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
/*
 * Copyright (C) 2012 Red Hat, Inc.
 *
 * This file is released under the GPL.
 */

#include "dm-cache-metadata.h"

#include "persistent-data/dm-array.h"
#include "persistent-data/dm-bitset.h"
#include "persistent-data/dm-space-map.h"
#include "persistent-data/dm-space-map-disk.h"
#include "persistent-data/dm-transaction-manager.h"

#include <linux/device-mapper.h>

/*----------------------------------------------------------------*/

#define DM_MSG_PREFIX   "cache metadata"

#define CACHE_SUPERBLOCK_MAGIC 06142003
#define CACHE_SUPERBLOCK_LOCATION 0
#define CACHE_VERSION 1
#define CACHE_METADATA_CACHE_SIZE 64

/*
 *  3 for btree insert +
 *  2 for btree lookup used within space map
 */
#define CACHE_MAX_CONCURRENT_LOCKS 5
#define SPACE_MAP_ROOT_SIZE 128

enum superblock_flag_bits {
	/* for spotting crashes that would invalidate the dirty bitset */
	CLEAN_SHUTDOWN,
};

/*
 * Each mapping from cache block -> origin block carries a set of flags.
 */
enum mapping_bits {
	/*
	 * A valid mapping.  Because we're using an array we clear this
	 * flag for an non existant mapping.
	 */
	M_VALID = 1,

	/*
	 * The data on the cache is different from that on the origin.
	 */
	M_DIRTY = 2
};

struct cache_disk_superblock {
	__le32 csum;
	__le32 flags;
	__le64 blocknr;

	__u8 uuid[16];
	__le64 magic;
	__le32 version;

	__u8 policy_name[CACHE_POLICY_NAME_SIZE];
	__le32 policy_hint_size;

	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
	__le64 mapping_root;
	__le64 hint_root;

	__le64 discard_root;
	__le64 discard_block_size;
	__le64 discard_nr_blocks;

	__le32 data_block_size;
	__le32 metadata_block_size;
	__le32 cache_blocks;

	__le32 compat_flags;
	__le32 compat_ro_flags;
	__le32 incompat_flags;

	__le32 read_hits;
	__le32 read_misses;
	__le32 write_hits;
	__le32 write_misses;

	__le32 policy_version[CACHE_POLICY_VERSION_SIZE];
} __packed;

struct dm_cache_metadata {
	struct block_device *bdev;
	struct dm_block_manager *bm;
	struct dm_space_map *metadata_sm;
	struct dm_transaction_manager *tm;

	struct dm_array_info info;
	struct dm_array_info hint_info;
	struct dm_disk_bitset discard_info;

	struct rw_semaphore root_lock;
	dm_block_t root;
	dm_block_t hint_root;
	dm_block_t discard_root;

	sector_t discard_block_size;
	dm_dblock_t discard_nr_blocks;

	sector_t data_block_size;
	dm_cblock_t cache_blocks;
	bool changed:1;
	bool clean_when_opened:1;

	char policy_name[CACHE_POLICY_NAME_SIZE];
	unsigned policy_version[CACHE_POLICY_VERSION_SIZE];
	size_t policy_hint_size;
	struct dm_cache_statistics stats;
};

/*-------------------------------------------------------------------
 * superblock validator
 *-----------------------------------------------------------------*/

#define SUPERBLOCK_CSUM_XOR 9031977

static void sb_prepare_for_write(struct dm_block_validator *v,
				 struct dm_block *b,
				 size_t sb_block_size)
{
	struct cache_disk_superblock *disk_super = dm_block_data(b);

	disk_super->blocknr = cpu_to_le64(dm_block_location(b));
	disk_super->csum = cpu_to_le32(dm_bm_checksum(&disk_super->flags,
						      sb_block_size - sizeof(__le32),
						      SUPERBLOCK_CSUM_XOR));
}

static int sb_check(struct dm_block_validator *v,
		    struct dm_block *b,
		    size_t sb_block_size)
{
	struct cache_disk_superblock *disk_super = dm_block_data(b);
	__le32 csum_le;

	if (dm_block_location(b) != le64_to_cpu(disk_super->blocknr)) {
		DMERR("sb_check failed: blocknr %llu: wanted %llu",
		      le64_to_cpu(disk_super->blocknr),
		      (unsigned long long)dm_block_location(b));
		return -ENOTBLK;
	}

	if (le64_to_cpu(disk_super->magic) != CACHE_SUPERBLOCK_MAGIC) {
		DMERR("sb_check failed: magic %llu: wanted %llu",
		      le64_to_cpu(disk_super->magic),
		      (unsigned long long)CACHE_SUPERBLOCK_MAGIC);
		return -EILSEQ;
	}

	csum_le = cpu_to_le32(dm_bm_checksum(&disk_super->flags,
					     sb_block_size - sizeof(__le32),
					     SUPERBLOCK_CSUM_XOR));
	if (csum_le != disk_super->csum) {
		DMERR("sb_check failed: csum %u: wanted %u",
		      le32_to_cpu(csum_le), le32_to_cpu(disk_super->csum));
		return -EILSEQ;
	}

	return 0;
}

static struct dm_block_validator sb_validator = {
	.name = "superblock",
	.prepare_for_write = sb_prepare_for_write,
	.check = sb_check
};

/*----------------------------------------------------------------*/

static int superblock_read_lock(struct dm_cache_metadata *cmd,
				struct dm_block **sblock)
{
	return dm_bm_read_lock(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
			       &sb_validator, sblock);
}

static int superblock_lock_zero(struct dm_cache_metadata *cmd,
				struct dm_block **sblock)
{
	return dm_bm_write_lock_zero(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
				     &sb_validator, sblock);
}

static int superblock_lock(struct dm_cache_metadata *cmd,
			   struct dm_block **sblock)
{
	return dm_bm_write_lock(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
				&sb_validator, sblock);
}

/*----------------------------------------------------------------*/

static int __superblock_all_zeroes(struct dm_block_manager *bm, int *result)
{
	int r;
	unsigned i;
	struct dm_block *b;
	__le64 *data_le, zero = cpu_to_le64(0);
	unsigned sb_block_size = dm_bm_block_size(bm) / sizeof(__le64);

	/*
	 * We can't use a validator here - it may be all zeroes.
	 */
	r = dm_bm_read_lock(bm, CACHE_SUPERBLOCK_LOCATION, NULL, &b);
	if (r)
		return r;

	data_le = dm_block_data(b);
	*result = 1;
	for (i = 0; i < sb_block_size; i++) {
		if (data_le[i] != zero) {
			*result = 0;
			break;
		}
	}

	return dm_bm_unlock(b);
}

static void __setup_mapping_info(struct dm_cache_metadata *cmd)
{
	struct dm_btree_value_type vt;

	vt.context = NULL;
	vt.size = sizeof(__le64);
	vt.inc = NULL;
	vt.dec = NULL;
	vt.equal = NULL;
	dm_array_info_init(&cmd->info, cmd->tm, &vt);

	if (cmd->policy_hint_size) {
		vt.size = sizeof(__le32);
		dm_array_info_init(&cmd->hint_info, cmd->tm, &vt);
	}
}

static int __write_initial_superblock(struct dm_cache_metadata *cmd)
{
	int r;
	struct dm_block *sblock;
	size_t metadata_len;
	struct cache_disk_superblock *disk_super;
	sector_t bdev_size = i_size_read(cmd->bdev->bd_inode) >> SECTOR_SHIFT;

	/* FIXME: see if we can lose the max sectors limit */
	if (bdev_size > DM_CACHE_METADATA_MAX_SECTORS)
		bdev_size = DM_CACHE_METADATA_MAX_SECTORS;

	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
	if (r < 0)
		return r;

	r = dm_tm_pre_commit(cmd->tm);
	if (r < 0)
		return r;

	r = superblock_lock_zero(cmd, &sblock);
	if (r)
		return r;

	disk_super = dm_block_data(sblock);
	disk_super->flags = 0;
	memset(disk_super->uuid, 0, sizeof(disk_super->uuid));
	disk_super->magic = cpu_to_le64(CACHE_SUPERBLOCK_MAGIC);
	disk_super->version = cpu_to_le32(CACHE_VERSION);
	memset(disk_super->policy_name, 0, sizeof(disk_super->policy_name));
	memset(disk_super->policy_version, 0, sizeof(disk_super->policy_version));
	disk_super->policy_hint_size = 0;

	r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root,
			    metadata_len);
	if (r < 0)
		goto bad_locked;

	disk_super->mapping_root = cpu_to_le64(cmd->root);
	disk_super->hint_root = cpu_to_le64(cmd->hint_root);
	disk_super->discard_root = cpu_to_le64(cmd->discard_root);
	disk_super->discard_block_size = cpu_to_le64(cmd->discard_block_size);
	disk_super->discard_nr_blocks = cpu_to_le64(from_dblock(cmd->discard_nr_blocks));
	disk_super->metadata_block_size = cpu_to_le32(DM_CACHE_METADATA_BLOCK_SIZE >> SECTOR_SHIFT);
	disk_super->data_block_size = cpu_to_le32(cmd->data_block_size);
	disk_super->cache_blocks = cpu_to_le32(0);

	disk_super->read_hits = cpu_to_le32(0);
	disk_super->read_misses = cpu_to_le32(0);
	disk_super->write_hits = cpu_to_le32(0);
	disk_super->write_misses = cpu_to_le32(0);

	return dm_tm_commit(cmd->tm, sblock);

bad_locked:
	dm_bm_unlock(sblock);
	return r;
}

static int __format_metadata(struct dm_cache_metadata *cmd)
{
	int r;

	r = dm_tm_create_with_sm(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
				 &cmd->tm, &cmd->metadata_sm);
	if (r < 0) {
		DMERR("tm_create_with_sm failed");
		return r;
	}

	__setup_mapping_info(cmd);

	r = dm_array_empty(&cmd->info, &cmd->root);
	if (r < 0)
		goto bad;

	dm_disk_bitset_init(cmd->tm, &cmd->discard_info);

	r = dm_bitset_empty(&cmd->discard_info, &cmd->discard_root);
	if (r < 0)
		goto bad;

	cmd->discard_block_size = 0;
	cmd->discard_nr_blocks = 0;

	r = __write_initial_superblock(cmd);
	if (r)
		goto bad;

	cmd->clean_when_opened = true;
	return 0;

bad:
	dm_tm_destroy(cmd->tm);
	dm_sm_destroy(cmd->metadata_sm);

	return r;
}

static int __check_incompat_features(struct cache_disk_superblock *disk_super,
				     struct dm_cache_metadata *cmd)
{
	uint32_t features;

	features = le32_to_cpu(disk_super->incompat_flags) & ~DM_CACHE_FEATURE_INCOMPAT_SUPP;
	if (features) {
		DMERR("could not access metadata due to unsupported optional features (%lx).",
		      (unsigned long)features);
		return -EINVAL;
	}

	/*
	 * Check for read-only metadata to skip the following RDWR checks.
	 */
	if (get_disk_ro(cmd->bdev->bd_disk))
		return 0;

	features = le32_to_cpu(disk_super->compat_ro_flags) & ~DM_CACHE_FEATURE_COMPAT_RO_SUPP;
	if (features) {
		DMERR("could not access metadata RDWR due to unsupported optional features (%lx).",
		      (unsigned long)features);
		return -EINVAL;
	}

	return 0;
}

static int __open_metadata(struct dm_cache_metadata *cmd)
{
	int r;
	struct dm_block *sblock;
	struct cache_disk_superblock *disk_super;
	unsigned long sb_flags;

	r = superblock_read_lock(cmd, &sblock);
	if (r < 0) {
		DMERR("couldn't read lock superblock");
		return r;
	}

	disk_super = dm_block_data(sblock);

	r = __check_incompat_features(disk_super, cmd);
	if (r < 0)
		goto bad;

	r = dm_tm_open_with_sm(cmd->bm, CACHE_SUPERBLOCK_LOCATION,
			       disk_super->metadata_space_map_root,
			       sizeof(disk_super->metadata_space_map_root),
			       &cmd->tm, &cmd->metadata_sm);
	if (r < 0) {
		DMERR("tm_open_with_sm failed");
		goto bad;
	}

	__setup_mapping_info(cmd);
	dm_disk_bitset_init(cmd->tm, &cmd->discard_info);
	sb_flags = le32_to_cpu(disk_super->flags);
	cmd->clean_when_opened = test_bit(CLEAN_SHUTDOWN, &sb_flags);
	return dm_bm_unlock(sblock);

bad:
	dm_bm_unlock(sblock);
	return r;
}

static int __open_or_format_metadata(struct dm_cache_metadata *cmd,
				     bool format_device)
{
	int r, unformatted;

	r = __superblock_all_zeroes(cmd->bm, &unformatted);
	if (r)
		return r;

	if (unformatted)
		return format_device ? __format_metadata(cmd) : -EPERM;

	return __open_metadata(cmd);
}

static int __create_persistent_data_objects(struct dm_cache_metadata *cmd,
					    bool may_format_device)
{
	int r;
	cmd->bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE,
					  CACHE_METADATA_CACHE_SIZE,
					  CACHE_MAX_CONCURRENT_LOCKS);
	if (IS_ERR(cmd->bm)) {
		DMERR("could not create block manager");
		return PTR_ERR(cmd->bm);
	}

	r = __open_or_format_metadata(cmd, may_format_device);
	if (r)
		dm_block_manager_destroy(cmd->bm);

	return r;
}

static void __destroy_persistent_data_objects(struct dm_cache_metadata *cmd)
{
	dm_sm_destroy(cmd->metadata_sm);
	dm_tm_destroy(cmd->tm);
	dm_block_manager_destroy(cmd->bm);
}

typedef unsigned long (*flags_mutator)(unsigned long);

static void update_flags(struct cache_disk_superblock *disk_super,
			 flags_mutator mutator)
{
	uint32_t sb_flags = mutator(le32_to_cpu(disk_super->flags));
	disk_super->flags = cpu_to_le32(sb_flags);
}

static unsigned long set_clean_shutdown(unsigned long flags)
{
	set_bit(CLEAN_SHUTDOWN, &flags);
	return flags;
}

static unsigned long clear_clean_shutdown(unsigned long flags)
{
	clear_bit(CLEAN_SHUTDOWN, &flags);
	return flags;
}

static void read_superblock_fields(struct dm_cache_metadata *cmd,
				   struct cache_disk_superblock *disk_super)
{
	cmd->root = le64_to_cpu(disk_super->mapping_root);
	cmd->hint_root = le64_to_cpu(disk_super->hint_root);
	cmd->discard_root = le64_to_cpu(disk_super->discard_root);
	cmd->discard_block_size = le64_to_cpu(disk_super->discard_block_size);
	cmd->discard_nr_blocks = to_dblock(le64_to_cpu(disk_super->discard_nr_blocks));
	cmd->data_block_size = le32_to_cpu(disk_super->data_block_size);
	cmd->cache_blocks = to_cblock(le32_to_cpu(disk_super->cache_blocks));
	strncpy(cmd->policy_name, disk_super->policy_name, sizeof(cmd->policy_name));
	cmd->policy_version[0] = le32_to_cpu(disk_super->policy_version[0]);
	cmd->policy_version[1] = le32_to_cpu(disk_super->policy_version[1]);
	cmd->policy_version[2] = le32_to_cpu(disk_super->policy_version[2]);
	cmd->policy_hint_size = le32_to_cpu(disk_super->policy_hint_size);

	cmd->stats.read_hits = le32_to_cpu(disk_super->read_hits);
	cmd->stats.read_misses = le32_to_cpu(disk_super->read_misses);
	cmd->stats.write_hits = le32_to_cpu(disk_super->write_hits);
	cmd->stats.write_misses = le32_to_cpu(disk_super->write_misses);

	cmd->changed = false;
}

/*
 * The mutator updates the superblock flags.
 */
static int __begin_transaction_flags(struct dm_cache_metadata *cmd,
				     flags_mutator mutator)
{
	int r;
	struct cache_disk_superblock *disk_super;
	struct dm_block *sblock;

	r = superblock_lock(cmd, &sblock);
	if (r)
		return r;

	disk_super = dm_block_data(sblock);
	update_flags(disk_super, mutator);
	read_superblock_fields(cmd, disk_super);

	return dm_bm_flush_and_unlock(cmd->bm, sblock);
}

static int __begin_transaction(struct dm_cache_metadata *cmd)
{
	int r;
	struct cache_disk_superblock *disk_super;
	struct dm_block *sblock;

	/*
	 * We re-read the superblock every time.  Shouldn't need to do this
	 * really.
	 */
	r = superblock_read_lock(cmd, &sblock);
	if (r)
		return r;

	disk_super = dm_block_data(sblock);
	read_superblock_fields(cmd, disk_super);
	dm_bm_unlock(sblock);

	return 0;
}

static int __commit_transaction(struct dm_cache_metadata *cmd,
				flags_mutator mutator)
{
	int r;
	size_t metadata_len;
	struct cache_disk_superblock *disk_super;
	struct dm_block *sblock;

	/*
	 * We need to know if the cache_disk_superblock exceeds a 512-byte sector.
	 */
	BUILD_BUG_ON(sizeof(struct cache_disk_superblock) > 512);

	r = dm_bitset_flush(&cmd->discard_info, cmd->discard_root,
			    &cmd->discard_root);
	if (r)
		return r;

	r = dm_tm_pre_commit(cmd->tm);
	if (r < 0)
		return r;

	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
	if (r < 0)
		return r;

	r = superblock_lock(cmd, &sblock);
	if (r)
		return r;

	disk_super = dm_block_data(sblock);

	if (mutator)
		update_flags(disk_super, mutator);

	disk_super->mapping_root = cpu_to_le64(cmd->root);
	disk_super->hint_root = cpu_to_le64(cmd->hint_root);
	disk_super->discard_root = cpu_to_le64(cmd->discard_root);
	disk_super->discard_block_size = cpu_to_le64(cmd->discard_block_size);
	disk_super->discard_nr_blocks = cpu_to_le64(from_dblock(cmd->discard_nr_blocks));
	disk_super->cache_blocks = cpu_to_le32(from_cblock(cmd->cache_blocks));
	strncpy(disk_super->policy_name, cmd->policy_name, sizeof(disk_super->policy_name));
	disk_super->policy_version[0] = cpu_to_le32(cmd->policy_version[0]);
	disk_super->policy_version[1] = cpu_to_le32(cmd->policy_version[1]);
	disk_super->policy_version[2] = cpu_to_le32(cmd->policy_version[2]);

	disk_super->read_hits = cpu_to_le32(cmd->stats.read_hits);
	disk_super->read_misses = cpu_to_le32(cmd->stats.read_misses);
	disk_super->write_hits = cpu_to_le32(cmd->stats.write_hits);
	disk_super->write_misses = cpu_to_le32(cmd->stats.write_misses);

	r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root,
			    metadata_len);
	if (r < 0) {
		dm_bm_unlock(sblock);
		return r;
	}

	return dm_tm_commit(cmd->tm, sblock);
}

/*----------------------------------------------------------------*/

/*
 * The mappings are held in a dm-array that has 64-bit values stored in
 * little-endian format.  The index is the cblock, the high 48bits of the
 * value are the oblock and the low 16 bit the flags.
 */
#define FLAGS_MASK ((1 << 16) - 1)

static __le64 pack_value(dm_oblock_t block, unsigned flags)
{
	uint64_t value = from_oblock(block);
	value <<= 16;
	value = value | (flags & FLAGS_MASK);
	return cpu_to_le64(value);
}

static void unpack_value(__le64 value_le, dm_oblock_t *block, unsigned *flags)
{
	uint64_t value = le64_to_cpu(value_le);
	uint64_t b = value >> 16;
	*block = to_oblock(b);
	*flags = value & FLAGS_MASK;
}

/*----------------------------------------------------------------*/

struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev,
						 sector_t data_block_size,
						 bool may_format_device,
						 size_t policy_hint_size)
{
	int r;
	struct dm_cache_metadata *cmd;

	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
	if (!cmd) {
		DMERR("could not allocate metadata struct");
		return NULL;
	}

	init_rwsem(&cmd->root_lock);
	cmd->bdev = bdev;
	cmd->data_block_size = data_block_size;
	cmd->cache_blocks = 0;
	cmd->policy_hint_size = policy_hint_size;
	cmd->changed = true;

	r = __create_persistent_data_objects(cmd, may_format_device);
	if (r) {
		kfree(cmd);
		return ERR_PTR(r);
	}

	r = __begin_transaction_flags(cmd, clear_clean_shutdown);
	if (r < 0) {
		dm_cache_metadata_close(cmd);
		return ERR_PTR(r);
	}

	return cmd;
}

void dm_cache_metadata_close(struct dm_cache_metadata *cmd)
{
	__destroy_persistent_data_objects(cmd);
	kfree(cmd);
}

int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size)
{
	int r;
	__le64 null_mapping = pack_value(0, 0);

	down_write(&cmd->root_lock);
	__dm_bless_for_disk(&null_mapping);
	r = dm_array_resize(&cmd->info, cmd->root, from_cblock(cmd->cache_blocks),
			    from_cblock(new_cache_size),
			    &null_mapping, &cmd->root);
	if (!r)
		cmd->cache_blocks = new_cache_size;
	cmd->changed = true;
	up_write(&cmd->root_lock);

	return r;
}

int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd,
				   sector_t discard_block_size,
				   dm_dblock_t new_nr_entries)
{
	int r;

	down_write(&cmd->root_lock);
	r = dm_bitset_resize(&cmd->discard_info,
			     cmd->discard_root,
			     from_dblock(cmd->discard_nr_blocks),
			     from_dblock(new_nr_entries),
			     false, &cmd->discard_root);
	if (!r) {
		cmd->discard_block_size = discard_block_size;
		cmd->discard_nr_blocks = new_nr_entries;
	}

	cmd->changed = true;
	up_write(&cmd->root_lock);

	return r;
}

static int __set_discard(struct dm_cache_metadata *cmd, dm_dblock_t b)
{
	return dm_bitset_set_bit(&cmd->discard_info, cmd->discard_root,
				 from_dblock(b), &cmd->discard_root);
}

static int __clear_discard(struct dm_cache_metadata *cmd, dm_dblock_t b)
{
	return dm_bitset_clear_bit(&cmd->discard_info, cmd->discard_root,
				   from_dblock(b), &cmd->discard_root);
}

static int __is_discarded(struct dm_cache_metadata *cmd, dm_dblock_t b,
			  bool *is_discarded)
{
	return dm_bitset_test_bit(&cmd->discard_info, cmd->discard_root,
				  from_dblock(b), &cmd->discard_root,
				  is_discarded);
}

static int __discard(struct dm_cache_metadata *cmd,
		     dm_dblock_t dblock, bool discard)
{
	int r;

	r = (discard ? __set_discard : __clear_discard)(cmd, dblock);
	if (r)
		return r;

	cmd->changed = true;
	return 0;
}

int dm_cache_set_discard(struct dm_cache_metadata *cmd,
			 dm_dblock_t dblock, bool discard)
{
	int r;

	down_write(&cmd->root_lock);
	r = __discard(cmd, dblock, discard);
	up_write(&cmd->root_lock);

	return r;
}

static int __load_discards(struct dm_cache_metadata *cmd,
			   load_discard_fn fn, void *context)
{
	int r = 0;
	dm_block_t b;
	bool discard;

	for (b = 0; b < from_dblock(cmd->discard_nr_blocks); b++) {
		dm_dblock_t dblock = to_dblock(b);

		if (cmd->clean_when_opened) {
			r = __is_discarded(cmd, dblock, &discard);
			if (r)
				return r;
		} else
			discard = false;

		r = fn(context, cmd->discard_block_size, dblock, discard);
		if (r)
			break;
	}

	return r;
}

int dm_cache_load_discards(struct dm_cache_metadata *cmd,
			   load_discard_fn fn, void *context)
{
	int r;

	down_read(&cmd->root_lock);
	r = __load_discards(cmd, fn, context);
	up_read(&cmd->root_lock);

	return r;
}

dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd)
{
	dm_cblock_t r;

	down_read(&cmd->root_lock);
	r = cmd->cache_blocks;
	up_read(&cmd->root_lock);

	return r;
}

static int __remove(struct dm_cache_metadata *cmd, dm_cblock_t cblock)
{
	int r;
	__le64 value = pack_value(0, 0);

	__dm_bless_for_disk(&value);
	r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock),
			       &value, &cmd->root);
	if (r)
		return r;

	cmd->changed = true;
	return 0;
}

int dm_cache_remove_mapping(struct dm_cache_metadata *cmd, dm_cblock_t cblock)
{
	int r;

	down_write(&cmd->root_lock);
	r = __remove(cmd, cblock);
	up_write(&cmd->root_lock);

	return r;
}

static int __insert(struct dm_cache_metadata *cmd,
		    dm_cblock_t cblock, dm_oblock_t oblock)
{
	int r;
	__le64 value = pack_value(oblock, M_VALID);
	__dm_bless_for_disk(&value);

	r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock),
			       &value, &cmd->root);
	if (r)
		return r;

	cmd->changed = true;
	return 0;
}

int dm_cache_insert_mapping(struct dm_cache_metadata *cmd,
			    dm_cblock_t cblock, dm_oblock_t oblock)
{
	int r;

	down_write(&cmd->root_lock);
	r = __insert(cmd, cblock, oblock);
	up_write(&cmd->root_lock);

	return r;
}

struct thunk {
	load_mapping_fn fn;
	void *context;

	struct dm_cache_metadata *cmd;
	bool respect_dirty_flags;
	bool hints_valid;
};

static bool policy_unchanged(struct dm_cache_metadata *cmd,
			     struct dm_cache_policy *policy)
{
	const char *policy_name = dm_cache_policy_get_name(policy);
	const unsigned *policy_version = dm_cache_policy_get_version(policy);
	size_t policy_hint_size = dm_cache_policy_get_hint_size(policy);

	/*
	 * Ensure policy names match.
	 */
	if (strncmp(cmd->policy_name, policy_name, sizeof(cmd->policy_name)))
		return false;

	/*
	 * Ensure policy major versions match.
	 */
	if (cmd->policy_version[0] != policy_version[0])
		return false;

	/*
	 * Ensure policy hint sizes match.
	 */
	if (cmd->policy_hint_size != policy_hint_size)
		return false;

	return true;
}

static bool hints_array_initialized(struct dm_cache_metadata *cmd)
{
	return cmd->hint_root && cmd->policy_hint_size;
}

static bool hints_array_available(struct dm_cache_metadata *cmd,
				  struct dm_cache_policy *policy)
{
	return cmd->clean_when_opened && policy_unchanged(cmd, policy) &&
		hints_array_initialized(cmd);
}

static int __load_mapping(void *context, uint64_t cblock, void *leaf)
{
	int r = 0;
	bool dirty;
	__le64 value;
	__le32 hint_value = 0;
	dm_oblock_t oblock;
	unsigned flags;
	struct thunk *thunk = context;
	struct dm_cache_metadata *cmd = thunk->cmd;

	memcpy(&value, leaf, sizeof(value));
	unpack_value(value, &oblock, &flags);

	if (flags & M_VALID) {
		if (thunk->hints_valid) {
			r = dm_array_get_value(&cmd->hint_info, cmd->hint_root,
					       cblock, &hint_value);
			if (r && r != -ENODATA)
				return r;
		}

		dirty = thunk->respect_dirty_flags ? (flags & M_DIRTY) : true;
		r = thunk->fn(thunk->context, oblock, to_cblock(cblock),
			      dirty, le32_to_cpu(hint_value), thunk->hints_valid);
	}

	return r;
}

static int __load_mappings(struct dm_cache_metadata *cmd,
			   struct dm_cache_policy *policy,
			   load_mapping_fn fn, void *context)
{
	struct thunk thunk;

	thunk.fn = fn;
	thunk.context = context;

	thunk.cmd = cmd;
	thunk.respect_dirty_flags = cmd->clean_when_opened;
	thunk.hints_valid = hints_array_available(cmd, policy);

	return dm_array_walk(&cmd->info, cmd->root, __load_mapping, &thunk);
}

int dm_cache_load_mappings(struct dm_cache_metadata *cmd,
			   struct dm_cache_policy *policy,
			   load_mapping_fn fn, void *context)
{
	int r;

	down_read(&cmd->root_lock);
	r = __load_mappings(cmd, policy, fn, context);
	up_read(&cmd->root_lock);

	return r;
}

static int __dump_mapping(void *context, uint64_t cblock, void *leaf)
{
	int r = 0;
	__le64 value;
	dm_oblock_t oblock;
	unsigned flags;

	memcpy(&value, leaf, sizeof(value));
	unpack_value(value, &oblock, &flags);

	return r;
}

static int __dump_mappings(struct dm_cache_metadata *cmd)
{
	return dm_array_walk(&cmd->info, cmd->root, __dump_mapping, NULL);
}

void dm_cache_dump(struct dm_cache_metadata *cmd)
{
	down_read(&cmd->root_lock);
	__dump_mappings(cmd);
	up_read(&cmd->root_lock);
}

int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd)
{
	int r;

	down_read(&cmd->root_lock);
	r = cmd->changed;
	up_read(&cmd->root_lock);

	return r;
}

static int __dirty(struct dm_cache_metadata *cmd, dm_cblock_t cblock, bool dirty)
{
	int r;
	unsigned flags;
	dm_oblock_t oblock;
	__le64 value;

	r = dm_array_get_value(&cmd->info, cmd->root, from_cblock(cblock), &value);
	if (r)
		return r;

	unpack_value(value, &oblock, &flags);

	if (((flags & M_DIRTY) && dirty) || (!(flags & M_DIRTY) && !dirty))
		/* nothing to be done */
		return 0;

	value = pack_value(oblock, (flags & ~M_DIRTY) | (dirty ? M_DIRTY : 0));
	__dm_bless_for_disk(&value);

	r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock),
			       &value, &cmd->root);
	if (r)
		return r;

	cmd->changed = true;
	return 0;

}

int dm_cache_set_dirty(struct dm_cache_metadata *cmd,
		       dm_cblock_t cblock, bool dirty)
{
	int r;

	down_write(&cmd->root_lock);
	r = __dirty(cmd, cblock, dirty);
	up_write(&cmd->root_lock);

	return r;
}

void dm_cache_metadata_get_stats(struct dm_cache_metadata *cmd,
				 struct dm_cache_statistics *stats)
{
	down_read(&cmd->root_lock);
	memcpy(stats, &cmd->stats, sizeof(*stats));
	up_read(&cmd->root_lock);
}

void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd,
				 struct dm_cache_statistics *stats)
{
	down_write(&cmd->root_lock);
	memcpy(&cmd->stats, stats, sizeof(*stats));
	up_write(&cmd->root_lock);
}

int dm_cache_commit(struct dm_cache_metadata *cmd, bool clean_shutdown)
{
	int r;
	flags_mutator mutator = (clean_shutdown ? set_clean_shutdown :
				 clear_clean_shutdown);

	down_write(&cmd->root_lock);
	r = __commit_transaction(cmd, mutator);
	if (r)
		goto out;

	r = __begin_transaction(cmd);

out:
	up_write(&cmd->root_lock);
	return r;
}

int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd,
					   dm_block_t *result)
{
	int r = -EINVAL;

	down_read(&cmd->root_lock);
	r = dm_sm_get_nr_free(cmd->metadata_sm, result);
	up_read(&cmd->root_lock);

	return r;
}

int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd,
				   dm_block_t *result)
{
	int r = -EINVAL;

	down_read(&cmd->root_lock);
	r = dm_sm_get_nr_blocks(cmd->metadata_sm, result);
	up_read(&cmd->root_lock);

	return r;
}

/*----------------------------------------------------------------*/

static int begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
{
	int r;
	__le32 value;
	size_t hint_size;
	const char *policy_name = dm_cache_policy_get_name(policy);
	const unsigned *policy_version = dm_cache_policy_get_version(policy);

	if (!policy_name[0] ||
	    (strlen(policy_name) > sizeof(cmd->policy_name) - 1))
		return -EINVAL;

	if (!policy_unchanged(cmd, policy)) {
		strncpy(cmd->policy_name, policy_name, sizeof(cmd->policy_name));
		memcpy(cmd->policy_version, policy_version, sizeof(cmd->policy_version));

		hint_size = dm_cache_policy_get_hint_size(policy);
		if (!hint_size)
			return 0; /* short-circuit hints initialization */
		cmd->policy_hint_size = hint_size;

		if (cmd->hint_root) {
			r = dm_array_del(&cmd->hint_info, cmd->hint_root);
			if (r)
				return r;
		}

		r = dm_array_empty(&cmd->hint_info, &cmd->hint_root);
		if (r)
			return r;

		value = cpu_to_le32(0);
		__dm_bless_for_disk(&value);
		r = dm_array_resize(&cmd->hint_info, cmd->hint_root, 0,
				    from_cblock(cmd->cache_blocks),
				    &value, &cmd->hint_root);
		if (r)
			return r;
	}

	return 0;
}

int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
{
	int r;

	down_write(&cmd->root_lock);
	r = begin_hints(cmd, policy);
	up_write(&cmd->root_lock);

	return r;
}

static int save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
		     uint32_t hint)
{
	int r;
	__le32 value = cpu_to_le32(hint);
	__dm_bless_for_disk(&value);

	r = dm_array_set_value(&cmd->hint_info, cmd->hint_root,
			       from_cblock(cblock), &value, &cmd->hint_root);
	cmd->changed = true;

	return r;
}

int dm_cache_save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
		       uint32_t hint)
{
	int r;

	if (!hints_array_initialized(cmd))
		return 0;

	down_write(&cmd->root_lock);
	r = save_hint(cmd, cblock, hint);
	up_write(&cmd->root_lock);

	return r;
}