aboutsummaryrefslogtreecommitdiff
path: root/mm/zswap.c
blob: 6b862518d817ba83f88a403c579a834bc1c0528b (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
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
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
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
/*
 * zswap.c - zswap driver file
 *
 * zswap is a backend for frontswap that takes pages that are in the process
 * of being swapped out and attempts to compress and store them in a
 * RAM-based memory pool.  This can result in a significant I/O reduction on
 * the swap device and, in the case where decompressing from RAM is faster
 * than reading from the swap device, can also improve workload performance.
 *
 * Copyright (C) 2012  Seth Jennings <sjenning@linux.vnet.ibm.com>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version 2
 * of the License, or (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
*/

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/cpu.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/atomic.h>
#include <linux/frontswap.h>
#include <linux/rbtree.h>
#include <linux/swap.h>
#include <linux/crypto.h>
#include <linux/mempool.h>
#include <linux/zbud.h>

#include <linux/mm_types.h>
#include <linux/page-flags.h>
#include <linux/swapops.h>
#include <linux/writeback.h>
#include <linux/pagemap.h>

/*********************************
* statistics
**********************************/
/* Number of memory pages used by the compressed pool */
static u64 zswap_pool_pages;
/* The number of compressed pages currently stored in zswap */
static atomic_t zswap_stored_pages = ATOMIC_INIT(0);

/*
 * The statistics below are not protected from concurrent access for
 * performance reasons so they may not be a 100% accurate.  However,
 * they do provide useful information on roughly how many times a
 * certain event is occurring.
*/

/* Pool limit was hit (see zswap_max_pool_percent) */
static u64 zswap_pool_limit_hit;
/* Pages written back when pool limit was reached */
static u64 zswap_written_back_pages;
/* Store failed due to a reclaim failure after pool limit was reached */
static u64 zswap_reject_reclaim_fail;
/* Compressed page was too big for the allocator to (optimally) store */
static u64 zswap_reject_compress_poor;
/* Store failed because underlying allocator could not get memory */
static u64 zswap_reject_alloc_fail;
/* Store failed because the entry metadata could not be allocated (rare) */
static u64 zswap_reject_kmemcache_fail;
/* Duplicate store was encountered (rare) */
static u64 zswap_duplicate_entry;

/*********************************
* tunables
**********************************/
/* Enable/disable zswap (disabled by default, fixed at boot for now) */
static bool zswap_enabled __read_mostly;
module_param_named(enabled, zswap_enabled, bool, 0);

/* Compressor to be used by zswap (fixed at boot for now) */
#define ZSWAP_COMPRESSOR_DEFAULT "lzo"
static char *zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
module_param_named(compressor, zswap_compressor, charp, 0);

/* The maximum percentage of memory that the compressed pool can occupy */
static unsigned int zswap_max_pool_percent = 20;
module_param_named(max_pool_percent,
			zswap_max_pool_percent, uint, 0644);

/*********************************
* compression functions
**********************************/
/* per-cpu compression transforms */
static struct crypto_comp * __percpu *zswap_comp_pcpu_tfms;

enum comp_op {
	ZSWAP_COMPOP_COMPRESS,
	ZSWAP_COMPOP_DECOMPRESS
};

static int zswap_comp_op(enum comp_op op, const u8 *src, unsigned int slen,
				u8 *dst, unsigned int *dlen)
{
	struct crypto_comp *tfm;
	int ret;

	tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, get_cpu());
	switch (op) {
	case ZSWAP_COMPOP_COMPRESS:
		ret = crypto_comp_compress(tfm, src, slen, dst, dlen);
		break;
	case ZSWAP_COMPOP_DECOMPRESS:
		ret = crypto_comp_decompress(tfm, src, slen, dst, dlen);
		break;
	default:
		ret = -EINVAL;
	}

	put_cpu();
	return ret;
}

static int __init zswap_comp_init(void)
{
	if (!crypto_has_comp(zswap_compressor, 0, 0)) {
		pr_info("%s compressor not available\n", zswap_compressor);
		/* fall back to default compressor */
		zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
		if (!crypto_has_comp(zswap_compressor, 0, 0))
			/* can't even load the default compressor */
			return -ENODEV;
	}
	pr_info("using %s compressor\n", zswap_compressor);

	/* alloc percpu transforms */
	zswap_comp_pcpu_tfms = alloc_percpu(struct crypto_comp *);
	if (!zswap_comp_pcpu_tfms)
		return -ENOMEM;
	return 0;
}

static void zswap_comp_exit(void)
{
	/* free percpu transforms */
	if (zswap_comp_pcpu_tfms)
		free_percpu(zswap_comp_pcpu_tfms);
}

/*********************************
* data structures
**********************************/
/*
 * struct zswap_entry
 *
 * This structure contains the metadata for tracking a single compressed
 * page within zswap.
 *
 * rbnode - links the entry into red-black tree for the appropriate swap type
 * refcount - the number of outstanding reference to the entry. This is needed
 *            to protect against premature freeing of the entry by code
 *            concurent calls to load, invalidate, and writeback.  The lock
 *            for the zswap_tree structure that contains the entry must
 *            be held while changing the refcount.  Since the lock must
 *            be held, there is no reason to also make refcount atomic.
 * offset - the swap offset for the entry.  Index into the red-black tree.
 * handle - zsmalloc allocation handle that stores the compressed page data
 * length - the length in bytes of the compressed page data.  Needed during
 *           decompression
 */
struct zswap_entry {
	struct rb_node rbnode;
	pgoff_t offset;
	int refcount;
	unsigned int length;
	unsigned long handle;
};

struct zswap_header {
	swp_entry_t swpentry;
};

/*
 * The tree lock in the zswap_tree struct protects a few things:
 * - the rbtree
 * - the refcount field of each entry in the tree
 */
struct zswap_tree {
	struct rb_root rbroot;
	spinlock_t lock;
	struct zbud_pool *pool;
};

static struct zswap_tree *zswap_trees[MAX_SWAPFILES];

/*********************************
* zswap entry functions
**********************************/
static struct kmem_cache *zswap_entry_cache;

static int zswap_entry_cache_create(void)
{
	zswap_entry_cache = KMEM_CACHE(zswap_entry, 0);
	return (zswap_entry_cache == NULL);
}

static void zswap_entry_cache_destory(void)
{
	kmem_cache_destroy(zswap_entry_cache);
}

static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp)
{
	struct zswap_entry *entry;
	entry = kmem_cache_alloc(zswap_entry_cache, gfp);
	if (!entry)
		return NULL;
	entry->refcount = 1;
	return entry;
}

static void zswap_entry_cache_free(struct zswap_entry *entry)
{
	kmem_cache_free(zswap_entry_cache, entry);
}

/* caller must hold the tree lock */
static void zswap_entry_get(struct zswap_entry *entry)
{
	entry->refcount++;
}

/* caller must hold the tree lock */
static int zswap_entry_put(struct zswap_entry *entry)
{
	entry->refcount--;
	return entry->refcount;
}

/*********************************
* rbtree functions
**********************************/
static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset)
{
	struct rb_node *node = root->rb_node;
	struct zswap_entry *entry;

	while (node) {
		entry = rb_entry(node, struct zswap_entry, rbnode);
		if (entry->offset > offset)
			node = node->rb_left;
		else if (entry->offset < offset)
			node = node->rb_right;
		else
			return entry;
	}
	return NULL;
}

/*
 * In the case that a entry with the same offset is found, a pointer to
 * the existing entry is stored in dupentry and the function returns -EEXIST
 */
static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry,
			struct zswap_entry **dupentry)
{
	struct rb_node **link = &root->rb_node, *parent = NULL;
	struct zswap_entry *myentry;

	while (*link) {
		parent = *link;
		myentry = rb_entry(parent, struct zswap_entry, rbnode);
		if (myentry->offset > entry->offset)
			link = &(*link)->rb_left;
		else if (myentry->offset < entry->offset)
			link = &(*link)->rb_right;
		else {
			*dupentry = myentry;
			return -EEXIST;
		}
	}
	rb_link_node(&entry->rbnode, parent, link);
	rb_insert_color(&entry->rbnode, root);
	return 0;
}

/*********************************
* per-cpu code
**********************************/
static DEFINE_PER_CPU(u8 *, zswap_dstmem);

static int __zswap_cpu_notifier(unsigned long action, unsigned long cpu)
{
	struct crypto_comp *tfm;
	u8 *dst;

	switch (action) {
	case CPU_UP_PREPARE:
		tfm = crypto_alloc_comp(zswap_compressor, 0, 0);
		if (IS_ERR(tfm)) {
			pr_err("can't allocate compressor transform\n");
			return NOTIFY_BAD;
		}
		*per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = tfm;
		dst = kmalloc(PAGE_SIZE * 2, GFP_KERNEL);
		if (!dst) {
			pr_err("can't allocate compressor buffer\n");
			crypto_free_comp(tfm);
			*per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL;
			return NOTIFY_BAD;
		}
		per_cpu(zswap_dstmem, cpu) = dst;
		break;
	case CPU_DEAD:
	case CPU_UP_CANCELED:
		tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu);
		if (tfm) {
			crypto_free_comp(tfm);
			*per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL;
		}
		dst = per_cpu(zswap_dstmem, cpu);
		kfree(dst);
		per_cpu(zswap_dstmem, cpu) = NULL;
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static int zswap_cpu_notifier(struct notifier_block *nb,
				unsigned long action, void *pcpu)
{
	unsigned long cpu = (unsigned long)pcpu;
	return __zswap_cpu_notifier(action, cpu);
}

static struct notifier_block zswap_cpu_notifier_block = {
	.notifier_call = zswap_cpu_notifier
};

static int zswap_cpu_init(void)
{
	unsigned long cpu;

	get_online_cpus();
	for_each_online_cpu(cpu)
		if (__zswap_cpu_notifier(CPU_UP_PREPARE, cpu) != NOTIFY_OK)
			goto cleanup;
	register_cpu_notifier(&zswap_cpu_notifier_block);
	put_online_cpus();
	return 0;

cleanup:
	for_each_online_cpu(cpu)
		__zswap_cpu_notifier(CPU_UP_CANCELED, cpu);
	put_online_cpus();
	return -ENOMEM;
}

/*********************************
* helpers
**********************************/
static bool zswap_is_full(void)
{
	return (totalram_pages * zswap_max_pool_percent / 100 <
		zswap_pool_pages);
}

/*
 * Carries out the common pattern of freeing and entry's zsmalloc allocation,
 * freeing the entry itself, and decrementing the number of stored pages.
 */
static void zswap_free_entry(struct zswap_tree *tree, struct zswap_entry *entry)
{
	zbud_free(tree->pool, entry->handle);
	zswap_entry_cache_free(entry);
	atomic_dec(&zswap_stored_pages);
	zswap_pool_pages = zbud_get_pool_size(tree->pool);
}

/*********************************
* writeback code
**********************************/
/* return enum for zswap_get_swap_cache_page */
enum zswap_get_swap_ret {
	ZSWAP_SWAPCACHE_NEW,
	ZSWAP_SWAPCACHE_EXIST,
	ZSWAP_SWAPCACHE_FAIL,
};

/*
 * zswap_get_swap_cache_page
 *
 * This is an adaption of read_swap_cache_async()
 *
 * This function tries to find a page with the given swap entry
 * in the swapper_space address space (the swap cache).  If the page
 * is found, it is returned in retpage.  Otherwise, a page is allocated,
 * added to the swap cache, and returned in retpage.
 *
 * If success, the swap cache page is returned in retpage
 * Returns ZSWAP_SWAPCACHE_EXIST if page was already in the swap cache
 * Returns ZSWAP_SWAPCACHE_NEW if the new page needs to be populated,
 *     the new page is added to swapcache and locked
 * Returns ZSWAP_SWAPCACHE_FAIL on error
 */
static int zswap_get_swap_cache_page(swp_entry_t entry,
				struct page **retpage)
{
	struct page *found_page, *new_page = NULL;
	struct address_space *swapper_space = swap_address_space(entry);
	int err;

	*retpage = NULL;
	do {
		/*
		 * First check the swap cache.  Since this is normally
		 * called after lookup_swap_cache() failed, re-calling
		 * that would confuse statistics.
		 */
		found_page = find_get_page(swapper_space, entry.val);
		if (found_page)
			break;

		/*
		 * Get a new page to read into from swap.
		 */
		if (!new_page) {
			new_page = alloc_page(GFP_KERNEL);
			if (!new_page)
				break; /* Out of memory */
		}

		/*
		 * call radix_tree_preload() while we can wait.
		 */
		err = radix_tree_preload(GFP_KERNEL);
		if (err)
			break;

		/*
		 * Swap entry may have been freed since our caller observed it.
		 */
		err = swapcache_prepare(entry);
		if (err == -EEXIST) { /* seems racy */
			radix_tree_preload_end();
			continue;
		}
		if (err) { /* swp entry is obsolete ? */
			radix_tree_preload_end();
			break;
		}

		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
		__set_page_locked(new_page);
		SetPageSwapBacked(new_page);
		err = __add_to_swap_cache(new_page, entry);
		if (likely(!err)) {
			radix_tree_preload_end();
			lru_cache_add_anon(new_page);
			*retpage = new_page;
			return ZSWAP_SWAPCACHE_NEW;
		}
		radix_tree_preload_end();
		ClearPageSwapBacked(new_page);
		__clear_page_locked(new_page);
		/*
		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
		 * clear SWAP_HAS_CACHE flag.
		 */
		swapcache_free(entry, NULL);
	} while (err != -ENOMEM);

	if (new_page)
		page_cache_release(new_page);
	if (!found_page)
		return ZSWAP_SWAPCACHE_FAIL;
	*retpage = found_page;
	return ZSWAP_SWAPCACHE_EXIST;
}

/*
 * Attempts to free an entry by adding a page to the swap cache,
 * decompressing the entry data into the page, and issuing a
 * bio write to write the page back to the swap device.
 *
 * This can be thought of as a "resumed writeback" of the page
 * to the swap device.  We are basically resuming the same swap
 * writeback path that was intercepted with the frontswap_store()
 * in the first place.  After the page has been decompressed into
 * the swap cache, the compressed version stored by zswap can be
 * freed.
 */
static int zswap_writeback_entry(struct zbud_pool *pool, unsigned long handle)
{
	struct zswap_header *zhdr;
	swp_entry_t swpentry;
	struct zswap_tree *tree;
	pgoff_t offset;
	struct zswap_entry *entry;
	struct page *page;
	u8 *src, *dst;
	unsigned int dlen;
	int ret, refcount;
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_NONE,
	};

	/* extract swpentry from data */
	zhdr = zbud_map(pool, handle);
	swpentry = zhdr->swpentry; /* here */
	zbud_unmap(pool, handle);
	tree = zswap_trees[swp_type(swpentry)];
	offset = swp_offset(swpentry);
	BUG_ON(pool != tree->pool);

	/* find and ref zswap entry */
	spin_lock(&tree->lock);
	entry = zswap_rb_search(&tree->rbroot, offset);
	if (!entry) {
		/* entry was invalidated */
		spin_unlock(&tree->lock);
		return 0;
	}
	zswap_entry_get(entry);
	spin_unlock(&tree->lock);
	BUG_ON(offset != entry->offset);

	/* try to allocate swap cache page */
	switch (zswap_get_swap_cache_page(swpentry, &page)) {
	case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */
		ret = -ENOMEM;
		goto fail;

	case ZSWAP_SWAPCACHE_EXIST:
		/* page is already in the swap cache, ignore for now */
		page_cache_release(page);
		ret = -EEXIST;
		goto fail;

	case ZSWAP_SWAPCACHE_NEW: /* page is locked */
		/* decompress */
		dlen = PAGE_SIZE;
		src = (u8 *)zbud_map(tree->pool, entry->handle) +
			sizeof(struct zswap_header);
		dst = kmap_atomic(page);
		ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src,
				entry->length, dst, &dlen);
		kunmap_atomic(dst);
		zbud_unmap(tree->pool, entry->handle);
		BUG_ON(ret);
		BUG_ON(dlen != PAGE_SIZE);

		/* page is up to date */
		SetPageUptodate(page);
	}

	/* start writeback */
	__swap_writepage(page, &wbc, end_swap_bio_write);
	page_cache_release(page);
	zswap_written_back_pages++;

	spin_lock(&tree->lock);

	/* drop local reference */
	zswap_entry_put(entry);
	/* drop the initial reference from entry creation */
	refcount = zswap_entry_put(entry);

	/*
	 * There are three possible values for refcount here:
	 * (1) refcount is 1, load is in progress, unlink from rbtree,
	 *     load will free
	 * (2) refcount is 0, (normal case) entry is valid,
	 *     remove from rbtree and free entry
	 * (3) refcount is -1, invalidate happened during writeback,
	 *     free entry
	 */
	if (refcount >= 0) {
		/* no invalidate yet, remove from rbtree */
		rb_erase(&entry->rbnode, &tree->rbroot);
	}
	spin_unlock(&tree->lock);
	if (refcount <= 0) {
		/* free the entry */
		zswap_free_entry(tree, entry);
		return 0;
	}
	return -EAGAIN;

fail:
	spin_lock(&tree->lock);
	refcount = zswap_entry_put(entry);
	if (refcount <= 0) {
		/* invalidate happened, consider writeback as success */
		zswap_free_entry(tree, entry);
		ret = 0;
	}
	spin_unlock(&tree->lock);
	return ret;
}

/*********************************
* frontswap hooks
**********************************/
/* attempts to compress and store an single page */
static int zswap_frontswap_store(unsigned type, pgoff_t offset,
				struct page *page)
{
	struct zswap_tree *tree = zswap_trees[type];
	struct zswap_entry *entry, *dupentry;
	int ret;
	unsigned int dlen = PAGE_SIZE, len;
	unsigned long handle;
	char *buf;
	u8 *src, *dst;
	struct zswap_header *zhdr;

	if (!tree) {
		ret = -ENODEV;
		goto reject;
	}

	/* reclaim space if needed */
	if (zswap_is_full()) {
		zswap_pool_limit_hit++;
		if (zbud_reclaim_page(tree->pool, 8)) {
			zswap_reject_reclaim_fail++;
			ret = -ENOMEM;
			goto reject;
		}
	}

	/* allocate entry */
	entry = zswap_entry_cache_alloc(GFP_KERNEL);
	if (!entry) {
		zswap_reject_kmemcache_fail++;
		ret = -ENOMEM;
		goto reject;
	}

	/* compress */
	dst = get_cpu_var(zswap_dstmem);
	src = kmap_atomic(page);
	ret = zswap_comp_op(ZSWAP_COMPOP_COMPRESS, src, PAGE_SIZE, dst, &dlen);
	kunmap_atomic(src);
	if (ret) {
		ret = -EINVAL;
		goto freepage;
	}

	/* store */
	len = dlen + sizeof(struct zswap_header);
	ret = zbud_alloc(tree->pool, len, __GFP_NORETRY | __GFP_NOWARN,
		&handle);
	if (ret == -ENOSPC) {
		zswap_reject_compress_poor++;
		goto freepage;
	}
	if (ret) {
		zswap_reject_alloc_fail++;
		goto freepage;
	}
	zhdr = zbud_map(tree->pool, handle);
	zhdr->swpentry = swp_entry(type, offset);
	buf = (u8 *)(zhdr + 1);
	memcpy(buf, dst, dlen);
	zbud_unmap(tree->pool, handle);
	put_cpu_var(zswap_dstmem);

	/* populate entry */
	entry->offset = offset;
	entry->handle = handle;
	entry->length = dlen;

	/* map */
	spin_lock(&tree->lock);
	do {
		ret = zswap_rb_insert(&tree->rbroot, entry, &dupentry);
		if (ret == -EEXIST) {
			zswap_duplicate_entry++;
			/* remove from rbtree */
			rb_erase(&dupentry->rbnode, &tree->rbroot);
			if (!zswap_entry_put(dupentry)) {
				/* free */
				zswap_free_entry(tree, dupentry);
			}
		}
	} while (ret == -EEXIST);
	spin_unlock(&tree->lock);

	/* update stats */
	atomic_inc(&zswap_stored_pages);
	zswap_pool_pages = zbud_get_pool_size(tree->pool);

	return 0;

freepage:
	put_cpu_var(zswap_dstmem);
	zswap_entry_cache_free(entry);
reject:
	return ret;
}

/*
 * returns 0 if the page was successfully decompressed
 * return -1 on entry not found or error
*/
static int zswap_frontswap_load(unsigned type, pgoff_t offset,
				struct page *page)
{
	struct zswap_tree *tree = zswap_trees[type];
	struct zswap_entry *entry;
	u8 *src, *dst;
	unsigned int dlen;
	int refcount, ret;

	/* find */
	spin_lock(&tree->lock);
	entry = zswap_rb_search(&tree->rbroot, offset);
	if (!entry) {
		/* entry was written back */
		spin_unlock(&tree->lock);
		return -1;
	}
	zswap_entry_get(entry);
	spin_unlock(&tree->lock);

	/* decompress */
	dlen = PAGE_SIZE;
	src = (u8 *)zbud_map(tree->pool, entry->handle) +
			sizeof(struct zswap_header);
	dst = kmap_atomic(page);
	ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length,
		dst, &dlen);
	kunmap_atomic(dst);
	zbud_unmap(tree->pool, entry->handle);
	BUG_ON(ret);

	spin_lock(&tree->lock);
	refcount = zswap_entry_put(entry);
	if (likely(refcount)) {
		spin_unlock(&tree->lock);
		return 0;
	}
	spin_unlock(&tree->lock);

	/*
	 * We don't have to unlink from the rbtree because
	 * zswap_writeback_entry() or zswap_frontswap_invalidate page()
	 * has already done this for us if we are the last reference.
	 */
	/* free */

	zswap_free_entry(tree, entry);

	return 0;
}

/* frees an entry in zswap */
static void zswap_frontswap_invalidate_page(unsigned type, pgoff_t offset)
{
	struct zswap_tree *tree = zswap_trees[type];
	struct zswap_entry *entry;
	int refcount;

	/* find */
	spin_lock(&tree->lock);
	entry = zswap_rb_search(&tree->rbroot, offset);
	if (!entry) {
		/* entry was written back */
		spin_unlock(&tree->lock);
		return;
	}

	/* remove from rbtree */
	rb_erase(&entry->rbnode, &tree->rbroot);

	/* drop the initial reference from entry creation */
	refcount = zswap_entry_put(entry);

	spin_unlock(&tree->lock);

	if (refcount) {
		/* writeback in progress, writeback will free */
		return;
	}

	/* free */
	zswap_free_entry(tree, entry);
}

/* frees all zswap entries for the given swap type */
static void zswap_frontswap_invalidate_area(unsigned type)
{
	struct zswap_tree *tree = zswap_trees[type];
	struct zswap_entry *entry, *n;

	if (!tree)
		return;

	/* walk the tree and free everything */
	spin_lock(&tree->lock);
	rbtree_postorder_for_each_entry_safe(entry, n, &tree->rbroot, rbnode) {
		zbud_free(tree->pool, entry->handle);
		zswap_entry_cache_free(entry);
		atomic_dec(&zswap_stored_pages);
	}
	tree->rbroot = RB_ROOT;
	spin_unlock(&tree->lock);

	zbud_destroy_pool(tree->pool);
	kfree(tree);
	zswap_trees[type] = NULL;
}

static struct zbud_ops zswap_zbud_ops = {
	.evict = zswap_writeback_entry
};

static void zswap_frontswap_init(unsigned type)
{
	struct zswap_tree *tree;

	tree = kzalloc(sizeof(struct zswap_tree), GFP_KERNEL);
	if (!tree)
		goto err;
	tree->pool = zbud_create_pool(GFP_KERNEL, &zswap_zbud_ops);
	if (!tree->pool)
		goto freetree;
	tree->rbroot = RB_ROOT;
	spin_lock_init(&tree->lock);
	zswap_trees[type] = tree;
	return;

freetree:
	kfree(tree);
err:
	pr_err("alloc failed, zswap disabled for swap type %d\n", type);
}

static struct frontswap_ops zswap_frontswap_ops = {
	.store = zswap_frontswap_store,
	.load = zswap_frontswap_load,
	.invalidate_page = zswap_frontswap_invalidate_page,
	.invalidate_area = zswap_frontswap_invalidate_area,
	.init = zswap_frontswap_init
};

/*********************************
* debugfs functions
**********************************/
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>

static struct dentry *zswap_debugfs_root;

static int __init zswap_debugfs_init(void)
{
	if (!debugfs_initialized())
		return -ENODEV;

	zswap_debugfs_root = debugfs_create_dir("zswap", NULL);
	if (!zswap_debugfs_root)
		return -ENOMEM;

	debugfs_create_u64("pool_limit_hit", S_IRUGO,
			zswap_debugfs_root, &zswap_pool_limit_hit);
	debugfs_create_u64("reject_reclaim_fail", S_IRUGO,
			zswap_debugfs_root, &zswap_reject_reclaim_fail);
	debugfs_create_u64("reject_alloc_fail", S_IRUGO,
			zswap_debugfs_root, &zswap_reject_alloc_fail);
	debugfs_create_u64("reject_kmemcache_fail", S_IRUGO,
			zswap_debugfs_root, &zswap_reject_kmemcache_fail);
	debugfs_create_u64("reject_compress_poor", S_IRUGO,
			zswap_debugfs_root, &zswap_reject_compress_poor);
	debugfs_create_u64("written_back_pages", S_IRUGO,
			zswap_debugfs_root, &zswap_written_back_pages);
	debugfs_create_u64("duplicate_entry", S_IRUGO,
			zswap_debugfs_root, &zswap_duplicate_entry);
	debugfs_create_u64("pool_pages", S_IRUGO,
			zswap_debugfs_root, &zswap_pool_pages);
	debugfs_create_atomic_t("stored_pages", S_IRUGO,
			zswap_debugfs_root, &zswap_stored_pages);

	return 0;
}

static void __exit zswap_debugfs_exit(void)
{
	debugfs_remove_recursive(zswap_debugfs_root);
}
#else
static int __init zswap_debugfs_init(void)
{
	return 0;
}

static void __exit zswap_debugfs_exit(void) { }
#endif

/*********************************
* module init and exit
**********************************/
static int __init init_zswap(void)
{
	if (!zswap_enabled)
		return 0;

	pr_info("loading zswap\n");
	if (zswap_entry_cache_create()) {
		pr_err("entry cache creation failed\n");
		goto error;
	}
	if (zswap_comp_init()) {
		pr_err("compressor initialization failed\n");
		goto compfail;
	}
	if (zswap_cpu_init()) {
		pr_err("per-cpu initialization failed\n");
		goto pcpufail;
	}
	frontswap_register_ops(&zswap_frontswap_ops);
	if (zswap_debugfs_init())
		pr_warn("debugfs initialization failed\n");
	return 0;
pcpufail:
	zswap_comp_exit();
compfail:
	zswap_entry_cache_destory();
error:
	return -ENOMEM;
}
/* must be late so crypto has time to come up */
late_initcall(init_zswap);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Seth Jennings <sjenning@linux.vnet.ibm.com>");
MODULE_DESCRIPTION("Compressed cache for swap pages");