Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: bda3caca23ca69af2fe97592aa817a29b87851d6 (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
/*
 * Copyright (C) 2012 Red Hat, Inc.
 *
 * Author: Mikulas Patocka <mpatocka@redhat.com>
 *
 * Based on Chromium dm-verity driver (C) 2011 The Chromium OS Authors
 *
 * This file is released under the GPLv2.
 *
 * In the file "/sys/module/dm_verity/parameters/prefetch_cluster" you can set
 * default prefetch value. Data are read in "prefetch_cluster" chunks from the
 * hash device. Setting this greatly improves performance when data and hash
 * are on the same disk on different partitions on devices with poor random
 * access behavior.
 */

#include "dm-verity.h"
#include "dm-verity-fec.h"

#include <linux/module.h>
#include <linux/reboot.h>

#define DM_MSG_PREFIX			"verity"

#define DM_VERITY_ENV_LENGTH		42
#define DM_VERITY_ENV_VAR_NAME		"DM_VERITY_ERR_BLOCK_NR"

#define DM_VERITY_DEFAULT_PREFETCH_SIZE	262144

#define DM_VERITY_MAX_CORRUPTED_ERRS	100

#define DM_VERITY_OPT_LOGGING		"ignore_corruption"
#define DM_VERITY_OPT_RESTART		"restart_on_corruption"
#define DM_VERITY_OPT_IGN_ZEROES	"ignore_zero_blocks"

#define DM_VERITY_OPTS_MAX		(2 + DM_VERITY_OPTS_FEC)

static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE;

module_param_named(prefetch_cluster, dm_verity_prefetch_cluster, uint, S_IRUGO | S_IWUSR);

struct dm_verity_prefetch_work {
	struct work_struct work;
	struct dm_verity *v;
	sector_t block;
	unsigned n_blocks;
};

/*
 * Auxiliary structure appended to each dm-bufio buffer. If the value
 * hash_verified is nonzero, hash of the block has been verified.
 *
 * The variable hash_verified is set to 0 when allocating the buffer, then
 * it can be changed to 1 and it is never reset to 0 again.
 *
 * There is no lock around this value, a race condition can at worst cause
 * that multiple processes verify the hash of the same buffer simultaneously
 * and write 1 to hash_verified simultaneously.
 * This condition is harmless, so we don't need locking.
 */
struct buffer_aux {
	int hash_verified;
};

/*
 * Initialize struct buffer_aux for a freshly created buffer.
 */
static void dm_bufio_alloc_callback(struct dm_buffer *buf)
{
	struct buffer_aux *aux = dm_bufio_get_aux_data(buf);

	aux->hash_verified = 0;
}

/*
 * Translate input sector number to the sector number on the target device.
 */
static sector_t verity_map_sector(struct dm_verity *v, sector_t bi_sector)
{
	return v->data_start + dm_target_offset(v->ti, bi_sector);
}

/*
 * Return hash position of a specified block at a specified tree level
 * (0 is the lowest level).
 * The lowest "hash_per_block_bits"-bits of the result denote hash position
 * inside a hash block. The remaining bits denote location of the hash block.
 */
static sector_t verity_position_at_level(struct dm_verity *v, sector_t block,
					 int level)
{
	return block >> (level * v->hash_per_block_bits);
}

/*
 * Callback function for asynchrnous crypto API completion notification
 */
static void verity_op_done(struct crypto_async_request *base, int err)
{
	struct verity_result *res = (struct verity_result *)base->data;

	if (err == -EINPROGRESS)
		return;

	res->err = err;
	complete(&res->completion);
}

/*
 * Wait for async crypto API callback
 */
static inline int verity_complete_op(struct verity_result *res, int ret)
{
	switch (ret) {
	case 0:
		break;

	case -EINPROGRESS:
	case -EBUSY:
		ret = wait_for_completion_interruptible(&res->completion);
		if (!ret)
			ret = res->err;
		reinit_completion(&res->completion);
		break;

	default:
		DMERR("verity_wait_hash: crypto op submission failed: %d", ret);
	}

	if (unlikely(ret < 0))
		DMERR("verity_wait_hash: crypto op failed: %d", ret);

	return ret;
}

static int verity_hash_update(struct dm_verity *v, struct ahash_request *req,
				const u8 *data, size_t len,
				struct verity_result *res)
{
	struct scatterlist sg;

	sg_init_one(&sg, data, len);
	ahash_request_set_crypt(req, &sg, NULL, len);

	return verity_complete_op(res, crypto_ahash_update(req));
}

/*
 * Wrapper for crypto_ahash_init, which handles verity salting.
 */
static int verity_hash_init(struct dm_verity *v, struct ahash_request *req,
				struct verity_result *res)
{
	int r;

	ahash_request_set_tfm(req, v->tfm);
	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP |
					CRYPTO_TFM_REQ_MAY_BACKLOG,
					verity_op_done, (void *)res);
	init_completion(&res->completion);

	r = verity_complete_op(res, crypto_ahash_init(req));

	if (unlikely(r < 0)) {
		DMERR("crypto_ahash_init failed: %d", r);
		return r;
	}

	if (likely(v->salt_size && (v->version >= 1)))
		r = verity_hash_update(v, req, v->salt, v->salt_size, res);

	return r;
}

static int verity_hash_final(struct dm_verity *v, struct ahash_request *req,
			     u8 *digest, struct verity_result *res)
{
	int r;

	if (unlikely(v->salt_size && (!v->version))) {
		r = verity_hash_update(v, req, v->salt, v->salt_size, res);

		if (r < 0) {
			DMERR("verity_hash_final failed updating salt: %d", r);
			goto out;
		}
	}

	ahash_request_set_crypt(req, NULL, digest, 0);
	r = verity_complete_op(res, crypto_ahash_final(req));
out:
	return r;
}

int verity_hash(struct dm_verity *v, struct ahash_request *req,
		const u8 *data, size_t len, u8 *digest)
{
	int r;
	struct verity_result res;

	r = verity_hash_init(v, req, &res);
	if (unlikely(r < 0))
		goto out;

	r = verity_hash_update(v, req, data, len, &res);
	if (unlikely(r < 0))
		goto out;

	r = verity_hash_final(v, req, digest, &res);

out:
	return r;
}

static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level,
				 sector_t *hash_block, unsigned *offset)
{
	sector_t position = verity_position_at_level(v, block, level);
	unsigned idx;

	*hash_block = v->hash_level_block[level] + (position >> v->hash_per_block_bits);

	if (!offset)
		return;

	idx = position & ((1 << v->hash_per_block_bits) - 1);
	if (!v->version)
		*offset = idx * v->digest_size;
	else
		*offset = idx << (v->hash_dev_block_bits - v->hash_per_block_bits);
}

/*
 * Handle verification errors.
 */
static int verity_handle_err(struct dm_verity *v, enum verity_block_type type,
			     unsigned long long block)
{
	char verity_env[DM_VERITY_ENV_LENGTH];
	char *envp[] = { verity_env, NULL };
	const char *type_str = "";
	struct mapped_device *md = dm_table_get_md(v->ti->table);

	/* Corruption should be visible in device status in all modes */
	v->hash_failed = 1;

	if (v->corrupted_errs >= DM_VERITY_MAX_CORRUPTED_ERRS)
		goto out;

	v->corrupted_errs++;

	switch (type) {
	case DM_VERITY_BLOCK_TYPE_DATA:
		type_str = "data";
		break;
	case DM_VERITY_BLOCK_TYPE_METADATA:
		type_str = "metadata";
		break;
	default:
		BUG();
	}

	DMERR("%s: %s block %llu is corrupted", v->data_dev->name, type_str,
		block);

	if (v->corrupted_errs == DM_VERITY_MAX_CORRUPTED_ERRS)
		DMERR("%s: reached maximum errors", v->data_dev->name);

	snprintf(verity_env, DM_VERITY_ENV_LENGTH, "%s=%d,%llu",
		DM_VERITY_ENV_VAR_NAME, type, block);

	kobject_uevent_env(&disk_to_dev(dm_disk(md))->kobj, KOBJ_CHANGE, envp);

out:
	if (v->mode == DM_VERITY_MODE_LOGGING)
		return 0;

	if (v->mode == DM_VERITY_MODE_RESTART)
		kernel_restart("dm-verity device corrupted");

	return 1;
}

/*
 * Verify hash of a metadata block pertaining to the specified data block
 * ("block" argument) at a specified level ("level" argument).
 *
 * On successful return, verity_io_want_digest(v, io) contains the hash value
 * for a lower tree level or for the data block (if we're at the lowest level).
 *
 * If "skip_unverified" is true, unverified buffer is skipped and 1 is returned.
 * If "skip_unverified" is false, unverified buffer is hashed and verified
 * against current value of verity_io_want_digest(v, io).
 */
static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io,
			       sector_t block, int level, bool skip_unverified,
			       u8 *want_digest)
{
	struct dm_buffer *buf;
	struct buffer_aux *aux;
	u8 *data;
	int r;
	sector_t hash_block;
	unsigned offset;

	verity_hash_at_level(v, block, level, &hash_block, &offset);

	data = dm_bufio_read(v->bufio, hash_block, &buf);
	if (IS_ERR(data))
		return PTR_ERR(data);

	aux = dm_bufio_get_aux_data(buf);

	if (!aux->hash_verified) {
		if (skip_unverified) {
			r = 1;
			goto release_ret_r;
		}

		r = verity_hash(v, verity_io_hash_req(v, io),
				data, 1 << v->hash_dev_block_bits,
				verity_io_real_digest(v, io));
		if (unlikely(r < 0))
			goto release_ret_r;

		if (likely(memcmp(verity_io_real_digest(v, io), want_digest,
				  v->digest_size) == 0))
			aux->hash_verified = 1;
		else if (verity_fec_decode(v, io,
					   DM_VERITY_BLOCK_TYPE_METADATA,
					   hash_block, data, NULL) == 0)
			aux->hash_verified = 1;
		else if (verity_handle_err(v,
					   DM_VERITY_BLOCK_TYPE_METADATA,
					   hash_block)) {
			r = -EIO;
			goto release_ret_r;
		}
	}

	data += offset;
	memcpy(want_digest, data, v->digest_size);
	r = 0;

release_ret_r:
	dm_bufio_release(buf);
	return r;
}

/*
 * Find a hash for a given block, write it to digest and verify the integrity
 * of the hash tree if necessary.
 */
int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
			  sector_t block, u8 *digest, bool *is_zero)
{
	int r = 0, i;

	if (likely(v->levels)) {
		/*
		 * First, we try to get the requested hash for
		 * the current block. If the hash block itself is
		 * verified, zero is returned. If it isn't, this
		 * function returns 1 and we fall back to whole
		 * chain verification.
		 */
		r = verity_verify_level(v, io, block, 0, true, digest);
		if (likely(r <= 0))
			goto out;
	}

	memcpy(digest, v->root_digest, v->digest_size);

	for (i = v->levels - 1; i >= 0; i--) {
		r = verity_verify_level(v, io, block, i, false, digest);
		if (unlikely(r))
			goto out;
	}
out:
	if (!r && v->zero_digest)
		*is_zero = !memcmp(v->zero_digest, digest, v->digest_size);
	else
		*is_zero = false;

	return r;
}

/*
 * Calculates the digest for the given bio
 */
int verity_for_io_block(struct dm_verity *v, struct dm_verity_io *io,
			struct bvec_iter *iter, struct verity_result *res)
{
	unsigned int todo = 1 << v->data_dev_block_bits;
	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);
	struct scatterlist sg;
	struct ahash_request *req = verity_io_hash_req(v, io);

	do {
		int r;
		unsigned int len;
		struct bio_vec bv = bio_iter_iovec(bio, *iter);

		sg_init_table(&sg, 1);

		len = bv.bv_len;

		if (likely(len >= todo))
			len = todo;
		/*
		 * Operating on a single page at a time looks suboptimal
		 * until you consider the typical block size is 4,096B.
		 * Going through this loops twice should be very rare.
		 */
		sg_set_page(&sg, bv.bv_page, len, bv.bv_offset);
		ahash_request_set_crypt(req, &sg, NULL, len);
		r = verity_complete_op(res, crypto_ahash_update(req));

		if (unlikely(r < 0)) {
			DMERR("verity_for_io_block crypto op failed: %d", r);
			return r;
		}

		bio_advance_iter(bio, iter, len);
		todo -= len;
	} while (todo);

	return 0;
}

/*
 * Calls function process for 1 << v->data_dev_block_bits bytes in the bio_vec
 * starting from iter.
 */
int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
			struct bvec_iter *iter,
			int (*process)(struct dm_verity *v,
				       struct dm_verity_io *io, u8 *data,
				       size_t len))
{
	unsigned todo = 1 << v->data_dev_block_bits;
	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);

	do {
		int r;
		u8 *page;
		unsigned len;
		struct bio_vec bv = bio_iter_iovec(bio, *iter);

		page = kmap_atomic(bv.bv_page);
		len = bv.bv_len;

		if (likely(len >= todo))
			len = todo;

		r = process(v, io, page + bv.bv_offset, len);
		kunmap_atomic(page);

		if (r < 0)
			return r;

		bio_advance_iter(bio, iter, len);
		todo -= len;
	} while (todo);

	return 0;
}

static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io,
			  u8 *data, size_t len)
{
	memset(data, 0, len);
	return 0;
}

/*
 * Verify one "dm_verity_io" structure.
 */
static int verity_verify_io(struct dm_verity_io *io)
{
	bool is_zero;
	struct dm_verity *v = io->v;
	struct bvec_iter start;
	unsigned b;
	struct verity_result res;

	for (b = 0; b < io->n_blocks; b++) {
		int r;
		struct ahash_request *req = verity_io_hash_req(v, io);

		r = verity_hash_for_block(v, io, io->block + b,
					  verity_io_want_digest(v, io),
					  &is_zero);
		if (unlikely(r < 0))
			return r;

		if (is_zero) {
			/*
			 * If we expect a zero block, don't validate, just
			 * return zeros.
			 */
			r = verity_for_bv_block(v, io, &io->iter,
						verity_bv_zero);
			if (unlikely(r < 0))
				return r;

			continue;
		}

		r = verity_hash_init(v, req, &res);
		if (unlikely(r < 0))
			return r;

		start = io->iter;
		r = verity_for_io_block(v, io, &io->iter, &res);
		if (unlikely(r < 0))
			return r;

		r = verity_hash_final(v, req, verity_io_real_digest(v, io),
					&res);
		if (unlikely(r < 0))
			return r;

		if (likely(memcmp(verity_io_real_digest(v, io),
				  verity_io_want_digest(v, io), v->digest_size) == 0))
			continue;
		else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA,
					   io->block + b, NULL, &start) == 0)
			continue;
		else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA,
					   io->block + b))
			return -EIO;
	}

	return 0;
}

/*
 * End one "io" structure with a given error.
 */
static void verity_finish_io(struct dm_verity_io *io, blk_status_t status)
{
	struct dm_verity *v = io->v;
	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);

	bio->bi_end_io = io->orig_bi_end_io;
	bio->bi_status = status;

	verity_fec_finish_io(io);

	bio_endio(bio);
}

static void verity_work(struct work_struct *w)
{
	struct dm_verity_io *io = container_of(w, struct dm_verity_io, work);

	verity_finish_io(io, errno_to_blk_status(verity_verify_io(io)));
}

static void verity_end_io(struct bio *bio)
{
	struct dm_verity_io *io = bio->bi_private;

	if (bio->bi_status && !verity_fec_is_enabled(io->v)) {
		verity_finish_io(io, bio->bi_status);
		return;
	}

	INIT_WORK(&io->work, verity_work);
	queue_work(io->v->verify_wq, &io->work);
}

/*
 * Prefetch buffers for the specified io.
 * The root buffer is not prefetched, it is assumed that it will be cached
 * all the time.
 */
static void verity_prefetch_io(struct work_struct *work)
{
	struct dm_verity_prefetch_work *pw =
		container_of(work, struct dm_verity_prefetch_work, work);
	struct dm_verity *v = pw->v;
	int i;

	for (i = v->levels - 2; i >= 0; i--) {
		sector_t hash_block_start;
		sector_t hash_block_end;
		verity_hash_at_level(v, pw->block, i, &hash_block_start, NULL);
		verity_hash_at_level(v, pw->block + pw->n_blocks - 1, i, &hash_block_end, NULL);
		if (!i) {
			unsigned cluster = ACCESS_ONCE(dm_verity_prefetch_cluster);

			cluster >>= v->data_dev_block_bits;
			if (unlikely(!cluster))
				goto no_prefetch_cluster;

			if (unlikely(cluster & (cluster - 1)))
				cluster = 1 << __fls(cluster);

			hash_block_start &= ~(sector_t)(cluster - 1);
			hash_block_end |= cluster - 1;
			if (unlikely(hash_block_end >= v->hash_blocks))
				hash_block_end = v->hash_blocks - 1;
		}
no_prefetch_cluster:
		dm_bufio_prefetch(v->bufio, hash_block_start,
				  hash_block_end - hash_block_start + 1);
	}

	kfree(pw);
}

static void verity_submit_prefetch(struct dm_verity *v, struct dm_verity_io *io)
{
	struct dm_verity_prefetch_work *pw;

	pw = kmalloc(sizeof(struct dm_verity_prefetch_work),
		GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);

	if (!pw)
		return;

	INIT_WORK(&pw->work, verity_prefetch_io);
	pw->v = v;
	pw->block = io->block;
	pw->n_blocks = io->n_blocks;
	queue_work(v->verify_wq, &pw->work);
}

/*
 * Bio map function. It allocates dm_verity_io structure and bio vector and
 * fills them. Then it issues prefetches and the I/O.
 */
static int verity_map(struct dm_target *ti, struct bio *bio)
{
	struct dm_verity *v = ti->private;
	struct dm_verity_io *io;

	bio_set_dev(bio, v->data_dev->bdev);
	bio->bi_iter.bi_sector = verity_map_sector(v, bio->bi_iter.bi_sector);

	if (((unsigned)bio->bi_iter.bi_sector | bio_sectors(bio)) &
	    ((1 << (v->data_dev_block_bits - SECTOR_SHIFT)) - 1)) {
		DMERR_LIMIT("unaligned io");
		return DM_MAPIO_KILL;
	}

	if (bio_end_sector(bio) >>
	    (v->data_dev_block_bits - SECTOR_SHIFT) > v->data_blocks) {
		DMERR_LIMIT("io out of range");
		return DM_MAPIO_KILL;
	}

	if (bio_data_dir(bio) == WRITE)
		return DM_MAPIO_KILL;

	io = dm_per_bio_data(bio, ti->per_io_data_size);
	io->v = v;
	io->orig_bi_end_io = bio->bi_end_io;
	io->block = bio->bi_iter.bi_sector >> (v->data_dev_block_bits - SECTOR_SHIFT);
	io->n_blocks = bio->bi_iter.bi_size >> v->data_dev_block_bits;

	bio->bi_end_io = verity_end_io;
	bio->bi_private = io;
	io->iter = bio->bi_iter;

	verity_fec_init_io(io);

	verity_submit_prefetch(v, io);

	generic_make_request(bio);

	return DM_MAPIO_SUBMITTED;
}

/*
 * Status: V (valid) or C (corruption found)
 */
static void verity_status(struct dm_target *ti, status_type_t type,
			  unsigned status_flags, char *result, unsigned maxlen)
{
	struct dm_verity *v = ti->private;
	unsigned args = 0;
	unsigned sz = 0;
	unsigned x;

	switch (type) {
	case STATUSTYPE_INFO:
		DMEMIT("%c", v->hash_failed ? 'C' : 'V');
		break;
	case STATUSTYPE_TABLE:
		DMEMIT("%u %s %s %u %u %llu %llu %s ",
			v->version,
			v->data_dev->name,
			v->hash_dev->name,
			1 << v->data_dev_block_bits,
			1 << v->hash_dev_block_bits,
			(unsigned long long)v->data_blocks,
			(unsigned long long)v->hash_start,
			v->alg_name
			);
		for (x = 0; x < v->digest_size; x++)
			DMEMIT("%02x", v->root_digest[x]);
		DMEMIT(" ");
		if (!v->salt_size)
			DMEMIT("-");
		else
			for (x = 0; x < v->salt_size; x++)
				DMEMIT("%02x", v->salt[x]);
		if (v->mode != DM_VERITY_MODE_EIO)
			args++;
		if (verity_fec_is_enabled(v))
			args += DM_VERITY_OPTS_FEC;
		if (v->zero_digest)
			args++;
		if (!args)
			return;
		DMEMIT(" %u", args);
		if (v->mode != DM_VERITY_MODE_EIO) {
			DMEMIT(" ");
			switch (v->mode) {
			case DM_VERITY_MODE_LOGGING:
				DMEMIT(DM_VERITY_OPT_LOGGING);
				break;
			case DM_VERITY_MODE_RESTART:
				DMEMIT(DM_VERITY_OPT_RESTART);
				break;
			default:
				BUG();
			}
		}
		if (v->zero_digest)
			DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES);
		sz = verity_fec_status_table(v, sz, result, maxlen);
		break;
	}
}

static int verity_prepare_ioctl(struct dm_target *ti,
		struct block_device **bdev, fmode_t *mode)
{
	struct dm_verity *v = ti->private;

	*bdev = v->data_dev->bdev;

	if (v->data_start ||
	    ti->len != i_size_read(v->data_dev->bdev->bd_inode) >> SECTOR_SHIFT)
		return 1;
	return 0;
}

static int verity_iterate_devices(struct dm_target *ti,
				  iterate_devices_callout_fn fn, void *data)
{
	struct dm_verity *v = ti->private;

	return fn(ti, v->data_dev, v->data_start, ti->len, data);
}

static void verity_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
	struct dm_verity *v = ti->private;

	if (limits->logical_block_size < 1 << v->data_dev_block_bits)
		limits->logical_block_size = 1 << v->data_dev_block_bits;

	if (limits->physical_block_size < 1 << v->data_dev_block_bits)
		limits->physical_block_size = 1 << v->data_dev_block_bits;

	blk_limits_io_min(limits, limits->logical_block_size);
}

static void verity_dtr(struct dm_target *ti)
{
	struct dm_verity *v = ti->private;

	if (v->verify_wq)
		destroy_workqueue(v->verify_wq);

	if (v->bufio)
		dm_bufio_client_destroy(v->bufio);

	kfree(v->salt);
	kfree(v->root_digest);
	kfree(v->zero_digest);

	if (v->tfm)
		crypto_free_ahash(v->tfm);

	kfree(v->alg_name);

	if (v->hash_dev)
		dm_put_device(ti, v->hash_dev);

	if (v->data_dev)
		dm_put_device(ti, v->data_dev);

	verity_fec_dtr(v);

	kfree(v);
}

static int verity_alloc_zero_digest(struct dm_verity *v)
{
	int r = -ENOMEM;
	struct ahash_request *req;
	u8 *zero_data;

	v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL);

	if (!v->zero_digest)
		return r;

	req = kmalloc(v->ahash_reqsize, GFP_KERNEL);

	if (!req)
		return r; /* verity_dtr will free zero_digest */

	zero_data = kzalloc(1 << v->data_dev_block_bits, GFP_KERNEL);

	if (!zero_data)
		goto out;

	r = verity_hash(v, req, zero_data, 1 << v->data_dev_block_bits,
			v->zero_digest);

out:
	kfree(req);
	kfree(zero_data);

	return r;
}

static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v)
{
	int r;
	unsigned argc;
	struct dm_target *ti = v->ti;
	const char *arg_name;

	static const struct dm_arg _args[] = {
		{0, DM_VERITY_OPTS_MAX, "Invalid number of feature args"},
	};

	r = dm_read_arg_group(_args, as, &argc, &ti->error);
	if (r)
		return -EINVAL;

	if (!argc)
		return 0;

	do {
		arg_name = dm_shift_arg(as);
		argc--;

		if (!strcasecmp(arg_name, DM_VERITY_OPT_LOGGING)) {
			v->mode = DM_VERITY_MODE_LOGGING;
			continue;

		} else if (!strcasecmp(arg_name, DM_VERITY_OPT_RESTART)) {
			v->mode = DM_VERITY_MODE_RESTART;
			continue;

		} else if (!strcasecmp(arg_name, DM_VERITY_OPT_IGN_ZEROES)) {
			r = verity_alloc_zero_digest(v);
			if (r) {
				ti->error = "Cannot allocate zero digest";
				return r;
			}
			continue;

		} else if (verity_is_fec_opt_arg(arg_name)) {
			r = verity_fec_parse_opt_args(as, v, &argc, arg_name);
			if (r)
				return r;
			continue;
		}

		ti->error = "Unrecognized verity feature request";
		return -EINVAL;
	} while (argc && !r);

	return r;
}

/*
 * Target parameters:
 *	<version>	The current format is version 1.
 *			Vsn 0 is compatible with original Chromium OS releases.
 *	<data device>
 *	<hash device>
 *	<data block size>
 *	<hash block size>
 *	<the number of data blocks>
 *	<hash start block>
 *	<algorithm>
 *	<digest>
 *	<salt>		Hex string or "-" if no salt.
 */
static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
{
	struct dm_verity *v;
	struct dm_arg_set as;
	unsigned int num;
	unsigned long long num_ll;
	int r;
	int i;
	sector_t hash_position;
	char dummy;

	v = kzalloc(sizeof(struct dm_verity), GFP_KERNEL);
	if (!v) {
		ti->error = "Cannot allocate verity structure";
		return -ENOMEM;
	}
	ti->private = v;
	v->ti = ti;

	r = verity_fec_ctr_alloc(v);
	if (r)
		goto bad;

	if ((dm_table_get_mode(ti->table) & ~FMODE_READ)) {
		ti->error = "Device must be readonly";
		r = -EINVAL;
		goto bad;
	}

	if (argc < 10) {
		ti->error = "Not enough arguments";
		r = -EINVAL;
		goto bad;
	}

	if (sscanf(argv[0], "%u%c", &num, &dummy) != 1 ||
	    num > 1) {
		ti->error = "Invalid version";
		r = -EINVAL;
		goto bad;
	}
	v->version = num;

	r = dm_get_device(ti, argv[1], FMODE_READ, &v->data_dev);
	if (r) {
		ti->error = "Data device lookup failed";
		goto bad;
	}

	r = dm_get_device(ti, argv[2], FMODE_READ, &v->hash_dev);
	if (r) {
		ti->error = "Hash device lookup failed";
		goto bad;
	}

	if (sscanf(argv[3], "%u%c", &num, &dummy) != 1 ||
	    !num || (num & (num - 1)) ||
	    num < bdev_logical_block_size(v->data_dev->bdev) ||
	    num > PAGE_SIZE) {
		ti->error = "Invalid data device block size";
		r = -EINVAL;
		goto bad;
	}
	v->data_dev_block_bits = __ffs(num);

	if (sscanf(argv[4], "%u%c", &num, &dummy) != 1 ||
	    !num || (num & (num - 1)) ||
	    num < bdev_logical_block_size(v->hash_dev->bdev) ||
	    num > INT_MAX) {
		ti->error = "Invalid hash device block size";
		r = -EINVAL;
		goto bad;
	}
	v->hash_dev_block_bits = __ffs(num);

	if (sscanf(argv[5], "%llu%c", &num_ll, &dummy) != 1 ||
	    (sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT))
	    >> (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll) {
		ti->error = "Invalid data blocks";
		r = -EINVAL;
		goto bad;
	}
	v->data_blocks = num_ll;

	if (ti->len > (v->data_blocks << (v->data_dev_block_bits - SECTOR_SHIFT))) {
		ti->error = "Data device is too small";
		r = -EINVAL;
		goto bad;
	}

	if (sscanf(argv[6], "%llu%c", &num_ll, &dummy) != 1 ||
	    (sector_t)(num_ll << (v->hash_dev_block_bits - SECTOR_SHIFT))
	    >> (v->hash_dev_block_bits - SECTOR_SHIFT) != num_ll) {
		ti->error = "Invalid hash start";
		r = -EINVAL;
		goto bad;
	}
	v->hash_start = num_ll;

	v->alg_name = kstrdup(argv[7], GFP_KERNEL);
	if (!v->alg_name) {
		ti->error = "Cannot allocate algorithm name";
		r = -ENOMEM;
		goto bad;
	}

	v->tfm = crypto_alloc_ahash(v->alg_name, 0, 0);
	if (IS_ERR(v->tfm)) {
		ti->error = "Cannot initialize hash function";
		r = PTR_ERR(v->tfm);
		v->tfm = NULL;
		goto bad;
	}
	v->digest_size = crypto_ahash_digestsize(v->tfm);
	if ((1 << v->hash_dev_block_bits) < v->digest_size * 2) {
		ti->error = "Digest size too big";
		r = -EINVAL;
		goto bad;
	}
	v->ahash_reqsize = sizeof(struct ahash_request) +
		crypto_ahash_reqsize(v->tfm);

	v->root_digest = kmalloc(v->digest_size, GFP_KERNEL);
	if (!v->root_digest) {
		ti->error = "Cannot allocate root digest";
		r = -ENOMEM;
		goto bad;
	}
	if (strlen(argv[8]) != v->digest_size * 2 ||
	    hex2bin(v->root_digest, argv[8], v->digest_size)) {
		ti->error = "Invalid root digest";
		r = -EINVAL;
		goto bad;
	}

	if (strcmp(argv[9], "-")) {
		v->salt_size = strlen(argv[9]) / 2;
		v->salt = kmalloc(v->salt_size, GFP_KERNEL);
		if (!v->salt) {
			ti->error = "Cannot allocate salt";
			r = -ENOMEM;
			goto bad;
		}
		if (strlen(argv[9]) != v->salt_size * 2 ||
		    hex2bin(v->salt, argv[9], v->salt_size)) {
			ti->error = "Invalid salt";
			r = -EINVAL;
			goto bad;
		}
	}

	argv += 10;
	argc -= 10;

	/* Optional parameters */
	if (argc) {
		as.argc = argc;
		as.argv = argv;

		r = verity_parse_opt_args(&as, v);
		if (r < 0)
			goto bad;
	}

	v->hash_per_block_bits =
		__fls((1 << v->hash_dev_block_bits) / v->digest_size);

	v->levels = 0;
	if (v->data_blocks)
		while (v->hash_per_block_bits * v->levels < 64 &&
		       (unsigned long long)(v->data_blocks - 1) >>
		       (v->hash_per_block_bits * v->levels))
			v->levels++;

	if (v->levels > DM_VERITY_MAX_LEVELS) {
		ti->error = "Too many tree levels";
		r = -E2BIG;
		goto bad;
	}

	hash_position = v->hash_start;
	for (i = v->levels - 1; i >= 0; i--) {
		sector_t s;
		v->hash_level_block[i] = hash_position;
		s = (v->data_blocks + ((sector_t)1 << ((i + 1) * v->hash_per_block_bits)) - 1)
					>> ((i + 1) * v->hash_per_block_bits);
		if (hash_position + s < hash_position) {
			ti->error = "Hash device offset overflow";
			r = -E2BIG;
			goto bad;
		}
		hash_position += s;
	}
	v->hash_blocks = hash_position;

	v->bufio = dm_bufio_client_create(v->hash_dev->bdev,
		1 << v->hash_dev_block_bits, 1, sizeof(struct buffer_aux),
		dm_bufio_alloc_callback, NULL);
	if (IS_ERR(v->bufio)) {
		ti->error = "Cannot initialize dm-bufio";
		r = PTR_ERR(v->bufio);
		v->bufio = NULL;
		goto bad;
	}

	if (dm_bufio_get_device_size(v->bufio) < v->hash_blocks) {
		ti->error = "Hash device is too small";
		r = -E2BIG;
		goto bad;
	}

	/* WQ_UNBOUND greatly improves performance when running on ramdisk */
	v->verify_wq = alloc_workqueue("kverityd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus());
	if (!v->verify_wq) {
		ti->error = "Cannot allocate workqueue";
		r = -ENOMEM;
		goto bad;
	}

	ti->per_io_data_size = sizeof(struct dm_verity_io) +
				v->ahash_reqsize + v->digest_size * 2;

	r = verity_fec_ctr(v);
	if (r)
		goto bad;

	ti->per_io_data_size = roundup(ti->per_io_data_size,
				       __alignof__(struct dm_verity_io));

	return 0;

bad:
	verity_dtr(ti);

	return r;
}

static struct target_type verity_target = {
	.name		= "verity",
	.version	= {1, 3, 0},
	.module		= THIS_MODULE,
	.ctr		= verity_ctr,
	.dtr		= verity_dtr,
	.map		= verity_map,
	.status		= verity_status,
	.prepare_ioctl	= verity_prepare_ioctl,
	.iterate_devices = verity_iterate_devices,
	.io_hints	= verity_io_hints,
};

static int __init dm_verity_init(void)
{
	int r;

	r = dm_register_target(&verity_target);
	if (r < 0)
		DMERR("register failed %d", r);

	return r;
}

static void __exit dm_verity_exit(void)
{
	dm_unregister_target(&verity_target);
}

module_init(dm_verity_init);
module_exit(dm_verity_exit);

MODULE_AUTHOR("Mikulas Patocka <mpatocka@redhat.com>");
MODULE_AUTHOR("Mandeep Baines <msb@chromium.org>");
MODULE_AUTHOR("Will Drewry <wad@chromium.org>");
MODULE_DESCRIPTION(DM_NAME " target for transparent disk integrity checking");
MODULE_LICENSE("GPL");