z3fold.c 24.3 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
55 56 57 58 59 60 61
 * @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
62
	spinlock_t page_lock;
63 64 65 66 67 68 69
	unsigned short first_chunks;
	unsigned short middle_chunks;
	unsigned short last_chunks;
	unsigned short start_middle;
	unsigned short first_num:2;
};

70 71 72 73
/*
 * 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
74 75 76 77 78
 * 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.
79 80 81 82 83
 */
#define NCHUNKS_ORDER	6

#define CHUNK_SHIFT	(PAGE_SHIFT - NCHUNKS_ORDER)
#define CHUNK_SIZE	(1 << CHUNK_SHIFT)
84 85 86
#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)
87 88
#define NCHUNKS		((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT)

89
#define BUDDY_MASK	(0x3)
90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113

/**
 * 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.
 * @buddied:	list tracking the z3fold pages that contain 3 buddies;
 *		these z3fold pages are full
 * @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 buddied;
	struct list_head lru;
V
Vitaly Wool 已提交
114
	atomic64_t pages_nr;
115 116 117 118 119 120 121 122 123 124 125 126 127 128
	const struct z3fold_ops *ops;
	struct zpool *zpool;
	const struct zpool_ops *zpool_ops;
};

/*
 * Internal z3fold page flags
 */
enum z3fold_page_flags {
	UNDER_RECLAIM = 0,
	PAGE_HEADLESS,
	MIDDLE_CHUNK_MAPPED,
};

129

130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152
/*****************
 * 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(UNDER_RECLAIM, &page->private);
	clear_bit(PAGE_HEADLESS, &page->private);
	clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);

V
Vitaly Wool 已提交
153
	spin_lock_init(&zhdr->page_lock);
154 155 156 157 158 159 160 161 162 163 164 165 166 167 168
	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 */
static void free_z3fold_page(struct z3fold_header *zhdr)
{
	__free_page(virt_to_page(zhdr));
}

V
Vitaly Wool 已提交
169 170 171 172 173 174 175 176 177 178 179 180 181
/* 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);
}


182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201
/*
 * 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);
}

202 203 204 205 206
/*
 * (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.
 */
207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
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 ?
227
			0 : zhdr->start_middle - ZHDR_CHUNKS;
228
		int nfree_after = zhdr->last_chunks ?
229 230
			0 : TOTAL_CHUNKS -
				(zhdr->start_middle + zhdr->middle_chunks);
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
		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->buddied);
	INIT_LIST_HEAD(&pool->lru);
V
Vitaly Wool 已提交
262
	atomic64_set(&pool->pages_nr, 0);
263 264 265 266 267 268 269 270 271 272 273 274 275 276 277
	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);
}

278 279 280 281 282 283 284 285 286
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
287
#define BIG_CHUNK_GAP	3
288 289 290 291 292
/* Has to be called with lock held */
static int z3fold_compact_page(struct z3fold_header *zhdr)
{
	struct page *page = virt_to_page(zhdr);

293 294
	if (test_bit(MIDDLE_CHUNK_MAPPED, &page->private))
		return 0; /* can't move middle chunk, it's used */
295

296 297 298 299 300 301
	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);
302 303 304 305
		zhdr->first_chunks = zhdr->middle_chunks;
		zhdr->middle_chunks = 0;
		zhdr->start_middle = 0;
		zhdr->first_num++;
V
Vitaly Wool 已提交
306
		return 1;
307
	}
V
Vitaly Wool 已提交
308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330

	/*
	 * 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;
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
}

/**
 * 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
374 375
			spin_lock(&pool->lock);
			zhdr = list_first_entry_or_null(&pool->unbuddied[i],
376
						struct z3fold_header, buddy);
V
Vitaly Wool 已提交
377 378 379 380 381 382 383 384 385 386 387 388
			if (!zhdr) {
				spin_unlock(&pool->lock);
				continue;
			}
			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)
389
					bud = LAST;
V
Vitaly Wool 已提交
390 391 392 393 394 395 396 397 398 399 400 401 402 403
				else
					bud = FIRST;
			} else if (zhdr->last_chunks == 0)
				bud = LAST;
			else if (zhdr->middle_chunks == 0)
				bud = MIDDLE;
			else {
				spin_lock(&pool->lock);
				list_add(&zhdr->buddy, &pool->buddied);
				spin_unlock(&pool->lock);
				z3fold_page_unlock(zhdr);
				pr_err("No free chunks in unbuddied\n");
				WARN_ON(1);
				continue;
404
			}
V
Vitaly Wool 已提交
405
			goto found;
406 407 408 409 410 411 412 413
		}
		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
414

V
Vitaly Wool 已提交
415
	atomic64_inc(&pool->pages_nr);
416 417 418 419
	zhdr = init_z3fold_page(page);

	if (bud == HEADLESS) {
		set_bit(PAGE_HEADLESS, &page->private);
V
Vitaly Wool 已提交
420
		spin_lock(&pool->lock);
421 422
		goto headless;
	}
V
Vitaly Wool 已提交
423
	z3fold_page_lock(zhdr);
424 425 426 427 428 429 430 431

found:
	if (bud == FIRST)
		zhdr->first_chunks = chunks;
	else if (bud == LAST)
		zhdr->last_chunks = chunks;
	else {
		zhdr->middle_chunks = chunks;
432
		zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS;
433 434
	}

V
Vitaly Wool 已提交
435
	spin_lock(&pool->lock);
436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454
	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]);
	} else {
		/* Add to buddied list */
		list_add(&zhdr->buddy, &pool->buddied);
	}

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
455 456
	if (bud != HEADLESS)
		z3fold_page_unlock(zhdr);
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

	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
485
		z3fold_page_lock(zhdr);
486
		bud = handle_to_buddy(handle);
487 488 489 490 491 492 493 494 495 496 497 498 499 500 501

		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
502
			z3fold_page_unlock(zhdr);
503 504 505 506 507 508
			return;
		}
	}

	if (test_bit(UNDER_RECLAIM, &page->private)) {
		/* z3fold page is under reclaim, reclaim will free */
V
Vitaly Wool 已提交
509 510
		if (bud != HEADLESS)
			z3fold_page_unlock(zhdr);
511 512 513
		return;
	}

V
Vitaly Wool 已提交
514
	/* Remove from existing buddy list */
V
Vitaly Wool 已提交
515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531
	if (bud != HEADLESS) {
		spin_lock(&pool->lock);
		/*
		 * this object may have been removed from its list by
		 * z3fold_alloc(). In that case we just do nothing,
		 * z3fold_alloc() will allocate an object and add the page
		 * to the relevant list.
		 */
		if (!list_empty(&zhdr->buddy)) {
			list_del(&zhdr->buddy);
		} else {
			spin_unlock(&pool->lock);
			z3fold_page_unlock(zhdr);
			return;
		}
		spin_unlock(&pool->lock);
	}
532 533 534 535 536

	if (bud == HEADLESS ||
	    (zhdr->first_chunks == 0 && zhdr->middle_chunks == 0 &&
			zhdr->last_chunks == 0)) {
		/* z3fold page is empty, free */
V
Vitaly Wool 已提交
537
		spin_lock(&pool->lock);
538
		list_del(&page->lru);
V
Vitaly Wool 已提交
539
		spin_unlock(&pool->lock);
540
		clear_bit(PAGE_HEADLESS, &page->private);
V
Vitaly Wool 已提交
541 542
		if (bud != HEADLESS)
			z3fold_page_unlock(zhdr);
543
		free_z3fold_page(zhdr);
V
Vitaly Wool 已提交
544
		atomic64_dec(&pool->pages_nr);
545 546 547
	} else {
		z3fold_compact_page(zhdr);
		/* Add to the unbuddied list */
V
Vitaly Wool 已提交
548
		spin_lock(&pool->lock);
549 550
		freechunks = num_free_chunks(zhdr);
		list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
V
Vitaly Wool 已提交
551 552
		spin_unlock(&pool->lock);
		z3fold_page_unlock(zhdr);
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
	}

}

/**
 * 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
601
	if (!pool->ops || !pool->ops->evict || retries == 0) {
602 603 604 605
		spin_unlock(&pool->lock);
		return -EINVAL;
	}
	for (i = 0; i < retries; i++) {
V
Vitaly Wool 已提交
606 607 608 609
		if (list_empty(&pool->lru)) {
			spin_unlock(&pool->lock);
			return -EINVAL;
		}
610 611 612 613 614 615 616 617
		page = list_last_entry(&pool->lru, struct page, lru);
		list_del(&page->lru);

		/* Protect z3fold page against free */
		set_bit(UNDER_RECLAIM, &page->private);
		zhdr = page_address(page);
		if (!test_bit(PAGE_HEADLESS, &page->private)) {
			list_del(&zhdr->buddy);
V
Vitaly Wool 已提交
618 619
			spin_unlock(&pool->lock);
			z3fold_page_lock(zhdr);
620 621 622 623 624 625 626 627 628 629 630 631 632 633
			/*
			 * 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
634
			z3fold_page_unlock(zhdr);
635 636 637
		} else {
			first_handle = encode_handle(zhdr, HEADLESS);
			last_handle = middle_handle = 0;
V
Vitaly Wool 已提交
638
			spin_unlock(&pool->lock);
639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657
		}

		/* 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
658 659
		if (!test_bit(PAGE_HEADLESS, &page->private))
			z3fold_page_lock(zhdr);
660 661 662 663 664 665 666 667
		clear_bit(UNDER_RECLAIM, &page->private);
		if ((test_bit(PAGE_HEADLESS, &page->private) && ret == 0) ||
		    (zhdr->first_chunks == 0 && zhdr->last_chunks == 0 &&
		     zhdr->middle_chunks == 0)) {
			/*
			 * All buddies are now free, free the z3fold page and
			 * return success.
			 */
V
Vitaly Wool 已提交
668 669
			if (!test_and_clear_bit(PAGE_HEADLESS, &page->private))
				z3fold_page_unlock(zhdr);
670
			free_z3fold_page(zhdr);
V
Vitaly Wool 已提交
671
			atomic64_dec(&pool->pages_nr);
672
			return 0;
673 674 675 676 677
		}  else if (!test_bit(PAGE_HEADLESS, &page->private)) {
			if (zhdr->first_chunks != 0 &&
			    zhdr->last_chunks != 0 &&
			    zhdr->middle_chunks != 0) {
				/* Full, add to buddied list */
V
Vitaly Wool 已提交
678
				spin_lock(&pool->lock);
679
				list_add(&zhdr->buddy, &pool->buddied);
V
Vitaly Wool 已提交
680
				spin_unlock(&pool->lock);
681 682 683
			} else {
				z3fold_compact_page(zhdr);
				/* add to unbuddied list */
V
Vitaly Wool 已提交
684
				spin_lock(&pool->lock);
685 686 687
				freechunks = num_free_chunks(zhdr);
				list_add(&zhdr->buddy,
					 &pool->unbuddied[freechunks]);
V
Vitaly Wool 已提交
688
				spin_unlock(&pool->lock);
689
			}
690 691
		}

V
Vitaly Wool 已提交
692 693 694 695
		if (!test_bit(PAGE_HEADLESS, &page->private))
			z3fold_page_unlock(zhdr);

		spin_lock(&pool->lock);
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
		/* add to beginning of LRU */
		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
727
	z3fold_page_lock(zhdr);
728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745
	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
746 747

	z3fold_page_unlock(zhdr);
748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765
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
766
	if (test_bit(PAGE_HEADLESS, &page->private))
767 768
		return;

V
Vitaly Wool 已提交
769
	z3fold_page_lock(zhdr);
770 771 772
	buddy = handle_to_buddy(handle);
	if (buddy == MIDDLE)
		clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
V
Vitaly Wool 已提交
773
	z3fold_page_unlock(zhdr);
774 775 776 777 778 779
}

/**
 * z3fold_get_pool_size() - gets the z3fold pool size in pages
 * @pool:	pool whose size is being queried
 *
V
Vitaly Wool 已提交
780
 * Returns: size in pages of the given pool.
781 782 783
 */
static u64 z3fold_get_pool_size(struct z3fold_pool *pool)
{
V
Vitaly Wool 已提交
784
	return atomic64_read(&pool->pages_nr);
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
}

/*****************
 * 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)
{
883 884
	/* Make sure the z3fold header is not larger than the page size */
	BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE);
885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900
	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");