summaryrefslogtreecommitdiffstats
path: root/kernel/drivers/block/zram/zram_drv.c
blob: 6e134f4759c0c9e98b93f221e7687004d4418342 (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
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
/*
 * Compressed RAM block device
 *
 * Copyright (C) 2008, 2009, 2010  Nitin Gupta
 *               2012, 2013 Minchan Kim
 *
 * This code is released using a dual license strategy: BSD/GPL
 * You can choose the licence that better fits your requirements.
 *
 * Released under the terms of 3-clause BSD License
 * Released under the terms of GNU General Public License Version 2.0
 *
 */

#define KMSG_COMPONENT "zram"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

#ifdef CONFIG_ZRAM_DEBUG
#define DEBUG
#endif

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/device.h>
#include <linux/genhd.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/vmalloc.h>
#include <linux/err.h>

#include "zram_drv.h"

/* Globals */
static int zram_major;
static struct zram *zram_devices;
static const char *default_compressor = "lzo";

/* Module params (documentation at end) */
static unsigned int num_devices = 1;

static inline void deprecated_attr_warn(const char *name)
{
	pr_warn_once("%d (%s) Attribute %s (and others) will be removed. %s\n",
			task_pid_nr(current),
			current->comm,
			name,
			"See zram documentation.");
}

#define ZRAM_ATTR_RO(name)						\
static ssize_t name##_show(struct device *d,		\
				struct device_attribute *attr, char *b)	\
{									\
	struct zram *zram = dev_to_zram(d);				\
									\
	deprecated_attr_warn(__stringify(name));			\
	return scnprintf(b, PAGE_SIZE, "%llu\n",			\
		(u64)atomic64_read(&zram->stats.name));			\
}									\
static DEVICE_ATTR_RO(name);

static inline bool init_done(struct zram *zram)
{
	return zram->disksize;
}

static inline struct zram *dev_to_zram(struct device *dev)
{
	return (struct zram *)dev_to_disk(dev)->private_data;
}

static ssize_t compact_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	unsigned long nr_migrated;
	struct zram *zram = dev_to_zram(dev);
	struct zram_meta *meta;

	down_read(&zram->init_lock);
	if (!init_done(zram)) {
		up_read(&zram->init_lock);
		return -EINVAL;
	}

	meta = zram->meta;
	nr_migrated = zs_compact(meta->mem_pool);
	atomic64_add(nr_migrated, &zram->stats.num_migrated);
	up_read(&zram->init_lock);

	return len;
}

static ssize_t disksize_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct zram *zram = dev_to_zram(dev);

	return scnprintf(buf, PAGE_SIZE, "%llu\n", zram->disksize);
}

static ssize_t initstate_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	u32 val;
	struct zram *zram = dev_to_zram(dev);

	down_read(&zram->init_lock);
	val = init_done(zram);
	up_read(&zram->init_lock);

	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
}

static ssize_t orig_data_size_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct zram *zram = dev_to_zram(dev);

	deprecated_attr_warn("orig_data_size");
	return scnprintf(buf, PAGE_SIZE, "%llu\n",
		(u64)(atomic64_read(&zram->stats.pages_stored)) << PAGE_SHIFT);
}

static ssize_t mem_used_total_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	u64 val = 0;
	struct zram *zram = dev_to_zram(dev);

	deprecated_attr_warn("mem_used_total");
	down_read(&zram->init_lock);
	if (init_done(zram)) {
		struct zram_meta *meta = zram->meta;
		val = zs_get_total_pages(meta->mem_pool);
	}
	up_read(&zram->init_lock);

	return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
}

static ssize_t max_comp_streams_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	int val;
	struct zram *zram = dev_to_zram(dev);

	down_read(&zram->init_lock);
	val = zram->max_comp_streams;
	up_read(&zram->init_lock);

	return scnprintf(buf, PAGE_SIZE, "%d\n", val);
}

static ssize_t mem_limit_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	u64 val;
	struct zram *zram = dev_to_zram(dev);

	deprecated_attr_warn("mem_limit");
	down_read(&zram->init_lock);
	val = zram->limit_pages;
	up_read(&zram->init_lock);

	return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
}

static ssize_t mem_limit_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	u64 limit;
	char *tmp;
	struct zram *zram = dev_to_zram(dev);

	limit = memparse(buf, &tmp);
	if (buf == tmp) /* no chars parsed, invalid input */
		return -EINVAL;

	down_write(&zram->init_lock);
	zram->limit_pages = PAGE_ALIGN(limit) >> PAGE_SHIFT;
	up_write(&zram->init_lock);

	return len;
}

static ssize_t mem_used_max_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	u64 val = 0;
	struct zram *zram = dev_to_zram(dev);

	deprecated_attr_warn("mem_used_max");
	down_read(&zram->init_lock);
	if (init_done(zram))
		val = atomic_long_read(&zram->stats.max_used_pages);
	up_read(&zram->init_lock);

	return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
}

static ssize_t mem_used_max_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	int err;
	unsigned long val;
	struct zram *zram = dev_to_zram(dev);

	err = kstrtoul(buf, 10, &val);
	if (err || val != 0)
		return -EINVAL;

	down_read(&zram->init_lock);
	if (init_done(zram)) {
		struct zram_meta *meta = zram->meta;
		atomic_long_set(&zram->stats.max_used_pages,
				zs_get_total_pages(meta->mem_pool));
	}
	up_read(&zram->init_lock);

	return len;
}

static ssize_t max_comp_streams_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	int num;
	struct zram *zram = dev_to_zram(dev);
	int ret;

	ret = kstrtoint(buf, 0, &num);
	if (ret < 0)
		return ret;
	if (num < 1)
		return -EINVAL;

	down_write(&zram->init_lock);
	if (init_done(zram)) {
		if (!zcomp_set_max_streams(zram->comp, num)) {
			pr_info("Cannot change max compression streams\n");
			ret = -EINVAL;
			goto out;
		}
	}

	zram->max_comp_streams = num;
	ret = len;
out:
	up_write(&zram->init_lock);
	return ret;
}

static ssize_t comp_algorithm_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	size_t sz;
	struct zram *zram = dev_to_zram(dev);

	down_read(&zram->init_lock);
	sz = zcomp_available_show(zram->compressor, buf);
	up_read(&zram->init_lock);

	return sz;
}

static ssize_t comp_algorithm_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	struct zram *zram = dev_to_zram(dev);
	down_write(&zram->init_lock);
	if (init_done(zram)) {
		up_write(&zram->init_lock);
		pr_info("Can't change algorithm for initialized device\n");
		return -EBUSY;
	}
	strlcpy(zram->compressor, buf, sizeof(zram->compressor));
	up_write(&zram->init_lock);
	return len;
}

/* flag operations needs meta->tb_lock */
static int zram_test_flag(struct zram_meta *meta, u32 index,
			enum zram_pageflags flag)
{
	return meta->table[index].value & BIT(flag);
}

static void zram_set_flag(struct zram_meta *meta, u32 index,
			enum zram_pageflags flag)
{
	meta->table[index].value |= BIT(flag);
}

static void zram_clear_flag(struct zram_meta *meta, u32 index,
			enum zram_pageflags flag)
{
	meta->table[index].value &= ~BIT(flag);
}

static size_t zram_get_obj_size(struct zram_meta *meta, u32 index)
{
	return meta->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1);
}

static void zram_set_obj_size(struct zram_meta *meta,
					u32 index, size_t size)
{
	unsigned long flags = meta->table[index].value >> ZRAM_FLAG_SHIFT;

	meta->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size;
}

static inline int is_partial_io(struct bio_vec *bvec)
{
	return bvec->bv_len != PAGE_SIZE;
}

/*
 * Check if request is within bounds and aligned on zram logical blocks.
 */
static inline int valid_io_request(struct zram *zram,
		sector_t start, unsigned int size)
{
	u64 end, bound;

	/* unaligned request */
	if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
		return 0;
	if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
		return 0;

	end = start + (size >> SECTOR_SHIFT);
	bound = zram->disksize >> SECTOR_SHIFT;
	/* out of range range */
	if (unlikely(start >= bound || end > bound || start > end))
		return 0;

	/* I/O request is valid */
	return 1;
}

static void zram_meta_free(struct zram_meta *meta, u64 disksize)
{
	size_t num_pages = disksize >> PAGE_SHIFT;
	size_t index;

	/* Free all pages that are still in this zram device */
	for (index = 0; index < num_pages; index++) {
		unsigned long handle = meta->table[index].handle;

		if (!handle)
			continue;

		zs_free(meta->mem_pool, handle);
	}

	zs_destroy_pool(meta->mem_pool);
	vfree(meta->table);
	kfree(meta);
}

static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize)
{
	size_t num_pages;
	char pool_name[8];
	struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);

	if (!meta)
		return NULL;

	num_pages = disksize >> PAGE_SHIFT;
	meta->table = vzalloc(num_pages * sizeof(*meta->table));
	if (!meta->table) {
		pr_err("Error allocating zram address table\n");
		goto out_error;
	}

	snprintf(pool_name, sizeof(pool_name), "zram%d", device_id);
	meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO | __GFP_HIGHMEM);
	if (!meta->mem_pool) {
		pr_err("Error creating memory pool\n");
		goto out_error;
	}

	return meta;

out_error:
	vfree(meta->table);
	kfree(meta);
	return NULL;
}

static inline bool zram_meta_get(struct zram *zram)
{
	if (atomic_inc_not_zero(&zram->refcount))
		return true;
	return false;
}

static inline void zram_meta_put(struct zram *zram)
{
	atomic_dec(&zram->refcount);
}

static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
{
	if (*offset + bvec->bv_len >= PAGE_SIZE)
		(*index)++;
	*offset = (*offset + bvec->bv_len) % PAGE_SIZE;
}

static int page_zero_filled(void *ptr)
{
	unsigned int pos;
	unsigned long *page;

	page = (unsigned long *)ptr;

	for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
		if (page[pos])
			return 0;
	}

	return 1;
}

static void handle_zero_page(struct bio_vec *bvec)
{
	struct page *page = bvec->bv_page;
	void *user_mem;

	user_mem = kmap_atomic(page);
	if (is_partial_io(bvec))
		memset(user_mem + bvec->bv_offset, 0, bvec->bv_len);
	else
		clear_page(user_mem);
	kunmap_atomic(user_mem);

	flush_dcache_page(page);
}


/*
 * To protect concurrent access to the same index entry,
 * caller should hold this table index entry's bit_spinlock to
 * indicate this index entry is accessing.
 */
static void zram_free_page(struct zram *zram, size_t index)
{
	struct zram_meta *meta = zram->meta;
	unsigned long handle = meta->table[index].handle;

	if (unlikely(!handle)) {
		/*
		 * No memory is allocated for zero filled pages.
		 * Simply clear zero page flag.
		 */
		if (zram_test_flag(meta, index, ZRAM_ZERO)) {
			zram_clear_flag(meta, index, ZRAM_ZERO);
			atomic64_dec(&zram->stats.zero_pages);
		}
		return;
	}

	zs_free(meta->mem_pool, handle);

	atomic64_sub(zram_get_obj_size(meta, index),
			&zram->stats.compr_data_size);
	atomic64_dec(&zram->stats.pages_stored);

	meta->table[index].handle = 0;
	zram_set_obj_size(meta, index, 0);
}

static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
{
	int ret = 0;
	unsigned char *cmem;
	struct zram_meta *meta = zram->meta;
	unsigned long handle;
	size_t size;

	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
	handle = meta->table[index].handle;
	size = zram_get_obj_size(meta, index);

	if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
		clear_page(mem);
		return 0;
	}

	cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
	if (size == PAGE_SIZE)
		copy_page(mem, cmem);
	else
		ret = zcomp_decompress(zram->comp, cmem, size, mem);
	zs_unmap_object(meta->mem_pool, handle);
	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);

	/* Should NEVER happen. Return bio error if it does. */
	if (unlikely(ret)) {
		pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
		return ret;
	}

	return 0;
}

static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
			  u32 index, int offset)
{
	int ret;
	struct page *page;
	unsigned char *user_mem, *uncmem = NULL;
	struct zram_meta *meta = zram->meta;
	page = bvec->bv_page;

	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
	if (unlikely(!meta->table[index].handle) ||
			zram_test_flag(meta, index, ZRAM_ZERO)) {
		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
		handle_zero_page(bvec);
		return 0;
	}
	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);

	if (is_partial_io(bvec))
		/* Use  a temporary buffer to decompress the page */
		uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);

	user_mem = kmap_atomic(page);
	if (!is_partial_io(bvec))
		uncmem = user_mem;

	if (!uncmem) {
		pr_info("Unable to allocate temp memory\n");
		ret = -ENOMEM;
		goto out_cleanup;
	}

	ret = zram_decompress_page(zram, uncmem, index);
	/* Should NEVER happen. Return bio error if it does. */
	if (unlikely(ret))
		goto out_cleanup;

	if (is_partial_io(bvec))
		memcpy(user_mem + bvec->bv_offset, uncmem + offset,
				bvec->bv_len);

	flush_dcache_page(page);
	ret = 0;
out_cleanup:
	kunmap_atomic(user_mem);
	if (is_partial_io(bvec))
		kfree(uncmem);
	return ret;
}

static inline void update_used_max(struct zram *zram,
					const unsigned long pages)
{
	unsigned long old_max, cur_max;

	old_max = atomic_long_read(&zram->stats.max_used_pages);

	do {
		cur_max = old_max;
		if (pages > cur_max)
			old_max = atomic_long_cmpxchg(
				&zram->stats.max_used_pages, cur_max, pages);
	} while (old_max != cur_max);
}

static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
			   int offset)
{
	int ret = 0;
	size_t clen;
	unsigned long handle;
	struct page *page;
	unsigned char *user_mem, *cmem, *src, *uncmem = NULL;
	struct zram_meta *meta = zram->meta;
	struct zcomp_strm *zstrm;
	bool locked = false;
	unsigned long alloced_pages;

	page = bvec->bv_page;
	if (is_partial_io(bvec)) {
		/*
		 * This is a partial IO. We need to read the full page
		 * before to write the changes.
		 */
		uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
		if (!uncmem) {
			ret = -ENOMEM;
			goto out;
		}
		ret = zram_decompress_page(zram, uncmem, index);
		if (ret)
			goto out;
	}

	zstrm = zcomp_strm_find(zram->comp);
	locked = true;
	user_mem = kmap_atomic(page);

	if (is_partial_io(bvec)) {
		memcpy(uncmem + offset, user_mem + bvec->bv_offset,
		       bvec->bv_len);
		kunmap_atomic(user_mem);
		user_mem = NULL;
	} else {
		uncmem = user_mem;
	}

	if (page_zero_filled(uncmem)) {
		if (user_mem)
			kunmap_atomic(user_mem);
		/* Free memory associated with this sector now. */
		bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
		zram_free_page(zram, index);
		zram_set_flag(meta, index, ZRAM_ZERO);
		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);

		atomic64_inc(&zram->stats.zero_pages);
		ret = 0;
		goto out;
	}

	ret = zcomp_compress(zram->comp, zstrm, uncmem, &clen);
	if (!is_partial_io(bvec)) {
		kunmap_atomic(user_mem);
		user_mem = NULL;
		uncmem = NULL;
	}

	if (unlikely(ret)) {
		pr_err("Compression failed! err=%d\n", ret);
		goto out;
	}
	src = zstrm->buffer;
	if (unlikely(clen > max_zpage_size)) {
		clen = PAGE_SIZE;
		if (is_partial_io(bvec))
			src = uncmem;
	}

	handle = zs_malloc(meta->mem_pool, clen);
	if (!handle) {
		pr_info("Error allocating memory for compressed page: %u, size=%zu\n",
			index, clen);
		ret = -ENOMEM;
		goto out;
	}

	alloced_pages = zs_get_total_pages(meta->mem_pool);
	if (zram->limit_pages && alloced_pages > zram->limit_pages) {
		zs_free(meta->mem_pool, handle);
		ret = -ENOMEM;
		goto out;
	}

	update_used_max(zram, alloced_pages);

	cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);

	if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
		src = kmap_atomic(page);
		copy_page(cmem, src);
		kunmap_atomic(src);
	} else {
		memcpy(cmem, src, clen);
	}

	zcomp_strm_release(zram->comp, zstrm);
	locked = false;
	zs_unmap_object(meta->mem_pool, handle);

	/*
	 * Free memory associated with this sector
	 * before overwriting unused sectors.
	 */
	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
	zram_free_page(zram, index);

	meta->table[index].handle = handle;
	zram_set_obj_size(meta, index, clen);
	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);

	/* Update stats */
	atomic64_add(clen, &zram->stats.compr_data_size);
	atomic64_inc(&zram->stats.pages_stored);
out:
	if (locked)
		zcomp_strm_release(zram->comp, zstrm);
	if (is_partial_io(bvec))
		kfree(uncmem);
	return ret;
}

static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
			int offset, int rw)
{
	unsigned long start_time = jiffies;
	int ret;

	generic_start_io_acct(rw, bvec->bv_len >> SECTOR_SHIFT,
			&zram->disk->part0);

	if (rw == READ) {
		atomic64_inc(&zram->stats.num_reads);
		ret = zram_bvec_read(zram, bvec, index, offset);
	} else {
		atomic64_inc(&zram->stats.num_writes);
		ret = zram_bvec_write(zram, bvec, index, offset);
	}

	generic_end_io_acct(rw, &zram->disk->part0, start_time);

	if (unlikely(ret)) {
		if (rw == READ)
			atomic64_inc(&zram->stats.failed_reads);
		else
			atomic64_inc(&zram->stats.failed_writes);
	}

	return ret;
}

/*
 * zram_bio_discard - handler on discard request
 * @index: physical block index in PAGE_SIZE units
 * @offset: byte offset within physical block
 */
static void zram_bio_discard(struct zram *zram, u32 index,
			     int offset, struct bio *bio)
{
	size_t n = bio->bi_iter.bi_size;
	struct zram_meta *meta = zram->meta;

	/*
	 * zram manages data in physical block size units. Because logical block
	 * size isn't identical with physical block size on some arch, we
	 * could get a discard request pointing to a specific offset within a
	 * certain physical block.  Although we can handle this request by
	 * reading that physiclal block and decompressing and partially zeroing
	 * and re-compressing and then re-storing it, this isn't reasonable
	 * because our intent with a discard request is to save memory.  So
	 * skipping this logical block is appropriate here.
	 */
	if (offset) {
		if (n <= (PAGE_SIZE - offset))
			return;

		n -= (PAGE_SIZE - offset);
		index++;
	}

	while (n >= PAGE_SIZE) {
		bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
		zram_free_page(zram, index);
		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
		atomic64_inc(&zram->stats.notify_free);
		index++;
		n -= PAGE_SIZE;
	}
}

static void zram_reset_device(struct zram *zram)
{
	struct zram_meta *meta;
	struct zcomp *comp;
	u64 disksize;

	down_write(&zram->init_lock);

	zram->limit_pages = 0;

	if (!init_done(zram)) {
		up_write(&zram->init_lock);
		return;
	}

	meta = zram->meta;
	comp = zram->comp;
	disksize = zram->disksize;
	/*
	 * Refcount will go down to 0 eventually and r/w handler
	 * cannot handle further I/O so it will bail out by
	 * check zram_meta_get.
	 */
	zram_meta_put(zram);
	/*
	 * We want to free zram_meta in process context to avoid
	 * deadlock between reclaim path and any other locks.
	 */
	wait_event(zram->io_done, atomic_read(&zram->refcount) == 0);

	/* Reset stats */
	memset(&zram->stats, 0, sizeof(zram->stats));
	zram->disksize = 0;
	zram->max_comp_streams = 1;

	set_capacity(zram->disk, 0);
	part_stat_set_all(&zram->disk->part0, 0);

	up_write(&zram->init_lock);
	/* I/O operation under all of CPU are done so let's free */
	zram_meta_free(meta, disksize);
	zcomp_destroy(comp);
}

static ssize_t disksize_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	u64 disksize;
	struct zcomp *comp;
	struct zram_meta *meta;
	struct zram *zram = dev_to_zram(dev);
	int err;

	disksize = memparse(buf, NULL);
	if (!disksize)
		return -EINVAL;

	disksize = PAGE_ALIGN(disksize);
	meta = zram_meta_alloc(zram->disk->first_minor, disksize);
	if (!meta)
		return -ENOMEM;

	comp = zcomp_create(zram->compressor, zram->max_comp_streams);
	if (IS_ERR(comp)) {
		pr_info("Cannot initialise %s compressing backend\n",
				zram->compressor);
		err = PTR_ERR(comp);
		goto out_free_meta;
	}

	down_write(&zram->init_lock);
	if (init_done(zram)) {
		pr_info("Cannot change disksize for initialized device\n");
		err = -EBUSY;
		goto out_destroy_comp;
	}

	init_waitqueue_head(&zram->io_done);
	atomic_set(&zram->refcount, 1);
	zram->meta = meta;
	zram->comp = comp;
	zram->disksize = disksize;
	set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
	up_write(&zram->init_lock);

	/*
	 * Revalidate disk out of the init_lock to avoid lockdep splat.
	 * It's okay because disk's capacity is protected by init_lock
	 * so that revalidate_disk always sees up-to-date capacity.
	 */
	revalidate_disk(zram->disk);

	return len;

out_destroy_comp:
	up_write(&zram->init_lock);
	zcomp_destroy(comp);
out_free_meta:
	zram_meta_free(meta, disksize);
	return err;
}

static ssize_t reset_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	int ret;
	unsigned short do_reset;
	struct zram *zram;
	struct block_device *bdev;

	zram = dev_to_zram(dev);
	bdev = bdget_disk(zram->disk, 0);

	if (!bdev)
		return -ENOMEM;

	mutex_lock(&bdev->bd_mutex);
	/* Do not reset an active device! */
	if (bdev->bd_openers) {
		ret = -EBUSY;
		goto out;
	}

	ret = kstrtou16(buf, 10, &do_reset);
	if (ret)
		goto out;

	if (!do_reset) {
		ret = -EINVAL;
		goto out;
	}

	/* Make sure all pending I/O is finished */
	fsync_bdev(bdev);
	zram_reset_device(zram);

	mutex_unlock(&bdev->bd_mutex);
	revalidate_disk(zram->disk);
	bdput(bdev);

	return len;

out:
	mutex_unlock(&bdev->bd_mutex);
	bdput(bdev);
	return ret;
}

static void __zram_make_request(struct zram *zram, struct bio *bio)
{
	int offset, rw;
	u32 index;
	struct bio_vec bvec;
	struct bvec_iter iter;

	index = bio->bi_iter.bi_sector >> SECTORS_PER_PAGE_SHIFT;
	offset = (bio->bi_iter.bi_sector &
		  (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;

	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
		zram_bio_discard(zram, index, offset, bio);
		bio_endio(bio, 0);
		return;
	}

	rw = bio_data_dir(bio);
	bio_for_each_segment(bvec, bio, iter) {
		int max_transfer_size = PAGE_SIZE - offset;

		if (bvec.bv_len > max_transfer_size) {
			/*
			 * zram_bvec_rw() can only make operation on a single
			 * zram page. Split the bio vector.
			 */
			struct bio_vec bv;

			bv.bv_page = bvec.bv_page;
			bv.bv_len = max_transfer_size;
			bv.bv_offset = bvec.bv_offset;

			if (zram_bvec_rw(zram, &bv, index, offset, rw) < 0)
				goto out;

			bv.bv_len = bvec.bv_len - max_transfer_size;
			bv.bv_offset += max_transfer_size;
			if (zram_bvec_rw(zram, &bv, index + 1, 0, rw) < 0)
				goto out;
		} else
			if (zram_bvec_rw(zram, &bvec, index, offset, rw) < 0)
				goto out;

		update_position(&index, &offset, &bvec);
	}

	set_bit(BIO_UPTODATE, &bio->bi_flags);
	bio_endio(bio, 0);
	return;

out:
	bio_io_error(bio);
}

/*
 * Handler function for all zram I/O requests.
 */
static void zram_make_request(struct request_queue *queue, struct bio *bio)
{
	struct zram *zram = queue->queuedata;

	if (unlikely(!zram_meta_get(zram)))
		goto error;

	if (!valid_io_request(zram, bio->bi_iter.bi_sector,
					bio->bi_iter.bi_size)) {
		atomic64_inc(&zram->stats.invalid_io);
		goto put_zram;
	}

	__zram_make_request(zram, bio);
	zram_meta_put(zram);
	return;
put_zram:
	zram_meta_put(zram);
error:
	bio_io_error(bio);
}

static void zram_slot_free_notify(struct block_device *bdev,
				unsigned long index)
{
	struct zram *zram;
	struct zram_meta *meta;

	zram = bdev->bd_disk->private_data;
	meta = zram->meta;

	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
	zram_free_page(zram, index);
	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
	atomic64_inc(&zram->stats.notify_free);
}

static int zram_rw_page(struct block_device *bdev, sector_t sector,
		       struct page *page, int rw)
{
	int offset, err = -EIO;
	u32 index;
	struct zram *zram;
	struct bio_vec bv;

	zram = bdev->bd_disk->private_data;
	if (unlikely(!zram_meta_get(zram)))
		goto out;

	if (!valid_io_request(zram, sector, PAGE_SIZE)) {
		atomic64_inc(&zram->stats.invalid_io);
		err = -EINVAL;
		goto put_zram;
	}

	index = sector >> SECTORS_PER_PAGE_SHIFT;
	offset = sector & (SECTORS_PER_PAGE - 1) << SECTOR_SHIFT;

	bv.bv_page = page;
	bv.bv_len = PAGE_SIZE;
	bv.bv_offset = 0;

	err = zram_bvec_rw(zram, &bv, index, offset, rw);
put_zram:
	zram_meta_put(zram);
out:
	/*
	 * If I/O fails, just return error(ie, non-zero) without
	 * calling page_endio.
	 * It causes resubmit the I/O with bio request by upper functions
	 * of rw_page(e.g., swap_readpage, __swap_writepage) and
	 * bio->bi_end_io does things to handle the error
	 * (e.g., SetPageError, set_page_dirty and extra works).
	 */
	if (err == 0)
		page_endio(page, rw, 0);
	return err;
}

static const struct block_device_operations zram_devops = {
	.swap_slot_free_notify = zram_slot_free_notify,
	.rw_page = zram_rw_page,
	.owner = THIS_MODULE
};

static DEVICE_ATTR_WO(compact);
static DEVICE_ATTR_RW(disksize);
static DEVICE_ATTR_RO(initstate);
static DEVICE_ATTR_WO(reset);
static DEVICE_ATTR_RO(orig_data_size);
static DEVICE_ATTR_RO(mem_used_total);
static DEVICE_ATTR_RW(mem_limit);
static DEVICE_ATTR_RW(mem_used_max);
static DEVICE_ATTR_RW(max_comp_streams);
static DEVICE_ATTR_RW(comp_algorithm);

static ssize_t io_stat_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct zram *zram = dev_to_zram(dev);
	ssize_t ret;

	down_read(&zram->init_lock);
	ret = scnprintf(buf, PAGE_SIZE,
			"%8llu %8llu %8llu %8llu\n",
			(u64)atomic64_read(&zram->stats.failed_reads),
			(u64)atomic64_read(&zram->stats.failed_writes),
			(u64)atomic64_read(&zram->stats.invalid_io),
			(u64)atomic64_read(&zram->stats.notify_free));
	up_read(&zram->init_lock);

	return ret;
}

static ssize_t mm_stat_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct zram *zram = dev_to_zram(dev);
	u64 orig_size, mem_used = 0;
	long max_used;
	ssize_t ret;

	down_read(&zram->init_lock);
	if (init_done(zram))
		mem_used = zs_get_total_pages(zram->meta->mem_pool);

	orig_size = atomic64_read(&zram->stats.pages_stored);
	max_used = atomic_long_read(&zram->stats.max_used_pages);

	ret = scnprintf(buf, PAGE_SIZE,
			"%8llu %8llu %8llu %8lu %8ld %8llu %8llu\n",
			orig_size << PAGE_SHIFT,
			(u64)atomic64_read(&zram->stats.compr_data_size),
			mem_used << PAGE_SHIFT,
			zram->limit_pages << PAGE_SHIFT,
			max_used << PAGE_SHIFT,
			(u64)atomic64_read(&zram->stats.zero_pages),
			(u64)atomic64_read(&zram->stats.num_migrated));
	up_read(&zram->init_lock);

	return ret;
}

static DEVICE_ATTR_RO(io_stat);
static DEVICE_ATTR_RO(mm_stat);
ZRAM_ATTR_RO(num_reads);
ZRAM_ATTR_RO(num_writes);
ZRAM_ATTR_RO(failed_reads);
ZRAM_ATTR_RO(failed_writes);
ZRAM_ATTR_RO(invalid_io);
ZRAM_ATTR_RO(notify_free);
ZRAM_ATTR_RO(zero_pages);
ZRAM_ATTR_RO(compr_data_size);

static struct attribute *zram_disk_attrs[] = {
	&dev_attr_disksize.attr,
	&dev_attr_initstate.attr,
	&dev_attr_reset.attr,
	&dev_attr_num_reads.attr,
	&dev_attr_num_writes.attr,
	&dev_attr_failed_reads.attr,
	&dev_attr_failed_writes.attr,
	&dev_attr_compact.attr,
	&dev_attr_invalid_io.attr,
	&dev_attr_notify_free.attr,
	&dev_attr_zero_pages.attr,
	&dev_attr_orig_data_size.attr,
	&dev_attr_compr_data_size.attr,
	&dev_attr_mem_used_total.attr,
	&dev_attr_mem_limit.attr,
	&dev_attr_mem_used_max.attr,
	&dev_attr_max_comp_streams.attr,
	&dev_attr_comp_algorithm.attr,
	&dev_attr_io_stat.attr,
	&dev_attr_mm_stat.attr,
	NULL,
};

static struct attribute_group zram_disk_attr_group = {
	.attrs = zram_disk_attrs,
};

static int create_device(struct zram *zram, int device_id)
{
	struct request_queue *queue;
	int ret = -ENOMEM;

	init_rwsem(&zram->init_lock);

	queue = blk_alloc_queue(GFP_KERNEL);
	if (!queue) {
		pr_err("Error allocating disk queue for device %d\n",
			device_id);
		goto out;
	}

	blk_queue_make_request(queue, zram_make_request);

	 /* gendisk structure */
	zram->disk = alloc_disk(1);
	if (!zram->disk) {
		pr_warn("Error allocating disk structure for device %d\n",
			device_id);
		ret = -ENOMEM;
		goto out_free_queue;
	}

	zram->disk->major = zram_major;
	zram->disk->first_minor = device_id;
	zram->disk->fops = &zram_devops;
	zram->disk->queue = queue;
	zram->disk->queue->queuedata = zram;
	zram->disk->private_data = zram;
	snprintf(zram->disk->disk_name, 16, "zram%d", device_id);

	/* Actual capacity set using syfs (/sys/block/zram<id>/disksize */
	set_capacity(zram->disk, 0);
	/* zram devices sort of resembles non-rotational disks */
	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue);
	/*
	 * To ensure that we always get PAGE_SIZE aligned
	 * and n*PAGE_SIZED sized I/O requests.
	 */
	blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
	blk_queue_logical_block_size(zram->disk->queue,
					ZRAM_LOGICAL_BLOCK_SIZE);
	blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
	zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
	zram->disk->queue->limits.max_discard_sectors = UINT_MAX;
	/*
	 * zram_bio_discard() will clear all logical blocks if logical block
	 * size is identical with physical block size(PAGE_SIZE). But if it is
	 * different, we will skip discarding some parts of logical blocks in
	 * the part of the request range which isn't aligned to physical block
	 * size.  So we can't ensure that all discarded logical blocks are
	 * zeroed.
	 */
	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
		zram->disk->queue->limits.discard_zeroes_data = 1;
	else
		zram->disk->queue->limits.discard_zeroes_data = 0;
	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);

	add_disk(zram->disk);

	ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj,
				&zram_disk_attr_group);
	if (ret < 0) {
		pr_warn("Error creating sysfs group");
		goto out_free_disk;
	}
	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
	zram->meta = NULL;
	zram->max_comp_streams = 1;
	return 0;

out_free_disk:
	del_gendisk(zram->disk);
	put_disk(zram->disk);
out_free_queue:
	blk_cleanup_queue(queue);
out:
	return ret;
}

static void destroy_devices(unsigned int nr)
{
	struct zram *zram;
	unsigned int i;

	for (i = 0; i < nr; i++) {
		zram = &zram_devices[i];
		/*
		 * Remove sysfs first, so no one will perform a disksize
		 * store while we destroy the devices
		 */
		sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
				&zram_disk_attr_group);

		zram_reset_device(zram);

		blk_cleanup_queue(zram->disk->queue);
		del_gendisk(zram->disk);
		put_disk(zram->disk);
	}

	kfree(zram_devices);
	unregister_blkdev(zram_major, "zram");
	pr_info("Destroyed %u device(s)\n", nr);
}

static int __init zram_init(void)
{
	int ret, dev_id;

	if (num_devices > max_num_devices) {
		pr_warn("Invalid value for num_devices: %u\n",
				num_devices);
		return -EINVAL;
	}

	zram_major = register_blkdev(0, "zram");
	if (zram_major <= 0) {
		pr_warn("Unable to get major number\n");
		return -EBUSY;
	}

	/* Allocate the device array and initialize each one */
	zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
	if (!zram_devices) {
		unregister_blkdev(zram_major, "zram");
		return -ENOMEM;
	}

	for (dev_id = 0; dev_id < num_devices; dev_id++) {
		ret = create_device(&zram_devices[dev_id], dev_id);
		if (ret)
			goto out_error;
	}

	pr_info("Created %u device(s)\n", num_devices);
	return 0;

out_error:
	destroy_devices(dev_id);
	return ret;
}

static void __exit zram_exit(void)
{
	destroy_devices(num_devices);
}

module_init(zram_init);
module_exit(zram_exit);

module_param(num_devices, uint, 0);
MODULE_PARM_DESC(num_devices, "Number of zram devices");

MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
MODULE_DESCRIPTION("Compressed RAM Block Device");