forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
xfs_log_recover.c
4052 lines (3713 loc) · 110 KB
/
xfs_log_recover.c
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
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would 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 the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_error.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_imap.h"
#include "xfs_alloc.h"
#include "xfs_ialloc.h"
#include "xfs_log_priv.h"
#include "xfs_buf_item.h"
#include "xfs_log_recover.h"
#include "xfs_extfree_item.h"
#include "xfs_trans_priv.h"
#include "xfs_quota.h"
#include "xfs_rw.h"
STATIC int xlog_find_zeroed(xlog_t *, xfs_daddr_t *);
STATIC int xlog_clear_stale_blocks(xlog_t *, xfs_lsn_t);
STATIC void xlog_recover_insert_item_backq(xlog_recover_item_t **q,
xlog_recover_item_t *item);
#if defined(DEBUG)
STATIC void xlog_recover_check_summary(xlog_t *);
STATIC void xlog_recover_check_ail(xfs_mount_t *, xfs_log_item_t *, int);
#else
#define xlog_recover_check_summary(log)
#define xlog_recover_check_ail(mp, lip, gen)
#endif
/*
* Sector aligned buffer routines for buffer create/read/write/access
*/
#define XLOG_SECTOR_ROUNDUP_BBCOUNT(log, bbs) \
( ((log)->l_sectbb_mask && (bbs & (log)->l_sectbb_mask)) ? \
((bbs + (log)->l_sectbb_mask + 1) & ~(log)->l_sectbb_mask) : (bbs) )
#define XLOG_SECTOR_ROUNDDOWN_BLKNO(log, bno) ((bno) & ~(log)->l_sectbb_mask)
xfs_buf_t *
xlog_get_bp(
xlog_t *log,
int num_bblks)
{
ASSERT(num_bblks > 0);
if (log->l_sectbb_log) {
if (num_bblks > 1)
num_bblks += XLOG_SECTOR_ROUNDUP_BBCOUNT(log, 1);
num_bblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, num_bblks);
}
return xfs_buf_get_noaddr(BBTOB(num_bblks), log->l_mp->m_logdev_targp);
}
void
xlog_put_bp(
xfs_buf_t *bp)
{
xfs_buf_free(bp);
}
/*
* nbblks should be uint, but oh well. Just want to catch that 32-bit length.
*/
int
xlog_bread(
xlog_t *log,
xfs_daddr_t blk_no,
int nbblks,
xfs_buf_t *bp)
{
int error;
if (log->l_sectbb_log) {
blk_no = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, blk_no);
nbblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, nbblks);
}
ASSERT(nbblks > 0);
ASSERT(BBTOB(nbblks) <= XFS_BUF_SIZE(bp));
ASSERT(bp);
XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
XFS_BUF_READ(bp);
XFS_BUF_BUSY(bp);
XFS_BUF_SET_COUNT(bp, BBTOB(nbblks));
XFS_BUF_SET_TARGET(bp, log->l_mp->m_logdev_targp);
xfsbdstrat(log->l_mp, bp);
if ((error = xfs_iowait(bp)))
xfs_ioerror_alert("xlog_bread", log->l_mp,
bp, XFS_BUF_ADDR(bp));
return error;
}
/*
* Write out the buffer at the given block for the given number of blocks.
* The buffer is kept locked across the write and is returned locked.
* This can only be used for synchronous log writes.
*/
STATIC int
xlog_bwrite(
xlog_t *log,
xfs_daddr_t blk_no,
int nbblks,
xfs_buf_t *bp)
{
int error;
if (log->l_sectbb_log) {
blk_no = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, blk_no);
nbblks = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, nbblks);
}
ASSERT(nbblks > 0);
ASSERT(BBTOB(nbblks) <= XFS_BUF_SIZE(bp));
XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no);
XFS_BUF_ZEROFLAGS(bp);
XFS_BUF_BUSY(bp);
XFS_BUF_HOLD(bp);
XFS_BUF_PSEMA(bp, PRIBIO);
XFS_BUF_SET_COUNT(bp, BBTOB(nbblks));
XFS_BUF_SET_TARGET(bp, log->l_mp->m_logdev_targp);
if ((error = xfs_bwrite(log->l_mp, bp)))
xfs_ioerror_alert("xlog_bwrite", log->l_mp,
bp, XFS_BUF_ADDR(bp));
return error;
}
STATIC xfs_caddr_t
xlog_align(
xlog_t *log,
xfs_daddr_t blk_no,
int nbblks,
xfs_buf_t *bp)
{
xfs_caddr_t ptr;
if (!log->l_sectbb_log)
return XFS_BUF_PTR(bp);
ptr = XFS_BUF_PTR(bp) + BBTOB((int)blk_no & log->l_sectbb_mask);
ASSERT(XFS_BUF_SIZE(bp) >=
BBTOB(nbblks + (blk_no & log->l_sectbb_mask)));
return ptr;
}
#ifdef DEBUG
/*
* dump debug superblock and log record information
*/
STATIC void
xlog_header_check_dump(
xfs_mount_t *mp,
xlog_rec_header_t *head)
{
int b;
cmn_err(CE_DEBUG, "%s: SB : uuid = ", __FUNCTION__);
for (b = 0; b < 16; b++)
cmn_err(CE_DEBUG, "%02x", ((uchar_t *)&mp->m_sb.sb_uuid)[b]);
cmn_err(CE_DEBUG, ", fmt = %d\n", XLOG_FMT);
cmn_err(CE_DEBUG, " log : uuid = ");
for (b = 0; b < 16; b++)
cmn_err(CE_DEBUG, "%02x",((uchar_t *)&head->h_fs_uuid)[b]);
cmn_err(CE_DEBUG, ", fmt = %d\n", INT_GET(head->h_fmt, ARCH_CONVERT));
}
#else
#define xlog_header_check_dump(mp, head)
#endif
/*
* check log record header for recovery
*/
STATIC int
xlog_header_check_recover(
xfs_mount_t *mp,
xlog_rec_header_t *head)
{
ASSERT(INT_GET(head->h_magicno, ARCH_CONVERT) == XLOG_HEADER_MAGIC_NUM);
/*
* IRIX doesn't write the h_fmt field and leaves it zeroed
* (XLOG_FMT_UNKNOWN). This stops us from trying to recover
* a dirty log created in IRIX.
*/
if (unlikely(INT_GET(head->h_fmt, ARCH_CONVERT) != XLOG_FMT)) {
xlog_warn(
"XFS: dirty log written in incompatible format - can't recover");
xlog_header_check_dump(mp, head);
XFS_ERROR_REPORT("xlog_header_check_recover(1)",
XFS_ERRLEVEL_HIGH, mp);
return XFS_ERROR(EFSCORRUPTED);
} else if (unlikely(!uuid_equal(&mp->m_sb.sb_uuid, &head->h_fs_uuid))) {
xlog_warn(
"XFS: dirty log entry has mismatched uuid - can't recover");
xlog_header_check_dump(mp, head);
XFS_ERROR_REPORT("xlog_header_check_recover(2)",
XFS_ERRLEVEL_HIGH, mp);
return XFS_ERROR(EFSCORRUPTED);
}
return 0;
}
/*
* read the head block of the log and check the header
*/
STATIC int
xlog_header_check_mount(
xfs_mount_t *mp,
xlog_rec_header_t *head)
{
ASSERT(INT_GET(head->h_magicno, ARCH_CONVERT) == XLOG_HEADER_MAGIC_NUM);
if (uuid_is_nil(&head->h_fs_uuid)) {
/*
* IRIX doesn't write the h_fs_uuid or h_fmt fields. If
* h_fs_uuid is nil, we assume this log was last mounted
* by IRIX and continue.
*/
xlog_warn("XFS: nil uuid in log - IRIX style log");
} else if (unlikely(!uuid_equal(&mp->m_sb.sb_uuid, &head->h_fs_uuid))) {
xlog_warn("XFS: log has mismatched uuid - can't recover");
xlog_header_check_dump(mp, head);
XFS_ERROR_REPORT("xlog_header_check_mount",
XFS_ERRLEVEL_HIGH, mp);
return XFS_ERROR(EFSCORRUPTED);
}
return 0;
}
STATIC void
xlog_recover_iodone(
struct xfs_buf *bp)
{
xfs_mount_t *mp;
ASSERT(XFS_BUF_FSPRIVATE(bp, void *));
if (XFS_BUF_GETERROR(bp)) {
/*
* We're not going to bother about retrying
* this during recovery. One strike!
*/
mp = XFS_BUF_FSPRIVATE(bp, xfs_mount_t *);
xfs_ioerror_alert("xlog_recover_iodone",
mp, bp, XFS_BUF_ADDR(bp));
xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
}
XFS_BUF_SET_FSPRIVATE(bp, NULL);
XFS_BUF_CLR_IODONE_FUNC(bp);
xfs_biodone(bp);
}
/*
* This routine finds (to an approximation) the first block in the physical
* log which contains the given cycle. It uses a binary search algorithm.
* Note that the algorithm can not be perfect because the disk will not
* necessarily be perfect.
*/
int
xlog_find_cycle_start(
xlog_t *log,
xfs_buf_t *bp,
xfs_daddr_t first_blk,
xfs_daddr_t *last_blk,
uint cycle)
{
xfs_caddr_t offset;
xfs_daddr_t mid_blk;
uint mid_cycle;
int error;
mid_blk = BLK_AVG(first_blk, *last_blk);
while (mid_blk != first_blk && mid_blk != *last_blk) {
if ((error = xlog_bread(log, mid_blk, 1, bp)))
return error;
offset = xlog_align(log, mid_blk, 1, bp);
mid_cycle = GET_CYCLE(offset, ARCH_CONVERT);
if (mid_cycle == cycle) {
*last_blk = mid_blk;
/* last_half_cycle == mid_cycle */
} else {
first_blk = mid_blk;
/* first_half_cycle == mid_cycle */
}
mid_blk = BLK_AVG(first_blk, *last_blk);
}
ASSERT((mid_blk == first_blk && mid_blk+1 == *last_blk) ||
(mid_blk == *last_blk && mid_blk-1 == first_blk));
return 0;
}
/*
* Check that the range of blocks does not contain the cycle number
* given. The scan needs to occur from front to back and the ptr into the
* region must be updated since a later routine will need to perform another
* test. If the region is completely good, we end up returning the same
* last block number.
*
* Set blkno to -1 if we encounter no errors. This is an invalid block number
* since we don't ever expect logs to get this large.
*/
STATIC int
xlog_find_verify_cycle(
xlog_t *log,
xfs_daddr_t start_blk,
int nbblks,
uint stop_on_cycle_no,
xfs_daddr_t *new_blk)
{
xfs_daddr_t i, j;
uint cycle;
xfs_buf_t *bp;
xfs_daddr_t bufblks;
xfs_caddr_t buf = NULL;
int error = 0;
bufblks = 1 << ffs(nbblks);
while (!(bp = xlog_get_bp(log, bufblks))) {
/* can't get enough memory to do everything in one big buffer */
bufblks >>= 1;
if (bufblks <= log->l_sectbb_log)
return ENOMEM;
}
for (i = start_blk; i < start_blk + nbblks; i += bufblks) {
int bcount;
bcount = min(bufblks, (start_blk + nbblks - i));
if ((error = xlog_bread(log, i, bcount, bp)))
goto out;
buf = xlog_align(log, i, bcount, bp);
for (j = 0; j < bcount; j++) {
cycle = GET_CYCLE(buf, ARCH_CONVERT);
if (cycle == stop_on_cycle_no) {
*new_blk = i+j;
goto out;
}
buf += BBSIZE;
}
}
*new_blk = -1;
out:
xlog_put_bp(bp);
return error;
}
/*
* Potentially backup over partial log record write.
*
* In the typical case, last_blk is the number of the block directly after
* a good log record. Therefore, we subtract one to get the block number
* of the last block in the given buffer. extra_bblks contains the number
* of blocks we would have read on a previous read. This happens when the
* last log record is split over the end of the physical log.
*
* extra_bblks is the number of blocks potentially verified on a previous
* call to this routine.
*/
STATIC int
xlog_find_verify_log_record(
xlog_t *log,
xfs_daddr_t start_blk,
xfs_daddr_t *last_blk,
int extra_bblks)
{
xfs_daddr_t i;
xfs_buf_t *bp;
xfs_caddr_t offset = NULL;
xlog_rec_header_t *head = NULL;
int error = 0;
int smallmem = 0;
int num_blks = *last_blk - start_blk;
int xhdrs;
ASSERT(start_blk != 0 || *last_blk != start_blk);
if (!(bp = xlog_get_bp(log, num_blks))) {
if (!(bp = xlog_get_bp(log, 1)))
return ENOMEM;
smallmem = 1;
} else {
if ((error = xlog_bread(log, start_blk, num_blks, bp)))
goto out;
offset = xlog_align(log, start_blk, num_blks, bp);
offset += ((num_blks - 1) << BBSHIFT);
}
for (i = (*last_blk) - 1; i >= 0; i--) {
if (i < start_blk) {
/* valid log record not found */
xlog_warn(
"XFS: Log inconsistent (didn't find previous header)");
ASSERT(0);
error = XFS_ERROR(EIO);
goto out;
}
if (smallmem) {
if ((error = xlog_bread(log, i, 1, bp)))
goto out;
offset = xlog_align(log, i, 1, bp);
}
head = (xlog_rec_header_t *)offset;
if (XLOG_HEADER_MAGIC_NUM ==
INT_GET(head->h_magicno, ARCH_CONVERT))
break;
if (!smallmem)
offset -= BBSIZE;
}
/*
* We hit the beginning of the physical log & still no header. Return
* to caller. If caller can handle a return of -1, then this routine
* will be called again for the end of the physical log.
*/
if (i == -1) {
error = -1;
goto out;
}
/*
* We have the final block of the good log (the first block
* of the log record _before_ the head. So we check the uuid.
*/
if ((error = xlog_header_check_mount(log->l_mp, head)))
goto out;
/*
* We may have found a log record header before we expected one.
* last_blk will be the 1st block # with a given cycle #. We may end
* up reading an entire log record. In this case, we don't want to
* reset last_blk. Only when last_blk points in the middle of a log
* record do we update last_blk.
*/
if (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb)) {
uint h_size = INT_GET(head->h_size, ARCH_CONVERT);
xhdrs = h_size / XLOG_HEADER_CYCLE_SIZE;
if (h_size % XLOG_HEADER_CYCLE_SIZE)
xhdrs++;
} else {
xhdrs = 1;
}
if (*last_blk - i + extra_bblks
!= BTOBB(INT_GET(head->h_len, ARCH_CONVERT)) + xhdrs)
*last_blk = i;
out:
xlog_put_bp(bp);
return error;
}
/*
* Head is defined to be the point of the log where the next log write
* write could go. This means that incomplete LR writes at the end are
* eliminated when calculating the head. We aren't guaranteed that previous
* LR have complete transactions. We only know that a cycle number of
* current cycle number -1 won't be present in the log if we start writing
* from our current block number.
*
* last_blk contains the block number of the first block with a given
* cycle number.
*
* Return: zero if normal, non-zero if error.
*/
STATIC int
xlog_find_head(
xlog_t *log,
xfs_daddr_t *return_head_blk)
{
xfs_buf_t *bp;
xfs_caddr_t offset;
xfs_daddr_t new_blk, first_blk, start_blk, last_blk, head_blk;
int num_scan_bblks;
uint first_half_cycle, last_half_cycle;
uint stop_on_cycle;
int error, log_bbnum = log->l_logBBsize;
/* Is the end of the log device zeroed? */
if ((error = xlog_find_zeroed(log, &first_blk)) == -1) {
*return_head_blk = first_blk;
/* Is the whole lot zeroed? */
if (!first_blk) {
/* Linux XFS shouldn't generate totally zeroed logs -
* mkfs etc write a dummy unmount record to a fresh
* log so we can store the uuid in there
*/
xlog_warn("XFS: totally zeroed log");
}
return 0;
} else if (error) {
xlog_warn("XFS: empty log check failed");
return error;
}
first_blk = 0; /* get cycle # of 1st block */
bp = xlog_get_bp(log, 1);
if (!bp)
return ENOMEM;
if ((error = xlog_bread(log, 0, 1, bp)))
goto bp_err;
offset = xlog_align(log, 0, 1, bp);
first_half_cycle = GET_CYCLE(offset, ARCH_CONVERT);
last_blk = head_blk = log_bbnum - 1; /* get cycle # of last block */
if ((error = xlog_bread(log, last_blk, 1, bp)))
goto bp_err;
offset = xlog_align(log, last_blk, 1, bp);
last_half_cycle = GET_CYCLE(offset, ARCH_CONVERT);
ASSERT(last_half_cycle != 0);
/*
* If the 1st half cycle number is equal to the last half cycle number,
* then the entire log is stamped with the same cycle number. In this
* case, head_blk can't be set to zero (which makes sense). The below
* math doesn't work out properly with head_blk equal to zero. Instead,
* we set it to log_bbnum which is an invalid block number, but this
* value makes the math correct. If head_blk doesn't changed through
* all the tests below, *head_blk is set to zero at the very end rather
* than log_bbnum. In a sense, log_bbnum and zero are the same block
* in a circular file.
*/
if (first_half_cycle == last_half_cycle) {
/*
* In this case we believe that the entire log should have
* cycle number last_half_cycle. We need to scan backwards
* from the end verifying that there are no holes still
* containing last_half_cycle - 1. If we find such a hole,
* then the start of that hole will be the new head. The
* simple case looks like
* x | x ... | x - 1 | x
* Another case that fits this picture would be
* x | x + 1 | x ... | x
* In this case the head really is somewhere at the end of the
* log, as one of the latest writes at the beginning was
* incomplete.
* One more case is
* x | x + 1 | x ... | x - 1 | x
* This is really the combination of the above two cases, and
* the head has to end up at the start of the x-1 hole at the
* end of the log.
*
* In the 256k log case, we will read from the beginning to the
* end of the log and search for cycle numbers equal to x-1.
* We don't worry about the x+1 blocks that we encounter,
* because we know that they cannot be the head since the log
* started with x.
*/
head_blk = log_bbnum;
stop_on_cycle = last_half_cycle - 1;
} else {
/*
* In this case we want to find the first block with cycle
* number matching last_half_cycle. We expect the log to be
* some variation on
* x + 1 ... | x ...
* The first block with cycle number x (last_half_cycle) will
* be where the new head belongs. First we do a binary search
* for the first occurrence of last_half_cycle. The binary
* search may not be totally accurate, so then we scan back
* from there looking for occurrences of last_half_cycle before
* us. If that backwards scan wraps around the beginning of
* the log, then we look for occurrences of last_half_cycle - 1
* at the end of the log. The cases we're looking for look
* like
* x + 1 ... | x | x + 1 | x ...
* ^ binary search stopped here
* or
* x + 1 ... | x ... | x - 1 | x
* <---------> less than scan distance
*/
stop_on_cycle = last_half_cycle;
if ((error = xlog_find_cycle_start(log, bp, first_blk,
&head_blk, last_half_cycle)))
goto bp_err;
}
/*
* Now validate the answer. Scan back some number of maximum possible
* blocks and make sure each one has the expected cycle number. The
* maximum is determined by the total possible amount of buffering
* in the in-core log. The following number can be made tighter if
* we actually look at the block size of the filesystem.
*/
num_scan_bblks = XLOG_TOTAL_REC_SHIFT(log);
if (head_blk >= num_scan_bblks) {
/*
* We are guaranteed that the entire check can be performed
* in one buffer.
*/
start_blk = head_blk - num_scan_bblks;
if ((error = xlog_find_verify_cycle(log,
start_blk, num_scan_bblks,
stop_on_cycle, &new_blk)))
goto bp_err;
if (new_blk != -1)
head_blk = new_blk;
} else { /* need to read 2 parts of log */
/*
* We are going to scan backwards in the log in two parts.
* First we scan the physical end of the log. In this part
* of the log, we are looking for blocks with cycle number
* last_half_cycle - 1.
* If we find one, then we know that the log starts there, as
* we've found a hole that didn't get written in going around
* the end of the physical log. The simple case for this is
* x + 1 ... | x ... | x - 1 | x
* <---------> less than scan distance
* If all of the blocks at the end of the log have cycle number
* last_half_cycle, then we check the blocks at the start of
* the log looking for occurrences of last_half_cycle. If we
* find one, then our current estimate for the location of the
* first occurrence of last_half_cycle is wrong and we move
* back to the hole we've found. This case looks like
* x + 1 ... | x | x + 1 | x ...
* ^ binary search stopped here
* Another case we need to handle that only occurs in 256k
* logs is
* x + 1 ... | x ... | x+1 | x ...
* ^ binary search stops here
* In a 256k log, the scan at the end of the log will see the
* x + 1 blocks. We need to skip past those since that is
* certainly not the head of the log. By searching for
* last_half_cycle-1 we accomplish that.
*/
start_blk = log_bbnum - num_scan_bblks + head_blk;
ASSERT(head_blk <= INT_MAX &&
(xfs_daddr_t) num_scan_bblks - head_blk >= 0);
if ((error = xlog_find_verify_cycle(log, start_blk,
num_scan_bblks - (int)head_blk,
(stop_on_cycle - 1), &new_blk)))
goto bp_err;
if (new_blk != -1) {
head_blk = new_blk;
goto bad_blk;
}
/*
* Scan beginning of log now. The last part of the physical
* log is good. This scan needs to verify that it doesn't find
* the last_half_cycle.
*/
start_blk = 0;
ASSERT(head_blk <= INT_MAX);
if ((error = xlog_find_verify_cycle(log,
start_blk, (int)head_blk,
stop_on_cycle, &new_blk)))
goto bp_err;
if (new_blk != -1)
head_blk = new_blk;
}
bad_blk:
/*
* Now we need to make sure head_blk is not pointing to a block in
* the middle of a log record.
*/
num_scan_bblks = XLOG_REC_SHIFT(log);
if (head_blk >= num_scan_bblks) {
start_blk = head_blk - num_scan_bblks; /* don't read head_blk */
/* start ptr at last block ptr before head_blk */
if ((error = xlog_find_verify_log_record(log, start_blk,
&head_blk, 0)) == -1) {
error = XFS_ERROR(EIO);
goto bp_err;
} else if (error)
goto bp_err;
} else {
start_blk = 0;
ASSERT(head_blk <= INT_MAX);
if ((error = xlog_find_verify_log_record(log, start_blk,
&head_blk, 0)) == -1) {
/* We hit the beginning of the log during our search */
start_blk = log_bbnum - num_scan_bblks + head_blk;
new_blk = log_bbnum;
ASSERT(start_blk <= INT_MAX &&
(xfs_daddr_t) log_bbnum-start_blk >= 0);
ASSERT(head_blk <= INT_MAX);
if ((error = xlog_find_verify_log_record(log,
start_blk, &new_blk,
(int)head_blk)) == -1) {
error = XFS_ERROR(EIO);
goto bp_err;
} else if (error)
goto bp_err;
if (new_blk != log_bbnum)
head_blk = new_blk;
} else if (error)
goto bp_err;
}
xlog_put_bp(bp);
if (head_blk == log_bbnum)
*return_head_blk = 0;
else
*return_head_blk = head_blk;
/*
* When returning here, we have a good block number. Bad block
* means that during a previous crash, we didn't have a clean break
* from cycle number N to cycle number N-1. In this case, we need
* to find the first block with cycle number N-1.
*/
return 0;
bp_err:
xlog_put_bp(bp);
if (error)
xlog_warn("XFS: failed to find log head");
return error;
}
/*
* Find the sync block number or the tail of the log.
*
* This will be the block number of the last record to have its
* associated buffers synced to disk. Every log record header has
* a sync lsn embedded in it. LSNs hold block numbers, so it is easy
* to get a sync block number. The only concern is to figure out which
* log record header to believe.
*
* The following algorithm uses the log record header with the largest
* lsn. The entire log record does not need to be valid. We only care
* that the header is valid.
*
* We could speed up search by using current head_blk buffer, but it is not
* available.
*/
int
xlog_find_tail(
xlog_t *log,
xfs_daddr_t *head_blk,
xfs_daddr_t *tail_blk)
{
xlog_rec_header_t *rhead;
xlog_op_header_t *op_head;
xfs_caddr_t offset = NULL;
xfs_buf_t *bp;
int error, i, found;
xfs_daddr_t umount_data_blk;
xfs_daddr_t after_umount_blk;
xfs_lsn_t tail_lsn;
int hblks;
found = 0;
/*
* Find previous log record
*/
if ((error = xlog_find_head(log, head_blk)))
return error;
bp = xlog_get_bp(log, 1);
if (!bp)
return ENOMEM;
if (*head_blk == 0) { /* special case */
if ((error = xlog_bread(log, 0, 1, bp)))
goto bread_err;
offset = xlog_align(log, 0, 1, bp);
if (GET_CYCLE(offset, ARCH_CONVERT) == 0) {
*tail_blk = 0;
/* leave all other log inited values alone */
goto exit;
}
}
/*
* Search backwards looking for log record header block
*/
ASSERT(*head_blk < INT_MAX);
for (i = (int)(*head_blk) - 1; i >= 0; i--) {
if ((error = xlog_bread(log, i, 1, bp)))
goto bread_err;
offset = xlog_align(log, i, 1, bp);
if (XLOG_HEADER_MAGIC_NUM ==
INT_GET(*(uint *)offset, ARCH_CONVERT)) {
found = 1;
break;
}
}
/*
* If we haven't found the log record header block, start looking
* again from the end of the physical log. XXXmiken: There should be
* a check here to make sure we didn't search more than N blocks in
* the previous code.
*/
if (!found) {
for (i = log->l_logBBsize - 1; i >= (int)(*head_blk); i--) {
if ((error = xlog_bread(log, i, 1, bp)))
goto bread_err;
offset = xlog_align(log, i, 1, bp);
if (XLOG_HEADER_MAGIC_NUM ==
INT_GET(*(uint*)offset, ARCH_CONVERT)) {
found = 2;
break;
}
}
}
if (!found) {
xlog_warn("XFS: xlog_find_tail: couldn't find sync record");
ASSERT(0);
return XFS_ERROR(EIO);
}
/* find blk_no of tail of log */
rhead = (xlog_rec_header_t *)offset;
*tail_blk = BLOCK_LSN(INT_GET(rhead->h_tail_lsn, ARCH_CONVERT));
/*
* Reset log values according to the state of the log when we
* crashed. In the case where head_blk == 0, we bump curr_cycle
* one because the next write starts a new cycle rather than
* continuing the cycle of the last good log record. At this
* point we have guaranteed that all partial log records have been
* accounted for. Therefore, we know that the last good log record
* written was complete and ended exactly on the end boundary
* of the physical log.
*/
log->l_prev_block = i;
log->l_curr_block = (int)*head_blk;
log->l_curr_cycle = INT_GET(rhead->h_cycle, ARCH_CONVERT);
if (found == 2)
log->l_curr_cycle++;
log->l_tail_lsn = INT_GET(rhead->h_tail_lsn, ARCH_CONVERT);
log->l_last_sync_lsn = INT_GET(rhead->h_lsn, ARCH_CONVERT);
log->l_grant_reserve_cycle = log->l_curr_cycle;
log->l_grant_reserve_bytes = BBTOB(log->l_curr_block);
log->l_grant_write_cycle = log->l_curr_cycle;
log->l_grant_write_bytes = BBTOB(log->l_curr_block);
/*
* Look for unmount record. If we find it, then we know there
* was a clean unmount. Since 'i' could be the last block in
* the physical log, we convert to a log block before comparing
* to the head_blk.
*
* Save the current tail lsn to use to pass to
* xlog_clear_stale_blocks() below. We won't want to clear the
* unmount record if there is one, so we pass the lsn of the
* unmount record rather than the block after it.
*/
if (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb)) {
int h_size = INT_GET(rhead->h_size, ARCH_CONVERT);
int h_version = INT_GET(rhead->h_version, ARCH_CONVERT);
if ((h_version & XLOG_VERSION_2) &&
(h_size > XLOG_HEADER_CYCLE_SIZE)) {
hblks = h_size / XLOG_HEADER_CYCLE_SIZE;
if (h_size % XLOG_HEADER_CYCLE_SIZE)
hblks++;
} else {
hblks = 1;
}
} else {
hblks = 1;
}
after_umount_blk = (i + hblks + (int)
BTOBB(INT_GET(rhead->h_len, ARCH_CONVERT))) % log->l_logBBsize;
tail_lsn = log->l_tail_lsn;
if (*head_blk == after_umount_blk &&
INT_GET(rhead->h_num_logops, ARCH_CONVERT) == 1) {
umount_data_blk = (i + hblks) % log->l_logBBsize;
if ((error = xlog_bread(log, umount_data_blk, 1, bp))) {
goto bread_err;
}
offset = xlog_align(log, umount_data_blk, 1, bp);
op_head = (xlog_op_header_t *)offset;
if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) {
/*
* Set tail and last sync so that newly written
* log records will point recovery to after the
* current unmount record.
*/
ASSIGN_ANY_LSN_HOST(log->l_tail_lsn, log->l_curr_cycle,
after_umount_blk);
ASSIGN_ANY_LSN_HOST(log->l_last_sync_lsn, log->l_curr_cycle,
after_umount_blk);
*tail_blk = after_umount_blk;
/*
* Note that the unmount was clean. If the unmount
* was not clean, we need to know this to rebuild the
* superblock counters from the perag headers if we
* have a filesystem using non-persistent counters.
*/
log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN;
}
}
/*
* Make sure that there are no blocks in front of the head
* with the same cycle number as the head. This can happen
* because we allow multiple outstanding log writes concurrently,
* and the later writes might make it out before earlier ones.
*
* We use the lsn from before modifying it so that we'll never
* overwrite the unmount record after a clean unmount.
*
* Do this only if we are going to recover the filesystem
*
* NOTE: This used to say "if (!readonly)"
* However on Linux, we can & do recover a read-only filesystem.
* We only skip recovery if NORECOVERY is specified on mount,
* in which case we would not be here.
*
* But... if the -device- itself is readonly, just skip this.
* We can't recover this device anyway, so it won't matter.
*/
if (!xfs_readonly_buftarg(log->l_mp->m_logdev_targp)) {
error = xlog_clear_stale_blocks(log, tail_lsn);
}
bread_err:
exit:
xlog_put_bp(bp);
if (error)
xlog_warn("XFS: failed to locate log tail");
return error;
}
/*
* Is the log zeroed at all?
*
* The last binary search should be changed to perform an X block read
* once X becomes small enough. You can then search linearly through
* the X blocks. This will cut down on the number of reads we need to do.
*
* If the log is partially zeroed, this routine will pass back the blkno
* of the first block with cycle number 0. It won't have a complete LR
* preceding it.
*
* Return:
* 0 => the log is completely written to
* -1 => use *blk_no as the first block of the log
* >0 => error has occurred
*/
int
xlog_find_zeroed(
xlog_t *log,
xfs_daddr_t *blk_no)
{
xfs_buf_t *bp;
xfs_caddr_t offset;
uint first_cycle, last_cycle;
xfs_daddr_t new_blk, last_blk, start_blk;
xfs_daddr_t num_scan_bblks;
int error, log_bbnum = log->l_logBBsize;