summaryrefslogtreecommitdiff
path: root/fs/ubifs/replay.c
blob: 08f5036a9056dedacd9813229540cb6f9b66762c (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
/*
 * This file is part of UBIFS.
 *
 * Copyright (C) 2006-2008 Nokia Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published by
 * the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc., 51
 * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
 *
 * Authors: Adrian Hunter
 *          Artem Bityutskiy (Битюцкий Артём)
 */

/*
 * This file contains journal replay code. It runs when the file-system is being
 * mounted and requires no locking.
 *
 * The larger is the journal, the longer it takes to scan it, so the longer it
 * takes to mount UBIFS. This is why the journal has limited size which may be
 * changed depending on the system requirements. But a larger journal gives
 * faster I/O speed because it writes the index less frequently. So this is a
 * trade-off. Also, the journal is indexed by the in-memory index (TNC), so the
 * larger is the journal, the more memory its index may consume.
 */

#include "ubifs.h"

/**
 * struct replay_entry - replay tree entry.
 * @lnum: logical eraseblock number of the node
 * @offs: node offset
 * @len: node length
 * @deletion: non-zero if this entry corresponds to a node deletion
 * @sqnum: node sequence number
 * @rb: links the replay tree
 * @key: node key
 * @nm: directory entry name
 * @old_size: truncation old size
 * @new_size: truncation new size
 *
 * UBIFS journal replay must compare node sequence numbers, which means it must
 * build a tree of node information to insert into the TNC.
 */
struct replay_entry {
	int lnum;
	int offs;
	int len;
	unsigned int deletion:1;
	unsigned long long sqnum;
	struct rb_node rb;
	union ubifs_key key;
	union {
		struct qstr nm;
		struct {
			loff_t old_size;
			loff_t new_size;
		};
	};
};

/**
 * struct bud_entry - entry in the list of buds to replay.
 * @list: next bud in the list
 * @bud: bud description object
 * @sqnum: reference node sequence number
 * @free: free bytes in the bud
 * @dirty: dirty bytes in the bud
 */
struct bud_entry {
	struct list_head list;
	struct ubifs_bud *bud;
	unsigned long long sqnum;
	int free;
	int dirty;
};

/**
 * set_bud_lprops - set free and dirty space used by a bud.
 * @c: UBIFS file-system description object
 * @b: bud entry which describes the bud
 *
 * This function makes sure the LEB properties of bud @b are set correctly
 * after the replay. Returns zero in case of success and a negative error code
 * in case of failure.
 */
static int set_bud_lprops(struct ubifs_info *c, struct bud_entry *b)
{
	const struct ubifs_lprops *lp;
	int err = 0, dirty;

	ubifs_get_lprops(c);

	lp = ubifs_lpt_lookup_dirty(c, b->bud->lnum);
	if (IS_ERR(lp)) {
		err = PTR_ERR(lp);
		goto out;
	}

	dirty = lp->dirty;
	if (b->bud->start == 0 && (lp->free != c->leb_size || lp->dirty != 0)) {
		/*
		 * The LEB was added to the journal with a starting offset of
		 * zero which means the LEB must have been empty. The LEB
		 * property values should be @lp->free == @c->leb_size and
		 * @lp->dirty == 0, but that is not the case. The reason is that
		 * the LEB had been garbage collected before it became the bud,
		 * and there was not commit inbetween. The garbage collector
		 * resets the free and dirty space without recording it
		 * anywhere except lprops, so if there was no commit then
		 * lprops does not have that information.
		 *
		 * We do not need to adjust free space because the scan has told
		 * us the exact value which is recorded in the replay entry as
		 * @b->free.
		 *
		 * However we do need to subtract from the dirty space the
		 * amount of space that the garbage collector reclaimed, which
		 * is the whole LEB minus the amount of space that was free.
		 */
		dbg_mnt("bud LEB %d was GC'd (%d free, %d dirty)", b->bud->lnum,
			lp->free, lp->dirty);
		dbg_gc("bud LEB %d was GC'd (%d free, %d dirty)", b->bud->lnum,
			lp->free, lp->dirty);
		dirty -= c->leb_size - lp->free;
		/*
		 * If the replay order was perfect the dirty space would now be
		 * zero. The order is not perfect because the journal heads
		 * race with each other. This is not a problem but is does mean
		 * that the dirty space may temporarily exceed c->leb_size
		 * during the replay.
		 */
		if (dirty != 0)
			dbg_msg("LEB %d lp: %d free %d dirty "
				"replay: %d free %d dirty", b->bud->lnum,
				lp->free, lp->dirty, b->free, b->dirty);
	}
	lp = ubifs_change_lp(c, lp, b->free, dirty + b->dirty,
			     lp->flags | LPROPS_TAKEN, 0);
	if (IS_ERR(lp)) {
		err = PTR_ERR(lp);
		goto out;
	}

	/* Make sure the journal head points to the latest bud */
	err = ubifs_wbuf_seek_nolock(&c->jheads[b->bud->jhead].wbuf,
				     b->bud->lnum, c->leb_size - b->free,
				     UBI_SHORTTERM);

out:
	ubifs_release_lprops(c);
	return err;
}

/**
 * set_buds_lprops - set free and dirty space for all replayed buds.
 * @c: UBIFS file-system description object
 *
 * This function sets LEB properties for all replayed buds. Returns zero in
 * case of success and a negative error code in case of failure.
 */
static int set_buds_lprops(struct ubifs_info *c)
{
	struct bud_entry *b;
	int err;

	list_for_each_entry(b, &c->replay_buds, list) {
		err = set_bud_lprops(c, b);
		if (err)
			return err;
	}

	return 0;
}

/**
 * trun_remove_range - apply a replay entry for a truncation to the TNC.
 * @c: UBIFS file-system description object
 * @r: replay entry of truncation
 */
static int trun_remove_range(struct ubifs_info *c, struct replay_entry *r)
{
	unsigned min_blk, max_blk;
	union ubifs_key min_key, max_key;
	ino_t ino;

	min_blk = r->new_size / UBIFS_BLOCK_SIZE;
	if (r->new_size & (UBIFS_BLOCK_SIZE - 1))
		min_blk += 1;

	max_blk = r->old_size / UBIFS_BLOCK_SIZE;
	if ((r->old_size & (UBIFS_BLOCK_SIZE - 1)) == 0)
		max_blk -= 1;

	ino = key_inum(c, &r->key);

	data_key_init(c, &min_key, ino, min_blk);
	data_key_init(c, &max_key, ino, max_blk);

	return ubifs_tnc_remove_range(c, &min_key, &max_key);
}

/**
 * apply_replay_entry - apply a replay entry to the TNC.
 * @c: UBIFS file-system description object
 * @r: replay entry to apply
 *
 * Apply a replay entry to the TNC.
 */
static int apply_replay_entry(struct ubifs_info *c, struct replay_entry *r)
{
	int err;

	dbg_mnt("LEB %d:%d len %d deletion %d sqnum %llu %s", r->lnum,
		r->offs, r->len, r->deletion, r->sqnum, DBGKEY(&r->key));

	/* Set c->replay_sqnum to help deal with dangling branches. */
	c->replay_sqnum = r->sqnum;

	if (is_hash_key(c, &r->key)) {
		if (r->deletion)
			err = ubifs_tnc_remove_nm(c, &r->key, &r->nm);
		else
			err = ubifs_tnc_add_nm(c, &r->key, r->lnum, r->offs,
					       r->len, &r->nm);
	} else {
		if (r->deletion)
			switch (key_type(c, &r->key)) {
			case UBIFS_INO_KEY:
			{
				ino_t inum = key_inum(c, &r->key);

				err = ubifs_tnc_remove_ino(c, inum);
				break;
			}
			case UBIFS_TRUN_KEY:
				err = trun_remove_range(c, r);
				break;
			default:
				err = ubifs_tnc_remove(c, &r->key);
				break;
			}
		else
			err = ubifs_tnc_add(c, &r->key, r->lnum, r->offs,
					    r->len);
		if (err)
			return err;

		if (c->need_recovery)
			err = ubifs_recover_size_accum(c, &r->key, r->deletion,
						       r->new_size);
	}

	return err;
}

/**
 * destroy_replay_tree - destroy the replay.
 * @c: UBIFS file-system description object
 *
 * Destroy the replay tree.
 */
static void destroy_replay_tree(struct ubifs_info *c)
{
	struct rb_node *this = c->replay_tree.rb_node;
	struct replay_entry *r;

	while (this) {
		if (this->rb_left) {
			this = this->rb_left;
			continue;
		} else if (this->rb_right) {
			this = this->rb_right;
			continue;
		}
		r = rb_entry(this, struct replay_entry, rb);
		this = rb_parent(this);
		if (this) {
			if (this->rb_left == &r->rb)
				this->rb_left = NULL;
			else
				this->rb_right = NULL;
		}
		if (is_hash_key(c, &r->key))
			kfree(r->nm.name);
		kfree(r);
	}
	c->replay_tree = RB_ROOT;
}

/**
 * apply_replay_tree - apply the replay tree to the TNC.
 * @c: UBIFS file-system description object
 *
 * Apply the replay tree.
 * Returns zero in case of success and a negative error code in case of
 * failure.
 */
static int apply_replay_tree(struct ubifs_info *c)
{
	struct rb_node *this = rb_first(&c->replay_tree);

	while (this) {
		struct replay_entry *r;
		int err;

		cond_resched();

		r = rb_entry(this, struct replay_entry, rb);
		err = apply_replay_entry(c, r);
		if (err)
			return err;
		this = rb_next(this);
	}
	return 0;
}

/**
 * insert_node - insert a node to the replay tree.
 * @c: UBIFS file-system description object
 * @lnum: node logical eraseblock number
 * @offs: node offset
 * @len: node length
 * @key: node key
 * @sqnum: sequence number
 * @deletion: non-zero if this is a deletion
 * @used: number of bytes in use in a LEB
 * @old_size: truncation old size
 * @new_size: truncation new size
 *
 * This function inserts a scanned non-direntry node to the replay tree. The
 * replay tree is an RB-tree containing @struct replay_entry elements which are
 * indexed by the sequence number. The replay tree is applied at the very end
 * of the replay process. Since the tree is sorted in sequence number order,
 * the older modifications are applied first. This function returns zero in
 * case of success and a negative error code in case of failure.
 */
static int insert_node(struct ubifs_info *c, int lnum, int offs, int len,
		       union ubifs_key *key, unsigned long long sqnum,
		       int deletion, int *used, loff_t old_size,
		       loff_t new_size)
{
	struct rb_node **p = &c->replay_tree.rb_node, *parent = NULL;
	struct replay_entry *r;

	if (key_inum(c, key) >= c->highest_inum)
		c->highest_inum = key_inum(c, key);

	dbg_mnt("add LEB %d:%d, key %s", lnum, offs, DBGKEY(key));
	while (*p) {
		parent = *p;
		r = rb_entry(parent, struct replay_entry, rb);
		if (sqnum < r->sqnum) {
			p = &(*p)->rb_left;
			continue;
		} else if (sqnum > r->sqnum) {
			p = &(*p)->rb_right;
			continue;
		}
		ubifs_err("duplicate sqnum in replay");
		return -EINVAL;
	}

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

	if (!deletion)
		*used += ALIGN(len, 8);
	r->lnum = lnum;
	r->offs = offs;
	r->len = len;
	r->deletion = !!deletion;
	r->sqnum = sqnum;
	key_copy(c, key, &r->key);
	r->old_size = old_size;
	r->new_size = new_size;

	rb_link_node(&r->rb, parent, p);
	rb_insert_color(&r->rb, &c->replay_tree);
	return 0;
}

/**
 * insert_dent - insert a directory entry node into the replay tree.
 * @c: UBIFS file-system description object
 * @lnum: node logical eraseblock number
 * @offs: node offset
 * @len: node length
 * @key: node key
 * @name: directory entry name
 * @nlen: directory entry name length
 * @sqnum: sequence number
 * @deletion: non-zero if this is a deletion
 * @used: number of bytes in use in a LEB
 *
 * This function inserts a scanned directory entry node to the replay tree.
 * Returns zero in case of success and a negative error code in case of
 * failure.
 *
 * This function is also used for extended attribute entries because they are
 * implemented as directory entry nodes.
 */
static int insert_dent(struct ubifs_info *c, int lnum, int offs, int len,
		       union ubifs_key *key, const char *name, int nlen,
		       unsigned long long sqnum, int deletion, int *used)
{
	struct rb_node **p = &c->replay_tree.rb_node, *parent = NULL;
	struct replay_entry *r;
	char *nbuf;

	if (key_inum(c, key) >= c->highest_inum)
		c->highest_inum = key_inum(c, key);

	dbg_mnt("add LEB %d:%d, key %s", lnum, offs, DBGKEY(key));
	while (*p) {
		parent = *p;
		r = rb_entry(parent, struct replay_entry, rb);
		if (sqnum < r->sqnum) {
			p = &(*p)->rb_left;
			continue;
		}
		if (sqnum > r->sqnum) {
			p = &(*p)->rb_right;
			continue;
		}
		ubifs_err("duplicate sqnum in replay");
		return -EINVAL;
	}

	r = kzalloc(sizeof(struct replay_entry), GFP_KERNEL);
	if (!r)
		return -ENOMEM;
	nbuf = kmalloc(nlen + 1, GFP_KERNEL);
	if (!nbuf) {
		kfree(r);
		return -ENOMEM;
	}

	if (!deletion)
		*used += ALIGN(len, 8);
	r->lnum = lnum;
	r->offs = offs;
	r->len = len;
	r->deletion = !!deletion;
	r->sqnum = sqnum;
	key_copy(c, key, &r->key);
	r->nm.len = nlen;
	memcpy(nbuf, name, nlen);
	nbuf[nlen] = '\0';
	r->nm.name = nbuf;

	ubifs_assert(!*p);
	rb_link_node(&r->rb, parent, p);
	rb_insert_color(&r->rb, &c->replay_tree);
	return 0;
}

/**
 * ubifs_validate_entry - validate directory or extended attribute entry node.
 * @c: UBIFS file-system description object
 * @dent: the node to validate
 *
 * This function validates directory or extended attribute entry node @dent.
 * Returns zero if the node is all right and a %-EINVAL if not.
 */
int ubifs_validate_entry(struct ubifs_info *c,
			 const struct ubifs_dent_node *dent)
{
	int key_type = key_type_flash(c, dent->key);
	int nlen = le16_to_cpu(dent->nlen);

	if (le32_to_cpu(dent->ch.len) != nlen + UBIFS_DENT_NODE_SZ + 1 ||
	    dent->type >= UBIFS_ITYPES_CNT ||
	    nlen > UBIFS_MAX_NLEN || dent->name[nlen] != 0 ||
	    strnlen(dent->name, nlen) != nlen ||
	    le64_to_cpu(dent->inum) > MAX_INUM) {
		ubifs_err("bad %s node", key_type == UBIFS_DENT_KEY ?
			  "directory entry" : "extended attribute entry");
		return -EINVAL;
	}

	if (key_type != UBIFS_DENT_KEY && key_type != UBIFS_XENT_KEY) {
		ubifs_err("bad key type %d", key_type);
		return -EINVAL;
	}

	return 0;
}

/**
 * replay_bud - replay a bud logical eraseblock.
 * @c: UBIFS file-system description object
 * @lnum: bud logical eraseblock number to replay
 * @offs: bud start offset
 * @jhead: journal head to which this bud belongs
 * @free: amount of free space in the bud is returned here
 * @dirty: amount of dirty space from padding and deletion nodes is returned
 * here
 *
 * This function returns zero in case of success and a negative error code in
 * case of failure.
 */
static int replay_bud(struct ubifs_info *c, int lnum, int offs, int jhead,
		      int *free, int *dirty)
{
	int err = 0, used = 0;
	struct ubifs_scan_leb *sleb;
	struct ubifs_scan_node *snod;
	struct ubifs_bud *bud;

	dbg_mnt("replay bud LEB %d, head %d, offs %d", lnum, jhead, offs);
	if (c->need_recovery)
		sleb = ubifs_recover_leb(c, lnum, offs, c->sbuf, jhead != GCHD);
	else
		sleb = ubifs_scan(c, lnum, offs, c->sbuf, 0);
	if (IS_ERR(sleb))
		return PTR_ERR(sleb);

	/*
	 * The bud does not have to start from offset zero - the beginning of
	 * the 'lnum' LEB may contain previously committed data. One of the
	 * things we have to do in replay is to correctly update lprops with
	 * newer information about this LEB.
	 *
	 * At this point lprops thinks that this LEB has 'c->leb_size - offs'
	 * bytes of free space because it only contain information about
	 * committed data.
	 *
	 * But we know that real amount of free space is 'c->leb_size -
	 * sleb->endpt', and the space in the 'lnum' LEB between 'offs' and
	 * 'sleb->endpt' is used by bud data. We have to correctly calculate
	 * how much of these data are dirty and update lprops with this
	 * information.
	 *
	 * The dirt in that LEB region is comprised of padding nodes, deletion
	 * nodes, truncation nodes and nodes which are obsoleted by subsequent
	 * nodes in this LEB. So instead of calculating clean space, we
	 * calculate used space ('used' variable).
	 */

	list_for_each_entry(snod, &sleb->nodes, list) {
		int deletion = 0;

		cond_resched();

		if (snod->sqnum >= SQNUM_WATERMARK) {
			ubifs_err("file system's life ended");
			goto out_dump;
		}

		if (snod->sqnum > c->max_sqnum)
			c->max_sqnum = snod->sqnum;

		switch (snod->type) {
		case UBIFS_INO_NODE:
		{
			struct ubifs_ino_node *ino = snod->node;
			loff_t new_size = le64_to_cpu(ino->size);

			if (le32_to_cpu(ino->nlink) == 0)
				deletion = 1;
			err = insert_node(c, lnum, snod->offs, snod->len,
					  &snod->key, snod->sqnum, deletion,
					  &used, 0, new_size);
			break;
		}
		case UBIFS_DATA_NODE:
		{
			struct ubifs_data_node *dn = snod->node;
			loff_t new_size = le32_to_cpu(dn->size) +
					  key_block(c, &snod->key) *
					  UBIFS_BLOCK_SIZE;

			err = insert_node(c, lnum, snod->offs, snod->len,
					  &snod->key, snod->sqnum, deletion,
					  &used, 0, new_size);
			break;
		}
		case UBIFS_DENT_NODE:
		case UBIFS_XENT_NODE:
		{
			struct ubifs_dent_node *dent = snod->node;

			err = ubifs_validate_entry(c, dent);
			if (err)
				goto out_dump;

			err = insert_dent(c, lnum, snod->offs, snod->len,
					  &snod->key, dent->name,
					  le16_to_cpu(dent->nlen), snod->sqnum,
					  !le64_to_cpu(dent->inum), &used);
			break;
		}
		case UBIFS_TRUN_NODE:
		{
			struct ubifs_trun_node *trun = snod->node;
			loff_t old_size = le64_to_cpu(trun->old_size);
			loff_t new_size = le64_to_cpu(trun->new_size);
			union ubifs_key key;

			/* Validate truncation node */
			if (old_size < 0 || old_size > c->max_inode_sz ||
			    new_size < 0 || new_size > c->max_inode_sz ||
			    old_size <= new_size) {
				ubifs_err("bad truncation node");
				goto out_dump;
			}

			/*
			 * Create a fake truncation key just to use the same
			 * functions which expect nodes to have keys.
			 */
			trun_key_init(c, &key, le32_to_cpu(trun->inum));
			err = insert_node(c, lnum, snod->offs, snod->len,
					  &key, snod->sqnum, 1, &used,
					  old_size, new_size);
			break;
		}
		default:
			ubifs_err("unexpected node type %d in bud LEB %d:%d",
				  snod->type, lnum, snod->offs);
			err = -EINVAL;
			goto out_dump;
		}
		if (err)
			goto out;
	}

	bud = ubifs_search_bud(c, lnum);
	if (!bud)
		BUG();

	ubifs_assert(sleb->endpt - offs >= used);
	ubifs_assert(sleb->endpt % c->min_io_size == 0);

	*dirty = sleb->endpt - offs - used;
	*free = c->leb_size - sleb->endpt;
	dbg_mnt("bud LEB %d replied: dirty %d, free %d", lnum, *dirty, *free);

out:
	ubifs_scan_destroy(sleb);
	return err;

out_dump:
	ubifs_err("bad node is at LEB %d:%d", lnum, snod->offs);
	dbg_dump_node(c, snod->node);
	ubifs_scan_destroy(sleb);
	return -EINVAL;
}

/**
 * replay_buds - replay all buds.
 * @c: UBIFS file-system description object
 *
 * This function returns zero in case of success and a negative error code in
 * case of failure.
 */
static int replay_buds(struct ubifs_info *c)
{
	struct bud_entry *b;
	int err;
	unsigned long long prev_sqnum = 0;

	list_for_each_entry(b, &c->replay_buds, list) {
		err = replay_bud(c, b->bud->lnum, b->bud->start, b->bud->jhead,
				 &b->free, &b->dirty);
		if (err)
			return err;

		ubifs_assert(b->sqnum > prev_sqnum);
		prev_sqnum = b->sqnum;
	}

	return 0;
}

/**
 * destroy_bud_list - destroy the list of buds to replay.
 * @c: UBIFS file-system description object
 */
static void destroy_bud_list(struct ubifs_info *c)
{
	struct bud_entry *b;

	while (!list_empty(&c->replay_buds)) {
		b = list_entry(c->replay_buds.next, struct bud_entry, list);
		list_del(&b->list);
		kfree(b);
	}
}

/**
 * add_replay_bud - add a bud to the list of buds to replay.
 * @c: UBIFS file-system description object
 * @lnum: bud logical eraseblock number to replay
 * @offs: bud start offset
 * @jhead: journal head to which this bud belongs
 * @sqnum: reference node sequence number
 *
 * This function returns zero in case of success and a negative error code in
 * case of failure.
 */
static int add_replay_bud(struct ubifs_info *c, int lnum, int offs, int jhead,
			  unsigned long long sqnum)
{
	struct ubifs_bud *bud;
	struct bud_entry *b;

	dbg_mnt("add replay bud LEB %d:%d, head %d", lnum, offs, jhead);

	bud = kmalloc(sizeof(struct ubifs_bud), GFP_KERNEL);
	if (!bud)
		return -ENOMEM;

	b = kmalloc(sizeof(struct bud_entry), GFP_KERNEL);
	if (!b) {
		kfree(bud);
		return -ENOMEM;
	}

	bud->lnum = lnum;
	bud->start = offs;
	bud->jhead = jhead;
	ubifs_add_bud(c, bud);

	b->bud = bud;
	b->sqnum = sqnum;
	list_add_tail(&b->list, &c->replay_buds);

	return 0;
}

/**
 * validate_ref - validate a reference node.
 * @c: UBIFS file-system description object
 * @ref: the reference node to validate
 * @ref_lnum: LEB number of the reference node
 * @ref_offs: reference node offset
 *
 * This function returns %1 if a bud reference already exists for the LEB. %0 is
 * returned if the reference node is new, otherwise %-EINVAL is returned if
 * validation failed.
 */
static int validate_ref(struct ubifs_info *c, const struct ubifs_ref_node *ref)
{
	struct ubifs_bud *bud;
	int lnum = le32_to_cpu(ref->lnum);
	unsigned int offs = le32_to_cpu(ref->offs);
	unsigned int jhead = le32_to_cpu(ref->jhead);

	/*
	 * ref->offs may point to the end of LEB when the journal head points
	 * to the end of LEB and we write reference node for it during commit.
	 * So this is why we require 'offs > c->leb_size'.
	 */
	if (jhead >= c->jhead_cnt || lnum >= c->leb_cnt ||
	    lnum < c->main_first || offs > c->leb_size ||
	    offs & (c->min_io_size - 1))
		return -EINVAL;

	/* Make sure we have not already looked at this bud */
	bud = ubifs_search_bud(c, lnum);
	if (bud) {
		if (bud->jhead == jhead && bud->start <= offs)
			return 1;
		ubifs_err("bud at LEB %d:%d was already referred", lnum, offs);
		return -EINVAL;
	}

	return 0;
}

/**
 * replay_log_leb - replay a log logical eraseblock.
 * @c: UBIFS file-system description object
 * @lnum: log logical eraseblock to replay
 * @offs: offset to start replaying from
 * @sbuf: scan buffer
 *
 * This function replays a log LEB and returns zero in case of success, %1 if
 * this is the last LEB in the log, and a negative error code in case of
 * failure.
 */
static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf)
{
	int err;
	struct ubifs_scan_leb *sleb;
	struct ubifs_scan_node *snod;
	const struct ubifs_cs_node *node;

	dbg_mnt("replay log LEB %d:%d", lnum, offs);
	sleb = ubifs_scan(c, lnum, offs, sbuf, c->need_recovery);
	if (IS_ERR(sleb)) {
		if (PTR_ERR(sleb) != -EUCLEAN || !c->need_recovery)
			return PTR_ERR(sleb);
		/*
		 * Note, the below function will recover this log LEB only if
		 * it is the last, because unclean reboots can possibly corrupt
		 * only the tail of the log.
		 */
		sleb = ubifs_recover_log_leb(c, lnum, offs, sbuf);
		if (IS_ERR(sleb))
			return PTR_ERR(sleb);
	}

	if (sleb->nodes_cnt == 0) {
		err = 1;
		goto out;
	}

	node = sleb->buf;
	snod = list_entry(sleb->nodes.next, struct ubifs_scan_node, list);
	if (c->cs_sqnum == 0) {
		/*
		 * This is the first log LEB we are looking at, make sure that
		 * the first node is a commit start node. Also record its
		 * sequence number so that UBIFS can determine where the log
		 * ends, because all nodes which were have higher sequence
		 * numbers.
		 */
		if (snod->type != UBIFS_CS_NODE) {
			dbg_err("first log node at LEB %d:%d is not CS node",
				lnum, offs);
			goto out_dump;
		}
		if (le64_to_cpu(node->cmt_no) != c->cmt_no) {
			dbg_err("first CS node at LEB %d:%d has wrong "
				"commit number %llu expected %llu",
				lnum, offs,
				(unsigned long long)le64_to_cpu(node->cmt_no),
				c->cmt_no);
			goto out_dump;
		}

		c->cs_sqnum = le64_to_cpu(node->ch.sqnum);
		dbg_mnt("commit start sqnum %llu", c->cs_sqnum);
	}

	if (snod->sqnum < c->cs_sqnum) {
		/*
		 * This means that we reached end of log and now
		 * look to the older log data, which was already
		 * committed but the eraseblock was not erased (UBIFS
		 * only un-maps it). So this basically means we have to
		 * exit with "end of log" code.
		 */
		err = 1;
		goto out;
	}

	/* Make sure the first node sits at offset zero of the LEB */
	if (snod->offs != 0) {
		dbg_err("first node is not at zero offset");
		goto out_dump;
	}

	list_for_each_entry(snod, &sleb->nodes, list) {
		cond_resched();

		if (snod->sqnum >= SQNUM_WATERMARK) {
			ubifs_err("file system's life ended");
			goto out_dump;
		}

		if (snod->sqnum < c->cs_sqnum) {
			dbg_err("bad sqnum %llu, commit sqnum %llu",
				snod->sqnum, c->cs_sqnum);
			goto out_dump;
		}

		if (snod->sqnum > c->max_sqnum)
			c->max_sqnum = snod->sqnum;

		switch (snod->type) {
		case UBIFS_REF_NODE: {
			const struct ubifs_ref_node *ref = snod->node;

			err = validate_ref(c, ref);
			if (err == 1)
				break; /* Already have this bud */
			if (err)
				goto out_dump;

			err = add_replay_bud(c, le32_to_cpu(ref->lnum),
					     le32_to_cpu(ref->offs),
					     le32_to_cpu(ref->jhead),
					     snod->sqnum);
			if (err)
				goto out;

			break;
		}
		case UBIFS_CS_NODE:
			/* Make sure it sits at the beginning of LEB */
			if (snod->offs != 0) {
				ubifs_err("unexpected node in log");
				goto out_dump;
			}
			break;
		default:
			ubifs_err("unexpected node in log");
			goto out_dump;
		}
	}

	if (sleb->endpt || c->lhead_offs >= c->leb_size) {
		c->lhead_lnum = lnum;
		c->lhead_offs = sleb->endpt;
	}

	err = !sleb->endpt;
out:
	ubifs_scan_destroy(sleb);
	return err;

out_dump:
	ubifs_err("log error detected while replaying the log at LEB %d:%d",
		  lnum, offs + snod->offs);
	dbg_dump_node(c, snod->node);
	ubifs_scan_destroy(sleb);
	return -EINVAL;
}

/**
 * take_ihead - update the status of the index head in lprops to 'taken'.
 * @c: UBIFS file-system description object
 *
 * This function returns the amount of free space in the index head LEB or a
 * negative error code.
 */
static int take_ihead(struct ubifs_info *c)
{
	const struct ubifs_lprops *lp;
	int err, free;

	ubifs_get_lprops(c);

	lp = ubifs_lpt_lookup_dirty(c, c->ihead_lnum);
	if (IS_ERR(lp)) {
		err = PTR_ERR(lp);
		goto out;
	}

	free = lp->free;

	lp = ubifs_change_lp(c, lp, LPROPS_NC, LPROPS_NC,
			     lp->flags | LPROPS_TAKEN, 0);
	if (IS_ERR(lp)) {
		err = PTR_ERR(lp);
		goto out;
	}

	err = free;
out:
	ubifs_release_lprops(c);
	return err;
}

/**
 * ubifs_replay_journal - replay journal.
 * @c: UBIFS file-system description object
 *
 * This function scans the journal, replays and cleans it up. It makes sure all
 * memory data structures related to uncommitted journal are built (dirty TNC
 * tree, tree of buds, modified lprops, etc).
 */
int ubifs_replay_journal(struct ubifs_info *c)
{
	int err, i, lnum, offs, free;

	BUILD_BUG_ON(UBIFS_TRUN_KEY > 5);

	/* Update the status of the index head in lprops to 'taken' */
	free = take_ihead(c);
	if (free < 0)
		return free; /* Error code */

	if (c->ihead_offs != c->leb_size - free) {
		ubifs_err("bad index head LEB %d:%d", c->ihead_lnum,
			  c->ihead_offs);
		return -EINVAL;
	}

	dbg_mnt("start replaying the journal");
	c->replaying = 1;
	lnum = c->ltail_lnum = c->lhead_lnum;
	offs = c->lhead_offs;

	for (i = 0; i < c->log_lebs; i++, lnum++) {
		if (lnum >= UBIFS_LOG_LNUM + c->log_lebs) {
			/*
			 * The log is logically circular, we reached the last
			 * LEB, switch to the first one.
			 */
			lnum = UBIFS_LOG_LNUM;
			offs = 0;
		}
		err = replay_log_leb(c, lnum, offs, c->sbuf);
		if (err == 1)
			/* We hit the end of the log */
			break;
		if (err)
			goto out;
		offs = 0;
	}

	err = replay_buds(c);
	if (err)
		goto out;

	err = apply_replay_tree(c);
	if (err)
		goto out;

	err = set_buds_lprops(c);
	if (err)
		goto out;

	/*
	 * UBIFS budgeting calculations use @c->bi.uncommitted_idx variable
	 * to roughly estimate index growth. Things like @c->bi.min_idx_lebs
	 * depend on it. This means we have to initialize it to make sure
	 * budgeting works properly.
	 */
	c->bi.uncommitted_idx = atomic_long_read(&c->dirty_zn_cnt);
	c->bi.uncommitted_idx *= c->max_idx_node_sz;

	ubifs_assert(c->bud_bytes <= c->max_bud_bytes || c->need_recovery);
	dbg_mnt("finished, log head LEB %d:%d, max_sqnum %llu, "
		"highest_inum %lu", c->lhead_lnum, c->lhead_offs, c->max_sqnum,
		(unsigned long)c->highest_inum);
out:
	destroy_replay_tree(c);
	destroy_bud_list(c);
	c->replaying = 0;
	return err;
}