z3fold.c 23.6 KB
Newer Older
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
/*
 * z3fold.c
 *
 * Author: Vitaly Wool <vitaly.wool@konsulko.com>
 * Copyright (C) 2016, Sony Mobile Communications Inc.
 *
 * This implementation is based on zbud written by Seth Jennings.
 *
 * z3fold is an special purpose allocator for storing compressed pages. It
 * can store up to three compressed pages per page which improves the
 * compression ratio of zbud while retaining its main concepts (e. g. always
 * storing an integral number of objects per page) and simplicity.
 * It still has simple and deterministic reclaim properties that make it
 * preferable to a higher density approach (with no requirement on integral
 * number of object per page) when reclaim is used.
 *
 * As in zbud, pages are divided into "chunks".  The size of the chunks is
 * fixed at compile time and is determined by NCHUNKS_ORDER below.
 *
 * z3fold doesn't export any API and is meant to be used via zpool API.
 */

#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/zpool.h>

/*****************
 * Structures
*****************/
37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53
struct z3fold_pool;
struct z3fold_ops {
	int (*evict)(struct z3fold_pool *pool, unsigned long handle);
};

enum buddy {
	HEADLESS = 0,
	FIRST,
	MIDDLE,
	LAST,
	BUDDIES_MAX
};

/*
 * struct z3fold_header - z3fold page metadata occupying the first chunk of each
 *			z3fold page, except for HEADLESS pages
 * @buddy:	links the z3fold page into the relevant list in the pool
V
Vitaly Wool 已提交
54
 * @page_lock:		per-page lock
V
Vitaly Wool 已提交
55
 * @refcount:		reference cound for the z3fold page
56 57 58 59 60 61 62
 * @first_chunks:	the size of the first buddy in chunks, 0 if free
 * @middle_chunks:	the size of the middle buddy in chunks, 0 if free
 * @last_chunks:	the size of the last buddy in chunks, 0 if free
 * @first_num:		the starting number (for the first handle)
 */
struct z3fold_header {
	struct list_head buddy;
V
Vitaly Wool 已提交
63
	spinlock_t page_lock;
V
Vitaly Wool 已提交
64
	struct kref refcount;
65 66 67 68 69 70 71
	unsigned short first_chunks;
	unsigned short middle_chunks;
	unsigned short last_chunks;
	unsigned short start_middle;
	unsigned short first_num:2;
};

72 73 74 75
/*
 * 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
76 77 78 79 80
 * allocation granularity will be in chunks of size PAGE_SIZE/64. Some chunks
 * in the beginning of an allocated page are occupied by z3fold header, so
 * NCHUNKS will be calculated to 63 (or 62 in case CONFIG_DEBUG_SPINLOCK=y),
 * which shows the max number of free chunks in z3fold page, also there will
 * be 63, or 62, respectively, freelists per pool.
81 82 83 84 85
 */
#define NCHUNKS_ORDER	6

#define CHUNK_SHIFT	(PAGE_SHIFT - NCHUNKS_ORDER)
#define CHUNK_SIZE	(1 << CHUNK_SHIFT)
86 87 88
#define ZHDR_SIZE_ALIGNED round_up(sizeof(struct z3fold_header), CHUNK_SIZE)
#define ZHDR_CHUNKS	(ZHDR_SIZE_ALIGNED >> CHUNK_SHIFT)
#define TOTAL_CHUNKS	(PAGE_SIZE >> CHUNK_SHIFT)
89 90
#define NCHUNKS		((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT)

91
#define BUDDY_MASK	(0x3)
92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112

/**
 * struct z3fold_pool - stores metadata for each z3fold pool
 * @lock:	protects all pool fields and first|last_chunk fields of any
 *		z3fold page in the pool
 * @unbuddied:	array of lists tracking z3fold pages that contain 2- buddies;
 *		the lists each z3fold page is added to depends on the size of
 *		its free region.
 * @lru:	list tracking the z3fold pages in LRU order by most recently
 *		added buddy.
 * @pages_nr:	number of z3fold 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 z3fold pool.
 */
struct z3fold_pool {
	spinlock_t lock;
	struct list_head unbuddied[NCHUNKS];
	struct list_head lru;
V
Vitaly Wool 已提交
113
	atomic64_t pages_nr;
114 115 116 117 118 119 120 121 122
	const struct z3fold_ops *ops;
	struct zpool *zpool;
	const struct zpool_ops *zpool_ops;
};

/*
 * Internal z3fold page flags
 */
enum z3fold_page_flags {
V
Vitaly Wool 已提交
123
	PAGE_HEADLESS = 0,
124 125 126
	MIDDLE_CHUNK_MAPPED,
};

127

128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149
/*****************
 * Helpers
*****************/

/* Converts an allocation size in bytes to size in z3fold 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 z3fold header of a newly allocated z3fold page */
static struct z3fold_header *init_z3fold_page(struct page *page)
{
	struct z3fold_header *zhdr = page_address(page);

	INIT_LIST_HEAD(&page->lru);
	clear_bit(PAGE_HEADLESS, &page->private);
	clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);

V
Vitaly Wool 已提交
150
	spin_lock_init(&zhdr->page_lock);
V
Vitaly Wool 已提交
151
	kref_init(&zhdr->refcount);
152 153 154 155 156 157 158 159 160 161
	zhdr->first_chunks = 0;
	zhdr->middle_chunks = 0;
	zhdr->last_chunks = 0;
	zhdr->first_num = 0;
	zhdr->start_middle = 0;
	INIT_LIST_HEAD(&zhdr->buddy);
	return zhdr;
}

/* Resets the struct page fields and frees the page */
V
Vitaly Wool 已提交
162
static void free_z3fold_page(struct page *page)
163
{
V
Vitaly Wool 已提交
164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179
	__free_page(page);
}

static void release_z3fold_page(struct kref *ref)
{
	struct z3fold_header *zhdr;
	struct page *page;

	zhdr = container_of(ref, struct z3fold_header, refcount);
	page = virt_to_page(zhdr);

	if (!list_empty(&zhdr->buddy))
		list_del(&zhdr->buddy);
	if (!list_empty(&page->lru))
		list_del(&page->lru);
	free_z3fold_page(page);
180 181
}

V
Vitaly Wool 已提交
182 183 184 185 186 187 188 189 190 191 192 193
/* Lock a z3fold page */
static inline void z3fold_page_lock(struct z3fold_header *zhdr)
{
	spin_lock(&zhdr->page_lock);
}

/* Unlock a z3fold page */
static inline void z3fold_page_unlock(struct z3fold_header *zhdr)
{
	spin_unlock(&zhdr->page_lock);
}

194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213
/*
 * Encodes the handle of a particular buddy within a z3fold page
 * Pool lock should be held as this function accesses first_num
 */
static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud)
{
	unsigned long handle;

	handle = (unsigned long)zhdr;
	if (bud != HEADLESS)
		handle += (bud + zhdr->first_num) & BUDDY_MASK;
	return handle;
}

/* Returns the z3fold page where a given handle is stored */
static struct z3fold_header *handle_to_z3fold_header(unsigned long handle)
{
	return (struct z3fold_header *)(handle & PAGE_MASK);
}

214 215 216 217 218
/*
 * (handle & BUDDY_MASK) < zhdr->first_num is possible in encode_handle
 *  but that doesn't matter. because the masking will result in the
 *  correct buddy number.
 */
219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238
static enum buddy handle_to_buddy(unsigned long handle)
{
	struct z3fold_header *zhdr = handle_to_z3fold_header(handle);
	return (handle - zhdr->first_num) & BUDDY_MASK;
}

/*
 * Returns the number of free chunks in a z3fold page.
 * NB: can't be used with HEADLESS pages.
 */
static int num_free_chunks(struct z3fold_header *zhdr)
{
	int nfree;
	/*
	 * If there is a middle object, pick up the bigger free space
	 * either before or after it. Otherwise just subtract the number
	 * of chunks occupied by the first and the last objects.
	 */
	if (zhdr->middle_chunks != 0) {
		int nfree_before = zhdr->first_chunks ?
239
			0 : zhdr->start_middle - ZHDR_CHUNKS;
240
		int nfree_after = zhdr->last_chunks ?
241 242
			0 : TOTAL_CHUNKS -
				(zhdr->start_middle + zhdr->middle_chunks);
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
		nfree = max(nfree_before, nfree_after);
	} else
		nfree = NCHUNKS - zhdr->first_chunks - zhdr->last_chunks;
	return nfree;
}

/*****************
 * API Functions
*****************/
/**
 * z3fold_create_pool() - create a new z3fold pool
 * @gfp:	gfp flags when allocating the z3fold pool structure
 * @ops:	user-defined operations for the z3fold pool
 *
 * Return: pointer to the new z3fold pool or NULL if the metadata allocation
 * failed.
 */
static struct z3fold_pool *z3fold_create_pool(gfp_t gfp,
		const struct z3fold_ops *ops)
{
	struct z3fold_pool *pool;
	int i;

	pool = kzalloc(sizeof(struct z3fold_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->lru);
V
Vitaly Wool 已提交
273
	atomic64_set(&pool->pages_nr, 0);
274 275 276 277 278 279 280 281 282 283 284 285 286 287 288
	pool->ops = ops;
	return pool;
}

/**
 * z3fold_destroy_pool() - destroys an existing z3fold pool
 * @pool:	the z3fold pool to be destroyed
 *
 * The pool should be emptied before this function is called.
 */
static void z3fold_destroy_pool(struct z3fold_pool *pool)
{
	kfree(pool);
}

289 290 291 292 293 294 295 296 297
static inline void *mchunk_memmove(struct z3fold_header *zhdr,
				unsigned short dst_chunk)
{
	void *beg = zhdr;
	return memmove(beg + (dst_chunk << CHUNK_SHIFT),
		       beg + (zhdr->start_middle << CHUNK_SHIFT),
		       zhdr->middle_chunks << CHUNK_SHIFT);
}

V
Vitaly Wool 已提交
298
#define BIG_CHUNK_GAP	3
299 300 301 302 303
/* Has to be called with lock held */
static int z3fold_compact_page(struct z3fold_header *zhdr)
{
	struct page *page = virt_to_page(zhdr);

304 305
	if (test_bit(MIDDLE_CHUNK_MAPPED, &page->private))
		return 0; /* can't move middle chunk, it's used */
306

307 308 309 310 311 312
	if (zhdr->middle_chunks == 0)
		return 0; /* nothing to compact */

	if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) {
		/* move to the beginning */
		mchunk_memmove(zhdr, ZHDR_CHUNKS);
313 314 315 316
		zhdr->first_chunks = zhdr->middle_chunks;
		zhdr->middle_chunks = 0;
		zhdr->start_middle = 0;
		zhdr->first_num++;
V
Vitaly Wool 已提交
317
		return 1;
318
	}
V
Vitaly Wool 已提交
319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341

	/*
	 * moving data is expensive, so let's only do that if
	 * there's substantial gain (at least BIG_CHUNK_GAP chunks)
	 */
	if (zhdr->first_chunks != 0 && zhdr->last_chunks == 0 &&
	    zhdr->start_middle - (zhdr->first_chunks + ZHDR_CHUNKS) >=
			BIG_CHUNK_GAP) {
		mchunk_memmove(zhdr, zhdr->first_chunks + ZHDR_CHUNKS);
		zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS;
		return 1;
	} else if (zhdr->last_chunks != 0 && zhdr->first_chunks == 0 &&
		   TOTAL_CHUNKS - (zhdr->last_chunks + zhdr->start_middle
					+ zhdr->middle_chunks) >=
			BIG_CHUNK_GAP) {
		unsigned short new_start = TOTAL_CHUNKS - zhdr->last_chunks -
			zhdr->middle_chunks;
		mchunk_memmove(zhdr, new_start);
		zhdr->start_middle = new_start;
		return 1;
	}

	return 0;
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
}

/**
 * z3fold_alloc() - allocates a region of a given size
 * @pool:	z3fold 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 z3fold 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.
 */
static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp,
			unsigned long *handle)
{
	int chunks = 0, i, freechunks;
	struct z3fold_header *zhdr = NULL;
	enum buddy bud;
	struct page *page;

	if (!size || (gfp & __GFP_HIGHMEM))
		return -EINVAL;

	if (size > PAGE_SIZE)
		return -ENOSPC;

	if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE)
		bud = HEADLESS;
	else {
		chunks = size_to_chunks(size);

		/* First, try to find an unbuddied z3fold page. */
		zhdr = NULL;
		for_each_unbuddied_list(i, chunks) {
V
Vitaly Wool 已提交
385 386
			spin_lock(&pool->lock);
			zhdr = list_first_entry_or_null(&pool->unbuddied[i],
387
						struct z3fold_header, buddy);
V
Vitaly Wool 已提交
388 389 390 391
			if (!zhdr) {
				spin_unlock(&pool->lock);
				continue;
			}
V
Vitaly Wool 已提交
392
			kref_get(&zhdr->refcount);
V
Vitaly Wool 已提交
393 394 395 396 397 398 399 400
			list_del_init(&zhdr->buddy);
			spin_unlock(&pool->lock);

			page = virt_to_page(zhdr);
			z3fold_page_lock(zhdr);
			if (zhdr->first_chunks == 0) {
				if (zhdr->middle_chunks != 0 &&
				    chunks >= zhdr->start_middle)
401
					bud = LAST;
V
Vitaly Wool 已提交
402 403 404 405 406 407 408
				else
					bud = FIRST;
			} else if (zhdr->last_chunks == 0)
				bud = LAST;
			else if (zhdr->middle_chunks == 0)
				bud = MIDDLE;
			else {
V
Vitaly Wool 已提交
409
				z3fold_page_unlock(zhdr);
V
Vitaly Wool 已提交
410
				spin_lock(&pool->lock);
V
Vitaly Wool 已提交
411 412 413
				if (kref_put(&zhdr->refcount,
					     release_z3fold_page))
					atomic64_dec(&pool->pages_nr);
V
Vitaly Wool 已提交
414 415 416 417
				spin_unlock(&pool->lock);
				pr_err("No free chunks in unbuddied\n");
				WARN_ON(1);
				continue;
418
			}
V
Vitaly Wool 已提交
419
			goto found;
420 421 422 423 424 425 426 427
		}
		bud = FIRST;
	}

	/* Couldn't find unbuddied z3fold page, create new one */
	page = alloc_page(gfp);
	if (!page)
		return -ENOMEM;
V
Vitaly Wool 已提交
428

V
Vitaly Wool 已提交
429
	atomic64_inc(&pool->pages_nr);
430 431 432 433
	zhdr = init_z3fold_page(page);

	if (bud == HEADLESS) {
		set_bit(PAGE_HEADLESS, &page->private);
V
Vitaly Wool 已提交
434
		spin_lock(&pool->lock);
435 436
		goto headless;
	}
V
Vitaly Wool 已提交
437
	z3fold_page_lock(zhdr);
438 439 440 441 442 443 444 445

found:
	if (bud == FIRST)
		zhdr->first_chunks = chunks;
	else if (bud == LAST)
		zhdr->last_chunks = chunks;
	else {
		zhdr->middle_chunks = chunks;
446
		zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS;
447 448
	}

V
Vitaly Wool 已提交
449
	spin_lock(&pool->lock);
450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465
	if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0 ||
			zhdr->middle_chunks == 0) {
		/* Add to unbuddied list */
		freechunks = num_free_chunks(zhdr);
		list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
	}

headless:
	/* Add/move z3fold page to beginning of LRU */
	if (!list_empty(&page->lru))
		list_del(&page->lru);

	list_add(&page->lru, &pool->lru);

	*handle = encode_handle(zhdr, bud);
	spin_unlock(&pool->lock);
V
Vitaly Wool 已提交
466 467
	if (bud != HEADLESS)
		z3fold_page_unlock(zhdr);
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

	return 0;
}

/**
 * z3fold_free() - frees the allocation associated with the given handle
 * @pool:	pool in which the allocation resided
 * @handle:	handle associated with the allocation returned by z3fold_alloc()
 *
 * In the case that the z3fold 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 z3fold_reclaim_page() below).
 */
static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
{
	struct z3fold_header *zhdr;
	int freechunks;
	struct page *page;
	enum buddy bud;

	zhdr = handle_to_z3fold_header(handle);
	page = virt_to_page(zhdr);

	if (test_bit(PAGE_HEADLESS, &page->private)) {
		/* HEADLESS page stored */
		bud = HEADLESS;
	} else {
V
Vitaly Wool 已提交
496
		z3fold_page_lock(zhdr);
497
		bud = handle_to_buddy(handle);
498 499 500 501 502 503 504 505 506 507 508 509 510 511 512

		switch (bud) {
		case FIRST:
			zhdr->first_chunks = 0;
			break;
		case MIDDLE:
			zhdr->middle_chunks = 0;
			zhdr->start_middle = 0;
			break;
		case LAST:
			zhdr->last_chunks = 0;
			break;
		default:
			pr_err("%s: unknown bud %d\n", __func__, bud);
			WARN_ON(1);
V
Vitaly Wool 已提交
513
			z3fold_page_unlock(zhdr);
514 515 516 517
			return;
		}
	}

V
Vitaly Wool 已提交
518
	if (bud == HEADLESS) {
V
Vitaly Wool 已提交
519
		spin_lock(&pool->lock);
520
		list_del(&page->lru);
V
Vitaly Wool 已提交
521
		spin_unlock(&pool->lock);
V
Vitaly Wool 已提交
522
		free_z3fold_page(page);
V
Vitaly Wool 已提交
523
		atomic64_dec(&pool->pages_nr);
524
	} else {
V
Vitaly Wool 已提交
525 526 527 528 529 530 531 532 533 534 535 536
		if (zhdr->first_chunks != 0 || zhdr->middle_chunks != 0 ||
		    zhdr->last_chunks != 0) {
			z3fold_compact_page(zhdr);
			/* Add to the unbuddied list */
			spin_lock(&pool->lock);
			if (!list_empty(&zhdr->buddy))
				list_del(&zhdr->buddy);
			freechunks = num_free_chunks(zhdr);
			list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
			spin_unlock(&pool->lock);
		}
		z3fold_page_unlock(zhdr);
V
Vitaly Wool 已提交
537
		spin_lock(&pool->lock);
V
Vitaly Wool 已提交
538 539
		if (kref_put(&zhdr->refcount, release_z3fold_page))
			atomic64_dec(&pool->pages_nr);
V
Vitaly Wool 已提交
540
		spin_unlock(&pool->lock);
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
	}

}

/**
 * z3fold_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
 *
 * z3fold reclaim is different from normal system reclaim in that it is done
 * from the bottom, up. This is because only the bottom layer, z3fold, has
 * information on how the allocations are organized within each z3fold page.
 * This has the potential to create interesting locking situations between
 * z3fold and the user, however.
 *
 * To avoid these, this is how z3fold_reclaim_page() should be called:

 * The user detects a page should be reclaimed and calls z3fold_reclaim_page().
 * z3fold_reclaim_page() will remove a z3fold 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. z3fold_reclaim_page() will add the z3fold page back to the
 * appropriate list and try the next z3fold 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 z3fold_free() on the handle. z3fold_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 z3fold page are successfully evicted, then the
 * z3fold 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.
 */
static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
{
	int i, ret = 0, freechunks;
	struct z3fold_header *zhdr;
	struct page *page;
	unsigned long first_handle = 0, middle_handle = 0, last_handle = 0;

	spin_lock(&pool->lock);
V
Vitaly Wool 已提交
589
	if (!pool->ops || !pool->ops->evict || retries == 0) {
590 591 592 593
		spin_unlock(&pool->lock);
		return -EINVAL;
	}
	for (i = 0; i < retries; i++) {
V
Vitaly Wool 已提交
594 595 596 597
		if (list_empty(&pool->lru)) {
			spin_unlock(&pool->lock);
			return -EINVAL;
		}
598
		page = list_last_entry(&pool->lru, struct page, lru);
V
Vitaly Wool 已提交
599
		list_del_init(&page->lru);
600 601 602

		zhdr = page_address(page);
		if (!test_bit(PAGE_HEADLESS, &page->private)) {
V
Vitaly Wool 已提交
603 604 605
			if (!list_empty(&zhdr->buddy))
				list_del_init(&zhdr->buddy);
			kref_get(&zhdr->refcount);
V
Vitaly Wool 已提交
606 607
			spin_unlock(&pool->lock);
			z3fold_page_lock(zhdr);
608 609 610 611 612 613 614 615 616 617 618 619 620 621
			/*
			 * 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;
			middle_handle = 0;
			if (zhdr->first_chunks)
				first_handle = encode_handle(zhdr, FIRST);
			if (zhdr->middle_chunks)
				middle_handle = encode_handle(zhdr, MIDDLE);
			if (zhdr->last_chunks)
				last_handle = encode_handle(zhdr, LAST);
V
Vitaly Wool 已提交
622
			z3fold_page_unlock(zhdr);
623 624 625
		} else {
			first_handle = encode_handle(zhdr, HEADLESS);
			last_handle = middle_handle = 0;
V
Vitaly Wool 已提交
626
			spin_unlock(&pool->lock);
627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645
		}

		/* Issue the eviction callback(s) */
		if (middle_handle) {
			ret = pool->ops->evict(pool, middle_handle);
			if (ret)
				goto next;
		}
		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:
V
Vitaly Wool 已提交
646 647 648 649
		if (test_bit(PAGE_HEADLESS, &page->private)) {
			if (ret == 0) {
				free_z3fold_page(page);
				return 0;
650
			} else {
V
Vitaly Wool 已提交
651 652 653 654 655 656 657 658
				spin_lock(&pool->lock);
			}
		} else {
			z3fold_page_lock(zhdr);
			if ((zhdr->first_chunks || zhdr->last_chunks ||
			     zhdr->middle_chunks) &&
			    !(zhdr->first_chunks && zhdr->last_chunks &&
			      zhdr->middle_chunks)) {
659 660
				z3fold_compact_page(zhdr);
				/* add to unbuddied list */
V
Vitaly Wool 已提交
661
				spin_lock(&pool->lock);
662 663 664
				freechunks = num_free_chunks(zhdr);
				list_add(&zhdr->buddy,
					 &pool->unbuddied[freechunks]);
V
Vitaly Wool 已提交
665
				spin_unlock(&pool->lock);
666
			}
V
Vitaly Wool 已提交
667
			z3fold_page_unlock(zhdr);
V
Vitaly Wool 已提交
668 669 670 671 672 673
			spin_lock(&pool->lock);
			if (kref_put(&zhdr->refcount, release_z3fold_page)) {
				atomic64_dec(&pool->pages_nr);
				return 0;
			}
		}
V
Vitaly Wool 已提交
674

V
Vitaly Wool 已提交
675 676 677 678 679
		/*
		 * Add to the beginning of LRU.
		 * Pool lock has to be kept here to ensure the page has
		 * not already been released
		 */
680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709
		list_add(&page->lru, &pool->lru);
	}
	spin_unlock(&pool->lock);
	return -EAGAIN;
}

/**
 * z3fold_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
 *
 * Extracts the buddy number from handle and constructs the pointer to the
 * correct starting chunk within the page.
 *
 * Returns: a pointer to the mapped allocation
 */
static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle)
{
	struct z3fold_header *zhdr;
	struct page *page;
	void *addr;
	enum buddy buddy;

	zhdr = handle_to_z3fold_header(handle);
	addr = zhdr;
	page = virt_to_page(zhdr);

	if (test_bit(PAGE_HEADLESS, &page->private))
		goto out;

V
Vitaly Wool 已提交
710
	z3fold_page_lock(zhdr);
711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728
	buddy = handle_to_buddy(handle);
	switch (buddy) {
	case FIRST:
		addr += ZHDR_SIZE_ALIGNED;
		break;
	case MIDDLE:
		addr += zhdr->start_middle << CHUNK_SHIFT;
		set_bit(MIDDLE_CHUNK_MAPPED, &page->private);
		break;
	case LAST:
		addr += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT);
		break;
	default:
		pr_err("unknown buddy id %d\n", buddy);
		WARN_ON(1);
		addr = NULL;
		break;
	}
V
Vitaly Wool 已提交
729 730

	z3fold_page_unlock(zhdr);
731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748
out:
	return addr;
}

/**
 * z3fold_unmap() - unmaps the allocation associated with the given handle
 * @pool:	pool in which the allocation resides
 * @handle:	handle associated with the allocation to be unmapped
 */
static void z3fold_unmap(struct z3fold_pool *pool, unsigned long handle)
{
	struct z3fold_header *zhdr;
	struct page *page;
	enum buddy buddy;

	zhdr = handle_to_z3fold_header(handle);
	page = virt_to_page(zhdr);

V
Vitaly Wool 已提交
749
	if (test_bit(PAGE_HEADLESS, &page->private))
750 751
		return;

V
Vitaly Wool 已提交
752
	z3fold_page_lock(zhdr);
753 754 755
	buddy = handle_to_buddy(handle);
	if (buddy == MIDDLE)
		clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
V
Vitaly Wool 已提交
756
	z3fold_page_unlock(zhdr);
757 758 759 760 761 762
}

/**
 * z3fold_get_pool_size() - gets the z3fold pool size in pages
 * @pool:	pool whose size is being queried
 *
V
Vitaly Wool 已提交
763
 * Returns: size in pages of the given pool.
764 765 766
 */
static u64 z3fold_get_pool_size(struct z3fold_pool *pool)
{
V
Vitaly Wool 已提交
767
	return atomic64_read(&pool->pages_nr);
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
}

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

static int z3fold_zpool_evict(struct z3fold_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 const struct z3fold_ops z3fold_zpool_ops = {
	.evict =	z3fold_zpool_evict
};

static void *z3fold_zpool_create(const char *name, gfp_t gfp,
			       const struct zpool_ops *zpool_ops,
			       struct zpool *zpool)
{
	struct z3fold_pool *pool;

	pool = z3fold_create_pool(gfp, zpool_ops ? &z3fold_zpool_ops : NULL);
	if (pool) {
		pool->zpool = zpool;
		pool->zpool_ops = zpool_ops;
	}
	return pool;
}

static void z3fold_zpool_destroy(void *pool)
{
	z3fold_destroy_pool(pool);
}

static int z3fold_zpool_malloc(void *pool, size_t size, gfp_t gfp,
			unsigned long *handle)
{
	return z3fold_alloc(pool, size, gfp, handle);
}
static void z3fold_zpool_free(void *pool, unsigned long handle)
{
	z3fold_free(pool, handle);
}

static int z3fold_zpool_shrink(void *pool, unsigned int pages,
			unsigned int *reclaimed)
{
	unsigned int total = 0;
	int ret = -EINVAL;

	while (total < pages) {
		ret = z3fold_reclaim_page(pool, 8);
		if (ret < 0)
			break;
		total++;
	}

	if (reclaimed)
		*reclaimed = total;

	return ret;
}

static void *z3fold_zpool_map(void *pool, unsigned long handle,
			enum zpool_mapmode mm)
{
	return z3fold_map(pool, handle);
}
static void z3fold_zpool_unmap(void *pool, unsigned long handle)
{
	z3fold_unmap(pool, handle);
}

static u64 z3fold_zpool_total_size(void *pool)
{
	return z3fold_get_pool_size(pool) * PAGE_SIZE;
}

static struct zpool_driver z3fold_zpool_driver = {
	.type =		"z3fold",
	.owner =	THIS_MODULE,
	.create =	z3fold_zpool_create,
	.destroy =	z3fold_zpool_destroy,
	.malloc =	z3fold_zpool_malloc,
	.free =		z3fold_zpool_free,
	.shrink =	z3fold_zpool_shrink,
	.map =		z3fold_zpool_map,
	.unmap =	z3fold_zpool_unmap,
	.total_size =	z3fold_zpool_total_size,
};

MODULE_ALIAS("zpool-z3fold");

static int __init init_z3fold(void)
{
866 867
	/* Make sure the z3fold header is not larger than the page size */
	BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE);
868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883
	zpool_register_driver(&z3fold_zpool_driver);

	return 0;
}

static void __exit exit_z3fold(void)
{
	zpool_unregister_driver(&z3fold_zpool_driver);
}

module_init(init_z3fold);
module_exit(exit_z3fold);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Vitaly Wool <vitalywool@gmail.com>");
MODULE_DESCRIPTION("3-Fold Allocator for Compressed Pages");