forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathxfs_qm.c
1963 lines (1723 loc) · 46.6 KB
/
xfs_qm.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) 2000-2005 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_inode.h"
#include "xfs_ialloc.h"
#include "xfs_itable.h"
#include "xfs_quota.h"
#include "xfs_error.h"
#include "xfs_bmap.h"
#include "xfs_bmap_btree.h"
#include "xfs_bmap_util.h"
#include "xfs_trans.h"
#include "xfs_trans_space.h"
#include "xfs_qm.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_cksum.h"
/*
* The global quota manager. There is only one of these for the entire
* system, _not_ one per file system. XQM keeps track of the overall
* quota functionality, including maintaining the freelist and hash
* tables of dquots.
*/
STATIC int xfs_qm_init_quotainos(xfs_mount_t *);
STATIC int xfs_qm_init_quotainfo(xfs_mount_t *);
STATIC void xfs_qm_destroy_quotainos(xfs_quotainfo_t *qi);
STATIC void xfs_qm_dqfree_one(struct xfs_dquot *dqp);
/*
* We use the batch lookup interface to iterate over the dquots as it
* currently is the only interface into the radix tree code that allows
* fuzzy lookups instead of exact matches. Holding the lock over multiple
* operations is fine as all callers are used either during mount/umount
* or quotaoff.
*/
#define XFS_DQ_LOOKUP_BATCH 32
STATIC int
xfs_qm_dquot_walk(
struct xfs_mount *mp,
int type,
int (*execute)(struct xfs_dquot *dqp, void *data),
void *data)
{
struct xfs_quotainfo *qi = mp->m_quotainfo;
struct radix_tree_root *tree = xfs_dquot_tree(qi, type);
uint32_t next_index;
int last_error = 0;
int skipped;
int nr_found;
restart:
skipped = 0;
next_index = 0;
nr_found = 0;
while (1) {
struct xfs_dquot *batch[XFS_DQ_LOOKUP_BATCH];
int error = 0;
int i;
mutex_lock(&qi->qi_tree_lock);
nr_found = radix_tree_gang_lookup(tree, (void **)batch,
next_index, XFS_DQ_LOOKUP_BATCH);
if (!nr_found) {
mutex_unlock(&qi->qi_tree_lock);
break;
}
for (i = 0; i < nr_found; i++) {
struct xfs_dquot *dqp = batch[i];
next_index = be32_to_cpu(dqp->q_core.d_id) + 1;
error = execute(batch[i], data);
if (error == -EAGAIN) {
skipped++;
continue;
}
if (error && last_error != -EFSCORRUPTED)
last_error = error;
}
mutex_unlock(&qi->qi_tree_lock);
/* bail out if the filesystem is corrupted. */
if (last_error == -EFSCORRUPTED) {
skipped = 0;
break;
}
/* we're done if id overflows back to zero */
if (!next_index)
break;
}
if (skipped) {
delay(1);
goto restart;
}
return last_error;
}
/*
* Purge a dquot from all tracking data structures and free it.
*/
STATIC int
xfs_qm_dqpurge(
struct xfs_dquot *dqp,
void *data)
{
struct xfs_mount *mp = dqp->q_mount;
struct xfs_quotainfo *qi = mp->m_quotainfo;
xfs_dqlock(dqp);
if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) {
xfs_dqunlock(dqp);
return -EAGAIN;
}
dqp->dq_flags |= XFS_DQ_FREEING;
xfs_dqflock(dqp);
/*
* If we are turning this type of quotas off, we don't care
* about the dirty metadata sitting in this dquot. OTOH, if
* we're unmounting, we do care, so we flush it and wait.
*/
if (XFS_DQ_IS_DIRTY(dqp)) {
struct xfs_buf *bp = NULL;
int error;
/*
* We don't care about getting disk errors here. We need
* to purge this dquot anyway, so we go ahead regardless.
*/
error = xfs_qm_dqflush(dqp, &bp);
if (!error) {
error = xfs_bwrite(bp);
xfs_buf_relse(bp);
}
xfs_dqflock(dqp);
}
ASSERT(atomic_read(&dqp->q_pincount) == 0);
ASSERT(XFS_FORCED_SHUTDOWN(mp) ||
!test_bit(XFS_LI_IN_AIL, &dqp->q_logitem.qli_item.li_flags));
xfs_dqfunlock(dqp);
xfs_dqunlock(dqp);
radix_tree_delete(xfs_dquot_tree(qi, dqp->q_core.d_flags),
be32_to_cpu(dqp->q_core.d_id));
qi->qi_dquots--;
/*
* We move dquots to the freelist as soon as their reference count
* hits zero, so it really should be on the freelist here.
*/
ASSERT(!list_empty(&dqp->q_lru));
list_lru_del(&qi->qi_lru, &dqp->q_lru);
XFS_STATS_DEC(mp, xs_qm_dquot_unused);
xfs_qm_dqdestroy(dqp);
return 0;
}
/*
* Purge the dquot cache.
*/
void
xfs_qm_dqpurge_all(
struct xfs_mount *mp,
uint flags)
{
if (flags & XFS_QMOPT_UQUOTA)
xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL);
if (flags & XFS_QMOPT_GQUOTA)
xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL);
if (flags & XFS_QMOPT_PQUOTA)
xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_dqpurge, NULL);
}
/*
* Just destroy the quotainfo structure.
*/
void
xfs_qm_unmount(
struct xfs_mount *mp)
{
if (mp->m_quotainfo) {
xfs_qm_dqpurge_all(mp, XFS_QMOPT_QUOTALL);
xfs_qm_destroy_quotainfo(mp);
}
}
/*
* Called from the vfsops layer.
*/
void
xfs_qm_unmount_quotas(
xfs_mount_t *mp)
{
/*
* Release the dquots that root inode, et al might be holding,
* before we flush quotas and blow away the quotainfo structure.
*/
ASSERT(mp->m_rootip);
xfs_qm_dqdetach(mp->m_rootip);
if (mp->m_rbmip)
xfs_qm_dqdetach(mp->m_rbmip);
if (mp->m_rsumip)
xfs_qm_dqdetach(mp->m_rsumip);
/*
* Release the quota inodes.
*/
if (mp->m_quotainfo) {
if (mp->m_quotainfo->qi_uquotaip) {
xfs_irele(mp->m_quotainfo->qi_uquotaip);
mp->m_quotainfo->qi_uquotaip = NULL;
}
if (mp->m_quotainfo->qi_gquotaip) {
xfs_irele(mp->m_quotainfo->qi_gquotaip);
mp->m_quotainfo->qi_gquotaip = NULL;
}
if (mp->m_quotainfo->qi_pquotaip) {
xfs_irele(mp->m_quotainfo->qi_pquotaip);
mp->m_quotainfo->qi_pquotaip = NULL;
}
}
}
STATIC int
xfs_qm_dqattach_one(
xfs_inode_t *ip,
xfs_dqid_t id,
uint type,
bool doalloc,
xfs_dquot_t **IO_idqpp)
{
xfs_dquot_t *dqp;
int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
error = 0;
/*
* See if we already have it in the inode itself. IO_idqpp is &i_udquot
* or &i_gdquot. This made the code look weird, but made the logic a lot
* simpler.
*/
dqp = *IO_idqpp;
if (dqp) {
trace_xfs_dqattach_found(dqp);
return 0;
}
/*
* Find the dquot from somewhere. This bumps the reference count of
* dquot and returns it locked. This can return ENOENT if dquot didn't
* exist on disk and we didn't ask it to allocate; ESRCH if quotas got
* turned off suddenly.
*/
error = xfs_qm_dqget_inode(ip, type, doalloc, &dqp);
if (error)
return error;
trace_xfs_dqattach_get(dqp);
/*
* dqget may have dropped and re-acquired the ilock, but it guarantees
* that the dquot returned is the one that should go in the inode.
*/
*IO_idqpp = dqp;
xfs_dqunlock(dqp);
return 0;
}
static bool
xfs_qm_need_dqattach(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
if (!XFS_IS_QUOTA_RUNNING(mp))
return false;
if (!XFS_IS_QUOTA_ON(mp))
return false;
if (!XFS_NOT_DQATTACHED(mp, ip))
return false;
if (xfs_is_quota_inode(&mp->m_sb, ip->i_ino))
return false;
return true;
}
/*
* Given a locked inode, attach dquot(s) to it, taking U/G/P-QUOTAON
* into account.
* If @doalloc is true, the dquot(s) will be allocated if needed.
* Inode may get unlocked and relocked in here, and the caller must deal with
* the consequences.
*/
int
xfs_qm_dqattach_locked(
xfs_inode_t *ip,
bool doalloc)
{
xfs_mount_t *mp = ip->i_mount;
int error = 0;
if (!xfs_qm_need_dqattach(ip))
return 0;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
if (XFS_IS_UQUOTA_ON(mp) && !ip->i_udquot) {
error = xfs_qm_dqattach_one(ip, ip->i_d.di_uid, XFS_DQ_USER,
doalloc, &ip->i_udquot);
if (error)
goto done;
ASSERT(ip->i_udquot);
}
if (XFS_IS_GQUOTA_ON(mp) && !ip->i_gdquot) {
error = xfs_qm_dqattach_one(ip, ip->i_d.di_gid, XFS_DQ_GROUP,
doalloc, &ip->i_gdquot);
if (error)
goto done;
ASSERT(ip->i_gdquot);
}
if (XFS_IS_PQUOTA_ON(mp) && !ip->i_pdquot) {
error = xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ,
doalloc, &ip->i_pdquot);
if (error)
goto done;
ASSERT(ip->i_pdquot);
}
done:
/*
* Don't worry about the dquots that we may have attached before any
* error - they'll get detached later if it has not already been done.
*/
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
return error;
}
int
xfs_qm_dqattach(
struct xfs_inode *ip)
{
int error;
if (!xfs_qm_need_dqattach(ip))
return 0;
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_qm_dqattach_locked(ip, false);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
/*
* Release dquots (and their references) if any.
* The inode should be locked EXCL except when this's called by
* xfs_ireclaim.
*/
void
xfs_qm_dqdetach(
xfs_inode_t *ip)
{
if (!(ip->i_udquot || ip->i_gdquot || ip->i_pdquot))
return;
trace_xfs_dquot_dqdetach(ip);
ASSERT(!xfs_is_quota_inode(&ip->i_mount->m_sb, ip->i_ino));
if (ip->i_udquot) {
xfs_qm_dqrele(ip->i_udquot);
ip->i_udquot = NULL;
}
if (ip->i_gdquot) {
xfs_qm_dqrele(ip->i_gdquot);
ip->i_gdquot = NULL;
}
if (ip->i_pdquot) {
xfs_qm_dqrele(ip->i_pdquot);
ip->i_pdquot = NULL;
}
}
struct xfs_qm_isolate {
struct list_head buffers;
struct list_head dispose;
};
static enum lru_status
xfs_qm_dquot_isolate(
struct list_head *item,
struct list_lru_one *lru,
spinlock_t *lru_lock,
void *arg)
__releases(lru_lock) __acquires(lru_lock)
{
struct xfs_dquot *dqp = container_of(item,
struct xfs_dquot, q_lru);
struct xfs_qm_isolate *isol = arg;
if (!xfs_dqlock_nowait(dqp))
goto out_miss_busy;
/*
* This dquot has acquired a reference in the meantime remove it from
* the freelist and try again.
*/
if (dqp->q_nrefs) {
xfs_dqunlock(dqp);
XFS_STATS_INC(dqp->q_mount, xs_qm_dqwants);
trace_xfs_dqreclaim_want(dqp);
list_lru_isolate(lru, &dqp->q_lru);
XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot_unused);
return LRU_REMOVED;
}
/*
* If the dquot is dirty, flush it. If it's already being flushed, just
* skip it so there is time for the IO to complete before we try to
* reclaim it again on the next LRU pass.
*/
if (!xfs_dqflock_nowait(dqp)) {
xfs_dqunlock(dqp);
goto out_miss_busy;
}
if (XFS_DQ_IS_DIRTY(dqp)) {
struct xfs_buf *bp = NULL;
int error;
trace_xfs_dqreclaim_dirty(dqp);
/* we have to drop the LRU lock to flush the dquot */
spin_unlock(lru_lock);
error = xfs_qm_dqflush(dqp, &bp);
if (error)
goto out_unlock_dirty;
xfs_buf_delwri_queue(bp, &isol->buffers);
xfs_buf_relse(bp);
goto out_unlock_dirty;
}
xfs_dqfunlock(dqp);
/*
* Prevent lookups now that we are past the point of no return.
*/
dqp->dq_flags |= XFS_DQ_FREEING;
xfs_dqunlock(dqp);
ASSERT(dqp->q_nrefs == 0);
list_lru_isolate_move(lru, &dqp->q_lru, &isol->dispose);
XFS_STATS_DEC(dqp->q_mount, xs_qm_dquot_unused);
trace_xfs_dqreclaim_done(dqp);
XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaims);
return LRU_REMOVED;
out_miss_busy:
trace_xfs_dqreclaim_busy(dqp);
XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses);
return LRU_SKIP;
out_unlock_dirty:
trace_xfs_dqreclaim_busy(dqp);
XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses);
xfs_dqunlock(dqp);
spin_lock(lru_lock);
return LRU_RETRY;
}
static unsigned long
xfs_qm_shrink_scan(
struct shrinker *shrink,
struct shrink_control *sc)
{
struct xfs_quotainfo *qi = container_of(shrink,
struct xfs_quotainfo, qi_shrinker);
struct xfs_qm_isolate isol;
unsigned long freed;
int error;
if ((sc->gfp_mask & (__GFP_FS|__GFP_DIRECT_RECLAIM)) != (__GFP_FS|__GFP_DIRECT_RECLAIM))
return 0;
INIT_LIST_HEAD(&isol.buffers);
INIT_LIST_HEAD(&isol.dispose);
freed = list_lru_shrink_walk(&qi->qi_lru, sc,
xfs_qm_dquot_isolate, &isol);
error = xfs_buf_delwri_submit(&isol.buffers);
if (error)
xfs_warn(NULL, "%s: dquot reclaim failed", __func__);
while (!list_empty(&isol.dispose)) {
struct xfs_dquot *dqp;
dqp = list_first_entry(&isol.dispose, struct xfs_dquot, q_lru);
list_del_init(&dqp->q_lru);
xfs_qm_dqfree_one(dqp);
}
return freed;
}
static unsigned long
xfs_qm_shrink_count(
struct shrinker *shrink,
struct shrink_control *sc)
{
struct xfs_quotainfo *qi = container_of(shrink,
struct xfs_quotainfo, qi_shrinker);
return list_lru_shrink_count(&qi->qi_lru, sc);
}
STATIC void
xfs_qm_set_defquota(
xfs_mount_t *mp,
uint type,
xfs_quotainfo_t *qinf)
{
xfs_dquot_t *dqp;
struct xfs_def_quota *defq;
struct xfs_disk_dquot *ddqp;
int error;
error = xfs_qm_dqget_uncached(mp, 0, type, &dqp);
if (error)
return;
ddqp = &dqp->q_core;
defq = xfs_get_defquota(dqp, qinf);
/*
* Timers and warnings have been already set, let's just set the
* default limits for this quota type
*/
defq->bhardlimit = be64_to_cpu(ddqp->d_blk_hardlimit);
defq->bsoftlimit = be64_to_cpu(ddqp->d_blk_softlimit);
defq->ihardlimit = be64_to_cpu(ddqp->d_ino_hardlimit);
defq->isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
defq->rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
defq->rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
xfs_qm_dqdestroy(dqp);
}
/* Initialize quota time limits from the root dquot. */
static void
xfs_qm_init_timelimits(
struct xfs_mount *mp,
struct xfs_quotainfo *qinf)
{
struct xfs_disk_dquot *ddqp;
struct xfs_dquot *dqp;
uint type;
int error;
qinf->qi_btimelimit = XFS_QM_BTIMELIMIT;
qinf->qi_itimelimit = XFS_QM_ITIMELIMIT;
qinf->qi_rtbtimelimit = XFS_QM_RTBTIMELIMIT;
qinf->qi_bwarnlimit = XFS_QM_BWARNLIMIT;
qinf->qi_iwarnlimit = XFS_QM_IWARNLIMIT;
qinf->qi_rtbwarnlimit = XFS_QM_RTBWARNLIMIT;
/*
* We try to get the limits from the superuser's limits fields.
* This is quite hacky, but it is standard quota practice.
*
* Since we may not have done a quotacheck by this point, just read
* the dquot without attaching it to any hashtables or lists.
*
* Timers and warnings are globally set by the first timer found in
* user/group/proj quota types, otherwise a default value is used.
* This should be split into different fields per quota type.
*/
if (XFS_IS_UQUOTA_RUNNING(mp))
type = XFS_DQ_USER;
else if (XFS_IS_GQUOTA_RUNNING(mp))
type = XFS_DQ_GROUP;
else
type = XFS_DQ_PROJ;
error = xfs_qm_dqget_uncached(mp, 0, type, &dqp);
if (error)
return;
ddqp = &dqp->q_core;
/*
* The warnings and timers set the grace period given to
* a user or group before he or she can not perform any
* more writing. If it is zero, a default is used.
*/
if (ddqp->d_btimer)
qinf->qi_btimelimit = be32_to_cpu(ddqp->d_btimer);
if (ddqp->d_itimer)
qinf->qi_itimelimit = be32_to_cpu(ddqp->d_itimer);
if (ddqp->d_rtbtimer)
qinf->qi_rtbtimelimit = be32_to_cpu(ddqp->d_rtbtimer);
if (ddqp->d_bwarns)
qinf->qi_bwarnlimit = be16_to_cpu(ddqp->d_bwarns);
if (ddqp->d_iwarns)
qinf->qi_iwarnlimit = be16_to_cpu(ddqp->d_iwarns);
if (ddqp->d_rtbwarns)
qinf->qi_rtbwarnlimit = be16_to_cpu(ddqp->d_rtbwarns);
xfs_qm_dqdestroy(dqp);
}
/*
* This initializes all the quota information that's kept in the
* mount structure
*/
STATIC int
xfs_qm_init_quotainfo(
struct xfs_mount *mp)
{
struct xfs_quotainfo *qinf;
int error;
ASSERT(XFS_IS_QUOTA_RUNNING(mp));
qinf = mp->m_quotainfo = kmem_zalloc(sizeof(xfs_quotainfo_t), KM_SLEEP);
error = list_lru_init(&qinf->qi_lru);
if (error)
goto out_free_qinf;
/*
* See if quotainodes are setup, and if not, allocate them,
* and change the superblock accordingly.
*/
error = xfs_qm_init_quotainos(mp);
if (error)
goto out_free_lru;
INIT_RADIX_TREE(&qinf->qi_uquota_tree, GFP_NOFS);
INIT_RADIX_TREE(&qinf->qi_gquota_tree, GFP_NOFS);
INIT_RADIX_TREE(&qinf->qi_pquota_tree, GFP_NOFS);
mutex_init(&qinf->qi_tree_lock);
/* mutex used to serialize quotaoffs */
mutex_init(&qinf->qi_quotaofflock);
/* Precalc some constants */
qinf->qi_dqchunklen = XFS_FSB_TO_BB(mp, XFS_DQUOT_CLUSTER_SIZE_FSB);
qinf->qi_dqperchunk = xfs_calc_dquots_per_chunk(qinf->qi_dqchunklen);
mp->m_qflags |= (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_CHKD);
xfs_qm_init_timelimits(mp, qinf);
if (XFS_IS_UQUOTA_RUNNING(mp))
xfs_qm_set_defquota(mp, XFS_DQ_USER, qinf);
if (XFS_IS_GQUOTA_RUNNING(mp))
xfs_qm_set_defquota(mp, XFS_DQ_GROUP, qinf);
if (XFS_IS_PQUOTA_RUNNING(mp))
xfs_qm_set_defquota(mp, XFS_DQ_PROJ, qinf);
qinf->qi_shrinker.count_objects = xfs_qm_shrink_count;
qinf->qi_shrinker.scan_objects = xfs_qm_shrink_scan;
qinf->qi_shrinker.seeks = DEFAULT_SEEKS;
qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE;
error = register_shrinker(&qinf->qi_shrinker);
if (error)
goto out_free_inos;
return 0;
out_free_inos:
mutex_destroy(&qinf->qi_quotaofflock);
mutex_destroy(&qinf->qi_tree_lock);
xfs_qm_destroy_quotainos(qinf);
out_free_lru:
list_lru_destroy(&qinf->qi_lru);
out_free_qinf:
kmem_free(qinf);
mp->m_quotainfo = NULL;
return error;
}
/*
* Gets called when unmounting a filesystem or when all quotas get
* turned off.
* This purges the quota inodes, destroys locks and frees itself.
*/
void
xfs_qm_destroy_quotainfo(
xfs_mount_t *mp)
{
xfs_quotainfo_t *qi;
qi = mp->m_quotainfo;
ASSERT(qi != NULL);
unregister_shrinker(&qi->qi_shrinker);
list_lru_destroy(&qi->qi_lru);
xfs_qm_destroy_quotainos(qi);
mutex_destroy(&qi->qi_tree_lock);
mutex_destroy(&qi->qi_quotaofflock);
kmem_free(qi);
mp->m_quotainfo = NULL;
}
/*
* Create an inode and return with a reference already taken, but unlocked
* This is how we create quota inodes
*/
STATIC int
xfs_qm_qino_alloc(
xfs_mount_t *mp,
xfs_inode_t **ip,
uint flags)
{
xfs_trans_t *tp;
int error;
bool need_alloc = true;
*ip = NULL;
/*
* With superblock that doesn't have separate pquotino, we
* share an inode between gquota and pquota. If the on-disk
* superblock has GQUOTA and the filesystem is now mounted
* with PQUOTA, just use sb_gquotino for sb_pquotino and
* vice-versa.
*/
if (!xfs_sb_version_has_pquotino(&mp->m_sb) &&
(flags & (XFS_QMOPT_PQUOTA|XFS_QMOPT_GQUOTA))) {
xfs_ino_t ino = NULLFSINO;
if ((flags & XFS_QMOPT_PQUOTA) &&
(mp->m_sb.sb_gquotino != NULLFSINO)) {
ino = mp->m_sb.sb_gquotino;
ASSERT(mp->m_sb.sb_pquotino == NULLFSINO);
} else if ((flags & XFS_QMOPT_GQUOTA) &&
(mp->m_sb.sb_pquotino != NULLFSINO)) {
ino = mp->m_sb.sb_pquotino;
ASSERT(mp->m_sb.sb_gquotino == NULLFSINO);
}
if (ino != NULLFSINO) {
error = xfs_iget(mp, NULL, ino, 0, 0, ip);
if (error)
return error;
mp->m_sb.sb_gquotino = NULLFSINO;
mp->m_sb.sb_pquotino = NULLFSINO;
need_alloc = false;
}
}
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_create,
XFS_QM_QINOCREATE_SPACE_RES(mp), 0, 0, &tp);
if (error)
return error;
if (need_alloc) {
error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, ip);
if (error) {
xfs_trans_cancel(tp);
return error;
}
}
/*
* Make the changes in the superblock, and log those too.
* sbfields arg may contain fields other than *QUOTINO;
* VERSIONNUM for example.
*/
spin_lock(&mp->m_sb_lock);
if (flags & XFS_QMOPT_SBVERSION) {
ASSERT(!xfs_sb_version_hasquota(&mp->m_sb));
xfs_sb_version_addquota(&mp->m_sb);
mp->m_sb.sb_uquotino = NULLFSINO;
mp->m_sb.sb_gquotino = NULLFSINO;
mp->m_sb.sb_pquotino = NULLFSINO;
/* qflags will get updated fully _after_ quotacheck */
mp->m_sb.sb_qflags = mp->m_qflags & XFS_ALL_QUOTA_ACCT;
}
if (flags & XFS_QMOPT_UQUOTA)
mp->m_sb.sb_uquotino = (*ip)->i_ino;
else if (flags & XFS_QMOPT_GQUOTA)
mp->m_sb.sb_gquotino = (*ip)->i_ino;
else
mp->m_sb.sb_pquotino = (*ip)->i_ino;
spin_unlock(&mp->m_sb_lock);
xfs_log_sb(tp);
error = xfs_trans_commit(tp);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
xfs_alert(mp, "%s failed (error %d)!", __func__, error);
}
if (need_alloc)
xfs_finish_inode_setup(*ip);
return error;
}
STATIC void
xfs_qm_reset_dqcounts(
xfs_mount_t *mp,
xfs_buf_t *bp,
xfs_dqid_t id,
uint type)
{
struct xfs_dqblk *dqb;
int j;
xfs_failaddr_t fa;
trace_xfs_reset_dqcounts(bp, _RET_IP_);
/*
* Reset all counters and timers. They'll be
* started afresh by xfs_qm_quotacheck.
*/
#ifdef DEBUG
j = (int)XFS_FSB_TO_B(mp, XFS_DQUOT_CLUSTER_SIZE_FSB) /
sizeof(xfs_dqblk_t);
ASSERT(mp->m_quotainfo->qi_dqperchunk == j);
#endif
dqb = bp->b_addr;
for (j = 0; j < mp->m_quotainfo->qi_dqperchunk; j++) {
struct xfs_disk_dquot *ddq;
ddq = (struct xfs_disk_dquot *)&dqb[j];
/*
* Do a sanity check, and if needed, repair the dqblk. Don't
* output any warnings because it's perfectly possible to
* find uninitialised dquot blks. See comment in
* xfs_dquot_verify.
*/
fa = xfs_dqblk_verify(mp, &dqb[j], id + j, type);
if (fa)
xfs_dqblk_repair(mp, &dqb[j], id + j, type);
/*
* Reset type in case we are reusing group quota file for
* project quotas or vice versa
*/
ddq->d_flags = type;
ddq->d_bcount = 0;
ddq->d_icount = 0;
ddq->d_rtbcount = 0;
ddq->d_btimer = 0;
ddq->d_itimer = 0;
ddq->d_rtbtimer = 0;
ddq->d_bwarns = 0;
ddq->d_iwarns = 0;
ddq->d_rtbwarns = 0;
if (xfs_sb_version_hascrc(&mp->m_sb)) {
xfs_update_cksum((char *)&dqb[j],
sizeof(struct xfs_dqblk),
XFS_DQUOT_CRC_OFF);
}
}
}
STATIC int
xfs_qm_reset_dqcounts_all(
struct xfs_mount *mp,
xfs_dqid_t firstid,
xfs_fsblock_t bno,
xfs_filblks_t blkcnt,
uint flags,
struct list_head *buffer_list)
{
struct xfs_buf *bp;
int error;
int type;
ASSERT(blkcnt > 0);
type = flags & XFS_QMOPT_UQUOTA ? XFS_DQ_USER :
(flags & XFS_QMOPT_PQUOTA ? XFS_DQ_PROJ : XFS_DQ_GROUP);
error = 0;
/*
* Blkcnt arg can be a very big number, and might even be
* larger than the log itself. So, we have to break it up into
* manageable-sized transactions.
* Note that we don't start a permanent transaction here; we might
* not be able to get a log reservation for the whole thing up front,
* and we don't really care to either, because we just discard
* everything if we were to crash in the middle of this loop.
*/
while (blkcnt--) {
error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, bno),
mp->m_quotainfo->qi_dqchunklen, 0, &bp,
&xfs_dquot_buf_ops);
/*
* CRC and validation errors will return a EFSCORRUPTED here. If
* this occurs, re-read without CRC validation so that we can
* repair the damage via xfs_qm_reset_dqcounts(). This process
* will leave a trace in the log indicating corruption has
* been detected.
*/
if (error == -EFSCORRUPTED) {
error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, bno),
mp->m_quotainfo->qi_dqchunklen, 0, &bp,
NULL);
}
if (error)
break;
/*
* A corrupt buffer might not have a verifier attached, so
* make sure we have the correct one attached before writeback
* occurs.
*/
bp->b_ops = &xfs_dquot_buf_ops;
xfs_qm_reset_dqcounts(mp, bp, firstid, type);
xfs_buf_delwri_queue(bp, buffer_list);
xfs_buf_relse(bp);
/* goto the next block. */
bno++;
firstid += mp->m_quotainfo->qi_dqperchunk;
}
return error;
}
/*
* Iterate over all allocated dquot blocks in this quota inode, zeroing all
* counters for every chunk of dquots that we find.
*/
STATIC int
xfs_qm_reset_dqcounts_buf(
struct xfs_mount *mp,
struct xfs_inode *qip,
uint flags,
struct list_head *buffer_list)
{
struct xfs_bmbt_irec *map;
int i, nmaps; /* number of map entries */
int error; /* return value */
xfs_fileoff_t lblkno;
xfs_filblks_t maxlblkcnt;
xfs_dqid_t firstid;
xfs_fsblock_t rablkno;
xfs_filblks_t rablkcnt;
error = 0;
/*
* This looks racy, but we can't keep an inode lock across a
* trans_reserve. But, this gets called during quotacheck, and that
* happens only at mount time which is single threaded.
*/
if (qip->i_d.di_nblocks == 0)
return 0;
map = kmem_alloc(XFS_DQITER_MAP_SIZE * sizeof(*map), KM_SLEEP);
lblkno = 0;
maxlblkcnt = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
do {
uint lock_mode;
nmaps = XFS_DQITER_MAP_SIZE;
/*
* We aren't changing the inode itself. Just changing
* some of its data. No new blocks are added here, and
* the inode is never added to the transaction.
*/
lock_mode = xfs_ilock_data_map_shared(qip);
error = xfs_bmapi_read(qip, lblkno, maxlblkcnt - lblkno,
map, &nmaps, 0);