(init_zbud);
module_exit(exit_zbud);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Seth Jennings <sjennings@variantweb.net>");
MODULE_DESCRIPTION("Buddy Allocator for Compressed Pages");
OpenPOWER on IntegriCloud