-
Notifications
You must be signed in to change notification settings - Fork 14
/
Copy pathxfs_bmap_util.c
1728 lines (1499 loc) · 44.7 KB
/
xfs_bmap_util.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.
* Copyright (c) 2012 Red Hat, 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_mount.h"
#include "xfs_defer.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_error.h"
#include "xfs_quota.h"
#include "xfs_trans_space.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_iomap.h"
#include "xfs_reflink.h"
#include "xfs_rtbitmap.h"
#include "xfs_rtgroup.h"
/* Kernel only BMAP related definitions and functions */
/*
* Convert the given file system block to a disk block. We have to treat it
* differently based on whether the file is a real time file or not, because the
* bmap code does.
*/
xfs_daddr_t
xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
{
if (XFS_IS_REALTIME_INODE(ip))
return xfs_rtb_to_daddr(ip->i_mount, fsb);
return XFS_FSB_TO_DADDR(ip->i_mount, fsb);
}
/*
* Routine to zero an extent on disk allocated to the specific inode.
*/
int
xfs_zero_extent(
struct xfs_inode *ip,
xfs_fsblock_t start_fsb,
xfs_off_t count_fsb)
{
return blkdev_issue_zeroout(xfs_inode_buftarg(ip)->bt_bdev,
xfs_fsb_to_db(ip, start_fsb),
XFS_FSB_TO_BB(ip->i_mount, count_fsb),
GFP_KERNEL, 0);
}
/*
* Extent tree block counting routines.
*/
/*
* Count leaf blocks given a range of extent records. Delayed allocation
* extents are not counted towards the totals.
*/
xfs_extnum_t
xfs_bmap_count_leaves(
struct xfs_ifork *ifp,
xfs_filblks_t *count)
{
struct xfs_iext_cursor icur;
struct xfs_bmbt_irec got;
xfs_extnum_t numrecs = 0;
for_each_xfs_iext(ifp, &icur, &got) {
if (!isnullstartblock(got.br_startblock)) {
*count += got.br_blockcount;
numrecs++;
}
}
return numrecs;
}
/*
* Count fsblocks of the given fork. Delayed allocation extents are
* not counted towards the totals.
*/
int
xfs_bmap_count_blocks(
struct xfs_trans *tp,
struct xfs_inode *ip,
int whichfork,
xfs_extnum_t *nextents,
xfs_filblks_t *count)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_btree_cur *cur;
xfs_filblks_t btblocks = 0;
int error;
*nextents = 0;
*count = 0;
if (!ifp)
return 0;
switch (ifp->if_format) {
case XFS_DINODE_FMT_BTREE:
error = xfs_iread_extents(tp, ip, whichfork);
if (error)
return error;
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
error = xfs_btree_count_blocks(cur, &btblocks);
xfs_btree_del_cursor(cur, error);
if (error)
return error;
/*
* xfs_btree_count_blocks includes the root block contained in
* the inode fork in @btblocks, so subtract one because we're
* only interested in allocated disk blocks.
*/
*count += btblocks - 1;
fallthrough;
case XFS_DINODE_FMT_EXTENTS:
*nextents = xfs_bmap_count_leaves(ifp, count);
break;
}
return 0;
}
static int
xfs_getbmap_report_one(
struct xfs_inode *ip,
struct getbmapx *bmv,
struct kgetbmap *out,
int64_t bmv_end,
struct xfs_bmbt_irec *got)
{
struct kgetbmap *p = out + bmv->bmv_entries;
bool shared = false;
int error;
error = xfs_reflink_trim_around_shared(ip, got, &shared);
if (error)
return error;
if (isnullstartblock(got->br_startblock) ||
got->br_startblock == DELAYSTARTBLOCK) {
/*
* Take the flush completion as being a point-in-time snapshot
* where there are no delalloc extents, and if any new ones
* have been created racily, just skip them as being 'after'
* the flush and so don't get reported.
*/
if (!(bmv->bmv_iflags & BMV_IF_DELALLOC))
return 0;
p->bmv_oflags |= BMV_OF_DELALLOC;
p->bmv_block = -2;
} else {
p->bmv_block = xfs_fsb_to_db(ip, got->br_startblock);
}
if (got->br_state == XFS_EXT_UNWRITTEN &&
(bmv->bmv_iflags & BMV_IF_PREALLOC))
p->bmv_oflags |= BMV_OF_PREALLOC;
if (shared)
p->bmv_oflags |= BMV_OF_SHARED;
p->bmv_offset = XFS_FSB_TO_BB(ip->i_mount, got->br_startoff);
p->bmv_length = XFS_FSB_TO_BB(ip->i_mount, got->br_blockcount);
bmv->bmv_offset = p->bmv_offset + p->bmv_length;
bmv->bmv_length = max(0LL, bmv_end - bmv->bmv_offset);
bmv->bmv_entries++;
return 0;
}
static void
xfs_getbmap_report_hole(
struct xfs_inode *ip,
struct getbmapx *bmv,
struct kgetbmap *out,
int64_t bmv_end,
xfs_fileoff_t bno,
xfs_fileoff_t end)
{
struct kgetbmap *p = out + bmv->bmv_entries;
if (bmv->bmv_iflags & BMV_IF_NO_HOLES)
return;
p->bmv_block = -1;
p->bmv_offset = XFS_FSB_TO_BB(ip->i_mount, bno);
p->bmv_length = XFS_FSB_TO_BB(ip->i_mount, end - bno);
bmv->bmv_offset = p->bmv_offset + p->bmv_length;
bmv->bmv_length = max(0LL, bmv_end - bmv->bmv_offset);
bmv->bmv_entries++;
}
static inline bool
xfs_getbmap_full(
struct getbmapx *bmv)
{
return bmv->bmv_length == 0 || bmv->bmv_entries >= bmv->bmv_count - 1;
}
static bool
xfs_getbmap_next_rec(
struct xfs_bmbt_irec *rec,
xfs_fileoff_t total_end)
{
xfs_fileoff_t end = rec->br_startoff + rec->br_blockcount;
if (end == total_end)
return false;
rec->br_startoff += rec->br_blockcount;
if (!isnullstartblock(rec->br_startblock) &&
rec->br_startblock != DELAYSTARTBLOCK)
rec->br_startblock += rec->br_blockcount;
rec->br_blockcount = total_end - end;
return true;
}
/*
* Get inode's extents as described in bmv, and format for output.
* Calls formatter to fill the user's buffer until all extents
* are mapped, until the passed-in bmv->bmv_count slots have
* been filled, or until the formatter short-circuits the loop,
* if it is tracking filled-in extents on its own.
*/
int /* error code */
xfs_getbmap(
struct xfs_inode *ip,
struct getbmapx *bmv, /* user bmap structure */
struct kgetbmap *out)
{
struct xfs_mount *mp = ip->i_mount;
int iflags = bmv->bmv_iflags;
int whichfork, lock, error = 0;
int64_t bmv_end, max_len;
xfs_fileoff_t bno, first_bno;
struct xfs_ifork *ifp;
struct xfs_bmbt_irec got, rec;
xfs_filblks_t len;
struct xfs_iext_cursor icur;
if (bmv->bmv_iflags & ~BMV_IF_VALID)
return -EINVAL;
#ifndef DEBUG
/* Only allow CoW fork queries if we're debugging. */
if (iflags & BMV_IF_COWFORK)
return -EINVAL;
#endif
if ((iflags & BMV_IF_ATTRFORK) && (iflags & BMV_IF_COWFORK))
return -EINVAL;
if (bmv->bmv_length < -1)
return -EINVAL;
bmv->bmv_entries = 0;
if (bmv->bmv_length == 0)
return 0;
if (iflags & BMV_IF_ATTRFORK)
whichfork = XFS_ATTR_FORK;
else if (iflags & BMV_IF_COWFORK)
whichfork = XFS_COW_FORK;
else
whichfork = XFS_DATA_FORK;
xfs_ilock(ip, XFS_IOLOCK_SHARED);
switch (whichfork) {
case XFS_ATTR_FORK:
lock = xfs_ilock_attr_map_shared(ip);
if (!xfs_inode_has_attr_fork(ip))
goto out_unlock_ilock;
max_len = 1LL << 32;
break;
case XFS_COW_FORK:
lock = XFS_ILOCK_SHARED;
xfs_ilock(ip, lock);
/* No CoW fork? Just return */
if (!xfs_ifork_ptr(ip, whichfork))
goto out_unlock_ilock;
if (xfs_get_cowextsz_hint(ip))
max_len = mp->m_super->s_maxbytes;
else
max_len = XFS_ISIZE(ip);
break;
case XFS_DATA_FORK:
if (!(iflags & BMV_IF_DELALLOC) &&
(ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_disk_size)) {
error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (error)
goto out_unlock_iolock;
/*
* Even after flushing the inode, there can still be
* delalloc blocks on the inode beyond EOF due to
* speculative preallocation. These are not removed
* until the release function is called or the inode
* is inactivated. Hence we cannot assert here that
* ip->i_delayed_blks == 0.
*/
}
if (xfs_get_extsz_hint(ip) ||
(ip->i_diflags & XFS_DIFLAG_PREALLOC))
max_len = mp->m_super->s_maxbytes;
else
max_len = XFS_ISIZE(ip);
lock = xfs_ilock_data_map_shared(ip);
break;
}
ifp = xfs_ifork_ptr(ip, whichfork);
switch (ifp->if_format) {
case XFS_DINODE_FMT_EXTENTS:
case XFS_DINODE_FMT_BTREE:
break;
case XFS_DINODE_FMT_LOCAL:
/* Local format inode forks report no extents. */
goto out_unlock_ilock;
default:
error = -EINVAL;
goto out_unlock_ilock;
}
if (bmv->bmv_length == -1) {
max_len = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, max_len));
bmv->bmv_length = max(0LL, max_len - bmv->bmv_offset);
}
bmv_end = bmv->bmv_offset + bmv->bmv_length;
first_bno = bno = XFS_BB_TO_FSBT(mp, bmv->bmv_offset);
len = XFS_BB_TO_FSB(mp, bmv->bmv_length);
error = xfs_iread_extents(NULL, ip, whichfork);
if (error)
goto out_unlock_ilock;
if (!xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got)) {
/*
* Report a whole-file hole if the delalloc flag is set to
* stay compatible with the old implementation.
*/
if (iflags & BMV_IF_DELALLOC)
xfs_getbmap_report_hole(ip, bmv, out, bmv_end, bno,
XFS_B_TO_FSB(mp, XFS_ISIZE(ip)));
goto out_unlock_ilock;
}
while (!xfs_getbmap_full(bmv)) {
xfs_trim_extent(&got, first_bno, len);
/*
* Report an entry for a hole if this extent doesn't directly
* follow the previous one.
*/
if (got.br_startoff > bno) {
xfs_getbmap_report_hole(ip, bmv, out, bmv_end, bno,
got.br_startoff);
if (xfs_getbmap_full(bmv))
break;
}
/*
* In order to report shared extents accurately, we report each
* distinct shared / unshared part of a single bmbt record with
* an individual getbmapx record.
*/
bno = got.br_startoff + got.br_blockcount;
rec = got;
do {
error = xfs_getbmap_report_one(ip, bmv, out, bmv_end,
&rec);
if (error || xfs_getbmap_full(bmv))
goto out_unlock_ilock;
} while (xfs_getbmap_next_rec(&rec, bno));
if (!xfs_iext_next_extent(ifp, &icur, &got)) {
xfs_fileoff_t end = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
if (bmv->bmv_entries > 0)
out[bmv->bmv_entries - 1].bmv_oflags |=
BMV_OF_LAST;
if (whichfork != XFS_ATTR_FORK && bno < end &&
!xfs_getbmap_full(bmv)) {
xfs_getbmap_report_hole(ip, bmv, out, bmv_end,
bno, end);
}
break;
}
if (bno >= first_bno + len)
break;
}
out_unlock_ilock:
xfs_iunlock(ip, lock);
out_unlock_iolock:
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
return error;
}
/*
* Dead simple method of punching delalyed allocation blocks from a range in
* the inode. This will always punch out both the start and end blocks, even
* if the ranges only partially overlap them, so it is up to the caller to
* ensure that partial blocks are not passed in.
*/
void
xfs_bmap_punch_delalloc_range(
struct xfs_inode *ip,
int whichfork,
xfs_off_t start_byte,
xfs_off_t end_byte)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, start_byte);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, end_byte);
struct xfs_bmbt_irec got, del;
struct xfs_iext_cursor icur;
ASSERT(!xfs_need_iread_extents(ifp));
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
goto out_unlock;
while (got.br_startoff + got.br_blockcount > start_fsb) {
del = got;
xfs_trim_extent(&del, start_fsb, end_fsb - start_fsb);
/*
* A delete can push the cursor forward. Step back to the
* previous extent on non-delalloc or extents outside the
* target range.
*/
if (!del.br_blockcount ||
!isnullstartblock(del.br_startblock)) {
if (!xfs_iext_prev_extent(ifp, &icur, &got))
break;
continue;
}
xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, &del);
if (!xfs_iext_get_extent(ifp, &icur, &got))
break;
}
if (whichfork == XFS_COW_FORK && !ifp->if_bytes)
xfs_inode_clear_cowblocks_tag(ip);
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
/*
* Test whether it is appropriate to check an inode for and free post EOF
* blocks.
*/
bool
xfs_can_free_eofblocks(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
bool found_blocks = false;
xfs_fileoff_t end_fsb;
xfs_fileoff_t last_fsb;
struct xfs_bmbt_irec imap;
struct xfs_iext_cursor icur;
/*
* Caller must either hold the exclusive io lock; or be inactivating
* the inode, which guarantees there are no other users of the inode.
*/
if (!(VFS_I(ip)->i_state & I_FREEING))
xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL);
/* prealloc/delalloc exists only on regular files */
if (!S_ISREG(VFS_I(ip)->i_mode))
return false;
/*
* Zero sized files with no cached pages and delalloc blocks will not
* have speculative prealloc/delalloc blocks to remove.
*/
if (VFS_I(ip)->i_size == 0 &&
VFS_I(ip)->i_mapping->nrpages == 0 &&
ip->i_delayed_blks == 0)
return false;
/* If we haven't read in the extent list, then don't do it now. */
if (xfs_need_iread_extents(&ip->i_df))
return false;
/*
* Do not free real extents in preallocated files unless the file has
* delalloc blocks and we are forced to remove them.
*/
if ((ip->i_diflags & XFS_DIFLAG_PREALLOC) && !ip->i_delayed_blks)
return false;
/*
* Do not try to free post-EOF blocks if EOF is beyond the end of the
* range supported by the page cache, because the truncation will loop
* forever.
*/
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
if (xfs_inode_has_bigrtalloc(ip))
end_fsb = xfs_fileoff_roundup_rtx(mp, end_fsb);
last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
if (last_fsb <= end_fsb)
return false;
/*
* Check if there is an post-EOF extent to free. If there are any
* delalloc blocks attached to the inode (data fork delalloc
* reservations or CoW extents of any kind), we need to free them so
* that inactivation doesn't fail to erase them.
*/
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (ip->i_delayed_blks ||
xfs_iext_lookup_extent(ip, &ip->i_df, end_fsb, &icur, &imap))
found_blocks = true;
xfs_iunlock(ip, XFS_ILOCK_SHARED);
return found_blocks;
}
/*
* This is called to free any blocks beyond eof. The caller must hold
* IOLOCK_EXCL unless we are in the inode reclaim path and have the only
* reference to the inode.
*/
int
xfs_free_eofblocks(
struct xfs_inode *ip)
{
struct xfs_trans *tp;
struct xfs_mount *mp = ip->i_mount;
int error;
/* Attach the dquots to the inode up front. */
error = xfs_qm_dqattach(ip);
if (error)
return error;
/* Wait on dio to ensure i_size has settled. */
inode_dio_wait(VFS_I(ip));
/*
* For preallocated files only free delayed allocations.
*
* Note that this means we also leave speculative preallocations in
* place for preallocated files.
*/
if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) {
if (ip->i_delayed_blks) {
xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK,
round_up(XFS_ISIZE(ip), mp->m_sb.sb_blocksize),
LLONG_MAX);
}
xfs_inode_clear_eofblocks_tag(ip);
return 0;
}
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error) {
ASSERT(xfs_is_shutdown(mp));
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Do not update the on-disk file size. If we update the on-disk file
* size and then the system crashes before the contents of the file are
* flushed to disk then the files may be full of holes (ie NULL files
* bug).
*/
error = xfs_itruncate_extents_flags(&tp, ip, XFS_DATA_FORK,
XFS_ISIZE(ip), XFS_BMAPI_NODISCARD);
if (error)
goto err_cancel;
error = xfs_trans_commit(tp);
if (error)
goto out_unlock;
xfs_inode_clear_eofblocks_tag(ip);
goto out_unlock;
err_cancel:
/*
* If we get an error at this point we simply don't
* bother truncating the file.
*/
xfs_trans_cancel(tp);
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
int
xfs_alloc_file_space(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len)
{
xfs_mount_t *mp = ip->i_mount;
xfs_off_t count;
xfs_filblks_t allocatesize_fsb;
xfs_extlen_t extsz, temp;
xfs_fileoff_t startoffset_fsb;
xfs_fileoff_t endoffset_fsb;
int rt;
xfs_trans_t *tp;
xfs_bmbt_irec_t imaps[1], *imapp;
int error;
if (xfs_is_always_cow_inode(ip))
return 0;
trace_xfs_alloc_file_space(ip);
if (xfs_is_shutdown(mp))
return -EIO;
error = xfs_qm_dqattach(ip);
if (error)
return error;
if (len <= 0)
return -EINVAL;
rt = XFS_IS_REALTIME_INODE(ip);
extsz = xfs_get_extsz_hint(ip);
count = len;
imapp = &imaps[0];
startoffset_fsb = XFS_B_TO_FSBT(mp, offset);
endoffset_fsb = XFS_B_TO_FSB(mp, offset + count);
allocatesize_fsb = endoffset_fsb - startoffset_fsb;
/*
* Allocate file space until done or until there is an error
*/
while (allocatesize_fsb && !error) {
xfs_fileoff_t s, e;
unsigned int dblocks, rblocks, resblks;
int nimaps = 1;
/*
* Determine space reservations for data/realtime.
*/
if (unlikely(extsz)) {
s = startoffset_fsb;
do_div(s, extsz);
s *= extsz;
e = startoffset_fsb + allocatesize_fsb;
div_u64_rem(startoffset_fsb, extsz, &temp);
if (temp)
e += temp;
div_u64_rem(e, extsz, &temp);
if (temp)
e += extsz - temp;
} else {
s = 0;
e = allocatesize_fsb;
}
/*
* The transaction reservation is limited to a 32-bit block
* count, hence we need to limit the number of blocks we are
* trying to reserve to avoid an overflow. We can't allocate
* more than @nimaps extents, and an extent is limited on disk
* to XFS_BMBT_MAX_EXTLEN (21 bits), so use that to enforce the
* limit.
*/
resblks = min_t(xfs_fileoff_t, (e - s),
(XFS_MAX_BMBT_EXTLEN * nimaps));
if (unlikely(rt)) {
dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
rblocks = resblks;
} else {
dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks);
rblocks = 0;
}
error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write,
dblocks, rblocks, false, &tp);
if (error)
break;
error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK,
XFS_IEXT_ADD_NOSPLIT_CNT);
if (error)
goto error;
/*
* If the allocator cannot find a single free extent large
* enough to cover the start block of the requested range,
* xfs_bmapi_write will return -ENOSR.
*
* In that case we simply need to keep looping with the same
* startoffset_fsb so that one of the following allocations
* will eventually reach the requested range.
*/
error = xfs_bmapi_write(tp, ip, startoffset_fsb,
allocatesize_fsb, XFS_BMAPI_PREALLOC, 0, imapp,
&nimaps);
if (error) {
if (error != -ENOSR)
goto error;
error = 0;
} else {
startoffset_fsb += imapp->br_blockcount;
allocatesize_fsb -= imapp->br_blockcount;
}
ip->i_diflags |= XFS_DIFLAG_PREALLOC;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
return error;
error:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
static int
xfs_unmap_extent(
struct xfs_inode *ip,
xfs_fileoff_t startoffset_fsb,
xfs_filblks_t len_fsb,
int *done)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
uint resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
int error;
error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks, 0,
false, &tp);
if (error)
return error;
error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK,
XFS_IEXT_PUNCH_HOLE_CNT);
if (error)
goto out_trans_cancel;
error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, done);
if (error)
goto out_trans_cancel;
error = xfs_trans_commit(tp);
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
out_trans_cancel:
xfs_trans_cancel(tp);
goto out_unlock;
}
/* Caller must first wait for the completion of any pending DIOs if required. */
int
xfs_flush_unmap_range(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len)
{
struct inode *inode = VFS_I(ip);
xfs_off_t rounding, start, end;
int error;
/*
* Make sure we extend the flush out to extent alignment
* boundaries so any extent range overlapping the start/end
* of the modification we are about to do is clean and idle.
*/
rounding = max_t(xfs_off_t, xfs_inode_alloc_unitsize(ip), PAGE_SIZE);
start = rounddown_64(offset, rounding);
end = roundup_64(offset + len, rounding) - 1;
error = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (error)
return error;
truncate_pagecache_range(inode, start, end);
return 0;
}
int
xfs_free_file_space(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t startoffset_fsb;
xfs_fileoff_t endoffset_fsb;
int done = 0, error;
trace_xfs_free_file_space(ip);
error = xfs_qm_dqattach(ip);
if (error)
return error;
if (len <= 0) /* if nothing being freed */
return 0;
/*
* Now AIO and DIO has drained we flush and (if necessary) invalidate
* the cached range over the first operation we are about to run.
*/
error = xfs_flush_unmap_range(ip, offset, len);
if (error)
return error;
startoffset_fsb = XFS_B_TO_FSB(mp, offset);
endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
/* We can only free complete realtime extents. */
if (xfs_inode_has_bigrtalloc(ip)) {
startoffset_fsb = xfs_fileoff_roundup_rtx(mp, startoffset_fsb);
endoffset_fsb = xfs_fileoff_rounddown_rtx(mp, endoffset_fsb);
}
/*
* Need to zero the stuff we're not freeing, on disk.
*/
if (endoffset_fsb > startoffset_fsb) {
while (!done) {
error = xfs_unmap_extent(ip, startoffset_fsb,
endoffset_fsb - startoffset_fsb, &done);
if (error)
return error;
}
}
/*
* Now that we've unmap all full blocks we'll have to zero out any
* partial block at the beginning and/or end. xfs_zero_range is smart
* enough to skip any holes, including those we just created, but we
* must take care not to zero beyond EOF and enlarge i_size.
*/
if (offset >= XFS_ISIZE(ip))
return 0;
if (offset + len > XFS_ISIZE(ip))
len = XFS_ISIZE(ip) - offset;
error = xfs_zero_range(ip, offset, len, NULL);
if (error)
return error;
/*
* If we zeroed right up to EOF and EOF straddles a page boundary we
* must make sure that the post-EOF area is also zeroed because the
* page could be mmap'd and xfs_zero_range doesn't do that for us.
* Writeback of the eof page will do this, albeit clumsily.
*/
if (offset + len >= XFS_ISIZE(ip) && offset_in_page(offset + len) > 0) {
error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
round_down(offset + len, PAGE_SIZE), LLONG_MAX);
}
return error;
}
static int
xfs_prepare_shift(
struct xfs_inode *ip,
loff_t offset)
{
unsigned int rounding;
int error;
/*
* Trim eofblocks to avoid shifting uninitialized post-eof preallocation
* into the accessible region of the file.
*/
if (xfs_can_free_eofblocks(ip)) {
error = xfs_free_eofblocks(ip);
if (error)
return error;
}
/*
* Shift operations must stabilize the start block offset boundary along
* with the full range of the operation. If we don't, a COW writeback
* completion could race with an insert, front merge with the start
* extent (after split) during the shift and corrupt the file. Start
* with the allocation unit just prior to the start to stabilize the
* boundary.
*/
rounding = xfs_inode_alloc_unitsize(ip);
offset = rounddown_64(offset, rounding);
if (offset)
offset -= rounding;
/*
* Writeback and invalidate cache for the remainder of the file as we're
* about to shift down every extent from offset to EOF.
*/
error = xfs_flush_unmap_range(ip, offset, XFS_ISIZE(ip));
if (error)
return error;
/*
* Clean out anything hanging around in the cow fork now that
* we've flushed all the dirty data out to disk to avoid having
* CoW extents at the wrong offsets.
*/
if (xfs_inode_has_cow_data(ip)) {
error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF,
true);
if (error)
return error;
}
return 0;
}
/*
* xfs_collapse_file_space()
* This routine frees disk space and shift extent for the given file.
* The first thing we do is to free data blocks in the specified range
* by calling xfs_free_file_space(). It would also sync dirty data
* and invalidate page cache over the region on which collapse range
* is working. And Shift extent records to the left to cover a hole.
* RETURNS:
* 0 on success
* errno on error
*
*/
int
xfs_collapse_file_space(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
int error;
xfs_fileoff_t next_fsb = XFS_B_TO_FSB(mp, offset + len);
xfs_fileoff_t shift_fsb = XFS_B_TO_FSB(mp, len);
bool done = false;
xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL);
trace_xfs_collapse_file_space(ip);
error = xfs_free_file_space(ip, offset, len);
if (error)
return error;
error = xfs_prepare_shift(ip, offset);
if (error)
return error;
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp);
if (error)
return error;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
while (!done) {
error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,