forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
quota.c
1761 lines (1463 loc) · 42.3 KB
/
quota.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) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
*
* This copyrighted material is made available to anyone wishing to use,
* modify, copy, or redistribute it subject to the terms and conditions
* of the GNU General Public License version 2.
*/
/*
* Quota change tags are associated with each transaction that allocates or
* deallocates space. Those changes are accumulated locally to each node (in a
* per-node file) and then are periodically synced to the quota file. This
* avoids the bottleneck of constantly touching the quota file, but introduces
* fuzziness in the current usage value of IDs that are being used on different
* nodes in the cluster simultaneously. So, it is possible for a user on
* multiple nodes to overrun their quota, but that overrun is controlable.
* Since quota tags are part of transactions, there is no need for a quota check
* program to be run on node crashes or anything like that.
*
* There are couple of knobs that let the administrator manage the quota
* fuzziness. "quota_quantum" sets the maximum time a quota change can be
* sitting on one node before being synced to the quota file. (The default is
* 60 seconds.) Another knob, "quota_scale" controls how quickly the frequency
* of quota file syncs increases as the user moves closer to their limit. The
* more frequent the syncs, the more accurate the quota enforcement, but that
* means that there is more contention between the nodes for the quota file.
* The default value is one. This sets the maximum theoretical quota overrun
* (with infinite node with infinite bandwidth) to twice the user's limit. (In
* practice, the maximum overrun you see should be much less.) A "quota_scale"
* number greater than one makes quota syncs more frequent and reduces the
* maximum overrun. Numbers less than one (but greater than zero) make quota
* syncs less frequent.
*
* GFS quotas also use per-ID Lock Value Blocks (LVBs) to cache the contents of
* the quota file, so it is not being constantly read.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/sort.h>
#include <linux/fs.h>
#include <linux/bio.h>
#include <linux/gfs2_ondisk.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/quota.h>
#include <linux/dqblk_xfs.h>
#include <linux/lockref.h>
#include <linux/list_lru.h>
#include <linux/rcupdate.h>
#include <linux/rculist_bl.h>
#include <linux/bit_spinlock.h>
#include <linux/jhash.h>
#include <linux/vmalloc.h>
#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "glops.h"
#include "log.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "super.h"
#include "trans.h"
#include "inode.h"
#include "util.h"
#define GFS2_QD_HASH_SHIFT 12
#define GFS2_QD_HASH_SIZE BIT(GFS2_QD_HASH_SHIFT)
#define GFS2_QD_HASH_MASK (GFS2_QD_HASH_SIZE - 1)
/* Lock order: qd_lock -> bucket lock -> qd->lockref.lock -> lru lock */
/* -> sd_bitmap_lock */
static DEFINE_SPINLOCK(qd_lock);
struct list_lru gfs2_qd_lru;
static struct hlist_bl_head qd_hash_table[GFS2_QD_HASH_SIZE];
static unsigned int gfs2_qd_hash(const struct gfs2_sbd *sdp,
const struct kqid qid)
{
unsigned int h;
h = jhash(&sdp, sizeof(struct gfs2_sbd *), 0);
h = jhash(&qid, sizeof(struct kqid), h);
return h & GFS2_QD_HASH_MASK;
}
static inline void spin_lock_bucket(unsigned int hash)
{
hlist_bl_lock(&qd_hash_table[hash]);
}
static inline void spin_unlock_bucket(unsigned int hash)
{
hlist_bl_unlock(&qd_hash_table[hash]);
}
static void gfs2_qd_dealloc(struct rcu_head *rcu)
{
struct gfs2_quota_data *qd = container_of(rcu, struct gfs2_quota_data, qd_rcu);
kmem_cache_free(gfs2_quotad_cachep, qd);
}
static void gfs2_qd_dispose(struct list_head *list)
{
struct gfs2_quota_data *qd;
struct gfs2_sbd *sdp;
while (!list_empty(list)) {
qd = list_entry(list->next, struct gfs2_quota_data, qd_lru);
sdp = qd->qd_gl->gl_name.ln_sbd;
list_del(&qd->qd_lru);
/* Free from the filesystem-specific list */
spin_lock(&qd_lock);
list_del(&qd->qd_list);
spin_unlock(&qd_lock);
spin_lock_bucket(qd->qd_hash);
hlist_bl_del_rcu(&qd->qd_hlist);
spin_unlock_bucket(qd->qd_hash);
gfs2_assert_warn(sdp, !qd->qd_change);
gfs2_assert_warn(sdp, !qd->qd_slot_count);
gfs2_assert_warn(sdp, !qd->qd_bh_count);
gfs2_glock_put(qd->qd_gl);
atomic_dec(&sdp->sd_quota_count);
/* Delete it from the common reclaim list */
call_rcu(&qd->qd_rcu, gfs2_qd_dealloc);
}
}
static enum lru_status gfs2_qd_isolate(struct list_head *item,
struct list_lru_one *lru, spinlock_t *lru_lock, void *arg)
{
struct list_head *dispose = arg;
struct gfs2_quota_data *qd = list_entry(item, struct gfs2_quota_data, qd_lru);
if (!spin_trylock(&qd->qd_lockref.lock))
return LRU_SKIP;
if (qd->qd_lockref.count == 0) {
lockref_mark_dead(&qd->qd_lockref);
list_lru_isolate_move(lru, &qd->qd_lru, dispose);
}
spin_unlock(&qd->qd_lockref.lock);
return LRU_REMOVED;
}
static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
LIST_HEAD(dispose);
unsigned long freed;
if (!(sc->gfp_mask & __GFP_FS))
return SHRINK_STOP;
freed = list_lru_shrink_walk(&gfs2_qd_lru, sc,
gfs2_qd_isolate, &dispose);
gfs2_qd_dispose(&dispose);
return freed;
}
static unsigned long gfs2_qd_shrink_count(struct shrinker *shrink,
struct shrink_control *sc)
{
return vfs_pressure_ratio(list_lru_shrink_count(&gfs2_qd_lru, sc));
}
struct shrinker gfs2_qd_shrinker = {
.count_objects = gfs2_qd_shrink_count,
.scan_objects = gfs2_qd_shrink_scan,
.seeks = DEFAULT_SEEKS,
.flags = SHRINKER_NUMA_AWARE,
};
static u64 qd2index(struct gfs2_quota_data *qd)
{
struct kqid qid = qd->qd_id;
return (2 * (u64)from_kqid(&init_user_ns, qid)) +
((qid.type == USRQUOTA) ? 0 : 1);
}
static u64 qd2offset(struct gfs2_quota_data *qd)
{
u64 offset;
offset = qd2index(qd);
offset *= sizeof(struct gfs2_quota);
return offset;
}
static struct gfs2_quota_data *qd_alloc(unsigned hash, struct gfs2_sbd *sdp, struct kqid qid)
{
struct gfs2_quota_data *qd;
int error;
qd = kmem_cache_zalloc(gfs2_quotad_cachep, GFP_NOFS);
if (!qd)
return NULL;
qd->qd_sbd = sdp;
qd->qd_lockref.count = 1;
spin_lock_init(&qd->qd_lockref.lock);
qd->qd_id = qid;
qd->qd_slot = -1;
INIT_LIST_HEAD(&qd->qd_lru);
qd->qd_hash = hash;
error = gfs2_glock_get(sdp, qd2index(qd),
&gfs2_quota_glops, CREATE, &qd->qd_gl);
if (error)
goto fail;
return qd;
fail:
kmem_cache_free(gfs2_quotad_cachep, qd);
return NULL;
}
static struct gfs2_quota_data *gfs2_qd_search_bucket(unsigned int hash,
const struct gfs2_sbd *sdp,
struct kqid qid)
{
struct gfs2_quota_data *qd;
struct hlist_bl_node *h;
hlist_bl_for_each_entry_rcu(qd, h, &qd_hash_table[hash], qd_hlist) {
if (!qid_eq(qd->qd_id, qid))
continue;
if (qd->qd_sbd != sdp)
continue;
if (lockref_get_not_dead(&qd->qd_lockref)) {
list_lru_del(&gfs2_qd_lru, &qd->qd_lru);
return qd;
}
}
return NULL;
}
static int qd_get(struct gfs2_sbd *sdp, struct kqid qid,
struct gfs2_quota_data **qdp)
{
struct gfs2_quota_data *qd, *new_qd;
unsigned int hash = gfs2_qd_hash(sdp, qid);
rcu_read_lock();
*qdp = qd = gfs2_qd_search_bucket(hash, sdp, qid);
rcu_read_unlock();
if (qd)
return 0;
new_qd = qd_alloc(hash, sdp, qid);
if (!new_qd)
return -ENOMEM;
spin_lock(&qd_lock);
spin_lock_bucket(hash);
*qdp = qd = gfs2_qd_search_bucket(hash, sdp, qid);
if (qd == NULL) {
*qdp = new_qd;
list_add(&new_qd->qd_list, &sdp->sd_quota_list);
hlist_bl_add_head_rcu(&new_qd->qd_hlist, &qd_hash_table[hash]);
atomic_inc(&sdp->sd_quota_count);
}
spin_unlock_bucket(hash);
spin_unlock(&qd_lock);
if (qd) {
gfs2_glock_put(new_qd->qd_gl);
kmem_cache_free(gfs2_quotad_cachep, new_qd);
}
return 0;
}
static void qd_hold(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
gfs2_assert(sdp, !__lockref_is_dead(&qd->qd_lockref));
lockref_get(&qd->qd_lockref);
}
static void qd_put(struct gfs2_quota_data *qd)
{
if (lockref_put_or_lock(&qd->qd_lockref))
return;
qd->qd_lockref.count = 0;
list_lru_add(&gfs2_qd_lru, &qd->qd_lru);
spin_unlock(&qd->qd_lockref.lock);
}
static int slot_get(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_sbd;
unsigned int bit;
int error = 0;
spin_lock(&sdp->sd_bitmap_lock);
if (qd->qd_slot_count != 0)
goto out;
error = -ENOSPC;
bit = find_first_zero_bit(sdp->sd_quota_bitmap, sdp->sd_quota_slots);
if (bit < sdp->sd_quota_slots) {
set_bit(bit, sdp->sd_quota_bitmap);
qd->qd_slot = bit;
error = 0;
out:
qd->qd_slot_count++;
}
spin_unlock(&sdp->sd_bitmap_lock);
return error;
}
static void slot_hold(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_sbd;
spin_lock(&sdp->sd_bitmap_lock);
gfs2_assert(sdp, qd->qd_slot_count);
qd->qd_slot_count++;
spin_unlock(&sdp->sd_bitmap_lock);
}
static void slot_put(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_sbd;
spin_lock(&sdp->sd_bitmap_lock);
gfs2_assert(sdp, qd->qd_slot_count);
if (!--qd->qd_slot_count) {
BUG_ON(!test_and_clear_bit(qd->qd_slot, sdp->sd_quota_bitmap));
qd->qd_slot = -1;
}
spin_unlock(&sdp->sd_bitmap_lock);
}
static int bh_get(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
unsigned int block, offset;
struct buffer_head *bh;
int error;
struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
mutex_lock(&sdp->sd_quota_mutex);
if (qd->qd_bh_count++) {
mutex_unlock(&sdp->sd_quota_mutex);
return 0;
}
block = qd->qd_slot / sdp->sd_qc_per_block;
offset = qd->qd_slot % sdp->sd_qc_per_block;
bh_map.b_size = BIT(ip->i_inode.i_blkbits);
error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0);
if (error)
goto fail;
error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, 0, &bh);
if (error)
goto fail;
error = -EIO;
if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_QC))
goto fail_brelse;
qd->qd_bh = bh;
qd->qd_bh_qc = (struct gfs2_quota_change *)
(bh->b_data + sizeof(struct gfs2_meta_header) +
offset * sizeof(struct gfs2_quota_change));
mutex_unlock(&sdp->sd_quota_mutex);
return 0;
fail_brelse:
brelse(bh);
fail:
qd->qd_bh_count--;
mutex_unlock(&sdp->sd_quota_mutex);
return error;
}
static void bh_put(struct gfs2_quota_data *qd)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
mutex_lock(&sdp->sd_quota_mutex);
gfs2_assert(sdp, qd->qd_bh_count);
if (!--qd->qd_bh_count) {
brelse(qd->qd_bh);
qd->qd_bh = NULL;
qd->qd_bh_qc = NULL;
}
mutex_unlock(&sdp->sd_quota_mutex);
}
static int qd_check_sync(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd,
u64 *sync_gen)
{
if (test_bit(QDF_LOCKED, &qd->qd_flags) ||
!test_bit(QDF_CHANGE, &qd->qd_flags) ||
(sync_gen && (qd->qd_sync_gen >= *sync_gen)))
return 0;
if (!lockref_get_not_dead(&qd->qd_lockref))
return 0;
list_move_tail(&qd->qd_list, &sdp->sd_quota_list);
set_bit(QDF_LOCKED, &qd->qd_flags);
qd->qd_change_sync = qd->qd_change;
slot_hold(qd);
return 1;
}
static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp)
{
struct gfs2_quota_data *qd = NULL;
int error;
int found = 0;
*qdp = NULL;
if (sdp->sd_vfs->s_flags & MS_RDONLY)
return 0;
spin_lock(&qd_lock);
list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
found = qd_check_sync(sdp, qd, &sdp->sd_quota_sync_gen);
if (found)
break;
}
if (!found)
qd = NULL;
spin_unlock(&qd_lock);
if (qd) {
gfs2_assert_warn(sdp, qd->qd_change_sync);
error = bh_get(qd);
if (error) {
clear_bit(QDF_LOCKED, &qd->qd_flags);
slot_put(qd);
qd_put(qd);
return error;
}
}
*qdp = qd;
return 0;
}
static void qd_unlock(struct gfs2_quota_data *qd)
{
gfs2_assert_warn(qd->qd_gl->gl_name.ln_sbd,
test_bit(QDF_LOCKED, &qd->qd_flags));
clear_bit(QDF_LOCKED, &qd->qd_flags);
bh_put(qd);
slot_put(qd);
qd_put(qd);
}
static int qdsb_get(struct gfs2_sbd *sdp, struct kqid qid,
struct gfs2_quota_data **qdp)
{
int error;
error = qd_get(sdp, qid, qdp);
if (error)
return error;
error = slot_get(*qdp);
if (error)
goto fail;
error = bh_get(*qdp);
if (error)
goto fail_slot;
return 0;
fail_slot:
slot_put(*qdp);
fail:
qd_put(*qdp);
return error;
}
static void qdsb_put(struct gfs2_quota_data *qd)
{
bh_put(qd);
slot_put(qd);
qd_put(qd);
}
/**
* gfs2_qa_alloc - make sure we have a quota allocations data structure,
* if necessary
* @ip: the inode for this reservation
*/
int gfs2_qa_alloc(struct gfs2_inode *ip)
{
int error = 0;
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return 0;
down_write(&ip->i_rw_mutex);
if (ip->i_qadata == NULL) {
ip->i_qadata = kmem_cache_zalloc(gfs2_qadata_cachep, GFP_NOFS);
if (!ip->i_qadata)
error = -ENOMEM;
}
up_write(&ip->i_rw_mutex);
return error;
}
void gfs2_qa_delete(struct gfs2_inode *ip, atomic_t *wcount)
{
down_write(&ip->i_rw_mutex);
if (ip->i_qadata && ((wcount == NULL) || (atomic_read(wcount) <= 1))) {
kmem_cache_free(gfs2_qadata_cachep, ip->i_qadata);
ip->i_qadata = NULL;
}
up_write(&ip->i_rw_mutex);
}
int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_quota_data **qd;
int error;
if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return 0;
if (ip->i_qadata == NULL) {
error = gfs2_rsqa_alloc(ip);
if (error)
return error;
}
qd = ip->i_qadata->qa_qd;
if (gfs2_assert_warn(sdp, !ip->i_qadata->qa_qd_num) ||
gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)))
return -EIO;
error = qdsb_get(sdp, make_kqid_uid(ip->i_inode.i_uid), qd);
if (error)
goto out;
ip->i_qadata->qa_qd_num++;
qd++;
error = qdsb_get(sdp, make_kqid_gid(ip->i_inode.i_gid), qd);
if (error)
goto out;
ip->i_qadata->qa_qd_num++;
qd++;
if (!uid_eq(uid, NO_UID_QUOTA_CHANGE) &&
!uid_eq(uid, ip->i_inode.i_uid)) {
error = qdsb_get(sdp, make_kqid_uid(uid), qd);
if (error)
goto out;
ip->i_qadata->qa_qd_num++;
qd++;
}
if (!gid_eq(gid, NO_GID_QUOTA_CHANGE) &&
!gid_eq(gid, ip->i_inode.i_gid)) {
error = qdsb_get(sdp, make_kqid_gid(gid), qd);
if (error)
goto out;
ip->i_qadata->qa_qd_num++;
qd++;
}
out:
if (error)
gfs2_quota_unhold(ip);
return error;
}
void gfs2_quota_unhold(struct gfs2_inode *ip)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
u32 x;
if (ip->i_qadata == NULL)
return;
gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags));
for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
qdsb_put(ip->i_qadata->qa_qd[x]);
ip->i_qadata->qa_qd[x] = NULL;
}
ip->i_qadata->qa_qd_num = 0;
}
static int sort_qd(const void *a, const void *b)
{
const struct gfs2_quota_data *qd_a = *(const struct gfs2_quota_data **)a;
const struct gfs2_quota_data *qd_b = *(const struct gfs2_quota_data **)b;
if (qid_lt(qd_a->qd_id, qd_b->qd_id))
return -1;
if (qid_lt(qd_b->qd_id, qd_a->qd_id))
return 1;
return 0;
}
static void do_qc(struct gfs2_quota_data *qd, s64 change)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
struct gfs2_quota_change *qc = qd->qd_bh_qc;
s64 x;
mutex_lock(&sdp->sd_quota_mutex);
gfs2_trans_add_meta(ip->i_gl, qd->qd_bh);
if (!test_bit(QDF_CHANGE, &qd->qd_flags)) {
qc->qc_change = 0;
qc->qc_flags = 0;
if (qd->qd_id.type == USRQUOTA)
qc->qc_flags = cpu_to_be32(GFS2_QCF_USER);
qc->qc_id = cpu_to_be32(from_kqid(&init_user_ns, qd->qd_id));
}
x = be64_to_cpu(qc->qc_change) + change;
qc->qc_change = cpu_to_be64(x);
spin_lock(&qd_lock);
qd->qd_change = x;
spin_unlock(&qd_lock);
if (!x) {
gfs2_assert_warn(sdp, test_bit(QDF_CHANGE, &qd->qd_flags));
clear_bit(QDF_CHANGE, &qd->qd_flags);
qc->qc_flags = 0;
qc->qc_id = 0;
slot_put(qd);
qd_put(qd);
} else if (!test_and_set_bit(QDF_CHANGE, &qd->qd_flags)) {
qd_hold(qd);
slot_hold(qd);
}
if (change < 0) /* Reset quiet flag if we freed some blocks */
clear_bit(QDF_QMSG_QUIET, &qd->qd_flags);
mutex_unlock(&sdp->sd_quota_mutex);
}
static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index,
unsigned off, void *buf, unsigned bytes)
{
struct inode *inode = &ip->i_inode;
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct address_space *mapping = inode->i_mapping;
struct page *page;
struct buffer_head *bh;
void *kaddr;
u64 blk;
unsigned bsize = sdp->sd_sb.sb_bsize, bnum = 0, boff = 0;
unsigned to_write = bytes, pg_off = off;
int done = 0;
blk = index << (PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift);
boff = off % bsize;
page = find_or_create_page(mapping, index, GFP_NOFS);
if (!page)
return -ENOMEM;
if (!page_has_buffers(page))
create_empty_buffers(page, bsize, 0);
bh = page_buffers(page);
while (!done) {
/* Find the beginning block within the page */
if (pg_off >= ((bnum * bsize) + bsize)) {
bh = bh->b_this_page;
bnum++;
blk++;
continue;
}
if (!buffer_mapped(bh)) {
gfs2_block_map(inode, blk, bh, 1);
if (!buffer_mapped(bh))
goto unlock_out;
/* If it's a newly allocated disk block, zero it */
if (buffer_new(bh))
zero_user(page, bnum * bsize, bh->b_size);
}
if (PageUptodate(page))
set_buffer_uptodate(bh);
if (!buffer_uptodate(bh)) {
ll_rw_block(REQ_OP_READ, REQ_META, 1, &bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
goto unlock_out;
}
gfs2_trans_add_data(ip->i_gl, bh);
/* If we need to write to the next block as well */
if (to_write > (bsize - boff)) {
pg_off += (bsize - boff);
to_write -= (bsize - boff);
boff = pg_off % bsize;
continue;
}
done = 1;
}
/* Write to the page, now that we have setup the buffer(s) */
kaddr = kmap_atomic(page);
memcpy(kaddr + off, buf, bytes);
flush_dcache_page(page);
kunmap_atomic(kaddr);
unlock_page(page);
put_page(page);
return 0;
unlock_out:
unlock_page(page);
put_page(page);
return -EIO;
}
static int gfs2_write_disk_quota(struct gfs2_inode *ip, struct gfs2_quota *qp,
loff_t loc)
{
unsigned long pg_beg;
unsigned pg_off, nbytes, overflow = 0;
int pg_oflow = 0, error;
void *ptr;
nbytes = sizeof(struct gfs2_quota);
pg_beg = loc >> PAGE_SHIFT;
pg_off = loc % PAGE_SIZE;
/* If the quota straddles a page boundary, split the write in two */
if ((pg_off + nbytes) > PAGE_SIZE) {
pg_oflow = 1;
overflow = (pg_off + nbytes) - PAGE_SIZE;
}
ptr = qp;
error = gfs2_write_buf_to_page(ip, pg_beg, pg_off, ptr,
nbytes - overflow);
/* If there's an overflow, write the remaining bytes to the next page */
if (!error && pg_oflow)
error = gfs2_write_buf_to_page(ip, pg_beg + 1, 0,
ptr + nbytes - overflow,
overflow);
return error;
}
/**
* gfs2_adjust_quota - adjust record of current block usage
* @ip: The quota inode
* @loc: Offset of the entry in the quota file
* @change: The amount of usage change to record
* @qd: The quota data
* @fdq: The updated limits to record
*
* This function was mostly borrowed from gfs2_block_truncate_page which was
* in turn mostly borrowed from ext3
*
* Returns: 0 or -ve on error
*/
static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
s64 change, struct gfs2_quota_data *qd,
struct qc_dqblk *fdq)
{
struct inode *inode = &ip->i_inode;
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_quota q;
int err;
u64 size;
if (gfs2_is_stuffed(ip)) {
err = gfs2_unstuff_dinode(ip, NULL);
if (err)
return err;
}
memset(&q, 0, sizeof(struct gfs2_quota));
err = gfs2_internal_read(ip, (char *)&q, &loc, sizeof(q));
if (err < 0)
return err;
loc -= sizeof(q); /* gfs2_internal_read would've advanced the loc ptr */
err = -EIO;
be64_add_cpu(&q.qu_value, change);
if (((s64)be64_to_cpu(q.qu_value)) < 0)
q.qu_value = 0; /* Never go negative on quota usage */
qd->qd_qb.qb_value = q.qu_value;
if (fdq) {
if (fdq->d_fieldmask & QC_SPC_SOFT) {
q.qu_warn = cpu_to_be64(fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift);
qd->qd_qb.qb_warn = q.qu_warn;
}
if (fdq->d_fieldmask & QC_SPC_HARD) {
q.qu_limit = cpu_to_be64(fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift);
qd->qd_qb.qb_limit = q.qu_limit;
}
if (fdq->d_fieldmask & QC_SPACE) {
q.qu_value = cpu_to_be64(fdq->d_space >> sdp->sd_sb.sb_bsize_shift);
qd->qd_qb.qb_value = q.qu_value;
}
}
err = gfs2_write_disk_quota(ip, &q, loc);
if (!err) {
size = loc + sizeof(struct gfs2_quota);
if (size > inode->i_size)
i_size_write(inode, size);
inode->i_mtime = inode->i_atime = current_time(inode);
mark_inode_dirty(inode);
set_bit(QDF_REFRESH, &qd->qd_flags);
}
return err;
}
static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
{
struct gfs2_sbd *sdp = (*qda)->qd_gl->gl_name.ln_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
unsigned int data_blocks, ind_blocks;
struct gfs2_holder *ghs, i_gh;
unsigned int qx, x;
struct gfs2_quota_data *qd;
unsigned reserved;
loff_t offset;
unsigned int nalloc = 0, blocks;
int error;
error = gfs2_rsqa_alloc(ip);
if (error)
return error;
gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota),
&data_blocks, &ind_blocks);
ghs = kmalloc(num_qd * sizeof(struct gfs2_holder), GFP_NOFS);
if (!ghs)
return -ENOMEM;
sort(qda, num_qd, sizeof(struct gfs2_quota_data *), sort_qd, NULL);
inode_lock(&ip->i_inode);
for (qx = 0; qx < num_qd; qx++) {
error = gfs2_glock_nq_init(qda[qx]->qd_gl, LM_ST_EXCLUSIVE,
GL_NOCACHE, &ghs[qx]);
if (error)
goto out;
}
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
if (error)
goto out;
for (x = 0; x < num_qd; x++) {
offset = qd2offset(qda[x]);
if (gfs2_write_alloc_required(ip, offset,
sizeof(struct gfs2_quota)))
nalloc++;
}
/*
* 1 blk for unstuffing inode if stuffed. We add this extra
* block to the reservation unconditionally. If the inode
* doesn't need unstuffing, the block will be released to the
* rgrp since it won't be allocated during the transaction
*/
/* +3 in the end for unstuffing block, inode size update block
* and another block in case quota straddles page boundary and
* two blocks need to be updated instead of 1 */
blocks = num_qd * data_blocks + RES_DINODE + num_qd + 3;
reserved = 1 + (nalloc * (data_blocks + ind_blocks));
ap.target = reserved;
error = gfs2_inplace_reserve(ip, &ap);
if (error)
goto out_alloc;
if (nalloc)
blocks += gfs2_rg_blocks(ip, reserved) + nalloc * ind_blocks + RES_STATFS;
error = gfs2_trans_begin(sdp, blocks, 0);
if (error)
goto out_ipres;
for (x = 0; x < num_qd; x++) {
qd = qda[x];
offset = qd2offset(qd);
error = gfs2_adjust_quota(ip, offset, qd->qd_change_sync, qd, NULL);
if (error)
goto out_end_trans;
do_qc(qd, -qd->qd_change_sync);
set_bit(QDF_REFRESH, &qd->qd_flags);
}
error = 0;
out_end_trans:
gfs2_trans_end(sdp);
out_ipres:
gfs2_inplace_release(ip);
out_alloc:
gfs2_glock_dq_uninit(&i_gh);
out:
while (qx--)
gfs2_glock_dq_uninit(&ghs[qx]);
inode_unlock(&ip->i_inode);
kfree(ghs);
gfs2_log_flush(ip->i_gl->gl_name.ln_sbd, ip->i_gl, NORMAL_FLUSH);
return error;
}
static int update_qd(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd)
{
struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
struct gfs2_quota q;
struct gfs2_quota_lvb *qlvb;
loff_t pos;
int error;
memset(&q, 0, sizeof(struct gfs2_quota));
pos = qd2offset(qd);
error = gfs2_internal_read(ip, (char *)&q, &pos, sizeof(q));
if (error < 0)
return error;
qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr;
qlvb->qb_magic = cpu_to_be32(GFS2_MAGIC);
qlvb->__pad = 0;
qlvb->qb_limit = q.qu_limit;
qlvb->qb_warn = q.qu_warn;
qlvb->qb_value = q.qu_value;
qd->qd_qb = *qlvb;
return 0;
}
static int do_glock(struct gfs2_quota_data *qd, int force_refresh,
struct gfs2_holder *q_gh)
{
struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
struct gfs2_holder i_gh;
int error;
restart:
error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_SHARED, 0, q_gh);
if (error)
return error;
if (test_and_clear_bit(QDF_REFRESH, &qd->qd_flags))