aboutsummaryrefslogtreecommitdiff
path: root/fs/gfs2/quota.c
blob: 228a46596188e18ede47d23d983fa1ae007be47e (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
/*
 * 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 to 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.
 */

#include <linux/sched.h>
#include <linux/slab.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/lm_interface.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 "ops_address.h"
#include "util.h"

#define QUOTA_USER 1
#define QUOTA_GROUP 0

struct gfs2_quota_host {
	u64 qu_limit;
	u64 qu_warn;
	s64 qu_value;
	u32 qu_ll_next;
};

struct gfs2_quota_change_host {
	u64 qc_change;
	u32 qc_flags; /* GFS2_QCF_... */
	u32 qc_id;
};

static u64 qd2offset(struct gfs2_quota_data *qd)
{
	u64 offset;

	offset = 2 * (u64)qd->qd_id + !test_bit(QDF_USER, &qd->qd_flags);
	offset *= sizeof(struct gfs2_quota);

	return offset;
}

static int qd_alloc(struct gfs2_sbd *sdp, int user, u32 id,
		    struct gfs2_quota_data **qdp)
{
	struct gfs2_quota_data *qd;
	int error;

	qd = kzalloc(sizeof(struct gfs2_quota_data), GFP_NOFS);
	if (!qd)
		return -ENOMEM;

	qd->qd_count = 1;
	qd->qd_id = id;
	if (user)
		set_bit(QDF_USER, &qd->qd_flags);
	qd->qd_slot = -1;

	error = gfs2_glock_get(sdp, 2 * (u64)id + !user,
			      &gfs2_quota_glops, CREATE, &qd->qd_gl);
	if (error)
		goto fail;

	error = gfs2_lvb_hold(qd->qd_gl);
	gfs2_glock_put(qd->qd_gl);
	if (error)
		goto fail;

	*qdp = qd;

	return 0;

fail:
	kfree(qd);
	return error;
}

static int qd_get(struct gfs2_sbd *sdp, int user, u32 id, int create,
		  struct gfs2_quota_data **qdp)
{
	struct gfs2_quota_data *qd = NULL, *new_qd = NULL;
	int error, found;

	*qdp = NULL;

	for (;;) {
		found = 0;
		spin_lock(&sdp->sd_quota_spin);
		list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
			if (qd->qd_id == id &&
			    !test_bit(QDF_USER, &qd->qd_flags) == !user) {
				qd->qd_count++;
				found = 1;
				break;
			}
		}

		if (!found)
			qd = NULL;

		if (!qd && new_qd) {
			qd = new_qd;
			list_add(&qd->qd_list, &sdp->sd_quota_list);
			atomic_inc(&sdp->sd_quota_count);
			new_qd = NULL;
		}

		spin_unlock(&sdp->sd_quota_spin);

		if (qd || !create) {
			if (new_qd) {
				gfs2_lvb_unhold(new_qd->qd_gl);
				kfree(new_qd);
			}
			*qdp = qd;
			return 0;
		}

		error = qd_alloc(sdp, user, id, &new_qd);
		if (error)
			return error;
	}
}

static void qd_hold(struct gfs2_quota_data *qd)
{
	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;

	spin_lock(&sdp->sd_quota_spin);
	gfs2_assert(sdp, qd->qd_count);
	qd->qd_count++;
	spin_unlock(&sdp->sd_quota_spin);
}

static void qd_put(struct gfs2_quota_data *qd)
{
	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
	spin_lock(&sdp->sd_quota_spin);
	gfs2_assert(sdp, qd->qd_count);
	if (!--qd->qd_count)
		qd->qd_last_touched = jiffies;
	spin_unlock(&sdp->sd_quota_spin);
}

static int slot_get(struct gfs2_quota_data *qd)
{
	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
	unsigned int c, o = 0, b;
	unsigned char byte = 0;

	spin_lock(&sdp->sd_quota_spin);

	if (qd->qd_slot_count++) {
		spin_unlock(&sdp->sd_quota_spin);
		return 0;
	}

	for (c = 0; c < sdp->sd_quota_chunks; c++)
		for (o = 0; o < PAGE_SIZE; o++) {
			byte = sdp->sd_quota_bitmap[c][o];
			if (byte != 0xFF)
				goto found;
		}

	goto fail;

found:
	for (b = 0; b < 8; b++)
		if (!(byte & (1 << b)))
			break;
	qd->qd_slot = c * (8 * PAGE_SIZE) + o * 8 + b;

	if (qd->qd_slot >= sdp->sd_quota_slots)
		goto fail;

	sdp->sd_quota_bitmap[c][o] |= 1 << b;

	spin_unlock(&sdp->sd_quota_spin);

	return 0;

fail:
	qd->qd_slot_count--;
	spin_unlock(&sdp->sd_quota_spin);
	return -ENOSPC;
}

static void slot_hold(struct gfs2_quota_data *qd)
{
	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;

	spin_lock(&sdp->sd_quota_spin);
	gfs2_assert(sdp, qd->qd_slot_count);
	qd->qd_slot_count++;
	spin_unlock(&sdp->sd_quota_spin);
}

static void slot_put(struct gfs2_quota_data *qd)
{
	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;

	spin_lock(&sdp->sd_quota_spin);
	gfs2_assert(sdp, qd->qd_slot_count);
	if (!--qd->qd_slot_count) {
		gfs2_icbit_munge(sdp, sdp->sd_quota_bitmap, qd->qd_slot, 0);
		qd->qd_slot = -1;
	}
	spin_unlock(&sdp->sd_quota_spin);
}

static int bh_get(struct gfs2_quota_data *qd)
{
	struct gfs2_sbd *sdp = qd->qd_gl->gl_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 = 1 << 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, &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_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_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(&sdp->sd_quota_spin);

	list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
		if (test_bit(QDF_LOCKED, &qd->qd_flags) ||
		    !test_bit(QDF_CHANGE, &qd->qd_flags) ||
		    qd->qd_sync_gen >= sdp->sd_quota_sync_gen)
			continue;

		list_move_tail(&qd->qd_list, &sdp->sd_quota_list);

		set_bit(QDF_LOCKED, &qd->qd_flags);
		gfs2_assert_warn(sdp, qd->qd_count);
		qd->qd_count++;
		qd->qd_change_sync = qd->qd_change;
		gfs2_assert_warn(sdp, qd->qd_slot_count);
		qd->qd_slot_count++;
		found = 1;

		break;
	}

	if (!found)
		qd = NULL;

	spin_unlock(&sdp->sd_quota_spin);

	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 int qd_trylock(struct gfs2_quota_data *qd)
{
	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;

	if (sdp->sd_vfs->s_flags & MS_RDONLY)
		return 0;

	spin_lock(&sdp->sd_quota_spin);

	if (test_bit(QDF_LOCKED, &qd->qd_flags) ||
	    !test_bit(QDF_CHANGE, &qd->qd_flags)) {
		spin_unlock(&sdp->sd_quota_spin);
		return 0;
	}

	list_move_tail(&qd->qd_list, &sdp->sd_quota_list);

	set_bit(QDF_LOCKED, &qd->qd_flags);
	gfs2_assert_warn(sdp, qd->qd_count);
	qd->qd_count++;
	qd->qd_change_sync = qd->qd_change;
	gfs2_assert_warn(sdp, qd->qd_slot_count);
	qd->qd_slot_count++;

	spin_unlock(&sdp->sd_quota_spin);

	gfs2_assert_warn(sdp, qd->qd_change_sync);
	if (bh_get(qd)) {
		clear_bit(QDF_LOCKED, &qd->qd_flags);
		slot_put(qd);
		qd_put(qd);
		return 0;
	}

	return 1;
}

static void qd_unlock(struct gfs2_quota_data *qd)
{
	gfs2_assert_warn(qd->qd_gl->gl_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, int user, u32 id, int create,
		    struct gfs2_quota_data **qdp)
{
	int error;

	error = qd_get(sdp, user, id, create, 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);
}

int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct gfs2_alloc *al = ip->i_alloc;
	struct gfs2_quota_data **qd = al->al_qd;
	int error;

	if (gfs2_assert_warn(sdp, !al->al_qd_num) ||
	    gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)))
		return -EIO;

	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
		return 0;

	error = qdsb_get(sdp, QUOTA_USER, ip->i_inode.i_uid, CREATE, qd);
	if (error)
		goto out;
	al->al_qd_num++;
	qd++;

	error = qdsb_get(sdp, QUOTA_GROUP, ip->i_inode.i_gid, CREATE, qd);
	if (error)
		goto out;
	al->al_qd_num++;
	qd++;

	if (uid != NO_QUOTA_CHANGE && uid != ip->i_inode.i_uid) {
		error = qdsb_get(sdp, QUOTA_USER, uid, CREATE, qd);
		if (error)
			goto out;
		al->al_qd_num++;
		qd++;
	}

	if (gid != NO_QUOTA_CHANGE && gid != ip->i_inode.i_gid) {
		error = qdsb_get(sdp, QUOTA_GROUP, gid, CREATE, qd);
		if (error)
			goto out;
		al->al_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);
	struct gfs2_alloc *al = ip->i_alloc;
	unsigned int x;

	gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags));

	for (x = 0; x < al->al_qd_num; x++) {
		qdsb_put(al->al_qd[x]);
		al->al_qd[x] = NULL;
	}
	al->al_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 (!test_bit(QDF_USER, &qd_a->qd_flags) !=
	    !test_bit(QDF_USER, &qd_b->qd_flags)) {
		if (test_bit(QDF_USER, &qd_a->qd_flags))
			return -1;
		else
			return 1;
	}
	if (qd_a->qd_id < qd_b->qd_id)
		return -1;
	if (qd_a->qd_id > qd_b->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_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_bh(ip->i_gl, qd->qd_bh, 1);

	if (!test_bit(QDF_CHANGE, &qd->qd_flags)) {
		qc->qc_change = 0;
		qc->qc_flags = 0;
		if (test_bit(QDF_USER, &qd->qd_flags))
			qc->qc_flags = cpu_to_be32(GFS2_QCF_USER);
		qc->qc_id = cpu_to_be32(qd->qd_id);
	}

	x = be64_to_cpu(qc->qc_change) + change;
	qc->qc_change = cpu_to_be64(x);

	spin_lock(&sdp->sd_quota_spin);
	qd->qd_change = x;
	spin_unlock(&sdp->sd_quota_spin);

	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);
	}

	mutex_unlock(&sdp->sd_quota_mutex);
}

static void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf)
{
	const struct gfs2_quota *str = buf;

	qu->qu_limit = be64_to_cpu(str->qu_limit);
	qu->qu_warn = be64_to_cpu(str->qu_warn);
	qu->qu_value = be64_to_cpu(str->qu_value);
	qu->qu_ll_next = be32_to_cpu(str->qu_ll_next);
}

static void gfs2_quota_out(const struct gfs2_quota_host *qu, void *buf)
{
	struct gfs2_quota *str = buf;

	str->qu_limit = cpu_to_be64(qu->qu_limit);
	str->qu_warn = cpu_to_be64(qu->qu_warn);
	str->qu_value = cpu_to_be64(qu->qu_value);
	str->qu_ll_next = cpu_to_be32(qu->qu_ll_next);
	memset(&str->qu_reserved, 0, sizeof(str->qu_reserved));
}

/**
 * gfs2_adjust_quota
 *
 * This function was mostly borrowed from gfs2_block_truncate_page which was
 * in turn mostly borrowed from ext3
 */
static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
			     s64 change, struct gfs2_quota_data *qd)
{
	struct inode *inode = &ip->i_inode;
	struct address_space *mapping = inode->i_mapping;
	unsigned long index = loc >> PAGE_CACHE_SHIFT;
	unsigned offset = loc & (PAGE_CACHE_SIZE - 1);
	unsigned blocksize, iblock, pos;
	struct buffer_head *bh;
	struct page *page;
	void *kaddr;
	char *ptr;
	struct gfs2_quota_host qp;
	s64 value;
	int err = -EIO;

	if (gfs2_is_stuffed(ip))
		gfs2_unstuff_dinode(ip, NULL);
	
	page = grab_cache_page(mapping, index);
	if (!page)
		return -ENOMEM;

	blocksize = inode->i_sb->s_blocksize;
	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);

	if (!page_has_buffers(page))
		create_empty_buffers(page, blocksize, 0);

	bh = page_buffers(page);
	pos = blocksize;
	while (offset >= pos) {
		bh = bh->b_this_page;
		iblock++;
		pos += blocksize;
	}

	if (!buffer_mapped(bh)) {
		gfs2_block_map(inode, iblock, bh, 1);
		if (!buffer_mapped(bh))
			goto unlock;
	}

	if (PageUptodate(page))
		set_buffer_uptodate(bh);

	if (!buffer_uptodate(bh)) {
		ll_rw_block(READ_META, 1, &bh);
		wait_on_buffer(bh);
		if (!buffer_uptodate(bh))
			goto unlock;
	}

	gfs2_trans_add_bh(ip->i_gl, bh, 0);

	kaddr = kmap_atomic(page, KM_USER0);
	ptr = kaddr + offset;
	gfs2_quota_in(&qp, ptr);
	qp.qu_value += change;
	value = qp.qu_value;
	gfs2_quota_out(&qp, ptr);
	flush_dcache_page(page);
	kunmap_atomic(kaddr, KM_USER0);
	err = 0;
	qd->qd_qb.qb_magic = cpu_to_be32(GFS2_MAGIC);
	qd->qd_qb.qb_value = cpu_to_be64(value);
	((struct gfs2_quota_lvb*)(qd->qd_gl->gl_lvb))->qb_magic = cpu_to_be32(GFS2_MAGIC);
	((struct gfs2_quota_lvb*)(qd->qd_gl->gl_lvb))->qb_value = cpu_to_be64(value);
unlock:
	unlock_page(page);
	page_cache_release(page);
	return err;
}

static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
{
	struct gfs2_sbd *sdp = (*qda)->qd_gl->gl_sbd;
	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
	unsigned int data_blocks, ind_blocks;
	struct gfs2_holder *ghs, i_gh;
	unsigned int qx, x;
	struct gfs2_quota_data *qd;
	loff_t offset;
	unsigned int nalloc = 0, blocks;
	struct gfs2_alloc *al = NULL;
	int error;

	gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota),
			      &data_blocks, &ind_blocks);

	ghs = kcalloc(num_qd, sizeof(struct gfs2_holder), GFP_NOFS);
	if (!ghs)
		return -ENOMEM;

	sort(qda, num_qd, sizeof(struct gfs2_quota_data *), sort_qd, NULL);
	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++) {
		int alloc_required;

		offset = qd2offset(qda[x]);
		error = gfs2_write_alloc_required(ip, offset,
						  sizeof(struct gfs2_quota),
						  &alloc_required);
		if (error)
			goto out_gunlock;
		if (alloc_required)
			nalloc++;
	}

	al = gfs2_alloc_get(ip);
	if (!al) {
		error = -ENOMEM;
		goto out_gunlock;
	}
	/* 
	 * 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
	 */
	al->al_requested = 1;
	/* +1 in the end for block requested above for unstuffing */
	blocks = num_qd * data_blocks + RES_DINODE + num_qd + 1;

	if (nalloc)
		al->al_requested += nalloc * (data_blocks + ind_blocks);		
	error = gfs2_inplace_reserve(ip);
	if (error)
		goto out_alloc;

	if (nalloc)
		blocks += al->al_rgd->rd_length + 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,
					  (struct gfs2_quota_data *)
					  qd);
		if (error)
			goto out_end_trans;

		do_qc(qd, -qd->qd_change_sync);
	}

	error = 0;

out_end_trans:
	gfs2_trans_end(sdp);
out_ipres:
	gfs2_inplace_release(ip);
out_alloc:
	gfs2_alloc_put(ip);
out_gunlock:
	gfs2_glock_dq_uninit(&i_gh);
out:
	while (qx--)
		gfs2_glock_dq_uninit(&ghs[qx]);
	kfree(ghs);
	gfs2_log_flush(ip->i_gl->gl_sbd, ip->i_gl);
	return error;
}

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_sbd;
	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
	struct gfs2_holder i_gh;
	struct gfs2_quota_host q;
	char buf[sizeof(struct gfs2_quota)];
	int error;
	struct gfs2_quota_lvb *qlvb;

restart:
	error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_SHARED, 0, q_gh);
	if (error)
		return error;

	qd->qd_qb = *(struct gfs2_quota_lvb *)qd->qd_gl->gl_lvb;

	if (force_refresh || qd->qd_qb.qb_magic != cpu_to_be32(GFS2_MAGIC)) {
		loff_t pos;
		gfs2_glock_dq_uninit(q_gh);
		error = gfs2_glock_nq_init(qd->qd_gl,
					  LM_ST_EXCLUSIVE, GL_NOCACHE,
					  q_gh);
		if (error)
			return error;

		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
		if (error)
			goto fail;

		memset(buf, 0, sizeof(struct gfs2_quota));
		pos = qd2offset(qd);
		error = gfs2_internal_read(ip, NULL, buf, &pos,
					   sizeof(struct gfs2_quota));
		if (error < 0)
			goto fail_gunlock;

		gfs2_glock_dq_uninit(&i_gh);


		gfs2_quota_in(&q, buf);
		qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lvb;
		qlvb->qb_magic = cpu_to_be32(GFS2_MAGIC);
		qlvb->__pad = 0;
		qlvb->qb_limit = cpu_to_be64(q.qu_limit);
		qlvb->qb_warn = cpu_to_be64(q.qu_warn);
		qlvb->qb_value = cpu_to_be64(q.qu_value);
		qd->qd_qb = *qlvb;

		if (gfs2_glock_is_blocking(qd->qd_gl)) {
			gfs2_glock_dq_uninit(q_gh);
			force_refresh = 0;
			goto restart;
		}
	}

	return 0;

fail_gunlock:
	gfs2_glock_dq_uninit(&i_gh);
fail:
	gfs2_glock_dq_uninit(q_gh);
	return error;
}

int gfs2_quota_lock(struct gfs2_inode *ip, u32 uid, u32 gid)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct gfs2_alloc *al = ip->i_alloc;
	unsigned int x;
	int error = 0;

	gfs2_quota_hold(ip, uid, gid);

	if (capable(CAP_SYS_RESOURCE) ||
	    sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
		return 0;

	sort(al->al_qd, al->al_qd_num, sizeof(struct gfs2_quota_data *),
	     sort_qd, NULL);

	for (x = 0; x < al->al_qd_num; x++) {
		error = do_glock(al->al_qd[x], NO_FORCE, &al->al_qd_ghs[x]);
		if (error)
			break;
	}

	if (!error)
		set_bit(GIF_QD_LOCKED, &ip->i_flags);
	else {
		while (x--)
			gfs2_glock_dq_uninit(&al->al_qd_ghs[x]);
		gfs2_quota_unhold(ip);
	}

	return error;
}

static int need_sync(struct gfs2_quota_data *qd)
{
	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
	struct gfs2_tune *gt = &sdp->sd_tune;
	s64 value;
	unsigned int num, den;
	int do_sync = 1;

	if (!qd->qd_qb.qb_limit)
		return 0;

	spin_lock(&sdp->sd_quota_spin);
	value = qd->qd_change;
	spin_unlock(&sdp->sd_quota_spin);

	spin_lock(&gt->gt_spin);
	num = gt->gt_quota_scale_num;
	den = gt->gt_quota_scale_den;
	spin_unlock(&gt->gt_spin);

	if (value < 0)
		do_sync = 0;
	else if ((s64)be64_to_cpu(qd->qd_qb.qb_value) >=
		 (s64)be64_to_cpu(qd->qd_qb.qb_limit))
		do_sync = 0;
	else {
		value *= gfs2_jindex_size(sdp) * num;
		value = div_s64(value, den);
		value += (s64)be64_to_cpu(qd->qd_qb.qb_value);
		if (value < (s64)be64_to_cpu(qd->qd_qb.qb_limit))
			do_sync = 0;
	}

	return do_sync;
}

void gfs2_quota_unlock(struct gfs2_inode *ip)
{
	struct gfs2_alloc *al = ip->i_alloc;
	struct gfs2_quota_data *qda[4];
	unsigned int count = 0;
	unsigned int x;

	if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags))
		goto out;

	for (x = 0; x < al->al_qd_num; x++) {
		struct gfs2_quota_data *qd;
		int sync;

		qd = al->al_qd[x];
		sync = need_sync(qd);

		gfs2_glock_dq_uninit(&al->al_qd_ghs[x]);

		if (sync && qd_trylock(qd))
			qda[count++] = qd;
	}

	if (count) {
		do_sync(count, qda);
		for (x = 0; x < count; x++)
			qd_unlock(qda[x]);
	}

out:
	gfs2_quota_unhold(ip);
}

#define MAX_LINE 256

static int print_message(struct gfs2_quota_data *qd, char *type)
{
	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;

	printk(KERN_INFO "GFS2: fsid=%s: quota %s for %s %u\r\n",
	       sdp->sd_fsname, type,
	       (test_bit(QDF_USER, &qd->qd_flags)) ? "user" : "group",
	       qd->qd_id);

	return 0;
}

int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct gfs2_alloc *al = ip->i_alloc;
	struct gfs2_quota_data *qd;
	s64 value;
	unsigned int x;
	int error = 0;

	if (!test_bit(GIF_QD_LOCKED, &ip->i_flags))
		return 0;

        if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
                return 0;

	for (x = 0; x < al->al_qd_num; x++) {
		qd = al->al_qd[x];

		if (!((qd->qd_id == uid && test_bit(QDF_USER, &qd->qd_flags)) ||
		      (qd->qd_id == gid && !test_bit(QDF_USER, &qd->qd_flags))))
			continue;

		value = (s64)be64_to_cpu(qd->qd_qb.qb_value);
		spin_lock(&sdp->sd_quota_spin);
		value += qd->qd_change;
		spin_unlock(&sdp->sd_quota_spin);

		if (be64_to_cpu(qd->qd_qb.qb_limit) && (s64)be64_to_cpu(qd->qd_qb.qb_limit) < value) {
			print_message(qd, "exceeded");
			error = -EDQUOT;
			break;
		} else if (be64_to_cpu(qd->qd_qb.qb_warn) &&
			   (s64)be64_to_cpu(qd->qd_qb.qb_warn) < value &&
			   time_after_eq(jiffies, qd->qd_last_warn +
					 gfs2_tune_get(sdp,
						gt_quota_warn_period) * HZ)) {
			error = print_message(qd, "warning");
			qd->qd_last_warn = jiffies;
		}
	}

	return error;
}

void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
		       u32 uid, u32 gid)
{
	struct gfs2_alloc *al = ip->i_alloc;
	struct gfs2_quota_data *qd;
	unsigned int x;

	if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), change))
		return;
	if (ip->i_diskflags & GFS2_DIF_SYSTEM)
		return;

	for (x = 0; x < al->al_qd_num; x++) {
		qd = al->al_qd[x];

		if ((qd->qd_id == uid && test_bit(QDF_USER, &qd->qd_flags)) ||
		    (qd->qd_id == gid && !test_bit(QDF_USER, &qd->qd_flags))) {
			do_qc(qd, change);
		}
	}
}

int gfs2_quota_sync(struct gfs2_sbd *sdp)
{
	struct gfs2_quota_data **qda;
	unsigned int max_qd = gfs2_tune_get(sdp, gt_quota_simul_sync);
	unsigned int num_qd;
	unsigned int x;
	int error = 0;

	sdp->sd_quota_sync_gen++;

	qda = kcalloc(max_qd, sizeof(struct gfs2_quota_data *), GFP_KERNEL);
	if (!qda)
		return -ENOMEM;

	do {
		num_qd = 0;

		for (;;) {
			error = qd_fish(sdp, qda + num_qd);
			if (error || !qda[num_qd])
				break;
			if (++num_qd == max_qd)
				break;
		}

		if (num_qd) {
			if (!error)
				error = do_sync(num_qd, qda);
			if (!error)
				for (x = 0; x < num_qd; x++)
					qda[x]->qd_sync_gen =
						sdp->sd_quota_sync_gen;

			for (x = 0; x < num_qd; x++)
				qd_unlock(qda[x]);
		}
	} while (!error && num_qd == max_qd);

	kfree(qda);

	return error;
}

int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id)
{
	struct gfs2_quota_data *qd;
	struct gfs2_holder q_gh;
	int error;

	error = qd_get(sdp, user, id, CREATE, &qd);
	if (error)
		return error;

	error = do_glock(qd, FORCE, &q_gh);
	if (!error)
		gfs2_glock_dq_uninit(&q_gh);

	qd_put(qd);

	return error;
}

static void gfs2_quota_change_in(struct gfs2_quota_change_host *qc, const void *buf)
{
	const struct gfs2_quota_change *str = buf;

	qc->qc_change = be64_to_cpu(str->qc_change);
	qc->qc_flags = be32_to_cpu(str->qc_flags);
	qc->qc_id = be32_to_cpu(str->qc_id);
}

int gfs2_quota_init(struct gfs2_sbd *sdp)
{
	struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
	unsigned int blocks = ip->i_disksize >> sdp->sd_sb.sb_bsize_shift;
	unsigned int x, slot = 0;
	unsigned int found = 0;
	u64 dblock;
	u32 extlen = 0;
	int error;

	if (!ip->i_disksize || ip->i_disksize > (64 << 20) ||
	    ip->i_disksize & (sdp->sd_sb.sb_bsize - 1)) {
		gfs2_consist_inode(ip);
		return -EIO;
	}
	sdp->sd_quota_slots = blocks * sdp->sd_qc_per_block;
	sdp->sd_quota_chunks = DIV_ROUND_UP(sdp->sd_quota_slots, 8 * PAGE_SIZE);

	error = -ENOMEM;

	sdp->sd_quota_bitmap = kcalloc(sdp->sd_quota_chunks,
				       sizeof(unsigned char *), GFP_NOFS);
	if (!sdp->sd_quota_bitmap)
		return error;

	for (x = 0; x < sdp->sd_quota_chunks; x++) {
		sdp->sd_quota_bitmap[x] = kzalloc(PAGE_SIZE, GFP_NOFS);
		if (!sdp->sd_quota_bitmap[x])
			goto fail;
	}

	for (x = 0; x < blocks; x++) {
		struct buffer_head *bh;
		unsigned int y;

		if (!extlen) {
			int new = 0;
			error = gfs2_extent_map(&ip->i_inode, x, &new, &dblock, &extlen);
			if (error)
				goto fail;
		}
		error = -EIO;
		bh = gfs2_meta_ra(ip->i_gl, dblock, extlen);
		if (!bh)
			goto fail;
		if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_QC)) {
			brelse(bh);
			goto fail;
		}

		for (y = 0; y < sdp->sd_qc_per_block && slot < sdp->sd_quota_slots;
		     y++, slot++) {
			struct gfs2_quota_change_host qc;
			struct gfs2_quota_data *qd;

			gfs2_quota_change_in(&qc, bh->b_data +
					  sizeof(struct gfs2_meta_header) +
					  y * sizeof(struct gfs2_quota_change));
			if (!qc.qc_change)
				continue;

			error = qd_alloc(sdp, (qc.qc_flags & GFS2_QCF_USER),
					 qc.qc_id, &qd);
			if (error) {
				brelse(bh);
				goto fail;
			}

			set_bit(QDF_CHANGE, &qd->qd_flags);
			qd->qd_change = qc.qc_change;
			qd->qd_slot = slot;
			qd->qd_slot_count = 1;
			qd->qd_last_touched = jiffies;

			spin_lock(&sdp->sd_quota_spin);
			gfs2_icbit_munge(sdp, sdp->sd_quota_bitmap, slot, 1);
			list_add(&qd->qd_list, &sdp->sd_quota_list);
			atomic_inc(&sdp->sd_quota_count);
			spin_unlock(&sdp->sd_quota_spin);

			found++;
		}

		brelse(bh);
		dblock++;
		extlen--;
	}

	if (found)
		fs_info(sdp, "found %u quota changes\n", found);

	return 0;

fail:
	gfs2_quota_cleanup(sdp);
	return error;
}

void gfs2_quota_scan(struct gfs2_sbd *sdp)
{
	struct gfs2_quota_data *qd, *safe;
	LIST_HEAD(dead);

	spin_lock(&sdp->sd_quota_spin);
	list_for_each_entry_safe(qd, safe, &sdp->sd_quota_list, qd_list) {
		if (!qd->qd_count &&
		    time_after_eq(jiffies, qd->qd_last_touched +
			        gfs2_tune_get(sdp, gt_quota_cache_secs) * HZ)) {
			list_move(&qd->qd_list, &dead);
			gfs2_assert_warn(sdp,
					 atomic_read(&sdp->sd_quota_count) > 0);
			atomic_dec(&sdp->sd_quota_count);
		}
	}
	spin_unlock(&sdp->sd_quota_spin);

	while (!list_empty(&dead)) {
		qd = list_entry(dead.next, struct gfs2_quota_data, qd_list);
		list_del(&qd->qd_list);

		gfs2_assert_warn(sdp, !qd->qd_change);
		gfs2_assert_warn(sdp, !qd->qd_slot_count);
		gfs2_assert_warn(sdp, !qd->qd_bh_count);

		gfs2_lvb_unhold(qd->qd_gl);
		kfree(qd);
	}
}

void gfs2_quota_cleanup(struct gfs2_sbd *sdp)
{
	struct list_head *head = &sdp->sd_quota_list;
	struct gfs2_quota_data *qd;
	unsigned int x;

	spin_lock(&sdp->sd_quota_spin);
	while (!list_empty(head)) {
		qd = list_entry(head->prev, struct gfs2_quota_data, qd_list);

		if (qd->qd_count > 1 ||
		    (qd->qd_count && !test_bit(QDF_CHANGE, &qd->qd_flags))) {
			list_move(&qd->qd_list, head);
			spin_unlock(&sdp->sd_quota_spin);
			schedule();
			spin_lock(&sdp->sd_quota_spin);
			continue;
		}

		list_del(&qd->qd_list);
		atomic_dec(&sdp->sd_quota_count);
		spin_unlock(&sdp->sd_quota_spin);

		if (!qd->qd_count) {
			gfs2_assert_warn(sdp, !qd->qd_change);
			gfs2_assert_warn(sdp, !qd->qd_slot_count);
		} else
			gfs2_assert_warn(sdp, qd->qd_slot_count == 1);
		gfs2_assert_warn(sdp, !qd->qd_bh_count);

		gfs2_lvb_unhold(qd->qd_gl);
		kfree(qd);

		spin_lock(&sdp->sd_quota_spin);
	}
	spin_unlock(&sdp->sd_quota_spin);

	gfs2_assert_warn(sdp, !atomic_read(&sdp->sd_quota_count));

	if (sdp->sd_quota_bitmap) {
		for (x = 0; x < sdp->sd_quota_chunks; x++)
			kfree(sdp->sd_quota_bitmap[x]);
		kfree(sdp->sd_quota_bitmap);
	}
}