Free Electrons

Embedded Linux Experts

   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
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
/*
 * 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

#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/backing-dev.h>
#include <linux/string.h>
#include <linux/vmalloc.h>
#include <linux/err.h>
#include <linux/idr.h>
#include <linux/sysfs.h>
#include <linux/cpuhotplug.h>

#include "zram_drv.h"

static DEFINE_IDR(zram_index_idr);
/* idr index must be protected */
static DEFINE_MUTEX(zram_index_mutex);

static int zram_major;
static const char *default_compressor = "lzo";

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

static void zram_free_page(struct zram *zram, size_t index);

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 unsigned long zram_get_handle(struct zram *zram, u32 index)
{
	return zram->table[index].handle;
}

static void zram_set_handle(struct zram *zram, u32 index, unsigned long handle)
{
	zram->table[index].handle = handle;
}

/* flag operations require table entry bit_spin_lock() being held */
static int zram_test_flag(struct zram *zram, u32 index,
			enum zram_pageflags flag)
{
	return zram->table[index].value & BIT(flag);
}

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

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

static inline void zram_set_element(struct zram *zram, u32 index,
			unsigned long element)
{
	zram->table[index].element = element;
}

static unsigned long zram_get_element(struct zram *zram, u32 index)
{
	return zram->table[index].element;
}

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

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

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

#if PAGE_SIZE != 4096
static inline bool is_partial_io(struct bio_vec *bvec)
{
	return bvec->bv_len != PAGE_SIZE;
}
#else
static inline bool is_partial_io(struct bio_vec *bvec)
{
	return false;
}
#endif

static void zram_revalidate_disk(struct zram *zram)
{
	revalidate_disk(zram->disk);
	/* revalidate_disk reset the BDI_CAP_STABLE_WRITES so set again */
	zram->disk->queue->backing_dev_info->capabilities |=
		BDI_CAP_STABLE_WRITES;
}

/*
 * Check if request is within bounds and aligned on zram logical blocks.
 */
static inline bool 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 false;
	if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
		return false;

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

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

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

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 inline void zram_fill_page(void *ptr, unsigned long len,
					unsigned long value)
{
	WARN_ON_ONCE(!IS_ALIGNED(len, sizeof(unsigned long)));
	memset_l(ptr, value, len / sizeof(unsigned long));
}

static bool page_same_filled(void *ptr, unsigned long *element)
{
	unsigned int pos;
	unsigned long *page;
	unsigned long val;

	page = (unsigned long *)ptr;
	val = page[0];

	for (pos = 1; pos < PAGE_SIZE / sizeof(*page); pos++) {
		if (val != page[pos])
			return false;
	}

	*element = val;

	return true;
}

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 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 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_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)) {
		atomic_long_set(&zram->stats.max_used_pages,
				zs_get_total_pages(zram->mem_pool));
	}
	up_read(&zram->init_lock);

	return len;
}

#ifdef CONFIG_ZRAM_WRITEBACK
static bool zram_wb_enabled(struct zram *zram)
{
	return zram->backing_dev;
}

static void reset_bdev(struct zram *zram)
{
	struct block_device *bdev;

	if (!zram_wb_enabled(zram))
		return;

	bdev = zram->bdev;
	if (zram->old_block_size)
		set_blocksize(bdev, zram->old_block_size);
	blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
	/* hope filp_close flush all of IO */
	filp_close(zram->backing_dev, NULL);
	zram->backing_dev = NULL;
	zram->old_block_size = 0;
	zram->bdev = NULL;

	kvfree(zram->bitmap);
	zram->bitmap = NULL;
}

static ssize_t backing_dev_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct zram *zram = dev_to_zram(dev);
	struct file *file = zram->backing_dev;
	char *p;
	ssize_t ret;

	down_read(&zram->init_lock);
	if (!zram_wb_enabled(zram)) {
		memcpy(buf, "none\n", 5);
		up_read(&zram->init_lock);
		return 5;
	}

	p = file_path(file, buf, PAGE_SIZE - 1);
	if (IS_ERR(p)) {
		ret = PTR_ERR(p);
		goto out;
	}

	ret = strlen(p);
	memmove(buf, p, ret);
	buf[ret++] = '\n';
out:
	up_read(&zram->init_lock);
	return ret;
}

static ssize_t backing_dev_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	char *file_name;
	struct file *backing_dev = NULL;
	struct inode *inode;
	struct address_space *mapping;
	unsigned int bitmap_sz, old_block_size = 0;
	unsigned long nr_pages, *bitmap = NULL;
	struct block_device *bdev = NULL;
	int err;
	struct zram *zram = dev_to_zram(dev);

	file_name = kmalloc(PATH_MAX, GFP_KERNEL);
	if (!file_name)
		return -ENOMEM;

	down_write(&zram->init_lock);
	if (init_done(zram)) {
		pr_info("Can't setup backing device for initialized device\n");
		err = -EBUSY;
		goto out;
	}

	strlcpy(file_name, buf, len);

	backing_dev = filp_open(file_name, O_RDWR|O_LARGEFILE, 0);
	if (IS_ERR(backing_dev)) {
		err = PTR_ERR(backing_dev);
		backing_dev = NULL;
		goto out;
	}

	mapping = backing_dev->f_mapping;
	inode = mapping->host;

	/* Support only block device in this moment */
	if (!S_ISBLK(inode->i_mode)) {
		err = -ENOTBLK;
		goto out;
	}

	bdev = bdgrab(I_BDEV(inode));
	err = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram);
	if (err < 0)
		goto out;

	nr_pages = i_size_read(inode) >> PAGE_SHIFT;
	bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long);
	bitmap = kvzalloc(bitmap_sz, GFP_KERNEL);
	if (!bitmap) {
		err = -ENOMEM;
		goto out;
	}

	old_block_size = block_size(bdev);
	err = set_blocksize(bdev, PAGE_SIZE);
	if (err)
		goto out;

	reset_bdev(zram);
	spin_lock_init(&zram->bitmap_lock);

	zram->old_block_size = old_block_size;
	zram->bdev = bdev;
	zram->backing_dev = backing_dev;
	zram->bitmap = bitmap;
	zram->nr_pages = nr_pages;
	up_write(&zram->init_lock);

	pr_info("setup backing device %s\n", file_name);
	kfree(file_name);

	return len;
out:
	if (bitmap)
		kvfree(bitmap);

	if (bdev)
		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);

	if (backing_dev)
		filp_close(backing_dev, NULL);

	up_write(&zram->init_lock);

	kfree(file_name);

	return err;
}

static unsigned long get_entry_bdev(struct zram *zram)
{
	unsigned long entry;

	spin_lock(&zram->bitmap_lock);
	/* skip 0 bit to confuse zram.handle = 0 */
	entry = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1);
	if (entry == zram->nr_pages) {
		spin_unlock(&zram->bitmap_lock);
		return 0;
	}

	set_bit(entry, zram->bitmap);
	spin_unlock(&zram->bitmap_lock);

	return entry;
}

static void put_entry_bdev(struct zram *zram, unsigned long entry)
{
	int was_set;

	spin_lock(&zram->bitmap_lock);
	was_set = test_and_clear_bit(entry, zram->bitmap);
	spin_unlock(&zram->bitmap_lock);
	WARN_ON_ONCE(!was_set);
}

void zram_page_end_io(struct bio *bio)
{
	struct page *page = bio->bi_io_vec[0].bv_page;

	page_endio(page, op_is_write(bio_op(bio)),
			blk_status_to_errno(bio->bi_status));
	bio_put(bio);
}

/*
 * Returns 1 if the submission is successful.
 */
static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
			unsigned long entry, struct bio *parent)
{
	struct bio *bio;

	bio = bio_alloc(GFP_ATOMIC, 1);
	if (!bio)
		return -ENOMEM;

	bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
	bio_set_dev(bio, zram->bdev);
	if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) {
		bio_put(bio);
		return -EIO;
	}

	if (!parent) {
		bio->bi_opf = REQ_OP_READ;
		bio->bi_end_io = zram_page_end_io;
	} else {
		bio->bi_opf = parent->bi_opf;
		bio_chain(bio, parent);
	}

	submit_bio(bio);
	return 1;
}

struct zram_work {
	struct work_struct work;
	struct zram *zram;
	unsigned long entry;
	struct bio *bio;
};

#if PAGE_SIZE != 4096
static void zram_sync_read(struct work_struct *work)
{
	struct bio_vec bvec;
	struct zram_work *zw = container_of(work, struct zram_work, work);
	struct zram *zram = zw->zram;
	unsigned long entry = zw->entry;
	struct bio *bio = zw->bio;

	read_from_bdev_async(zram, &bvec, entry, bio);
}

/*
 * Block layer want one ->make_request_fn to be active at a time
 * so if we use chained IO with parent IO in same context,
 * it's a deadlock. To avoid, it, it uses worker thread context.
 */
static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
				unsigned long entry, struct bio *bio)
{
	struct zram_work work;

	work.zram = zram;
	work.entry = entry;
	work.bio = bio;

	INIT_WORK_ONSTACK(&work.work, zram_sync_read);
	queue_work(system_unbound_wq, &work.work);
	flush_work(&work.work);
	destroy_work_on_stack(&work.work);

	return 1;
}
#else
static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
				unsigned long entry, struct bio *bio)
{
	WARN_ON(1);
	return -EIO;
}
#endif

static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
			unsigned long entry, struct bio *parent, bool sync)
{
	if (sync)
		return read_from_bdev_sync(zram, bvec, entry, parent);
	else
		return read_from_bdev_async(zram, bvec, entry, parent);
}

static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
					u32 index, struct bio *parent,
					unsigned long *pentry)
{
	struct bio *bio;
	unsigned long entry;

	bio = bio_alloc(GFP_ATOMIC, 1);
	if (!bio)
		return -ENOMEM;

	entry = get_entry_bdev(zram);
	if (!entry) {
		bio_put(bio);
		return -ENOSPC;
	}

	bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
	bio_set_dev(bio, zram->bdev);
	if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len,
					bvec->bv_offset)) {
		bio_put(bio);
		put_entry_bdev(zram, entry);
		return -EIO;
	}

	if (!parent) {
		bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
		bio->bi_end_io = zram_page_end_io;
	} else {
		bio->bi_opf = parent->bi_opf;
		bio_chain(bio, parent);
	}

	submit_bio(bio);
	*pentry = entry;

	return 0;
}

static void zram_wb_clear(struct zram *zram, u32 index)
{
	unsigned long entry;

	zram_clear_flag(zram, index, ZRAM_WB);
	entry = zram_get_element(zram, index);
	zram_set_element(zram, index, 0);
	put_entry_bdev(zram, entry);
}

#else
static bool zram_wb_enabled(struct zram *zram) { return false; }
static inline void reset_bdev(struct zram *zram) {};
static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
					u32 index, struct bio *parent,
					unsigned long *pentry)

{
	return -EIO;
}

static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
			unsigned long entry, struct bio *parent, bool sync)
{
	return -EIO;
}
static void zram_wb_clear(struct zram *zram, u32 index) {}
#endif


/*
 * We switched to per-cpu streams and this attr is not needed anymore.
 * However, we will keep it around for some time, because:
 * a) we may revert per-cpu streams in the future
 * b) it's visible to user space and we need to follow our 2 years
 *    retirement rule; but we already have a number of 'soon to be
 *    altered' attrs, so max_comp_streams need to wait for the next
 *    layoff cycle.
 */
static ssize_t max_comp_streams_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	return scnprintf(buf, PAGE_SIZE, "%d\n", num_online_cpus());
}

static ssize_t max_comp_streams_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	return len;
}

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);
	char compressor[ARRAY_SIZE(zram->compressor)];
	size_t sz;

	strlcpy(compressor, buf, sizeof(compressor));
	/* ignore trailing newline */
	sz = strlen(compressor);
	if (sz > 0 && compressor[sz - 1] == '\n')
		compressor[sz - 1] = 0x00;

	if (!zcomp_available_algorithm(compressor))
		return -EINVAL;

	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;
	}

	strcpy(zram->compressor, compressor);
	up_write(&zram->init_lock);
	return len;
}

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

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

	zs_compact(zram->mem_pool);
	up_read(&zram->init_lock);

	return len;
}

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);
	struct zs_pool_stats pool_stats;
	u64 orig_size, mem_used = 0;
	long max_used;
	ssize_t ret;

	memset(&pool_stats, 0x00, sizeof(struct zs_pool_stats));

	down_read(&zram->init_lock);
	if (init_done(zram)) {
		mem_used = zs_get_total_pages(zram->mem_pool);
		zs_pool_stats(zram->mem_pool, &pool_stats);
	}

	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 %8lu\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.same_pages),
			pool_stats.pages_compacted);
	up_read(&zram->init_lock);

	return ret;
}

static ssize_t debug_stat_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	int version = 1;
	struct zram *zram = dev_to_zram(dev);
	ssize_t ret;

	down_read(&zram->init_lock);
	ret = scnprintf(buf, PAGE_SIZE,
			"version: %d\n%8llu\n",
			version,
			(u64)atomic64_read(&zram->stats.writestall));
	up_read(&zram->init_lock);

	return ret;
}

static DEVICE_ATTR_RO(io_stat);
static DEVICE_ATTR_RO(mm_stat);
static DEVICE_ATTR_RO(debug_stat);

static void zram_slot_lock(struct zram *zram, u32 index)
{
	bit_spin_lock(ZRAM_ACCESS, &zram->table[index].value);
}

static void zram_slot_unlock(struct zram *zram, u32 index)
{
	bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value);
}

static void zram_meta_free(struct zram *zram, 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++)
		zram_free_page(zram, index);

	zs_destroy_pool(zram->mem_pool);
	vfree(zram->table);
}

static bool zram_meta_alloc(struct zram *zram, u64 disksize)
{
	size_t num_pages;

	num_pages = disksize >> PAGE_SHIFT;
	zram->table = vzalloc(num_pages * sizeof(*zram->table));
	if (!zram->table)
		return false;

	zram->mem_pool = zs_create_pool(zram->disk->disk_name);
	if (!zram->mem_pool) {
		vfree(zram->table);
		return false;
	}

	return true;
}

/*
 * 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)
{
	unsigned long handle;

	if (zram_wb_enabled(zram) && zram_test_flag(zram, index, ZRAM_WB)) {
		zram_wb_clear(zram, index);
		atomic64_dec(&zram->stats.pages_stored);
		return;
	}

	/*
	 * No memory is allocated for same element filled pages.
	 * Simply clear same page flag.
	 */
	if (zram_test_flag(zram, index, ZRAM_SAME)) {
		zram_clear_flag(zram, index, ZRAM_SAME);
		zram_set_element(zram, index, 0);
		atomic64_dec(&zram->stats.same_pages);
		atomic64_dec(&zram->stats.pages_stored);
		return;
	}

	handle = zram_get_handle(zram, index);
	if (!handle)
		return;

	zs_free(zram->mem_pool, handle);

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

	zram_set_handle(zram, index, 0);
	zram_set_obj_size(zram, index, 0);
}

static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
				struct bio *bio, bool partial_io)
{
	int ret;
	unsigned long handle;
	unsigned int size;
	void *src, *dst;

	if (zram_wb_enabled(zram)) {
		zram_slot_lock(zram, index);
		if (zram_test_flag(zram, index, ZRAM_WB)) {
			struct bio_vec bvec;

			zram_slot_unlock(zram, index);

			bvec.bv_page = page;
			bvec.bv_len = PAGE_SIZE;
			bvec.bv_offset = 0;
			return read_from_bdev(zram, &bvec,
					zram_get_element(zram, index),
					bio, partial_io);
		}
		zram_slot_unlock(zram, index);
	}

	zram_slot_lock(zram, index);
	handle = zram_get_handle(zram, index);
	if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) {
		unsigned long value;
		void *mem;

		value = handle ? zram_get_element(zram, index) : 0;
		mem = kmap_atomic(page);
		zram_fill_page(mem, PAGE_SIZE, value);
		kunmap_atomic(mem);
		zram_slot_unlock(zram, index);
		return 0;
	}

	size = zram_get_obj_size(zram, index);

	src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
	if (size == PAGE_SIZE) {
		dst = kmap_atomic(page);
		memcpy(dst, src, PAGE_SIZE);
		kunmap_atomic(dst);
		ret = 0;
	} else {
		struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);

		dst = kmap_atomic(page);
		ret = zcomp_decompress(zstrm, src, size, dst);
		kunmap_atomic(dst);
		zcomp_stream_put(zram->comp);
	}
	zs_unmap_object(zram->mem_pool, handle);
	zram_slot_unlock(zram, index);

	/* 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;
}

static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
				u32 index, int offset, struct bio *bio)
{
	int ret;
	struct page *page;

	page = bvec->bv_page;
	if (is_partial_io(bvec)) {
		/* Use a temporary buffer to decompress the page */
		page = alloc_page(GFP_NOIO|__GFP_HIGHMEM);
		if (!page)
			return -ENOMEM;
	}

	ret = __zram_bvec_read(zram, page, index, bio, is_partial_io(bvec));
	if (unlikely(ret))
		goto out;

	if (is_partial_io(bvec)) {
		void *dst = kmap_atomic(bvec->bv_page);
		void *src = kmap_atomic(page);

		memcpy(dst + bvec->bv_offset, src + offset, bvec->bv_len);
		kunmap_atomic(src);
		kunmap_atomic(dst);
	}
out:
	if (is_partial_io(bvec))
		__free_page(page);

	return ret;
}

static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
				u32 index, struct bio *bio)
{
	int ret = 0;
	unsigned long alloced_pages;
	unsigned long handle = 0;
	unsigned int comp_len = 0;
	void *src, *dst, *mem;
	struct zcomp_strm *zstrm;
	struct page *page = bvec->bv_page;
	unsigned long element = 0;
	enum zram_pageflags flags = 0;
	bool allow_wb = true;

	mem = kmap_atomic(page);
	if (page_same_filled(mem, &element)) {
		kunmap_atomic(mem);
		/* Free memory associated with this sector now. */
		flags = ZRAM_SAME;
		atomic64_inc(&zram->stats.same_pages);
		goto out;
	}
	kunmap_atomic(mem);

compress_again:
	zstrm = zcomp_stream_get(zram->comp);
	src = kmap_atomic(page);
	ret = zcomp_compress(zstrm, src, &comp_len);
	kunmap_atomic(src);

	if (unlikely(ret)) {
		zcomp_stream_put(zram->comp);
		pr_err("Compression failed! err=%d\n", ret);
		zs_free(zram->mem_pool, handle);
		return ret;
	}

	if (unlikely(comp_len > max_zpage_size)) {
		if (zram_wb_enabled(zram) && allow_wb) {
			zcomp_stream_put(zram->comp);
			ret = write_to_bdev(zram, bvec, index, bio, &element);
			if (!ret) {
				flags = ZRAM_WB;
				ret = 1;
				goto out;
			}
			allow_wb = false;
			goto compress_again;
		}
		comp_len = PAGE_SIZE;
	}

	/*
	 * handle allocation has 2 paths:
	 * a) fast path is executed with preemption disabled (for
	 *  per-cpu streams) and has __GFP_DIRECT_RECLAIM bit clear,
	 *  since we can't sleep;
	 * b) slow path enables preemption and attempts to allocate
	 *  the page with __GFP_DIRECT_RECLAIM bit set. we have to
	 *  put per-cpu compression stream and, thus, to re-do
	 *  the compression once handle is allocated.
	 *
	 * if we have a 'non-null' handle here then we are coming
	 * from the slow path and handle has already been allocated.
	 */
	if (!handle)
		handle = zs_malloc(zram->mem_pool, comp_len,
				__GFP_KSWAPD_RECLAIM |
				__GFP_NOWARN |
				__GFP_HIGHMEM |
				__GFP_MOVABLE);
	if (!handle) {
		zcomp_stream_put(zram->comp);
		atomic64_inc(&zram->stats.writestall);
		handle = zs_malloc(zram->mem_pool, comp_len,
				GFP_NOIO | __GFP_HIGHMEM |
				__GFP_MOVABLE);
		if (handle)
			goto compress_again;
		return -ENOMEM;
	}

	alloced_pages = zs_get_total_pages(zram->mem_pool);
	update_used_max(zram, alloced_pages);

	if (zram->limit_pages && alloced_pages > zram->limit_pages) {
		zcomp_stream_put(zram->comp);
		zs_free(zram->mem_pool, handle);
		return -ENOMEM;
	}

	dst = zs_map_object(zram->mem_pool, handle, ZS_MM_WO);

	src = zstrm->buffer;
	if (comp_len == PAGE_SIZE)
		src = kmap_atomic(page);
	memcpy(dst, src, comp_len);
	if (comp_len == PAGE_SIZE)
		kunmap_atomic(src);

	zcomp_stream_put(zram->comp);
	zs_unmap_object(zram->mem_pool, handle);
	atomic64_add(comp_len, &zram->stats.compr_data_size);
out:
	/*
	 * Free memory associated with this sector
	 * before overwriting unused sectors.
	 */
	zram_slot_lock(zram, index);
	zram_free_page(zram, index);

	if (flags) {
		zram_set_flag(zram, index, flags);
		zram_set_element(zram, index, element);
	}  else {
		zram_set_handle(zram, index, handle);
		zram_set_obj_size(zram, index, comp_len);
	}
	zram_slot_unlock(zram, index);

	/* Update stats */
	atomic64_inc(&zram->stats.pages_stored);
	return ret;
}

static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
				u32 index, int offset, struct bio *bio)
{
	int ret;
	struct page *page = NULL;
	void *src;
	struct bio_vec vec;

	vec = *bvec;
	if (is_partial_io(bvec)) {
		void *dst;
		/*
		 * This is a partial IO. We need to read the full page
		 * before to write the changes.
		 */
		page = alloc_page(GFP_NOIO|__GFP_HIGHMEM);
		if (!page)
			return -ENOMEM;

		ret = __zram_bvec_read(zram, page, index, bio, true);
		if (ret)
			goto out;

		src = kmap_atomic(bvec->bv_page);
		dst = kmap_atomic(page);
		memcpy(dst + offset, src + bvec->bv_offset, bvec->bv_len);
		kunmap_atomic(dst);
		kunmap_atomic(src);

		vec.bv_page = page;
		vec.bv_len = PAGE_SIZE;
		vec.bv_offset = 0;
	}

	ret = __zram_bvec_write(zram, &vec, index, bio);
out:
	if (is_partial_io(bvec))
		__free_page(page);
	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;

	/*
	 * 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) {
		zram_slot_lock(zram, index);
		zram_free_page(zram, index);
		zram_slot_unlock(zram, index);
		atomic64_inc(&zram->stats.notify_free);
		index++;
		n -= PAGE_SIZE;
	}
}

/*
 * Returns errno if it has some problem. Otherwise return 0 or 1.
 * Returns 0 if IO request was done synchronously
 * Returns 1 if IO request was successfully submitted.
 */
static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
			int offset, bool is_write, struct bio *bio)
{
	unsigned long start_time = jiffies;
	int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ;
	struct request_queue *q = zram->disk->queue;
	int ret;

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

	if (!is_write) {
		atomic64_inc(&zram->stats.num_reads);
		ret = zram_bvec_read(zram, bvec, index, offset, bio);
		flush_dcache_page(bvec->bv_page);
	} else {
		atomic64_inc(&zram->stats.num_writes);
		ret = zram_bvec_write(zram, bvec, index, offset, bio);
	}

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

	if (unlikely(ret < 0)) {
		if (!is_write)
			atomic64_inc(&zram->stats.failed_reads);
		else
			atomic64_inc(&zram->stats.failed_writes);
	}

	return ret;
}

static void __zram_make_request(struct zram *zram, struct bio *bio)
{
	int offset;
	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;

	switch (bio_op(bio)) {
	case REQ_OP_DISCARD:
	case REQ_OP_WRITE_ZEROES:
		zram_bio_discard(zram, index, offset, bio);
		bio_endio(bio);
		return;
	default:
		break;
	}

	bio_for_each_segment(bvec, bio, iter) {
		struct bio_vec bv = bvec;
		unsigned int unwritten = bvec.bv_len;

		do {
			bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset,
							unwritten);
			if (zram_bvec_rw(zram, &bv, index, offset,
					op_is_write(bio_op(bio)), bio) < 0)
				goto out;

			bv.bv_offset += bv.bv_len;
			unwritten -= bv.bv_len;

			update_position(&index, &offset, &bv);
		} while (unwritten);
	}

	bio_endio(bio);
	return;

out:
	bio_io_error(bio);
}

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

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

	__zram_make_request(zram, bio);
	return BLK_QC_T_NONE;

error:
	bio_io_error(bio);
	return BLK_QC_T_NONE;
}

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

	zram = bdev->bd_disk->private_data;

	zram_slot_lock(zram, index);
	zram_free_page(zram, index);
	zram_slot_unlock(zram, index);
	atomic64_inc(&zram->stats.notify_free);
}

static int zram_rw_page(struct block_device *bdev, sector_t sector,
		       struct page *page, bool is_write)
{
	int offset, ret;
	u32 index;
	struct zram *zram;
	struct bio_vec bv;

	if (PageTransHuge(page))
		return -ENOTSUPP;
	zram = bdev->bd_disk->private_data;

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

	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;

	ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL);
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 (unlikely(ret < 0))
		return ret;

	switch (ret) {
	case 0:
		page_endio(page, is_write, 0);
		break;
	case 1:
		ret = 0;
		break;
	default:
		WARN_ON(1);
	}
	return ret;
}

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

	down_write(&zram->init_lock);

	zram->limit_pages = 0;

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

	comp = zram->comp;
	disksize = zram->disksize;
	zram->disksize = 0;

	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(zram, disksize);
	memset(&zram->stats, 0, sizeof(zram->stats));
	zcomp_destroy(comp);
	reset_bdev(zram);
}

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 *zram = dev_to_zram(dev);
	int err;

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

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

	disksize = PAGE_ALIGN(disksize);
	if (!zram_meta_alloc(zram, disksize)) {
		err = -ENOMEM;
		goto out_unlock;
	}

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

	zram->comp = comp;
	zram->disksize = disksize;
	set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
	zram_revalidate_disk(zram);
	up_write(&zram->init_lock);

	return len;

out_free_meta:
	zram_meta_free(zram, disksize);
out_unlock:
	up_write(&zram->init_lock);
	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;

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

	if (!do_reset)
		return -EINVAL;

	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 or claimed device */
	if (bdev->bd_openers || zram->claim) {
		mutex_unlock(&bdev->bd_mutex);
		bdput(bdev);
		return -EBUSY;
	}

	/* From now on, anyone can't open /dev/zram[0-9] */
	zram->claim = true;
	mutex_unlock(&bdev->bd_mutex);

	/* Make sure all the pending I/O are finished */
	fsync_bdev(bdev);
	zram_reset_device(zram);
	zram_revalidate_disk(zram);
	bdput(bdev);

	mutex_lock(&bdev->bd_mutex);
	zram->claim = false;
	mutex_unlock(&bdev->bd_mutex);

	return len;
}

static int zram_open(struct block_device *bdev, fmode_t mode)
{
	int ret = 0;
	struct zram *zram;

	WARN_ON(!mutex_is_locked(&bdev->bd_mutex));

	zram = bdev->bd_disk->private_data;
	/* zram was claimed to reset so open request fails */
	if (zram->claim)
		ret = -EBUSY;

	return ret;
}

static const struct block_device_operations zram_devops = {
	.open = zram_open,
	.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_WO(mem_limit);
static DEVICE_ATTR_WO(mem_used_max);
static DEVICE_ATTR_RW(max_comp_streams);
static DEVICE_ATTR_RW(comp_algorithm);
#ifdef CONFIG_ZRAM_WRITEBACK
static DEVICE_ATTR_RW(backing_dev);
#endif

static struct attribute *zram_disk_attrs[] = {
	&dev_attr_disksize.attr,
	&dev_attr_initstate.attr,
	&dev_attr_reset.attr,
	&dev_attr_compact.attr,
	&dev_attr_mem_limit.attr,
	&dev_attr_mem_used_max.attr,
	&dev_attr_max_comp_streams.attr,
	&dev_attr_comp_algorithm.attr,
#ifdef CONFIG_ZRAM_WRITEBACK
	&dev_attr_backing_dev.attr,
#endif
	&dev_attr_io_stat.attr,
	&dev_attr_mm_stat.attr,
	&dev_attr_debug_stat.attr,
	NULL,
};

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

/*
 * Allocate and initialize new zram device. the function returns
 * '>= 0' device_id upon success, and negative value otherwise.
 */
static int zram_add(void)
{
	struct zram *zram;
	struct request_queue *queue;
	int ret, device_id;

	zram = kzalloc(sizeof(struct zram), GFP_KERNEL);
	if (!zram)
		return -ENOMEM;

	ret = idr_alloc(&zram_index_idr, zram, 0, 0, GFP_KERNEL);
	if (ret < 0)
		goto out_free_dev;
	device_id = ret;

	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);
		ret = -ENOMEM;
		goto out_free_idr;
	}

	blk_queue_make_request(queue, zram_make_request);

	/* gendisk structure */
	zram->disk = alloc_disk(1);
	if (!zram->disk) {
		pr_err("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;
	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);

	/*
	 * 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)
		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);

	add_disk(zram->disk);

	ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj,
				&zram_disk_attr_group);
	if (ret < 0) {
		pr_err("Error creating sysfs group for device %d\n",
				device_id);
		goto out_free_disk;
	}
	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));

	pr_info("Added device: %s\n", zram->disk->disk_name);
	return device_id;

out_free_disk:
	del_gendisk(zram->disk);
	put_disk(zram->disk);
out_free_queue:
	blk_cleanup_queue(queue);
out_free_idr:
	idr_remove(&zram_index_idr, device_id);
out_free_dev:
	kfree(zram);
	return ret;
}

static int zram_remove(struct zram *zram)
{
	struct block_device *bdev;

	bdev = bdget_disk(zram->disk, 0);
	if (!bdev)
		return -ENOMEM;

	mutex_lock(&bdev->bd_mutex);
	if (bdev->bd_openers || zram->claim) {
		mutex_unlock(&bdev->bd_mutex);
		bdput(bdev);
		return -EBUSY;
	}

	zram->claim = true;
	mutex_unlock(&bdev->bd_mutex);

	/*
	 * Remove sysfs first, so no one will perform a disksize
	 * store while we destroy the devices. This also helps during
	 * hot_remove -- zram_reset_device() is the last holder of
	 * ->init_lock, no later/concurrent disksize_store() or any
	 * other sysfs handlers are possible.
	 */
	sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
			&zram_disk_attr_group);

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

	pr_info("Removed device: %s\n", zram->disk->disk_name);

	blk_cleanup_queue(zram->disk->queue);
	del_gendisk(zram->disk);
	put_disk(zram->disk);
	kfree(zram);
	return 0;
}

/* zram-control sysfs attributes */

/*
 * NOTE: hot_add attribute is not the usual read-only sysfs attribute. In a
 * sense that reading from this file does alter the state of your system -- it
 * creates a new un-initialized zram device and returns back this device's
 * device_id (or an error code if it fails to create a new device).
 */
static ssize_t hot_add_show(struct class *class,
			struct class_attribute *attr,
			char *buf)
{
	int ret;

	mutex_lock(&zram_index_mutex);
	ret = zram_add();
	mutex_unlock(&zram_index_mutex);

	if (ret < 0)
		return ret;
	return scnprintf(buf, PAGE_SIZE, "%d\n", ret);
}
static CLASS_ATTR_RO(hot_add);

static ssize_t hot_remove_store(struct class *class,
			struct class_attribute *attr,
			const char *buf,
			size_t count)
{
	struct zram *zram;
	int ret, dev_id;

	/* dev_id is gendisk->first_minor, which is `int' */
	ret = kstrtoint(buf, 10, &dev_id);
	if (ret)
		return ret;
	if (dev_id < 0)
		return -EINVAL;

	mutex_lock(&zram_index_mutex);

	zram = idr_find(&zram_index_idr, dev_id);
	if (zram) {
		ret = zram_remove(zram);
		if (!ret)
			idr_remove(&zram_index_idr, dev_id);
	} else {
		ret = -ENODEV;
	}

	mutex_unlock(&zram_index_mutex);
	return ret ? ret : count;
}
static CLASS_ATTR_WO(hot_remove);

static struct attribute *zram_control_class_attrs[] = {
	&class_attr_hot_add.attr,
	&class_attr_hot_remove.attr,
	NULL,
};
ATTRIBUTE_GROUPS(zram_control_class);

static struct class zram_control_class = {
	.name		= "zram-control",
	.owner		= THIS_MODULE,
	.class_groups	= zram_control_class_groups,
};

static int zram_remove_cb(int id, void *ptr, void *data)
{
	zram_remove(ptr);
	return 0;
}

static void destroy_devices(void)
{
	class_unregister(&zram_control_class);
	idr_for_each(&zram_index_idr, &zram_remove_cb, NULL);
	idr_destroy(&zram_index_idr);
	unregister_blkdev(zram_major, "zram");
	cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
}

static int __init zram_init(void)
{
	int ret;

	ret = cpuhp_setup_state_multi(CPUHP_ZCOMP_PREPARE, "block/zram:prepare",
				      zcomp_cpu_up_prepare, zcomp_cpu_dead);
	if (ret < 0)
		return ret;

	ret = class_register(&zram_control_class);
	if (ret) {
		pr_err("Unable to register zram-control class\n");
		cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
		return ret;
	}

	zram_major = register_blkdev(0, "zram");
	if (zram_major <= 0) {
		pr_err("Unable to get major number\n");
		class_unregister(&zram_control_class);
		cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
		return -EBUSY;
	}

	while (num_devices != 0) {
		mutex_lock(&zram_index_mutex);
		ret = zram_add();
		mutex_unlock(&zram_index_mutex);
		if (ret < 0)
			goto out_error;
		num_devices--;
	}

	return 0;

out_error:
	destroy_devices();
	return ret;
}

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

module_init(zram_init);
module_exit(zram_exit);

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

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