-
Notifications
You must be signed in to change notification settings - Fork 52.9k
/
xfs_bmap.c
6232 lines (5564 loc) · 166 KB
/
xfs_bmap.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
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_dir2.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_trans.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_bmap_btree.h"
#include "xfs_rtalloc.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_trans_space.h"
#include "xfs_buf_item.h"
#include "xfs_trace.h"
#include "xfs_attr_leaf.h"
#include "xfs_filestream.h"
#include "xfs_rmap.h"
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
#include "xfs_refcount.h"
#include "xfs_icache.h"
#include "xfs_iomap.h"
struct kmem_cache *xfs_bmap_intent_cache;
/*
* Miscellaneous helper functions
*/
/*
* Compute and fill in the value of the maximum depth of a bmap btree
* in this filesystem. Done once, during mount.
*/
void
xfs_bmap_compute_maxlevels(
xfs_mount_t *mp, /* file system mount structure */
int whichfork) /* data or attr fork */
{
uint64_t maxblocks; /* max blocks at this level */
xfs_extnum_t maxleafents; /* max leaf entries possible */
int level; /* btree level */
int maxrootrecs; /* max records in root block */
int minleafrecs; /* min records in leaf block */
int minnoderecs; /* min records in node block */
int sz; /* root block size */
/*
* The maximum number of extents in a fork, hence the maximum number of
* leaf entries, is controlled by the size of the on-disk extent count.
*
* Note that we can no longer assume that if we are in ATTR1 that the
* fork offset of all the inodes will be
* (xfs_default_attroffset(ip) >> 3) because we could have mounted with
* ATTR2 and then mounted back with ATTR1, keeping the i_forkoff's fixed
* but probably at various positions. Therefore, for both ATTR1 and
* ATTR2 we have to assume the worst case scenario of a minimum size
* available.
*/
maxleafents = xfs_iext_max_nextents(xfs_has_large_extent_counts(mp),
whichfork);
if (whichfork == XFS_DATA_FORK)
sz = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
else
sz = XFS_BMDR_SPACE_CALC(MINABTPTRS);
maxrootrecs = xfs_bmdr_maxrecs(sz, 0);
minleafrecs = mp->m_bmap_dmnr[0];
minnoderecs = mp->m_bmap_dmnr[1];
maxblocks = howmany_64(maxleafents, minleafrecs);
for (level = 1; maxblocks > 1; level++) {
if (maxblocks <= maxrootrecs)
maxblocks = 1;
else
maxblocks = howmany_64(maxblocks, minnoderecs);
}
mp->m_bm_maxlevels[whichfork] = level;
ASSERT(mp->m_bm_maxlevels[whichfork] <= xfs_bmbt_maxlevels_ondisk());
}
unsigned int
xfs_bmap_compute_attr_offset(
struct xfs_mount *mp)
{
if (mp->m_sb.sb_inodesize == 256)
return XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
return XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
}
STATIC int /* error */
xfs_bmbt_lookup_eq(
struct xfs_btree_cur *cur,
struct xfs_bmbt_irec *irec,
int *stat) /* success/failure */
{
cur->bc_rec.b = *irec;
return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
}
STATIC int /* error */
xfs_bmbt_lookup_first(
struct xfs_btree_cur *cur,
int *stat) /* success/failure */
{
cur->bc_rec.b.br_startoff = 0;
cur->bc_rec.b.br_startblock = 0;
cur->bc_rec.b.br_blockcount = 0;
return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
}
/*
* Check if the inode needs to be converted to btree format.
*/
static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork)
{
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
return whichfork != XFS_COW_FORK &&
ifp->if_format == XFS_DINODE_FMT_EXTENTS &&
ifp->if_nextents > XFS_IFORK_MAXEXT(ip, whichfork);
}
/*
* Check if the inode should be converted to extent format.
*/
static inline bool xfs_bmap_wants_extents(struct xfs_inode *ip, int whichfork)
{
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
return whichfork != XFS_COW_FORK &&
ifp->if_format == XFS_DINODE_FMT_BTREE &&
ifp->if_nextents <= XFS_IFORK_MAXEXT(ip, whichfork);
}
/*
* Update the record referred to by cur to the value given by irec
* This either works (return 0) or gets an EFSCORRUPTED error.
*/
STATIC int
xfs_bmbt_update(
struct xfs_btree_cur *cur,
struct xfs_bmbt_irec *irec)
{
union xfs_btree_rec rec;
xfs_bmbt_disk_set_all(&rec.bmbt, irec);
return xfs_btree_update(cur, &rec);
}
/*
* Compute the worst-case number of indirect blocks that will be used
* for ip's delayed extent of length "len".
*/
STATIC xfs_filblks_t
xfs_bmap_worst_indlen(
xfs_inode_t *ip, /* incore inode pointer */
xfs_filblks_t len) /* delayed extent length */
{
int level; /* btree level number */
int maxrecs; /* maximum record count at this level */
xfs_mount_t *mp; /* mount structure */
xfs_filblks_t rval; /* return value */
mp = ip->i_mount;
maxrecs = mp->m_bmap_dmxr[0];
for (level = 0, rval = 0;
level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK);
level++) {
len += maxrecs - 1;
do_div(len, maxrecs);
rval += len;
if (len == 1)
return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
level - 1;
if (level == 0)
maxrecs = mp->m_bmap_dmxr[1];
}
return rval;
}
/*
* Calculate the default attribute fork offset for newly created inodes.
*/
uint
xfs_default_attroffset(
struct xfs_inode *ip)
{
if (ip->i_df.if_format == XFS_DINODE_FMT_DEV)
return roundup(sizeof(xfs_dev_t), 8);
return M_IGEO(ip->i_mount)->attr_fork_offset;
}
/*
* Helper routine to reset inode i_forkoff field when switching attribute fork
* from local to extent format - we reset it where possible to make space
* available for inline data fork extents.
*/
STATIC void
xfs_bmap_forkoff_reset(
xfs_inode_t *ip,
int whichfork)
{
if (whichfork == XFS_ATTR_FORK &&
ip->i_df.if_format != XFS_DINODE_FMT_DEV &&
ip->i_df.if_format != XFS_DINODE_FMT_BTREE) {
uint dfl_forkoff = xfs_default_attroffset(ip) >> 3;
if (dfl_forkoff > ip->i_forkoff)
ip->i_forkoff = dfl_forkoff;
}
}
#ifdef DEBUG
STATIC struct xfs_buf *
xfs_bmap_get_bp(
struct xfs_btree_cur *cur,
xfs_fsblock_t bno)
{
struct xfs_log_item *lip;
int i;
if (!cur)
return NULL;
for (i = 0; i < cur->bc_maxlevels; i++) {
if (!cur->bc_levels[i].bp)
break;
if (xfs_buf_daddr(cur->bc_levels[i].bp) == bno)
return cur->bc_levels[i].bp;
}
/* Chase down all the log items to see if the bp is there */
list_for_each_entry(lip, &cur->bc_tp->t_items, li_trans) {
struct xfs_buf_log_item *bip = (struct xfs_buf_log_item *)lip;
if (bip->bli_item.li_type == XFS_LI_BUF &&
xfs_buf_daddr(bip->bli_buf) == bno)
return bip->bli_buf;
}
return NULL;
}
STATIC void
xfs_check_block(
struct xfs_btree_block *block,
xfs_mount_t *mp,
int root,
short sz)
{
int i, j, dmxr;
__be64 *pp, *thispa; /* pointer to block address */
xfs_bmbt_key_t *prevp, *keyp;
ASSERT(be16_to_cpu(block->bb_level) > 0);
prevp = NULL;
for( i = 1; i <= xfs_btree_get_numrecs(block); i++) {
dmxr = mp->m_bmap_dmxr[0];
keyp = XFS_BMBT_KEY_ADDR(mp, block, i);
if (prevp) {
ASSERT(be64_to_cpu(prevp->br_startoff) <
be64_to_cpu(keyp->br_startoff));
}
prevp = keyp;
/*
* Compare the block numbers to see if there are dups.
*/
if (root)
pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, i, sz);
else
pp = XFS_BMBT_PTR_ADDR(mp, block, i, dmxr);
for (j = i+1; j <= be16_to_cpu(block->bb_numrecs); j++) {
if (root)
thispa = XFS_BMAP_BROOT_PTR_ADDR(mp, block, j, sz);
else
thispa = XFS_BMBT_PTR_ADDR(mp, block, j, dmxr);
if (*thispa == *pp) {
xfs_warn(mp, "%s: thispa(%d) == pp(%d) %lld",
__func__, j, i,
(unsigned long long)be64_to_cpu(*thispa));
xfs_err(mp, "%s: ptrs are equal in node\n",
__func__);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
}
}
}
}
/*
* Check that the extents for the inode ip are in the right order in all
* btree leaves. THis becomes prohibitively expensive for large extent count
* files, so don't bother with inodes that have more than 10,000 extents in
* them. The btree record ordering checks will still be done, so for such large
* bmapbt constructs that is going to catch most corruptions.
*/
STATIC void
xfs_bmap_check_leaf_extents(
struct xfs_btree_cur *cur, /* btree cursor or null */
xfs_inode_t *ip, /* incore inode pointer */
int whichfork) /* data or attr fork */
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_btree_block *block; /* current btree block */
xfs_fsblock_t bno; /* block # of "block" */
struct xfs_buf *bp; /* buffer for "block" */
int error; /* error return value */
xfs_extnum_t i=0, j; /* index into the extents list */
int level; /* btree level, for checking */
__be64 *pp; /* pointer to block address */
xfs_bmbt_rec_t *ep; /* pointer to current extent */
xfs_bmbt_rec_t last = {0, 0}; /* last extent in prev block */
xfs_bmbt_rec_t *nextp; /* pointer to next extent */
int bp_release = 0;
if (ifp->if_format != XFS_DINODE_FMT_BTREE)
return;
/* skip large extent count inodes */
if (ip->i_df.if_nextents > 10000)
return;
bno = NULLFSBLOCK;
block = ifp->if_broot;
/*
* Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
*/
level = be16_to_cpu(block->bb_level);
ASSERT(level > 0);
xfs_check_block(block, mp, 1, ifp->if_broot_bytes);
pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
bno = be64_to_cpu(*pp);
ASSERT(bno != NULLFSBLOCK);
ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
/*
* Go down the tree until leaf level is reached, following the first
* pointer (leftmost) at each level.
*/
while (level-- > 0) {
/* See if buf is in cur first */
bp_release = 0;
bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno));
if (!bp) {
bp_release = 1;
error = xfs_btree_read_bufl(mp, NULL, bno, &bp,
XFS_BMAP_BTREE_REF,
&xfs_bmbt_buf_ops);
if (error)
goto error_norelse;
}
block = XFS_BUF_TO_BLOCK(bp);
if (level == 0)
break;
/*
* Check this block for basic sanity (increasing keys and
* no duplicate blocks).
*/
xfs_check_block(block, mp, 0, 0);
pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
bno = be64_to_cpu(*pp);
if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, bno))) {
error = -EFSCORRUPTED;
goto error0;
}
if (bp_release) {
bp_release = 0;
xfs_trans_brelse(NULL, bp);
}
}
/*
* Here with bp and block set to the leftmost leaf node in the tree.
*/
i = 0;
/*
* Loop over all leaf nodes checking that all extents are in the right order.
*/
for (;;) {
xfs_fsblock_t nextbno;
xfs_extnum_t num_recs;
num_recs = xfs_btree_get_numrecs(block);
/*
* Read-ahead the next leaf block, if any.
*/
nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
/*
* Check all the extents to make sure they are OK.
* If we had a previous block, the last entry should
* conform with the first entry in this one.
*/
ep = XFS_BMBT_REC_ADDR(mp, block, 1);
if (i) {
ASSERT(xfs_bmbt_disk_get_startoff(&last) +
xfs_bmbt_disk_get_blockcount(&last) <=
xfs_bmbt_disk_get_startoff(ep));
}
for (j = 1; j < num_recs; j++) {
nextp = XFS_BMBT_REC_ADDR(mp, block, j + 1);
ASSERT(xfs_bmbt_disk_get_startoff(ep) +
xfs_bmbt_disk_get_blockcount(ep) <=
xfs_bmbt_disk_get_startoff(nextp));
ep = nextp;
}
last = *ep;
i += num_recs;
if (bp_release) {
bp_release = 0;
xfs_trans_brelse(NULL, bp);
}
bno = nextbno;
/*
* If we've reached the end, stop.
*/
if (bno == NULLFSBLOCK)
break;
bp_release = 0;
bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno));
if (!bp) {
bp_release = 1;
error = xfs_btree_read_bufl(mp, NULL, bno, &bp,
XFS_BMAP_BTREE_REF,
&xfs_bmbt_buf_ops);
if (error)
goto error_norelse;
}
block = XFS_BUF_TO_BLOCK(bp);
}
return;
error0:
xfs_warn(mp, "%s: at error0", __func__);
if (bp_release)
xfs_trans_brelse(NULL, bp);
error_norelse:
xfs_warn(mp, "%s: BAD after btree leaves for %llu extents",
__func__, i);
xfs_err(mp, "%s: CORRUPTED BTREE OR SOMETHING", __func__);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
return;
}
/*
* Validate that the bmbt_irecs being returned from bmapi are valid
* given the caller's original parameters. Specifically check the
* ranges of the returned irecs to ensure that they only extend beyond
* the given parameters if the XFS_BMAPI_ENTIRE flag was set.
*/
STATIC void
xfs_bmap_validate_ret(
xfs_fileoff_t bno,
xfs_filblks_t len,
uint32_t flags,
xfs_bmbt_irec_t *mval,
int nmap,
int ret_nmap)
{
int i; /* index to map values */
ASSERT(ret_nmap <= nmap);
for (i = 0; i < ret_nmap; i++) {
ASSERT(mval[i].br_blockcount > 0);
if (!(flags & XFS_BMAPI_ENTIRE)) {
ASSERT(mval[i].br_startoff >= bno);
ASSERT(mval[i].br_blockcount <= len);
ASSERT(mval[i].br_startoff + mval[i].br_blockcount <=
bno + len);
} else {
ASSERT(mval[i].br_startoff < bno + len);
ASSERT(mval[i].br_startoff + mval[i].br_blockcount >
bno);
}
ASSERT(i == 0 ||
mval[i - 1].br_startoff + mval[i - 1].br_blockcount ==
mval[i].br_startoff);
ASSERT(mval[i].br_startblock != DELAYSTARTBLOCK &&
mval[i].br_startblock != HOLESTARTBLOCK);
ASSERT(mval[i].br_state == XFS_EXT_NORM ||
mval[i].br_state == XFS_EXT_UNWRITTEN);
}
}
#else
#define xfs_bmap_check_leaf_extents(cur, ip, whichfork) do { } while (0)
#define xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap) do { } while (0)
#endif /* DEBUG */
/*
* Inode fork format manipulation functions
*/
/*
* Convert the inode format to extent format if it currently is in btree format,
* but the extent list is small enough that it fits into the extent format.
*
* Since the extents are already in-core, all we have to do is give up the space
* for the btree root and pitch the leaf block.
*/
STATIC int /* error */
xfs_bmap_btree_to_extents(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_inode *ip, /* incore inode pointer */
struct xfs_btree_cur *cur, /* btree cursor */
int *logflagsp, /* inode logging flags */
int whichfork) /* data or attr fork */
{
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_mount *mp = ip->i_mount;
struct xfs_btree_block *rblock = ifp->if_broot;
struct xfs_btree_block *cblock;/* child btree block */
xfs_fsblock_t cbno; /* child block number */
struct xfs_buf *cbp; /* child block's buffer */
int error; /* error return value */
__be64 *pp; /* ptr to block address */
struct xfs_owner_info oinfo;
/* check if we actually need the extent format first: */
if (!xfs_bmap_wants_extents(ip, whichfork))
return 0;
ASSERT(cur);
ASSERT(whichfork != XFS_COW_FORK);
ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE);
ASSERT(be16_to_cpu(rblock->bb_level) == 1);
ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1);
ASSERT(xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0) == 1);
pp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, ifp->if_broot_bytes);
cbno = be64_to_cpu(*pp);
#ifdef DEBUG
if (XFS_IS_CORRUPT(cur->bc_mp, !xfs_btree_check_lptr(cur, cbno, 1)))
return -EFSCORRUPTED;
#endif
error = xfs_btree_read_bufl(mp, tp, cbno, &cbp, XFS_BMAP_BTREE_REF,
&xfs_bmbt_buf_ops);
if (error)
return error;
cblock = XFS_BUF_TO_BLOCK(cbp);
if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
return error;
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo);
ip->i_nblocks--;
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
xfs_trans_binval(tp, cbp);
if (cur->bc_levels[0].bp == cbp)
cur->bc_levels[0].bp = NULL;
xfs_iroot_realloc(ip, -1, whichfork);
ASSERT(ifp->if_broot == NULL);
ifp->if_format = XFS_DINODE_FMT_EXTENTS;
*logflagsp |= XFS_ILOG_CORE | xfs_ilog_fext(whichfork);
return 0;
}
/*
* Convert an extents-format file into a btree-format file.
* The new file will have a root block (in the inode) and a single child block.
*/
STATIC int /* error */
xfs_bmap_extents_to_btree(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_inode *ip, /* incore inode pointer */
struct xfs_btree_cur **curp, /* cursor returned to caller */
int wasdel, /* converting a delayed alloc */
int *logflagsp, /* inode logging flags */
int whichfork) /* data or attr fork */
{
struct xfs_btree_block *ablock; /* allocated (child) bt block */
struct xfs_buf *abp; /* buffer for ablock */
struct xfs_alloc_arg args; /* allocation arguments */
struct xfs_bmbt_rec *arp; /* child record pointer */
struct xfs_btree_block *block; /* btree root block */
struct xfs_btree_cur *cur; /* bmap btree cursor */
int error; /* error return value */
struct xfs_ifork *ifp; /* inode fork pointer */
struct xfs_bmbt_key *kp; /* root block key pointer */
struct xfs_mount *mp; /* mount structure */
xfs_bmbt_ptr_t *pp; /* root block address pointer */
struct xfs_iext_cursor icur;
struct xfs_bmbt_irec rec;
xfs_extnum_t cnt = 0;
mp = ip->i_mount;
ASSERT(whichfork != XFS_COW_FORK);
ifp = xfs_ifork_ptr(ip, whichfork);
ASSERT(ifp->if_format == XFS_DINODE_FMT_EXTENTS);
/*
* Make space in the inode incore. This needs to be undone if we fail
* to expand the root.
*/
xfs_iroot_realloc(ip, 1, whichfork);
/*
* Fill in the root.
*/
block = ifp->if_broot;
xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
XFS_BTNUM_BMAP, 1, 1, ip->i_ino,
XFS_BTREE_LONG_PTRS);
/*
* Need a cursor. Can't allocate until bb_level is filled in.
*/
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
cur->bc_ino.flags = wasdel ? XFS_BTCUR_BMBT_WASDEL : 0;
/*
* Convert to a btree with two levels, one record in root.
*/
ifp->if_format = XFS_DINODE_FMT_BTREE;
memset(&args, 0, sizeof(args));
args.tp = tp;
args.mp = mp;
xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork);
args.minlen = args.maxlen = args.prod = 1;
args.wasdel = wasdel;
*logflagsp = 0;
error = xfs_alloc_vextent_start_ag(&args,
XFS_INO_TO_FSB(mp, ip->i_ino));
if (error)
goto out_root_realloc;
/*
* Allocation can't fail, the space was reserved.
*/
if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
error = -ENOSPC;
goto out_root_realloc;
}
cur->bc_ino.allocated++;
ip->i_nblocks++;
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
error = xfs_trans_get_buf(tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, args.fsbno),
mp->m_bsize, 0, &abp);
if (error)
goto out_unreserve_dquot;
/*
* Fill in the child block.
*/
abp->b_ops = &xfs_bmbt_buf_ops;
ablock = XFS_BUF_TO_BLOCK(abp);
xfs_btree_init_block_int(mp, ablock, xfs_buf_daddr(abp),
XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
XFS_BTREE_LONG_PTRS);
for_each_xfs_iext(ifp, &icur, &rec) {
if (isnullstartblock(rec.br_startblock))
continue;
arp = XFS_BMBT_REC_ADDR(mp, ablock, 1 + cnt);
xfs_bmbt_disk_set_all(arp, &rec);
cnt++;
}
ASSERT(cnt == ifp->if_nextents);
xfs_btree_set_numrecs(ablock, cnt);
/*
* Fill in the root key and pointer.
*/
kp = XFS_BMBT_KEY_ADDR(mp, block, 1);
arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
kp->br_startoff = cpu_to_be64(xfs_bmbt_disk_get_startoff(arp));
pp = XFS_BMBT_PTR_ADDR(mp, block, 1, xfs_bmbt_get_maxrecs(cur,
be16_to_cpu(block->bb_level)));
*pp = cpu_to_be64(args.fsbno);
/*
* Do all this logging at the end so that
* the root is at the right level.
*/
xfs_btree_log_block(cur, abp, XFS_BB_ALL_BITS);
xfs_btree_log_recs(cur, abp, 1, be16_to_cpu(ablock->bb_numrecs));
ASSERT(*curp == NULL);
*curp = cur;
*logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork);
return 0;
out_unreserve_dquot:
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
out_root_realloc:
xfs_iroot_realloc(ip, -1, whichfork);
ifp->if_format = XFS_DINODE_FMT_EXTENTS;
ASSERT(ifp->if_broot == NULL);
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
return error;
}
/*
* Convert a local file to an extents file.
* This code is out of bounds for data forks of regular files,
* since the file data needs to get logged so things will stay consistent.
* (The bmap-level manipulations are ok, though).
*/
void
xfs_bmap_local_to_extents_empty(
struct xfs_trans *tp,
struct xfs_inode *ip,
int whichfork)
{
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
ASSERT(whichfork != XFS_COW_FORK);
ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
ASSERT(ifp->if_bytes == 0);
ASSERT(ifp->if_nextents == 0);
xfs_bmap_forkoff_reset(ip, whichfork);
ifp->if_u1.if_root = NULL;
ifp->if_height = 0;
ifp->if_format = XFS_DINODE_FMT_EXTENTS;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
STATIC int /* error */
xfs_bmap_local_to_extents(
xfs_trans_t *tp, /* transaction pointer */
xfs_inode_t *ip, /* incore inode pointer */
xfs_extlen_t total, /* total blocks needed by transaction */
int *logflagsp, /* inode logging flags */
int whichfork,
void (*init_fn)(struct xfs_trans *tp,
struct xfs_buf *bp,
struct xfs_inode *ip,
struct xfs_ifork *ifp))
{
int error = 0;
int flags; /* logging flags returned */
struct xfs_ifork *ifp; /* inode fork pointer */
xfs_alloc_arg_t args; /* allocation arguments */
struct xfs_buf *bp; /* buffer for extent block */
struct xfs_bmbt_irec rec;
struct xfs_iext_cursor icur;
/*
* We don't want to deal with the case of keeping inode data inline yet.
* So sending the data fork of a regular inode is invalid.
*/
ASSERT(!(S_ISREG(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK));
ifp = xfs_ifork_ptr(ip, whichfork);
ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
if (!ifp->if_bytes) {
xfs_bmap_local_to_extents_empty(tp, ip, whichfork);
flags = XFS_ILOG_CORE;
goto done;
}
flags = 0;
error = 0;
memset(&args, 0, sizeof(args));
args.tp = tp;
args.mp = ip->i_mount;
args.total = total;
args.minlen = args.maxlen = args.prod = 1;
xfs_rmap_ino_owner(&args.oinfo, ip->i_ino, whichfork, 0);
/*
* Allocate a block. We know we need only one, since the
* file currently fits in an inode.
*/
args.total = total;
args.minlen = args.maxlen = args.prod = 1;
error = xfs_alloc_vextent_start_ag(&args,
XFS_INO_TO_FSB(args.mp, ip->i_ino));
if (error)
goto done;
/* Can't fail, the space was reserved. */
ASSERT(args.fsbno != NULLFSBLOCK);
ASSERT(args.len == 1);
error = xfs_trans_get_buf(tp, args.mp->m_ddev_targp,
XFS_FSB_TO_DADDR(args.mp, args.fsbno),
args.mp->m_bsize, 0, &bp);
if (error)
goto done;
/*
* Initialize the block, copy the data and log the remote buffer.
*
* The callout is responsible for logging because the remote format
* might differ from the local format and thus we don't know how much to
* log here. Note that init_fn must also set the buffer log item type
* correctly.
*/
init_fn(tp, bp, ip, ifp);
/* account for the change in fork size */
xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
xfs_bmap_local_to_extents_empty(tp, ip, whichfork);
flags |= XFS_ILOG_CORE;
ifp->if_u1.if_root = NULL;
ifp->if_height = 0;
rec.br_startoff = 0;
rec.br_startblock = args.fsbno;
rec.br_blockcount = 1;
rec.br_state = XFS_EXT_NORM;
xfs_iext_first(ifp, &icur);
xfs_iext_insert(ip, &icur, &rec, 0);
ifp->if_nextents = 1;
ip->i_nblocks = 1;
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
flags |= xfs_ilog_fext(whichfork);
done:
*logflagsp = flags;
return error;
}
/*
* Called from xfs_bmap_add_attrfork to handle btree format files.
*/
STATIC int /* error */
xfs_bmap_add_attrfork_btree(
xfs_trans_t *tp, /* transaction pointer */
xfs_inode_t *ip, /* incore inode pointer */
int *flags) /* inode logging flags */
{
struct xfs_btree_block *block = ip->i_df.if_broot;
struct xfs_btree_cur *cur; /* btree cursor */
int error; /* error return value */
xfs_mount_t *mp; /* file system mount struct */
int stat; /* newroot status */
mp = ip->i_mount;
if (XFS_BMAP_BMDR_SPACE(block) <= xfs_inode_data_fork_size(ip))
*flags |= XFS_ILOG_DBROOT;
else {
cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
error = xfs_bmbt_lookup_first(cur, &stat);
if (error)
goto error0;
/* must be at least one entry */
if (XFS_IS_CORRUPT(mp, stat != 1)) {
error = -EFSCORRUPTED;
goto error0;
}
if ((error = xfs_btree_new_iroot(cur, flags, &stat)))
goto error0;
if (stat == 0) {
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
return -ENOSPC;
}
cur->bc_ino.allocated = 0;
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
}
return 0;
error0:
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
return error;
}
/*
* Called from xfs_bmap_add_attrfork to handle extents format files.
*/
STATIC int /* error */
xfs_bmap_add_attrfork_extents(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_inode *ip, /* incore inode pointer */
int *flags) /* inode logging flags */
{
struct xfs_btree_cur *cur; /* bmap btree cursor */
int error; /* error return value */
if (ip->i_df.if_nextents * sizeof(struct xfs_bmbt_rec) <=
xfs_inode_data_fork_size(ip))
return 0;
cur = NULL;
error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, flags,
XFS_DATA_FORK);
if (cur) {
cur->bc_ino.allocated = 0;
xfs_btree_del_cursor(cur, error);
}
return error;
}
/*
* Called from xfs_bmap_add_attrfork to handle local format files. Each
* different data fork content type needs a different callout to do the
* conversion. Some are basic and only require special block initialisation
* callouts for the data formating, others (directories) are so specialised they
* handle everything themselves.
*
* XXX (dgc): investigate whether directory conversion can use the generic
* formatting callout. It should be possible - it's just a very complex
* formatter.
*/
STATIC int /* error */
xfs_bmap_add_attrfork_local(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_inode *ip, /* incore inode pointer */
int *flags) /* inode logging flags */
{
struct xfs_da_args dargs; /* args for dir/attr code */
if (ip->i_df.if_bytes <= xfs_inode_data_fork_size(ip))
return 0;
if (S_ISDIR(VFS_I(ip)->i_mode)) {
memset(&dargs, 0, sizeof(dargs));
dargs.geo = ip->i_mount->m_dir_geo;
dargs.dp = ip;
dargs.total = dargs.geo->fsbcount;
dargs.whichfork = XFS_DATA_FORK;
dargs.trans = tp;
return xfs_dir2_sf_to_block(&dargs);
}
if (S_ISLNK(VFS_I(ip)->i_mode))
return xfs_bmap_local_to_extents(tp, ip, 1, flags,
XFS_DATA_FORK,
xfs_symlink_local_to_remote);
/* should only be called for types that support local format data */
ASSERT(0);
return -EFSCORRUPTED;
}
/*
* Set an inode attr fork offset based on the format of the data fork.
*/
static int
xfs_bmap_set_attrforkoff(
struct xfs_inode *ip,
int size,
int *version)
{
int default_size = xfs_default_attroffset(ip) >> 3;
switch (ip->i_df.if_format) {
case XFS_DINODE_FMT_DEV:
ip->i_forkoff = default_size;
break;
case XFS_DINODE_FMT_LOCAL:
case XFS_DINODE_FMT_EXTENTS:
case XFS_DINODE_FMT_BTREE:
ip->i_forkoff = xfs_attr_shortform_bytesfit(ip, size);
if (!ip->i_forkoff)
ip->i_forkoff = default_size;
else if (xfs_has_attr2(ip->i_mount) && version)
*version = 2;
break;
default:
ASSERT(0);
return -EINVAL;
}
return 0;
}
/*
* Convert inode from non-attributed to attributed.
* Must not be in a transaction, ip must not be locked.
*/
int /* error code */
xfs_bmap_add_attrfork(
xfs_inode_t *ip, /* incore inode pointer */
int size, /* space new attribute needs */